diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/README.md b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/README.md new file mode 100644 index 0000000000000000000000000000000000000000..40b830a2d1779ad6b944879155eda6a400cc10fe --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/README.md @@ -0,0 +1,5 @@ +system=default_seed-0 +data=birdclef2025_15s +train=birdclef2025_convnext_tiny +model=birdclef2025_convnext_tiny +criterion=birdclef2025_categorical_cross_entropy diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/config.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d7bcf5117e09ddec5bac07f468eafb026f07ca2a --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/config.yaml @@ -0,0 +1,221 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250429-091731 + tensorboard_dir: ./tensorboard/20250429-091731 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.ConvNeXtTiny + weights: ${const:torchvision.models.ConvNeXt_Tiny_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/hydra.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..148828efb026866d6ff9494d75644774101363c7 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250429-091731/log/20250429-091735 + sweep: + dir: multirun/${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/20250429-091731/log/20250429-091735 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_15s + - train=birdclef2025_convnext_tiny + - model=birdclef2025_convnext_tiny + - optimizer=adamw_1e-4_decay_5e-2 + - lr_scheduler=none + - criterion=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/20250429-091731 + - train.output.tensorboard_dir=./tensorboard/20250429-091731 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_15s,lr_scheduler=none,model=birdclef2025_convnext_tiny,optimizer=adamw_1e-4_decay_5e-2,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/20250429-091731,train.output.tensorboard_dir=./tensorboard/20250429-091731,train.resume.continue_from=,train=birdclef2025_convnext_tiny + 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/ConvNeXtTiny + 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/ConvNeXtTiny/conf + schema: file + provider: command-line + - path: '' + schema: structured + provider: schema + output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adamw_1e-4_decay_5e-2 + model: birdclef2025_convnext_tiny + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_convnext_tiny + 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 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/overrides.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0363eb03a77ef8ea6e1a0697acad596fc290d551 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_15s +- train=birdclef2025_convnext_tiny +- model=birdclef2025_convnext_tiny +- optimizer=adamw_1e-4_decay_5e-2 +- lr_scheduler=none +- criterion=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/20250429-091731 +- train.output.tensorboard_dir=./tensorboard/20250429-091731 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8389026c9219583fe6f4098cf3156b5fe3d915a8 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/.hydra/resolved_config.yaml @@ -0,0 +1,280 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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: true + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2024BaselineMelSpectrogram + 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/20250429-091731 + tensorboard_dir: ./tensorboard/20250429-091731 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250429-091731/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250429-091731/model/epoch{epoch}.pth + last: + path: ./exp/20250429-091731/model/last.pth + best_epoch: + path: ./exp/20250429-091731/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.ConvNeXtTiny + weights: IMAGENET1K_V1 + num_classes: 206 +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/train.log b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/train.log new file mode 100644 index 0000000000000000000000000000000000000000..3256725d8bffefa00a7b6a6ba116fa5728b9e7e5 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/log/20250429-091735/train.log @@ -0,0 +1,4088 @@ +[2025-04-29 09:18:07,732][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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250429-091731 + tensorboard_dir: ./tensorboard/20250429-091731 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.ConvNeXtTiny + weights: ${const:torchvision.models.ConvNeXt_Tiny_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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} + +[2025-04-29 09:18:07,732][BaseTrainer][INFO] - ConvNeXtTiny( + (backbone): Sequential( + (0): Conv2dNormActivation( + (0): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4)) + (1): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True) + ) + (1): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0058823529411764705, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.011764705882352941, mode=row) + ) + ) + (2): Sequential( + (0): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(96, 192, kernel_size=(2, 2), stride=(2, 2)) + ) + (3): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.017647058823529415, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.023529411764705882, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.029411764705882353, mode=row) + ) + ) + (4): Sequential( + (0): LayerNorm2d((192,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(192, 384, kernel_size=(2, 2), stride=(2, 2)) + ) + (5): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.03529411764705883, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0411764705882353, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.047058823529411764, mode=row) + ) + (3): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.052941176470588235, mode=row) + ) + (4): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.058823529411764705, mode=row) + ) + (5): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.06470588235294118, mode=row) + ) + (6): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.07058823529411766, mode=row) + ) + (7): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.07647058823529412, mode=row) + ) + (8): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0823529411764706, mode=row) + ) + ) + (6): Sequential( + (0): LayerNorm2d((384,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(384, 768, kernel_size=(2, 2), stride=(2, 2)) + ) + (7): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.08823529411764706, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.09411764705882353, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.1, mode=row) + ) + ) + ) + (avgpool): AdaptiveAvgPool2d(output_size=1) + (classifier): Sequential( + (0): LayerNorm2d((768,), eps=1e-06, elementwise_affine=True) + (1): Flatten(start_dim=1, end_dim=-1) + (2): Linear(in_features=768, out_features=206, bias=True) + ) +) +[2025-04-29 09:18:07,735][BaseTrainer][INFO] - # of parameters: 27978542. +[2025-04-29 09:18:24,980][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.39541482925415, cross_entropy: 5.39541482925415 +[2025-04-29 09:18:25,808][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.326910495758057, cross_entropy: 5.326910495758057 +[2025-04-29 09:18:26,707][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.276432037353516, cross_entropy: 5.276432037353516 +[2025-04-29 09:18:27,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.297133445739746, cross_entropy: 5.297133445739746 +[2025-04-29 09:18:28,483][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.221197128295898, cross_entropy: 5.221197128295898 +[2025-04-29 09:18:30,740][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.210458755493164, cross_entropy: 5.210458755493164 +[2025-04-29 09:18:31,731][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 5.265125274658203, cross_entropy: 5.265125274658203 +[2025-04-29 09:18:36,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.225888729095459, cross_entropy: 5.225888729095459 +[2025-04-29 09:18:36,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 5.163714408874512, cross_entropy: 5.163714408874512 +[2025-04-29 09:18:41,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.1530914306640625, cross_entropy: 5.1530914306640625 +[2025-04-29 09:18:41,914][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.14111328125, cross_entropy: 5.14111328125 +[2025-04-29 09:18:45,555][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 5.044879913330078, cross_entropy: 5.044879913330078 +[2025-04-29 09:18:46,402][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.976496696472168, cross_entropy: 4.976496696472168 +[2025-04-29 09:18:50,924][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 5.002640247344971, cross_entropy: 5.002640247344971 +[2025-04-29 09:18:51,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.948158264160156, cross_entropy: 4.948158264160156 +[2025-04-29 09:18:55,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 5.001103401184082, cross_entropy: 5.001103401184082 +[2025-04-29 09:18:56,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.056065559387207, cross_entropy: 5.056065559387207 +[2025-04-29 09:18:59,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.071576118469238, cross_entropy: 5.071576118469238 +[2025-04-29 09:19:00,262][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.945376873016357, cross_entropy: 4.945376873016357 +[2025-04-29 09:19:03,336][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.916522026062012, cross_entropy: 4.916522026062012 +[2025-04-29 09:19:04,182][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.842896461486816, cross_entropy: 4.842896461486816 +[2025-04-29 09:19:07,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.863093376159668, cross_entropy: 4.863093376159668 +[2025-04-29 09:19:08,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.6864728927612305, cross_entropy: 4.6864728927612305 +[2025-04-29 09:19:11,835][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 5.0499444007873535, cross_entropy: 5.0499444007873535 +[2025-04-29 09:19:12,671][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.596187114715576, cross_entropy: 4.596187114715576 +[2025-04-29 09:19:16,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.9312262535095215, cross_entropy: 4.9312262535095215 +[2025-04-29 09:19:16,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.858762741088867, cross_entropy: 4.858762741088867 +[2025-04-29 09:19:20,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.709715843200684, cross_entropy: 4.709715843200684 +[2025-04-29 09:19:21,431][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.981616020202637, cross_entropy: 4.981616020202637 +[2025-04-29 09:19:24,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.783123970031738, cross_entropy: 4.783123970031738 +[2025-04-29 09:19:25,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.804059028625488, cross_entropy: 4.804059028625488 +[2025-04-29 09:19:27,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.680903911590576, cross_entropy: 4.680903911590576 +[2025-04-29 09:19:28,786][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.808039665222168, cross_entropy: 4.808039665222168 +[2025-04-29 09:19:32,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.8227763175964355, cross_entropy: 4.8227763175964355 +[2025-04-29 09:19:33,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.6005353927612305, cross_entropy: 4.6005353927612305 +[2025-04-29 09:19:36,120][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.923259735107422, cross_entropy: 4.923259735107422 +[2025-04-29 09:19:36,967][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.747910976409912, cross_entropy: 4.747910976409912 +[2025-04-29 09:19:39,901][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.771886825561523, cross_entropy: 4.771886825561523 +[2025-04-29 09:19:40,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.598780155181885, cross_entropy: 4.598780155181885 +[2025-04-29 09:19:44,394][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.775224208831787, cross_entropy: 4.775224208831787 +[2025-04-29 09:19:45,247][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.679765701293945, cross_entropy: 4.679765701293945 +[2025-04-29 09:19:48,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.795788764953613, cross_entropy: 4.795788764953613 +[2025-04-29 09:19:49,081][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.885064125061035, cross_entropy: 4.885064125061035 +[2025-04-29 09:19:51,957][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.774516582489014, cross_entropy: 4.774516582489014 +[2025-04-29 09:19:52,790][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.720393180847168, cross_entropy: 4.720393180847168 +[2025-04-29 09:19:55,905][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.505476951599121, cross_entropy: 4.505476951599121 +[2025-04-29 09:19:56,763][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.767792224884033, cross_entropy: 4.767792224884033 +[2025-04-29 09:19:59,601][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.515321254730225, cross_entropy: 4.515321254730225 +[2025-04-29 09:20:00,436][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.484206199645996, cross_entropy: 4.484206199645996 +[2025-04-29 09:20:04,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.687824249267578, cross_entropy: 4.687824249267578 +[2025-04-29 09:20:05,545][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.556356906890869, cross_entropy: 4.556356906890869 +[2025-04-29 09:20:08,185][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.775062084197998, cross_entropy: 4.775062084197998 +[2025-04-29 09:20:09,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.4374213218688965, cross_entropy: 4.4374213218688965 +[2025-04-29 09:20:11,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.759738445281982, cross_entropy: 4.759738445281982 +[2025-04-29 09:20:12,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.587895393371582, cross_entropy: 4.587895393371582 +[2025-04-29 09:20:15,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.671651840209961, cross_entropy: 4.671651840209961 +[2025-04-29 09:20:16,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.448115348815918, cross_entropy: 4.448115348815918 +[2025-04-29 09:20:18,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.710867881774902, cross_entropy: 4.710867881774902 +[2025-04-29 09:20:19,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.678606033325195, cross_entropy: 4.678606033325195 +[2025-04-29 09:20:21,521][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.686911582946777, cross_entropy: 4.686911582946777 +[2025-04-29 09:20:22,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.650328636169434, cross_entropy: 4.650328636169434 +[2025-04-29 09:20:25,576][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.753284454345703, cross_entropy: 4.753284454345703 +[2025-04-29 09:20:26,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.827296257019043, cross_entropy: 4.827296257019043 +[2025-04-29 09:20:30,349][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.724641799926758, cross_entropy: 4.724641799926758 +[2025-04-29 09:20:31,166][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.675200462341309, cross_entropy: 4.675200462341309 +[2025-04-29 09:20:34,558][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.701305389404297, cross_entropy: 4.701305389404297 +[2025-04-29 09:20:35,404][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.521664142608643, cross_entropy: 4.521664142608643 +[2025-04-29 09:20:38,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.556984901428223, cross_entropy: 4.556984901428223 +[2025-04-29 09:20:39,245][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.591421127319336, cross_entropy: 4.591421127319336 +[2025-04-29 09:20:42,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.550356864929199, cross_entropy: 4.550356864929199 +[2025-04-29 09:20:43,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.766571998596191, cross_entropy: 4.766571998596191 +[2025-04-29 09:20:47,370][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.409924507141113, cross_entropy: 4.409924507141113 +[2025-04-29 09:20:48,207][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 4.5840864181518555, cross_entropy: 4.5840864181518555 +[2025-04-29 09:20:50,593][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.459896564483643, cross_entropy: 4.459896564483643 +[2025-04-29 09:20:51,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.560616493225098, cross_entropy: 4.560616493225098 +[2025-04-29 09:20:54,512][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.53794002532959, cross_entropy: 4.53794002532959 +[2025-04-29 09:20:55,363][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.470128059387207, cross_entropy: 4.470128059387207 +[2025-04-29 09:20:59,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.751114845275879, cross_entropy: 4.751114845275879 +[2025-04-29 09:20:59,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.649249076843262, cross_entropy: 4.649249076843262 +[2025-04-29 09:21:03,568][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.480862140655518, cross_entropy: 4.480862140655518 +[2025-04-29 09:21:04,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.799219131469727, cross_entropy: 4.799219131469727 +[2025-04-29 09:21:07,000][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.554509162902832, cross_entropy: 4.554509162902832 +[2025-04-29 09:21:07,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.582938194274902, cross_entropy: 4.582938194274902 +[2025-04-29 09:21:10,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.25062370300293, cross_entropy: 4.25062370300293 +[2025-04-29 09:21:11,788][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.262301921844482, cross_entropy: 4.262301921844482 +[2025-04-29 09:21:14,987][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 4.449458122253418, cross_entropy: 4.449458122253418 +[2025-04-29 09:21:15,829][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.625925540924072, cross_entropy: 4.625925540924072 +[2025-04-29 09:21:18,721][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.314150810241699, cross_entropy: 4.314150810241699 +[2025-04-29 09:21:19,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.410458087921143, cross_entropy: 4.410458087921143 +[2025-04-29 09:21:22,633][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.438906192779541, cross_entropy: 4.438906192779541 +[2025-04-29 09:21:23,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.150539398193359, cross_entropy: 4.150539398193359 +[2025-04-29 09:21:26,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 4.60145378112793, cross_entropy: 4.60145378112793 +[2025-04-29 09:21:27,195][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 4.378594398498535, cross_entropy: 4.378594398498535 +[2025-04-29 09:21:30,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.384273529052734, cross_entropy: 4.384273529052734 +[2025-04-29 09:21:30,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.28433895111084, cross_entropy: 4.28433895111084 +[2025-04-29 09:21:33,283][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 4.316105842590332, cross_entropy: 4.316105842590332 +[2025-04-29 09:21:34,100][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.464640140533447, cross_entropy: 4.464640140533447 +[2025-04-29 09:21:37,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 4.369460105895996, cross_entropy: 4.369460105895996 +[2025-04-29 09:21:37,911][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.416576385498047, cross_entropy: 4.416576385498047 +[2025-04-29 09:21:41,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 4.425522804260254, cross_entropy: 4.425522804260254 +[2025-04-29 09:21:41,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.398844242095947, cross_entropy: 4.398844242095947 +[2025-04-29 09:21:44,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 4.407689094543457, cross_entropy: 4.407689094543457 +[2025-04-29 09:21:45,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.521717071533203, cross_entropy: 4.521717071533203 +[2025-04-29 09:21:47,462][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 4.424776077270508, cross_entropy: 4.424776077270508 +[2025-04-29 09:21:48,288][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 4.030255317687988, cross_entropy: 4.030255317687988 +[2025-04-29 09:21:51,023][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.244585990905762, cross_entropy: 4.244585990905762 +[2025-04-29 09:21:51,861][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 4.5764689445495605, cross_entropy: 4.5764689445495605 +[2025-04-29 09:21:54,765][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.158109664916992, cross_entropy: 4.158109664916992 +[2025-04-29 09:21:55,584][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 4.239748001098633, cross_entropy: 4.239748001098633 +[2025-04-29 09:21:58,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.4874491691589355, cross_entropy: 4.4874491691589355 +[2025-04-29 09:21:59,465][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.9433844089508057, cross_entropy: 3.9433844089508057 +[2025-04-29 09:22:02,397][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 4.150274753570557, cross_entropy: 4.150274753570557 +[2025-04-29 09:22:03,213][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.514612197875977, cross_entropy: 4.514612197875977 +[2025-04-29 09:22:06,440][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.480466842651367, cross_entropy: 4.480466842651367 +[2025-04-29 09:22:07,281][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.091066837310791, cross_entropy: 4.091066837310791 +[2025-04-29 09:22:10,836][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 4.478976726531982, cross_entropy: 4.478976726531982 +[2025-04-29 09:22:11,672][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 4.243259906768799, cross_entropy: 4.243259906768799 +[2025-04-29 09:22:14,126][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.209486961364746, cross_entropy: 4.209486961364746 +[2025-04-29 09:22:14,967][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.169050693511963, cross_entropy: 4.169050693511963 +[2025-04-29 09:22:17,609][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.001333236694336, cross_entropy: 4.001333236694336 +[2025-04-29 09:22:18,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.616253852844238, cross_entropy: 4.616253852844238 +[2025-04-29 09:22:21,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 4.252390384674072, cross_entropy: 4.252390384674072 +[2025-04-29 09:22:21,989][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 4.591151237487793, cross_entropy: 4.591151237487793 +[2025-04-29 09:22:24,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 4.035207271575928, cross_entropy: 4.035207271575928 +[2025-04-29 09:22:25,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 3.9895572662353516, cross_entropy: 3.9895572662353516 +[2025-04-29 09:22:28,217][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 4.275299072265625, cross_entropy: 4.275299072265625 +[2025-04-29 09:22:29,032][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 4.5521440505981445, cross_entropy: 4.5521440505981445 +[2025-04-29 09:22:31,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.389959335327148, cross_entropy: 4.389959335327148 +[2025-04-29 09:22:32,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 3.8864307403564453, cross_entropy: 3.8864307403564453 +[2025-04-29 09:22:34,907][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.95345139503479, cross_entropy: 3.95345139503479 +[2025-04-29 09:22:35,722][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.013337135314941, cross_entropy: 4.013337135314941 +[2025-04-29 09:22:39,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 4.273968696594238, cross_entropy: 4.273968696594238 +[2025-04-29 09:22:39,867][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 3.7099058628082275, cross_entropy: 3.7099058628082275 +[2025-04-29 09:22:42,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.1591877937316895, cross_entropy: 4.1591877937316895 +[2025-04-29 09:22:43,121][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.347381591796875, cross_entropy: 4.347381591796875 +[2025-04-29 09:22:45,608][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 4.110365867614746, cross_entropy: 4.110365867614746 +[2025-04-29 09:22:46,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.9589247703552246, cross_entropy: 3.9589247703552246 +[2025-04-29 09:22:48,908][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 3.9795725345611572, cross_entropy: 3.9795725345611572 +[2025-04-29 09:22:49,738][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 3.964128255844116, cross_entropy: 3.964128255844116 +[2025-04-29 09:22:52,498][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 4.093176364898682, cross_entropy: 4.093176364898682 +[2025-04-29 09:22:53,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 3.9284348487854004, cross_entropy: 3.9284348487854004 +[2025-04-29 09:22:57,824][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.900289297103882, cross_entropy: 3.900289297103882 +[2025-04-29 09:22:58,647][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 4.0073018074035645, cross_entropy: 4.0073018074035645 +[2025-04-29 09:23:01,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.408718585968018, cross_entropy: 4.408718585968018 +[2025-04-29 09:23:02,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 3.8802404403686523, cross_entropy: 3.8802404403686523 +[2025-04-29 09:23:04,841][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 4.139453887939453, cross_entropy: 4.139453887939453 +[2025-04-29 09:23:05,682][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.189776420593262, cross_entropy: 4.189776420593262 +[2025-04-29 09:23:08,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.7750091552734375, cross_entropy: 3.7750091552734375 +[2025-04-29 09:23:09,120][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.289154529571533, cross_entropy: 4.289154529571533 +[2025-04-29 09:23:11,753][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 3.8338890075683594, cross_entropy: 3.8338890075683594 +[2025-04-29 09:23:12,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.363583564758301, cross_entropy: 3.363583564758301 +[2025-04-29 09:23:15,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.611438512802124, cross_entropy: 3.611438512802124 +[2025-04-29 09:23:16,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 3.7655587196350098, cross_entropy: 3.7655587196350098 +[2025-04-29 09:23:18,879][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 4.154061317443848, cross_entropy: 4.154061317443848 +[2025-04-29 09:23:19,706][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.587141990661621, cross_entropy: 3.587141990661621 +[2025-04-29 09:23:23,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.5382375717163086, cross_entropy: 3.5382375717163086 +[2025-04-29 09:23:24,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.075933933258057, cross_entropy: 4.075933933258057 +[2025-04-29 09:23:26,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 4.095848560333252, cross_entropy: 4.095848560333252 +[2025-04-29 09:23:27,595][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 3.7181434631347656, cross_entropy: 3.7181434631347656 +[2025-04-29 09:23:31,146][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.608071804046631, cross_entropy: 3.608071804046631 +[2025-04-29 09:23:31,959][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.66677188873291, cross_entropy: 3.66677188873291 +[2025-04-29 09:23:35,360][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.4586291313171387, cross_entropy: 3.4586291313171387 +[2025-04-29 09:23:36,202][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 3.368171215057373, cross_entropy: 3.368171215057373 +[2025-04-29 09:23:38,975][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.6624362468719482, cross_entropy: 3.6624362468719482 +[2025-04-29 09:23:39,792][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 4.069570064544678, cross_entropy: 4.069570064544678 +[2025-04-29 09:23:42,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.058381080627441, cross_entropy: 4.058381080627441 +[2025-04-29 09:23:43,624][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.5890750885009766, cross_entropy: 3.5890750885009766 +[2025-04-29 09:23:46,764][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.7067887783050537, cross_entropy: 3.7067887783050537 +[2025-04-29 09:23:47,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.209527969360352, cross_entropy: 4.209527969360352 +[2025-04-29 09:23:51,787][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.765777587890625, cross_entropy: 3.765777587890625 +[2025-04-29 09:23:52,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.345106840133667, cross_entropy: 3.345106840133667 +[2025-04-29 09:23:55,837][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.6664021015167236, cross_entropy: 3.6664021015167236 +[2025-04-29 09:23:56,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.5870089530944824, cross_entropy: 3.5870089530944824 +[2025-04-29 09:23:59,693][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.005295753479004, cross_entropy: 4.005295753479004 +[2025-04-29 09:24:00,543][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.19697380065918, cross_entropy: 4.19697380065918 +[2025-04-29 09:24:04,402][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.8445444107055664, cross_entropy: 3.8445444107055664 +[2025-04-29 09:24:05,223][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.536665439605713, cross_entropy: 3.536665439605713 +[2025-04-29 09:24:08,312][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.4942073822021484, cross_entropy: 3.4942073822021484 +[2025-04-29 09:24:09,147][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.333893299102783, cross_entropy: 3.333893299102783 +[2025-04-29 09:24:12,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.347431182861328, cross_entropy: 3.347431182861328 +[2025-04-29 09:24:13,141][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 3.8975820541381836, cross_entropy: 3.8975820541381836 +[2025-04-29 09:24:16,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.459169864654541, cross_entropy: 3.459169864654541 +[2025-04-29 09:24:17,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 3.5912256240844727, cross_entropy: 3.5912256240844727 +[2025-04-29 09:24:21,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.194398403167725, cross_entropy: 4.194398403167725 +[2025-04-29 09:24:22,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.655391216278076, cross_entropy: 3.655391216278076 +[2025-04-29 09:24:25,783][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.8998849391937256, cross_entropy: 3.8998849391937256 +[2025-04-29 09:24:26,640][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.3496246337890625, cross_entropy: 3.3496246337890625 +[2025-04-29 09:24:30,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.9864258766174316, cross_entropy: 3.9864258766174316 +[2025-04-29 09:24:31,084][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 4.064568042755127, cross_entropy: 4.064568042755127 +[2025-04-29 09:24:33,844][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.1498632431030273, cross_entropy: 3.1498632431030273 +[2025-04-29 09:24:34,690][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 3.815615653991699, cross_entropy: 3.815615653991699 +[2025-04-29 09:24:37,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.6574442386627197, cross_entropy: 3.6574442386627197 +[2025-04-29 09:24:38,311][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.044040679931641, cross_entropy: 4.044040679931641 +[2025-04-29 09:24:41,077][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.4583375453948975, cross_entropy: 3.4583375453948975 +[2025-04-29 09:24:41,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 3.9782609939575195, cross_entropy: 3.9782609939575195 +[2025-04-29 09:24:44,428][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.6655774116516113, cross_entropy: 3.6655774116516113 +[2025-04-29 09:24:45,914][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 4.134226322174072, cross_entropy: 4.134226322174072 +[2025-04-29 09:24:48,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 3.0329248905181885, cross_entropy: 3.0329248905181885 +[2025-04-29 09:24:49,799][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.337099075317383, cross_entropy: 3.337099075317383 +[2025-04-29 09:24:52,975][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.3725452423095703, cross_entropy: 3.3725452423095703 +[2025-04-29 09:24:53,857][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 3.1981194019317627, cross_entropy: 3.1981194019317627 +[2025-04-29 09:24:56,972][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 3.1348307132720947, cross_entropy: 3.1348307132720947 +[2025-04-29 09:24:58,218][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.9110255241394043, cross_entropy: 3.9110255241394043 +[2025-04-29 09:25:00,702][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.507582902908325, cross_entropy: 3.507582902908325 +[2025-04-29 09:25:02,003][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.355930805206299, cross_entropy: 4.355930805206299 +[2025-04-29 09:25:05,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.5849833488464355, cross_entropy: 3.5849833488464355 +[2025-04-29 09:25:06,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 2.977262020111084, cross_entropy: 2.977262020111084 +[2025-04-29 09:25:09,796][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.3401846885681152, cross_entropy: 3.3401846885681152 +[2025-04-29 09:25:10,696][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 3.179917335510254, cross_entropy: 3.179917335510254 +[2025-04-29 09:25:13,565][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.2250592708587646, cross_entropy: 3.2250592708587646 +[2025-04-29 09:25:14,558][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.606757640838623, cross_entropy: 3.606757640838623 +[2025-04-29 09:25:17,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.718599319458008, cross_entropy: 3.718599319458008 +[2025-04-29 09:25:18,603][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 4.319202423095703, cross_entropy: 4.319202423095703 +[2025-04-29 09:25:22,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 3.239699363708496, cross_entropy: 3.239699363708496 +[2025-04-29 09:25:23,254][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 2.9308674335479736, cross_entropy: 2.9308674335479736 +[2025-04-29 09:25:26,553][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 4.255859851837158, cross_entropy: 4.255859851837158 +[2025-04-29 09:25:27,383][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.2998600006103516, cross_entropy: 3.2998600006103516 +[2025-04-29 09:25:30,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 2.840189218521118, cross_entropy: 2.840189218521118 +[2025-04-29 09:25:31,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 4.093425750732422, cross_entropy: 4.093425750732422 +[2025-04-29 09:25:35,400][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 4.001673698425293, cross_entropy: 4.001673698425293 +[2025-04-29 09:25:36,308][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.6771678924560547, cross_entropy: 3.6771678924560547 +[2025-04-29 09:25:39,921][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 3.0820770263671875, cross_entropy: 3.0820770263671875 +[2025-04-29 09:25:40,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.878755569458008, cross_entropy: 3.878755569458008 +[2025-04-29 09:25:43,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.8422179222106934, cross_entropy: 3.8422179222106934 +[2025-04-29 09:25:44,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 3.529238224029541, cross_entropy: 3.529238224029541 +[2025-04-29 09:25:47,039][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 2.9696929454803467, cross_entropy: 2.9696929454803467 +[2025-04-29 09:25:48,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.184412956237793, cross_entropy: 3.184412956237793 +[2025-04-29 09:25:52,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.2467145919799805, cross_entropy: 3.2467145919799805 +[2025-04-29 09:25:53,101][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 3.4684972763061523, cross_entropy: 3.4684972763061523 +[2025-04-29 09:25:55,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 3.8232104778289795, cross_entropy: 3.8232104778289795 +[2025-04-29 09:25:57,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 3.558706760406494, cross_entropy: 3.558706760406494 +[2025-04-29 09:25:59,648][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 3.2877321243286133, cross_entropy: 3.2877321243286133 +[2025-04-29 09:26:01,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 3.3647708892822266, cross_entropy: 3.3647708892822266 +[2025-04-29 09:26:05,428][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 3.347053050994873, cross_entropy: 3.347053050994873 +[2025-04-29 09:26:06,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.2112343311309814, cross_entropy: 3.2112343311309814 +[2025-04-29 09:26:09,312][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.2050161361694336, cross_entropy: 3.2050161361694336 +[2025-04-29 09:26:10,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 3.2745392322540283, cross_entropy: 3.2745392322540283 +[2025-04-29 09:26:13,380][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 3.5332674980163574, cross_entropy: 3.5332674980163574 +[2025-04-29 09:26:14,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.0338873863220215, cross_entropy: 3.0338873863220215 +[2025-04-29 09:26:17,573][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.067615509033203, cross_entropy: 3.067615509033203 +[2025-04-29 09:26:18,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 2.9713501930236816, cross_entropy: 2.9713501930236816 +[2025-04-29 09:26:22,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 3.9377291202545166, cross_entropy: 3.9377291202545166 +[2025-04-29 09:26:23,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 2.8160312175750732, cross_entropy: 2.8160312175750732 +[2025-04-29 09:26:27,151][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 3.1135003566741943, cross_entropy: 3.1135003566741943 +[2025-04-29 09:26:27,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.524998664855957, cross_entropy: 3.524998664855957 +[2025-04-29 09:26:30,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 2.7283074855804443, cross_entropy: 2.7283074855804443 +[2025-04-29 09:26:31,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.575133800506592, cross_entropy: 3.575133800506592 +[2025-04-29 09:26:35,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 4.1706390380859375, cross_entropy: 4.1706390380859375 +[2025-04-29 09:26:36,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.5348587036132812, cross_entropy: 3.5348587036132812 +[2025-04-29 09:26:39,020][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 3.8844170570373535, cross_entropy: 3.8844170570373535 +[2025-04-29 09:26:39,867][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.1709327697753906, cross_entropy: 3.1709327697753906 +[2025-04-29 09:26:43,832][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 3.4615232944488525, cross_entropy: 3.4615232944488525 +[2025-04-29 09:26:44,675][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.0560312271118164, cross_entropy: 3.0560312271118164 +[2025-04-29 09:26:47,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 3.0191450119018555, cross_entropy: 3.0191450119018555 +[2025-04-29 09:26:48,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 2.589146614074707, cross_entropy: 2.589146614074707 +[2025-04-29 09:26:51,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.1659088134765625, cross_entropy: 3.1659088134765625 +[2025-04-29 09:26:52,746][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 4.0518622398376465, cross_entropy: 4.0518622398376465 +[2025-04-29 09:26:56,157][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 3.57011079788208, cross_entropy: 3.57011079788208 +[2025-04-29 09:26:56,976][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 3.6438050270080566, cross_entropy: 3.6438050270080566 +[2025-04-29 09:27:00,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 3.0115065574645996, cross_entropy: 3.0115065574645996 +[2025-04-29 09:27:00,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.6655375957489014, cross_entropy: 2.6655375957489014 +[2025-04-29 09:27:04,047][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 4.098105430603027, cross_entropy: 4.098105430603027 +[2025-04-29 09:27:04,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 3.2355294227600098, cross_entropy: 3.2355294227600098 +[2025-04-29 09:27:08,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 2.9059054851531982, cross_entropy: 2.9059054851531982 +[2025-04-29 09:27:09,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 3.0254883766174316, cross_entropy: 3.0254883766174316 +[2025-04-29 09:27:12,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.121757984161377, cross_entropy: 3.121757984161377 +[2025-04-29 09:27:13,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 3.209777355194092, cross_entropy: 3.209777355194092 +[2025-04-29 09:27:17,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.553668260574341, cross_entropy: 2.553668260574341 +[2025-04-29 09:27:17,853][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 3.426056385040283, cross_entropy: 3.426056385040283 +[2025-04-29 09:27:20,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.9959728717803955, cross_entropy: 3.9959728717803955 +[2025-04-29 09:27:21,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.8754842281341553, cross_entropy: 3.8754842281341553 +[2025-04-29 09:27:24,553][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 3.8026933670043945, cross_entropy: 3.8026933670043945 +[2025-04-29 09:27:25,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.691904067993164, cross_entropy: 3.691904067993164 +[2025-04-29 09:27:28,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.01995849609375, cross_entropy: 3.01995849609375 +[2025-04-29 09:27:29,212][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 4.063004970550537, cross_entropy: 4.063004970550537 +[2025-04-29 09:27:32,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 3.701338291168213, cross_entropy: 3.701338291168213 +[2025-04-29 09:27:33,071][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.171990394592285, cross_entropy: 3.171990394592285 +[2025-04-29 09:27:36,229][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 2.7353808879852295, cross_entropy: 2.7353808879852295 +[2025-04-29 09:27:37,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.068312644958496, cross_entropy: 4.068312644958496 +[2025-04-29 09:27:39,748][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.2871851921081543, cross_entropy: 3.2871851921081543 +[2025-04-29 09:27:40,600][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 3.4145426750183105, cross_entropy: 3.4145426750183105 +[2025-04-29 09:27:43,625][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.0831451416015625, cross_entropy: 3.0831451416015625 +[2025-04-29 09:27:44,475][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.5385801792144775, cross_entropy: 3.5385801792144775 +[2025-04-29 09:27:47,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.7438554763793945, cross_entropy: 2.7438554763793945 +[2025-04-29 09:27:48,364][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.7161736488342285, cross_entropy: 2.7161736488342285 +[2025-04-29 09:27:51,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.3943965435028076, cross_entropy: 3.3943965435028076 +[2025-04-29 09:27:52,345][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 2.7792716026306152, cross_entropy: 2.7792716026306152 +[2025-04-29 09:27:55,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 2.5371835231781006, cross_entropy: 2.5371835231781006 +[2025-04-29 09:27:56,080][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.612921953201294, cross_entropy: 3.612921953201294 +[2025-04-29 09:28:00,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.7193307876586914, cross_entropy: 2.7193307876586914 +[2025-04-29 09:28:01,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.8898892402648926, cross_entropy: 2.8898892402648926 +[2025-04-29 09:28:03,986][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.3302454948425293, cross_entropy: 3.3302454948425293 +[2025-04-29 09:28:06,645][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 3.80611252784729, cross_entropy: 3.80611252784729 +[2025-04-29 09:28:07,540][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.7819268703460693, cross_entropy: 2.7819268703460693 +[2025-04-29 09:28:10,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.6868438720703125, cross_entropy: 2.6868438720703125 +[2025-04-29 09:28:11,864][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.08197021484375, cross_entropy: 3.08197021484375 +[2025-04-29 09:28:15,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 4.137067794799805, cross_entropy: 4.137067794799805 +[2025-04-29 09:28:16,277][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 2.55039119720459, cross_entropy: 2.55039119720459 +[2025-04-29 09:28:19,569][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.0061631202697754, cross_entropy: 3.0061631202697754 +[2025-04-29 09:28:20,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 2.465473175048828, cross_entropy: 2.465473175048828 +[2025-04-29 09:28:24,025][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.081207752227783, cross_entropy: 2.081207752227783 +[2025-04-29 09:28:25,149][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 2.6789064407348633, cross_entropy: 2.6789064407348633 +[2025-04-29 09:28:28,454][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.8405890464782715, cross_entropy: 2.8405890464782715 +[2025-04-29 09:28:29,349][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 2.3531689643859863, cross_entropy: 2.3531689643859863 +[2025-04-29 09:28:32,439][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 3.2868635654449463, cross_entropy: 3.2868635654449463 +[2025-04-29 09:28:33,317][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.3530869483947754, cross_entropy: 2.3530869483947754 +[2025-04-29 09:28:37,648][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 2.940899133682251, cross_entropy: 2.940899133682251 +[2025-04-29 09:28:38,495][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 2.8004629611968994, cross_entropy: 2.8004629611968994 +[2025-04-29 09:28:41,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 2.234809398651123, cross_entropy: 2.234809398651123 +[2025-04-29 09:28:42,275][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.6824951171875, cross_entropy: 2.6824951171875 +[2025-04-29 09:28:46,017][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 3.4887447357177734, cross_entropy: 3.4887447357177734 +[2025-04-29 09:28:46,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.100102424621582, cross_entropy: 3.100102424621582 +[2025-04-29 09:28:49,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 2.8744659423828125, cross_entropy: 2.8744659423828125 +[2025-04-29 09:28:50,636][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.0561718940734863, cross_entropy: 3.0561718940734863 +[2025-04-29 09:28:54,135][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.757225513458252, cross_entropy: 2.757225513458252 +[2025-04-29 09:28:54,980][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.3507046699523926, cross_entropy: 3.3507046699523926 +[2025-04-29 09:28:57,794][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.625072479248047, cross_entropy: 2.625072479248047 +[2025-04-29 09:28:58,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.1128714084625244, cross_entropy: 3.1128714084625244 +[2025-04-29 09:29:01,474][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.051450252532959, cross_entropy: 3.051450252532959 +[2025-04-29 09:29:02,321][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.396385669708252, cross_entropy: 2.396385669708252 +[2025-04-29 09:29:04,988][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 3.7349929809570312, cross_entropy: 3.7349929809570312 +[2025-04-29 09:29:05,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 2.7083094120025635, cross_entropy: 2.7083094120025635 +[2025-04-29 09:29:08,943][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 2.446925163269043, cross_entropy: 2.446925163269043 +[2025-04-29 09:29:09,791][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 3.642958641052246, cross_entropy: 3.642958641052246 +[2025-04-29 09:29:12,595][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 2.8606324195861816, cross_entropy: 2.8606324195861816 +[2025-04-29 09:29:13,491][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 2.6187920570373535, cross_entropy: 2.6187920570373535 +[2025-04-29 09:29:16,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.680335521697998, cross_entropy: 2.680335521697998 +[2025-04-29 09:29:17,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 3.694591760635376, cross_entropy: 3.694591760635376 +[2025-04-29 09:29:20,715][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 2.969877004623413, cross_entropy: 2.969877004623413 +[2025-04-29 09:29:21,546][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.9796550273895264, cross_entropy: 3.9796550273895264 +[2025-04-29 09:29:24,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.180285930633545, cross_entropy: 3.180285930633545 +[2025-04-29 09:29:24,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 2.380168914794922, cross_entropy: 2.380168914794922 +[2025-04-29 09:29:28,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.358889579772949, cross_entropy: 3.358889579772949 +[2025-04-29 09:29:29,134][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 2.500415325164795, cross_entropy: 2.500415325164795 +[2025-04-29 09:29:31,801][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 3.4483115673065186, cross_entropy: 3.4483115673065186 +[2025-04-29 09:29:32,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.6838603019714355, cross_entropy: 2.6838603019714355 +[2025-04-29 09:29:35,820][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 2.057425022125244, cross_entropy: 2.057425022125244 +[2025-04-29 09:29:36,745][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 2.3739640712738037, cross_entropy: 2.3739640712738037 +[2025-04-29 09:29:39,633][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.519301414489746, cross_entropy: 2.519301414489746 +[2025-04-29 09:29:40,935][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 2.4879870414733887, cross_entropy: 2.4879870414733887 +[2025-04-29 09:29:43,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.3802292346954346, cross_entropy: 3.3802292346954346 +[2025-04-29 09:29:45,091][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.23462176322937, cross_entropy: 3.23462176322937 +[2025-04-29 09:29:47,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 3.018707036972046, cross_entropy: 3.018707036972046 +[2025-04-29 09:29:48,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.0177130699157715, cross_entropy: 2.0177130699157715 +[2025-04-29 09:29:51,756][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.6813769340515137, cross_entropy: 3.6813769340515137 +[2025-04-29 09:29:53,710][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 2.8895819187164307, cross_entropy: 2.8895819187164307 +[2025-04-29 09:29:55,654][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.3848257064819336, cross_entropy: 2.3848257064819336 +[2025-04-29 09:29:58,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.2770981788635254, cross_entropy: 2.2770981788635254 +[2025-04-29 09:29:59,711][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 2.885246753692627, cross_entropy: 2.885246753692627 +[2025-04-29 09:30:02,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.356804847717285, cross_entropy: 2.356804847717285 +[2025-04-29 09:30:03,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.5892229080200195, cross_entropy: 2.5892229080200195 +[2025-04-29 09:30:06,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.404222011566162, cross_entropy: 2.404222011566162 +[2025-04-29 09:30:07,264][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.5981881618499756, cross_entropy: 2.5981881618499756 +[2025-04-29 09:30:10,474][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 2.7209551334381104, cross_entropy: 2.7209551334381104 +[2025-04-29 09:30:11,295][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 2.784273862838745, cross_entropy: 2.784273862838745 +[2025-04-29 09:30:22,641][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.147103786468506, cross_entropy: 3.147103786468506 +[2025-04-29 09:33:33,644][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.8195385932922363, cross_entropy: 3.8195385932922363 +[2025-04-29 09:33:33,644][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.2236948013305664, cross_entropy: 2.2236948013305664 +[2025-04-29 09:33:34,223][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 09:33:34,784][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch1.pth. +[2025-04-29 09:33:35,341][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 09:33:40,072][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 2.5435891151428223, cross_entropy: 2.5435891151428223 +[2025-04-29 09:33:40,963][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 3.327740430831909, cross_entropy: 3.327740430831909 +[2025-04-29 09:33:44,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.4221138954162598, cross_entropy: 3.4221138954162598 +[2025-04-29 09:33:45,400][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 2.448209762573242, cross_entropy: 2.448209762573242 +[2025-04-29 09:33:48,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 3.2879323959350586, cross_entropy: 3.2879323959350586 +[2025-04-29 09:33:48,997][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 2.153442859649658, cross_entropy: 2.153442859649658 +[2025-04-29 09:33:51,378][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.372978448867798, cross_entropy: 2.372978448867798 +[2025-04-29 09:33:52,245][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 3.02410626411438, cross_entropy: 3.02410626411438 +[2025-04-29 09:33:55,188][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.607694625854492, cross_entropy: 2.607694625854492 +[2025-04-29 09:33:56,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.184307098388672, cross_entropy: 2.184307098388672 +[2025-04-29 09:33:59,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.3853304386138916, cross_entropy: 2.3853304386138916 +[2025-04-29 09:34:00,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 2.0867321491241455, cross_entropy: 2.0867321491241455 +[2025-04-29 09:34:03,566][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 2.363980770111084, cross_entropy: 2.363980770111084 +[2025-04-29 09:34:04,424][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.201469659805298, cross_entropy: 2.201469659805298 +[2025-04-29 09:34:07,436][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.4801855087280273, cross_entropy: 3.4801855087280273 +[2025-04-29 09:34:08,291][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 1.994592547416687, cross_entropy: 1.994592547416687 +[2025-04-29 09:34:11,382][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.871901273727417, cross_entropy: 2.871901273727417 +[2025-04-29 09:34:12,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 3.4330973625183105, cross_entropy: 3.4330973625183105 +[2025-04-29 09:34:15,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.7445855140686035, cross_entropy: 3.7445855140686035 +[2025-04-29 09:34:16,210][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.4974398612976074, cross_entropy: 2.4974398612976074 +[2025-04-29 09:34:20,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.519651412963867, cross_entropy: 3.519651412963867 +[2025-04-29 09:34:21,085][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 3.1611251831054688, cross_entropy: 3.1611251831054688 +[2025-04-29 09:34:24,686][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.1246986389160156, cross_entropy: 3.1246986389160156 +[2025-04-29 09:34:25,543][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.208132266998291, cross_entropy: 3.208132266998291 +[2025-04-29 09:34:28,938][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.4652481079101562, cross_entropy: 3.4652481079101562 +[2025-04-29 09:34:29,759][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.797095775604248, cross_entropy: 2.797095775604248 +[2025-04-29 09:34:33,795][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 2.985452175140381, cross_entropy: 2.985452175140381 +[2025-04-29 09:34:34,615][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.3076438903808594, cross_entropy: 2.3076438903808594 +[2025-04-29 09:34:37,847][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 2.6594910621643066, cross_entropy: 2.6594910621643066 +[2025-04-29 09:34:38,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 2.019900321960449, cross_entropy: 2.019900321960449 +[2025-04-29 09:34:41,626][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.632625102996826, cross_entropy: 2.632625102996826 +[2025-04-29 09:34:42,478][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.6306371688842773, cross_entropy: 2.6306371688842773 +[2025-04-29 09:34:45,396][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 3.2200965881347656, cross_entropy: 3.2200965881347656 +[2025-04-29 09:34:46,247][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 2.9920058250427246, cross_entropy: 2.9920058250427246 +[2025-04-29 09:34:48,423][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.6907854080200195, cross_entropy: 2.6907854080200195 +[2025-04-29 09:34:49,275][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 2.4736478328704834, cross_entropy: 2.4736478328704834 +[2025-04-29 09:34:52,403][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 2.6388564109802246, cross_entropy: 2.6388564109802246 +[2025-04-29 09:34:53,256][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 2.794051170349121, cross_entropy: 2.794051170349121 +[2025-04-29 09:34:56,190][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 2.353036403656006, cross_entropy: 2.353036403656006 +[2025-04-29 09:34:57,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.5097270011901855, cross_entropy: 2.5097270011901855 +[2025-04-29 09:34:59,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.5385186672210693, cross_entropy: 3.5385186672210693 +[2025-04-29 09:35:00,202][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.996088981628418, cross_entropy: 2.996088981628418 +[2025-04-29 09:35:03,367][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 2.3915915489196777, cross_entropy: 2.3915915489196777 +[2025-04-29 09:35:04,199][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 3.609434127807617, cross_entropy: 3.609434127807617 +[2025-04-29 09:35:06,907][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 2.0944771766662598, cross_entropy: 2.0944771766662598 +[2025-04-29 09:35:07,729][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 2.1507651805877686, cross_entropy: 2.1507651805877686 +[2025-04-29 09:35:10,853][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.7349510192871094, cross_entropy: 3.7349510192871094 +[2025-04-29 09:35:11,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 3.7808351516723633, cross_entropy: 3.7808351516723633 +[2025-04-29 09:35:14,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.536923885345459, cross_entropy: 3.536923885345459 +[2025-04-29 09:35:15,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 2.3763365745544434, cross_entropy: 2.3763365745544434 +[2025-04-29 09:35:18,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 2.8668408393859863, cross_entropy: 2.8668408393859863 +[2025-04-29 09:35:19,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 2.196681499481201, cross_entropy: 2.196681499481201 +[2025-04-29 09:35:22,854][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.173142671585083, cross_entropy: 3.173142671585083 +[2025-04-29 09:35:23,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.6483728885650635, cross_entropy: 3.6483728885650635 +[2025-04-29 09:35:26,494][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.194887161254883, cross_entropy: 3.194887161254883 +[2025-04-29 09:35:27,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.4136505126953125, cross_entropy: 2.4136505126953125 +[2025-04-29 09:35:31,703][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.391831874847412, cross_entropy: 2.391831874847412 +[2025-04-29 09:35:32,522][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.1650662422180176, cross_entropy: 2.1650662422180176 +[2025-04-29 09:35:37,106][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.077263593673706, cross_entropy: 3.077263593673706 +[2025-04-29 09:35:37,958][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 2.5507354736328125, cross_entropy: 2.5507354736328125 +[2025-04-29 09:35:40,121][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 2.328181743621826, cross_entropy: 2.328181743621826 +[2025-04-29 09:35:40,975][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 2.326143264770508, cross_entropy: 2.326143264770508 +[2025-04-29 09:35:44,172][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.600851535797119, cross_entropy: 2.600851535797119 +[2025-04-29 09:35:45,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 2.486942768096924, cross_entropy: 2.486942768096924 +[2025-04-29 09:35:47,720][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 3.4078714847564697, cross_entropy: 3.4078714847564697 +[2025-04-29 09:35:48,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 2.6235265731811523, cross_entropy: 2.6235265731811523 +[2025-04-29 09:35:51,184][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.000257968902588, cross_entropy: 2.000257968902588 +[2025-04-29 09:35:52,005][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 2.6468353271484375, cross_entropy: 2.6468353271484375 +[2025-04-29 09:35:54,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.7783493995666504, cross_entropy: 2.7783493995666504 +[2025-04-29 09:35:55,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 2.373232841491699, cross_entropy: 2.373232841491699 +[2025-04-29 09:35:59,075][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 2.7280240058898926, cross_entropy: 2.7280240058898926 +[2025-04-29 09:35:59,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.6957969665527344, cross_entropy: 2.6957969665527344 +[2025-04-29 09:36:02,749][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 1.9255328178405762, cross_entropy: 1.9255328178405762 +[2025-04-29 09:36:03,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 2.418470859527588, cross_entropy: 2.418470859527588 +[2025-04-29 09:36:06,075][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 3.9362590312957764, cross_entropy: 3.9362590312957764 +[2025-04-29 09:36:06,896][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 1.606865406036377, cross_entropy: 1.606865406036377 +[2025-04-29 09:36:09,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 3.143444061279297, cross_entropy: 3.143444061279297 +[2025-04-29 09:36:10,700][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.3752646446228027, cross_entropy: 3.3752646446228027 +[2025-04-29 09:36:13,331][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.481719732284546, cross_entropy: 3.481719732284546 +[2025-04-29 09:36:14,197][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 2.0141868591308594, cross_entropy: 2.0141868591308594 +[2025-04-29 09:36:16,041][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.5827527046203613, cross_entropy: 2.5827527046203613 +[2025-04-29 09:36:16,900][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.3637237548828125, cross_entropy: 3.3637237548828125 +[2025-04-29 09:36:20,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 3.3251686096191406, cross_entropy: 3.3251686096191406 +[2025-04-29 09:36:20,856][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 2.130810260772705, cross_entropy: 2.130810260772705 +[2025-04-29 09:36:24,241][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 2.2357239723205566, cross_entropy: 2.2357239723205566 +[2025-04-29 09:36:25,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 2.196770668029785, cross_entropy: 2.196770668029785 +[2025-04-29 09:36:28,422][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.1506314277648926, cross_entropy: 3.1506314277648926 +[2025-04-29 09:36:29,289][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.6912143230438232, cross_entropy: 3.6912143230438232 +[2025-04-29 09:36:31,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 2.143101215362549, cross_entropy: 2.143101215362549 +[2025-04-29 09:36:32,755][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.663212776184082, cross_entropy: 2.663212776184082 +[2025-04-29 09:36:35,248][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 2.4597229957580566, cross_entropy: 2.4597229957580566 +[2025-04-29 09:36:36,105][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.3081917762756348, cross_entropy: 3.3081917762756348 +[2025-04-29 09:36:38,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 2.925370931625366, cross_entropy: 2.925370931625366 +[2025-04-29 09:36:39,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 2.491572856903076, cross_entropy: 2.491572856903076 +[2025-04-29 09:36:42,197][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 1.9716429710388184, cross_entropy: 1.9716429710388184 +[2025-04-29 09:36:43,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 3.1962337493896484, cross_entropy: 3.1962337493896484 +[2025-04-29 09:36:45,692][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 2.1411032676696777, cross_entropy: 2.1411032676696777 +[2025-04-29 09:36:46,520][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.2834346294403076, cross_entropy: 2.2834346294403076 +[2025-04-29 09:36:50,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.0683753490448, cross_entropy: 3.0683753490448 +[2025-04-29 09:36:51,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.094564437866211, cross_entropy: 3.094564437866211 +[2025-04-29 09:36:54,159][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.104613780975342, cross_entropy: 3.104613780975342 +[2025-04-29 09:36:55,018][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 2.291846513748169, cross_entropy: 2.291846513748169 +[2025-04-29 09:36:58,587][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.001800775527954, cross_entropy: 2.001800775527954 +[2025-04-29 09:36:59,450][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.676588535308838, cross_entropy: 2.676588535308838 +[2025-04-29 09:37:01,785][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.262136697769165, cross_entropy: 3.262136697769165 +[2025-04-29 09:37:02,647][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.2176711559295654, cross_entropy: 3.2176711559295654 +[2025-04-29 09:37:04,926][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 3.208756685256958, cross_entropy: 3.208756685256958 +[2025-04-29 09:37:05,779][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 2.155740261077881, cross_entropy: 2.155740261077881 +[2025-04-29 09:37:08,341][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 1.844308614730835, cross_entropy: 1.844308614730835 +[2025-04-29 09:37:09,199][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.2910499572753906, cross_entropy: 3.2910499572753906 +[2025-04-29 09:37:12,405][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.6981327533721924, cross_entropy: 2.6981327533721924 +[2025-04-29 09:37:13,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.6871042251586914, cross_entropy: 3.6871042251586914 +[2025-04-29 09:37:17,796][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 1.852770447731018, cross_entropy: 1.852770447731018 +[2025-04-29 09:37:18,654][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 1.8882876634597778, cross_entropy: 1.8882876634597778 +[2025-04-29 09:37:22,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 2.359869956970215, cross_entropy: 2.359869956970215 +[2025-04-29 09:37:23,004][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.368009567260742, cross_entropy: 3.368009567260742 +[2025-04-29 09:37:25,385][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.711285352706909, cross_entropy: 2.711285352706909 +[2025-04-29 09:37:26,248][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.2737226486206055, cross_entropy: 3.2737226486206055 +[2025-04-29 09:37:29,357][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 2.880887508392334, cross_entropy: 2.880887508392334 +[2025-04-29 09:37:30,222][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 2.027369499206543, cross_entropy: 2.027369499206543 +[2025-04-29 09:37:33,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.376634359359741, cross_entropy: 3.376634359359741 +[2025-04-29 09:37:33,980][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.198831081390381, cross_entropy: 2.198831081390381 +[2025-04-29 09:37:37,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 1.756090521812439, cross_entropy: 1.756090521812439 +[2025-04-29 09:37:38,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 2.1817708015441895, cross_entropy: 2.1817708015441895 +[2025-04-29 09:37:41,937][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 2.3350682258605957, cross_entropy: 2.3350682258605957 +[2025-04-29 09:37:42,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.6389546394348145, cross_entropy: 2.6389546394348145 +[2025-04-29 09:37:47,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 2.0221619606018066, cross_entropy: 2.0221619606018066 +[2025-04-29 09:37:48,193][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 2.4864327907562256, cross_entropy: 2.4864327907562256 +[2025-04-29 09:37:50,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 2.4572641849517822, cross_entropy: 2.4572641849517822 +[2025-04-29 09:37:51,701][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.4876914024353027, cross_entropy: 2.4876914024353027 +[2025-04-29 09:37:54,726][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.6035828590393066, cross_entropy: 2.6035828590393066 +[2025-04-29 09:37:55,583][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 3.173312187194824, cross_entropy: 3.173312187194824 +[2025-04-29 09:37:58,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.705939292907715, cross_entropy: 2.705939292907715 +[2025-04-29 09:37:59,073][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.276951313018799, cross_entropy: 2.276951313018799 +[2025-04-29 09:38:01,854][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 3.403839111328125, cross_entropy: 3.403839111328125 +[2025-04-29 09:38:02,713][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.6720049381256104, cross_entropy: 3.6720049381256104 +[2025-04-29 09:38:07,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.151196241378784, cross_entropy: 2.151196241378784 +[2025-04-29 09:38:07,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 2.21358585357666, cross_entropy: 2.21358585357666 +[2025-04-29 09:38:09,701][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 1.8866393566131592, cross_entropy: 1.8866393566131592 +[2025-04-29 09:38:10,529][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 3.5215983390808105, cross_entropy: 3.5215983390808105 +[2025-04-29 09:38:13,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.5767710208892822, cross_entropy: 3.5767710208892822 +[2025-04-29 09:38:14,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.4727063179016113, cross_entropy: 2.4727063179016113 +[2025-04-29 09:38:16,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.1402034759521484, cross_entropy: 3.1402034759521484 +[2025-04-29 09:38:17,611][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 3.376063823699951, cross_entropy: 3.376063823699951 +[2025-04-29 09:38:20,706][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.16576886177063, cross_entropy: 2.16576886177063 +[2025-04-29 09:38:21,569][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 2.8303794860839844, cross_entropy: 2.8303794860839844 +[2025-04-29 09:38:24,485][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.5801000595092773, cross_entropy: 2.5801000595092773 +[2025-04-29 09:38:25,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 3.722942352294922, cross_entropy: 3.722942352294922 +[2025-04-29 09:38:28,749][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.654337167739868, cross_entropy: 2.654337167739868 +[2025-04-29 09:38:29,607][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.5540618896484375, cross_entropy: 3.5540618896484375 +[2025-04-29 09:38:32,336][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.1794381141662598, cross_entropy: 2.1794381141662598 +[2025-04-29 09:38:33,161][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 1.7177600860595703, cross_entropy: 1.7177600860595703 +[2025-04-29 09:38:36,368][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 2.10345458984375, cross_entropy: 2.10345458984375 +[2025-04-29 09:38:37,226][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 3.714573383331299, cross_entropy: 3.714573383331299 +[2025-04-29 09:38:40,351][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 2.9906835556030273, cross_entropy: 2.9906835556030273 +[2025-04-29 09:38:41,204][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.2099127769470215, cross_entropy: 2.2099127769470215 +[2025-04-29 09:38:44,043][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 2.997166156768799, cross_entropy: 2.997166156768799 +[2025-04-29 09:38:44,906][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.1517326831817627, cross_entropy: 3.1517326831817627 +[2025-04-29 09:38:47,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 2.153970718383789, cross_entropy: 2.153970718383789 +[2025-04-29 09:38:48,176][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 1.7527413368225098, cross_entropy: 1.7527413368225098 +[2025-04-29 09:38:51,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 1.5675641298294067, cross_entropy: 1.5675641298294067 +[2025-04-29 09:38:51,867][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.0574350357055664, cross_entropy: 3.0574350357055664 +[2025-04-29 09:38:55,096][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.6501498222351074, cross_entropy: 2.6501498222351074 +[2025-04-29 09:38:55,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 2.1032180786132812, cross_entropy: 2.1032180786132812 +[2025-04-29 09:38:58,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 2.706425666809082, cross_entropy: 2.706425666809082 +[2025-04-29 09:38:59,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.10548734664917, cross_entropy: 2.10548734664917 +[2025-04-29 09:39:02,369][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 3.274691581726074, cross_entropy: 3.274691581726074 +[2025-04-29 09:39:03,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.1422924995422363, cross_entropy: 2.1422924995422363 +[2025-04-29 09:39:06,297][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 3.4748711585998535, cross_entropy: 3.4748711585998535 +[2025-04-29 09:39:07,155][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.609970808029175, cross_entropy: 2.609970808029175 +[2025-04-29 09:39:10,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 2.465850591659546, cross_entropy: 2.465850591659546 +[2025-04-29 09:39:11,420][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.1953420639038086, cross_entropy: 2.1953420639038086 +[2025-04-29 09:39:15,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.415029525756836, cross_entropy: 2.415029525756836 +[2025-04-29 09:39:16,308][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.530648708343506, cross_entropy: 2.530648708343506 +[2025-04-29 09:39:18,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.1016907691955566, cross_entropy: 2.1016907691955566 +[2025-04-29 09:39:19,171][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 3.0736281871795654, cross_entropy: 3.0736281871795654 +[2025-04-29 09:39:22,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 1.9333293437957764, cross_entropy: 1.9333293437957764 +[2025-04-29 09:39:22,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 3.386674404144287, cross_entropy: 3.386674404144287 +[2025-04-29 09:39:26,507][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 3.1477792263031006, cross_entropy: 3.1477792263031006 +[2025-04-29 09:39:27,367][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.2782013416290283, cross_entropy: 3.2782013416290283 +[2025-04-29 09:39:29,816][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 1.8252198696136475, cross_entropy: 1.8252198696136475 +[2025-04-29 09:39:30,644][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 1.9320544004440308, cross_entropy: 1.9320544004440308 +[2025-04-29 09:39:33,360][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 2.4684154987335205, cross_entropy: 2.4684154987335205 +[2025-04-29 09:39:34,182][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.0016491413116455, cross_entropy: 2.0016491413116455 +[2025-04-29 09:39:36,992][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.2244598865509033, cross_entropy: 2.2244598865509033 +[2025-04-29 09:39:37,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 2.6755056381225586, cross_entropy: 2.6755056381225586 +[2025-04-29 09:39:40,695][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 1.8453537225723267, cross_entropy: 1.8453537225723267 +[2025-04-29 09:39:41,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 2.1532928943634033, cross_entropy: 2.1532928943634033 +[2025-04-29 09:39:45,147][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 2.7888898849487305, cross_entropy: 2.7888898849487305 +[2025-04-29 09:39:46,015][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.0085325241088867, cross_entropy: 2.0085325241088867 +[2025-04-29 09:39:49,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.492682933807373, cross_entropy: 3.492682933807373 +[2025-04-29 09:39:49,993][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 1.866685390472412, cross_entropy: 1.866685390472412 +[2025-04-29 09:39:52,722][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.5228097438812256, cross_entropy: 2.5228097438812256 +[2025-04-29 09:39:53,585][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 1.671837329864502, cross_entropy: 1.671837329864502 +[2025-04-29 09:39:55,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.2616772651672363, cross_entropy: 2.2616772651672363 +[2025-04-29 09:39:56,789][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.3708345890045166, cross_entropy: 2.3708345890045166 +[2025-04-29 09:40:00,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.4858479499816895, cross_entropy: 3.4858479499816895 +[2025-04-29 09:40:01,254][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 2.2527475357055664, cross_entropy: 2.2527475357055664 +[2025-04-29 09:40:03,868][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.656114101409912, cross_entropy: 3.656114101409912 +[2025-04-29 09:40:04,724][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 3.432413101196289, cross_entropy: 3.432413101196289 +[2025-04-29 09:40:07,021][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 2.32087779045105, cross_entropy: 2.32087779045105 +[2025-04-29 09:40:07,879][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 3.6196205615997314, cross_entropy: 3.6196205615997314 +[2025-04-29 09:40:10,803][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.243755340576172, cross_entropy: 3.243755340576172 +[2025-04-29 09:40:11,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.058370590209961, cross_entropy: 2.058370590209961 +[2025-04-29 09:40:14,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.022911548614502, cross_entropy: 2.022911548614502 +[2025-04-29 09:40:15,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 2.033574104309082, cross_entropy: 2.033574104309082 +[2025-04-29 09:40:18,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.6891918182373047, cross_entropy: 2.6891918182373047 +[2025-04-29 09:40:19,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 1.7931861877441406, cross_entropy: 1.7931861877441406 +[2025-04-29 09:40:23,623][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 2.3475446701049805, cross_entropy: 2.3475446701049805 +[2025-04-29 09:40:24,467][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 2.8164868354797363, cross_entropy: 2.8164868354797363 +[2025-04-29 09:40:27,278][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 2.142258405685425, cross_entropy: 2.142258405685425 +[2025-04-29 09:40:28,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 3.531562089920044, cross_entropy: 3.531562089920044 +[2025-04-29 09:40:31,220][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.950066566467285, cross_entropy: 2.950066566467285 +[2025-04-29 09:40:32,085][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.0428287982940674, cross_entropy: 2.0428287982940674 +[2025-04-29 09:40:34,836][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 1.7850674390792847, cross_entropy: 1.7850674390792847 +[2025-04-29 09:40:35,665][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 3.1403112411499023, cross_entropy: 3.1403112411499023 +[2025-04-29 09:40:38,447][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 3.4309732913970947, cross_entropy: 3.4309732913970947 +[2025-04-29 09:40:39,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 3.3917183876037598, cross_entropy: 3.3917183876037598 +[2025-04-29 09:40:41,980][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 1.949648141860962, cross_entropy: 1.949648141860962 +[2025-04-29 09:40:42,839][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.660940647125244, cross_entropy: 2.660940647125244 +[2025-04-29 09:40:45,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.102531909942627, cross_entropy: 3.102531909942627 +[2025-04-29 09:40:46,354][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.1584439277648926, cross_entropy: 2.1584439277648926 +[2025-04-29 09:40:49,342][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.266537666320801, cross_entropy: 2.266537666320801 +[2025-04-29 09:40:50,202][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.499387741088867, cross_entropy: 2.499387741088867 +[2025-04-29 09:40:52,899][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.0605156421661377, cross_entropy: 2.0605156421661377 +[2025-04-29 09:40:53,760][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 1.9028630256652832, cross_entropy: 1.9028630256652832 +[2025-04-29 09:40:55,805][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 1.9706497192382812, cross_entropy: 1.9706497192382812 +[2025-04-29 09:40:56,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.484837055206299, cross_entropy: 3.484837055206299 +[2025-04-29 09:40:59,646][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 2.518617630004883, cross_entropy: 2.518617630004883 +[2025-04-29 09:41:00,553][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 3.428835391998291, cross_entropy: 3.428835391998291 +[2025-04-29 09:41:03,712][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 2.175954580307007, cross_entropy: 2.175954580307007 +[2025-04-29 09:41:04,558][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.0973262786865234, cross_entropy: 2.0973262786865234 +[2025-04-29 09:41:07,447][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 1.8950111865997314, cross_entropy: 1.8950111865997314 +[2025-04-29 09:41:08,270][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.825254201889038, cross_entropy: 1.825254201889038 +[2025-04-29 09:41:10,576][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.8275861740112305, cross_entropy: 2.8275861740112305 +[2025-04-29 09:41:11,436][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.1741507053375244, cross_entropy: 2.1741507053375244 +[2025-04-29 09:41:14,679][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 1.7248671054840088, cross_entropy: 1.7248671054840088 +[2025-04-29 09:41:15,502][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 2.196268081665039, cross_entropy: 2.196268081665039 +[2025-04-29 09:41:19,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 1.8984743356704712, cross_entropy: 1.8984743356704712 +[2025-04-29 09:41:20,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 1.8742406368255615, cross_entropy: 1.8742406368255615 +[2025-04-29 09:41:23,306][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 2.201068639755249, cross_entropy: 2.201068639755249 +[2025-04-29 09:41:24,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 3.130906581878662, cross_entropy: 3.130906581878662 +[2025-04-29 09:41:26,804][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.2316675186157227, cross_entropy: 3.2316675186157227 +[2025-04-29 09:41:27,662][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.5881314277648926, cross_entropy: 2.5881314277648926 +[2025-04-29 09:41:30,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 2.4962453842163086, cross_entropy: 2.4962453842163086 +[2025-04-29 09:41:30,967][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 3.183936595916748, cross_entropy: 3.183936595916748 +[2025-04-29 09:41:33,674][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 1.8950257301330566, cross_entropy: 1.8950257301330566 +[2025-04-29 09:41:34,542][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 1.980522871017456, cross_entropy: 1.980522871017456 +[2025-04-29 09:41:36,783][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.268764019012451, cross_entropy: 2.268764019012451 +[2025-04-29 09:41:37,645][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 1.9803752899169922, cross_entropy: 1.9803752899169922 +[2025-04-29 09:41:40,351][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.3638641834259033, cross_entropy: 3.3638641834259033 +[2025-04-29 09:41:41,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.5524845123291016, cross_entropy: 3.5524845123291016 +[2025-04-29 09:41:43,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.0021424293518066, cross_entropy: 3.0021424293518066 +[2025-04-29 09:41:44,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.4633734226226807, cross_entropy: 3.4633734226226807 +[2025-04-29 09:41:47,515][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 3.3226990699768066, cross_entropy: 3.3226990699768066 +[2025-04-29 09:41:48,378][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 1.997121810913086, cross_entropy: 1.997121810913086 +[2025-04-29 09:41:51,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 2.308042287826538, cross_entropy: 2.308042287826538 +[2025-04-29 09:41:52,455][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 1.9038081169128418, cross_entropy: 1.9038081169128418 +[2025-04-29 09:41:55,431][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.140753984451294, cross_entropy: 2.140753984451294 +[2025-04-29 09:41:56,290][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.864593029022217, cross_entropy: 2.864593029022217 +[2025-04-29 09:41:59,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.1407227516174316, cross_entropy: 2.1407227516174316 +[2025-04-29 09:42:00,308][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 1.8694289922714233, cross_entropy: 1.8694289922714233 +[2025-04-29 09:42:03,967][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.1781492233276367, cross_entropy: 2.1781492233276367 +[2025-04-29 09:42:04,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 1.755993127822876, cross_entropy: 1.755993127822876 +[2025-04-29 09:42:07,646][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.192568778991699, cross_entropy: 2.192568778991699 +[2025-04-29 09:42:08,491][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.649479389190674, cross_entropy: 2.649479389190674 +[2025-04-29 09:42:11,289][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 3.6211612224578857, cross_entropy: 3.6211612224578857 +[2025-04-29 09:42:12,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 1.9362961053848267, cross_entropy: 1.9362961053848267 +[2025-04-29 09:42:14,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 1.6380548477172852, cross_entropy: 1.6380548477172852 +[2025-04-29 09:42:15,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 2.9985053539276123, cross_entropy: 2.9985053539276123 +[2025-04-29 09:42:18,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 1.590371012687683, cross_entropy: 1.590371012687683 +[2025-04-29 09:42:19,051][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 2.2420992851257324, cross_entropy: 2.2420992851257324 +[2025-04-29 09:42:21,173][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 2.971658706665039, cross_entropy: 2.971658706665039 +[2025-04-29 09:42:22,001][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 1.812256097793579, cross_entropy: 1.812256097793579 +[2025-04-29 09:42:24,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 1.9539762735366821, cross_entropy: 1.9539762735366821 +[2025-04-29 09:42:25,816][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 3.447894811630249, cross_entropy: 3.447894811630249 +[2025-04-29 09:42:28,637][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 1.7005747556686401, cross_entropy: 1.7005747556686401 +[2025-04-29 09:42:29,461][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 2.377121925354004, cross_entropy: 2.377121925354004 +[2025-04-29 09:42:32,728][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 1.7260675430297852, cross_entropy: 1.7260675430297852 +[2025-04-29 09:42:33,549][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 1.7357616424560547, cross_entropy: 1.7357616424560547 +[2025-04-29 09:42:36,186][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.4979560375213623, cross_entropy: 3.4979560375213623 +[2025-04-29 09:42:37,042][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 3.0718464851379395, cross_entropy: 3.0718464851379395 +[2025-04-29 09:42:39,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 2.526988983154297, cross_entropy: 2.526988983154297 +[2025-04-29 09:42:40,355][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 2.090567111968994, cross_entropy: 2.090567111968994 +[2025-04-29 09:42:43,058][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.98826265335083, cross_entropy: 2.98826265335083 +[2025-04-29 09:42:43,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 3.3093080520629883, cross_entropy: 3.3093080520629883 +[2025-04-29 09:42:46,320][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.0802173614501953, cross_entropy: 3.0802173614501953 +[2025-04-29 09:42:47,169][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 1.9083819389343262, cross_entropy: 1.9083819389343262 +[2025-04-29 09:42:49,265][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 2.877997875213623, cross_entropy: 2.877997875213623 +[2025-04-29 09:42:50,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.1382012367248535, cross_entropy: 3.1382012367248535 +[2025-04-29 09:42:53,350][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 3.3071823120117188, cross_entropy: 3.3071823120117188 +[2025-04-29 09:42:54,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.7056868076324463, cross_entropy: 2.7056868076324463 +[2025-04-29 09:42:56,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.2316431999206543, cross_entropy: 3.2316431999206543 +[2025-04-29 09:42:57,114][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 3.318655014038086, cross_entropy: 3.318655014038086 +[2025-04-29 09:43:00,219][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 3.534905433654785, cross_entropy: 3.534905433654785 +[2025-04-29 09:43:01,084][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.469343662261963, cross_entropy: 2.469343662261963 +[2025-04-29 09:43:03,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 2.544008493423462, cross_entropy: 2.544008493423462 +[2025-04-29 09:43:04,164][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.639305830001831, cross_entropy: 1.639305830001831 +[2025-04-29 09:43:07,408][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 2.986520290374756, cross_entropy: 2.986520290374756 +[2025-04-29 09:43:08,240][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 2.962325096130371, cross_entropy: 2.962325096130371 +[2025-04-29 09:43:11,285][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 1.7073845863342285, cross_entropy: 1.7073845863342285 +[2025-04-29 09:43:12,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 1.9013867378234863, cross_entropy: 1.9013867378234863 +[2025-04-29 09:43:15,545][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.4922707080841064, cross_entropy: 2.4922707080841064 +[2025-04-29 09:43:16,405][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 3.3163390159606934, cross_entropy: 3.3163390159606934 +[2025-04-29 09:43:18,925][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 1.6536318063735962, cross_entropy: 1.6536318063735962 +[2025-04-29 09:43:19,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 1.7567923069000244, cross_entropy: 1.7567923069000244 +[2025-04-29 09:43:23,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 2.338198184967041, cross_entropy: 2.338198184967041 +[2025-04-29 09:43:24,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 3.733517646789551, cross_entropy: 3.733517646789551 +[2025-04-29 09:43:26,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 3.4588353633880615, cross_entropy: 3.4588353633880615 +[2025-04-29 09:43:27,526][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.6196835041046143, cross_entropy: 1.6196835041046143 +[2025-04-29 09:43:31,124][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 1.8291079998016357, cross_entropy: 1.8291079998016357 +[2025-04-29 09:43:31,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 1.6485676765441895, cross_entropy: 1.6485676765441895 +[2025-04-29 09:43:35,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.1919894218444824, cross_entropy: 3.1919894218444824 +[2025-04-29 09:43:35,867][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 1.4299325942993164, cross_entropy: 1.4299325942993164 +[2025-04-29 09:43:38,295][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 1.8084802627563477, cross_entropy: 1.8084802627563477 +[2025-04-29 09:43:39,160][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 1.7730944156646729, cross_entropy: 1.7730944156646729 +[2025-04-29 09:43:42,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 2.8349251747131348, cross_entropy: 2.8349251747131348 +[2025-04-29 09:43:43,026][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.5676379203796387, cross_entropy: 2.5676379203796387 +[2025-04-29 09:43:45,976][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 1.764833927154541, cross_entropy: 1.764833927154541 +[2025-04-29 09:43:46,811][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 2.6366491317749023, cross_entropy: 2.6366491317749023 +[2025-04-29 09:43:49,838][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.0925588607788086, cross_entropy: 2.0925588607788086 +[2025-04-29 09:43:50,694][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 3.242760181427002, cross_entropy: 3.242760181427002 +[2025-04-29 09:43:53,110][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 1.5157151222229004, cross_entropy: 1.5157151222229004 +[2025-04-29 09:43:53,969][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 1.9027949571609497, cross_entropy: 1.9027949571609497 +[2025-04-29 09:43:56,687][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 1.6236851215362549, cross_entropy: 1.6236851215362549 +[2025-04-29 09:43:57,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 2.4042458534240723, cross_entropy: 2.4042458534240723 +[2025-04-29 09:43:59,360][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 1.8144545555114746, cross_entropy: 1.8144545555114746 +[2025-04-29 09:44:00,210][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.322805643081665, cross_entropy: 3.322805643081665 +[2025-04-29 09:44:03,217][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.4299787282943726, cross_entropy: 1.4299787282943726 +[2025-04-29 09:44:04,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.3460006713867188, cross_entropy: 2.3460006713867188 +[2025-04-29 09:44:06,143][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.1472694873809814, cross_entropy: 3.1472694873809814 +[2025-04-29 09:44:06,985][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.478459358215332, cross_entropy: 3.478459358215332 +[2025-04-29 09:44:09,109][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 1.3974584341049194, cross_entropy: 1.3974584341049194 +[2025-04-29 09:44:09,938][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 3.1490471363067627, cross_entropy: 3.1490471363067627 +[2025-04-29 09:44:12,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 1.680917739868164, cross_entropy: 1.680917739868164 +[2025-04-29 09:44:13,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 1.926234245300293, cross_entropy: 1.926234245300293 +[2025-04-29 09:44:15,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.3584322929382324, cross_entropy: 3.3584322929382324 +[2025-04-29 09:44:16,458][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 1.809207558631897, cross_entropy: 1.809207558631897 +[2025-04-29 09:44:18,850][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 2.2367982864379883, cross_entropy: 2.2367982864379883 +[2025-04-29 09:44:19,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.6456971168518066, cross_entropy: 2.6456971168518066 +[2025-04-29 09:44:22,778][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.1740634441375732, cross_entropy: 3.1740634441375732 +[2025-04-29 09:44:23,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 1.9832334518432617, cross_entropy: 1.9832334518432617 +[2025-04-29 09:44:25,843][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 1.7031469345092773, cross_entropy: 1.7031469345092773 +[2025-04-29 09:44:26,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 1.7352356910705566, cross_entropy: 1.7352356910705566 +[2025-04-29 09:44:29,283][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 2.621595859527588, cross_entropy: 2.621595859527588 +[2025-04-29 09:44:30,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.01387882232666, cross_entropy: 3.01387882232666 +[2025-04-29 09:44:32,969][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.126833915710449, cross_entropy: 3.126833915710449 +[2025-04-29 09:44:33,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 2.935364246368408, cross_entropy: 2.935364246368408 +[2025-04-29 09:44:38,333][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.721787452697754, cross_entropy: 2.721787452697754 +[2025-04-29 09:44:39,154][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.108607769012451, cross_entropy: 2.108607769012451 +[2025-04-29 09:44:41,970][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.636101722717285, cross_entropy: 2.636101722717285 +[2025-04-29 09:44:42,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 1.3691096305847168, cross_entropy: 1.3691096305847168 +[2025-04-29 09:44:45,456][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.7686355113983154, cross_entropy: 1.7686355113983154 +[2025-04-29 09:44:46,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 2.209019422531128, cross_entropy: 2.209019422531128 +[2025-04-29 09:44:48,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 1.578583002090454, cross_entropy: 1.578583002090454 +[2025-04-29 09:44:49,293][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 1.4469002485275269, cross_entropy: 1.4469002485275269 +[2025-04-29 09:47:32,213][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.5790855884552, cross_entropy: 2.5790855884552 +[2025-04-29 09:47:32,214][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.5599831342697144, cross_entropy: 1.5599831342697144 +[2025-04-29 09:47:33,191][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 09:47:33,751][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch2.pth. +[2025-04-29 09:47:34,669][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 09:47:40,329][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 2.16884708404541, cross_entropy: 2.16884708404541 +[2025-04-29 09:47:41,193][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.9998975992202759, cross_entropy: 1.9998975992202759 +[2025-04-29 09:47:44,219][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 3.153946876525879, cross_entropy: 3.153946876525879 +[2025-04-29 09:47:45,077][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 1.528085708618164, cross_entropy: 1.528085708618164 +[2025-04-29 09:47:47,247][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.3555402755737305, cross_entropy: 1.3555402755737305 +[2025-04-29 09:47:48,128][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 3.135606050491333, cross_entropy: 3.135606050491333 +[2025-04-29 09:47:51,082][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.9675326347351074, cross_entropy: 1.9675326347351074 +[2025-04-29 09:47:52,572][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 1.938217282295227, cross_entropy: 1.938217282295227 +[2025-04-29 09:47:55,450][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.556010365486145, cross_entropy: 1.556010365486145 +[2025-04-29 09:47:56,454][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 3.061180591583252, cross_entropy: 3.061180591583252 +[2025-04-29 09:47:59,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 1.9339238405227661, cross_entropy: 1.9339238405227661 +[2025-04-29 09:48:00,547][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 2.970052719116211, cross_entropy: 2.970052719116211 +[2025-04-29 09:48:03,037][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.2221577167510986, cross_entropy: 1.2221577167510986 +[2025-04-29 09:48:03,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 1.6643551588058472, cross_entropy: 1.6643551588058472 +[2025-04-29 09:48:07,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.8780698776245117, cross_entropy: 2.8780698776245117 +[2025-04-29 09:48:07,920][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 1.4141392707824707, cross_entropy: 1.4141392707824707 +[2025-04-29 09:48:11,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.181016445159912, cross_entropy: 3.181016445159912 +[2025-04-29 09:48:12,060][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.441619873046875, cross_entropy: 2.441619873046875 +[2025-04-29 09:48:14,984][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.6056482791900635, cross_entropy: 1.6056482791900635 +[2025-04-29 09:48:15,845][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.8391883373260498, cross_entropy: 1.8391883373260498 +[2025-04-29 09:48:19,306][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 2.980112314224243, cross_entropy: 2.980112314224243 +[2025-04-29 09:48:20,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.7910094261169434, cross_entropy: 1.7910094261169434 +[2025-04-29 09:48:22,761][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 2.024754524230957, cross_entropy: 2.024754524230957 +[2025-04-29 09:48:23,619][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 1.1149396896362305, cross_entropy: 1.1149396896362305 +[2025-04-29 09:48:26,652][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 2.865001678466797, cross_entropy: 2.865001678466797 +[2025-04-29 09:48:27,516][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 1.4327600002288818, cross_entropy: 1.4327600002288818 +[2025-04-29 09:48:29,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 2.9273247718811035, cross_entropy: 2.9273247718811035 +[2025-04-29 09:48:30,228][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.3501288890838623, cross_entropy: 2.3501288890838623 +[2025-04-29 09:48:33,139][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 1.5270144939422607, cross_entropy: 1.5270144939422607 +[2025-04-29 09:48:33,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.3654088973999023, cross_entropy: 2.3654088973999023 +[2025-04-29 09:48:36,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.0550320148468018, cross_entropy: 1.0550320148468018 +[2025-04-29 09:48:37,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 1.5115362405776978, cross_entropy: 1.5115362405776978 +[2025-04-29 09:48:39,893][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.1678545475006104, cross_entropy: 3.1678545475006104 +[2025-04-29 09:48:40,749][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 2.6740498542785645, cross_entropy: 2.6740498542785645 +[2025-04-29 09:48:43,124][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 1.7112188339233398, cross_entropy: 1.7112188339233398 +[2025-04-29 09:48:43,978][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 2.914243221282959, cross_entropy: 2.914243221282959 +[2025-04-29 09:48:46,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.193725347518921, cross_entropy: 2.193725347518921 +[2025-04-29 09:48:47,234][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.6264753341674805, cross_entropy: 1.6264753341674805 +[2025-04-29 09:48:49,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 2.837364673614502, cross_entropy: 2.837364673614502 +[2025-04-29 09:48:50,867][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 2.0943691730499268, cross_entropy: 2.0943691730499268 +[2025-04-29 09:48:54,763][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.1775367259979248, cross_entropy: 1.1775367259979248 +[2025-04-29 09:48:55,587][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 1.11100435256958, cross_entropy: 1.11100435256958 +[2025-04-29 09:48:58,127][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 2.298774242401123, cross_entropy: 2.298774242401123 +[2025-04-29 09:48:58,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.1720962524414062, cross_entropy: 2.1720962524414062 +[2025-04-29 09:49:01,558][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 3.350106716156006, cross_entropy: 3.350106716156006 +[2025-04-29 09:49:02,415][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 2.6306562423706055, cross_entropy: 2.6306562423706055 +[2025-04-29 09:49:04,518][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.5509490966796875, cross_entropy: 1.5509490966796875 +[2025-04-29 09:49:05,342][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.5553717613220215, cross_entropy: 2.5553717613220215 +[2025-04-29 09:49:07,998][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.8652586936950684, cross_entropy: 2.8652586936950684 +[2025-04-29 09:49:08,817][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 3.1378695964813232, cross_entropy: 3.1378695964813232 +[2025-04-29 09:49:11,223][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 3.125357151031494, cross_entropy: 3.125357151031494 +[2025-04-29 09:49:12,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 1.7705882787704468, cross_entropy: 1.7705882787704468 +[2025-04-29 09:49:14,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 1.8417205810546875, cross_entropy: 1.8417205810546875 +[2025-04-29 09:49:15,237][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.068117141723633, cross_entropy: 3.068117141723633 +[2025-04-29 09:49:17,826][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 1.5606000423431396, cross_entropy: 1.5606000423431396 +[2025-04-29 09:49:18,727][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 1.7034833431243896, cross_entropy: 1.7034833431243896 +[2025-04-29 09:49:21,067][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.0364298820495605, cross_entropy: 3.0364298820495605 +[2025-04-29 09:49:21,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 1.9311573505401611, cross_entropy: 1.9311573505401611 +[2025-04-29 09:49:23,959][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 1.4124022722244263, cross_entropy: 1.4124022722244263 +[2025-04-29 09:49:25,068][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 1.7804603576660156, cross_entropy: 1.7804603576660156 +[2025-04-29 09:49:27,293][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.8045289516448975, cross_entropy: 2.8045289516448975 +[2025-04-29 09:49:28,625][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 1.1925116777420044, cross_entropy: 1.1925116777420044 +[2025-04-29 09:49:30,974][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 1.4266393184661865, cross_entropy: 1.4266393184661865 +[2025-04-29 09:49:31,845][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 2.9647321701049805, cross_entropy: 2.9647321701049805 +[2025-04-29 09:49:34,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 2.9941015243530273, cross_entropy: 2.9941015243530273 +[2025-04-29 09:49:35,205][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.329397201538086, cross_entropy: 2.329397201538086 +[2025-04-29 09:49:37,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.822613000869751, cross_entropy: 1.822613000869751 +[2025-04-29 09:49:38,742][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.205565929412842, cross_entropy: 3.205565929412842 +[2025-04-29 09:49:41,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.960604667663574, cross_entropy: 2.960604667663574 +[2025-04-29 09:49:42,165][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 1.4840489625930786, cross_entropy: 1.4840489625930786 +[2025-04-29 09:49:44,005][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 1.3787803649902344, cross_entropy: 1.3787803649902344 +[2025-04-29 09:49:44,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 1.786292314529419, cross_entropy: 1.786292314529419 +[2025-04-29 09:49:47,595][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 1.8323707580566406, cross_entropy: 1.8323707580566406 +[2025-04-29 09:49:48,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.8802709579467773, cross_entropy: 2.8802709579467773 +[2025-04-29 09:49:51,683][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 2.9540934562683105, cross_entropy: 2.9540934562683105 +[2025-04-29 09:49:52,535][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 3.4850902557373047, cross_entropy: 3.4850902557373047 +[2025-04-29 09:49:55,211][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 1.6962085962295532, cross_entropy: 1.6962085962295532 +[2025-04-29 09:49:56,063][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 3.120943546295166, cross_entropy: 3.120943546295166 +[2025-04-29 09:49:58,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.058422327041626, cross_entropy: 3.058422327041626 +[2025-04-29 09:49:58,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 2.054069995880127, cross_entropy: 2.054069995880127 +[2025-04-29 09:50:01,897][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 1.431437373161316, cross_entropy: 1.431437373161316 +[2025-04-29 09:50:02,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.4607412815093994, cross_entropy: 1.4607412815093994 +[2025-04-29 09:50:05,036][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 2.4295639991760254, cross_entropy: 2.4295639991760254 +[2025-04-29 09:50:05,891][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 2.701362133026123, cross_entropy: 2.701362133026123 +[2025-04-29 09:50:08,026][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 1.5979440212249756, cross_entropy: 1.5979440212249756 +[2025-04-29 09:50:08,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.023237705230713, cross_entropy: 2.023237705230713 +[2025-04-29 09:50:11,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 1.2716995477676392, cross_entropy: 1.2716995477676392 +[2025-04-29 09:50:11,924][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 1.4660760164260864, cross_entropy: 1.4660760164260864 +[2025-04-29 09:50:14,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 1.549924373626709, cross_entropy: 1.549924373626709 +[2025-04-29 09:50:14,942][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 2.758833885192871, cross_entropy: 2.758833885192871 +[2025-04-29 09:50:17,442][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 1.618849277496338, cross_entropy: 1.618849277496338 +[2025-04-29 09:50:18,277][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.6910159587860107, cross_entropy: 1.6910159587860107 +[2025-04-29 09:50:20,985][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.6392983198165894, cross_entropy: 1.6392983198165894 +[2025-04-29 09:50:21,834][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 3.1096386909484863, cross_entropy: 3.1096386909484863 +[2025-04-29 09:50:24,485][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.182446241378784, cross_entropy: 3.182446241378784 +[2025-04-29 09:50:25,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.868656873703003, cross_entropy: 1.868656873703003 +[2025-04-29 09:50:28,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 1.6927157640457153, cross_entropy: 1.6927157640457153 +[2025-04-29 09:50:29,041][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 1.6364301443099976, cross_entropy: 1.6364301443099976 +[2025-04-29 09:50:31,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 1.8676635026931763, cross_entropy: 1.8676635026931763 +[2025-04-29 09:50:32,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.13783860206604, cross_entropy: 2.13783860206604 +[2025-04-29 09:50:35,265][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.2703769207000732, cross_entropy: 2.2703769207000732 +[2025-04-29 09:50:36,081][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 1.5621240139007568, cross_entropy: 1.5621240139007568 +[2025-04-29 09:50:38,740][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 1.1853039264678955, cross_entropy: 1.1853039264678955 +[2025-04-29 09:50:39,582][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.948807716369629, cross_entropy: 1.948807716369629 +[2025-04-29 09:50:42,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 1.5780024528503418, cross_entropy: 1.5780024528503418 +[2025-04-29 09:50:43,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.5498690605163574, cross_entropy: 2.5498690605163574 +[2025-04-29 09:50:46,028][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.884523868560791, cross_entropy: 2.884523868560791 +[2025-04-29 09:50:46,873][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 2.036642074584961, cross_entropy: 2.036642074584961 +[2025-04-29 09:50:49,198][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 1.7589422464370728, cross_entropy: 1.7589422464370728 +[2025-04-29 09:50:50,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.560325860977173, cross_entropy: 2.560325860977173 +[2025-04-29 09:50:52,045][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 3.4819068908691406, cross_entropy: 3.4819068908691406 +[2025-04-29 09:50:52,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.8105864524841309, cross_entropy: 1.8105864524841309 +[2025-04-29 09:50:55,347][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 2.4896793365478516, cross_entropy: 2.4896793365478516 +[2025-04-29 09:50:56,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 1.0846655368804932, cross_entropy: 1.0846655368804932 +[2025-04-29 09:50:58,339][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 1.2287952899932861, cross_entropy: 1.2287952899932861 +[2025-04-29 09:50:59,391][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 3.292041063308716, cross_entropy: 3.292041063308716 +[2025-04-29 09:51:02,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 1.3447108268737793, cross_entropy: 1.3447108268737793 +[2025-04-29 09:51:03,946][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 3.2328739166259766, cross_entropy: 3.2328739166259766 +[2025-04-29 09:51:06,464][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 2.246807336807251, cross_entropy: 2.246807336807251 +[2025-04-29 09:51:08,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.518972873687744, cross_entropy: 2.518972873687744 +[2025-04-29 09:51:09,759][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 2.0314316749572754, cross_entropy: 2.0314316749572754 +[2025-04-29 09:51:10,647][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 3.533482074737549, cross_entropy: 3.533482074737549 +[2025-04-29 09:51:13,153][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 3.247323513031006, cross_entropy: 3.247323513031006 +[2025-04-29 09:51:13,970][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 3.0642051696777344, cross_entropy: 3.0642051696777344 +[2025-04-29 09:51:17,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 1.675219178199768, cross_entropy: 1.675219178199768 +[2025-04-29 09:51:17,831][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 1.6197946071624756, cross_entropy: 1.6197946071624756 +[2025-04-29 09:51:20,509][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 2.2639265060424805, cross_entropy: 2.2639265060424805 +[2025-04-29 09:51:21,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 1.916003704071045, cross_entropy: 1.916003704071045 +[2025-04-29 09:51:23,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 1.8681814670562744, cross_entropy: 1.8681814670562744 +[2025-04-29 09:51:24,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 1.5976506471633911, cross_entropy: 1.5976506471633911 +[2025-04-29 09:51:26,210][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.953688144683838, cross_entropy: 2.953688144683838 +[2025-04-29 09:51:27,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 2.089094400405884, cross_entropy: 2.089094400405884 +[2025-04-29 09:51:29,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 1.1856036186218262, cross_entropy: 1.1856036186218262 +[2025-04-29 09:51:30,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.933528423309326, cross_entropy: 2.933528423309326 +[2025-04-29 09:51:34,064][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 1.785577416419983, cross_entropy: 1.785577416419983 +[2025-04-29 09:51:34,910][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.7168879508972168, cross_entropy: 1.7168879508972168 +[2025-04-29 09:51:37,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.6487877368927, cross_entropy: 2.6487877368927 +[2025-04-29 09:51:38,490][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.2984135150909424, cross_entropy: 1.2984135150909424 +[2025-04-29 09:51:40,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.6747899055480957, cross_entropy: 2.6747899055480957 +[2025-04-29 09:51:41,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 3.1888320446014404, cross_entropy: 3.1888320446014404 +[2025-04-29 09:51:44,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.1891582012176514, cross_entropy: 2.1891582012176514 +[2025-04-29 09:51:45,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 3.0075361728668213, cross_entropy: 3.0075361728668213 +[2025-04-29 09:51:47,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 3.509188652038574, cross_entropy: 3.509188652038574 +[2025-04-29 09:51:48,487][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.369149684906006, cross_entropy: 2.369149684906006 +[2025-04-29 09:51:50,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.881044864654541, cross_entropy: 2.881044864654541 +[2025-04-29 09:51:51,466][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 1.9468820095062256, cross_entropy: 1.9468820095062256 +[2025-04-29 09:51:53,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.3193557262420654, cross_entropy: 1.3193557262420654 +[2025-04-29 09:51:54,521][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 2.2698864936828613, cross_entropy: 2.2698864936828613 +[2025-04-29 09:51:56,458][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 3.1265358924865723, cross_entropy: 3.1265358924865723 +[2025-04-29 09:51:57,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 2.074911117553711, cross_entropy: 2.074911117553711 +[2025-04-29 09:51:59,519][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.2990670204162598, cross_entropy: 1.2990670204162598 +[2025-04-29 09:52:00,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.0648393630981445, cross_entropy: 2.0648393630981445 +[2025-04-29 09:52:03,636][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.028806447982788, cross_entropy: 2.028806447982788 +[2025-04-29 09:52:04,483][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 2.1938416957855225, cross_entropy: 2.1938416957855225 +[2025-04-29 09:52:06,584][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.0872912406921387, cross_entropy: 2.0872912406921387 +[2025-04-29 09:52:07,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.7750589847564697, cross_entropy: 2.7750589847564697 +[2025-04-29 09:52:09,896][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.3538737297058105, cross_entropy: 1.3538737297058105 +[2025-04-29 09:52:10,750][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 2.374605417251587, cross_entropy: 2.374605417251587 +[2025-04-29 09:52:13,223][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 1.8943941593170166, cross_entropy: 1.8943941593170166 +[2025-04-29 09:52:14,066][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 3.34354305267334, cross_entropy: 3.34354305267334 +[2025-04-29 09:52:17,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 2.8417868614196777, cross_entropy: 2.8417868614196777 +[2025-04-29 09:52:18,085][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 2.102330207824707, cross_entropy: 2.102330207824707 +[2025-04-29 09:52:21,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.327261209487915, cross_entropy: 3.327261209487915 +[2025-04-29 09:52:22,229][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 2.8588647842407227, cross_entropy: 2.8588647842407227 +[2025-04-29 09:52:25,153][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 1.671574354171753, cross_entropy: 1.671574354171753 +[2025-04-29 09:52:25,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 3.061321258544922, cross_entropy: 3.061321258544922 +[2025-04-29 09:52:28,129][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 2.1128525733947754, cross_entropy: 2.1128525733947754 +[2025-04-29 09:52:28,982][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 1.6143896579742432, cross_entropy: 1.6143896579742432 +[2025-04-29 09:52:31,547][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 2.207350254058838, cross_entropy: 2.207350254058838 +[2025-04-29 09:52:32,402][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 1.5559712648391724, cross_entropy: 1.5559712648391724 +[2025-04-29 09:52:34,859][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 3.4644062519073486, cross_entropy: 3.4644062519073486 +[2025-04-29 09:52:35,699][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 1.9647032022476196, cross_entropy: 1.9647032022476196 +[2025-04-29 09:52:37,552][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 2.8322994709014893, cross_entropy: 2.8322994709014893 +[2025-04-29 09:52:38,697][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.2937192916870117, cross_entropy: 2.2937192916870117 +[2025-04-29 09:52:41,338][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 3.062643527984619, cross_entropy: 3.062643527984619 +[2025-04-29 09:52:42,502][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.9730324745178223, cross_entropy: 2.9730324745178223 +[2025-04-29 09:52:44,558][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.2323732376098633, cross_entropy: 2.2323732376098633 +[2025-04-29 09:52:45,639][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 1.2131885290145874, cross_entropy: 1.2131885290145874 +[2025-04-29 09:52:48,770][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.5088390111923218, cross_entropy: 1.5088390111923218 +[2025-04-29 09:52:49,588][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 1.8966854810714722, cross_entropy: 1.8966854810714722 +[2025-04-29 09:52:52,122][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.6504056453704834, cross_entropy: 1.6504056453704834 +[2025-04-29 09:52:52,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 3.61515736579895, cross_entropy: 3.61515736579895 +[2025-04-29 09:52:56,024][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 1.4428691864013672, cross_entropy: 1.4428691864013672 +[2025-04-29 09:52:56,869][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 1.8575234413146973, cross_entropy: 1.8575234413146973 +[2025-04-29 09:52:58,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 1.42287278175354, cross_entropy: 1.42287278175354 +[2025-04-29 09:52:59,728][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 1.0262079238891602, cross_entropy: 1.0262079238891602 +[2025-04-29 09:53:01,569][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.3737940788269043, cross_entropy: 2.3737940788269043 +[2025-04-29 09:53:02,427][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 3.226259231567383, cross_entropy: 3.226259231567383 +[2025-04-29 09:53:05,050][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 1.376779317855835, cross_entropy: 1.376779317855835 +[2025-04-29 09:53:05,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 2.3984177112579346, cross_entropy: 2.3984177112579346 +[2025-04-29 09:53:08,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 3.3944907188415527, cross_entropy: 3.3944907188415527 +[2025-04-29 09:53:09,395][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 1.4350430965423584, cross_entropy: 1.4350430965423584 +[2025-04-29 09:53:11,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 1.5932164192199707, cross_entropy: 1.5932164192199707 +[2025-04-29 09:53:12,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 2.229990243911743, cross_entropy: 2.229990243911743 +[2025-04-29 09:53:15,586][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 1.8343889713287354, cross_entropy: 1.8343889713287354 +[2025-04-29 09:53:16,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 1.491307020187378, cross_entropy: 1.491307020187378 +[2025-04-29 09:53:19,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 2.8399012088775635, cross_entropy: 2.8399012088775635 +[2025-04-29 09:53:20,327][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 1.4445090293884277, cross_entropy: 1.4445090293884277 +[2025-04-29 09:53:23,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.8307123184204102, cross_entropy: 1.8307123184204102 +[2025-04-29 09:53:23,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 1.8026844263076782, cross_entropy: 1.8026844263076782 +[2025-04-29 09:53:26,764][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.17437744140625, cross_entropy: 2.17437744140625 +[2025-04-29 09:53:27,587][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.867149591445923, cross_entropy: 2.867149591445923 +[2025-04-29 09:53:30,936][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.023306369781494, cross_entropy: 3.023306369781494 +[2025-04-29 09:53:31,786][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 1.0287644863128662, cross_entropy: 1.0287644863128662 +[2025-04-29 09:53:34,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.2524218559265137, cross_entropy: 3.2524218559265137 +[2025-04-29 09:53:34,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 1.2689653635025024, cross_entropy: 1.2689653635025024 +[2025-04-29 09:53:37,020][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 3.0252766609191895, cross_entropy: 3.0252766609191895 +[2025-04-29 09:53:37,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 1.3641371726989746, cross_entropy: 1.3641371726989746 +[2025-04-29 09:53:40,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.7428226470947266, cross_entropy: 2.7428226470947266 +[2025-04-29 09:53:40,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 0.7962310314178467, cross_entropy: 0.7962310314178467 +[2025-04-29 09:53:43,517][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 1.528160810470581, cross_entropy: 1.528160810470581 +[2025-04-29 09:53:44,373][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.636628270149231, cross_entropy: 1.636628270149231 +[2025-04-29 09:53:47,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 1.8416175842285156, cross_entropy: 1.8416175842285156 +[2025-04-29 09:53:48,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.527932643890381, cross_entropy: 2.527932643890381 +[2025-04-29 09:53:51,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.6546201705932617, cross_entropy: 1.6546201705932617 +[2025-04-29 09:53:52,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 3.542874813079834, cross_entropy: 3.542874813079834 +[2025-04-29 09:53:54,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.7729854583740234, cross_entropy: 2.7729854583740234 +[2025-04-29 09:53:55,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 2.914562463760376, cross_entropy: 2.914562463760376 +[2025-04-29 09:53:57,578][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 1.4061774015426636, cross_entropy: 1.4061774015426636 +[2025-04-29 09:53:58,568][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 1.9613378047943115, cross_entropy: 1.9613378047943115 +[2025-04-29 09:54:01,292][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.4984498023986816, cross_entropy: 1.4984498023986816 +[2025-04-29 09:54:02,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 1.6873772144317627, cross_entropy: 1.6873772144317627 +[2025-04-29 09:54:05,054][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 1.722673773765564, cross_entropy: 1.722673773765564 +[2025-04-29 09:54:06,685][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 1.6221811771392822, cross_entropy: 1.6221811771392822 +[2025-04-29 09:54:09,048][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 1.6721200942993164, cross_entropy: 1.6721200942993164 +[2025-04-29 09:54:10,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.8166241645812988, cross_entropy: 1.8166241645812988 +[2025-04-29 09:54:12,409][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.1469229459762573, cross_entropy: 1.1469229459762573 +[2025-04-29 09:54:13,502][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 2.2629754543304443, cross_entropy: 2.2629754543304443 +[2025-04-29 09:54:17,459][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.500363826751709, cross_entropy: 1.500363826751709 +[2025-04-29 09:54:18,314][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 1.7775750160217285, cross_entropy: 1.7775750160217285 +[2025-04-29 09:54:20,944][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.313795804977417, cross_entropy: 2.313795804977417 +[2025-04-29 09:54:21,798][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 2.3126485347747803, cross_entropy: 2.3126485347747803 +[2025-04-29 09:54:24,921][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 3.2976298332214355, cross_entropy: 3.2976298332214355 +[2025-04-29 09:54:25,775][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 2.55537748336792, cross_entropy: 2.55537748336792 +[2025-04-29 09:54:30,032][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 2.443781614303589, cross_entropy: 2.443781614303589 +[2025-04-29 09:54:30,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 1.8910722732543945, cross_entropy: 1.8910722732543945 +[2025-04-29 09:54:33,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 2.9673142433166504, cross_entropy: 2.9673142433166504 +[2025-04-29 09:54:33,844][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 2.9553961753845215, cross_entropy: 2.9553961753845215 +[2025-04-29 09:54:36,629][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.1405560970306396, cross_entropy: 2.1405560970306396 +[2025-04-29 09:54:37,557][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 3.347226142883301, cross_entropy: 3.347226142883301 +[2025-04-29 09:54:40,086][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.8617520332336426, cross_entropy: 2.8617520332336426 +[2025-04-29 09:54:40,907][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 3.1327333450317383, cross_entropy: 3.1327333450317383 +[2025-04-29 09:54:43,598][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.8913679122924805, cross_entropy: 2.8913679122924805 +[2025-04-29 09:54:44,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 2.102465867996216, cross_entropy: 2.102465867996216 +[2025-04-29 09:54:46,726][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.631983757019043, cross_entropy: 1.631983757019043 +[2025-04-29 09:54:48,474][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 1.706305980682373, cross_entropy: 1.706305980682373 +[2025-04-29 09:54:50,235][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 2.684393882751465, cross_entropy: 2.684393882751465 +[2025-04-29 09:54:52,372][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.3350244760513306, cross_entropy: 1.3350244760513306 +[2025-04-29 09:54:54,222][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.877060890197754, cross_entropy: 2.877060890197754 +[2025-04-29 09:54:55,439][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 1.3381543159484863, cross_entropy: 1.3381543159484863 +[2025-04-29 09:54:58,252][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.019202709197998, cross_entropy: 2.019202709197998 +[2025-04-29 09:54:59,109][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.8503570556640625, cross_entropy: 1.8503570556640625 +[2025-04-29 09:55:01,491][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 1.2768205404281616, cross_entropy: 1.2768205404281616 +[2025-04-29 09:55:02,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 3.034752130508423, cross_entropy: 3.034752130508423 +[2025-04-29 09:55:06,450][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 1.5528905391693115, cross_entropy: 1.5528905391693115 +[2025-04-29 09:55:07,307][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 1.2968965768814087, cross_entropy: 1.2968965768814087 +[2025-04-29 09:55:11,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.9393621683120728, cross_entropy: 1.9393621683120728 +[2025-04-29 09:55:11,917][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 1.3075220584869385, cross_entropy: 1.3075220584869385 +[2025-04-29 09:55:14,561][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.76274836063385, cross_entropy: 1.76274836063385 +[2025-04-29 09:55:15,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 1.9312310218811035, cross_entropy: 1.9312310218811035 +[2025-04-29 09:55:18,509][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 0.9982273578643799, cross_entropy: 0.9982273578643799 +[2025-04-29 09:55:19,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.8314725160598755, cross_entropy: 1.8314725160598755 +[2025-04-29 09:55:21,941][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.256086826324463, cross_entropy: 3.256086826324463 +[2025-04-29 09:55:22,818][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.5976648330688477, cross_entropy: 1.5976648330688477 +[2025-04-29 09:55:25,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 1.2577614784240723, cross_entropy: 1.2577614784240723 +[2025-04-29 09:55:26,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 3.2548608779907227, cross_entropy: 3.2548608779907227 +[2025-04-29 09:55:29,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 1.5184444189071655, cross_entropy: 1.5184444189071655 +[2025-04-29 09:55:30,021][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.1158332824707031, cross_entropy: 1.1158332824707031 +[2025-04-29 09:55:33,275][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 1.6572606563568115, cross_entropy: 1.6572606563568115 +[2025-04-29 09:55:34,097][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 3.3999953269958496, cross_entropy: 3.3999953269958496 +[2025-04-29 09:55:37,272][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.3057003021240234, cross_entropy: 3.3057003021240234 +[2025-04-29 09:55:38,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.8620226383209229, cross_entropy: 1.8620226383209229 +[2025-04-29 09:55:40,457][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 2.1985878944396973, cross_entropy: 2.1985878944396973 +[2025-04-29 09:55:41,312][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.0491302013397217, cross_entropy: 2.0491302013397217 +[2025-04-29 09:55:43,647][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 1.435789704322815, cross_entropy: 1.435789704322815 +[2025-04-29 09:55:44,553][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 2.0030670166015625, cross_entropy: 2.0030670166015625 +[2025-04-29 09:55:46,863][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 1.8226990699768066, cross_entropy: 1.8226990699768066 +[2025-04-29 09:55:47,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 1.8669238090515137, cross_entropy: 1.8669238090515137 +[2025-04-29 09:55:50,585][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.8586196899414062, cross_entropy: 1.8586196899414062 +[2025-04-29 09:55:51,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 1.2229130268096924, cross_entropy: 1.2229130268096924 +[2025-04-29 09:55:53,704][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.4826955795288086, cross_entropy: 1.4826955795288086 +[2025-04-29 09:55:54,863][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 1.2850736379623413, cross_entropy: 1.2850736379623413 +[2025-04-29 09:55:56,800][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.9136885404586792, cross_entropy: 1.9136885404586792 +[2025-04-29 09:55:58,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 3.297247886657715, cross_entropy: 3.297247886657715 +[2025-04-29 09:56:00,216][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.3748879432678223, cross_entropy: 1.3748879432678223 +[2025-04-29 09:56:01,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 2.812964916229248, cross_entropy: 2.812964916229248 +[2025-04-29 09:56:03,712][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.1109061241149902, cross_entropy: 2.1109061241149902 +[2025-04-29 09:56:05,658][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.6280772686004639, cross_entropy: 1.6280772686004639 +[2025-04-29 09:56:06,505][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/iteration1000.pth. +[2025-04-29 09:56:07,401][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.8974714279174805, cross_entropy: 2.8974714279174805 +[2025-04-29 09:56:09,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.8107489347457886, cross_entropy: 1.8107489347457886 +[2025-04-29 09:56:09,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 2.955178737640381, cross_entropy: 2.955178737640381 +[2025-04-29 09:56:12,720][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.9186500310897827, cross_entropy: 1.9186500310897827 +[2025-04-29 09:56:13,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.7594144344329834, cross_entropy: 1.7594144344329834 +[2025-04-29 09:56:16,499][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 1.6340076923370361, cross_entropy: 1.6340076923370361 +[2025-04-29 09:56:17,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.5909934043884277, cross_entropy: 2.5909934043884277 +[2025-04-29 09:56:20,705][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 1.4623510837554932, cross_entropy: 1.4623510837554932 +[2025-04-29 09:56:21,644][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 1.339871883392334, cross_entropy: 1.339871883392334 +[2025-04-29 09:56:23,750][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.526904582977295, cross_entropy: 2.526904582977295 +[2025-04-29 09:56:24,791][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 2.8988571166992188, cross_entropy: 2.8988571166992188 +[2025-04-29 09:56:26,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 1.8912467956542969, cross_entropy: 1.8912467956542969 +[2025-04-29 09:56:28,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 2.1328892707824707, cross_entropy: 2.1328892707824707 +[2025-04-29 09:56:31,444][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 2.365485191345215, cross_entropy: 2.365485191345215 +[2025-04-29 09:56:32,300][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.5469259023666382, cross_entropy: 1.5469259023666382 +[2025-04-29 09:56:34,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 2.0582549571990967, cross_entropy: 2.0582549571990967 +[2025-04-29 09:56:35,709][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 1.481870174407959, cross_entropy: 1.481870174407959 +[2025-04-29 09:56:38,572][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.013331890106201, cross_entropy: 2.013331890106201 +[2025-04-29 09:56:39,447][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.473461151123047, cross_entropy: 2.473461151123047 +[2025-04-29 09:56:42,148][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 1.7683112621307373, cross_entropy: 1.7683112621307373 +[2025-04-29 09:56:43,022][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 1.7125937938690186, cross_entropy: 1.7125937938690186 +[2025-04-29 09:56:45,661][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 1.5809601545333862, cross_entropy: 1.5809601545333862 +[2025-04-29 09:56:46,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.5515248775482178, cross_entropy: 1.5515248775482178 +[2025-04-29 09:56:48,709][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 3.070460081100464, cross_entropy: 3.070460081100464 +[2025-04-29 09:56:50,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.5513015985488892, cross_entropy: 1.5513015985488892 +[2025-04-29 09:56:52,409][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.1741318702697754, cross_entropy: 2.1741318702697754 +[2025-04-29 09:56:54,530][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 1.3635681867599487, cross_entropy: 1.3635681867599487 +[2025-04-29 09:56:55,789][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.683095693588257, cross_entropy: 2.683095693588257 +[2025-04-29 09:56:58,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.3869307041168213, cross_entropy: 2.3869307041168213 +[2025-04-29 09:56:59,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.541378378868103, cross_entropy: 1.541378378868103 +[2025-04-29 09:57:01,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.4620946645736694, cross_entropy: 1.4620946645736694 +[2025-04-29 09:57:03,206][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 1.2794842720031738, cross_entropy: 1.2794842720031738 +[2025-04-29 09:57:07,511][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 3.043545722961426, cross_entropy: 3.043545722961426 +[2025-04-29 09:57:08,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 1.8329601287841797, cross_entropy: 1.8329601287841797 +[2025-04-29 09:57:10,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 2.761416435241699, cross_entropy: 2.761416435241699 +[2025-04-29 09:57:11,705][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 1.1134716272354126, cross_entropy: 1.1134716272354126 +[2025-04-29 09:57:15,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 3.204237222671509, cross_entropy: 3.204237222671509 +[2025-04-29 09:57:15,945][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.5974528789520264, cross_entropy: 1.5974528789520264 +[2025-04-29 09:57:18,846][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 1.503095269203186, cross_entropy: 1.503095269203186 +[2025-04-29 09:57:19,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 2.2848494052886963, cross_entropy: 2.2848494052886963 +[2025-04-29 09:57:22,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 3.00285005569458, cross_entropy: 3.00285005569458 +[2025-04-29 09:57:23,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 1.6858208179473877, cross_entropy: 1.6858208179473877 +[2025-04-29 09:57:26,006][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.053501605987549, cross_entropy: 3.053501605987549 +[2025-04-29 09:57:26,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 1.6600160598754883, cross_entropy: 1.6600160598754883 +[2025-04-29 09:57:28,776][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 1.1622791290283203, cross_entropy: 1.1622791290283203 +[2025-04-29 09:57:29,628][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 2.4598798751831055, cross_entropy: 2.4598798751831055 +[2025-04-29 09:57:32,479][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.4869571924209595, cross_entropy: 1.4869571924209595 +[2025-04-29 09:57:33,332][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.853633403778076, cross_entropy: 2.853633403778076 +[2025-04-29 09:57:35,601][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 1.743457555770874, cross_entropy: 1.743457555770874 +[2025-04-29 09:57:36,614][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.44790780544281, cross_entropy: 1.44790780544281 +[2025-04-29 09:57:38,713][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 1.2477973699569702, cross_entropy: 1.2477973699569702 +[2025-04-29 09:57:39,611][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.1777567863464355, cross_entropy: 2.1777567863464355 +[2025-04-29 09:57:43,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.6358931064605713, cross_entropy: 1.6358931064605713 +[2025-04-29 09:57:43,865][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.257713794708252, cross_entropy: 2.257713794708252 +[2025-04-29 09:57:46,934][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.3485262393951416, cross_entropy: 1.3485262393951416 +[2025-04-29 09:57:47,755][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 2.9080700874328613, cross_entropy: 2.9080700874328613 +[2025-04-29 09:57:50,172][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 1.3411215543746948, cross_entropy: 1.3411215543746948 +[2025-04-29 09:57:51,078][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.4434959888458252, cross_entropy: 1.4434959888458252 +[2025-04-29 09:57:54,975][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.7486090660095215, cross_entropy: 1.7486090660095215 +[2025-04-29 09:57:55,792][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.7223811149597168, cross_entropy: 1.7223811149597168 +[2025-04-29 09:57:58,510][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.373263955116272, cross_entropy: 1.373263955116272 +[2025-04-29 09:57:59,328][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 2.503415107727051, cross_entropy: 2.503415107727051 +[2025-04-29 09:58:02,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 2.4274775981903076, cross_entropy: 2.4274775981903076 +[2025-04-29 09:58:03,277][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 3.1135878562927246, cross_entropy: 3.1135878562927246 +[2025-04-29 09:58:06,771][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 1.0773205757141113, cross_entropy: 1.0773205757141113 +[2025-04-29 09:58:07,626][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.4936866760253906, cross_entropy: 1.4936866760253906 +[2025-04-29 09:58:10,068][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.3789498805999756, cross_entropy: 1.3789498805999756 +[2025-04-29 09:58:10,809][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 3.1730244159698486, cross_entropy: 3.1730244159698486 +[2025-04-29 10:00:52,061][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.1256816387176514, cross_entropy: 2.1256816387176514 +[2025-04-29 10:00:52,062][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.299344778060913, cross_entropy: 1.299344778060913 +[2025-04-29 10:00:53,024][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 10:00:53,579][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch3.pth. +[2025-04-29 10:00:54,500][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 10:00:58,990][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 0.9176369309425354, cross_entropy: 0.9176369309425354 +[2025-04-29 10:00:59,871][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 2.298470973968506, cross_entropy: 2.298470973968506 +[2025-04-29 10:01:02,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 2.6782381534576416, cross_entropy: 2.6782381534576416 +[2025-04-29 10:01:04,734][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.6212995052337646, cross_entropy: 1.6212995052337646 +[2025-04-29 10:01:06,171][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 2.887233257293701, cross_entropy: 2.887233257293701 +[2025-04-29 10:01:07,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.5982569456100464, cross_entropy: 1.5982569456100464 +[2025-04-29 10:01:09,745][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.5190508365631104, cross_entropy: 1.5190508365631104 +[2025-04-29 10:01:10,858][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 1.0932366847991943, cross_entropy: 1.0932366847991943 +[2025-04-29 10:01:14,721][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.282762050628662, cross_entropy: 1.282762050628662 +[2025-04-29 10:01:15,577][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.2566437721252441, cross_entropy: 1.2566437721252441 +[2025-04-29 10:01:17,913][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 2.787193775177002, cross_entropy: 2.787193775177002 +[2025-04-29 10:01:18,763][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.8367762565612793, cross_entropy: 2.8367762565612793 +[2025-04-29 10:01:21,579][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 2.6592330932617188, cross_entropy: 2.6592330932617188 +[2025-04-29 10:01:22,406][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.8794116973876953, cross_entropy: 2.8794116973876953 +[2025-04-29 10:01:25,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 2.465641498565674, cross_entropy: 2.465641498565674 +[2025-04-29 10:01:26,721][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 2.8654284477233887, cross_entropy: 2.8654284477233887 +[2025-04-29 10:01:29,169][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.8809847831726074, cross_entropy: 2.8809847831726074 +[2025-04-29 10:01:30,018][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 1.3014730215072632, cross_entropy: 1.3014730215072632 +[2025-04-29 10:01:32,596][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.234649181365967, cross_entropy: 3.234649181365967 +[2025-04-29 10:01:33,420][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.149801254272461, cross_entropy: 2.149801254272461 +[2025-04-29 10:01:36,352][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 2.851314067840576, cross_entropy: 2.851314067840576 +[2025-04-29 10:01:37,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.353859782218933, cross_entropy: 1.353859782218933 +[2025-04-29 10:01:40,174][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.266299247741699, cross_entropy: 2.266299247741699 +[2025-04-29 10:01:41,053][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 1.2499881982803345, cross_entropy: 1.2499881982803345 +[2025-04-29 10:01:43,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 1.7146966457366943, cross_entropy: 1.7146966457366943 +[2025-04-29 10:01:44,703][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 2.8259851932525635, cross_entropy: 2.8259851932525635 +[2025-04-29 10:01:46,600][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 3.1798079013824463, cross_entropy: 3.1798079013824463 +[2025-04-29 10:01:48,165][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 1.853425145149231, cross_entropy: 1.853425145149231 +[2025-04-29 10:01:51,029][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.2194790840148926, cross_entropy: 2.2194790840148926 +[2025-04-29 10:01:52,059][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 1.3359336853027344, cross_entropy: 1.3359336853027344 +[2025-04-29 10:01:55,619][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 1.7604997158050537, cross_entropy: 1.7604997158050537 +[2025-04-29 10:01:56,436][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 0.8990364074707031, cross_entropy: 0.8990364074707031 +[2025-04-29 10:01:59,474][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 2.932218551635742, cross_entropy: 2.932218551635742 +[2025-04-29 10:02:00,324][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 1.8776185512542725, cross_entropy: 1.8776185512542725 +[2025-04-29 10:02:03,767][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 3.1185269355773926, cross_entropy: 3.1185269355773926 +[2025-04-29 10:02:04,662][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 1.2794020175933838, cross_entropy: 1.2794020175933838 +[2025-04-29 10:02:07,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.4157345294952393, cross_entropy: 1.4157345294952393 +[2025-04-29 10:02:08,532][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 2.648869752883911, cross_entropy: 2.648869752883911 +[2025-04-29 10:02:11,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 1.119039535522461, cross_entropy: 1.119039535522461 +[2025-04-29 10:02:12,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 2.603703498840332, cross_entropy: 2.603703498840332 +[2025-04-29 10:02:14,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 1.7597635984420776, cross_entropy: 1.7597635984420776 +[2025-04-29 10:02:15,744][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 2.6519455909729004, cross_entropy: 2.6519455909729004 +[2025-04-29 10:02:18,873][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 1.1061503887176514, cross_entropy: 1.1061503887176514 +[2025-04-29 10:02:19,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.015620708465576, cross_entropy: 2.015620708465576 +[2025-04-29 10:02:22,407][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 1.7383227348327637, cross_entropy: 1.7383227348327637 +[2025-04-29 10:02:23,263][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.4622678756713867, cross_entropy: 2.4622678756713867 +[2025-04-29 10:02:27,442][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.5018653869628906, cross_entropy: 2.5018653869628906 +[2025-04-29 10:02:28,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.5001887083053589, cross_entropy: 1.5001887083053589 +[2025-04-29 10:02:31,169][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 3.024726390838623, cross_entropy: 3.024726390838623 +[2025-04-29 10:02:32,021][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 1.133366346359253, cross_entropy: 1.133366346359253 +[2025-04-29 10:02:34,598][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.7338736057281494, cross_entropy: 1.7338736057281494 +[2025-04-29 10:02:35,454][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.7627003192901611, cross_entropy: 1.7627003192901611 +[2025-04-29 10:02:37,941][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.5063586235046387, cross_entropy: 2.5063586235046387 +[2025-04-29 10:02:38,827][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.333530902862549, cross_entropy: 2.333530902862549 +[2025-04-29 10:02:41,482][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 1.4573715925216675, cross_entropy: 1.4573715925216675 +[2025-04-29 10:02:42,348][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 3.090099334716797, cross_entropy: 3.090099334716797 +[2025-04-29 10:02:45,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.7771074771881104, cross_entropy: 2.7771074771881104 +[2025-04-29 10:02:45,933][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.075653076171875, cross_entropy: 2.075653076171875 +[2025-04-29 10:02:49,381][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 3.0912680625915527, cross_entropy: 3.0912680625915527 +[2025-04-29 10:02:50,234][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.8452720642089844, cross_entropy: 2.8452720642089844 +[2025-04-29 10:02:52,253][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.1451470851898193, cross_entropy: 1.1451470851898193 +[2025-04-29 10:02:53,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.944805860519409, cross_entropy: 2.944805860519409 +[2025-04-29 10:02:55,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 3.1581623554229736, cross_entropy: 3.1581623554229736 +[2025-04-29 10:02:56,400][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 3.020862102508545, cross_entropy: 3.020862102508545 +[2025-04-29 10:02:59,305][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.539449691772461, cross_entropy: 2.539449691772461 +[2025-04-29 10:03:00,654][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 2.426659107208252, cross_entropy: 2.426659107208252 +[2025-04-29 10:03:02,685][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.1523661613464355, cross_entropy: 2.1523661613464355 +[2025-04-29 10:03:04,147][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 1.6515886783599854, cross_entropy: 1.6515886783599854 +[2025-04-29 10:03:06,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.655505657196045, cross_entropy: 2.655505657196045 +[2025-04-29 10:03:07,642][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 0.9508851766586304, cross_entropy: 0.9508851766586304 +[2025-04-29 10:03:09,270][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 1.3425133228302002, cross_entropy: 1.3425133228302002 +[2025-04-29 10:03:11,878][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.1767523288726807, cross_entropy: 1.1767523288726807 +[2025-04-29 10:03:12,816][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 2.692392349243164, cross_entropy: 2.692392349243164 +[2025-04-29 10:03:15,739][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.241957187652588, cross_entropy: 1.241957187652588 +[2025-04-29 10:03:16,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 1.0459113121032715, cross_entropy: 1.0459113121032715 +[2025-04-29 10:03:19,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 3.120511054992676, cross_entropy: 3.120511054992676 +[2025-04-29 10:03:20,107][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.0154365301132202, cross_entropy: 1.0154365301132202 +[2025-04-29 10:03:22,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 1.417480707168579, cross_entropy: 1.417480707168579 +[2025-04-29 10:03:23,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 2.880892515182495, cross_entropy: 2.880892515182495 +[2025-04-29 10:03:25,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.9081001281738281, cross_entropy: 1.9081001281738281 +[2025-04-29 10:03:26,482][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.2380099296569824, cross_entropy: 3.2380099296569824 +[2025-04-29 10:03:30,340][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 1.3280901908874512, cross_entropy: 1.3280901908874512 +[2025-04-29 10:03:31,161][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 1.2317453622817993, cross_entropy: 1.2317453622817993 +[2025-04-29 10:03:34,022][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 2.6950676441192627, cross_entropy: 2.6950676441192627 +[2025-04-29 10:03:34,883][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.091120958328247, cross_entropy: 1.091120958328247 +[2025-04-29 10:03:37,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 1.2202519178390503, cross_entropy: 1.2202519178390503 +[2025-04-29 10:03:38,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.6475343704223633, cross_entropy: 1.6475343704223633 +[2025-04-29 10:03:41,294][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 2.792116165161133, cross_entropy: 2.792116165161133 +[2025-04-29 10:03:42,126][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 3.227023124694824, cross_entropy: 3.227023124694824 +[2025-04-29 10:03:44,728][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 1.3698887825012207, cross_entropy: 1.3698887825012207 +[2025-04-29 10:03:45,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.142731189727783, cross_entropy: 3.142731189727783 +[2025-04-29 10:03:48,343][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.6120781898498535, cross_entropy: 1.6120781898498535 +[2025-04-29 10:03:49,164][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.4794769287109375, cross_entropy: 1.4794769287109375 +[2025-04-29 10:03:51,949][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.7861642837524414, cross_entropy: 2.7861642837524414 +[2025-04-29 10:03:52,806][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 1.6437811851501465, cross_entropy: 1.6437811851501465 +[2025-04-29 10:03:55,452][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.948386311531067, cross_entropy: 1.948386311531067 +[2025-04-29 10:03:56,338][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 1.5104010105133057, cross_entropy: 1.5104010105133057 +[2025-04-29 10:03:58,767][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.649644374847412, cross_entropy: 1.649644374847412 +[2025-04-29 10:03:59,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 1.292769432067871, cross_entropy: 1.292769432067871 +[2025-04-29 10:04:03,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.5132392644882202, cross_entropy: 1.5132392644882202 +[2025-04-29 10:04:03,974][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 1.656614899635315, cross_entropy: 1.656614899635315 +[2025-04-29 10:04:07,990][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.3145174980163574, cross_entropy: 2.3145174980163574 +[2025-04-29 10:04:08,810][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 0.7418824434280396, cross_entropy: 0.7418824434280396 +[2025-04-29 10:04:11,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 2.891792058944702, cross_entropy: 2.891792058944702 +[2025-04-29 10:04:12,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.591087579727173, cross_entropy: 2.591087579727173 +[2025-04-29 10:04:14,816][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.4164185523986816, cross_entropy: 1.4164185523986816 +[2025-04-29 10:04:15,639][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.1993093490600586, cross_entropy: 3.1993093490600586 +[2025-04-29 10:04:18,145][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 1.9921237230300903, cross_entropy: 1.9921237230300903 +[2025-04-29 10:04:19,001][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 1.1970078945159912, cross_entropy: 1.1970078945159912 +[2025-04-29 10:04:21,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 1.2528938055038452, cross_entropy: 1.2528938055038452 +[2025-04-29 10:04:22,766][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 1.0892822742462158, cross_entropy: 1.0892822742462158 +[2025-04-29 10:04:25,318][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.8277491331100464, cross_entropy: 1.8277491331100464 +[2025-04-29 10:04:26,185][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 1.7926157712936401, cross_entropy: 1.7926157712936401 +[2025-04-29 10:04:29,685][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.0528578758239746, cross_entropy: 2.0528578758239746 +[2025-04-29 10:04:30,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 2.7353429794311523, cross_entropy: 2.7353429794311523 +[2025-04-29 10:04:32,791][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 1.3386280536651611, cross_entropy: 1.3386280536651611 +[2025-04-29 10:04:33,649][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.7348380088806152, cross_entropy: 2.7348380088806152 +[2025-04-29 10:04:36,641][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 2.2061195373535156, cross_entropy: 2.2061195373535156 +[2025-04-29 10:04:37,509][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 2.3362836837768555, cross_entropy: 2.3362836837768555 +[2025-04-29 10:04:39,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 1.2582828998565674, cross_entropy: 1.2582828998565674 +[2025-04-29 10:04:40,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.1666793823242188, cross_entropy: 3.1666793823242188 +[2025-04-29 10:04:42,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 1.137481451034546, cross_entropy: 1.137481451034546 +[2025-04-29 10:04:43,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.1133134365081787, cross_entropy: 2.1133134365081787 +[2025-04-29 10:04:46,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 1.464848518371582, cross_entropy: 1.464848518371582 +[2025-04-29 10:04:47,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.5914318561553955, cross_entropy: 1.5914318561553955 +[2025-04-29 10:04:49,792][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.0874483585357666, cross_entropy: 1.0874483585357666 +[2025-04-29 10:04:50,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 3.2897942066192627, cross_entropy: 3.2897942066192627 +[2025-04-29 10:04:53,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.836259365081787, cross_entropy: 2.836259365081787 +[2025-04-29 10:04:54,810][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.3253098726272583, cross_entropy: 1.3253098726272583 +[2025-04-29 10:04:57,491][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 1.3067314624786377, cross_entropy: 1.3067314624786377 +[2025-04-29 10:04:58,345][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 3.1203932762145996, cross_entropy: 3.1203932762145996 +[2025-04-29 10:05:01,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.9431686401367188, cross_entropy: 2.9431686401367188 +[2025-04-29 10:05:01,978][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 1.5757304430007935, cross_entropy: 1.5757304430007935 +[2025-04-29 10:05:04,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.1748299598693848, cross_entropy: 1.1748299598693848 +[2025-04-29 10:05:04,948][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.2537620067596436, cross_entropy: 1.2537620067596436 +[2025-04-29 10:05:07,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 3.04071044921875, cross_entropy: 3.04071044921875 +[2025-04-29 10:05:08,632][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 1.7983518838882446, cross_entropy: 1.7983518838882446 +[2025-04-29 10:05:11,066][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.7747719287872314, cross_entropy: 2.7747719287872314 +[2025-04-29 10:05:11,886][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 0.7694647312164307, cross_entropy: 0.7694647312164307 +[2025-04-29 10:05:15,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.1036124229431152, cross_entropy: 2.1036124229431152 +[2025-04-29 10:05:16,028][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 2.9723336696624756, cross_entropy: 2.9723336696624756 +[2025-04-29 10:05:18,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 1.387578010559082, cross_entropy: 1.387578010559082 +[2025-04-29 10:05:19,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 2.9530985355377197, cross_entropy: 2.9530985355377197 +[2025-04-29 10:05:21,184][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 1.974104642868042, cross_entropy: 1.974104642868042 +[2025-04-29 10:05:22,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 0.9652740359306335, cross_entropy: 0.9652740359306335 +[2025-04-29 10:05:25,203][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.1275396347045898, cross_entropy: 1.1275396347045898 +[2025-04-29 10:05:26,128][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 1.3877264261245728, cross_entropy: 1.3877264261245728 +[2025-04-29 10:05:28,602][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 2.955497980117798, cross_entropy: 2.955497980117798 +[2025-04-29 10:05:30,735][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 1.2895227670669556, cross_entropy: 1.2895227670669556 +[2025-04-29 10:05:31,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 1.197486162185669, cross_entropy: 1.197486162185669 +[2025-04-29 10:05:34,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.169710636138916, cross_entropy: 1.169710636138916 +[2025-04-29 10:05:35,274][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 2.6122820377349854, cross_entropy: 2.6122820377349854 +[2025-04-29 10:05:38,780][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.9480583667755127, cross_entropy: 1.9480583667755127 +[2025-04-29 10:05:39,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.244879961013794, cross_entropy: 1.244879961013794 +[2025-04-29 10:05:42,232][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 2.111510753631592, cross_entropy: 2.111510753631592 +[2025-04-29 10:05:43,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.1011464595794678, cross_entropy: 2.1011464595794678 +[2025-04-29 10:05:46,193][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.3565921783447266, cross_entropy: 2.3565921783447266 +[2025-04-29 10:05:47,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 2.3355579376220703, cross_entropy: 2.3355579376220703 +[2025-04-29 10:05:49,491][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.1018033027648926, cross_entropy: 3.1018033027648926 +[2025-04-29 10:05:50,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 2.634268283843994, cross_entropy: 2.634268283843994 +[2025-04-29 10:05:52,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 0.8322939872741699, cross_entropy: 0.8322939872741699 +[2025-04-29 10:05:53,418][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 2.946540355682373, cross_entropy: 2.946540355682373 +[2025-04-29 10:05:56,084][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 1.1980726718902588, cross_entropy: 1.1980726718902588 +[2025-04-29 10:05:56,966][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.146847724914551, cross_entropy: 2.146847724914551 +[2025-04-29 10:05:59,126][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 2.2979843616485596, cross_entropy: 2.2979843616485596 +[2025-04-29 10:06:00,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.3378145694732666, cross_entropy: 1.3378145694732666 +[2025-04-29 10:06:02,827][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 2.3517398834228516, cross_entropy: 2.3517398834228516 +[2025-04-29 10:06:04,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.7613980770111084, cross_entropy: 1.7613980770111084 +[2025-04-29 10:06:06,168][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 2.076279878616333, cross_entropy: 2.076279878616333 +[2025-04-29 10:06:07,188][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 1.1912986040115356, cross_entropy: 1.1912986040115356 +[2025-04-29 10:06:09,577][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 1.2210638523101807, cross_entropy: 1.2210638523101807 +[2025-04-29 10:06:10,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 1.0695667266845703, cross_entropy: 1.0695667266845703 +[2025-04-29 10:06:14,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 1.6451160907745361, cross_entropy: 1.6451160907745361 +[2025-04-29 10:06:14,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 1.3050328493118286, cross_entropy: 1.3050328493118286 +[2025-04-29 10:06:17,330][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 3.1133129596710205, cross_entropy: 3.1133129596710205 +[2025-04-29 10:06:18,264][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 3.1364331245422363, cross_entropy: 3.1364331245422363 +[2025-04-29 10:06:20,751][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 1.9127249717712402, cross_entropy: 1.9127249717712402 +[2025-04-29 10:06:21,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.1546944379806519, cross_entropy: 1.1546944379806519 +[2025-04-29 10:06:24,882][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 1.1367244720458984, cross_entropy: 1.1367244720458984 +[2025-04-29 10:06:25,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 2.3527073860168457, cross_entropy: 2.3527073860168457 +[2025-04-29 10:06:28,240][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 1.2864634990692139, cross_entropy: 1.2864634990692139 +[2025-04-29 10:06:29,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 2.0693230628967285, cross_entropy: 2.0693230628967285 +[2025-04-29 10:06:31,003][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 3.0092716217041016, cross_entropy: 3.0092716217041016 +[2025-04-29 10:06:31,913][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 1.39178466796875, cross_entropy: 1.39178466796875 +[2025-04-29 10:06:34,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.613401412963867, cross_entropy: 2.613401412963867 +[2025-04-29 10:06:35,299][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 1.8519887924194336, cross_entropy: 1.8519887924194336 +[2025-04-29 10:06:37,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.6106956005096436, cross_entropy: 1.6106956005096436 +[2025-04-29 10:06:38,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.0330431461334229, cross_entropy: 1.0330431461334229 +[2025-04-29 10:06:41,463][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 2.350703001022339, cross_entropy: 2.350703001022339 +[2025-04-29 10:06:42,442][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 0.8839722871780396, cross_entropy: 0.8839722871780396 +[2025-04-29 10:06:46,206][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.5100560188293457, cross_entropy: 2.5100560188293457 +[2025-04-29 10:06:47,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 2.5190176963806152, cross_entropy: 2.5190176963806152 +[2025-04-29 10:06:50,232][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 2.392198324203491, cross_entropy: 2.392198324203491 +[2025-04-29 10:06:51,093][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 3.1129260063171387, cross_entropy: 3.1129260063171387 +[2025-04-29 10:06:55,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.2216306924819946, cross_entropy: 1.2216306924819946 +[2025-04-29 10:06:56,102][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.8402233123779297, cross_entropy: 2.8402233123779297 +[2025-04-29 10:06:59,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 2.1875836849212646, cross_entropy: 2.1875836849212646 +[2025-04-29 10:07:00,079][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.696377754211426, cross_entropy: 2.696377754211426 +[2025-04-29 10:07:03,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 2.9918346405029297, cross_entropy: 2.9918346405029297 +[2025-04-29 10:07:04,176][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 1.6032472848892212, cross_entropy: 1.6032472848892212 +[2025-04-29 10:07:07,004][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.2881691455841064, cross_entropy: 1.2881691455841064 +[2025-04-29 10:07:07,825][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 2.602893829345703, cross_entropy: 2.602893829345703 +[2025-04-29 10:07:10,336][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 1.0523167848587036, cross_entropy: 1.0523167848587036 +[2025-04-29 10:07:11,156][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 2.509596824645996, cross_entropy: 2.509596824645996 +[2025-04-29 10:07:14,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 1.1436060667037964, cross_entropy: 1.1436060667037964 +[2025-04-29 10:07:15,198][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.558511257171631, cross_entropy: 2.558511257171631 +[2025-04-29 10:07:17,647][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 1.6630706787109375, cross_entropy: 1.6630706787109375 +[2025-04-29 10:07:18,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 2.1780953407287598, cross_entropy: 2.1780953407287598 +[2025-04-29 10:07:20,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 1.6167988777160645, cross_entropy: 1.6167988777160645 +[2025-04-29 10:07:21,411][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 2.078080892562866, cross_entropy: 2.078080892562866 +[2025-04-29 10:07:23,972][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.1188364028930664, cross_entropy: 1.1188364028930664 +[2025-04-29 10:07:24,790][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 0.9824685454368591, cross_entropy: 0.9824685454368591 +[2025-04-29 10:07:26,940][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 2.981039524078369, cross_entropy: 2.981039524078369 +[2025-04-29 10:07:27,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 3.1865878105163574, cross_entropy: 3.1865878105163574 +[2025-04-29 10:07:29,879][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.935811758041382, cross_entropy: 2.935811758041382 +[2025-04-29 10:07:30,697][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 1.1371548175811768, cross_entropy: 1.1371548175811768 +[2025-04-29 10:07:33,277][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 1.911420226097107, cross_entropy: 1.911420226097107 +[2025-04-29 10:07:34,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.4494919776916504, cross_entropy: 2.4494919776916504 +[2025-04-29 10:07:36,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.9433573484420776, cross_entropy: 1.9433573484420776 +[2025-04-29 10:07:37,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.8932127952575684, cross_entropy: 2.8932127952575684 +[2025-04-29 10:07:39,593][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 1.1466115713119507, cross_entropy: 1.1466115713119507 +[2025-04-29 10:07:40,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.3426589965820312, cross_entropy: 2.3426589965820312 +[2025-04-29 10:07:42,911][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 1.2534916400909424, cross_entropy: 1.2534916400909424 +[2025-04-29 10:07:43,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 1.166027545928955, cross_entropy: 1.166027545928955 +[2025-04-29 10:07:46,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 1.0483379364013672, cross_entropy: 1.0483379364013672 +[2025-04-29 10:07:47,014][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.165337562561035, cross_entropy: 3.165337562561035 +[2025-04-29 10:07:49,912][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 1.1791374683380127, cross_entropy: 1.1791374683380127 +[2025-04-29 10:07:51,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 1.8175932168960571, cross_entropy: 1.8175932168960571 +[2025-04-29 10:07:53,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 1.166457176208496, cross_entropy: 1.166457176208496 +[2025-04-29 10:07:55,702][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 2.6510705947875977, cross_entropy: 2.6510705947875977 +[2025-04-29 10:07:56,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.4993083477020264, cross_entropy: 2.4993083477020264 +[2025-04-29 10:07:59,595][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 1.1872121095657349, cross_entropy: 1.1872121095657349 +[2025-04-29 10:08:00,462][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.0162835121154785, cross_entropy: 2.0162835121154785 +[2025-04-29 10:08:03,128][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 3.0090503692626953, cross_entropy: 3.0090503692626953 +[2025-04-29 10:08:04,176][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.1013025045394897, cross_entropy: 1.1013025045394897 +[2025-04-29 10:08:06,255][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.740598678588867, cross_entropy: 2.740598678588867 +[2025-04-29 10:08:07,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 1.8636056184768677, cross_entropy: 1.8636056184768677 +[2025-04-29 10:08:10,344][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 1.546030044555664, cross_entropy: 1.546030044555664 +[2025-04-29 10:08:11,200][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 1.46518874168396, cross_entropy: 1.46518874168396 +[2025-04-29 10:08:13,647][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.1547751426696777, cross_entropy: 1.1547751426696777 +[2025-04-29 10:08:14,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 3.0786564350128174, cross_entropy: 3.0786564350128174 +[2025-04-29 10:08:17,717][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.6703076362609863, cross_entropy: 2.6703076362609863 +[2025-04-29 10:08:18,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 0.7905541658401489, cross_entropy: 0.7905541658401489 +[2025-04-29 10:08:22,197][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 3.159642219543457, cross_entropy: 3.159642219543457 +[2025-04-29 10:08:23,537][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.6031265258789062, cross_entropy: 1.6031265258789062 +[2025-04-29 10:08:25,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 1.316718339920044, cross_entropy: 1.316718339920044 +[2025-04-29 10:08:26,820][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.935169219970703, cross_entropy: 2.935169219970703 +[2025-04-29 10:08:29,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 1.8566745519638062, cross_entropy: 1.8566745519638062 +[2025-04-29 10:08:29,878][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 1.9568915367126465, cross_entropy: 1.9568915367126465 +[2025-04-29 10:08:33,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 0.9000435471534729, cross_entropy: 0.9000435471534729 +[2025-04-29 10:08:34,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.6536636352539062, cross_entropy: 2.6536636352539062 +[2025-04-29 10:08:37,706][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 1.8786014318466187, cross_entropy: 1.8786014318466187 +[2025-04-29 10:08:38,563][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 1.1331193447113037, cross_entropy: 1.1331193447113037 +[2025-04-29 10:08:41,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 2.7973570823669434, cross_entropy: 2.7973570823669434 +[2025-04-29 10:08:41,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.4488680362701416, cross_entropy: 2.4488680362701416 +[2025-04-29 10:08:45,328][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 1.142116904258728, cross_entropy: 1.142116904258728 +[2025-04-29 10:08:46,181][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 2.9338886737823486, cross_entropy: 2.9338886737823486 +[2025-04-29 10:08:48,666][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.562650442123413, cross_entropy: 1.562650442123413 +[2025-04-29 10:08:49,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.0492634773254395, cross_entropy: 1.0492634773254395 +[2025-04-29 10:08:52,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.6126651763916016, cross_entropy: 1.6126651763916016 +[2025-04-29 10:08:53,728][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 1.2478141784667969, cross_entropy: 1.2478141784667969 +[2025-04-29 10:08:57,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 2.4365310668945312, cross_entropy: 2.4365310668945312 +[2025-04-29 10:08:58,545][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 1.3689323663711548, cross_entropy: 1.3689323663711548 +[2025-04-29 10:09:01,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 2.8282055854797363, cross_entropy: 2.8282055854797363 +[2025-04-29 10:09:02,401][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 2.566601276397705, cross_entropy: 2.566601276397705 +[2025-04-29 10:09:04,847][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.5526294708251953, cross_entropy: 2.5526294708251953 +[2025-04-29 10:09:05,702][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.404696464538574, cross_entropy: 2.404696464538574 +[2025-04-29 10:09:08,144][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.63926100730896, cross_entropy: 2.63926100730896 +[2025-04-29 10:09:08,974][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 2.9209556579589844, cross_entropy: 2.9209556579589844 +[2025-04-29 10:09:11,777][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 2.991570472717285, cross_entropy: 2.991570472717285 +[2025-04-29 10:09:12,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.554687023162842, cross_entropy: 2.554687023162842 +[2025-04-29 10:09:14,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.1526505947113037, cross_entropy: 1.1526505947113037 +[2025-04-29 10:09:15,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 3.3939218521118164, cross_entropy: 3.3939218521118164 +[2025-04-29 10:09:18,990][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 1.6382038593292236, cross_entropy: 1.6382038593292236 +[2025-04-29 10:09:19,812][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 2.7693276405334473, cross_entropy: 2.7693276405334473 +[2025-04-29 10:09:23,144][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 2.999765396118164, cross_entropy: 2.999765396118164 +[2025-04-29 10:09:23,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 1.6032289266586304, cross_entropy: 1.6032289266586304 +[2025-04-29 10:09:26,360][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 2.5092668533325195, cross_entropy: 2.5092668533325195 +[2025-04-29 10:09:27,217][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 1.7052867412567139, cross_entropy: 1.7052867412567139 +[2025-04-29 10:09:30,365][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 2.5688302516937256, cross_entropy: 2.5688302516937256 +[2025-04-29 10:09:31,219][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 1.3918617963790894, cross_entropy: 1.3918617963790894 +[2025-04-29 10:09:34,403][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 2.5215165615081787, cross_entropy: 2.5215165615081787 +[2025-04-29 10:09:35,254][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 1.4217643737792969, cross_entropy: 1.4217643737792969 +[2025-04-29 10:09:38,258][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.8880844116210938, cross_entropy: 2.8880844116210938 +[2025-04-29 10:09:39,113][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 2.5061187744140625, cross_entropy: 2.5061187744140625 +[2025-04-29 10:09:41,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 1.8948509693145752, cross_entropy: 1.8948509693145752 +[2025-04-29 10:09:42,364][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.2607643604278564, cross_entropy: 3.2607643604278564 +[2025-04-29 10:09:44,543][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 1.314194917678833, cross_entropy: 1.314194917678833 +[2025-04-29 10:09:45,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4475202560424805, cross_entropy: 1.4475202560424805 +[2025-04-29 10:09:47,954][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 1.1272817850112915, cross_entropy: 1.1272817850112915 +[2025-04-29 10:09:48,835][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 1.3928558826446533, cross_entropy: 1.3928558826446533 +[2025-04-29 10:09:51,273][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 1.5202594995498657, cross_entropy: 1.5202594995498657 +[2025-04-29 10:09:52,183][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 2.341233253479004, cross_entropy: 2.341233253479004 +[2025-04-29 10:09:54,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 2.7179458141326904, cross_entropy: 2.7179458141326904 +[2025-04-29 10:09:55,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 3.0657591819763184, cross_entropy: 3.0657591819763184 +[2025-04-29 10:09:57,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 2.0936994552612305, cross_entropy: 2.0936994552612305 +[2025-04-29 10:09:59,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 1.899280309677124, cross_entropy: 1.899280309677124 +[2025-04-29 10:10:02,030][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.5307015180587769, cross_entropy: 1.5307015180587769 +[2025-04-29 10:10:02,980][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 0.9978097677230835, cross_entropy: 0.9978097677230835 +[2025-04-29 10:10:05,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 2.1074421405792236, cross_entropy: 2.1074421405792236 +[2025-04-29 10:10:06,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.0838754177093506, cross_entropy: 1.0838754177093506 +[2025-04-29 10:10:09,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.6903653144836426, cross_entropy: 2.6903653144836426 +[2025-04-29 10:10:10,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.0269665718078613, cross_entropy: 1.0269665718078613 +[2025-04-29 10:10:12,624][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 2.749927520751953, cross_entropy: 2.749927520751953 +[2025-04-29 10:10:13,967][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 0.9019415378570557, cross_entropy: 0.9019415378570557 +[2025-04-29 10:10:15,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.733170509338379, cross_entropy: 2.733170509338379 +[2025-04-29 10:10:16,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 2.9208900928497314, cross_entropy: 2.9208900928497314 +[2025-04-29 10:10:19,439][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 1.347275972366333, cross_entropy: 1.347275972366333 +[2025-04-29 10:10:20,344][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.5844459533691406, cross_entropy: 2.5844459533691406 +[2025-04-29 10:10:23,800][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.120525360107422, cross_entropy: 2.120525360107422 +[2025-04-29 10:10:24,611][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.9382450580596924, cross_entropy: 2.9382450580596924 +[2025-04-29 10:10:26,845][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.0951812267303467, cross_entropy: 1.0951812267303467 +[2025-04-29 10:10:27,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.2039097547531128, cross_entropy: 1.2039097547531128 +[2025-04-29 10:10:29,993][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 1.499070405960083, cross_entropy: 1.499070405960083 +[2025-04-29 10:10:30,924][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 1.3324329853057861, cross_entropy: 1.3324329853057861 +[2025-04-29 10:10:33,687][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.4243922233581543, cross_entropy: 1.4243922233581543 +[2025-04-29 10:10:34,527][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 2.016263484954834, cross_entropy: 2.016263484954834 +[2025-04-29 10:10:37,037][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 2.5785202980041504, cross_entropy: 2.5785202980041504 +[2025-04-29 10:10:37,888][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.3771543502807617, cross_entropy: 2.3771543502807617 +[2025-04-29 10:10:40,279][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 1.5835418701171875, cross_entropy: 1.5835418701171875 +[2025-04-29 10:10:41,125][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.7747961282730103, cross_entropy: 1.7747961282730103 +[2025-04-29 10:10:43,817][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.869063377380371, cross_entropy: 1.869063377380371 +[2025-04-29 10:10:44,635][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 1.9100549221038818, cross_entropy: 1.9100549221038818 +[2025-04-29 10:10:47,226][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 2.348106622695923, cross_entropy: 2.348106622695923 +[2025-04-29 10:10:48,072][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 2.9013266563415527, cross_entropy: 2.9013266563415527 +[2025-04-29 10:10:50,205][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 1.740952968597412, cross_entropy: 1.740952968597412 +[2025-04-29 10:10:51,018][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 2.6830806732177734, cross_entropy: 2.6830806732177734 +[2025-04-29 10:10:53,403][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 2.4401607513427734, cross_entropy: 2.4401607513427734 +[2025-04-29 10:10:54,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 2.4677929878234863, cross_entropy: 2.4677929878234863 +[2025-04-29 10:10:56,929][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.0145111083984375, cross_entropy: 1.0145111083984375 +[2025-04-29 10:10:57,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.7079460620880127, cross_entropy: 1.7079460620880127 +[2025-04-29 10:10:59,859][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 2.9564976692199707, cross_entropy: 2.9564976692199707 +[2025-04-29 10:11:00,739][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 1.2195085287094116, cross_entropy: 1.2195085287094116 +[2025-04-29 10:11:03,753][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 1.1531939506530762, cross_entropy: 1.1531939506530762 +[2025-04-29 10:11:04,612][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 2.4481124877929688, cross_entropy: 2.4481124877929688 +[2025-04-29 10:11:07,200][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.5479869842529297, cross_entropy: 2.5479869842529297 +[2025-04-29 10:11:08,140][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.6674778461456299, cross_entropy: 1.6674778461456299 +[2025-04-29 10:11:10,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 1.294808030128479, cross_entropy: 1.294808030128479 +[2025-04-29 10:11:11,730][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 2.893035650253296, cross_entropy: 2.893035650253296 +[2025-04-29 10:11:14,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 2.8168492317199707, cross_entropy: 2.8168492317199707 +[2025-04-29 10:11:15,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 1.1688048839569092, cross_entropy: 1.1688048839569092 +[2025-04-29 10:11:17,787][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 0.9281303882598877, cross_entropy: 0.9281303882598877 +[2025-04-29 10:11:18,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 2.5509002208709717, cross_entropy: 2.5509002208709717 +[2025-04-29 10:11:21,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.3095614910125732, cross_entropy: 1.3095614910125732 +[2025-04-29 10:11:22,352][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 1.6613147258758545, cross_entropy: 1.6613147258758545 +[2025-04-29 10:11:25,066][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 0.836706817150116, cross_entropy: 0.836706817150116 +[2025-04-29 10:11:25,920][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.4496103525161743, cross_entropy: 1.4496103525161743 +[2025-04-29 10:11:28,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 1.8921236991882324, cross_entropy: 1.8921236991882324 +[2025-04-29 10:11:29,233][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.372760534286499, cross_entropy: 1.372760534286499 +[2025-04-29 10:11:31,907][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 2.786123752593994, cross_entropy: 2.786123752593994 +[2025-04-29 10:11:32,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 2.7003962993621826, cross_entropy: 2.7003962993621826 +[2025-04-29 10:11:34,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 1.5963714122772217, cross_entropy: 1.5963714122772217 +[2025-04-29 10:11:35,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 1.1644612550735474, cross_entropy: 1.1644612550735474 +[2025-04-29 10:11:39,029][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 3.2225613594055176, cross_entropy: 3.2225613594055176 +[2025-04-29 10:11:39,842][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 2.65590763092041, cross_entropy: 2.65590763092041 +[2025-04-29 10:11:41,771][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 1.4886242151260376, cross_entropy: 1.4886242151260376 +[2025-04-29 10:14:15,858][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.0035221576690674, cross_entropy: 2.0035221576690674 +[2025-04-29 10:14:15,859][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.1794763803482056, cross_entropy: 1.1794763803482056 +[2025-04-29 10:14:16,815][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 10:14:17,374][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch4.pth. +[2025-04-29 10:14:18,290][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 10:14:22,783][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 0.8251672387123108, cross_entropy: 0.8251672387123108 +[2025-04-29 10:14:23,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 0.9467841386795044, cross_entropy: 0.9467841386795044 +[2025-04-29 10:14:26,846][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.7421600818634033, cross_entropy: 1.7421600818634033 +[2025-04-29 10:14:27,747][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 2.887451410293579, cross_entropy: 2.887451410293579 +[2025-04-29 10:14:30,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 2.351569175720215, cross_entropy: 2.351569175720215 +[2025-04-29 10:14:31,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 0.8703755140304565, cross_entropy: 0.8703755140304565 +[2025-04-29 10:14:33,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.8693034648895264, cross_entropy: 2.8693034648895264 +[2025-04-29 10:14:34,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 1.676471471786499, cross_entropy: 1.676471471786499 +[2025-04-29 10:14:37,982][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 1.5339527130126953, cross_entropy: 1.5339527130126953 +[2025-04-29 10:14:38,808][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 2.7524163722991943, cross_entropy: 2.7524163722991943 +[2025-04-29 10:14:41,917][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 0.9174724817276001, cross_entropy: 0.9174724817276001 +[2025-04-29 10:14:42,772][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 2.7916345596313477, cross_entropy: 2.7916345596313477 +[2025-04-29 10:14:45,574][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.5072522163391113, cross_entropy: 2.5072522163391113 +[2025-04-29 10:14:46,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 1.2118208408355713, cross_entropy: 1.2118208408355713 +[2025-04-29 10:14:49,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 1.4084696769714355, cross_entropy: 1.4084696769714355 +[2025-04-29 10:14:51,115][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 1.3805725574493408, cross_entropy: 1.3805725574493408 +[2025-04-29 10:14:53,441][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 1.50543212890625, cross_entropy: 1.50543212890625 +[2025-04-29 10:14:55,503][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 2.8928356170654297, cross_entropy: 2.8928356170654297 +[2025-04-29 10:14:56,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 1.5477405786514282, cross_entropy: 1.5477405786514282 +[2025-04-29 10:14:58,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.466540813446045, cross_entropy: 1.466540813446045 +[2025-04-29 10:15:00,841][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.8940298557281494, cross_entropy: 1.8940298557281494 +[2025-04-29 10:15:03,042][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 2.9433345794677734, cross_entropy: 2.9433345794677734 +[2025-04-29 10:15:04,914][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 2.887399196624756, cross_entropy: 2.887399196624756 +[2025-04-29 10:15:06,116][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 0.9092437028884888, cross_entropy: 0.9092437028884888 +[2025-04-29 10:15:08,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 3.2260146141052246, cross_entropy: 3.2260146141052246 +[2025-04-29 10:15:10,193][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 0.9958193302154541, cross_entropy: 0.9958193302154541 +[2025-04-29 10:15:11,329][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 0.9928386807441711, cross_entropy: 0.9928386807441711 +[2025-04-29 10:15:14,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.5068325996398926, cross_entropy: 1.5068325996398926 +[2025-04-29 10:15:15,075][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.532726764678955, cross_entropy: 2.532726764678955 +[2025-04-29 10:15:17,999][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 0.8689495325088501, cross_entropy: 0.8689495325088501 +[2025-04-29 10:15:18,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.2215840816497803, cross_entropy: 1.2215840816497803 +[2025-04-29 10:15:21,437][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 0.7912312746047974, cross_entropy: 0.7912312746047974 +[2025-04-29 10:15:22,310][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.4071699380874634, cross_entropy: 1.4071699380874634 +[2025-04-29 10:15:24,620][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 1.7111400365829468, cross_entropy: 1.7111400365829468 +[2025-04-29 10:15:26,359][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 2.3662991523742676, cross_entropy: 2.3662991523742676 +[2025-04-29 10:15:29,035][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.5844725370407104, cross_entropy: 1.5844725370407104 +[2025-04-29 10:15:30,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 2.9371891021728516, cross_entropy: 2.9371891021728516 +[2025-04-29 10:15:32,368][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 2.68341326713562, cross_entropy: 2.68341326713562 +[2025-04-29 10:15:33,750][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 2.3637795448303223, cross_entropy: 2.3637795448303223 +[2025-04-29 10:15:37,459][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.150911808013916, cross_entropy: 1.150911808013916 +[2025-04-29 10:15:38,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 1.716901183128357, cross_entropy: 1.716901183128357 +[2025-04-29 10:15:41,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.1508296728134155, cross_entropy: 1.1508296728134155 +[2025-04-29 10:15:42,774][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.413394808769226, cross_entropy: 1.413394808769226 +[2025-04-29 10:15:45,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 2.759939670562744, cross_entropy: 2.759939670562744 +[2025-04-29 10:15:46,347][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 2.595522165298462, cross_entropy: 2.595522165298462 +[2025-04-29 10:15:49,566][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.0205386877059937, cross_entropy: 1.0205386877059937 +[2025-04-29 10:15:50,409][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.2096225023269653, cross_entropy: 1.2096225023269653 +[2025-04-29 10:15:52,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.2024643421173096, cross_entropy: 1.2024643421173096 +[2025-04-29 10:15:53,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.156930923461914, cross_entropy: 2.156930923461914 +[2025-04-29 10:15:56,759][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.0534418821334839, cross_entropy: 1.0534418821334839 +[2025-04-29 10:15:57,616][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 1.1920620203018188, cross_entropy: 1.1920620203018188 +[2025-04-29 10:15:59,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 2.9905874729156494, cross_entropy: 2.9905874729156494 +[2025-04-29 10:16:00,735][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 3.01590633392334, cross_entropy: 3.01590633392334 +[2025-04-29 10:16:03,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.842271327972412, cross_entropy: 2.842271327972412 +[2025-04-29 10:16:03,970][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.625478744506836, cross_entropy: 2.625478744506836 +[2025-04-29 10:16:06,355][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.5498039722442627, cross_entropy: 2.5498039722442627 +[2025-04-29 10:16:07,220][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 1.922454833984375, cross_entropy: 1.922454833984375 +[2025-04-29 10:16:10,105][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.1399216651916504, cross_entropy: 2.1399216651916504 +[2025-04-29 10:16:10,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 2.908665657043457, cross_entropy: 2.908665657043457 +[2025-04-29 10:16:13,075][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 3.012148857116699, cross_entropy: 3.012148857116699 +[2025-04-29 10:16:13,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 2.564070701599121, cross_entropy: 2.564070701599121 +[2025-04-29 10:16:16,771][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 0.9945623874664307, cross_entropy: 0.9945623874664307 +[2025-04-29 10:16:17,627][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 2.9308948516845703, cross_entropy: 2.9308948516845703 +[2025-04-29 10:16:20,011][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.413162112236023, cross_entropy: 1.413162112236023 +[2025-04-29 10:16:20,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.82839298248291, cross_entropy: 2.82839298248291 +[2025-04-29 10:16:22,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 1.0501275062561035, cross_entropy: 1.0501275062561035 +[2025-04-29 10:16:24,154][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 2.6271185874938965, cross_entropy: 2.6271185874938965 +[2025-04-29 10:16:26,878][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 0.9939712285995483, cross_entropy: 0.9939712285995483 +[2025-04-29 10:16:27,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 3.146904706954956, cross_entropy: 3.146904706954956 +[2025-04-29 10:16:30,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 0.9659084677696228, cross_entropy: 0.9659084677696228 +[2025-04-29 10:16:31,554][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 1.6247997283935547, cross_entropy: 1.6247997283935547 +[2025-04-29 10:16:34,459][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 1.589776873588562, cross_entropy: 1.589776873588562 +[2025-04-29 10:16:35,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.210517168045044, cross_entropy: 1.210517168045044 +[2025-04-29 10:16:38,620][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 1.8418294191360474, cross_entropy: 1.8418294191360474 +[2025-04-29 10:16:39,474][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.4125418663024902, cross_entropy: 2.4125418663024902 +[2025-04-29 10:16:41,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 1.2593168020248413, cross_entropy: 1.2593168020248413 +[2025-04-29 10:16:42,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.095787525177002, cross_entropy: 1.095787525177002 +[2025-04-29 10:16:44,290][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 2.194143533706665, cross_entropy: 2.194143533706665 +[2025-04-29 10:16:46,016][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.304295539855957, cross_entropy: 1.304295539855957 +[2025-04-29 10:16:48,104][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.133013367652893, cross_entropy: 1.133013367652893 +[2025-04-29 10:16:49,971][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 1.3782248497009277, cross_entropy: 1.3782248497009277 +[2025-04-29 10:16:52,351][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.9546475410461426, cross_entropy: 2.9546475410461426 +[2025-04-29 10:16:53,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.870511293411255, cross_entropy: 2.870511293411255 +[2025-04-29 10:16:55,984][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 1.1124591827392578, cross_entropy: 1.1124591827392578 +[2025-04-29 10:16:56,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.971813678741455, cross_entropy: 2.971813678741455 +[2025-04-29 10:16:59,361][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 0.8970144987106323, cross_entropy: 0.8970144987106323 +[2025-04-29 10:17:00,304][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.816728115081787, cross_entropy: 2.816728115081787 +[2025-04-29 10:17:03,287][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.0981000661849976, cross_entropy: 1.0981000661849976 +[2025-04-29 10:17:04,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.3433195352554321, cross_entropy: 1.3433195352554321 +[2025-04-29 10:17:06,298][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.8718976974487305, cross_entropy: 1.8718976974487305 +[2025-04-29 10:17:08,076][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 1.9239132404327393, cross_entropy: 1.9239132404327393 +[2025-04-29 10:17:09,445][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.180030345916748, cross_entropy: 3.180030345916748 +[2025-04-29 10:17:11,445][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.6762185096740723, cross_entropy: 2.6762185096740723 +[2025-04-29 10:17:12,850][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 1.1994891166687012, cross_entropy: 1.1994891166687012 +[2025-04-29 10:17:15,325][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 2.7526512145996094, cross_entropy: 2.7526512145996094 +[2025-04-29 10:17:16,206][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.1082327365875244, cross_entropy: 1.1082327365875244 +[2025-04-29 10:17:18,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.3988900184631348, cross_entropy: 2.3988900184631348 +[2025-04-29 10:17:19,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 1.657564401626587, cross_entropy: 1.657564401626587 +[2025-04-29 10:17:22,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 1.1294035911560059, cross_entropy: 1.1294035911560059 +[2025-04-29 10:17:23,135][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.2819732427597046, cross_entropy: 1.2819732427597046 +[2025-04-29 10:17:25,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.987356662750244, cross_entropy: 2.987356662750244 +[2025-04-29 10:17:27,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.698953151702881, cross_entropy: 2.698953151702881 +[2025-04-29 10:17:28,967][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.415795922279358, cross_entropy: 1.415795922279358 +[2025-04-29 10:17:30,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.196234703063965, cross_entropy: 2.196234703063965 +[2025-04-29 10:17:32,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 1.7414724826812744, cross_entropy: 1.7414724826812744 +[2025-04-29 10:17:35,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 2.3918120861053467, cross_entropy: 2.3918120861053467 +[2025-04-29 10:17:36,213][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 1.6287353038787842, cross_entropy: 1.6287353038787842 +[2025-04-29 10:17:38,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 0.8792411088943481, cross_entropy: 0.8792411088943481 +[2025-04-29 10:17:39,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.1967930793762207, cross_entropy: 1.1967930793762207 +[2025-04-29 10:17:41,645][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.665590763092041, cross_entropy: 1.665590763092041 +[2025-04-29 10:17:42,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 2.3656716346740723, cross_entropy: 2.3656716346740723 +[2025-04-29 10:17:45,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 0.7446272373199463, cross_entropy: 0.7446272373199463 +[2025-04-29 10:17:47,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 0.9283459186553955, cross_entropy: 0.9283459186553955 +[2025-04-29 10:17:49,478][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 2.604562759399414, cross_entropy: 2.604562759399414 +[2025-04-29 10:17:50,367][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.0837626457214355, cross_entropy: 1.0837626457214355 +[2025-04-29 10:17:52,973][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 0.7978786826133728, cross_entropy: 0.7978786826133728 +[2025-04-29 10:17:53,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 2.362833023071289, cross_entropy: 2.362833023071289 +[2025-04-29 10:17:56,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.6710370779037476, cross_entropy: 1.6710370779037476 +[2025-04-29 10:17:57,368][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 0.9000391364097595, cross_entropy: 0.9000391364097595 +[2025-04-29 10:18:00,310][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.013998031616211, cross_entropy: 2.013998031616211 +[2025-04-29 10:18:01,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 0.9381139278411865, cross_entropy: 0.9381139278411865 +[2025-04-29 10:18:02,809][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 2.11722731590271, cross_entropy: 2.11722731590271 +[2025-04-29 10:18:03,635][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 1.2627307176589966, cross_entropy: 1.2627307176589966 +[2025-04-29 10:18:05,935][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.5387158393859863, cross_entropy: 2.5387158393859863 +[2025-04-29 10:18:06,868][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 1.427544355392456, cross_entropy: 1.427544355392456 +[2025-04-29 10:18:09,561][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 1.0370936393737793, cross_entropy: 1.0370936393737793 +[2025-04-29 10:18:11,124][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.1612110137939453, cross_entropy: 1.1612110137939453 +[2025-04-29 10:18:13,518][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 2.97467041015625, cross_entropy: 2.97467041015625 +[2025-04-29 10:18:14,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.3710739612579346, cross_entropy: 1.3710739612579346 +[2025-04-29 10:18:17,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 1.4609096050262451, cross_entropy: 1.4609096050262451 +[2025-04-29 10:18:18,576][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.6712539196014404, cross_entropy: 1.6712539196014404 +[2025-04-29 10:18:20,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 2.1635961532592773, cross_entropy: 2.1635961532592773 +[2025-04-29 10:18:21,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 1.3425630331039429, cross_entropy: 1.3425630331039429 +[2025-04-29 10:18:24,628][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.5663869380950928, cross_entropy: 2.5663869380950928 +[2025-04-29 10:18:25,482][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 2.7562642097473145, cross_entropy: 2.7562642097473145 +[2025-04-29 10:18:28,771][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 3.1185784339904785, cross_entropy: 3.1185784339904785 +[2025-04-29 10:18:29,592][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 1.7582143545150757, cross_entropy: 1.7582143545150757 +[2025-04-29 10:18:32,993][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 2.8650622367858887, cross_entropy: 2.8650622367858887 +[2025-04-29 10:18:33,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 2.0836293697357178, cross_entropy: 2.0836293697357178 +[2025-04-29 10:18:36,349][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 1.8575232028961182, cross_entropy: 1.8575232028961182 +[2025-04-29 10:18:37,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.6513304710388184, cross_entropy: 1.6513304710388184 +[2025-04-29 10:18:40,040][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 1.7823007106781006, cross_entropy: 1.7823007106781006 +[2025-04-29 10:18:40,895][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 2.6756324768066406, cross_entropy: 2.6756324768066406 +[2025-04-29 10:18:43,382][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.4204213619232178, cross_entropy: 1.4204213619232178 +[2025-04-29 10:18:44,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.2678329944610596, cross_entropy: 1.2678329944610596 +[2025-04-29 10:18:46,728][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 1.1747078895568848, cross_entropy: 1.1747078895568848 +[2025-04-29 10:18:47,584][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 1.5615718364715576, cross_entropy: 1.5615718364715576 +[2025-04-29 10:18:50,269][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.801661968231201, cross_entropy: 2.801661968231201 +[2025-04-29 10:18:51,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.2416391372680664, cross_entropy: 1.2416391372680664 +[2025-04-29 10:18:53,852][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.0346461534500122, cross_entropy: 1.0346461534500122 +[2025-04-29 10:18:55,091][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 1.1825778484344482, cross_entropy: 1.1825778484344482 +[2025-04-29 10:18:57,226][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 2.7597174644470215, cross_entropy: 2.7597174644470215 +[2025-04-29 10:18:58,043][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.2299039363861084, cross_entropy: 1.2299039363861084 +[2025-04-29 10:19:00,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 3.1297566890716553, cross_entropy: 3.1297566890716553 +[2025-04-29 10:19:01,066][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 1.7767329216003418, cross_entropy: 1.7767329216003418 +[2025-04-29 10:19:03,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 3.07633113861084, cross_entropy: 3.07633113861084 +[2025-04-29 10:19:04,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 0.6585434675216675, cross_entropy: 0.6585434675216675 +[2025-04-29 10:19:07,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 2.2914180755615234, cross_entropy: 2.2914180755615234 +[2025-04-29 10:19:08,213][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.0264294147491455, cross_entropy: 1.0264294147491455 +[2025-04-29 10:19:10,961][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 1.2239634990692139, cross_entropy: 1.2239634990692139 +[2025-04-29 10:19:11,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 1.7820048332214355, cross_entropy: 1.7820048332214355 +[2025-04-29 10:19:14,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.3024427890777588, cross_entropy: 1.3024427890777588 +[2025-04-29 10:19:15,675][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 1.97925865650177, cross_entropy: 1.97925865650177 +[2025-04-29 10:19:18,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 2.778447389602661, cross_entropy: 2.778447389602661 +[2025-04-29 10:19:19,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 2.419635772705078, cross_entropy: 2.419635772705078 +[2025-04-29 10:19:22,082][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 1.08610999584198, cross_entropy: 1.08610999584198 +[2025-04-29 10:19:22,942][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 0.8630884885787964, cross_entropy: 0.8630884885787964 +[2025-04-29 10:19:25,993][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 2.4672293663024902, cross_entropy: 2.4672293663024902 +[2025-04-29 10:19:26,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.170107126235962, cross_entropy: 1.170107126235962 +[2025-04-29 10:19:29,804][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 1.372506856918335, cross_entropy: 1.372506856918335 +[2025-04-29 10:19:30,662][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.2905969619750977, cross_entropy: 1.2905969619750977 +[2025-04-29 10:19:32,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 2.9877371788024902, cross_entropy: 2.9877371788024902 +[2025-04-29 10:19:33,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 1.296079397201538, cross_entropy: 1.296079397201538 +[2025-04-29 10:19:35,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 1.692674160003662, cross_entropy: 1.692674160003662 +[2025-04-29 10:19:36,674][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 2.947390079498291, cross_entropy: 2.947390079498291 +[2025-04-29 10:19:39,373][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.3751263618469238, cross_entropy: 1.3751263618469238 +[2025-04-29 10:19:40,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.3270480632781982, cross_entropy: 2.3270480632781982 +[2025-04-29 10:19:43,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 2.5692405700683594, cross_entropy: 2.5692405700683594 +[2025-04-29 10:19:44,441][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.0161945819854736, cross_entropy: 1.0161945819854736 +[2025-04-29 10:19:46,814][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 2.0950608253479004, cross_entropy: 2.0950608253479004 +[2025-04-29 10:19:48,480][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 1.0737519264221191, cross_entropy: 1.0737519264221191 +[2025-04-29 10:19:50,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 1.388010859489441, cross_entropy: 1.388010859489441 +[2025-04-29 10:19:51,183][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 1.4235360622406006, cross_entropy: 1.4235360622406006 +[2025-04-29 10:19:55,152][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.3111515045166016, cross_entropy: 2.3111515045166016 +[2025-04-29 10:19:56,011][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.2183375358581543, cross_entropy: 2.2183375358581543 +[2025-04-29 10:19:59,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 1.0176680088043213, cross_entropy: 1.0176680088043213 +[2025-04-29 10:19:59,989][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.658291816711426, cross_entropy: 2.658291816711426 +[2025-04-29 10:20:03,449][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.397894859313965, cross_entropy: 2.397894859313965 +[2025-04-29 10:20:04,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.667011260986328, cross_entropy: 2.667011260986328 +[2025-04-29 10:20:06,998][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 3.0731701850891113, cross_entropy: 3.0731701850891113 +[2025-04-29 10:20:07,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.2435802221298218, cross_entropy: 1.2435802221298218 +[2025-04-29 10:20:10,294][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 1.9930225610733032, cross_entropy: 1.9930225610733032 +[2025-04-29 10:20:11,123][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.392285704612732, cross_entropy: 1.392285704612732 +[2025-04-29 10:20:14,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.5597774982452393, cross_entropy: 2.5597774982452393 +[2025-04-29 10:20:15,141][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.2761518955230713, cross_entropy: 2.2761518955230713 +[2025-04-29 10:20:18,382][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 1.1923969984054565, cross_entropy: 1.1923969984054565 +[2025-04-29 10:20:19,241][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.092293381690979, cross_entropy: 1.092293381690979 +[2025-04-29 10:20:22,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.3800525665283203, cross_entropy: 1.3800525665283203 +[2025-04-29 10:20:23,142][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 0.9698425531387329, cross_entropy: 0.9698425531387329 +[2025-04-29 10:20:25,173][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.492809534072876, cross_entropy: 2.492809534072876 +[2025-04-29 10:20:25,991][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.4001522064208984, cross_entropy: 1.4001522064208984 +[2025-04-29 10:20:29,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 2.8232808113098145, cross_entropy: 2.8232808113098145 +[2025-04-29 10:20:30,239][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 1.3647830486297607, cross_entropy: 1.3647830486297607 +[2025-04-29 10:20:33,077][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 2.630967855453491, cross_entropy: 2.630967855453491 +[2025-04-29 10:20:33,899][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.446624517440796, cross_entropy: 2.446624517440796 +[2025-04-29 10:20:36,891][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.1799147129058838, cross_entropy: 1.1799147129058838 +[2025-04-29 10:20:37,747][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.558868408203125, cross_entropy: 1.558868408203125 +[2025-04-29 10:20:41,272][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.0667535066604614, cross_entropy: 1.0667535066604614 +[2025-04-29 10:20:42,105][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.1617823839187622, cross_entropy: 1.1617823839187622 +[2025-04-29 10:20:45,236][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 1.3303570747375488, cross_entropy: 1.3303570747375488 +[2025-04-29 10:20:46,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 0.9884399175643921, cross_entropy: 0.9884399175643921 +[2025-04-29 10:20:48,403][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.5835044384002686, cross_entropy: 2.5835044384002686 +[2025-04-29 10:20:49,220][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 1.7552471160888672, cross_entropy: 1.7552471160888672 +[2025-04-29 10:20:51,851][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 2.6105265617370605, cross_entropy: 2.6105265617370605 +[2025-04-29 10:20:52,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 1.1946874856948853, cross_entropy: 1.1946874856948853 +[2025-04-29 10:20:54,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.2394325733184814, cross_entropy: 1.2394325733184814 +[2025-04-29 10:20:55,707][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.5999436378479004, cross_entropy: 2.5999436378479004 +[2025-04-29 10:20:57,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 0.8520075678825378, cross_entropy: 0.8520075678825378 +[2025-04-29 10:20:58,711][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 1.8503637313842773, cross_entropy: 1.8503637313842773 +[2025-04-29 10:21:00,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 1.139745831489563, cross_entropy: 1.139745831489563 +[2025-04-29 10:21:01,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.2103240489959717, cross_entropy: 1.2103240489959717 +[2025-04-29 10:21:04,245][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 1.896522045135498, cross_entropy: 1.896522045135498 +[2025-04-29 10:21:05,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 1.1831027269363403, cross_entropy: 1.1831027269363403 +[2025-04-29 10:21:09,242][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 0.834722638130188, cross_entropy: 0.834722638130188 +[2025-04-29 10:21:10,109][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 0.9760245680809021, cross_entropy: 0.9760245680809021 +[2025-04-29 10:21:13,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 2.8463385105133057, cross_entropy: 2.8463385105133057 +[2025-04-29 10:21:13,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.5135873556137085, cross_entropy: 1.5135873556137085 +[2025-04-29 10:21:16,160][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 0.8831623792648315, cross_entropy: 0.8831623792648315 +[2025-04-29 10:21:16,981][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 2.6890227794647217, cross_entropy: 2.6890227794647217 +[2025-04-29 10:21:20,569][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 1.4438115358352661, cross_entropy: 1.4438115358352661 +[2025-04-29 10:21:21,390][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 2.489691734313965, cross_entropy: 2.489691734313965 +[2025-04-29 10:21:24,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.0482614040374756, cross_entropy: 1.0482614040374756 +[2025-04-29 10:21:25,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.7275915145874023, cross_entropy: 2.7275915145874023 +[2025-04-29 10:21:27,422][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.0809245109558105, cross_entropy: 2.0809245109558105 +[2025-04-29 10:21:28,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.9008326530456543, cross_entropy: 2.9008326530456543 +[2025-04-29 10:21:30,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 0.8691974878311157, cross_entropy: 0.8691974878311157 +[2025-04-29 10:21:31,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 2.3412609100341797, cross_entropy: 2.3412609100341797 +[2025-04-29 10:21:34,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 1.8485735654830933, cross_entropy: 1.8485735654830933 +[2025-04-29 10:21:35,016][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.4947113990783691, cross_entropy: 1.4947113990783691 +[2025-04-29 10:21:37,406][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.1984400749206543, cross_entropy: 1.1984400749206543 +[2025-04-29 10:21:38,266][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.0765633583068848, cross_entropy: 2.0765633583068848 +[2025-04-29 10:21:41,719][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.2893505096435547, cross_entropy: 1.2893505096435547 +[2025-04-29 10:21:42,538][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.8047380447387695, cross_entropy: 2.8047380447387695 +[2025-04-29 10:21:45,593][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 2.982246160507202, cross_entropy: 2.982246160507202 +[2025-04-29 10:21:46,418][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 1.0074905157089233, cross_entropy: 1.0074905157089233 +[2025-04-29 10:21:49,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 0.9691398739814758, cross_entropy: 0.9691398739814758 +[2025-04-29 10:21:50,168][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 2.3700366020202637, cross_entropy: 2.3700366020202637 +[2025-04-29 10:21:53,124][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 2.42490816116333, cross_entropy: 2.42490816116333 +[2025-04-29 10:21:53,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 1.263875961303711, cross_entropy: 1.263875961303711 +[2025-04-29 10:21:56,863][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 2.311051845550537, cross_entropy: 2.311051845550537 +[2025-04-29 10:21:57,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.061493158340454, cross_entropy: 2.061493158340454 +[2025-04-29 10:22:00,754][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 2.3719370365142822, cross_entropy: 2.3719370365142822 +[2025-04-29 10:22:01,621][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 0.925891101360321, cross_entropy: 0.925891101360321 +[2025-04-29 10:22:04,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 1.692380666732788, cross_entropy: 1.692380666732788 +[2025-04-29 10:22:05,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.6123483180999756, cross_entropy: 2.6123483180999756 +[2025-04-29 10:22:07,587][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 0.9887921214103699, cross_entropy: 0.9887921214103699 +[2025-04-29 10:22:08,437][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.4735872745513916, cross_entropy: 1.4735872745513916 +[2025-04-29 10:22:10,967][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.6225335597991943, cross_entropy: 1.6225335597991943 +[2025-04-29 10:22:11,801][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 2.232611656188965, cross_entropy: 2.232611656188965 +[2025-04-29 10:22:14,306][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.6747815608978271, cross_entropy: 1.6747815608978271 +[2025-04-29 10:22:15,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 0.7831584811210632, cross_entropy: 0.7831584811210632 +[2025-04-29 10:22:17,693][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.9383587837219238, cross_entropy: 1.9383587837219238 +[2025-04-29 10:22:18,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 2.0812411308288574, cross_entropy: 2.0812411308288574 +[2025-04-29 10:22:20,602][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 0.8360788226127625, cross_entropy: 0.8360788226127625 +[2025-04-29 10:22:21,425][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 1.8711055517196655, cross_entropy: 1.8711055517196655 +[2025-04-29 10:22:24,346][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.722470998764038, cross_entropy: 2.722470998764038 +[2025-04-29 10:22:25,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.5227267742156982, cross_entropy: 2.5227267742156982 +[2025-04-29 10:22:28,034][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 2.899346351623535, cross_entropy: 2.899346351623535 +[2025-04-29 10:22:28,937][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.7106800079345703, cross_entropy: 2.7106800079345703 +[2025-04-29 10:22:31,147][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.9844143390655518, cross_entropy: 1.9844143390655518 +[2025-04-29 10:22:32,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 2.933032512664795, cross_entropy: 2.933032512664795 +[2025-04-29 10:22:33,925][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.4434349536895752, cross_entropy: 1.4434349536895752 +[2025-04-29 10:22:34,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 1.3789598941802979, cross_entropy: 1.3789598941802979 +[2025-04-29 10:22:37,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 0.8398267030715942, cross_entropy: 0.8398267030715942 +[2025-04-29 10:22:38,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 1.5552520751953125, cross_entropy: 1.5552520751953125 +[2025-04-29 10:22:40,901][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.9169501066207886, cross_entropy: 1.9169501066207886 +[2025-04-29 10:22:42,015][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 1.0788096189498901, cross_entropy: 1.0788096189498901 +[2025-04-29 10:22:43,998][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 1.3608241081237793, cross_entropy: 1.3608241081237793 +[2025-04-29 10:22:45,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.348973274230957, cross_entropy: 1.348973274230957 +[2025-04-29 10:22:47,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.072403907775879, cross_entropy: 1.072403907775879 +[2025-04-29 10:22:48,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 3.1576437950134277, cross_entropy: 3.1576437950134277 +[2025-04-29 10:22:50,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 1.2286078929901123, cross_entropy: 1.2286078929901123 +[2025-04-29 10:22:52,369][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.7918751239776611, cross_entropy: 1.7918751239776611 +[2025-04-29 10:22:54,318][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 2.6161091327667236, cross_entropy: 2.6161091327667236 +[2025-04-29 10:22:55,819][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 1.3476295471191406, cross_entropy: 1.3476295471191406 +[2025-04-29 10:22:57,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 1.088024377822876, cross_entropy: 1.088024377822876 +[2025-04-29 10:22:59,881][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 1.627500057220459, cross_entropy: 1.627500057220459 +[2025-04-29 10:23:00,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 1.5842607021331787, cross_entropy: 1.5842607021331787 +[2025-04-29 10:23:04,183][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 2.780820369720459, cross_entropy: 2.780820369720459 +[2025-04-29 10:23:05,028][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.6032817363739014, cross_entropy: 2.6032817363739014 +[2025-04-29 10:23:07,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 2.323589324951172, cross_entropy: 2.323589324951172 +[2025-04-29 10:23:08,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.5673965215682983, cross_entropy: 1.5673965215682983 +[2025-04-29 10:23:10,751][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 2.282968044281006, cross_entropy: 2.282968044281006 +[2025-04-29 10:23:11,573][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.8967970609664917, cross_entropy: 1.8967970609664917 +[2025-04-29 10:23:14,094][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 2.976534128189087, cross_entropy: 2.976534128189087 +[2025-04-29 10:23:14,962][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.1163341999053955, cross_entropy: 1.1163341999053955 +[2025-04-29 10:23:17,605][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.0579509735107422, cross_entropy: 1.0579509735107422 +[2025-04-29 10:23:18,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.3083237409591675, cross_entropy: 1.3083237409591675 +[2025-04-29 10:23:20,844][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 0.8011109828948975, cross_entropy: 0.8011109828948975 +[2025-04-29 10:23:21,706][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.7989511489868164, cross_entropy: 2.7989511489868164 +[2025-04-29 10:23:24,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 1.4316253662109375, cross_entropy: 1.4316253662109375 +[2025-04-29 10:23:25,508][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 1.9661569595336914, cross_entropy: 1.9661569595336914 +[2025-04-29 10:23:27,592][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 2.4802842140197754, cross_entropy: 2.4802842140197754 +[2025-04-29 10:23:28,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 2.3168675899505615, cross_entropy: 2.3168675899505615 +[2025-04-29 10:23:31,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.626042366027832, cross_entropy: 2.626042366027832 +[2025-04-29 10:23:32,456][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 2.705894708633423, cross_entropy: 2.705894708633423 +[2025-04-29 10:23:34,506][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.0878615379333496, cross_entropy: 1.0878615379333496 +[2025-04-29 10:23:36,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.0976123809814453, cross_entropy: 1.0976123809814453 +[2025-04-29 10:23:37,996][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 2.76423978805542, cross_entropy: 2.76423978805542 +[2025-04-29 10:23:39,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 1.848860263824463, cross_entropy: 1.848860263824463 +[2025-04-29 10:23:42,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.2734307050704956, cross_entropy: 1.2734307050704956 +[2025-04-29 10:23:42,957][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.426248550415039, cross_entropy: 2.426248550415039 +[2025-04-29 10:23:45,446][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 0.7158793210983276, cross_entropy: 0.7158793210983276 +[2025-04-29 10:23:46,297][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.8308813571929932, cross_entropy: 1.8308813571929932 +[2025-04-29 10:23:51,477][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.2587063312530518, cross_entropy: 1.2587063312530518 +[2025-04-29 10:23:52,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 1.829009771347046, cross_entropy: 1.829009771347046 +[2025-04-29 10:23:54,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 1.3796722888946533, cross_entropy: 1.3796722888946533 +[2025-04-29 10:23:54,911][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.7464033365249634, cross_entropy: 1.7464033365249634 +[2025-04-29 10:23:57,487][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 0.94329434633255, cross_entropy: 0.94329434633255 +[2025-04-29 10:23:58,335][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.1814208030700684, cross_entropy: 2.1814208030700684 +[2025-04-29 10:24:00,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.5373561382293701, cross_entropy: 1.5373561382293701 +[2025-04-29 10:24:01,426][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.2303109169006348, cross_entropy: 1.2303109169006348 +[2025-04-29 10:24:05,038][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 2.970046281814575, cross_entropy: 2.970046281814575 +[2025-04-29 10:24:05,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 1.3777843713760376, cross_entropy: 1.3777843713760376 +[2025-04-29 10:24:08,012][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.2079541683197021, cross_entropy: 1.2079541683197021 +[2025-04-29 10:24:08,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.582754611968994, cross_entropy: 2.582754611968994 +[2025-04-29 10:24:11,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 2.7869296073913574, cross_entropy: 2.7869296073913574 +[2025-04-29 10:24:12,557][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 0.8673154711723328, cross_entropy: 0.8673154711723328 +[2025-04-29 10:24:14,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 2.2667198181152344, cross_entropy: 2.2667198181152344 +[2025-04-29 10:24:15,379][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 1.306290626525879, cross_entropy: 1.306290626525879 +[2025-04-29 10:24:17,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.7868363857269287, cross_entropy: 2.7868363857269287 +[2025-04-29 10:24:18,651][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.2146034240722656, cross_entropy: 2.2146034240722656 +[2025-04-29 10:24:20,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.84042489528656, cross_entropy: 1.84042489528656 +[2025-04-29 10:24:21,579][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 1.335623025894165, cross_entropy: 1.335623025894165 +[2025-04-29 10:24:23,985][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 0.9979758858680725, cross_entropy: 0.9979758858680725 +[2025-04-29 10:24:24,841][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 1.9429137706756592, cross_entropy: 1.9429137706756592 +[2025-04-29 10:24:27,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 0.956486165523529, cross_entropy: 0.956486165523529 +[2025-04-29 10:24:28,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.213064432144165, cross_entropy: 2.213064432144165 +[2025-04-29 10:24:31,325][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 1.2888761758804321, cross_entropy: 1.2888761758804321 +[2025-04-29 10:24:32,158][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 2.511246919631958, cross_entropy: 2.511246919631958 +[2025-04-29 10:24:35,573][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 1.1239936351776123, cross_entropy: 1.1239936351776123 +[2025-04-29 10:24:36,432][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 2.066924571990967, cross_entropy: 2.066924571990967 +[2025-04-29 10:24:39,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 1.2871360778808594, cross_entropy: 1.2871360778808594 +[2025-04-29 10:24:40,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 3.358086585998535, cross_entropy: 3.358086585998535 +[2025-04-29 10:24:42,977][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.227036952972412, cross_entropy: 2.227036952972412 +[2025-04-29 10:24:43,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.799668550491333, cross_entropy: 1.799668550491333 +[2025-04-29 10:24:46,419][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 2.255553960800171, cross_entropy: 2.255553960800171 +[2025-04-29 10:24:47,241][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 1.670976161956787, cross_entropy: 1.670976161956787 +[2025-04-29 10:24:49,894][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 0.9935948252677917, cross_entropy: 0.9935948252677917 +[2025-04-29 10:24:50,756][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.008425235748291, cross_entropy: 1.008425235748291 +[2025-04-29 10:24:53,498][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 1.415604591369629, cross_entropy: 1.415604591369629 +[2025-04-29 10:24:54,323][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.9199721813201904, cross_entropy: 1.9199721813201904 +[2025-04-29 10:24:57,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.481065273284912, cross_entropy: 1.481065273284912 +[2025-04-29 10:24:57,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 1.3928275108337402, cross_entropy: 1.3928275108337402 +[2025-04-29 10:24:59,670][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 1.3754463195800781, cross_entropy: 1.3754463195800781 +[2025-04-29 10:25:00,414][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.372501015663147, cross_entropy: 1.372501015663147 +[2025-04-29 10:27:43,779][BaseTrainer][INFO] - [Epoch 5/10] (train) 1.8180333375930786, cross_entropy: 1.8180333375930786 +[2025-04-29 10:27:43,780][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.1160227060317993, cross_entropy: 1.1160227060317993 +[2025-04-29 10:27:44,675][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 10:27:45,227][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch5.pth. +[2025-04-29 10:27:46,106][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 10:27:51,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 3.0260748863220215, cross_entropy: 3.0260748863220215 +[2025-04-29 10:27:52,096][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.6727781295776367, cross_entropy: 1.6727781295776367 +[2025-04-29 10:27:54,884][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 1.5413506031036377, cross_entropy: 1.5413506031036377 +[2025-04-29 10:27:55,786][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 1.3900622129440308, cross_entropy: 1.3900622129440308 +[2025-04-29 10:27:58,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.336581230163574, cross_entropy: 2.336581230163574 +[2025-04-29 10:27:59,373][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 2.9661831855773926, cross_entropy: 2.9661831855773926 +[2025-04-29 10:28:02,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 1.1502268314361572, cross_entropy: 1.1502268314361572 +[2025-04-29 10:28:03,087][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.981811285018921, cross_entropy: 1.981811285018921 +[2025-04-29 10:28:06,707][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.8447198867797852, cross_entropy: 1.8447198867797852 +[2025-04-29 10:28:07,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.490448474884033, cross_entropy: 2.490448474884033 +[2025-04-29 10:28:10,725][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.7363195419311523, cross_entropy: 2.7363195419311523 +[2025-04-29 10:28:11,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 1.2321077585220337, cross_entropy: 1.2321077585220337 +[2025-04-29 10:28:13,946][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 1.8954055309295654, cross_entropy: 1.8954055309295654 +[2025-04-29 10:28:14,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.4075627326965332, cross_entropy: 1.4075627326965332 +[2025-04-29 10:28:17,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 0.9831545352935791, cross_entropy: 0.9831545352935791 +[2025-04-29 10:28:18,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.4768338203430176, cross_entropy: 2.4768338203430176 +[2025-04-29 10:28:20,265][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.0633447170257568, cross_entropy: 1.0633447170257568 +[2025-04-29 10:28:21,206][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 1.354694128036499, cross_entropy: 1.354694128036499 +[2025-04-29 10:28:24,670][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.4152085781097412, cross_entropy: 1.4152085781097412 +[2025-04-29 10:28:25,521][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 1.530733346939087, cross_entropy: 1.530733346939087 +[2025-04-29 10:28:28,058][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 0.7085157036781311, cross_entropy: 0.7085157036781311 +[2025-04-29 10:28:28,933][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 2.9693081378936768, cross_entropy: 2.9693081378936768 +[2025-04-29 10:28:30,638][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 2.8489222526550293, cross_entropy: 2.8489222526550293 +[2025-04-29 10:28:31,769][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 0.5730098485946655, cross_entropy: 0.5730098485946655 +[2025-04-29 10:28:34,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 1.9770842790603638, cross_entropy: 1.9770842790603638 +[2025-04-29 10:28:35,108][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 1.0293405055999756, cross_entropy: 1.0293405055999756 +[2025-04-29 10:28:38,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 2.816394805908203, cross_entropy: 2.816394805908203 +[2025-04-29 10:28:38,907][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.5263075828552246, cross_entropy: 2.5263075828552246 +[2025-04-29 10:28:41,503][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.422363519668579, cross_entropy: 1.422363519668579 +[2025-04-29 10:28:42,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 0.8434455990791321, cross_entropy: 0.8434455990791321 +[2025-04-29 10:28:45,119][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 2.2804114818573, cross_entropy: 2.2804114818573 +[2025-04-29 10:28:46,013][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.5545735359191895, cross_entropy: 2.5545735359191895 +[2025-04-29 10:28:47,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 2.514894962310791, cross_entropy: 2.514894962310791 +[2025-04-29 10:28:48,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 0.9575484395027161, cross_entropy: 0.9575484395027161 +[2025-04-29 10:28:51,063][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.2174856662750244, cross_entropy: 2.2174856662750244 +[2025-04-29 10:28:52,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 0.8129802942276001, cross_entropy: 0.8129802942276001 +[2025-04-29 10:28:54,782][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.8407988548278809, cross_entropy: 1.8407988548278809 +[2025-04-29 10:28:57,401][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 2.745680570602417, cross_entropy: 2.745680570602417 +[2025-04-29 10:28:58,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 1.4692405462265015, cross_entropy: 1.4692405462265015 +[2025-04-29 10:29:01,388][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.0639586448669434, cross_entropy: 1.0639586448669434 +[2025-04-29 10:29:02,238][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 1.8780553340911865, cross_entropy: 1.8780553340911865 +[2025-04-29 10:29:04,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 1.0735139846801758, cross_entropy: 1.0735139846801758 +[2025-04-29 10:29:05,773][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 0.7293724417686462, cross_entropy: 0.7293724417686462 +[2025-04-29 10:29:08,247][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 0.7588515281677246, cross_entropy: 0.7588515281677246 +[2025-04-29 10:29:09,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 0.9726981520652771, cross_entropy: 0.9726981520652771 +[2025-04-29 10:29:12,096][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.1283116340637207, cross_entropy: 2.1283116340637207 +[2025-04-29 10:29:12,978][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 1.0698575973510742, cross_entropy: 1.0698575973510742 +[2025-04-29 10:29:15,991][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 2.6626744270324707, cross_entropy: 2.6626744270324707 +[2025-04-29 10:29:16,811][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.3671081066131592, cross_entropy: 1.3671081066131592 +[2025-04-29 10:29:19,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.3118129968643188, cross_entropy: 1.3118129968643188 +[2025-04-29 10:29:20,214][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 1.7484318017959595, cross_entropy: 1.7484318017959595 +[2025-04-29 10:29:22,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 0.8965689539909363, cross_entropy: 0.8965689539909363 +[2025-04-29 10:29:23,782][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.714923620223999, cross_entropy: 2.714923620223999 +[2025-04-29 10:29:26,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.5668094158172607, cross_entropy: 1.5668094158172607 +[2025-04-29 10:29:27,283][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.7207194566726685, cross_entropy: 1.7207194566726685 +[2025-04-29 10:29:30,354][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 1.0382074117660522, cross_entropy: 1.0382074117660522 +[2025-04-29 10:29:31,212][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 2.410665512084961, cross_entropy: 2.410665512084961 +[2025-04-29 10:29:34,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 0.758634090423584, cross_entropy: 0.758634090423584 +[2025-04-29 10:29:34,939][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.742143154144287, cross_entropy: 2.742143154144287 +[2025-04-29 10:29:37,656][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 0.8279862403869629, cross_entropy: 0.8279862403869629 +[2025-04-29 10:29:38,481][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 0.7580471634864807, cross_entropy: 0.7580471634864807 +[2025-04-29 10:29:41,088][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 1.35453200340271, cross_entropy: 1.35453200340271 +[2025-04-29 10:29:41,947][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.1339750289916992, cross_entropy: 1.1339750289916992 +[2025-04-29 10:29:44,659][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.4396169185638428, cross_entropy: 1.4396169185638428 +[2025-04-29 10:29:45,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.320241928100586, cross_entropy: 2.320241928100586 +[2025-04-29 10:29:47,718][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 0.6428302526473999, cross_entropy: 0.6428302526473999 +[2025-04-29 10:29:48,574][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 2.7422924041748047, cross_entropy: 2.7422924041748047 +[2025-04-29 10:29:51,207][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 0.8468426465988159, cross_entropy: 0.8468426465988159 +[2025-04-29 10:29:52,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 0.8522592186927795, cross_entropy: 0.8522592186927795 +[2025-04-29 10:29:54,793][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 2.3917250633239746, cross_entropy: 2.3917250633239746 +[2025-04-29 10:29:55,650][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 1.9387022256851196, cross_entropy: 1.9387022256851196 +[2025-04-29 10:29:58,295][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.473488688468933, cross_entropy: 1.473488688468933 +[2025-04-29 10:29:59,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 0.7672466039657593, cross_entropy: 0.7672466039657593 +[2025-04-29 10:30:02,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.659074068069458, cross_entropy: 1.659074068069458 +[2025-04-29 10:30:02,957][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 0.8336730003356934, cross_entropy: 0.8336730003356934 +[2025-04-29 10:30:05,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 0.9998659491539001, cross_entropy: 0.9998659491539001 +[2025-04-29 10:30:06,395][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.5087532997131348, cross_entropy: 2.5087532997131348 +[2025-04-29 10:30:08,645][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 1.2737548351287842, cross_entropy: 1.2737548351287842 +[2025-04-29 10:30:09,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.7054858207702637, cross_entropy: 2.7054858207702637 +[2025-04-29 10:30:12,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 2.542710542678833, cross_entropy: 2.542710542678833 +[2025-04-29 10:30:13,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.0960361957550049, cross_entropy: 1.0960361957550049 +[2025-04-29 10:30:15,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 1.230018138885498, cross_entropy: 1.230018138885498 +[2025-04-29 10:30:16,733][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.755998373031616, cross_entropy: 2.755998373031616 +[2025-04-29 10:30:19,477][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 2.656724214553833, cross_entropy: 2.656724214553833 +[2025-04-29 10:30:20,344][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.1139777898788452, cross_entropy: 1.1139777898788452 +[2025-04-29 10:30:22,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.0580034255981445, cross_entropy: 2.0580034255981445 +[2025-04-29 10:30:23,630][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 1.7929637432098389, cross_entropy: 1.7929637432098389 +[2025-04-29 10:30:25,718][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.4897809028625488, cross_entropy: 1.4897809028625488 +[2025-04-29 10:30:27,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 2.6746320724487305, cross_entropy: 2.6746320724487305 +[2025-04-29 10:30:28,924][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 0.7388956546783447, cross_entropy: 0.7388956546783447 +[2025-04-29 10:30:31,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 0.7429263591766357, cross_entropy: 0.7429263591766357 +[2025-04-29 10:30:32,461][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.5132644176483154, cross_entropy: 1.5132644176483154 +[2025-04-29 10:30:35,447][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.2691154479980469, cross_entropy: 1.2691154479980469 +[2025-04-29 10:30:36,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 0.7721555233001709, cross_entropy: 0.7721555233001709 +[2025-04-29 10:30:38,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 0.6727597713470459, cross_entropy: 0.6727597713470459 +[2025-04-29 10:30:39,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.2913291454315186, cross_entropy: 1.2913291454315186 +[2025-04-29 10:30:42,671][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.111443519592285, cross_entropy: 2.111443519592285 +[2025-04-29 10:30:43,955][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.2922165393829346, cross_entropy: 1.2922165393829346 +[2025-04-29 10:30:45,983][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.2938814163208008, cross_entropy: 1.2938814163208008 +[2025-04-29 10:30:47,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.5833317041397095, cross_entropy: 1.5833317041397095 +[2025-04-29 10:30:49,501][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 2.153402805328369, cross_entropy: 2.153402805328369 +[2025-04-29 10:30:50,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.0958781242370605, cross_entropy: 2.0958781242370605 +[2025-04-29 10:30:53,004][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 1.0084505081176758, cross_entropy: 1.0084505081176758 +[2025-04-29 10:30:54,552][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.8867112398147583, cross_entropy: 0.8867112398147583 +[2025-04-29 10:30:57,484][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.4230804443359375, cross_entropy: 1.4230804443359375 +[2025-04-29 10:30:58,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 1.4126403331756592, cross_entropy: 1.4126403331756592 +[2025-04-29 10:31:01,534][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 1.6730763912200928, cross_entropy: 1.6730763912200928 +[2025-04-29 10:31:02,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 2.8786001205444336, cross_entropy: 2.8786001205444336 +[2025-04-29 10:31:04,964][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.043527364730835, cross_entropy: 1.043527364730835 +[2025-04-29 10:31:05,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 2.0631418228149414, cross_entropy: 2.0631418228149414 +[2025-04-29 10:31:08,884][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 2.2608706951141357, cross_entropy: 2.2608706951141357 +[2025-04-29 10:31:09,735][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 2.691831588745117, cross_entropy: 2.691831588745117 +[2025-04-29 10:31:12,001][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.109760284423828, cross_entropy: 2.109760284423828 +[2025-04-29 10:31:12,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.606708288192749, cross_entropy: 1.606708288192749 +[2025-04-29 10:31:15,974][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.396040678024292, cross_entropy: 2.396040678024292 +[2025-04-29 10:31:16,919][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 1.8894562721252441, cross_entropy: 1.8894562721252441 +[2025-04-29 10:31:19,574][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 2.7794904708862305, cross_entropy: 2.7794904708862305 +[2025-04-29 10:31:20,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 1.2013592720031738, cross_entropy: 1.2013592720031738 +[2025-04-29 10:31:23,018][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 0.9649209976196289, cross_entropy: 0.9649209976196289 +[2025-04-29 10:31:23,893][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 2.5270416736602783, cross_entropy: 2.5270416736602783 +[2025-04-29 10:31:26,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.7600412368774414, cross_entropy: 2.7600412368774414 +[2025-04-29 10:31:27,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.2533583641052246, cross_entropy: 1.2533583641052246 +[2025-04-29 10:31:29,421][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 2.8733038902282715, cross_entropy: 2.8733038902282715 +[2025-04-29 10:31:31,462][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 0.8775333166122437, cross_entropy: 0.8775333166122437 +[2025-04-29 10:31:32,936][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.4334368705749512, cross_entropy: 1.4334368705749512 +[2025-04-29 10:31:35,027][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 0.7354072332382202, cross_entropy: 0.7354072332382202 +[2025-04-29 10:31:37,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.9017724990844727, cross_entropy: 1.9017724990844727 +[2025-04-29 10:31:38,850][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 1.0568180084228516, cross_entropy: 1.0568180084228516 +[2025-04-29 10:31:42,131][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 2.6150026321411133, cross_entropy: 2.6150026321411133 +[2025-04-29 10:31:42,997][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 1.0471361875534058, cross_entropy: 1.0471361875534058 +[2025-04-29 10:31:45,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 1.05221426486969, cross_entropy: 1.05221426486969 +[2025-04-29 10:31:46,438][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.7592037916183472, cross_entropy: 1.7592037916183472 +[2025-04-29 10:31:49,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 2.710155487060547, cross_entropy: 2.710155487060547 +[2025-04-29 10:31:50,268][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 1.2503890991210938, cross_entropy: 1.2503890991210938 +[2025-04-29 10:31:53,321][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 1.9214694499969482, cross_entropy: 1.9214694499969482 +[2025-04-29 10:31:54,542][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 2.775275230407715, cross_entropy: 2.775275230407715 +[2025-04-29 10:31:56,211][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 0.818066418170929, cross_entropy: 0.818066418170929 +[2025-04-29 10:31:57,603][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.6888246536254883, cross_entropy: 1.6888246536254883 +[2025-04-29 10:32:00,206][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.0950953960418701, cross_entropy: 1.0950953960418701 +[2025-04-29 10:32:01,174][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.386993885040283, cross_entropy: 2.386993885040283 +[2025-04-29 10:32:03,052][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.1830185651779175, cross_entropy: 1.1830185651779175 +[2025-04-29 10:32:04,628][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 0.806033730506897, cross_entropy: 0.806033730506897 +[2025-04-29 10:32:06,550][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 1.6426467895507812, cross_entropy: 1.6426467895507812 +[2025-04-29 10:32:08,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 1.4682047367095947, cross_entropy: 1.4682047367095947 +[2025-04-29 10:32:09,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 2.9075121879577637, cross_entropy: 2.9075121879577637 +[2025-04-29 10:32:11,313][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 0.8958863019943237, cross_entropy: 0.8958863019943237 +[2025-04-29 10:32:13,277][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 1.465686559677124, cross_entropy: 1.465686559677124 +[2025-04-29 10:32:14,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.96095871925354, cross_entropy: 1.96095871925354 +[2025-04-29 10:32:16,517][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 1.2061941623687744, cross_entropy: 1.2061941623687744 +[2025-04-29 10:32:18,354][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.654346466064453, cross_entropy: 2.654346466064453 +[2025-04-29 10:32:19,811][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.2839319705963135, cross_entropy: 2.2839319705963135 +[2025-04-29 10:32:22,180][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.578148603439331, cross_entropy: 2.578148603439331 +[2025-04-29 10:32:23,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 2.7517573833465576, cross_entropy: 2.7517573833465576 +[2025-04-29 10:32:26,005][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.2095627784729004, cross_entropy: 1.2095627784729004 +[2025-04-29 10:32:27,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 2.906872272491455, cross_entropy: 2.906872272491455 +[2025-04-29 10:32:29,942][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 2.04152512550354, cross_entropy: 2.04152512550354 +[2025-04-29 10:32:30,797][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.609518051147461, cross_entropy: 2.609518051147461 +[2025-04-29 10:32:33,228][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 0.7037211060523987, cross_entropy: 0.7037211060523987 +[2025-04-29 10:32:34,114][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.9532396793365479, cross_entropy: 1.9532396793365479 +[2025-04-29 10:32:36,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 2.6276254653930664, cross_entropy: 2.6276254653930664 +[2025-04-29 10:32:37,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.699228286743164, cross_entropy: 1.699228286743164 +[2025-04-29 10:32:40,674][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 3.02118182182312, cross_entropy: 3.02118182182312 +[2025-04-29 10:32:41,604][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 0.8234219551086426, cross_entropy: 0.8234219551086426 +[2025-04-29 10:32:44,557][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 0.8396985530853271, cross_entropy: 0.8396985530853271 +[2025-04-29 10:32:45,453][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 2.0559892654418945, cross_entropy: 2.0559892654418945 +[2025-04-29 10:32:47,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.530914068222046, cross_entropy: 2.530914068222046 +[2025-04-29 10:32:49,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 0.8650489449501038, cross_entropy: 0.8650489449501038 +[2025-04-29 10:32:50,776][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.5626518726348877, cross_entropy: 1.5626518726348877 +[2025-04-29 10:32:52,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 1.1069798469543457, cross_entropy: 1.1069798469543457 +[2025-04-29 10:32:55,534][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 0.6659442782402039, cross_entropy: 0.6659442782402039 +[2025-04-29 10:32:56,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 1.4939672946929932, cross_entropy: 1.4939672946929932 +[2025-04-29 10:32:59,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.0568852424621582, cross_entropy: 1.0568852424621582 +[2025-04-29 10:33:00,450][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 0.8636877536773682, cross_entropy: 0.8636877536773682 +[2025-04-29 10:33:04,600][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.6657328605651855, cross_entropy: 1.6657328605651855 +[2025-04-29 10:33:05,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 0.4699884057044983, cross_entropy: 0.4699884057044983 +[2025-04-29 10:33:09,243][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 2.1530966758728027, cross_entropy: 2.1530966758728027 +[2025-04-29 10:33:10,066][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.3388181924819946, cross_entropy: 1.3388181924819946 +[2025-04-29 10:33:12,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 0.9975202679634094, cross_entropy: 0.9975202679634094 +[2025-04-29 10:33:13,300][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.270225763320923, cross_entropy: 2.270225763320923 +[2025-04-29 10:33:15,579][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.059704303741455, cross_entropy: 1.059704303741455 +[2025-04-29 10:33:16,438][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 2.149951457977295, cross_entropy: 2.149951457977295 +[2025-04-29 10:33:19,826][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 1.465631365776062, cross_entropy: 1.465631365776062 +[2025-04-29 10:33:20,683][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 0.6710454225540161, cross_entropy: 0.6710454225540161 +[2025-04-29 10:33:24,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.239180564880371, cross_entropy: 2.239180564880371 +[2025-04-29 10:33:24,989][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.2868512868881226, cross_entropy: 1.2868512868881226 +[2025-04-29 10:33:27,822][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.6524264812469482, cross_entropy: 1.6524264812469482 +[2025-04-29 10:33:28,678][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 1.3492825031280518, cross_entropy: 1.3492825031280518 +[2025-04-29 10:33:31,628][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 0.8503108024597168, cross_entropy: 0.8503108024597168 +[2025-04-29 10:33:32,479][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 2.1982600688934326, cross_entropy: 2.1982600688934326 +[2025-04-29 10:33:34,396][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.8954079151153564, cross_entropy: 2.8954079151153564 +[2025-04-29 10:33:35,216][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 2.5113768577575684, cross_entropy: 2.5113768577575684 +[2025-04-29 10:33:37,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.5616190433502197, cross_entropy: 2.5616190433502197 +[2025-04-29 10:33:38,696][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 0.7181575298309326, cross_entropy: 0.7181575298309326 +[2025-04-29 10:33:41,397][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 1.1486821174621582, cross_entropy: 1.1486821174621582 +[2025-04-29 10:33:42,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.096606969833374, cross_entropy: 1.096606969833374 +[2025-04-29 10:33:44,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 2.479492425918579, cross_entropy: 2.479492425918579 +[2025-04-29 10:33:45,558][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 3.0299582481384277, cross_entropy: 3.0299582481384277 +[2025-04-29 10:33:47,950][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 1.2232990264892578, cross_entropy: 1.2232990264892578 +[2025-04-29 10:33:48,811][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 2.7832889556884766, cross_entropy: 2.7832889556884766 +[2025-04-29 10:33:51,952][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.2112317085266113, cross_entropy: 1.2112317085266113 +[2025-04-29 10:33:52,821][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 0.4755682349205017, cross_entropy: 0.4755682349205017 +[2025-04-29 10:33:54,857][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 0.6133228540420532, cross_entropy: 0.6133228540420532 +[2025-04-29 10:33:55,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 0.6354568004608154, cross_entropy: 0.6354568004608154 +[2025-04-29 10:33:57,880][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 2.2241129875183105, cross_entropy: 2.2241129875183105 +[2025-04-29 10:33:58,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 0.645774245262146, cross_entropy: 0.645774245262146 +[2025-04-29 10:34:01,601][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 0.9878819584846497, cross_entropy: 0.9878819584846497 +[2025-04-29 10:34:02,433][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 0.7529491186141968, cross_entropy: 0.7529491186141968 +[2025-04-29 10:34:04,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 0.6300827264785767, cross_entropy: 0.6300827264785767 +[2025-04-29 10:34:05,855][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 1.1682755947113037, cross_entropy: 1.1682755947113037 +[2025-04-29 10:34:07,802][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 2.6136200428009033, cross_entropy: 2.6136200428009033 +[2025-04-29 10:34:09,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 2.4261183738708496, cross_entropy: 2.4261183738708496 +[2025-04-29 10:34:10,889][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 2.9783551692962646, cross_entropy: 2.9783551692962646 +[2025-04-29 10:34:13,486][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 1.0154743194580078, cross_entropy: 1.0154743194580078 +[2025-04-29 10:34:15,370][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.1541848182678223, cross_entropy: 1.1541848182678223 +[2025-04-29 10:34:16,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.611945867538452, cross_entropy: 2.611945867538452 +[2025-04-29 10:34:19,133][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 1.3258216381072998, cross_entropy: 1.3258216381072998 +[2025-04-29 10:34:20,022][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 1.2859163284301758, cross_entropy: 1.2859163284301758 +[2025-04-29 10:34:23,347][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 3.1175007820129395, cross_entropy: 3.1175007820129395 +[2025-04-29 10:34:24,241][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 1.1256301403045654, cross_entropy: 1.1256301403045654 +[2025-04-29 10:34:27,010][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 0.8903236389160156, cross_entropy: 0.8903236389160156 +[2025-04-29 10:34:27,580][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/iteration2000.pth. +[2025-04-29 10:34:28,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.6461910009384155, cross_entropy: 1.6461910009384155 +[2025-04-29 10:34:31,261][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 1.6840133666992188, cross_entropy: 1.6840133666992188 +[2025-04-29 10:34:32,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 1.7628216743469238, cross_entropy: 1.7628216743469238 +[2025-04-29 10:34:35,845][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 2.2937300205230713, cross_entropy: 2.2937300205230713 +[2025-04-29 10:34:36,708][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 0.9684175252914429, cross_entropy: 0.9684175252914429 +[2025-04-29 10:34:38,985][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 0.9820590615272522, cross_entropy: 0.9820590615272522 +[2025-04-29 10:34:39,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 1.805487871170044, cross_entropy: 1.805487871170044 +[2025-04-29 10:34:41,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.650541305541992, cross_entropy: 2.650541305541992 +[2025-04-29 10:34:42,736][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.4746506214141846, cross_entropy: 1.4746506214141846 +[2025-04-29 10:34:45,175][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.648799180984497, cross_entropy: 1.648799180984497 +[2025-04-29 10:34:46,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 1.8141546249389648, cross_entropy: 1.8141546249389648 +[2025-04-29 10:34:49,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 0.6156632900238037, cross_entropy: 0.6156632900238037 +[2025-04-29 10:34:50,271][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.133077621459961, cross_entropy: 1.133077621459961 +[2025-04-29 10:34:54,750][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 2.9249982833862305, cross_entropy: 2.9249982833862305 +[2025-04-29 10:34:55,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.580254077911377, cross_entropy: 1.580254077911377 +[2025-04-29 10:34:57,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 1.5402932167053223, cross_entropy: 1.5402932167053223 +[2025-04-29 10:34:58,586][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 2.725961685180664, cross_entropy: 2.725961685180664 +[2025-04-29 10:35:01,778][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 2.149406909942627, cross_entropy: 2.149406909942627 +[2025-04-29 10:35:02,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 1.1532659530639648, cross_entropy: 1.1532659530639648 +[2025-04-29 10:35:05,626][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 1.078343152999878, cross_entropy: 1.078343152999878 +[2025-04-29 10:35:06,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 0.8150864839553833, cross_entropy: 0.8150864839553833 +[2025-04-29 10:35:09,557][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.4246013164520264, cross_entropy: 2.4246013164520264 +[2025-04-29 10:35:10,416][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.0436229705810547, cross_entropy: 1.0436229705810547 +[2025-04-29 10:35:12,980][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 1.5297662019729614, cross_entropy: 1.5297662019729614 +[2025-04-29 10:35:13,833][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 2.12424635887146, cross_entropy: 2.12424635887146 +[2025-04-29 10:35:17,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 0.7929656505584717, cross_entropy: 0.7929656505584717 +[2025-04-29 10:35:17,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 2.6872918605804443, cross_entropy: 2.6872918605804443 +[2025-04-29 10:35:20,150][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.1316825151443481, cross_entropy: 1.1316825151443481 +[2025-04-29 10:35:20,970][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.6345601081848145, cross_entropy: 2.6345601081848145 +[2025-04-29 10:35:24,244][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.3766520023345947, cross_entropy: 1.3766520023345947 +[2025-04-29 10:35:25,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 1.8363142013549805, cross_entropy: 1.8363142013549805 +[2025-04-29 10:35:28,774][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 2.0520894527435303, cross_entropy: 2.0520894527435303 +[2025-04-29 10:35:29,637][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.4525835514068604, cross_entropy: 1.4525835514068604 +[2025-04-29 10:35:32,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.9756295680999756, cross_entropy: 1.9756295680999756 +[2025-04-29 10:35:33,499][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 0.6651620268821716, cross_entropy: 0.6651620268821716 +[2025-04-29 10:35:36,946][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 2.2664167881011963, cross_entropy: 2.2664167881011963 +[2025-04-29 10:35:37,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 2.718064785003662, cross_entropy: 2.718064785003662 +[2025-04-29 10:35:40,815][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 0.9571230411529541, cross_entropy: 0.9571230411529541 +[2025-04-29 10:35:41,670][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 1.930172085762024, cross_entropy: 1.930172085762024 +[2025-04-29 10:35:44,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 1.7830928564071655, cross_entropy: 1.7830928564071655 +[2025-04-29 10:35:45,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 0.7186822891235352, cross_entropy: 0.7186822891235352 +[2025-04-29 10:35:47,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.783810019493103, cross_entropy: 1.783810019493103 +[2025-04-29 10:35:48,285][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.0356667041778564, cross_entropy: 2.0356667041778564 +[2025-04-29 10:35:51,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.2489330768585205, cross_entropy: 2.2489330768585205 +[2025-04-29 10:35:52,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 1.3867278099060059, cross_entropy: 1.3867278099060059 +[2025-04-29 10:35:55,292][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 0.8540574908256531, cross_entropy: 0.8540574908256531 +[2025-04-29 10:35:56,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 2.1177752017974854, cross_entropy: 2.1177752017974854 +[2025-04-29 10:35:58,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 1.6985808610916138, cross_entropy: 1.6985808610916138 +[2025-04-29 10:35:59,841][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.33308744430542, cross_entropy: 1.33308744430542 +[2025-04-29 10:36:02,882][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 2.135601758956909, cross_entropy: 2.135601758956909 +[2025-04-29 10:36:03,703][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.2057311534881592, cross_entropy: 1.2057311534881592 +[2025-04-29 10:36:07,868][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.6577792167663574, cross_entropy: 2.6577792167663574 +[2025-04-29 10:36:08,723][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.6699124574661255, cross_entropy: 1.6699124574661255 +[2025-04-29 10:36:11,387][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 0.9253293871879578, cross_entropy: 0.9253293871879578 +[2025-04-29 10:36:12,250][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.1795059442520142, cross_entropy: 1.1795059442520142 +[2025-04-29 10:36:15,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.2341926097869873, cross_entropy: 2.2341926097869873 +[2025-04-29 10:36:15,884][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 2.5597681999206543, cross_entropy: 2.5597681999206543 +[2025-04-29 10:36:18,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.2041170597076416, cross_entropy: 2.2041170597076416 +[2025-04-29 10:36:19,257][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 1.2723321914672852, cross_entropy: 1.2723321914672852 +[2025-04-29 10:36:22,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 2.5519704818725586, cross_entropy: 2.5519704818725586 +[2025-04-29 10:36:22,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 2.272718667984009, cross_entropy: 2.272718667984009 +[2025-04-29 10:36:25,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.3831565380096436, cross_entropy: 1.3831565380096436 +[2025-04-29 10:36:26,435][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 1.13998281955719, cross_entropy: 1.13998281955719 +[2025-04-29 10:36:29,463][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 0.9691830277442932, cross_entropy: 0.9691830277442932 +[2025-04-29 10:36:30,316][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 0.8992980718612671, cross_entropy: 0.8992980718612671 +[2025-04-29 10:36:32,736][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 0.851327657699585, cross_entropy: 0.851327657699585 +[2025-04-29 10:36:33,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 2.1927058696746826, cross_entropy: 2.1927058696746826 +[2025-04-29 10:36:37,103][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 2.7639548778533936, cross_entropy: 2.7639548778533936 +[2025-04-29 10:36:39,243][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 0.8862526416778564, cross_entropy: 0.8862526416778564 +[2025-04-29 10:36:40,646][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.5005079507827759, cross_entropy: 1.5005079507827759 +[2025-04-29 10:36:42,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.249415397644043, cross_entropy: 1.249415397644043 +[2025-04-29 10:36:44,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.3603198528289795, cross_entropy: 1.3603198528289795 +[2025-04-29 10:36:47,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 0.8704156875610352, cross_entropy: 0.8704156875610352 +[2025-04-29 10:36:47,946][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 0.7175884246826172, cross_entropy: 0.7175884246826172 +[2025-04-29 10:36:50,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 1.803452491760254, cross_entropy: 1.803452491760254 +[2025-04-29 10:36:51,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 1.9955575466156006, cross_entropy: 1.9955575466156006 +[2025-04-29 10:36:53,790][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 2.987842082977295, cross_entropy: 2.987842082977295 +[2025-04-29 10:36:54,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 1.8538148403167725, cross_entropy: 1.8538148403167725 +[2025-04-29 10:36:57,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 2.411406993865967, cross_entropy: 2.411406993865967 +[2025-04-29 10:36:58,014][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.6285901069641113, cross_entropy: 2.6285901069641113 +[2025-04-29 10:37:00,464][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.667149543762207, cross_entropy: 2.667149543762207 +[2025-04-29 10:37:01,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 1.9847266674041748, cross_entropy: 1.9847266674041748 +[2025-04-29 10:37:05,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.8196003437042236, cross_entropy: 1.8196003437042236 +[2025-04-29 10:37:05,902][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 3.1101152896881104, cross_entropy: 3.1101152896881104 +[2025-04-29 10:37:08,708][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 2.2271811962127686, cross_entropy: 2.2271811962127686 +[2025-04-29 10:37:09,557][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 1.0400364398956299, cross_entropy: 1.0400364398956299 +[2025-04-29 10:37:12,077][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 0.8809542655944824, cross_entropy: 0.8809542655944824 +[2025-04-29 10:37:12,930][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.6958118677139282, cross_entropy: 1.6958118677139282 +[2025-04-29 10:37:16,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.0909450054168701, cross_entropy: 1.0909450054168701 +[2025-04-29 10:37:16,938][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 0.5462499856948853, cross_entropy: 0.5462499856948853 +[2025-04-29 10:37:20,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 1.8220248222351074, cross_entropy: 1.8220248222351074 +[2025-04-29 10:37:21,137][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 2.6822946071624756, cross_entropy: 2.6822946071624756 +[2025-04-29 10:37:23,413][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 0.9501239061355591, cross_entropy: 0.9501239061355591 +[2025-04-29 10:37:24,268][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 2.967543363571167, cross_entropy: 2.967543363571167 +[2025-04-29 10:37:27,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 0.9713433384895325, cross_entropy: 0.9713433384895325 +[2025-04-29 10:37:28,327][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 2.4608516693115234, cross_entropy: 2.4608516693115234 +[2025-04-29 10:37:30,916][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 0.6707829833030701, cross_entropy: 0.6707829833030701 +[2025-04-29 10:37:31,768][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.301232099533081, cross_entropy: 1.301232099533081 +[2025-04-29 10:37:34,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 0.782606840133667, cross_entropy: 0.782606840133667 +[2025-04-29 10:37:35,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.1435109376907349, cross_entropy: 1.1435109376907349 +[2025-04-29 10:37:38,004][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.4160983562469482, cross_entropy: 1.4160983562469482 +[2025-04-29 10:37:38,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 1.2376646995544434, cross_entropy: 1.2376646995544434 +[2025-04-29 10:37:41,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 2.2373781204223633, cross_entropy: 2.2373781204223633 +[2025-04-29 10:37:42,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 1.96510910987854, cross_entropy: 1.96510910987854 +[2025-04-29 10:37:45,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 0.9180275797843933, cross_entropy: 0.9180275797843933 +[2025-04-29 10:37:45,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.1104023456573486, cross_entropy: 2.1104023456573486 +[2025-04-29 10:37:48,498][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 0.8645115494728088, cross_entropy: 0.8645115494728088 +[2025-04-29 10:37:49,319][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 1.1349468231201172, cross_entropy: 1.1349468231201172 +[2025-04-29 10:37:51,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 0.9584231972694397, cross_entropy: 0.9584231972694397 +[2025-04-29 10:37:52,607][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 0.9279671311378479, cross_entropy: 0.9279671311378479 +[2025-04-29 10:37:55,222][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 0.7716143131256104, cross_entropy: 0.7716143131256104 +[2025-04-29 10:37:56,106][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.073885202407837, cross_entropy: 1.073885202407837 +[2025-04-29 10:37:58,753][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.1347873210906982, cross_entropy: 1.1347873210906982 +[2025-04-29 10:37:59,657][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 1.72953462600708, cross_entropy: 1.72953462600708 +[2025-04-29 10:38:02,798][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.2450604438781738, cross_entropy: 1.2450604438781738 +[2025-04-29 10:38:03,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 2.115448236465454, cross_entropy: 2.115448236465454 +[2025-04-29 10:38:06,222][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 1.6281037330627441, cross_entropy: 1.6281037330627441 +[2025-04-29 10:38:07,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.2990350723266602, cross_entropy: 1.2990350723266602 +[2025-04-29 10:38:10,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 1.118774652481079, cross_entropy: 1.118774652481079 +[2025-04-29 10:38:11,199][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 1.1001636981964111, cross_entropy: 1.1001636981964111 +[2025-04-29 10:38:14,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 1.9665610790252686, cross_entropy: 1.9665610790252686 +[2025-04-29 10:38:15,311][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 1.2187309265136719, cross_entropy: 1.2187309265136719 +[2025-04-29 10:38:17,443][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 2.9558115005493164, cross_entropy: 2.9558115005493164 +[2025-04-29 10:38:18,835][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.0749123096466064, cross_entropy: 1.0749123096466064 +[2025-04-29 10:38:20,857][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 2.596644163131714, cross_entropy: 2.596644163131714 +[2025-04-29 10:38:21,908][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 2.2239818572998047, cross_entropy: 2.2239818572998047 +[2025-04-29 10:38:24,360][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 2.770399808883667, cross_entropy: 2.770399808883667 +[2025-04-29 10:38:25,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 0.823869526386261, cross_entropy: 0.823869526386261 +[2025-04-29 10:38:28,591][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 2.097388744354248, cross_entropy: 2.097388744354248 +[2025-04-29 10:38:29,481][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.3926225900650024, cross_entropy: 1.3926225900650024 +[2025-04-29 10:38:32,342][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 2.329561471939087, cross_entropy: 2.329561471939087 +[2025-04-29 10:38:33,225][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.2123613357543945, cross_entropy: 1.2123613357543945 +[2025-04-29 10:38:35,195][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 2.9148945808410645, cross_entropy: 2.9148945808410645 +[2025-04-29 10:38:36,478][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.7915327548980713, cross_entropy: 1.7915327548980713 +[2025-04-29 10:38:38,446][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 1.2759766578674316, cross_entropy: 1.2759766578674316 +[2025-04-29 10:38:39,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 2.3389432430267334, cross_entropy: 2.3389432430267334 +[2025-04-29 10:41:19,749][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.6634304523468018, cross_entropy: 1.6634304523468018 +[2025-04-29 10:41:19,750][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.0413918495178223, cross_entropy: 1.0413918495178223 +[2025-04-29 10:41:20,689][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 10:41:21,229][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch6.pth. +[2025-04-29 10:41:22,163][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 10:41:26,677][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.703892230987549, cross_entropy: 2.703892230987549 +[2025-04-29 10:41:27,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.076019287109375, cross_entropy: 2.076019287109375 +[2025-04-29 10:41:29,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 2.364543914794922, cross_entropy: 2.364543914794922 +[2025-04-29 10:41:31,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 0.7359475493431091, cross_entropy: 0.7359475493431091 +[2025-04-29 10:41:33,874][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 2.0833821296691895, cross_entropy: 2.0833821296691895 +[2025-04-29 10:41:34,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.6651666164398193, cross_entropy: 1.6651666164398193 +[2025-04-29 10:41:37,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.012702465057373, cross_entropy: 2.012702465057373 +[2025-04-29 10:41:38,468][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 0.8970676064491272, cross_entropy: 0.8970676064491272 +[2025-04-29 10:41:41,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.4206476211547852, cross_entropy: 1.4206476211547852 +[2025-04-29 10:41:42,194][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.2002577781677246, cross_entropy: 1.2002577781677246 +[2025-04-29 10:41:45,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 2.8213815689086914, cross_entropy: 2.8213815689086914 +[2025-04-29 10:41:46,276][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.1356487274169922, cross_entropy: 1.1356487274169922 +[2025-04-29 10:41:49,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 0.9269353151321411, cross_entropy: 0.9269353151321411 +[2025-04-29 10:41:50,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 0.5407456755638123, cross_entropy: 0.5407456755638123 +[2025-04-29 10:41:53,596][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 1.6796025037765503, cross_entropy: 1.6796025037765503 +[2025-04-29 10:41:54,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.7726612091064453, cross_entropy: 2.7726612091064453 +[2025-04-29 10:41:57,291][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.681340217590332, cross_entropy: 2.681340217590332 +[2025-04-29 10:41:58,143][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 2.686184883117676, cross_entropy: 2.686184883117676 +[2025-04-29 10:42:01,413][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.487314224243164, cross_entropy: 2.487314224243164 +[2025-04-29 10:42:02,263][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 2.7587742805480957, cross_entropy: 2.7587742805480957 +[2025-04-29 10:42:04,818][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.4836151599884033, cross_entropy: 1.4836151599884033 +[2025-04-29 10:42:05,636][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 1.5856062173843384, cross_entropy: 1.5856062173843384 +[2025-04-29 10:42:07,727][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 0.8059842586517334, cross_entropy: 0.8059842586517334 +[2025-04-29 10:42:08,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.3274648189544678, cross_entropy: 2.3274648189544678 +[2025-04-29 10:42:12,144][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 0.815690279006958, cross_entropy: 0.815690279006958 +[2025-04-29 10:42:12,997][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.736238956451416, cross_entropy: 2.736238956451416 +[2025-04-29 10:42:15,890][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.042200803756714, cross_entropy: 2.042200803756714 +[2025-04-29 10:42:16,710][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 0.8258652687072754, cross_entropy: 0.8258652687072754 +[2025-04-29 10:42:19,508][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.1783863306045532, cross_entropy: 1.1783863306045532 +[2025-04-29 10:42:20,361][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 0.4827467203140259, cross_entropy: 0.4827467203140259 +[2025-04-29 10:42:22,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.683566093444824, cross_entropy: 2.683566093444824 +[2025-04-29 10:42:23,495][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 0.4603925943374634, cross_entropy: 0.4603925943374634 +[2025-04-29 10:42:27,074][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 1.3562936782836914, cross_entropy: 1.3562936782836914 +[2025-04-29 10:42:27,890][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 0.7528584003448486, cross_entropy: 0.7528584003448486 +[2025-04-29 10:42:30,569][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 1.9464256763458252, cross_entropy: 1.9464256763458252 +[2025-04-29 10:42:31,421][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 2.093055486679077, cross_entropy: 2.093055486679077 +[2025-04-29 10:42:33,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 1.784475564956665, cross_entropy: 1.784475564956665 +[2025-04-29 10:42:34,695][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.3445634841918945, cross_entropy: 1.3445634841918945 +[2025-04-29 10:42:37,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 0.6295921802520752, cross_entropy: 0.6295921802520752 +[2025-04-29 10:42:38,514][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 2.370140552520752, cross_entropy: 2.370140552520752 +[2025-04-29 10:42:41,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 0.7170023918151855, cross_entropy: 0.7170023918151855 +[2025-04-29 10:42:42,259][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.9573183059692383, cross_entropy: 2.9573183059692383 +[2025-04-29 10:42:44,901][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.680931568145752, cross_entropy: 2.680931568145752 +[2025-04-29 10:42:45,792][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 1.3840608596801758, cross_entropy: 1.3840608596801758 +[2025-04-29 10:42:48,299][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 0.6581798195838928, cross_entropy: 0.6581798195838928 +[2025-04-29 10:42:49,152][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.7787984609603882, cross_entropy: 1.7787984609603882 +[2025-04-29 10:42:51,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 2.3770763874053955, cross_entropy: 2.3770763874053955 +[2025-04-29 10:42:52,261][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 0.48671257495880127, cross_entropy: 0.48671257495880127 +[2025-04-29 10:42:54,872][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.3002729415893555, cross_entropy: 2.3002729415893555 +[2025-04-29 10:42:55,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 0.6898356080055237, cross_entropy: 0.6898356080055237 +[2025-04-29 10:42:58,654][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.9749505519866943, cross_entropy: 2.9749505519866943 +[2025-04-29 10:42:59,506][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.8793525695800781, cross_entropy: 1.8793525695800781 +[2025-04-29 10:43:01,743][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 0.8383955359458923, cross_entropy: 0.8383955359458923 +[2025-04-29 10:43:02,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.7572669982910156, cross_entropy: 2.7572669982910156 +[2025-04-29 10:43:05,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 2.605097770690918, cross_entropy: 2.605097770690918 +[2025-04-29 10:43:06,693][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.345174789428711, cross_entropy: 2.345174789428711 +[2025-04-29 10:43:08,873][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 0.7071374654769897, cross_entropy: 0.7071374654769897 +[2025-04-29 10:43:09,691][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.0233820676803589, cross_entropy: 1.0233820676803589 +[2025-04-29 10:43:12,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 1.1193792819976807, cross_entropy: 1.1193792819976807 +[2025-04-29 10:43:13,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.651715636253357, cross_entropy: 1.651715636253357 +[2025-04-29 10:43:15,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.1633265018463135, cross_entropy: 2.1633265018463135 +[2025-04-29 10:43:16,788][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.5866703987121582, cross_entropy: 1.5866703987121582 +[2025-04-29 10:43:20,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.9883322715759277, cross_entropy: 1.9883322715759277 +[2025-04-29 10:43:21,162][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 0.6935908794403076, cross_entropy: 0.6935908794403076 +[2025-04-29 10:43:24,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 1.2807248830795288, cross_entropy: 1.2807248830795288 +[2025-04-29 10:43:25,022][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.60331130027771, cross_entropy: 1.60331130027771 +[2025-04-29 10:43:27,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.0365538597106934, cross_entropy: 1.0365538597106934 +[2025-04-29 10:43:28,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 1.206669569015503, cross_entropy: 1.206669569015503 +[2025-04-29 10:43:31,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 0.6251369118690491, cross_entropy: 0.6251369118690491 +[2025-04-29 10:43:31,942][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 0.6967169046401978, cross_entropy: 0.6967169046401978 +[2025-04-29 10:43:34,582][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.0077359676361084, cross_entropy: 2.0077359676361084 +[2025-04-29 10:43:35,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 0.8612192869186401, cross_entropy: 0.8612192869186401 +[2025-04-29 10:43:38,598][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 0.9480629563331604, cross_entropy: 0.9480629563331604 +[2025-04-29 10:43:39,415][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 1.5533846616744995, cross_entropy: 1.5533846616744995 +[2025-04-29 10:43:42,423][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 2.1804027557373047, cross_entropy: 2.1804027557373047 +[2025-04-29 10:43:43,245][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 2.117311954498291, cross_entropy: 2.117311954498291 +[2025-04-29 10:43:46,383][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.636181592941284, cross_entropy: 2.636181592941284 +[2025-04-29 10:43:47,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 0.9879291653633118, cross_entropy: 0.9879291653633118 +[2025-04-29 10:43:50,426][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 1.9800817966461182, cross_entropy: 1.9800817966461182 +[2025-04-29 10:43:51,241][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 0.7252483367919922, cross_entropy: 0.7252483367919922 +[2025-04-29 10:43:53,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 2.8571183681488037, cross_entropy: 2.8571183681488037 +[2025-04-29 10:43:54,654][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 2.4223673343658447, cross_entropy: 2.4223673343658447 +[2025-04-29 10:43:57,349][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 1.4447863101959229, cross_entropy: 1.4447863101959229 +[2025-04-29 10:43:58,203][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 0.6065071821212769, cross_entropy: 0.6065071821212769 +[2025-04-29 10:44:01,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.4002060890197754, cross_entropy: 1.4002060890197754 +[2025-04-29 10:44:01,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 1.6246845722198486, cross_entropy: 1.6246845722198486 +[2025-04-29 10:44:04,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 0.8027594089508057, cross_entropy: 0.8027594089508057 +[2025-04-29 10:44:05,647][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 0.7110503911972046, cross_entropy: 0.7110503911972046 +[2025-04-29 10:44:08,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 1.1878225803375244, cross_entropy: 1.1878225803375244 +[2025-04-29 10:44:09,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.5177655220031738, cross_entropy: 1.5177655220031738 +[2025-04-29 10:44:12,140][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 2.6013925075531006, cross_entropy: 2.6013925075531006 +[2025-04-29 10:44:12,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 1.156947135925293, cross_entropy: 1.156947135925293 +[2025-04-29 10:44:16,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.0529943704605103, cross_entropy: 1.0529943704605103 +[2025-04-29 10:44:17,110][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 2.08646821975708, cross_entropy: 2.08646821975708 +[2025-04-29 10:44:19,494][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 1.7364795207977295, cross_entropy: 1.7364795207977295 +[2025-04-29 10:44:20,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 0.8231154680252075, cross_entropy: 0.8231154680252075 +[2025-04-29 10:44:22,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.8290966749191284, cross_entropy: 1.8290966749191284 +[2025-04-29 10:44:23,660][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 0.5276623964309692, cross_entropy: 0.5276623964309692 +[2025-04-29 10:44:26,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.7045834064483643, cross_entropy: 1.7045834064483643 +[2025-04-29 10:44:27,645][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.2786476612091064, cross_entropy: 1.2786476612091064 +[2025-04-29 10:44:30,581][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 2.6358375549316406, cross_entropy: 2.6358375549316406 +[2025-04-29 10:44:31,397][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 2.3016810417175293, cross_entropy: 2.3016810417175293 +[2025-04-29 10:44:35,042][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 1.8687901496887207, cross_entropy: 1.8687901496887207 +[2025-04-29 10:44:35,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 2.8920583724975586, cross_entropy: 2.8920583724975586 +[2025-04-29 10:44:39,209][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.6335227489471436, cross_entropy: 1.6335227489471436 +[2025-04-29 10:44:40,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 2.2325761318206787, cross_entropy: 2.2325761318206787 +[2025-04-29 10:44:43,200][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 0.7351343631744385, cross_entropy: 0.7351343631744385 +[2025-04-29 10:44:44,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.7785625457763672, cross_entropy: 1.7785625457763672 +[2025-04-29 10:44:46,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 0.7907103300094604, cross_entropy: 0.7907103300094604 +[2025-04-29 10:44:47,173][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 1.0836913585662842, cross_entropy: 1.0836913585662842 +[2025-04-29 10:44:49,596][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 0.9647749662399292, cross_entropy: 0.9647749662399292 +[2025-04-29 10:44:50,454][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 0.8000563383102417, cross_entropy: 0.8000563383102417 +[2025-04-29 10:44:53,332][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.19065260887146, cross_entropy: 1.19065260887146 +[2025-04-29 10:44:54,187][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 2.002802610397339, cross_entropy: 2.002802610397339 +[2025-04-29 10:44:57,235][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 0.684228241443634, cross_entropy: 0.684228241443634 +[2025-04-29 10:44:58,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 1.7439544200897217, cross_entropy: 1.7439544200897217 +[2025-04-29 10:45:00,801][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.029921293258667, cross_entropy: 1.029921293258667 +[2025-04-29 10:45:01,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.2537178993225098, cross_entropy: 2.2537178993225098 +[2025-04-29 10:45:03,968][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.524247169494629, cross_entropy: 2.524247169494629 +[2025-04-29 10:45:04,784][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 2.429668426513672, cross_entropy: 2.429668426513672 +[2025-04-29 10:45:07,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.9574558734893799, cross_entropy: 1.9574558734893799 +[2025-04-29 10:45:08,556][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 1.3389369249343872, cross_entropy: 1.3389369249343872 +[2025-04-29 10:45:10,715][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.5340676307678223, cross_entropy: 2.5340676307678223 +[2025-04-29 10:45:11,565][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.6229023933410645, cross_entropy: 1.6229023933410645 +[2025-04-29 10:45:14,565][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 2.011960029602051, cross_entropy: 2.011960029602051 +[2025-04-29 10:45:15,420][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 0.7741274237632751, cross_entropy: 0.7741274237632751 +[2025-04-29 10:45:18,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 1.1274958848953247, cross_entropy: 1.1274958848953247 +[2025-04-29 10:45:18,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.549081563949585, cross_entropy: 1.549081563949585 +[2025-04-29 10:45:21,660][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 0.6858395338058472, cross_entropy: 0.6858395338058472 +[2025-04-29 10:45:22,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 0.74364173412323, cross_entropy: 0.74364173412323 +[2025-04-29 10:45:26,179][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 2.875318765640259, cross_entropy: 2.875318765640259 +[2025-04-29 10:45:26,997][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.9841954708099365, cross_entropy: 2.9841954708099365 +[2025-04-29 10:45:29,134][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 0.5502936244010925, cross_entropy: 0.5502936244010925 +[2025-04-29 10:45:29,983][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 0.901830792427063, cross_entropy: 0.901830792427063 +[2025-04-29 10:45:31,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 1.3879557847976685, cross_entropy: 1.3879557847976685 +[2025-04-29 10:45:32,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 0.5420772433280945, cross_entropy: 0.5420772433280945 +[2025-04-29 10:45:36,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 1.1718734502792358, cross_entropy: 1.1718734502792358 +[2025-04-29 10:45:36,908][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.148362159729004, cross_entropy: 1.148362159729004 +[2025-04-29 10:45:38,843][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.2716219425201416, cross_entropy: 1.2716219425201416 +[2025-04-29 10:45:39,722][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.752807140350342, cross_entropy: 2.752807140350342 +[2025-04-29 10:45:42,509][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 2.6838626861572266, cross_entropy: 2.6838626861572266 +[2025-04-29 10:45:43,430][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.3223209381103516, cross_entropy: 1.3223209381103516 +[2025-04-29 10:45:46,605][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 0.6502911448478699, cross_entropy: 0.6502911448478699 +[2025-04-29 10:45:47,457][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.7618446350097656, cross_entropy: 2.7618446350097656 +[2025-04-29 10:45:50,283][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.802914023399353, cross_entropy: 1.802914023399353 +[2025-04-29 10:45:51,128][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.7286982536315918, cross_entropy: 1.7286982536315918 +[2025-04-29 10:45:54,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 1.952092170715332, cross_entropy: 1.952092170715332 +[2025-04-29 10:45:55,527][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 1.5934162139892578, cross_entropy: 1.5934162139892578 +[2025-04-29 10:45:58,101][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 1.6005141735076904, cross_entropy: 1.6005141735076904 +[2025-04-29 10:45:58,919][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 1.6116782426834106, cross_entropy: 1.6116782426834106 +[2025-04-29 10:46:01,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.602506160736084, cross_entropy: 2.602506160736084 +[2025-04-29 10:46:02,541][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 1.1045774221420288, cross_entropy: 1.1045774221420288 +[2025-04-29 10:46:05,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 1.3663289546966553, cross_entropy: 1.3663289546966553 +[2025-04-29 10:46:05,980][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 2.931705951690674, cross_entropy: 2.931705951690674 +[2025-04-29 10:46:09,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 0.7611691355705261, cross_entropy: 0.7611691355705261 +[2025-04-29 10:46:09,984][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 0.8324301242828369, cross_entropy: 0.8324301242828369 +[2025-04-29 10:46:11,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.0241210460662842, cross_entropy: 1.0241210460662842 +[2025-04-29 10:46:12,784][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 0.986395001411438, cross_entropy: 0.986395001411438 +[2025-04-29 10:46:15,893][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.3802462816238403, cross_entropy: 1.3802462816238403 +[2025-04-29 10:46:16,711][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 0.8857938647270203, cross_entropy: 0.8857938647270203 +[2025-04-29 10:46:20,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 1.870415449142456, cross_entropy: 1.870415449142456 +[2025-04-29 10:46:20,868][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.422287106513977, cross_entropy: 1.422287106513977 +[2025-04-29 10:46:22,673][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 0.7933061122894287, cross_entropy: 0.7933061122894287 +[2025-04-29 10:46:23,519][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 1.8271145820617676, cross_entropy: 1.8271145820617676 +[2025-04-29 10:46:27,029][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 2.8867080211639404, cross_entropy: 2.8867080211639404 +[2025-04-29 10:46:27,943][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 2.941253185272217, cross_entropy: 2.941253185272217 +[2025-04-29 10:46:30,066][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 2.0993266105651855, cross_entropy: 2.0993266105651855 +[2025-04-29 10:46:30,991][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 0.903508186340332, cross_entropy: 0.903508186340332 +[2025-04-29 10:46:33,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.1803491115570068, cross_entropy: 1.1803491115570068 +[2025-04-29 10:46:34,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 0.6111195087432861, cross_entropy: 0.6111195087432861 +[2025-04-29 10:46:37,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 2.136915683746338, cross_entropy: 2.136915683746338 +[2025-04-29 10:46:38,352][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 1.4935235977172852, cross_entropy: 1.4935235977172852 +[2025-04-29 10:46:41,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.0446093082427979, cross_entropy: 1.0446093082427979 +[2025-04-29 10:46:42,507][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 0.5740962028503418, cross_entropy: 0.5740962028503418 +[2025-04-29 10:46:45,380][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 1.853432059288025, cross_entropy: 1.853432059288025 +[2025-04-29 10:46:46,230][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.1925160884857178, cross_entropy: 1.1925160884857178 +[2025-04-29 10:46:48,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 1.2177116870880127, cross_entropy: 1.2177116870880127 +[2025-04-29 10:46:49,777][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 0.419386088848114, cross_entropy: 0.419386088848114 +[2025-04-29 10:46:52,767][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 0.5246686935424805, cross_entropy: 0.5246686935424805 +[2025-04-29 10:46:53,624][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 2.1973695755004883, cross_entropy: 2.1973695755004883 +[2025-04-29 10:46:56,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.6337027549743652, cross_entropy: 2.6337027549743652 +[2025-04-29 10:46:57,004][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 0.9946678876876831, cross_entropy: 0.9946678876876831 +[2025-04-29 10:46:59,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.2640728950500488, cross_entropy: 1.2640728950500488 +[2025-04-29 10:47:00,504][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 0.6583683490753174, cross_entropy: 0.6583683490753174 +[2025-04-29 10:47:03,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.7198193073272705, cross_entropy: 1.7198193073272705 +[2025-04-29 10:47:04,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.6732232570648193, cross_entropy: 2.6732232570648193 +[2025-04-29 10:47:08,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 1.2384393215179443, cross_entropy: 1.2384393215179443 +[2025-04-29 10:47:09,521][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 2.2599925994873047, cross_entropy: 2.2599925994873047 +[2025-04-29 10:47:12,845][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.478832483291626, cross_entropy: 1.478832483291626 +[2025-04-29 10:47:13,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 0.7625122666358948, cross_entropy: 0.7625122666358948 +[2025-04-29 10:47:16,719][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 0.6330429315567017, cross_entropy: 0.6330429315567017 +[2025-04-29 10:47:17,575][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.684922695159912, cross_entropy: 1.684922695159912 +[2025-04-29 10:47:20,447][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 2.5203840732574463, cross_entropy: 2.5203840732574463 +[2025-04-29 10:47:21,297][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.3303937911987305, cross_entropy: 2.3303937911987305 +[2025-04-29 10:47:24,025][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 2.0549259185791016, cross_entropy: 2.0549259185791016 +[2025-04-29 10:47:24,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.1089584827423096, cross_entropy: 1.1089584827423096 +[2025-04-29 10:47:27,673][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 2.4112675189971924, cross_entropy: 2.4112675189971924 +[2025-04-29 10:47:28,527][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 1.154321551322937, cross_entropy: 1.154321551322937 +[2025-04-29 10:47:31,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 2.48945951461792, cross_entropy: 2.48945951461792 +[2025-04-29 10:47:32,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.0260862112045288, cross_entropy: 1.0260862112045288 +[2025-04-29 10:47:34,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.786266326904297, cross_entropy: 2.786266326904297 +[2025-04-29 10:47:35,481][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 0.6074663996696472, cross_entropy: 0.6074663996696472 +[2025-04-29 10:47:38,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.384361982345581, cross_entropy: 1.384361982345581 +[2025-04-29 10:47:39,442][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.4450578689575195, cross_entropy: 2.4450578689575195 +[2025-04-29 10:47:41,365][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 0.9393038749694824, cross_entropy: 0.9393038749694824 +[2025-04-29 10:47:42,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 2.5593366622924805, cross_entropy: 2.5593366622924805 +[2025-04-29 10:47:44,204][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 0.6861310005187988, cross_entropy: 0.6861310005187988 +[2025-04-29 10:47:45,022][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 0.6671685576438904, cross_entropy: 0.6671685576438904 +[2025-04-29 10:47:47,486][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 0.9460410475730896, cross_entropy: 0.9460410475730896 +[2025-04-29 10:47:48,335][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 2.1356453895568848, cross_entropy: 2.1356453895568848 +[2025-04-29 10:47:50,644][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 2.619535446166992, cross_entropy: 2.619535446166992 +[2025-04-29 10:47:51,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 0.6186054944992065, cross_entropy: 0.6186054944992065 +[2025-04-29 10:47:53,916][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 2.3885772228240967, cross_entropy: 2.3885772228240967 +[2025-04-29 10:47:54,772][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 0.576808750629425, cross_entropy: 0.576808750629425 +[2025-04-29 10:47:58,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.0276775360107422, cross_entropy: 1.0276775360107422 +[2025-04-29 10:47:58,871][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 1.6854196786880493, cross_entropy: 1.6854196786880493 +[2025-04-29 10:48:01,385][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.5523200035095215, cross_entropy: 2.5523200035095215 +[2025-04-29 10:48:02,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 1.850178599357605, cross_entropy: 1.850178599357605 +[2025-04-29 10:48:04,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 2.5777835845947266, cross_entropy: 2.5777835845947266 +[2025-04-29 10:48:05,841][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 1.5016424655914307, cross_entropy: 1.5016424655914307 +[2025-04-29 10:48:08,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 0.4671351909637451, cross_entropy: 0.4671351909637451 +[2025-04-29 10:48:09,290][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 2.9535326957702637, cross_entropy: 2.9535326957702637 +[2025-04-29 10:48:11,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 1.8274598121643066, cross_entropy: 1.8274598121643066 +[2025-04-29 10:48:13,940][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 0.8410970568656921, cross_entropy: 0.8410970568656921 +[2025-04-29 10:48:15,162][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 2.542410373687744, cross_entropy: 2.542410373687744 +[2025-04-29 10:48:17,436][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 0.6461185216903687, cross_entropy: 0.6461185216903687 +[2025-04-29 10:48:18,560][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 2.0192487239837646, cross_entropy: 2.0192487239837646 +[2025-04-29 10:48:21,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.0184475183486938, cross_entropy: 1.0184475183486938 +[2025-04-29 10:48:22,320][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 2.3725156784057617, cross_entropy: 2.3725156784057617 +[2025-04-29 10:48:25,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 0.6413711905479431, cross_entropy: 0.6413711905479431 +[2025-04-29 10:48:25,961][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 0.8689512610435486, cross_entropy: 0.8689512610435486 +[2025-04-29 10:48:28,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 2.8009121417999268, cross_entropy: 2.8009121417999268 +[2025-04-29 10:48:29,880][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 0.49107295274734497, cross_entropy: 0.49107295274734497 +[2025-04-29 10:48:32,425][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.5354580879211426, cross_entropy: 2.5354580879211426 +[2025-04-29 10:48:34,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.1875112056732178, cross_entropy: 1.1875112056732178 +[2025-04-29 10:48:35,872][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 1.0201890468597412, cross_entropy: 1.0201890468597412 +[2025-04-29 10:48:38,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 0.8685860633850098, cross_entropy: 0.8685860633850098 +[2025-04-29 10:48:39,278][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 0.8014012575149536, cross_entropy: 0.8014012575149536 +[2025-04-29 10:48:42,586][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.7857213020324707, cross_entropy: 2.7857213020324707 +[2025-04-29 10:48:43,439][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 1.0747743844985962, cross_entropy: 1.0747743844985962 +[2025-04-29 10:48:45,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.777153968811035, cross_entropy: 2.777153968811035 +[2025-04-29 10:48:46,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 0.738650381565094, cross_entropy: 0.738650381565094 +[2025-04-29 10:48:49,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.8064872026443481, cross_entropy: 1.8064872026443481 +[2025-04-29 10:48:50,227][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 2.7255632877349854, cross_entropy: 2.7255632877349854 +[2025-04-29 10:48:52,739][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.7164406776428223, cross_entropy: 1.7164406776428223 +[2025-04-29 10:48:53,559][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 2.380397319793701, cross_entropy: 2.380397319793701 +[2025-04-29 10:48:56,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 0.9075286388397217, cross_entropy: 0.9075286388397217 +[2025-04-29 10:48:57,309][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 1.3212170600891113, cross_entropy: 1.3212170600891113 +[2025-04-29 10:49:00,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 0.9254347681999207, cross_entropy: 0.9254347681999207 +[2025-04-29 10:49:01,348][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.4730305671691895, cross_entropy: 2.4730305671691895 +[2025-04-29 10:49:03,833][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 2.6354174613952637, cross_entropy: 2.6354174613952637 +[2025-04-29 10:49:04,691][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 0.6682359576225281, cross_entropy: 0.6682359576225281 +[2025-04-29 10:49:07,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 0.7281755208969116, cross_entropy: 0.7281755208969116 +[2025-04-29 10:49:07,902][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.0202993154525757, cross_entropy: 1.0202993154525757 +[2025-04-29 10:49:10,520][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 0.5956876873970032, cross_entropy: 0.5956876873970032 +[2025-04-29 10:49:11,336][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.628965377807617, cross_entropy: 2.628965377807617 +[2025-04-29 10:49:14,207][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.577298164367676, cross_entropy: 2.577298164367676 +[2025-04-29 10:49:15,060][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 0.7752430438995361, cross_entropy: 0.7752430438995361 +[2025-04-29 10:49:18,266][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.8363796472549438, cross_entropy: 1.8363796472549438 +[2025-04-29 10:49:19,123][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 0.865800678730011, cross_entropy: 0.865800678730011 +[2025-04-29 10:49:21,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 0.8438551425933838, cross_entropy: 0.8438551425933838 +[2025-04-29 10:49:22,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 2.904005527496338, cross_entropy: 2.904005527496338 +[2025-04-29 10:49:24,898][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.1071040630340576, cross_entropy: 1.1071040630340576 +[2025-04-29 10:49:25,748][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.393637776374817, cross_entropy: 1.393637776374817 +[2025-04-29 10:49:28,250][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.8253607749938965, cross_entropy: 2.8253607749938965 +[2025-04-29 10:49:29,066][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 2.175800085067749, cross_entropy: 2.175800085067749 +[2025-04-29 10:49:31,620][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 2.508944034576416, cross_entropy: 2.508944034576416 +[2025-04-29 10:49:32,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 1.0585213899612427, cross_entropy: 1.0585213899612427 +[2025-04-29 10:49:35,906][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 1.6544502973556519, cross_entropy: 1.6544502973556519 +[2025-04-29 10:49:36,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.0823533535003662, cross_entropy: 1.0823533535003662 +[2025-04-29 10:49:39,753][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 1.459859848022461, cross_entropy: 1.459859848022461 +[2025-04-29 10:49:40,604][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 0.9398660659790039, cross_entropy: 0.9398660659790039 +[2025-04-29 10:49:43,249][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.389230728149414, cross_entropy: 2.389230728149414 +[2025-04-29 10:49:44,103][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.5090198516845703, cross_entropy: 1.5090198516845703 +[2025-04-29 10:49:47,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.6455936431884766, cross_entropy: 2.6455936431884766 +[2025-04-29 10:49:48,015][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 3.065521717071533, cross_entropy: 3.065521717071533 +[2025-04-29 10:49:50,426][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.2755272388458252, cross_entropy: 1.2755272388458252 +[2025-04-29 10:49:51,280][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 1.7901508808135986, cross_entropy: 1.7901508808135986 +[2025-04-29 10:49:54,088][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 0.6597009897232056, cross_entropy: 0.6597009897232056 +[2025-04-29 10:49:54,904][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.8388410806655884, cross_entropy: 1.8388410806655884 +[2025-04-29 10:49:57,800][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.8086912631988525, cross_entropy: 1.8086912631988525 +[2025-04-29 10:49:58,653][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 0.9050330519676208, cross_entropy: 0.9050330519676208 +[2025-04-29 10:50:00,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.7673532962799072, cross_entropy: 2.7673532962799072 +[2025-04-29 10:50:01,514][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.3492916822433472, cross_entropy: 1.3492916822433472 +[2025-04-29 10:50:04,191][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 0.7085700035095215, cross_entropy: 0.7085700035095215 +[2025-04-29 10:50:05,046][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.6627614498138428, cross_entropy: 2.6627614498138428 +[2025-04-29 10:50:08,179][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.680025339126587, cross_entropy: 1.680025339126587 +[2025-04-29 10:50:09,033][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 2.5660178661346436, cross_entropy: 2.5660178661346436 +[2025-04-29 10:50:11,788][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 2.2984962463378906, cross_entropy: 2.2984962463378906 +[2025-04-29 10:50:12,635][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.6172585487365723, cross_entropy: 2.6172585487365723 +[2025-04-29 10:50:14,744][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.4111402034759521, cross_entropy: 1.4111402034759521 +[2025-04-29 10:50:15,599][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 0.9443541765213013, cross_entropy: 0.9443541765213013 +[2025-04-29 10:50:17,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 0.8759702444076538, cross_entropy: 0.8759702444076538 +[2025-04-29 10:50:18,766][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.2431306838989258, cross_entropy: 1.2431306838989258 +[2025-04-29 10:50:22,454][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 0.41321319341659546, cross_entropy: 0.41321319341659546 +[2025-04-29 10:50:23,306][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 2.556319236755371, cross_entropy: 2.556319236755371 +[2025-04-29 10:50:25,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.2480216026306152, cross_entropy: 2.2480216026306152 +[2025-04-29 10:50:26,452][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 1.30596923828125, cross_entropy: 1.30596923828125 +[2025-04-29 10:50:29,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.867311954498291, cross_entropy: 2.867311954498291 +[2025-04-29 10:50:30,166][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 2.6106581687927246, cross_entropy: 2.6106581687927246 +[2025-04-29 10:50:32,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 1.9245011806488037, cross_entropy: 1.9245011806488037 +[2025-04-29 10:50:33,642][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 0.9406063556671143, cross_entropy: 0.9406063556671143 +[2025-04-29 10:50:36,284][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.1070998907089233, cross_entropy: 1.1070998907089233 +[2025-04-29 10:50:37,136][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.1789062023162842, cross_entropy: 1.1789062023162842 +[2025-04-29 10:50:39,627][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.4159115552902222, cross_entropy: 1.4159115552902222 +[2025-04-29 10:50:40,446][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.0286550521850586, cross_entropy: 2.0286550521850586 +[2025-04-29 10:50:43,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 2.4204978942871094, cross_entropy: 2.4204978942871094 +[2025-04-29 10:50:44,787][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.5403003692626953, cross_entropy: 2.5403003692626953 +[2025-04-29 10:50:47,699][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 1.1847736835479736, cross_entropy: 1.1847736835479736 +[2025-04-29 10:50:48,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.248354911804199, cross_entropy: 2.248354911804199 +[2025-04-29 10:50:51,430][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 2.770815134048462, cross_entropy: 2.770815134048462 +[2025-04-29 10:50:52,260][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.2756868600845337, cross_entropy: 1.2756868600845337 +[2025-04-29 10:50:54,698][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 0.8873729705810547, cross_entropy: 0.8873729705810547 +[2025-04-29 10:50:55,563][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.5711069107055664, cross_entropy: 1.5711069107055664 +[2025-04-29 10:50:58,643][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.998481273651123, cross_entropy: 1.998481273651123 +[2025-04-29 10:50:59,518][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.9864087104797363, cross_entropy: 1.9864087104797363 +[2025-04-29 10:51:02,039][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.1321158409118652, cross_entropy: 1.1321158409118652 +[2025-04-29 10:51:03,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.6395385265350342, cross_entropy: 1.6395385265350342 +[2025-04-29 10:51:05,263][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 2.87686824798584, cross_entropy: 2.87686824798584 +[2025-04-29 10:51:06,170][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 0.7783070802688599, cross_entropy: 0.7783070802688599 +[2025-04-29 10:51:08,778][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 1.8900526762008667, cross_entropy: 1.8900526762008667 +[2025-04-29 10:51:09,690][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 0.7423923015594482, cross_entropy: 0.7423923015594482 +[2025-04-29 10:51:11,983][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 2.7977027893066406, cross_entropy: 2.7977027893066406 +[2025-04-29 10:51:12,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.1727380752563477, cross_entropy: 2.1727380752563477 +[2025-04-29 10:51:15,822][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 2.3528380393981934, cross_entropy: 2.3528380393981934 +[2025-04-29 10:51:16,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 1.3196985721588135, cross_entropy: 1.3196985721588135 +[2025-04-29 10:51:19,151][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 2.304401397705078, cross_entropy: 2.304401397705078 +[2025-04-29 10:51:20,062][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.8515338897705078, cross_entropy: 1.8515338897705078 +[2025-04-29 10:51:22,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.361194133758545, cross_entropy: 1.361194133758545 +[2025-04-29 10:51:23,618][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 0.5457134246826172, cross_entropy: 0.5457134246826172 +[2025-04-29 10:51:26,469][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 2.2686524391174316, cross_entropy: 2.2686524391174316 +[2025-04-29 10:51:27,674][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.6021937131881714, cross_entropy: 1.6021937131881714 +[2025-04-29 10:51:30,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.672891139984131, cross_entropy: 2.672891139984131 +[2025-04-29 10:51:31,469][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.740350365638733, cross_entropy: 1.740350365638733 +[2025-04-29 10:51:34,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 2.669213056564331, cross_entropy: 2.669213056564331 +[2025-04-29 10:51:34,955][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.3684496879577637, cross_entropy: 1.3684496879577637 +[2025-04-29 10:51:37,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 0.8672675490379333, cross_entropy: 0.8672675490379333 +[2025-04-29 10:51:39,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 2.5578792095184326, cross_entropy: 2.5578792095184326 +[2025-04-29 10:51:41,296][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 0.7951648235321045, cross_entropy: 0.7951648235321045 +[2025-04-29 10:51:42,425][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.2160282135009766, cross_entropy: 2.2160282135009766 +[2025-04-29 10:51:45,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 1.240365743637085, cross_entropy: 1.240365743637085 +[2025-04-29 10:51:46,773][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.7850031852722168, cross_entropy: 1.7850031852722168 +[2025-04-29 10:51:49,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.7163190841674805, cross_entropy: 2.7163190841674805 +[2025-04-29 10:51:50,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.6566718816757202, cross_entropy: 0.6566718816757202 +[2025-04-29 10:51:53,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 3.01552152633667, cross_entropy: 3.01552152633667 +[2025-04-29 10:51:54,105][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.226348876953125, cross_entropy: 1.226348876953125 +[2025-04-29 10:51:57,056][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 2.6529388427734375, cross_entropy: 2.6529388427734375 +[2025-04-29 10:51:57,898][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 1.0322973728179932, cross_entropy: 1.0322973728179932 +[2025-04-29 10:52:00,380][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 2.2794904708862305, cross_entropy: 2.2794904708862305 +[2025-04-29 10:52:01,480][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 2.2126293182373047, cross_entropy: 2.2126293182373047 +[2025-04-29 10:52:04,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 0.9551833868026733, cross_entropy: 0.9551833868026733 +[2025-04-29 10:52:05,316][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 2.431035041809082, cross_entropy: 2.431035041809082 +[2025-04-29 10:52:07,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.694218397140503, cross_entropy: 1.694218397140503 +[2025-04-29 10:52:08,666][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 2.680138111114502, cross_entropy: 2.680138111114502 +[2025-04-29 10:52:09,872][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 2.371580123901367, cross_entropy: 2.371580123901367 +[2025-04-29 10:52:10,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.36151123046875, cross_entropy: 2.36151123046875 +[2025-04-29 10:54:35,432][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.6393829584121704, cross_entropy: 1.6393829584121704 +[2025-04-29 10:54:35,433][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.01361882686615, cross_entropy: 1.01361882686615 +[2025-04-29 10:54:36,291][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 10:54:36,782][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch7.pth. +[2025-04-29 10:54:37,596][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 10:54:41,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 0.6448760032653809, cross_entropy: 0.6448760032653809 +[2025-04-29 10:54:42,808][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 1.1854578256607056, cross_entropy: 1.1854578256607056 +[2025-04-29 10:54:45,576][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 0.9386035203933716, cross_entropy: 0.9386035203933716 +[2025-04-29 10:54:46,415][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.1919031143188477, cross_entropy: 2.1919031143188477 +[2025-04-29 10:54:48,741][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.4374711513519287, cross_entropy: 1.4374711513519287 +[2025-04-29 10:54:49,578][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 2.3426594734191895, cross_entropy: 2.3426594734191895 +[2025-04-29 10:54:52,246][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.7662642002105713, cross_entropy: 0.7662642002105713 +[2025-04-29 10:54:53,093][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 1.9672455787658691, cross_entropy: 1.9672455787658691 +[2025-04-29 10:54:55,209][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.4097241163253784, cross_entropy: 1.4097241163253784 +[2025-04-29 10:54:56,044][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.982064127922058, cross_entropy: 1.982064127922058 +[2025-04-29 10:54:58,262][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 0.5107505321502686, cross_entropy: 0.5107505321502686 +[2025-04-29 10:54:59,097][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.7007863521575928, cross_entropy: 0.7007863521575928 +[2025-04-29 10:55:02,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 1.9957833290100098, cross_entropy: 1.9957833290100098 +[2025-04-29 10:55:03,508][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.1921889781951904, cross_entropy: 2.1921889781951904 +[2025-04-29 10:55:06,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 1.448183298110962, cross_entropy: 1.448183298110962 +[2025-04-29 10:55:07,763][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 2.1908984184265137, cross_entropy: 2.1908984184265137 +[2025-04-29 10:55:11,026][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 0.9557796716690063, cross_entropy: 0.9557796716690063 +[2025-04-29 10:55:11,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 0.770912766456604, cross_entropy: 0.770912766456604 +[2025-04-29 10:55:14,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 1.0649895668029785, cross_entropy: 1.0649895668029785 +[2025-04-29 10:55:15,082][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.737947702407837, cross_entropy: 1.737947702407837 +[2025-04-29 10:55:17,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 0.7608861327171326, cross_entropy: 0.7608861327171326 +[2025-04-29 10:55:18,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 1.2227081060409546, cross_entropy: 1.2227081060409546 +[2025-04-29 10:55:20,538][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 0.9705425500869751, cross_entropy: 0.9705425500869751 +[2025-04-29 10:55:21,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 0.8723983764648438, cross_entropy: 0.8723983764648438 +[2025-04-29 10:55:23,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 1.4953382015228271, cross_entropy: 1.4953382015228271 +[2025-04-29 10:55:24,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 0.8045660257339478, cross_entropy: 0.8045660257339478 +[2025-04-29 10:55:26,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.834452748298645, cross_entropy: 0.834452748298645 +[2025-04-29 10:55:27,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 0.7073098421096802, cross_entropy: 0.7073098421096802 +[2025-04-29 10:55:30,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 2.1038389205932617, cross_entropy: 2.1038389205932617 +[2025-04-29 10:55:31,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.018436312675476, cross_entropy: 1.018436312675476 +[2025-04-29 10:55:33,539][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.7070174217224121, cross_entropy: 0.7070174217224121 +[2025-04-29 10:55:34,355][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 0.8364111185073853, cross_entropy: 0.8364111185073853 +[2025-04-29 10:55:37,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 0.7572654485702515, cross_entropy: 0.7572654485702515 +[2025-04-29 10:55:38,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 0.8268386125564575, cross_entropy: 0.8268386125564575 +[2025-04-29 10:55:40,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 0.8129076361656189, cross_entropy: 0.8129076361656189 +[2025-04-29 10:55:41,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 0.7153112292289734, cross_entropy: 0.7153112292289734 +[2025-04-29 10:55:43,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.3612732887268066, cross_entropy: 2.3612732887268066 +[2025-04-29 10:55:43,919][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.7229626178741455, cross_entropy: 2.7229626178741455 +[2025-04-29 10:55:45,792][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.6665284633636475, cross_entropy: 1.6665284633636475 +[2025-04-29 10:55:46,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.376268744468689, cross_entropy: 1.376268744468689 +[2025-04-29 10:55:48,468][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 0.7885320782661438, cross_entropy: 0.7885320782661438 +[2025-04-29 10:55:49,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.2774144411087036, cross_entropy: 1.2774144411087036 +[2025-04-29 10:55:51,468][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 2.717291831970215, cross_entropy: 2.717291831970215 +[2025-04-29 10:55:52,316][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 2.6025233268737793, cross_entropy: 2.6025233268737793 +[2025-04-29 10:55:54,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 0.8982496857643127, cross_entropy: 0.8982496857643127 +[2025-04-29 10:55:55,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 1.9718127250671387, cross_entropy: 1.9718127250671387 +[2025-04-29 10:55:57,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 0.8863934278488159, cross_entropy: 0.8863934278488159 +[2025-04-29 10:55:58,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 1.417597770690918, cross_entropy: 1.417597770690918 +[2025-04-29 10:56:00,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.1022965908050537, cross_entropy: 2.1022965908050537 +[2025-04-29 10:56:01,740][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 0.8898829817771912, cross_entropy: 0.8898829817771912 +[2025-04-29 10:56:05,035][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.437093734741211, cross_entropy: 2.437093734741211 +[2025-04-29 10:56:05,881][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 2.2949538230895996, cross_entropy: 2.2949538230895996 +[2025-04-29 10:56:07,934][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.7847673892974854, cross_entropy: 0.7847673892974854 +[2025-04-29 10:56:08,774][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.5238595008850098, cross_entropy: 1.5238595008850098 +[2025-04-29 10:56:11,278][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 1.6004786491394043, cross_entropy: 1.6004786491394043 +[2025-04-29 10:56:12,095][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 2.094602584838867, cross_entropy: 2.094602584838867 +[2025-04-29 10:56:14,081][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 0.5066794753074646, cross_entropy: 0.5066794753074646 +[2025-04-29 10:56:14,924][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 0.6592113971710205, cross_entropy: 0.6592113971710205 +[2025-04-29 10:56:17,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 1.574157953262329, cross_entropy: 1.574157953262329 +[2025-04-29 10:56:17,889][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.89288330078125, cross_entropy: 0.89288330078125 +[2025-04-29 10:56:19,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 0.4971087574958801, cross_entropy: 0.4971087574958801 +[2025-04-29 10:56:20,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 2.218266010284424, cross_entropy: 2.218266010284424 +[2025-04-29 10:56:22,419][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.3453586101531982, cross_entropy: 2.3453586101531982 +[2025-04-29 10:56:23,228][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 1.7478935718536377, cross_entropy: 1.7478935718536377 +[2025-04-29 10:56:25,642][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.462745189666748, cross_entropy: 2.462745189666748 +[2025-04-29 10:56:26,477][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 1.8867931365966797, cross_entropy: 1.8867931365966797 +[2025-04-29 10:56:28,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.1662254333496094, cross_entropy: 2.1662254333496094 +[2025-04-29 10:56:29,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 0.4912671446800232, cross_entropy: 0.4912671446800232 +[2025-04-29 10:56:31,675][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 0.7265632152557373, cross_entropy: 0.7265632152557373 +[2025-04-29 10:56:32,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 0.5213544368743896, cross_entropy: 0.5213544368743896 +[2025-04-29 10:56:34,293][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.609224796295166, cross_entropy: 1.609224796295166 +[2025-04-29 10:56:35,134][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 0.6777489185333252, cross_entropy: 0.6777489185333252 +[2025-04-29 10:56:37,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.053705096244812, cross_entropy: 1.053705096244812 +[2025-04-29 10:56:38,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.108453392982483, cross_entropy: 1.108453392982483 +[2025-04-29 10:56:40,407][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 0.8571881055831909, cross_entropy: 0.8571881055831909 +[2025-04-29 10:56:41,220][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.284723997116089, cross_entropy: 2.284723997116089 +[2025-04-29 10:56:43,115][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.001344919204712, cross_entropy: 1.001344919204712 +[2025-04-29 10:56:43,953][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.0614511966705322, cross_entropy: 1.0614511966705322 +[2025-04-29 10:56:46,317][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 0.6672744750976562, cross_entropy: 0.6672744750976562 +[2025-04-29 10:56:47,154][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 1.2684900760650635, cross_entropy: 1.2684900760650635 +[2025-04-29 10:56:48,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 0.7560093402862549, cross_entropy: 0.7560093402862549 +[2025-04-29 10:56:49,754][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.2530128955841064, cross_entropy: 1.2530128955841064 +[2025-04-29 10:56:51,373][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 1.4311946630477905, cross_entropy: 1.4311946630477905 +[2025-04-29 10:56:52,516][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.6772682666778564, cross_entropy: 1.6772682666778564 +[2025-04-29 10:56:54,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 0.8085232973098755, cross_entropy: 0.8085232973098755 +[2025-04-29 10:56:55,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 1.8016716241836548, cross_entropy: 1.8016716241836548 +[2025-04-29 10:56:57,413][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.5820274353027344, cross_entropy: 2.5820274353027344 +[2025-04-29 10:56:58,295][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.0448079109191895, cross_entropy: 2.0448079109191895 +[2025-04-29 10:57:00,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 2.4030160903930664, cross_entropy: 2.4030160903930664 +[2025-04-29 10:57:01,076][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 2.968566656112671, cross_entropy: 2.968566656112671 +[2025-04-29 10:57:03,077][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.817974090576172, cross_entropy: 2.817974090576172 +[2025-04-29 10:57:03,915][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 2.635465145111084, cross_entropy: 2.635465145111084 +[2025-04-29 10:57:05,701][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 2.7009236812591553, cross_entropy: 2.7009236812591553 +[2025-04-29 10:57:06,601][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.450408935546875, cross_entropy: 2.450408935546875 +[2025-04-29 10:57:09,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 2.5809402465820312, cross_entropy: 2.5809402465820312 +[2025-04-29 10:57:09,869][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 2.5327887535095215, cross_entropy: 2.5327887535095215 +[2025-04-29 10:57:11,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.650096893310547, cross_entropy: 2.650096893310547 +[2025-04-29 10:57:12,282][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 0.6968221664428711, cross_entropy: 0.6968221664428711 +[2025-04-29 10:57:14,322][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.3911761045455933, cross_entropy: 1.3911761045455933 +[2025-04-29 10:57:15,199][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.128071904182434, cross_entropy: 1.128071904182434 +[2025-04-29 10:57:17,278][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.634915351867676, cross_entropy: 2.634915351867676 +[2025-04-29 10:57:18,148][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 1.34307861328125, cross_entropy: 1.34307861328125 +[2025-04-29 10:57:20,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.140869140625, cross_entropy: 2.140869140625 +[2025-04-29 10:57:21,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 2.4246504306793213, cross_entropy: 2.4246504306793213 +[2025-04-29 10:57:22,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 0.720934271812439, cross_entropy: 0.720934271812439 +[2025-04-29 10:57:23,660][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 0.612545371055603, cross_entropy: 0.612545371055603 +[2025-04-29 10:57:25,362][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 0.6740459203720093, cross_entropy: 0.6740459203720093 +[2025-04-29 10:57:26,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 0.7503244280815125, cross_entropy: 0.7503244280815125 +[2025-04-29 10:57:28,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.1494057178497314, cross_entropy: 1.1494057178497314 +[2025-04-29 10:57:29,402][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.472689151763916, cross_entropy: 2.472689151763916 +[2025-04-29 10:57:30,931][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 0.9069616794586182, cross_entropy: 0.9069616794586182 +[2025-04-29 10:57:32,749][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 0.6399780511856079, cross_entropy: 0.6399780511856079 +[2025-04-29 10:57:33,765][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 0.7431328296661377, cross_entropy: 0.7431328296661377 +[2025-04-29 10:57:36,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 2.1104979515075684, cross_entropy: 2.1104979515075684 +[2025-04-29 10:57:37,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 1.2172925472259521, cross_entropy: 1.2172925472259521 +[2025-04-29 10:57:40,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 2.6640172004699707, cross_entropy: 2.6640172004699707 +[2025-04-29 10:57:40,840][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 1.3010778427124023, cross_entropy: 1.3010778427124023 +[2025-04-29 10:57:43,117][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 0.9548654556274414, cross_entropy: 0.9548654556274414 +[2025-04-29 10:57:43,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 0.959406316280365, cross_entropy: 0.959406316280365 +[2025-04-29 10:57:45,701][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 0.7887914180755615, cross_entropy: 0.7887914180755615 +[2025-04-29 10:57:46,534][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 1.8677055835723877, cross_entropy: 1.8677055835723877 +[2025-04-29 10:57:48,703][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 0.8250805735588074, cross_entropy: 0.8250805735588074 +[2025-04-29 10:57:49,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 0.7871059775352478, cross_entropy: 0.7871059775352478 +[2025-04-29 10:57:51,855][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.228672742843628, cross_entropy: 1.228672742843628 +[2025-04-29 10:57:52,664][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.6632364988327026, cross_entropy: 1.6632364988327026 +[2025-04-29 10:57:54,634][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.7216460704803467, cross_entropy: 1.7216460704803467 +[2025-04-29 10:57:55,465][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 1.356968879699707, cross_entropy: 1.356968879699707 +[2025-04-29 10:57:57,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 0.5411081910133362, cross_entropy: 0.5411081910133362 +[2025-04-29 10:57:57,818][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.4116164445877075, cross_entropy: 1.4116164445877075 +[2025-04-29 10:57:59,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 2.4657204151153564, cross_entropy: 2.4657204151153564 +[2025-04-29 10:58:00,612][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 0.46695175766944885, cross_entropy: 0.46695175766944885 +[2025-04-29 10:58:02,632][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 0.7234579920768738, cross_entropy: 0.7234579920768738 +[2025-04-29 10:58:03,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 0.9784269332885742, cross_entropy: 0.9784269332885742 +[2025-04-29 10:58:06,004][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.310942530632019, cross_entropy: 1.310942530632019 +[2025-04-29 10:58:06,836][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.6719605922698975, cross_entropy: 2.6719605922698975 +[2025-04-29 10:58:08,822][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 1.0083746910095215, cross_entropy: 1.0083746910095215 +[2025-04-29 10:58:09,656][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 0.9798141717910767, cross_entropy: 0.9798141717910767 +[2025-04-29 10:58:11,956][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 1.1384706497192383, cross_entropy: 1.1384706497192383 +[2025-04-29 10:58:12,791][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 1.0882587432861328, cross_entropy: 1.0882587432861328 +[2025-04-29 10:58:14,663][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 2.3465018272399902, cross_entropy: 2.3465018272399902 +[2025-04-29 10:58:15,508][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 0.8793714642524719, cross_entropy: 0.8793714642524719 +[2025-04-29 10:58:17,964][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.3241777420043945, cross_entropy: 2.3241777420043945 +[2025-04-29 10:58:18,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 0.9433652758598328, cross_entropy: 0.9433652758598328 +[2025-04-29 10:58:20,176][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.243889331817627, cross_entropy: 2.243889331817627 +[2025-04-29 10:58:21,013][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 0.9447032809257507, cross_entropy: 0.9447032809257507 +[2025-04-29 10:58:22,865][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 1.0204750299453735, cross_entropy: 1.0204750299453735 +[2025-04-29 10:58:23,699][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.6672534942626953, cross_entropy: 1.6672534942626953 +[2025-04-29 10:58:25,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 2.6309430599212646, cross_entropy: 2.6309430599212646 +[2025-04-29 10:58:26,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 2.7882795333862305, cross_entropy: 2.7882795333862305 +[2025-04-29 10:58:28,192][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 0.6058523654937744, cross_entropy: 0.6058523654937744 +[2025-04-29 10:58:29,075][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 1.4063187837600708, cross_entropy: 1.4063187837600708 +[2025-04-29 10:58:30,947][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 2.5889265537261963, cross_entropy: 2.5889265537261963 +[2025-04-29 10:58:31,757][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.5947597026824951, cross_entropy: 1.5947597026824951 +[2025-04-29 10:58:33,498][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.297008991241455, cross_entropy: 1.297008991241455 +[2025-04-29 10:58:34,955][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 0.5098240971565247, cross_entropy: 0.5098240971565247 +[2025-04-29 10:58:36,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.2263884544372559, cross_entropy: 1.2263884544372559 +[2025-04-29 10:58:37,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 0.6581531763076782, cross_entropy: 0.6581531763076782 +[2025-04-29 10:58:38,647][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 1.25782310962677, cross_entropy: 1.25782310962677 +[2025-04-29 10:58:40,340][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 0.8853400945663452, cross_entropy: 0.8853400945663452 +[2025-04-29 10:58:42,098][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 0.8233134746551514, cross_entropy: 0.8233134746551514 +[2025-04-29 10:58:43,070][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 2.2123937606811523, cross_entropy: 2.2123937606811523 +[2025-04-29 10:58:45,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 2.459402322769165, cross_entropy: 2.459402322769165 +[2025-04-29 10:58:46,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 0.9884160161018372, cross_entropy: 0.9884160161018372 +[2025-04-29 10:58:48,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 1.5716192722320557, cross_entropy: 1.5716192722320557 +[2025-04-29 10:58:49,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.5037460327148438, cross_entropy: 2.5037460327148438 +[2025-04-29 10:58:51,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.0619618892669678, cross_entropy: 1.0619618892669678 +[2025-04-29 10:58:52,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 1.585634708404541, cross_entropy: 1.585634708404541 +[2025-04-29 10:58:53,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 0.8371911644935608, cross_entropy: 0.8371911644935608 +[2025-04-29 10:58:56,436][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.88637638092041, cross_entropy: 2.88637638092041 +[2025-04-29 10:58:57,271][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.0384763479232788, cross_entropy: 1.0384763479232788 +[2025-04-29 10:58:59,886][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.0978400707244873, cross_entropy: 1.0978400707244873 +[2025-04-29 10:59:00,724][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 0.6206090450286865, cross_entropy: 0.6206090450286865 +[2025-04-29 10:59:02,286][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.758439540863037, cross_entropy: 2.758439540863037 +[2025-04-29 10:59:03,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 2.667487144470215, cross_entropy: 2.667487144470215 +[2025-04-29 10:59:05,524][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 1.4058994054794312, cross_entropy: 1.4058994054794312 +[2025-04-29 10:59:06,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.6977053880691528, cross_entropy: 0.6977053880691528 +[2025-04-29 10:59:08,330][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 0.509680449962616, cross_entropy: 0.509680449962616 +[2025-04-29 10:59:09,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.6213035583496094, cross_entropy: 2.6213035583496094 +[2025-04-29 10:59:11,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.7445768117904663, cross_entropy: 1.7445768117904663 +[2025-04-29 10:59:12,559][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.3231663703918457, cross_entropy: 2.3231663703918457 +[2025-04-29 10:59:14,400][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.0875329971313477, cross_entropy: 2.0875329971313477 +[2025-04-29 10:59:15,612][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 1.0189932584762573, cross_entropy: 1.0189932584762573 +[2025-04-29 10:59:17,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 0.6820722222328186, cross_entropy: 0.6820722222328186 +[2025-04-29 10:59:18,693][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 0.5812963247299194, cross_entropy: 0.5812963247299194 +[2025-04-29 10:59:20,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 1.4618511199951172, cross_entropy: 1.4618511199951172 +[2025-04-29 10:59:21,564][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 0.8411147594451904, cross_entropy: 0.8411147594451904 +[2025-04-29 10:59:23,985][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 2.7041375637054443, cross_entropy: 2.7041375637054443 +[2025-04-29 10:59:24,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 1.9926705360412598, cross_entropy: 1.9926705360412598 +[2025-04-29 10:59:26,993][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 0.8146646022796631, cross_entropy: 0.8146646022796631 +[2025-04-29 10:59:27,824][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 1.0494587421417236, cross_entropy: 1.0494587421417236 +[2025-04-29 10:59:29,431][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.545163631439209, cross_entropy: 2.545163631439209 +[2025-04-29 10:59:30,287][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.1036992073059082, cross_entropy: 1.1036992073059082 +[2025-04-29 10:59:32,469][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 0.830683708190918, cross_entropy: 0.830683708190918 +[2025-04-29 10:59:33,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 0.6116091012954712, cross_entropy: 0.6116091012954712 +[2025-04-29 10:59:35,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 1.8055129051208496, cross_entropy: 1.8055129051208496 +[2025-04-29 10:59:36,583][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 0.716715931892395, cross_entropy: 0.716715931892395 +[2025-04-29 10:59:37,948][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 0.8305726051330566, cross_entropy: 0.8305726051330566 +[2025-04-29 10:59:38,770][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 0.679413914680481, cross_entropy: 0.679413914680481 +[2025-04-29 10:59:40,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 1.8043570518493652, cross_entropy: 1.8043570518493652 +[2025-04-29 10:59:41,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.2106525897979736, cross_entropy: 1.2106525897979736 +[2025-04-29 10:59:43,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.7243635654449463, cross_entropy: 1.7243635654449463 +[2025-04-29 10:59:44,842][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 1.3254033327102661, cross_entropy: 1.3254033327102661 +[2025-04-29 10:59:46,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 0.6980250477790833, cross_entropy: 0.6980250477790833 +[2025-04-29 10:59:47,855][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 1.226367712020874, cross_entropy: 1.226367712020874 +[2025-04-29 10:59:50,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 2.4620790481567383, cross_entropy: 2.4620790481567383 +[2025-04-29 10:59:51,042][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 2.240196466445923, cross_entropy: 2.240196466445923 +[2025-04-29 10:59:52,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 0.8296709656715393, cross_entropy: 0.8296709656715393 +[2025-04-29 10:59:53,710][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.1531660556793213, cross_entropy: 1.1531660556793213 +[2025-04-29 10:59:55,567][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 0.8800438046455383, cross_entropy: 0.8800438046455383 +[2025-04-29 10:59:56,451][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 0.8884228467941284, cross_entropy: 0.8884228467941284 +[2025-04-29 10:59:58,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 0.5408430695533752, cross_entropy: 0.5408430695533752 +[2025-04-29 10:59:59,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.6928205490112305, cross_entropy: 2.6928205490112305 +[2025-04-29 11:00:02,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 0.8055891990661621, cross_entropy: 0.8055891990661621 +[2025-04-29 11:00:02,834][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.472013235092163, cross_entropy: 2.472013235092163 +[2025-04-29 11:00:05,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.669121265411377, cross_entropy: 2.669121265411377 +[2025-04-29 11:00:05,966][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 0.7311279773712158, cross_entropy: 0.7311279773712158 +[2025-04-29 11:00:08,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 1.017949104309082, cross_entropy: 1.017949104309082 +[2025-04-29 11:00:09,073][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 0.9783572554588318, cross_entropy: 0.9783572554588318 +[2025-04-29 11:00:11,211][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 1.0524994134902954, cross_entropy: 1.0524994134902954 +[2025-04-29 11:00:12,056][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.2514305114746094, cross_entropy: 2.2514305114746094 +[2025-04-29 11:00:14,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 1.4326586723327637, cross_entropy: 1.4326586723327637 +[2025-04-29 11:00:15,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 1.9762957096099854, cross_entropy: 1.9762957096099854 +[2025-04-29 11:00:17,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 1.4167661666870117, cross_entropy: 1.4167661666870117 +[2025-04-29 11:00:17,951][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 0.8492171764373779, cross_entropy: 0.8492171764373779 +[2025-04-29 11:00:19,585][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.246441125869751, cross_entropy: 1.246441125869751 +[2025-04-29 11:00:20,424][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.7134509086608887, cross_entropy: 2.7134509086608887 +[2025-04-29 11:00:22,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.5114339590072632, cross_entropy: 1.5114339590072632 +[2025-04-29 11:00:23,728][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 0.7447935342788696, cross_entropy: 0.7447935342788696 +[2025-04-29 11:00:26,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.264613628387451, cross_entropy: 2.264613628387451 +[2025-04-29 11:00:27,142][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.7968827486038208, cross_entropy: 1.7968827486038208 +[2025-04-29 11:00:28,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 1.685625433921814, cross_entropy: 1.685625433921814 +[2025-04-29 11:00:29,688][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 0.5423462390899658, cross_entropy: 0.5423462390899658 +[2025-04-29 11:00:31,577][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 2.7990167140960693, cross_entropy: 2.7990167140960693 +[2025-04-29 11:00:32,423][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 3.0184624195098877, cross_entropy: 3.0184624195098877 +[2025-04-29 11:00:34,719][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.0205540657043457, cross_entropy: 1.0205540657043457 +[2025-04-29 11:00:35,554][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.235200881958008, cross_entropy: 2.235200881958008 +[2025-04-29 11:00:37,869][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.0508487224578857, cross_entropy: 1.0508487224578857 +[2025-04-29 11:00:38,678][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 0.8704270720481873, cross_entropy: 0.8704270720481873 +[2025-04-29 11:00:41,061][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 2.214813232421875, cross_entropy: 2.214813232421875 +[2025-04-29 11:00:41,906][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 2.481693744659424, cross_entropy: 2.481693744659424 +[2025-04-29 11:00:43,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 2.517080545425415, cross_entropy: 2.517080545425415 +[2025-04-29 11:00:44,493][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 1.898984670639038, cross_entropy: 1.898984670639038 +[2025-04-29 11:00:47,316][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 0.6494200825691223, cross_entropy: 0.6494200825691223 +[2025-04-29 11:00:48,153][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 2.554039478302002, cross_entropy: 2.554039478302002 +[2025-04-29 11:00:50,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.74314546585083, cross_entropy: 2.74314546585083 +[2025-04-29 11:00:51,006][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.6839685440063477, cross_entropy: 2.6839685440063477 +[2025-04-29 11:00:53,855][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.7750275135040283, cross_entropy: 1.7750275135040283 +[2025-04-29 11:00:54,667][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.467679738998413, cross_entropy: 1.467679738998413 +[2025-04-29 11:00:56,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.1384727954864502, cross_entropy: 1.1384727954864502 +[2025-04-29 11:00:57,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.0389466285705566, cross_entropy: 2.0389466285705566 +[2025-04-29 11:00:58,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.192615032196045, cross_entropy: 2.192615032196045 +[2025-04-29 11:00:59,731][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.7302019596099854, cross_entropy: 1.7302019596099854 +[2025-04-29 11:01:01,662][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.7396628856658936, cross_entropy: 1.7396628856658936 +[2025-04-29 11:01:02,501][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.2749202251434326, cross_entropy: 2.2749202251434326 +[2025-04-29 11:01:04,039][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.346492290496826, cross_entropy: 2.346492290496826 +[2025-04-29 11:01:04,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.244478702545166, cross_entropy: 2.244478702545166 +[2025-04-29 11:01:06,716][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 2.239974021911621, cross_entropy: 2.239974021911621 +[2025-04-29 11:01:07,598][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.480351209640503, cross_entropy: 1.480351209640503 +[2025-04-29 11:01:09,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 2.0119340419769287, cross_entropy: 2.0119340419769287 +[2025-04-29 11:01:10,542][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 0.9941254258155823, cross_entropy: 0.9941254258155823 +[2025-04-29 11:01:12,664][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 2.3135509490966797, cross_entropy: 2.3135509490966797 +[2025-04-29 11:01:13,998][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.0082855224609375, cross_entropy: 1.0082855224609375 +[2025-04-29 11:01:15,735][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 2.4216461181640625, cross_entropy: 2.4216461181640625 +[2025-04-29 11:01:17,177][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 2.5662686824798584, cross_entropy: 2.5662686824798584 +[2025-04-29 11:01:19,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.0151355266571045, cross_entropy: 2.0151355266571045 +[2025-04-29 11:01:19,987][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 2.375603199005127, cross_entropy: 2.375603199005127 +[2025-04-29 11:01:21,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.8184871673583984, cross_entropy: 1.8184871673583984 +[2025-04-29 11:01:22,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 0.4482109844684601, cross_entropy: 0.4482109844684601 +[2025-04-29 11:01:25,280][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 0.8407520055770874, cross_entropy: 0.8407520055770874 +[2025-04-29 11:01:26,159][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.360863447189331, cross_entropy: 2.360863447189331 +[2025-04-29 11:01:27,670][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 2.2615060806274414, cross_entropy: 2.2615060806274414 +[2025-04-29 11:01:29,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.407787561416626, cross_entropy: 2.407787561416626 +[2025-04-29 11:01:31,191][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 0.6460475921630859, cross_entropy: 0.6460475921630859 +[2025-04-29 11:01:32,169][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.5109734535217285, cross_entropy: 2.5109734535217285 +[2025-04-29 11:01:33,889][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.272068977355957, cross_entropy: 2.272068977355957 +[2025-04-29 11:01:35,448][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 0.7512834072113037, cross_entropy: 0.7512834072113037 +[2025-04-29 11:01:37,139][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.1611037254333496, cross_entropy: 1.1611037254333496 +[2025-04-29 11:01:38,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.7109425067901611, cross_entropy: 1.7109425067901611 +[2025-04-29 11:01:39,756][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 2.354832410812378, cross_entropy: 2.354832410812378 +[2025-04-29 11:01:40,628][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 1.5185532569885254, cross_entropy: 1.5185532569885254 +[2025-04-29 11:01:42,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 0.8049032688140869, cross_entropy: 0.8049032688140869 +[2025-04-29 11:01:43,994][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 1.5942943096160889, cross_entropy: 1.5942943096160889 +[2025-04-29 11:01:45,758][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.375303030014038, cross_entropy: 2.375303030014038 +[2025-04-29 11:01:46,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.6451668739318848, cross_entropy: 2.6451668739318848 +[2025-04-29 11:01:48,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 1.8878378868103027, cross_entropy: 1.8878378868103027 +[2025-04-29 11:01:49,428][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.7316231727600098, cross_entropy: 2.7316231727600098 +[2025-04-29 11:01:51,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 2.397521734237671, cross_entropy: 2.397521734237671 +[2025-04-29 11:01:52,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.4764869213104248, cross_entropy: 1.4764869213104248 +[2025-04-29 11:01:54,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 1.7455744743347168, cross_entropy: 1.7455744743347168 +[2025-04-29 11:01:55,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.121734380722046, cross_entropy: 1.121734380722046 +[2025-04-29 11:01:57,826][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 0.5172953009605408, cross_entropy: 0.5172953009605408 +[2025-04-29 11:01:58,666][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 1.4288959503173828, cross_entropy: 1.4288959503173828 +[2025-04-29 11:02:01,036][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 2.219062328338623, cross_entropy: 2.219062328338623 +[2025-04-29 11:02:01,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 1.7215138673782349, cross_entropy: 1.7215138673782349 +[2025-04-29 11:02:04,069][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 2.1006669998168945, cross_entropy: 2.1006669998168945 +[2025-04-29 11:02:04,905][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 2.5276734828948975, cross_entropy: 2.5276734828948975 +[2025-04-29 11:02:06,863][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.276279926300049, cross_entropy: 2.276279926300049 +[2025-04-29 11:02:07,698][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.1949124336242676, cross_entropy: 2.1949124336242676 +[2025-04-29 11:02:09,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.7397270202636719, cross_entropy: 1.7397270202636719 +[2025-04-29 11:02:10,349][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.882981300354004, cross_entropy: 2.882981300354004 +[2025-04-29 11:02:12,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.0731568336486816, cross_entropy: 2.0731568336486816 +[2025-04-29 11:02:13,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.4572036266326904, cross_entropy: 1.4572036266326904 +[2025-04-29 11:02:15,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 0.5295449495315552, cross_entropy: 0.5295449495315552 +[2025-04-29 11:02:15,964][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 1.0114085674285889, cross_entropy: 1.0114085674285889 +[2025-04-29 11:02:18,015][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 2.0864388942718506, cross_entropy: 2.0864388942718506 +[2025-04-29 11:02:18,869][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.684792399406433, cross_entropy: 1.684792399406433 +[2025-04-29 11:02:20,395][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 0.7658883929252625, cross_entropy: 0.7658883929252625 +[2025-04-29 11:02:21,235][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 2.7985899448394775, cross_entropy: 2.7985899448394775 +[2025-04-29 11:02:23,212][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 2.24356746673584, cross_entropy: 2.24356746673584 +[2025-04-29 11:02:24,059][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.3775824308395386, cross_entropy: 1.3775824308395386 +[2025-04-29 11:02:26,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 0.7594175934791565, cross_entropy: 0.7594175934791565 +[2025-04-29 11:02:27,290][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 2.916933298110962, cross_entropy: 2.916933298110962 +[2025-04-29 11:02:29,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 1.9800035953521729, cross_entropy: 1.9800035953521729 +[2025-04-29 11:02:30,227][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 0.9389233589172363, cross_entropy: 0.9389233589172363 +[2025-04-29 11:02:31,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.6374573111534119, cross_entropy: 0.6374573111534119 +[2025-04-29 11:02:32,942][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.4046945571899414, cross_entropy: 1.4046945571899414 +[2025-04-29 11:02:34,084][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.6051120758056641, cross_entropy: 0.6051120758056641 +[2025-04-29 11:02:35,760][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.5776925086975098, cross_entropy: 2.5776925086975098 +[2025-04-29 11:02:37,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 2.618109703063965, cross_entropy: 2.618109703063965 +[2025-04-29 11:02:38,882][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.0421390533447266, cross_entropy: 1.0421390533447266 +[2025-04-29 11:02:40,522][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.38633131980896, cross_entropy: 2.38633131980896 +[2025-04-29 11:02:41,492][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 2.0106325149536133, cross_entropy: 2.0106325149536133 +[2025-04-29 11:02:42,967][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 2.5511250495910645, cross_entropy: 2.5511250495910645 +[2025-04-29 11:02:44,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.8655939102172852, cross_entropy: 1.8655939102172852 +[2025-04-29 11:02:45,726][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.967341423034668, cross_entropy: 1.967341423034668 +[2025-04-29 11:02:48,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 1.2952216863632202, cross_entropy: 1.2952216863632202 +[2025-04-29 11:02:48,879][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 1.9270185232162476, cross_entropy: 1.9270185232162476 +[2025-04-29 11:02:50,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 2.184962272644043, cross_entropy: 2.184962272644043 +[2025-04-29 11:02:51,613][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.072490930557251, cross_entropy: 1.072490930557251 +[2025-04-29 11:02:54,708][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.2346456050872803, cross_entropy: 1.2346456050872803 +[2025-04-29 11:02:55,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 0.703166127204895, cross_entropy: 0.703166127204895 +[2025-04-29 11:02:57,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.7852160930633545, cross_entropy: 1.7852160930633545 +[2025-04-29 11:02:58,276][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.7351845502853394, cross_entropy: 1.7351845502853394 +[2025-04-29 11:03:00,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.1830264329910278, cross_entropy: 1.1830264329910278 +[2025-04-29 11:03:01,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 2.031531810760498, cross_entropy: 2.031531810760498 +[2025-04-29 11:03:03,138][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.576844334602356, cross_entropy: 0.576844334602356 +[2025-04-29 11:03:03,969][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 2.737105369567871, cross_entropy: 2.737105369567871 +[2025-04-29 11:03:06,210][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 3.046558380126953, cross_entropy: 3.046558380126953 +[2025-04-29 11:03:07,123][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 2.699070453643799, cross_entropy: 2.699070453643799 +[2025-04-29 11:03:09,524][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 1.485267996788025, cross_entropy: 1.485267996788025 +[2025-04-29 11:03:10,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 0.7034684419631958, cross_entropy: 0.7034684419631958 +[2025-04-29 11:03:11,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 0.8814298510551453, cross_entropy: 0.8814298510551453 +[2025-04-29 11:03:12,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.709434986114502, cross_entropy: 2.709434986114502 +[2025-04-29 11:03:14,070][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.0303508043289185, cross_entropy: 1.0303508043289185 +[2025-04-29 11:03:15,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 2.9105069637298584, cross_entropy: 2.9105069637298584 +[2025-04-29 11:03:17,578][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 1.5529358386993408, cross_entropy: 1.5529358386993408 +[2025-04-29 11:03:18,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.3355579376220703, cross_entropy: 2.3355579376220703 +[2025-04-29 11:03:20,599][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 0.8621079325675964, cross_entropy: 0.8621079325675964 +[2025-04-29 11:03:21,548][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 1.798532485961914, cross_entropy: 1.798532485961914 +[2025-04-29 11:03:23,567][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 0.6229836940765381, cross_entropy: 0.6229836940765381 +[2025-04-29 11:03:24,719][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 0.9607033729553223, cross_entropy: 0.9607033729553223 +[2025-04-29 11:03:27,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 0.6989860534667969, cross_entropy: 0.6989860534667969 +[2025-04-29 11:03:28,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 2.8290278911590576, cross_entropy: 2.8290278911590576 +[2025-04-29 11:03:30,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.609745502471924, cross_entropy: 2.609745502471924 +[2025-04-29 11:03:31,737][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 1.5797580480575562, cross_entropy: 1.5797580480575562 +[2025-04-29 11:03:32,793][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 0.6202145218849182, cross_entropy: 0.6202145218849182 +[2025-04-29 11:05:39,520][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.5646708011627197, cross_entropy: 1.5646708011627197 +[2025-04-29 11:05:39,521][BaseTrainer][INFO] - [Epoch 8/10] (validation) 0.9562171697616577, cross_entropy: 0.9562171697616577 +[2025-04-29 11:05:40,399][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 11:05:40,878][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch8.pth. +[2025-04-29 11:05:41,682][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 11:05:46,054][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.3459527492523193, cross_entropy: 1.3459527492523193 +[2025-04-29 11:05:46,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 0.8123019933700562, cross_entropy: 0.8123019933700562 +[2025-04-29 11:05:49,351][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 0.7569146752357483, cross_entropy: 0.7569146752357483 +[2025-04-29 11:05:50,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 0.929380476474762, cross_entropy: 0.929380476474762 +[2025-04-29 11:05:51,844][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 0.6893374919891357, cross_entropy: 0.6893374919891357 +[2025-04-29 11:05:52,674][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 0.747198760509491, cross_entropy: 0.747198760509491 +[2025-04-29 11:05:54,460][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 1.7001221179962158, cross_entropy: 1.7001221179962158 +[2025-04-29 11:05:55,293][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.4288835525512695, cross_entropy: 2.4288835525512695 +[2025-04-29 11:05:57,225][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 0.7612589597702026, cross_entropy: 0.7612589597702026 +[2025-04-29 11:05:58,036][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 2.4503464698791504, cross_entropy: 2.4503464698791504 +[2025-04-29 11:06:00,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 2.0181992053985596, cross_entropy: 2.0181992053985596 +[2025-04-29 11:06:01,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.7906566858291626, cross_entropy: 0.7906566858291626 +[2025-04-29 11:06:03,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.028151035308838, cross_entropy: 2.028151035308838 +[2025-04-29 11:06:04,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 2.328693389892578, cross_entropy: 2.328693389892578 +[2025-04-29 11:06:05,823][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.136323928833008, cross_entropy: 2.136323928833008 +[2025-04-29 11:06:06,668][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.47904735803604126, cross_entropy: 0.47904735803604126 +[2025-04-29 11:06:08,716][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 0.7499223947525024, cross_entropy: 0.7499223947525024 +[2025-04-29 11:06:09,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.4011383056640625, cross_entropy: 1.4011383056640625 +[2025-04-29 11:06:12,035][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.5223963260650635, cross_entropy: 1.5223963260650635 +[2025-04-29 11:06:12,875][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.8776912689208984, cross_entropy: 1.8776912689208984 +[2025-04-29 11:06:14,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 0.5420571565628052, cross_entropy: 0.5420571565628052 +[2025-04-29 11:06:15,752][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 0.9045121669769287, cross_entropy: 0.9045121669769287 +[2025-04-29 11:06:18,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.5602946281433105, cross_entropy: 2.5602946281433105 +[2025-04-29 11:06:19,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 0.7784870266914368, cross_entropy: 0.7784870266914368 +[2025-04-29 11:06:20,857][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 0.6408776640892029, cross_entropy: 0.6408776640892029 +[2025-04-29 11:06:21,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 1.2363768815994263, cross_entropy: 1.2363768815994263 +[2025-04-29 11:06:23,639][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 0.9676141142845154, cross_entropy: 0.9676141142845154 +[2025-04-29 11:06:24,448][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 0.7701542973518372, cross_entropy: 0.7701542973518372 +[2025-04-29 11:06:27,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.666135311126709, cross_entropy: 2.666135311126709 +[2025-04-29 11:06:28,288][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 0.887589156627655, cross_entropy: 0.887589156627655 +[2025-04-29 11:06:30,843][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.7956573963165283, cross_entropy: 2.7956573963165283 +[2025-04-29 11:06:31,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 0.6259560585021973, cross_entropy: 0.6259560585021973 +[2025-04-29 11:06:33,145][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 2.758718490600586, cross_entropy: 2.758718490600586 +[2025-04-29 11:06:33,953][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 0.7647900581359863, cross_entropy: 0.7647900581359863 +[2025-04-29 11:06:36,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 0.9333170652389526, cross_entropy: 0.9333170652389526 +[2025-04-29 11:06:37,522][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 0.7425599098205566, cross_entropy: 0.7425599098205566 +[2025-04-29 11:06:39,584][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 0.6216378808021545, cross_entropy: 0.6216378808021545 +[2025-04-29 11:06:40,426][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 1.620685338973999, cross_entropy: 1.620685338973999 +[2025-04-29 11:06:42,488][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.0881770849227905, cross_entropy: 1.0881770849227905 +[2025-04-29 11:06:43,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.3834879398345947, cross_entropy: 2.3834879398345947 +[2025-04-29 11:06:45,838][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 1.1572729349136353, cross_entropy: 1.1572729349136353 +[2025-04-29 11:06:46,651][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 1.2089142799377441, cross_entropy: 1.2089142799377441 +[2025-04-29 11:06:49,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 1.1241563558578491, cross_entropy: 1.1241563558578491 +[2025-04-29 11:06:50,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 2.4522993564605713, cross_entropy: 2.4522993564605713 +[2025-04-29 11:06:52,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 1.7959706783294678, cross_entropy: 1.7959706783294678 +[2025-04-29 11:06:52,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 1.2169153690338135, cross_entropy: 1.2169153690338135 +[2025-04-29 11:06:54,934][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 2.6590938568115234, cross_entropy: 2.6590938568115234 +[2025-04-29 11:06:55,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 0.7238882780075073, cross_entropy: 0.7238882780075073 +[2025-04-29 11:06:57,897][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 2.3060050010681152, cross_entropy: 2.3060050010681152 +[2025-04-29 11:06:58,707][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 2.1194937229156494, cross_entropy: 2.1194937229156494 +[2025-04-29 11:07:00,750][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 0.4441925585269928, cross_entropy: 0.4441925585269928 +[2025-04-29 11:07:01,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.4775091409683228, cross_entropy: 1.4775091409683228 +[2025-04-29 11:07:03,951][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 2.3505845069885254, cross_entropy: 2.3505845069885254 +[2025-04-29 11:07:04,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.8228802680969238, cross_entropy: 1.8228802680969238 +[2025-04-29 11:07:07,152][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 0.5193220973014832, cross_entropy: 0.5193220973014832 +[2025-04-29 11:07:07,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 0.5341491103172302, cross_entropy: 0.5341491103172302 +[2025-04-29 11:07:09,596][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 2.2084474563598633, cross_entropy: 2.2084474563598633 +[2025-04-29 11:07:10,434][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 0.7738121747970581, cross_entropy: 0.7738121747970581 +[2025-04-29 11:07:11,949][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.0029370784759521, cross_entropy: 1.0029370784759521 +[2025-04-29 11:07:12,760][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 0.9292779564857483, cross_entropy: 0.9292779564857483 +[2025-04-29 11:07:14,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 1.997124195098877, cross_entropy: 1.997124195098877 +[2025-04-29 11:07:15,742][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 0.5588780641555786, cross_entropy: 0.5588780641555786 +[2025-04-29 11:07:17,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 0.7401924729347229, cross_entropy: 0.7401924729347229 +[2025-04-29 11:07:18,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 0.5529180765151978, cross_entropy: 0.5529180765151978 +[2025-04-29 11:07:20,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.8544037342071533, cross_entropy: 2.8544037342071533 +[2025-04-29 11:07:21,094][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.5806512236595154, cross_entropy: 0.5806512236595154 +[2025-04-29 11:07:22,968][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.8439232110977173, cross_entropy: 0.8439232110977173 +[2025-04-29 11:07:23,833][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.6680562496185303, cross_entropy: 0.6680562496185303 +[2025-04-29 11:07:25,174][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 2.2985429763793945, cross_entropy: 2.2985429763793945 +[2025-04-29 11:07:26,145][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 0.526714563369751, cross_entropy: 0.526714563369751 +[2025-04-29 11:07:27,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 2.2567074298858643, cross_entropy: 2.2567074298858643 +[2025-04-29 11:07:29,321][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 0.5696901082992554, cross_entropy: 0.5696901082992554 +[2025-04-29 11:07:31,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 2.3189306259155273, cross_entropy: 2.3189306259155273 +[2025-04-29 11:07:32,094][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 0.9244252443313599, cross_entropy: 0.9244252443313599 +[2025-04-29 11:07:34,189][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 1.0124642848968506, cross_entropy: 1.0124642848968506 +[2025-04-29 11:07:35,059][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.013460159301758, cross_entropy: 2.013460159301758 +[2025-04-29 11:07:36,802][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 0.3801429271697998, cross_entropy: 0.3801429271697998 +[2025-04-29 11:07:37,668][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.6159422397613525, cross_entropy: 0.6159422397613525 +[2025-04-29 11:07:39,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 0.9427613615989685, cross_entropy: 0.9427613615989685 +[2025-04-29 11:07:40,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 0.5845714807510376, cross_entropy: 0.5845714807510376 +[2025-04-29 11:07:42,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 0.41214513778686523, cross_entropy: 0.41214513778686523 +[2025-04-29 11:07:43,803][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.6768313646316528, cross_entropy: 0.6768313646316528 +[2025-04-29 11:07:45,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 2.5492472648620605, cross_entropy: 2.5492472648620605 +[2025-04-29 11:07:46,474][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 0.651611328125, cross_entropy: 0.651611328125 +[2025-04-29 11:07:49,126][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.5961024761199951, cross_entropy: 1.5961024761199951 +[2025-04-29 11:07:49,967][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.55294930934906, cross_entropy: 1.55294930934906 +[2025-04-29 11:07:52,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 0.7511887550354004, cross_entropy: 0.7511887550354004 +[2025-04-29 11:07:53,100][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.1507357358932495, cross_entropy: 1.1507357358932495 +[2025-04-29 11:07:54,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 2.3887405395507812, cross_entropy: 2.3887405395507812 +[2025-04-29 11:07:55,818][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 1.069880485534668, cross_entropy: 1.069880485534668 +[2025-04-29 11:07:57,621][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.139742851257324, cross_entropy: 2.139742851257324 +[2025-04-29 11:07:58,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 1.1301571130752563, cross_entropy: 1.1301571130752563 +[2025-04-29 11:08:00,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 0.8258180618286133, cross_entropy: 0.8258180618286133 +[2025-04-29 11:08:00,905][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.853288471698761, cross_entropy: 0.853288471698761 +[2025-04-29 11:08:03,352][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.454747200012207, cross_entropy: 2.454747200012207 +[2025-04-29 11:08:04,164][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 2.448169708251953, cross_entropy: 2.448169708251953 +[2025-04-29 11:08:06,399][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 0.9749422073364258, cross_entropy: 0.9749422073364258 +[2025-04-29 11:08:07,210][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 2.5692641735076904, cross_entropy: 2.5692641735076904 +[2025-04-29 11:08:09,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.6080751419067383, cross_entropy: 1.6080751419067383 +[2025-04-29 11:08:09,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.688742756843567, cross_entropy: 1.688742756843567 +[2025-04-29 11:08:12,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.554931640625, cross_entropy: 2.554931640625 +[2025-04-29 11:08:12,917][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 1.1864155530929565, cross_entropy: 1.1864155530929565 +[2025-04-29 11:08:14,588][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 2.3182380199432373, cross_entropy: 2.3182380199432373 +[2025-04-29 11:08:15,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 0.36770790815353394, cross_entropy: 0.36770790815353394 +[2025-04-29 11:08:17,177][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 1.6393136978149414, cross_entropy: 1.6393136978149414 +[2025-04-29 11:08:18,035][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 0.9877245426177979, cross_entropy: 0.9877245426177979 +[2025-04-29 11:08:20,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.6836061477661133, cross_entropy: 2.6836061477661133 +[2025-04-29 11:08:21,233][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 2.2925610542297363, cross_entropy: 2.2925610542297363 +[2025-04-29 11:08:23,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 1.2703276872634888, cross_entropy: 1.2703276872634888 +[2025-04-29 11:08:24,302][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.7271899580955505, cross_entropy: 0.7271899580955505 +[2025-04-29 11:08:26,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 0.8062280416488647, cross_entropy: 0.8062280416488647 +[2025-04-29 11:08:27,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 1.143970012664795, cross_entropy: 1.143970012664795 +[2025-04-29 11:08:29,079][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 0.2857986092567444, cross_entropy: 0.2857986092567444 +[2025-04-29 11:08:31,254][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 0.35036465525627136, cross_entropy: 0.35036465525627136 +[2025-04-29 11:08:32,683][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.3063502311706543, cross_entropy: 2.3063502311706543 +[2025-04-29 11:08:33,665][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 0.6621075868606567, cross_entropy: 0.6621075868606567 +[2025-04-29 11:08:35,573][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 1.3828668594360352, cross_entropy: 1.3828668594360352 +[2025-04-29 11:08:36,450][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 0.4325979948043823, cross_entropy: 0.4325979948043823 +[2025-04-29 11:08:38,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 0.9172790050506592, cross_entropy: 0.9172790050506592 +[2025-04-29 11:08:39,635][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.6534953117370605, cross_entropy: 2.6534953117370605 +[2025-04-29 11:08:41,633][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 1.315258502960205, cross_entropy: 1.315258502960205 +[2025-04-29 11:08:42,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 0.7752948999404907, cross_entropy: 0.7752948999404907 +[2025-04-29 11:08:44,784][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.4393653869628906, cross_entropy: 2.4393653869628906 +[2025-04-29 11:08:45,756][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.1708641052246094, cross_entropy: 2.1708641052246094 +[2025-04-29 11:08:47,891][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.9645490646362305, cross_entropy: 1.9645490646362305 +[2025-04-29 11:08:48,899][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 2.1186397075653076, cross_entropy: 2.1186397075653076 +[2025-04-29 11:08:50,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 1.3459314107894897, cross_entropy: 1.3459314107894897 +[2025-04-29 11:08:51,800][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 0.6388342976570129, cross_entropy: 0.6388342976570129 +[2025-04-29 11:08:54,879][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 0.7861257195472717, cross_entropy: 0.7861257195472717 +[2025-04-29 11:08:55,736][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 1.6233060359954834, cross_entropy: 1.6233060359954834 +[2025-04-29 11:08:58,699][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 2.100983142852783, cross_entropy: 2.100983142852783 +[2025-04-29 11:08:59,544][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.1889777183532715, cross_entropy: 2.1889777183532715 +[2025-04-29 11:09:02,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.8583824634552002, cross_entropy: 1.8583824634552002 +[2025-04-29 11:09:02,878][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 0.5144234895706177, cross_entropy: 0.5144234895706177 +[2025-04-29 11:09:04,197][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.9991422891616821, cross_entropy: 1.9991422891616821 +[2025-04-29 11:09:05,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.1557834148406982, cross_entropy: 1.1557834148406982 +[2025-04-29 11:09:09,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 1.2347638607025146, cross_entropy: 1.2347638607025146 +[2025-04-29 11:09:09,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 1.402402639389038, cross_entropy: 1.402402639389038 +[2025-04-29 11:09:11,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 1.7801220417022705, cross_entropy: 1.7801220417022705 +[2025-04-29 11:09:12,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 1.6881641149520874, cross_entropy: 1.6881641149520874 +[2025-04-29 11:09:14,897][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 0.5238196849822998, cross_entropy: 0.5238196849822998 +[2025-04-29 11:09:15,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 1.7056927680969238, cross_entropy: 1.7056927680969238 +[2025-04-29 11:09:17,846][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 1.8819031715393066, cross_entropy: 1.8819031715393066 +[2025-04-29 11:09:18,659][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 1.0594041347503662, cross_entropy: 1.0594041347503662 +[2025-04-29 11:09:20,744][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 2.4792041778564453, cross_entropy: 2.4792041778564453 +[2025-04-29 11:09:21,554][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 1.670302152633667, cross_entropy: 1.670302152633667 +[2025-04-29 11:09:24,849][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 2.2335939407348633, cross_entropy: 2.2335939407348633 +[2025-04-29 11:09:25,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 2.412522792816162, cross_entropy: 2.412522792816162 +[2025-04-29 11:09:27,662][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.7078114748001099, cross_entropy: 0.7078114748001099 +[2025-04-29 11:09:28,498][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.6223912239074707, cross_entropy: 2.6223912239074707 +[2025-04-29 11:09:30,732][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 0.7095758318901062, cross_entropy: 0.7095758318901062 +[2025-04-29 11:09:31,543][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 1.5444637537002563, cross_entropy: 1.5444637537002563 +[2025-04-29 11:09:32,053][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/iteration3000.pth. +[2025-04-29 11:09:34,019][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 2.279249906539917, cross_entropy: 2.279249906539917 +[2025-04-29 11:09:34,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.711583375930786, cross_entropy: 2.711583375930786 +[2025-04-29 11:09:37,125][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 0.7489467859268188, cross_entropy: 0.7489467859268188 +[2025-04-29 11:09:37,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 0.6877566576004028, cross_entropy: 0.6877566576004028 +[2025-04-29 11:09:41,003][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 0.9327570199966431, cross_entropy: 0.9327570199966431 +[2025-04-29 11:09:41,838][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 0.6906914710998535, cross_entropy: 0.6906914710998535 +[2025-04-29 11:09:43,878][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 0.7224674224853516, cross_entropy: 0.7224674224853516 +[2025-04-29 11:09:44,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 0.6054928302764893, cross_entropy: 0.6054928302764893 +[2025-04-29 11:09:46,505][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 0.7638890743255615, cross_entropy: 0.7638890743255615 +[2025-04-29 11:09:47,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 1.2030709981918335, cross_entropy: 1.2030709981918335 +[2025-04-29 11:09:49,927][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 2.2910866737365723, cross_entropy: 2.2910866737365723 +[2025-04-29 11:09:50,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 0.9841588735580444, cross_entropy: 0.9841588735580444 +[2025-04-29 11:09:52,639][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.1072747707366943, cross_entropy: 2.1072747707366943 +[2025-04-29 11:09:53,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 2.05120849609375, cross_entropy: 2.05120849609375 +[2025-04-29 11:09:55,792][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.033475399017334, cross_entropy: 1.033475399017334 +[2025-04-29 11:09:56,627][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 0.9879007935523987, cross_entropy: 0.9879007935523987 +[2025-04-29 11:09:58,673][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.7583513855934143, cross_entropy: 0.7583513855934143 +[2025-04-29 11:09:59,510][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 0.8186978101730347, cross_entropy: 0.8186978101730347 +[2025-04-29 11:10:01,147][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 0.5695175528526306, cross_entropy: 0.5695175528526306 +[2025-04-29 11:10:01,984][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 0.9013615846633911, cross_entropy: 0.9013615846633911 +[2025-04-29 11:10:04,134][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.295346260070801, cross_entropy: 2.295346260070801 +[2025-04-29 11:10:04,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 0.6087747812271118, cross_entropy: 0.6087747812271118 +[2025-04-29 11:10:07,132][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 2.270059585571289, cross_entropy: 2.270059585571289 +[2025-04-29 11:10:07,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 2.225409507751465, cross_entropy: 2.225409507751465 +[2025-04-29 11:10:09,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 0.670423686504364, cross_entropy: 0.670423686504364 +[2025-04-29 11:10:10,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.0064194202423096, cross_entropy: 1.0064194202423096 +[2025-04-29 11:10:12,182][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 0.6348369121551514, cross_entropy: 0.6348369121551514 +[2025-04-29 11:10:12,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 0.975277304649353, cross_entropy: 0.975277304649353 +[2025-04-29 11:10:15,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.6422274112701416, cross_entropy: 2.6422274112701416 +[2025-04-29 11:10:16,234][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 2.3687939643859863, cross_entropy: 2.3687939643859863 +[2025-04-29 11:10:17,898][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 0.7540276050567627, cross_entropy: 0.7540276050567627 +[2025-04-29 11:10:18,740][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 1.5578569173812866, cross_entropy: 1.5578569173812866 +[2025-04-29 11:10:20,683][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 0.7288960814476013, cross_entropy: 0.7288960814476013 +[2025-04-29 11:10:21,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 1.567126989364624, cross_entropy: 1.567126989364624 +[2025-04-29 11:10:22,871][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.2593302726745605, cross_entropy: 2.2593302726745605 +[2025-04-29 11:10:23,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 1.066641092300415, cross_entropy: 1.066641092300415 +[2025-04-29 11:10:25,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 2.5394792556762695, cross_entropy: 2.5394792556762695 +[2025-04-29 11:10:26,660][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 0.43397247791290283, cross_entropy: 0.43397247791290283 +[2025-04-29 11:10:28,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 0.88251131772995, cross_entropy: 0.88251131772995 +[2025-04-29 11:10:29,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 0.9282631874084473, cross_entropy: 0.9282631874084473 +[2025-04-29 11:10:32,843][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.3180131912231445, cross_entropy: 2.3180131912231445 +[2025-04-29 11:10:33,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 2.140793800354004, cross_entropy: 2.140793800354004 +[2025-04-29 11:10:35,172][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 0.6153208017349243, cross_entropy: 0.6153208017349243 +[2025-04-29 11:10:36,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 2.611320972442627, cross_entropy: 2.611320972442627 +[2025-04-29 11:10:37,911][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 1.5998406410217285, cross_entropy: 1.5998406410217285 +[2025-04-29 11:10:38,747][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.9210686683654785, cross_entropy: 1.9210686683654785 +[2025-04-29 11:10:40,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 2.494431495666504, cross_entropy: 2.494431495666504 +[2025-04-29 11:10:41,446][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.997267246246338, cross_entropy: 1.997267246246338 +[2025-04-29 11:10:43,485][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.8413152694702148, cross_entropy: 0.8413152694702148 +[2025-04-29 11:10:44,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.5961004495620728, cross_entropy: 1.5961004495620728 +[2025-04-29 11:10:47,324][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.46844521164894104, cross_entropy: 0.46844521164894104 +[2025-04-29 11:10:48,157][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.4368200302124023, cross_entropy: 2.4368200302124023 +[2025-04-29 11:10:49,916][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 0.6787703037261963, cross_entropy: 0.6787703037261963 +[2025-04-29 11:10:50,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 0.8248201608657837, cross_entropy: 0.8248201608657837 +[2025-04-29 11:10:52,839][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.1767735481262207, cross_entropy: 2.1767735481262207 +[2025-04-29 11:10:53,682][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 0.8702406287193298, cross_entropy: 0.8702406287193298 +[2025-04-29 11:10:55,330][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 0.6158119440078735, cross_entropy: 0.6158119440078735 +[2025-04-29 11:10:56,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 2.8068883419036865, cross_entropy: 2.8068883419036865 +[2025-04-29 11:10:57,810][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.2583441734313965, cross_entropy: 2.2583441734313965 +[2025-04-29 11:10:58,645][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 2.664760112762451, cross_entropy: 2.664760112762451 +[2025-04-29 11:11:00,985][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 2.678917646408081, cross_entropy: 2.678917646408081 +[2025-04-29 11:11:01,825][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 0.9016947746276855, cross_entropy: 0.9016947746276855 +[2025-04-29 11:11:03,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.3006186485290527, cross_entropy: 1.3006186485290527 +[2025-04-29 11:11:04,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.3996210098266602, cross_entropy: 1.3996210098266602 +[2025-04-29 11:11:06,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.212179660797119, cross_entropy: 2.212179660797119 +[2025-04-29 11:11:07,238][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 0.7129842042922974, cross_entropy: 0.7129842042922974 +[2025-04-29 11:11:09,228][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 2.677929162979126, cross_entropy: 2.677929162979126 +[2025-04-29 11:11:10,118][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.089923858642578, cross_entropy: 2.089923858642578 +[2025-04-29 11:11:11,939][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 0.6906061172485352, cross_entropy: 0.6906061172485352 +[2025-04-29 11:11:13,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 1.9435231685638428, cross_entropy: 1.9435231685638428 +[2025-04-29 11:11:14,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 0.5508706569671631, cross_entropy: 0.5508706569671631 +[2025-04-29 11:11:16,657][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 0.6101357340812683, cross_entropy: 0.6101357340812683 +[2025-04-29 11:11:17,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 2.1935014724731445, cross_entropy: 2.1935014724731445 +[2025-04-29 11:11:19,492][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 0.711269199848175, cross_entropy: 0.711269199848175 +[2025-04-29 11:11:20,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 2.5706558227539062, cross_entropy: 2.5706558227539062 +[2025-04-29 11:11:21,828][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 1.9558106660842896, cross_entropy: 1.9558106660842896 +[2025-04-29 11:11:23,091][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 0.38188087940216064, cross_entropy: 0.38188087940216064 +[2025-04-29 11:11:24,483][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.5185132026672363, cross_entropy: 2.5185132026672363 +[2025-04-29 11:11:25,509][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 1.2018297910690308, cross_entropy: 1.2018297910690308 +[2025-04-29 11:11:27,581][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 0.7984141111373901, cross_entropy: 0.7984141111373901 +[2025-04-29 11:11:28,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.9977550506591797, cross_entropy: 0.9977550506591797 +[2025-04-29 11:11:30,440][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 0.5903664827346802, cross_entropy: 0.5903664827346802 +[2025-04-29 11:11:31,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.9338577389717102, cross_entropy: 0.9338577389717102 +[2025-04-29 11:11:33,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 0.4578824043273926, cross_entropy: 0.4578824043273926 +[2025-04-29 11:11:34,123][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 0.8318967819213867, cross_entropy: 0.8318967819213867 +[2025-04-29 11:11:35,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 0.9896727800369263, cross_entropy: 0.9896727800369263 +[2025-04-29 11:11:36,836][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 0.674541175365448, cross_entropy: 0.674541175365448 +[2025-04-29 11:11:38,478][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 0.6978142261505127, cross_entropy: 0.6978142261505127 +[2025-04-29 11:11:39,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.170701026916504, cross_entropy: 1.170701026916504 +[2025-04-29 11:11:40,899][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.7957438230514526, cross_entropy: 1.7957438230514526 +[2025-04-29 11:11:42,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 0.775039553642273, cross_entropy: 0.775039553642273 +[2025-04-29 11:11:44,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 0.6939430832862854, cross_entropy: 0.6939430832862854 +[2025-04-29 11:11:44,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 1.5208961963653564, cross_entropy: 1.5208961963653564 +[2025-04-29 11:11:46,902][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 0.6799950003623962, cross_entropy: 0.6799950003623962 +[2025-04-29 11:11:47,714][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 0.6406899690628052, cross_entropy: 0.6406899690628052 +[2025-04-29 11:11:49,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 0.5538439750671387, cross_entropy: 0.5538439750671387 +[2025-04-29 11:11:50,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.9496591091156006, cross_entropy: 1.9496591091156006 +[2025-04-29 11:11:52,086][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.3595974445343018, cross_entropy: 1.3595974445343018 +[2025-04-29 11:11:53,295][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 1.1603118181228638, cross_entropy: 1.1603118181228638 +[2025-04-29 11:11:56,199][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.4846177101135254, cross_entropy: 2.4846177101135254 +[2025-04-29 11:11:57,034][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 0.560019850730896, cross_entropy: 0.560019850730896 +[2025-04-29 11:11:58,539][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 0.8226203918457031, cross_entropy: 0.8226203918457031 +[2025-04-29 11:11:59,408][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 2.4405903816223145, cross_entropy: 2.4405903816223145 +[2025-04-29 11:12:01,401][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 1.8158905506134033, cross_entropy: 1.8158905506134033 +[2025-04-29 11:12:02,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.067244529724121, cross_entropy: 1.067244529724121 +[2025-04-29 11:12:04,472][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 0.831588625907898, cross_entropy: 0.831588625907898 +[2025-04-29 11:12:05,326][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.206244945526123, cross_entropy: 2.206244945526123 +[2025-04-29 11:12:07,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.4245738983154297, cross_entropy: 2.4245738983154297 +[2025-04-29 11:12:08,436][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 0.9172536134719849, cross_entropy: 0.9172536134719849 +[2025-04-29 11:12:10,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 2.7846503257751465, cross_entropy: 2.7846503257751465 +[2025-04-29 11:12:11,123][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 2.220470428466797, cross_entropy: 2.220470428466797 +[2025-04-29 11:12:13,351][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 2.0092246532440186, cross_entropy: 2.0092246532440186 +[2025-04-29 11:12:14,183][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 2.1051125526428223, cross_entropy: 2.1051125526428223 +[2025-04-29 11:12:15,530][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 0.5834938287734985, cross_entropy: 0.5834938287734985 +[2025-04-29 11:12:16,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.0973289012908936, cross_entropy: 1.0973289012908936 +[2025-04-29 11:12:17,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 0.6767537593841553, cross_entropy: 0.6767537593841553 +[2025-04-29 11:12:19,909][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 1.286700963973999, cross_entropy: 1.286700963973999 +[2025-04-29 11:12:21,127][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 2.480271816253662, cross_entropy: 2.480271816253662 +[2025-04-29 11:12:23,052][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 0.7810258865356445, cross_entropy: 0.7810258865356445 +[2025-04-29 11:12:24,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 0.7470675110816956, cross_entropy: 0.7470675110816956 +[2025-04-29 11:12:26,208][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.020768165588379, cross_entropy: 2.020768165588379 +[2025-04-29 11:12:27,081][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 2.2112207412719727, cross_entropy: 2.2112207412719727 +[2025-04-29 11:12:28,897][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 0.7261766195297241, cross_entropy: 0.7261766195297241 +[2025-04-29 11:12:29,905][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 2.52571439743042, cross_entropy: 2.52571439743042 +[2025-04-29 11:12:31,505][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 0.5573813319206238, cross_entropy: 0.5573813319206238 +[2025-04-29 11:12:32,411][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 0.792709231376648, cross_entropy: 0.792709231376648 +[2025-04-29 11:12:35,196][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 0.9226594567298889, cross_entropy: 0.9226594567298889 +[2025-04-29 11:12:36,006][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.157777190208435, cross_entropy: 1.157777190208435 +[2025-04-29 11:12:38,157][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.1381915807724, cross_entropy: 1.1381915807724 +[2025-04-29 11:12:39,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.587824821472168, cross_entropy: 2.587824821472168 +[2025-04-29 11:12:41,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 1.7582645416259766, cross_entropy: 1.7582645416259766 +[2025-04-29 11:12:41,887][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 0.6061145067214966, cross_entropy: 0.6061145067214966 +[2025-04-29 11:12:44,008][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 0.5460165739059448, cross_entropy: 0.5460165739059448 +[2025-04-29 11:12:44,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 2.363311290740967, cross_entropy: 2.363311290740967 +[2025-04-29 11:12:46,944][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 0.861853301525116, cross_entropy: 0.861853301525116 +[2025-04-29 11:12:47,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 1.5969865322113037, cross_entropy: 1.5969865322113037 +[2025-04-29 11:12:49,361][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 0.7847267389297485, cross_entropy: 0.7847267389297485 +[2025-04-29 11:12:50,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 0.8341662883758545, cross_entropy: 0.8341662883758545 +[2025-04-29 11:12:51,950][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 1.284515619277954, cross_entropy: 1.284515619277954 +[2025-04-29 11:12:52,806][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 2.2744734287261963, cross_entropy: 2.2744734287261963 +[2025-04-29 11:12:54,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 0.9889606237411499, cross_entropy: 0.9889606237411499 +[2025-04-29 11:12:55,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 1.2465260028839111, cross_entropy: 1.2465260028839111 +[2025-04-29 11:12:58,220][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 0.7610796689987183, cross_entropy: 0.7610796689987183 +[2025-04-29 11:12:59,058][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 0.8245209455490112, cross_entropy: 0.8245209455490112 +[2025-04-29 11:13:00,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 2.503816604614258, cross_entropy: 2.503816604614258 +[2025-04-29 11:13:01,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 0.8335518836975098, cross_entropy: 0.8335518836975098 +[2025-04-29 11:13:03,896][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 0.8320716023445129, cross_entropy: 0.8320716023445129 +[2025-04-29 11:13:04,732][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.2367480993270874, cross_entropy: 1.2367480993270874 +[2025-04-29 11:13:06,337][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 0.9473719000816345, cross_entropy: 0.9473719000816345 +[2025-04-29 11:13:07,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 0.6913146376609802, cross_entropy: 0.6913146376609802 +[2025-04-29 11:13:08,684][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 2.2108163833618164, cross_entropy: 2.2108163833618164 +[2025-04-29 11:13:09,554][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 2.8589916229248047, cross_entropy: 2.8589916229248047 +[2025-04-29 11:13:11,964][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 0.7150144577026367, cross_entropy: 0.7150144577026367 +[2025-04-29 11:13:12,794][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.43572095036506653, cross_entropy: 0.43572095036506653 +[2025-04-29 11:13:14,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 2.525219440460205, cross_entropy: 2.525219440460205 +[2025-04-29 11:13:16,358][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 1.056862473487854, cross_entropy: 1.056862473487854 +[2025-04-29 11:13:17,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 2.5582032203674316, cross_entropy: 2.5582032203674316 +[2025-04-29 11:13:19,693][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 0.900402307510376, cross_entropy: 0.900402307510376 +[2025-04-29 11:13:20,634][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 2.267326831817627, cross_entropy: 2.267326831817627 +[2025-04-29 11:13:23,282][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 1.0819393396377563, cross_entropy: 1.0819393396377563 +[2025-04-29 11:13:24,116][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 0.7896138429641724, cross_entropy: 0.7896138429641724 +[2025-04-29 11:13:26,090][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 0.9128818511962891, cross_entropy: 0.9128818511962891 +[2025-04-29 11:13:26,945][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 2.007345199584961, cross_entropy: 2.007345199584961 +[2025-04-29 11:13:29,738][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 0.9493876695632935, cross_entropy: 0.9493876695632935 +[2025-04-29 11:13:30,546][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 1.967149257659912, cross_entropy: 1.967149257659912 +[2025-04-29 11:13:32,716][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 2.3626086711883545, cross_entropy: 2.3626086711883545 +[2025-04-29 11:13:33,549][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.7867562770843506, cross_entropy: 2.7867562770843506 +[2025-04-29 11:13:35,187][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 0.7164931297302246, cross_entropy: 0.7164931297302246 +[2025-04-29 11:13:36,019][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.1013622283935547, cross_entropy: 1.1013622283935547 +[2025-04-29 11:13:37,416][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 0.8138754963874817, cross_entropy: 0.8138754963874817 +[2025-04-29 11:13:38,276][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.018125534057617, cross_entropy: 2.018125534057617 +[2025-04-29 11:13:40,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 1.2707469463348389, cross_entropy: 1.2707469463348389 +[2025-04-29 11:13:41,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 1.437821865081787, cross_entropy: 1.437821865081787 +[2025-04-29 11:13:43,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 0.4392218291759491, cross_entropy: 0.4392218291759491 +[2025-04-29 11:13:44,567][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 2.2050247192382812, cross_entropy: 2.2050247192382812 +[2025-04-29 11:13:46,288][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.7548701763153076, cross_entropy: 1.7548701763153076 +[2025-04-29 11:13:47,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.5979678630828857, cross_entropy: 1.5979678630828857 +[2025-04-29 11:13:49,781][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.2425389289855957, cross_entropy: 1.2425389289855957 +[2025-04-29 11:13:51,994][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 1.069707989692688, cross_entropy: 1.069707989692688 +[2025-04-29 11:13:52,834][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 0.5539987683296204, cross_entropy: 0.5539987683296204 +[2025-04-29 11:13:55,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 2.149923324584961, cross_entropy: 2.149923324584961 +[2025-04-29 11:13:56,085][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.3036725521087646, cross_entropy: 1.3036725521087646 +[2025-04-29 11:13:57,744][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 0.7486767768859863, cross_entropy: 0.7486767768859863 +[2025-04-29 11:13:58,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 1.513697862625122, cross_entropy: 1.513697862625122 +[2025-04-29 11:14:00,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 2.487727165222168, cross_entropy: 2.487727165222168 +[2025-04-29 11:14:01,782][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 1.1605838537216187, cross_entropy: 1.1605838537216187 +[2025-04-29 11:14:02,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 0.7816936373710632, cross_entropy: 0.7816936373710632 +[2025-04-29 11:14:05,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 1.1619234085083008, cross_entropy: 1.1619234085083008 +[2025-04-29 11:14:06,317][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 2.054145097732544, cross_entropy: 2.054145097732544 +[2025-04-29 11:14:08,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 0.8001174926757812, cross_entropy: 0.8001174926757812 +[2025-04-29 11:14:09,055][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 2.180938720703125, cross_entropy: 2.180938720703125 +[2025-04-29 11:14:10,562][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 2.03981351852417, cross_entropy: 2.03981351852417 +[2025-04-29 11:14:11,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 0.5805222988128662, cross_entropy: 0.5805222988128662 +[2025-04-29 11:14:13,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 1.4587680101394653, cross_entropy: 1.4587680101394653 +[2025-04-29 11:14:14,623][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 2.4130373001098633, cross_entropy: 2.4130373001098633 +[2025-04-29 11:14:16,431][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.2511789798736572, cross_entropy: 2.2511789798736572 +[2025-04-29 11:14:18,488][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 0.7822471857070923, cross_entropy: 0.7822471857070923 +[2025-04-29 11:14:19,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.2682013511657715, cross_entropy: 2.2682013511657715 +[2025-04-29 11:14:21,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 1.991456151008606, cross_entropy: 1.991456151008606 +[2025-04-29 11:14:22,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 0.8121976256370544, cross_entropy: 0.8121976256370544 +[2025-04-29 11:14:24,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 0.9543269872665405, cross_entropy: 0.9543269872665405 +[2025-04-29 11:14:25,030][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.3796169757843018, cross_entropy: 2.3796169757843018 +[2025-04-29 11:14:26,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 2.680616855621338, cross_entropy: 2.680616855621338 +[2025-04-29 11:14:27,246][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 0.530095636844635, cross_entropy: 0.530095636844635 +[2025-04-29 11:16:35,324][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.4074541330337524, cross_entropy: 1.4074541330337524 +[2025-04-29 11:16:35,324][BaseTrainer][INFO] - [Epoch 9/10] (validation) 0.9584693312644958, cross_entropy: 0.9584693312644958 +[2025-04-29 11:16:35,793][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch9.pth. +[2025-04-29 11:16:36,596][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 11:16:40,850][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.3052141666412354, cross_entropy: 1.3052141666412354 +[2025-04-29 11:16:41,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.849209189414978, cross_entropy: 1.849209189414978 +[2025-04-29 11:16:43,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 2.3160481452941895, cross_entropy: 2.3160481452941895 +[2025-04-29 11:16:44,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 0.7015909552574158, cross_entropy: 0.7015909552574158 +[2025-04-29 11:16:46,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.482227087020874, cross_entropy: 2.482227087020874 +[2025-04-29 11:16:47,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.2102303504943848, cross_entropy: 1.2102303504943848 +[2025-04-29 11:16:49,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.0334858894348145, cross_entropy: 2.0334858894348145 +[2025-04-29 11:16:50,011][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 1.8422319889068604, cross_entropy: 1.8422319889068604 +[2025-04-29 11:16:52,404][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.197939872741699, cross_entropy: 2.197939872741699 +[2025-04-29 11:16:53,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 0.9750664234161377, cross_entropy: 0.9750664234161377 +[2025-04-29 11:16:55,916][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.194607734680176, cross_entropy: 2.194607734680176 +[2025-04-29 11:16:56,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 1.5520613193511963, cross_entropy: 1.5520613193511963 +[2025-04-29 11:16:58,123][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.171281099319458, cross_entropy: 1.171281099319458 +[2025-04-29 11:16:58,936][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 0.9201689958572388, cross_entropy: 0.9201689958572388 +[2025-04-29 11:17:00,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 1.012246012687683, cross_entropy: 1.012246012687683 +[2025-04-29 11:17:01,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 1.6466468572616577, cross_entropy: 1.6466468572616577 +[2025-04-29 11:17:03,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 1.5723271369934082, cross_entropy: 1.5723271369934082 +[2025-04-29 11:17:04,134][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.6283297538757324, cross_entropy: 2.6283297538757324 +[2025-04-29 11:17:05,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.5133042335510254, cross_entropy: 2.5133042335510254 +[2025-04-29 11:17:06,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 2.4307055473327637, cross_entropy: 2.4307055473327637 +[2025-04-29 11:17:08,665][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 0.5082387328147888, cross_entropy: 0.5082387328147888 +[2025-04-29 11:17:09,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 1.4478826522827148, cross_entropy: 1.4478826522827148 +[2025-04-29 11:17:11,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 1.9020240306854248, cross_entropy: 1.9020240306854248 +[2025-04-29 11:17:12,408][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 0.8527623414993286, cross_entropy: 0.8527623414993286 +[2025-04-29 11:17:14,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 0.8101931214332581, cross_entropy: 0.8101931214332581 +[2025-04-29 11:17:15,383][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 1.5913114547729492, cross_entropy: 1.5913114547729492 +[2025-04-29 11:17:17,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 1.9018137454986572, cross_entropy: 1.9018137454986572 +[2025-04-29 11:17:18,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.1083321571350098, cross_entropy: 2.1083321571350098 +[2025-04-29 11:17:20,884][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.5040111541748047, cross_entropy: 2.5040111541748047 +[2025-04-29 11:17:21,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 0.4661353826522827, cross_entropy: 0.4661353826522827 +[2025-04-29 11:17:24,206][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 1.9487190246582031, cross_entropy: 1.9487190246582031 +[2025-04-29 11:17:25,041][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 0.6595777273178101, cross_entropy: 0.6595777273178101 +[2025-04-29 11:17:27,954][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 2.1901473999023438, cross_entropy: 2.1901473999023438 +[2025-04-29 11:17:28,762][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 0.5373251438140869, cross_entropy: 0.5373251438140869 +[2025-04-29 11:17:31,505][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.1523511409759521, cross_entropy: 1.1523511409759521 +[2025-04-29 11:17:32,344][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 0.7367293834686279, cross_entropy: 0.7367293834686279 +[2025-04-29 11:17:34,577][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.732199192047119, cross_entropy: 2.732199192047119 +[2025-04-29 11:17:35,412][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 2.7810606956481934, cross_entropy: 2.7810606956481934 +[2025-04-29 11:17:37,414][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 0.6005886197090149, cross_entropy: 0.6005886197090149 +[2025-04-29 11:17:38,225][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 2.426683187484741, cross_entropy: 2.426683187484741 +[2025-04-29 11:17:40,111][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 0.5089884996414185, cross_entropy: 0.5089884996414185 +[2025-04-29 11:17:40,947][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 1.9440667629241943, cross_entropy: 1.9440667629241943 +[2025-04-29 11:17:43,062][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 0.9501489996910095, cross_entropy: 0.9501489996910095 +[2025-04-29 11:17:43,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 1.1591473817825317, cross_entropy: 1.1591473817825317 +[2025-04-29 11:17:46,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 2.5857930183410645, cross_entropy: 2.5857930183410645 +[2025-04-29 11:17:47,248][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 1.829917550086975, cross_entropy: 1.829917550086975 +[2025-04-29 11:17:49,467][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.7640916109085083, cross_entropy: 1.7640916109085083 +[2025-04-29 11:17:50,309][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 0.47576579451560974, cross_entropy: 0.47576579451560974 +[2025-04-29 11:17:51,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 0.42821258306503296, cross_entropy: 0.42821258306503296 +[2025-04-29 11:17:52,831][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 1.9036059379577637, cross_entropy: 1.9036059379577637 +[2025-04-29 11:17:54,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 0.6466917991638184, cross_entropy: 0.6466917991638184 +[2025-04-29 11:17:55,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 1.0997629165649414, cross_entropy: 1.0997629165649414 +[2025-04-29 11:17:57,898][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 2.1012046337127686, cross_entropy: 2.1012046337127686 +[2025-04-29 11:17:58,731][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 0.44071125984191895, cross_entropy: 0.44071125984191895 +[2025-04-29 11:18:01,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 0.5535404086112976, cross_entropy: 0.5535404086112976 +[2025-04-29 11:18:02,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 0.6098002195358276, cross_entropy: 0.6098002195358276 +[2025-04-29 11:18:04,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.400244951248169, cross_entropy: 1.400244951248169 +[2025-04-29 11:18:05,273][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.4051966071128845, cross_entropy: 0.4051966071128845 +[2025-04-29 11:18:07,835][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.1818971633911133, cross_entropy: 1.1818971633911133 +[2025-04-29 11:18:08,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 0.8254257440567017, cross_entropy: 0.8254257440567017 +[2025-04-29 11:18:10,630][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 0.6781659722328186, cross_entropy: 0.6781659722328186 +[2025-04-29 11:18:11,475][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.4661988019943237, cross_entropy: 1.4661988019943237 +[2025-04-29 11:18:13,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 0.6097840070724487, cross_entropy: 0.6097840070724487 +[2025-04-29 11:18:14,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 0.5931901931762695, cross_entropy: 0.5931901931762695 +[2025-04-29 11:18:16,229][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 0.8977960348129272, cross_entropy: 0.8977960348129272 +[2025-04-29 11:18:17,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 2.0877838134765625, cross_entropy: 2.0877838134765625 +[2025-04-29 11:18:19,529][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 0.7657115459442139, cross_entropy: 0.7657115459442139 +[2025-04-29 11:18:20,363][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 0.917473554611206, cross_entropy: 0.917473554611206 +[2025-04-29 11:18:22,726][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 1.542759656906128, cross_entropy: 1.542759656906128 +[2025-04-29 11:18:23,560][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 1.8584263324737549, cross_entropy: 1.8584263324737549 +[2025-04-29 11:18:25,636][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 2.176774740219116, cross_entropy: 2.176774740219116 +[2025-04-29 11:18:26,445][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 2.6926918029785156, cross_entropy: 2.6926918029785156 +[2025-04-29 11:18:28,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.6362577676773071, cross_entropy: 1.6362577676773071 +[2025-04-29 11:18:29,109][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.0104517936706543, cross_entropy: 2.0104517936706543 +[2025-04-29 11:18:31,594][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 1.9479221105575562, cross_entropy: 1.9479221105575562 +[2025-04-29 11:18:32,434][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 2.318528652191162, cross_entropy: 2.318528652191162 +[2025-04-29 11:18:34,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.2129504680633545, cross_entropy: 1.2129504680633545 +[2025-04-29 11:18:35,528][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 0.9586014151573181, cross_entropy: 0.9586014151573181 +[2025-04-29 11:18:37,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 0.5707126259803772, cross_entropy: 0.5707126259803772 +[2025-04-29 11:18:38,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.45123839378356934, cross_entropy: 0.45123839378356934 +[2025-04-29 11:18:40,521][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 0.5991020202636719, cross_entropy: 0.5991020202636719 +[2025-04-29 11:18:41,331][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 2.65305757522583, cross_entropy: 2.65305757522583 +[2025-04-29 11:18:43,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 0.6133556365966797, cross_entropy: 0.6133556365966797 +[2025-04-29 11:18:44,434][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 0.6704117059707642, cross_entropy: 0.6704117059707642 +[2025-04-29 11:18:46,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 0.49490588903427124, cross_entropy: 0.49490588903427124 +[2025-04-29 11:18:47,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 2.079066276550293, cross_entropy: 2.079066276550293 +[2025-04-29 11:18:49,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 0.9511435031890869, cross_entropy: 0.9511435031890869 +[2025-04-29 11:18:50,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 2.285088300704956, cross_entropy: 2.285088300704956 +[2025-04-29 11:18:52,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.1673834323883057, cross_entropy: 2.1673834323883057 +[2025-04-29 11:18:53,206][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 0.7334911227226257, cross_entropy: 0.7334911227226257 +[2025-04-29 11:18:55,541][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.7420258522033691, cross_entropy: 1.7420258522033691 +[2025-04-29 11:18:56,373][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.3330285549163818, cross_entropy: 1.3330285549163818 +[2025-04-29 11:18:58,642][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 1.9411225318908691, cross_entropy: 1.9411225318908691 +[2025-04-29 11:18:59,453][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 1.330358862876892, cross_entropy: 1.330358862876892 +[2025-04-29 11:19:01,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.262925386428833, cross_entropy: 1.262925386428833 +[2025-04-29 11:19:02,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.5317054986953735, cross_entropy: 1.5317054986953735 +[2025-04-29 11:19:05,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 1.194034218788147, cross_entropy: 1.194034218788147 +[2025-04-29 11:19:06,753][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 2.3916943073272705, cross_entropy: 2.3916943073272705 +[2025-04-29 11:19:08,563][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.3668270111083984, cross_entropy: 1.3668270111083984 +[2025-04-29 11:19:09,398][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 1.9248701333999634, cross_entropy: 1.9248701333999634 +[2025-04-29 11:19:11,175][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 0.5483880043029785, cross_entropy: 0.5483880043029785 +[2025-04-29 11:19:12,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.8254880905151367, cross_entropy: 1.8254880905151367 +[2025-04-29 11:19:13,427][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 0.42232537269592285, cross_entropy: 0.42232537269592285 +[2025-04-29 11:19:14,328][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 1.5301669836044312, cross_entropy: 1.5301669836044312 +[2025-04-29 11:19:16,622][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 0.7601408958435059, cross_entropy: 0.7601408958435059 +[2025-04-29 11:19:17,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 1.8639583587646484, cross_entropy: 1.8639583587646484 +[2025-04-29 11:19:18,854][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.7865066528320312, cross_entropy: 1.7865066528320312 +[2025-04-29 11:19:20,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.6741783618927002, cross_entropy: 0.6741783618927002 +[2025-04-29 11:19:22,032][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.2298836708068848, cross_entropy: 2.2298836708068848 +[2025-04-29 11:19:23,278][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 0.7560844421386719, cross_entropy: 0.7560844421386719 +[2025-04-29 11:19:24,817][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 1.8894926309585571, cross_entropy: 1.8894926309585571 +[2025-04-29 11:19:26,130][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 0.4873011112213135, cross_entropy: 0.4873011112213135 +[2025-04-29 11:19:27,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 1.0833461284637451, cross_entropy: 1.0833461284637451 +[2025-04-29 11:19:28,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 0.5763822197914124, cross_entropy: 0.5763822197914124 +[2025-04-29 11:19:30,564][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 0.4187750220298767, cross_entropy: 0.4187750220298767 +[2025-04-29 11:19:31,454][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 0.830923855304718, cross_entropy: 0.830923855304718 +[2025-04-29 11:19:33,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.4104377031326294, cross_entropy: 1.4104377031326294 +[2025-04-29 11:19:34,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 0.5264754295349121, cross_entropy: 0.5264754295349121 +[2025-04-29 11:19:37,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.0538268089294434, cross_entropy: 1.0538268089294434 +[2025-04-29 11:19:37,901][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 0.4915083348751068, cross_entropy: 0.4915083348751068 +[2025-04-29 11:19:40,018][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 0.559471845626831, cross_entropy: 0.559471845626831 +[2025-04-29 11:19:40,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 0.9475440382957458, cross_entropy: 0.9475440382957458 +[2025-04-29 11:19:42,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 2.440175771713257, cross_entropy: 2.440175771713257 +[2025-04-29 11:19:43,577][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.5088858604431152, cross_entropy: 2.5088858604431152 +[2025-04-29 11:19:45,453][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 2.399975299835205, cross_entropy: 2.399975299835205 +[2025-04-29 11:19:46,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 0.7028231024742126, cross_entropy: 0.7028231024742126 +[2025-04-29 11:19:48,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 0.7434479594230652, cross_entropy: 0.7434479594230652 +[2025-04-29 11:19:49,439][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 2.195404529571533, cross_entropy: 2.195404529571533 +[2025-04-29 11:19:50,845][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 1.2578191757202148, cross_entropy: 1.2578191757202148 +[2025-04-29 11:19:51,704][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 2.47414493560791, cross_entropy: 2.47414493560791 +[2025-04-29 11:19:54,114][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 0.5820879936218262, cross_entropy: 0.5820879936218262 +[2025-04-29 11:19:54,945][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 2.4956209659576416, cross_entropy: 2.4956209659576416 +[2025-04-29 11:19:57,689][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 0.7012964487075806, cross_entropy: 0.7012964487075806 +[2025-04-29 11:19:58,522][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 2.627129554748535, cross_entropy: 2.627129554748535 +[2025-04-29 11:20:01,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 2.6339497566223145, cross_entropy: 2.6339497566223145 +[2025-04-29 11:20:02,149][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.243928074836731, cross_entropy: 1.243928074836731 +[2025-04-29 11:20:04,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 1.1304718255996704, cross_entropy: 1.1304718255996704 +[2025-04-29 11:20:04,971][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 2.103170156478882, cross_entropy: 2.103170156478882 +[2025-04-29 11:20:06,537][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 0.9300116300582886, cross_entropy: 0.9300116300582886 +[2025-04-29 11:20:07,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.8020994663238525, cross_entropy: 1.8020994663238525 +[2025-04-29 11:20:09,423][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 0.40511274337768555, cross_entropy: 0.40511274337768555 +[2025-04-29 11:20:10,257][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 0.6313709020614624, cross_entropy: 0.6313709020614624 +[2025-04-29 11:20:12,785][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.4439096450805664, cross_entropy: 2.4439096450805664 +[2025-04-29 11:20:13,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 1.7683446407318115, cross_entropy: 1.7683446407318115 +[2025-04-29 11:20:15,695][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.670173168182373, cross_entropy: 2.670173168182373 +[2025-04-29 11:20:16,533][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 1.5422205924987793, cross_entropy: 1.5422205924987793 +[2025-04-29 11:20:18,514][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 2.5226526260375977, cross_entropy: 2.5226526260375977 +[2025-04-29 11:20:19,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.0880067348480225, cross_entropy: 1.0880067348480225 +[2025-04-29 11:20:21,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 0.5620982646942139, cross_entropy: 0.5620982646942139 +[2025-04-29 11:20:22,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.2494957447052, cross_entropy: 2.2494957447052 +[2025-04-29 11:20:24,623][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 0.416278600692749, cross_entropy: 0.416278600692749 +[2025-04-29 11:20:25,482][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.4500551223754883, cross_entropy: 2.4500551223754883 +[2025-04-29 11:20:27,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 0.6427116990089417, cross_entropy: 0.6427116990089417 +[2025-04-29 11:20:28,418][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.338819980621338, cross_entropy: 2.338819980621338 +[2025-04-29 11:20:30,477][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 0.36221858859062195, cross_entropy: 0.36221858859062195 +[2025-04-29 11:20:31,330][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 0.5363419055938721, cross_entropy: 0.5363419055938721 +[2025-04-29 11:20:33,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 0.9464942216873169, cross_entropy: 0.9464942216873169 +[2025-04-29 11:20:34,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 0.5834513902664185, cross_entropy: 0.5834513902664185 +[2025-04-29 11:20:36,339][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.1838231086730957, cross_entropy: 1.1838231086730957 +[2025-04-29 11:20:37,498][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 0.8609209656715393, cross_entropy: 0.8609209656715393 +[2025-04-29 11:20:39,370][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 2.1857542991638184, cross_entropy: 2.1857542991638184 +[2025-04-29 11:20:40,450][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 1.3529527187347412, cross_entropy: 1.3529527187347412 +[2025-04-29 11:20:42,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 1.6664668321609497, cross_entropy: 1.6664668321609497 +[2025-04-29 11:20:43,422][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.2617664337158203, cross_entropy: 2.2617664337158203 +[2025-04-29 11:20:44,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 2.3291072845458984, cross_entropy: 2.3291072845458984 +[2025-04-29 11:20:46,812][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.2365403175354004, cross_entropy: 2.2365403175354004 +[2025-04-29 11:20:47,667][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 0.7519750595092773, cross_entropy: 0.7519750595092773 +[2025-04-29 11:20:49,423][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.713465690612793, cross_entropy: 0.713465690612793 +[2025-04-29 11:20:50,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 0.5615569353103638, cross_entropy: 0.5615569353103638 +[2025-04-29 11:20:52,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.358150005340576, cross_entropy: 2.358150005340576 +[2025-04-29 11:20:54,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 0.5935027599334717, cross_entropy: 0.5935027599334717 +[2025-04-29 11:20:54,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.5528855323791504, cross_entropy: 0.5528855323791504 +[2025-04-29 11:20:56,886][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 0.871334433555603, cross_entropy: 0.871334433555603 +[2025-04-29 11:20:57,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.8638207912445068, cross_entropy: 0.8638207912445068 +[2025-04-29 11:20:59,508][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 0.4249112904071808, cross_entropy: 0.4249112904071808 +[2025-04-29 11:21:00,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.918494462966919, cross_entropy: 1.918494462966919 +[2025-04-29 11:21:02,396][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 0.4349765181541443, cross_entropy: 0.4349765181541443 +[2025-04-29 11:21:03,216][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 1.843557357788086, cross_entropy: 1.843557357788086 +[2025-04-29 11:21:05,878][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.8991037607192993, cross_entropy: 1.8991037607192993 +[2025-04-29 11:21:06,709][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 1.9289331436157227, cross_entropy: 1.9289331436157227 +[2025-04-29 11:21:08,463][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 0.717677116394043, cross_entropy: 0.717677116394043 +[2025-04-29 11:21:09,322][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.43580320477485657, cross_entropy: 0.43580320477485657 +[2025-04-29 11:21:11,760][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 2.217909336090088, cross_entropy: 2.217909336090088 +[2025-04-29 11:21:12,591][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.3088064193725586, cross_entropy: 2.3088064193725586 +[2025-04-29 11:21:14,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.432372808456421, cross_entropy: 1.432372808456421 +[2025-04-29 11:21:15,705][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.5855181217193604, cross_entropy: 1.5855181217193604 +[2025-04-29 11:21:18,244][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 1.7012860774993896, cross_entropy: 1.7012860774993896 +[2025-04-29 11:21:19,074][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 0.9791278839111328, cross_entropy: 0.9791278839111328 +[2025-04-29 11:21:21,555][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 0.9725725650787354, cross_entropy: 0.9725725650787354 +[2025-04-29 11:21:22,369][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 2.2897157669067383, cross_entropy: 2.2897157669067383 +[2025-04-29 11:21:24,103][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 1.9760538339614868, cross_entropy: 1.9760538339614868 +[2025-04-29 11:21:24,934][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 0.6710903644561768, cross_entropy: 0.6710903644561768 +[2025-04-29 11:21:26,517][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 2.1596665382385254, cross_entropy: 2.1596665382385254 +[2025-04-29 11:21:27,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 0.4708139896392822, cross_entropy: 0.4708139896392822 +[2025-04-29 11:21:29,729][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.6847758293151855, cross_entropy: 2.6847758293151855 +[2025-04-29 11:21:30,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 1.4329841136932373, cross_entropy: 1.4329841136932373 +[2025-04-29 11:21:32,697][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 2.338531970977783, cross_entropy: 2.338531970977783 +[2025-04-29 11:21:33,505][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 0.6005996465682983, cross_entropy: 0.6005996465682983 +[2025-04-29 11:21:35,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 0.45810526609420776, cross_entropy: 0.45810526609420776 +[2025-04-29 11:21:36,725][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.2312285900115967, cross_entropy: 2.2312285900115967 +[2025-04-29 11:21:39,012][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 0.709855318069458, cross_entropy: 0.709855318069458 +[2025-04-29 11:21:39,852][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.6695189476013184, cross_entropy: 2.6695189476013184 +[2025-04-29 11:21:43,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 0.4516434669494629, cross_entropy: 0.4516434669494629 +[2025-04-29 11:21:43,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 1.6840825080871582, cross_entropy: 1.6840825080871582 +[2025-04-29 11:21:46,089][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 2.0034165382385254, cross_entropy: 2.0034165382385254 +[2025-04-29 11:21:46,927][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 0.5126550197601318, cross_entropy: 0.5126550197601318 +[2025-04-29 11:21:48,884][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 0.5358147621154785, cross_entropy: 0.5358147621154785 +[2025-04-29 11:21:49,719][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 0.7599083185195923, cross_entropy: 0.7599083185195923 +[2025-04-29 11:21:51,615][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 0.8822994828224182, cross_entropy: 0.8822994828224182 +[2025-04-29 11:21:52,438][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 2.1216816902160645, cross_entropy: 2.1216816902160645 +[2025-04-29 11:21:54,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 1.3495289087295532, cross_entropy: 1.3495289087295532 +[2025-04-29 11:21:55,028][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 0.5979260206222534, cross_entropy: 0.5979260206222534 +[2025-04-29 11:21:57,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 2.0633373260498047, cross_entropy: 2.0633373260498047 +[2025-04-29 11:21:58,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.231326103210449, cross_entropy: 2.231326103210449 +[2025-04-29 11:22:00,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 0.9353382587432861, cross_entropy: 0.9353382587432861 +[2025-04-29 11:22:01,002][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 2.6396851539611816, cross_entropy: 2.6396851539611816 +[2025-04-29 11:22:02,858][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 0.6087154746055603, cross_entropy: 0.6087154746055603 +[2025-04-29 11:22:03,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 1.0153471231460571, cross_entropy: 1.0153471231460571 +[2025-04-29 11:22:05,428][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 0.46861833333969116, cross_entropy: 0.46861833333969116 +[2025-04-29 11:22:06,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 3.0496010780334473, cross_entropy: 3.0496010780334473 +[2025-04-29 11:22:08,413][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 0.5974990129470825, cross_entropy: 0.5974990129470825 +[2025-04-29 11:22:09,265][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.905771255493164, cross_entropy: 1.905771255493164 +[2025-04-29 11:22:11,436][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 0.6112395524978638, cross_entropy: 0.6112395524978638 +[2025-04-29 11:22:12,257][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 0.38619354367256165, cross_entropy: 0.38619354367256165 +[2025-04-29 11:22:13,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 0.7383499145507812, cross_entropy: 0.7383499145507812 +[2025-04-29 11:22:14,800][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.595369338989258, cross_entropy: 2.595369338989258 +[2025-04-29 11:22:17,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.5305520296096802, cross_entropy: 1.5305520296096802 +[2025-04-29 11:22:18,616][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 1.1383802890777588, cross_entropy: 1.1383802890777588 +[2025-04-29 11:22:21,360][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 2.885305404663086, cross_entropy: 2.885305404663086 +[2025-04-29 11:22:22,176][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.3346439599990845, cross_entropy: 1.3346439599990845 +[2025-04-29 11:22:24,261][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 2.074303150177002, cross_entropy: 2.074303150177002 +[2025-04-29 11:22:25,103][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 0.5544235706329346, cross_entropy: 0.5544235706329346 +[2025-04-29 11:22:27,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.0828166007995605, cross_entropy: 1.0828166007995605 +[2025-04-29 11:22:27,986][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 0.6727354526519775, cross_entropy: 0.6727354526519775 +[2025-04-29 11:22:30,181][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 0.7410588264465332, cross_entropy: 0.7410588264465332 +[2025-04-29 11:22:30,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 0.48634952306747437, cross_entropy: 0.48634952306747437 +[2025-04-29 11:22:33,210][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 1.0062297582626343, cross_entropy: 1.0062297582626343 +[2025-04-29 11:22:34,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 2.629021644592285, cross_entropy: 2.629021644592285 +[2025-04-29 11:22:36,463][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.8515698909759521, cross_entropy: 1.8515698909759521 +[2025-04-29 11:22:37,296][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.4515998363494873, cross_entropy: 1.4515998363494873 +[2025-04-29 11:22:39,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 0.41015711426734924, cross_entropy: 0.41015711426734924 +[2025-04-29 11:22:40,074][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.102424383163452, cross_entropy: 2.102424383163452 +[2025-04-29 11:22:41,945][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.4683637619018555, cross_entropy: 2.4683637619018555 +[2025-04-29 11:22:42,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.3976167142391205, cross_entropy: 0.3976167142391205 +[2025-04-29 11:22:44,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 1.9157111644744873, cross_entropy: 1.9157111644744873 +[2025-04-29 11:22:45,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 1.4047060012817383, cross_entropy: 1.4047060012817383 +[2025-04-29 11:22:47,770][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 2.2045297622680664, cross_entropy: 2.2045297622680664 +[2025-04-29 11:22:48,603][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.6745424270629883, cross_entropy: 2.6745424270629883 +[2025-04-29 11:22:50,816][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 0.642876148223877, cross_entropy: 0.642876148223877 +[2025-04-29 11:22:51,650][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 0.7049473524093628, cross_entropy: 0.7049473524093628 +[2025-04-29 11:22:53,630][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 0.7164399027824402, cross_entropy: 0.7164399027824402 +[2025-04-29 11:22:54,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.4788143634796143, cross_entropy: 2.4788143634796143 +[2025-04-29 11:22:55,845][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 1.032773733139038, cross_entropy: 1.032773733139038 +[2025-04-29 11:22:56,677][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 0.9562891721725464, cross_entropy: 0.9562891721725464 +[2025-04-29 11:22:58,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.5725162029266357, cross_entropy: 1.5725162029266357 +[2025-04-29 11:22:59,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 2.578672409057617, cross_entropy: 2.578672409057617 +[2025-04-29 11:23:00,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 1.2603119611740112, cross_entropy: 1.2603119611740112 +[2025-04-29 11:23:02,901][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 0.5933045148849487, cross_entropy: 0.5933045148849487 +[2025-04-29 11:23:03,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 0.6252028942108154, cross_entropy: 0.6252028942108154 +[2025-04-29 11:23:05,752][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.2781641483306885, cross_entropy: 1.2781641483306885 +[2025-04-29 11:23:06,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 1.779625654220581, cross_entropy: 1.779625654220581 +[2025-04-29 11:23:08,716][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 0.9137059450149536, cross_entropy: 0.9137059450149536 +[2025-04-29 11:23:09,560][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 1.200965404510498, cross_entropy: 1.200965404510498 +[2025-04-29 11:23:11,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 0.9946102499961853, cross_entropy: 0.9946102499961853 +[2025-04-29 11:23:12,284][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.6160759925842285, cross_entropy: 2.6160759925842285 +[2025-04-29 11:23:14,597][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.6699168682098389, cross_entropy: 0.6699168682098389 +[2025-04-29 11:23:15,406][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 0.5468893051147461, cross_entropy: 0.5468893051147461 +[2025-04-29 11:23:17,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.4967267513275146, cross_entropy: 1.4967267513275146 +[2025-04-29 11:23:18,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 0.21307513117790222, cross_entropy: 0.21307513117790222 +[2025-04-29 11:23:21,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.7778006196022034, cross_entropy: 0.7778006196022034 +[2025-04-29 11:23:22,044][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 1.6054744720458984, cross_entropy: 1.6054744720458984 +[2025-04-29 11:23:24,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 0.7386560440063477, cross_entropy: 0.7386560440063477 +[2025-04-29 11:23:25,527][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.6528016924858093, cross_entropy: 0.6528016924858093 +[2025-04-29 11:23:27,461][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 0.4073456823825836, cross_entropy: 0.4073456823825836 +[2025-04-29 11:23:28,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.5919132232666016, cross_entropy: 2.5919132232666016 +[2025-04-29 11:23:30,449][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.337867259979248, cross_entropy: 2.337867259979248 +[2025-04-29 11:23:31,335][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.155165672302246, cross_entropy: 2.155165672302246 +[2025-04-29 11:23:33,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 1.9560109376907349, cross_entropy: 1.9560109376907349 +[2025-04-29 11:23:34,337][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 2.4017810821533203, cross_entropy: 2.4017810821533203 +[2025-04-29 11:23:36,130][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 1.561565637588501, cross_entropy: 1.561565637588501 +[2025-04-29 11:23:37,086][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 2.609187126159668, cross_entropy: 2.609187126159668 +[2025-04-29 11:23:39,046][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.4651402235031128, cross_entropy: 0.4651402235031128 +[2025-04-29 11:23:39,907][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 0.9313059449195862, cross_entropy: 0.9313059449195862 +[2025-04-29 11:23:42,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 0.7467560172080994, cross_entropy: 0.7467560172080994 +[2025-04-29 11:23:43,701][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.600161552429199, cross_entropy: 2.600161552429199 +[2025-04-29 11:23:45,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 2.3232898712158203, cross_entropy: 2.3232898712158203 +[2025-04-29 11:23:46,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 1.4478014707565308, cross_entropy: 1.4478014707565308 +[2025-04-29 11:23:49,089][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 1.5968557596206665, cross_entropy: 1.5968557596206665 +[2025-04-29 11:23:49,933][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.09689998626709, cross_entropy: 2.09689998626709 +[2025-04-29 11:23:51,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 2.067314624786377, cross_entropy: 2.067314624786377 +[2025-04-29 11:23:52,713][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 2.300278425216675, cross_entropy: 2.300278425216675 +[2025-04-29 11:23:56,435][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.0584356784820557, cross_entropy: 2.0584356784820557 +[2025-04-29 11:23:57,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 2.4439778327941895, cross_entropy: 2.4439778327941895 +[2025-04-29 11:23:58,860][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 0.6380085945129395, cross_entropy: 0.6380085945129395 +[2025-04-29 11:23:59,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 2.2408385276794434, cross_entropy: 2.2408385276794434 +[2025-04-29 11:24:01,955][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 1.0091402530670166, cross_entropy: 1.0091402530670166 +[2025-04-29 11:24:02,789][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 2.4145402908325195, cross_entropy: 2.4145402908325195 +[2025-04-29 11:24:04,982][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.0866894721984863, cross_entropy: 1.0866894721984863 +[2025-04-29 11:24:05,791][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 0.6317667365074158, cross_entropy: 0.6317667365074158 +[2025-04-29 11:24:08,234][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 1.6479926109313965, cross_entropy: 1.6479926109313965 +[2025-04-29 11:24:09,073][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 1.1621594429016113, cross_entropy: 1.1621594429016113 +[2025-04-29 11:24:10,559][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 0.6911826133728027, cross_entropy: 0.6911826133728027 +[2025-04-29 11:24:11,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 0.7588173151016235, cross_entropy: 0.7588173151016235 +[2025-04-29 11:24:13,274][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.029980182647705, cross_entropy: 2.029980182647705 +[2025-04-29 11:24:14,086][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.491633892059326, cross_entropy: 2.491633892059326 +[2025-04-29 11:24:15,999][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 0.6324431896209717, cross_entropy: 0.6324431896209717 +[2025-04-29 11:24:16,834][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 2.316840648651123, cross_entropy: 2.316840648651123 +[2025-04-29 11:24:19,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 1.6290233135223389, cross_entropy: 1.6290233135223389 +[2025-04-29 11:24:19,838][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.9627721309661865, cross_entropy: 0.9627721309661865 +[2025-04-29 11:24:21,715][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.4306588172912598, cross_entropy: 2.4306588172912598 +[2025-04-29 11:24:22,550][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.8563472032546997, cross_entropy: 1.8563472032546997 +[2025-04-29 11:24:24,304][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.846839189529419, cross_entropy: 1.846839189529419 +[2025-04-29 11:24:25,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.6401232481002808, cross_entropy: 1.6401232481002808 +[2025-04-29 11:24:27,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 2.419224977493286, cross_entropy: 2.419224977493286 +[2025-04-29 11:24:28,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 1.7165913581848145, cross_entropy: 1.7165913581848145 +[2025-04-29 11:24:30,284][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 0.6212244033813477, cross_entropy: 0.6212244033813477 +[2025-04-29 11:24:31,170][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 2.4178619384765625, cross_entropy: 2.4178619384765625 +[2025-04-29 11:24:33,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 0.8122603297233582, cross_entropy: 0.8122603297233582 +[2025-04-29 11:24:34,620][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 0.6264330148696899, cross_entropy: 0.6264330148696899 +[2025-04-29 11:24:36,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.4472506046295166, cross_entropy: 1.4472506046295166 +[2025-04-29 11:24:37,690][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.8282580375671387, cross_entropy: 2.8282580375671387 +[2025-04-29 11:24:38,858][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 2.010880947113037, cross_entropy: 2.010880947113037 +[2025-04-29 11:24:40,261][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 0.7427563667297363, cross_entropy: 0.7427563667297363 +[2025-04-29 11:24:41,680][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 0.7314246892929077, cross_entropy: 0.7314246892929077 +[2025-04-29 11:24:42,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 1.849743366241455, cross_entropy: 1.849743366241455 +[2025-04-29 11:24:44,230][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 1.2066196203231812, cross_entropy: 1.2066196203231812 +[2025-04-29 11:24:45,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.0417447090148926, cross_entropy: 2.0417447090148926 +[2025-04-29 11:24:46,923][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 0.7703959345817566, cross_entropy: 0.7703959345817566 +[2025-04-29 11:24:48,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.679642915725708, cross_entropy: 1.679642915725708 +[2025-04-29 11:24:50,024][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.5736892819404602, cross_entropy: 0.5736892819404602 +[2025-04-29 11:24:50,887][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 0.5700377225875854, cross_entropy: 0.5700377225875854 +[2025-04-29 11:24:52,869][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 0.6211315393447876, cross_entropy: 0.6211315393447876 +[2025-04-29 11:24:53,733][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 0.5982897281646729, cross_entropy: 0.5982897281646729 +[2025-04-29 11:24:56,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.0602271556854248, cross_entropy: 1.0602271556854248 +[2025-04-29 11:24:57,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 0.977165699005127, cross_entropy: 0.977165699005127 +[2025-04-29 11:25:00,014][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.0900036096572876, cross_entropy: 1.0900036096572876 +[2025-04-29 11:25:00,825][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 0.6402407884597778, cross_entropy: 0.6402407884597778 +[2025-04-29 11:25:03,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.3980958461761475, cross_entropy: 2.3980958461761475 +[2025-04-29 11:25:03,928][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 2.5560173988342285, cross_entropy: 2.5560173988342285 +[2025-04-29 11:25:05,947][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.9465570449829102, cross_entropy: 1.9465570449829102 +[2025-04-29 11:25:06,768][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 0.29468822479248047, cross_entropy: 0.29468822479248047 +[2025-04-29 11:25:08,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 0.7765809297561646, cross_entropy: 0.7765809297561646 +[2025-04-29 11:25:09,714][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 0.7272655367851257, cross_entropy: 0.7272655367851257 +[2025-04-29 11:25:12,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.5401558876037598, cross_entropy: 2.5401558876037598 +[2025-04-29 11:25:12,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 2.437014579772949, cross_entropy: 2.437014579772949 +[2025-04-29 11:25:14,779][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.5281050205230713, cross_entropy: 2.5281050205230713 +[2025-04-29 11:25:15,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 2.517406940460205, cross_entropy: 2.517406940460205 +[2025-04-29 11:25:17,773][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.7920269966125488, cross_entropy: 1.7920269966125488 +[2025-04-29 11:25:18,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 0.8491419553756714, cross_entropy: 0.8491419553756714 +[2025-04-29 11:25:20,357][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 0.5195000767707825, cross_entropy: 0.5195000767707825 +[2025-04-29 11:25:21,216][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 0.4750789403915405, cross_entropy: 0.4750789403915405 +[2025-04-29 11:25:23,410][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.6917010545730591, cross_entropy: 0.6917010545730591 +[2025-04-29 11:25:24,218][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 0.48247230052948, cross_entropy: 0.48247230052948 +[2025-04-29 11:25:25,963][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.227710485458374, cross_entropy: 1.227710485458374 +[2025-04-29 11:25:26,775][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.4130817651748657, cross_entropy: 1.4130817651748657 +[2025-04-29 11:25:27,762][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 2.3669347763061523, cross_entropy: 2.3669347763061523 +[2025-04-29 11:27:42,523][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.4122122526168823, cross_entropy: 1.4122122526168823 +[2025-04-29 11:27:42,524][BaseTrainer][INFO] - [Epoch 10/10] (validation) 0.9200575351715088, cross_entropy: 0.9200575351715088 +[2025-04-29 11:27:43,384][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/best_epoch.pth. +[2025-04-29 11:27:43,847][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/epoch10.pth. +[2025-04-29 11:27:44,616][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. +[2025-04-29 11:27:45,429][BaseTrainer][INFO] - Save model: ./exp/20250429-091731/model/last.pth. diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/best_epoch.pth b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..42e2e0a1a146266f19afcbb4eba325f50eae2f04 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c8c76a73f858b31c3e5e91cedb5bec0403da0ca62ebdd29cf069f83c4e130ff +size 335992470 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/last.pth b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..11b41ccc04bf3d388928a0aae0acf8f34aaced3f --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-091731/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eaca39c63d46df4018baadf070d222fdf55f1e611da5930fc7c02009442a642 +size 335953326 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/config.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4edcd4d304e6b96b1f10da0f80b519a32e8c7621 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/config.yaml @@ -0,0 +1,223 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-174600 + tensorboard_dir: ./tensorboard/20250429-174600 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.ConvNeXtTiny + weights: ${const:torchvision.models.ConvNeXt_Tiny_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/hydra.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..85d6aace9f1385e86298821ebd8f4036b442361e --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250429-174600/log/20250429-174603 + sweep: + dir: multirun/${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/20250429-174600/log/20250429-174603 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_convnext_tiny + - model=birdclef2025_convnext_tiny + - optimizer=adamw_1e-4_decay_5e-2 + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250429-174600 + - train.output.tensorboard_dir=./tensorboard/20250429-174600 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_15s,lr_scheduler=none,model=birdclef2025_convnext_tiny,optimizer=adamw_1e-4_decay_5e-2,preprocess.dump_format=birdclef2025,preprocess=birdclef2025,system=cuda,train.dataset.train.feature_dir=/kaggle/input/birdclef-2025,train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250429-174600,train.output.tensorboard_dir=./tensorboard/20250429-174600,train.resume.continue_from=,train=birdclef2025_reshape_convnext_tiny + 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/ConvNeXtTiny + 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/ConvNeXtTiny/conf + schema: file + provider: command-line + - path: '' + schema: structured + provider: schema + output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adamw_1e-4_decay_5e-2 + model: birdclef2025_convnext_tiny + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_convnext_tiny + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_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 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/overrides.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5ff727f816b334e8bbd0791bde3b664badaec8cf --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_convnext_tiny +- model=birdclef2025_convnext_tiny +- optimizer=adamw_1e-4_decay_5e-2 +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250429-174600 +- train.output.tensorboard_dir=./tensorboard/20250429-174600 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cd87425877105f21dcecd83629632f7f19d63de5 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/.hydra/resolved_config.yaml @@ -0,0 +1,282 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250429-174600 + tensorboard_dir: ./tensorboard/20250429-174600 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250429-174600/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250429-174600/model/epoch{epoch}.pth + last: + path: ./exp/20250429-174600/model/last.pth + best_epoch: + path: ./exp/20250429-174600/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.ConvNeXtTiny + weights: IMAGENET1K_V1 + num_classes: 206 +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/train.log b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/train.log new file mode 100644 index 0000000000000000000000000000000000000000..084636e6b4ea49b38b53a838e235fbb32da1c669 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/log/20250429-174603/train.log @@ -0,0 +1,4091 @@ +[2025-04-29 17:46:31,918][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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-174600 + tensorboard_dir: ./tensorboard/20250429-174600 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.ConvNeXtTiny + weights: ${const:torchvision.models.ConvNeXt_Tiny_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.AdamW + lr: 0.0001 + weight_decay: 0.05 +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} + +[2025-04-29 17:46:31,918][BaseTrainer][INFO] - ConvNeXtTiny( + (backbone): Sequential( + (0): Conv2dNormActivation( + (0): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4)) + (1): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True) + ) + (1): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0058823529411764705, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(96, 96, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=96) + (1): Permute() + (2): LayerNorm((96,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=96, out_features=384, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=384, out_features=96, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.011764705882352941, mode=row) + ) + ) + (2): Sequential( + (0): LayerNorm2d((96,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(96, 192, kernel_size=(2, 2), stride=(2, 2)) + ) + (3): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.017647058823529415, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.023529411764705882, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(192, 192, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=192) + (1): Permute() + (2): LayerNorm((192,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=192, out_features=768, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=768, out_features=192, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.029411764705882353, mode=row) + ) + ) + (4): Sequential( + (0): LayerNorm2d((192,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(192, 384, kernel_size=(2, 2), stride=(2, 2)) + ) + (5): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.03529411764705883, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0411764705882353, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.047058823529411764, mode=row) + ) + (3): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.052941176470588235, mode=row) + ) + (4): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.058823529411764705, mode=row) + ) + (5): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.06470588235294118, mode=row) + ) + (6): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.07058823529411766, mode=row) + ) + (7): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.07647058823529412, mode=row) + ) + (8): CNBlock( + (block): Sequential( + (0): Conv2d(384, 384, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=384) + (1): Permute() + (2): LayerNorm((384,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=384, out_features=1536, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=1536, out_features=384, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.0823529411764706, mode=row) + ) + ) + (6): Sequential( + (0): LayerNorm2d((384,), eps=1e-06, elementwise_affine=True) + (1): Conv2d(384, 768, kernel_size=(2, 2), stride=(2, 2)) + ) + (7): Sequential( + (0): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.08823529411764706, mode=row) + ) + (1): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.09411764705882353, mode=row) + ) + (2): CNBlock( + (block): Sequential( + (0): Conv2d(768, 768, kernel_size=(7, 7), stride=(1, 1), padding=(3, 3), groups=768) + (1): Permute() + (2): LayerNorm((768,), eps=1e-06, elementwise_affine=True) + (3): Linear(in_features=768, out_features=3072, bias=True) + (4): GELU(approximate='none') + (5): Linear(in_features=3072, out_features=768, bias=True) + (6): Permute() + ) + (stochastic_depth): StochasticDepth(p=0.1, mode=row) + ) + ) + ) + (avgpool): AdaptiveAvgPool2d(output_size=1) + (classifier): Sequential( + (0): LayerNorm2d((768,), eps=1e-06, elementwise_affine=True) + (1): Flatten(start_dim=1, end_dim=-1) + (2): Linear(in_features=768, out_features=206, bias=True) + ) +) +[2025-04-29 17:46:31,921][BaseTrainer][INFO] - # of parameters: 27978542. +[2025-04-29 17:46:51,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.376641273498535, cross_entropy: 5.376641273498535 +[2025-04-29 17:46:52,950][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.312026023864746, cross_entropy: 5.312026023864746 +[2025-04-29 17:46:53,986][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.27780818939209, cross_entropy: 5.27780818939209 +[2025-04-29 17:46:55,077][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.321934700012207, cross_entropy: 5.321934700012207 +[2025-04-29 17:46:56,205][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.203423500061035, cross_entropy: 5.203423500061035 +[2025-04-29 17:46:58,137][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.188291549682617, cross_entropy: 5.188291549682617 +[2025-04-29 17:46:59,244][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 5.233580112457275, cross_entropy: 5.233580112457275 +[2025-04-29 17:47:03,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.191223621368408, cross_entropy: 5.191223621368408 +[2025-04-29 17:47:04,202][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 5.152655601501465, cross_entropy: 5.152655601501465 +[2025-04-29 17:47:07,771][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.084836959838867, cross_entropy: 5.084836959838867 +[2025-04-29 17:47:08,857][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.160213470458984, cross_entropy: 5.160213470458984 +[2025-04-29 17:47:12,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 5.043108940124512, cross_entropy: 5.043108940124512 +[2025-04-29 17:47:13,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.957451820373535, cross_entropy: 4.957451820373535 +[2025-04-29 17:47:18,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.992649078369141, cross_entropy: 4.992649078369141 +[2025-04-29 17:47:19,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.82185173034668, cross_entropy: 4.82185173034668 +[2025-04-29 17:47:22,472][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 5.031904220581055, cross_entropy: 5.031904220581055 +[2025-04-29 17:47:23,528][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.100973129272461, cross_entropy: 5.100973129272461 +[2025-04-29 17:47:26,726][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.039768218994141, cross_entropy: 5.039768218994141 +[2025-04-29 17:47:27,783][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.945712566375732, cross_entropy: 4.945712566375732 +[2025-04-29 17:47:30,651][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.910451412200928, cross_entropy: 4.910451412200928 +[2025-04-29 17:47:31,687][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.891071319580078, cross_entropy: 4.891071319580078 +[2025-04-29 17:47:35,190][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.818423271179199, cross_entropy: 4.818423271179199 +[2025-04-29 17:47:36,241][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.651951789855957, cross_entropy: 4.651951789855957 +[2025-04-29 17:47:39,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 5.034424781799316, cross_entropy: 5.034424781799316 +[2025-04-29 17:47:40,077][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.565324783325195, cross_entropy: 4.565324783325195 +[2025-04-29 17:47:43,725][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.976114749908447, cross_entropy: 4.976114749908447 +[2025-04-29 17:47:44,758][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.841283798217773, cross_entropy: 4.841283798217773 +[2025-04-29 17:47:48,425][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.716811180114746, cross_entropy: 4.716811180114746 +[2025-04-29 17:47:49,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 5.003815650939941, cross_entropy: 5.003815650939941 +[2025-04-29 17:47:52,800][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.7728986740112305, cross_entropy: 4.7728986740112305 +[2025-04-29 17:47:53,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.807315826416016, cross_entropy: 4.807315826416016 +[2025-04-29 17:47:56,247][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.718504905700684, cross_entropy: 4.718504905700684 +[2025-04-29 17:47:57,299][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.847777843475342, cross_entropy: 4.847777843475342 +[2025-04-29 17:48:00,600][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.851305961608887, cross_entropy: 4.851305961608887 +[2025-04-29 17:48:01,646][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.6127824783325195, cross_entropy: 4.6127824783325195 +[2025-04-29 17:48:04,650][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.892227649688721, cross_entropy: 4.892227649688721 +[2025-04-29 17:48:05,707][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.760605812072754, cross_entropy: 4.760605812072754 +[2025-04-29 17:48:08,522][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.747416973114014, cross_entropy: 4.747416973114014 +[2025-04-29 17:48:09,573][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.610195636749268, cross_entropy: 4.610195636749268 +[2025-04-29 17:48:12,848][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.788339614868164, cross_entropy: 4.788339614868164 +[2025-04-29 17:48:13,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.6864423751831055, cross_entropy: 4.6864423751831055 +[2025-04-29 17:48:17,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.774243354797363, cross_entropy: 4.774243354797363 +[2025-04-29 17:48:18,517][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.873464584350586, cross_entropy: 4.873464584350586 +[2025-04-29 17:48:21,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.770915985107422, cross_entropy: 4.770915985107422 +[2025-04-29 17:48:22,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.7253265380859375, cross_entropy: 4.7253265380859375 +[2025-04-29 17:48:25,476][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.555655479431152, cross_entropy: 4.555655479431152 +[2025-04-29 17:48:26,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.744180202484131, cross_entropy: 4.744180202484131 +[2025-04-29 17:48:29,856][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.5664777755737305, cross_entropy: 4.5664777755737305 +[2025-04-29 17:48:30,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.555988788604736, cross_entropy: 4.555988788604736 +[2025-04-29 17:48:35,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.736114501953125, cross_entropy: 4.736114501953125 +[2025-04-29 17:48:36,384][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.5414042472839355, cross_entropy: 4.5414042472839355 +[2025-04-29 17:48:39,277][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.843523979187012, cross_entropy: 4.843523979187012 +[2025-04-29 17:48:40,311][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.45950984954834, cross_entropy: 4.45950984954834 +[2025-04-29 17:48:43,176][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.814383029937744, cross_entropy: 4.814383029937744 +[2025-04-29 17:48:44,227][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.580887794494629, cross_entropy: 4.580887794494629 +[2025-04-29 17:48:47,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.71505069732666, cross_entropy: 4.71505069732666 +[2025-04-29 17:48:48,666][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.507774353027344, cross_entropy: 4.507774353027344 +[2025-04-29 17:48:51,295][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.750196933746338, cross_entropy: 4.750196933746338 +[2025-04-29 17:48:52,350][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.728370666503906, cross_entropy: 4.728370666503906 +[2025-04-29 17:48:55,172][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.7065019607543945, cross_entropy: 4.7065019607543945 +[2025-04-29 17:48:56,206][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.695921897888184, cross_entropy: 4.695921897888184 +[2025-04-29 17:48:59,696][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.792250156402588, cross_entropy: 4.792250156402588 +[2025-04-29 17:49:00,746][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.864690780639648, cross_entropy: 4.864690780639648 +[2025-04-29 17:49:04,822][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.703803062438965, cross_entropy: 4.703803062438965 +[2025-04-29 17:49:05,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.695967674255371, cross_entropy: 4.695967674255371 +[2025-04-29 17:49:09,462][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.7378034591674805, cross_entropy: 4.7378034591674805 +[2025-04-29 17:49:10,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.630002498626709, cross_entropy: 4.630002498626709 +[2025-04-29 17:49:13,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.627467155456543, cross_entropy: 4.627467155456543 +[2025-04-29 17:49:14,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.664760589599609, cross_entropy: 4.664760589599609 +[2025-04-29 17:49:18,281][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.678044319152832, cross_entropy: 4.678044319152832 +[2025-04-29 17:49:19,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.816386699676514, cross_entropy: 4.816386699676514 +[2025-04-29 17:49:23,011][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.488626480102539, cross_entropy: 4.488626480102539 +[2025-04-29 17:49:24,047][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 4.663271903991699, cross_entropy: 4.663271903991699 +[2025-04-29 17:49:26,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.632810592651367, cross_entropy: 4.632810592651367 +[2025-04-29 17:49:27,466][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.598424434661865, cross_entropy: 4.598424434661865 +[2025-04-29 17:49:30,483][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.588326454162598, cross_entropy: 4.588326454162598 +[2025-04-29 17:49:31,535][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.64769172668457, cross_entropy: 4.64769172668457 +[2025-04-29 17:49:35,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.831207275390625, cross_entropy: 4.831207275390625 +[2025-04-29 17:49:36,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.717135906219482, cross_entropy: 4.717135906219482 +[2025-04-29 17:49:39,857][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.575945854187012, cross_entropy: 4.575945854187012 +[2025-04-29 17:49:40,903][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.878664970397949, cross_entropy: 4.878664970397949 +[2025-04-29 17:49:44,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.611279487609863, cross_entropy: 4.611279487609863 +[2025-04-29 17:49:45,103][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.751533508300781, cross_entropy: 4.751533508300781 +[2025-04-29 17:49:48,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.4573974609375, cross_entropy: 4.4573974609375 +[2025-04-29 17:49:49,713][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.396502494812012, cross_entropy: 4.396502494812012 +[2025-04-29 17:49:53,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 4.610512733459473, cross_entropy: 4.610512733459473 +[2025-04-29 17:49:54,183][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.730539321899414, cross_entropy: 4.730539321899414 +[2025-04-29 17:49:57,015][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.436934471130371, cross_entropy: 4.436934471130371 +[2025-04-29 17:49:58,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.580586910247803, cross_entropy: 4.580586910247803 +[2025-04-29 17:50:00,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.503360271453857, cross_entropy: 4.503360271453857 +[2025-04-29 17:50:01,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.259140491485596, cross_entropy: 4.259140491485596 +[2025-04-29 17:50:05,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 4.643581867218018, cross_entropy: 4.643581867218018 +[2025-04-29 17:50:06,126][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 4.44301700592041, cross_entropy: 4.44301700592041 +[2025-04-29 17:50:09,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.586359977722168, cross_entropy: 4.586359977722168 +[2025-04-29 17:50:10,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.4715118408203125, cross_entropy: 4.4715118408203125 +[2025-04-29 17:50:13,370][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 4.511094093322754, cross_entropy: 4.511094093322754 +[2025-04-29 17:50:14,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.563320159912109, cross_entropy: 4.563320159912109 +[2025-04-29 17:50:17,630][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 4.672549247741699, cross_entropy: 4.672549247741699 +[2025-04-29 17:50:18,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.615907192230225, cross_entropy: 4.615907192230225 +[2025-04-29 17:50:22,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 4.540011882781982, cross_entropy: 4.540011882781982 +[2025-04-29 17:50:23,240][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.559947967529297, cross_entropy: 4.559947967529297 +[2025-04-29 17:50:26,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 4.563340187072754, cross_entropy: 4.563340187072754 +[2025-04-29 17:50:27,270][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.632449626922607, cross_entropy: 4.632449626922607 +[2025-04-29 17:50:30,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 4.516787528991699, cross_entropy: 4.516787528991699 +[2025-04-29 17:50:31,082][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 4.154585838317871, cross_entropy: 4.154585838317871 +[2025-04-29 17:50:34,279][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.5116777420043945, cross_entropy: 4.5116777420043945 +[2025-04-29 17:50:35,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 4.780315399169922, cross_entropy: 4.780315399169922 +[2025-04-29 17:50:38,365][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.3365678787231445, cross_entropy: 4.3365678787231445 +[2025-04-29 17:50:39,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 4.30385684967041, cross_entropy: 4.30385684967041 +[2025-04-29 17:50:43,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.627620697021484, cross_entropy: 4.627620697021484 +[2025-04-29 17:50:44,150][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 4.187677383422852, cross_entropy: 4.187677383422852 +[2025-04-29 17:50:47,597][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 4.382656574249268, cross_entropy: 4.382656574249268 +[2025-04-29 17:50:48,633][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.612682342529297, cross_entropy: 4.612682342529297 +[2025-04-29 17:50:52,089][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.56655216217041, cross_entropy: 4.56655216217041 +[2025-04-29 17:50:53,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.1728291511535645, cross_entropy: 4.1728291511535645 +[2025-04-29 17:50:56,985][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 4.707494735717773, cross_entropy: 4.707494735717773 +[2025-04-29 17:50:58,034][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 4.260464191436768, cross_entropy: 4.260464191436768 +[2025-04-29 17:51:01,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.389378547668457, cross_entropy: 4.389378547668457 +[2025-04-29 17:51:02,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.397577285766602, cross_entropy: 4.397577285766602 +[2025-04-29 17:51:04,950][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.336797714233398, cross_entropy: 4.336797714233398 +[2025-04-29 17:51:06,002][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.763155460357666, cross_entropy: 4.763155460357666 +[2025-04-29 17:51:09,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 4.443346977233887, cross_entropy: 4.443346977233887 +[2025-04-29 17:51:10,146][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 4.743277549743652, cross_entropy: 4.743277549743652 +[2025-04-29 17:51:12,980][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 4.287128448486328, cross_entropy: 4.287128448486328 +[2025-04-29 17:51:14,028][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.172093391418457, cross_entropy: 4.172093391418457 +[2025-04-29 17:51:16,989][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 4.541013717651367, cross_entropy: 4.541013717651367 +[2025-04-29 17:51:18,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 4.759218215942383, cross_entropy: 4.759218215942383 +[2025-04-29 17:51:21,018][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.484979629516602, cross_entropy: 4.484979629516602 +[2025-04-29 17:51:22,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 4.228219032287598, cross_entropy: 4.228219032287598 +[2025-04-29 17:51:24,874][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 4.172604084014893, cross_entropy: 4.172604084014893 +[2025-04-29 17:51:25,938][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.27127742767334, cross_entropy: 4.27127742767334 +[2025-04-29 17:51:29,437][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 4.379690647125244, cross_entropy: 4.379690647125244 +[2025-04-29 17:51:30,469][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 3.976649522781372, cross_entropy: 3.976649522781372 +[2025-04-29 17:51:33,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.2220306396484375, cross_entropy: 4.2220306396484375 +[2025-04-29 17:51:34,331][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.535080432891846, cross_entropy: 4.535080432891846 +[2025-04-29 17:51:37,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 4.378232002258301, cross_entropy: 4.378232002258301 +[2025-04-29 17:51:38,153][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 4.188755035400391, cross_entropy: 4.188755035400391 +[2025-04-29 17:51:41,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.177050590515137, cross_entropy: 4.177050590515137 +[2025-04-29 17:51:42,345][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.205628871917725, cross_entropy: 4.205628871917725 +[2025-04-29 17:51:45,293][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 4.314925193786621, cross_entropy: 4.314925193786621 +[2025-04-29 17:51:46,346][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.068294525146484, cross_entropy: 4.068294525146484 +[2025-04-29 17:51:50,692][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 4.103962421417236, cross_entropy: 4.103962421417236 +[2025-04-29 17:51:51,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 4.234317779541016, cross_entropy: 4.234317779541016 +[2025-04-29 17:51:54,698][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.579280853271484, cross_entropy: 4.579280853271484 +[2025-04-29 17:51:55,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.095944881439209, cross_entropy: 4.095944881439209 +[2025-04-29 17:51:58,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 4.273802757263184, cross_entropy: 4.273802757263184 +[2025-04-29 17:51:59,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.2708587646484375, cross_entropy: 4.2708587646484375 +[2025-04-29 17:52:03,142][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.942866086959839, cross_entropy: 3.942866086959839 +[2025-04-29 17:52:04,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.46511173248291, cross_entropy: 4.46511173248291 +[2025-04-29 17:52:07,357][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.02994441986084, cross_entropy: 4.02994441986084 +[2025-04-29 17:52:08,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.8050827980041504, cross_entropy: 3.8050827980041504 +[2025-04-29 17:52:11,536][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.835383415222168, cross_entropy: 3.835383415222168 +[2025-04-29 17:52:12,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.02242374420166, cross_entropy: 4.02242374420166 +[2025-04-29 17:52:15,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 4.256205081939697, cross_entropy: 4.256205081939697 +[2025-04-29 17:52:16,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.787349224090576, cross_entropy: 3.787349224090576 +[2025-04-29 17:52:20,221][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.8148133754730225, cross_entropy: 3.8148133754730225 +[2025-04-29 17:52:21,274][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.298106670379639, cross_entropy: 4.298106670379639 +[2025-04-29 17:52:24,085][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 4.336304664611816, cross_entropy: 4.336304664611816 +[2025-04-29 17:52:25,145][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 3.9939422607421875, cross_entropy: 3.9939422607421875 +[2025-04-29 17:52:28,521][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.8628337383270264, cross_entropy: 3.8628337383270264 +[2025-04-29 17:52:29,554][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.870954751968384, cross_entropy: 3.870954751968384 +[2025-04-29 17:52:33,184][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.8274242877960205, cross_entropy: 3.8274242877960205 +[2025-04-29 17:52:34,217][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 3.8112101554870605, cross_entropy: 3.8112101554870605 +[2025-04-29 17:52:37,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.97564959526062, cross_entropy: 3.97564959526062 +[2025-04-29 17:52:38,248][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 4.278403282165527, cross_entropy: 4.278403282165527 +[2025-04-29 17:52:41,169][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.291913986206055, cross_entropy: 4.291913986206055 +[2025-04-29 17:52:42,218][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.886064052581787, cross_entropy: 3.886064052581787 +[2025-04-29 17:52:45,405][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.9795305728912354, cross_entropy: 3.9795305728912354 +[2025-04-29 17:52:46,449][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.418846607208252, cross_entropy: 4.418846607208252 +[2025-04-29 17:52:50,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.9908249378204346, cross_entropy: 3.9908249378204346 +[2025-04-29 17:52:51,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.643308162689209, cross_entropy: 3.643308162689209 +[2025-04-29 17:52:54,519][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.8903520107269287, cross_entropy: 3.8903520107269287 +[2025-04-29 17:52:55,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.7742223739624023, cross_entropy: 3.7742223739624023 +[2025-04-29 17:52:58,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.140007972717285, cross_entropy: 4.140007972717285 +[2025-04-29 17:52:59,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.463659286499023, cross_entropy: 4.463659286499023 +[2025-04-29 17:53:03,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.9357573986053467, cross_entropy: 3.9357573986053467 +[2025-04-29 17:53:04,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.7262821197509766, cross_entropy: 3.7262821197509766 +[2025-04-29 17:53:07,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.7987723350524902, cross_entropy: 3.7987723350524902 +[2025-04-29 17:53:08,869][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.6240296363830566, cross_entropy: 3.6240296363830566 +[2025-04-29 17:53:12,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.7007808685302734, cross_entropy: 3.7007808685302734 +[2025-04-29 17:53:13,123][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 3.9624695777893066, cross_entropy: 3.9624695777893066 +[2025-04-29 17:53:16,360][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.7632060050964355, cross_entropy: 3.7632060050964355 +[2025-04-29 17:53:17,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 3.9568238258361816, cross_entropy: 3.9568238258361816 +[2025-04-29 17:53:21,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.246981620788574, cross_entropy: 4.246981620788574 +[2025-04-29 17:53:22,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.873166084289551, cross_entropy: 3.873166084289551 +[2025-04-29 17:53:25,755][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 4.063899517059326, cross_entropy: 4.063899517059326 +[2025-04-29 17:53:26,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.6894969940185547, cross_entropy: 3.6894969940185547 +[2025-04-29 17:53:30,198][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 4.099842071533203, cross_entropy: 4.099842071533203 +[2025-04-29 17:53:31,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 4.227521896362305, cross_entropy: 4.227521896362305 +[2025-04-29 17:53:34,060][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.46806001663208, cross_entropy: 3.46806001663208 +[2025-04-29 17:53:35,114][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 4.105534076690674, cross_entropy: 4.105534076690674 +[2025-04-29 17:53:38,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.7834606170654297, cross_entropy: 3.7834606170654297 +[2025-04-29 17:53:39,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.128844738006592, cross_entropy: 4.128844738006592 +[2025-04-29 17:53:41,917][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.705310821533203, cross_entropy: 3.705310821533203 +[2025-04-29 17:53:42,949][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 4.085590839385986, cross_entropy: 4.085590839385986 +[2025-04-29 17:53:45,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.921952486038208, cross_entropy: 3.921952486038208 +[2025-04-29 17:53:46,755][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 4.081808090209961, cross_entropy: 4.081808090209961 +[2025-04-29 17:53:49,834][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 3.3536834716796875, cross_entropy: 3.3536834716796875 +[2025-04-29 17:53:50,906][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.6445696353912354, cross_entropy: 3.6445696353912354 +[2025-04-29 17:53:54,385][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.7141575813293457, cross_entropy: 3.7141575813293457 +[2025-04-29 17:53:55,554][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 3.606360912322998, cross_entropy: 3.606360912322998 +[2025-04-29 17:53:58,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 3.517500400543213, cross_entropy: 3.517500400543213 +[2025-04-29 17:53:59,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 4.1768670082092285, cross_entropy: 4.1768670082092285 +[2025-04-29 17:54:02,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.7170138359069824, cross_entropy: 3.7170138359069824 +[2025-04-29 17:54:03,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.427411079406738, cross_entropy: 4.427411079406738 +[2025-04-29 17:54:06,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.8307547569274902, cross_entropy: 3.8307547569274902 +[2025-04-29 17:54:07,873][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 3.3228936195373535, cross_entropy: 3.3228936195373535 +[2025-04-29 17:54:11,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.635908603668213, cross_entropy: 3.635908603668213 +[2025-04-29 17:54:12,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 3.6332809925079346, cross_entropy: 3.6332809925079346 +[2025-04-29 17:54:15,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.5478203296661377, cross_entropy: 3.5478203296661377 +[2025-04-29 17:54:16,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.799429416656494, cross_entropy: 3.799429416656494 +[2025-04-29 17:54:19,267][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.962428569793701, cross_entropy: 3.962428569793701 +[2025-04-29 17:54:20,364][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 4.425600051879883, cross_entropy: 4.425600051879883 +[2025-04-29 17:54:23,656][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 3.5650339126586914, cross_entropy: 3.5650339126586914 +[2025-04-29 17:54:24,708][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.262298583984375, cross_entropy: 3.262298583984375 +[2025-04-29 17:54:27,642][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 4.325968265533447, cross_entropy: 4.325968265533447 +[2025-04-29 17:54:28,704][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.464021682739258, cross_entropy: 3.464021682739258 +[2025-04-29 17:54:31,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 3.0039868354797363, cross_entropy: 3.0039868354797363 +[2025-04-29 17:54:33,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 4.193727493286133, cross_entropy: 4.193727493286133 +[2025-04-29 17:54:36,289][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 4.179626941680908, cross_entropy: 4.179626941680908 +[2025-04-29 17:54:37,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.796527862548828, cross_entropy: 3.796527862548828 +[2025-04-29 17:54:40,792][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 3.2078232765197754, cross_entropy: 3.2078232765197754 +[2025-04-29 17:54:41,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 4.1575446128845215, cross_entropy: 4.1575446128845215 +[2025-04-29 17:54:44,257][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.98944091796875, cross_entropy: 3.98944091796875 +[2025-04-29 17:54:46,208][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 3.6186845302581787, cross_entropy: 3.6186845302581787 +[2025-04-29 17:54:48,404][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.191740036010742, cross_entropy: 3.191740036010742 +[2025-04-29 17:54:50,594][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.587127208709717, cross_entropy: 3.587127208709717 +[2025-04-29 17:54:53,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.4284043312072754, cross_entropy: 3.4284043312072754 +[2025-04-29 17:54:54,161][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 3.6327528953552246, cross_entropy: 3.6327528953552246 +[2025-04-29 17:54:56,724][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 3.9729061126708984, cross_entropy: 3.9729061126708984 +[2025-04-29 17:54:58,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 3.8405630588531494, cross_entropy: 3.8405630588531494 +[2025-04-29 17:55:01,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 3.692922830581665, cross_entropy: 3.692922830581665 +[2025-04-29 17:55:02,473][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 3.6160686016082764, cross_entropy: 3.6160686016082764 +[2025-04-29 17:55:06,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 3.6085915565490723, cross_entropy: 3.6085915565490723 +[2025-04-29 17:55:07,451][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.3924083709716797, cross_entropy: 3.3924083709716797 +[2025-04-29 17:55:10,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.3894810676574707, cross_entropy: 3.3894810676574707 +[2025-04-29 17:55:11,335][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 3.6016454696655273, cross_entropy: 3.6016454696655273 +[2025-04-29 17:55:14,400][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 3.541375160217285, cross_entropy: 3.541375160217285 +[2025-04-29 17:55:15,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.3645429611206055, cross_entropy: 3.3645429611206055 +[2025-04-29 17:55:18,499][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.4454894065856934, cross_entropy: 3.4454894065856934 +[2025-04-29 17:55:19,550][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.251265048980713, cross_entropy: 3.251265048980713 +[2025-04-29 17:55:23,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 3.9825940132141113, cross_entropy: 3.9825940132141113 +[2025-04-29 17:55:24,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 3.02419376373291, cross_entropy: 3.02419376373291 +[2025-04-29 17:55:28,204][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 3.3885765075683594, cross_entropy: 3.3885765075683594 +[2025-04-29 17:55:29,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.589026927947998, cross_entropy: 3.589026927947998 +[2025-04-29 17:55:31,858][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 3.0575647354125977, cross_entropy: 3.0575647354125977 +[2025-04-29 17:55:32,921][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.8032727241516113, cross_entropy: 3.8032727241516113 +[2025-04-29 17:55:36,185][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 4.254520893096924, cross_entropy: 4.254520893096924 +[2025-04-29 17:55:37,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.629981279373169, cross_entropy: 3.629981279373169 +[2025-04-29 17:55:40,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 4.037923812866211, cross_entropy: 4.037923812866211 +[2025-04-29 17:55:41,106][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.4552135467529297, cross_entropy: 3.4552135467529297 +[2025-04-29 17:55:45,085][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 3.6416611671447754, cross_entropy: 3.6416611671447754 +[2025-04-29 17:55:46,132][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.3411827087402344, cross_entropy: 3.3411827087402344 +[2025-04-29 17:55:48,805][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 3.2680044174194336, cross_entropy: 3.2680044174194336 +[2025-04-29 17:55:49,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 2.8502511978149414, cross_entropy: 2.8502511978149414 +[2025-04-29 17:55:53,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.3906240463256836, cross_entropy: 3.3906240463256836 +[2025-04-29 17:55:54,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 4.221794605255127, cross_entropy: 4.221794605255127 +[2025-04-29 17:55:57,471][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 3.7726008892059326, cross_entropy: 3.7726008892059326 +[2025-04-29 17:55:58,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 3.801835536956787, cross_entropy: 3.801835536956787 +[2025-04-29 17:56:01,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 3.2300758361816406, cross_entropy: 3.2300758361816406 +[2025-04-29 17:56:02,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.9646215438842773, cross_entropy: 2.9646215438842773 +[2025-04-29 17:56:05,796][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 4.133560657501221, cross_entropy: 4.133560657501221 +[2025-04-29 17:56:06,865][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 3.6286849975585938, cross_entropy: 3.6286849975585938 +[2025-04-29 17:56:09,893][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.167900323867798, cross_entropy: 3.167900323867798 +[2025-04-29 17:56:10,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 3.319026470184326, cross_entropy: 3.319026470184326 +[2025-04-29 17:56:14,358][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.4320645332336426, cross_entropy: 3.4320645332336426 +[2025-04-29 17:56:15,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 3.427687883377075, cross_entropy: 3.427687883377075 +[2025-04-29 17:56:18,696][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.7244019508361816, cross_entropy: 2.7244019508361816 +[2025-04-29 17:56:19,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 3.503833293914795, cross_entropy: 3.503833293914795 +[2025-04-29 17:56:22,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 4.146646022796631, cross_entropy: 4.146646022796631 +[2025-04-29 17:56:23,407][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 4.013215065002441, cross_entropy: 4.013215065002441 +[2025-04-29 17:56:26,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 3.860724687576294, cross_entropy: 3.860724687576294 +[2025-04-29 17:56:27,596][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.8546671867370605, cross_entropy: 3.8546671867370605 +[2025-04-29 17:56:30,633][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.2297415733337402, cross_entropy: 3.2297415733337402 +[2025-04-29 17:56:31,689][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 4.244211196899414, cross_entropy: 4.244211196899414 +[2025-04-29 17:56:34,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 3.882190227508545, cross_entropy: 3.882190227508545 +[2025-04-29 17:56:35,540][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.314055919647217, cross_entropy: 3.314055919647217 +[2025-04-29 17:56:38,673][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 3.0154314041137695, cross_entropy: 3.0154314041137695 +[2025-04-29 17:56:39,714][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.190751552581787, cross_entropy: 4.190751552581787 +[2025-04-29 17:56:42,414][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.2984085083007812, cross_entropy: 3.2984085083007812 +[2025-04-29 17:56:43,499][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 3.550485134124756, cross_entropy: 3.550485134124756 +[2025-04-29 17:56:46,252][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.1051018238067627, cross_entropy: 3.1051018238067627 +[2025-04-29 17:56:47,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.676774024963379, cross_entropy: 3.676774024963379 +[2025-04-29 17:56:50,458][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 3.078439950942993, cross_entropy: 3.078439950942993 +[2025-04-29 17:56:51,676][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.9370760917663574, cross_entropy: 2.9370760917663574 +[2025-04-29 17:56:54,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.384711265563965, cross_entropy: 3.384711265563965 +[2025-04-29 17:56:55,524][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.093350410461426, cross_entropy: 3.093350410461426 +[2025-04-29 17:56:58,699][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 2.694624423980713, cross_entropy: 2.694624423980713 +[2025-04-29 17:57:00,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.7547268867492676, cross_entropy: 3.7547268867492676 +[2025-04-29 17:57:03,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.829864025115967, cross_entropy: 2.829864025115967 +[2025-04-29 17:57:04,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.025587558746338, cross_entropy: 3.025587558746338 +[2025-04-29 17:57:07,145][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.4712250232696533, cross_entropy: 3.4712250232696533 +[2025-04-29 17:57:10,423][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 4.027530670166016, cross_entropy: 4.027530670166016 +[2025-04-29 17:57:11,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.96112322807312, cross_entropy: 2.96112322807312 +[2025-04-29 17:57:14,123][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.972364664077759, cross_entropy: 2.972364664077759 +[2025-04-29 17:57:15,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.3414156436920166, cross_entropy: 3.3414156436920166 +[2025-04-29 17:57:19,006][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 4.208799362182617, cross_entropy: 4.208799362182617 +[2025-04-29 17:57:20,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 2.780439853668213, cross_entropy: 2.780439853668213 +[2025-04-29 17:57:23,472][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.171987533569336, cross_entropy: 3.171987533569336 +[2025-04-29 17:57:24,532][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 2.800704002380371, cross_entropy: 2.800704002380371 +[2025-04-29 17:57:27,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.5326731204986572, cross_entropy: 2.5326731204986572 +[2025-04-29 17:57:28,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.0759313106536865, cross_entropy: 3.0759313106536865 +[2025-04-29 17:57:31,769][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 3.110567092895508, cross_entropy: 3.110567092895508 +[2025-04-29 17:57:33,236][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 2.5674853324890137, cross_entropy: 2.5674853324890137 +[2025-04-29 17:57:36,300][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 3.407498359680176, cross_entropy: 3.407498359680176 +[2025-04-29 17:57:37,414][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.7290830612182617, cross_entropy: 2.7290830612182617 +[2025-04-29 17:57:41,664][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 3.153331756591797, cross_entropy: 3.153331756591797 +[2025-04-29 17:57:42,715][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.134232997894287, cross_entropy: 3.134232997894287 +[2025-04-29 17:57:45,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 2.606752872467041, cross_entropy: 2.606752872467041 +[2025-04-29 17:57:46,749][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.7439968585968018, cross_entropy: 2.7439968585968018 +[2025-04-29 17:57:50,431][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 3.7405500411987305, cross_entropy: 3.7405500411987305 +[2025-04-29 17:57:51,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.2891812324523926, cross_entropy: 3.2891812324523926 +[2025-04-29 17:57:54,724][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.0847084522247314, cross_entropy: 3.0847084522247314 +[2025-04-29 17:57:55,762][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.279879093170166, cross_entropy: 3.279879093170166 +[2025-04-29 17:57:58,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.958583354949951, cross_entropy: 2.958583354949951 +[2025-04-29 17:57:59,715][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.504558563232422, cross_entropy: 3.504558563232422 +[2025-04-29 17:58:02,631][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.9821043014526367, cross_entropy: 2.9821043014526367 +[2025-04-29 17:58:03,701][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.3061466217041016, cross_entropy: 3.3061466217041016 +[2025-04-29 17:58:06,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.3542473316192627, cross_entropy: 3.3542473316192627 +[2025-04-29 17:58:07,846][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.830871343612671, cross_entropy: 2.830871343612671 +[2025-04-29 17:58:11,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 3.878788948059082, cross_entropy: 3.878788948059082 +[2025-04-29 17:58:12,151][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 3.0356221199035645, cross_entropy: 3.0356221199035645 +[2025-04-29 17:58:15,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 2.5573387145996094, cross_entropy: 2.5573387145996094 +[2025-04-29 17:58:16,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 3.765073299407959, cross_entropy: 3.765073299407959 +[2025-04-29 17:58:19,558][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.0595507621765137, cross_entropy: 3.0595507621765137 +[2025-04-29 17:58:20,614][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 2.8920183181762695, cross_entropy: 2.8920183181762695 +[2025-04-29 17:58:23,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.892287492752075, cross_entropy: 2.892287492752075 +[2025-04-29 17:58:24,869][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 3.8311386108398438, cross_entropy: 3.8311386108398438 +[2025-04-29 17:58:28,479][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.166694402694702, cross_entropy: 3.166694402694702 +[2025-04-29 17:58:29,526][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.95705246925354, cross_entropy: 3.95705246925354 +[2025-04-29 17:58:31,861][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.3979921340942383, cross_entropy: 3.3979921340942383 +[2025-04-29 17:58:32,891][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 2.5950441360473633, cross_entropy: 2.5950441360473633 +[2025-04-29 17:58:36,058][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.423525810241699, cross_entropy: 3.423525810241699 +[2025-04-29 17:58:37,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 2.8502373695373535, cross_entropy: 2.8502373695373535 +[2025-04-29 17:58:40,032][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 3.467989206314087, cross_entropy: 3.467989206314087 +[2025-04-29 17:58:41,061][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.7782468795776367, cross_entropy: 2.7782468795776367 +[2025-04-29 17:58:44,356][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 2.4447827339172363, cross_entropy: 2.4447827339172363 +[2025-04-29 17:58:45,410][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 2.6292214393615723, cross_entropy: 2.6292214393615723 +[2025-04-29 17:58:48,433][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.7765743732452393, cross_entropy: 2.7765743732452393 +[2025-04-29 17:58:49,485][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 2.8193917274475098, cross_entropy: 2.8193917274475098 +[2025-04-29 17:58:53,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.555830955505371, cross_entropy: 3.555830955505371 +[2025-04-29 17:58:54,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.3698418140411377, cross_entropy: 3.3698418140411377 +[2025-04-29 17:58:57,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 3.1037797927856445, cross_entropy: 3.1037797927856445 +[2025-04-29 17:58:58,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.439667224884033, cross_entropy: 2.439667224884033 +[2025-04-29 17:59:01,723][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.669607639312744, cross_entropy: 3.669607639312744 +[2025-04-29 17:59:02,784][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.1565394401550293, cross_entropy: 3.1565394401550293 +[2025-04-29 17:59:05,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.7522027492523193, cross_entropy: 2.7522027492523193 +[2025-04-29 17:59:07,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.6950197219848633, cross_entropy: 2.6950197219848633 +[2025-04-29 17:59:09,885][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 2.9952049255371094, cross_entropy: 2.9952049255371094 +[2025-04-29 17:59:10,945][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.6702756881713867, cross_entropy: 2.6702756881713867 +[2025-04-29 17:59:14,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.8388900756835938, cross_entropy: 2.8388900756835938 +[2025-04-29 17:59:15,162][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.522024631500244, cross_entropy: 2.522024631500244 +[2025-04-29 17:59:18,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.88224458694458, cross_entropy: 2.88224458694458 +[2025-04-29 17:59:19,347][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 2.993212938308716, cross_entropy: 2.993212938308716 +[2025-04-29 17:59:21,877][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.0053353309631348, cross_entropy: 3.0053353309631348 +[2025-04-29 17:59:34,692][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.3669261932373047, cross_entropy: 3.3669261932373047 +[2025-04-29 18:02:43,933][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.984675645828247, cross_entropy: 3.984675645828247 +[2025-04-29 18:02:43,934][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.428849458694458, cross_entropy: 2.428849458694458 +[2025-04-29 18:02:44,436][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 18:02:44,921][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch1.pth. +[2025-04-29 18:02:45,407][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 18:02:50,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 2.757333993911743, cross_entropy: 2.757333993911743 +[2025-04-29 18:02:51,337][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 3.5638458728790283, cross_entropy: 3.5638458728790283 +[2025-04-29 18:02:54,397][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.5854852199554443, cross_entropy: 3.5854852199554443 +[2025-04-29 18:02:55,485][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 2.8085360527038574, cross_entropy: 2.8085360527038574 +[2025-04-29 18:02:57,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 3.5297601222991943, cross_entropy: 3.5297601222991943 +[2025-04-29 18:02:58,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 2.398733615875244, cross_entropy: 2.398733615875244 +[2025-04-29 18:03:01,497][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.641977310180664, cross_entropy: 2.641977310180664 +[2025-04-29 18:03:02,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 3.272367000579834, cross_entropy: 3.272367000579834 +[2025-04-29 18:03:05,672][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.8522915840148926, cross_entropy: 2.8522915840148926 +[2025-04-29 18:03:06,702][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.4067227840423584, cross_entropy: 2.4067227840423584 +[2025-04-29 18:03:10,124][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.7697367668151855, cross_entropy: 2.7697367668151855 +[2025-04-29 18:03:11,187][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 2.4260005950927734, cross_entropy: 2.4260005950927734 +[2025-04-29 18:03:14,260][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 2.7025322914123535, cross_entropy: 2.7025322914123535 +[2025-04-29 18:03:15,323][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.415483236312866, cross_entropy: 2.415483236312866 +[2025-04-29 18:03:18,185][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.7168548107147217, cross_entropy: 3.7168548107147217 +[2025-04-29 18:03:19,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 2.3111841678619385, cross_entropy: 2.3111841678619385 +[2025-04-29 18:03:22,218][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 3.1427526473999023, cross_entropy: 3.1427526473999023 +[2025-04-29 18:03:23,269][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 3.4913129806518555, cross_entropy: 3.4913129806518555 +[2025-04-29 18:03:26,666][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.718129873275757, cross_entropy: 3.718129873275757 +[2025-04-29 18:03:27,725][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.630980968475342, cross_entropy: 2.630980968475342 +[2025-04-29 18:03:30,476][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.661954164505005, cross_entropy: 3.661954164505005 +[2025-04-29 18:03:31,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 3.1960813999176025, cross_entropy: 3.1960813999176025 +[2025-04-29 18:03:34,546][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.1998038291931152, cross_entropy: 3.1998038291931152 +[2025-04-29 18:03:35,578][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.5042853355407715, cross_entropy: 3.5042853355407715 +[2025-04-29 18:03:38,597][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.637599468231201, cross_entropy: 3.637599468231201 +[2025-04-29 18:03:39,653][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.9775052070617676, cross_entropy: 2.9775052070617676 +[2025-04-29 18:03:43,451][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.1970877647399902, cross_entropy: 3.1970877647399902 +[2025-04-29 18:03:44,482][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.4875478744506836, cross_entropy: 2.4875478744506836 +[2025-04-29 18:03:47,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 2.7999796867370605, cross_entropy: 2.7999796867370605 +[2025-04-29 18:03:48,781][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 1.9908702373504639, cross_entropy: 1.9908702373504639 +[2025-04-29 18:03:51,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.897613048553467, cross_entropy: 2.897613048553467 +[2025-04-29 18:03:52,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.7895021438598633, cross_entropy: 2.7895021438598633 +[2025-04-29 18:03:55,593][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 3.401125907897949, cross_entropy: 3.401125907897949 +[2025-04-29 18:03:56,627][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 3.0984339714050293, cross_entropy: 3.0984339714050293 +[2025-04-29 18:03:59,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.8610568046569824, cross_entropy: 2.8610568046569824 +[2025-04-29 18:04:00,172][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 2.571042537689209, cross_entropy: 2.571042537689209 +[2025-04-29 18:04:02,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 2.876607894897461, cross_entropy: 2.876607894897461 +[2025-04-29 18:04:03,671][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 2.9659454822540283, cross_entropy: 2.9659454822540283 +[2025-04-29 18:04:06,814][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 2.508288860321045, cross_entropy: 2.508288860321045 +[2025-04-29 18:04:07,877][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.768846035003662, cross_entropy: 2.768846035003662 +[2025-04-29 18:04:10,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.7037270069122314, cross_entropy: 3.7037270069122314 +[2025-04-29 18:04:11,121][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 3.1575653553009033, cross_entropy: 3.1575653553009033 +[2025-04-29 18:04:14,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 2.6180033683776855, cross_entropy: 2.6180033683776855 +[2025-04-29 18:04:15,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 3.703172445297241, cross_entropy: 3.703172445297241 +[2025-04-29 18:04:18,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 2.355142831802368, cross_entropy: 2.355142831802368 +[2025-04-29 18:04:19,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 2.292806625366211, cross_entropy: 2.292806625366211 +[2025-04-29 18:04:22,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.8618927001953125, cross_entropy: 3.8618927001953125 +[2025-04-29 18:04:23,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 3.858665704727173, cross_entropy: 3.858665704727173 +[2025-04-29 18:04:26,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.6282334327697754, cross_entropy: 3.6282334327697754 +[2025-04-29 18:04:27,290][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 2.54893159866333, cross_entropy: 2.54893159866333 +[2025-04-29 18:04:30,010][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 2.9831490516662598, cross_entropy: 2.9831490516662598 +[2025-04-29 18:04:31,067][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 2.3657870292663574, cross_entropy: 2.3657870292663574 +[2025-04-29 18:04:33,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.387010335922241, cross_entropy: 3.387010335922241 +[2025-04-29 18:04:34,656][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.705714225769043, cross_entropy: 3.705714225769043 +[2025-04-29 18:04:37,757][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.354081153869629, cross_entropy: 3.354081153869629 +[2025-04-29 18:04:38,822][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.5728955268859863, cross_entropy: 2.5728955268859863 +[2025-04-29 18:04:42,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.638519287109375, cross_entropy: 2.638519287109375 +[2025-04-29 18:04:43,659][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.4181277751922607, cross_entropy: 2.4181277751922607 +[2025-04-29 18:04:47,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.2029976844787598, cross_entropy: 3.2029976844787598 +[2025-04-29 18:04:48,559][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 2.7072606086730957, cross_entropy: 2.7072606086730957 +[2025-04-29 18:04:51,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 2.5417580604553223, cross_entropy: 2.5417580604553223 +[2025-04-29 18:04:52,359][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 2.533022403717041, cross_entropy: 2.533022403717041 +[2025-04-29 18:04:55,381][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.9179112911224365, cross_entropy: 2.9179112911224365 +[2025-04-29 18:04:56,437][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 2.840095043182373, cross_entropy: 2.840095043182373 +[2025-04-29 18:04:58,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 3.537416934967041, cross_entropy: 3.537416934967041 +[2025-04-29 18:04:59,993][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 2.729418992996216, cross_entropy: 2.729418992996216 +[2025-04-29 18:05:02,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.1631956100463867, cross_entropy: 2.1631956100463867 +[2025-04-29 18:05:03,335][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 2.8271758556365967, cross_entropy: 2.8271758556365967 +[2025-04-29 18:05:05,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.963780641555786, cross_entropy: 2.963780641555786 +[2025-04-29 18:05:06,638][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 2.6672534942626953, cross_entropy: 2.6672534942626953 +[2025-04-29 18:05:09,760][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 2.8092527389526367, cross_entropy: 2.8092527389526367 +[2025-04-29 18:05:10,815][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.6252565383911133, cross_entropy: 2.6252565383911133 +[2025-04-29 18:05:13,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 2.2174055576324463, cross_entropy: 2.2174055576324463 +[2025-04-29 18:05:14,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 2.676206350326538, cross_entropy: 2.676206350326538 +[2025-04-29 18:05:17,291][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 4.122720241546631, cross_entropy: 4.122720241546631 +[2025-04-29 18:05:18,347][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 1.8499022722244263, cross_entropy: 1.8499022722244263 +[2025-04-29 18:05:21,241][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 3.3284878730773926, cross_entropy: 3.3284878730773926 +[2025-04-29 18:05:22,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.414785861968994, cross_entropy: 3.414785861968994 +[2025-04-29 18:05:25,520][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.524879217147827, cross_entropy: 3.524879217147827 +[2025-04-29 18:05:26,553][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 2.137638807296753, cross_entropy: 2.137638807296753 +[2025-04-29 18:05:28,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.8307628631591797, cross_entropy: 2.8307628631591797 +[2025-04-29 18:05:29,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.4458723068237305, cross_entropy: 3.4458723068237305 +[2025-04-29 18:05:32,910][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 3.5514116287231445, cross_entropy: 3.5514116287231445 +[2025-04-29 18:05:33,941][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 2.241992712020874, cross_entropy: 2.241992712020874 +[2025-04-29 18:05:37,129][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 2.4311203956604004, cross_entropy: 2.4311203956604004 +[2025-04-29 18:05:38,186][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 2.4916183948516846, cross_entropy: 2.4916183948516846 +[2025-04-29 18:05:40,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.485051155090332, cross_entropy: 3.485051155090332 +[2025-04-29 18:05:42,018][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.782492160797119, cross_entropy: 3.782492160797119 +[2025-04-29 18:05:44,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 2.586836099624634, cross_entropy: 2.586836099624634 +[2025-04-29 18:05:45,552][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.812690258026123, cross_entropy: 2.812690258026123 +[2025-04-29 18:05:47,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 2.626984119415283, cross_entropy: 2.626984119415283 +[2025-04-29 18:05:48,898][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.4252142906188965, cross_entropy: 3.4252142906188965 +[2025-04-29 18:05:52,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.094918727874756, cross_entropy: 3.094918727874756 +[2025-04-29 18:05:53,189][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 2.7323131561279297, cross_entropy: 2.7323131561279297 +[2025-04-29 18:05:55,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.262882709503174, cross_entropy: 2.262882709503174 +[2025-04-29 18:05:56,853][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 3.4183194637298584, cross_entropy: 3.4183194637298584 +[2025-04-29 18:05:59,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 2.3710732460021973, cross_entropy: 2.3710732460021973 +[2025-04-29 18:06:00,454][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.3546743392944336, cross_entropy: 2.3546743392944336 +[2025-04-29 18:06:03,645][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.1842281818389893, cross_entropy: 3.1842281818389893 +[2025-04-29 18:06:04,700][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.3421168327331543, cross_entropy: 3.3421168327331543 +[2025-04-29 18:06:07,900][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.3786323070526123, cross_entropy: 3.3786323070526123 +[2025-04-29 18:06:08,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 2.3792312145233154, cross_entropy: 2.3792312145233154 +[2025-04-29 18:06:11,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.184572696685791, cross_entropy: 2.184572696685791 +[2025-04-29 18:06:12,952][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.8568015098571777, cross_entropy: 2.8568015098571777 +[2025-04-29 18:06:15,245][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.4643239974975586, cross_entropy: 3.4643239974975586 +[2025-04-29 18:06:16,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.3432068824768066, cross_entropy: 3.3432068824768066 +[2025-04-29 18:06:18,658][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 3.270766258239746, cross_entropy: 3.270766258239746 +[2025-04-29 18:06:19,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 2.2934277057647705, cross_entropy: 2.2934277057647705 +[2025-04-29 18:06:22,489][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 1.971949577331543, cross_entropy: 1.971949577331543 +[2025-04-29 18:06:23,558][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.341919422149658, cross_entropy: 3.341919422149658 +[2025-04-29 18:06:26,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.8557088375091553, cross_entropy: 2.8557088375091553 +[2025-04-29 18:06:27,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.847318649291992, cross_entropy: 3.847318649291992 +[2025-04-29 18:06:31,972][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 2.142975330352783, cross_entropy: 2.142975330352783 +[2025-04-29 18:06:33,004][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 2.169262409210205, cross_entropy: 2.169262409210205 +[2025-04-29 18:06:36,567][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 2.498410224914551, cross_entropy: 2.498410224914551 +[2025-04-29 18:06:37,625][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.617929697036743, cross_entropy: 3.617929697036743 +[2025-04-29 18:06:40,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 3.101200580596924, cross_entropy: 3.101200580596924 +[2025-04-29 18:06:41,280][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.3441832065582275, cross_entropy: 3.3441832065582275 +[2025-04-29 18:06:44,176][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 2.9084360599517822, cross_entropy: 2.9084360599517822 +[2025-04-29 18:06:45,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 2.3016438484191895, cross_entropy: 2.3016438484191895 +[2025-04-29 18:06:48,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.5051019191741943, cross_entropy: 3.5051019191741943 +[2025-04-29 18:06:49,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.3030636310577393, cross_entropy: 2.3030636310577393 +[2025-04-29 18:06:52,054][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 1.9688444137573242, cross_entropy: 1.9688444137573242 +[2025-04-29 18:06:53,110][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 2.493572950363159, cross_entropy: 2.493572950363159 +[2025-04-29 18:06:56,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 2.49584698677063, cross_entropy: 2.49584698677063 +[2025-04-29 18:06:57,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.978699207305908, cross_entropy: 2.978699207305908 +[2025-04-29 18:07:01,212][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 2.2512288093566895, cross_entropy: 2.2512288093566895 +[2025-04-29 18:07:02,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 2.541095733642578, cross_entropy: 2.541095733642578 +[2025-04-29 18:07:04,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 2.522035598754883, cross_entropy: 2.522035598754883 +[2025-04-29 18:07:05,655][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.600903272628784, cross_entropy: 2.600903272628784 +[2025-04-29 18:07:08,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.8168506622314453, cross_entropy: 2.8168506622314453 +[2025-04-29 18:07:09,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 3.266653299331665, cross_entropy: 3.266653299331665 +[2025-04-29 18:07:12,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.769932746887207, cross_entropy: 2.769932746887207 +[2025-04-29 18:07:13,079][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.6051416397094727, cross_entropy: 2.6051416397094727 +[2025-04-29 18:07:15,793][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 3.4394283294677734, cross_entropy: 3.4394283294677734 +[2025-04-29 18:07:16,844][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.6465516090393066, cross_entropy: 3.6465516090393066 +[2025-04-29 18:07:20,543][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.226332187652588, cross_entropy: 2.226332187652588 +[2025-04-29 18:07:21,598][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 2.2677886486053467, cross_entropy: 2.2677886486053467 +[2025-04-29 18:07:23,297][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 2.067619800567627, cross_entropy: 2.067619800567627 +[2025-04-29 18:07:24,328][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 3.4560439586639404, cross_entropy: 3.4560439586639404 +[2025-04-29 18:07:27,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.7121777534484863, cross_entropy: 3.7121777534484863 +[2025-04-29 18:07:28,406][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.681666851043701, cross_entropy: 2.681666851043701 +[2025-04-29 18:07:31,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.104245901107788, cross_entropy: 3.104245901107788 +[2025-04-29 18:07:32,081][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 3.6345925331115723, cross_entropy: 3.6345925331115723 +[2025-04-29 18:07:35,005][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.3873367309570312, cross_entropy: 2.3873367309570312 +[2025-04-29 18:07:36,060][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 2.8082046508789062, cross_entropy: 2.8082046508789062 +[2025-04-29 18:07:38,866][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.814396619796753, cross_entropy: 2.814396619796753 +[2025-04-29 18:07:39,928][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 3.812481164932251, cross_entropy: 3.812481164932251 +[2025-04-29 18:07:43,043][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.7822751998901367, cross_entropy: 2.7822751998901367 +[2025-04-29 18:07:44,107][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.723818302154541, cross_entropy: 3.723818302154541 +[2025-04-29 18:07:47,092][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.4147517681121826, cross_entropy: 2.4147517681121826 +[2025-04-29 18:07:48,127][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 1.9663209915161133, cross_entropy: 1.9663209915161133 +[2025-04-29 18:07:51,009][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 2.071789264678955, cross_entropy: 2.071789264678955 +[2025-04-29 18:07:52,072][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 3.7869648933410645, cross_entropy: 3.7869648933410645 +[2025-04-29 18:07:54,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.0918121337890625, cross_entropy: 3.0918121337890625 +[2025-04-29 18:07:55,862][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.3147122859954834, cross_entropy: 2.3147122859954834 +[2025-04-29 18:07:58,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 3.069455623626709, cross_entropy: 3.069455623626709 +[2025-04-29 18:07:59,396][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.2295467853546143, cross_entropy: 3.2295467853546143 +[2025-04-29 18:08:02,117][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 2.4627251625061035, cross_entropy: 2.4627251625061035 +[2025-04-29 18:08:03,174][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 1.9251158237457275, cross_entropy: 1.9251158237457275 +[2025-04-29 18:08:06,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 1.7509205341339111, cross_entropy: 1.7509205341339111 +[2025-04-29 18:08:07,101][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.166199207305908, cross_entropy: 3.166199207305908 +[2025-04-29 18:08:10,505][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.7743687629699707, cross_entropy: 2.7743687629699707 +[2025-04-29 18:08:11,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 2.2451353073120117, cross_entropy: 2.2451353073120117 +[2025-04-29 18:08:13,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 2.943169355392456, cross_entropy: 2.943169355392456 +[2025-04-29 18:08:14,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.3418691158294678, cross_entropy: 2.3418691158294678 +[2025-04-29 18:08:18,199][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 3.2160303592681885, cross_entropy: 3.2160303592681885 +[2025-04-29 18:08:19,253][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.3612632751464844, cross_entropy: 2.3612632751464844 +[2025-04-29 18:08:21,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 3.6000852584838867, cross_entropy: 3.6000852584838867 +[2025-04-29 18:08:22,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.838895797729492, cross_entropy: 2.838895797729492 +[2025-04-29 18:08:25,848][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 2.4607253074645996, cross_entropy: 2.4607253074645996 +[2025-04-29 18:08:26,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.3929619789123535, cross_entropy: 2.3929619789123535 +[2025-04-29 18:08:30,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.5660276412963867, cross_entropy: 2.5660276412963867 +[2025-04-29 18:08:31,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.841689109802246, cross_entropy: 2.841689109802246 +[2025-04-29 18:08:34,061][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.164243698120117, cross_entropy: 2.164243698120117 +[2025-04-29 18:08:35,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 3.1887083053588867, cross_entropy: 3.1887083053588867 +[2025-04-29 18:08:38,218][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 2.1655001640319824, cross_entropy: 2.1655001640319824 +[2025-04-29 18:08:39,283][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 3.4964001178741455, cross_entropy: 3.4964001178741455 +[2025-04-29 18:08:42,748][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 3.206587314605713, cross_entropy: 3.206587314605713 +[2025-04-29 18:08:43,781][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.3138537406921387, cross_entropy: 3.3138537406921387 +[2025-04-29 18:08:46,023][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.152963161468506, cross_entropy: 2.152963161468506 +[2025-04-29 18:08:47,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 2.1246538162231445, cross_entropy: 2.1246538162231445 +[2025-04-29 18:08:49,747][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 2.714595317840576, cross_entropy: 2.714595317840576 +[2025-04-29 18:08:50,803][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.2565975189208984, cross_entropy: 2.2565975189208984 +[2025-04-29 18:08:53,292][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.398993730545044, cross_entropy: 2.398993730545044 +[2025-04-29 18:08:54,350][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 2.86775279045105, cross_entropy: 2.86775279045105 +[2025-04-29 18:08:57,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.0024986267089844, cross_entropy: 2.0024986267089844 +[2025-04-29 18:08:58,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 2.4053964614868164, cross_entropy: 2.4053964614868164 +[2025-04-29 18:09:00,460][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 2.8897900581359863, cross_entropy: 2.8897900581359863 +[2025-04-29 18:09:01,520][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.093045234680176, cross_entropy: 2.093045234680176 +[2025-04-29 18:09:04,121][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.3763577938079834, cross_entropy: 3.3763577938079834 +[2025-04-29 18:09:05,185][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 1.979646921157837, cross_entropy: 1.979646921157837 +[2025-04-29 18:09:07,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.626305103302002, cross_entropy: 2.626305103302002 +[2025-04-29 18:09:09,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 1.789478063583374, cross_entropy: 1.789478063583374 +[2025-04-29 18:09:11,088][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.459264039993286, cross_entropy: 2.459264039993286 +[2025-04-29 18:09:12,119][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.4553656578063965, cross_entropy: 2.4553656578063965 +[2025-04-29 18:09:15,281][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.5590550899505615, cross_entropy: 3.5590550899505615 +[2025-04-29 18:09:16,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 2.3978633880615234, cross_entropy: 2.3978633880615234 +[2025-04-29 18:09:19,077][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.882720470428467, cross_entropy: 3.882720470428467 +[2025-04-29 18:09:20,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 3.539306640625, cross_entropy: 3.539306640625 +[2025-04-29 18:09:22,169][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 2.3753890991210938, cross_entropy: 2.3753890991210938 +[2025-04-29 18:09:23,222][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 3.5519652366638184, cross_entropy: 3.5519652366638184 +[2025-04-29 18:09:26,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.188228130340576, cross_entropy: 3.188228130340576 +[2025-04-29 18:09:27,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.1195292472839355, cross_entropy: 2.1195292472839355 +[2025-04-29 18:09:29,996][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.2401273250579834, cross_entropy: 2.2401273250579834 +[2025-04-29 18:09:31,029][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 2.1319732666015625, cross_entropy: 2.1319732666015625 +[2025-04-29 18:09:34,392][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.832035541534424, cross_entropy: 2.832035541534424 +[2025-04-29 18:09:35,435][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 1.9210753440856934, cross_entropy: 1.9210753440856934 +[2025-04-29 18:09:39,546][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 2.618366003036499, cross_entropy: 2.618366003036499 +[2025-04-29 18:09:40,580][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 2.836402416229248, cross_entropy: 2.836402416229248 +[2025-04-29 18:09:43,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 2.0581541061401367, cross_entropy: 2.0581541061401367 +[2025-04-29 18:09:44,352][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 3.613832473754883, cross_entropy: 3.613832473754883 +[2025-04-29 18:09:47,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.9966955184936523, cross_entropy: 2.9966955184936523 +[2025-04-29 18:09:48,615][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.22871732711792, cross_entropy: 2.22871732711792 +[2025-04-29 18:09:51,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.2233786582946777, cross_entropy: 2.2233786582946777 +[2025-04-29 18:09:52,420][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 3.298983573913574, cross_entropy: 3.298983573913574 +[2025-04-29 18:09:55,037][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 3.413647413253784, cross_entropy: 3.413647413253784 +[2025-04-29 18:09:56,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 3.531996488571167, cross_entropy: 3.531996488571167 +[2025-04-29 18:09:59,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.067075729370117, cross_entropy: 2.067075729370117 +[2025-04-29 18:10:00,143][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.9066381454467773, cross_entropy: 2.9066381454467773 +[2025-04-29 18:10:02,562][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.258424758911133, cross_entropy: 3.258424758911133 +[2025-04-29 18:10:03,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.3503639698028564, cross_entropy: 2.3503639698028564 +[2025-04-29 18:10:06,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.5644021034240723, cross_entropy: 2.5644021034240723 +[2025-04-29 18:10:07,062][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.677424669265747, cross_entropy: 2.677424669265747 +[2025-04-29 18:10:09,785][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.225407123565674, cross_entropy: 2.225407123565674 +[2025-04-29 18:10:10,821][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.087409496307373, cross_entropy: 2.087409496307373 +[2025-04-29 18:10:13,440][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 2.184016466140747, cross_entropy: 2.184016466140747 +[2025-04-29 18:10:14,469][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.5676558017730713, cross_entropy: 3.5676558017730713 +[2025-04-29 18:10:17,859][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 2.7378103733062744, cross_entropy: 2.7378103733062744 +[2025-04-29 18:10:18,890][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 3.647325277328491, cross_entropy: 3.647325277328491 +[2025-04-29 18:10:22,005][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 2.4128291606903076, cross_entropy: 2.4128291606903076 +[2025-04-29 18:10:23,059][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.3228819370269775, cross_entropy: 2.3228819370269775 +[2025-04-29 18:10:25,668][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 2.069972515106201, cross_entropy: 2.069972515106201 +[2025-04-29 18:10:26,723][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.9618630409240723, cross_entropy: 1.9618630409240723 +[2025-04-29 18:10:28,609][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.992666721343994, cross_entropy: 2.992666721343994 +[2025-04-29 18:10:29,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.345986843109131, cross_entropy: 2.345986843109131 +[2025-04-29 18:10:32,499][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 1.945129632949829, cross_entropy: 1.945129632949829 +[2025-04-29 18:10:33,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 2.263237953186035, cross_entropy: 2.263237953186035 +[2025-04-29 18:10:36,725][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 2.066849946975708, cross_entropy: 2.066849946975708 +[2025-04-29 18:10:37,764][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.0532407760620117, cross_entropy: 2.0532407760620117 +[2025-04-29 18:10:40,650][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 2.461946725845337, cross_entropy: 2.461946725845337 +[2025-04-29 18:10:41,713][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 3.2837328910827637, cross_entropy: 3.2837328910827637 +[2025-04-29 18:10:44,865][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.35428786277771, cross_entropy: 3.35428786277771 +[2025-04-29 18:10:45,927][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.7153308391571045, cross_entropy: 2.7153308391571045 +[2025-04-29 18:10:48,429][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 2.6203818321228027, cross_entropy: 2.6203818321228027 +[2025-04-29 18:10:49,498][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 3.461069345474243, cross_entropy: 3.461069345474243 +[2025-04-29 18:10:51,673][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.0605111122131348, cross_entropy: 2.0605111122131348 +[2025-04-29 18:10:52,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 2.0936646461486816, cross_entropy: 2.0936646461486816 +[2025-04-29 18:10:54,966][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.4230847358703613, cross_entropy: 2.4230847358703613 +[2025-04-29 18:10:56,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 2.2147486209869385, cross_entropy: 2.2147486209869385 +[2025-04-29 18:10:58,502][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.5002098083496094, cross_entropy: 3.5002098083496094 +[2025-04-29 18:10:59,572][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.5930187702178955, cross_entropy: 3.5930187702178955 +[2025-04-29 18:11:02,168][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.1816349029541016, cross_entropy: 3.1816349029541016 +[2025-04-29 18:11:03,200][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.5135598182678223, cross_entropy: 3.5135598182678223 +[2025-04-29 18:11:06,623][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 3.47436785697937, cross_entropy: 3.47436785697937 +[2025-04-29 18:11:07,655][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 2.1363251209259033, cross_entropy: 2.1363251209259033 +[2025-04-29 18:11:11,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 2.4004499912261963, cross_entropy: 2.4004499912261963 +[2025-04-29 18:11:12,065][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.1065714359283447, cross_entropy: 2.1065714359283447 +[2025-04-29 18:11:14,845][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.315352439880371, cross_entropy: 2.315352439880371 +[2025-04-29 18:11:15,903][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.926565647125244, cross_entropy: 2.926565647125244 +[2025-04-29 18:11:18,854][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.1792232990264893, cross_entropy: 2.1792232990264893 +[2025-04-29 18:11:19,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.0992684364318848, cross_entropy: 2.0992684364318848 +[2025-04-29 18:11:23,668][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.3017807006835938, cross_entropy: 2.3017807006835938 +[2025-04-29 18:11:24,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 1.976494312286377, cross_entropy: 1.976494312286377 +[2025-04-29 18:11:28,075][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.592369556427002, cross_entropy: 2.592369556427002 +[2025-04-29 18:11:29,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.74027943611145, cross_entropy: 2.74027943611145 +[2025-04-29 18:11:31,833][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 3.643667697906494, cross_entropy: 3.643667697906494 +[2025-04-29 18:11:32,864][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 2.121737003326416, cross_entropy: 2.121737003326416 +[2025-04-29 18:11:35,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 1.924149513244629, cross_entropy: 1.924149513244629 +[2025-04-29 18:11:36,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 3.082793951034546, cross_entropy: 3.082793951034546 +[2025-04-29 18:11:39,625][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 1.7662220001220703, cross_entropy: 1.7662220001220703 +[2025-04-29 18:11:40,663][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 2.38822078704834, cross_entropy: 2.38822078704834 +[2025-04-29 18:11:42,836][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.0660195350646973, cross_entropy: 3.0660195350646973 +[2025-04-29 18:11:43,866][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 1.7822816371917725, cross_entropy: 1.7822816371917725 +[2025-04-29 18:11:47,131][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 2.178708076477051, cross_entropy: 2.178708076477051 +[2025-04-29 18:11:48,163][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 3.5958328247070312, cross_entropy: 3.5958328247070312 +[2025-04-29 18:11:51,330][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 1.9057295322418213, cross_entropy: 1.9057295322418213 +[2025-04-29 18:11:52,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 2.6824891567230225, cross_entropy: 2.6824891567230225 +[2025-04-29 18:11:55,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.0122499465942383, cross_entropy: 2.0122499465942383 +[2025-04-29 18:11:56,353][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.101088523864746, cross_entropy: 2.101088523864746 +[2025-04-29 18:11:58,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.6540565490722656, cross_entropy: 3.6540565490722656 +[2025-04-29 18:11:59,567][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 3.0804121494293213, cross_entropy: 3.0804121494293213 +[2025-04-29 18:12:02,290][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 2.675198793411255, cross_entropy: 2.675198793411255 +[2025-04-29 18:12:03,345][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 2.270280361175537, cross_entropy: 2.270280361175537 +[2025-04-29 18:12:06,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 3.125244617462158, cross_entropy: 3.125244617462158 +[2025-04-29 18:12:07,198][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 3.565948486328125, cross_entropy: 3.565948486328125 +[2025-04-29 18:12:09,594][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.1466429233551025, cross_entropy: 3.1466429233551025 +[2025-04-29 18:12:10,624][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 2.1017165184020996, cross_entropy: 2.1017165184020996 +[2025-04-29 18:12:13,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 2.953350067138672, cross_entropy: 2.953350067138672 +[2025-04-29 18:12:14,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.2276058197021484, cross_entropy: 3.2276058197021484 +[2025-04-29 18:12:17,318][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 3.3483004570007324, cross_entropy: 3.3483004570007324 +[2025-04-29 18:12:18,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.829376220703125, cross_entropy: 2.829376220703125 +[2025-04-29 18:12:20,751][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.343780755996704, cross_entropy: 3.343780755996704 +[2025-04-29 18:12:21,815][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 3.3908982276916504, cross_entropy: 3.3908982276916504 +[2025-04-29 18:12:24,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 3.627295970916748, cross_entropy: 3.627295970916748 +[2025-04-29 18:12:25,290][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.6508030891418457, cross_entropy: 2.6508030891418457 +[2025-04-29 18:12:27,047][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 2.8034963607788086, cross_entropy: 2.8034963607788086 +[2025-04-29 18:12:28,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.7720859050750732, cross_entropy: 1.7720859050750732 +[2025-04-29 18:12:30,827][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.2010085582733154, cross_entropy: 3.2010085582733154 +[2025-04-29 18:12:31,938][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.1460623741149902, cross_entropy: 3.1460623741149902 +[2025-04-29 18:12:34,692][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 2.0214028358459473, cross_entropy: 2.0214028358459473 +[2025-04-29 18:12:35,750][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 1.992315411567688, cross_entropy: 1.992315411567688 +[2025-04-29 18:12:38,727][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.5595815181732178, cross_entropy: 2.5595815181732178 +[2025-04-29 18:12:39,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 3.4481472969055176, cross_entropy: 3.4481472969055176 +[2025-04-29 18:12:42,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 1.8800389766693115, cross_entropy: 1.8800389766693115 +[2025-04-29 18:12:43,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 1.9220647811889648, cross_entropy: 1.9220647811889648 +[2025-04-29 18:12:47,200][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 2.5224900245666504, cross_entropy: 2.5224900245666504 +[2025-04-29 18:12:48,262][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 3.786008358001709, cross_entropy: 3.786008358001709 +[2025-04-29 18:12:51,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 3.430802822113037, cross_entropy: 3.430802822113037 +[2025-04-29 18:12:52,284][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.9066753387451172, cross_entropy: 1.9066753387451172 +[2025-04-29 18:12:55,546][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 1.829744815826416, cross_entropy: 1.829744815826416 +[2025-04-29 18:12:56,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 1.8827264308929443, cross_entropy: 1.8827264308929443 +[2025-04-29 18:12:59,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.242605209350586, cross_entropy: 3.242605209350586 +[2025-04-29 18:13:00,806][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 1.6739696264266968, cross_entropy: 1.6739696264266968 +[2025-04-29 18:13:03,653][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.0114517211914062, cross_entropy: 2.0114517211914062 +[2025-04-29 18:13:04,710][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.0561816692352295, cross_entropy: 2.0561816692352295 +[2025-04-29 18:13:07,605][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 2.9205470085144043, cross_entropy: 2.9205470085144043 +[2025-04-29 18:13:08,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.775212049484253, cross_entropy: 2.775212049484253 +[2025-04-29 18:13:11,658][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 1.8912357091903687, cross_entropy: 1.8912357091903687 +[2025-04-29 18:13:12,694][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 2.8733999729156494, cross_entropy: 2.8733999729156494 +[2025-04-29 18:13:15,858][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.4002230167388916, cross_entropy: 2.4002230167388916 +[2025-04-29 18:13:16,918][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 3.200632095336914, cross_entropy: 3.200632095336914 +[2025-04-29 18:13:19,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 1.8833110332489014, cross_entropy: 1.8833110332489014 +[2025-04-29 18:13:20,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.0763072967529297, cross_entropy: 2.0763072967529297 +[2025-04-29 18:13:23,257][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 1.862825632095337, cross_entropy: 1.862825632095337 +[2025-04-29 18:13:24,314][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 2.4727625846862793, cross_entropy: 2.4727625846862793 +[2025-04-29 18:13:26,712][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.0211193561553955, cross_entropy: 2.0211193561553955 +[2025-04-29 18:13:27,775][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.42960262298584, cross_entropy: 3.42960262298584 +[2025-04-29 18:13:30,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.692282795906067, cross_entropy: 1.692282795906067 +[2025-04-29 18:13:31,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.5526976585388184, cross_entropy: 2.5526976585388184 +[2025-04-29 18:13:33,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.2632944583892822, cross_entropy: 3.2632944583892822 +[2025-04-29 18:13:34,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.5782785415649414, cross_entropy: 3.5782785415649414 +[2025-04-29 18:13:37,447][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 1.512113332748413, cross_entropy: 1.512113332748413 +[2025-04-29 18:13:38,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 3.1262876987457275, cross_entropy: 3.1262876987457275 +[2025-04-29 18:13:41,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 1.9776785373687744, cross_entropy: 1.9776785373687744 +[2025-04-29 18:13:42,200][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 2.302692413330078, cross_entropy: 2.302692413330078 +[2025-04-29 18:13:44,441][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.5097012519836426, cross_entropy: 3.5097012519836426 +[2025-04-29 18:13:45,564][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 1.8229384422302246, cross_entropy: 1.8229384422302246 +[2025-04-29 18:13:48,214][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 2.323899269104004, cross_entropy: 2.323899269104004 +[2025-04-29 18:13:49,245][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.662111520767212, cross_entropy: 2.662111520767212 +[2025-04-29 18:13:52,488][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.444720506668091, cross_entropy: 3.444720506668091 +[2025-04-29 18:13:53,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 2.1978743076324463, cross_entropy: 2.1978743076324463 +[2025-04-29 18:13:56,709][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 1.8645719289779663, cross_entropy: 1.8645719289779663 +[2025-04-29 18:13:57,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 1.9907243251800537, cross_entropy: 1.9907243251800537 +[2025-04-29 18:14:00,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 2.5619022846221924, cross_entropy: 2.5619022846221924 +[2025-04-29 18:14:01,401][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.036668062210083, cross_entropy: 3.036668062210083 +[2025-04-29 18:14:04,499][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.3532490730285645, cross_entropy: 3.3532490730285645 +[2025-04-29 18:14:05,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 3.0505847930908203, cross_entropy: 3.0505847930908203 +[2025-04-29 18:14:09,295][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 3.002931594848633, cross_entropy: 3.002931594848633 +[2025-04-29 18:14:10,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.3341336250305176, cross_entropy: 2.3341336250305176 +[2025-04-29 18:14:12,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.774198055267334, cross_entropy: 2.774198055267334 +[2025-04-29 18:14:14,027][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 1.5734140872955322, cross_entropy: 1.5734140872955322 +[2025-04-29 18:14:16,347][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.760063648223877, cross_entropy: 1.760063648223877 +[2025-04-29 18:14:17,377][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 2.4377753734588623, cross_entropy: 2.4377753734588623 +[2025-04-29 18:14:19,952][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 1.7676146030426025, cross_entropy: 1.7676146030426025 +[2025-04-29 18:14:20,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 1.6139609813690186, cross_entropy: 1.6139609813690186 +[2025-04-29 18:17:07,176][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.7405455112457275, cross_entropy: 2.7405455112457275 +[2025-04-29 18:17:07,177][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.7418818473815918, cross_entropy: 1.7418818473815918 +[2025-04-29 18:17:08,046][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 18:17:08,528][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch2.pth. +[2025-04-29 18:17:09,340][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 18:17:14,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 2.413239002227783, cross_entropy: 2.413239002227783 +[2025-04-29 18:17:15,926][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 2.1411256790161133, cross_entropy: 2.1411256790161133 +[2025-04-29 18:17:19,095][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 3.267547845840454, cross_entropy: 3.267547845840454 +[2025-04-29 18:17:20,133][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 1.7654953002929688, cross_entropy: 1.7654953002929688 +[2025-04-29 18:17:22,416][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.6078426837921143, cross_entropy: 1.6078426837921143 +[2025-04-29 18:17:23,534][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 3.264645576477051, cross_entropy: 3.264645576477051 +[2025-04-29 18:17:26,230][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.9765956401824951, cross_entropy: 1.9765956401824951 +[2025-04-29 18:17:27,310][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 1.9796230792999268, cross_entropy: 1.9796230792999268 +[2025-04-29 18:17:30,297][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.5594877004623413, cross_entropy: 1.5594877004623413 +[2025-04-29 18:17:31,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 3.1258015632629395, cross_entropy: 3.1258015632629395 +[2025-04-29 18:17:34,581][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.212975263595581, cross_entropy: 2.212975263595581 +[2025-04-29 18:17:35,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 3.0300185680389404, cross_entropy: 3.0300185680389404 +[2025-04-29 18:17:38,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.3801931142807007, cross_entropy: 1.3801931142807007 +[2025-04-29 18:17:39,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 1.96623694896698, cross_entropy: 1.96623694896698 +[2025-04-29 18:17:43,036][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 3.038069248199463, cross_entropy: 3.038069248199463 +[2025-04-29 18:17:44,295][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 1.6047312021255493, cross_entropy: 1.6047312021255493 +[2025-04-29 18:17:47,138][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.3542370796203613, cross_entropy: 3.3542370796203613 +[2025-04-29 18:17:48,213][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.6211776733398438, cross_entropy: 2.6211776733398438 +[2025-04-29 18:17:51,371][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.8323043584823608, cross_entropy: 1.8323043584823608 +[2025-04-29 18:17:52,431][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.996159315109253, cross_entropy: 1.996159315109253 +[2025-04-29 18:17:55,783][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 2.9824094772338867, cross_entropy: 2.9824094772338867 +[2025-04-29 18:17:56,831][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.8542572259902954, cross_entropy: 1.8542572259902954 +[2025-04-29 18:17:59,174][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 2.2277119159698486, cross_entropy: 2.2277119159698486 +[2025-04-29 18:18:00,207][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 1.3897137641906738, cross_entropy: 1.3897137641906738 +[2025-04-29 18:18:03,305][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 2.935809850692749, cross_entropy: 2.935809850692749 +[2025-04-29 18:18:04,337][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 1.6654765605926514, cross_entropy: 1.6654765605926514 +[2025-04-29 18:18:06,376][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 3.2031471729278564, cross_entropy: 3.2031471729278564 +[2025-04-29 18:18:07,439][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.5817036628723145, cross_entropy: 2.5817036628723145 +[2025-04-29 18:18:10,840][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 1.781813383102417, cross_entropy: 1.781813383102417 +[2025-04-29 18:18:11,903][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.6274476051330566, cross_entropy: 2.6274476051330566 +[2025-04-29 18:18:14,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.2233915328979492, cross_entropy: 1.2233915328979492 +[2025-04-29 18:18:15,470][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 1.747859001159668, cross_entropy: 1.747859001159668 +[2025-04-29 18:18:18,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.3656368255615234, cross_entropy: 3.3656368255615234 +[2025-04-29 18:18:19,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 2.8113183975219727, cross_entropy: 2.8113183975219727 +[2025-04-29 18:18:22,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 1.8591164350509644, cross_entropy: 1.8591164350509644 +[2025-04-29 18:18:23,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.024416446685791, cross_entropy: 3.024416446685791 +[2025-04-29 18:18:26,310][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.2955093383789062, cross_entropy: 2.2955093383789062 +[2025-04-29 18:18:27,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.9619660377502441, cross_entropy: 1.9619660377502441 +[2025-04-29 18:18:30,486][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 2.9447484016418457, cross_entropy: 2.9447484016418457 +[2025-04-29 18:18:31,556][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 2.3248064517974854, cross_entropy: 2.3248064517974854 +[2025-04-29 18:18:35,266][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.2442412376403809, cross_entropy: 1.2442412376403809 +[2025-04-29 18:18:36,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 1.3715872764587402, cross_entropy: 1.3715872764587402 +[2025-04-29 18:18:38,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 2.4100093841552734, cross_entropy: 2.4100093841552734 +[2025-04-29 18:18:39,854][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.3284990787506104, cross_entropy: 2.3284990787506104 +[2025-04-29 18:18:42,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 3.5130844116210938, cross_entropy: 3.5130844116210938 +[2025-04-29 18:18:44,060][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 2.6558237075805664, cross_entropy: 2.6558237075805664 +[2025-04-29 18:18:46,678][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.7657358646392822, cross_entropy: 1.7657358646392822 +[2025-04-29 18:18:47,727][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.6717987060546875, cross_entropy: 2.6717987060546875 +[2025-04-29 18:18:50,306][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 3.0465307235717773, cross_entropy: 3.0465307235717773 +[2025-04-29 18:18:51,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 3.215869426727295, cross_entropy: 3.215869426727295 +[2025-04-29 18:18:53,590][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 3.226837158203125, cross_entropy: 3.226837158203125 +[2025-04-29 18:18:54,625][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 1.8208122253417969, cross_entropy: 1.8208122253417969 +[2025-04-29 18:18:57,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.055870294570923, cross_entropy: 2.055870294570923 +[2025-04-29 18:18:58,439][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.093717336654663, cross_entropy: 3.093717336654663 +[2025-04-29 18:19:01,398][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 1.708510398864746, cross_entropy: 1.708510398864746 +[2025-04-29 18:19:02,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 1.8363826274871826, cross_entropy: 1.8363826274871826 +[2025-04-29 18:19:05,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.1913652420043945, cross_entropy: 3.1913652420043945 +[2025-04-29 18:19:06,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.0429458618164062, cross_entropy: 2.0429458618164062 +[2025-04-29 18:19:08,688][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 1.609228491783142, cross_entropy: 1.609228491783142 +[2025-04-29 18:19:09,750][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 2.0267484188079834, cross_entropy: 2.0267484188079834 +[2025-04-29 18:19:12,015][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 3.0265631675720215, cross_entropy: 3.0265631675720215 +[2025-04-29 18:19:13,084][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 1.3821070194244385, cross_entropy: 1.3821070194244385 +[2025-04-29 18:19:15,809][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 1.6691663265228271, cross_entropy: 1.6691663265228271 +[2025-04-29 18:19:16,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 2.92683482170105, cross_entropy: 2.92683482170105 +[2025-04-29 18:19:19,474][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.0800819396972656, cross_entropy: 3.0800819396972656 +[2025-04-29 18:19:20,540][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.6044464111328125, cross_entropy: 2.6044464111328125 +[2025-04-29 18:19:23,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 2.003434181213379, cross_entropy: 2.003434181213379 +[2025-04-29 18:19:24,137][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.2812318801879883, cross_entropy: 3.2812318801879883 +[2025-04-29 18:19:26,900][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 3.0144760608673096, cross_entropy: 3.0144760608673096 +[2025-04-29 18:19:27,962][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 1.6977317333221436, cross_entropy: 1.6977317333221436 +[2025-04-29 18:19:29,882][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 1.5463206768035889, cross_entropy: 1.5463206768035889 +[2025-04-29 18:19:30,916][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 1.9169186353683472, cross_entropy: 1.9169186353683472 +[2025-04-29 18:19:34,142][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 2.0314440727233887, cross_entropy: 2.0314440727233887 +[2025-04-29 18:19:35,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.932814121246338, cross_entropy: 2.932814121246338 +[2025-04-29 18:19:38,313][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 2.9812536239624023, cross_entropy: 2.9812536239624023 +[2025-04-29 18:19:39,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 3.4439568519592285, cross_entropy: 3.4439568519592285 +[2025-04-29 18:19:41,911][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 1.8438124656677246, cross_entropy: 1.8438124656677246 +[2025-04-29 18:19:42,970][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 3.341914415359497, cross_entropy: 3.341914415359497 +[2025-04-29 18:19:45,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.2547216415405273, cross_entropy: 3.2547216415405273 +[2025-04-29 18:19:46,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 2.181701421737671, cross_entropy: 2.181701421737671 +[2025-04-29 18:19:49,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 1.6319087743759155, cross_entropy: 1.6319087743759155 +[2025-04-29 18:19:50,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.5773147344589233, cross_entropy: 1.5773147344589233 +[2025-04-29 18:19:53,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 2.6647114753723145, cross_entropy: 2.6647114753723145 +[2025-04-29 18:19:54,250][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 2.825885772705078, cross_entropy: 2.825885772705078 +[2025-04-29 18:19:56,970][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 1.7979910373687744, cross_entropy: 1.7979910373687744 +[2025-04-29 18:19:58,029][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.2149477005004883, cross_entropy: 2.2149477005004883 +[2025-04-29 18:20:00,423][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 1.177816390991211, cross_entropy: 1.177816390991211 +[2025-04-29 18:20:01,455][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 1.55083429813385, cross_entropy: 1.55083429813385 +[2025-04-29 18:20:03,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 1.6339128017425537, cross_entropy: 1.6339128017425537 +[2025-04-29 18:20:05,063][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 2.8682663440704346, cross_entropy: 2.8682663440704346 +[2025-04-29 18:20:07,534][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 1.7627313137054443, cross_entropy: 1.7627313137054443 +[2025-04-29 18:20:08,596][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.92079758644104, cross_entropy: 1.92079758644104 +[2025-04-29 18:20:11,253][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.7695008516311646, cross_entropy: 1.7695008516311646 +[2025-04-29 18:20:12,284][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 3.2180371284484863, cross_entropy: 3.2180371284484863 +[2025-04-29 18:20:15,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.333918809890747, cross_entropy: 3.333918809890747 +[2025-04-29 18:20:16,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.8375194072723389, cross_entropy: 1.8375194072723389 +[2025-04-29 18:20:18,652][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 1.8690555095672607, cross_entropy: 1.8690555095672607 +[2025-04-29 18:20:19,684][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 1.7696945667266846, cross_entropy: 1.7696945667266846 +[2025-04-29 18:20:22,893][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 1.919177770614624, cross_entropy: 1.919177770614624 +[2025-04-29 18:20:23,927][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.222196578979492, cross_entropy: 2.222196578979492 +[2025-04-29 18:20:26,824][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.3729114532470703, cross_entropy: 2.3729114532470703 +[2025-04-29 18:20:27,855][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 1.710716724395752, cross_entropy: 1.710716724395752 +[2025-04-29 18:20:30,996][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 1.416404366493225, cross_entropy: 1.416404366493225 +[2025-04-29 18:20:32,058][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.9688127040863037, cross_entropy: 1.9688127040863037 +[2025-04-29 18:20:35,305][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 1.8590387105941772, cross_entropy: 1.8590387105941772 +[2025-04-29 18:20:36,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.7245376110076904, cross_entropy: 2.7245376110076904 +[2025-04-29 18:20:39,029][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.911147356033325, cross_entropy: 2.911147356033325 +[2025-04-29 18:20:40,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 2.3228352069854736, cross_entropy: 2.3228352069854736 +[2025-04-29 18:20:42,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 1.938529372215271, cross_entropy: 1.938529372215271 +[2025-04-29 18:20:43,800][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.7785351276397705, cross_entropy: 2.7785351276397705 +[2025-04-29 18:20:46,578][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 3.4960713386535645, cross_entropy: 3.4960713386535645 +[2025-04-29 18:20:47,639][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.8463338613510132, cross_entropy: 1.8463338613510132 +[2025-04-29 18:20:50,240][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 2.4788670539855957, cross_entropy: 2.4788670539855957 +[2025-04-29 18:20:51,288][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 1.0611932277679443, cross_entropy: 1.0611932277679443 +[2025-04-29 18:20:54,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 1.332749843597412, cross_entropy: 1.332749843597412 +[2025-04-29 18:20:55,468][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 3.459125518798828, cross_entropy: 3.459125518798828 +[2025-04-29 18:20:59,090][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 1.58549964427948, cross_entropy: 1.58549964427948 +[2025-04-29 18:21:00,149][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 3.331904172897339, cross_entropy: 3.331904172897339 +[2025-04-29 18:21:03,012][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 2.3153328895568848, cross_entropy: 2.3153328895568848 +[2025-04-29 18:21:04,130][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.631044864654541, cross_entropy: 2.631044864654541 +[2025-04-29 18:21:07,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 2.1536972522735596, cross_entropy: 2.1536972522735596 +[2025-04-29 18:21:08,183][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 3.578913688659668, cross_entropy: 3.578913688659668 +[2025-04-29 18:21:10,777][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 3.3586459159851074, cross_entropy: 3.3586459159851074 +[2025-04-29 18:21:11,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 3.297309637069702, cross_entropy: 3.297309637069702 +[2025-04-29 18:21:14,846][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 1.8104658126831055, cross_entropy: 1.8104658126831055 +[2025-04-29 18:21:15,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 1.8535547256469727, cross_entropy: 1.8535547256469727 +[2025-04-29 18:21:18,884][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 2.324673652648926, cross_entropy: 2.324673652648926 +[2025-04-29 18:21:19,945][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 2.116209030151367, cross_entropy: 2.116209030151367 +[2025-04-29 18:21:22,343][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 1.975376844406128, cross_entropy: 1.975376844406128 +[2025-04-29 18:21:23,403][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 1.6204876899719238, cross_entropy: 1.6204876899719238 +[2025-04-29 18:21:26,251][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.999009132385254, cross_entropy: 2.999009132385254 +[2025-04-29 18:21:27,286][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 2.1171374320983887, cross_entropy: 2.1171374320983887 +[2025-04-29 18:21:30,349][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 1.278576135635376, cross_entropy: 1.278576135635376 +[2025-04-29 18:21:31,405][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 3.0362930297851562, cross_entropy: 3.0362930297851562 +[2025-04-29 18:21:35,302][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 1.9809025526046753, cross_entropy: 1.9809025526046753 +[2025-04-29 18:21:36,360][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.796473741531372, cross_entropy: 1.796473741531372 +[2025-04-29 18:21:39,320][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.7262797355651855, cross_entropy: 2.7262797355651855 +[2025-04-29 18:21:40,378][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.5379374027252197, cross_entropy: 1.5379374027252197 +[2025-04-29 18:21:42,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.6592488288879395, cross_entropy: 2.6592488288879395 +[2025-04-29 18:21:43,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 3.1897990703582764, cross_entropy: 3.1897990703582764 +[2025-04-29 18:21:46,984][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.237821102142334, cross_entropy: 2.237821102142334 +[2025-04-29 18:21:48,040][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 2.9999985694885254, cross_entropy: 2.9999985694885254 +[2025-04-29 18:21:50,166][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 3.56638503074646, cross_entropy: 3.56638503074646 +[2025-04-29 18:21:51,223][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.4511852264404297, cross_entropy: 2.4511852264404297 +[2025-04-29 18:21:53,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.9948513507843018, cross_entropy: 2.9948513507843018 +[2025-04-29 18:21:54,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.222327709197998, cross_entropy: 2.222327709197998 +[2025-04-29 18:21:57,610][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.6636443138122559, cross_entropy: 1.6636443138122559 +[2025-04-29 18:21:58,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 2.418567419052124, cross_entropy: 2.418567419052124 +[2025-04-29 18:22:01,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 3.325533866882324, cross_entropy: 3.325533866882324 +[2025-04-29 18:22:02,382][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 2.311330795288086, cross_entropy: 2.311330795288086 +[2025-04-29 18:22:05,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.4708876609802246, cross_entropy: 1.4708876609802246 +[2025-04-29 18:22:06,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.2674455642700195, cross_entropy: 2.2674455642700195 +[2025-04-29 18:22:09,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.0371546745300293, cross_entropy: 2.0371546745300293 +[2025-04-29 18:22:10,901][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 2.289862632751465, cross_entropy: 2.289862632751465 +[2025-04-29 18:22:13,429][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.224233627319336, cross_entropy: 2.224233627319336 +[2025-04-29 18:22:14,491][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.7213516235351562, cross_entropy: 2.7213516235351562 +[2025-04-29 18:22:16,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.561497688293457, cross_entropy: 1.561497688293457 +[2025-04-29 18:22:17,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 2.553314685821533, cross_entropy: 2.553314685821533 +[2025-04-29 18:22:20,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 2.0585989952087402, cross_entropy: 2.0585989952087402 +[2025-04-29 18:22:21,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 3.4125137329101562, cross_entropy: 3.4125137329101562 +[2025-04-29 18:22:25,026][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 2.9159090518951416, cross_entropy: 2.9159090518951416 +[2025-04-29 18:22:26,087][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 2.2039477825164795, cross_entropy: 2.2039477825164795 +[2025-04-29 18:22:29,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.3446993827819824, cross_entropy: 3.3446993827819824 +[2025-04-29 18:22:30,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 2.9497077465057373, cross_entropy: 2.9497077465057373 +[2025-04-29 18:22:34,113][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 1.7638894319534302, cross_entropy: 1.7638894319534302 +[2025-04-29 18:22:35,149][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 3.179447889328003, cross_entropy: 3.179447889328003 +[2025-04-29 18:22:37,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 2.3856563568115234, cross_entropy: 2.3856563568115234 +[2025-04-29 18:22:38,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 1.774756908416748, cross_entropy: 1.774756908416748 +[2025-04-29 18:22:41,653][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 2.313171863555908, cross_entropy: 2.313171863555908 +[2025-04-29 18:22:42,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 1.863527774810791, cross_entropy: 1.863527774810791 +[2025-04-29 18:22:45,190][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 3.4705471992492676, cross_entropy: 3.4705471992492676 +[2025-04-29 18:22:46,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.2081563472747803, cross_entropy: 2.2081563472747803 +[2025-04-29 18:22:48,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 2.9525434970855713, cross_entropy: 2.9525434970855713 +[2025-04-29 18:22:49,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.548584222793579, cross_entropy: 2.548584222793579 +[2025-04-29 18:22:53,066][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 3.1845507621765137, cross_entropy: 3.1845507621765137 +[2025-04-29 18:22:54,127][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 3.0865559577941895, cross_entropy: 3.0865559577941895 +[2025-04-29 18:22:57,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.277461051940918, cross_entropy: 2.277461051940918 +[2025-04-29 18:22:58,204][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 1.4267743825912476, cross_entropy: 1.4267743825912476 +[2025-04-29 18:23:02,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.7239048480987549, cross_entropy: 1.7239048480987549 +[2025-04-29 18:23:03,396][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 1.9757273197174072, cross_entropy: 1.9757273197174072 +[2025-04-29 18:23:06,095][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.953500509262085, cross_entropy: 1.953500509262085 +[2025-04-29 18:23:07,148][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 3.6799120903015137, cross_entropy: 3.6799120903015137 +[2025-04-29 18:23:10,222][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 1.6499534845352173, cross_entropy: 1.6499534845352173 +[2025-04-29 18:23:11,258][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 1.905994176864624, cross_entropy: 1.905994176864624 +[2025-04-29 18:23:13,722][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 1.6475934982299805, cross_entropy: 1.6475934982299805 +[2025-04-29 18:23:14,758][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 1.2135183811187744, cross_entropy: 1.2135183811187744 +[2025-04-29 18:23:17,424][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.423215389251709, cross_entropy: 2.423215389251709 +[2025-04-29 18:23:18,480][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 3.2803196907043457, cross_entropy: 3.2803196907043457 +[2025-04-29 18:23:21,164][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 1.555544376373291, cross_entropy: 1.555544376373291 +[2025-04-29 18:23:22,222][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 2.4977285861968994, cross_entropy: 2.4977285861968994 +[2025-04-29 18:23:25,132][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 3.477506637573242, cross_entropy: 3.477506637573242 +[2025-04-29 18:23:26,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 1.4477014541625977, cross_entropy: 1.4477014541625977 +[2025-04-29 18:23:28,856][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 1.5486137866973877, cross_entropy: 1.5486137866973877 +[2025-04-29 18:23:29,915][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 2.477569341659546, cross_entropy: 2.477569341659546 +[2025-04-29 18:23:32,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 1.973421573638916, cross_entropy: 1.973421573638916 +[2025-04-29 18:23:33,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 1.5164787769317627, cross_entropy: 1.5164787769317627 +[2025-04-29 18:23:36,727][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 3.073190212249756, cross_entropy: 3.073190212249756 +[2025-04-29 18:23:37,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 1.6266905069351196, cross_entropy: 1.6266905069351196 +[2025-04-29 18:23:40,355][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.9244184494018555, cross_entropy: 1.9244184494018555 +[2025-04-29 18:23:41,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 1.88785982131958, cross_entropy: 1.88785982131958 +[2025-04-29 18:23:44,489][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.2398905754089355, cross_entropy: 2.2398905754089355 +[2025-04-29 18:23:45,547][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.9493937492370605, cross_entropy: 2.9493937492370605 +[2025-04-29 18:23:48,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 2.9998350143432617, cross_entropy: 2.9998350143432617 +[2025-04-29 18:23:49,469][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 1.2369177341461182, cross_entropy: 1.2369177341461182 +[2025-04-29 18:23:52,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.3351454734802246, cross_entropy: 3.3351454734802246 +[2025-04-29 18:23:53,246][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 1.4982054233551025, cross_entropy: 1.4982054233551025 +[2025-04-29 18:23:55,557][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.9966793060302734, cross_entropy: 2.9966793060302734 +[2025-04-29 18:23:56,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 1.4969011545181274, cross_entropy: 1.4969011545181274 +[2025-04-29 18:23:58,874][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.8608832359313965, cross_entropy: 2.8608832359313965 +[2025-04-29 18:23:59,938][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 1.0629236698150635, cross_entropy: 1.0629236698150635 +[2025-04-29 18:24:02,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 1.592198133468628, cross_entropy: 1.592198133468628 +[2025-04-29 18:24:03,674][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.8031224012374878, cross_entropy: 1.8031224012374878 +[2025-04-29 18:24:06,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 1.9875739812850952, cross_entropy: 1.9875739812850952 +[2025-04-29 18:24:07,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.852193593978882, cross_entropy: 2.852193593978882 +[2025-04-29 18:24:10,113][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.8930405378341675, cross_entropy: 1.8930405378341675 +[2025-04-29 18:24:11,188][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 3.5557448863983154, cross_entropy: 3.5557448863983154 +[2025-04-29 18:24:13,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.903717517852783, cross_entropy: 2.903717517852783 +[2025-04-29 18:24:15,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.0521650314331055, cross_entropy: 3.0521650314331055 +[2025-04-29 18:24:17,421][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 1.547715425491333, cross_entropy: 1.547715425491333 +[2025-04-29 18:24:18,480][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 2.2601795196533203, cross_entropy: 2.2601795196533203 +[2025-04-29 18:24:21,317][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.6000860929489136, cross_entropy: 1.6000860929489136 +[2025-04-29 18:24:22,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 1.8251560926437378, cross_entropy: 1.8251560926437378 +[2025-04-29 18:24:25,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 1.7681933641433716, cross_entropy: 1.7681933641433716 +[2025-04-29 18:24:26,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 1.8381632566452026, cross_entropy: 1.8381632566452026 +[2025-04-29 18:24:30,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 1.7637732028961182, cross_entropy: 1.7637732028961182 +[2025-04-29 18:24:31,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.9688503742218018, cross_entropy: 1.9688503742218018 +[2025-04-29 18:24:33,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.2766377925872803, cross_entropy: 1.2766377925872803 +[2025-04-29 18:24:34,469][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 2.4187240600585938, cross_entropy: 2.4187240600585938 +[2025-04-29 18:24:38,440][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.716616153717041, cross_entropy: 1.716616153717041 +[2025-04-29 18:24:39,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 2.002962350845337, cross_entropy: 2.002962350845337 +[2025-04-29 18:24:41,788][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.474975109100342, cross_entropy: 2.474975109100342 +[2025-04-29 18:24:42,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 2.614459753036499, cross_entropy: 2.614459753036499 +[2025-04-29 18:24:45,657][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 3.3088650703430176, cross_entropy: 3.3088650703430176 +[2025-04-29 18:24:46,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 2.5478596687316895, cross_entropy: 2.5478596687316895 +[2025-04-29 18:24:50,525][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 2.5238540172576904, cross_entropy: 2.5238540172576904 +[2025-04-29 18:24:51,581][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.019009828567505, cross_entropy: 2.019009828567505 +[2025-04-29 18:24:53,924][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.0611069202423096, cross_entropy: 3.0611069202423096 +[2025-04-29 18:24:54,991][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 3.0347397327423096, cross_entropy: 3.0347397327423096 +[2025-04-29 18:24:57,212][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 1.9849491119384766, cross_entropy: 1.9849491119384766 +[2025-04-29 18:24:58,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 3.2460036277770996, cross_entropy: 3.2460036277770996 +[2025-04-29 18:25:00,821][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.873776435852051, cross_entropy: 2.873776435852051 +[2025-04-29 18:25:01,854][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 3.2522706985473633, cross_entropy: 3.2522706985473633 +[2025-04-29 18:25:04,507][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.8610639572143555, cross_entropy: 2.8610639572143555 +[2025-04-29 18:25:05,570][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 2.2293596267700195, cross_entropy: 2.2293596267700195 +[2025-04-29 18:25:08,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.7517151832580566, cross_entropy: 1.7517151832580566 +[2025-04-29 18:25:09,972][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 1.8510597944259644, cross_entropy: 1.8510597944259644 +[2025-04-29 18:25:12,398][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 2.7120275497436523, cross_entropy: 2.7120275497436523 +[2025-04-29 18:25:13,787][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.5573488473892212, cross_entropy: 1.5573488473892212 +[2025-04-29 18:25:16,403][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 3.0254623889923096, cross_entropy: 3.0254623889923096 +[2025-04-29 18:25:17,463][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 1.5507519245147705, cross_entropy: 1.5507519245147705 +[2025-04-29 18:25:20,584][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.2158491611480713, cross_entropy: 2.2158491611480713 +[2025-04-29 18:25:21,642][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.963820219039917, cross_entropy: 1.963820219039917 +[2025-04-29 18:25:24,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 1.3765408992767334, cross_entropy: 1.3765408992767334 +[2025-04-29 18:25:25,136][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 3.0522446632385254, cross_entropy: 3.0522446632385254 +[2025-04-29 18:25:29,207][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 1.5523128509521484, cross_entropy: 1.5523128509521484 +[2025-04-29 18:25:30,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 1.5079036951065063, cross_entropy: 1.5079036951065063 +[2025-04-29 18:25:33,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.9461796283721924, cross_entropy: 1.9461796283721924 +[2025-04-29 18:25:34,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 1.4780504703521729, cross_entropy: 1.4780504703521729 +[2025-04-29 18:25:37,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.8017020225524902, cross_entropy: 1.8017020225524902 +[2025-04-29 18:25:38,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.0580272674560547, cross_entropy: 2.0580272674560547 +[2025-04-29 18:25:41,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 1.1021950244903564, cross_entropy: 1.1021950244903564 +[2025-04-29 18:25:42,733][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.9256175756454468, cross_entropy: 1.9256175756454468 +[2025-04-29 18:25:45,573][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.3672492504119873, cross_entropy: 3.3672492504119873 +[2025-04-29 18:25:46,631][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.7037920951843262, cross_entropy: 1.7037920951843262 +[2025-04-29 18:25:49,087][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 1.4259083271026611, cross_entropy: 1.4259083271026611 +[2025-04-29 18:25:50,150][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 3.2559895515441895, cross_entropy: 3.2559895515441895 +[2025-04-29 18:25:52,611][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 1.795515775680542, cross_entropy: 1.795515775680542 +[2025-04-29 18:25:53,686][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.244974970817566, cross_entropy: 1.244974970817566 +[2025-04-29 18:25:56,472][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 1.703925609588623, cross_entropy: 1.703925609588623 +[2025-04-29 18:25:57,545][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 3.452915906906128, cross_entropy: 3.452915906906128 +[2025-04-29 18:26:00,071][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.3068881034851074, cross_entropy: 3.3068881034851074 +[2025-04-29 18:26:01,129][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.877169132232666, cross_entropy: 1.877169132232666 +[2025-04-29 18:26:03,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 2.37192964553833, cross_entropy: 2.37192964553833 +[2025-04-29 18:26:05,107][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.1502280235290527, cross_entropy: 2.1502280235290527 +[2025-04-29 18:26:06,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 1.3833234310150146, cross_entropy: 1.3833234310150146 +[2025-04-29 18:26:08,716][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 2.0618274211883545, cross_entropy: 2.0618274211883545 +[2025-04-29 18:26:10,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 1.8376691341400146, cross_entropy: 1.8376691341400146 +[2025-04-29 18:26:12,354][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 1.9767343997955322, cross_entropy: 1.9767343997955322 +[2025-04-29 18:26:14,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.820237159729004, cross_entropy: 1.820237159729004 +[2025-04-29 18:26:16,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 1.4254775047302246, cross_entropy: 1.4254775047302246 +[2025-04-29 18:26:18,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.6579827070236206, cross_entropy: 1.6579827070236206 +[2025-04-29 18:26:19,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 1.3563768863677979, cross_entropy: 1.3563768863677979 +[2025-04-29 18:26:21,532][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.995145559310913, cross_entropy: 1.995145559310913 +[2025-04-29 18:26:23,389][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 3.5457348823547363, cross_entropy: 3.5457348823547363 +[2025-04-29 18:26:25,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.620416283607483, cross_entropy: 1.620416283607483 +[2025-04-29 18:26:27,462][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 3.0260066986083984, cross_entropy: 3.0260066986083984 +[2025-04-29 18:26:29,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.214076519012451, cross_entropy: 2.214076519012451 +[2025-04-29 18:26:31,335][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.7591650485992432, cross_entropy: 1.7591650485992432 +[2025-04-29 18:26:32,073][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/iteration1000.pth. +[2025-04-29 18:26:33,145][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.918635368347168, cross_entropy: 2.918635368347168 +[2025-04-29 18:26:35,105][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.9162315130233765, cross_entropy: 1.9162315130233765 +[2025-04-29 18:26:36,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.119351625442505, cross_entropy: 3.119351625442505 +[2025-04-29 18:26:38,592][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.7590323686599731, cross_entropy: 1.7590323686599731 +[2025-04-29 18:26:40,116][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.9892070293426514, cross_entropy: 1.9892070293426514 +[2025-04-29 18:26:41,884][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 1.8342365026474, cross_entropy: 1.8342365026474 +[2025-04-29 18:26:43,646][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.682363510131836, cross_entropy: 2.682363510131836 +[2025-04-29 18:26:46,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 1.5173237323760986, cross_entropy: 1.5173237323760986 +[2025-04-29 18:26:47,711][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 1.5180423259735107, cross_entropy: 1.5180423259735107 +[2025-04-29 18:26:49,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.5692520141601562, cross_entropy: 2.5692520141601562 +[2025-04-29 18:26:51,454][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 2.9787979125976562, cross_entropy: 2.9787979125976562 +[2025-04-29 18:26:53,009][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.0781593322753906, cross_entropy: 2.0781593322753906 +[2025-04-29 18:26:54,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 2.3228774070739746, cross_entropy: 2.3228774070739746 +[2025-04-29 18:26:57,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 2.5343918800354004, cross_entropy: 2.5343918800354004 +[2025-04-29 18:26:58,490][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.8209036588668823, cross_entropy: 1.8209036588668823 +[2025-04-29 18:27:01,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 2.2604947090148926, cross_entropy: 2.2604947090148926 +[2025-04-29 18:27:02,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 1.7346993684768677, cross_entropy: 1.7346993684768677 +[2025-04-29 18:27:05,073][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.1191391944885254, cross_entropy: 2.1191391944885254 +[2025-04-29 18:27:06,184][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.592703342437744, cross_entropy: 2.592703342437744 +[2025-04-29 18:27:09,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 1.9153519868850708, cross_entropy: 1.9153519868850708 +[2025-04-29 18:27:10,285][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 1.8508150577545166, cross_entropy: 1.8508150577545166 +[2025-04-29 18:27:12,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 1.7217844724655151, cross_entropy: 1.7217844724655151 +[2025-04-29 18:27:13,806][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.686009407043457, cross_entropy: 1.686009407043457 +[2025-04-29 18:27:16,020][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 3.233459949493408, cross_entropy: 3.233459949493408 +[2025-04-29 18:27:18,251][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.5342649221420288, cross_entropy: 1.5342649221420288 +[2025-04-29 18:27:20,262][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.3310394287109375, cross_entropy: 2.3310394287109375 +[2025-04-29 18:27:22,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 1.459186315536499, cross_entropy: 1.459186315536499 +[2025-04-29 18:27:23,993][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.718975305557251, cross_entropy: 2.718975305557251 +[2025-04-29 18:27:26,505][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.4595210552215576, cross_entropy: 2.4595210552215576 +[2025-04-29 18:27:27,867][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.421722173690796, cross_entropy: 1.421722173690796 +[2025-04-29 18:27:29,822][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.5083942413330078, cross_entropy: 1.5083942413330078 +[2025-04-29 18:27:30,943][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 1.3611805438995361, cross_entropy: 1.3611805438995361 +[2025-04-29 18:27:35,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 3.143307685852051, cross_entropy: 3.143307685852051 +[2025-04-29 18:27:36,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 1.9108939170837402, cross_entropy: 1.9108939170837402 +[2025-04-29 18:27:39,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 2.7758169174194336, cross_entropy: 2.7758169174194336 +[2025-04-29 18:27:40,116][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 1.3830842971801758, cross_entropy: 1.3830842971801758 +[2025-04-29 18:27:43,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 3.4691524505615234, cross_entropy: 3.4691524505615234 +[2025-04-29 18:27:44,198][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.7249444723129272, cross_entropy: 1.7249444723129272 +[2025-04-29 18:27:47,303][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 1.654869556427002, cross_entropy: 1.654869556427002 +[2025-04-29 18:27:48,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 2.5483241081237793, cross_entropy: 2.5483241081237793 +[2025-04-29 18:27:51,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 3.1337623596191406, cross_entropy: 3.1337623596191406 +[2025-04-29 18:27:52,429][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 1.6782399415969849, cross_entropy: 1.6782399415969849 +[2025-04-29 18:27:55,158][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.1660852432250977, cross_entropy: 3.1660852432250977 +[2025-04-29 18:27:56,221][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 1.8384870290756226, cross_entropy: 1.8384870290756226 +[2025-04-29 18:27:58,807][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 1.349395990371704, cross_entropy: 1.349395990371704 +[2025-04-29 18:27:59,869][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 2.597144842147827, cross_entropy: 2.597144842147827 +[2025-04-29 18:28:02,255][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.563568115234375, cross_entropy: 1.563568115234375 +[2025-04-29 18:28:03,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.935598850250244, cross_entropy: 2.935598850250244 +[2025-04-29 18:28:05,060][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 1.934662103652954, cross_entropy: 1.934662103652954 +[2025-04-29 18:28:06,146][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.5295592546463013, cross_entropy: 1.5295592546463013 +[2025-04-29 18:28:08,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 1.4731788635253906, cross_entropy: 1.4731788635253906 +[2025-04-29 18:28:09,433][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.329000949859619, cross_entropy: 2.329000949859619 +[2025-04-29 18:28:12,692][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.7225115299224854, cross_entropy: 1.7225115299224854 +[2025-04-29 18:28:14,124][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.3222596645355225, cross_entropy: 2.3222596645355225 +[2025-04-29 18:28:16,873][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.3764218091964722, cross_entropy: 1.3764218091964722 +[2025-04-29 18:28:17,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.0054187774658203, cross_entropy: 3.0054187774658203 +[2025-04-29 18:28:20,794][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 1.4374608993530273, cross_entropy: 1.4374608993530273 +[2025-04-29 18:28:21,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.6069200038909912, cross_entropy: 1.6069200038909912 +[2025-04-29 18:28:25,642][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.6627953052520752, cross_entropy: 1.6627953052520752 +[2025-04-29 18:28:26,677][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.759479284286499, cross_entropy: 1.759479284286499 +[2025-04-29 18:28:28,849][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.571930170059204, cross_entropy: 1.571930170059204 +[2025-04-29 18:28:30,096][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 2.831584930419922, cross_entropy: 2.831584930419922 +[2025-04-29 18:28:32,817][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 2.505952835083008, cross_entropy: 2.505952835083008 +[2025-04-29 18:28:33,895][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.9618988037109375, cross_entropy: 2.9618988037109375 +[2025-04-29 18:28:37,083][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 1.3214354515075684, cross_entropy: 1.3214354515075684 +[2025-04-29 18:28:38,140][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.5881098508834839, cross_entropy: 1.5881098508834839 +[2025-04-29 18:28:40,632][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.406542181968689, cross_entropy: 1.406542181968689 +[2025-04-29 18:28:41,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 3.2213902473449707, cross_entropy: 3.2213902473449707 +[2025-04-29 18:31:32,709][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.251600980758667, cross_entropy: 2.251600980758667 +[2025-04-29 18:31:32,709][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.4447561502456665, cross_entropy: 1.4447561502456665 +[2025-04-29 18:31:33,638][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 18:31:34,140][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch3.pth. +[2025-04-29 18:31:34,927][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 18:31:39,753][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.1575143337249756, cross_entropy: 1.1575143337249756 +[2025-04-29 18:31:40,872][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 2.4659371376037598, cross_entropy: 2.4659371376037598 +[2025-04-29 18:31:44,327][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 2.9071922302246094, cross_entropy: 2.9071922302246094 +[2025-04-29 18:31:45,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.6189231872558594, cross_entropy: 1.6189231872558594 +[2025-04-29 18:31:48,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 2.9096412658691406, cross_entropy: 2.9096412658691406 +[2025-04-29 18:31:49,165][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.5867667198181152, cross_entropy: 1.5867667198181152 +[2025-04-29 18:31:51,992][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.7368264198303223, cross_entropy: 1.7368264198303223 +[2025-04-29 18:31:53,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 1.2646522521972656, cross_entropy: 1.2646522521972656 +[2025-04-29 18:31:57,316][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.378717303276062, cross_entropy: 1.378717303276062 +[2025-04-29 18:31:58,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.3591902256011963, cross_entropy: 1.3591902256011963 +[2025-04-29 18:32:01,060][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 2.839627742767334, cross_entropy: 2.839627742767334 +[2025-04-29 18:32:02,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.894369602203369, cross_entropy: 2.894369602203369 +[2025-04-29 18:32:04,801][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 2.8935461044311523, cross_entropy: 2.8935461044311523 +[2025-04-29 18:32:05,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.8785455226898193, cross_entropy: 2.8785455226898193 +[2025-04-29 18:32:09,586][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 2.555243968963623, cross_entropy: 2.555243968963623 +[2025-04-29 18:32:10,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 2.949726104736328, cross_entropy: 2.949726104736328 +[2025-04-29 18:32:13,806][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 3.0562095642089844, cross_entropy: 3.0562095642089844 +[2025-04-29 18:32:14,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 1.3760426044464111, cross_entropy: 1.3760426044464111 +[2025-04-29 18:32:17,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.3539557456970215, cross_entropy: 3.3539557456970215 +[2025-04-29 18:32:18,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.27372407913208, cross_entropy: 2.27372407913208 +[2025-04-29 18:32:21,799][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 2.867065191268921, cross_entropy: 2.867065191268921 +[2025-04-29 18:32:22,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.6282603740692139, cross_entropy: 1.6282603740692139 +[2025-04-29 18:32:26,055][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.466917037963867, cross_entropy: 2.466917037963867 +[2025-04-29 18:32:27,115][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 1.3960453271865845, cross_entropy: 1.3960453271865845 +[2025-04-29 18:32:29,695][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 1.7549867630004883, cross_entropy: 1.7549867630004883 +[2025-04-29 18:32:30,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 3.0330896377563477, cross_entropy: 3.0330896377563477 +[2025-04-29 18:32:33,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 3.2085251808166504, cross_entropy: 3.2085251808166504 +[2025-04-29 18:32:34,549][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 2.018953323364258, cross_entropy: 2.018953323364258 +[2025-04-29 18:32:37,972][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.28275465965271, cross_entropy: 2.28275465965271 +[2025-04-29 18:32:39,030][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 1.4167369604110718, cross_entropy: 1.4167369604110718 +[2025-04-29 18:32:42,521][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 1.9708974361419678, cross_entropy: 1.9708974361419678 +[2025-04-29 18:32:43,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.1196129322052002, cross_entropy: 1.1196129322052002 +[2025-04-29 18:32:46,050][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 2.8511626720428467, cross_entropy: 2.8511626720428467 +[2025-04-29 18:32:47,105][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.0062785148620605, cross_entropy: 2.0062785148620605 +[2025-04-29 18:32:49,905][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 3.110013008117676, cross_entropy: 3.110013008117676 +[2025-04-29 18:32:50,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 1.4091401100158691, cross_entropy: 1.4091401100158691 +[2025-04-29 18:32:53,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.4899200201034546, cross_entropy: 1.4899200201034546 +[2025-04-29 18:32:54,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 2.7431721687316895, cross_entropy: 2.7431721687316895 +[2025-04-29 18:32:57,872][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 1.0813692808151245, cross_entropy: 1.0813692808151245 +[2025-04-29 18:32:58,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 2.8929288387298584, cross_entropy: 2.8929288387298584 +[2025-04-29 18:33:01,440][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.0112361907958984, cross_entropy: 2.0112361907958984 +[2025-04-29 18:33:02,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 2.7591097354888916, cross_entropy: 2.7591097354888916 +[2025-04-29 18:33:05,552][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 1.3296778202056885, cross_entropy: 1.3296778202056885 +[2025-04-29 18:33:06,585][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.190150260925293, cross_entropy: 2.190150260925293 +[2025-04-29 18:33:09,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 1.824669361114502, cross_entropy: 1.824669361114502 +[2025-04-29 18:33:10,703][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.6747517585754395, cross_entropy: 2.6747517585754395 +[2025-04-29 18:33:14,466][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.5282506942749023, cross_entropy: 2.5282506942749023 +[2025-04-29 18:33:15,499][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.8265184164047241, cross_entropy: 1.8265184164047241 +[2025-04-29 18:33:18,654][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 2.974787712097168, cross_entropy: 2.974787712097168 +[2025-04-29 18:33:19,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 1.2391141653060913, cross_entropy: 1.2391141653060913 +[2025-04-29 18:33:22,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.7045319080352783, cross_entropy: 1.7045319080352783 +[2025-04-29 18:33:23,511][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.7638112306594849, cross_entropy: 1.7638112306594849 +[2025-04-29 18:33:26,277][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.5015058517456055, cross_entropy: 2.5015058517456055 +[2025-04-29 18:33:27,312][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.48018741607666, cross_entropy: 2.48018741607666 +[2025-04-29 18:33:30,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 1.6847143173217773, cross_entropy: 1.6847143173217773 +[2025-04-29 18:33:31,283][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 3.065305233001709, cross_entropy: 3.065305233001709 +[2025-04-29 18:33:33,914][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.8572585582733154, cross_entropy: 2.8572585582733154 +[2025-04-29 18:33:34,976][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.2047414779663086, cross_entropy: 2.2047414779663086 +[2025-04-29 18:33:38,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 3.1863784790039062, cross_entropy: 3.1863784790039062 +[2025-04-29 18:33:39,726][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.9297780990600586, cross_entropy: 2.9297780990600586 +[2025-04-29 18:33:41,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.3768577575683594, cross_entropy: 1.3768577575683594 +[2025-04-29 18:33:42,853][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 3.087705612182617, cross_entropy: 3.087705612182617 +[2025-04-29 18:33:46,179][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 3.0468192100524902, cross_entropy: 3.0468192100524902 +[2025-04-29 18:33:47,238][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 3.107377529144287, cross_entropy: 3.107377529144287 +[2025-04-29 18:33:49,890][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.6073355674743652, cross_entropy: 2.6073355674743652 +[2025-04-29 18:33:50,923][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 2.5262839794158936, cross_entropy: 2.5262839794158936 +[2025-04-29 18:33:53,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.21738600730896, cross_entropy: 2.21738600730896 +[2025-04-29 18:33:54,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 1.8032057285308838, cross_entropy: 1.8032057285308838 +[2025-04-29 18:33:57,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.661099910736084, cross_entropy: 2.661099910736084 +[2025-04-29 18:33:58,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 1.1296889781951904, cross_entropy: 1.1296889781951904 +[2025-04-29 18:34:00,896][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 1.42820405960083, cross_entropy: 1.42820405960083 +[2025-04-29 18:34:02,040][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.3735802173614502, cross_entropy: 1.3735802173614502 +[2025-04-29 18:34:04,891][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 2.900247097015381, cross_entropy: 2.900247097015381 +[2025-04-29 18:34:05,986][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.3340485095977783, cross_entropy: 1.3340485095977783 +[2025-04-29 18:34:08,297][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 1.1369686126708984, cross_entropy: 1.1369686126708984 +[2025-04-29 18:34:09,382][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 3.1646921634674072, cross_entropy: 3.1646921634674072 +[2025-04-29 18:34:12,113][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.0721265077590942, cross_entropy: 1.0721265077590942 +[2025-04-29 18:34:13,221][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 1.5776863098144531, cross_entropy: 1.5776863098144531 +[2025-04-29 18:34:15,567][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 2.872774124145508, cross_entropy: 2.872774124145508 +[2025-04-29 18:34:16,637][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.941666841506958, cross_entropy: 1.941666841506958 +[2025-04-29 18:34:19,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.4330077171325684, cross_entropy: 3.4330077171325684 +[2025-04-29 18:34:20,773][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 1.4128358364105225, cross_entropy: 1.4128358364105225 +[2025-04-29 18:34:23,170][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 1.4257805347442627, cross_entropy: 1.4257805347442627 +[2025-04-29 18:34:24,299][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 2.7185416221618652, cross_entropy: 2.7185416221618652 +[2025-04-29 18:34:27,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.1004128456115723, cross_entropy: 1.1004128456115723 +[2025-04-29 18:34:28,264][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 1.194429874420166, cross_entropy: 1.194429874420166 +[2025-04-29 18:34:30,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.7465426921844482, cross_entropy: 1.7465426921844482 +[2025-04-29 18:34:31,785][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 2.9041409492492676, cross_entropy: 2.9041409492492676 +[2025-04-29 18:34:34,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 3.332369327545166, cross_entropy: 3.332369327545166 +[2025-04-29 18:34:35,384][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 1.403533935546875, cross_entropy: 1.403533935546875 +[2025-04-29 18:34:38,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.342526912689209, cross_entropy: 3.342526912689209 +[2025-04-29 18:34:39,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.69119131565094, cross_entropy: 1.69119131565094 +[2025-04-29 18:34:42,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.4712340831756592, cross_entropy: 1.4712340831756592 +[2025-04-29 18:34:43,476][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.902885913848877, cross_entropy: 2.902885913848877 +[2025-04-29 18:34:46,436][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 1.8763728141784668, cross_entropy: 1.8763728141784668 +[2025-04-29 18:34:47,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.9509925842285156, cross_entropy: 1.9509925842285156 +[2025-04-29 18:34:50,808][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 1.6369949579238892, cross_entropy: 1.6369949579238892 +[2025-04-29 18:34:51,840][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.7663987874984741, cross_entropy: 1.7663987874984741 +[2025-04-29 18:34:55,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 1.3465969562530518, cross_entropy: 1.3465969562530518 +[2025-04-29 18:34:56,264][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.7296366691589355, cross_entropy: 1.7296366691589355 +[2025-04-29 18:34:59,240][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 1.6503918170928955, cross_entropy: 1.6503918170928955 +[2025-04-29 18:35:00,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.449681043624878, cross_entropy: 2.449681043624878 +[2025-04-29 18:35:02,238][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 0.9178275465965271, cross_entropy: 0.9178275465965271 +[2025-04-29 18:35:03,324][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 3.0137391090393066, cross_entropy: 3.0137391090393066 +[2025-04-29 18:35:06,108][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.782520294189453, cross_entropy: 2.782520294189453 +[2025-04-29 18:35:07,140][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.5382328033447266, cross_entropy: 1.5382328033447266 +[2025-04-29 18:35:10,320][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.2514090538024902, cross_entropy: 3.2514090538024902 +[2025-04-29 18:35:11,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 2.2065563201904297, cross_entropy: 2.2065563201904297 +[2025-04-29 18:35:13,945][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 1.3120605945587158, cross_entropy: 1.3120605945587158 +[2025-04-29 18:35:15,000][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 1.3694087266921997, cross_entropy: 1.3694087266921997 +[2025-04-29 18:35:17,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 1.3059966564178467, cross_entropy: 1.3059966564178467 +[2025-04-29 18:35:18,294][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.9224814176559448, cross_entropy: 1.9224814176559448 +[2025-04-29 18:35:21,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 1.8551959991455078, cross_entropy: 1.8551959991455078 +[2025-04-29 18:35:22,624][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.121209144592285, cross_entropy: 2.121209144592285 +[2025-04-29 18:35:25,445][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 2.7269153594970703, cross_entropy: 2.7269153594970703 +[2025-04-29 18:35:26,558][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 1.5692883729934692, cross_entropy: 1.5692883729934692 +[2025-04-29 18:35:29,607][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.774651050567627, cross_entropy: 2.774651050567627 +[2025-04-29 18:35:30,659][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 2.2659335136413574, cross_entropy: 2.2659335136413574 +[2025-04-29 18:35:33,396][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 2.373391628265381, cross_entropy: 2.373391628265381 +[2025-04-29 18:35:34,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 1.3554811477661133, cross_entropy: 1.3554811477661133 +[2025-04-29 18:35:36,977][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.3173422813415527, cross_entropy: 3.3173422813415527 +[2025-04-29 18:35:38,008][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 1.282015085220337, cross_entropy: 1.282015085220337 +[2025-04-29 18:35:41,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.1544816493988037, cross_entropy: 2.1544816493988037 +[2025-04-29 18:35:42,223][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 1.5566309690475464, cross_entropy: 1.5566309690475464 +[2025-04-29 18:35:44,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.542301058769226, cross_entropy: 1.542301058769226 +[2025-04-29 18:35:45,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.2919152975082397, cross_entropy: 1.2919152975082397 +[2025-04-29 18:35:47,985][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 3.1498522758483887, cross_entropy: 3.1498522758483887 +[2025-04-29 18:35:49,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 3.061758518218994, cross_entropy: 3.061758518218994 +[2025-04-29 18:35:51,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.473647952079773, cross_entropy: 1.473647952079773 +[2025-04-29 18:35:52,540][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 1.3070824146270752, cross_entropy: 1.3070824146270752 +[2025-04-29 18:35:55,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 3.2597694396972656, cross_entropy: 3.2597694396972656 +[2025-04-29 18:35:56,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 3.110168933868408, cross_entropy: 3.110168933868408 +[2025-04-29 18:35:59,140][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 1.624941110610962, cross_entropy: 1.624941110610962 +[2025-04-29 18:36:00,194][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.3124586343765259, cross_entropy: 1.3124586343765259 +[2025-04-29 18:36:02,608][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.4432088136672974, cross_entropy: 1.4432088136672974 +[2025-04-29 18:36:03,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 3.353252649307251, cross_entropy: 3.353252649307251 +[2025-04-29 18:36:06,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 1.8457386493682861, cross_entropy: 1.8457386493682861 +[2025-04-29 18:36:07,698][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.798837661743164, cross_entropy: 2.798837661743164 +[2025-04-29 18:36:10,349][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 0.8754383325576782, cross_entropy: 0.8754383325576782 +[2025-04-29 18:36:11,380][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.234673023223877, cross_entropy: 2.234673023223877 +[2025-04-29 18:36:13,640][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.024801731109619, cross_entropy: 3.024801731109619 +[2025-04-29 18:36:14,699][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 1.5860728025436401, cross_entropy: 1.5860728025436401 +[2025-04-29 18:36:17,156][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 2.9361941814422607, cross_entropy: 2.9361941814422607 +[2025-04-29 18:36:18,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.0682826042175293, cross_entropy: 2.0682826042175293 +[2025-04-29 18:36:21,230][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 1.1175618171691895, cross_entropy: 1.1175618171691895 +[2025-04-29 18:36:22,287][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.0925767421722412, cross_entropy: 1.0925767421722412 +[2025-04-29 18:36:25,737][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 1.4378811120986938, cross_entropy: 1.4378811120986938 +[2025-04-29 18:36:26,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.01585054397583, cross_entropy: 3.01585054397583 +[2025-04-29 18:36:30,765][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 1.4482324123382568, cross_entropy: 1.4482324123382568 +[2025-04-29 18:36:31,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 1.3157145977020264, cross_entropy: 1.3157145977020264 +[2025-04-29 18:36:34,420][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.2168447971343994, cross_entropy: 1.2168447971343994 +[2025-04-29 18:36:35,452][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 2.7075326442718506, cross_entropy: 2.7075326442718506 +[2025-04-29 18:36:39,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.9735773801803589, cross_entropy: 1.9735773801803589 +[2025-04-29 18:36:40,180][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.3641226291656494, cross_entropy: 1.3641226291656494 +[2025-04-29 18:36:42,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 2.1532411575317383, cross_entropy: 2.1532411575317383 +[2025-04-29 18:36:43,102][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.2926549911499023, cross_entropy: 2.2926549911499023 +[2025-04-29 18:36:45,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.407564163208008, cross_entropy: 2.407564163208008 +[2025-04-29 18:36:47,050][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 2.3590662479400635, cross_entropy: 2.3590662479400635 +[2025-04-29 18:36:49,780][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.103200912475586, cross_entropy: 3.103200912475586 +[2025-04-29 18:36:50,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 2.751321315765381, cross_entropy: 2.751321315765381 +[2025-04-29 18:36:52,979][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 1.131598949432373, cross_entropy: 1.131598949432373 +[2025-04-29 18:36:54,037][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 3.162722587585449, cross_entropy: 3.162722587585449 +[2025-04-29 18:36:57,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 1.3306896686553955, cross_entropy: 1.3306896686553955 +[2025-04-29 18:36:58,711][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.300276041030884, cross_entropy: 2.300276041030884 +[2025-04-29 18:37:01,292][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 2.3801119327545166, cross_entropy: 2.3801119327545166 +[2025-04-29 18:37:02,325][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.4240059852600098, cross_entropy: 1.4240059852600098 +[2025-04-29 18:37:05,611][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 2.563001871109009, cross_entropy: 2.563001871109009 +[2025-04-29 18:37:06,646][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.9144039154052734, cross_entropy: 1.9144039154052734 +[2025-04-29 18:37:09,442][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.9433817863464355, cross_entropy: 1.9433817863464355 +[2025-04-29 18:37:10,500][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 1.2136435508728027, cross_entropy: 1.2136435508728027 +[2025-04-29 18:37:13,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 1.298267126083374, cross_entropy: 1.298267126083374 +[2025-04-29 18:37:14,196][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 1.3262828588485718, cross_entropy: 1.3262828588485718 +[2025-04-29 18:37:16,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 1.6714129447937012, cross_entropy: 1.6714129447937012 +[2025-04-29 18:37:17,958][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 1.2925554513931274, cross_entropy: 1.2925554513931274 +[2025-04-29 18:37:20,843][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 3.0732741355895996, cross_entropy: 3.0732741355895996 +[2025-04-29 18:37:21,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 3.097029685974121, cross_entropy: 3.097029685974121 +[2025-04-29 18:37:24,452][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 2.095792293548584, cross_entropy: 2.095792293548584 +[2025-04-29 18:37:25,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.3727046251296997, cross_entropy: 1.3727046251296997 +[2025-04-29 18:37:28,731][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 1.2204629182815552, cross_entropy: 1.2204629182815552 +[2025-04-29 18:37:29,792][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 2.3861446380615234, cross_entropy: 2.3861446380615234 +[2025-04-29 18:37:32,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 1.4867689609527588, cross_entropy: 1.4867689609527588 +[2025-04-29 18:37:33,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 2.205827236175537, cross_entropy: 2.205827236175537 +[2025-04-29 18:37:35,458][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 3.2293994426727295, cross_entropy: 3.2293994426727295 +[2025-04-29 18:37:36,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 1.548683524131775, cross_entropy: 1.548683524131775 +[2025-04-29 18:37:38,961][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.5136194229125977, cross_entropy: 2.5136194229125977 +[2025-04-29 18:37:39,992][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 1.8578290939331055, cross_entropy: 1.8578290939331055 +[2025-04-29 18:37:42,615][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.7708771228790283, cross_entropy: 1.7708771228790283 +[2025-04-29 18:37:43,672][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.2356446981430054, cross_entropy: 1.2356446981430054 +[2025-04-29 18:37:46,729][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 2.487962007522583, cross_entropy: 2.487962007522583 +[2025-04-29 18:37:47,784][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 0.9499152302742004, cross_entropy: 0.9499152302742004 +[2025-04-29 18:37:51,006][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.5500340461730957, cross_entropy: 2.5500340461730957 +[2025-04-29 18:37:52,041][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 2.5748720169067383, cross_entropy: 2.5748720169067383 +[2025-04-29 18:37:54,788][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 2.421433448791504, cross_entropy: 2.421433448791504 +[2025-04-29 18:37:55,845][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 3.0979912281036377, cross_entropy: 3.0979912281036377 +[2025-04-29 18:37:59,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.2987234592437744, cross_entropy: 1.2987234592437744 +[2025-04-29 18:38:00,597][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.978829860687256, cross_entropy: 2.978829860687256 +[2025-04-29 18:38:03,580][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 2.329723834991455, cross_entropy: 2.329723834991455 +[2025-04-29 18:38:04,614][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.8646764755249023, cross_entropy: 2.8646764755249023 +[2025-04-29 18:38:08,107][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 3.061478614807129, cross_entropy: 3.061478614807129 +[2025-04-29 18:38:09,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 1.7401639223098755, cross_entropy: 1.7401639223098755 +[2025-04-29 18:38:11,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.4294748306274414, cross_entropy: 1.4294748306274414 +[2025-04-29 18:38:12,835][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 2.832127094268799, cross_entropy: 2.832127094268799 +[2025-04-29 18:38:15,187][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 1.162642478942871, cross_entropy: 1.162642478942871 +[2025-04-29 18:38:16,254][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 2.4773640632629395, cross_entropy: 2.4773640632629395 +[2025-04-29 18:38:19,025][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 1.3271429538726807, cross_entropy: 1.3271429538726807 +[2025-04-29 18:38:20,088][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.530843734741211, cross_entropy: 2.530843734741211 +[2025-04-29 18:38:22,305][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 1.7589927911758423, cross_entropy: 1.7589927911758423 +[2025-04-29 18:38:23,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 2.335696220397949, cross_entropy: 2.335696220397949 +[2025-04-29 18:38:25,362][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 1.6739155054092407, cross_entropy: 1.6739155054092407 +[2025-04-29 18:38:26,428][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 2.1840176582336426, cross_entropy: 2.1840176582336426 +[2025-04-29 18:38:28,973][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.091118335723877, cross_entropy: 1.091118335723877 +[2025-04-29 18:38:30,006][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 1.1380181312561035, cross_entropy: 1.1380181312561035 +[2025-04-29 18:38:32,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 3.166219472885132, cross_entropy: 3.166219472885132 +[2025-04-29 18:38:33,596][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 3.242288112640381, cross_entropy: 3.242288112640381 +[2025-04-29 18:38:36,102][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 3.014237880706787, cross_entropy: 3.014237880706787 +[2025-04-29 18:38:37,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 1.3636828660964966, cross_entropy: 1.3636828660964966 +[2025-04-29 18:38:39,589][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 1.9791035652160645, cross_entropy: 1.9791035652160645 +[2025-04-29 18:38:40,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.5034077167510986, cross_entropy: 2.5034077167510986 +[2025-04-29 18:38:43,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 2.125828266143799, cross_entropy: 2.125828266143799 +[2025-04-29 18:38:44,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.9502573013305664, cross_entropy: 2.9502573013305664 +[2025-04-29 18:38:47,114][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 1.2707680463790894, cross_entropy: 1.2707680463790894 +[2025-04-29 18:38:48,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.5915865898132324, cross_entropy: 2.5915865898132324 +[2025-04-29 18:38:50,892][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 1.3780043125152588, cross_entropy: 1.3780043125152588 +[2025-04-29 18:38:51,954][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 1.3414099216461182, cross_entropy: 1.3414099216461182 +[2025-04-29 18:38:53,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 1.1762902736663818, cross_entropy: 1.1762902736663818 +[2025-04-29 18:38:54,932][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.2931952476501465, cross_entropy: 3.2931952476501465 +[2025-04-29 18:38:57,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 1.2744801044464111, cross_entropy: 1.2744801044464111 +[2025-04-29 18:38:58,507][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 1.8080451488494873, cross_entropy: 1.8080451488494873 +[2025-04-29 18:39:01,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 1.4033007621765137, cross_entropy: 1.4033007621765137 +[2025-04-29 18:39:02,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 2.726165771484375, cross_entropy: 2.726165771484375 +[2025-04-29 18:39:04,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.684457778930664, cross_entropy: 2.684457778930664 +[2025-04-29 18:39:06,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 1.3867201805114746, cross_entropy: 1.3867201805114746 +[2025-04-29 18:39:08,979][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.16605281829834, cross_entropy: 2.16605281829834 +[2025-04-29 18:39:10,335][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 3.077885389328003, cross_entropy: 3.077885389328003 +[2025-04-29 18:39:13,057][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.2122896909713745, cross_entropy: 1.2122896909713745 +[2025-04-29 18:39:14,150][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.7646031379699707, cross_entropy: 2.7646031379699707 +[2025-04-29 18:39:16,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 1.9353537559509277, cross_entropy: 1.9353537559509277 +[2025-04-29 18:39:17,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 1.8771051168441772, cross_entropy: 1.8771051168441772 +[2025-04-29 18:39:20,580][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 1.6749560832977295, cross_entropy: 1.6749560832977295 +[2025-04-29 18:39:21,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.2405099868774414, cross_entropy: 1.2405099868774414 +[2025-04-29 18:39:24,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 3.093679428100586, cross_entropy: 3.093679428100586 +[2025-04-29 18:39:25,737][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.8116378784179688, cross_entropy: 2.8116378784179688 +[2025-04-29 18:39:28,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 0.9085221886634827, cross_entropy: 0.9085221886634827 +[2025-04-29 18:39:30,004][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 3.1565139293670654, cross_entropy: 3.1565139293670654 +[2025-04-29 18:39:33,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.7969419956207275, cross_entropy: 1.7969419956207275 +[2025-04-29 18:39:34,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 1.4962632656097412, cross_entropy: 1.4962632656097412 +[2025-04-29 18:39:37,268][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 3.080972671508789, cross_entropy: 3.080972671508789 +[2025-04-29 18:39:38,300][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 1.9469234943389893, cross_entropy: 1.9469234943389893 +[2025-04-29 18:39:40,908][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.08565092086792, cross_entropy: 2.08565092086792 +[2025-04-29 18:39:41,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 0.9038849472999573, cross_entropy: 0.9038849472999573 +[2025-04-29 18:39:44,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.9629428386688232, cross_entropy: 2.9629428386688232 +[2025-04-29 18:39:45,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 2.061652421951294, cross_entropy: 2.061652421951294 +[2025-04-29 18:39:48,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 1.2005386352539062, cross_entropy: 1.2005386352539062 +[2025-04-29 18:39:49,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 2.900829792022705, cross_entropy: 2.900829792022705 +[2025-04-29 18:39:52,562][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.6259818077087402, cross_entropy: 2.6259818077087402 +[2025-04-29 18:39:53,651][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 1.2929010391235352, cross_entropy: 1.2929010391235352 +[2025-04-29 18:39:55,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 3.1917386054992676, cross_entropy: 3.1917386054992676 +[2025-04-29 18:39:57,010][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.7591439485549927, cross_entropy: 1.7591439485549927 +[2025-04-29 18:40:00,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.1486862897872925, cross_entropy: 1.1486862897872925 +[2025-04-29 18:40:02,112][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.8712806701660156, cross_entropy: 1.8712806701660156 +[2025-04-29 18:40:04,052][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 1.313306450843811, cross_entropy: 1.313306450843811 +[2025-04-29 18:40:05,822][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 2.521252393722534, cross_entropy: 2.521252393722534 +[2025-04-29 18:40:07,642][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 1.5149734020233154, cross_entropy: 1.5149734020233154 +[2025-04-29 18:40:09,705][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 2.9705233573913574, cross_entropy: 2.9705233573913574 +[2025-04-29 18:40:11,860][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 2.6274495124816895, cross_entropy: 2.6274495124816895 +[2025-04-29 18:40:13,392][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.7242612838745117, cross_entropy: 2.7242612838745117 +[2025-04-29 18:40:15,193][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.4082820415496826, cross_entropy: 2.4082820415496826 +[2025-04-29 18:40:17,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.8023324012756348, cross_entropy: 2.8023324012756348 +[2025-04-29 18:40:19,414][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 2.972306251525879, cross_entropy: 2.972306251525879 +[2025-04-29 18:40:20,939][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 3.0124900341033936, cross_entropy: 3.0124900341033936 +[2025-04-29 18:40:22,441][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.7223587036132812, cross_entropy: 2.7223587036132812 +[2025-04-29 18:40:24,478][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.3630081415176392, cross_entropy: 1.3630081415176392 +[2025-04-29 18:40:26,184][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 3.4547171592712402, cross_entropy: 3.4547171592712402 +[2025-04-29 18:40:28,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 1.740006446838379, cross_entropy: 1.740006446838379 +[2025-04-29 18:40:29,986][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 3.0134010314941406, cross_entropy: 3.0134010314941406 +[2025-04-29 18:40:33,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 3.051438570022583, cross_entropy: 3.051438570022583 +[2025-04-29 18:40:34,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 1.7116806507110596, cross_entropy: 1.7116806507110596 +[2025-04-29 18:40:36,398][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 2.6776247024536133, cross_entropy: 2.6776247024536133 +[2025-04-29 18:40:38,085][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 1.944104790687561, cross_entropy: 1.944104790687561 +[2025-04-29 18:40:40,379][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 2.695431709289551, cross_entropy: 2.695431709289551 +[2025-04-29 18:40:41,728][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 1.612710952758789, cross_entropy: 1.612710952758789 +[2025-04-29 18:40:44,779][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 2.5601284503936768, cross_entropy: 2.5601284503936768 +[2025-04-29 18:40:45,832][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 1.6058087348937988, cross_entropy: 1.6058087348937988 +[2025-04-29 18:40:48,798][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.945338249206543, cross_entropy: 2.945338249206543 +[2025-04-29 18:40:49,854][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 2.648766040802002, cross_entropy: 2.648766040802002 +[2025-04-29 18:40:52,515][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.025391101837158, cross_entropy: 2.025391101837158 +[2025-04-29 18:40:53,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.241924285888672, cross_entropy: 3.241924285888672 +[2025-04-29 18:40:55,989][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 1.5622624158859253, cross_entropy: 1.5622624158859253 +[2025-04-29 18:40:57,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4202989339828491, cross_entropy: 1.4202989339828491 +[2025-04-29 18:40:59,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 1.2304823398590088, cross_entropy: 1.2304823398590088 +[2025-04-29 18:41:02,174][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 1.5499216318130493, cross_entropy: 1.5499216318130493 +[2025-04-29 18:41:03,221][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 1.6173843145370483, cross_entropy: 1.6173843145370483 +[2025-04-29 18:41:06,038][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 2.417422294616699, cross_entropy: 2.417422294616699 +[2025-04-29 18:41:07,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 2.9387142658233643, cross_entropy: 2.9387142658233643 +[2025-04-29 18:41:10,004][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 3.189473867416382, cross_entropy: 3.189473867416382 +[2025-04-29 18:41:11,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 2.2206780910491943, cross_entropy: 2.2206780910491943 +[2025-04-29 18:41:14,293][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 1.9700043201446533, cross_entropy: 1.9700043201446533 +[2025-04-29 18:41:15,407][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.6747571229934692, cross_entropy: 1.6747571229934692 +[2025-04-29 18:41:18,132][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 1.126630425453186, cross_entropy: 1.126630425453186 +[2025-04-29 18:41:19,195][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 2.3026108741760254, cross_entropy: 2.3026108741760254 +[2025-04-29 18:41:22,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.3394027948379517, cross_entropy: 1.3394027948379517 +[2025-04-29 18:41:23,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.7640833854675293, cross_entropy: 2.7640833854675293 +[2025-04-29 18:41:26,155][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.2756510972976685, cross_entropy: 1.2756510972976685 +[2025-04-29 18:41:27,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 2.8919875621795654, cross_entropy: 2.8919875621795654 +[2025-04-29 18:41:30,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 1.045069694519043, cross_entropy: 1.045069694519043 +[2025-04-29 18:41:31,432][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.7367703914642334, cross_entropy: 2.7367703914642334 +[2025-04-29 18:41:33,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 3.10831880569458, cross_entropy: 3.10831880569458 +[2025-04-29 18:41:34,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 1.392789602279663, cross_entropy: 1.392789602279663 +[2025-04-29 18:41:37,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.708258628845215, cross_entropy: 2.708258628845215 +[2025-04-29 18:41:38,843][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.2327375411987305, cross_entropy: 2.2327375411987305 +[2025-04-29 18:41:41,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.950939655303955, cross_entropy: 2.950939655303955 +[2025-04-29 18:41:42,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.1207693815231323, cross_entropy: 1.1207693815231323 +[2025-04-29 18:41:45,056][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.4079012870788574, cross_entropy: 1.4079012870788574 +[2025-04-29 18:41:46,179][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 1.6350667476654053, cross_entropy: 1.6350667476654053 +[2025-04-29 18:41:49,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 1.3492342233657837, cross_entropy: 1.3492342233657837 +[2025-04-29 18:41:50,489][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.5695277452468872, cross_entropy: 1.5695277452468872 +[2025-04-29 18:41:52,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 2.096497058868408, cross_entropy: 2.096497058868408 +[2025-04-29 18:41:53,790][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 2.552199363708496, cross_entropy: 2.552199363708496 +[2025-04-29 18:41:56,401][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.4646620750427246, cross_entropy: 2.4646620750427246 +[2025-04-29 18:41:57,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 1.6748301982879639, cross_entropy: 1.6748301982879639 +[2025-04-29 18:41:59,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 2.0769805908203125, cross_entropy: 2.0769805908203125 +[2025-04-29 18:42:01,300][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.9363725185394287, cross_entropy: 1.9363725185394287 +[2025-04-29 18:42:03,441][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.1225385665893555, cross_entropy: 2.1225385665893555 +[2025-04-29 18:42:04,735][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 2.3304190635681152, cross_entropy: 2.3304190635681152 +[2025-04-29 18:42:07,524][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 3.004815101623535, cross_entropy: 3.004815101623535 +[2025-04-29 18:42:08,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 1.8319852352142334, cross_entropy: 1.8319852352142334 +[2025-04-29 18:42:11,205][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 2.7289531230926514, cross_entropy: 2.7289531230926514 +[2025-04-29 18:42:12,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 2.545476198196411, cross_entropy: 2.545476198196411 +[2025-04-29 18:42:14,791][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 2.4791877269744873, cross_entropy: 2.4791877269744873 +[2025-04-29 18:42:15,868][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.094292163848877, cross_entropy: 1.094292163848877 +[2025-04-29 18:42:18,124][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.8540668487548828, cross_entropy: 1.8540668487548828 +[2025-04-29 18:42:19,845][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 3.1916799545288086, cross_entropy: 3.1916799545288086 +[2025-04-29 18:42:22,892][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 1.2614883184432983, cross_entropy: 1.2614883184432983 +[2025-04-29 18:42:23,972][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 1.2349138259887695, cross_entropy: 1.2349138259887695 +[2025-04-29 18:42:26,601][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 2.7098963260650635, cross_entropy: 2.7098963260650635 +[2025-04-29 18:42:27,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.661318302154541, cross_entropy: 2.661318302154541 +[2025-04-29 18:42:30,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.7102656364440918, cross_entropy: 1.7102656364440918 +[2025-04-29 18:42:32,029][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 1.2125897407531738, cross_entropy: 1.2125897407531738 +[2025-04-29 18:42:34,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 3.022327184677124, cross_entropy: 3.022327184677124 +[2025-04-29 18:42:35,419][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 2.874891519546509, cross_entropy: 2.874891519546509 +[2025-04-29 18:42:38,447][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 1.2526028156280518, cross_entropy: 1.2526028156280518 +[2025-04-29 18:42:39,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 1.112213373184204, cross_entropy: 1.112213373184204 +[2025-04-29 18:42:42,138][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 2.818490982055664, cross_entropy: 2.818490982055664 +[2025-04-29 18:42:43,273][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.2248082160949707, cross_entropy: 1.2248082160949707 +[2025-04-29 18:42:45,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 1.5565365552902222, cross_entropy: 1.5565365552902222 +[2025-04-29 18:42:46,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 0.9631458520889282, cross_entropy: 0.9631458520889282 +[2025-04-29 18:42:48,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.5079811811447144, cross_entropy: 1.5079811811447144 +[2025-04-29 18:42:50,824][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 1.9454703330993652, cross_entropy: 1.9454703330993652 +[2025-04-29 18:42:52,948][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.4311699867248535, cross_entropy: 1.4311699867248535 +[2025-04-29 18:42:54,973][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 2.618401527404785, cross_entropy: 2.618401527404785 +[2025-04-29 18:42:56,866][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 2.707219123840332, cross_entropy: 2.707219123840332 +[2025-04-29 18:42:58,551][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 1.6903724670410156, cross_entropy: 1.6903724670410156 +[2025-04-29 18:43:00,759][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 1.380389928817749, cross_entropy: 1.380389928817749 +[2025-04-29 18:43:02,474][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 3.435776472091675, cross_entropy: 3.435776472091675 +[2025-04-29 18:43:04,854][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 2.6682887077331543, cross_entropy: 2.6682887077331543 +[2025-04-29 18:43:05,794][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 1.5492420196533203, cross_entropy: 1.5492420196533203 +[2025-04-29 18:45:49,381][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.1102707386016846, cross_entropy: 2.1102707386016846 +[2025-04-29 18:45:49,382][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.2672134637832642, cross_entropy: 1.2672134637832642 +[2025-04-29 18:45:50,230][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 18:45:50,739][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch4.pth. +[2025-04-29 18:45:51,533][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 18:45:56,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 0.860637903213501, cross_entropy: 0.860637903213501 +[2025-04-29 18:45:57,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.1223493814468384, cross_entropy: 1.1223493814468384 +[2025-04-29 18:46:00,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.957190752029419, cross_entropy: 1.957190752029419 +[2025-04-29 18:46:01,517][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 2.9557652473449707, cross_entropy: 2.9557652473449707 +[2025-04-29 18:46:04,741][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 2.4466192722320557, cross_entropy: 2.4466192722320557 +[2025-04-29 18:46:05,799][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 0.966865062713623, cross_entropy: 0.966865062713623 +[2025-04-29 18:46:08,596][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.936554193496704, cross_entropy: 2.936554193496704 +[2025-04-29 18:46:09,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 1.6761583089828491, cross_entropy: 1.6761583089828491 +[2025-04-29 18:46:13,008][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 1.4198439121246338, cross_entropy: 1.4198439121246338 +[2025-04-29 18:46:14,069][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 2.844388484954834, cross_entropy: 2.844388484954834 +[2025-04-29 18:46:16,589][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 1.147963523864746, cross_entropy: 1.147963523864746 +[2025-04-29 18:46:17,622][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 2.9881138801574707, cross_entropy: 2.9881138801574707 +[2025-04-29 18:46:20,551][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.514026403427124, cross_entropy: 2.514026403427124 +[2025-04-29 18:46:21,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 1.2512041330337524, cross_entropy: 1.2512041330337524 +[2025-04-29 18:46:24,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 1.6784217357635498, cross_entropy: 1.6784217357635498 +[2025-04-29 18:46:25,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 1.697371006011963, cross_entropy: 1.697371006011963 +[2025-04-29 18:46:28,326][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 1.6264524459838867, cross_entropy: 1.6264524459838867 +[2025-04-29 18:46:29,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 2.9824399948120117, cross_entropy: 2.9824399948120117 +[2025-04-29 18:46:32,106][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 1.7649387121200562, cross_entropy: 1.7649387121200562 +[2025-04-29 18:46:33,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.567995309829712, cross_entropy: 1.567995309829712 +[2025-04-29 18:46:36,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.9138933420181274, cross_entropy: 1.9138933420181274 +[2025-04-29 18:46:38,163][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 3.0704071521759033, cross_entropy: 3.0704071521759033 +[2025-04-29 18:46:40,469][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 2.9363796710968018, cross_entropy: 2.9363796710968018 +[2025-04-29 18:46:41,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.1161866188049316, cross_entropy: 1.1161866188049316 +[2025-04-29 18:46:43,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 3.3266429901123047, cross_entropy: 3.3266429901123047 +[2025-04-29 18:46:46,326][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.1636697053909302, cross_entropy: 1.1636697053909302 +[2025-04-29 18:46:47,416][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 1.0524314641952515, cross_entropy: 1.0524314641952515 +[2025-04-29 18:46:50,370][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.5017274618148804, cross_entropy: 1.5017274618148804 +[2025-04-29 18:46:51,401][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.6507625579833984, cross_entropy: 2.6507625579833984 +[2025-04-29 18:46:54,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 0.9736099243164062, cross_entropy: 0.9736099243164062 +[2025-04-29 18:46:55,507][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.2912304401397705, cross_entropy: 1.2912304401397705 +[2025-04-29 18:46:58,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 0.9199701547622681, cross_entropy: 0.9199701547622681 +[2025-04-29 18:46:59,302][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.478715181350708, cross_entropy: 1.478715181350708 +[2025-04-29 18:47:01,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 1.8234485387802124, cross_entropy: 1.8234485387802124 +[2025-04-29 18:47:02,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 2.4073405265808105, cross_entropy: 2.4073405265808105 +[2025-04-29 18:47:05,793][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.6086379289627075, cross_entropy: 1.6086379289627075 +[2025-04-29 18:47:06,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.0269079208374023, cross_entropy: 3.0269079208374023 +[2025-04-29 18:47:09,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 2.698660135269165, cross_entropy: 2.698660135269165 +[2025-04-29 18:47:10,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 2.4856748580932617, cross_entropy: 2.4856748580932617 +[2025-04-29 18:47:14,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.1603487730026245, cross_entropy: 1.1603487730026245 +[2025-04-29 18:47:15,440][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 1.6416552066802979, cross_entropy: 1.6416552066802979 +[2025-04-29 18:47:18,098][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.1737043857574463, cross_entropy: 1.1737043857574463 +[2025-04-29 18:47:19,160][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.33774733543396, cross_entropy: 1.33774733543396 +[2025-04-29 18:47:21,881][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 2.8878064155578613, cross_entropy: 2.8878064155578613 +[2025-04-29 18:47:22,941][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 2.767332077026367, cross_entropy: 2.767332077026367 +[2025-04-29 18:47:25,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.0398030281066895, cross_entropy: 1.0398030281066895 +[2025-04-29 18:47:26,941][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.283940315246582, cross_entropy: 1.283940315246582 +[2025-04-29 18:47:29,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.377191424369812, cross_entropy: 1.377191424369812 +[2025-04-29 18:47:30,336][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.1762285232543945, cross_entropy: 2.1762285232543945 +[2025-04-29 18:47:32,411][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.0797849893569946, cross_entropy: 1.0797849893569946 +[2025-04-29 18:47:33,546][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 1.323077917098999, cross_entropy: 1.323077917098999 +[2025-04-29 18:47:35,764][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 3.2498879432678223, cross_entropy: 3.2498879432678223 +[2025-04-29 18:47:36,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 2.9840211868286133, cross_entropy: 2.9840211868286133 +[2025-04-29 18:47:39,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.964066982269287, cross_entropy: 2.964066982269287 +[2025-04-29 18:47:40,671][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.7423603534698486, cross_entropy: 2.7423603534698486 +[2025-04-29 18:47:43,144][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.6518890857696533, cross_entropy: 2.6518890857696533 +[2025-04-29 18:47:44,317][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 1.9816699028015137, cross_entropy: 1.9816699028015137 +[2025-04-29 18:47:46,912][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.1116116046905518, cross_entropy: 2.1116116046905518 +[2025-04-29 18:47:47,964][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 3.0019402503967285, cross_entropy: 3.0019402503967285 +[2025-04-29 18:47:50,190][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 2.9705395698547363, cross_entropy: 2.9705395698547363 +[2025-04-29 18:47:51,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 2.7281408309936523, cross_entropy: 2.7281408309936523 +[2025-04-29 18:47:54,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 1.1206998825073242, cross_entropy: 1.1206998825073242 +[2025-04-29 18:47:55,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 3.046910285949707, cross_entropy: 3.046910285949707 +[2025-04-29 18:47:58,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.5264898538589478, cross_entropy: 1.5264898538589478 +[2025-04-29 18:47:59,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 3.042426586151123, cross_entropy: 3.042426586151123 +[2025-04-29 18:48:01,575][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 1.1160869598388672, cross_entropy: 1.1160869598388672 +[2025-04-29 18:48:02,743][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 2.6453442573547363, cross_entropy: 2.6453442573547363 +[2025-04-29 18:48:05,657][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 1.1513843536376953, cross_entropy: 1.1513843536376953 +[2025-04-29 18:48:06,748][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 3.0976884365081787, cross_entropy: 3.0976884365081787 +[2025-04-29 18:48:09,690][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 1.0073333978652954, cross_entropy: 1.0073333978652954 +[2025-04-29 18:48:10,830][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 1.6076316833496094, cross_entropy: 1.6076316833496094 +[2025-04-29 18:48:14,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 1.7298169136047363, cross_entropy: 1.7298169136047363 +[2025-04-29 18:48:15,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.35660982131958, cross_entropy: 1.35660982131958 +[2025-04-29 18:48:18,690][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 1.770877480506897, cross_entropy: 1.770877480506897 +[2025-04-29 18:48:19,723][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.54702091217041, cross_entropy: 2.54702091217041 +[2025-04-29 18:48:22,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 1.3594721555709839, cross_entropy: 1.3594721555709839 +[2025-04-29 18:48:23,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.2458796501159668, cross_entropy: 1.2458796501159668 +[2025-04-29 18:48:26,161][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 2.3642215728759766, cross_entropy: 2.3642215728759766 +[2025-04-29 18:48:27,220][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.4762566089630127, cross_entropy: 1.4762566089630127 +[2025-04-29 18:48:30,412][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.3277819156646729, cross_entropy: 1.3277819156646729 +[2025-04-29 18:48:31,473][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 1.4448955059051514, cross_entropy: 1.4448955059051514 +[2025-04-29 18:48:34,779][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.930450439453125, cross_entropy: 2.930450439453125 +[2025-04-29 18:48:35,839][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 3.0651018619537354, cross_entropy: 3.0651018619537354 +[2025-04-29 18:48:38,345][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 1.2179783582687378, cross_entropy: 1.2179783582687378 +[2025-04-29 18:48:39,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 3.1582870483398438, cross_entropy: 3.1582870483398438 +[2025-04-29 18:48:41,952][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.1441569328308105, cross_entropy: 1.1441569328308105 +[2025-04-29 18:48:43,025][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 3.0032598972320557, cross_entropy: 3.0032598972320557 +[2025-04-29 18:48:46,502][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.3620799779891968, cross_entropy: 1.3620799779891968 +[2025-04-29 18:48:47,571][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.651942491531372, cross_entropy: 1.651942491531372 +[2025-04-29 18:48:49,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.6654999256134033, cross_entropy: 1.6654999256134033 +[2025-04-29 18:48:50,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.074603796005249, cross_entropy: 2.074603796005249 +[2025-04-29 18:48:53,045][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.1421399116516113, cross_entropy: 3.1421399116516113 +[2025-04-29 18:48:54,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.8901829719543457, cross_entropy: 2.8901829719543457 +[2025-04-29 18:48:56,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 1.40043306350708, cross_entropy: 1.40043306350708 +[2025-04-29 18:48:57,516][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 2.9560227394104004, cross_entropy: 2.9560227394104004 +[2025-04-29 18:48:59,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.1281657218933105, cross_entropy: 1.1281657218933105 +[2025-04-29 18:49:00,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.5476317405700684, cross_entropy: 2.5476317405700684 +[2025-04-29 18:49:03,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 1.8235490322113037, cross_entropy: 1.8235490322113037 +[2025-04-29 18:49:04,228][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 1.1500993967056274, cross_entropy: 1.1500993967056274 +[2025-04-29 18:49:07,050][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3467406034469604, cross_entropy: 1.3467406034469604 +[2025-04-29 18:49:08,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 3.095125198364258, cross_entropy: 3.095125198364258 +[2025-04-29 18:49:10,759][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.8412084579467773, cross_entropy: 2.8412084579467773 +[2025-04-29 18:49:11,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.4450808763504028, cross_entropy: 1.4450808763504028 +[2025-04-29 18:49:15,209][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.400672435760498, cross_entropy: 2.400672435760498 +[2025-04-29 18:49:16,269][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 1.9004467725753784, cross_entropy: 1.9004467725753784 +[2025-04-29 18:49:19,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 2.5750656127929688, cross_entropy: 2.5750656127929688 +[2025-04-29 18:49:20,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 1.7067703008651733, cross_entropy: 1.7067703008651733 +[2025-04-29 18:49:23,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.0555001497268677, cross_entropy: 1.0555001497268677 +[2025-04-29 18:49:24,625][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.258786678314209, cross_entropy: 1.258786678314209 +[2025-04-29 18:49:27,116][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.7623310089111328, cross_entropy: 1.7623310089111328 +[2025-04-29 18:49:28,150][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 2.4972903728485107, cross_entropy: 2.4972903728485107 +[2025-04-29 18:49:31,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 0.9416518807411194, cross_entropy: 0.9416518807411194 +[2025-04-29 18:49:32,612][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.1344454288482666, cross_entropy: 1.1344454288482666 +[2025-04-29 18:49:35,860][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 2.7245986461639404, cross_entropy: 2.7245986461639404 +[2025-04-29 18:49:36,924][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.2173845767974854, cross_entropy: 1.2173845767974854 +[2025-04-29 18:49:39,679][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 0.8114250898361206, cross_entropy: 0.8114250898361206 +[2025-04-29 18:49:40,709][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 2.450970411300659, cross_entropy: 2.450970411300659 +[2025-04-29 18:49:43,976][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.8651981353759766, cross_entropy: 1.8651981353759766 +[2025-04-29 18:49:45,009][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 0.9872187376022339, cross_entropy: 0.9872187376022339 +[2025-04-29 18:49:49,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.1149024963378906, cross_entropy: 2.1149024963378906 +[2025-04-29 18:49:50,148][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 0.9894636869430542, cross_entropy: 0.9894636869430542 +[2025-04-29 18:49:52,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 2.1215643882751465, cross_entropy: 2.1215643882751465 +[2025-04-29 18:49:53,263][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 1.4644792079925537, cross_entropy: 1.4644792079925537 +[2025-04-29 18:49:56,109][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.6512255668640137, cross_entropy: 2.6512255668640137 +[2025-04-29 18:49:57,168][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 1.5505865812301636, cross_entropy: 1.5505865812301636 +[2025-04-29 18:49:59,825][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 1.384413480758667, cross_entropy: 1.384413480758667 +[2025-04-29 18:50:00,880][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.311755657196045, cross_entropy: 1.311755657196045 +[2025-04-29 18:50:03,892][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 2.9870283603668213, cross_entropy: 2.9870283603668213 +[2025-04-29 18:50:04,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.5264651775360107, cross_entropy: 1.5264651775360107 +[2025-04-29 18:50:07,748][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 1.6169164180755615, cross_entropy: 1.6169164180755615 +[2025-04-29 18:50:08,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.868299961090088, cross_entropy: 1.868299961090088 +[2025-04-29 18:50:11,277][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 2.3540830612182617, cross_entropy: 2.3540830612182617 +[2025-04-29 18:50:12,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 1.364664912223816, cross_entropy: 1.364664912223816 +[2025-04-29 18:50:14,766][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.601177215576172, cross_entropy: 2.601177215576172 +[2025-04-29 18:50:15,822][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 2.8372228145599365, cross_entropy: 2.8372228145599365 +[2025-04-29 18:50:18,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 3.263702392578125, cross_entropy: 3.263702392578125 +[2025-04-29 18:50:19,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 1.8806167840957642, cross_entropy: 1.8806167840957642 +[2025-04-29 18:50:23,064][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 2.9158294200897217, cross_entropy: 2.9158294200897217 +[2025-04-29 18:50:24,122][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 2.142434597015381, cross_entropy: 2.142434597015381 +[2025-04-29 18:50:26,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 1.949141025543213, cross_entropy: 1.949141025543213 +[2025-04-29 18:50:27,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.7355635166168213, cross_entropy: 1.7355635166168213 +[2025-04-29 18:50:30,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 1.8116559982299805, cross_entropy: 1.8116559982299805 +[2025-04-29 18:50:31,464][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 2.5909740924835205, cross_entropy: 2.5909740924835205 +[2025-04-29 18:50:33,965][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.595412015914917, cross_entropy: 1.595412015914917 +[2025-04-29 18:50:35,024][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.4068968296051025, cross_entropy: 1.4068968296051025 +[2025-04-29 18:50:37,803][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 1.201744794845581, cross_entropy: 1.201744794845581 +[2025-04-29 18:50:38,864][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 1.639378309249878, cross_entropy: 1.639378309249878 +[2025-04-29 18:50:41,927][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.8772664070129395, cross_entropy: 2.8772664070129395 +[2025-04-29 18:50:42,959][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.2631571292877197, cross_entropy: 1.2631571292877197 +[2025-04-29 18:50:45,878][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.0525519847869873, cross_entropy: 1.0525519847869873 +[2025-04-29 18:50:46,908][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 1.2484530210494995, cross_entropy: 1.2484530210494995 +[2025-04-29 18:50:49,386][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 2.9400711059570312, cross_entropy: 2.9400711059570312 +[2025-04-29 18:50:50,419][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.27667236328125, cross_entropy: 1.27667236328125 +[2025-04-29 18:50:52,924][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 3.1666486263275146, cross_entropy: 3.1666486263275146 +[2025-04-29 18:50:53,957][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 1.8838547468185425, cross_entropy: 1.8838547468185425 +[2025-04-29 18:50:56,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 3.282987594604492, cross_entropy: 3.282987594604492 +[2025-04-29 18:50:57,594][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 0.7555426359176636, cross_entropy: 0.7555426359176636 +[2025-04-29 18:51:00,409][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 2.231492280960083, cross_entropy: 2.231492280960083 +[2025-04-29 18:51:01,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.1456341743469238, cross_entropy: 1.1456341743469238 +[2025-04-29 18:51:03,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 1.478039026260376, cross_entropy: 1.478039026260376 +[2025-04-29 18:51:05,026][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 1.8221479654312134, cross_entropy: 1.8221479654312134 +[2025-04-29 18:51:07,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.3893399238586426, cross_entropy: 1.3893399238586426 +[2025-04-29 18:51:08,920][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 2.098614454269409, cross_entropy: 2.098614454269409 +[2025-04-29 18:51:11,743][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 2.9014291763305664, cross_entropy: 2.9014291763305664 +[2025-04-29 18:51:12,797][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 2.5746970176696777, cross_entropy: 2.5746970176696777 +[2025-04-29 18:51:15,275][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 1.2446098327636719, cross_entropy: 1.2446098327636719 +[2025-04-29 18:51:16,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 1.051112174987793, cross_entropy: 1.051112174987793 +[2025-04-29 18:51:19,064][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 2.488429546356201, cross_entropy: 2.488429546356201 +[2025-04-29 18:51:20,131][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.3166587352752686, cross_entropy: 1.3166587352752686 +[2025-04-29 18:51:22,974][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 1.4686431884765625, cross_entropy: 1.4686431884765625 +[2025-04-29 18:51:24,037][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.5360634326934814, cross_entropy: 1.5360634326934814 +[2025-04-29 18:51:26,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 2.936471462249756, cross_entropy: 2.936471462249756 +[2025-04-29 18:51:27,794][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 1.4741706848144531, cross_entropy: 1.4741706848144531 +[2025-04-29 18:51:29,648][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 1.8377726078033447, cross_entropy: 1.8377726078033447 +[2025-04-29 18:51:30,680][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 3.029668092727661, cross_entropy: 3.029668092727661 +[2025-04-29 18:51:33,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.5302956104278564, cross_entropy: 1.5302956104278564 +[2025-04-29 18:51:34,632][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.3472044467926025, cross_entropy: 2.3472044467926025 +[2025-04-29 18:51:37,498][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 2.675858497619629, cross_entropy: 2.675858497619629 +[2025-04-29 18:51:38,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.1775389909744263, cross_entropy: 1.1775389909744263 +[2025-04-29 18:51:41,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 2.2300286293029785, cross_entropy: 2.2300286293029785 +[2025-04-29 18:51:42,277][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 1.1186203956604004, cross_entropy: 1.1186203956604004 +[2025-04-29 18:51:44,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 1.5000882148742676, cross_entropy: 1.5000882148742676 +[2025-04-29 18:51:45,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 1.529369592666626, cross_entropy: 1.529369592666626 +[2025-04-29 18:51:49,438][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.3431973457336426, cross_entropy: 2.3431973457336426 +[2025-04-29 18:51:50,470][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.288508892059326, cross_entropy: 2.288508892059326 +[2025-04-29 18:51:53,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 1.1522899866104126, cross_entropy: 1.1522899866104126 +[2025-04-29 18:51:54,914][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.579441547393799, cross_entropy: 2.579441547393799 +[2025-04-29 18:51:58,516][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.61543345451355, cross_entropy: 2.61543345451355 +[2025-04-29 18:51:59,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.5776424407958984, cross_entropy: 2.5776424407958984 +[2025-04-29 18:52:02,510][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 3.1015779972076416, cross_entropy: 3.1015779972076416 +[2025-04-29 18:52:03,581][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.3904515504837036, cross_entropy: 1.3904515504837036 +[2025-04-29 18:52:06,021][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 1.987673044204712, cross_entropy: 1.987673044204712 +[2025-04-29 18:52:07,084][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.4617092609405518, cross_entropy: 1.4617092609405518 +[2025-04-29 18:52:09,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.712347984313965, cross_entropy: 2.712347984313965 +[2025-04-29 18:52:10,843][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.3029651641845703, cross_entropy: 2.3029651641845703 +[2025-04-29 18:52:14,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 1.4154317378997803, cross_entropy: 1.4154317378997803 +[2025-04-29 18:52:15,176][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.1774613857269287, cross_entropy: 1.1774613857269287 +[2025-04-29 18:52:18,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.4493046998977661, cross_entropy: 1.4493046998977661 +[2025-04-29 18:52:19,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 1.0290415287017822, cross_entropy: 1.0290415287017822 +[2025-04-29 18:52:21,271][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.5283164978027344, cross_entropy: 2.5283164978027344 +[2025-04-29 18:52:22,344][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.620500087738037, cross_entropy: 1.620500087738037 +[2025-04-29 18:52:25,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 2.8039259910583496, cross_entropy: 2.8039259910583496 +[2025-04-29 18:52:26,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 1.513968586921692, cross_entropy: 1.513968586921692 +[2025-04-29 18:52:29,629][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 2.7604408264160156, cross_entropy: 2.7604408264160156 +[2025-04-29 18:52:30,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.5236244201660156, cross_entropy: 2.5236244201660156 +[2025-04-29 18:52:33,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.3443924188613892, cross_entropy: 1.3443924188613892 +[2025-04-29 18:52:34,489][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.6750633716583252, cross_entropy: 1.6750633716583252 +[2025-04-29 18:52:38,133][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.2459208965301514, cross_entropy: 1.2459208965301514 +[2025-04-29 18:52:39,193][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.0144754648208618, cross_entropy: 1.0144754648208618 +[2025-04-29 18:52:41,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 1.5358043909072876, cross_entropy: 1.5358043909072876 +[2025-04-29 18:52:42,530][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.0984346866607666, cross_entropy: 1.0984346866607666 +[2025-04-29 18:52:44,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.729994297027588, cross_entropy: 2.729994297027588 +[2025-04-29 18:52:45,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 1.758145809173584, cross_entropy: 1.758145809173584 +[2025-04-29 18:52:47,763][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 2.8207693099975586, cross_entropy: 2.8207693099975586 +[2025-04-29 18:52:48,797][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 1.3214659690856934, cross_entropy: 1.3214659690856934 +[2025-04-29 18:52:51,362][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.3555129766464233, cross_entropy: 1.3555129766464233 +[2025-04-29 18:52:52,396][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.629678249359131, cross_entropy: 2.629678249359131 +[2025-04-29 18:52:54,896][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 0.9567941427230835, cross_entropy: 0.9567941427230835 +[2025-04-29 18:52:55,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 1.8934507369995117, cross_entropy: 1.8934507369995117 +[2025-04-29 18:52:58,327][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 1.2854307889938354, cross_entropy: 1.2854307889938354 +[2025-04-29 18:52:59,384][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.3514856100082397, cross_entropy: 1.3514856100082397 +[2025-04-29 18:53:02,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 2.049530506134033, cross_entropy: 2.049530506134033 +[2025-04-29 18:53:03,186][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 1.0813162326812744, cross_entropy: 1.0813162326812744 +[2025-04-29 18:53:06,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 0.9086977243423462, cross_entropy: 0.9086977243423462 +[2025-04-29 18:53:07,973][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.0342707633972168, cross_entropy: 1.0342707633972168 +[2025-04-29 18:53:10,743][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 2.9368977546691895, cross_entropy: 2.9368977546691895 +[2025-04-29 18:53:11,798][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.7245169878005981, cross_entropy: 1.7245169878005981 +[2025-04-29 18:53:14,758][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 0.9831447005271912, cross_entropy: 0.9831447005271912 +[2025-04-29 18:53:15,792][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 2.6504392623901367, cross_entropy: 2.6504392623901367 +[2025-04-29 18:53:19,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 1.525054693222046, cross_entropy: 1.525054693222046 +[2025-04-29 18:53:20,418][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 2.731563091278076, cross_entropy: 2.731563091278076 +[2025-04-29 18:53:23,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.2734875679016113, cross_entropy: 1.2734875679016113 +[2025-04-29 18:53:24,337][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.951148748397827, cross_entropy: 2.951148748397827 +[2025-04-29 18:53:26,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.1514980792999268, cross_entropy: 2.1514980792999268 +[2025-04-29 18:53:27,871][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.850951671600342, cross_entropy: 2.850951671600342 +[2025-04-29 18:53:30,370][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 0.7875024080276489, cross_entropy: 0.7875024080276489 +[2025-04-29 18:53:31,443][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 2.259953498840332, cross_entropy: 2.259953498840332 +[2025-04-29 18:53:34,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 1.8553950786590576, cross_entropy: 1.8553950786590576 +[2025-04-29 18:53:35,251][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.6758471727371216, cross_entropy: 1.6758471727371216 +[2025-04-29 18:53:38,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.2649638652801514, cross_entropy: 1.2649638652801514 +[2025-04-29 18:53:39,146][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.146331787109375, cross_entropy: 2.146331787109375 +[2025-04-29 18:53:42,670][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.3677351474761963, cross_entropy: 1.3677351474761963 +[2025-04-29 18:53:43,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.8953781127929688, cross_entropy: 2.8953781127929688 +[2025-04-29 18:53:46,375][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 3.122959613800049, cross_entropy: 3.122959613800049 +[2025-04-29 18:53:47,426][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 1.054264783859253, cross_entropy: 1.054264783859253 +[2025-04-29 18:53:50,421][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 0.8936576247215271, cross_entropy: 0.8936576247215271 +[2025-04-29 18:53:51,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 2.3697526454925537, cross_entropy: 2.3697526454925537 +[2025-04-29 18:53:54,508][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 2.6898796558380127, cross_entropy: 2.6898796558380127 +[2025-04-29 18:53:55,568][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 1.354729175567627, cross_entropy: 1.354729175567627 +[2025-04-29 18:53:57,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 2.456223487854004, cross_entropy: 2.456223487854004 +[2025-04-29 18:53:58,919][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.1508445739746094, cross_entropy: 2.1508445739746094 +[2025-04-29 18:54:01,969][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 2.5280838012695312, cross_entropy: 2.5280838012695312 +[2025-04-29 18:54:03,028][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 0.985068678855896, cross_entropy: 0.985068678855896 +[2025-04-29 18:54:06,642][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 1.8152196407318115, cross_entropy: 1.8152196407318115 +[2025-04-29 18:54:07,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.6099748611450195, cross_entropy: 2.6099748611450195 +[2025-04-29 18:54:10,039][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 1.048897385597229, cross_entropy: 1.048897385597229 +[2025-04-29 18:54:11,101][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.5962860584259033, cross_entropy: 1.5962860584259033 +[2025-04-29 18:54:13,948][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.8206499814987183, cross_entropy: 1.8206499814987183 +[2025-04-29 18:54:15,007][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 2.3299307823181152, cross_entropy: 2.3299307823181152 +[2025-04-29 18:54:17,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.780461072921753, cross_entropy: 1.780461072921753 +[2025-04-29 18:54:18,482][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 0.8830934166908264, cross_entropy: 0.8830934166908264 +[2025-04-29 18:54:21,438][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.9123852252960205, cross_entropy: 1.9123852252960205 +[2025-04-29 18:54:22,502][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 2.1654725074768066, cross_entropy: 2.1654725074768066 +[2025-04-29 18:54:24,719][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 1.03956139087677, cross_entropy: 1.03956139087677 +[2025-04-29 18:54:25,778][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 2.0164217948913574, cross_entropy: 2.0164217948913574 +[2025-04-29 18:54:28,752][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.766153573989868, cross_entropy: 2.766153573989868 +[2025-04-29 18:54:29,786][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.5673153400421143, cross_entropy: 2.5673153400421143 +[2025-04-29 18:54:32,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 2.903635263442993, cross_entropy: 2.903635263442993 +[2025-04-29 18:54:33,923][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.6772778034210205, cross_entropy: 2.6772778034210205 +[2025-04-29 18:54:36,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 2.023926019668579, cross_entropy: 2.023926019668579 +[2025-04-29 18:54:37,518][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 2.98093843460083, cross_entropy: 2.98093843460083 +[2025-04-29 18:54:40,079][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.6694039106369019, cross_entropy: 1.6694039106369019 +[2025-04-29 18:54:41,142][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 1.353523850440979, cross_entropy: 1.353523850440979 +[2025-04-29 18:54:43,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 0.9172697067260742, cross_entropy: 0.9172697067260742 +[2025-04-29 18:54:44,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 1.7399003505706787, cross_entropy: 1.7399003505706787 +[2025-04-29 18:54:47,776][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 2.00689697265625, cross_entropy: 2.00689697265625 +[2025-04-29 18:54:48,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 1.2172434329986572, cross_entropy: 1.2172434329986572 +[2025-04-29 18:54:51,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 1.5190874338150024, cross_entropy: 1.5190874338150024 +[2025-04-29 18:54:52,341][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.4894232749938965, cross_entropy: 1.4894232749938965 +[2025-04-29 18:54:54,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.1558377742767334, cross_entropy: 1.1558377742767334 +[2025-04-29 18:54:55,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 3.224976062774658, cross_entropy: 3.224976062774658 +[2025-04-29 18:54:58,530][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 1.2650797367095947, cross_entropy: 1.2650797367095947 +[2025-04-29 18:54:59,633][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.9654678106307983, cross_entropy: 1.9654678106307983 +[2025-04-29 18:55:02,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 2.7764830589294434, cross_entropy: 2.7764830589294434 +[2025-04-29 18:55:03,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 1.4458057880401611, cross_entropy: 1.4458057880401611 +[2025-04-29 18:55:06,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 1.1389763355255127, cross_entropy: 1.1389763355255127 +[2025-04-29 18:55:07,188][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 1.6659998893737793, cross_entropy: 1.6659998893737793 +[2025-04-29 18:55:09,611][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 1.6321009397506714, cross_entropy: 1.6321009397506714 +[2025-04-29 18:55:11,662][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 3.06497859954834, cross_entropy: 3.06497859954834 +[2025-04-29 18:55:13,347][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.86601185798645, cross_entropy: 2.86601185798645 +[2025-04-29 18:55:15,115][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 2.409193992614746, cross_entropy: 2.409193992614746 +[2025-04-29 18:55:17,674][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.6494381427764893, cross_entropy: 1.6494381427764893 +[2025-04-29 18:55:19,219][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 2.3557844161987305, cross_entropy: 2.3557844161987305 +[2025-04-29 18:55:21,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.8892321586608887, cross_entropy: 1.8892321586608887 +[2025-04-29 18:55:22,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 2.9211716651916504, cross_entropy: 2.9211716651916504 +[2025-04-29 18:55:25,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.3294819593429565, cross_entropy: 1.3294819593429565 +[2025-04-29 18:55:26,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.1078908443450928, cross_entropy: 1.1078908443450928 +[2025-04-29 18:55:29,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.4827604293823242, cross_entropy: 1.4827604293823242 +[2025-04-29 18:55:30,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 0.9208322167396545, cross_entropy: 0.9208322167396545 +[2025-04-29 18:55:33,408][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.865244150161743, cross_entropy: 2.865244150161743 +[2025-04-29 18:55:34,445][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 1.6770765781402588, cross_entropy: 1.6770765781402588 +[2025-04-29 18:55:36,864][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 1.9484477043151855, cross_entropy: 1.9484477043151855 +[2025-04-29 18:55:37,929][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 2.620450019836426, cross_entropy: 2.620450019836426 +[2025-04-29 18:55:41,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 2.4681317806243896, cross_entropy: 2.4681317806243896 +[2025-04-29 18:55:42,164][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.721299886703491, cross_entropy: 2.721299886703491 +[2025-04-29 18:55:44,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 2.745997428894043, cross_entropy: 2.745997428894043 +[2025-04-29 18:55:46,007][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.1774680614471436, cross_entropy: 1.1774680614471436 +[2025-04-29 18:55:49,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.2666008472442627, cross_entropy: 1.2666008472442627 +[2025-04-29 18:55:50,191][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 2.8843865394592285, cross_entropy: 2.8843865394592285 +[2025-04-29 18:55:52,820][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 1.8656762838363647, cross_entropy: 1.8656762838363647 +[2025-04-29 18:55:53,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.3900299072265625, cross_entropy: 1.3900299072265625 +[2025-04-29 18:55:56,759][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.5465168952941895, cross_entropy: 2.5465168952941895 +[2025-04-29 18:55:57,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 0.7836309671401978, cross_entropy: 0.7836309671401978 +[2025-04-29 18:56:00,721][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.9648030996322632, cross_entropy: 1.9648030996322632 +[2025-04-29 18:56:01,807][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.397628903388977, cross_entropy: 1.397628903388977 +[2025-04-29 18:56:04,705][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 1.972442626953125, cross_entropy: 1.972442626953125 +[2025-04-29 18:56:05,764][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 1.4760768413543701, cross_entropy: 1.4760768413543701 +[2025-04-29 18:56:07,532][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.8904802799224854, cross_entropy: 1.8904802799224854 +[2025-04-29 18:56:08,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 1.0356954336166382, cross_entropy: 1.0356954336166382 +[2025-04-29 18:56:11,197][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.212959051132202, cross_entropy: 2.212959051132202 +[2025-04-29 18:56:12,259][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.533388614654541, cross_entropy: 1.533388614654541 +[2025-04-29 18:56:15,230][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.2502726316452026, cross_entropy: 1.2502726316452026 +[2025-04-29 18:56:16,460][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 2.909705400466919, cross_entropy: 2.909705400466919 +[2025-04-29 18:56:19,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 1.3758831024169922, cross_entropy: 1.3758831024169922 +[2025-04-29 18:56:20,242][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.24131441116333, cross_entropy: 1.24131441116333 +[2025-04-29 18:56:22,677][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.7164952754974365, cross_entropy: 2.7164952754974365 +[2025-04-29 18:56:24,108][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 2.8073463439941406, cross_entropy: 2.8073463439941406 +[2025-04-29 18:56:26,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 1.0816242694854736, cross_entropy: 1.0816242694854736 +[2025-04-29 18:56:27,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 2.5638556480407715, cross_entropy: 2.5638556480407715 +[2025-04-29 18:56:29,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 1.4316508769989014, cross_entropy: 1.4316508769989014 +[2025-04-29 18:56:31,327][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.9812419414520264, cross_entropy: 2.9812419414520264 +[2025-04-29 18:56:33,568][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.193495273590088, cross_entropy: 2.193495273590088 +[2025-04-29 18:56:34,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.8407104015350342, cross_entropy: 1.8407104015350342 +[2025-04-29 18:56:37,462][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 1.3911749124526978, cross_entropy: 1.3911749124526978 +[2025-04-29 18:56:38,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.1387474536895752, cross_entropy: 1.1387474536895752 +[2025-04-29 18:56:41,039][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 1.8926315307617188, cross_entropy: 1.8926315307617188 +[2025-04-29 18:56:42,295][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 0.9777536392211914, cross_entropy: 0.9777536392211914 +[2025-04-29 18:56:44,828][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.140723705291748, cross_entropy: 2.140723705291748 +[2025-04-29 18:56:46,627][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 1.3543763160705566, cross_entropy: 1.3543763160705566 +[2025-04-29 18:56:48,927][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 2.4640464782714844, cross_entropy: 2.4640464782714844 +[2025-04-29 18:56:50,282][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 1.1893823146820068, cross_entropy: 1.1893823146820068 +[2025-04-29 18:56:52,529][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 2.077883243560791, cross_entropy: 2.077883243560791 +[2025-04-29 18:56:53,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 1.3429206609725952, cross_entropy: 1.3429206609725952 +[2025-04-29 18:56:56,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 3.476963520050049, cross_entropy: 3.476963520050049 +[2025-04-29 18:56:57,833][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.1334357261657715, cross_entropy: 2.1334357261657715 +[2025-04-29 18:56:59,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.9244810342788696, cross_entropy: 1.9244810342788696 +[2025-04-29 18:57:01,370][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 2.258486270904541, cross_entropy: 2.258486270904541 +[2025-04-29 18:57:02,927][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 1.74927818775177, cross_entropy: 1.74927818775177 +[2025-04-29 18:57:05,087][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.0853601694107056, cross_entropy: 1.0853601694107056 +[2025-04-29 18:57:06,780][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.0687031745910645, cross_entropy: 1.0687031745910645 +[2025-04-29 18:57:09,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 1.284074068069458, cross_entropy: 1.284074068069458 +[2025-04-29 18:57:10,359][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.897237777709961, cross_entropy: 1.897237777709961 +[2025-04-29 18:57:12,803][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.577620267868042, cross_entropy: 1.577620267868042 +[2025-04-29 18:57:13,951][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 1.5419490337371826, cross_entropy: 1.5419490337371826 +[2025-04-29 18:57:16,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 1.5299983024597168, cross_entropy: 1.5299983024597168 +[2025-04-29 18:57:17,044][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.2258504629135132, cross_entropy: 1.2258504629135132 +[2025-04-29 18:59:59,918][BaseTrainer][INFO] - [Epoch 5/10] (train) 1.9109594821929932, cross_entropy: 1.9109594821929932 +[2025-04-29 18:59:59,919][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.1874922513961792, cross_entropy: 1.1874922513961792 +[2025-04-29 19:00:00,767][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 19:00:01,255][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch5.pth. +[2025-04-29 19:00:02,062][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 19:00:06,876][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 3.092844009399414, cross_entropy: 3.092844009399414 +[2025-04-29 19:00:08,082][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.7011497020721436, cross_entropy: 1.7011497020721436 +[2025-04-29 19:00:10,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 1.5718694925308228, cross_entropy: 1.5718694925308228 +[2025-04-29 19:00:11,682][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 1.5453473329544067, cross_entropy: 1.5453473329544067 +[2025-04-29 19:00:14,987][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.280148506164551, cross_entropy: 2.280148506164551 +[2025-04-29 19:00:16,019][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 3.0671470165252686, cross_entropy: 3.0671470165252686 +[2025-04-29 19:00:18,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 1.2842884063720703, cross_entropy: 1.2842884063720703 +[2025-04-29 19:00:19,747][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 2.010859251022339, cross_entropy: 2.010859251022339 +[2025-04-29 19:00:23,612][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 2.017117977142334, cross_entropy: 2.017117977142334 +[2025-04-29 19:00:24,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.456836700439453, cross_entropy: 2.456836700439453 +[2025-04-29 19:00:27,793][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.918910503387451, cross_entropy: 2.918910503387451 +[2025-04-29 19:00:28,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 1.3285033702850342, cross_entropy: 1.3285033702850342 +[2025-04-29 19:00:31,795][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 2.2149059772491455, cross_entropy: 2.2149059772491455 +[2025-04-29 19:00:32,828][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.555450201034546, cross_entropy: 1.555450201034546 +[2025-04-29 19:00:35,510][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 1.0251647233963013, cross_entropy: 1.0251647233963013 +[2025-04-29 19:00:36,570][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.577637195587158, cross_entropy: 2.577637195587158 +[2025-04-29 19:00:39,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.0715014934539795, cross_entropy: 1.0715014934539795 +[2025-04-29 19:00:40,362][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 1.4909350872039795, cross_entropy: 1.4909350872039795 +[2025-04-29 19:00:43,796][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.6003954410552979, cross_entropy: 1.6003954410552979 +[2025-04-29 19:00:44,861][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 1.5593550205230713, cross_entropy: 1.5593550205230713 +[2025-04-29 19:00:47,768][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 0.7726559638977051, cross_entropy: 0.7726559638977051 +[2025-04-29 19:00:48,832][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 3.211155414581299, cross_entropy: 3.211155414581299 +[2025-04-29 19:00:51,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 2.9245314598083496, cross_entropy: 2.9245314598083496 +[2025-04-29 19:00:52,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 0.6658550500869751, cross_entropy: 0.6658550500869751 +[2025-04-29 19:00:54,785][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 1.9239685535430908, cross_entropy: 1.9239685535430908 +[2025-04-29 19:00:55,845][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 1.055957555770874, cross_entropy: 1.055957555770874 +[2025-04-29 19:00:58,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 2.984004497528076, cross_entropy: 2.984004497528076 +[2025-04-29 19:00:59,770][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.528829574584961, cross_entropy: 2.528829574584961 +[2025-04-29 19:01:02,117][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.5742276906967163, cross_entropy: 1.5742276906967163 +[2025-04-29 19:01:03,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 1.062249779701233, cross_entropy: 1.062249779701233 +[2025-04-29 19:01:06,104][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 2.4017529487609863, cross_entropy: 2.4017529487609863 +[2025-04-29 19:01:07,137][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.51228666305542, cross_entropy: 2.51228666305542 +[2025-04-29 19:01:09,585][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 2.499143123626709, cross_entropy: 2.499143123626709 +[2025-04-29 19:01:10,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 1.0023170709609985, cross_entropy: 1.0023170709609985 +[2025-04-29 19:01:13,046][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.208552837371826, cross_entropy: 2.208552837371826 +[2025-04-29 19:01:14,077][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 0.9242067933082581, cross_entropy: 0.9242067933082581 +[2025-04-29 19:01:16,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.931925654411316, cross_entropy: 1.931925654411316 +[2025-04-29 19:01:17,858][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 2.9237165451049805, cross_entropy: 2.9237165451049805 +[2025-04-29 19:01:20,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 1.5879350900650024, cross_entropy: 1.5879350900650024 +[2025-04-29 19:01:21,744][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.1258732080459595, cross_entropy: 1.1258732080459595 +[2025-04-29 19:01:24,374][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 2.0550079345703125, cross_entropy: 2.0550079345703125 +[2025-04-29 19:01:25,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 1.1589199304580688, cross_entropy: 1.1589199304580688 +[2025-04-29 19:01:27,864][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 0.8870398998260498, cross_entropy: 0.8870398998260498 +[2025-04-29 19:01:28,921][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 0.7848160266876221, cross_entropy: 0.7848160266876221 +[2025-04-29 19:01:31,591][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 1.0780020952224731, cross_entropy: 1.0780020952224731 +[2025-04-29 19:01:32,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.3293490409851074, cross_entropy: 2.3293490409851074 +[2025-04-29 19:01:36,095][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 1.2668421268463135, cross_entropy: 1.2668421268463135 +[2025-04-29 19:01:37,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 2.846428155899048, cross_entropy: 2.846428155899048 +[2025-04-29 19:01:39,148][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.4554855823516846, cross_entropy: 1.4554855823516846 +[2025-04-29 19:01:40,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.4695343971252441, cross_entropy: 1.4695343971252441 +[2025-04-29 19:01:42,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 1.7780135869979858, cross_entropy: 1.7780135869979858 +[2025-04-29 19:01:43,786][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 0.9119860529899597, cross_entropy: 0.9119860529899597 +[2025-04-29 19:01:46,253][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.755495548248291, cross_entropy: 2.755495548248291 +[2025-04-29 19:01:47,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.68185293674469, cross_entropy: 1.68185293674469 +[2025-04-29 19:01:49,850][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.8646131753921509, cross_entropy: 1.8646131753921509 +[2025-04-29 19:01:50,970][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 1.1283180713653564, cross_entropy: 1.1283180713653564 +[2025-04-29 19:01:53,475][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 2.3993539810180664, cross_entropy: 2.3993539810180664 +[2025-04-29 19:01:54,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 0.9790708422660828, cross_entropy: 0.9790708422660828 +[2025-04-29 19:01:57,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.8368425369262695, cross_entropy: 2.8368425369262695 +[2025-04-29 19:01:58,216][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 0.8455749750137329, cross_entropy: 0.8455749750137329 +[2025-04-29 19:02:01,344][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 0.7953377366065979, cross_entropy: 0.7953377366065979 +[2025-04-29 19:02:02,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 1.4931755065917969, cross_entropy: 1.4931755065917969 +[2025-04-29 19:02:04,957][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.2547818422317505, cross_entropy: 1.2547818422317505 +[2025-04-29 19:02:06,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.3225630521774292, cross_entropy: 1.3225630521774292 +[2025-04-29 19:02:08,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.4269204139709473, cross_entropy: 2.4269204139709473 +[2025-04-29 19:02:09,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 0.6570720672607422, cross_entropy: 0.6570720672607422 +[2025-04-29 19:02:12,193][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 2.8123159408569336, cross_entropy: 2.8123159408569336 +[2025-04-29 19:02:13,224][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.0371277332305908, cross_entropy: 1.0371277332305908 +[2025-04-29 19:02:15,802][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 1.0783733129501343, cross_entropy: 1.0783733129501343 +[2025-04-29 19:02:16,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 2.411961317062378, cross_entropy: 2.411961317062378 +[2025-04-29 19:02:20,130][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 1.973270297050476, cross_entropy: 1.973270297050476 +[2025-04-29 19:02:21,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.6486276388168335, cross_entropy: 1.6486276388168335 +[2025-04-29 19:02:24,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 0.8473204374313354, cross_entropy: 0.8473204374313354 +[2025-04-29 19:02:25,486][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.7393481731414795, cross_entropy: 1.7393481731414795 +[2025-04-29 19:02:28,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 0.938761293888092, cross_entropy: 0.938761293888092 +[2025-04-29 19:02:29,073][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.218998670578003, cross_entropy: 1.218998670578003 +[2025-04-29 19:02:31,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.637535810470581, cross_entropy: 2.637535810470581 +[2025-04-29 19:02:32,464][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 1.4601764678955078, cross_entropy: 1.4601764678955078 +[2025-04-29 19:02:35,208][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.8080997467041016, cross_entropy: 2.8080997467041016 +[2025-04-29 19:02:36,263][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 2.623384714126587, cross_entropy: 2.623384714126587 +[2025-04-29 19:02:39,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.1401948928833008, cross_entropy: 1.1401948928833008 +[2025-04-29 19:02:40,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 1.2985864877700806, cross_entropy: 1.2985864877700806 +[2025-04-29 19:02:42,863][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.7506611347198486, cross_entropy: 2.7506611347198486 +[2025-04-29 19:02:43,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 2.9021096229553223, cross_entropy: 2.9021096229553223 +[2025-04-29 19:02:46,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.2110406160354614, cross_entropy: 1.2110406160354614 +[2025-04-29 19:02:47,903][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.054553508758545, cross_entropy: 2.054553508758545 +[2025-04-29 19:02:50,254][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 1.8323243856430054, cross_entropy: 1.8323243856430054 +[2025-04-29 19:02:51,310][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.384185791015625, cross_entropy: 1.384185791015625 +[2025-04-29 19:02:54,058][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 2.73982572555542, cross_entropy: 2.73982572555542 +[2025-04-29 19:02:55,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 0.8407303094863892, cross_entropy: 0.8407303094863892 +[2025-04-29 19:02:58,221][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 0.9188151359558105, cross_entropy: 0.9188151359558105 +[2025-04-29 19:02:59,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.659428596496582, cross_entropy: 1.659428596496582 +[2025-04-29 19:03:01,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.4954882860183716, cross_entropy: 1.4954882860183716 +[2025-04-29 19:03:02,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 0.9142353534698486, cross_entropy: 0.9142353534698486 +[2025-04-29 19:03:05,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 0.8447109460830688, cross_entropy: 0.8447109460830688 +[2025-04-29 19:03:06,097][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.2833210229873657, cross_entropy: 1.2833210229873657 +[2025-04-29 19:03:08,421][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.2088584899902344, cross_entropy: 2.2088584899902344 +[2025-04-29 19:03:09,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.396517038345337, cross_entropy: 1.396517038345337 +[2025-04-29 19:03:12,556][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.356299638748169, cross_entropy: 1.356299638748169 +[2025-04-29 19:03:13,592][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.629259705543518, cross_entropy: 1.629259705543518 +[2025-04-29 19:03:16,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 2.2397048473358154, cross_entropy: 2.2397048473358154 +[2025-04-29 19:03:17,319][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.231008768081665, cross_entropy: 2.231008768081665 +[2025-04-29 19:03:19,676][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 1.0344852209091187, cross_entropy: 1.0344852209091187 +[2025-04-29 19:03:20,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.9838868379592896, cross_entropy: 0.9838868379592896 +[2025-04-29 19:03:24,225][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.519871711730957, cross_entropy: 1.519871711730957 +[2025-04-29 19:03:25,280][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 1.640166163444519, cross_entropy: 1.640166163444519 +[2025-04-29 19:03:28,367][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 1.7590901851654053, cross_entropy: 1.7590901851654053 +[2025-04-29 19:03:29,427][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 2.970679759979248, cross_entropy: 2.970679759979248 +[2025-04-29 19:03:31,908][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.1371254920959473, cross_entropy: 1.1371254920959473 +[2025-04-29 19:03:32,941][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 2.163121223449707, cross_entropy: 2.163121223449707 +[2025-04-29 19:03:35,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 2.381033182144165, cross_entropy: 2.381033182144165 +[2025-04-29 19:03:36,955][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 2.7770676612854004, cross_entropy: 2.7770676612854004 +[2025-04-29 19:03:39,280][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.2041757106781006, cross_entropy: 2.2041757106781006 +[2025-04-29 19:03:40,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.4565445184707642, cross_entropy: 1.4565445184707642 +[2025-04-29 19:03:43,542][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.432600975036621, cross_entropy: 2.432600975036621 +[2025-04-29 19:03:44,574][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 2.0752620697021484, cross_entropy: 2.0752620697021484 +[2025-04-29 19:03:47,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 2.8144173622131348, cross_entropy: 2.8144173622131348 +[2025-04-29 19:03:48,592][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 1.3284027576446533, cross_entropy: 1.3284027576446533 +[2025-04-29 19:03:51,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 1.0919606685638428, cross_entropy: 1.0919606685638428 +[2025-04-29 19:03:52,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 2.4866113662719727, cross_entropy: 2.4866113662719727 +[2025-04-29 19:03:54,923][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 3.012894868850708, cross_entropy: 3.012894868850708 +[2025-04-29 19:03:55,981][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.314382791519165, cross_entropy: 1.314382791519165 +[2025-04-29 19:03:58,094][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 2.7985639572143555, cross_entropy: 2.7985639572143555 +[2025-04-29 19:03:59,155][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 0.9600460529327393, cross_entropy: 0.9600460529327393 +[2025-04-29 19:04:01,364][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.4864894151687622, cross_entropy: 1.4864894151687622 +[2025-04-29 19:04:02,397][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 0.8755911588668823, cross_entropy: 0.8755911588668823 +[2025-04-29 19:04:06,488][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.9472577571868896, cross_entropy: 1.9472577571868896 +[2025-04-29 19:04:07,548][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 1.139500379562378, cross_entropy: 1.139500379562378 +[2025-04-29 19:04:10,322][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 2.7545015811920166, cross_entropy: 2.7545015811920166 +[2025-04-29 19:04:11,373][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 1.1274759769439697, cross_entropy: 1.1274759769439697 +[2025-04-29 19:04:14,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 1.3840856552124023, cross_entropy: 1.3840856552124023 +[2025-04-29 19:04:15,457][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.7962720394134521, cross_entropy: 1.7962720394134521 +[2025-04-29 19:04:18,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 2.7964863777160645, cross_entropy: 2.7964863777160645 +[2025-04-29 19:04:19,433][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 1.3038692474365234, cross_entropy: 1.3038692474365234 +[2025-04-29 19:04:22,548][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 2.012922763824463, cross_entropy: 2.012922763824463 +[2025-04-29 19:04:23,608][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 2.750417947769165, cross_entropy: 2.750417947769165 +[2025-04-29 19:04:25,619][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 0.8762844800949097, cross_entropy: 0.8762844800949097 +[2025-04-29 19:04:26,679][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.8253822326660156, cross_entropy: 1.8253822326660156 +[2025-04-29 19:04:29,646][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.2856754064559937, cross_entropy: 1.2856754064559937 +[2025-04-29 19:04:30,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.4704296588897705, cross_entropy: 2.4704296588897705 +[2025-04-29 19:04:32,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.3792908191680908, cross_entropy: 1.3792908191680908 +[2025-04-29 19:04:33,575][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 0.8527758121490479, cross_entropy: 0.8527758121490479 +[2025-04-29 19:04:36,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 1.8154008388519287, cross_entropy: 1.8154008388519287 +[2025-04-29 19:04:37,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 1.6432385444641113, cross_entropy: 1.6432385444641113 +[2025-04-29 19:04:39,564][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 2.9896302223205566, cross_entropy: 2.9896302223205566 +[2025-04-29 19:04:40,594][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 0.929780125617981, cross_entropy: 0.929780125617981 +[2025-04-29 19:04:43,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 1.7040796279907227, cross_entropy: 1.7040796279907227 +[2025-04-29 19:04:44,197][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.977142333984375, cross_entropy: 1.977142333984375 +[2025-04-29 19:04:46,362][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 1.3565700054168701, cross_entropy: 1.3565700054168701 +[2025-04-29 19:04:47,415][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.7784485816955566, cross_entropy: 2.7784485816955566 +[2025-04-29 19:04:50,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.434138774871826, cross_entropy: 2.434138774871826 +[2025-04-29 19:04:51,318][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.682945966720581, cross_entropy: 2.682945966720581 +[2025-04-29 19:04:54,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 2.6571693420410156, cross_entropy: 2.6571693420410156 +[2025-04-29 19:04:55,437][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.2633204460144043, cross_entropy: 1.2633204460144043 +[2025-04-29 19:04:57,662][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 2.923856496810913, cross_entropy: 2.923856496810913 +[2025-04-29 19:04:58,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 2.033252239227295, cross_entropy: 2.033252239227295 +[2025-04-29 19:05:01,532][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.6044669151306152, cross_entropy: 2.6044669151306152 +[2025-04-29 19:05:02,589][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 0.7847464084625244, cross_entropy: 0.7847464084625244 +[2025-04-29 19:05:05,605][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 2.01106858253479, cross_entropy: 2.01106858253479 +[2025-04-29 19:05:06,637][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 2.7235190868377686, cross_entropy: 2.7235190868377686 +[2025-04-29 19:05:09,713][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.8580985069274902, cross_entropy: 1.8580985069274902 +[2025-04-29 19:05:10,768][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 2.9476876258850098, cross_entropy: 2.9476876258850098 +[2025-04-29 19:05:13,997][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 0.9358353614807129, cross_entropy: 0.9358353614807129 +[2025-04-29 19:05:15,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 0.9871982336044312, cross_entropy: 0.9871982336044312 +[2025-04-29 19:05:18,146][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 2.190974235534668, cross_entropy: 2.190974235534668 +[2025-04-29 19:05:19,200][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.6193699836730957, cross_entropy: 2.6193699836730957 +[2025-04-29 19:05:21,895][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 0.9606004953384399, cross_entropy: 0.9606004953384399 +[2025-04-29 19:05:22,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.6687960624694824, cross_entropy: 1.6687960624694824 +[2025-04-29 19:05:25,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 1.1144306659698486, cross_entropy: 1.1144306659698486 +[2025-04-29 19:05:26,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 0.6963049173355103, cross_entropy: 0.6963049173355103 +[2025-04-29 19:05:29,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 1.518911600112915, cross_entropy: 1.518911600112915 +[2025-04-29 19:05:30,497][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.2372081279754639, cross_entropy: 1.2372081279754639 +[2025-04-29 19:05:32,806][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 0.8906018137931824, cross_entropy: 0.8906018137931824 +[2025-04-29 19:05:34,308][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.7516615390777588, cross_entropy: 1.7516615390777588 +[2025-04-29 19:05:36,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 0.5313711762428284, cross_entropy: 0.5313711762428284 +[2025-04-29 19:05:38,701][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 2.298705577850342, cross_entropy: 2.298705577850342 +[2025-04-29 19:05:39,978][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.4249523878097534, cross_entropy: 1.4249523878097534 +[2025-04-29 19:05:42,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.0510308742523193, cross_entropy: 1.0510308742523193 +[2025-04-29 19:05:44,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.3622708320617676, cross_entropy: 2.3622708320617676 +[2025-04-29 19:05:45,484][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.10689377784729, cross_entropy: 1.10689377784729 +[2025-04-29 19:05:47,555][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 2.1663362979888916, cross_entropy: 2.1663362979888916 +[2025-04-29 19:05:49,075][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 1.7009212970733643, cross_entropy: 1.7009212970733643 +[2025-04-29 19:05:52,299][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 0.7966415882110596, cross_entropy: 0.7966415882110596 +[2025-04-29 19:05:53,940][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.3974409103393555, cross_entropy: 2.3974409103393555 +[2025-04-29 19:05:55,622][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.4773228168487549, cross_entropy: 1.4773228168487549 +[2025-04-29 19:05:57,664][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.5899171829223633, cross_entropy: 1.5899171829223633 +[2025-04-29 19:05:59,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 1.470686435699463, cross_entropy: 1.470686435699463 +[2025-04-29 19:06:01,158][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 0.9568988680839539, cross_entropy: 0.9568988680839539 +[2025-04-29 19:06:03,408][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 2.328162670135498, cross_entropy: 2.328162670135498 +[2025-04-29 19:06:04,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.9327549934387207, cross_entropy: 2.9327549934387207 +[2025-04-29 19:06:06,819][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 2.512559413909912, cross_entropy: 2.512559413909912 +[2025-04-29 19:06:08,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.624541759490967, cross_entropy: 2.624541759490967 +[2025-04-29 19:06:10,756][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 0.7916570901870728, cross_entropy: 0.7916570901870728 +[2025-04-29 19:06:11,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 1.2338907718658447, cross_entropy: 1.2338907718658447 +[2025-04-29 19:06:14,749][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.0200750827789307, cross_entropy: 1.0200750827789307 +[2025-04-29 19:06:15,863][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 2.488654136657715, cross_entropy: 2.488654136657715 +[2025-04-29 19:06:18,074][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.951159954071045, cross_entropy: 2.951159954071045 +[2025-04-29 19:06:19,179][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 1.35394287109375, cross_entropy: 1.35394287109375 +[2025-04-29 19:06:21,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 2.8588051795959473, cross_entropy: 2.8588051795959473 +[2025-04-29 19:06:22,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.2838797569274902, cross_entropy: 1.2838797569274902 +[2025-04-29 19:06:25,466][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 0.6213135719299316, cross_entropy: 0.6213135719299316 +[2025-04-29 19:06:26,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 0.6413965225219727, cross_entropy: 0.6413965225219727 +[2025-04-29 19:06:29,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 0.7461886405944824, cross_entropy: 0.7461886405944824 +[2025-04-29 19:06:30,343][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 2.329277992248535, cross_entropy: 2.329277992248535 +[2025-04-29 19:06:33,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 0.6310246586799622, cross_entropy: 0.6310246586799622 +[2025-04-29 19:06:34,068][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.185136318206787, cross_entropy: 1.185136318206787 +[2025-04-29 19:06:37,537][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 0.959864616394043, cross_entropy: 0.959864616394043 +[2025-04-29 19:06:38,591][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 0.6652867794036865, cross_entropy: 0.6652867794036865 +[2025-04-29 19:06:40,938][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 1.2908587455749512, cross_entropy: 1.2908587455749512 +[2025-04-29 19:06:42,001][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 2.7411816120147705, cross_entropy: 2.7411816120147705 +[2025-04-29 19:06:45,526][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 2.4757065773010254, cross_entropy: 2.4757065773010254 +[2025-04-29 19:06:46,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 2.9686620235443115, cross_entropy: 2.9686620235443115 +[2025-04-29 19:06:49,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 0.9835758209228516, cross_entropy: 0.9835758209228516 +[2025-04-29 19:06:50,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.153602957725525, cross_entropy: 1.153602957725525 +[2025-04-29 19:06:52,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.7165474891662598, cross_entropy: 2.7165474891662598 +[2025-04-29 19:06:53,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 1.483965516090393, cross_entropy: 1.483965516090393 +[2025-04-29 19:06:56,286][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 1.3901221752166748, cross_entropy: 1.3901221752166748 +[2025-04-29 19:06:57,348][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 3.2212166786193848, cross_entropy: 3.2212166786193848 +[2025-04-29 19:07:00,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 1.1614055633544922, cross_entropy: 1.1614055633544922 +[2025-04-29 19:07:01,222][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 0.9846636056900024, cross_entropy: 0.9846636056900024 +[2025-04-29 19:07:02,019][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/iteration2000.pth. +[2025-04-29 19:07:04,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.8807018995285034, cross_entropy: 1.8807018995285034 +[2025-04-29 19:07:05,186][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 1.8251104354858398, cross_entropy: 1.8251104354858398 +[2025-04-29 19:07:08,126][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 1.792305827140808, cross_entropy: 1.792305827140808 +[2025-04-29 19:07:09,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 2.235045909881592, cross_entropy: 2.235045909881592 +[2025-04-29 19:07:11,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 1.0873453617095947, cross_entropy: 1.0873453617095947 +[2025-04-29 19:07:12,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 1.1359639167785645, cross_entropy: 1.1359639167785645 +[2025-04-29 19:07:15,324][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 1.8759551048278809, cross_entropy: 1.8759551048278809 +[2025-04-29 19:07:16,383][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.9099440574645996, cross_entropy: 2.9099440574645996 +[2025-04-29 19:07:19,163][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.5274431705474854, cross_entropy: 1.5274431705474854 +[2025-04-29 19:07:20,223][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.7469158172607422, cross_entropy: 1.7469158172607422 +[2025-04-29 19:07:22,378][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 1.948503017425537, cross_entropy: 1.948503017425537 +[2025-04-29 19:07:23,411][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 0.7437673211097717, cross_entropy: 0.7437673211097717 +[2025-04-29 19:07:25,939][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.359097957611084, cross_entropy: 1.359097957611084 +[2025-04-29 19:07:27,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 2.977059841156006, cross_entropy: 2.977059841156006 +[2025-04-29 19:07:30,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.8074589967727661, cross_entropy: 1.8074589967727661 +[2025-04-29 19:07:31,504][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 1.6520411968231201, cross_entropy: 1.6520411968231201 +[2025-04-29 19:07:34,080][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 2.7765491008758545, cross_entropy: 2.7765491008758545 +[2025-04-29 19:07:35,111][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 2.1938533782958984, cross_entropy: 2.1938533782958984 +[2025-04-29 19:07:38,204][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 1.297597885131836, cross_entropy: 1.297597885131836 +[2025-04-29 19:07:39,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 1.157423734664917, cross_entropy: 1.157423734664917 +[2025-04-29 19:07:42,252][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 0.9268280863761902, cross_entropy: 0.9268280863761902 +[2025-04-29 19:07:43,283][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.644197463989258, cross_entropy: 2.644197463989258 +[2025-04-29 19:07:46,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.3451852798461914, cross_entropy: 1.3451852798461914 +[2025-04-29 19:07:47,900][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 1.7038710117340088, cross_entropy: 1.7038710117340088 +[2025-04-29 19:07:50,841][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 2.1272058486938477, cross_entropy: 2.1272058486938477 +[2025-04-29 19:07:51,874][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 0.9030352234840393, cross_entropy: 0.9030352234840393 +[2025-04-29 19:07:54,607][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 2.714496374130249, cross_entropy: 2.714496374130249 +[2025-04-29 19:07:55,639][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.256056308746338, cross_entropy: 1.256056308746338 +[2025-04-29 19:07:59,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.7954061031341553, cross_entropy: 2.7954061031341553 +[2025-04-29 19:08:00,111][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.4361070394515991, cross_entropy: 1.4361070394515991 +[2025-04-29 19:08:03,059][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 1.9790546894073486, cross_entropy: 1.9790546894073486 +[2025-04-29 19:08:04,116][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 2.0809221267700195, cross_entropy: 2.0809221267700195 +[2025-04-29 19:08:06,916][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.5727908611297607, cross_entropy: 1.5727908611297607 +[2025-04-29 19:08:07,977][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 2.1601359844207764, cross_entropy: 2.1601359844207764 +[2025-04-29 19:08:11,580][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 0.917368471622467, cross_entropy: 0.917368471622467 +[2025-04-29 19:08:12,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 2.319197177886963, cross_entropy: 2.319197177886963 +[2025-04-29 19:08:15,261][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 2.661051034927368, cross_entropy: 2.661051034927368 +[2025-04-29 19:08:16,324][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.0886409282684326, cross_entropy: 1.0886409282684326 +[2025-04-29 19:08:18,867][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 2.0405943393707275, cross_entropy: 2.0405943393707275 +[2025-04-29 19:08:19,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 1.846092700958252, cross_entropy: 1.846092700958252 +[2025-04-29 19:08:22,593][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 0.7181384563446045, cross_entropy: 0.7181384563446045 +[2025-04-29 19:08:23,657][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.840198040008545, cross_entropy: 1.840198040008545 +[2025-04-29 19:08:26,548][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.135359525680542, cross_entropy: 2.135359525680542 +[2025-04-29 19:08:27,583][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.4059371948242188, cross_entropy: 2.4059371948242188 +[2025-04-29 19:08:31,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 1.5981223583221436, cross_entropy: 1.5981223583221436 +[2025-04-29 19:08:32,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 1.1114113330841064, cross_entropy: 1.1114113330841064 +[2025-04-29 19:08:35,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 2.192213535308838, cross_entropy: 2.192213535308838 +[2025-04-29 19:08:36,083][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 1.7112398147583008, cross_entropy: 1.7112398147583008 +[2025-04-29 19:08:38,973][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.3649835586547852, cross_entropy: 1.3649835586547852 +[2025-04-29 19:08:40,007][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 2.2601451873779297, cross_entropy: 2.2601451873779297 +[2025-04-29 19:08:42,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.3419052362442017, cross_entropy: 1.3419052362442017 +[2025-04-29 19:08:43,487][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.7354464530944824, cross_entropy: 2.7354464530944824 +[2025-04-29 19:08:46,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.6935300827026367, cross_entropy: 1.6935300827026367 +[2025-04-29 19:08:47,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 0.9865797758102417, cross_entropy: 0.9865797758102417 +[2025-04-29 19:08:50,733][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.4590389728546143, cross_entropy: 1.4590389728546143 +[2025-04-29 19:08:51,776][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.2960939407348633, cross_entropy: 2.2960939407348633 +[2025-04-29 19:08:54,521][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 2.710339307785034, cross_entropy: 2.710339307785034 +[2025-04-29 19:08:55,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.2768654823303223, cross_entropy: 2.2768654823303223 +[2025-04-29 19:08:58,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 1.5063238143920898, cross_entropy: 1.5063238143920898 +[2025-04-29 19:08:59,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 2.700143337249756, cross_entropy: 2.700143337249756 +[2025-04-29 19:09:01,849][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 2.4962306022644043, cross_entropy: 2.4962306022644043 +[2025-04-29 19:09:02,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.430749773979187, cross_entropy: 1.430749773979187 +[2025-04-29 19:09:06,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 1.2669159173965454, cross_entropy: 1.2669159173965454 +[2025-04-29 19:09:07,180][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 1.0762375593185425, cross_entropy: 1.0762375593185425 +[2025-04-29 19:09:10,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 1.0462348461151123, cross_entropy: 1.0462348461151123 +[2025-04-29 19:09:11,682][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 0.9145525693893433, cross_entropy: 0.9145525693893433 +[2025-04-29 19:09:14,738][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 2.3709592819213867, cross_entropy: 2.3709592819213867 +[2025-04-29 19:09:15,799][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 2.627575397491455, cross_entropy: 2.627575397491455 +[2025-04-29 19:09:20,397][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 1.1248092651367188, cross_entropy: 1.1248092651367188 +[2025-04-29 19:09:21,453][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.601444959640503, cross_entropy: 1.601444959640503 +[2025-04-29 19:09:23,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.487534999847412, cross_entropy: 1.487534999847412 +[2025-04-29 19:09:24,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.4903733730316162, cross_entropy: 1.4903733730316162 +[2025-04-29 19:09:27,904][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 1.120111346244812, cross_entropy: 1.120111346244812 +[2025-04-29 19:09:28,972][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 0.9297135472297668, cross_entropy: 0.9297135472297668 +[2025-04-29 19:09:30,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 1.8283330202102661, cross_entropy: 1.8283330202102661 +[2025-04-29 19:09:31,823][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 2.111098527908325, cross_entropy: 2.111098527908325 +[2025-04-29 19:09:34,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 3.0443367958068848, cross_entropy: 3.0443367958068848 +[2025-04-29 19:09:35,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 1.9027223587036133, cross_entropy: 1.9027223587036133 +[2025-04-29 19:09:38,975][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 2.485383987426758, cross_entropy: 2.485383987426758 +[2025-04-29 19:09:40,015][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.6869609355926514, cross_entropy: 2.6869609355926514 +[2025-04-29 19:09:42,640][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.684046745300293, cross_entropy: 2.684046745300293 +[2025-04-29 19:09:43,713][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 2.1340255737304688, cross_entropy: 2.1340255737304688 +[2025-04-29 19:09:47,194][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 2.0092623233795166, cross_entropy: 2.0092623233795166 +[2025-04-29 19:09:48,256][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 3.1854588985443115, cross_entropy: 3.1854588985443115 +[2025-04-29 19:09:50,462][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 2.262171745300293, cross_entropy: 2.262171745300293 +[2025-04-29 19:09:51,523][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 1.235680341720581, cross_entropy: 1.235680341720581 +[2025-04-29 19:09:53,971][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 0.9155133962631226, cross_entropy: 0.9155133962631226 +[2025-04-29 19:09:55,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.7433841228485107, cross_entropy: 1.7433841228485107 +[2025-04-29 19:09:58,510][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.0768680572509766, cross_entropy: 1.0768680572509766 +[2025-04-29 19:09:59,572][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 0.7600079774856567, cross_entropy: 0.7600079774856567 +[2025-04-29 19:10:02,245][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.029520034790039, cross_entropy: 2.029520034790039 +[2025-04-29 19:10:03,307][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 2.6879422664642334, cross_entropy: 2.6879422664642334 +[2025-04-29 19:10:05,753][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.0632990598678589, cross_entropy: 1.0632990598678589 +[2025-04-29 19:10:06,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 2.8005478382110596, cross_entropy: 2.8005478382110596 +[2025-04-29 19:10:10,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 1.0934404134750366, cross_entropy: 1.0934404134750366 +[2025-04-29 19:10:11,631][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 2.635392189025879, cross_entropy: 2.635392189025879 +[2025-04-29 19:10:14,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 0.7341545820236206, cross_entropy: 0.7341545820236206 +[2025-04-29 19:10:15,752][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.4516267776489258, cross_entropy: 1.4516267776489258 +[2025-04-29 19:10:18,287][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 0.9116250276565552, cross_entropy: 0.9116250276565552 +[2025-04-29 19:10:19,325][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.2129030227661133, cross_entropy: 1.2129030227661133 +[2025-04-29 19:10:22,255][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.5426710844039917, cross_entropy: 1.5426710844039917 +[2025-04-29 19:10:23,322][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 1.2788352966308594, cross_entropy: 1.2788352966308594 +[2025-04-29 19:10:26,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 2.3187665939331055, cross_entropy: 2.3187665939331055 +[2025-04-29 19:10:27,352][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.0942633152008057, cross_entropy: 2.0942633152008057 +[2025-04-29 19:10:29,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.193170428276062, cross_entropy: 1.193170428276062 +[2025-04-29 19:10:30,616][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.2795655727386475, cross_entropy: 2.2795655727386475 +[2025-04-29 19:10:33,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.246024250984192, cross_entropy: 1.246024250984192 +[2025-04-29 19:10:34,353][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 1.090371012687683, cross_entropy: 1.090371012687683 +[2025-04-29 19:10:36,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 0.9900006055831909, cross_entropy: 0.9900006055831909 +[2025-04-29 19:10:37,961][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.0971770286560059, cross_entropy: 1.0971770286560059 +[2025-04-29 19:10:40,612][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 0.9135864973068237, cross_entropy: 0.9135864973068237 +[2025-04-29 19:10:41,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.0423355102539062, cross_entropy: 1.0423355102539062 +[2025-04-29 19:10:44,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.1675078868865967, cross_entropy: 1.1675078868865967 +[2025-04-29 19:10:45,261][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 1.890946865081787, cross_entropy: 1.890946865081787 +[2025-04-29 19:10:48,879][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.2724204063415527, cross_entropy: 1.2724204063415527 +[2025-04-29 19:10:49,950][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 2.294914960861206, cross_entropy: 2.294914960861206 +[2025-04-29 19:10:52,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 1.8128772974014282, cross_entropy: 1.8128772974014282 +[2025-04-29 19:10:53,437][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.4099847078323364, cross_entropy: 1.4099847078323364 +[2025-04-29 19:10:56,777][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 1.2986750602722168, cross_entropy: 1.2986750602722168 +[2025-04-29 19:10:57,854][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 1.1660422086715698, cross_entropy: 1.1660422086715698 +[2025-04-29 19:11:00,458][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 1.9979844093322754, cross_entropy: 1.9979844093322754 +[2025-04-29 19:11:01,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 1.1354643106460571, cross_entropy: 1.1354643106460571 +[2025-04-29 19:11:04,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 2.8853516578674316, cross_entropy: 2.8853516578674316 +[2025-04-29 19:11:05,212][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.14673912525177, cross_entropy: 1.14673912525177 +[2025-04-29 19:11:08,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 2.7284369468688965, cross_entropy: 2.7284369468688965 +[2025-04-29 19:11:09,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 2.4812870025634766, cross_entropy: 2.4812870025634766 +[2025-04-29 19:11:11,806][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 2.9097392559051514, cross_entropy: 2.9097392559051514 +[2025-04-29 19:11:12,874][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 0.9614489078521729, cross_entropy: 0.9614489078521729 +[2025-04-29 19:11:16,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 2.1044116020202637, cross_entropy: 2.1044116020202637 +[2025-04-29 19:11:17,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.5106836557388306, cross_entropy: 1.5106836557388306 +[2025-04-29 19:11:20,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 2.4367787837982178, cross_entropy: 2.4367787837982178 +[2025-04-29 19:11:21,146][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.4460062980651855, cross_entropy: 1.4460062980651855 +[2025-04-29 19:11:23,296][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 2.929826259613037, cross_entropy: 2.929826259613037 +[2025-04-29 19:11:24,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.8465865850448608, cross_entropy: 1.8465865850448608 +[2025-04-29 19:11:26,604][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 1.291043758392334, cross_entropy: 1.291043758392334 +[2025-04-29 19:11:27,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 2.4630560874938965, cross_entropy: 2.4630560874938965 +[2025-04-29 19:14:11,451][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.7590380907058716, cross_entropy: 1.7590380907058716 +[2025-04-29 19:14:11,451][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.1025116443634033, cross_entropy: 1.1025116443634033 +[2025-04-29 19:14:12,329][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 19:14:12,866][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch6.pth. +[2025-04-29 19:14:13,660][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 19:14:18,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.918689489364624, cross_entropy: 2.918689489364624 +[2025-04-29 19:14:19,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.164594888687134, cross_entropy: 2.164594888687134 +[2025-04-29 19:14:22,024][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 2.5584042072296143, cross_entropy: 2.5584042072296143 +[2025-04-29 19:14:23,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 0.6933929920196533, cross_entropy: 0.6933929920196533 +[2025-04-29 19:14:26,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 2.1565258502960205, cross_entropy: 2.1565258502960205 +[2025-04-29 19:14:27,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.7511253356933594, cross_entropy: 1.7511253356933594 +[2025-04-29 19:14:30,196][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.061553716659546, cross_entropy: 2.061553716659546 +[2025-04-29 19:14:31,255][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.033247470855713, cross_entropy: 1.033247470855713 +[2025-04-29 19:14:34,178][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.528456211090088, cross_entropy: 1.528456211090088 +[2025-04-29 19:14:35,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.369729995727539, cross_entropy: 1.369729995727539 +[2025-04-29 19:14:38,395][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 2.875980854034424, cross_entropy: 2.875980854034424 +[2025-04-29 19:14:39,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.2271803617477417, cross_entropy: 1.2271803617477417 +[2025-04-29 19:14:42,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 1.0376832485198975, cross_entropy: 1.0376832485198975 +[2025-04-29 19:14:43,571][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 0.5854707956314087, cross_entropy: 0.5854707956314087 +[2025-04-29 19:14:46,080][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 1.7835593223571777, cross_entropy: 1.7835593223571777 +[2025-04-29 19:14:47,147][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.759875535964966, cross_entropy: 2.759875535964966 +[2025-04-29 19:14:50,099][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.6870949268341064, cross_entropy: 2.6870949268341064 +[2025-04-29 19:14:51,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 2.6763086318969727, cross_entropy: 2.6763086318969727 +[2025-04-29 19:14:54,201][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.4611763954162598, cross_entropy: 2.4611763954162598 +[2025-04-29 19:14:55,265][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 2.9446005821228027, cross_entropy: 2.9446005821228027 +[2025-04-29 19:14:58,459][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.4737268686294556, cross_entropy: 1.4737268686294556 +[2025-04-29 19:14:59,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 1.6462244987487793, cross_entropy: 1.6462244987487793 +[2025-04-29 19:15:01,506][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 0.9281191229820251, cross_entropy: 0.9281191229820251 +[2025-04-29 19:15:02,577][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.2713305950164795, cross_entropy: 2.2713305950164795 +[2025-04-29 19:15:06,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 0.8370896577835083, cross_entropy: 0.8370896577835083 +[2025-04-29 19:15:07,329][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.6423356533050537, cross_entropy: 2.6423356533050537 +[2025-04-29 19:15:10,079][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.0712528228759766, cross_entropy: 2.0712528228759766 +[2025-04-29 19:15:11,138][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 1.1153134107589722, cross_entropy: 1.1153134107589722 +[2025-04-29 19:15:13,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.2486536502838135, cross_entropy: 1.2486536502838135 +[2025-04-29 19:15:14,666][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 0.5098527669906616, cross_entropy: 0.5098527669906616 +[2025-04-29 19:15:17,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.6949868202209473, cross_entropy: 2.6949868202209473 +[2025-04-29 19:15:18,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 0.48260533809661865, cross_entropy: 0.48260533809661865 +[2025-04-29 19:15:21,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 1.5372331142425537, cross_entropy: 1.5372331142425537 +[2025-04-29 19:15:22,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 0.8380720615386963, cross_entropy: 0.8380720615386963 +[2025-04-29 19:15:25,331][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.014190673828125, cross_entropy: 2.014190673828125 +[2025-04-29 19:15:26,397][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 2.0280823707580566, cross_entropy: 2.0280823707580566 +[2025-04-29 19:15:28,667][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 1.984480381011963, cross_entropy: 1.984480381011963 +[2025-04-29 19:15:29,731][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.5450505018234253, cross_entropy: 1.5450505018234253 +[2025-04-29 19:15:32,996][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 0.635816752910614, cross_entropy: 0.635816752910614 +[2025-04-29 19:15:34,029][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 2.492793083190918, cross_entropy: 2.492793083190918 +[2025-04-29 19:15:37,259][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 0.7508122324943542, cross_entropy: 0.7508122324943542 +[2025-04-29 19:15:38,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 3.1176741123199463, cross_entropy: 3.1176741123199463 +[2025-04-29 19:15:40,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.826817274093628, cross_entropy: 2.826817274093628 +[2025-04-29 19:15:41,966][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 1.2284313440322876, cross_entropy: 1.2284313440322876 +[2025-04-29 19:15:45,121][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 0.8902812600135803, cross_entropy: 0.8902812600135803 +[2025-04-29 19:15:46,157][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.8665094375610352, cross_entropy: 1.8665094375610352 +[2025-04-29 19:15:48,543][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 2.3814339637756348, cross_entropy: 2.3814339637756348 +[2025-04-29 19:15:49,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 0.7076262831687927, cross_entropy: 0.7076262831687927 +[2025-04-29 19:15:52,264][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.4193673133850098, cross_entropy: 2.4193673133850098 +[2025-04-29 19:15:53,332][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 0.8078973293304443, cross_entropy: 0.8078973293304443 +[2025-04-29 19:15:56,573][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.7756619453430176, cross_entropy: 2.7756619453430176 +[2025-04-29 19:15:57,631][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.8893518447875977, cross_entropy: 1.8893518447875977 +[2025-04-29 19:15:59,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 1.0975627899169922, cross_entropy: 1.0975627899169922 +[2025-04-29 19:16:00,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.823887348175049, cross_entropy: 2.823887348175049 +[2025-04-29 19:16:03,140][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 2.6353964805603027, cross_entropy: 2.6353964805603027 +[2025-04-29 19:16:04,203][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.3424668312072754, cross_entropy: 2.3424668312072754 +[2025-04-29 19:16:06,327][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 0.9229737520217896, cross_entropy: 0.9229737520217896 +[2025-04-29 19:16:07,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.15959632396698, cross_entropy: 1.15959632396698 +[2025-04-29 19:16:09,988][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 1.1941967010498047, cross_entropy: 1.1941967010498047 +[2025-04-29 19:16:11,163][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.62949800491333, cross_entropy: 1.62949800491333 +[2025-04-29 19:16:13,218][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.3259549140930176, cross_entropy: 2.3259549140930176 +[2025-04-29 19:16:14,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.7519444227218628, cross_entropy: 1.7519444227218628 +[2025-04-29 19:16:17,710][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 2.1290247440338135, cross_entropy: 2.1290247440338135 +[2025-04-29 19:16:18,800][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 0.8402261734008789, cross_entropy: 0.8402261734008789 +[2025-04-29 19:16:21,756][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 1.422419786453247, cross_entropy: 1.422419786453247 +[2025-04-29 19:16:22,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.632075548171997, cross_entropy: 1.632075548171997 +[2025-04-29 19:16:25,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.149936556816101, cross_entropy: 1.149936556816101 +[2025-04-29 19:16:27,039][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 1.3260866403579712, cross_entropy: 1.3260866403579712 +[2025-04-29 19:16:29,595][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 0.7601310014724731, cross_entropy: 0.7601310014724731 +[2025-04-29 19:16:30,627][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 0.7548056840896606, cross_entropy: 0.7548056840896606 +[2025-04-29 19:16:33,266][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.1405911445617676, cross_entropy: 2.1405911445617676 +[2025-04-29 19:16:34,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 0.8432707786560059, cross_entropy: 0.8432707786560059 +[2025-04-29 19:16:37,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 1.0573480129241943, cross_entropy: 1.0573480129241943 +[2025-04-29 19:16:38,561][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 1.6750738620758057, cross_entropy: 1.6750738620758057 +[2025-04-29 19:16:41,248][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 2.2346882820129395, cross_entropy: 2.2346882820129395 +[2025-04-29 19:16:42,284][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 2.300161838531494, cross_entropy: 2.300161838531494 +[2025-04-29 19:16:45,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.6736958026885986, cross_entropy: 2.6736958026885986 +[2025-04-29 19:16:46,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 1.199959635734558, cross_entropy: 1.199959635734558 +[2025-04-29 19:16:49,852][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 1.922236442565918, cross_entropy: 1.922236442565918 +[2025-04-29 19:16:50,914][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 0.7105512619018555, cross_entropy: 0.7105512619018555 +[2025-04-29 19:16:53,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 2.913398265838623, cross_entropy: 2.913398265838623 +[2025-04-29 19:16:54,278][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 2.329779624938965, cross_entropy: 2.329779624938965 +[2025-04-29 19:16:57,448][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 1.3715660572052002, cross_entropy: 1.3715660572052002 +[2025-04-29 19:16:58,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 0.7284411191940308, cross_entropy: 0.7284411191940308 +[2025-04-29 19:17:01,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.6531938314437866, cross_entropy: 1.6531938314437866 +[2025-04-29 19:17:02,166][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 1.628587245941162, cross_entropy: 1.628587245941162 +[2025-04-29 19:17:04,841][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 0.931340217590332, cross_entropy: 0.931340217590332 +[2025-04-29 19:17:05,905][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 0.7350220680236816, cross_entropy: 0.7350220680236816 +[2025-04-29 19:17:09,075][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 1.1941741704940796, cross_entropy: 1.1941741704940796 +[2025-04-29 19:17:10,109][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.6600852012634277, cross_entropy: 1.6600852012634277 +[2025-04-29 19:17:12,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 2.554392099380493, cross_entropy: 2.554392099380493 +[2025-04-29 19:17:13,745][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 1.3352224826812744, cross_entropy: 1.3352224826812744 +[2025-04-29 19:17:17,015][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.1580712795257568, cross_entropy: 1.1580712795257568 +[2025-04-29 19:17:18,050][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 2.292903423309326, cross_entropy: 2.292903423309326 +[2025-04-29 19:17:20,827][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 1.8821349143981934, cross_entropy: 1.8821349143981934 +[2025-04-29 19:17:21,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 0.8853203058242798, cross_entropy: 0.8853203058242798 +[2025-04-29 19:17:24,492][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.8825623989105225, cross_entropy: 1.8825623989105225 +[2025-04-29 19:17:25,531][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 0.5750910043716431, cross_entropy: 0.5750910043716431 +[2025-04-29 19:17:28,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.6778066158294678, cross_entropy: 1.6778066158294678 +[2025-04-29 19:17:29,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.3428757190704346, cross_entropy: 1.3428757190704346 +[2025-04-29 19:17:31,997][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 2.6882078647613525, cross_entropy: 2.6882078647613525 +[2025-04-29 19:17:33,032][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 2.49393892288208, cross_entropy: 2.49393892288208 +[2025-04-29 19:17:36,988][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.0146546363830566, cross_entropy: 2.0146546363830566 +[2025-04-29 19:17:38,053][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 2.823543071746826, cross_entropy: 2.823543071746826 +[2025-04-29 19:17:41,571][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.5626099109649658, cross_entropy: 1.5626099109649658 +[2025-04-29 19:17:42,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 2.370382785797119, cross_entropy: 2.370382785797119 +[2025-04-29 19:17:45,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 0.8889408111572266, cross_entropy: 0.8889408111572266 +[2025-04-29 19:17:46,370][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.8983603715896606, cross_entropy: 1.8983603715896606 +[2025-04-29 19:17:48,690][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 0.7463647723197937, cross_entropy: 0.7463647723197937 +[2025-04-29 19:17:49,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 1.1273701190948486, cross_entropy: 1.1273701190948486 +[2025-04-29 19:17:52,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 1.0252264738082886, cross_entropy: 1.0252264738082886 +[2025-04-29 19:17:53,571][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 0.914747953414917, cross_entropy: 0.914747953414917 +[2025-04-29 19:17:56,511][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.2509777545928955, cross_entropy: 1.2509777545928955 +[2025-04-29 19:17:57,581][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 2.0226244926452637, cross_entropy: 2.0226244926452637 +[2025-04-29 19:18:00,444][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 0.720035195350647, cross_entropy: 0.720035195350647 +[2025-04-29 19:18:01,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 1.7808215618133545, cross_entropy: 1.7808215618133545 +[2025-04-29 19:18:04,382][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.1093404293060303, cross_entropy: 1.1093404293060303 +[2025-04-29 19:18:05,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.251169443130493, cross_entropy: 2.251169443130493 +[2025-04-29 19:18:07,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.7029922008514404, cross_entropy: 2.7029922008514404 +[2025-04-29 19:18:08,860][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 2.524989128112793, cross_entropy: 2.524989128112793 +[2025-04-29 19:18:12,188][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 2.079092025756836, cross_entropy: 2.079092025756836 +[2025-04-29 19:18:13,252][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 1.4124107360839844, cross_entropy: 1.4124107360839844 +[2025-04-29 19:18:15,699][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.515589714050293, cross_entropy: 2.515589714050293 +[2025-04-29 19:18:16,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.7110393047332764, cross_entropy: 1.7110393047332764 +[2025-04-29 19:18:19,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 2.0373566150665283, cross_entropy: 2.0373566150665283 +[2025-04-29 19:18:20,479][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 0.9431590437889099, cross_entropy: 0.9431590437889099 +[2025-04-29 19:18:23,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 1.159972906112671, cross_entropy: 1.159972906112671 +[2025-04-29 19:18:24,366][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.4443196058273315, cross_entropy: 1.4443196058273315 +[2025-04-29 19:18:27,300][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 0.7754966020584106, cross_entropy: 0.7754966020584106 +[2025-04-29 19:18:28,365][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 0.8455898761749268, cross_entropy: 0.8455898761749268 +[2025-04-29 19:18:31,486][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 2.8645858764648438, cross_entropy: 2.8645858764648438 +[2025-04-29 19:18:32,556][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.8949620723724365, cross_entropy: 2.8949620723724365 +[2025-04-29 19:18:35,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 0.7247124314308167, cross_entropy: 0.7247124314308167 +[2025-04-29 19:18:36,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 0.9649477005004883, cross_entropy: 0.9649477005004883 +[2025-04-29 19:18:38,894][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 1.558714509010315, cross_entropy: 1.558714509010315 +[2025-04-29 19:18:39,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 0.5127866268157959, cross_entropy: 0.5127866268157959 +[2025-04-29 19:18:43,573][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 1.2432105541229248, cross_entropy: 1.2432105541229248 +[2025-04-29 19:18:44,639][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.3304831981658936, cross_entropy: 1.3304831981658936 +[2025-04-29 19:18:46,707][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.1591356992721558, cross_entropy: 1.1591356992721558 +[2025-04-29 19:18:47,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.899951457977295, cross_entropy: 2.899951457977295 +[2025-04-29 19:18:50,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 2.747213125228882, cross_entropy: 2.747213125228882 +[2025-04-29 19:18:51,702][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.4543544054031372, cross_entropy: 1.4543544054031372 +[2025-04-29 19:18:54,552][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 0.8760595917701721, cross_entropy: 0.8760595917701721 +[2025-04-29 19:18:55,616][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.6998322010040283, cross_entropy: 2.6998322010040283 +[2025-04-29 19:18:58,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.8388663530349731, cross_entropy: 1.8388663530349731 +[2025-04-29 19:18:59,180][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.7870228290557861, cross_entropy: 1.7870228290557861 +[2025-04-29 19:19:02,717][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 1.9528450965881348, cross_entropy: 1.9528450965881348 +[2025-04-29 19:19:03,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 1.662825107574463, cross_entropy: 1.662825107574463 +[2025-04-29 19:19:06,280][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 1.6971328258514404, cross_entropy: 1.6971328258514404 +[2025-04-29 19:19:07,340][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 1.8694978952407837, cross_entropy: 1.8694978952407837 +[2025-04-29 19:19:09,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.5644378662109375, cross_entropy: 2.5644378662109375 +[2025-04-29 19:19:10,728][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 1.1439273357391357, cross_entropy: 1.1439273357391357 +[2025-04-29 19:19:13,626][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 1.4681169986724854, cross_entropy: 1.4681169986724854 +[2025-04-29 19:19:14,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 3.0038270950317383, cross_entropy: 3.0038270950317383 +[2025-04-29 19:19:17,696][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 0.8515489101409912, cross_entropy: 0.8515489101409912 +[2025-04-29 19:19:18,758][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 0.8932799696922302, cross_entropy: 0.8932799696922302 +[2025-04-29 19:19:21,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.0076079368591309, cross_entropy: 1.0076079368591309 +[2025-04-29 19:19:22,107][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 1.1440374851226807, cross_entropy: 1.1440374851226807 +[2025-04-29 19:19:25,098][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.4351272583007812, cross_entropy: 1.4351272583007812 +[2025-04-29 19:19:26,135][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 1.0525801181793213, cross_entropy: 1.0525801181793213 +[2025-04-29 19:19:29,021][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 1.897467017173767, cross_entropy: 1.897467017173767 +[2025-04-29 19:19:30,058][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.4859589338302612, cross_entropy: 1.4859589338302612 +[2025-04-29 19:19:32,732][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 0.8140609264373779, cross_entropy: 0.8140609264373779 +[2025-04-29 19:19:33,772][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 1.9528741836547852, cross_entropy: 1.9528741836547852 +[2025-04-29 19:19:37,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 2.737827777862549, cross_entropy: 2.737827777862549 +[2025-04-29 19:19:38,463][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 2.9959616661071777, cross_entropy: 2.9959616661071777 +[2025-04-29 19:19:41,193][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 2.150507926940918, cross_entropy: 2.150507926940918 +[2025-04-29 19:19:42,249][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 0.8914473056793213, cross_entropy: 0.8914473056793213 +[2025-04-29 19:19:45,030][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.1764501333236694, cross_entropy: 1.1764501333236694 +[2025-04-29 19:19:46,093][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 0.731498122215271, cross_entropy: 0.731498122215271 +[2025-04-29 19:19:48,827][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 2.1420252323150635, cross_entropy: 2.1420252323150635 +[2025-04-29 19:19:49,863][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 1.6101782321929932, cross_entropy: 1.6101782321929932 +[2025-04-29 19:19:53,695][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.0298519134521484, cross_entropy: 1.0298519134521484 +[2025-04-29 19:19:54,728][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 0.56368088722229, cross_entropy: 0.56368088722229 +[2025-04-29 19:19:57,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 1.8633917570114136, cross_entropy: 1.8633917570114136 +[2025-04-29 19:19:58,694][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.120800256729126, cross_entropy: 1.120800256729126 +[2025-04-29 19:20:01,559][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 1.1838963031768799, cross_entropy: 1.1838963031768799 +[2025-04-29 19:20:02,592][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 0.5639623403549194, cross_entropy: 0.5639623403549194 +[2025-04-29 19:20:05,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 0.6771844029426575, cross_entropy: 0.6771844029426575 +[2025-04-29 19:20:06,191][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 2.340928792953491, cross_entropy: 2.340928792953491 +[2025-04-29 19:20:08,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.7689859867095947, cross_entropy: 2.7689859867095947 +[2025-04-29 19:20:10,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 1.1496639251708984, cross_entropy: 1.1496639251708984 +[2025-04-29 19:20:12,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.3700041770935059, cross_entropy: 1.3700041770935059 +[2025-04-29 19:20:13,486][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 0.7651797533035278, cross_entropy: 0.7651797533035278 +[2025-04-29 19:20:16,348][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.936252236366272, cross_entropy: 1.936252236366272 +[2025-04-29 19:20:17,384][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.6639652252197266, cross_entropy: 2.6639652252197266 +[2025-04-29 19:20:21,778][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 1.3054602146148682, cross_entropy: 1.3054602146148682 +[2025-04-29 19:20:22,813][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 2.2724437713623047, cross_entropy: 2.2724437713623047 +[2025-04-29 19:20:26,091][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.6175202131271362, cross_entropy: 1.6175202131271362 +[2025-04-29 19:20:27,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 0.8224301338195801, cross_entropy: 0.8224301338195801 +[2025-04-29 19:20:30,209][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 0.7330061197280884, cross_entropy: 0.7330061197280884 +[2025-04-29 19:20:31,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.807753324508667, cross_entropy: 1.807753324508667 +[2025-04-29 19:20:34,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 2.6541595458984375, cross_entropy: 2.6541595458984375 +[2025-04-29 19:20:35,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.237476348876953, cross_entropy: 2.237476348876953 +[2025-04-29 19:20:38,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 2.1573686599731445, cross_entropy: 2.1573686599731445 +[2025-04-29 19:20:39,116][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.1692756414413452, cross_entropy: 1.1692756414413452 +[2025-04-29 19:20:41,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 2.429265260696411, cross_entropy: 2.429265260696411 +[2025-04-29 19:20:42,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 1.2815828323364258, cross_entropy: 1.2815828323364258 +[2025-04-29 19:20:45,531][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 2.6028056144714355, cross_entropy: 2.6028056144714355 +[2025-04-29 19:20:46,597][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.1973199844360352, cross_entropy: 1.1973199844360352 +[2025-04-29 19:20:49,605][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.8465261459350586, cross_entropy: 2.8465261459350586 +[2025-04-29 19:20:50,668][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 0.7173793911933899, cross_entropy: 0.7173793911933899 +[2025-04-29 19:20:53,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.435882329940796, cross_entropy: 1.435882329940796 +[2025-04-29 19:20:54,211][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.4901716709136963, cross_entropy: 2.4901716709136963 +[2025-04-29 19:20:56,755][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 0.9671889543533325, cross_entropy: 0.9671889543533325 +[2025-04-29 19:20:57,834][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 2.5381360054016113, cross_entropy: 2.5381360054016113 +[2025-04-29 19:20:59,921][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 0.8207542896270752, cross_entropy: 0.8207542896270752 +[2025-04-29 19:21:00,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 0.9002089500427246, cross_entropy: 0.9002089500427246 +[2025-04-29 19:21:03,259][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 0.8317355513572693, cross_entropy: 0.8317355513572693 +[2025-04-29 19:21:04,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 2.120468854904175, cross_entropy: 2.120468854904175 +[2025-04-29 19:21:07,077][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 2.777865171432495, cross_entropy: 2.777865171432495 +[2025-04-29 19:21:08,147][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 0.8310211896896362, cross_entropy: 0.8310211896896362 +[2025-04-29 19:21:11,039][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 2.4785866737365723, cross_entropy: 2.4785866737365723 +[2025-04-29 19:21:12,108][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 0.8160523176193237, cross_entropy: 0.8160523176193237 +[2025-04-29 19:21:14,832][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.2085275650024414, cross_entropy: 1.2085275650024414 +[2025-04-29 19:21:15,899][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 1.6958105564117432, cross_entropy: 1.6958105564117432 +[2025-04-29 19:21:18,351][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.6716437339782715, cross_entropy: 2.6716437339782715 +[2025-04-29 19:21:19,387][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 1.8609840869903564, cross_entropy: 1.8609840869903564 +[2025-04-29 19:21:22,488][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 2.5928282737731934, cross_entropy: 2.5928282737731934 +[2025-04-29 19:21:23,550][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 1.611119270324707, cross_entropy: 1.611119270324707 +[2025-04-29 19:21:26,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 0.573999285697937, cross_entropy: 0.573999285697937 +[2025-04-29 19:21:27,361][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 3.175123929977417, cross_entropy: 3.175123929977417 +[2025-04-29 19:21:30,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 1.9050233364105225, cross_entropy: 1.9050233364105225 +[2025-04-29 19:21:31,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 0.7444971203804016, cross_entropy: 0.7444971203804016 +[2025-04-29 19:21:33,957][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 2.733891487121582, cross_entropy: 2.733891487121582 +[2025-04-29 19:21:35,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 0.7219144701957703, cross_entropy: 0.7219144701957703 +[2025-04-29 19:21:37,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 2.0370075702667236, cross_entropy: 2.0370075702667236 +[2025-04-29 19:21:39,063][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.1649376153945923, cross_entropy: 1.1649376153945923 +[2025-04-29 19:21:41,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 2.470402717590332, cross_entropy: 2.470402717590332 +[2025-04-29 19:21:43,006][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 0.6746203899383545, cross_entropy: 0.6746203899383545 +[2025-04-29 19:21:45,120][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 0.6579264402389526, cross_entropy: 0.6579264402389526 +[2025-04-29 19:21:46,568][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 3.0789968967437744, cross_entropy: 3.0789968967437744 +[2025-04-29 19:21:48,886][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 0.5865973830223083, cross_entropy: 0.5865973830223083 +[2025-04-29 19:21:49,985][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.689232349395752, cross_entropy: 2.689232349395752 +[2025-04-29 19:21:53,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.2846710681915283, cross_entropy: 1.2846710681915283 +[2025-04-29 19:21:54,456][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 1.231380820274353, cross_entropy: 1.231380820274353 +[2025-04-29 19:21:57,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 0.9621495604515076, cross_entropy: 0.9621495604515076 +[2025-04-29 19:21:58,698][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 0.7602545022964478, cross_entropy: 0.7602545022964478 +[2025-04-29 19:22:02,108][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.584815502166748, cross_entropy: 2.584815502166748 +[2025-04-29 19:22:03,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 1.1964683532714844, cross_entropy: 1.1964683532714844 +[2025-04-29 19:22:05,638][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.949523448944092, cross_entropy: 2.949523448944092 +[2025-04-29 19:22:06,702][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 0.8252551555633545, cross_entropy: 0.8252551555633545 +[2025-04-29 19:22:09,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.9541645050048828, cross_entropy: 1.9541645050048828 +[2025-04-29 19:22:10,722][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 2.7640247344970703, cross_entropy: 2.7640247344970703 +[2025-04-29 19:22:13,267][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.7527375221252441, cross_entropy: 1.7527375221252441 +[2025-04-29 19:22:14,303][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 2.517921209335327, cross_entropy: 2.517921209335327 +[2025-04-29 19:22:17,182][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 1.0858309268951416, cross_entropy: 1.0858309268951416 +[2025-04-29 19:22:18,219][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 1.4924321174621582, cross_entropy: 1.4924321174621582 +[2025-04-29 19:22:21,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 0.9912152290344238, cross_entropy: 0.9912152290344238 +[2025-04-29 19:22:22,490][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.4465208053588867, cross_entropy: 2.4465208053588867 +[2025-04-29 19:22:24,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 2.760158061981201, cross_entropy: 2.760158061981201 +[2025-04-29 19:22:25,576][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 0.7855100631713867, cross_entropy: 0.7855100631713867 +[2025-04-29 19:22:28,228][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 0.8824010491371155, cross_entropy: 0.8824010491371155 +[2025-04-29 19:22:29,272][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.049976110458374, cross_entropy: 1.049976110458374 +[2025-04-29 19:22:32,284][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 0.7088731527328491, cross_entropy: 0.7088731527328491 +[2025-04-29 19:22:33,344][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.5910720825195312, cross_entropy: 2.5910720825195312 +[2025-04-29 19:22:36,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.7357380390167236, cross_entropy: 2.7357380390167236 +[2025-04-29 19:22:37,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 0.8212330937385559, cross_entropy: 0.8212330937385559 +[2025-04-29 19:22:39,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.8585903644561768, cross_entropy: 1.8585903644561768 +[2025-04-29 19:22:40,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 0.9101529121398926, cross_entropy: 0.9101529121398926 +[2025-04-29 19:22:43,668][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 0.9891964197158813, cross_entropy: 0.9891964197158813 +[2025-04-29 19:22:44,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 2.819672107696533, cross_entropy: 2.819672107696533 +[2025-04-29 19:22:47,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.1340829133987427, cross_entropy: 1.1340829133987427 +[2025-04-29 19:22:48,457][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.4528393745422363, cross_entropy: 1.4528393745422363 +[2025-04-29 19:22:51,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.914482831954956, cross_entropy: 2.914482831954956 +[2025-04-29 19:22:52,299][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 2.122450113296509, cross_entropy: 2.122450113296509 +[2025-04-29 19:22:55,036][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 2.610959768295288, cross_entropy: 2.610959768295288 +[2025-04-29 19:22:56,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 1.180856466293335, cross_entropy: 1.180856466293335 +[2025-04-29 19:22:59,782][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 1.7483267784118652, cross_entropy: 1.7483267784118652 +[2025-04-29 19:23:00,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.024444341659546, cross_entropy: 1.024444341659546 +[2025-04-29 19:23:03,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 1.5196272134780884, cross_entropy: 1.5196272134780884 +[2025-04-29 19:23:04,468][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 1.107497215270996, cross_entropy: 1.107497215270996 +[2025-04-29 19:23:07,181][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.5619759559631348, cross_entropy: 2.5619759559631348 +[2025-04-29 19:23:08,247][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.656203269958496, cross_entropy: 1.656203269958496 +[2025-04-29 19:23:11,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.6481995582580566, cross_entropy: 2.6481995582580566 +[2025-04-29 19:23:12,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 3.0191872119903564, cross_entropy: 3.0191872119903564 +[2025-04-29 19:23:15,070][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.3756513595581055, cross_entropy: 1.3756513595581055 +[2025-04-29 19:23:16,105][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 1.8365402221679688, cross_entropy: 1.8365402221679688 +[2025-04-29 19:23:19,078][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 0.7206438779830933, cross_entropy: 0.7206438779830933 +[2025-04-29 19:23:20,144][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.877528429031372, cross_entropy: 1.877528429031372 +[2025-04-29 19:23:23,090][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.8846831321716309, cross_entropy: 1.8846831321716309 +[2025-04-29 19:23:24,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 0.9845458269119263, cross_entropy: 0.9845458269119263 +[2025-04-29 19:23:26,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.7662532329559326, cross_entropy: 2.7662532329559326 +[2025-04-29 19:23:27,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.5149281024932861, cross_entropy: 1.5149281024932861 +[2025-04-29 19:23:30,376][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 0.9303852915763855, cross_entropy: 0.9303852915763855 +[2025-04-29 19:23:31,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.759315252304077, cross_entropy: 2.759315252304077 +[2025-04-29 19:23:34,463][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.8323380947113037, cross_entropy: 1.8323380947113037 +[2025-04-29 19:23:35,501][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 2.673135280609131, cross_entropy: 2.673135280609131 +[2025-04-29 19:23:38,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 2.32246994972229, cross_entropy: 2.32246994972229 +[2025-04-29 19:23:39,552][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.594632625579834, cross_entropy: 2.594632625579834 +[2025-04-29 19:23:41,955][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.4749488830566406, cross_entropy: 1.4749488830566406 +[2025-04-29 19:23:43,024][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 0.8935225605964661, cross_entropy: 0.8935225605964661 +[2025-04-29 19:23:46,010][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 0.8826062679290771, cross_entropy: 0.8826062679290771 +[2025-04-29 19:23:47,074][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.273646593093872, cross_entropy: 1.273646593093872 +[2025-04-29 19:23:50,023][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 0.45164456963539124, cross_entropy: 0.45164456963539124 +[2025-04-29 19:23:51,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 2.605985164642334, cross_entropy: 2.605985164642334 +[2025-04-29 19:23:53,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.3904953002929688, cross_entropy: 2.3904953002929688 +[2025-04-29 19:23:55,042][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 1.4238452911376953, cross_entropy: 1.4238452911376953 +[2025-04-29 19:23:57,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 3.048196315765381, cross_entropy: 3.048196315765381 +[2025-04-29 19:23:58,767][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 2.647502899169922, cross_entropy: 2.647502899169922 +[2025-04-29 19:24:01,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.1457724571228027, cross_entropy: 2.1457724571228027 +[2025-04-29 19:24:02,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 0.8715388774871826, cross_entropy: 0.8715388774871826 +[2025-04-29 19:24:05,366][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.3026542663574219, cross_entropy: 1.3026542663574219 +[2025-04-29 19:24:06,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.3188250064849854, cross_entropy: 1.3188250064849854 +[2025-04-29 19:24:08,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.567663550376892, cross_entropy: 1.567663550376892 +[2025-04-29 19:24:09,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.1783552169799805, cross_entropy: 2.1783552169799805 +[2025-04-29 19:24:13,177][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 2.581435441970825, cross_entropy: 2.581435441970825 +[2025-04-29 19:24:14,211][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.6622135639190674, cross_entropy: 2.6622135639190674 +[2025-04-29 19:24:17,666][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 1.2620699405670166, cross_entropy: 1.2620699405670166 +[2025-04-29 19:24:18,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.3311307430267334, cross_entropy: 2.3311307430267334 +[2025-04-29 19:24:21,755][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 2.936234474182129, cross_entropy: 2.936234474182129 +[2025-04-29 19:24:22,819][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.2810816764831543, cross_entropy: 1.2810816764831543 +[2025-04-29 19:24:25,171][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.0903778076171875, cross_entropy: 1.0903778076171875 +[2025-04-29 19:24:26,244][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.8164653778076172, cross_entropy: 1.8164653778076172 +[2025-04-29 19:24:29,300][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 2.089423656463623, cross_entropy: 2.089423656463623 +[2025-04-29 19:24:30,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.9719840288162231, cross_entropy: 1.9719840288162231 +[2025-04-29 19:24:33,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.3864021301269531, cross_entropy: 1.3864021301269531 +[2025-04-29 19:24:34,311][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.7923015356063843, cross_entropy: 1.7923015356063843 +[2025-04-29 19:24:37,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 2.981600522994995, cross_entropy: 2.981600522994995 +[2025-04-29 19:24:38,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 0.852153480052948, cross_entropy: 0.852153480052948 +[2025-04-29 19:24:40,447][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.1440305709838867, cross_entropy: 2.1440305709838867 +[2025-04-29 19:24:41,756][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 0.7982249855995178, cross_entropy: 0.7982249855995178 +[2025-04-29 19:24:43,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 2.929115056991577, cross_entropy: 2.929115056991577 +[2025-04-29 19:24:45,207][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.266416549682617, cross_entropy: 2.266416549682617 +[2025-04-29 19:24:47,604][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 2.477905750274658, cross_entropy: 2.477905750274658 +[2025-04-29 19:24:50,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 1.487703561782837, cross_entropy: 1.487703561782837 +[2025-04-29 19:24:51,110][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 2.4259676933288574, cross_entropy: 2.4259676933288574 +[2025-04-29 19:24:53,904][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.8765654563903809, cross_entropy: 1.8765654563903809 +[2025-04-29 19:24:54,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.3349525928497314, cross_entropy: 1.3349525928497314 +[2025-04-29 19:24:57,776][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 0.6153907775878906, cross_entropy: 0.6153907775878906 +[2025-04-29 19:24:59,227][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 2.405651807785034, cross_entropy: 2.405651807785034 +[2025-04-29 19:25:02,011][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.6396366357803345, cross_entropy: 1.6396366357803345 +[2025-04-29 19:25:03,097][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.856889247894287, cross_entropy: 2.856889247894287 +[2025-04-29 19:25:05,634][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.806807279586792, cross_entropy: 1.806807279586792 +[2025-04-29 19:25:06,731][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 2.6960973739624023, cross_entropy: 2.6960973739624023 +[2025-04-29 19:25:10,355][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.3246041536331177, cross_entropy: 1.3246041536331177 +[2025-04-29 19:25:11,439][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.0590083599090576, cross_entropy: 1.0590083599090576 +[2025-04-29 19:25:14,832][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 2.433529853820801, cross_entropy: 2.433529853820801 +[2025-04-29 19:25:15,868][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 0.8416159749031067, cross_entropy: 0.8416159749031067 +[2025-04-29 19:25:18,934][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.3746275901794434, cross_entropy: 2.3746275901794434 +[2025-04-29 19:25:19,970][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 1.4665541648864746, cross_entropy: 1.4665541648864746 +[2025-04-29 19:25:23,270][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.8034669160842896, cross_entropy: 1.8034669160842896 +[2025-04-29 19:25:24,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.651094436645508, cross_entropy: 2.651094436645508 +[2025-04-29 19:25:26,971][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.7819532752037048, cross_entropy: 0.7819532752037048 +[2025-04-29 19:25:28,032][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 3.0285556316375732, cross_entropy: 3.0285556316375732 +[2025-04-29 19:25:31,078][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.3273385763168335, cross_entropy: 1.3273385763168335 +[2025-04-29 19:25:32,112][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 2.6440439224243164, cross_entropy: 2.6440439224243164 +[2025-04-29 19:25:35,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 1.1678247451782227, cross_entropy: 1.1678247451782227 +[2025-04-29 19:25:36,372][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 2.3163018226623535, cross_entropy: 2.3163018226623535 +[2025-04-29 19:25:39,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 2.2563252449035645, cross_entropy: 2.2563252449035645 +[2025-04-29 19:25:40,821][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 0.9401453733444214, cross_entropy: 0.9401453733444214 +[2025-04-29 19:25:44,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 2.47921085357666, cross_entropy: 2.47921085357666 +[2025-04-29 19:25:45,093][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.7037291526794434, cross_entropy: 1.7037291526794434 +[2025-04-29 19:25:47,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 2.831958532333374, cross_entropy: 2.831958532333374 +[2025-04-29 19:25:48,280][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 2.3199057579040527, cross_entropy: 2.3199057579040527 +[2025-04-29 19:25:49,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.311194896697998, cross_entropy: 2.311194896697998 +[2025-04-29 19:28:37,542][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.7151345014572144, cross_entropy: 1.7151345014572144 +[2025-04-29 19:28:37,543][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.092358946800232, cross_entropy: 1.092358946800232 +[2025-04-29 19:28:38,429][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 19:28:38,910][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch7.pth. +[2025-04-29 19:28:39,702][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 19:28:44,652][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 0.7361629605293274, cross_entropy: 0.7361629605293274 +[2025-04-29 19:28:45,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 1.1459288597106934, cross_entropy: 1.1459288597106934 +[2025-04-29 19:28:49,202][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.102815866470337, cross_entropy: 1.102815866470337 +[2025-04-29 19:28:50,265][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.3372912406921387, cross_entropy: 2.3372912406921387 +[2025-04-29 19:28:53,267][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.4889397621154785, cross_entropy: 1.4889397621154785 +[2025-04-29 19:28:54,584][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 2.5295515060424805, cross_entropy: 2.5295515060424805 +[2025-04-29 19:28:57,884][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.8645580410957336, cross_entropy: 0.8645580410957336 +[2025-04-29 19:28:58,970][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.1123616695404053, cross_entropy: 2.1123616695404053 +[2025-04-29 19:29:01,923][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.5347981452941895, cross_entropy: 1.5347981452941895 +[2025-04-29 19:29:03,120][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.9422401189804077, cross_entropy: 1.9422401189804077 +[2025-04-29 19:29:05,349][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 0.6564199924468994, cross_entropy: 0.6564199924468994 +[2025-04-29 19:29:06,799][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.8647477626800537, cross_entropy: 0.8647477626800537 +[2025-04-29 19:29:10,219][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 2.0936484336853027, cross_entropy: 2.0936484336853027 +[2025-04-29 19:29:11,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.0675671100616455, cross_entropy: 2.0675671100616455 +[2025-04-29 19:29:15,679][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 1.4539759159088135, cross_entropy: 1.4539759159088135 +[2025-04-29 19:29:16,742][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 2.2758913040161133, cross_entropy: 2.2758913040161133 +[2025-04-29 19:29:20,834][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 1.024324893951416, cross_entropy: 1.024324893951416 +[2025-04-29 19:29:21,897][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 0.9195432662963867, cross_entropy: 0.9195432662963867 +[2025-04-29 19:29:25,089][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 1.1546660661697388, cross_entropy: 1.1546660661697388 +[2025-04-29 19:29:26,146][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.9294415712356567, cross_entropy: 1.9294415712356567 +[2025-04-29 19:29:29,323][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 0.6042361855506897, cross_entropy: 0.6042361855506897 +[2025-04-29 19:29:30,379][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 1.204879879951477, cross_entropy: 1.204879879951477 +[2025-04-29 19:29:32,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.104587197303772, cross_entropy: 1.104587197303772 +[2025-04-29 19:29:33,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 0.9107397794723511, cross_entropy: 0.9107397794723511 +[2025-04-29 19:29:36,816][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 1.608799695968628, cross_entropy: 1.608799695968628 +[2025-04-29 19:29:37,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 0.9702019691467285, cross_entropy: 0.9702019691467285 +[2025-04-29 19:29:40,785][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.9219063520431519, cross_entropy: 0.9219063520431519 +[2025-04-29 19:29:41,820][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 0.8104822039604187, cross_entropy: 0.8104822039604187 +[2025-04-29 19:29:45,210][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 2.279201030731201, cross_entropy: 2.279201030731201 +[2025-04-29 19:29:46,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 0.9733643531799316, cross_entropy: 0.9733643531799316 +[2025-04-29 19:29:48,897][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.8947341442108154, cross_entropy: 0.8947341442108154 +[2025-04-29 19:29:49,930][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 0.8723437786102295, cross_entropy: 0.8723437786102295 +[2025-04-29 19:29:53,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 0.772060751914978, cross_entropy: 0.772060751914978 +[2025-04-29 19:29:54,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 0.8972145915031433, cross_entropy: 0.8972145915031433 +[2025-04-29 19:29:56,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 1.0284626483917236, cross_entropy: 1.0284626483917236 +[2025-04-29 19:29:57,675][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 0.944652795791626, cross_entropy: 0.944652795791626 +[2025-04-29 19:30:00,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.492929458618164, cross_entropy: 2.492929458618164 +[2025-04-29 19:30:01,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.529489517211914, cross_entropy: 2.529489517211914 +[2025-04-29 19:30:03,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.8367382287979126, cross_entropy: 1.8367382287979126 +[2025-04-29 19:30:04,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.4976582527160645, cross_entropy: 1.4976582527160645 +[2025-04-29 19:30:07,246][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 0.8089720010757446, cross_entropy: 0.8089720010757446 +[2025-04-29 19:30:08,304][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.2444312572479248, cross_entropy: 1.2444312572479248 +[2025-04-29 19:30:11,030][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 2.7028112411499023, cross_entropy: 2.7028112411499023 +[2025-04-29 19:30:12,064][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 2.7139151096343994, cross_entropy: 2.7139151096343994 +[2025-04-29 19:30:15,302][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 0.989543080329895, cross_entropy: 0.989543080329895 +[2025-04-29 19:30:16,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.017308235168457, cross_entropy: 2.017308235168457 +[2025-04-29 19:30:18,775][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 0.8423032760620117, cross_entropy: 0.8423032760620117 +[2025-04-29 19:30:19,808][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 1.5108160972595215, cross_entropy: 1.5108160972595215 +[2025-04-29 19:30:22,658][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.169384002685547, cross_entropy: 2.169384002685547 +[2025-04-29 19:30:23,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 1.129556655883789, cross_entropy: 1.129556655883789 +[2025-04-29 19:30:27,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.462329864501953, cross_entropy: 2.462329864501953 +[2025-04-29 19:30:28,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 2.5172276496887207, cross_entropy: 2.5172276496887207 +[2025-04-29 19:30:31,028][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.9285891652107239, cross_entropy: 0.9285891652107239 +[2025-04-29 19:30:32,062][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.6585755348205566, cross_entropy: 1.6585755348205566 +[2025-04-29 19:30:35,338][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 1.6981754302978516, cross_entropy: 1.6981754302978516 +[2025-04-29 19:30:36,410][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 2.2667746543884277, cross_entropy: 2.2667746543884277 +[2025-04-29 19:30:38,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 0.5966268181800842, cross_entropy: 0.5966268181800842 +[2025-04-29 19:30:39,885][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 0.6458328366279602, cross_entropy: 0.6458328366279602 +[2025-04-29 19:30:42,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 1.7063121795654297, cross_entropy: 1.7063121795654297 +[2025-04-29 19:30:43,667][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.99799644947052, cross_entropy: 0.99799644947052 +[2025-04-29 19:30:46,189][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 0.6612673997879028, cross_entropy: 0.6612673997879028 +[2025-04-29 19:30:47,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 2.3421173095703125, cross_entropy: 2.3421173095703125 +[2025-04-29 19:30:50,178][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.3960118293762207, cross_entropy: 2.3960118293762207 +[2025-04-29 19:30:51,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 1.8809030055999756, cross_entropy: 1.8809030055999756 +[2025-04-29 19:30:54,042][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.534489631652832, cross_entropy: 2.534489631652832 +[2025-04-29 19:30:55,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 1.9990960359573364, cross_entropy: 1.9990960359573364 +[2025-04-29 19:30:58,318][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.3546032905578613, cross_entropy: 2.3546032905578613 +[2025-04-29 19:30:59,371][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 0.6470904350280762, cross_entropy: 0.6470904350280762 +[2025-04-29 19:31:02,408][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 0.9647215604782104, cross_entropy: 0.9647215604782104 +[2025-04-29 19:31:03,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 0.6585419178009033, cross_entropy: 0.6585419178009033 +[2025-04-29 19:31:06,038][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.7286478281021118, cross_entropy: 1.7286478281021118 +[2025-04-29 19:31:07,078][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 0.7500734329223633, cross_entropy: 0.7500734329223633 +[2025-04-29 19:31:09,347][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.1066908836364746, cross_entropy: 1.1066908836364746 +[2025-04-29 19:31:10,398][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.0574054718017578, cross_entropy: 1.0574054718017578 +[2025-04-29 19:31:13,011][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 0.8949432373046875, cross_entropy: 0.8949432373046875 +[2025-04-29 19:31:14,078][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.390547275543213, cross_entropy: 2.390547275543213 +[2025-04-29 19:31:16,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.1733791828155518, cross_entropy: 1.1733791828155518 +[2025-04-29 19:31:17,453][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.1454802751541138, cross_entropy: 1.1454802751541138 +[2025-04-29 19:31:20,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 0.7684595584869385, cross_entropy: 0.7684595584869385 +[2025-04-29 19:31:21,530][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 1.256941795349121, cross_entropy: 1.256941795349121 +[2025-04-29 19:31:24,074][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 0.675104558467865, cross_entropy: 0.675104558467865 +[2025-04-29 19:31:25,107][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.4099223613739014, cross_entropy: 1.4099223613739014 +[2025-04-29 19:31:27,535][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 1.413187861442566, cross_entropy: 1.413187861442566 +[2025-04-29 19:31:28,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.8450429439544678, cross_entropy: 1.8450429439544678 +[2025-04-29 19:31:31,094][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 0.8900248408317566, cross_entropy: 0.8900248408317566 +[2025-04-29 19:31:32,199][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 1.7917232513427734, cross_entropy: 1.7917232513427734 +[2025-04-29 19:31:35,779][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.490718364715576, cross_entropy: 2.490718364715576 +[2025-04-29 19:31:36,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.075901508331299, cross_entropy: 2.075901508331299 +[2025-04-29 19:31:39,374][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 2.4908885955810547, cross_entropy: 2.4908885955810547 +[2025-04-29 19:31:40,405][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 2.99396014213562, cross_entropy: 2.99396014213562 +[2025-04-29 19:31:43,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.891394853591919, cross_entropy: 2.891394853591919 +[2025-04-29 19:31:44,407][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 2.6938657760620117, cross_entropy: 2.6938657760620117 +[2025-04-29 19:31:46,968][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 2.752833843231201, cross_entropy: 2.752833843231201 +[2025-04-29 19:31:48,000][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.502060890197754, cross_entropy: 2.502060890197754 +[2025-04-29 19:31:50,930][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 2.697399139404297, cross_entropy: 2.697399139404297 +[2025-04-29 19:31:52,081][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 2.5017642974853516, cross_entropy: 2.5017642974853516 +[2025-04-29 19:31:54,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.6809988021850586, cross_entropy: 2.6809988021850586 +[2025-04-29 19:31:55,415][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 0.6906062364578247, cross_entropy: 0.6906062364578247 +[2025-04-29 19:31:58,426][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.4615017175674438, cross_entropy: 1.4615017175674438 +[2025-04-29 19:31:59,530][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.1966568231582642, cross_entropy: 1.1966568231582642 +[2025-04-29 19:32:02,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.673664093017578, cross_entropy: 2.673664093017578 +[2025-04-29 19:32:03,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 1.5520297288894653, cross_entropy: 1.5520297288894653 +[2025-04-29 19:32:06,734][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.208003520965576, cross_entropy: 2.208003520965576 +[2025-04-29 19:32:07,798][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 2.3616716861724854, cross_entropy: 2.3616716861724854 +[2025-04-29 19:32:10,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 0.7628154754638672, cross_entropy: 0.7628154754638672 +[2025-04-29 19:32:11,768][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 0.6887719631195068, cross_entropy: 0.6887719631195068 +[2025-04-29 19:32:14,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 0.7489703893661499, cross_entropy: 0.7489703893661499 +[2025-04-29 19:32:15,511][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 0.7351316213607788, cross_entropy: 0.7351316213607788 +[2025-04-29 19:32:18,819][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.1899484395980835, cross_entropy: 1.1899484395980835 +[2025-04-29 19:32:19,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.380373477935791, cross_entropy: 2.380373477935791 +[2025-04-29 19:32:22,288][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 0.9991920590400696, cross_entropy: 0.9991920590400696 +[2025-04-29 19:32:23,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 0.7237732410430908, cross_entropy: 0.7237732410430908 +[2025-04-29 19:32:26,191][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 0.7269490957260132, cross_entropy: 0.7269490957260132 +[2025-04-29 19:32:27,225][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 2.2978403568267822, cross_entropy: 2.2978403568267822 +[2025-04-29 19:32:30,219][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 1.1706658601760864, cross_entropy: 1.1706658601760864 +[2025-04-29 19:32:31,265][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 2.508741855621338, cross_entropy: 2.508741855621338 +[2025-04-29 19:32:34,192][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 1.3507736921310425, cross_entropy: 1.3507736921310425 +[2025-04-29 19:32:35,253][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.0521628856658936, cross_entropy: 1.0521628856658936 +[2025-04-29 19:32:38,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 1.0387639999389648, cross_entropy: 1.0387639999389648 +[2025-04-29 19:32:39,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 0.9122554063796997, cross_entropy: 0.9122554063796997 +[2025-04-29 19:32:41,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 1.8558541536331177, cross_entropy: 1.8558541536331177 +[2025-04-29 19:32:42,682][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 0.8163952827453613, cross_entropy: 0.8163952827453613 +[2025-04-29 19:32:44,879][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 0.854874849319458, cross_entropy: 0.854874849319458 +[2025-04-29 19:32:46,674][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.485754132270813, cross_entropy: 1.485754132270813 +[2025-04-29 19:32:47,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.7590534687042236, cross_entropy: 1.7590534687042236 +[2025-04-29 19:32:50,527][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.7520191669464111, cross_entropy: 1.7520191669464111 +[2025-04-29 19:32:51,618][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 1.4246561527252197, cross_entropy: 1.4246561527252197 +[2025-04-29 19:32:54,139][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 0.5599740743637085, cross_entropy: 0.5599740743637085 +[2025-04-29 19:32:55,227][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.5041929483413696, cross_entropy: 1.5041929483413696 +[2025-04-29 19:32:57,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 2.518991231918335, cross_entropy: 2.518991231918335 +[2025-04-29 19:32:58,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 0.5425281524658203, cross_entropy: 0.5425281524658203 +[2025-04-29 19:33:00,993][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 0.8507726192474365, cross_entropy: 0.8507726192474365 +[2025-04-29 19:33:02,436][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 0.978208065032959, cross_entropy: 0.978208065032959 +[2025-04-29 19:33:05,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.4013586044311523, cross_entropy: 1.4013586044311523 +[2025-04-29 19:33:06,269][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.7370011806488037, cross_entropy: 2.7370011806488037 +[2025-04-29 19:33:09,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 1.1355266571044922, cross_entropy: 1.1355266571044922 +[2025-04-29 19:33:10,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 1.0231208801269531, cross_entropy: 1.0231208801269531 +[2025-04-29 19:33:13,365][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 1.2705495357513428, cross_entropy: 1.2705495357513428 +[2025-04-29 19:33:14,453][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 1.1960651874542236, cross_entropy: 1.1960651874542236 +[2025-04-29 19:33:16,792][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 2.429762363433838, cross_entropy: 2.429762363433838 +[2025-04-29 19:33:17,869][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 1.0260429382324219, cross_entropy: 1.0260429382324219 +[2025-04-29 19:33:21,112][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.503188133239746, cross_entropy: 2.503188133239746 +[2025-04-29 19:33:22,228][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.002096176147461, cross_entropy: 1.002096176147461 +[2025-04-29 19:33:24,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.3411026000976562, cross_entropy: 2.3411026000976562 +[2025-04-29 19:33:25,709][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 1.0430623292922974, cross_entropy: 1.0430623292922974 +[2025-04-29 19:33:28,678][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 1.1715939044952393, cross_entropy: 1.1715939044952393 +[2025-04-29 19:33:29,924][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.849111557006836, cross_entropy: 1.849111557006836 +[2025-04-29 19:33:32,525][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 2.6059584617614746, cross_entropy: 2.6059584617614746 +[2025-04-29 19:33:33,624][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 2.7970170974731445, cross_entropy: 2.7970170974731445 +[2025-04-29 19:33:36,387][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 0.7180609703063965, cross_entropy: 0.7180609703063965 +[2025-04-29 19:33:37,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 1.5541815757751465, cross_entropy: 1.5541815757751465 +[2025-04-29 19:33:39,785][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 2.652116298675537, cross_entropy: 2.652116298675537 +[2025-04-29 19:33:41,221][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.6705513000488281, cross_entropy: 1.6705513000488281 +[2025-04-29 19:33:43,676][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.4335861206054688, cross_entropy: 1.4335861206054688 +[2025-04-29 19:33:44,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 0.6181306838989258, cross_entropy: 0.6181306838989258 +[2025-04-29 19:33:47,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.4805068969726562, cross_entropy: 1.4805068969726562 +[2025-04-29 19:33:48,931][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 0.8361779451370239, cross_entropy: 0.8361779451370239 +[2025-04-29 19:33:51,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 1.4617172479629517, cross_entropy: 1.4617172479629517 +[2025-04-29 19:33:52,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 1.0499004125595093, cross_entropy: 1.0499004125595093 +[2025-04-29 19:33:54,925][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 0.8867148160934448, cross_entropy: 0.8867148160934448 +[2025-04-29 19:33:56,097][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 2.2408411502838135, cross_entropy: 2.2408411502838135 +[2025-04-29 19:33:59,362][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 2.503617286682129, cross_entropy: 2.503617286682129 +[2025-04-29 19:34:00,539][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 1.1779801845550537, cross_entropy: 1.1779801845550537 +[2025-04-29 19:34:03,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 1.7017760276794434, cross_entropy: 1.7017760276794434 +[2025-04-29 19:34:04,248][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.5282950401306152, cross_entropy: 2.5282950401306152 +[2025-04-29 19:34:06,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.182674527168274, cross_entropy: 1.182674527168274 +[2025-04-29 19:34:08,049][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 1.6622939109802246, cross_entropy: 1.6622939109802246 +[2025-04-29 19:34:10,461][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 1.0747990608215332, cross_entropy: 1.0747990608215332 +[2025-04-29 19:34:13,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.832949638366699, cross_entropy: 2.832949638366699 +[2025-04-29 19:34:15,033][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.132096767425537, cross_entropy: 1.132096767425537 +[2025-04-29 19:34:17,852][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.2914793491363525, cross_entropy: 1.2914793491363525 +[2025-04-29 19:34:18,972][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 0.868639349937439, cross_entropy: 0.868639349937439 +[2025-04-29 19:34:21,697][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.726666212081909, cross_entropy: 2.726666212081909 +[2025-04-29 19:34:23,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 2.6846556663513184, cross_entropy: 2.6846556663513184 +[2025-04-29 19:34:26,095][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 1.4599981307983398, cross_entropy: 1.4599981307983398 +[2025-04-29 19:34:27,204][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.9159163236618042, cross_entropy: 0.9159163236618042 +[2025-04-29 19:34:29,744][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 0.535800576210022, cross_entropy: 0.535800576210022 +[2025-04-29 19:34:30,829][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.4954020977020264, cross_entropy: 2.4954020977020264 +[2025-04-29 19:34:33,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.7801265716552734, cross_entropy: 1.7801265716552734 +[2025-04-29 19:34:35,747][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.4356822967529297, cross_entropy: 2.4356822967529297 +[2025-04-29 19:34:37,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.1482725143432617, cross_entropy: 2.1482725143432617 +[2025-04-29 19:34:39,579][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 1.1455907821655273, cross_entropy: 1.1455907821655273 +[2025-04-29 19:34:42,262][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 0.6821355819702148, cross_entropy: 0.6821355819702148 +[2025-04-29 19:34:43,388][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 0.6456149816513062, cross_entropy: 0.6456149816513062 +[2025-04-29 19:34:46,267][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 1.583434820175171, cross_entropy: 1.583434820175171 +[2025-04-29 19:34:47,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 0.866248607635498, cross_entropy: 0.866248607635498 +[2025-04-29 19:34:50,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 2.7369003295898438, cross_entropy: 2.7369003295898438 +[2025-04-29 19:34:51,401][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 2.1389811038970947, cross_entropy: 2.1389811038970947 +[2025-04-29 19:34:54,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 0.8348289728164673, cross_entropy: 0.8348289728164673 +[2025-04-29 19:34:55,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 1.1416106224060059, cross_entropy: 1.1416106224060059 +[2025-04-29 19:34:58,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.5719523429870605, cross_entropy: 2.5719523429870605 +[2025-04-29 19:34:59,448][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.0923711061477661, cross_entropy: 1.0923711061477661 +[2025-04-29 19:35:02,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 0.8557441234588623, cross_entropy: 0.8557441234588623 +[2025-04-29 19:35:03,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 0.6119014620780945, cross_entropy: 0.6119014620780945 +[2025-04-29 19:35:06,154][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 1.8154489994049072, cross_entropy: 1.8154489994049072 +[2025-04-29 19:35:07,236][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 0.7646539211273193, cross_entropy: 0.7646539211273193 +[2025-04-29 19:35:09,151][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 0.9305912852287292, cross_entropy: 0.9305912852287292 +[2025-04-29 19:35:10,456][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 0.7629595994949341, cross_entropy: 0.7629595994949341 +[2025-04-29 19:35:13,062][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 1.925105094909668, cross_entropy: 1.925105094909668 +[2025-04-29 19:35:14,190][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.314849853515625, cross_entropy: 1.314849853515625 +[2025-04-29 19:35:17,385][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.8256077766418457, cross_entropy: 1.8256077766418457 +[2025-04-29 19:35:18,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 1.3907501697540283, cross_entropy: 1.3907501697540283 +[2025-04-29 19:35:21,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 0.9221482276916504, cross_entropy: 0.9221482276916504 +[2025-04-29 19:35:22,593][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 1.386401653289795, cross_entropy: 1.386401653289795 +[2025-04-29 19:35:25,580][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 2.4770994186401367, cross_entropy: 2.4770994186401367 +[2025-04-29 19:35:26,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 2.190694570541382, cross_entropy: 2.190694570541382 +[2025-04-29 19:35:29,399][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 0.8815658688545227, cross_entropy: 0.8815658688545227 +[2025-04-29 19:35:30,777][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.0961894989013672, cross_entropy: 1.0961894989013672 +[2025-04-29 19:35:32,989][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 0.9726176261901855, cross_entropy: 0.9726176261901855 +[2025-04-29 19:35:34,644][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 1.014585018157959, cross_entropy: 1.014585018157959 +[2025-04-29 19:35:37,179][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 0.582787275314331, cross_entropy: 0.582787275314331 +[2025-04-29 19:35:38,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.892749547958374, cross_entropy: 2.892749547958374 +[2025-04-29 19:35:41,303][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 0.9077420234680176, cross_entropy: 0.9077420234680176 +[2025-04-29 19:35:42,345][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.565185546875, cross_entropy: 2.565185546875 +[2025-04-29 19:35:45,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.9138433933258057, cross_entropy: 2.9138433933258057 +[2025-04-29 19:35:46,518][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 0.7625576853752136, cross_entropy: 0.7625576853752136 +[2025-04-29 19:35:49,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 1.2409813404083252, cross_entropy: 1.2409813404083252 +[2025-04-29 19:35:50,668][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 1.0650663375854492, cross_entropy: 1.0650663375854492 +[2025-04-29 19:35:53,381][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 1.065138578414917, cross_entropy: 1.065138578414917 +[2025-04-29 19:35:54,520][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.4059858322143555, cross_entropy: 2.4059858322143555 +[2025-04-29 19:35:57,583][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 1.4471006393432617, cross_entropy: 1.4471006393432617 +[2025-04-29 19:35:58,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.1906373500823975, cross_entropy: 2.1906373500823975 +[2025-04-29 19:36:00,753][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 1.3394473791122437, cross_entropy: 1.3394473791122437 +[2025-04-29 19:36:01,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 0.9691559076309204, cross_entropy: 0.9691559076309204 +[2025-04-29 19:36:04,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.174885630607605, cross_entropy: 1.174885630607605 +[2025-04-29 19:36:05,520][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.866927146911621, cross_entropy: 2.866927146911621 +[2025-04-29 19:36:08,224][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.592564344406128, cross_entropy: 1.592564344406128 +[2025-04-29 19:36:09,364][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 0.8301730155944824, cross_entropy: 0.8301730155944824 +[2025-04-29 19:36:12,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.363715171813965, cross_entropy: 2.363715171813965 +[2025-04-29 19:36:13,235][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.8440587520599365, cross_entropy: 1.8440587520599365 +[2025-04-29 19:36:15,522][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 1.7122061252593994, cross_entropy: 1.7122061252593994 +[2025-04-29 19:36:17,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 0.6197959184646606, cross_entropy: 0.6197959184646606 +[2025-04-29 19:36:18,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 2.919996976852417, cross_entropy: 2.919996976852417 +[2025-04-29 19:36:21,291][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 2.9771740436553955, cross_entropy: 2.9771740436553955 +[2025-04-29 19:36:23,206][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.1252453327178955, cross_entropy: 1.1252453327178955 +[2025-04-29 19:36:25,070][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.344292163848877, cross_entropy: 2.344292163848877 +[2025-04-29 19:36:27,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.0152673721313477, cross_entropy: 1.0152673721313477 +[2025-04-29 19:36:29,114][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 0.8580167293548584, cross_entropy: 0.8580167293548584 +[2025-04-29 19:36:31,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 2.262260913848877, cross_entropy: 2.262260913848877 +[2025-04-29 19:36:33,828][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 2.62261962890625, cross_entropy: 2.62261962890625 +[2025-04-29 19:36:34,948][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 2.575613021850586, cross_entropy: 2.575613021850586 +[2025-04-29 19:36:37,671][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 1.9091527462005615, cross_entropy: 1.9091527462005615 +[2025-04-29 19:36:39,426][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 0.7553362846374512, cross_entropy: 0.7553362846374512 +[2025-04-29 19:36:41,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 2.563002347946167, cross_entropy: 2.563002347946167 +[2025-04-29 19:36:43,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.897284984588623, cross_entropy: 2.897284984588623 +[2025-04-29 19:36:45,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.6801583766937256, cross_entropy: 2.6801583766937256 +[2025-04-29 19:36:48,349][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.9729629755020142, cross_entropy: 1.9729629755020142 +[2025-04-29 19:36:49,381][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.519376277923584, cross_entropy: 1.519376277923584 +[2025-04-29 19:36:52,262][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.1709301471710205, cross_entropy: 1.1709301471710205 +[2025-04-29 19:36:53,295][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.1950504779815674, cross_entropy: 2.1950504779815674 +[2025-04-29 19:36:55,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.287689208984375, cross_entropy: 2.287689208984375 +[2025-04-29 19:36:56,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.7931890487670898, cross_entropy: 1.7931890487670898 +[2025-04-29 19:36:59,479][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.819242238998413, cross_entropy: 1.819242238998413 +[2025-04-29 19:37:00,692][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.299010753631592, cross_entropy: 2.299010753631592 +[2025-04-29 19:37:02,920][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.4006686210632324, cross_entropy: 2.4006686210632324 +[2025-04-29 19:37:04,683][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.266386032104492, cross_entropy: 2.266386032104492 +[2025-04-29 19:37:06,918][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 2.3575353622436523, cross_entropy: 2.3575353622436523 +[2025-04-29 19:37:08,314][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.5868281126022339, cross_entropy: 1.5868281126022339 +[2025-04-29 19:37:10,779][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 2.144820213317871, cross_entropy: 2.144820213317871 +[2025-04-29 19:37:12,398][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.0805060863494873, cross_entropy: 1.0805060863494873 +[2025-04-29 19:37:14,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 2.291813850402832, cross_entropy: 2.291813850402832 +[2025-04-29 19:37:16,562][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.016383409500122, cross_entropy: 1.016383409500122 +[2025-04-29 19:37:18,859][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 2.428269863128662, cross_entropy: 2.428269863128662 +[2025-04-29 19:37:20,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 2.6991794109344482, cross_entropy: 2.6991794109344482 +[2025-04-29 19:37:23,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.1507105827331543, cross_entropy: 2.1507105827331543 +[2025-04-29 19:37:24,724][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 2.474285364151001, cross_entropy: 2.474285364151001 +[2025-04-29 19:37:26,890][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.8906877040863037, cross_entropy: 1.8906877040863037 +[2025-04-29 19:37:29,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 0.5021668672561646, cross_entropy: 0.5021668672561646 +[2025-04-29 19:37:30,729][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 1.0043919086456299, cross_entropy: 1.0043919086456299 +[2025-04-29 19:37:32,915][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.503795623779297, cross_entropy: 2.503795623779297 +[2025-04-29 19:37:34,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 2.4317212104797363, cross_entropy: 2.4317212104797363 +[2025-04-29 19:37:37,019][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.4463064670562744, cross_entropy: 2.4463064670562744 +[2025-04-29 19:37:38,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 0.6931634545326233, cross_entropy: 0.6931634545326233 +[2025-04-29 19:37:40,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.5500903129577637, cross_entropy: 2.5500903129577637 +[2025-04-29 19:37:42,473][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.3435604572296143, cross_entropy: 2.3435604572296143 +[2025-04-29 19:37:44,677][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 0.8720011711120605, cross_entropy: 0.8720011711120605 +[2025-04-29 19:37:46,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.2890172004699707, cross_entropy: 1.2890172004699707 +[2025-04-29 19:37:48,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.7713167667388916, cross_entropy: 1.7713167667388916 +[2025-04-29 19:37:50,036][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 2.3210041522979736, cross_entropy: 2.3210041522979736 +[2025-04-29 19:37:51,994][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 1.5542688369750977, cross_entropy: 1.5542688369750977 +[2025-04-29 19:37:53,788][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 0.7162402868270874, cross_entropy: 0.7162402868270874 +[2025-04-29 19:37:55,953][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 1.6360583305358887, cross_entropy: 1.6360583305358887 +[2025-04-29 19:37:58,031][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.392897129058838, cross_entropy: 2.392897129058838 +[2025-04-29 19:37:59,542][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.7584218978881836, cross_entropy: 2.7584218978881836 +[2025-04-29 19:38:01,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 2.097397804260254, cross_entropy: 2.097397804260254 +[2025-04-29 19:38:03,033][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.7497847080230713, cross_entropy: 2.7497847080230713 +[2025-04-29 19:38:05,898][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 2.428150177001953, cross_entropy: 2.428150177001953 +[2025-04-29 19:38:06,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.4213790893554688, cross_entropy: 1.4213790893554688 +[2025-04-29 19:38:09,794][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 1.8013331890106201, cross_entropy: 1.8013331890106201 +[2025-04-29 19:38:10,873][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.1534361839294434, cross_entropy: 1.1534361839294434 +[2025-04-29 19:38:14,407][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 0.6306254863739014, cross_entropy: 0.6306254863739014 +[2025-04-29 19:38:15,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 1.4150958061218262, cross_entropy: 1.4150958061218262 +[2025-04-29 19:38:18,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 2.5163326263427734, cross_entropy: 2.5163326263427734 +[2025-04-29 19:38:19,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 1.8957529067993164, cross_entropy: 1.8957529067993164 +[2025-04-29 19:38:22,679][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 2.063824415206909, cross_entropy: 2.063824415206909 +[2025-04-29 19:38:23,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 2.5117392539978027, cross_entropy: 2.5117392539978027 +[2025-04-29 19:38:26,758][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.4776902198791504, cross_entropy: 2.4776902198791504 +[2025-04-29 19:38:27,818][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.0943851470947266, cross_entropy: 2.0943851470947266 +[2025-04-29 19:38:30,409][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.8093421459197998, cross_entropy: 1.8093421459197998 +[2025-04-29 19:38:31,472][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.8551125526428223, cross_entropy: 2.8551125526428223 +[2025-04-29 19:38:34,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.143129587173462, cross_entropy: 2.143129587173462 +[2025-04-29 19:38:35,501][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.510439395904541, cross_entropy: 1.510439395904541 +[2025-04-29 19:38:38,336][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 0.6242904663085938, cross_entropy: 0.6242904663085938 +[2025-04-29 19:38:39,369][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.975156843662262, cross_entropy: 0.975156843662262 +[2025-04-29 19:38:42,221][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 2.1257505416870117, cross_entropy: 2.1257505416870117 +[2025-04-29 19:38:43,256][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.8280835151672363, cross_entropy: 1.8280835151672363 +[2025-04-29 19:38:45,997][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 0.7602005004882812, cross_entropy: 0.7602005004882812 +[2025-04-29 19:38:47,064][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 2.708852767944336, cross_entropy: 2.708852767944336 +[2025-04-29 19:38:49,291][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 2.2613401412963867, cross_entropy: 2.2613401412963867 +[2025-04-29 19:38:50,354][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.5757330656051636, cross_entropy: 1.5757330656051636 +[2025-04-29 19:38:53,293][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 0.9025521278381348, cross_entropy: 0.9025521278381348 +[2025-04-29 19:38:54,354][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 2.930349588394165, cross_entropy: 2.930349588394165 +[2025-04-29 19:38:56,438][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 2.1333043575286865, cross_entropy: 2.1333043575286865 +[2025-04-29 19:38:57,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.1563708782196045, cross_entropy: 1.1563708782196045 +[2025-04-29 19:39:00,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.7247273921966553, cross_entropy: 0.7247273921966553 +[2025-04-29 19:39:01,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.457229733467102, cross_entropy: 1.457229733467102 +[2025-04-29 19:39:04,047][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.8089806437492371, cross_entropy: 0.8089806437492371 +[2025-04-29 19:39:05,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.619727373123169, cross_entropy: 2.619727373123169 +[2025-04-29 19:39:08,755][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 2.740898609161377, cross_entropy: 2.740898609161377 +[2025-04-29 19:39:09,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.1230415105819702, cross_entropy: 1.1230415105819702 +[2025-04-29 19:39:12,376][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.347923755645752, cross_entropy: 2.347923755645752 +[2025-04-29 19:39:13,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 2.050934314727783, cross_entropy: 2.050934314727783 +[2025-04-29 19:39:15,809][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 2.6433019638061523, cross_entropy: 2.6433019638061523 +[2025-04-29 19:39:17,158][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.9094903469085693, cross_entropy: 1.9094903469085693 +[2025-04-29 19:39:19,362][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 2.125033140182495, cross_entropy: 2.125033140182495 +[2025-04-29 19:39:20,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 1.522629976272583, cross_entropy: 1.522629976272583 +[2025-04-29 19:39:23,352][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 1.855517029762268, cross_entropy: 1.855517029762268 +[2025-04-29 19:39:24,624][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 2.1899428367614746, cross_entropy: 2.1899428367614746 +[2025-04-29 19:39:27,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.104655385017395, cross_entropy: 1.104655385017395 +[2025-04-29 19:39:28,187][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.2585654258728027, cross_entropy: 1.2585654258728027 +[2025-04-29 19:39:31,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 0.721132218837738, cross_entropy: 0.721132218837738 +[2025-04-29 19:39:32,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.9041850566864014, cross_entropy: 1.9041850566864014 +[2025-04-29 19:39:35,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.742773175239563, cross_entropy: 1.742773175239563 +[2025-04-29 19:39:37,015][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.3323984146118164, cross_entropy: 1.3323984146118164 +[2025-04-29 19:39:40,072][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 2.1314566135406494, cross_entropy: 2.1314566135406494 +[2025-04-29 19:39:41,144][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.7083703875541687, cross_entropy: 0.7083703875541687 +[2025-04-29 19:39:43,805][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 2.7199573516845703, cross_entropy: 2.7199573516845703 +[2025-04-29 19:39:44,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 3.0575015544891357, cross_entropy: 3.0575015544891357 +[2025-04-29 19:39:48,344][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 2.7849950790405273, cross_entropy: 2.7849950790405273 +[2025-04-29 19:39:49,404][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 1.5187551975250244, cross_entropy: 1.5187551975250244 +[2025-04-29 19:39:52,087][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 0.8714144825935364, cross_entropy: 0.8714144825935364 +[2025-04-29 19:39:53,144][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 1.000872254371643, cross_entropy: 1.000872254371643 +[2025-04-29 19:39:55,772][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.555610418319702, cross_entropy: 2.555610418319702 +[2025-04-29 19:39:56,802][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.093437671661377, cross_entropy: 1.093437671661377 +[2025-04-29 19:40:00,344][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 2.9308054447174072, cross_entropy: 2.9308054447174072 +[2025-04-29 19:40:01,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 1.6850593090057373, cross_entropy: 1.6850593090057373 +[2025-04-29 19:40:04,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.4597957134246826, cross_entropy: 2.4597957134246826 +[2025-04-29 19:40:05,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 0.9335578680038452, cross_entropy: 0.9335578680038452 +[2025-04-29 19:40:09,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.0024518966674805, cross_entropy: 2.0024518966674805 +[2025-04-29 19:40:10,159][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 0.7949036359786987, cross_entropy: 0.7949036359786987 +[2025-04-29 19:40:13,398][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 0.9164761304855347, cross_entropy: 0.9164761304855347 +[2025-04-29 19:40:14,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 0.8555895090103149, cross_entropy: 0.8555895090103149 +[2025-04-29 19:40:16,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 2.7997398376464844, cross_entropy: 2.7997398376464844 +[2025-04-29 19:40:17,974][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.632591724395752, cross_entropy: 2.632591724395752 +[2025-04-29 19:40:20,373][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 1.6414539813995361, cross_entropy: 1.6414539813995361 +[2025-04-29 19:40:21,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 0.6308464407920837, cross_entropy: 0.6308464407920837 +[2025-04-29 19:43:10,658][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.6394613981246948, cross_entropy: 1.6394613981246948 +[2025-04-29 19:43:10,659][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.0336416959762573, cross_entropy: 1.0336416959762573 +[2025-04-29 19:43:11,538][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 19:43:12,017][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch8.pth. +[2025-04-29 19:43:12,841][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 19:43:18,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.5236265659332275, cross_entropy: 1.5236265659332275 +[2025-04-29 19:43:19,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 0.9148432016372681, cross_entropy: 0.9148432016372681 +[2025-04-29 19:43:22,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 0.8579410314559937, cross_entropy: 0.8579410314559937 +[2025-04-29 19:43:23,499][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 1.1054490804672241, cross_entropy: 1.1054490804672241 +[2025-04-29 19:43:26,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 0.9032517671585083, cross_entropy: 0.9032517671585083 +[2025-04-29 19:43:27,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 0.8388620615005493, cross_entropy: 0.8388620615005493 +[2025-04-29 19:43:30,000][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 1.695307731628418, cross_entropy: 1.695307731628418 +[2025-04-29 19:43:31,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.521744728088379, cross_entropy: 2.521744728088379 +[2025-04-29 19:43:33,850][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 0.96036696434021, cross_entropy: 0.96036696434021 +[2025-04-29 19:43:34,890][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 2.5426321029663086, cross_entropy: 2.5426321029663086 +[2025-04-29 19:43:37,948][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 2.13441801071167, cross_entropy: 2.13441801071167 +[2025-04-29 19:43:38,979][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.8222464919090271, cross_entropy: 0.8222464919090271 +[2025-04-29 19:43:41,898][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.2451419830322266, cross_entropy: 2.2451419830322266 +[2025-04-29 19:43:42,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 2.295606851577759, cross_entropy: 2.295606851577759 +[2025-04-29 19:43:45,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.1700026988983154, cross_entropy: 2.1700026988983154 +[2025-04-29 19:43:46,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.5350854396820068, cross_entropy: 0.5350854396820068 +[2025-04-29 19:43:48,823][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 0.8348613977432251, cross_entropy: 0.8348613977432251 +[2025-04-29 19:43:49,883][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.348759651184082, cross_entropy: 1.348759651184082 +[2025-04-29 19:43:52,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.4488728046417236, cross_entropy: 1.4488728046417236 +[2025-04-29 19:43:53,506][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.8814020156860352, cross_entropy: 1.8814020156860352 +[2025-04-29 19:43:56,165][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 0.6210090517997742, cross_entropy: 0.6210090517997742 +[2025-04-29 19:43:57,222][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 0.9372552633285522, cross_entropy: 0.9372552633285522 +[2025-04-29 19:44:00,525][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.6241230964660645, cross_entropy: 2.6241230964660645 +[2025-04-29 19:44:01,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 0.8469719886779785, cross_entropy: 0.8469719886779785 +[2025-04-29 19:44:03,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 0.667808473110199, cross_entropy: 0.667808473110199 +[2025-04-29 19:44:05,057][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 1.326216220855713, cross_entropy: 1.326216220855713 +[2025-04-29 19:44:07,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.0925889015197754, cross_entropy: 1.0925889015197754 +[2025-04-29 19:44:08,800][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 0.9927669167518616, cross_entropy: 0.9927669167518616 +[2025-04-29 19:44:12,346][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.712616205215454, cross_entropy: 2.712616205215454 +[2025-04-29 19:44:13,418][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.0231823921203613, cross_entropy: 1.0231823921203613 +[2025-04-29 19:44:16,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.933446168899536, cross_entropy: 2.933446168899536 +[2025-04-29 19:44:17,660][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 0.7357659339904785, cross_entropy: 0.7357659339904785 +[2025-04-29 19:44:20,087][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 2.6804494857788086, cross_entropy: 2.6804494857788086 +[2025-04-29 19:44:21,136][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 0.9230490326881409, cross_entropy: 0.9230490326881409 +[2025-04-29 19:44:24,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 1.0016640424728394, cross_entropy: 1.0016640424728394 +[2025-04-29 19:44:26,027][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 0.7484651803970337, cross_entropy: 0.7484651803970337 +[2025-04-29 19:44:28,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 0.6716815829277039, cross_entropy: 0.6716815829277039 +[2025-04-29 19:44:29,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 1.699074149131775, cross_entropy: 1.699074149131775 +[2025-04-29 19:44:33,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.191005825996399, cross_entropy: 1.191005825996399 +[2025-04-29 19:44:34,144][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.4581680297851562, cross_entropy: 2.4581680297851562 +[2025-04-29 19:44:36,804][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 1.2264893054962158, cross_entropy: 1.2264893054962158 +[2025-04-29 19:44:37,871][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 1.1232671737670898, cross_entropy: 1.1232671737670898 +[2025-04-29 19:44:41,130][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 1.2412645816802979, cross_entropy: 1.2412645816802979 +[2025-04-29 19:44:42,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 2.5068392753601074, cross_entropy: 2.5068392753601074 +[2025-04-29 19:44:44,771][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 1.8534939289093018, cross_entropy: 1.8534939289093018 +[2025-04-29 19:44:45,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 1.2440423965454102, cross_entropy: 1.2440423965454102 +[2025-04-29 19:44:48,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 2.653473377227783, cross_entropy: 2.653473377227783 +[2025-04-29 19:44:49,336][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 0.8659923076629639, cross_entropy: 0.8659923076629639 +[2025-04-29 19:44:52,079][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 2.3172848224639893, cross_entropy: 2.3172848224639893 +[2025-04-29 19:44:53,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 2.1624693870544434, cross_entropy: 2.1624693870544434 +[2025-04-29 19:44:55,917][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 0.49726057052612305, cross_entropy: 0.49726057052612305 +[2025-04-29 19:44:56,976][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.5063849687576294, cross_entropy: 1.5063849687576294 +[2025-04-29 19:45:00,066][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 2.3505289554595947, cross_entropy: 2.3505289554595947 +[2025-04-29 19:45:01,102][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.9256489276885986, cross_entropy: 1.9256489276885986 +[2025-04-29 19:45:04,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 0.5520084500312805, cross_entropy: 0.5520084500312805 +[2025-04-29 19:45:05,480][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 0.6098078489303589, cross_entropy: 0.6098078489303589 +[2025-04-29 19:45:08,212][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 2.4760961532592773, cross_entropy: 2.4760961532592773 +[2025-04-29 19:45:09,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 0.7790003418922424, cross_entropy: 0.7790003418922424 +[2025-04-29 19:45:11,900][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.1129815578460693, cross_entropy: 1.1129815578460693 +[2025-04-29 19:45:12,961][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 1.2214114665985107, cross_entropy: 1.2214114665985107 +[2025-04-29 19:45:15,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.030250310897827, cross_entropy: 2.030250310897827 +[2025-04-29 19:45:16,607][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 0.7530447244644165, cross_entropy: 0.7530447244644165 +[2025-04-29 19:45:19,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 0.8776947855949402, cross_entropy: 0.8776947855949402 +[2025-04-29 19:45:20,242][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 0.6692919731140137, cross_entropy: 0.6692919731140137 +[2025-04-29 19:45:22,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.971322536468506, cross_entropy: 2.971322536468506 +[2025-04-29 19:45:23,779][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.5765256285667419, cross_entropy: 0.5765256285667419 +[2025-04-29 19:45:26,469][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.8834960460662842, cross_entropy: 0.8834960460662842 +[2025-04-29 19:45:27,525][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.7264746427536011, cross_entropy: 0.7264746427536011 +[2025-04-29 19:45:30,321][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 2.2714593410491943, cross_entropy: 2.2714593410491943 +[2025-04-29 19:45:31,383][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 0.6924168467521667, cross_entropy: 0.6924168467521667 +[2025-04-29 19:45:34,189][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 2.348658323287964, cross_entropy: 2.348658323287964 +[2025-04-29 19:45:35,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 0.5362160205841064, cross_entropy: 0.5362160205841064 +[2025-04-29 19:45:38,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 2.357631206512451, cross_entropy: 2.357631206512451 +[2025-04-29 19:45:39,270][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 0.9780230522155762, cross_entropy: 0.9780230522155762 +[2025-04-29 19:45:41,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 1.096114158630371, cross_entropy: 1.096114158630371 +[2025-04-29 19:45:43,042][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.0436654090881348, cross_entropy: 2.0436654090881348 +[2025-04-29 19:45:45,202][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 0.5551502704620361, cross_entropy: 0.5551502704620361 +[2025-04-29 19:45:46,260][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.8849663734436035, cross_entropy: 0.8849663734436035 +[2025-04-29 19:45:48,951][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 1.1030793190002441, cross_entropy: 1.1030793190002441 +[2025-04-29 19:45:50,007][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 0.6773980855941772, cross_entropy: 0.6773980855941772 +[2025-04-29 19:45:52,729][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 0.5278321504592896, cross_entropy: 0.5278321504592896 +[2025-04-29 19:45:53,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.7495483160018921, cross_entropy: 0.7495483160018921 +[2025-04-29 19:45:56,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 2.614882230758667, cross_entropy: 2.614882230758667 +[2025-04-29 19:45:57,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 0.7814999222755432, cross_entropy: 0.7814999222755432 +[2025-04-29 19:46:00,458][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.547208547592163, cross_entropy: 1.547208547592163 +[2025-04-29 19:46:01,525][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.5885746479034424, cross_entropy: 1.5885746479034424 +[2025-04-29 19:46:04,653][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 0.8526715040206909, cross_entropy: 0.8526715040206909 +[2025-04-29 19:46:05,684][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.258243203163147, cross_entropy: 1.258243203163147 +[2025-04-29 19:46:08,214][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 2.4823179244995117, cross_entropy: 2.4823179244995117 +[2025-04-29 19:46:09,271][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 1.276193618774414, cross_entropy: 1.276193618774414 +[2025-04-29 19:46:11,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.256542921066284, cross_entropy: 2.256542921066284 +[2025-04-29 19:46:12,664][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 1.259999394416809, cross_entropy: 1.259999394416809 +[2025-04-29 19:46:14,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 0.8598712682723999, cross_entropy: 0.8598712682723999 +[2025-04-29 19:46:15,984][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.8697794675827026, cross_entropy: 0.8697794675827026 +[2025-04-29 19:46:19,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.546919345855713, cross_entropy: 2.546919345855713 +[2025-04-29 19:46:20,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 2.4836440086364746, cross_entropy: 2.4836440086364746 +[2025-04-29 19:46:23,152][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 0.9681797027587891, cross_entropy: 0.9681797027587891 +[2025-04-29 19:46:24,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 2.6120877265930176, cross_entropy: 2.6120877265930176 +[2025-04-29 19:46:26,685][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.5871005058288574, cross_entropy: 1.5871005058288574 +[2025-04-29 19:46:27,717][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.7658226490020752, cross_entropy: 1.7658226490020752 +[2025-04-29 19:46:30,914][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.4553277492523193, cross_entropy: 2.4553277492523193 +[2025-04-29 19:46:31,970][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 1.2553927898406982, cross_entropy: 1.2553927898406982 +[2025-04-29 19:46:34,713][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 2.375812530517578, cross_entropy: 2.375812530517578 +[2025-04-29 19:46:35,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 0.465241938829422, cross_entropy: 0.465241938829422 +[2025-04-29 19:46:38,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 1.7240711450576782, cross_entropy: 1.7240711450576782 +[2025-04-29 19:46:39,263][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 1.064568281173706, cross_entropy: 1.064568281173706 +[2025-04-29 19:46:42,281][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.7255139350891113, cross_entropy: 2.7255139350891113 +[2025-04-29 19:46:43,342][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 2.3257956504821777, cross_entropy: 2.3257956504821777 +[2025-04-29 19:46:45,475][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 1.411308765411377, cross_entropy: 1.411308765411377 +[2025-04-29 19:46:46,583][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.7590686678886414, cross_entropy: 0.7590686678886414 +[2025-04-29 19:46:49,102][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 0.9140055775642395, cross_entropy: 0.9140055775642395 +[2025-04-29 19:46:50,833][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 1.1999828815460205, cross_entropy: 1.1999828815460205 +[2025-04-29 19:46:53,061][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 0.39546552300453186, cross_entropy: 0.39546552300453186 +[2025-04-29 19:46:54,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 0.49795636534690857, cross_entropy: 0.49795636534690857 +[2025-04-29 19:46:57,787][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.332002639770508, cross_entropy: 2.332002639770508 +[2025-04-29 19:46:58,905][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 0.843592643737793, cross_entropy: 0.843592643737793 +[2025-04-29 19:47:01,081][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 1.4617236852645874, cross_entropy: 1.4617236852645874 +[2025-04-29 19:47:02,147][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 0.558901846408844, cross_entropy: 0.558901846408844 +[2025-04-29 19:47:05,254][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 0.9298657178878784, cross_entropy: 0.9298657178878784 +[2025-04-29 19:47:06,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.7727370262145996, cross_entropy: 2.7727370262145996 +[2025-04-29 19:47:09,221][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 1.4050594568252563, cross_entropy: 1.4050594568252563 +[2025-04-29 19:47:10,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 0.947925865650177, cross_entropy: 0.947925865650177 +[2025-04-29 19:47:13,221][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.522477149963379, cross_entropy: 2.522477149963379 +[2025-04-29 19:47:14,501][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.203340530395508, cross_entropy: 2.203340530395508 +[2025-04-29 19:47:17,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.9535369873046875, cross_entropy: 1.9535369873046875 +[2025-04-29 19:47:18,297][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 2.2080631256103516, cross_entropy: 2.2080631256103516 +[2025-04-29 19:47:20,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 1.4322618246078491, cross_entropy: 1.4322618246078491 +[2025-04-29 19:47:21,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 0.7666162252426147, cross_entropy: 0.7666162252426147 +[2025-04-29 19:47:25,401][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 0.7902390360832214, cross_entropy: 0.7902390360832214 +[2025-04-29 19:47:26,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 1.7391105890274048, cross_entropy: 1.7391105890274048 +[2025-04-29 19:47:29,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 2.1143484115600586, cross_entropy: 2.1143484115600586 +[2025-04-29 19:47:30,802][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.1990087032318115, cross_entropy: 2.1990087032318115 +[2025-04-29 19:47:34,085][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.8687431812286377, cross_entropy: 1.8687431812286377 +[2025-04-29 19:47:35,146][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 0.6342701315879822, cross_entropy: 0.6342701315879822 +[2025-04-29 19:47:37,535][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 2.153792381286621, cross_entropy: 2.153792381286621 +[2025-04-29 19:47:38,567][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.268222689628601, cross_entropy: 1.268222689628601 +[2025-04-29 19:47:43,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 1.216820478439331, cross_entropy: 1.216820478439331 +[2025-04-29 19:47:44,475][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 1.405463457107544, cross_entropy: 1.405463457107544 +[2025-04-29 19:47:47,517][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 1.8765612840652466, cross_entropy: 1.8765612840652466 +[2025-04-29 19:47:48,579][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 1.5296030044555664, cross_entropy: 1.5296030044555664 +[2025-04-29 19:47:51,348][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 0.576849639415741, cross_entropy: 0.576849639415741 +[2025-04-29 19:47:52,405][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 1.8063870668411255, cross_entropy: 1.8063870668411255 +[2025-04-29 19:47:54,752][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.031388282775879, cross_entropy: 2.031388282775879 +[2025-04-29 19:47:55,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 1.2083395719528198, cross_entropy: 1.2083395719528198 +[2025-04-29 19:47:59,261][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 2.639569044113159, cross_entropy: 2.639569044113159 +[2025-04-29 19:48:00,316][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 1.8688769340515137, cross_entropy: 1.8688769340515137 +[2025-04-29 19:48:02,553][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 2.296173572540283, cross_entropy: 2.296173572540283 +[2025-04-29 19:48:03,606][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 2.512233018875122, cross_entropy: 2.512233018875122 +[2025-04-29 19:48:06,007][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.8632253408432007, cross_entropy: 0.8632253408432007 +[2025-04-29 19:48:07,040][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.6950926780700684, cross_entropy: 2.6950926780700684 +[2025-04-29 19:48:10,426][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 0.6498803496360779, cross_entropy: 0.6498803496360779 +[2025-04-29 19:48:11,486][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 1.7073811292648315, cross_entropy: 1.7073811292648315 +[2025-04-29 19:48:12,259][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/iteration3000.pth. +[2025-04-29 19:48:14,315][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 2.4694738388061523, cross_entropy: 2.4694738388061523 +[2025-04-29 19:48:15,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.8205251693725586, cross_entropy: 2.8205251693725586 +[2025-04-29 19:48:18,298][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 0.8394615650177002, cross_entropy: 0.8394615650177002 +[2025-04-29 19:48:19,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 0.7817223072052002, cross_entropy: 0.7817223072052002 +[2025-04-29 19:48:22,821][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 0.8775244951248169, cross_entropy: 0.8775244951248169 +[2025-04-29 19:48:23,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 0.6785393953323364, cross_entropy: 0.6785393953323364 +[2025-04-29 19:48:26,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 0.8365164995193481, cross_entropy: 0.8365164995193481 +[2025-04-29 19:48:27,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 0.8096736073493958, cross_entropy: 0.8096736073493958 +[2025-04-29 19:48:30,497][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 0.9177150726318359, cross_entropy: 0.9177150726318359 +[2025-04-29 19:48:31,538][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 1.303328037261963, cross_entropy: 1.303328037261963 +[2025-04-29 19:48:34,578][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 2.3359389305114746, cross_entropy: 2.3359389305114746 +[2025-04-29 19:48:35,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 0.9902795553207397, cross_entropy: 0.9902795553207397 +[2025-04-29 19:48:37,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.276103973388672, cross_entropy: 2.276103973388672 +[2025-04-29 19:48:39,038][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 2.0372605323791504, cross_entropy: 2.0372605323791504 +[2025-04-29 19:48:41,689][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.062220811843872, cross_entropy: 1.062220811843872 +[2025-04-29 19:48:42,724][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 1.1009292602539062, cross_entropy: 1.1009292602539062 +[2025-04-29 19:48:45,594][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.7424490451812744, cross_entropy: 0.7424490451812744 +[2025-04-29 19:48:46,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 0.7921721935272217, cross_entropy: 0.7921721935272217 +[2025-04-29 19:48:48,717][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 0.6743922233581543, cross_entropy: 0.6743922233581543 +[2025-04-29 19:48:49,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 0.9422018527984619, cross_entropy: 0.9422018527984619 +[2025-04-29 19:48:52,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.272639274597168, cross_entropy: 2.272639274597168 +[2025-04-29 19:48:53,616][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 0.7253226041793823, cross_entropy: 0.7253226041793823 +[2025-04-29 19:48:56,726][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 2.3127622604370117, cross_entropy: 2.3127622604370117 +[2025-04-29 19:48:57,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 2.361058235168457, cross_entropy: 2.361058235168457 +[2025-04-29 19:49:00,191][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 0.6888847351074219, cross_entropy: 0.6888847351074219 +[2025-04-29 19:49:01,245][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.0723745822906494, cross_entropy: 1.0723745822906494 +[2025-04-29 19:49:03,137][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 0.7011500000953674, cross_entropy: 0.7011500000953674 +[2025-04-29 19:49:04,194][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 1.0227558612823486, cross_entropy: 1.0227558612823486 +[2025-04-29 19:49:06,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.591372013092041, cross_entropy: 2.591372013092041 +[2025-04-29 19:49:07,803][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 2.5897836685180664, cross_entropy: 2.5897836685180664 +[2025-04-29 19:49:10,376][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 0.8969969749450684, cross_entropy: 0.8969969749450684 +[2025-04-29 19:49:11,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 1.8438571691513062, cross_entropy: 1.8438571691513062 +[2025-04-29 19:49:14,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 0.6700339317321777, cross_entropy: 0.6700339317321777 +[2025-04-29 19:49:15,541][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 1.638428807258606, cross_entropy: 1.638428807258606 +[2025-04-29 19:49:17,881][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.3328163623809814, cross_entropy: 2.3328163623809814 +[2025-04-29 19:49:18,911][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 1.187157392501831, cross_entropy: 1.187157392501831 +[2025-04-29 19:49:21,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 2.596181869506836, cross_entropy: 2.596181869506836 +[2025-04-29 19:49:22,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 0.5238922834396362, cross_entropy: 0.5238922834396362 +[2025-04-29 19:49:25,754][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 0.9497267603874207, cross_entropy: 0.9497267603874207 +[2025-04-29 19:49:26,813][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.046050786972046, cross_entropy: 1.046050786972046 +[2025-04-29 19:49:30,180][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.452775478363037, cross_entropy: 2.452775478363037 +[2025-04-29 19:49:31,209][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 2.2059924602508545, cross_entropy: 2.2059924602508545 +[2025-04-29 19:49:33,315][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 0.6454035043716431, cross_entropy: 0.6454035043716431 +[2025-04-29 19:49:34,369][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 2.557778835296631, cross_entropy: 2.557778835296631 +[2025-04-29 19:49:36,832][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 1.5474746227264404, cross_entropy: 1.5474746227264404 +[2025-04-29 19:49:37,863][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.8841372728347778, cross_entropy: 1.8841372728347778 +[2025-04-29 19:49:40,810][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 2.606595516204834, cross_entropy: 2.606595516204834 +[2025-04-29 19:49:41,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 2.0021753311157227, cross_entropy: 2.0021753311157227 +[2025-04-29 19:49:44,724][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.8695831298828125, cross_entropy: 0.8695831298828125 +[2025-04-29 19:49:45,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.654915690422058, cross_entropy: 1.654915690422058 +[2025-04-29 19:49:49,698][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.6433054804801941, cross_entropy: 0.6433054804801941 +[2025-04-29 19:49:50,750][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.3106000423431396, cross_entropy: 2.3106000423431396 +[2025-04-29 19:49:53,330][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 0.6540173292160034, cross_entropy: 0.6540173292160034 +[2025-04-29 19:49:54,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 0.8042175769805908, cross_entropy: 0.8042175769805908 +[2025-04-29 19:49:57,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.2950892448425293, cross_entropy: 2.2950892448425293 +[2025-04-29 19:49:58,792][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 0.9409011602401733, cross_entropy: 0.9409011602401733 +[2025-04-29 19:50:01,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 0.6853498220443726, cross_entropy: 0.6853498220443726 +[2025-04-29 19:50:02,209][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 2.705418586730957, cross_entropy: 2.705418586730957 +[2025-04-29 19:50:04,288][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.3449885845184326, cross_entropy: 2.3449885845184326 +[2025-04-29 19:50:05,319][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 2.8419861793518066, cross_entropy: 2.8419861793518066 +[2025-04-29 19:50:08,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 2.7762982845306396, cross_entropy: 2.7762982845306396 +[2025-04-29 19:50:09,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 0.9489949941635132, cross_entropy: 0.9489949941635132 +[2025-04-29 19:50:11,560][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.3274946212768555, cross_entropy: 1.3274946212768555 +[2025-04-29 19:50:12,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.396070957183838, cross_entropy: 1.396070957183838 +[2025-04-29 19:50:15,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.3971080780029297, cross_entropy: 2.3971080780029297 +[2025-04-29 19:50:16,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 0.8556639552116394, cross_entropy: 0.8556639552116394 +[2025-04-29 19:50:19,369][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 2.6370911598205566, cross_entropy: 2.6370911598205566 +[2025-04-29 19:50:20,487][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.138577699661255, cross_entropy: 2.138577699661255 +[2025-04-29 19:50:22,483][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 0.7200271487236023, cross_entropy: 0.7200271487236023 +[2025-04-29 19:50:24,885][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 2.049612045288086, cross_entropy: 2.049612045288086 +[2025-04-29 19:50:26,055][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 0.7755206823348999, cross_entropy: 0.7755206823348999 +[2025-04-29 19:50:28,943][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 0.7630362510681152, cross_entropy: 0.7630362510681152 +[2025-04-29 19:50:30,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 2.23995304107666, cross_entropy: 2.23995304107666 +[2025-04-29 19:50:32,604][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 0.8756589293479919, cross_entropy: 0.8756589293479919 +[2025-04-29 19:50:33,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 2.4866151809692383, cross_entropy: 2.4866151809692383 +[2025-04-29 19:50:36,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.147120952606201, cross_entropy: 2.147120952606201 +[2025-04-29 19:50:37,140][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 0.4048268795013428, cross_entropy: 0.4048268795013428 +[2025-04-29 19:50:39,615][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.4682722091674805, cross_entropy: 2.4682722091674805 +[2025-04-29 19:50:40,673][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 1.339629888534546, cross_entropy: 1.339629888534546 +[2025-04-29 19:50:43,787][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 0.9212703108787537, cross_entropy: 0.9212703108787537 +[2025-04-29 19:50:44,925][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.9720089435577393, cross_entropy: 0.9720089435577393 +[2025-04-29 19:50:47,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 0.6604653000831604, cross_entropy: 0.6604653000831604 +[2025-04-29 19:50:48,664][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.9411306381225586, cross_entropy: 0.9411306381225586 +[2025-04-29 19:50:51,935][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 0.6606349945068359, cross_entropy: 0.6606349945068359 +[2025-04-29 19:50:52,995][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.0022175312042236, cross_entropy: 1.0022175312042236 +[2025-04-29 19:50:55,648][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 1.0900626182556152, cross_entropy: 1.0900626182556152 +[2025-04-29 19:50:56,682][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 0.7724801898002625, cross_entropy: 0.7724801898002625 +[2025-04-29 19:50:59,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 0.649154543876648, cross_entropy: 0.649154543876648 +[2025-04-29 19:51:00,873][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.2855675220489502, cross_entropy: 1.2855675220489502 +[2025-04-29 19:51:03,560][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.7944332361221313, cross_entropy: 1.7944332361221313 +[2025-04-29 19:51:04,617][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 0.8690766096115112, cross_entropy: 0.8690766096115112 +[2025-04-29 19:51:07,482][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 0.6547724008560181, cross_entropy: 0.6547724008560181 +[2025-04-29 19:51:08,547][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 1.6459002494812012, cross_entropy: 1.6459002494812012 +[2025-04-29 19:51:11,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 0.7638826966285706, cross_entropy: 0.7638826966285706 +[2025-04-29 19:51:12,180][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 0.8107024431228638, cross_entropy: 0.8107024431228638 +[2025-04-29 19:51:14,863][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 0.8483469486236572, cross_entropy: 0.8483469486236572 +[2025-04-29 19:51:15,897][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.9945775270462036, cross_entropy: 1.9945775270462036 +[2025-04-29 19:51:18,548][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.3897390365600586, cross_entropy: 1.3897390365600586 +[2025-04-29 19:51:19,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 1.2438188791275024, cross_entropy: 1.2438188791275024 +[2025-04-29 19:51:24,584][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.6037697792053223, cross_entropy: 2.6037697792053223 +[2025-04-29 19:51:25,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 0.5844571590423584, cross_entropy: 0.5844571590423584 +[2025-04-29 19:51:27,626][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 0.8993622064590454, cross_entropy: 0.8993622064590454 +[2025-04-29 19:51:28,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 2.5887503623962402, cross_entropy: 2.5887503623962402 +[2025-04-29 19:51:31,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 1.9546371698379517, cross_entropy: 1.9546371698379517 +[2025-04-29 19:51:32,461][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.1817424297332764, cross_entropy: 1.1817424297332764 +[2025-04-29 19:51:35,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 0.8748743534088135, cross_entropy: 0.8748743534088135 +[2025-04-29 19:51:36,871][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.351975440979004, cross_entropy: 2.351975440979004 +[2025-04-29 19:51:39,542][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.4587624073028564, cross_entropy: 2.4587624073028564 +[2025-04-29 19:51:40,600][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 0.9791133999824524, cross_entropy: 0.9791133999824524 +[2025-04-29 19:51:42,890][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 2.920915365219116, cross_entropy: 2.920915365219116 +[2025-04-29 19:51:43,956][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 2.2621591091156006, cross_entropy: 2.2621591091156006 +[2025-04-29 19:51:46,384][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 2.116431713104248, cross_entropy: 2.116431713104248 +[2025-04-29 19:51:47,440][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 2.221055507659912, cross_entropy: 2.221055507659912 +[2025-04-29 19:51:49,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 0.5489062070846558, cross_entropy: 0.5489062070846558 +[2025-04-29 19:51:50,914][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.2735912799835205, cross_entropy: 1.2735912799835205 +[2025-04-29 19:51:53,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 0.5973016023635864, cross_entropy: 0.5973016023635864 +[2025-04-29 19:51:54,346][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 1.350313425064087, cross_entropy: 1.350313425064087 +[2025-04-29 19:51:57,610][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 2.6893553733825684, cross_entropy: 2.6893553733825684 +[2025-04-29 19:51:58,708][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 0.8725348711013794, cross_entropy: 0.8725348711013794 +[2025-04-29 19:52:01,762][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 0.8316479921340942, cross_entropy: 0.8316479921340942 +[2025-04-29 19:52:02,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.142549753189087, cross_entropy: 2.142549753189087 +[2025-04-29 19:52:05,334][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 2.2640912532806396, cross_entropy: 2.2640912532806396 +[2025-04-29 19:52:06,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 0.7658243179321289, cross_entropy: 0.7658243179321289 +[2025-04-29 19:52:08,955][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 2.5050437450408936, cross_entropy: 2.5050437450408936 +[2025-04-29 19:52:10,013][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 0.6634538173675537, cross_entropy: 0.6634538173675537 +[2025-04-29 19:52:12,573][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 0.7771847248077393, cross_entropy: 0.7771847248077393 +[2025-04-29 19:52:13,660][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 1.060670256614685, cross_entropy: 1.060670256614685 +[2025-04-29 19:52:16,751][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.1468491554260254, cross_entropy: 1.1468491554260254 +[2025-04-29 19:52:17,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.2147706747055054, cross_entropy: 1.2147706747055054 +[2025-04-29 19:52:20,673][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.924978256225586, cross_entropy: 2.924978256225586 +[2025-04-29 19:52:21,732][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 1.7981324195861816, cross_entropy: 1.7981324195861816 +[2025-04-29 19:52:24,059][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 0.6159127950668335, cross_entropy: 0.6159127950668335 +[2025-04-29 19:52:25,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 0.7139289975166321, cross_entropy: 0.7139289975166321 +[2025-04-29 19:52:27,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 2.3864548206329346, cross_entropy: 2.3864548206329346 +[2025-04-29 19:52:28,878][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 0.827775239944458, cross_entropy: 0.827775239944458 +[2025-04-29 19:52:31,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 1.6751408576965332, cross_entropy: 1.6751408576965332 +[2025-04-29 19:52:32,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 0.9064478874206543, cross_entropy: 0.9064478874206543 +[2025-04-29 19:52:35,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.0666353702545166, cross_entropy: 1.0666353702545166 +[2025-04-29 19:52:36,750][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 1.258334755897522, cross_entropy: 1.258334755897522 +[2025-04-29 19:52:39,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 2.4628710746765137, cross_entropy: 2.4628710746765137 +[2025-04-29 19:52:40,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.123011827468872, cross_entropy: 1.123011827468872 +[2025-04-29 19:52:42,991][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 1.3023148775100708, cross_entropy: 1.3023148775100708 +[2025-04-29 19:52:44,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 0.9368586540222168, cross_entropy: 0.9368586540222168 +[2025-04-29 19:52:47,102][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 0.8121040463447571, cross_entropy: 0.8121040463447571 +[2025-04-29 19:52:48,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 2.482482433319092, cross_entropy: 2.482482433319092 +[2025-04-29 19:52:50,182][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 0.8736406564712524, cross_entropy: 0.8736406564712524 +[2025-04-29 19:52:51,342][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 1.0976753234863281, cross_entropy: 1.0976753234863281 +[2025-04-29 19:52:54,003][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.3441193103790283, cross_entropy: 1.3441193103790283 +[2025-04-29 19:52:55,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 1.1476881504058838, cross_entropy: 1.1476881504058838 +[2025-04-29 19:52:57,448][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 0.7875862717628479, cross_entropy: 0.7875862717628479 +[2025-04-29 19:52:58,659][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 2.414398193359375, cross_entropy: 2.414398193359375 +[2025-04-29 19:53:01,487][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 2.8870627880096436, cross_entropy: 2.8870627880096436 +[2025-04-29 19:53:02,586][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 0.7350448369979858, cross_entropy: 0.7350448369979858 +[2025-04-29 19:53:04,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.48851317167282104, cross_entropy: 0.48851317167282104 +[2025-04-29 19:53:06,275][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 2.5926642417907715, cross_entropy: 2.5926642417907715 +[2025-04-29 19:53:09,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 1.0926647186279297, cross_entropy: 1.0926647186279297 +[2025-04-29 19:53:10,609][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 2.6671907901763916, cross_entropy: 2.6671907901763916 +[2025-04-29 19:53:13,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 1.0209590196609497, cross_entropy: 1.0209590196609497 +[2025-04-29 19:53:14,862][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 2.352952718734741, cross_entropy: 2.352952718734741 +[2025-04-29 19:53:18,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 1.178039312362671, cross_entropy: 1.178039312362671 +[2025-04-29 19:53:19,213][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 0.9133216738700867, cross_entropy: 0.9133216738700867 +[2025-04-29 19:53:21,315][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.0629642009735107, cross_entropy: 1.0629642009735107 +[2025-04-29 19:53:22,398][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 2.1310372352600098, cross_entropy: 2.1310372352600098 +[2025-04-29 19:53:25,881][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 1.0414345264434814, cross_entropy: 1.0414345264434814 +[2025-04-29 19:53:26,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 2.0248606204986572, cross_entropy: 2.0248606204986572 +[2025-04-29 19:53:29,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 2.3728737831115723, cross_entropy: 2.3728737831115723 +[2025-04-29 19:53:30,999][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.946790933609009, cross_entropy: 2.946790933609009 +[2025-04-29 19:53:33,723][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 0.7670220732688904, cross_entropy: 0.7670220732688904 +[2025-04-29 19:53:34,807][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.126591444015503, cross_entropy: 1.126591444015503 +[2025-04-29 19:53:36,930][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 0.80405193567276, cross_entropy: 0.80405193567276 +[2025-04-29 19:53:38,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.095573902130127, cross_entropy: 2.095573902130127 +[2025-04-29 19:53:40,543][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 1.4112684726715088, cross_entropy: 1.4112684726715088 +[2025-04-29 19:53:41,736][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 1.5039441585540771, cross_entropy: 1.5039441585540771 +[2025-04-29 19:53:44,742][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 0.605408787727356, cross_entropy: 0.605408787727356 +[2025-04-29 19:53:45,831][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 2.178102493286133, cross_entropy: 2.178102493286133 +[2025-04-29 19:53:48,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.8008188009262085, cross_entropy: 1.8008188009262085 +[2025-04-29 19:53:49,593][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.6232435703277588, cross_entropy: 1.6232435703277588 +[2025-04-29 19:53:53,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.344890832901001, cross_entropy: 1.344890832901001 +[2025-04-29 19:53:54,924][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 1.051966667175293, cross_entropy: 1.051966667175293 +[2025-04-29 19:53:56,426][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 0.7778933048248291, cross_entropy: 0.7778933048248291 +[2025-04-29 19:53:58,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 2.286747455596924, cross_entropy: 2.286747455596924 +[2025-04-29 19:54:00,161][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.368361234664917, cross_entropy: 1.368361234664917 +[2025-04-29 19:54:03,118][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 0.7866381406784058, cross_entropy: 0.7866381406784058 +[2025-04-29 19:54:04,804][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 1.601463794708252, cross_entropy: 1.601463794708252 +[2025-04-29 19:54:07,114][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 2.470059633255005, cross_entropy: 2.470059633255005 +[2025-04-29 19:54:08,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 1.2570134401321411, cross_entropy: 1.2570134401321411 +[2025-04-29 19:54:10,696][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 0.8653546571731567, cross_entropy: 0.8653546571731567 +[2025-04-29 19:54:13,321][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 1.168731451034546, cross_entropy: 1.168731451034546 +[2025-04-29 19:54:14,798][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 2.0564887523651123, cross_entropy: 2.0564887523651123 +[2025-04-29 19:54:16,999][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 0.8288780450820923, cross_entropy: 0.8288780450820923 +[2025-04-29 19:54:18,076][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 2.2727503776550293, cross_entropy: 2.2727503776550293 +[2025-04-29 19:54:20,861][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 2.156639575958252, cross_entropy: 2.156639575958252 +[2025-04-29 19:54:22,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 0.699600338935852, cross_entropy: 0.699600338935852 +[2025-04-29 19:54:25,017][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 1.6322574615478516, cross_entropy: 1.6322574615478516 +[2025-04-29 19:54:26,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 2.469433307647705, cross_entropy: 2.469433307647705 +[2025-04-29 19:54:28,206][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.40500807762146, cross_entropy: 2.40500807762146 +[2025-04-29 19:54:29,472][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 0.8541460633277893, cross_entropy: 0.8541460633277893 +[2025-04-29 19:54:31,592][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.3272366523742676, cross_entropy: 2.3272366523742676 +[2025-04-29 19:54:33,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.1034646034240723, cross_entropy: 2.1034646034240723 +[2025-04-29 19:54:35,191][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 0.837519645690918, cross_entropy: 0.837519645690918 +[2025-04-29 19:54:36,955][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 1.1345975399017334, cross_entropy: 1.1345975399017334 +[2025-04-29 19:54:38,875][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.49674654006958, cross_entropy: 2.49674654006958 +[2025-04-29 19:54:40,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 2.71453857421875, cross_entropy: 2.71453857421875 +[2025-04-29 19:54:41,611][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 0.5465136766433716, cross_entropy: 0.5465136766433716 +[2025-04-29 19:57:28,485][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.4844286441802979, cross_entropy: 1.4844286441802979 +[2025-04-29 19:57:28,486][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.0042051076889038, cross_entropy: 1.0042051076889038 +[2025-04-29 19:57:29,374][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 19:57:29,865][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch9.pth. +[2025-04-29 19:57:30,699][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 19:57:35,956][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.4689915180206299, cross_entropy: 1.4689915180206299 +[2025-04-29 19:57:37,088][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.9119924306869507, cross_entropy: 1.9119924306869507 +[2025-04-29 19:57:39,587][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 2.4102389812469482, cross_entropy: 2.4102389812469482 +[2025-04-29 19:57:40,623][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 0.7467156648635864, cross_entropy: 0.7467156648635864 +[2025-04-29 19:57:43,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.443296432495117, cross_entropy: 2.443296432495117 +[2025-04-29 19:57:44,856][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.3205982446670532, cross_entropy: 1.3205982446670532 +[2025-04-29 19:57:47,336][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.081559181213379, cross_entropy: 2.081559181213379 +[2025-04-29 19:57:48,401][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 1.9915311336517334, cross_entropy: 1.9915311336517334 +[2025-04-29 19:57:51,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.207118511199951, cross_entropy: 2.207118511199951 +[2025-04-29 19:57:52,802][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.015990972518921, cross_entropy: 1.015990972518921 +[2025-04-29 19:57:55,827][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.306875705718994, cross_entropy: 2.306875705718994 +[2025-04-29 19:57:56,887][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 1.5801095962524414, cross_entropy: 1.5801095962524414 +[2025-04-29 19:57:58,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.3019497394561768, cross_entropy: 1.3019497394561768 +[2025-04-29 19:58:00,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 0.9446496963500977, cross_entropy: 0.9446496963500977 +[2025-04-29 19:58:02,925][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 1.1256210803985596, cross_entropy: 1.1256210803985596 +[2025-04-29 19:58:03,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 1.7415374517440796, cross_entropy: 1.7415374517440796 +[2025-04-29 19:58:06,785][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 1.6424264907836914, cross_entropy: 1.6424264907836914 +[2025-04-29 19:58:07,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.647805690765381, cross_entropy: 2.647805690765381 +[2025-04-29 19:58:10,407][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.6790761947631836, cross_entropy: 2.6790761947631836 +[2025-04-29 19:58:11,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 2.4652953147888184, cross_entropy: 2.4652953147888184 +[2025-04-29 19:58:14,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 0.5974408388137817, cross_entropy: 0.5974408388137817 +[2025-04-29 19:58:15,228][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 1.4791555404663086, cross_entropy: 1.4791555404663086 +[2025-04-29 19:58:17,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 1.9220952987670898, cross_entropy: 1.9220952987670898 +[2025-04-29 19:58:18,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 0.8718112111091614, cross_entropy: 0.8718112111091614 +[2025-04-29 19:58:21,656][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 0.9381017684936523, cross_entropy: 0.9381017684936523 +[2025-04-29 19:58:22,718][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 1.6568294763565063, cross_entropy: 1.6568294763565063 +[2025-04-29 19:58:26,038][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 1.9715898036956787, cross_entropy: 1.9715898036956787 +[2025-04-29 19:58:27,076][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.157487392425537, cross_entropy: 2.157487392425537 +[2025-04-29 19:58:29,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.536912441253662, cross_entropy: 2.536912441253662 +[2025-04-29 19:58:30,610][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 0.5051776170730591, cross_entropy: 0.5051776170730591 +[2025-04-29 19:58:33,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.153531551361084, cross_entropy: 2.153531551361084 +[2025-04-29 19:58:34,666][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 0.67914217710495, cross_entropy: 0.67914217710495 +[2025-04-29 19:58:37,762][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 2.2799503803253174, cross_entropy: 2.2799503803253174 +[2025-04-29 19:58:38,824][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 0.5935670137405396, cross_entropy: 0.5935670137405396 +[2025-04-29 19:58:41,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.2042040824890137, cross_entropy: 1.2042040824890137 +[2025-04-29 19:58:43,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 0.792945384979248, cross_entropy: 0.792945384979248 +[2025-04-29 19:58:46,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.8065762519836426, cross_entropy: 2.8065762519836426 +[2025-04-29 19:58:47,210][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 2.671229362487793, cross_entropy: 2.671229362487793 +[2025-04-29 19:58:49,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 0.7215714454650879, cross_entropy: 0.7215714454650879 +[2025-04-29 19:58:50,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 2.5145175457000732, cross_entropy: 2.5145175457000732 +[2025-04-29 19:58:53,734][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 0.5111016035079956, cross_entropy: 0.5111016035079956 +[2025-04-29 19:58:54,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.052002191543579, cross_entropy: 2.052002191543579 +[2025-04-29 19:58:58,071][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 1.027679443359375, cross_entropy: 1.027679443359375 +[2025-04-29 19:58:59,119][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 1.1297175884246826, cross_entropy: 1.1297175884246826 +[2025-04-29 19:59:01,731][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 2.4068264961242676, cross_entropy: 2.4068264961242676 +[2025-04-29 19:59:02,789][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 1.8813332319259644, cross_entropy: 1.8813332319259644 +[2025-04-29 19:59:05,746][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.8740525245666504, cross_entropy: 1.8740525245666504 +[2025-04-29 19:59:06,804][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 0.7017109394073486, cross_entropy: 0.7017109394073486 +[2025-04-29 19:59:09,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 0.6215419769287109, cross_entropy: 0.6215419769287109 +[2025-04-29 19:59:10,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 1.9710898399353027, cross_entropy: 1.9710898399353027 +[2025-04-29 19:59:13,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 0.7351009845733643, cross_entropy: 0.7351009845733643 +[2025-04-29 19:59:14,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 1.2042983770370483, cross_entropy: 1.2042983770370483 +[2025-04-29 19:59:17,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 2.0722718238830566, cross_entropy: 2.0722718238830566 +[2025-04-29 19:59:18,632][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 0.5759618282318115, cross_entropy: 0.5759618282318115 +[2025-04-29 19:59:21,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 0.6161344051361084, cross_entropy: 0.6161344051361084 +[2025-04-29 19:59:22,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 0.7375133037567139, cross_entropy: 0.7375133037567139 +[2025-04-29 19:59:25,403][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.6852869987487793, cross_entropy: 1.6852869987487793 +[2025-04-29 19:59:26,461][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.4373639225959778, cross_entropy: 0.4373639225959778 +[2025-04-29 19:59:29,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.345047950744629, cross_entropy: 1.345047950744629 +[2025-04-29 19:59:30,744][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 0.8300265669822693, cross_entropy: 0.8300265669822693 +[2025-04-29 19:59:33,367][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 0.7165321111679077, cross_entropy: 0.7165321111679077 +[2025-04-29 19:59:34,398][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.659231424331665, cross_entropy: 1.659231424331665 +[2025-04-29 19:59:37,081][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 0.7094489336013794, cross_entropy: 0.7094489336013794 +[2025-04-29 19:59:38,147][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 0.6507511138916016, cross_entropy: 0.6507511138916016 +[2025-04-29 19:59:40,870][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 0.997836709022522, cross_entropy: 0.997836709022522 +[2025-04-29 19:59:41,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 2.315511703491211, cross_entropy: 2.315511703491211 +[2025-04-29 19:59:44,936][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 0.8980294466018677, cross_entropy: 0.8980294466018677 +[2025-04-29 19:59:46,000][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 0.9383572340011597, cross_entropy: 0.9383572340011597 +[2025-04-29 19:59:48,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 1.4941455125808716, cross_entropy: 1.4941455125808716 +[2025-04-29 19:59:49,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 1.8184051513671875, cross_entropy: 1.8184051513671875 +[2025-04-29 19:59:52,633][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 2.278754234313965, cross_entropy: 2.278754234313965 +[2025-04-29 19:59:53,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 2.5461435317993164, cross_entropy: 2.5461435317993164 +[2025-04-29 19:59:56,285][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.8101760149002075, cross_entropy: 1.8101760149002075 +[2025-04-29 19:59:57,346][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.0271074771881104, cross_entropy: 2.0271074771881104 +[2025-04-29 20:00:00,453][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 2.040842056274414, cross_entropy: 2.040842056274414 +[2025-04-29 20:00:01,510][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 2.428715467453003, cross_entropy: 2.428715467453003 +[2025-04-29 20:00:04,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.3980791568756104, cross_entropy: 1.3980791568756104 +[2025-04-29 20:00:05,370][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 0.9398933053016663, cross_entropy: 0.9398933053016663 +[2025-04-29 20:00:07,613][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 0.7225912809371948, cross_entropy: 0.7225912809371948 +[2025-04-29 20:00:08,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.5519639253616333, cross_entropy: 0.5519639253616333 +[2025-04-29 20:00:11,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 0.7138378024101257, cross_entropy: 0.7138378024101257 +[2025-04-29 20:00:12,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 2.5954928398132324, cross_entropy: 2.5954928398132324 +[2025-04-29 20:00:15,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 0.6120154857635498, cross_entropy: 0.6120154857635498 +[2025-04-29 20:00:16,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 0.6782779693603516, cross_entropy: 0.6782779693603516 +[2025-04-29 20:00:18,761][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 0.5091458559036255, cross_entropy: 0.5091458559036255 +[2025-04-29 20:00:19,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 2.064210891723633, cross_entropy: 2.064210891723633 +[2025-04-29 20:00:22,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 1.1022920608520508, cross_entropy: 1.1022920608520508 +[2025-04-29 20:00:23,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 2.2302229404449463, cross_entropy: 2.2302229404449463 +[2025-04-29 20:00:25,986][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.198800563812256, cross_entropy: 2.198800563812256 +[2025-04-29 20:00:27,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 0.6889293193817139, cross_entropy: 0.6889293193817139 +[2025-04-29 20:00:30,164][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.7723064422607422, cross_entropy: 1.7723064422607422 +[2025-04-29 20:00:31,223][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.4752731323242188, cross_entropy: 1.4752731323242188 +[2025-04-29 20:00:34,128][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.021897315979004, cross_entropy: 2.021897315979004 +[2025-04-29 20:00:35,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 1.4122246503829956, cross_entropy: 1.4122246503829956 +[2025-04-29 20:00:38,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.3071367740631104, cross_entropy: 1.3071367740631104 +[2025-04-29 20:00:39,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.7204065322875977, cross_entropy: 1.7204065322875977 +[2025-04-29 20:00:42,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 1.2994639873504639, cross_entropy: 1.2994639873504639 +[2025-04-29 20:00:43,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 2.4571902751922607, cross_entropy: 2.4571902751922607 +[2025-04-29 20:00:45,755][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.5233402252197266, cross_entropy: 1.5233402252197266 +[2025-04-29 20:00:46,818][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 2.122973918914795, cross_entropy: 2.122973918914795 +[2025-04-29 20:00:49,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 0.5693644285202026, cross_entropy: 0.5693644285202026 +[2025-04-29 20:00:50,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.9574121236801147, cross_entropy: 1.9574121236801147 +[2025-04-29 20:00:53,325][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 0.5909741520881653, cross_entropy: 0.5909741520881653 +[2025-04-29 20:00:54,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 1.4765534400939941, cross_entropy: 1.4765534400939941 +[2025-04-29 20:00:57,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 0.8846163749694824, cross_entropy: 0.8846163749694824 +[2025-04-29 20:00:58,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 1.952152967453003, cross_entropy: 1.952152967453003 +[2025-04-29 20:01:00,535][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.9124858379364014, cross_entropy: 1.9124858379364014 +[2025-04-29 20:01:01,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.6842658519744873, cross_entropy: 0.6842658519744873 +[2025-04-29 20:01:05,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.313018798828125, cross_entropy: 2.313018798828125 +[2025-04-29 20:01:06,157][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 0.8007766008377075, cross_entropy: 0.8007766008377075 +[2025-04-29 20:01:08,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 1.9420843124389648, cross_entropy: 1.9420843124389648 +[2025-04-29 20:01:09,558][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 0.525450587272644, cross_entropy: 0.525450587272644 +[2025-04-29 20:01:12,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 1.2443077564239502, cross_entropy: 1.2443077564239502 +[2025-04-29 20:01:13,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 0.7084066867828369, cross_entropy: 0.7084066867828369 +[2025-04-29 20:01:16,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 0.5644437074661255, cross_entropy: 0.5644437074661255 +[2025-04-29 20:01:17,502][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 0.8441133499145508, cross_entropy: 0.8441133499145508 +[2025-04-29 20:01:20,109][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.5126322507858276, cross_entropy: 1.5126322507858276 +[2025-04-29 20:01:21,141][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 0.6796842813491821, cross_entropy: 0.6796842813491821 +[2025-04-29 20:01:24,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.0537936687469482, cross_entropy: 1.0537936687469482 +[2025-04-29 20:01:25,701][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 0.5915060043334961, cross_entropy: 0.5915060043334961 +[2025-04-29 20:01:28,076][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 0.6233249306678772, cross_entropy: 0.6233249306678772 +[2025-04-29 20:01:29,111][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.0014522075653076, cross_entropy: 1.0014522075653076 +[2025-04-29 20:01:31,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 2.5103209018707275, cross_entropy: 2.5103209018707275 +[2025-04-29 20:01:32,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.5313775539398193, cross_entropy: 2.5313775539398193 +[2025-04-29 20:01:35,887][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 2.424617290496826, cross_entropy: 2.424617290496826 +[2025-04-29 20:01:36,960][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 0.8787263035774231, cross_entropy: 0.8787263035774231 +[2025-04-29 20:01:40,093][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 0.8241503834724426, cross_entropy: 0.8241503834724426 +[2025-04-29 20:01:41,127][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 2.263190746307373, cross_entropy: 2.263190746307373 +[2025-04-29 20:01:43,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 1.250730276107788, cross_entropy: 1.250730276107788 +[2025-04-29 20:01:44,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 2.6108036041259766, cross_entropy: 2.6108036041259766 +[2025-04-29 20:01:48,183][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 0.6206092238426208, cross_entropy: 0.6206092238426208 +[2025-04-29 20:01:49,241][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 2.4590249061584473, cross_entropy: 2.4590249061584473 +[2025-04-29 20:01:52,477][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 0.6599764823913574, cross_entropy: 0.6599764823913574 +[2025-04-29 20:01:53,541][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 2.5678188800811768, cross_entropy: 2.5678188800811768 +[2025-04-29 20:01:57,152][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 2.72693133354187, cross_entropy: 2.72693133354187 +[2025-04-29 20:01:58,209][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.2346572875976562, cross_entropy: 1.2346572875976562 +[2025-04-29 20:02:00,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 1.2898321151733398, cross_entropy: 1.2898321151733398 +[2025-04-29 20:02:01,788][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 2.2727084159851074, cross_entropy: 2.2727084159851074 +[2025-04-29 20:02:04,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 1.0534343719482422, cross_entropy: 1.0534343719482422 +[2025-04-29 20:02:05,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.9004366397857666, cross_entropy: 1.9004366397857666 +[2025-04-29 20:02:08,200][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 0.39245861768722534, cross_entropy: 0.39245861768722534 +[2025-04-29 20:02:09,254][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 0.6868022084236145, cross_entropy: 0.6868022084236145 +[2025-04-29 20:02:12,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.505312442779541, cross_entropy: 2.505312442779541 +[2025-04-29 20:02:13,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 1.868249773979187, cross_entropy: 1.868249773979187 +[2025-04-29 20:02:16,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.5746922492980957, cross_entropy: 2.5746922492980957 +[2025-04-29 20:02:17,680][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 1.5406982898712158, cross_entropy: 1.5406982898712158 +[2025-04-29 20:02:20,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 2.716385841369629, cross_entropy: 2.716385841369629 +[2025-04-29 20:02:21,704][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.1296250820159912, cross_entropy: 1.1296250820159912 +[2025-04-29 20:02:25,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 0.6506854295730591, cross_entropy: 0.6506854295730591 +[2025-04-29 20:02:26,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.415806770324707, cross_entropy: 2.415806770324707 +[2025-04-29 20:02:29,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 0.41324368119239807, cross_entropy: 0.41324368119239807 +[2025-04-29 20:02:30,232][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.5996437072753906, cross_entropy: 2.5996437072753906 +[2025-04-29 20:02:33,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 0.7242239117622375, cross_entropy: 0.7242239117622375 +[2025-04-29 20:02:34,130][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.3950233459472656, cross_entropy: 2.3950233459472656 +[2025-04-29 20:02:36,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 0.48498761653900146, cross_entropy: 0.48498761653900146 +[2025-04-29 20:02:37,951][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 0.629179835319519, cross_entropy: 0.629179835319519 +[2025-04-29 20:02:40,698][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 0.9841549396514893, cross_entropy: 0.9841549396514893 +[2025-04-29 20:02:41,734][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 0.6834989786148071, cross_entropy: 0.6834989786148071 +[2025-04-29 20:02:45,195][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.1686137914657593, cross_entropy: 1.1686137914657593 +[2025-04-29 20:02:46,265][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 0.9606360197067261, cross_entropy: 0.9606360197067261 +[2025-04-29 20:02:48,809][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 2.382469654083252, cross_entropy: 2.382469654083252 +[2025-04-29 20:02:49,872][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 1.331201434135437, cross_entropy: 1.331201434135437 +[2025-04-29 20:02:52,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 1.7310822010040283, cross_entropy: 1.7310822010040283 +[2025-04-29 20:02:53,705][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.4600043296813965, cross_entropy: 2.4600043296813965 +[2025-04-29 20:02:56,141][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 2.321091890335083, cross_entropy: 2.321091890335083 +[2025-04-29 20:02:57,194][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.307243824005127, cross_entropy: 2.307243824005127 +[2025-04-29 20:02:59,753][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 0.688500165939331, cross_entropy: 0.688500165939331 +[2025-04-29 20:03:00,812][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.7721819877624512, cross_entropy: 0.7721819877624512 +[2025-04-29 20:03:03,946][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 0.6138001680374146, cross_entropy: 0.6138001680374146 +[2025-04-29 20:03:04,979][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.3293471336364746, cross_entropy: 2.3293471336364746 +[2025-04-29 20:03:08,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 0.7403662204742432, cross_entropy: 0.7403662204742432 +[2025-04-29 20:03:09,503][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.6646846532821655, cross_entropy: 0.6646846532821655 +[2025-04-29 20:03:12,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 0.7521991729736328, cross_entropy: 0.7521991729736328 +[2025-04-29 20:03:13,521][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.8974436521530151, cross_entropy: 0.8974436521530151 +[2025-04-29 20:03:16,210][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 0.4658556878566742, cross_entropy: 0.4658556878566742 +[2025-04-29 20:03:17,270][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.9389028549194336, cross_entropy: 1.9389028549194336 +[2025-04-29 20:03:19,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 0.5674026608467102, cross_entropy: 0.5674026608467102 +[2025-04-29 20:03:20,595][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 1.9200754165649414, cross_entropy: 1.9200754165649414 +[2025-04-29 20:03:23,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.9799079895019531, cross_entropy: 1.9799079895019531 +[2025-04-29 20:03:25,044][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 1.9811304807662964, cross_entropy: 1.9811304807662964 +[2025-04-29 20:03:27,549][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 0.7920829057693481, cross_entropy: 0.7920829057693481 +[2025-04-29 20:03:28,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.5343375205993652, cross_entropy: 0.5343375205993652 +[2025-04-29 20:03:31,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 2.366288185119629, cross_entropy: 2.366288185119629 +[2025-04-29 20:03:32,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.5131144523620605, cross_entropy: 2.5131144523620605 +[2025-04-29 20:03:35,466][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.4513511657714844, cross_entropy: 1.4513511657714844 +[2025-04-29 20:03:36,497][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.6691676378250122, cross_entropy: 1.6691676378250122 +[2025-04-29 20:03:40,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 1.7617309093475342, cross_entropy: 1.7617309093475342 +[2025-04-29 20:03:41,293][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 0.9813408851623535, cross_entropy: 0.9813408851623535 +[2025-04-29 20:03:44,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 1.0720781087875366, cross_entropy: 1.0720781087875366 +[2025-04-29 20:03:45,905][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 2.3360977172851562, cross_entropy: 2.3360977172851562 +[2025-04-29 20:03:48,129][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 2.1083154678344727, cross_entropy: 2.1083154678344727 +[2025-04-29 20:03:49,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 0.6510276794433594, cross_entropy: 0.6510276794433594 +[2025-04-29 20:03:51,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 2.2414417266845703, cross_entropy: 2.2414417266845703 +[2025-04-29 20:03:52,561][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 0.5244572758674622, cross_entropy: 0.5244572758674622 +[2025-04-29 20:03:55,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.9082868099212646, cross_entropy: 2.9082868099212646 +[2025-04-29 20:03:56,572][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 1.5383477210998535, cross_entropy: 1.5383477210998535 +[2025-04-29 20:03:59,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 2.4713621139526367, cross_entropy: 2.4713621139526367 +[2025-04-29 20:04:00,539][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 0.7730343341827393, cross_entropy: 0.7730343341827393 +[2025-04-29 20:04:03,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 0.5076649785041809, cross_entropy: 0.5076649785041809 +[2025-04-29 20:04:04,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.1952757835388184, cross_entropy: 2.1952757835388184 +[2025-04-29 20:04:07,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 0.7291107773780823, cross_entropy: 0.7291107773780823 +[2025-04-29 20:04:08,308][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.8222265243530273, cross_entropy: 2.8222265243530273 +[2025-04-29 20:04:11,946][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 0.49370425939559937, cross_entropy: 0.49370425939559937 +[2025-04-29 20:04:12,977][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 1.7618505954742432, cross_entropy: 1.7618505954742432 +[2025-04-29 20:04:16,547][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 2.033519744873047, cross_entropy: 2.033519744873047 +[2025-04-29 20:04:17,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 0.5363760590553284, cross_entropy: 0.5363760590553284 +[2025-04-29 20:04:20,585][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 0.6351534128189087, cross_entropy: 0.6351534128189087 +[2025-04-29 20:04:21,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 0.9666733741760254, cross_entropy: 0.9666733741760254 +[2025-04-29 20:04:24,826][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 0.8166824579238892, cross_entropy: 0.8166824579238892 +[2025-04-29 20:04:25,884][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 2.168552875518799, cross_entropy: 2.168552875518799 +[2025-04-29 20:04:27,788][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 1.398280382156372, cross_entropy: 1.398280382156372 +[2025-04-29 20:04:28,819][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 0.6035119891166687, cross_entropy: 0.6035119891166687 +[2025-04-29 20:04:32,314][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 2.2359414100646973, cross_entropy: 2.2359414100646973 +[2025-04-29 20:04:33,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.514298677444458, cross_entropy: 2.514298677444458 +[2025-04-29 20:04:36,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 1.103128433227539, cross_entropy: 1.103128433227539 +[2025-04-29 20:04:37,149][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 2.731416702270508, cross_entropy: 2.731416702270508 +[2025-04-29 20:04:40,020][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 0.7409240007400513, cross_entropy: 0.7409240007400513 +[2025-04-29 20:04:41,073][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 1.0071179866790771, cross_entropy: 1.0071179866790771 +[2025-04-29 20:04:43,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 0.5140854716300964, cross_entropy: 0.5140854716300964 +[2025-04-29 20:04:44,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.976421594619751, cross_entropy: 2.976421594619751 +[2025-04-29 20:04:48,250][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 0.6578873991966248, cross_entropy: 0.6578873991966248 +[2025-04-29 20:04:49,285][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.9876092672348022, cross_entropy: 1.9876092672348022 +[2025-04-29 20:04:52,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 0.6403653025627136, cross_entropy: 0.6403653025627136 +[2025-04-29 20:04:53,083][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 0.4803192615509033, cross_entropy: 0.4803192615509033 +[2025-04-29 20:04:55,040][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 0.7864234447479248, cross_entropy: 0.7864234447479248 +[2025-04-29 20:04:56,100][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.733766555786133, cross_entropy: 2.733766555786133 +[2025-04-29 20:04:59,079][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.648959755897522, cross_entropy: 1.648959755897522 +[2025-04-29 20:05:00,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 1.1843544244766235, cross_entropy: 1.1843544244766235 +[2025-04-29 20:05:03,412][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 2.7995526790618896, cross_entropy: 2.7995526790618896 +[2025-04-29 20:05:04,446][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.3649448156356812, cross_entropy: 1.3649448156356812 +[2025-04-29 20:05:07,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 2.292698860168457, cross_entropy: 2.292698860168457 +[2025-04-29 20:05:08,373][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 0.6359591484069824, cross_entropy: 0.6359591484069824 +[2025-04-29 20:05:11,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.2482845783233643, cross_entropy: 1.2482845783233643 +[2025-04-29 20:05:12,205][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 0.7064664959907532, cross_entropy: 0.7064664959907532 +[2025-04-29 20:05:14,835][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 0.7851331233978271, cross_entropy: 0.7851331233978271 +[2025-04-29 20:05:15,868][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 0.5195677280426025, cross_entropy: 0.5195677280426025 +[2025-04-29 20:05:19,430][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 1.1934776306152344, cross_entropy: 1.1934776306152344 +[2025-04-29 20:05:20,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 2.665579319000244, cross_entropy: 2.665579319000244 +[2025-04-29 20:05:23,682][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.8235068321228027, cross_entropy: 1.8235068321228027 +[2025-04-29 20:05:24,741][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.5517436265945435, cross_entropy: 1.5517436265945435 +[2025-04-29 20:05:27,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 0.6603729128837585, cross_entropy: 0.6603729128837585 +[2025-04-29 20:05:28,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.1228482723236084, cross_entropy: 2.1228482723236084 +[2025-04-29 20:05:31,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.6004207134246826, cross_entropy: 2.6004207134246826 +[2025-04-29 20:05:32,356][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.4580247402191162, cross_entropy: 0.4580247402191162 +[2025-04-29 20:05:35,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.017408609390259, cross_entropy: 2.017408609390259 +[2025-04-29 20:05:36,197][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 1.4492751359939575, cross_entropy: 1.4492751359939575 +[2025-04-29 20:05:39,340][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 2.220369815826416, cross_entropy: 2.220369815826416 +[2025-04-29 20:05:40,403][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.9266130924224854, cross_entropy: 2.9266130924224854 +[2025-04-29 20:05:43,192][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 0.638807475566864, cross_entropy: 0.638807475566864 +[2025-04-29 20:05:44,250][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 0.8153102397918701, cross_entropy: 0.8153102397918701 +[2025-04-29 20:05:46,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 0.6767921447753906, cross_entropy: 0.6767921447753906 +[2025-04-29 20:05:48,013][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.59810209274292, cross_entropy: 2.59810209274292 +[2025-04-29 20:05:49,914][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 1.091876745223999, cross_entropy: 1.091876745223999 +[2025-04-29 20:05:50,973][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 1.0338351726531982, cross_entropy: 1.0338351726531982 +[2025-04-29 20:05:53,496][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.6918673515319824, cross_entropy: 1.6918673515319824 +[2025-04-29 20:05:54,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 2.553251266479492, cross_entropy: 2.553251266479492 +[2025-04-29 20:05:57,022][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 1.3593566417694092, cross_entropy: 1.3593566417694092 +[2025-04-29 20:05:58,542][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 0.7460983395576477, cross_entropy: 0.7460983395576477 +[2025-04-29 20:06:00,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 0.6159965395927429, cross_entropy: 0.6159965395927429 +[2025-04-29 20:06:02,478][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.306502103805542, cross_entropy: 1.306502103805542 +[2025-04-29 20:06:04,445][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 1.9956485033035278, cross_entropy: 1.9956485033035278 +[2025-04-29 20:06:06,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 0.8490225672721863, cross_entropy: 0.8490225672721863 +[2025-04-29 20:06:08,110][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 1.2793750762939453, cross_entropy: 1.2793750762939453 +[2025-04-29 20:06:09,847][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 0.9733884334564209, cross_entropy: 0.9733884334564209 +[2025-04-29 20:06:11,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.629246711730957, cross_entropy: 2.629246711730957 +[2025-04-29 20:06:13,626][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.6874666213989258, cross_entropy: 0.6874666213989258 +[2025-04-29 20:06:15,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 0.597028374671936, cross_entropy: 0.597028374671936 +[2025-04-29 20:06:17,517][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.540539026260376, cross_entropy: 1.540539026260376 +[2025-04-29 20:06:19,940][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 0.32432666420936584, cross_entropy: 0.32432666420936584 +[2025-04-29 20:06:21,541][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.802253246307373, cross_entropy: 0.802253246307373 +[2025-04-29 20:06:24,337][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 1.7851279973983765, cross_entropy: 1.7851279973983765 +[2025-04-29 20:06:25,732][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 0.8206468820571899, cross_entropy: 0.8206468820571899 +[2025-04-29 20:06:29,274][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.7707297801971436, cross_entropy: 0.7707297801971436 +[2025-04-29 20:06:30,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 0.4930069148540497, cross_entropy: 0.4930069148540497 +[2025-04-29 20:06:33,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.7170817852020264, cross_entropy: 2.7170817852020264 +[2025-04-29 20:06:34,213][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.743750810623169, cross_entropy: 2.743750810623169 +[2025-04-29 20:06:37,207][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.450622797012329, cross_entropy: 2.450622797012329 +[2025-04-29 20:06:38,239][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.0201897621154785, cross_entropy: 2.0201897621154785 +[2025-04-29 20:06:41,379][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 2.5954885482788086, cross_entropy: 2.5954885482788086 +[2025-04-29 20:06:42,437][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 1.7491048574447632, cross_entropy: 1.7491048574447632 +[2025-04-29 20:06:45,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 2.6931405067443848, cross_entropy: 2.6931405067443848 +[2025-04-29 20:06:46,553][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.5097887516021729, cross_entropy: 0.5097887516021729 +[2025-04-29 20:06:49,194][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 0.9655284881591797, cross_entropy: 0.9655284881591797 +[2025-04-29 20:06:50,250][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 0.906673014163971, cross_entropy: 0.906673014163971 +[2025-04-29 20:06:53,374][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.7576937675476074, cross_entropy: 2.7576937675476074 +[2025-04-29 20:06:54,434][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 2.444385051727295, cross_entropy: 2.444385051727295 +[2025-04-29 20:06:57,551][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 1.4783093929290771, cross_entropy: 1.4783093929290771 +[2025-04-29 20:06:58,620][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 1.7583417892456055, cross_entropy: 1.7583417892456055 +[2025-04-29 20:07:01,149][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.1606156826019287, cross_entropy: 2.1606156826019287 +[2025-04-29 20:07:02,180][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 2.160050392150879, cross_entropy: 2.160050392150879 +[2025-04-29 20:07:06,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 2.313713550567627, cross_entropy: 2.313713550567627 +[2025-04-29 20:07:07,752][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.112186908721924, cross_entropy: 2.112186908721924 +[2025-04-29 20:07:10,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 2.4240641593933105, cross_entropy: 2.4240641593933105 +[2025-04-29 20:07:11,226][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 0.7303638458251953, cross_entropy: 0.7303638458251953 +[2025-04-29 20:07:13,580][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 2.389268398284912, cross_entropy: 2.389268398284912 +[2025-04-29 20:07:14,611][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 0.9196181297302246, cross_entropy: 0.9196181297302246 +[2025-04-29 20:07:17,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 2.3793067932128906, cross_entropy: 2.3793067932128906 +[2025-04-29 20:07:18,655][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.195853590965271, cross_entropy: 1.195853590965271 +[2025-04-29 20:07:21,181][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 0.6375090479850769, cross_entropy: 0.6375090479850769 +[2025-04-29 20:07:22,246][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 1.7099609375, cross_entropy: 1.7099609375 +[2025-04-29 20:07:24,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 1.3424632549285889, cross_entropy: 1.3424632549285889 +[2025-04-29 20:07:25,942][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 0.7402738332748413, cross_entropy: 0.7402738332748413 +[2025-04-29 20:07:29,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 0.7587871551513672, cross_entropy: 0.7587871551513672 +[2025-04-29 20:07:30,182][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.117631673812866, cross_entropy: 2.117631673812866 +[2025-04-29 20:07:32,731][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.523974895477295, cross_entropy: 2.523974895477295 +[2025-04-29 20:07:33,796][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 0.5661224126815796, cross_entropy: 0.5661224126815796 +[2025-04-29 20:07:36,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 2.329174280166626, cross_entropy: 2.329174280166626 +[2025-04-29 20:07:37,564][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 1.7811096906661987, cross_entropy: 1.7811096906661987 +[2025-04-29 20:07:40,553][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 1.1022040843963623, cross_entropy: 1.1022040843963623 +[2025-04-29 20:07:41,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.433182716369629, cross_entropy: 2.433182716369629 +[2025-04-29 20:07:45,004][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 2.0741658210754395, cross_entropy: 2.0741658210754395 +[2025-04-29 20:07:46,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.9835072755813599, cross_entropy: 1.9835072755813599 +[2025-04-29 20:07:48,130][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.717120885848999, cross_entropy: 1.717120885848999 +[2025-04-29 20:07:49,200][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 2.574334144592285, cross_entropy: 2.574334144592285 +[2025-04-29 20:07:52,027][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 1.8797367811203003, cross_entropy: 1.8797367811203003 +[2025-04-29 20:07:53,091][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 0.735014796257019, cross_entropy: 0.735014796257019 +[2025-04-29 20:07:55,815][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 2.479063034057617, cross_entropy: 2.479063034057617 +[2025-04-29 20:07:56,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 0.7309664487838745, cross_entropy: 0.7309664487838745 +[2025-04-29 20:08:00,088][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 0.6465802192687988, cross_entropy: 0.6465802192687988 +[2025-04-29 20:08:01,150][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.521321177482605, cross_entropy: 1.521321177482605 +[2025-04-29 20:08:04,822][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.769235134124756, cross_entropy: 2.769235134124756 +[2025-04-29 20:08:05,856][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.9302380084991455, cross_entropy: 1.9302380084991455 +[2025-04-29 20:08:08,625][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 0.822219729423523, cross_entropy: 0.822219729423523 +[2025-04-29 20:08:09,690][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 0.7482209205627441, cross_entropy: 0.7482209205627441 +[2025-04-29 20:08:11,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 1.9250344038009644, cross_entropy: 1.9250344038009644 +[2025-04-29 20:08:12,975][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 1.2902247905731201, cross_entropy: 1.2902247905731201 +[2025-04-29 20:08:15,654][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.036515951156616, cross_entropy: 2.036515951156616 +[2025-04-29 20:08:16,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 0.8169623613357544, cross_entropy: 0.8169623613357544 +[2025-04-29 20:08:19,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.829627275466919, cross_entropy: 1.829627275466919 +[2025-04-29 20:08:20,682][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.7355433702468872, cross_entropy: 0.7355433702468872 +[2025-04-29 20:08:23,272][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 0.7063449621200562, cross_entropy: 0.7063449621200562 +[2025-04-29 20:08:24,308][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 0.6170490980148315, cross_entropy: 0.6170490980148315 +[2025-04-29 20:08:27,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 0.8168662190437317, cross_entropy: 0.8168662190437317 +[2025-04-29 20:08:28,173][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.0773518085479736, cross_entropy: 1.0773518085479736 +[2025-04-29 20:08:30,812][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 1.1394866704940796, cross_entropy: 1.1394866704940796 +[2025-04-29 20:08:31,892][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.0312321186065674, cross_entropy: 1.0312321186065674 +[2025-04-29 20:08:35,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 0.701799213886261, cross_entropy: 0.701799213886261 +[2025-04-29 20:08:36,407][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.1279540061950684, cross_entropy: 2.1279540061950684 +[2025-04-29 20:08:38,586][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 2.819459915161133, cross_entropy: 2.819459915161133 +[2025-04-29 20:08:39,818][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.973297357559204, cross_entropy: 1.973297357559204 +[2025-04-29 20:08:41,777][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 0.49982109665870667, cross_entropy: 0.49982109665870667 +[2025-04-29 20:08:43,808][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 0.8373639583587646, cross_entropy: 0.8373639583587646 +[2025-04-29 20:08:46,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 0.7683126330375671, cross_entropy: 0.7683126330375671 +[2025-04-29 20:08:48,261][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.6626133918762207, cross_entropy: 2.6626133918762207 +[2025-04-29 20:08:50,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 2.6104869842529297, cross_entropy: 2.6104869842529297 +[2025-04-29 20:08:51,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.6827168464660645, cross_entropy: 2.6827168464660645 +[2025-04-29 20:08:53,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 2.6291446685791016, cross_entropy: 2.6291446685791016 +[2025-04-29 20:08:55,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.8927397727966309, cross_entropy: 1.8927397727966309 +[2025-04-29 20:08:57,552][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 0.9493324756622314, cross_entropy: 0.9493324756622314 +[2025-04-29 20:08:58,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 0.4930175542831421, cross_entropy: 0.4930175542831421 +[2025-04-29 20:09:01,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 0.5719007253646851, cross_entropy: 0.5719007253646851 +[2025-04-29 20:09:02,705][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.7665318250656128, cross_entropy: 0.7665318250656128 +[2025-04-29 20:09:05,684][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 0.5925160646438599, cross_entropy: 0.5925160646438599 +[2025-04-29 20:09:06,772][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.3959686756134033, cross_entropy: 1.3959686756134033 +[2025-04-29 20:09:09,264][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.5562994480133057, cross_entropy: 1.5562994480133057 +[2025-04-29 20:09:10,199][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 2.3024072647094727, cross_entropy: 2.3024072647094727 +[2025-04-29 20:12:00,272][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.4857884645462036, cross_entropy: 1.4857884645462036 +[2025-04-29 20:12:00,273][BaseTrainer][INFO] - [Epoch 10/10] (validation) 0.9773313403129578, cross_entropy: 0.9773313403129578 +[2025-04-29 20:12:01,166][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/best_epoch.pth. +[2025-04-29 20:12:01,677][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/epoch10.pth. +[2025-04-29 20:12:02,481][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. +[2025-04-29 20:12:03,314][BaseTrainer][INFO] - Save model: ./exp/20250429-174600/model/last.pth. diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/best_epoch.pth b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..f441391139f26be7d966e355dab9bb206a817f3e --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86838ad0507b599924a8eca92c0e9295cbd0fdd4858fd662153e1bdd4f710914 +size 335992534 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/last.pth b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..60e5cb8222541cc9d1f843390e1347e77f91b698 --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/exp/20250429-174600/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e05e2aaadfca28516aeda2d907ddcba8accdb5118e03ce38f63ff28395b8a155 +size 335953390 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-091731/events.out.tfevents.1746371437.MacBook-Pro-2.local.7605.0 b/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-091731/events.out.tfevents.1746371437.MacBook-Pro-2.local.7605.0 new file mode 100644 index 0000000000000000000000000000000000000000..3808289b4941580f61cd6e63607d96448fe40e9d --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-091731/events.out.tfevents.1746371437.MacBook-Pro-2.local.7605.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123ef3c4dcd02d0f1242a960e9c030ab8bddee904817d8759f7f1f2022f6dde1 +size 472294 diff --git a/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-174600/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.1 b/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-174600/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.1 new file mode 100644 index 0000000000000000000000000000000000000000..6d6678668c5cb8d3eee0f44b46267b42bf4016bf --- /dev/null +++ b/recipes/BirdCLEF2025/ConvNeXtTiny/tensorboard/20250429-174600/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc80cd9207cda3799c3d6d15f9d93126653ea9174346166bb454b8c60954e6e +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d424837fa3376cb8f4abbde0dc7d402dad5e9fbb --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/README.md @@ -0,0 +1,7 @@ +system=default_seed-0 +data=birdclef2025_5s +train=birdclef2025_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.479 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7de2abf027f8e9c3a751fddf055b585bea98e991 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/config.yaml @@ -0,0 +1,219 @@ +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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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_5s/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_5s/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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250427-104215 + tensorboard_dir: ./tensorboard/20250427-104215 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cfe980ceb9f37de2bffbc21e029891fec1d98100 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250427-104215/log/20250427-104218 + sweep: + dir: multirun/${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/20250427-104215/log/20250427-104218 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_5s + - train=birdclef2025_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_5s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_5s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250427-104215 + - train.output.tensorboard_dir=./tensorboard/20250427-104215 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_5s,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_5s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_5s/list/validation.txt,train.output.exp_dir=./exp/20250427-104215,train.output.tensorboard_dir=./tensorboard/20250427-104215,train.resume.continue_from=,train=birdclef2025_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/20250427-104215/log/20250427-104218 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_5s + 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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0337e2bfbf81435912b904dac0ee437dbd966fed --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_5s +- train=birdclef2025_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_5s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_5s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250427-104215 +- train.output.tensorboard_dir=./tensorboard/20250427-104215 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..94e0950e48aa7925d536c37a5ad5d0837455e357 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/.hydra/resolved_config.yaml @@ -0,0 +1,278 @@ +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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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_5s/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_5s/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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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: 5 + decode_audio_as_waveform: true + decode_audio_as_monoral: true + training: true + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2024BaselineMelSpectrogram + 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: 5 + 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/20250427-104215 + tensorboard_dir: ./tensorboard/20250427-104215 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250427-104215/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250427-104215/model/epoch{epoch}.pth + last: + path: ./exp/20250427-104215/model/last.pth + best_epoch: + path: ./exp/20250427-104215/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/train.log new file mode 100644 index 0000000000000000000000000000000000000000..4c3603aaec3b23592308d31fd1a33e169e4b11be --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/log/20250427-104218/train.log @@ -0,0 +1,4277 @@ +[2025-04-27 10:42:46,582][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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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_5s/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_5s/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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250427-104215 + tensorboard_dir: ./tensorboard/20250427-104215 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-27 10:42:46,582][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) + ) +) +[2025-04-27 10:42:46,587][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-27 10:42:52,791][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.402828216552734, cross_entropy: 5.402828216552734 +[2025-04-27 10:42:52,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.358403205871582, cross_entropy: 5.358403205871582 +[2025-04-27 10:42:53,128][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.286766052246094, cross_entropy: 5.286766052246094 +[2025-04-27 10:42:53,455][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.270862579345703, cross_entropy: 5.270862579345703 +[2025-04-27 10:42:55,229][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.16791296005249, cross_entropy: 5.16791296005249 +[2025-04-27 10:42:56,408][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.1542463302612305, cross_entropy: 5.1542463302612305 +[2025-04-27 10:42:57,913][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 5.072203636169434, cross_entropy: 5.072203636169434 +[2025-04-27 10:42:58,946][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.030974864959717, cross_entropy: 5.030974864959717 +[2025-04-27 10:43:00,313][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.88051700592041, cross_entropy: 4.88051700592041 +[2025-04-27 10:43:02,227][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.998389720916748, cross_entropy: 4.998389720916748 +[2025-04-27 10:43:03,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.074865341186523, cross_entropy: 5.074865341186523 +[2025-04-27 10:43:04,914][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.886510372161865, cross_entropy: 4.886510372161865 +[2025-04-27 10:43:06,116][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.991847991943359, cross_entropy: 4.991847991943359 +[2025-04-27 10:43:08,786][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.796133518218994, cross_entropy: 4.796133518218994 +[2025-04-27 10:43:08,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.849936008453369, cross_entropy: 4.849936008453369 +[2025-04-27 10:43:11,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.7403340339660645, cross_entropy: 4.7403340339660645 +[2025-04-27 10:43:12,185][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.090527534484863, cross_entropy: 5.090527534484863 +[2025-04-27 10:43:14,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.160731315612793, cross_entropy: 5.160731315612793 +[2025-04-27 10:43:15,676][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.743875503540039, cross_entropy: 4.743875503540039 +[2025-04-27 10:43:16,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.867663860321045, cross_entropy: 4.867663860321045 +[2025-04-27 10:43:18,982][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.908306121826172, cross_entropy: 4.908306121826172 +[2025-04-27 10:43:19,150][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.885709762573242, cross_entropy: 4.885709762573242 +[2025-04-27 10:43:21,881][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.749273300170898, cross_entropy: 4.749273300170898 +[2025-04-27 10:43:22,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.832970142364502, cross_entropy: 4.832970142364502 +[2025-04-27 10:43:24,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.490292549133301, cross_entropy: 4.490292549133301 +[2025-04-27 10:43:25,568][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.780116558074951, cross_entropy: 4.780116558074951 +[2025-04-27 10:43:26,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.677016258239746, cross_entropy: 4.677016258239746 +[2025-04-27 10:43:28,502][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.705391883850098, cross_entropy: 4.705391883850098 +[2025-04-27 10:43:29,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.687017440795898, cross_entropy: 4.687017440795898 +[2025-04-27 10:43:31,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.790216445922852, cross_entropy: 4.790216445922852 +[2025-04-27 10:43:32,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.517735481262207, cross_entropy: 4.517735481262207 +[2025-04-27 10:43:34,689][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.957571029663086, cross_entropy: 4.957571029663086 +[2025-04-27 10:43:35,593][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.963041305541992, cross_entropy: 4.963041305541992 +[2025-04-27 10:43:37,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.629514694213867, cross_entropy: 4.629514694213867 +[2025-04-27 10:43:38,275][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.695986747741699, cross_entropy: 4.695986747741699 +[2025-04-27 10:43:40,766][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.327305793762207, cross_entropy: 4.327305793762207 +[2025-04-27 10:43:40,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.676278114318848, cross_entropy: 4.676278114318848 +[2025-04-27 10:43:43,524][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.477409362792969, cross_entropy: 4.477409362792969 +[2025-04-27 10:43:43,643][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.870438098907471, cross_entropy: 4.870438098907471 +[2025-04-27 10:43:47,297][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.598446369171143, cross_entropy: 4.598446369171143 +[2025-04-27 10:43:47,414][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.653407096862793, cross_entropy: 4.653407096862793 +[2025-04-27 10:43:50,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.511841773986816, cross_entropy: 4.511841773986816 +[2025-04-27 10:43:50,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.494890213012695, cross_entropy: 4.494890213012695 +[2025-04-27 10:43:52,732][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 5.007237911224365, cross_entropy: 5.007237911224365 +[2025-04-27 10:43:52,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.539331912994385, cross_entropy: 4.539331912994385 +[2025-04-27 10:43:55,720][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.499818801879883, cross_entropy: 4.499818801879883 +[2025-04-27 10:43:55,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.49253511428833, cross_entropy: 4.49253511428833 +[2025-04-27 10:43:58,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.68427038192749, cross_entropy: 4.68427038192749 +[2025-04-27 10:43:59,682][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.483449935913086, cross_entropy: 4.483449935913086 +[2025-04-27 10:44:01,039][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.467325687408447, cross_entropy: 4.467325687408447 +[2025-04-27 10:44:02,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.304100036621094, cross_entropy: 4.304100036621094 +[2025-04-27 10:44:04,015][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.791143417358398, cross_entropy: 4.791143417358398 +[2025-04-27 10:44:05,656][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.393040657043457, cross_entropy: 4.393040657043457 +[2025-04-27 10:44:07,718][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.437410831451416, cross_entropy: 4.437410831451416 +[2025-04-27 10:44:08,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.431714057922363, cross_entropy: 4.431714057922363 +[2025-04-27 10:44:10,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.556996822357178, cross_entropy: 4.556996822357178 +[2025-04-27 10:44:10,800][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.657999038696289, cross_entropy: 4.657999038696289 +[2025-04-27 10:44:13,315][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.428188323974609, cross_entropy: 4.428188323974609 +[2025-04-27 10:44:13,453][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.432502269744873, cross_entropy: 4.432502269744873 +[2025-04-27 10:44:16,545][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.214348793029785, cross_entropy: 4.214348793029785 +[2025-04-27 10:44:16,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.71253776550293, cross_entropy: 4.71253776550293 +[2025-04-27 10:44:19,512][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.516013145446777, cross_entropy: 4.516013145446777 +[2025-04-27 10:44:19,809][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.164304733276367, cross_entropy: 4.164304733276367 +[2025-04-27 10:44:22,354][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.062384128570557, cross_entropy: 4.062384128570557 +[2025-04-27 10:44:22,760][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.7260661125183105, cross_entropy: 4.7260661125183105 +[2025-04-27 10:44:25,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.65997314453125, cross_entropy: 4.65997314453125 +[2025-04-27 10:44:25,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.449431419372559, cross_entropy: 4.449431419372559 +[2025-04-27 10:44:28,486][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.5332794189453125, cross_entropy: 4.5332794189453125 +[2025-04-27 10:44:28,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.202844619750977, cross_entropy: 4.202844619750977 +[2025-04-27 10:44:30,754][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 3.992253065109253, cross_entropy: 3.992253065109253 +[2025-04-27 10:44:31,614][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.612575054168701, cross_entropy: 4.612575054168701 +[2025-04-27 10:44:33,778][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.115087509155273, cross_entropy: 4.115087509155273 +[2025-04-27 10:44:34,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 4.1266913414001465, cross_entropy: 4.1266913414001465 +[2025-04-27 10:44:37,012][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.205924034118652, cross_entropy: 4.205924034118652 +[2025-04-27 10:44:37,463][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.1643266677856445, cross_entropy: 4.1643266677856445 +[2025-04-27 10:44:40,442][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.465127944946289, cross_entropy: 4.465127944946289 +[2025-04-27 10:44:40,565][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.645942687988281, cross_entropy: 4.645942687988281 +[2025-04-27 10:44:43,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.331908702850342, cross_entropy: 4.331908702850342 +[2025-04-27 10:44:43,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.458756446838379, cross_entropy: 4.458756446838379 +[2025-04-27 10:44:45,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.4045305252075195, cross_entropy: 4.4045305252075195 +[2025-04-27 10:44:46,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.3310627937316895, cross_entropy: 4.3310627937316895 +[2025-04-27 10:44:48,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.416957378387451, cross_entropy: 4.416957378387451 +[2025-04-27 10:44:50,769][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.646510601043701, cross_entropy: 4.646510601043701 +[2025-04-27 10:44:51,590][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.434908866882324, cross_entropy: 4.434908866882324 +[2025-04-27 10:44:53,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.769504547119141, cross_entropy: 4.769504547119141 +[2025-04-27 10:44:54,457][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 4.2118120193481445, cross_entropy: 4.2118120193481445 +[2025-04-27 10:44:57,197][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.323062419891357, cross_entropy: 4.323062419891357 +[2025-04-27 10:44:57,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.405154228210449, cross_entropy: 4.405154228210449 +[2025-04-27 10:44:59,745][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.5554375648498535, cross_entropy: 4.5554375648498535 +[2025-04-27 10:45:00,806][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.175909042358398, cross_entropy: 4.175909042358398 +[2025-04-27 10:45:02,319][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.345595836639404, cross_entropy: 4.345595836639404 +[2025-04-27 10:45:03,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.934390068054199, cross_entropy: 3.934390068054199 +[2025-04-27 10:45:05,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.9842143058776855, cross_entropy: 3.9842143058776855 +[2025-04-27 10:45:06,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.637825012207031, cross_entropy: 4.637825012207031 +[2025-04-27 10:45:08,865][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.177845001220703, cross_entropy: 4.177845001220703 +[2025-04-27 10:45:09,423][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.8842172622680664, cross_entropy: 3.8842172622680664 +[2025-04-27 10:45:11,657][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.7824177742004395, cross_entropy: 4.7824177742004395 +[2025-04-27 10:45:12,633][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.9242019653320312, cross_entropy: 3.9242019653320312 +[2025-04-27 10:45:14,687][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.339331150054932, cross_entropy: 4.339331150054932 +[2025-04-27 10:45:16,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.862597942352295, cross_entropy: 3.862597942352295 +[2025-04-27 10:45:17,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.246477127075195, cross_entropy: 4.246477127075195 +[2025-04-27 10:45:19,139][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.8411903381347656, cross_entropy: 3.8411903381347656 +[2025-04-27 10:45:20,672][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.15595817565918, cross_entropy: 4.15595817565918 +[2025-04-27 10:45:22,186][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 4.077744483947754, cross_entropy: 4.077744483947754 +[2025-04-27 10:45:23,885][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.882056713104248, cross_entropy: 3.882056713104248 +[2025-04-27 10:45:24,994][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.561304092407227, cross_entropy: 4.561304092407227 +[2025-04-27 10:45:26,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.943514347076416, cross_entropy: 3.943514347076416 +[2025-04-27 10:45:28,302][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.354121208190918, cross_entropy: 4.354121208190918 +[2025-04-27 10:45:29,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.7252159118652344, cross_entropy: 3.7252159118652344 +[2025-04-27 10:45:31,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.4501848220825195, cross_entropy: 4.4501848220825195 +[2025-04-27 10:45:32,539][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.6332387924194336, cross_entropy: 3.6332387924194336 +[2025-04-27 10:45:34,006][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.9066057205200195, cross_entropy: 3.9066057205200195 +[2025-04-27 10:45:35,207][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.1377973556518555, cross_entropy: 4.1377973556518555 +[2025-04-27 10:45:36,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.287503242492676, cross_entropy: 4.287503242492676 +[2025-04-27 10:45:38,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 3.671879291534424, cross_entropy: 3.671879291534424 +[2025-04-27 10:45:39,297][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.6705965995788574, cross_entropy: 3.6705965995788574 +[2025-04-27 10:45:40,959][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.9331774711608887, cross_entropy: 3.9331774711608887 +[2025-04-27 10:45:42,346][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.1039252281188965, cross_entropy: 4.1039252281188965 +[2025-04-27 10:45:44,447][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.3819193840026855, cross_entropy: 4.3819193840026855 +[2025-04-27 10:45:45,015][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.1928253173828125, cross_entropy: 4.1928253173828125 +[2025-04-27 10:45:47,214][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.168978691101074, cross_entropy: 4.168978691101074 +[2025-04-27 10:45:48,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 3.6624460220336914, cross_entropy: 3.6624460220336914 +[2025-04-27 10:45:49,688][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 4.251075267791748, cross_entropy: 4.251075267791748 +[2025-04-27 10:45:50,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 4.056636810302734, cross_entropy: 4.056636810302734 +[2025-04-27 10:45:51,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.258029460906982, cross_entropy: 4.258029460906982 +[2025-04-27 10:45:53,010][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 3.856860637664795, cross_entropy: 3.856860637664795 +[2025-04-27 10:45:54,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.824641227722168, cross_entropy: 3.824641227722168 +[2025-04-27 10:45:55,176][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.047154426574707, cross_entropy: 4.047154426574707 +[2025-04-27 10:45:58,649][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 4.341988563537598, cross_entropy: 4.341988563537598 +[2025-04-27 10:45:58,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.7772445678710938, cross_entropy: 3.7772445678710938 +[2025-04-27 10:46:00,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 3.7098770141601562, cross_entropy: 3.7098770141601562 +[2025-04-27 10:46:01,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 3.5619959831237793, cross_entropy: 3.5619959831237793 +[2025-04-27 10:46:03,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.536048412322998, cross_entropy: 4.536048412322998 +[2025-04-27 10:46:03,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.01312780380249, cross_entropy: 4.01312780380249 +[2025-04-27 10:46:06,695][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.512204170227051, cross_entropy: 4.512204170227051 +[2025-04-27 10:46:06,809][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 4.131322860717773, cross_entropy: 4.131322860717773 +[2025-04-27 10:46:09,106][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.399232864379883, cross_entropy: 3.399232864379883 +[2025-04-27 10:46:09,217][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 3.999215841293335, cross_entropy: 3.999215841293335 +[2025-04-27 10:46:11,826][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.3580145835876465, cross_entropy: 4.3580145835876465 +[2025-04-27 10:46:11,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 4.183718681335449, cross_entropy: 4.183718681335449 +[2025-04-27 10:46:14,447][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.149435043334961, cross_entropy: 4.149435043334961 +[2025-04-27 10:46:14,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.6894192695617676, cross_entropy: 3.6894192695617676 +[2025-04-27 10:46:17,018][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.798574447631836, cross_entropy: 3.798574447631836 +[2025-04-27 10:46:17,128][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.040769100189209, cross_entropy: 4.040769100189209 +[2025-04-27 10:46:20,063][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.314640998840332, cross_entropy: 4.314640998840332 +[2025-04-27 10:46:20,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.9764137268066406, cross_entropy: 3.9764137268066406 +[2025-04-27 10:46:22,982][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.405712127685547, cross_entropy: 4.405712127685547 +[2025-04-27 10:46:23,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.615088939666748, cross_entropy: 3.615088939666748 +[2025-04-27 10:46:26,469][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.128636360168457, cross_entropy: 4.128636360168457 +[2025-04-27 10:46:26,580][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 3.6853909492492676, cross_entropy: 3.6853909492492676 +[2025-04-27 10:46:28,825][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.3611323833465576, cross_entropy: 3.3611323833465576 +[2025-04-27 10:46:28,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 4.281328201293945, cross_entropy: 4.281328201293945 +[2025-04-27 10:46:31,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.750326156616211, cross_entropy: 4.750326156616211 +[2025-04-27 10:46:31,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 3.366629123687744, cross_entropy: 3.366629123687744 +[2025-04-27 10:46:34,472][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.814049243927002, cross_entropy: 3.814049243927002 +[2025-04-27 10:46:34,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.577746868133545, cross_entropy: 3.577746868133545 +[2025-04-27 10:46:37,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 3.7373931407928467, cross_entropy: 3.7373931407928467 +[2025-04-27 10:46:37,428][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.4558839797973633, cross_entropy: 3.4558839797973633 +[2025-04-27 10:46:40,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 3.720043659210205, cross_entropy: 3.720043659210205 +[2025-04-27 10:46:40,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 4.497056007385254, cross_entropy: 4.497056007385254 +[2025-04-27 10:46:43,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.5369842052459717, cross_entropy: 3.5369842052459717 +[2025-04-27 10:46:43,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.940258026123047, cross_entropy: 3.940258026123047 +[2025-04-27 10:46:46,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.221889019012451, cross_entropy: 4.221889019012451 +[2025-04-27 10:46:46,689][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.3508877754211426, cross_entropy: 3.3508877754211426 +[2025-04-27 10:46:49,338][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 4.172765731811523, cross_entropy: 4.172765731811523 +[2025-04-27 10:46:49,443][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.560264587402344, cross_entropy: 4.560264587402344 +[2025-04-27 10:46:52,062][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 4.209925651550293, cross_entropy: 4.209925651550293 +[2025-04-27 10:46:52,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.461655616760254, cross_entropy: 3.461655616760254 +[2025-04-27 10:46:54,623][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 3.546004295349121, cross_entropy: 3.546004295349121 +[2025-04-27 10:46:54,754][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.371007204055786, cross_entropy: 3.371007204055786 +[2025-04-27 10:46:57,720][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.6355810165405273, cross_entropy: 3.6355810165405273 +[2025-04-27 10:46:57,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.459416389465332, cross_entropy: 3.459416389465332 +[2025-04-27 10:47:01,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 4.2882561683654785, cross_entropy: 4.2882561683654785 +[2025-04-27 10:47:01,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.490248203277588, cross_entropy: 4.490248203277588 +[2025-04-27 10:47:03,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.391822814941406, cross_entropy: 4.391822814941406 +[2025-04-27 10:47:03,537][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 4.077088356018066, cross_entropy: 4.077088356018066 +[2025-04-27 10:47:06,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.521005630493164, cross_entropy: 3.521005630493164 +[2025-04-27 10:47:06,492][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.186854839324951, cross_entropy: 3.186854839324951 +[2025-04-27 10:47:09,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.316410541534424, cross_entropy: 3.316410541534424 +[2025-04-27 10:47:09,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.1829161643981934, cross_entropy: 3.1829161643981934 +[2025-04-27 10:47:11,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 4.09882926940918, cross_entropy: 4.09882926940918 +[2025-04-27 10:47:12,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.52058744430542, cross_entropy: 3.52058744430542 +[2025-04-27 10:47:15,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 3.4291610717773438, cross_entropy: 3.4291610717773438 +[2025-04-27 10:47:15,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.100270748138428, cross_entropy: 4.100270748138428 +[2025-04-27 10:47:19,195][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 4.093760967254639, cross_entropy: 4.093760967254639 +[2025-04-27 10:47:19,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.4378790855407715, cross_entropy: 3.4378790855407715 +[2025-04-27 10:47:21,910][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.820901393890381, cross_entropy: 3.820901393890381 +[2025-04-27 10:47:22,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.8925490379333496, cross_entropy: 3.8925490379333496 +[2025-04-27 10:47:24,811][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 3.023374557495117, cross_entropy: 3.023374557495117 +[2025-04-27 10:47:24,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 4.059298515319824, cross_entropy: 4.059298515319824 +[2025-04-27 10:47:27,476][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 4.25270938873291, cross_entropy: 4.25270938873291 +[2025-04-27 10:47:27,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.2735843658447266, cross_entropy: 3.2735843658447266 +[2025-04-27 10:47:30,344][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.191575050354004, cross_entropy: 4.191575050354004 +[2025-04-27 10:47:30,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.351985454559326, cross_entropy: 3.351985454559326 +[2025-04-27 10:47:33,392][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 3.249011278152466, cross_entropy: 3.249011278152466 +[2025-04-27 10:47:33,498][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.9939041137695312, cross_entropy: 3.9939041137695312 +[2025-04-27 10:47:36,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 4.101161003112793, cross_entropy: 4.101161003112793 +[2025-04-27 10:47:36,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 3.5464155673980713, cross_entropy: 3.5464155673980713 +[2025-04-27 10:47:38,486][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.7540805339813232, cross_entropy: 3.7540805339813232 +[2025-04-27 10:47:38,595][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.3672375679016113, cross_entropy: 3.3672375679016113 +[2025-04-27 10:47:41,005][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 3.869049310684204, cross_entropy: 3.869049310684204 +[2025-04-27 10:47:41,117][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 4.208553314208984, cross_entropy: 4.208553314208984 +[2025-04-27 10:47:43,689][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.97810959815979, cross_entropy: 3.97810959815979 +[2025-04-27 10:47:43,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.57401180267334, cross_entropy: 3.57401180267334 +[2025-04-27 10:47:46,601][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 3.2258951663970947, cross_entropy: 3.2258951663970947 +[2025-04-27 10:47:46,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.173370599746704, cross_entropy: 3.173370599746704 +[2025-04-27 10:47:49,469][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 4.3061323165893555, cross_entropy: 4.3061323165893555 +[2025-04-27 10:47:49,585][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.0865330696105957, cross_entropy: 3.0865330696105957 +[2025-04-27 10:47:52,869][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 3.044929027557373, cross_entropy: 3.044929027557373 +[2025-04-27 10:47:52,978][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.6241748332977295, cross_entropy: 3.6241748332977295 +[2025-04-27 10:47:55,196][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 4.529994964599609, cross_entropy: 4.529994964599609 +[2025-04-27 10:47:55,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.575827121734619, cross_entropy: 3.575827121734619 +[2025-04-27 10:47:57,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.62497878074646, cross_entropy: 3.62497878074646 +[2025-04-27 10:47:57,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 4.0364484786987305, cross_entropy: 4.0364484786987305 +[2025-04-27 10:48:00,579][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.3093655109405518, cross_entropy: 3.3093655109405518 +[2025-04-27 10:48:00,703][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 4.032244682312012, cross_entropy: 4.032244682312012 +[2025-04-27 10:48:03,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.8206660747528076, cross_entropy: 3.8206660747528076 +[2025-04-27 10:48:03,369][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 3.528071165084839, cross_entropy: 3.528071165084839 +[2025-04-27 10:48:05,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 4.11496114730835, cross_entropy: 4.11496114730835 +[2025-04-27 10:48:05,961][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.4365131855010986, cross_entropy: 3.4365131855010986 +[2025-04-27 10:48:08,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.949653387069702, cross_entropy: 3.949653387069702 +[2025-04-27 10:48:08,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.223546981811523, cross_entropy: 4.223546981811523 +[2025-04-27 10:48:11,277][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.5786924362182617, cross_entropy: 3.5786924362182617 +[2025-04-27 10:48:11,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.7083301544189453, cross_entropy: 3.7083301544189453 +[2025-04-27 10:48:13,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 3.9846348762512207, cross_entropy: 3.9846348762512207 +[2025-04-27 10:48:14,058][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.191028118133545, cross_entropy: 3.191028118133545 +[2025-04-27 10:48:16,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.440833568572998, cross_entropy: 3.440833568572998 +[2025-04-27 10:48:16,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.345052719116211, cross_entropy: 3.345052719116211 +[2025-04-27 10:48:19,687][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 3.1534512042999268, cross_entropy: 3.1534512042999268 +[2025-04-27 10:48:19,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 4.1498823165893555, cross_entropy: 4.1498823165893555 +[2025-04-27 10:48:23,418][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 2.8398923873901367, cross_entropy: 2.8398923873901367 +[2025-04-27 10:48:23,528][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 4.060840606689453, cross_entropy: 4.060840606689453 +[2025-04-27 10:48:26,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 3.188455104827881, cross_entropy: 3.188455104827881 +[2025-04-27 10:48:26,431][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 3.0162241458892822, cross_entropy: 3.0162241458892822 +[2025-04-27 10:48:29,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.805427312850952, cross_entropy: 3.805427312850952 +[2025-04-27 10:48:29,274][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.3264036178588867, cross_entropy: 3.3264036178588867 +[2025-04-27 10:48:32,304][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 3.584481716156006, cross_entropy: 3.584481716156006 +[2025-04-27 10:48:32,425][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 3.9124460220336914, cross_entropy: 3.9124460220336914 +[2025-04-27 10:48:35,722][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.149946689605713, cross_entropy: 3.149946689605713 +[2025-04-27 10:48:35,851][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.8925724029541016, cross_entropy: 3.8925724029541016 +[2025-04-27 10:48:39,023][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.4744608402252197, cross_entropy: 3.4744608402252197 +[2025-04-27 10:48:39,144][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 3.974668264389038, cross_entropy: 3.974668264389038 +[2025-04-27 10:48:41,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 3.8538408279418945, cross_entropy: 3.8538408279418945 +[2025-04-27 10:48:41,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 3.293583869934082, cross_entropy: 3.293583869934082 +[2025-04-27 10:48:44,451][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.8110837936401367, cross_entropy: 3.8110837936401367 +[2025-04-27 10:48:44,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 3.697798252105713, cross_entropy: 3.697798252105713 +[2025-04-27 10:48:47,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 4.17890739440918, cross_entropy: 4.17890739440918 +[2025-04-27 10:48:47,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 3.5257790088653564, cross_entropy: 3.5257790088653564 +[2025-04-27 10:48:49,906][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.3728413581848145, cross_entropy: 3.3728413581848145 +[2025-04-27 10:48:50,011][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 2.98538875579834, cross_entropy: 2.98538875579834 +[2025-04-27 10:48:52,660][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 2.9140989780426025, cross_entropy: 2.9140989780426025 +[2025-04-27 10:48:52,776][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 3.060695171356201, cross_entropy: 3.060695171356201 +[2025-04-27 10:48:55,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.246795415878296, cross_entropy: 3.246795415878296 +[2025-04-27 10:48:55,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.9086368083953857, cross_entropy: 2.9086368083953857 +[2025-04-27 10:48:59,031][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.4157421588897705, cross_entropy: 3.4157421588897705 +[2025-04-27 10:48:59,154][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 4.1377129554748535, cross_entropy: 4.1377129554748535 +[2025-04-27 10:49:02,133][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 4.05728006362915, cross_entropy: 4.05728006362915 +[2025-04-27 10:49:02,259][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 3.0180625915527344, cross_entropy: 3.0180625915527344 +[2025-04-27 10:49:05,769][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 4.163965702056885, cross_entropy: 4.163965702056885 +[2025-04-27 10:49:05,885][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 4.237140655517578, cross_entropy: 4.237140655517578 +[2025-04-27 10:49:08,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.89898419380188, cross_entropy: 2.89898419380188 +[2025-04-27 10:49:08,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 3.6295695304870605, cross_entropy: 3.6295695304870605 +[2025-04-27 10:49:11,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 4.257471084594727, cross_entropy: 4.257471084594727 +[2025-04-27 10:49:11,610][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.1239218711853027, cross_entropy: 3.1239218711853027 +[2025-04-27 10:49:15,182][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 3.8187718391418457, cross_entropy: 3.8187718391418457 +[2025-04-27 10:49:15,297][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.3875842094421387, cross_entropy: 3.3875842094421387 +[2025-04-27 10:49:17,590][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 4.173079490661621, cross_entropy: 4.173079490661621 +[2025-04-27 10:49:17,707][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 3.3411192893981934, cross_entropy: 3.3411192893981934 +[2025-04-27 10:49:20,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 4.098393440246582, cross_entropy: 4.098393440246582 +[2025-04-27 10:49:20,360][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.7751033306121826, cross_entropy: 3.7751033306121826 +[2025-04-27 10:49:22,512][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.3306002616882324, cross_entropy: 3.3306002616882324 +[2025-04-27 10:49:22,615][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 3.21602463722229, cross_entropy: 3.21602463722229 +[2025-04-27 10:49:26,441][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.187565803527832, cross_entropy: 3.187565803527832 +[2025-04-27 10:49:26,550][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.7961902618408203, cross_entropy: 3.7961902618408203 +[2025-04-27 10:49:29,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.923816680908203, cross_entropy: 2.923816680908203 +[2025-04-27 10:49:29,519][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 3.3319201469421387, cross_entropy: 3.3319201469421387 +[2025-04-27 10:49:32,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.8278768062591553, cross_entropy: 3.8278768062591553 +[2025-04-27 10:49:32,811][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 2.789475202560425, cross_entropy: 2.789475202560425 +[2025-04-27 10:49:35,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.265820026397705, cross_entropy: 4.265820026397705 +[2025-04-27 10:49:35,389][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.7569565773010254, cross_entropy: 3.7569565773010254 +[2025-04-27 10:49:37,883][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 3.001572608947754, cross_entropy: 3.001572608947754 +[2025-04-27 10:49:37,988][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 4.309039115905762, cross_entropy: 4.309039115905762 +[2025-04-27 10:49:40,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.420189380645752, cross_entropy: 3.420189380645752 +[2025-04-27 10:49:40,795][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 3.894300937652588, cross_entropy: 3.894300937652588 +[2025-04-27 10:49:42,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.8672070503234863, cross_entropy: 2.8672070503234863 +[2025-04-27 10:49:43,098][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 4.318978309631348, cross_entropy: 4.318978309631348 +[2025-04-27 10:49:45,911][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.632363796234131, cross_entropy: 3.632363796234131 +[2025-04-27 10:49:46,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 4.035330295562744, cross_entropy: 4.035330295562744 +[2025-04-27 10:49:48,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.1886649131774902, cross_entropy: 3.1886649131774902 +[2025-04-27 10:49:48,801][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 4.28671932220459, cross_entropy: 4.28671932220459 +[2025-04-27 10:49:51,517][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.777492046356201, cross_entropy: 2.777492046356201 +[2025-04-27 10:49:51,629][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 2.9148905277252197, cross_entropy: 2.9148905277252197 +[2025-04-27 10:49:53,976][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 3.709305763244629, cross_entropy: 3.709305763244629 +[2025-04-27 10:49:54,079][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 3.4492194652557373, cross_entropy: 3.4492194652557373 +[2025-04-27 10:49:57,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 3.3745856285095215, cross_entropy: 3.3745856285095215 +[2025-04-27 10:49:57,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.806988000869751, cross_entropy: 3.806988000869751 +[2025-04-27 10:50:00,315][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 3.1749141216278076, cross_entropy: 3.1749141216278076 +[2025-04-27 10:50:00,419][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.868201971054077, cross_entropy: 3.868201971054077 +[2025-04-27 10:50:03,287][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.3785510063171387, cross_entropy: 3.3785510063171387 +[2025-04-27 10:50:03,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.957233190536499, cross_entropy: 3.957233190536499 +[2025-04-27 10:50:06,948][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 4.11934232711792, cross_entropy: 4.11934232711792 +[2025-04-27 10:50:07,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.8320677280426025, cross_entropy: 3.8320677280426025 +[2025-04-27 10:50:09,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 4.184572219848633, cross_entropy: 4.184572219848633 +[2025-04-27 10:50:09,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 3.2617204189300537, cross_entropy: 3.2617204189300537 +[2025-04-27 10:50:12,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 2.8950369358062744, cross_entropy: 2.8950369358062744 +[2025-04-27 10:50:12,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 3.334235191345215, cross_entropy: 3.334235191345215 +[2025-04-27 10:50:14,750][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 4.1171345710754395, cross_entropy: 4.1171345710754395 +[2025-04-27 10:50:14,865][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.3216373920440674, cross_entropy: 3.3216373920440674 +[2025-04-27 10:50:17,437][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.8169548511505127, cross_entropy: 3.8169548511505127 +[2025-04-27 10:50:17,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 3.8998241424560547, cross_entropy: 3.8998241424560547 +[2025-04-27 10:50:20,004][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.9409608840942383, cross_entropy: 2.9409608840942383 +[2025-04-27 10:50:20,117][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.363758087158203, cross_entropy: 3.363758087158203 +[2025-04-27 10:50:22,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.267864227294922, cross_entropy: 3.267864227294922 +[2025-04-27 10:50:23,046][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.574035167694092, cross_entropy: 3.574035167694092 +[2025-04-27 10:50:26,262][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 3.186126470565796, cross_entropy: 3.186126470565796 +[2025-04-27 10:50:26,369][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.934384346008301, cross_entropy: 3.934384346008301 +[2025-04-27 10:50:29,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 3.163060188293457, cross_entropy: 3.163060188293457 +[2025-04-27 10:50:29,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.3788647651672363, cross_entropy: 3.3788647651672363 +[2025-04-27 10:50:33,047][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.8899364471435547, cross_entropy: 3.8899364471435547 +[2025-04-27 10:50:33,151][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.7361419200897217, cross_entropy: 2.7361419200897217 +[2025-04-27 10:50:36,082][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 2.8496975898742676, cross_entropy: 2.8496975898742676 +[2025-04-27 10:50:36,198][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 3.532705307006836, cross_entropy: 3.532705307006836 +[2025-04-27 10:50:38,662][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.9691402912139893, cross_entropy: 3.9691402912139893 +[2025-04-27 10:50:38,769][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 2.855757713317871, cross_entropy: 2.855757713317871 +[2025-04-27 10:50:41,749][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 2.837031841278076, cross_entropy: 2.837031841278076 +[2025-04-27 10:50:41,853][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.9110000133514404, cross_entropy: 3.9110000133514404 +[2025-04-27 10:50:44,527][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 3.872678756713867, cross_entropy: 3.872678756713867 +[2025-04-27 10:50:44,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 2.8220980167388916, cross_entropy: 2.8220980167388916 +[2025-04-27 10:50:47,169][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.888434410095215, cross_entropy: 3.888434410095215 +[2025-04-27 10:50:47,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.19779372215271, cross_entropy: 3.19779372215271 +[2025-04-27 10:50:49,846][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.38791561126709, cross_entropy: 3.38791561126709 +[2025-04-27 10:50:49,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.1986148357391357, cross_entropy: 3.1986148357391357 +[2025-04-27 10:50:52,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 2.8529415130615234, cross_entropy: 2.8529415130615234 +[2025-04-27 10:50:52,985][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 4.172473907470703, cross_entropy: 4.172473907470703 +[2025-04-27 10:50:56,003][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 3.2556564807891846, cross_entropy: 3.2556564807891846 +[2025-04-27 10:50:56,111][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 3.92417573928833, cross_entropy: 3.92417573928833 +[2025-04-27 10:50:58,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 3.8402955532073975, cross_entropy: 3.8402955532073975 +[2025-04-27 10:50:58,781][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 2.826190233230591, cross_entropy: 2.826190233230591 +[2025-04-27 10:51:01,516][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.7890584468841553, cross_entropy: 2.7890584468841553 +[2025-04-27 10:51:01,637][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 4.069851875305176, cross_entropy: 4.069851875305176 +[2025-04-27 10:51:04,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.2232255935668945, cross_entropy: 3.2232255935668945 +[2025-04-27 10:51:04,548][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.9537858963012695, cross_entropy: 3.9537858963012695 +[2025-04-27 10:51:07,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 3.5447773933410645, cross_entropy: 3.5447773933410645 +[2025-04-27 10:51:07,673][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 3.9112415313720703, cross_entropy: 3.9112415313720703 +[2025-04-27 10:51:09,725][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.5038065910339355, cross_entropy: 3.5038065910339355 +[2025-04-27 10:51:09,841][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 2.9304943084716797, cross_entropy: 2.9304943084716797 +[2025-04-27 10:51:12,278][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 3.2554421424865723, cross_entropy: 3.2554421424865723 +[2025-04-27 10:51:12,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 3.399412155151367, cross_entropy: 3.399412155151367 +[2025-04-27 10:51:15,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 2.7423288822174072, cross_entropy: 2.7423288822174072 +[2025-04-27 10:51:15,283][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 3.723926544189453, cross_entropy: 3.723926544189453 +[2025-04-27 10:51:17,735][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.662923812866211, cross_entropy: 2.662923812866211 +[2025-04-27 10:51:17,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.8569040298461914, cross_entropy: 2.8569040298461914 +[2025-04-27 10:51:20,470][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.0587334632873535, cross_entropy: 3.0587334632873535 +[2025-04-27 10:51:20,580][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 4.222805023193359, cross_entropy: 4.222805023193359 +[2025-04-27 10:51:22,735][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.992576837539673, cross_entropy: 3.992576837539673 +[2025-04-27 10:51:24,049][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.4098446369171143, cross_entropy: 3.4098446369171143 +[2025-04-27 10:53:41,246][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.937533140182495, cross_entropy: 3.937533140182495 +[2025-04-27 10:53:41,247][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.7406983375549316, cross_entropy: 2.7406983375549316 +[2025-04-27 10:53:41,413][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 10:53:41,569][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch1.pth. +[2025-04-27 10:53:41,730][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 10:53:44,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.921238899230957, cross_entropy: 3.921238899230957 +[2025-04-27 10:53:44,585][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.711604356765747, cross_entropy: 2.711604356765747 +[2025-04-27 10:53:47,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 4.131155490875244, cross_entropy: 4.131155490875244 +[2025-04-27 10:53:47,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 2.294238567352295, cross_entropy: 2.294238567352295 +[2025-04-27 10:53:49,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.515756607055664, cross_entropy: 2.515756607055664 +[2025-04-27 10:53:49,187][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 4.200928688049316, cross_entropy: 4.200928688049316 +[2025-04-27 10:53:51,171][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 3.517010450363159, cross_entropy: 3.517010450363159 +[2025-04-27 10:53:51,298][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 2.574883460998535, cross_entropy: 2.574883460998535 +[2025-04-27 10:53:53,153][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.8011441230773926, cross_entropy: 2.8011441230773926 +[2025-04-27 10:53:53,276][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.745453119277954, cross_entropy: 2.745453119277954 +[2025-04-27 10:53:55,374][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.4248220920562744, cross_entropy: 2.4248220920562744 +[2025-04-27 10:53:55,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.9523043632507324, cross_entropy: 3.9523043632507324 +[2025-04-27 10:53:57,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.20554256439209, cross_entropy: 3.20554256439209 +[2025-04-27 10:53:57,867][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.8497190475463867, cross_entropy: 2.8497190475463867 +[2025-04-27 10:54:00,368][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.876884937286377, cross_entropy: 3.876884937286377 +[2025-04-27 10:54:00,480][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 3.7561607360839844, cross_entropy: 3.7561607360839844 +[2025-04-27 10:54:02,805][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 3.0839314460754395, cross_entropy: 3.0839314460754395 +[2025-04-27 10:54:02,910][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.5509395599365234, cross_entropy: 2.5509395599365234 +[2025-04-27 10:54:04,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.0369012355804443, cross_entropy: 3.0369012355804443 +[2025-04-27 10:54:05,000][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.8700060844421387, cross_entropy: 2.8700060844421387 +[2025-04-27 10:54:06,862][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 2.621929168701172, cross_entropy: 2.621929168701172 +[2025-04-27 10:54:06,982][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 2.762941598892212, cross_entropy: 2.762941598892212 +[2025-04-27 10:54:08,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.1955413818359375, cross_entropy: 3.1955413818359375 +[2025-04-27 10:54:08,943][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.9045443534851074, cross_entropy: 3.9045443534851074 +[2025-04-27 10:54:10,730][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 2.9259345531463623, cross_entropy: 2.9259345531463623 +[2025-04-27 10:54:10,833][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.720874309539795, cross_entropy: 2.720874309539795 +[2025-04-27 10:54:13,586][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 2.579385757446289, cross_entropy: 2.579385757446289 +[2025-04-27 10:54:13,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.9948277473449707, cross_entropy: 2.9948277473449707 +[2025-04-27 10:54:15,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 3.040191650390625, cross_entropy: 3.040191650390625 +[2025-04-27 10:54:15,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 3.277280330657959, cross_entropy: 3.277280330657959 +[2025-04-27 10:54:17,672][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.6337051391601562, cross_entropy: 2.6337051391601562 +[2025-04-27 10:54:17,776][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 3.4456899166107178, cross_entropy: 3.4456899166107178 +[2025-04-27 10:54:19,568][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.5797793865203857, cross_entropy: 2.5797793865203857 +[2025-04-27 10:54:19,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 4.016161918640137, cross_entropy: 4.016161918640137 +[2025-04-27 10:54:21,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.4625351428985596, cross_entropy: 2.4625351428985596 +[2025-04-27 10:54:21,798][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.859513759613037, cross_entropy: 3.859513759613037 +[2025-04-27 10:54:24,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.492750644683838, cross_entropy: 3.492750644683838 +[2025-04-27 10:54:24,557][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 3.9870307445526123, cross_entropy: 3.9870307445526123 +[2025-04-27 10:54:28,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 3.7445926666259766, cross_entropy: 3.7445926666259766 +[2025-04-27 10:54:28,195][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 3.32230281829834, cross_entropy: 3.32230281829834 +[2025-04-27 10:54:30,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.1711394786834717, cross_entropy: 3.1711394786834717 +[2025-04-27 10:54:30,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 3.0837862491607666, cross_entropy: 3.0837862491607666 +[2025-04-27 10:54:32,036][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 2.7523748874664307, cross_entropy: 2.7523748874664307 +[2025-04-27 10:54:32,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 3.3449063301086426, cross_entropy: 3.3449063301086426 +[2025-04-27 10:54:34,277][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 2.708024740219116, cross_entropy: 2.708024740219116 +[2025-04-27 10:54:34,381][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 4.035578727722168, cross_entropy: 4.035578727722168 +[2025-04-27 10:54:37,193][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.7672781944274902, cross_entropy: 3.7672781944274902 +[2025-04-27 10:54:37,306][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 4.080266952514648, cross_entropy: 4.080266952514648 +[2025-04-27 10:54:39,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.690915107727051, cross_entropy: 3.690915107727051 +[2025-04-27 10:54:39,692][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 3.122260808944702, cross_entropy: 3.122260808944702 +[2025-04-27 10:54:42,104][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.451535224914551, cross_entropy: 3.451535224914551 +[2025-04-27 10:54:42,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 3.331902503967285, cross_entropy: 3.331902503967285 +[2025-04-27 10:54:44,926][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.472705602645874, cross_entropy: 3.472705602645874 +[2025-04-27 10:54:45,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.3115570545196533, cross_entropy: 3.3115570545196533 +[2025-04-27 10:54:47,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.0146453380584717, cross_entropy: 3.0146453380584717 +[2025-04-27 10:54:47,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.8097100257873535, cross_entropy: 2.8097100257873535 +[2025-04-27 10:54:49,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.812326431274414, cross_entropy: 2.812326431274414 +[2025-04-27 10:54:49,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.7921833992004395, cross_entropy: 2.7921833992004395 +[2025-04-27 10:54:51,574][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 2.6605782508850098, cross_entropy: 2.6605782508850098 +[2025-04-27 10:54:51,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 2.4851136207580566, cross_entropy: 2.4851136207580566 +[2025-04-27 10:54:53,807][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 2.4020376205444336, cross_entropy: 2.4020376205444336 +[2025-04-27 10:54:53,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 4.044868469238281, cross_entropy: 4.044868469238281 +[2025-04-27 10:54:56,149][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.379943370819092, cross_entropy: 2.379943370819092 +[2025-04-27 10:54:56,252][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 2.4898338317871094, cross_entropy: 2.4898338317871094 +[2025-04-27 10:54:58,191][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 4.176735877990723, cross_entropy: 4.176735877990723 +[2025-04-27 10:54:58,294][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.2937686443328857, cross_entropy: 3.2937686443328857 +[2025-04-27 10:55:00,727][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.8660573959350586, cross_entropy: 2.8660573959350586 +[2025-04-27 10:55:00,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 2.5538716316223145, cross_entropy: 2.5538716316223145 +[2025-04-27 10:55:02,807][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.749056816101074, cross_entropy: 2.749056816101074 +[2025-04-27 10:55:02,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.1440179347991943, cross_entropy: 3.1440179347991943 +[2025-04-27 10:55:04,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.4322562217712402, cross_entropy: 3.4322562217712402 +[2025-04-27 10:55:04,814][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.950221061706543, cross_entropy: 2.950221061706543 +[2025-04-27 10:55:06,779][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.496413469314575, cross_entropy: 3.496413469314575 +[2025-04-27 10:55:06,900][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 2.9986186027526855, cross_entropy: 2.9986186027526855 +[2025-04-27 10:55:09,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.558548927307129, cross_entropy: 2.558548927307129 +[2025-04-27 10:55:09,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 2.7776365280151367, cross_entropy: 2.7776365280151367 +[2025-04-27 10:55:11,750][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 2.8103513717651367, cross_entropy: 2.8103513717651367 +[2025-04-27 10:55:11,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 4.045395851135254, cross_entropy: 4.045395851135254 +[2025-04-27 10:55:14,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 4.295525550842285, cross_entropy: 4.295525550842285 +[2025-04-27 10:55:14,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.3990678787231445, cross_entropy: 3.3990678787231445 +[2025-04-27 10:55:16,712][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.7747113704681396, cross_entropy: 2.7747113704681396 +[2025-04-27 10:55:16,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.8915529251098633, cross_entropy: 3.8915529251098633 +[2025-04-27 10:55:19,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.600663185119629, cross_entropy: 2.600663185119629 +[2025-04-27 10:55:19,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 2.9713613986968994, cross_entropy: 2.9713613986968994 +[2025-04-27 10:55:22,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.2932252883911133, cross_entropy: 3.2932252883911133 +[2025-04-27 10:55:22,213][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 2.4855852127075195, cross_entropy: 2.4855852127075195 +[2025-04-27 10:55:24,764][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 2.7301573753356934, cross_entropy: 2.7301573753356934 +[2025-04-27 10:55:24,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 2.495964527130127, cross_entropy: 2.495964527130127 +[2025-04-27 10:55:27,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.9818177223205566, cross_entropy: 3.9818177223205566 +[2025-04-27 10:55:27,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.687476634979248, cross_entropy: 2.687476634979248 +[2025-04-27 10:55:29,455][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.349097490310669, cross_entropy: 3.349097490310669 +[2025-04-27 10:55:29,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 2.5446481704711914, cross_entropy: 2.5446481704711914 +[2025-04-27 10:55:31,898][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.6141862869262695, cross_entropy: 3.6141862869262695 +[2025-04-27 10:55:32,002][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 2.5567100048065186, cross_entropy: 2.5567100048065186 +[2025-04-27 10:55:33,797][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 4.005644798278809, cross_entropy: 4.005644798278809 +[2025-04-27 10:55:33,901][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 3.1086487770080566, cross_entropy: 3.1086487770080566 +[2025-04-27 10:55:36,201][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.0008842945098877, cross_entropy: 3.0008842945098877 +[2025-04-27 10:55:36,321][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 3.726384162902832, cross_entropy: 3.726384162902832 +[2025-04-27 10:55:38,080][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.0446062088012695, cross_entropy: 3.0446062088012695 +[2025-04-27 10:55:38,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.0173614025115967, cross_entropy: 3.0173614025115967 +[2025-04-27 10:55:39,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 4.0518693923950195, cross_entropy: 4.0518693923950195 +[2025-04-27 10:55:40,059][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.0982766151428223, cross_entropy: 3.0982766151428223 +[2025-04-27 10:55:41,929][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 4.034767150878906, cross_entropy: 4.034767150878906 +[2025-04-27 10:55:42,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.2216808795928955, cross_entropy: 2.2216808795928955 +[2025-04-27 10:55:43,940][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 2.708163261413574, cross_entropy: 2.708163261413574 +[2025-04-27 10:55:44,059][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.983872175216675, cross_entropy: 3.983872175216675 +[2025-04-27 10:55:47,410][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.3800408840179443, cross_entropy: 2.3800408840179443 +[2025-04-27 10:55:47,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.5896105766296387, cross_entropy: 3.5896105766296387 +[2025-04-27 10:55:50,067][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.9992144107818604, cross_entropy: 3.9992144107818604 +[2025-04-27 10:55:50,185][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.777881145477295, cross_entropy: 3.777881145477295 +[2025-04-27 10:55:52,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 3.8599212169647217, cross_entropy: 3.8599212169647217 +[2025-04-27 10:55:52,136][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 2.3914225101470947, cross_entropy: 2.3914225101470947 +[2025-04-27 10:55:54,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 2.9296820163726807, cross_entropy: 2.9296820163726807 +[2025-04-27 10:55:54,859][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.2544264793395996, cross_entropy: 3.2544264793395996 +[2025-04-27 10:55:56,729][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 2.7313246726989746, cross_entropy: 2.7313246726989746 +[2025-04-27 10:55:56,834][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.1326849460601807, cross_entropy: 3.1326849460601807 +[2025-04-27 10:55:59,185][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.8381786346435547, cross_entropy: 2.8381786346435547 +[2025-04-27 10:55:59,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.487046003341675, cross_entropy: 3.487046003341675 +[2025-04-27 10:56:01,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 2.250480890274048, cross_entropy: 2.250480890274048 +[2025-04-27 10:56:01,415][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 3.369990825653076, cross_entropy: 3.369990825653076 +[2025-04-27 10:56:03,383][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.676081657409668, cross_entropy: 3.676081657409668 +[2025-04-27 10:56:03,503][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.859419584274292, cross_entropy: 2.859419584274292 +[2025-04-27 10:56:05,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 2.7771997451782227, cross_entropy: 2.7771997451782227 +[2025-04-27 10:56:05,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 3.0422229766845703, cross_entropy: 3.0422229766845703 +[2025-04-27 10:56:07,534][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 3.1704509258270264, cross_entropy: 3.1704509258270264 +[2025-04-27 10:56:07,654][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.5578277111053467, cross_entropy: 2.5578277111053467 +[2025-04-27 10:56:10,051][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.9142918586730957, cross_entropy: 3.9142918586730957 +[2025-04-27 10:56:10,155][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 2.7312703132629395, cross_entropy: 2.7312703132629395 +[2025-04-27 10:56:12,344][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 3.915964126586914, cross_entropy: 3.915964126586914 +[2025-04-27 10:56:12,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.8453102111816406, cross_entropy: 2.8453102111816406 +[2025-04-27 10:56:14,432][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.311730146408081, cross_entropy: 2.311730146408081 +[2025-04-27 10:56:14,549][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.598543882369995, cross_entropy: 2.598543882369995 +[2025-04-27 10:56:16,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 4.338151454925537, cross_entropy: 4.338151454925537 +[2025-04-27 10:56:16,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.7079880237579346, cross_entropy: 2.7079880237579346 +[2025-04-27 10:56:18,221][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 2.9367265701293945, cross_entropy: 2.9367265701293945 +[2025-04-27 10:56:18,351][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.2143537998199463, cross_entropy: 3.2143537998199463 +[2025-04-27 10:56:21,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.3203117847442627, cross_entropy: 2.3203117847442627 +[2025-04-27 10:56:21,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 2.6733264923095703, cross_entropy: 2.6733264923095703 +[2025-04-27 10:56:23,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 2.997887134552002, cross_entropy: 2.997887134552002 +[2025-04-27 10:56:23,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 2.97059965133667, cross_entropy: 2.97059965133667 +[2025-04-27 10:56:25,564][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.1366567611694336, cross_entropy: 3.1366567611694336 +[2025-04-27 10:56:25,686][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 4.190885543823242, cross_entropy: 4.190885543823242 +[2025-04-27 10:56:27,892][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.553638458251953, cross_entropy: 3.553638458251953 +[2025-04-27 10:56:28,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.5062036514282227, cross_entropy: 2.5062036514282227 +[2025-04-27 10:56:29,527][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 3.010817527770996, cross_entropy: 3.010817527770996 +[2025-04-27 10:56:29,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 2.9179933071136475, cross_entropy: 2.9179933071136475 +[2025-04-27 10:56:31,542][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.7882041931152344, cross_entropy: 2.7882041931152344 +[2025-04-27 10:56:31,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.422607898712158, cross_entropy: 2.422607898712158 +[2025-04-27 10:56:33,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 3.872321128845215, cross_entropy: 3.872321128845215 +[2025-04-27 10:56:34,437][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 2.9595305919647217, cross_entropy: 2.9595305919647217 +[2025-04-27 10:56:36,037][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.838654041290283, cross_entropy: 2.838654041290283 +[2025-04-27 10:56:36,259][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 2.662597417831421, cross_entropy: 2.662597417831421 +[2025-04-27 10:56:37,924][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.593996524810791, cross_entropy: 3.593996524810791 +[2025-04-27 10:56:38,219][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 3.090683698654175, cross_entropy: 3.090683698654175 +[2025-04-27 10:56:41,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.282322883605957, cross_entropy: 3.282322883605957 +[2025-04-27 10:56:41,457][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 3.283698320388794, cross_entropy: 3.283698320388794 +[2025-04-27 10:56:43,508][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 2.6520071029663086, cross_entropy: 2.6520071029663086 +[2025-04-27 10:56:43,612][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.017209768295288, cross_entropy: 3.017209768295288 +[2025-04-27 10:56:47,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.9491052627563477, cross_entropy: 3.9491052627563477 +[2025-04-27 10:56:47,233][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.890341281890869, cross_entropy: 2.890341281890869 +[2025-04-27 10:56:49,607][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 2.964996814727783, cross_entropy: 2.964996814727783 +[2025-04-27 10:56:49,718][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 2.6032819747924805, cross_entropy: 2.6032819747924805 +[2025-04-27 10:56:52,749][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.764508008956909, cross_entropy: 2.764508008956909 +[2025-04-27 10:56:52,853][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 2.536243200302124, cross_entropy: 2.536243200302124 +[2025-04-27 10:56:54,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 3.0721750259399414, cross_entropy: 3.0721750259399414 +[2025-04-27 10:56:54,743][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.84096622467041, cross_entropy: 2.84096622467041 +[2025-04-27 10:56:56,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 2.6295926570892334, cross_entropy: 2.6295926570892334 +[2025-04-27 10:56:56,878][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.9777519702911377, cross_entropy: 2.9777519702911377 +[2025-04-27 10:56:59,397][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 3.0572309494018555, cross_entropy: 3.0572309494018555 +[2025-04-27 10:56:59,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.4327797889709473, cross_entropy: 2.4327797889709473 +[2025-04-27 10:57:01,392][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.185168743133545, cross_entropy: 3.185168743133545 +[2025-04-27 10:57:01,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 4.2127532958984375, cross_entropy: 4.2127532958984375 +[2025-04-27 10:57:03,777][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 3.4672231674194336, cross_entropy: 3.4672231674194336 +[2025-04-27 10:57:03,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 3.4847707748413086, cross_entropy: 3.4847707748413086 +[2025-04-27 10:57:05,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 3.081378698348999, cross_entropy: 3.081378698348999 +[2025-04-27 10:57:05,994][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 4.115124702453613, cross_entropy: 4.115124702453613 +[2025-04-27 10:57:07,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 2.6900434494018555, cross_entropy: 2.6900434494018555 +[2025-04-27 10:57:08,053][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.4247822761535645, cross_entropy: 2.4247822761535645 +[2025-04-27 10:57:10,275][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 3.4852757453918457, cross_entropy: 3.4852757453918457 +[2025-04-27 10:57:10,397][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.0670595169067383, cross_entropy: 3.0670595169067383 +[2025-04-27 10:57:12,154][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.519352436065674, cross_entropy: 2.519352436065674 +[2025-04-27 10:57:12,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 2.2806382179260254, cross_entropy: 2.2806382179260254 +[2025-04-27 10:57:14,556][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 2.497704267501831, cross_entropy: 2.497704267501831 +[2025-04-27 10:57:14,677][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.4557812213897705, cross_entropy: 2.4557812213897705 +[2025-04-27 10:57:17,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 3.6094541549682617, cross_entropy: 3.6094541549682617 +[2025-04-27 10:57:17,430][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 3.5165553092956543, cross_entropy: 3.5165553092956543 +[2025-04-27 10:57:20,400][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.495433807373047, cross_entropy: 2.495433807373047 +[2025-04-27 10:57:20,504][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.21852445602417, cross_entropy: 3.21852445602417 +[2025-04-27 10:57:22,588][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 4.1420745849609375, cross_entropy: 4.1420745849609375 +[2025-04-27 10:57:22,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.263312339782715, cross_entropy: 2.263312339782715 +[2025-04-27 10:57:25,728][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 2.531644821166992, cross_entropy: 2.531644821166992 +[2025-04-27 10:57:25,832][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 2.285893678665161, cross_entropy: 2.285893678665161 +[2025-04-27 10:57:28,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.8575568199157715, cross_entropy: 2.8575568199157715 +[2025-04-27 10:57:28,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 4.221364974975586, cross_entropy: 4.221364974975586 +[2025-04-27 10:57:30,721][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.311586856842041, cross_entropy: 2.311586856842041 +[2025-04-27 10:57:30,825][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.9003586769104004, cross_entropy: 2.9003586769104004 +[2025-04-27 10:57:33,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.00911283493042, cross_entropy: 3.00911283493042 +[2025-04-27 10:57:33,346][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 2.410513401031494, cross_entropy: 2.410513401031494 +[2025-04-27 10:57:35,331][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.0901546478271484, cross_entropy: 3.0901546478271484 +[2025-04-27 10:57:35,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 3.155508518218994, cross_entropy: 3.155508518218994 +[2025-04-27 10:57:37,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 2.4226913452148438, cross_entropy: 2.4226913452148438 +[2025-04-27 10:57:37,249][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 3.377473831176758, cross_entropy: 3.377473831176758 +[2025-04-27 10:57:39,517][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 2.816915512084961, cross_entropy: 2.816915512084961 +[2025-04-27 10:57:39,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.916419506072998, cross_entropy: 2.916419506072998 +[2025-04-27 10:57:42,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 3.040144443511963, cross_entropy: 3.040144443511963 +[2025-04-27 10:57:42,129][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 2.4193785190582275, cross_entropy: 2.4193785190582275 +[2025-04-27 10:57:43,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 3.6575498580932617, cross_entropy: 3.6575498580932617 +[2025-04-27 10:57:45,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 3.611794948577881, cross_entropy: 3.611794948577881 +[2025-04-27 10:57:46,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 4.089404106140137, cross_entropy: 4.089404106140137 +[2025-04-27 10:57:47,185][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 3.587313175201416, cross_entropy: 3.587313175201416 +[2025-04-27 10:57:48,169][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 2.6900136470794678, cross_entropy: 2.6900136470794678 +[2025-04-27 10:57:49,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 3.1997573375701904, cross_entropy: 3.1997573375701904 +[2025-04-27 10:57:50,334][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.8062241077423096, cross_entropy: 2.8062241077423096 +[2025-04-27 10:57:51,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 3.81204891204834, cross_entropy: 3.81204891204834 +[2025-04-27 10:57:52,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 3.1385226249694824, cross_entropy: 3.1385226249694824 +[2025-04-27 10:57:53,002][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 3.162127733230591, cross_entropy: 3.162127733230591 +[2025-04-27 10:57:54,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 3.4581925868988037, cross_entropy: 3.4581925868988037 +[2025-04-27 10:57:54,907][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.998751640319824, cross_entropy: 2.998751640319824 +[2025-04-27 10:57:56,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.839932680130005, cross_entropy: 2.839932680130005 +[2025-04-27 10:57:57,556][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 3.1223161220550537, cross_entropy: 3.1223161220550537 +[2025-04-27 10:57:58,575][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 2.5609307289123535, cross_entropy: 2.5609307289123535 +[2025-04-27 10:57:59,948][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.978750705718994, cross_entropy: 2.978750705718994 +[2025-04-27 10:58:00,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 3.4062423706054688, cross_entropy: 3.4062423706054688 +[2025-04-27 10:58:02,162][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.640094041824341, cross_entropy: 2.640094041824341 +[2025-04-27 10:58:02,576][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 4.003307342529297, cross_entropy: 4.003307342529297 +[2025-04-27 10:58:05,176][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.5492806434631348, cross_entropy: 2.5492806434631348 +[2025-04-27 10:58:05,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 4.237443923950195, cross_entropy: 4.237443923950195 +[2025-04-27 10:58:08,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.7747089862823486, cross_entropy: 3.7747089862823486 +[2025-04-27 10:58:08,219][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 2.518110990524292, cross_entropy: 2.518110990524292 +[2025-04-27 10:58:10,635][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.290283441543579, cross_entropy: 2.290283441543579 +[2025-04-27 10:58:10,757][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 2.194861888885498, cross_entropy: 2.194861888885498 +[2025-04-27 10:58:12,640][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.8725967407226562, cross_entropy: 2.8725967407226562 +[2025-04-27 10:58:12,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 3.7603466510772705, cross_entropy: 3.7603466510772705 +[2025-04-27 10:58:14,761][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 3.0098977088928223, cross_entropy: 3.0098977088928223 +[2025-04-27 10:58:14,883][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.8221817016601562, cross_entropy: 2.8221817016601562 +[2025-04-27 10:58:16,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.8684349060058594, cross_entropy: 2.8684349060058594 +[2025-04-27 10:58:16,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 2.991366386413574, cross_entropy: 2.991366386413574 +[2025-04-27 10:58:19,138][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 2.7093114852905273, cross_entropy: 2.7093114852905273 +[2025-04-27 10:58:19,260][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 2.492312431335449, cross_entropy: 2.492312431335449 +[2025-04-27 10:58:21,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.3962955474853516, cross_entropy: 2.3962955474853516 +[2025-04-27 10:58:21,510][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 2.9875335693359375, cross_entropy: 2.9875335693359375 +[2025-04-27 10:58:24,012][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 2.4736642837524414, cross_entropy: 2.4736642837524414 +[2025-04-27 10:58:24,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.858248710632324, cross_entropy: 3.858248710632324 +[2025-04-27 10:58:26,529][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 4.04965877532959, cross_entropy: 4.04965877532959 +[2025-04-27 10:58:26,634][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 2.7176899909973145, cross_entropy: 2.7176899909973145 +[2025-04-27 10:58:29,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 2.838468074798584, cross_entropy: 2.838468074798584 +[2025-04-27 10:58:29,387][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.2386741638183594, cross_entropy: 2.2386741638183594 +[2025-04-27 10:58:33,026][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 3.883777618408203, cross_entropy: 3.883777618408203 +[2025-04-27 10:58:33,147][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 3.52773380279541, cross_entropy: 3.52773380279541 +[2025-04-27 10:58:35,059][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 3.2316222190856934, cross_entropy: 3.2316222190856934 +[2025-04-27 10:58:35,182][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.3551149368286133, cross_entropy: 3.3551149368286133 +[2025-04-27 10:58:37,323][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 2.659656047821045, cross_entropy: 2.659656047821045 +[2025-04-27 10:58:37,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 2.685194969177246, cross_entropy: 2.685194969177246 +[2025-04-27 10:58:39,676][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.0097646713256836, cross_entropy: 3.0097646713256836 +[2025-04-27 10:58:39,780][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.4671802520751953, cross_entropy: 2.4671802520751953 +[2025-04-27 10:58:42,346][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 2.662353038787842, cross_entropy: 2.662353038787842 +[2025-04-27 10:58:42,468][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 3.1047933101654053, cross_entropy: 3.1047933101654053 +[2025-04-27 10:58:45,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 3.998650074005127, cross_entropy: 3.998650074005127 +[2025-04-27 10:58:45,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.8941798210144043, cross_entropy: 2.8941798210144043 +[2025-04-27 10:58:47,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 3.97995662689209, cross_entropy: 3.97995662689209 +[2025-04-27 10:58:47,663][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.8623194694519043, cross_entropy: 2.8623194694519043 +[2025-04-27 10:58:49,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 3.2169532775878906, cross_entropy: 3.2169532775878906 +[2025-04-27 10:58:49,574][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 4.032587051391602, cross_entropy: 4.032587051391602 +[2025-04-27 10:58:51,385][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 3.1477065086364746, cross_entropy: 3.1477065086364746 +[2025-04-27 10:58:51,508][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.2794361114501953, cross_entropy: 2.2794361114501953 +[2025-04-27 10:58:53,647][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.7662887573242188, cross_entropy: 2.7662887573242188 +[2025-04-27 10:58:53,770][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 3.814377546310425, cross_entropy: 3.814377546310425 +[2025-04-27 10:58:55,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.6908304691314697, cross_entropy: 3.6908304691314697 +[2025-04-27 10:58:55,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 3.9637112617492676, cross_entropy: 3.9637112617492676 +[2025-04-27 10:58:57,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 3.604565382003784, cross_entropy: 3.604565382003784 +[2025-04-27 10:58:58,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 2.5226030349731445, cross_entropy: 2.5226030349731445 +[2025-04-27 10:58:59,931][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 2.2843399047851562, cross_entropy: 2.2843399047851562 +[2025-04-27 10:59:00,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 2.163970470428467, cross_entropy: 2.163970470428467 +[2025-04-27 10:59:02,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 2.934854745864868, cross_entropy: 2.934854745864868 +[2025-04-27 10:59:02,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 3.788651943206787, cross_entropy: 3.788651943206787 +[2025-04-27 10:59:04,572][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 3.04494571685791, cross_entropy: 3.04494571685791 +[2025-04-27 10:59:04,846][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 2.723574161529541, cross_entropy: 2.723574161529541 +[2025-04-27 10:59:06,328][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 2.4510931968688965, cross_entropy: 2.4510931968688965 +[2025-04-27 10:59:06,443][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.9848101139068604, cross_entropy: 2.9848101139068604 +[2025-04-27 10:59:08,588][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 3.2442679405212402, cross_entropy: 3.2442679405212402 +[2025-04-27 10:59:08,691][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 2.4494566917419434, cross_entropy: 2.4494566917419434 +[2025-04-27 10:59:10,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.5915513038635254, cross_entropy: 2.5915513038635254 +[2025-04-27 10:59:10,865][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 2.1820406913757324, cross_entropy: 2.1820406913757324 +[2025-04-27 10:59:12,684][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 2.002859115600586, cross_entropy: 2.002859115600586 +[2025-04-27 10:59:12,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.529122829437256, cross_entropy: 2.529122829437256 +[2025-04-27 10:59:14,507][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 3.1682324409484863, cross_entropy: 3.1682324409484863 +[2025-04-27 10:59:15,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.7347545623779297, cross_entropy: 3.7347545623779297 +[2025-04-27 10:59:16,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 2.6719424724578857, cross_entropy: 2.6719424724578857 +[2025-04-27 10:59:17,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 3.0851120948791504, cross_entropy: 3.0851120948791504 +[2025-04-27 10:59:19,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.6650795936584473, cross_entropy: 3.6650795936584473 +[2025-04-27 10:59:19,409][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 2.28082275390625, cross_entropy: 2.28082275390625 +[2025-04-27 10:59:22,019][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 3.7177321910858154, cross_entropy: 3.7177321910858154 +[2025-04-27 10:59:22,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.640869379043579, cross_entropy: 3.640869379043579 +[2025-04-27 10:59:24,285][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 3.894871473312378, cross_entropy: 3.894871473312378 +[2025-04-27 10:59:24,408][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.463930606842041, cross_entropy: 2.463930606842041 +[2025-04-27 10:59:26,518][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.9226064682006836, cross_entropy: 2.9226064682006836 +[2025-04-27 10:59:26,642][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 3.4005424976348877, cross_entropy: 3.4005424976348877 +[2025-04-27 10:59:28,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 2.3808164596557617, cross_entropy: 2.3808164596557617 +[2025-04-27 10:59:29,012][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 2.5796260833740234, cross_entropy: 2.5796260833740234 +[2025-04-27 10:59:31,416][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.5164928436279297, cross_entropy: 3.5164928436279297 +[2025-04-27 10:59:31,534][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 3.690609931945801, cross_entropy: 3.690609931945801 +[2025-04-27 10:59:34,221][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 2.284053325653076, cross_entropy: 2.284053325653076 +[2025-04-27 10:59:34,348][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.801380157470703, cross_entropy: 2.801380157470703 +[2025-04-27 10:59:36,309][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 3.1092865467071533, cross_entropy: 3.1092865467071533 +[2025-04-27 10:59:36,413][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 2.2273128032684326, cross_entropy: 2.2273128032684326 +[2025-04-27 10:59:38,470][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.8291454315185547, cross_entropy: 3.8291454315185547 +[2025-04-27 10:59:38,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 2.6259942054748535, cross_entropy: 2.6259942054748535 +[2025-04-27 10:59:40,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 2.72395396232605, cross_entropy: 2.72395396232605 +[2025-04-27 10:59:40,961][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 2.874817371368408, cross_entropy: 2.874817371368408 +[2025-04-27 10:59:43,627][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 3.1162428855895996, cross_entropy: 3.1162428855895996 +[2025-04-27 10:59:43,747][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 2.845344066619873, cross_entropy: 2.845344066619873 +[2025-04-27 10:59:45,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 3.3538687229156494, cross_entropy: 3.3538687229156494 +[2025-04-27 10:59:46,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.9835824966430664, cross_entropy: 3.9835824966430664 +[2025-04-27 10:59:48,259][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 4.285170555114746, cross_entropy: 4.285170555114746 +[2025-04-27 10:59:48,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.633596658706665, cross_entropy: 2.633596658706665 +[2025-04-27 10:59:50,461][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 3.7737667560577393, cross_entropy: 3.7737667560577393 +[2025-04-27 10:59:50,567][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 3.420238494873047, cross_entropy: 3.420238494873047 +[2025-04-27 10:59:53,101][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.863041639328003, cross_entropy: 2.863041639328003 +[2025-04-27 10:59:53,204][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.2481331825256348, cross_entropy: 3.2481331825256348 +[2025-04-27 10:59:55,516][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 3.3689002990722656, cross_entropy: 3.3689002990722656 +[2025-04-27 10:59:55,635][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.750227212905884, cross_entropy: 2.750227212905884 +[2025-04-27 10:59:57,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.977126359939575, cross_entropy: 2.977126359939575 +[2025-04-27 10:59:58,024][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.500399589538574, cross_entropy: 2.500399589538574 +[2025-04-27 10:59:59,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 4.034300804138184, cross_entropy: 4.034300804138184 +[2025-04-27 11:00:00,001][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 3.417386054992676, cross_entropy: 3.417386054992676 +[2025-04-27 11:00:01,995][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 2.627124309539795, cross_entropy: 2.627124309539795 +[2025-04-27 11:00:02,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 4.023112773895264, cross_entropy: 4.023112773895264 +[2025-04-27 11:00:04,094][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 2.6123578548431396, cross_entropy: 2.6123578548431396 +[2025-04-27 11:00:04,214][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 2.390401840209961, cross_entropy: 2.390401840209961 +[2025-04-27 11:00:06,308][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.550560474395752, cross_entropy: 2.550560474395752 +[2025-04-27 11:00:06,412][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.987898826599121, cross_entropy: 3.987898826599121 +[2025-04-27 11:00:08,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 2.663825035095215, cross_entropy: 2.663825035095215 +[2025-04-27 11:00:08,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.571181297302246, cross_entropy: 3.571181297302246 +[2025-04-27 11:00:10,694][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 2.694791793823242, cross_entropy: 2.694791793823242 +[2025-04-27 11:00:10,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 3.509888172149658, cross_entropy: 3.509888172149658 +[2025-04-27 11:00:12,609][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 2.3440628051757812, cross_entropy: 2.3440628051757812 +[2025-04-27 11:00:12,730][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 2.990278720855713, cross_entropy: 2.990278720855713 +[2025-04-27 11:00:15,161][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.9160614013671875, cross_entropy: 2.9160614013671875 +[2025-04-27 11:00:15,281][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 2.163893222808838, cross_entropy: 2.163893222808838 +[2025-04-27 11:00:17,211][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 3.0133097171783447, cross_entropy: 3.0133097171783447 +[2025-04-27 11:00:17,333][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.269432544708252, cross_entropy: 3.269432544708252 +[2025-04-27 11:00:19,679][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 3.2181620597839355, cross_entropy: 3.2181620597839355 +[2025-04-27 11:00:19,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 3.7263877391815186, cross_entropy: 3.7263877391815186 +[2025-04-27 11:00:22,382][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.821518659591675, cross_entropy: 3.821518659591675 +[2025-04-27 11:00:23,313][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 2.676675319671631, cross_entropy: 2.676675319671631 +[2025-04-27 11:00:24,286][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.7758049964904785, cross_entropy: 3.7758049964904785 +[2025-04-27 11:00:25,521][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 2.641850233078003, cross_entropy: 2.641850233078003 +[2025-04-27 11:00:27,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 2.6806607246398926, cross_entropy: 2.6806607246398926 +[2025-04-27 11:00:28,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.7113935947418213, cross_entropy: 2.7113935947418213 +[2025-04-27 11:00:29,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.9853248596191406, cross_entropy: 2.9853248596191406 +[2025-04-27 11:00:30,209][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.5086281299591064, cross_entropy: 2.5086281299591064 +[2025-04-27 11:00:31,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 3.7903084754943848, cross_entropy: 3.7903084754943848 +[2025-04-27 11:00:32,160][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 2.964646816253662, cross_entropy: 2.964646816253662 +[2025-04-27 11:00:33,949][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.3481836318969727, cross_entropy: 3.3481836318969727 +[2025-04-27 11:00:34,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 2.350881814956665, cross_entropy: 2.350881814956665 +[2025-04-27 11:00:36,526][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 2.9593780040740967, cross_entropy: 2.9593780040740967 +[2025-04-27 11:02:24,803][BaseTrainer][INFO] - [Epoch 2/10] (train) 3.086688280105591, cross_entropy: 3.086688280105591 +[2025-04-27 11:02:24,803][BaseTrainer][INFO] - [Epoch 2/10] (validation) 2.3136823177337646, cross_entropy: 2.3136823177337646 +[2025-04-27 11:02:25,029][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:02:25,191][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch2.pth. +[2025-04-27 11:02:25,397][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:02:28,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 3.51521897315979, cross_entropy: 3.51521897315979 +[2025-04-27 11:02:28,456][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.8999474048614502, cross_entropy: 1.8999474048614502 +[2025-04-27 11:02:31,241][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 2.424591541290283, cross_entropy: 2.424591541290283 +[2025-04-27 11:02:31,359][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 3.289816379547119, cross_entropy: 3.289816379547119 +[2025-04-27 11:02:33,792][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 2.3464417457580566, cross_entropy: 2.3464417457580566 +[2025-04-27 11:02:33,912][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 3.1230921745300293, cross_entropy: 3.1230921745300293 +[2025-04-27 11:02:35,794][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 2.1866462230682373, cross_entropy: 2.1866462230682373 +[2025-04-27 11:02:35,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 2.862107992172241, cross_entropy: 2.862107992172241 +[2025-04-27 11:02:38,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 2.1710729598999023, cross_entropy: 2.1710729598999023 +[2025-04-27 11:02:38,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 2.6569666862487793, cross_entropy: 2.6569666862487793 +[2025-04-27 11:02:39,832][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.953878879547119, cross_entropy: 2.953878879547119 +[2025-04-27 11:02:39,936][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 2.597506523132324, cross_entropy: 2.597506523132324 +[2025-04-27 11:02:41,769][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 2.5181307792663574, cross_entropy: 2.5181307792663574 +[2025-04-27 11:02:41,887][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.9332408905029297, cross_entropy: 2.9332408905029297 +[2025-04-27 11:02:43,443][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.406374216079712, cross_entropy: 2.406374216079712 +[2025-04-27 11:02:43,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 2.641831398010254, cross_entropy: 2.641831398010254 +[2025-04-27 11:02:46,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.948756217956543, cross_entropy: 3.948756217956543 +[2025-04-27 11:02:46,312][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.6474251747131348, cross_entropy: 2.6474251747131348 +[2025-04-27 11:02:48,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.872640609741211, cross_entropy: 1.872640609741211 +[2025-04-27 11:02:48,489][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 2.2995095252990723, cross_entropy: 2.2995095252990723 +[2025-04-27 11:02:50,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 3.7370188236236572, cross_entropy: 3.7370188236236572 +[2025-04-27 11:02:50,876][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 2.0456321239471436, cross_entropy: 2.0456321239471436 +[2025-04-27 11:02:52,720][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.7260680198669434, cross_entropy: 3.7260680198669434 +[2025-04-27 11:02:52,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 3.401277542114258, cross_entropy: 3.401277542114258 +[2025-04-27 11:02:55,058][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.7668704986572266, cross_entropy: 3.7668704986572266 +[2025-04-27 11:02:55,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 4.0108489990234375, cross_entropy: 4.0108489990234375 +[2025-04-27 11:02:57,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 2.482980251312256, cross_entropy: 2.482980251312256 +[2025-04-27 11:02:59,014][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.443657636642456, cross_entropy: 2.443657636642456 +[2025-04-27 11:02:59,118][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.5735347270965576, cross_entropy: 3.5735347270965576 +[2025-04-27 11:03:00,896][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.217823028564453, cross_entropy: 2.217823028564453 +[2025-04-27 11:03:01,185][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 2.2828621864318848, cross_entropy: 2.2828621864318848 +[2025-04-27 11:03:02,598][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 2.729863166809082, cross_entropy: 2.729863166809082 +[2025-04-27 11:03:03,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.4608678817749023, cross_entropy: 3.4608678817749023 +[2025-04-27 11:03:04,590][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 3.8796451091766357, cross_entropy: 3.8796451091766357 +[2025-04-27 11:03:05,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 3.7993173599243164, cross_entropy: 3.7993173599243164 +[2025-04-27 11:03:06,826][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.6748600006103516, cross_entropy: 3.6748600006103516 +[2025-04-27 11:03:07,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.3979663848876953, cross_entropy: 2.3979663848876953 +[2025-04-27 11:03:08,894][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 2.301001787185669, cross_entropy: 2.301001787185669 +[2025-04-27 11:03:09,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 1.9459081888198853, cross_entropy: 1.9459081888198853 +[2025-04-27 11:03:11,205][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 3.490757465362549, cross_entropy: 3.490757465362549 +[2025-04-27 11:03:11,908][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 2.386119842529297, cross_entropy: 2.386119842529297 +[2025-04-27 11:03:13,333][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 3.7473320960998535, cross_entropy: 3.7473320960998535 +[2025-04-27 11:03:13,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 2.2296464443206787, cross_entropy: 2.2296464443206787 +[2025-04-27 11:03:15,246][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.654636859893799, cross_entropy: 2.654636859893799 +[2025-04-27 11:03:16,981][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 3.4266719818115234, cross_entropy: 3.4266719818115234 +[2025-04-27 11:03:17,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 2.158385992050171, cross_entropy: 2.158385992050171 +[2025-04-27 11:03:19,182][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 2.303426504135132, cross_entropy: 2.303426504135132 +[2025-04-27 11:03:20,360][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 3.0451207160949707, cross_entropy: 3.0451207160949707 +[2025-04-27 11:03:21,579][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 3.3594048023223877, cross_entropy: 3.3594048023223877 +[2025-04-27 11:03:23,237][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 2.19848895072937, cross_entropy: 2.19848895072937 +[2025-04-27 11:03:23,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.34212589263916, cross_entropy: 2.34212589263916 +[2025-04-27 11:03:25,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 2.6391916275024414, cross_entropy: 2.6391916275024414 +[2025-04-27 11:03:25,977][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 3.270284652709961, cross_entropy: 3.270284652709961 +[2025-04-27 11:03:27,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 2.3693981170654297, cross_entropy: 2.3693981170654297 +[2025-04-27 11:03:29,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.6787004470825195, cross_entropy: 3.6787004470825195 +[2025-04-27 11:03:30,566][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.7271718978881836, cross_entropy: 2.7271718978881836 +[2025-04-27 11:03:31,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.6766316890716553, cross_entropy: 3.6766316890716553 +[2025-04-27 11:03:32,311][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 1.9247974157333374, cross_entropy: 1.9247974157333374 +[2025-04-27 11:03:33,733][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.704254627227783, cross_entropy: 3.704254627227783 +[2025-04-27 11:03:34,898][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 2.5297865867614746, cross_entropy: 2.5297865867614746 +[2025-04-27 11:03:35,761][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.8202037811279297, cross_entropy: 2.8202037811279297 +[2025-04-27 11:03:36,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 3.8329005241394043, cross_entropy: 3.8329005241394043 +[2025-04-27 11:03:37,740][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.6562533378601074, cross_entropy: 3.6562533378601074 +[2025-04-27 11:03:39,569][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 2.0956263542175293, cross_entropy: 2.0956263542175293 +[2025-04-27 11:03:40,079][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 4.012495994567871, cross_entropy: 4.012495994567871 +[2025-04-27 11:03:42,524][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 3.373901844024658, cross_entropy: 3.373901844024658 +[2025-04-27 11:03:42,645][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 2.22100830078125, cross_entropy: 2.22100830078125 +[2025-04-27 11:03:44,620][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 2.936058521270752, cross_entropy: 2.936058521270752 +[2025-04-27 11:03:44,750][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.67629337310791, cross_entropy: 2.67629337310791 +[2025-04-27 11:03:46,683][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 3.66064453125, cross_entropy: 3.66064453125 +[2025-04-27 11:03:46,796][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.8890180587768555, cross_entropy: 2.8890180587768555 +[2025-04-27 11:03:49,528][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.376554012298584, cross_entropy: 2.376554012298584 +[2025-04-27 11:03:49,650][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 2.690021276473999, cross_entropy: 2.690021276473999 +[2025-04-27 11:03:51,966][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 3.580261468887329, cross_entropy: 3.580261468887329 +[2025-04-27 11:03:52,087][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.690615177154541, cross_entropy: 3.690615177154541 +[2025-04-27 11:03:54,789][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 2.3062660694122314, cross_entropy: 2.3062660694122314 +[2025-04-27 11:03:54,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 3.0995688438415527, cross_entropy: 3.0995688438415527 +[2025-04-27 11:03:57,080][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 2.478210926055908, cross_entropy: 2.478210926055908 +[2025-04-27 11:03:57,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.322495937347412, cross_entropy: 3.322495937347412 +[2025-04-27 11:03:59,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 3.1651291847229004, cross_entropy: 3.1651291847229004 +[2025-04-27 11:03:59,340][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.4773051738739014, cross_entropy: 3.4773051738739014 +[2025-04-27 11:04:01,213][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 2.0688858032226562, cross_entropy: 2.0688858032226562 +[2025-04-27 11:04:01,340][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.3307244777679443, cross_entropy: 3.3307244777679443 +[2025-04-27 11:04:03,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 2.6361396312713623, cross_entropy: 2.6361396312713623 +[2025-04-27 11:04:03,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 2.6599607467651367, cross_entropy: 2.6599607467651367 +[2025-04-27 11:04:05,586][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.4644198417663574, cross_entropy: 2.4644198417663574 +[2025-04-27 11:04:05,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 2.681934118270874, cross_entropy: 2.681934118270874 +[2025-04-27 11:04:07,641][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.557321548461914, cross_entropy: 3.557321548461914 +[2025-04-27 11:04:07,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.601255178451538, cross_entropy: 3.601255178451538 +[2025-04-27 11:04:10,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 3.418487071990967, cross_entropy: 3.418487071990967 +[2025-04-27 11:04:10,206][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 3.7166504859924316, cross_entropy: 3.7166504859924316 +[2025-04-27 11:04:12,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 2.8757262229919434, cross_entropy: 2.8757262229919434 +[2025-04-27 11:04:12,319][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 2.1191978454589844, cross_entropy: 2.1191978454589844 +[2025-04-27 11:04:14,250][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.3101258277893066, cross_entropy: 2.3101258277893066 +[2025-04-27 11:04:14,356][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.5897510051727295, cross_entropy: 3.5897510051727295 +[2025-04-27 11:04:16,807][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 2.0286474227905273, cross_entropy: 2.0286474227905273 +[2025-04-27 11:04:16,929][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.6726222038269043, cross_entropy: 3.6726222038269043 +[2025-04-27 11:04:18,821][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.808724880218506, cross_entropy: 2.808724880218506 +[2025-04-27 11:04:18,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.680756092071533, cross_entropy: 2.680756092071533 +[2025-04-27 11:04:20,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 3.979586601257324, cross_entropy: 3.979586601257324 +[2025-04-27 11:04:21,042][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.5494120121002197, cross_entropy: 2.5494120121002197 +[2025-04-27 11:04:22,773][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 4.070486068725586, cross_entropy: 4.070486068725586 +[2025-04-27 11:04:22,898][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.906952381134033, cross_entropy: 2.906952381134033 +[2025-04-27 11:04:25,195][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 3.2759227752685547, cross_entropy: 3.2759227752685547 +[2025-04-27 11:04:25,316][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 2.564438581466675, cross_entropy: 2.564438581466675 +[2025-04-27 11:04:27,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 3.283169746398926, cross_entropy: 3.283169746398926 +[2025-04-27 11:04:27,445][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.525153160095215, cross_entropy: 2.525153160095215 +[2025-04-27 11:04:29,317][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 3.797220468521118, cross_entropy: 3.797220468521118 +[2025-04-27 11:04:29,437][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 2.874547243118286, cross_entropy: 2.874547243118286 +[2025-04-27 11:04:31,370][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.9108967781066895, cross_entropy: 2.9108967781066895 +[2025-04-27 11:04:31,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.6542727947235107, cross_entropy: 2.6542727947235107 +[2025-04-27 11:04:34,092][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 2.53438138961792, cross_entropy: 2.53438138961792 +[2025-04-27 11:04:34,211][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 2.5291366577148438, cross_entropy: 2.5291366577148438 +[2025-04-27 11:04:36,606][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 2.1449217796325684, cross_entropy: 2.1449217796325684 +[2025-04-27 11:04:36,727][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 3.2011165618896484, cross_entropy: 3.2011165618896484 +[2025-04-27 11:04:38,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.8090075254440308, cross_entropy: 1.8090075254440308 +[2025-04-27 11:04:38,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.7101848125457764, cross_entropy: 2.7101848125457764 +[2025-04-27 11:04:40,266][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 4.13846492767334, cross_entropy: 4.13846492767334 +[2025-04-27 11:04:40,369][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.7901785373687744, cross_entropy: 3.7901785373687744 +[2025-04-27 11:04:42,488][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 3.0233545303344727, cross_entropy: 3.0233545303344727 +[2025-04-27 11:04:42,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 2.113804817199707, cross_entropy: 2.113804817199707 +[2025-04-27 11:04:45,275][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 3.072960376739502, cross_entropy: 3.072960376739502 +[2025-04-27 11:04:45,395][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.653653144836426, cross_entropy: 2.653653144836426 +[2025-04-27 11:04:47,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 3.4473772048950195, cross_entropy: 3.4473772048950195 +[2025-04-27 11:04:47,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.610738754272461, cross_entropy: 3.610738754272461 +[2025-04-27 11:04:49,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.223210573196411, cross_entropy: 2.223210573196411 +[2025-04-27 11:04:49,694][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.924847960472107, cross_entropy: 1.924847960472107 +[2025-04-27 11:04:51,834][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 3.906355381011963, cross_entropy: 3.906355381011963 +[2025-04-27 11:04:51,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.3557982444763184, cross_entropy: 3.3557982444763184 +[2025-04-27 11:04:54,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.6380743980407715, cross_entropy: 2.6380743980407715 +[2025-04-27 11:04:54,742][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.4736714363098145, cross_entropy: 2.4736714363098145 +[2025-04-27 11:04:56,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 3.5202078819274902, cross_entropy: 3.5202078819274902 +[2025-04-27 11:04:56,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 3.0136361122131348, cross_entropy: 3.0136361122131348 +[2025-04-27 11:04:58,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.662383556365967, cross_entropy: 2.662383556365967 +[2025-04-27 11:04:58,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.622849464416504, cross_entropy: 2.622849464416504 +[2025-04-27 11:05:00,595][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 2.227409839630127, cross_entropy: 2.227409839630127 +[2025-04-27 11:05:00,700][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.8673758506774902, cross_entropy: 2.8673758506774902 +[2025-04-27 11:05:02,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 2.344069004058838, cross_entropy: 2.344069004058838 +[2025-04-27 11:05:03,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 3.169394016265869, cross_entropy: 3.169394016265869 +[2025-04-27 11:05:05,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 3.2237281799316406, cross_entropy: 3.2237281799316406 +[2025-04-27 11:05:05,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.7504985332489014, cross_entropy: 2.7504985332489014 +[2025-04-27 11:05:07,882][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.9430525302886963, cross_entropy: 1.9430525302886963 +[2025-04-27 11:05:07,986][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.9913525581359863, cross_entropy: 2.9913525581359863 +[2025-04-27 11:05:10,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 1.928964614868164, cross_entropy: 1.928964614868164 +[2025-04-27 11:05:10,256][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.541700839996338, cross_entropy: 2.541700839996338 +[2025-04-27 11:05:12,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.3297722339630127, cross_entropy: 2.3297722339630127 +[2025-04-27 11:05:12,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.7456172704696655, cross_entropy: 1.7456172704696655 +[2025-04-27 11:05:15,050][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.5186359882354736, cross_entropy: 3.5186359882354736 +[2025-04-27 11:05:15,172][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 2.019179105758667, cross_entropy: 2.019179105758667 +[2025-04-27 11:05:17,117][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 2.9293642044067383, cross_entropy: 2.9293642044067383 +[2025-04-27 11:05:17,238][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 2.2529096603393555, cross_entropy: 2.2529096603393555 +[2025-04-27 11:05:19,084][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 3.0397326946258545, cross_entropy: 3.0397326946258545 +[2025-04-27 11:05:19,204][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.6040310859680176, cross_entropy: 2.6040310859680176 +[2025-04-27 11:05:21,289][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 2.396733283996582, cross_entropy: 2.396733283996582 +[2025-04-27 11:05:21,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.8856263160705566, cross_entropy: 2.8856263160705566 +[2025-04-27 11:05:23,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 3.3626043796539307, cross_entropy: 3.3626043796539307 +[2025-04-27 11:05:24,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 2.28776216506958, cross_entropy: 2.28776216506958 +[2025-04-27 11:05:25,837][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 3.7174291610717773, cross_entropy: 3.7174291610717773 +[2025-04-27 11:05:27,240][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 2.3649487495422363, cross_entropy: 2.3649487495422363 +[2025-04-27 11:05:27,959][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 2.4618208408355713, cross_entropy: 2.4618208408355713 +[2025-04-27 11:05:30,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.6128177642822266, cross_entropy: 3.6128177642822266 +[2025-04-27 11:05:30,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 2.6156673431396484, cross_entropy: 2.6156673431396484 +[2025-04-27 11:05:32,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.878786563873291, cross_entropy: 3.878786563873291 +[2025-04-27 11:05:32,802][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 3.1178622245788574, cross_entropy: 3.1178622245788574 +[2025-04-27 11:05:34,775][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 3.276731014251709, cross_entropy: 3.276731014251709 +[2025-04-27 11:05:35,192][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 2.178727388381958, cross_entropy: 2.178727388381958 +[2025-04-27 11:05:36,778][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 2.150359630584717, cross_entropy: 2.150359630584717 +[2025-04-27 11:05:37,700][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 2.858424663543701, cross_entropy: 2.858424663543701 +[2025-04-27 11:05:38,797][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 2.3362646102905273, cross_entropy: 2.3362646102905273 +[2025-04-27 11:05:40,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.2825913429260254, cross_entropy: 3.2825913429260254 +[2025-04-27 11:05:40,931][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 2.3306355476379395, cross_entropy: 2.3306355476379395 +[2025-04-27 11:05:42,456][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.9679274559020996, cross_entropy: 2.9679274559020996 +[2025-04-27 11:05:43,214][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.420283317565918, cross_entropy: 3.420283317565918 +[2025-04-27 11:05:44,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.9153892993927, cross_entropy: 2.9153892993927 +[2025-04-27 11:05:45,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.7786707878112793, cross_entropy: 2.7786707878112793 +[2025-04-27 11:05:46,475][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.7677416801452637, cross_entropy: 2.7677416801452637 +[2025-04-27 11:05:47,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.690286636352539, cross_entropy: 2.690286636352539 +[2025-04-27 11:05:49,287][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 2.167698860168457, cross_entropy: 2.167698860168457 +[2025-04-27 11:05:49,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 2.1196560859680176, cross_entropy: 2.1196560859680176 +[2025-04-27 11:05:50,905][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 3.2291059494018555, cross_entropy: 3.2291059494018555 +[2025-04-27 11:05:51,947][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 2.2901182174682617, cross_entropy: 2.2901182174682617 +[2025-04-27 11:05:53,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.810901641845703, cross_entropy: 2.810901641845703 +[2025-04-27 11:05:54,899][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.9229555130004883, cross_entropy: 2.9229555130004883 +[2025-04-27 11:05:55,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.264004945755005, cross_entropy: 2.264004945755005 +[2025-04-27 11:05:57,481][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 3.065999984741211, cross_entropy: 3.065999984741211 +[2025-04-27 11:05:57,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 2.2994117736816406, cross_entropy: 2.2994117736816406 +[2025-04-27 11:05:59,699][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.7911672592163086, cross_entropy: 2.7911672592163086 +[2025-04-27 11:05:59,818][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 3.845578193664551, cross_entropy: 3.845578193664551 +[2025-04-27 11:06:02,081][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.2932910919189453, cross_entropy: 3.2932910919189453 +[2025-04-27 11:06:02,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.5564181804656982, cross_entropy: 3.5564181804656982 +[2025-04-27 11:06:04,190][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.7391021251678467, cross_entropy: 2.7391021251678467 +[2025-04-27 11:06:04,439][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 3.30714750289917, cross_entropy: 3.30714750289917 +[2025-04-27 11:06:06,313][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 3.1789069175720215, cross_entropy: 3.1789069175720215 +[2025-04-27 11:06:06,454][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 3.3971076011657715, cross_entropy: 3.3971076011657715 +[2025-04-27 11:06:08,042][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 3.3042850494384766, cross_entropy: 3.3042850494384766 +[2025-04-27 11:06:08,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 3.798658847808838, cross_entropy: 3.798658847808838 +[2025-04-27 11:06:10,442][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 2.289311408996582, cross_entropy: 2.289311408996582 +[2025-04-27 11:06:11,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 3.9059596061706543, cross_entropy: 3.9059596061706543 +[2025-04-27 11:06:12,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 2.1040024757385254, cross_entropy: 2.1040024757385254 +[2025-04-27 11:06:13,182][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 3.731963872909546, cross_entropy: 3.731963872909546 +[2025-04-27 11:06:15,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.612183094024658, cross_entropy: 2.612183094024658 +[2025-04-27 11:06:15,644][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.222867965698242, cross_entropy: 2.222867965698242 +[2025-04-27 11:06:17,805][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.6032958030700684, cross_entropy: 3.6032958030700684 +[2025-04-27 11:06:18,181][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.429255485534668, cross_entropy: 2.429255485534668 +[2025-04-27 11:06:19,928][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.7064077854156494, cross_entropy: 3.7064077854156494 +[2025-04-27 11:06:20,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 2.9505491256713867, cross_entropy: 2.9505491256713867 +[2025-04-27 11:06:22,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.980661392211914, cross_entropy: 2.980661392211914 +[2025-04-27 11:06:22,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 3.2676444053649902, cross_entropy: 3.2676444053649902 +[2025-04-27 11:06:24,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.455195426940918, cross_entropy: 2.455195426940918 +[2025-04-27 11:06:24,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.307363510131836, cross_entropy: 2.307363510131836 +[2025-04-27 11:06:26,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 3.072962522506714, cross_entropy: 3.072962522506714 +[2025-04-27 11:06:26,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 3.256488561630249, cross_entropy: 3.256488561630249 +[2025-04-27 11:06:28,746][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 2.2245657444000244, cross_entropy: 2.2245657444000244 +[2025-04-27 11:06:29,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.3032634258270264, cross_entropy: 2.3032634258270264 +[2025-04-27 11:06:31,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 2.0187268257141113, cross_entropy: 2.0187268257141113 +[2025-04-27 11:06:31,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 4.022496700286865, cross_entropy: 4.022496700286865 +[2025-04-27 11:06:33,294][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.565298318862915, cross_entropy: 2.565298318862915 +[2025-04-27 11:06:33,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.6393966674804688, cross_entropy: 3.6393966674804688 +[2025-04-27 11:06:35,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 3.103264331817627, cross_entropy: 3.103264331817627 +[2025-04-27 11:06:35,623][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 2.2018909454345703, cross_entropy: 2.2018909454345703 +[2025-04-27 11:06:37,524][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 2.2625021934509277, cross_entropy: 2.2625021934509277 +[2025-04-27 11:06:37,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 3.456286668777466, cross_entropy: 3.456286668777466 +[2025-04-27 11:06:39,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.6464338302612305, cross_entropy: 3.6464338302612305 +[2025-04-27 11:06:39,880][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.508119583129883, cross_entropy: 3.508119583129883 +[2025-04-27 11:06:42,017][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.686378240585327, cross_entropy: 3.686378240585327 +[2025-04-27 11:06:42,120][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 3.6651878356933594, cross_entropy: 3.6651878356933594 +[2025-04-27 11:06:44,390][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.7597782611846924, cross_entropy: 1.7597782611846924 +[2025-04-27 11:06:44,509][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.1237335205078125, cross_entropy: 3.1237335205078125 +[2025-04-27 11:06:46,989][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 2.3776044845581055, cross_entropy: 2.3776044845581055 +[2025-04-27 11:06:47,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.7067718505859375, cross_entropy: 3.7067718505859375 +[2025-04-27 11:06:49,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.7321197986602783, cross_entropy: 2.7321197986602783 +[2025-04-27 11:06:49,308][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.522566795349121, cross_entropy: 3.522566795349121 +[2025-04-27 11:06:52,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 2.5112836360931396, cross_entropy: 2.5112836360931396 +[2025-04-27 11:06:52,314][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 3.4167110919952393, cross_entropy: 3.4167110919952393 +[2025-04-27 11:06:55,402][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.682711124420166, cross_entropy: 3.682711124420166 +[2025-04-27 11:06:55,519][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.5973401069641113, cross_entropy: 2.5973401069641113 +[2025-04-27 11:06:57,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.5472309589385986, cross_entropy: 3.5472309589385986 +[2025-04-27 11:06:57,723][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 3.430954933166504, cross_entropy: 3.430954933166504 +[2025-04-27 11:06:59,556][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 3.0683751106262207, cross_entropy: 3.0683751106262207 +[2025-04-27 11:06:59,674][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 2.020087957382202, cross_entropy: 2.020087957382202 +[2025-04-27 11:07:01,656][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 3.33601713180542, cross_entropy: 3.33601713180542 +[2025-04-27 11:07:01,815][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 3.636549472808838, cross_entropy: 3.636549472808838 +[2025-04-27 11:07:03,827][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 3.904665470123291, cross_entropy: 3.904665470123291 +[2025-04-27 11:07:03,947][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 3.636247158050537, cross_entropy: 3.636247158050537 +[2025-04-27 11:07:06,034][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.8119889497756958, cross_entropy: 1.8119889497756958 +[2025-04-27 11:07:06,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.4339871406555176, cross_entropy: 2.4339871406555176 +[2025-04-27 11:07:08,376][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.671168327331543, cross_entropy: 3.671168327331543 +[2025-04-27 11:07:08,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 2.614436388015747, cross_entropy: 2.614436388015747 +[2025-04-27 11:07:10,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 3.0900092124938965, cross_entropy: 3.0900092124938965 +[2025-04-27 11:07:10,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.0897889137268066, cross_entropy: 2.0897889137268066 +[2025-04-27 11:07:12,724][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.688473701477051, cross_entropy: 2.688473701477051 +[2025-04-27 11:07:13,041][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 2.6409292221069336, cross_entropy: 2.6409292221069336 +[2025-04-27 11:07:15,150][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 2.40724515914917, cross_entropy: 2.40724515914917 +[2025-04-27 11:07:15,682][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 2.586975574493408, cross_entropy: 2.586975574493408 +[2025-04-27 11:07:16,901][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.910545825958252, cross_entropy: 3.910545825958252 +[2025-04-27 11:07:17,653][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 3.9830682277679443, cross_entropy: 3.9830682277679443 +[2025-04-27 11:07:18,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.7558403015136719, cross_entropy: 1.7558403015136719 +[2025-04-27 11:07:19,638][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 2.1898317337036133, cross_entropy: 2.1898317337036133 +[2025-04-27 11:07:22,118][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.8035868406295776, cross_entropy: 1.8035868406295776 +[2025-04-27 11:07:22,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.2116920948028564, cross_entropy: 2.2116920948028564 +[2025-04-27 11:07:24,267][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 2.649505376815796, cross_entropy: 2.649505376815796 +[2025-04-27 11:07:24,386][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 3.6114602088928223, cross_entropy: 3.6114602088928223 +[2025-04-27 11:07:26,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.1189990043640137, cross_entropy: 3.1189990043640137 +[2025-04-27 11:07:26,692][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 2.003404140472412, cross_entropy: 2.003404140472412 +[2025-04-27 11:07:28,543][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.5478787422180176, cross_entropy: 3.5478787422180176 +[2025-04-27 11:07:29,041][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 3.6420507431030273, cross_entropy: 3.6420507431030273 +[2025-04-27 11:07:31,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.6926681995391846, cross_entropy: 3.6926681995391846 +[2025-04-27 11:07:31,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 2.669060230255127, cross_entropy: 2.669060230255127 +[2025-04-27 11:07:33,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.4523534774780273, cross_entropy: 3.4523534774780273 +[2025-04-27 11:07:34,522][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 3.462869644165039, cross_entropy: 3.462869644165039 +[2025-04-27 11:07:36,292][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.5908303260803223, cross_entropy: 3.5908303260803223 +[2025-04-27 11:07:36,411][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 3.6449732780456543, cross_entropy: 3.6449732780456543 +[2025-04-27 11:07:38,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.7758045196533203, cross_entropy: 3.7758045196533203 +[2025-04-27 11:07:38,817][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.4864041805267334, cross_entropy: 2.4864041805267334 +[2025-04-27 11:07:40,251][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 3.3376388549804688, cross_entropy: 3.3376388549804688 +[2025-04-27 11:07:41,156][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 2.2191295623779297, cross_entropy: 2.2191295623779297 +[2025-04-27 11:07:42,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 2.8402936458587646, cross_entropy: 2.8402936458587646 +[2025-04-27 11:07:43,306][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 2.9220352172851562, cross_entropy: 2.9220352172851562 +[2025-04-27 11:07:44,795][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 2.6724886894226074, cross_entropy: 2.6724886894226074 +[2025-04-27 11:07:45,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 3.578547954559326, cross_entropy: 3.578547954559326 +[2025-04-27 11:07:47,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 2.0767321586608887, cross_entropy: 2.0767321586608887 +[2025-04-27 11:07:48,471][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.0824389457702637, cross_entropy: 3.0824389457702637 +[2025-04-27 11:07:48,647][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 2.5610690116882324, cross_entropy: 2.5610690116882324 +[2025-04-27 11:07:50,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 3.068530797958374, cross_entropy: 3.068530797958374 +[2025-04-27 11:07:50,602][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.948371171951294, cross_entropy: 1.948371171951294 +[2025-04-27 11:07:52,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 3.683769941329956, cross_entropy: 3.683769941329956 +[2025-04-27 11:07:53,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.711120367050171, cross_entropy: 2.711120367050171 +[2025-04-27 11:07:54,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 2.167487144470215, cross_entropy: 2.167487144470215 +[2025-04-27 11:07:54,726][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/iteration1000.pth. +[2025-04-27 11:07:55,693][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 3.0889406204223633, cross_entropy: 3.0889406204223633 +[2025-04-27 11:07:56,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 2.613959312438965, cross_entropy: 2.613959312438965 +[2025-04-27 11:07:57,542][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.5237770080566406, cross_entropy: 3.5237770080566406 +[2025-04-27 11:07:58,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 2.4893898963928223, cross_entropy: 2.4893898963928223 +[2025-04-27 11:07:59,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 2.2973313331604004, cross_entropy: 2.2973313331604004 +[2025-04-27 11:08:01,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.4279255867004395, cross_entropy: 2.4279255867004395 +[2025-04-27 11:08:02,147][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.308091163635254, cross_entropy: 2.308091163635254 +[2025-04-27 11:08:03,972][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.2210357189178467, cross_entropy: 2.2210357189178467 +[2025-04-27 11:08:04,684][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 3.1640543937683105, cross_entropy: 3.1640543937683105 +[2025-04-27 11:08:06,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.3148033618927, cross_entropy: 2.3148033618927 +[2025-04-27 11:08:07,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.3327531814575195, cross_entropy: 3.3327531814575195 +[2025-04-27 11:08:09,814][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.834437370300293, cross_entropy: 2.834437370300293 +[2025-04-27 11:08:10,844][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 2.1794447898864746, cross_entropy: 2.1794447898864746 +[2025-04-27 11:08:11,906][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 3.820481777191162, cross_entropy: 3.820481777191162 +[2025-04-27 11:08:12,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 2.2650020122528076, cross_entropy: 2.2650020122528076 +[2025-04-27 11:08:14,272][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.7772727012634277, cross_entropy: 3.7772727012634277 +[2025-04-27 11:08:15,246][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 3.0518014430999756, cross_entropy: 3.0518014430999756 +[2025-04-27 11:08:16,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 3.4928736686706543, cross_entropy: 3.4928736686706543 +[2025-04-27 11:08:17,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 1.9401661157608032, cross_entropy: 1.9401661157608032 +[2025-04-27 11:08:18,574][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 3.6253488063812256, cross_entropy: 3.6253488063812256 +[2025-04-27 11:08:19,245][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.677055835723877, cross_entropy: 3.677055835723877 +[2025-04-27 11:08:20,845][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.294490337371826, cross_entropy: 2.294490337371826 +[2025-04-27 11:08:21,261][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 2.6426501274108887, cross_entropy: 2.6426501274108887 +[2025-04-27 11:08:22,747][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 3.2588248252868652, cross_entropy: 3.2588248252868652 +[2025-04-27 11:08:23,878][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 2.215728998184204, cross_entropy: 2.215728998184204 +[2025-04-27 11:08:25,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.694652557373047, cross_entropy: 2.694652557373047 +[2025-04-27 11:08:27,468][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 3.549398899078369, cross_entropy: 3.549398899078369 +[2025-04-27 11:08:27,725][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.8472373485565186, cross_entropy: 2.8472373485565186 +[2025-04-27 11:08:29,475][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 3.0924975872039795, cross_entropy: 3.0924975872039795 +[2025-04-27 11:08:30,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 3.5855844020843506, cross_entropy: 3.5855844020843506 +[2025-04-27 11:08:31,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.9716304540634155, cross_entropy: 1.9716304540634155 +[2025-04-27 11:08:32,551][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.4416556358337402, cross_entropy: 3.4416556358337402 +[2025-04-27 11:08:33,065][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 2.170654058456421, cross_entropy: 2.170654058456421 +[2025-04-27 11:08:34,458][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 3.687814235687256, cross_entropy: 3.687814235687256 +[2025-04-27 11:08:35,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 2.001255512237549, cross_entropy: 2.001255512237549 +[2025-04-27 11:08:37,403][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 3.622136116027832, cross_entropy: 3.622136116027832 +[2025-04-27 11:08:37,833][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 3.096071720123291, cross_entropy: 3.096071720123291 +[2025-04-27 11:08:39,943][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 3.1112823486328125, cross_entropy: 3.1112823486328125 +[2025-04-27 11:08:40,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 4.003813743591309, cross_entropy: 4.003813743591309 +[2025-04-27 11:08:41,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.5604257583618164, cross_entropy: 3.5604257583618164 +[2025-04-27 11:08:42,528][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 2.5854809284210205, cross_entropy: 2.5854809284210205 +[2025-04-27 11:08:44,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 2.907242774963379, cross_entropy: 2.907242774963379 +[2025-04-27 11:08:44,628][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 4.157035827636719, cross_entropy: 4.157035827636719 +[2025-04-27 11:08:47,079][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.3711142539978027, cross_entropy: 2.3711142539978027 +[2025-04-27 11:08:47,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 3.3138747215270996, cross_entropy: 3.3138747215270996 +[2025-04-27 11:08:49,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 3.5731983184814453, cross_entropy: 3.5731983184814453 +[2025-04-27 11:08:49,755][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 2.081406593322754, cross_entropy: 2.081406593322754 +[2025-04-27 11:08:51,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.469721794128418, cross_entropy: 2.469721794128418 +[2025-04-27 11:08:51,786][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 3.6201281547546387, cross_entropy: 3.6201281547546387 +[2025-04-27 11:08:53,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 2.435009241104126, cross_entropy: 2.435009241104126 +[2025-04-27 11:08:54,121][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 3.5094289779663086, cross_entropy: 3.5094289779663086 +[2025-04-27 11:08:56,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 3.2617990970611572, cross_entropy: 3.2617990970611572 +[2025-04-27 11:08:56,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 2.227809429168701, cross_entropy: 2.227809429168701 +[2025-04-27 11:08:59,261][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.4791197776794434, cross_entropy: 2.4791197776794434 +[2025-04-27 11:08:59,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 2.5272014141082764, cross_entropy: 2.5272014141082764 +[2025-04-27 11:09:01,665][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.60534405708313, cross_entropy: 3.60534405708313 +[2025-04-27 11:09:01,787][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 3.5616707801818848, cross_entropy: 3.5616707801818848 +[2025-04-27 11:09:04,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 2.142526388168335, cross_entropy: 2.142526388168335 +[2025-04-27 11:09:04,272][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.946096658706665, cross_entropy: 1.946096658706665 +[2025-04-27 11:09:06,389][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 2.7745537757873535, cross_entropy: 2.7745537757873535 +[2025-04-27 11:09:06,499][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 2.4176158905029297, cross_entropy: 2.4176158905029297 +[2025-04-27 11:09:08,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 3.821469306945801, cross_entropy: 3.821469306945801 +[2025-04-27 11:09:08,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 3.3348588943481445, cross_entropy: 3.3348588943481445 +[2025-04-27 11:09:10,758][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 3.247925043106079, cross_entropy: 3.247925043106079 +[2025-04-27 11:09:10,879][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.1229052543640137, cross_entropy: 3.1229052543640137 +[2025-04-27 11:09:12,731][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 2.4914493560791016, cross_entropy: 2.4914493560791016 +[2025-04-27 11:09:12,834][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 3.225564479827881, cross_entropy: 3.225564479827881 +[2025-04-27 11:09:14,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.368368148803711, cross_entropy: 2.368368148803711 +[2025-04-27 11:11:03,426][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.9095120429992676, cross_entropy: 2.9095120429992676 +[2025-04-27 11:11:03,427][BaseTrainer][INFO] - [Epoch 3/10] (validation) 2.1416773796081543, cross_entropy: 2.1416773796081543 +[2025-04-27 11:11:03,632][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:11:03,789][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch3.pth. +[2025-04-27 11:11:03,997][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:11:06,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.8343994617462158, cross_entropy: 1.8343994617462158 +[2025-04-27 11:11:06,621][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 1.9227895736694336, cross_entropy: 1.9227895736694336 +[2025-04-27 11:11:08,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 2.461364269256592, cross_entropy: 2.461364269256592 +[2025-04-27 11:11:08,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 2.351745128631592, cross_entropy: 2.351745128631592 +[2025-04-27 11:11:10,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 2.2775325775146484, cross_entropy: 2.2775325775146484 +[2025-04-27 11:11:10,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 2.09745454788208, cross_entropy: 2.09745454788208 +[2025-04-27 11:11:12,876][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 2.277919292449951, cross_entropy: 2.277919292449951 +[2025-04-27 11:11:12,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 3.1771481037139893, cross_entropy: 3.1771481037139893 +[2025-04-27 11:11:14,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 2.305752992630005, cross_entropy: 2.305752992630005 +[2025-04-27 11:11:15,013][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 3.859005928039551, cross_entropy: 3.859005928039551 +[2025-04-27 11:11:16,891][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.5322561264038086, cross_entropy: 3.5322561264038086 +[2025-04-27 11:11:17,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.5596022605895996, cross_entropy: 2.5596022605895996 +[2025-04-27 11:11:18,955][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 2.1021766662597656, cross_entropy: 2.1021766662597656 +[2025-04-27 11:11:20,117][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 3.6532163619995117, cross_entropy: 3.6532163619995117 +[2025-04-27 11:11:20,735][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 2.002697706222534, cross_entropy: 2.002697706222534 +[2025-04-27 11:11:22,092][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.6928380727767944, cross_entropy: 1.6928380727767944 +[2025-04-27 11:11:22,786][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.9945430755615234, cross_entropy: 2.9945430755615234 +[2025-04-27 11:11:24,117][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 2.2633585929870605, cross_entropy: 2.2633585929870605 +[2025-04-27 11:11:26,073][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.7558531761169434, cross_entropy: 3.7558531761169434 +[2025-04-27 11:11:26,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.6815428733825684, cross_entropy: 2.6815428733825684 +[2025-04-27 11:11:28,120][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 1.9820753335952759, cross_entropy: 1.9820753335952759 +[2025-04-27 11:11:28,291][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 2.225696086883545, cross_entropy: 2.225696086883545 +[2025-04-27 11:11:30,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.9289331436157227, cross_entropy: 2.9289331436157227 +[2025-04-27 11:11:30,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 2.4078867435455322, cross_entropy: 2.4078867435455322 +[2025-04-27 11:11:32,732][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.953549385070801, cross_entropy: 2.953549385070801 +[2025-04-27 11:11:32,854][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 2.3080201148986816, cross_entropy: 2.3080201148986816 +[2025-04-27 11:11:35,855][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.8072876930236816, cross_entropy: 2.8072876930236816 +[2025-04-27 11:11:35,977][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.1911094188690186, cross_entropy: 3.1911094188690186 +[2025-04-27 11:11:38,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.5197579860687256, cross_entropy: 2.5197579860687256 +[2025-04-27 11:11:38,147][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.0107431411743164, cross_entropy: 2.0107431411743164 +[2025-04-27 11:11:39,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 3.129639148712158, cross_entropy: 3.129639148712158 +[2025-04-27 11:11:39,966][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.970788598060608, cross_entropy: 1.970788598060608 +[2025-04-27 11:11:42,196][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 2.030522346496582, cross_entropy: 2.030522346496582 +[2025-04-27 11:11:42,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.3410606384277344, cross_entropy: 2.3410606384277344 +[2025-04-27 11:11:44,182][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 3.3235931396484375, cross_entropy: 3.3235931396484375 +[2025-04-27 11:11:44,285][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 2.8099427223205566, cross_entropy: 2.8099427223205566 +[2025-04-27 11:11:46,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 2.1446681022644043, cross_entropy: 2.1446681022644043 +[2025-04-27 11:11:46,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 3.276670217514038, cross_entropy: 3.276670217514038 +[2025-04-27 11:11:48,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.6973490715026855, cross_entropy: 3.6973490715026855 +[2025-04-27 11:11:48,920][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 3.6102733612060547, cross_entropy: 3.6102733612060547 +[2025-04-27 11:11:51,932][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.0828709602355957, cross_entropy: 2.0828709602355957 +[2025-04-27 11:11:52,052][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 3.197181463241577, cross_entropy: 3.197181463241577 +[2025-04-27 11:11:54,115][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.5266737937927246, cross_entropy: 2.5266737937927246 +[2025-04-27 11:11:54,234][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.1050775051116943, cross_entropy: 2.1050775051116943 +[2025-04-27 11:11:56,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 3.0856773853302, cross_entropy: 3.0856773853302 +[2025-04-27 11:11:56,268][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 1.9040303230285645, cross_entropy: 1.9040303230285645 +[2025-04-27 11:11:58,721][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.2575604915618896, cross_entropy: 2.2575604915618896 +[2025-04-27 11:11:58,825][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.830525517463684, cross_entropy: 1.830525517463684 +[2025-04-27 11:12:01,046][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.8384169340133667, cross_entropy: 1.8384169340133667 +[2025-04-27 11:12:01,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.7069077491760254, cross_entropy: 2.7069077491760254 +[2025-04-27 11:12:03,179][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 2.0538253784179688, cross_entropy: 2.0538253784179688 +[2025-04-27 11:12:03,300][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 3.3213071823120117, cross_entropy: 3.3213071823120117 +[2025-04-27 11:12:05,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.520392894744873, cross_entropy: 2.520392894744873 +[2025-04-27 11:12:05,852][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.971132755279541, cross_entropy: 2.971132755279541 +[2025-04-27 11:12:07,707][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 3.7171664237976074, cross_entropy: 3.7171664237976074 +[2025-04-27 11:12:07,839][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.7401082515716553, cross_entropy: 1.7401082515716553 +[2025-04-27 11:12:09,489][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.2450904846191406, cross_entropy: 2.2450904846191406 +[2025-04-27 11:12:09,614][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.0978171825408936, cross_entropy: 2.0978171825408936 +[2025-04-27 11:12:12,291][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 2.190450668334961, cross_entropy: 2.190450668334961 +[2025-04-27 11:12:12,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.094386100769043, cross_entropy: 2.094386100769043 +[2025-04-27 11:12:13,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 2.05857253074646, cross_entropy: 2.05857253074646 +[2025-04-27 11:12:13,909][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.2575807571411133, cross_entropy: 2.2575807571411133 +[2025-04-27 11:12:16,283][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 3.3692917823791504, cross_entropy: 3.3692917823791504 +[2025-04-27 11:12:16,403][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 1.9493095874786377, cross_entropy: 1.9493095874786377 +[2025-04-27 11:12:18,569][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.9843785762786865, cross_entropy: 2.9843785762786865 +[2025-04-27 11:12:18,688][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.9790756702423096, cross_entropy: 1.9790756702423096 +[2025-04-27 11:12:21,213][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 3.2946717739105225, cross_entropy: 3.2946717739105225 +[2025-04-27 11:12:21,330][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.4275174140930176, cross_entropy: 3.4275174140930176 +[2025-04-27 11:12:24,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.5646464824676514, cross_entropy: 2.5646464824676514 +[2025-04-27 11:12:24,283][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.2563719749450684, cross_entropy: 2.2563719749450684 +[2025-04-27 11:12:26,310][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.845923900604248, cross_entropy: 2.845923900604248 +[2025-04-27 11:12:26,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 3.5632143020629883, cross_entropy: 3.5632143020629883 +[2025-04-27 11:12:28,483][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.7662198543548584, cross_entropy: 1.7662198543548584 +[2025-04-27 11:12:28,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 2.2317326068878174, cross_entropy: 2.2317326068878174 +[2025-04-27 11:12:30,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 2.8456692695617676, cross_entropy: 2.8456692695617676 +[2025-04-27 11:12:30,303][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 2.5076260566711426, cross_entropy: 2.5076260566711426 +[2025-04-27 11:12:32,032][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 2.0703840255737305, cross_entropy: 2.0703840255737305 +[2025-04-27 11:12:32,152][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 3.3232195377349854, cross_entropy: 3.3232195377349854 +[2025-04-27 11:12:33,679][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 3.5896921157836914, cross_entropy: 3.5896921157836914 +[2025-04-27 11:12:33,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 3.411522388458252, cross_entropy: 3.411522388458252 +[2025-04-27 11:12:35,651][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.439854145050049, cross_entropy: 3.439854145050049 +[2025-04-27 11:12:35,769][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 3.63344669342041, cross_entropy: 3.63344669342041 +[2025-04-27 11:12:37,864][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 2.7354190349578857, cross_entropy: 2.7354190349578857 +[2025-04-27 11:12:37,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 2.6517958641052246, cross_entropy: 2.6517958641052246 +[2025-04-27 11:12:39,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 2.2014708518981934, cross_entropy: 2.2014708518981934 +[2025-04-27 11:12:40,013][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 2.148451805114746, cross_entropy: 2.148451805114746 +[2025-04-27 11:12:42,556][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 3.2867956161499023, cross_entropy: 3.2867956161499023 +[2025-04-27 11:12:42,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 1.6433868408203125, cross_entropy: 1.6433868408203125 +[2025-04-27 11:12:44,987][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 2.379775047302246, cross_entropy: 2.379775047302246 +[2025-04-27 11:12:45,103][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 2.442631721496582, cross_entropy: 2.442631721496582 +[2025-04-27 11:12:47,067][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 1.9507750272750854, cross_entropy: 1.9507750272750854 +[2025-04-27 11:12:47,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 2.639842987060547, cross_entropy: 2.639842987060547 +[2025-04-27 11:12:49,391][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 3.702859401702881, cross_entropy: 3.702859401702881 +[2025-04-27 11:12:49,632][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.4091975688934326, cross_entropy: 2.4091975688934326 +[2025-04-27 11:12:51,849][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 2.9294281005859375, cross_entropy: 2.9294281005859375 +[2025-04-27 11:12:52,053][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 3.8200531005859375, cross_entropy: 3.8200531005859375 +[2025-04-27 11:12:54,060][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 3.1950316429138184, cross_entropy: 3.1950316429138184 +[2025-04-27 11:12:54,233][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 2.1181581020355225, cross_entropy: 2.1181581020355225 +[2025-04-27 11:12:56,581][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 3.74910831451416, cross_entropy: 3.74910831451416 +[2025-04-27 11:12:56,703][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.7619491815567017, cross_entropy: 1.7619491815567017 +[2025-04-27 11:12:58,950][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 3.352134943008423, cross_entropy: 3.352134943008423 +[2025-04-27 11:12:59,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 3.9094786643981934, cross_entropy: 3.9094786643981934 +[2025-04-27 11:13:00,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.9828317165374756, cross_entropy: 2.9828317165374756 +[2025-04-27 11:13:01,563][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 3.78824520111084, cross_entropy: 3.78824520111084 +[2025-04-27 11:13:02,930][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.28524112701416, cross_entropy: 2.28524112701416 +[2025-04-27 11:13:04,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 2.06988263130188, cross_entropy: 2.06988263130188 +[2025-04-27 11:13:05,237][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 2.1080660820007324, cross_entropy: 2.1080660820007324 +[2025-04-27 11:13:07,649][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 3.264540195465088, cross_entropy: 3.264540195465088 +[2025-04-27 11:13:07,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 3.130544424057007, cross_entropy: 3.130544424057007 +[2025-04-27 11:13:09,588][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 2.0737195014953613, cross_entropy: 2.0737195014953613 +[2025-04-27 11:13:09,711][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 1.7953295707702637, cross_entropy: 1.7953295707702637 +[2025-04-27 11:13:12,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 2.451752185821533, cross_entropy: 2.451752185821533 +[2025-04-27 11:13:12,298][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 1.9540069103240967, cross_entropy: 1.9540069103240967 +[2025-04-27 11:13:14,485][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 3.4275670051574707, cross_entropy: 3.4275670051574707 +[2025-04-27 11:13:14,663][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 3.1365408897399902, cross_entropy: 3.1365408897399902 +[2025-04-27 11:13:16,722][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.9238312244415283, cross_entropy: 2.9238312244415283 +[2025-04-27 11:13:16,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.0662708282470703, cross_entropy: 2.0662708282470703 +[2025-04-27 11:13:20,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 2.25223445892334, cross_entropy: 2.25223445892334 +[2025-04-27 11:13:20,215][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.9552385807037354, cross_entropy: 1.9552385807037354 +[2025-04-27 11:13:22,253][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.7111613750457764, cross_entropy: 2.7111613750457764 +[2025-04-27 11:13:22,374][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 2.892275333404541, cross_entropy: 2.892275333404541 +[2025-04-27 11:13:23,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 2.988825559616089, cross_entropy: 2.988825559616089 +[2025-04-27 11:13:24,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.4778969287872314, cross_entropy: 2.4778969287872314 +[2025-04-27 11:13:26,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 3.6948163509368896, cross_entropy: 3.6948163509368896 +[2025-04-27 11:13:27,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 2.1266462802886963, cross_entropy: 2.1266462802886963 +[2025-04-27 11:13:28,368][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 2.3728647232055664, cross_entropy: 2.3728647232055664 +[2025-04-27 11:13:29,780][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 2.4231767654418945, cross_entropy: 2.4231767654418945 +[2025-04-27 11:13:30,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.00335955619812, cross_entropy: 2.00335955619812 +[2025-04-27 11:13:32,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 2.4885172843933105, cross_entropy: 2.4885172843933105 +[2025-04-27 11:13:32,624][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 2.7225277423858643, cross_entropy: 2.7225277423858643 +[2025-04-27 11:13:34,434][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 2.4410102367401123, cross_entropy: 2.4410102367401123 +[2025-04-27 11:13:34,545][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.782041549682617, cross_entropy: 2.782041549682617 +[2025-04-27 11:13:37,609][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 1.9500823020935059, cross_entropy: 1.9500823020935059 +[2025-04-27 11:13:37,736][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 2.8681282997131348, cross_entropy: 2.8681282997131348 +[2025-04-27 11:13:39,829][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 2.9456417560577393, cross_entropy: 2.9456417560577393 +[2025-04-27 11:13:39,949][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.588961124420166, cross_entropy: 2.588961124420166 +[2025-04-27 11:13:41,631][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 3.691727876663208, cross_entropy: 3.691727876663208 +[2025-04-27 11:13:41,752][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.592956066131592, cross_entropy: 2.592956066131592 +[2025-04-27 11:13:44,167][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.9699859619140625, cross_entropy: 1.9699859619140625 +[2025-04-27 11:13:44,286][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.3776121139526367, cross_entropy: 2.3776121139526367 +[2025-04-27 11:13:46,248][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 2.289999485015869, cross_entropy: 2.289999485015869 +[2025-04-27 11:13:46,369][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 1.584067463874817, cross_entropy: 1.584067463874817 +[2025-04-27 11:13:49,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 2.2973172664642334, cross_entropy: 2.2973172664642334 +[2025-04-27 11:13:49,254][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 3.2745933532714844, cross_entropy: 3.2745933532714844 +[2025-04-27 11:13:51,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 2.8189635276794434, cross_entropy: 2.8189635276794434 +[2025-04-27 11:13:51,261][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 3.855513095855713, cross_entropy: 3.855513095855713 +[2025-04-27 11:13:53,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 3.1017796993255615, cross_entropy: 3.1017796993255615 +[2025-04-27 11:13:53,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.83970308303833, cross_entropy: 3.83970308303833 +[2025-04-27 11:13:55,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 3.3236474990844727, cross_entropy: 3.3236474990844727 +[2025-04-27 11:13:55,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 3.8040218353271484, cross_entropy: 3.8040218353271484 +[2025-04-27 11:13:57,291][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 2.442019462585449, cross_entropy: 2.442019462585449 +[2025-04-27 11:13:57,416][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 3.3909013271331787, cross_entropy: 3.3909013271331787 +[2025-04-27 11:13:59,573][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 3.5221261978149414, cross_entropy: 3.5221261978149414 +[2025-04-27 11:13:59,922][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.9425933361053467, cross_entropy: 1.9425933361053467 +[2025-04-27 11:14:01,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.846381425857544, cross_entropy: 1.846381425857544 +[2025-04-27 11:14:01,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.877454996109009, cross_entropy: 2.877454996109009 +[2025-04-27 11:14:03,696][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.5423645973205566, cross_entropy: 2.5423645973205566 +[2025-04-27 11:14:04,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 2.040297031402588, cross_entropy: 2.040297031402588 +[2025-04-27 11:14:05,814][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 2.2144174575805664, cross_entropy: 2.2144174575805664 +[2025-04-27 11:14:06,449][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 2.15716552734375, cross_entropy: 2.15716552734375 +[2025-04-27 11:14:07,938][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.179807186126709, cross_entropy: 2.179807186126709 +[2025-04-27 11:14:08,088][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 1.6040370464324951, cross_entropy: 1.6040370464324951 +[2025-04-27 11:14:10,570][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 2.3134474754333496, cross_entropy: 2.3134474754333496 +[2025-04-27 11:14:10,673][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.5108518600463867, cross_entropy: 2.5108518600463867 +[2025-04-27 11:14:12,840][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 2.154029369354248, cross_entropy: 2.154029369354248 +[2025-04-27 11:14:13,352][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 3.623352289199829, cross_entropy: 3.623352289199829 +[2025-04-27 11:14:15,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 3.113574743270874, cross_entropy: 3.113574743270874 +[2025-04-27 11:14:15,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 2.5096535682678223, cross_entropy: 2.5096535682678223 +[2025-04-27 11:14:17,605][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 2.354165554046631, cross_entropy: 2.354165554046631 +[2025-04-27 11:14:17,709][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 3.3937411308288574, cross_entropy: 3.3937411308288574 +[2025-04-27 11:14:19,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 3.3904170989990234, cross_entropy: 3.3904170989990234 +[2025-04-27 11:14:19,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 1.5556511878967285, cross_entropy: 1.5556511878967285 +[2025-04-27 11:14:22,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 3.192824125289917, cross_entropy: 3.192824125289917 +[2025-04-27 11:14:22,195][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 3.483213186264038, cross_entropy: 3.483213186264038 +[2025-04-27 11:14:24,685][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 3.2496957778930664, cross_entropy: 3.2496957778930664 +[2025-04-27 11:14:24,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 3.47967529296875, cross_entropy: 3.47967529296875 +[2025-04-27 11:14:27,320][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 2.464378833770752, cross_entropy: 2.464378833770752 +[2025-04-27 11:14:27,440][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 2.0298094749450684, cross_entropy: 2.0298094749450684 +[2025-04-27 11:14:29,654][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 3.601147174835205, cross_entropy: 3.601147174835205 +[2025-04-27 11:14:29,772][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 2.3508567810058594, cross_entropy: 2.3508567810058594 +[2025-04-27 11:14:32,358][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 2.677720546722412, cross_entropy: 2.677720546722412 +[2025-04-27 11:14:32,461][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.7044243812561035, cross_entropy: 1.7044243812561035 +[2025-04-27 11:14:34,618][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.853561520576477, cross_entropy: 1.853561520576477 +[2025-04-27 11:14:34,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 3.282717227935791, cross_entropy: 3.282717227935791 +[2025-04-27 11:14:36,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 1.7473199367523193, cross_entropy: 1.7473199367523193 +[2025-04-27 11:14:36,987][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 3.143218755722046, cross_entropy: 3.143218755722046 +[2025-04-27 11:14:40,031][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 2.466050148010254, cross_entropy: 2.466050148010254 +[2025-04-27 11:14:40,152][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 2.935941696166992, cross_entropy: 2.935941696166992 +[2025-04-27 11:14:42,311][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 3.455130100250244, cross_entropy: 3.455130100250244 +[2025-04-27 11:14:42,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 1.6564805507659912, cross_entropy: 1.6564805507659912 +[2025-04-27 11:14:44,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.3873777389526367, cross_entropy: 2.3873777389526367 +[2025-04-27 11:14:45,022][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 2.1764745712280273, cross_entropy: 2.1764745712280273 +[2025-04-27 11:14:47,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 2.31459903717041, cross_entropy: 2.31459903717041 +[2025-04-27 11:14:47,362][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 1.6832159757614136, cross_entropy: 1.6832159757614136 +[2025-04-27 11:14:49,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 2.337019920349121, cross_entropy: 2.337019920349121 +[2025-04-27 11:14:49,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.9438018798828125, cross_entropy: 2.9438018798828125 +[2025-04-27 11:14:51,848][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 3.5242629051208496, cross_entropy: 3.5242629051208496 +[2025-04-27 11:14:51,953][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.494396209716797, cross_entropy: 2.494396209716797 +[2025-04-27 11:14:54,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 3.8294930458068848, cross_entropy: 3.8294930458068848 +[2025-04-27 11:14:54,202][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 3.406362533569336, cross_entropy: 3.406362533569336 +[2025-04-27 11:14:55,874][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 3.2772645950317383, cross_entropy: 3.2772645950317383 +[2025-04-27 11:14:55,995][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 3.662705421447754, cross_entropy: 3.662705421447754 +[2025-04-27 11:14:57,749][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.9606590270996094, cross_entropy: 2.9606590270996094 +[2025-04-27 11:14:57,852][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.8946294784545898, cross_entropy: 1.8946294784545898 +[2025-04-27 11:15:00,224][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 3.7126641273498535, cross_entropy: 3.7126641273498535 +[2025-04-27 11:15:00,353][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.914219379425049, cross_entropy: 2.914219379425049 +[2025-04-27 11:15:03,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 1.9539107084274292, cross_entropy: 1.9539107084274292 +[2025-04-27 11:15:03,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 3.7676877975463867, cross_entropy: 3.7676877975463867 +[2025-04-27 11:15:05,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 2.915828227996826, cross_entropy: 2.915828227996826 +[2025-04-27 11:15:05,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 3.0231266021728516, cross_entropy: 3.0231266021728516 +[2025-04-27 11:15:07,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.843681812286377, cross_entropy: 1.843681812286377 +[2025-04-27 11:15:07,341][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 3.807250499725342, cross_entropy: 3.807250499725342 +[2025-04-27 11:15:09,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 2.3397653102874756, cross_entropy: 2.3397653102874756 +[2025-04-27 11:15:09,359][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 2.0415172576904297, cross_entropy: 2.0415172576904297 +[2025-04-27 11:15:11,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.724897861480713, cross_entropy: 2.724897861480713 +[2025-04-27 11:15:11,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.6517162322998047, cross_entropy: 2.6517162322998047 +[2025-04-27 11:15:13,661][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 2.314767360687256, cross_entropy: 2.314767360687256 +[2025-04-27 11:15:13,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.5554757118225098, cross_entropy: 2.5554757118225098 +[2025-04-27 11:15:15,623][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 2.186917304992676, cross_entropy: 2.186917304992676 +[2025-04-27 11:15:15,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 3.451429843902588, cross_entropy: 3.451429843902588 +[2025-04-27 11:15:17,417][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 3.1282622814178467, cross_entropy: 3.1282622814178467 +[2025-04-27 11:15:17,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.3941969871520996, cross_entropy: 2.3941969871520996 +[2025-04-27 11:15:19,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 3.5660552978515625, cross_entropy: 3.5660552978515625 +[2025-04-27 11:15:19,673][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.166212558746338, cross_entropy: 2.166212558746338 +[2025-04-27 11:15:22,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 3.4918179512023926, cross_entropy: 3.4918179512023926 +[2025-04-27 11:15:22,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 2.138071060180664, cross_entropy: 2.138071060180664 +[2025-04-27 11:15:25,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 2.1493310928344727, cross_entropy: 2.1493310928344727 +[2025-04-27 11:15:25,322][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 2.0221571922302246, cross_entropy: 2.0221571922302246 +[2025-04-27 11:15:27,092][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 1.85648512840271, cross_entropy: 1.85648512840271 +[2025-04-27 11:15:27,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 3.3045854568481445, cross_entropy: 3.3045854568481445 +[2025-04-27 11:15:29,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.7934131622314453, cross_entropy: 2.7934131622314453 +[2025-04-27 11:15:29,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 3.109110116958618, cross_entropy: 3.109110116958618 +[2025-04-27 11:15:31,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 3.675915241241455, cross_entropy: 3.675915241241455 +[2025-04-27 11:15:31,617][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.9281549453735352, cross_entropy: 1.9281549453735352 +[2025-04-27 11:15:34,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 2.6916940212249756, cross_entropy: 2.6916940212249756 +[2025-04-27 11:15:34,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.5818562507629395, cross_entropy: 2.5818562507629395 +[2025-04-27 11:15:37,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 2.557893753051758, cross_entropy: 2.557893753051758 +[2025-04-27 11:15:37,259][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 3.068488597869873, cross_entropy: 3.068488597869873 +[2025-04-27 11:15:39,386][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.6939961910247803, cross_entropy: 3.6939961910247803 +[2025-04-27 11:15:39,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 2.0852293968200684, cross_entropy: 2.0852293968200684 +[2025-04-27 11:15:42,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 3.3910295963287354, cross_entropy: 3.3910295963287354 +[2025-04-27 11:15:42,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.2037625312805176, cross_entropy: 2.2037625312805176 +[2025-04-27 11:15:44,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.994504451751709, cross_entropy: 2.994504451751709 +[2025-04-27 11:15:44,199][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 2.7333388328552246, cross_entropy: 2.7333388328552246 +[2025-04-27 11:15:45,794][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 3.1159892082214355, cross_entropy: 3.1159892082214355 +[2025-04-27 11:15:46,037][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 2.8341689109802246, cross_entropy: 2.8341689109802246 +[2025-04-27 11:15:48,270][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 3.8821957111358643, cross_entropy: 3.8821957111358643 +[2025-04-27 11:15:48,374][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.447147846221924, cross_entropy: 2.447147846221924 +[2025-04-27 11:15:50,771][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.627549648284912, cross_entropy: 2.627549648284912 +[2025-04-27 11:15:50,895][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 2.4142751693725586, cross_entropy: 2.4142751693725586 +[2025-04-27 11:15:52,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.0354719161987305, cross_entropy: 2.0354719161987305 +[2025-04-27 11:15:52,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 3.3047165870666504, cross_entropy: 3.3047165870666504 +[2025-04-27 11:15:55,000][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 3.012312412261963, cross_entropy: 3.012312412261963 +[2025-04-27 11:15:55,121][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 2.2919304370880127, cross_entropy: 2.2919304370880127 +[2025-04-27 11:15:57,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.008829116821289, cross_entropy: 2.008829116821289 +[2025-04-27 11:15:57,411][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 2.6495962142944336, cross_entropy: 2.6495962142944336 +[2025-04-27 11:15:59,260][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 3.4883739948272705, cross_entropy: 3.4883739948272705 +[2025-04-27 11:16:00,147][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 3.5009231567382812, cross_entropy: 3.5009231567382812 +[2025-04-27 11:16:01,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.7712440490722656, cross_entropy: 1.7712440490722656 +[2025-04-27 11:16:02,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 3.6051385402679443, cross_entropy: 3.6051385402679443 +[2025-04-27 11:16:05,374][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 3.59495210647583, cross_entropy: 3.59495210647583 +[2025-04-27 11:16:05,495][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 3.220259666442871, cross_entropy: 3.220259666442871 +[2025-04-27 11:16:06,985][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 2.6433868408203125, cross_entropy: 2.6433868408203125 +[2025-04-27 11:16:08,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 3.0891904830932617, cross_entropy: 3.0891904830932617 +[2025-04-27 11:16:08,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 2.0276989936828613, cross_entropy: 2.0276989936828613 +[2025-04-27 11:16:11,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 3.4227354526519775, cross_entropy: 3.4227354526519775 +[2025-04-27 11:16:11,637][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.993980884552002, cross_entropy: 2.993980884552002 +[2025-04-27 11:16:13,282][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.454099178314209, cross_entropy: 2.454099178314209 +[2025-04-27 11:16:14,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 3.4506778717041016, cross_entropy: 3.4506778717041016 +[2025-04-27 11:16:16,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 3.117403507232666, cross_entropy: 3.117403507232666 +[2025-04-27 11:16:16,798][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 3.6917428970336914, cross_entropy: 3.6917428970336914 +[2025-04-27 11:16:18,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 2.415605068206787, cross_entropy: 2.415605068206787 +[2025-04-27 11:16:18,785][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 2.1596384048461914, cross_entropy: 2.1596384048461914 +[2025-04-27 11:16:21,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.446871280670166, cross_entropy: 2.446871280670166 +[2025-04-27 11:16:21,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 3.5458784103393555, cross_entropy: 3.5458784103393555 +[2025-04-27 11:16:22,993][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 2.482408046722412, cross_entropy: 2.482408046722412 +[2025-04-27 11:16:23,615][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 2.6011242866516113, cross_entropy: 2.6011242866516113 +[2025-04-27 11:16:25,417][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 4.074091911315918, cross_entropy: 4.074091911315918 +[2025-04-27 11:16:26,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 3.580000400543213, cross_entropy: 3.580000400543213 +[2025-04-27 11:16:28,278][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 2.0965919494628906, cross_entropy: 2.0965919494628906 +[2025-04-27 11:16:28,933][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 2.0371110439300537, cross_entropy: 2.0371110439300537 +[2025-04-27 11:16:29,977][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 3.688717842102051, cross_entropy: 3.688717842102051 +[2025-04-27 11:16:31,824][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 2.5536084175109863, cross_entropy: 2.5536084175109863 +[2025-04-27 11:16:32,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.7309412956237793, cross_entropy: 2.7309412956237793 +[2025-04-27 11:16:33,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 2.834488868713379, cross_entropy: 2.834488868713379 +[2025-04-27 11:16:33,923][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 3.317457675933838, cross_entropy: 3.317457675933838 +[2025-04-27 11:16:36,342][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 2.436444044113159, cross_entropy: 2.436444044113159 +[2025-04-27 11:16:36,460][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 2.188704490661621, cross_entropy: 2.188704490661621 +[2025-04-27 11:16:38,287][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 3.7114696502685547, cross_entropy: 3.7114696502685547 +[2025-04-27 11:16:38,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 3.455996513366699, cross_entropy: 3.455996513366699 +[2025-04-27 11:16:40,955][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 3.6179661750793457, cross_entropy: 3.6179661750793457 +[2025-04-27 11:16:41,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 2.2888448238372803, cross_entropy: 2.2888448238372803 +[2025-04-27 11:16:43,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 2.3346076011657715, cross_entropy: 2.3346076011657715 +[2025-04-27 11:16:43,368][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 2.8116002082824707, cross_entropy: 2.8116002082824707 +[2025-04-27 11:16:45,423][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 2.3999874591827393, cross_entropy: 2.3999874591827393 +[2025-04-27 11:16:45,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 2.634038209915161, cross_entropy: 2.634038209915161 +[2025-04-27 11:16:48,850][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 3.47369384765625, cross_entropy: 3.47369384765625 +[2025-04-27 11:16:48,955][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 2.309981346130371, cross_entropy: 2.309981346130371 +[2025-04-27 11:16:51,125][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.5232725143432617, cross_entropy: 2.5232725143432617 +[2025-04-27 11:16:51,230][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 3.8624279499053955, cross_entropy: 3.8624279499053955 +[2025-04-27 11:16:53,051][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 2.7019906044006348, cross_entropy: 2.7019906044006348 +[2025-04-27 11:16:53,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.228773355484009, cross_entropy: 2.228773355484009 +[2025-04-27 11:16:54,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 3.4440038204193115, cross_entropy: 3.4440038204193115 +[2025-04-27 11:16:55,083][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.933722972869873, cross_entropy: 1.933722972869873 +[2025-04-27 11:16:56,938][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 3.558640956878662, cross_entropy: 3.558640956878662 +[2025-04-27 11:16:57,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 3.5628714561462402, cross_entropy: 3.5628714561462402 +[2025-04-27 11:16:58,942][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 3.0429444313049316, cross_entropy: 3.0429444313049316 +[2025-04-27 11:16:59,047][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 2.3126134872436523, cross_entropy: 2.3126134872436523 +[2025-04-27 11:17:01,061][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.505439281463623, cross_entropy: 2.505439281463623 +[2025-04-27 11:17:01,182][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 1.7586710453033447, cross_entropy: 1.7586710453033447 +[2025-04-27 11:17:02,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.559067726135254, cross_entropy: 2.559067726135254 +[2025-04-27 11:17:03,094][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.843794822692871, cross_entropy: 1.843794822692871 +[2025-04-27 11:17:05,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 2.0631179809570312, cross_entropy: 2.0631179809570312 +[2025-04-27 11:17:05,852][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 3.1935787200927734, cross_entropy: 3.1935787200927734 +[2025-04-27 11:17:07,853][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 3.221433401107788, cross_entropy: 3.221433401107788 +[2025-04-27 11:17:07,973][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.9407029151916504, cross_entropy: 1.9407029151916504 +[2025-04-27 11:17:09,914][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 1.5193986892700195, cross_entropy: 1.5193986892700195 +[2025-04-27 11:17:10,018][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 2.259113073348999, cross_entropy: 2.259113073348999 +[2025-04-27 11:17:12,494][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.711074113845825, cross_entropy: 2.711074113845825 +[2025-04-27 11:17:12,598][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 2.3757057189941406, cross_entropy: 2.3757057189941406 +[2025-04-27 11:17:15,383][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.7797613143920898, cross_entropy: 1.7797613143920898 +[2025-04-27 11:17:15,508][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.821602702140808, cross_entropy: 1.821602702140808 +[2025-04-27 11:17:17,346][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.2452986240386963, cross_entropy: 2.2452986240386963 +[2025-04-27 11:17:17,452][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 2.8410804271698, cross_entropy: 2.8410804271698 +[2025-04-27 11:17:19,670][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 2.235069751739502, cross_entropy: 2.235069751739502 +[2025-04-27 11:17:19,792][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.4210915565490723, cross_entropy: 2.4210915565490723 +[2025-04-27 11:17:22,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 2.9627017974853516, cross_entropy: 2.9627017974853516 +[2025-04-27 11:17:22,266][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 3.607232093811035, cross_entropy: 3.607232093811035 +[2025-04-27 11:17:24,663][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 2.0193440914154053, cross_entropy: 2.0193440914154053 +[2025-04-27 11:17:24,794][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 2.2454588413238525, cross_entropy: 2.2454588413238525 +[2025-04-27 11:17:26,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.9329092502593994, cross_entropy: 1.9329092502593994 +[2025-04-27 11:17:27,048][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 3.451427459716797, cross_entropy: 3.451427459716797 +[2025-04-27 11:17:29,213][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 2.9899864196777344, cross_entropy: 2.9899864196777344 +[2025-04-27 11:17:29,334][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 2.762031078338623, cross_entropy: 2.762031078338623 +[2025-04-27 11:17:31,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 2.127211093902588, cross_entropy: 2.127211093902588 +[2025-04-27 11:17:31,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.8289105892181396, cross_entropy: 2.8289105892181396 +[2025-04-27 11:17:33,623][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 2.411680221557617, cross_entropy: 2.411680221557617 +[2025-04-27 11:17:33,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.6845176219940186, cross_entropy: 2.6845176219940186 +[2025-04-27 11:17:35,690][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 2.9050350189208984, cross_entropy: 2.9050350189208984 +[2025-04-27 11:17:36,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 2.660731315612793, cross_entropy: 2.660731315612793 +[2025-04-27 11:17:37,546][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 3.155179977416992, cross_entropy: 3.155179977416992 +[2025-04-27 11:17:38,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.3913447856903076, cross_entropy: 3.3913447856903076 +[2025-04-27 11:17:39,626][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 3.5605733394622803, cross_entropy: 3.5605733394622803 +[2025-04-27 11:17:40,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 2.3287291526794434, cross_entropy: 2.3287291526794434 +[2025-04-27 11:17:41,791][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.7065792083740234, cross_entropy: 2.7065792083740234 +[2025-04-27 11:17:43,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 2.2940220832824707, cross_entropy: 2.2940220832824707 +[2025-04-27 11:17:45,890][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 3.4061923027038574, cross_entropy: 3.4061923027038574 +[2025-04-27 11:17:45,993][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.7306573390960693, cross_entropy: 2.7306573390960693 +[2025-04-27 11:17:48,014][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.9641233682632446, cross_entropy: 1.9641233682632446 +[2025-04-27 11:17:48,119][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 3.200860023498535, cross_entropy: 3.200860023498535 +[2025-04-27 11:17:50,667][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 2.267479181289673, cross_entropy: 2.267479181289673 +[2025-04-27 11:17:50,789][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 2.795322895050049, cross_entropy: 2.795322895050049 +[2025-04-27 11:17:52,850][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 2.1629467010498047, cross_entropy: 2.1629467010498047 +[2025-04-27 11:17:52,970][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 2.3347957134246826, cross_entropy: 2.3347957134246826 +[2025-04-27 11:17:55,093][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 1.9381587505340576, cross_entropy: 1.9381587505340576 +[2025-04-27 11:17:55,187][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 2.6200404167175293, cross_entropy: 2.6200404167175293 +[2025-04-27 11:19:44,523][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.6922311782836914, cross_entropy: 2.6922311782836914 +[2025-04-27 11:19:44,524][BaseTrainer][INFO] - [Epoch 4/10] (validation) 2.0329055786132812, cross_entropy: 2.0329055786132812 +[2025-04-27 11:19:44,767][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:19:44,928][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch4.pth. +[2025-04-27 11:19:45,135][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:19:48,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.738588333129883, cross_entropy: 2.738588333129883 +[2025-04-27 11:19:48,342][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.9013590812683105, cross_entropy: 1.9013590812683105 +[2025-04-27 11:19:50,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 2.1076598167419434, cross_entropy: 2.1076598167419434 +[2025-04-27 11:19:50,725][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.8758702278137207, cross_entropy: 1.8758702278137207 +[2025-04-27 11:19:52,769][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.92348051071167, cross_entropy: 1.92348051071167 +[2025-04-27 11:19:52,934][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.865100145339966, cross_entropy: 2.865100145339966 +[2025-04-27 11:19:54,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.535402297973633, cross_entropy: 2.535402297973633 +[2025-04-27 11:19:55,642][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.628291368484497, cross_entropy: 2.628291368484497 +[2025-04-27 11:19:56,902][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 3.3086462020874023, cross_entropy: 3.3086462020874023 +[2025-04-27 11:19:57,831][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 2.0974669456481934, cross_entropy: 2.0974669456481934 +[2025-04-27 11:19:59,014][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.4375460147857666, cross_entropy: 3.4375460147857666 +[2025-04-27 11:20:00,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 2.55676007270813, cross_entropy: 2.55676007270813 +[2025-04-27 11:20:00,977][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 3.3764727115631104, cross_entropy: 3.3764727115631104 +[2025-04-27 11:20:01,908][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.3815159797668457, cross_entropy: 2.3815159797668457 +[2025-04-27 11:20:02,965][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 3.6204586029052734, cross_entropy: 3.6204586029052734 +[2025-04-27 11:20:04,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.987963914871216, cross_entropy: 2.987963914871216 +[2025-04-27 11:20:04,944][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 3.0024051666259766, cross_entropy: 3.0024051666259766 +[2025-04-27 11:20:07,039][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 3.4619691371917725, cross_entropy: 3.4619691371917725 +[2025-04-27 11:20:07,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 3.111703872680664, cross_entropy: 3.111703872680664 +[2025-04-27 11:20:09,044][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.7507593631744385, cross_entropy: 1.7507593631744385 +[2025-04-27 11:20:09,299][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 2.0034379959106445, cross_entropy: 2.0034379959106445 +[2025-04-27 11:20:11,939][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 2.462286949157715, cross_entropy: 2.462286949157715 +[2025-04-27 11:20:12,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 2.2970118522644043, cross_entropy: 2.2970118522644043 +[2025-04-27 11:20:14,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 2.214773416519165, cross_entropy: 2.214773416519165 +[2025-04-27 11:20:14,474][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.8681764602661133, cross_entropy: 1.8681764602661133 +[2025-04-27 11:20:16,692][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.9318487644195557, cross_entropy: 1.9318487644195557 +[2025-04-27 11:20:16,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 2.0148942470550537, cross_entropy: 2.0148942470550537 +[2025-04-27 11:20:18,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.9782518148422241, cross_entropy: 1.9782518148422241 +[2025-04-27 11:20:18,902][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 3.4836390018463135, cross_entropy: 3.4836390018463135 +[2025-04-27 11:20:20,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 3.329026222229004, cross_entropy: 3.329026222229004 +[2025-04-27 11:20:21,011][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 2.117525577545166, cross_entropy: 2.117525577545166 +[2025-04-27 11:20:23,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 1.7882450819015503, cross_entropy: 1.7882450819015503 +[2025-04-27 11:20:24,199][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 2.0956099033355713, cross_entropy: 2.0956099033355713 +[2025-04-27 11:20:26,283][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 2.544832706451416, cross_entropy: 2.544832706451416 +[2025-04-27 11:20:26,640][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 2.2511041164398193, cross_entropy: 2.2511041164398193 +[2025-04-27 11:20:28,647][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.8399757146835327, cross_entropy: 1.8399757146835327 +[2025-04-27 11:20:29,227][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.791299343109131, cross_entropy: 3.791299343109131 +[2025-04-27 11:20:31,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 1.6524741649627686, cross_entropy: 1.6524741649627686 +[2025-04-27 11:20:31,712][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 3.380406379699707, cross_entropy: 3.380406379699707 +[2025-04-27 11:20:33,551][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.7464799880981445, cross_entropy: 1.7464799880981445 +[2025-04-27 11:20:34,215][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 2.318695545196533, cross_entropy: 2.318695545196533 +[2025-04-27 11:20:35,911][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.8618361949920654, cross_entropy: 1.8618361949920654 +[2025-04-27 11:20:36,851][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 2.1129777431488037, cross_entropy: 2.1129777431488037 +[2025-04-27 11:20:38,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.9677627086639404, cross_entropy: 1.9677627086639404 +[2025-04-27 11:20:39,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 2.409228563308716, cross_entropy: 2.409228563308716 +[2025-04-27 11:20:40,831][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 2.302419424057007, cross_entropy: 2.302419424057007 +[2025-04-27 11:20:41,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 2.339509963989258, cross_entropy: 2.339509963989258 +[2025-04-27 11:20:43,159][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.8722126483917236, cross_entropy: 1.8722126483917236 +[2025-04-27 11:20:44,323][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 3.903359889984131, cross_entropy: 3.903359889984131 +[2025-04-27 11:20:46,387][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 2.1230316162109375, cross_entropy: 2.1230316162109375 +[2025-04-27 11:20:46,509][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.92514705657959, cross_entropy: 2.92514705657959 +[2025-04-27 11:20:49,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.5921549797058105, cross_entropy: 1.5921549797058105 +[2025-04-27 11:20:49,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 2.1047282218933105, cross_entropy: 2.1047282218933105 +[2025-04-27 11:20:51,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 3.1919138431549072, cross_entropy: 3.1919138431549072 +[2025-04-27 11:20:51,277][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 3.5979175567626953, cross_entropy: 3.5979175567626953 +[2025-04-27 11:20:53,270][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 3.034047842025757, cross_entropy: 3.034047842025757 +[2025-04-27 11:20:53,386][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 3.7127938270568848, cross_entropy: 3.7127938270568848 +[2025-04-27 11:20:55,980][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 3.373854160308838, cross_entropy: 3.373854160308838 +[2025-04-27 11:20:56,101][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 1.8230836391448975, cross_entropy: 1.8230836391448975 +[2025-04-27 11:20:57,883][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 1.6193474531173706, cross_entropy: 1.6193474531173706 +[2025-04-27 11:20:57,986][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 1.5146374702453613, cross_entropy: 1.5146374702453613 +[2025-04-27 11:21:00,237][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 3.073850154876709, cross_entropy: 3.073850154876709 +[2025-04-27 11:21:00,362][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 2.7433810234069824, cross_entropy: 2.7433810234069824 +[2025-04-27 11:21:03,094][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 2.2323994636535645, cross_entropy: 2.2323994636535645 +[2025-04-27 11:21:03,208][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.062040328979492, cross_entropy: 2.062040328979492 +[2025-04-27 11:21:05,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 2.70562744140625, cross_entropy: 2.70562744140625 +[2025-04-27 11:21:05,255][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 3.5414133071899414, cross_entropy: 3.5414133071899414 +[2025-04-27 11:21:07,287][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 3.191716432571411, cross_entropy: 3.191716432571411 +[2025-04-27 11:21:07,391][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 2.132354259490967, cross_entropy: 2.132354259490967 +[2025-04-27 11:21:09,829][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 3.665872097015381, cross_entropy: 3.665872097015381 +[2025-04-27 11:21:09,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.648193359375, cross_entropy: 3.648193359375 +[2025-04-27 11:21:11,939][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.603611469268799, cross_entropy: 2.603611469268799 +[2025-04-27 11:21:12,100][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.8466317653656006, cross_entropy: 1.8466317653656006 +[2025-04-27 11:21:13,971][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 3.4471802711486816, cross_entropy: 3.4471802711486816 +[2025-04-27 11:21:14,860][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.5848569869995117, cross_entropy: 2.5848569869995117 +[2025-04-27 11:21:16,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 3.888490676879883, cross_entropy: 3.888490676879883 +[2025-04-27 11:21:19,126][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 3.4826462268829346, cross_entropy: 3.4826462268829346 +[2025-04-27 11:21:19,236][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 2.174189805984497, cross_entropy: 2.174189805984497 +[2025-04-27 11:21:21,168][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 2.411679267883301, cross_entropy: 2.411679267883301 +[2025-04-27 11:21:21,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 2.5498342514038086, cross_entropy: 2.5498342514038086 +[2025-04-27 11:21:23,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 2.4741933345794678, cross_entropy: 2.4741933345794678 +[2025-04-27 11:21:23,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 3.445523977279663, cross_entropy: 3.445523977279663 +[2025-04-27 11:21:26,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.6279821395874023, cross_entropy: 2.6279821395874023 +[2025-04-27 11:21:26,428][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 2.1415486335754395, cross_entropy: 2.1415486335754395 +[2025-04-27 11:21:29,918][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.4285805225372314, cross_entropy: 2.4285805225372314 +[2025-04-27 11:21:30,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.688755750656128, cross_entropy: 1.688755750656128 +[2025-04-27 11:21:31,958][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.2835867404937744, cross_entropy: 2.2835867404937744 +[2025-04-27 11:21:32,079][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 2.4269535541534424, cross_entropy: 2.4269535541534424 +[2025-04-27 11:21:33,709][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 2.194028854370117, cross_entropy: 2.194028854370117 +[2025-04-27 11:21:33,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 2.0607385635375977, cross_entropy: 2.0607385635375977 +[2025-04-27 11:21:35,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.40337872505188, cross_entropy: 2.40337872505188 +[2025-04-27 11:21:36,093][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 2.057915210723877, cross_entropy: 2.057915210723877 +[2025-04-27 11:21:38,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.0752739906311035, cross_entropy: 2.0752739906311035 +[2025-04-27 11:21:38,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 3.368649482727051, cross_entropy: 3.368649482727051 +[2025-04-27 11:21:40,050][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.5567892789840698, cross_entropy: 1.5567892789840698 +[2025-04-27 11:21:40,171][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 2.4830150604248047, cross_entropy: 2.4830150604248047 +[2025-04-27 11:21:41,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 3.0739352703094482, cross_entropy: 3.0739352703094482 +[2025-04-27 11:21:42,078][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 3.5563180446624756, cross_entropy: 3.5563180446624756 +[2025-04-27 11:21:43,755][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 3.305100917816162, cross_entropy: 3.305100917816162 +[2025-04-27 11:21:43,942][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 2.4306576251983643, cross_entropy: 2.4306576251983643 +[2025-04-27 11:21:45,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.43515682220459, cross_entropy: 2.43515682220459 +[2025-04-27 11:21:46,009][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.4318926334381104, cross_entropy: 2.4318926334381104 +[2025-04-27 11:21:47,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 2.0053257942199707, cross_entropy: 2.0053257942199707 +[2025-04-27 11:21:48,076][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 1.9275596141815186, cross_entropy: 1.9275596141815186 +[2025-04-27 11:21:50,046][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 3.2932848930358887, cross_entropy: 3.2932848930358887 +[2025-04-27 11:21:50,169][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.8757473230361938, cross_entropy: 1.8757473230361938 +[2025-04-27 11:21:51,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 3.4151980876922607, cross_entropy: 3.4151980876922607 +[2025-04-27 11:21:52,332][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 2.0033347606658936, cross_entropy: 2.0033347606658936 +[2025-04-27 11:21:53,936][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 2.286644458770752, cross_entropy: 2.286644458770752 +[2025-04-27 11:21:54,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 3.547959804534912, cross_entropy: 3.547959804534912 +[2025-04-27 11:21:55,922][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 3.499708652496338, cross_entropy: 3.499708652496338 +[2025-04-27 11:21:56,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 3.491894483566284, cross_entropy: 3.491894483566284 +[2025-04-27 11:21:58,136][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 2.171907663345337, cross_entropy: 2.171907663345337 +[2025-04-27 11:22:00,249][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 2.1972928047180176, cross_entropy: 2.1972928047180176 +[2025-04-27 11:22:00,974][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 2.093055486679077, cross_entropy: 2.093055486679077 +[2025-04-27 11:22:01,946][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.7142391204833984, cross_entropy: 2.7142391204833984 +[2025-04-27 11:22:03,412][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 2.302062511444092, cross_entropy: 2.302062511444092 +[2025-04-27 11:22:03,863][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 2.2329931259155273, cross_entropy: 2.2329931259155273 +[2025-04-27 11:22:05,368][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 3.2883572578430176, cross_entropy: 3.2883572578430176 +[2025-04-27 11:22:06,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 3.4551138877868652, cross_entropy: 3.4551138877868652 +[2025-04-27 11:22:07,283][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 2.349954128265381, cross_entropy: 2.349954128265381 +[2025-04-27 11:22:08,422][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 1.50184166431427, cross_entropy: 1.50184166431427 +[2025-04-27 11:22:09,333][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.618272066116333, cross_entropy: 3.618272066116333 +[2025-04-27 11:22:10,665][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.191555976867676, cross_entropy: 2.191555976867676 +[2025-04-27 11:22:11,358][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.815920829772949, cross_entropy: 2.815920829772949 +[2025-04-27 11:22:12,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 1.5327720642089844, cross_entropy: 1.5327720642089844 +[2025-04-27 11:22:13,416][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.6690219640731812, cross_entropy: 1.6690219640731812 +[2025-04-27 11:22:14,513][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 3.395435333251953, cross_entropy: 3.395435333251953 +[2025-04-27 11:22:15,756][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.6197943687438965, cross_entropy: 1.6197943687438965 +[2025-04-27 11:22:16,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.6655712127685547, cross_entropy: 2.6655712127685547 +[2025-04-27 11:22:17,923][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.951992154121399, cross_entropy: 1.951992154121399 +[2025-04-27 11:22:19,158][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 2.0581960678100586, cross_entropy: 2.0581960678100586 +[2025-04-27 11:22:20,318][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.9683971405029297, cross_entropy: 2.9683971405029297 +[2025-04-27 11:22:21,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 1.991896152496338, cross_entropy: 1.991896152496338 +[2025-04-27 11:22:22,686][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 2.0610201358795166, cross_entropy: 2.0610201358795166 +[2025-04-27 11:22:23,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 3.5256314277648926, cross_entropy: 3.5256314277648926 +[2025-04-27 11:22:24,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 3.7167153358459473, cross_entropy: 3.7167153358459473 +[2025-04-27 11:22:25,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 3.3000240325927734, cross_entropy: 3.3000240325927734 +[2025-04-27 11:22:26,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 1.526186466217041, cross_entropy: 1.526186466217041 +[2025-04-27 11:22:27,335][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 3.213676929473877, cross_entropy: 3.213676929473877 +[2025-04-27 11:22:29,623][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 2.1626617908477783, cross_entropy: 2.1626617908477783 +[2025-04-27 11:22:30,213][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 2.3521199226379395, cross_entropy: 2.3521199226379395 +[2025-04-27 11:22:32,115][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 3.763129234313965, cross_entropy: 3.763129234313965 +[2025-04-27 11:22:32,816][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 3.5991854667663574, cross_entropy: 3.5991854667663574 +[2025-04-27 11:22:34,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.5498731136322021, cross_entropy: 1.5498731136322021 +[2025-04-27 11:22:34,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 3.214994430541992, cross_entropy: 3.214994430541992 +[2025-04-27 11:22:36,445][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.9763107299804688, cross_entropy: 2.9763107299804688 +[2025-04-27 11:22:36,548][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.0295495986938477, cross_entropy: 2.0295495986938477 +[2025-04-27 11:22:39,643][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.9292840957641602, cross_entropy: 1.9292840957641602 +[2025-04-27 11:22:39,759][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.9063996076583862, cross_entropy: 1.9063996076583862 +[2025-04-27 11:22:42,245][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.548501968383789, cross_entropy: 3.548501968383789 +[2025-04-27 11:22:42,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 2.0149753093719482, cross_entropy: 2.0149753093719482 +[2025-04-27 11:22:44,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.9885960817337036, cross_entropy: 1.9885960817337036 +[2025-04-27 11:22:44,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 3.649230480194092, cross_entropy: 3.649230480194092 +[2025-04-27 11:22:47,575][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 3.337739944458008, cross_entropy: 3.337739944458008 +[2025-04-27 11:22:47,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.524651288986206, cross_entropy: 2.524651288986206 +[2025-04-27 11:22:49,739][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 2.077300786972046, cross_entropy: 2.077300786972046 +[2025-04-27 11:22:49,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.6214673519134521, cross_entropy: 1.6214673519134521 +[2025-04-27 11:22:51,598][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 2.9132235050201416, cross_entropy: 2.9132235050201416 +[2025-04-27 11:22:51,721][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 3.244230270385742, cross_entropy: 3.244230270385742 +[2025-04-27 11:22:53,460][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.784924030303955, cross_entropy: 2.784924030303955 +[2025-04-27 11:22:53,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.7767025232315063, cross_entropy: 1.7767025232315063 +[2025-04-27 11:22:55,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 3.512737274169922, cross_entropy: 3.512737274169922 +[2025-04-27 11:22:55,734][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 1.794877290725708, cross_entropy: 1.794877290725708 +[2025-04-27 11:22:57,388][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 3.7921581268310547, cross_entropy: 3.7921581268310547 +[2025-04-27 11:22:57,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 2.7112483978271484, cross_entropy: 2.7112483978271484 +[2025-04-27 11:22:59,674][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 3.622823715209961, cross_entropy: 3.622823715209961 +[2025-04-27 11:22:59,795][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 2.0297746658325195, cross_entropy: 2.0297746658325195 +[2025-04-27 11:23:01,411][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 2.278275728225708, cross_entropy: 2.278275728225708 +[2025-04-27 11:23:01,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 3.0023021697998047, cross_entropy: 3.0023021697998047 +[2025-04-27 11:23:04,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 2.2925453186035156, cross_entropy: 2.2925453186035156 +[2025-04-27 11:23:04,144][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 3.053649425506592, cross_entropy: 3.053649425506592 +[2025-04-27 11:23:06,507][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 3.313431739807129, cross_entropy: 3.313431739807129 +[2025-04-27 11:23:06,628][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 3.9059126377105713, cross_entropy: 3.9059126377105713 +[2025-04-27 11:23:08,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.8753976821899414, cross_entropy: 1.8753976821899414 +[2025-04-27 11:23:08,689][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 3.2576093673706055, cross_entropy: 3.2576093673706055 +[2025-04-27 11:23:10,896][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 3.1626133918762207, cross_entropy: 3.1626133918762207 +[2025-04-27 11:23:11,021][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 2.956425905227661, cross_entropy: 2.956425905227661 +[2025-04-27 11:23:13,042][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.956437110900879, cross_entropy: 1.956437110900879 +[2025-04-27 11:23:13,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 2.2665414810180664, cross_entropy: 2.2665414810180664 +[2025-04-27 11:23:15,528][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 3.302851676940918, cross_entropy: 3.302851676940918 +[2025-04-27 11:23:15,654][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 3.577446699142456, cross_entropy: 3.577446699142456 +[2025-04-27 11:23:17,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 3.8910820484161377, cross_entropy: 3.8910820484161377 +[2025-04-27 11:23:17,452][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.82137393951416, cross_entropy: 2.82137393951416 +[2025-04-27 11:23:19,373][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.56234073638916, cross_entropy: 2.56234073638916 +[2025-04-27 11:23:19,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 3.133993148803711, cross_entropy: 3.133993148803711 +[2025-04-27 11:23:21,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.368886709213257, cross_entropy: 2.368886709213257 +[2025-04-27 11:23:21,825][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.0232620239257812, cross_entropy: 2.0232620239257812 +[2025-04-27 11:23:23,996][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 3.0181519985198975, cross_entropy: 3.0181519985198975 +[2025-04-27 11:23:24,117][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.0816683769226074, cross_entropy: 2.0816683769226074 +[2025-04-27 11:23:26,209][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 2.89528751373291, cross_entropy: 2.89528751373291 +[2025-04-27 11:23:26,314][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 1.7255733013153076, cross_entropy: 1.7255733013153076 +[2025-04-27 11:23:27,867][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.9109117984771729, cross_entropy: 1.9109117984771729 +[2025-04-27 11:23:27,989][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 1.7109146118164062, cross_entropy: 1.7109146118164062 +[2025-04-27 11:23:30,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 3.1252071857452393, cross_entropy: 3.1252071857452393 +[2025-04-27 11:23:30,293][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 2.5545382499694824, cross_entropy: 2.5545382499694824 +[2025-04-27 11:23:33,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.5309247970581055, cross_entropy: 1.5309247970581055 +[2025-04-27 11:23:33,215][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 3.5290422439575195, cross_entropy: 3.5290422439575195 +[2025-04-27 11:23:35,287][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 3.2438206672668457, cross_entropy: 3.2438206672668457 +[2025-04-27 11:23:35,408][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.3817663192749023, cross_entropy: 2.3817663192749023 +[2025-04-27 11:23:37,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 2.648185968399048, cross_entropy: 2.648185968399048 +[2025-04-27 11:23:37,456][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 3.5029096603393555, cross_entropy: 3.5029096603393555 +[2025-04-27 11:23:39,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.4981493949890137, cross_entropy: 2.4981493949890137 +[2025-04-27 11:23:39,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 1.683371663093567, cross_entropy: 1.683371663093567 +[2025-04-27 11:23:42,010][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 3.7521467208862305, cross_entropy: 3.7521467208862305 +[2025-04-27 11:23:42,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 2.180551290512085, cross_entropy: 2.180551290512085 +[2025-04-27 11:23:44,171][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.8032206296920776, cross_entropy: 1.8032206296920776 +[2025-04-27 11:23:44,276][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.9566371440887451, cross_entropy: 1.9566371440887451 +[2025-04-27 11:23:46,510][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.5820577144622803, cross_entropy: 1.5820577144622803 +[2025-04-27 11:23:46,615][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 3.0181796550750732, cross_entropy: 3.0181796550750732 +[2025-04-27 11:23:48,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 2.1616125106811523, cross_entropy: 2.1616125106811523 +[2025-04-27 11:23:48,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 3.2293360233306885, cross_entropy: 3.2293360233306885 +[2025-04-27 11:23:51,002][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 3.3715660572052, cross_entropy: 3.3715660572052 +[2025-04-27 11:23:51,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.5183449983596802, cross_entropy: 1.5183449983596802 +[2025-04-27 11:23:53,149][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 2.357548713684082, cross_entropy: 2.357548713684082 +[2025-04-27 11:23:53,268][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 3.2692482471466064, cross_entropy: 3.2692482471466064 +[2025-04-27 11:23:55,136][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.8628365993499756, cross_entropy: 2.8628365993499756 +[2025-04-27 11:23:55,294][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 3.656200885772705, cross_entropy: 3.656200885772705 +[2025-04-27 11:23:57,155][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.9705121517181396, cross_entropy: 2.9705121517181396 +[2025-04-27 11:23:58,147][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.821082830429077, cross_entropy: 2.821082830429077 +[2025-04-27 11:23:59,340][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 3.3242270946502686, cross_entropy: 3.3242270946502686 +[2025-04-27 11:24:00,459][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 2.443143606185913, cross_entropy: 2.443143606185913 +[2025-04-27 11:24:01,421][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.3124446868896484, cross_entropy: 2.3124446868896484 +[2025-04-27 11:24:03,003][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 3.4682776927948, cross_entropy: 3.4682776927948 +[2025-04-27 11:24:03,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.8472957611083984, cross_entropy: 1.8472957611083984 +[2025-04-27 11:24:04,900][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.8183284997940063, cross_entropy: 1.8183284997940063 +[2025-04-27 11:24:05,990][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.4324105978012085, cross_entropy: 1.4324105978012085 +[2025-04-27 11:24:07,323][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 2.955289363861084, cross_entropy: 2.955289363861084 +[2025-04-27 11:24:08,325][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 2.0787105560302734, cross_entropy: 2.0787105560302734 +[2025-04-27 11:24:10,594][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.07487416267395, cross_entropy: 2.07487416267395 +[2025-04-27 11:24:10,715][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.7716715335845947, cross_entropy: 1.7716715335845947 +[2025-04-27 11:24:12,524][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.933861255645752, cross_entropy: 1.933861255645752 +[2025-04-27 11:24:12,672][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 3.729168176651001, cross_entropy: 3.729168176651001 +[2025-04-27 11:24:14,852][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 3.334062337875366, cross_entropy: 3.334062337875366 +[2025-04-27 11:24:14,955][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.6754612922668457, cross_entropy: 2.6754612922668457 +[2025-04-27 11:24:17,020][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 3.5817513465881348, cross_entropy: 3.5817513465881348 +[2025-04-27 11:24:17,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 2.3755693435668945, cross_entropy: 2.3755693435668945 +[2025-04-27 11:24:18,766][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 3.8423233032226562, cross_entropy: 3.8423233032226562 +[2025-04-27 11:24:18,974][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.8940162658691406, cross_entropy: 1.8940162658691406 +[2025-04-27 11:24:21,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 2.0195226669311523, cross_entropy: 2.0195226669311523 +[2025-04-27 11:24:21,745][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 3.483630657196045, cross_entropy: 3.483630657196045 +[2025-04-27 11:24:23,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 2.040289878845215, cross_entropy: 2.040289878845215 +[2025-04-27 11:24:25,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.611487627029419, cross_entropy: 2.611487627029419 +[2025-04-27 11:24:25,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 1.5191447734832764, cross_entropy: 1.5191447734832764 +[2025-04-27 11:24:27,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 3.4482245445251465, cross_entropy: 3.4482245445251465 +[2025-04-27 11:24:28,206][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 1.8511271476745605, cross_entropy: 1.8511271476745605 +[2025-04-27 11:24:29,082][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.802156925201416, cross_entropy: 1.802156925201416 +[2025-04-27 11:24:30,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 3.6653900146484375, cross_entropy: 3.6653900146484375 +[2025-04-27 11:24:30,967][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 3.627427101135254, cross_entropy: 3.627427101135254 +[2025-04-27 11:24:32,509][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 2.4803431034088135, cross_entropy: 2.4803431034088135 +[2025-04-27 11:24:32,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.5599746704101562, cross_entropy: 2.5599746704101562 +[2025-04-27 11:24:34,527][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 2.384953022003174, cross_entropy: 2.384953022003174 +[2025-04-27 11:24:35,093][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 2.0344555377960205, cross_entropy: 2.0344555377960205 +[2025-04-27 11:24:36,628][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.2292380332946777, cross_entropy: 2.2292380332946777 +[2025-04-27 11:24:36,996][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.1332814693450928, cross_entropy: 2.1332814693450928 +[2025-04-27 11:24:38,535][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 2.4081249237060547, cross_entropy: 2.4081249237060547 +[2025-04-27 11:24:39,458][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 3.2147951126098633, cross_entropy: 3.2147951126098633 +[2025-04-27 11:24:41,002][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 3.3874526023864746, cross_entropy: 3.3874526023864746 +[2025-04-27 11:24:41,998][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 2.0608928203582764, cross_entropy: 2.0608928203582764 +[2025-04-27 11:24:43,293][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 2.018040418624878, cross_entropy: 2.018040418624878 +[2025-04-27 11:24:44,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.7966837882995605, cross_entropy: 1.7966837882995605 +[2025-04-27 11:24:45,519][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 2.1620500087738037, cross_entropy: 2.1620500087738037 +[2025-04-27 11:24:47,122][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 2.091980457305908, cross_entropy: 2.091980457305908 +[2025-04-27 11:24:47,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 2.3819923400878906, cross_entropy: 2.3819923400878906 +[2025-04-27 11:24:49,945][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.7001278400421143, cross_entropy: 3.7001278400421143 +[2025-04-27 11:24:50,069][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.973414421081543, cross_entropy: 2.973414421081543 +[2025-04-27 11:24:52,485][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.2447593212127686, cross_entropy: 2.2447593212127686 +[2025-04-27 11:24:52,607][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.690319061279297, cross_entropy: 3.690319061279297 +[2025-04-27 11:24:55,371][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 1.8905141353607178, cross_entropy: 1.8905141353607178 +[2025-04-27 11:24:55,494][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 2.018373966217041, cross_entropy: 2.018373966217041 +[2025-04-27 11:24:58,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 2.6849400997161865, cross_entropy: 2.6849400997161865 +[2025-04-27 11:24:58,274][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 2.0284743309020996, cross_entropy: 2.0284743309020996 +[2025-04-27 11:25:00,264][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 2.2810451984405518, cross_entropy: 2.2810451984405518 +[2025-04-27 11:25:00,385][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 1.9891465902328491, cross_entropy: 1.9891465902328491 +[2025-04-27 11:25:02,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.559370994567871, cross_entropy: 2.559370994567871 +[2025-04-27 11:25:02,959][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 2.0914976596832275, cross_entropy: 2.0914976596832275 +[2025-04-27 11:25:05,947][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 3.3070850372314453, cross_entropy: 3.3070850372314453 +[2025-04-27 11:25:06,051][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.1589698791503906, cross_entropy: 2.1589698791503906 +[2025-04-27 11:25:08,291][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 2.1632041931152344, cross_entropy: 2.1632041931152344 +[2025-04-27 11:25:08,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 2.47642183303833, cross_entropy: 2.47642183303833 +[2025-04-27 11:25:10,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 2.37998366355896, cross_entropy: 2.37998366355896 +[2025-04-27 11:25:10,240][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 3.6434543132781982, cross_entropy: 3.6434543132781982 +[2025-04-27 11:25:12,239][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 3.268423318862915, cross_entropy: 3.268423318862915 +[2025-04-27 11:25:12,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 3.0279810428619385, cross_entropy: 3.0279810428619385 +[2025-04-27 11:25:14,617][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 1.878231167793274, cross_entropy: 1.878231167793274 +[2025-04-27 11:25:14,745][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 2.823180913925171, cross_entropy: 2.823180913925171 +[2025-04-27 11:25:16,801][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 3.160917282104492, cross_entropy: 3.160917282104492 +[2025-04-27 11:25:16,906][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 1.8626627922058105, cross_entropy: 1.8626627922058105 +[2025-04-27 11:25:19,064][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 2.3464229106903076, cross_entropy: 2.3464229106903076 +[2025-04-27 11:25:19,184][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.736976146697998, cross_entropy: 2.736976146697998 +[2025-04-27 11:25:21,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 2.149928331375122, cross_entropy: 2.149928331375122 +[2025-04-27 11:25:21,272][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.6888394355773926, cross_entropy: 1.6888394355773926 +[2025-04-27 11:25:23,939][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.9161269664764404, cross_entropy: 1.9161269664764404 +[2025-04-27 11:25:24,043][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.8938713073730469, cross_entropy: 1.8938713073730469 +[2025-04-27 11:25:26,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 2.648360252380371, cross_entropy: 2.648360252380371 +[2025-04-27 11:25:26,982][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 2.3796355724334717, cross_entropy: 2.3796355724334717 +[2025-04-27 11:25:28,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.5746700763702393, cross_entropy: 1.5746700763702393 +[2025-04-27 11:25:28,772][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 3.0419774055480957, cross_entropy: 3.0419774055480957 +[2025-04-27 11:25:30,750][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 3.771465301513672, cross_entropy: 3.771465301513672 +[2025-04-27 11:25:30,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 3.5325775146484375, cross_entropy: 3.5325775146484375 +[2025-04-27 11:25:32,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 2.8814642429351807, cross_entropy: 2.8814642429351807 +[2025-04-27 11:25:33,059][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 1.946303367614746, cross_entropy: 1.946303367614746 +[2025-04-27 11:25:34,424][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 3.6718592643737793, cross_entropy: 3.6718592643737793 +[2025-04-27 11:25:35,706][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 3.668156623840332, cross_entropy: 3.668156623840332 +[2025-04-27 11:25:36,570][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 1.5074926614761353, cross_entropy: 1.5074926614761353 +[2025-04-27 11:25:37,690][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.7873197793960571, cross_entropy: 1.7873197793960571 +[2025-04-27 11:25:38,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 2.0192108154296875, cross_entropy: 2.0192108154296875 +[2025-04-27 11:25:39,879][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 2.9640631675720215, cross_entropy: 2.9640631675720215 +[2025-04-27 11:25:41,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.9686622619628906, cross_entropy: 1.9686622619628906 +[2025-04-27 11:25:42,035][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 3.0435304641723633, cross_entropy: 3.0435304641723633 +[2025-04-27 11:25:43,337][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 2.2246484756469727, cross_entropy: 2.2246484756469727 +[2025-04-27 11:25:44,734][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.2551968097686768, cross_entropy: 2.2551968097686768 +[2025-04-27 11:25:46,031][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 2.3146395683288574, cross_entropy: 2.3146395683288574 +[2025-04-27 11:25:47,737][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.60447359085083, cross_entropy: 1.60447359085083 +[2025-04-27 11:25:47,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.7738244533538818, cross_entropy: 1.7738244533538818 +[2025-04-27 11:25:49,745][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 3.403390884399414, cross_entropy: 3.403390884399414 +[2025-04-27 11:25:50,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 2.019486904144287, cross_entropy: 2.019486904144287 +[2025-04-27 11:25:52,087][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 2.3623483180999756, cross_entropy: 2.3623483180999756 +[2025-04-27 11:25:52,291][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 3.2363104820251465, cross_entropy: 3.2363104820251465 +[2025-04-27 11:25:54,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.1319451332092285, cross_entropy: 2.1319451332092285 +[2025-04-27 11:25:54,650][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 3.3580827713012695, cross_entropy: 3.3580827713012695 +[2025-04-27 11:25:56,584][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 3.6793665885925293, cross_entropy: 3.6793665885925293 +[2025-04-27 11:25:56,879][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 3.1077756881713867, cross_entropy: 3.1077756881713867 +[2025-04-27 11:25:58,519][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 3.238194704055786, cross_entropy: 3.238194704055786 +[2025-04-27 11:25:59,325][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 3.3753018379211426, cross_entropy: 3.3753018379211426 +[2025-04-27 11:26:00,514][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 1.554403305053711, cross_entropy: 1.554403305053711 +[2025-04-27 11:26:01,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 2.2743141651153564, cross_entropy: 2.2743141651153564 +[2025-04-27 11:26:02,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.889371871948242, cross_entropy: 2.889371871948242 +[2025-04-27 11:26:04,751][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.3978939056396484, cross_entropy: 3.3978939056396484 +[2025-04-27 11:26:04,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 2.7392048835754395, cross_entropy: 2.7392048835754395 +[2025-04-27 11:26:06,874][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.3977389335632324, cross_entropy: 2.3977389335632324 +[2025-04-27 11:26:06,991][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 3.6437039375305176, cross_entropy: 3.6437039375305176 +[2025-04-27 11:26:08,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.584320068359375, cross_entropy: 1.584320068359375 +[2025-04-27 11:26:08,805][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 3.2480008602142334, cross_entropy: 3.2480008602142334 +[2025-04-27 11:26:10,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 3.0441057682037354, cross_entropy: 3.0441057682037354 +[2025-04-27 11:26:10,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 3.7727627754211426, cross_entropy: 3.7727627754211426 +[2025-04-27 11:26:12,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.8814239501953125, cross_entropy: 2.8814239501953125 +[2025-04-27 11:26:12,918][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 3.2950520515441895, cross_entropy: 3.2950520515441895 +[2025-04-27 11:26:15,176][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 3.463036060333252, cross_entropy: 3.463036060333252 +[2025-04-27 11:26:16,699][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.3823442459106445, cross_entropy: 3.3823442459106445 +[2025-04-27 11:26:17,929][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.411564826965332, cross_entropy: 2.411564826965332 +[2025-04-27 11:26:19,600][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 3.5020036697387695, cross_entropy: 3.5020036697387695 +[2025-04-27 11:26:20,025][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.449007987976074, cross_entropy: 3.449007987976074 +[2025-04-27 11:26:22,073][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.961806297302246, cross_entropy: 1.961806297302246 +[2025-04-27 11:26:22,405][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 3.415881395339966, cross_entropy: 3.415881395339966 +[2025-04-27 11:26:24,695][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 3.515590190887451, cross_entropy: 3.515590190887451 +[2025-04-27 11:26:24,808][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 3.4543933868408203, cross_entropy: 3.4543933868408203 +[2025-04-27 11:26:26,815][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.895756721496582, cross_entropy: 2.895756721496582 +[2025-04-27 11:26:27,389][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 2.0516228675842285, cross_entropy: 2.0516228675842285 +[2025-04-27 11:26:29,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.9596009254455566, cross_entropy: 1.9596009254455566 +[2025-04-27 11:26:29,613][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.5686535835266113, cross_entropy: 2.5686535835266113 +[2025-04-27 11:26:31,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 2.3315443992614746, cross_entropy: 2.3315443992614746 +[2025-04-27 11:26:32,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 2.0849058628082275, cross_entropy: 2.0849058628082275 +[2025-04-27 11:26:33,469][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 3.0743048191070557, cross_entropy: 3.0743048191070557 +[2025-04-27 11:26:34,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 3.7565062046051025, cross_entropy: 3.7565062046051025 +[2025-04-27 11:26:35,101][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 3.2962646484375, cross_entropy: 3.2962646484375 +[2025-04-27 11:28:23,697][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.611473321914673, cross_entropy: 2.611473321914673 +[2025-04-27 11:28:23,697][BaseTrainer][INFO] - [Epoch 5/10] (validation) 2.034925699234009, cross_entropy: 2.034925699234009 +[2025-04-27 11:28:23,860][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch5.pth. +[2025-04-27 11:28:24,076][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:28:26,885][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 1.2529237270355225, cross_entropy: 1.2529237270355225 +[2025-04-27 11:28:26,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 2.236663341522217, cross_entropy: 2.236663341522217 +[2025-04-27 11:28:28,443][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 3.246041774749756, cross_entropy: 3.246041774749756 +[2025-04-27 11:28:28,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 3.0736117362976074, cross_entropy: 3.0736117362976074 +[2025-04-27 11:28:30,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.5911784172058105, cross_entropy: 2.5911784172058105 +[2025-04-27 11:28:30,630][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 3.3469443321228027, cross_entropy: 3.3469443321228027 +[2025-04-27 11:28:32,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 3.167259454727173, cross_entropy: 3.167259454727173 +[2025-04-27 11:28:33,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.6052521467208862, cross_entropy: 1.6052521467208862 +[2025-04-27 11:28:34,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.989620566368103, cross_entropy: 1.989620566368103 +[2025-04-27 11:28:35,581][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.7682695388793945, cross_entropy: 2.7682695388793945 +[2025-04-27 11:28:37,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 3.033932685852051, cross_entropy: 3.033932685852051 +[2025-04-27 11:28:38,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 2.6024889945983887, cross_entropy: 2.6024889945983887 +[2025-04-27 11:28:38,971][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 3.225046396255493, cross_entropy: 3.225046396255493 +[2025-04-27 11:28:40,541][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 2.354135274887085, cross_entropy: 2.354135274887085 +[2025-04-27 11:28:40,907][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 1.5424549579620361, cross_entropy: 1.5424549579620361 +[2025-04-27 11:28:42,877][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.7066402435302734, cross_entropy: 2.7066402435302734 +[2025-04-27 11:28:43,180][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 2.1416258811950684, cross_entropy: 2.1416258811950684 +[2025-04-27 11:28:45,572][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.512937068939209, cross_entropy: 3.512937068939209 +[2025-04-27 11:28:45,690][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.8212320804595947, cross_entropy: 1.8212320804595947 +[2025-04-27 11:28:47,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 3.6111488342285156, cross_entropy: 3.6111488342285156 +[2025-04-27 11:28:47,745][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 2.6457271575927734, cross_entropy: 2.6457271575927734 +[2025-04-27 11:28:49,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.9300048351287842, cross_entropy: 1.9300048351287842 +[2025-04-27 11:28:49,875][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 1.5220482349395752, cross_entropy: 1.5220482349395752 +[2025-04-27 11:28:51,861][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.7942147254943848, cross_entropy: 2.7942147254943848 +[2025-04-27 11:28:52,035][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 1.7306938171386719, cross_entropy: 1.7306938171386719 +[2025-04-27 11:28:53,664][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.6004467010498047, cross_entropy: 2.6004467010498047 +[2025-04-27 11:28:54,222][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 3.069523572921753, cross_entropy: 3.069523572921753 +[2025-04-27 11:28:56,537][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.4908175468444824, cross_entropy: 2.4908175468444824 +[2025-04-27 11:28:56,655][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.647477388381958, cross_entropy: 1.647477388381958 +[2025-04-27 11:28:59,071][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 1.6675434112548828, cross_entropy: 1.6675434112548828 +[2025-04-27 11:28:59,191][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.6544275283813477, cross_entropy: 1.6544275283813477 +[2025-04-27 11:29:01,580][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.988265037536621, cross_entropy: 2.988265037536621 +[2025-04-27 11:29:01,695][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 3.3120903968811035, cross_entropy: 3.3120903968811035 +[2025-04-27 11:29:03,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 3.3784637451171875, cross_entropy: 3.3784637451171875 +[2025-04-27 11:29:04,075][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 1.6215161085128784, cross_entropy: 1.6215161085128784 +[2025-04-27 11:29:06,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 1.7592175006866455, cross_entropy: 1.7592175006866455 +[2025-04-27 11:29:06,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.4867771863937378, cross_entropy: 1.4867771863937378 +[2025-04-27 11:29:08,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 3.329586982727051, cross_entropy: 3.329586982727051 +[2025-04-27 11:29:08,664][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.8833093643188477, cross_entropy: 2.8833093643188477 +[2025-04-27 11:29:11,417][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.7231096029281616, cross_entropy: 1.7231096029281616 +[2025-04-27 11:29:11,533][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 3.756260395050049, cross_entropy: 3.756260395050049 +[2025-04-27 11:29:13,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 3.2972538471221924, cross_entropy: 3.2972538471221924 +[2025-04-27 11:29:13,561][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 2.0544257164001465, cross_entropy: 2.0544257164001465 +[2025-04-27 11:29:15,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 3.235752820968628, cross_entropy: 3.235752820968628 +[2025-04-27 11:29:15,513][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 2.9646589756011963, cross_entropy: 2.9646589756011963 +[2025-04-27 11:29:17,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.8458690643310547, cross_entropy: 2.8458690643310547 +[2025-04-27 11:29:17,779][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 3.4303479194641113, cross_entropy: 3.4303479194641113 +[2025-04-27 11:29:19,682][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 3.422598123550415, cross_entropy: 3.422598123550415 +[2025-04-27 11:29:19,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.8066062927246094, cross_entropy: 1.8066062927246094 +[2025-04-27 11:29:21,953][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 2.253434181213379, cross_entropy: 2.253434181213379 +[2025-04-27 11:29:22,071][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 3.127922534942627, cross_entropy: 3.127922534942627 +[2025-04-27 11:29:24,250][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 3.4099793434143066, cross_entropy: 3.4099793434143066 +[2025-04-27 11:29:24,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 3.282470941543579, cross_entropy: 3.282470941543579 +[2025-04-27 11:29:26,959][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.9135780334472656, cross_entropy: 1.9135780334472656 +[2025-04-27 11:29:27,084][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 2.3873541355133057, cross_entropy: 2.3873541355133057 +[2025-04-27 11:29:29,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 1.4748098850250244, cross_entropy: 1.4748098850250244 +[2025-04-27 11:29:29,436][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 3.481773853302002, cross_entropy: 3.481773853302002 +[2025-04-27 11:29:31,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.8515030145645142, cross_entropy: 1.8515030145645142 +[2025-04-27 11:29:31,665][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.4303441047668457, cross_entropy: 2.4303441047668457 +[2025-04-27 11:29:33,468][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.8562965393066406, cross_entropy: 2.8562965393066406 +[2025-04-27 11:29:33,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 2.701882839202881, cross_entropy: 2.701882839202881 +[2025-04-27 11:29:36,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.894529342651367, cross_entropy: 2.894529342651367 +[2025-04-27 11:29:36,167][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 3.472288131713867, cross_entropy: 3.472288131713867 +[2025-04-27 11:29:38,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 2.382382869720459, cross_entropy: 2.382382869720459 +[2025-04-27 11:29:38,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.8510055541992188, cross_entropy: 2.8510055541992188 +[2025-04-27 11:29:40,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 3.157649278640747, cross_entropy: 3.157649278640747 +[2025-04-27 11:29:40,235][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 1.4791197776794434, cross_entropy: 1.4791197776794434 +[2025-04-27 11:29:41,897][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.9862102270126343, cross_entropy: 1.9862102270126343 +[2025-04-27 11:29:42,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 2.8824353218078613, cross_entropy: 2.8824353218078613 +[2025-04-27 11:29:43,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.775437831878662, cross_entropy: 1.775437831878662 +[2025-04-27 11:29:43,888][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 2.6005029678344727, cross_entropy: 2.6005029678344727 +[2025-04-27 11:29:45,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.968034029006958, cross_entropy: 1.968034029006958 +[2025-04-27 11:29:46,354][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 1.808573842048645, cross_entropy: 1.808573842048645 +[2025-04-27 11:29:47,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.5812263488769531, cross_entropy: 1.5812263488769531 +[2025-04-27 11:29:49,353][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 1.653109073638916, cross_entropy: 1.653109073638916 +[2025-04-27 11:29:49,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.9735194444656372, cross_entropy: 1.9735194444656372 +[2025-04-27 11:29:51,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.0960402488708496, cross_entropy: 2.0960402488708496 +[2025-04-27 11:29:52,164][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.9123754501342773, cross_entropy: 2.9123754501342773 +[2025-04-27 11:29:53,787][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.1083571910858154, cross_entropy: 2.1083571910858154 +[2025-04-27 11:29:54,413][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 3.3108608722686768, cross_entropy: 3.3108608722686768 +[2025-04-27 11:29:56,298][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.9008276462554932, cross_entropy: 1.9008276462554932 +[2025-04-27 11:29:56,471][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 2.694579601287842, cross_entropy: 2.694579601287842 +[2025-04-27 11:29:58,337][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 1.7889455556869507, cross_entropy: 1.7889455556869507 +[2025-04-27 11:29:58,713][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.8082027435302734, cross_entropy: 1.8082027435302734 +[2025-04-27 11:30:01,190][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 2.1396172046661377, cross_entropy: 2.1396172046661377 +[2025-04-27 11:30:01,296][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.305436611175537, cross_entropy: 2.305436611175537 +[2025-04-27 11:30:03,422][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 3.102877140045166, cross_entropy: 3.102877140045166 +[2025-04-27 11:30:03,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 2.5673413276672363, cross_entropy: 2.5673413276672363 +[2025-04-27 11:30:05,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.519983172416687, cross_entropy: 1.519983172416687 +[2025-04-27 11:30:05,802][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.5633084774017334, cross_entropy: 1.5633084774017334 +[2025-04-27 11:30:08,216][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.9541025161743164, cross_entropy: 2.9541025161743164 +[2025-04-27 11:30:08,336][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.608361840248108, cross_entropy: 1.608361840248108 +[2025-04-27 11:30:10,953][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 3.6600918769836426, cross_entropy: 3.6600918769836426 +[2025-04-27 11:30:11,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.655726909637451, cross_entropy: 2.655726909637451 +[2025-04-27 11:30:13,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 2.7233238220214844, cross_entropy: 2.7233238220214844 +[2025-04-27 11:30:13,176][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.8408868312835693, cross_entropy: 1.8408868312835693 +[2025-04-27 11:30:14,769][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 3.066948413848877, cross_entropy: 3.066948413848877 +[2025-04-27 11:30:14,884][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 2.673037528991699, cross_entropy: 2.673037528991699 +[2025-04-27 11:30:16,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 2.3972134590148926, cross_entropy: 2.3972134590148926 +[2025-04-27 11:30:16,594][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.728365421295166, cross_entropy: 1.728365421295166 +[2025-04-27 11:30:18,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.8677805662155151, cross_entropy: 1.8677805662155151 +[2025-04-27 11:30:18,831][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.5845112800598145, cross_entropy: 2.5845112800598145 +[2025-04-27 11:30:20,494][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 3.0879359245300293, cross_entropy: 3.0879359245300293 +[2025-04-27 11:30:20,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 1.2773783206939697, cross_entropy: 1.2773783206939697 +[2025-04-27 11:30:22,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 2.5050501823425293, cross_entropy: 2.5050501823425293 +[2025-04-27 11:30:22,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.688004493713379, cross_entropy: 2.688004493713379 +[2025-04-27 11:30:25,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.2261955738067627, cross_entropy: 2.2261955738067627 +[2025-04-27 11:30:25,586][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 2.357970714569092, cross_entropy: 2.357970714569092 +[2025-04-27 11:30:27,919][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 3.311138153076172, cross_entropy: 3.311138153076172 +[2025-04-27 11:30:28,024][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 2.0368075370788574, cross_entropy: 2.0368075370788574 +[2025-04-27 11:30:30,238][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.7931265830993652, cross_entropy: 1.7931265830993652 +[2025-04-27 11:30:30,360][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.6557825803756714, cross_entropy: 1.6557825803756714 +[2025-04-27 11:30:32,558][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.8617448806762695, cross_entropy: 2.8617448806762695 +[2025-04-27 11:30:32,679][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 2.203225612640381, cross_entropy: 2.203225612640381 +[2025-04-27 11:30:34,910][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.708876848220825, cross_entropy: 2.708876848220825 +[2025-04-27 11:30:35,013][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 2.3763113021850586, cross_entropy: 2.3763113021850586 +[2025-04-27 11:30:36,987][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 3.414734363555908, cross_entropy: 3.414734363555908 +[2025-04-27 11:30:37,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 3.3939781188964844, cross_entropy: 3.3939781188964844 +[2025-04-27 11:30:38,775][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.4186248779296875, cross_entropy: 3.4186248779296875 +[2025-04-27 11:30:38,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.6049821376800537, cross_entropy: 1.6049821376800537 +[2025-04-27 11:30:40,907][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.1012494564056396, cross_entropy: 2.1012494564056396 +[2025-04-27 11:30:41,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 2.74470591545105, cross_entropy: 2.74470591545105 +[2025-04-27 11:30:42,564][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 2.340219736099243, cross_entropy: 2.340219736099243 +[2025-04-27 11:30:42,989][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 2.0930228233337402, cross_entropy: 2.0930228233337402 +[2025-04-27 11:30:44,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 2.4565482139587402, cross_entropy: 2.4565482139587402 +[2025-04-27 11:30:46,791][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.5157461166381836, cross_entropy: 2.5157461166381836 +[2025-04-27 11:30:46,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 3.6062171459198, cross_entropy: 3.6062171459198 +[2025-04-27 11:30:49,144][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 3.1751327514648438, cross_entropy: 3.1751327514648438 +[2025-04-27 11:30:49,295][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 2.655012845993042, cross_entropy: 2.655012845993042 +[2025-04-27 11:30:51,207][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 3.137441396713257, cross_entropy: 3.137441396713257 +[2025-04-27 11:30:51,324][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 3.3259341716766357, cross_entropy: 3.3259341716766357 +[2025-04-27 11:30:53,307][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 2.7717466354370117, cross_entropy: 2.7717466354370117 +[2025-04-27 11:30:53,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 3.20149827003479, cross_entropy: 3.20149827003479 +[2025-04-27 11:30:55,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.458496570587158, cross_entropy: 3.458496570587158 +[2025-04-27 11:30:55,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 2.369317054748535, cross_entropy: 2.369317054748535 +[2025-04-27 11:30:57,691][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 3.459243059158325, cross_entropy: 3.459243059158325 +[2025-04-27 11:30:57,814][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 2.069530487060547, cross_entropy: 2.069530487060547 +[2025-04-27 11:31:00,541][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.83412504196167, cross_entropy: 1.83412504196167 +[2025-04-27 11:31:00,644][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 2.302105665206909, cross_entropy: 2.302105665206909 +[2025-04-27 11:31:02,929][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 3.279649257659912, cross_entropy: 3.279649257659912 +[2025-04-27 11:31:03,049][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 3.425274133682251, cross_entropy: 3.425274133682251 +[2025-04-27 11:31:05,487][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.8305737972259521, cross_entropy: 1.8305737972259521 +[2025-04-27 11:31:05,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 2.4675137996673584, cross_entropy: 2.4675137996673584 +[2025-04-27 11:31:07,526][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 3.495231866836548, cross_entropy: 3.495231866836548 +[2025-04-27 11:31:07,649][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.9914593696594238, cross_entropy: 1.9914593696594238 +[2025-04-27 11:31:09,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 2.114885091781616, cross_entropy: 2.114885091781616 +[2025-04-27 11:31:09,720][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 2.5448925495147705, cross_entropy: 2.5448925495147705 +[2025-04-27 11:31:11,460][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.7105119228363037, cross_entropy: 1.7105119228363037 +[2025-04-27 11:31:11,585][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 2.44610595703125, cross_entropy: 2.44610595703125 +[2025-04-27 11:31:13,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 3.2265625, cross_entropy: 3.2265625 +[2025-04-27 11:31:13,929][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 3.3207709789276123, cross_entropy: 3.3207709789276123 +[2025-04-27 11:31:15,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 3.4820377826690674, cross_entropy: 3.4820377826690674 +[2025-04-27 11:31:15,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 1.9472110271453857, cross_entropy: 1.9472110271453857 +[2025-04-27 11:31:18,021][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 2.282454013824463, cross_entropy: 2.282454013824463 +[2025-04-27 11:31:18,144][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.8459333181381226, cross_entropy: 1.8459333181381226 +[2025-04-27 11:31:20,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.8841753005981445, cross_entropy: 1.8841753005981445 +[2025-04-27 11:31:20,283][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 3.166510581970215, cross_entropy: 3.166510581970215 +[2025-04-27 11:31:21,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.9778974056243896, cross_entropy: 2.9778974056243896 +[2025-04-27 11:31:22,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 3.6271185874938965, cross_entropy: 3.6271185874938965 +[2025-04-27 11:31:23,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 2.366281032562256, cross_entropy: 2.366281032562256 +[2025-04-27 11:31:23,944][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.9557080268859863, cross_entropy: 1.9557080268859863 +[2025-04-27 11:31:26,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.7151613235473633, cross_entropy: 1.7151613235473633 +[2025-04-27 11:31:26,349][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 3.0932135581970215, cross_entropy: 3.0932135581970215 +[2025-04-27 11:31:28,357][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 2.0043294429779053, cross_entropy: 2.0043294429779053 +[2025-04-27 11:31:28,478][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 2.8379878997802734, cross_entropy: 2.8379878997802734 +[2025-04-27 11:31:30,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.403322219848633, cross_entropy: 2.403322219848633 +[2025-04-27 11:31:30,223][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 3.4878227710723877, cross_entropy: 3.4878227710723877 +[2025-04-27 11:31:32,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 2.284698486328125, cross_entropy: 2.284698486328125 +[2025-04-27 11:31:32,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 3.665302276611328, cross_entropy: 3.665302276611328 +[2025-04-27 11:31:34,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.9637808799743652, cross_entropy: 2.9637808799743652 +[2025-04-27 11:31:34,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 1.8583945035934448, cross_entropy: 1.8583945035934448 +[2025-04-27 11:31:37,182][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.7640635967254639, cross_entropy: 1.7640635967254639 +[2025-04-27 11:31:37,300][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 3.297626495361328, cross_entropy: 3.297626495361328 +[2025-04-27 11:31:39,723][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 2.4644203186035156, cross_entropy: 2.4644203186035156 +[2025-04-27 11:31:39,827][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 3.5129036903381348, cross_entropy: 3.5129036903381348 +[2025-04-27 11:31:41,506][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.803086280822754, cross_entropy: 1.803086280822754 +[2025-04-27 11:31:41,625][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 2.573493480682373, cross_entropy: 2.573493480682373 +[2025-04-27 11:31:43,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.8528153896331787, cross_entropy: 1.8528153896331787 +[2025-04-27 11:31:44,010][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 1.933573603630066, cross_entropy: 1.933573603630066 +[2025-04-27 11:31:46,053][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.835357904434204, cross_entropy: 1.835357904434204 +[2025-04-27 11:31:46,171][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.3900179862976074, cross_entropy: 1.3900179862976074 +[2025-04-27 11:31:48,065][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 3.0546023845672607, cross_entropy: 3.0546023845672607 +[2025-04-27 11:31:48,168][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.664473533630371, cross_entropy: 1.664473533630371 +[2025-04-27 11:31:50,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.5045275688171387, cross_entropy: 2.5045275688171387 +[2025-04-27 11:31:50,153][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.8359594345092773, cross_entropy: 1.8359594345092773 +[2025-04-27 11:31:52,660][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 2.195066213607788, cross_entropy: 2.195066213607788 +[2025-04-27 11:31:52,778][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.042191743850708, cross_entropy: 2.042191743850708 +[2025-04-27 11:31:54,473][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 3.037938117980957, cross_entropy: 3.037938117980957 +[2025-04-27 11:31:54,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 2.7007925510406494, cross_entropy: 2.7007925510406494 +[2025-04-27 11:31:56,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 3.3118228912353516, cross_entropy: 3.3118228912353516 +[2025-04-27 11:31:56,736][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 2.6893692016601562, cross_entropy: 2.6893692016601562 +[2025-04-27 11:31:59,002][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.4978394508361816, cross_entropy: 2.4978394508361816 +[2025-04-27 11:31:59,124][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 2.23801326751709, cross_entropy: 2.23801326751709 +[2025-04-27 11:32:01,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 3.4629788398742676, cross_entropy: 3.4629788398742676 +[2025-04-27 11:32:01,254][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.545438528060913, cross_entropy: 1.545438528060913 +[2025-04-27 11:32:03,299][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.5708866119384766, cross_entropy: 3.5708866119384766 +[2025-04-27 11:32:03,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.3332746028900146, cross_entropy: 2.3332746028900146 +[2025-04-27 11:32:05,302][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 3.057149887084961, cross_entropy: 3.057149887084961 +[2025-04-27 11:32:05,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.693708896636963, cross_entropy: 1.693708896636963 +[2025-04-27 11:32:07,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 2.1877503395080566, cross_entropy: 2.1877503395080566 +[2025-04-27 11:32:07,514][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 3.3110828399658203, cross_entropy: 3.3110828399658203 +[2025-04-27 11:32:09,969][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 3.3068251609802246, cross_entropy: 3.3068251609802246 +[2025-04-27 11:32:10,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 3.0813217163085938, cross_entropy: 3.0813217163085938 +[2025-04-27 11:32:12,208][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 2.1762642860412598, cross_entropy: 2.1762642860412598 +[2025-04-27 11:32:12,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.8358542919158936, cross_entropy: 2.8358542919158936 +[2025-04-27 11:32:14,690][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.9786161184310913, cross_entropy: 1.9786161184310913 +[2025-04-27 11:32:14,806][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.9837082624435425, cross_entropy: 1.9837082624435425 +[2025-04-27 11:32:16,660][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 3.181185245513916, cross_entropy: 3.181185245513916 +[2025-04-27 11:32:16,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 2.043120861053467, cross_entropy: 2.043120861053467 +[2025-04-27 11:32:18,504][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.7804142236709595, cross_entropy: 1.7804142236709595 +[2025-04-27 11:32:18,627][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.5571452379226685, cross_entropy: 1.5571452379226685 +[2025-04-27 11:32:20,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 3.3624653816223145, cross_entropy: 3.3624653816223145 +[2025-04-27 11:32:20,754][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.638519763946533, cross_entropy: 2.638519763946533 +[2025-04-27 11:32:22,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 2.090782880783081, cross_entropy: 2.090782880783081 +[2025-04-27 11:32:23,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.759276866912842, cross_entropy: 2.759276866912842 +[2025-04-27 11:32:24,550][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 3.6470067501068115, cross_entropy: 3.6470067501068115 +[2025-04-27 11:32:25,126][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 3.304138660430908, cross_entropy: 3.304138660430908 +[2025-04-27 11:32:26,685][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 2.3784735202789307, cross_entropy: 2.3784735202789307 +[2025-04-27 11:32:27,111][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 3.321791648864746, cross_entropy: 3.321791648864746 +[2025-04-27 11:32:29,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 3.438300848007202, cross_entropy: 3.438300848007202 +[2025-04-27 11:32:29,521][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/iteration2000.pth. +[2025-04-27 11:32:29,660][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.4924001693725586, cross_entropy: 1.4924001693725586 +[2025-04-27 11:32:31,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 3.2875194549560547, cross_entropy: 3.2875194549560547 +[2025-04-27 11:32:31,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.94972562789917, cross_entropy: 2.94972562789917 +[2025-04-27 11:32:34,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 1.644370675086975, cross_entropy: 1.644370675086975 +[2025-04-27 11:32:35,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 3.2580747604370117, cross_entropy: 3.2580747604370117 +[2025-04-27 11:32:36,620][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.837088108062744, cross_entropy: 2.837088108062744 +[2025-04-27 11:32:37,481][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 3.605103015899658, cross_entropy: 3.605103015899658 +[2025-04-27 11:32:39,260][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.7076244354248047, cross_entropy: 2.7076244354248047 +[2025-04-27 11:32:40,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 2.1806936264038086, cross_entropy: 2.1806936264038086 +[2025-04-27 11:32:41,635][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 2.404604434967041, cross_entropy: 2.404604434967041 +[2025-04-27 11:32:42,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 3.4080843925476074, cross_entropy: 3.4080843925476074 +[2025-04-27 11:32:44,642][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 2.5055627822875977, cross_entropy: 2.5055627822875977 +[2025-04-27 11:32:44,912][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.964792013168335, cross_entropy: 1.964792013168335 +[2025-04-27 11:32:47,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 1.7295358180999756, cross_entropy: 1.7295358180999756 +[2025-04-27 11:32:47,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 2.0120906829833984, cross_entropy: 2.0120906829833984 +[2025-04-27 11:32:49,748][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.998568058013916, cross_entropy: 2.998568058013916 +[2025-04-27 11:32:49,867][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.8169939517974854, cross_entropy: 1.8169939517974854 +[2025-04-27 11:32:51,736][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 3.4872772693634033, cross_entropy: 3.4872772693634033 +[2025-04-27 11:32:51,857][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.719167709350586, cross_entropy: 2.719167709350586 +[2025-04-27 11:32:53,669][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 3.505082845687866, cross_entropy: 3.505082845687866 +[2025-04-27 11:32:53,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 2.870084762573242, cross_entropy: 2.870084762573242 +[2025-04-27 11:32:55,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.721038341522217, cross_entropy: 2.721038341522217 +[2025-04-27 11:32:55,765][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 2.403135061264038, cross_entropy: 2.403135061264038 +[2025-04-27 11:32:58,524][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 2.734947681427002, cross_entropy: 2.734947681427002 +[2025-04-27 11:32:58,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 1.7160780429840088, cross_entropy: 1.7160780429840088 +[2025-04-27 11:33:00,644][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 3.5612130165100098, cross_entropy: 3.5612130165100098 +[2025-04-27 11:33:00,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 1.834265947341919, cross_entropy: 1.834265947341919 +[2025-04-27 11:33:02,961][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 3.368195056915283, cross_entropy: 3.368195056915283 +[2025-04-27 11:33:03,083][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 3.125434398651123, cross_entropy: 3.125434398651123 +[2025-04-27 11:33:05,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.5280399322509766, cross_entropy: 1.5280399322509766 +[2025-04-27 11:33:05,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.9168059825897217, cross_entropy: 2.9168059825897217 +[2025-04-27 11:33:07,402][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 2.983016014099121, cross_entropy: 2.983016014099121 +[2025-04-27 11:33:07,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.8242831230163574, cross_entropy: 1.8242831230163574 +[2025-04-27 11:33:09,932][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 3.5838775634765625, cross_entropy: 3.5838775634765625 +[2025-04-27 11:33:10,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 2.5178003311157227, cross_entropy: 2.5178003311157227 +[2025-04-27 11:33:12,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 3.6599783897399902, cross_entropy: 3.6599783897399902 +[2025-04-27 11:33:12,761][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.9889347553253174, cross_entropy: 1.9889347553253174 +[2025-04-27 11:33:14,431][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.9529340267181396, cross_entropy: 1.9529340267181396 +[2025-04-27 11:33:14,534][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 3.3175973892211914, cross_entropy: 3.3175973892211914 +[2025-04-27 11:33:17,861][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 3.4446651935577393, cross_entropy: 3.4446651935577393 +[2025-04-27 11:33:17,986][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 1.6459503173828125, cross_entropy: 1.6459503173828125 +[2025-04-27 11:33:20,273][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 3.241706371307373, cross_entropy: 3.241706371307373 +[2025-04-27 11:33:20,376][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 3.432647228240967, cross_entropy: 3.432647228240967 +[2025-04-27 11:33:22,624][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.201777696609497, cross_entropy: 2.201777696609497 +[2025-04-27 11:33:22,751][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 3.1026172637939453, cross_entropy: 3.1026172637939453 +[2025-04-27 11:33:25,079][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 1.403268575668335, cross_entropy: 1.403268575668335 +[2025-04-27 11:33:25,203][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.5490248203277588, cross_entropy: 1.5490248203277588 +[2025-04-27 11:33:27,611][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.533921718597412, cross_entropy: 2.533921718597412 +[2025-04-27 11:33:27,741][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.543962836265564, cross_entropy: 1.543962836265564 +[2025-04-27 11:33:29,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 2.0376482009887695, cross_entropy: 2.0376482009887695 +[2025-04-27 11:33:30,024][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.452044129371643, cross_entropy: 1.452044129371643 +[2025-04-27 11:33:32,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 3.6754872798919678, cross_entropy: 3.6754872798919678 +[2025-04-27 11:33:32,364][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.7895311117172241, cross_entropy: 1.7895311117172241 +[2025-04-27 11:33:35,058][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.726233720779419, cross_entropy: 1.726233720779419 +[2025-04-27 11:33:35,180][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 2.5152411460876465, cross_entropy: 2.5152411460876465 +[2025-04-27 11:33:37,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 1.8380544185638428, cross_entropy: 1.8380544185638428 +[2025-04-27 11:33:37,999][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 2.01503324508667, cross_entropy: 2.01503324508667 +[2025-04-27 11:33:40,053][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.4852404594421387, cross_entropy: 2.4852404594421387 +[2025-04-27 11:33:40,171][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 3.259305238723755, cross_entropy: 3.259305238723755 +[2025-04-27 11:33:42,417][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 1.930145263671875, cross_entropy: 1.930145263671875 +[2025-04-27 11:33:42,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.9900373220443726, cross_entropy: 1.9900373220443726 +[2025-04-27 11:33:44,933][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.5067421197891235, cross_entropy: 1.5067421197891235 +[2025-04-27 11:33:45,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.8278615474700928, cross_entropy: 2.8278615474700928 +[2025-04-27 11:33:47,251][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 2.5634331703186035, cross_entropy: 2.5634331703186035 +[2025-04-27 11:33:47,379][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.4689621925354004, cross_entropy: 2.4689621925354004 +[2025-04-27 11:33:48,932][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 3.4050283432006836, cross_entropy: 3.4050283432006836 +[2025-04-27 11:33:49,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 3.4304089546203613, cross_entropy: 3.4304089546203613 +[2025-04-27 11:33:50,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 3.658395767211914, cross_entropy: 3.658395767211914 +[2025-04-27 11:33:50,993][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 2.18890118598938, cross_entropy: 2.18890118598938 +[2025-04-27 11:33:53,149][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.8091492652893066, cross_entropy: 1.8091492652893066 +[2025-04-27 11:33:53,267][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 2.159811496734619, cross_entropy: 2.159811496734619 +[2025-04-27 11:33:55,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 2.1653144359588623, cross_entropy: 2.1653144359588623 +[2025-04-27 11:33:55,291][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 3.280116558074951, cross_entropy: 3.280116558074951 +[2025-04-27 11:33:57,797][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.9237362146377563, cross_entropy: 1.9237362146377563 +[2025-04-27 11:33:57,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.497384548187256, cross_entropy: 2.497384548187256 +[2025-04-27 11:33:59,827][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 1.7794171571731567, cross_entropy: 1.7794171571731567 +[2025-04-27 11:33:59,950][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 1.9018172025680542, cross_entropy: 1.9018172025680542 +[2025-04-27 11:34:01,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.8985817432403564, cross_entropy: 2.8985817432403564 +[2025-04-27 11:34:02,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.850584626197815, cross_entropy: 1.850584626197815 +[2025-04-27 11:34:04,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.0514440536499023, cross_entropy: 2.0514440536499023 +[2025-04-27 11:34:04,125][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.1804821491241455, cross_entropy: 2.1804821491241455 +[2025-04-27 11:34:05,747][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 3.3240137100219727, cross_entropy: 3.3240137100219727 +[2025-04-27 11:34:06,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.904478669166565, cross_entropy: 1.904478669166565 +[2025-04-27 11:34:07,794][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 2.66611909866333, cross_entropy: 2.66611909866333 +[2025-04-27 11:34:08,226][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.7717241048812866, cross_entropy: 1.7717241048812866 +[2025-04-27 11:34:10,389][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 3.406853199005127, cross_entropy: 3.406853199005127 +[2025-04-27 11:34:10,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.5101799964904785, cross_entropy: 1.5101799964904785 +[2025-04-27 11:34:12,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.7193009853363037, cross_entropy: 1.7193009853363037 +[2025-04-27 11:34:12,918][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.8852936029434204, cross_entropy: 1.8852936029434204 +[2025-04-27 11:34:15,263][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 2.672287940979004, cross_entropy: 2.672287940979004 +[2025-04-27 11:34:15,384][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.9562394618988037, cross_entropy: 2.9562394618988037 +[2025-04-27 11:34:17,873][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 2.205137014389038, cross_entropy: 2.205137014389038 +[2025-04-27 11:34:17,993][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.9583535194396973, cross_entropy: 1.9583535194396973 +[2025-04-27 11:34:21,194][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 1.7632774114608765, cross_entropy: 1.7632774114608765 +[2025-04-27 11:34:21,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 1.2340970039367676, cross_entropy: 1.2340970039367676 +[2025-04-27 11:34:23,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.9300686120986938, cross_entropy: 1.9300686120986938 +[2025-04-27 11:34:23,766][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 2.3334240913391113, cross_entropy: 2.3334240913391113 +[2025-04-27 11:34:26,885][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.541509747505188, cross_entropy: 1.541509747505188 +[2025-04-27 11:34:27,008][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.788952112197876, cross_entropy: 1.788952112197876 +[2025-04-27 11:34:29,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 2.856931447982788, cross_entropy: 2.856931447982788 +[2025-04-27 11:34:30,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.5920900106430054, cross_entropy: 1.5920900106430054 +[2025-04-27 11:34:32,117][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 3.975098133087158, cross_entropy: 3.975098133087158 +[2025-04-27 11:34:32,245][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.9227666854858398, cross_entropy: 1.9227666854858398 +[2025-04-27 11:34:34,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 3.091517448425293, cross_entropy: 3.091517448425293 +[2025-04-27 11:34:34,757][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.7440941333770752, cross_entropy: 1.7440941333770752 +[2025-04-27 11:34:36,969][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.9765052795410156, cross_entropy: 2.9765052795410156 +[2025-04-27 11:34:37,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.600921630859375, cross_entropy: 1.600921630859375 +[2025-04-27 11:34:39,457][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 3.446938991546631, cross_entropy: 3.446938991546631 +[2025-04-27 11:34:39,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 3.411329746246338, cross_entropy: 3.411329746246338 +[2025-04-27 11:34:41,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 3.3585827350616455, cross_entropy: 3.3585827350616455 +[2025-04-27 11:34:41,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.8435561656951904, cross_entropy: 1.8435561656951904 +[2025-04-27 11:34:44,112][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 3.426492214202881, cross_entropy: 3.426492214202881 +[2025-04-27 11:34:44,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 2.4136228561401367, cross_entropy: 2.4136228561401367 +[2025-04-27 11:34:45,968][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 3.4365081787109375, cross_entropy: 3.4365081787109375 +[2025-04-27 11:34:46,090][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 2.6634974479675293, cross_entropy: 2.6634974479675293 +[2025-04-27 11:34:49,051][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 1.8385872840881348, cross_entropy: 1.8385872840881348 +[2025-04-27 11:34:49,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 3.5610971450805664, cross_entropy: 3.5610971450805664 +[2025-04-27 11:34:51,978][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.9887723922729492, cross_entropy: 1.9887723922729492 +[2025-04-27 11:34:52,081][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.550309658050537, cross_entropy: 3.550309658050537 +[2025-04-27 11:34:54,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.460319995880127, cross_entropy: 2.460319995880127 +[2025-04-27 11:34:54,493][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 3.4346365928649902, cross_entropy: 3.4346365928649902 +[2025-04-27 11:34:56,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 2.3129353523254395, cross_entropy: 2.3129353523254395 +[2025-04-27 11:34:57,063][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 2.12723708152771, cross_entropy: 2.12723708152771 +[2025-04-27 11:34:59,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.5783523321151733, cross_entropy: 1.5783523321151733 +[2025-04-27 11:34:59,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.9161734580993652, cross_entropy: 1.9161734580993652 +[2025-04-27 11:35:01,625][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.9242541790008545, cross_entropy: 1.9242541790008545 +[2025-04-27 11:35:01,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 1.7357450723648071, cross_entropy: 1.7357450723648071 +[2025-04-27 11:35:04,127][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 2.907115936279297, cross_entropy: 2.907115936279297 +[2025-04-27 11:35:04,232][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 3.7017812728881836, cross_entropy: 3.7017812728881836 +[2025-04-27 11:35:06,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 2.236741542816162, cross_entropy: 2.236741542816162 +[2025-04-27 11:35:06,645][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 2.0044262409210205, cross_entropy: 2.0044262409210205 +[2025-04-27 11:35:08,412][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.5577312707901, cross_entropy: 1.5577312707901 +[2025-04-27 11:35:08,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.788165807723999, cross_entropy: 1.788165807723999 +[2025-04-27 11:35:10,820][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 3.289107084274292, cross_entropy: 3.289107084274292 +[2025-04-27 11:35:10,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 3.088862180709839, cross_entropy: 3.088862180709839 +[2025-04-27 11:35:13,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 2.509791851043701, cross_entropy: 2.509791851043701 +[2025-04-27 11:37:06,762][BaseTrainer][INFO] - [Epoch 6/10] (train) 2.5081217288970947, cross_entropy: 2.5081217288970947 +[2025-04-27 11:37:06,762][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.9302870035171509, cross_entropy: 1.9302870035171509 +[2025-04-27 11:37:06,981][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:37:07,152][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch6.pth. +[2025-04-27 11:37:07,355][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:37:10,685][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.8379969596862793, cross_entropy: 2.8379969596862793 +[2025-04-27 11:37:10,807][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 3.041320562362671, cross_entropy: 3.041320562362671 +[2025-04-27 11:37:12,871][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 2.0276713371276855, cross_entropy: 2.0276713371276855 +[2025-04-27 11:37:12,977][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 1.316495418548584, cross_entropy: 1.316495418548584 +[2025-04-27 11:37:15,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 1.633542537689209, cross_entropy: 1.633542537689209 +[2025-04-27 11:37:15,913][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 2.1690609455108643, cross_entropy: 2.1690609455108643 +[2025-04-27 11:37:17,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 3.3189878463745117, cross_entropy: 3.3189878463745117 +[2025-04-27 11:37:17,873][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 2.442969560623169, cross_entropy: 2.442969560623169 +[2025-04-27 11:37:20,012][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 2.1427202224731445, cross_entropy: 2.1427202224731445 +[2025-04-27 11:37:20,133][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 2.0675244331359863, cross_entropy: 2.0675244331359863 +[2025-04-27 11:37:22,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 3.325547933578491, cross_entropy: 3.325547933578491 +[2025-04-27 11:37:22,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 2.834527015686035, cross_entropy: 2.834527015686035 +[2025-04-27 11:37:24,346][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 3.047985792160034, cross_entropy: 3.047985792160034 +[2025-04-27 11:37:24,809][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 3.6530988216400146, cross_entropy: 3.6530988216400146 +[2025-04-27 11:37:26,593][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.9342994689941406, cross_entropy: 2.9342994689941406 +[2025-04-27 11:37:26,864][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.920236587524414, cross_entropy: 2.920236587524414 +[2025-04-27 11:37:29,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.689342498779297, cross_entropy: 2.689342498779297 +[2025-04-27 11:37:29,516][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.4010002613067627, cross_entropy: 3.4010002613067627 +[2025-04-27 11:37:31,598][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 3.4279003143310547, cross_entropy: 3.4279003143310547 +[2025-04-27 11:37:31,753][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.9711922407150269, cross_entropy: 1.9711922407150269 +[2025-04-27 11:37:33,634][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.4956022500991821, cross_entropy: 1.4956022500991821 +[2025-04-27 11:37:33,804][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.9035279750823975, cross_entropy: 2.9035279750823975 +[2025-04-27 11:37:36,499][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 2.684760570526123, cross_entropy: 2.684760570526123 +[2025-04-27 11:37:36,670][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.8530640602111816, cross_entropy: 2.8530640602111816 +[2025-04-27 11:37:38,819][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 2.0738682746887207, cross_entropy: 2.0738682746887207 +[2025-04-27 11:37:39,020][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.873476028442383, cross_entropy: 2.873476028442383 +[2025-04-27 11:37:40,928][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 3.3133630752563477, cross_entropy: 3.3133630752563477 +[2025-04-27 11:37:41,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 3.1086511611938477, cross_entropy: 3.1086511611938477 +[2025-04-27 11:37:43,077][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.7699722051620483, cross_entropy: 1.7699722051620483 +[2025-04-27 11:37:43,660][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.697082757949829, cross_entropy: 1.697082757949829 +[2025-04-27 11:37:45,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.4379525184631348, cross_entropy: 2.4379525184631348 +[2025-04-27 11:37:46,230][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.928267240524292, cross_entropy: 2.928267240524292 +[2025-04-27 11:37:47,851][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.9829964637756348, cross_entropy: 2.9829964637756348 +[2025-04-27 11:37:48,741][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.6795611381530762, cross_entropy: 1.6795611381530762 +[2025-04-27 11:37:50,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 3.08282470703125, cross_entropy: 3.08282470703125 +[2025-04-27 11:37:50,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 2.2727458477020264, cross_entropy: 2.2727458477020264 +[2025-04-27 11:37:54,050][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 3.3979578018188477, cross_entropy: 3.3979578018188477 +[2025-04-27 11:37:54,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.4271588325500488, cross_entropy: 1.4271588325500488 +[2025-04-27 11:37:56,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 1.435939908027649, cross_entropy: 1.435939908027649 +[2025-04-27 11:37:56,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.7140159606933594, cross_entropy: 1.7140159606933594 +[2025-04-27 11:37:58,457][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.7918044328689575, cross_entropy: 1.7918044328689575 +[2025-04-27 11:37:58,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.575808525085449, cross_entropy: 2.575808525085449 +[2025-04-27 11:38:01,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 3.0673210620880127, cross_entropy: 3.0673210620880127 +[2025-04-27 11:38:01,170][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 3.7287955284118652, cross_entropy: 3.7287955284118652 +[2025-04-27 11:38:03,316][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.6912424564361572, cross_entropy: 2.6912424564361572 +[2025-04-27 11:38:03,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 2.9856300354003906, cross_entropy: 2.9856300354003906 +[2025-04-27 11:38:05,491][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 1.6040871143341064, cross_entropy: 1.6040871143341064 +[2025-04-27 11:38:05,616][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 3.123582363128662, cross_entropy: 3.123582363128662 +[2025-04-27 11:38:07,991][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.8349242210388184, cross_entropy: 2.8349242210388184 +[2025-04-27 11:38:08,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 2.158625602722168, cross_entropy: 2.158625602722168 +[2025-04-27 11:38:10,022][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 3.2098138332366943, cross_entropy: 3.2098138332366943 +[2025-04-27 11:38:10,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 3.609018325805664, cross_entropy: 3.609018325805664 +[2025-04-27 11:38:13,127][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 2.6038360595703125, cross_entropy: 2.6038360595703125 +[2025-04-27 11:38:13,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 3.258810043334961, cross_entropy: 3.258810043334961 +[2025-04-27 11:38:15,558][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 2.6223883628845215, cross_entropy: 2.6223883628845215 +[2025-04-27 11:38:15,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 1.828134536743164, cross_entropy: 1.828134536743164 +[2025-04-27 11:38:17,816][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 2.058863878250122, cross_entropy: 2.058863878250122 +[2025-04-27 11:38:17,941][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.5602577924728394, cross_entropy: 1.5602577924728394 +[2025-04-27 11:38:21,190][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 3.4440643787384033, cross_entropy: 3.4440643787384033 +[2025-04-27 11:38:21,313][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.7366485595703125, cross_entropy: 1.7366485595703125 +[2025-04-27 11:38:23,387][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.1517984867095947, cross_entropy: 2.1517984867095947 +[2025-04-27 11:38:23,491][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.8467870950698853, cross_entropy: 1.8467870950698853 +[2025-04-27 11:38:25,575][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.9901857376098633, cross_entropy: 1.9901857376098633 +[2025-04-27 11:38:25,695][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 1.4731166362762451, cross_entropy: 1.4731166362762451 +[2025-04-27 11:38:27,598][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.848862409591675, cross_entropy: 2.848862409591675 +[2025-04-27 11:38:27,703][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 2.286377191543579, cross_entropy: 2.286377191543579 +[2025-04-27 11:38:29,826][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.7455699443817139, cross_entropy: 1.7455699443817139 +[2025-04-27 11:38:29,949][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.7376372814178467, cross_entropy: 2.7376372814178467 +[2025-04-27 11:38:32,923][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 1.6075024604797363, cross_entropy: 1.6075024604797363 +[2025-04-27 11:38:33,046][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 2.6158981323242188, cross_entropy: 2.6158981323242188 +[2025-04-27 11:38:35,927][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 3.3458824157714844, cross_entropy: 3.3458824157714844 +[2025-04-27 11:38:36,046][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 3.222813129425049, cross_entropy: 3.222813129425049 +[2025-04-27 11:38:38,056][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 2.586874008178711, cross_entropy: 2.586874008178711 +[2025-04-27 11:38:38,177][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 3.531226396560669, cross_entropy: 3.531226396560669 +[2025-04-27 11:38:39,732][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 1.83333420753479, cross_entropy: 1.83333420753479 +[2025-04-27 11:38:39,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.7936913967132568, cross_entropy: 1.7936913967132568 +[2025-04-27 11:38:41,878][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.9463419914245605, cross_entropy: 2.9463419914245605 +[2025-04-27 11:38:41,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 2.4635443687438965, cross_entropy: 2.4635443687438965 +[2025-04-27 11:38:44,181][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.976247549057007, cross_entropy: 2.976247549057007 +[2025-04-27 11:38:44,285][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 3.0707409381866455, cross_entropy: 3.0707409381866455 +[2025-04-27 11:38:46,234][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 1.5502357482910156, cross_entropy: 1.5502357482910156 +[2025-04-27 11:38:46,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 3.0359761714935303, cross_entropy: 3.0359761714935303 +[2025-04-27 11:38:48,525][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 3.068946599960327, cross_entropy: 3.068946599960327 +[2025-04-27 11:38:48,636][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 2.2448620796203613, cross_entropy: 2.2448620796203613 +[2025-04-27 11:38:50,729][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.934105634689331, cross_entropy: 1.934105634689331 +[2025-04-27 11:38:50,851][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 1.992679238319397, cross_entropy: 1.992679238319397 +[2025-04-27 11:38:53,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 1.4652423858642578, cross_entropy: 1.4652423858642578 +[2025-04-27 11:38:53,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 2.525031089782715, cross_entropy: 2.525031089782715 +[2025-04-27 11:38:55,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 3.3648576736450195, cross_entropy: 3.3648576736450195 +[2025-04-27 11:38:55,398][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 2.0047082901000977, cross_entropy: 2.0047082901000977 +[2025-04-27 11:38:57,940][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 3.367112159729004, cross_entropy: 3.367112159729004 +[2025-04-27 11:38:58,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 3.3239736557006836, cross_entropy: 3.3239736557006836 +[2025-04-27 11:39:00,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 2.022214412689209, cross_entropy: 2.022214412689209 +[2025-04-27 11:39:00,623][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.8229585886001587, cross_entropy: 1.8229585886001587 +[2025-04-27 11:39:02,357][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 3.4078502655029297, cross_entropy: 3.4078502655029297 +[2025-04-27 11:39:02,547][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 2.030276298522949, cross_entropy: 2.030276298522949 +[2025-04-27 11:39:04,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.7015807628631592, cross_entropy: 1.7015807628631592 +[2025-04-27 11:39:05,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 2.1870810985565186, cross_entropy: 2.1870810985565186 +[2025-04-27 11:39:07,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 2.3659536838531494, cross_entropy: 2.3659536838531494 +[2025-04-27 11:39:07,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.9834167957305908, cross_entropy: 1.9834167957305908 +[2025-04-27 11:39:10,402][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 1.8986234664916992, cross_entropy: 1.8986234664916992 +[2025-04-27 11:39:10,524][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 1.8483119010925293, cross_entropy: 1.8483119010925293 +[2025-04-27 11:39:13,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.4686665534973145, cross_entropy: 2.4686665534973145 +[2025-04-27 11:39:13,370][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 2.081319808959961, cross_entropy: 2.081319808959961 +[2025-04-27 11:39:15,673][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.5963853597640991, cross_entropy: 1.5963853597640991 +[2025-04-27 11:39:15,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 3.178786277770996, cross_entropy: 3.178786277770996 +[2025-04-27 11:39:17,863][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 2.481363296508789, cross_entropy: 2.481363296508789 +[2025-04-27 11:39:17,978][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.6666841506958008, cross_entropy: 1.6666841506958008 +[2025-04-27 11:39:20,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 1.5983705520629883, cross_entropy: 1.5983705520629883 +[2025-04-27 11:39:20,641][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 1.686985731124878, cross_entropy: 1.686985731124878 +[2025-04-27 11:39:22,744][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 1.5513646602630615, cross_entropy: 1.5513646602630615 +[2025-04-27 11:39:22,850][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 1.579918622970581, cross_entropy: 1.579918622970581 +[2025-04-27 11:39:24,828][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.719246745109558, cross_entropy: 1.719246745109558 +[2025-04-27 11:39:24,932][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 2.323370933532715, cross_entropy: 2.323370933532715 +[2025-04-27 11:39:27,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 2.1318788528442383, cross_entropy: 2.1318788528442383 +[2025-04-27 11:39:27,260][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 1.6611413955688477, cross_entropy: 1.6611413955688477 +[2025-04-27 11:39:29,653][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.5246987342834473, cross_entropy: 1.5246987342834473 +[2025-04-27 11:39:29,776][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 1.618607759475708, cross_entropy: 1.618607759475708 +[2025-04-27 11:39:32,475][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.8570613861083984, cross_entropy: 2.8570613861083984 +[2025-04-27 11:39:32,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 3.767810821533203, cross_entropy: 3.767810821533203 +[2025-04-27 11:39:34,430][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.559607982635498, cross_entropy: 1.559607982635498 +[2025-04-27 11:39:34,552][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 2.461534023284912, cross_entropy: 2.461534023284912 +[2025-04-27 11:39:38,201][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.4626874923706055, cross_entropy: 2.4626874923706055 +[2025-04-27 11:39:38,325][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.5749218463897705, cross_entropy: 1.5749218463897705 +[2025-04-27 11:39:41,008][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 1.8621808290481567, cross_entropy: 1.8621808290481567 +[2025-04-27 11:39:41,140][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.7130794525146484, cross_entropy: 1.7130794525146484 +[2025-04-27 11:39:44,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.7200875282287598, cross_entropy: 3.7200875282287598 +[2025-04-27 11:39:45,092][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 3.168867349624634, cross_entropy: 3.168867349624634 +[2025-04-27 11:39:47,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 1.7460044622421265, cross_entropy: 1.7460044622421265 +[2025-04-27 11:39:47,270][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 3.4225704669952393, cross_entropy: 3.4225704669952393 +[2025-04-27 11:39:49,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 1.1483101844787598, cross_entropy: 1.1483101844787598 +[2025-04-27 11:39:49,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 1.7356107234954834, cross_entropy: 1.7356107234954834 +[2025-04-27 11:39:51,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 3.1785237789154053, cross_entropy: 3.1785237789154053 +[2025-04-27 11:39:51,788][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 3.351884365081787, cross_entropy: 3.351884365081787 +[2025-04-27 11:39:54,047][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 3.659489393234253, cross_entropy: 3.659489393234253 +[2025-04-27 11:39:54,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.9055233001708984, cross_entropy: 2.9055233001708984 +[2025-04-27 11:39:56,847][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 3.515279769897461, cross_entropy: 3.515279769897461 +[2025-04-27 11:39:56,972][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 2.2226290702819824, cross_entropy: 2.2226290702819824 +[2025-04-27 11:39:59,460][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.6521210670471191, cross_entropy: 1.6521210670471191 +[2025-04-27 11:39:59,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 3.317716598510742, cross_entropy: 3.317716598510742 +[2025-04-27 11:40:01,938][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 1.7697296142578125, cross_entropy: 1.7697296142578125 +[2025-04-27 11:40:02,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.7034341096878052, cross_entropy: 1.7034341096878052 +[2025-04-27 11:40:03,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 3.3157105445861816, cross_entropy: 3.3157105445861816 +[2025-04-27 11:40:04,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 3.209885597229004, cross_entropy: 3.209885597229004 +[2025-04-27 11:40:06,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 2.0971736907958984, cross_entropy: 2.0971736907958984 +[2025-04-27 11:40:07,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 2.549877166748047, cross_entropy: 2.549877166748047 +[2025-04-27 11:40:09,609][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 2.8264358043670654, cross_entropy: 2.8264358043670654 +[2025-04-27 11:40:09,731][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 2.2345175743103027, cross_entropy: 2.2345175743103027 +[2025-04-27 11:40:12,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 3.0159361362457275, cross_entropy: 3.0159361362457275 +[2025-04-27 11:40:12,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 2.9192957878112793, cross_entropy: 2.9192957878112793 +[2025-04-27 11:40:14,659][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.933650016784668, cross_entropy: 2.933650016784668 +[2025-04-27 11:40:14,794][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 3.1638574600219727, cross_entropy: 3.1638574600219727 +[2025-04-27 11:40:17,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.3867390155792236, cross_entropy: 2.3867390155792236 +[2025-04-27 11:40:17,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 3.2995615005493164, cross_entropy: 3.2995615005493164 +[2025-04-27 11:40:19,413][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 2.206430435180664, cross_entropy: 2.206430435180664 +[2025-04-27 11:40:19,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 1.8201380968093872, cross_entropy: 1.8201380968093872 +[2025-04-27 11:40:21,577][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 2.693746566772461, cross_entropy: 2.693746566772461 +[2025-04-27 11:40:21,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 1.7638826370239258, cross_entropy: 1.7638826370239258 +[2025-04-27 11:40:24,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 2.4309184551239014, cross_entropy: 2.4309184551239014 +[2025-04-27 11:40:24,495][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 2.262585163116455, cross_entropy: 2.262585163116455 +[2025-04-27 11:40:26,391][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 3.6640143394470215, cross_entropy: 3.6640143394470215 +[2025-04-27 11:40:26,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 2.5883092880249023, cross_entropy: 2.5883092880249023 +[2025-04-27 11:40:28,611][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.6564985513687134, cross_entropy: 1.6564985513687134 +[2025-04-27 11:40:28,740][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 3.2181575298309326, cross_entropy: 3.2181575298309326 +[2025-04-27 11:40:30,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.5448057651519775, cross_entropy: 1.5448057651519775 +[2025-04-27 11:40:30,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 2.9317455291748047, cross_entropy: 2.9317455291748047 +[2025-04-27 11:40:32,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 3.3976521492004395, cross_entropy: 3.3976521492004395 +[2025-04-27 11:40:32,297][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 1.9155361652374268, cross_entropy: 1.9155361652374268 +[2025-04-27 11:40:35,144][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.8147730827331543, cross_entropy: 1.8147730827331543 +[2025-04-27 11:40:35,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 2.98837947845459, cross_entropy: 2.98837947845459 +[2025-04-27 11:40:37,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 2.12701153755188, cross_entropy: 2.12701153755188 +[2025-04-27 11:40:37,610][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 3.4085166454315186, cross_entropy: 3.4085166454315186 +[2025-04-27 11:40:39,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 3.29732608795166, cross_entropy: 3.29732608795166 +[2025-04-27 11:40:39,636][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 3.302654266357422, cross_entropy: 3.302654266357422 +[2025-04-27 11:40:42,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 3.706329584121704, cross_entropy: 3.706329584121704 +[2025-04-27 11:40:42,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 3.5321407318115234, cross_entropy: 3.5321407318115234 +[2025-04-27 11:40:44,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 3.338240623474121, cross_entropy: 3.338240623474121 +[2025-04-27 11:40:44,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.691899299621582, cross_entropy: 1.691899299621582 +[2025-04-27 11:40:47,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 3.5700459480285645, cross_entropy: 3.5700459480285645 +[2025-04-27 11:40:47,585][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.3804271221160889, cross_entropy: 1.3804271221160889 +[2025-04-27 11:40:49,866][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.0140717029571533, cross_entropy: 2.0140717029571533 +[2025-04-27 11:40:49,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 3.2636494636535645, cross_entropy: 3.2636494636535645 +[2025-04-27 11:40:52,502][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 2.933393955230713, cross_entropy: 2.933393955230713 +[2025-04-27 11:40:52,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 3.1237826347351074, cross_entropy: 3.1237826347351074 +[2025-04-27 11:40:54,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 2.005044937133789, cross_entropy: 2.005044937133789 +[2025-04-27 11:40:54,988][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 1.3678237199783325, cross_entropy: 1.3678237199783325 +[2025-04-27 11:40:58,008][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 3.391571521759033, cross_entropy: 3.391571521759033 +[2025-04-27 11:40:58,133][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 3.3345983028411865, cross_entropy: 3.3345983028411865 +[2025-04-27 11:41:01,459][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.9566571712493896, cross_entropy: 1.9566571712493896 +[2025-04-27 11:41:01,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 2.5603115558624268, cross_entropy: 2.5603115558624268 +[2025-04-27 11:41:03,890][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 2.3747808933258057, cross_entropy: 2.3747808933258057 +[2025-04-27 11:41:03,995][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.5576766729354858, cross_entropy: 1.5576766729354858 +[2025-04-27 11:41:06,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 3.5802001953125, cross_entropy: 3.5802001953125 +[2025-04-27 11:41:06,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 1.8395357131958008, cross_entropy: 1.8395357131958008 +[2025-04-27 11:41:08,775][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 2.641058921813965, cross_entropy: 2.641058921813965 +[2025-04-27 11:41:08,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 3.1206910610198975, cross_entropy: 3.1206910610198975 +[2025-04-27 11:41:11,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 3.3406286239624023, cross_entropy: 3.3406286239624023 +[2025-04-27 11:41:11,714][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 2.9958419799804688, cross_entropy: 2.9958419799804688 +[2025-04-27 11:41:14,151][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.393409252166748, cross_entropy: 3.393409252166748 +[2025-04-27 11:41:14,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 2.5970458984375, cross_entropy: 2.5970458984375 +[2025-04-27 11:41:16,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 3.383371353149414, cross_entropy: 3.383371353149414 +[2025-04-27 11:41:16,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.5137953758239746, cross_entropy: 2.5137953758239746 +[2025-04-27 11:41:18,841][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.875556230545044, cross_entropy: 1.875556230545044 +[2025-04-27 11:41:18,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.8679721355438232, cross_entropy: 2.8679721355438232 +[2025-04-27 11:41:22,552][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.4632935523986816, cross_entropy: 3.4632935523986816 +[2025-04-27 11:41:22,659][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 1.8930829763412476, cross_entropy: 1.8930829763412476 +[2025-04-27 11:41:24,875][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 1.660588026046753, cross_entropy: 1.660588026046753 +[2025-04-27 11:41:24,993][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 3.1620888710021973, cross_entropy: 3.1620888710021973 +[2025-04-27 11:41:27,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 1.175607681274414, cross_entropy: 1.175607681274414 +[2025-04-27 11:41:27,210][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 3.5244388580322266, cross_entropy: 3.5244388580322266 +[2025-04-27 11:41:29,555][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 3.730654716491699, cross_entropy: 3.730654716491699 +[2025-04-27 11:41:29,661][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 3.5162997245788574, cross_entropy: 3.5162997245788574 +[2025-04-27 11:41:31,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 1.943302869796753, cross_entropy: 1.943302869796753 +[2025-04-27 11:41:31,966][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.2128344774246216, cross_entropy: 1.2128344774246216 +[2025-04-27 11:41:34,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.9687989950180054, cross_entropy: 1.9687989950180054 +[2025-04-27 11:41:34,718][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 2.781784772872925, cross_entropy: 2.781784772872925 +[2025-04-27 11:41:36,994][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 3.4351720809936523, cross_entropy: 3.4351720809936523 +[2025-04-27 11:41:37,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 3.364935874938965, cross_entropy: 3.364935874938965 +[2025-04-27 11:41:39,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 2.051776647567749, cross_entropy: 2.051776647567749 +[2025-04-27 11:41:39,573][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 1.711726188659668, cross_entropy: 1.711726188659668 +[2025-04-27 11:41:42,224][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 2.0155725479125977, cross_entropy: 2.0155725479125977 +[2025-04-27 11:41:42,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 1.644848108291626, cross_entropy: 1.644848108291626 +[2025-04-27 11:41:44,244][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.02878475189209, cross_entropy: 2.02878475189209 +[2025-04-27 11:41:44,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 3.1401212215423584, cross_entropy: 3.1401212215423584 +[2025-04-27 11:41:46,538][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 3.1618666648864746, cross_entropy: 3.1618666648864746 +[2025-04-27 11:41:46,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 3.29950213432312, cross_entropy: 3.29950213432312 +[2025-04-27 11:41:48,518][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 3.255906581878662, cross_entropy: 3.255906581878662 +[2025-04-27 11:41:48,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 2.8383307456970215, cross_entropy: 2.8383307456970215 +[2025-04-27 11:41:50,529][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.4741545915603638, cross_entropy: 1.4741545915603638 +[2025-04-27 11:41:50,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 1.7514985799789429, cross_entropy: 1.7514985799789429 +[2025-04-27 11:41:52,622][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.1382505893707275, cross_entropy: 2.1382505893707275 +[2025-04-27 11:41:52,914][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.5996655225753784, cross_entropy: 1.5996655225753784 +[2025-04-27 11:41:55,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 2.1717896461486816, cross_entropy: 2.1717896461486816 +[2025-04-27 11:41:55,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.571749687194824, cross_entropy: 2.571749687194824 +[2025-04-27 11:41:57,736][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.6260344982147217, cross_entropy: 1.6260344982147217 +[2025-04-27 11:41:57,840][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 2.1720035076141357, cross_entropy: 2.1720035076141357 +[2025-04-27 11:42:00,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 2.8571619987487793, cross_entropy: 2.8571619987487793 +[2025-04-27 11:42:00,362][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 1.9326763153076172, cross_entropy: 1.9326763153076172 +[2025-04-27 11:42:03,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.844424247741699, cross_entropy: 2.844424247741699 +[2025-04-27 11:42:03,277][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 3.1849942207336426, cross_entropy: 3.1849942207336426 +[2025-04-27 11:42:05,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.5951900482177734, cross_entropy: 2.5951900482177734 +[2025-04-27 11:42:05,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 1.7511928081512451, cross_entropy: 1.7511928081512451 +[2025-04-27 11:42:08,063][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 2.9767906665802, cross_entropy: 2.9767906665802 +[2025-04-27 11:42:08,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 3.6002097129821777, cross_entropy: 3.6002097129821777 +[2025-04-27 11:42:11,187][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.8495769500732422, cross_entropy: 1.8495769500732422 +[2025-04-27 11:42:11,309][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 3.017178535461426, cross_entropy: 3.017178535461426 +[2025-04-27 11:42:13,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 3.231895685195923, cross_entropy: 3.231895685195923 +[2025-04-27 11:42:13,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 3.278848171234131, cross_entropy: 3.278848171234131 +[2025-04-27 11:42:16,721][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 1.543971300125122, cross_entropy: 1.543971300125122 +[2025-04-27 11:42:16,827][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.8207225799560547, cross_entropy: 2.8207225799560547 +[2025-04-27 11:42:19,397][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.9671376943588257, cross_entropy: 1.9671376943588257 +[2025-04-27 11:42:19,500][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 2.3614132404327393, cross_entropy: 2.3614132404327393 +[2025-04-27 11:42:21,737][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 2.9921512603759766, cross_entropy: 2.9921512603759766 +[2025-04-27 11:42:21,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 3.412639856338501, cross_entropy: 3.412639856338501 +[2025-04-27 11:42:23,740][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 1.9876794815063477, cross_entropy: 1.9876794815063477 +[2025-04-27 11:42:23,844][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 3.185637950897217, cross_entropy: 3.185637950897217 +[2025-04-27 11:42:26,167][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.0441906452178955, cross_entropy: 2.0441906452178955 +[2025-04-27 11:42:26,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 3.516209602355957, cross_entropy: 3.516209602355957 +[2025-04-27 11:42:28,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.5249812602996826, cross_entropy: 1.5249812602996826 +[2025-04-27 11:42:28,492][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.0593881607055664, cross_entropy: 2.0593881607055664 +[2025-04-27 11:42:30,557][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 2.7651824951171875, cross_entropy: 2.7651824951171875 +[2025-04-27 11:42:30,680][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.7418112754821777, cross_entropy: 1.7418112754821777 +[2025-04-27 11:42:33,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.9467432498931885, cross_entropy: 1.9467432498931885 +[2025-04-27 11:42:33,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 2.2323384284973145, cross_entropy: 2.2323384284973145 +[2025-04-27 11:42:35,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.3357529640197754, cross_entropy: 2.3357529640197754 +[2025-04-27 11:42:35,803][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 2.309577226638794, cross_entropy: 2.309577226638794 +[2025-04-27 11:42:37,806][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 2.2804644107818604, cross_entropy: 2.2804644107818604 +[2025-04-27 11:42:37,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.4523727893829346, cross_entropy: 2.4523727893829346 +[2025-04-27 11:42:40,327][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 3.0810329914093018, cross_entropy: 3.0810329914093018 +[2025-04-27 11:42:40,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 2.29209566116333, cross_entropy: 2.29209566116333 +[2025-04-27 11:42:42,658][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 2.828205108642578, cross_entropy: 2.828205108642578 +[2025-04-27 11:42:42,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 2.0596861839294434, cross_entropy: 2.0596861839294434 +[2025-04-27 11:42:45,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.104060649871826, cross_entropy: 2.104060649871826 +[2025-04-27 11:42:46,068][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.9763237237930298, cross_entropy: 1.9763237237930298 +[2025-04-27 11:42:48,308][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 3.029492139816284, cross_entropy: 3.029492139816284 +[2025-04-27 11:42:48,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 3.2453601360321045, cross_entropy: 3.2453601360321045 +[2025-04-27 11:42:50,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.8866456747055054, cross_entropy: 1.8866456747055054 +[2025-04-27 11:42:50,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 3.1588172912597656, cross_entropy: 3.1588172912597656 +[2025-04-27 11:42:53,777][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.6798484325408936, cross_entropy: 1.6798484325408936 +[2025-04-27 11:42:53,883][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 2.009841203689575, cross_entropy: 2.009841203689575 +[2025-04-27 11:42:56,251][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 2.469568967819214, cross_entropy: 2.469568967819214 +[2025-04-27 11:42:56,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 1.7550610303878784, cross_entropy: 1.7550610303878784 +[2025-04-27 11:42:58,549][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.8725695610046387, cross_entropy: 2.8725695610046387 +[2025-04-27 11:42:58,672][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 2.4199137687683105, cross_entropy: 2.4199137687683105 +[2025-04-27 11:43:01,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 2.441957473754883, cross_entropy: 2.441957473754883 +[2025-04-27 11:43:01,254][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.128652334213257, cross_entropy: 2.128652334213257 +[2025-04-27 11:43:03,201][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.6152876615524292, cross_entropy: 1.6152876615524292 +[2025-04-27 11:43:03,327][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 1.5106782913208008, cross_entropy: 1.5106782913208008 +[2025-04-27 11:43:05,972][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 1.8660318851470947, cross_entropy: 1.8660318851470947 +[2025-04-27 11:43:06,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.6565842628479004, cross_entropy: 2.6565842628479004 +[2025-04-27 11:43:09,801][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.852473258972168, cross_entropy: 1.852473258972168 +[2025-04-27 11:43:09,927][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 2.2433524131774902, cross_entropy: 2.2433524131774902 +[2025-04-27 11:43:12,841][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 3.6772043704986572, cross_entropy: 3.6772043704986572 +[2025-04-27 11:43:12,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.6265904903411865, cross_entropy: 1.6265904903411865 +[2025-04-27 11:43:15,054][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 1.7121330499649048, cross_entropy: 1.7121330499649048 +[2025-04-27 11:43:15,179][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.8457019329071045, cross_entropy: 1.8457019329071045 +[2025-04-27 11:43:17,677][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 3.405792713165283, cross_entropy: 3.405792713165283 +[2025-04-27 11:43:17,782][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 2.173748016357422, cross_entropy: 2.173748016357422 +[2025-04-27 11:43:19,962][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.8759572505950928, cross_entropy: 2.8759572505950928 +[2025-04-27 11:43:20,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 3.434859037399292, cross_entropy: 3.434859037399292 +[2025-04-27 11:43:22,938][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.8420004844665527, cross_entropy: 2.8420004844665527 +[2025-04-27 11:43:23,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 1.8485682010650635, cross_entropy: 1.8485682010650635 +[2025-04-27 11:43:25,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.5583784580230713, cross_entropy: 1.5583784580230713 +[2025-04-27 11:43:26,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 2.1519408226013184, cross_entropy: 2.1519408226013184 +[2025-04-27 11:43:28,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.794132113456726, cross_entropy: 1.794132113456726 +[2025-04-27 11:43:28,232][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.6984925270080566, cross_entropy: 2.6984925270080566 +[2025-04-27 11:43:30,314][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 3.140415906906128, cross_entropy: 3.140415906906128 +[2025-04-27 11:43:30,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 3.4921998977661133, cross_entropy: 3.4921998977661133 +[2025-04-27 11:43:33,599][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 2.181105852127075, cross_entropy: 2.181105852127075 +[2025-04-27 11:43:33,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 1.808150291442871, cross_entropy: 1.808150291442871 +[2025-04-27 11:43:35,687][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 2.365025043487549, cross_entropy: 2.365025043487549 +[2025-04-27 11:43:35,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 2.1620919704437256, cross_entropy: 2.1620919704437256 +[2025-04-27 11:43:37,488][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 2.3003768920898438, cross_entropy: 2.3003768920898438 +[2025-04-27 11:43:37,611][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.9767154455184937, cross_entropy: 1.9767154455184937 +[2025-04-27 11:43:39,589][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 2.2392916679382324, cross_entropy: 2.2392916679382324 +[2025-04-27 11:43:39,713][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.8740410804748535, cross_entropy: 1.8740410804748535 +[2025-04-27 11:43:41,734][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 2.080646276473999, cross_entropy: 2.080646276473999 +[2025-04-27 11:43:41,839][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.8839365243911743, cross_entropy: 1.8839365243911743 +[2025-04-27 11:43:45,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 2.0014524459838867, cross_entropy: 2.0014524459838867 +[2025-04-27 11:43:45,366][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 3.1954121589660645, cross_entropy: 3.1954121589660645 +[2025-04-27 11:43:47,038][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.9000284671783447, cross_entropy: 2.9000284671783447 +[2025-04-27 11:43:47,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 1.9101758003234863, cross_entropy: 1.9101758003234863 +[2025-04-27 11:43:49,542][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.6691462993621826, cross_entropy: 1.6691462993621826 +[2025-04-27 11:43:49,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.582639694213867, cross_entropy: 2.582639694213867 +[2025-04-27 11:43:51,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 1.8128929138183594, cross_entropy: 1.8128929138183594 +[2025-04-27 11:43:51,777][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 3.4021289348602295, cross_entropy: 3.4021289348602295 +[2025-04-27 11:43:54,539][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 2.493804454803467, cross_entropy: 2.493804454803467 +[2025-04-27 11:43:54,649][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.9098412990570068, cross_entropy: 1.9098412990570068 +[2025-04-27 11:43:56,819][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.872412919998169, cross_entropy: 1.872412919998169 +[2025-04-27 11:43:56,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 2.0297608375549316, cross_entropy: 2.0297608375549316 +[2025-04-27 11:43:59,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 1.4657906293869019, cross_entropy: 1.4657906293869019 +[2025-04-27 11:43:59,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 2.954143524169922, cross_entropy: 2.954143524169922 +[2025-04-27 11:44:01,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 3.5626907348632812, cross_entropy: 3.5626907348632812 +[2025-04-27 11:44:01,255][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 2.9589293003082275, cross_entropy: 2.9589293003082275 +[2025-04-27 11:44:03,586][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 1.9509745836257935, cross_entropy: 1.9509745836257935 +[2025-04-27 11:44:03,691][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.6117403507232666, cross_entropy: 1.6117403507232666 +[2025-04-27 11:44:06,488][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.38478684425354, cross_entropy: 1.38478684425354 +[2025-04-27 11:44:06,613][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.988637924194336, cross_entropy: 1.988637924194336 +[2025-04-27 11:44:08,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 1.6061303615570068, cross_entropy: 1.6061303615570068 +[2025-04-27 11:44:08,828][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.1386091709136963, cross_entropy: 2.1386091709136963 +[2025-04-27 11:44:10,774][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 3.1322920322418213, cross_entropy: 3.1322920322418213 +[2025-04-27 11:44:10,898][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 2.7371582984924316, cross_entropy: 2.7371582984924316 +[2025-04-27 11:44:12,582][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 3.4862663745880127, cross_entropy: 3.4862663745880127 +[2025-04-27 11:44:12,703][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 1.503304123878479, cross_entropy: 1.503304123878479 +[2025-04-27 11:44:15,294][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 2.0295464992523193, cross_entropy: 2.0295464992523193 +[2025-04-27 11:44:15,414][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 2.8476171493530273, cross_entropy: 2.8476171493530273 +[2025-04-27 11:44:17,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 2.6392548084259033, cross_entropy: 2.6392548084259033 +[2025-04-27 11:44:17,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.254603862762451, cross_entropy: 2.254603862762451 +[2025-04-27 11:44:20,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 3.429295539855957, cross_entropy: 3.429295539855957 +[2025-04-27 11:44:20,359][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 2.389031410217285, cross_entropy: 2.389031410217285 +[2025-04-27 11:44:22,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 3.285299301147461, cross_entropy: 3.285299301147461 +[2025-04-27 11:44:22,327][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.978755235671997, cross_entropy: 1.978755235671997 +[2025-04-27 11:44:25,442][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 3.1536545753479004, cross_entropy: 3.1536545753479004 +[2025-04-27 11:44:25,568][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 1.689329981803894, cross_entropy: 1.689329981803894 +[2025-04-27 11:44:27,658][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.8035794496536255, cross_entropy: 1.8035794496536255 +[2025-04-27 11:44:27,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.671459436416626, cross_entropy: 2.671459436416626 +[2025-04-27 11:46:22,731][BaseTrainer][INFO] - [Epoch 7/10] (train) 2.462038278579712, cross_entropy: 2.462038278579712 +[2025-04-27 11:46:22,731][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.8305162191390991, cross_entropy: 1.8305162191390991 +[2025-04-27 11:46:22,960][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:46:23,513][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch7.pth. +[2025-04-27 11:46:23,732][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:46:27,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.7835912704467773, cross_entropy: 1.7835912704467773 +[2025-04-27 11:46:27,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.5223443508148193, cross_entropy: 2.5223443508148193 +[2025-04-27 11:46:29,909][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.6302905082702637, cross_entropy: 1.6302905082702637 +[2025-04-27 11:46:30,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 3.308851957321167, cross_entropy: 3.308851957321167 +[2025-04-27 11:46:32,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 3.043041467666626, cross_entropy: 3.043041467666626 +[2025-04-27 11:46:32,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.9615635871887207, cross_entropy: 1.9615635871887207 +[2025-04-27 11:46:35,199][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 1.4254751205444336, cross_entropy: 1.4254751205444336 +[2025-04-27 11:46:35,308][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 3.277308940887451, cross_entropy: 3.277308940887451 +[2025-04-27 11:46:37,259][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.6165099143981934, cross_entropy: 1.6165099143981934 +[2025-04-27 11:46:37,405][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 2.0918335914611816, cross_entropy: 2.0918335914611816 +[2025-04-27 11:46:40,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 3.4613232612609863, cross_entropy: 3.4613232612609863 +[2025-04-27 11:46:40,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.977447509765625, cross_entropy: 0.977447509765625 +[2025-04-27 11:46:42,716][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 1.691841959953308, cross_entropy: 1.691841959953308 +[2025-04-27 11:46:42,837][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 3.040435791015625, cross_entropy: 3.040435791015625 +[2025-04-27 11:46:44,979][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 1.4755887985229492, cross_entropy: 1.4755887985229492 +[2025-04-27 11:46:45,100][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 1.3479609489440918, cross_entropy: 1.3479609489440918 +[2025-04-27 11:46:47,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 2.4835398197174072, cross_entropy: 2.4835398197174072 +[2025-04-27 11:46:47,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.9069387912750244, cross_entropy: 2.9069387912750244 +[2025-04-27 11:46:49,862][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 3.350482940673828, cross_entropy: 3.350482940673828 +[2025-04-27 11:46:49,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.3686230182647705, cross_entropy: 1.3686230182647705 +[2025-04-27 11:46:52,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 2.0596354007720947, cross_entropy: 2.0596354007720947 +[2025-04-27 11:46:52,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 3.3663928508758545, cross_entropy: 3.3663928508758545 +[2025-04-27 11:46:54,337][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.8605841398239136, cross_entropy: 1.8605841398239136 +[2025-04-27 11:46:54,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.957900047302246, cross_entropy: 1.957900047302246 +[2025-04-27 11:46:56,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 3.464615821838379, cross_entropy: 3.464615821838379 +[2025-04-27 11:46:57,006][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 2.7075581550598145, cross_entropy: 2.7075581550598145 +[2025-04-27 11:46:58,797][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 1.6074450016021729, cross_entropy: 1.6074450016021729 +[2025-04-27 11:46:59,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.2880091667175293, cross_entropy: 3.2880091667175293 +[2025-04-27 11:47:01,170][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.682865858078003, cross_entropy: 1.682865858078003 +[2025-04-27 11:47:02,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.8227070569992065, cross_entropy: 1.8227070569992065 +[2025-04-27 11:47:03,855][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 1.8734407424926758, cross_entropy: 1.8734407424926758 +[2025-04-27 11:47:04,941][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.475368022918701, cross_entropy: 2.475368022918701 +[2025-04-27 11:47:06,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 1.746856689453125, cross_entropy: 1.746856689453125 +[2025-04-27 11:47:07,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 3.542747735977173, cross_entropy: 3.542747735977173 +[2025-04-27 11:47:08,691][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 3.5739083290100098, cross_entropy: 3.5739083290100098 +[2025-04-27 11:47:09,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.6636918783187866, cross_entropy: 1.6636918783187866 +[2025-04-27 11:47:11,268][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.3376059532165527, cross_entropy: 2.3376059532165527 +[2025-04-27 11:47:11,988][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 3.1775074005126953, cross_entropy: 3.1775074005126953 +[2025-04-27 11:47:13,542][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 2.4460220336914062, cross_entropy: 2.4460220336914062 +[2025-04-27 11:47:14,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 2.082357883453369, cross_entropy: 2.082357883453369 +[2025-04-27 11:47:15,619][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 3.796891689300537, cross_entropy: 3.796891689300537 +[2025-04-27 11:47:16,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 2.085606575012207, cross_entropy: 2.085606575012207 +[2025-04-27 11:47:17,999][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.924636960029602, cross_entropy: 1.924636960029602 +[2025-04-27 11:47:18,832][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.471206784248352, cross_entropy: 1.471206784248352 +[2025-04-27 11:47:19,988][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 1.5311408042907715, cross_entropy: 1.5311408042907715 +[2025-04-27 11:47:20,988][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 3.4793031215667725, cross_entropy: 3.4793031215667725 +[2025-04-27 11:47:22,161][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 2.0503313541412354, cross_entropy: 2.0503313541412354 +[2025-04-27 11:47:23,623][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 3.3148350715637207, cross_entropy: 3.3148350715637207 +[2025-04-27 11:47:24,530][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 3.1714277267456055, cross_entropy: 3.1714277267456055 +[2025-04-27 11:47:25,718][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.7594993114471436, cross_entropy: 2.7594993114471436 +[2025-04-27 11:47:26,672][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.4997875690460205, cross_entropy: 2.4997875690460205 +[2025-04-27 11:47:27,601][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.9893910884857178, cross_entropy: 1.9893910884857178 +[2025-04-27 11:47:28,493][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 1.3620789051055908, cross_entropy: 1.3620789051055908 +[2025-04-27 11:47:29,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 2.1448092460632324, cross_entropy: 2.1448092460632324 +[2025-04-27 11:47:30,338][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 3.11409330368042, cross_entropy: 3.11409330368042 +[2025-04-27 11:47:32,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 1.639634132385254, cross_entropy: 1.639634132385254 +[2025-04-27 11:47:32,274][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.7436017990112305, cross_entropy: 2.7436017990112305 +[2025-04-27 11:47:34,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 1.6092790365219116, cross_entropy: 1.6092790365219116 +[2025-04-27 11:47:34,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 2.566246271133423, cross_entropy: 2.566246271133423 +[2025-04-27 11:47:35,989][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 1.3336013555526733, cross_entropy: 1.3336013555526733 +[2025-04-27 11:47:37,456][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 2.6860580444335938, cross_entropy: 2.6860580444335938 +[2025-04-27 11:47:38,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 2.0612614154815674, cross_entropy: 2.0612614154815674 +[2025-04-27 11:47:39,675][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 3.4461655616760254, cross_entropy: 3.4461655616760254 +[2025-04-27 11:47:41,095][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 3.2885069847106934, cross_entropy: 3.2885069847106934 +[2025-04-27 11:47:41,852][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 3.0369527339935303, cross_entropy: 3.0369527339935303 +[2025-04-27 11:47:43,290][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 1.3001437187194824, cross_entropy: 1.3001437187194824 +[2025-04-27 11:47:45,226][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.8734161853790283, cross_entropy: 2.8734161853790283 +[2025-04-27 11:47:45,410][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 2.415778398513794, cross_entropy: 2.415778398513794 +[2025-04-27 11:47:47,622][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 1.6781980991363525, cross_entropy: 1.6781980991363525 +[2025-04-27 11:47:47,747][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 3.15057373046875, cross_entropy: 3.15057373046875 +[2025-04-27 11:47:50,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.3773186206817627, cross_entropy: 1.3773186206817627 +[2025-04-27 11:47:50,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 3.1565511226654053, cross_entropy: 3.1565511226654053 +[2025-04-27 11:47:52,784][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.6069296598434448, cross_entropy: 1.6069296598434448 +[2025-04-27 11:47:52,890][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.9804247617721558, cross_entropy: 1.9804247617721558 +[2025-04-27 11:47:55,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 2.1145052909851074, cross_entropy: 2.1145052909851074 +[2025-04-27 11:47:55,430][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 3.433720588684082, cross_entropy: 3.433720588684082 +[2025-04-27 11:47:58,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.8875913619995117, cross_entropy: 1.8875913619995117 +[2025-04-27 11:47:58,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.6691970825195312, cross_entropy: 1.6691970825195312 +[2025-04-27 11:47:59,779][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 3.1128945350646973, cross_entropy: 3.1128945350646973 +[2025-04-27 11:47:59,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 3.089531421661377, cross_entropy: 3.089531421661377 +[2025-04-27 11:48:01,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 1.9197494983673096, cross_entropy: 1.9197494983673096 +[2025-04-27 11:48:02,355][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.8699144124984741, cross_entropy: 1.8699144124984741 +[2025-04-27 11:48:04,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.380563259124756, cross_entropy: 2.380563259124756 +[2025-04-27 11:48:04,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.7018173933029175, cross_entropy: 1.7018173933029175 +[2025-04-27 11:48:07,129][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 2.8230676651000977, cross_entropy: 2.8230676651000977 +[2025-04-27 11:48:07,250][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 1.6199103593826294, cross_entropy: 1.6199103593826294 +[2025-04-27 11:48:10,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.3485922813415527, cross_entropy: 2.3485922813415527 +[2025-04-27 11:48:10,137][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 3.5967493057250977, cross_entropy: 3.5967493057250977 +[2025-04-27 11:48:12,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 1.6588244438171387, cross_entropy: 1.6588244438171387 +[2025-04-27 11:48:12,758][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 1.9745947122573853, cross_entropy: 1.9745947122573853 +[2025-04-27 11:48:14,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 3.2438302040100098, cross_entropy: 3.2438302040100098 +[2025-04-27 11:48:15,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 1.779632329940796, cross_entropy: 1.779632329940796 +[2025-04-27 11:48:17,873][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.455045461654663, cross_entropy: 1.455045461654663 +[2025-04-27 11:48:17,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.025496482849121, cross_entropy: 2.025496482849121 +[2025-04-27 11:48:20,630][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 2.2786197662353516, cross_entropy: 2.2786197662353516 +[2025-04-27 11:48:20,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 2.135209083557129, cross_entropy: 2.135209083557129 +[2025-04-27 11:48:22,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 3.075310707092285, cross_entropy: 3.075310707092285 +[2025-04-27 11:48:22,407][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 1.3488097190856934, cross_entropy: 1.3488097190856934 +[2025-04-27 11:48:24,607][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 2.323188066482544, cross_entropy: 2.323188066482544 +[2025-04-27 11:48:24,738][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.6449979543685913, cross_entropy: 1.6449979543685913 +[2025-04-27 11:48:27,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.673017978668213, cross_entropy: 2.673017978668213 +[2025-04-27 11:48:27,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.776716709136963, cross_entropy: 2.776716709136963 +[2025-04-27 11:48:29,734][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.7924885749816895, cross_entropy: 2.7924885749816895 +[2025-04-27 11:48:29,839][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.5398869514465332, cross_entropy: 1.5398869514465332 +[2025-04-27 11:48:31,974][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 3.756592035293579, cross_entropy: 3.756592035293579 +[2025-04-27 11:48:32,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 3.1287143230438232, cross_entropy: 3.1287143230438232 +[2025-04-27 11:48:34,098][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 2.002680778503418, cross_entropy: 2.002680778503418 +[2025-04-27 11:48:34,203][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 3.5132155418395996, cross_entropy: 3.5132155418395996 +[2025-04-27 11:48:36,337][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.3447273969650269, cross_entropy: 1.3447273969650269 +[2025-04-27 11:48:36,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.9119009971618652, cross_entropy: 2.9119009971618652 +[2025-04-27 11:48:38,345][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 2.6773972511291504, cross_entropy: 2.6773972511291504 +[2025-04-27 11:48:38,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 2.1487956047058105, cross_entropy: 2.1487956047058105 +[2025-04-27 11:48:40,469][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 2.330550193786621, cross_entropy: 2.330550193786621 +[2025-04-27 11:48:40,593][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 1.6373651027679443, cross_entropy: 1.6373651027679443 +[2025-04-27 11:48:43,015][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.4668781757354736, cross_entropy: 2.4668781757354736 +[2025-04-27 11:48:43,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.9961307048797607, cross_entropy: 1.9961307048797607 +[2025-04-27 11:48:45,242][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.4646730422973633, cross_entropy: 2.4646730422973633 +[2025-04-27 11:48:45,361][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.755791187286377, cross_entropy: 1.755791187286377 +[2025-04-27 11:48:47,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 3.0782761573791504, cross_entropy: 3.0782761573791504 +[2025-04-27 11:48:47,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 2.3736190795898438, cross_entropy: 2.3736190795898438 +[2025-04-27 11:48:49,298][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 2.9535651206970215, cross_entropy: 2.9535651206970215 +[2025-04-27 11:48:49,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 1.723029613494873, cross_entropy: 1.723029613494873 +[2025-04-27 11:48:51,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 3.1781768798828125, cross_entropy: 3.1781768798828125 +[2025-04-27 11:48:51,582][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 2.0781116485595703, cross_entropy: 2.0781116485595703 +[2025-04-27 11:48:54,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.7057305574417114, cross_entropy: 1.7057305574417114 +[2025-04-27 11:48:54,978][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.4644737243652344, cross_entropy: 1.4644737243652344 +[2025-04-27 11:48:57,416][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 3.2823843955993652, cross_entropy: 3.2823843955993652 +[2025-04-27 11:48:57,539][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 2.884709596633911, cross_entropy: 2.884709596633911 +[2025-04-27 11:48:59,695][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.6444025039672852, cross_entropy: 1.6444025039672852 +[2025-04-27 11:48:59,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 1.5772358179092407, cross_entropy: 1.5772358179092407 +[2025-04-27 11:49:01,708][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 3.239100456237793, cross_entropy: 3.239100456237793 +[2025-04-27 11:49:01,833][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 2.7850160598754883, cross_entropy: 2.7850160598754883 +[2025-04-27 11:49:04,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 3.008239269256592, cross_entropy: 3.008239269256592 +[2025-04-27 11:49:04,579][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 2.084407091140747, cross_entropy: 2.084407091140747 +[2025-04-27 11:49:06,697][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.8043081760406494, cross_entropy: 2.8043081760406494 +[2025-04-27 11:49:06,818][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 3.1385498046875, cross_entropy: 3.1385498046875 +[2025-04-27 11:49:09,072][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 3.362358570098877, cross_entropy: 3.362358570098877 +[2025-04-27 11:49:09,177][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 3.4759373664855957, cross_entropy: 3.4759373664855957 +[2025-04-27 11:49:11,698][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 2.439736843109131, cross_entropy: 2.439736843109131 +[2025-04-27 11:49:11,803][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 1.7469308376312256, cross_entropy: 1.7469308376312256 +[2025-04-27 11:49:14,515][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 1.4907399415969849, cross_entropy: 1.4907399415969849 +[2025-04-27 11:49:14,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.942427635192871, cross_entropy: 2.942427635192871 +[2025-04-27 11:49:16,729][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.704525113105774, cross_entropy: 1.704525113105774 +[2025-04-27 11:49:16,860][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 3.034019947052002, cross_entropy: 3.034019947052002 +[2025-04-27 11:49:18,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 3.547091245651245, cross_entropy: 3.547091245651245 +[2025-04-27 11:49:18,829][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 3.0765342712402344, cross_entropy: 3.0765342712402344 +[2025-04-27 11:49:20,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.5962631702423096, cross_entropy: 1.5962631702423096 +[2025-04-27 11:49:20,993][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 1.307571291923523, cross_entropy: 1.307571291923523 +[2025-04-27 11:49:23,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 1.27543044090271, cross_entropy: 1.27543044090271 +[2025-04-27 11:49:23,432][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.8902201652526855, cross_entropy: 1.8902201652526855 +[2025-04-27 11:49:25,589][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.742269992828369, cross_entropy: 2.742269992828369 +[2025-04-27 11:49:25,712][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.93207585811615, cross_entropy: 1.93207585811615 +[2025-04-27 11:49:27,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 2.3011059761047363, cross_entropy: 2.3011059761047363 +[2025-04-27 11:49:27,910][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.5701457262039185, cross_entropy: 1.5701457262039185 +[2025-04-27 11:49:30,103][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 2.4922356605529785, cross_entropy: 2.4922356605529785 +[2025-04-27 11:49:30,225][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.9194546937942505, cross_entropy: 1.9194546937942505 +[2025-04-27 11:49:32,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 1.811436653137207, cross_entropy: 1.811436653137207 +[2025-04-27 11:49:32,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 1.7210266590118408, cross_entropy: 1.7210266590118408 +[2025-04-27 11:49:34,676][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.740701675415039, cross_entropy: 2.740701675415039 +[2025-04-27 11:49:34,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 3.378004550933838, cross_entropy: 3.378004550933838 +[2025-04-27 11:49:36,923][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 2.0265581607818604, cross_entropy: 2.0265581607818604 +[2025-04-27 11:49:37,047][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 3.47704815864563, cross_entropy: 3.47704815864563 +[2025-04-27 11:49:38,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 3.184343099594116, cross_entropy: 3.184343099594116 +[2025-04-27 11:49:39,037][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 2.2655105590820312, cross_entropy: 2.2655105590820312 +[2025-04-27 11:49:41,024][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 3.103099822998047, cross_entropy: 3.103099822998047 +[2025-04-27 11:49:41,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.789965271949768, cross_entropy: 1.789965271949768 +[2025-04-27 11:49:42,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 3.2535400390625, cross_entropy: 3.2535400390625 +[2025-04-27 11:49:43,223][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 1.8352458477020264, cross_entropy: 1.8352458477020264 +[2025-04-27 11:49:45,161][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.5716772079467773, cross_entropy: 2.5716772079467773 +[2025-04-27 11:49:45,985][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.782407522201538, cross_entropy: 1.782407522201538 +[2025-04-27 11:49:47,515][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.4056490659713745, cross_entropy: 1.4056490659713745 +[2025-04-27 11:49:48,244][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 2.0154166221618652, cross_entropy: 2.0154166221618652 +[2025-04-27 11:49:50,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.077969551086426, cross_entropy: 2.077969551086426 +[2025-04-27 11:49:51,127][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 2.6417152881622314, cross_entropy: 2.6417152881622314 +[2025-04-27 11:49:52,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 1.2592105865478516, cross_entropy: 1.2592105865478516 +[2025-04-27 11:49:53,513][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 1.3369836807250977, cross_entropy: 1.3369836807250977 +[2025-04-27 11:49:54,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.8455889225006104, cross_entropy: 1.8455889225006104 +[2025-04-27 11:49:55,843][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.6720802783966064, cross_entropy: 2.6720802783966064 +[2025-04-27 11:49:57,148][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 2.127378463745117, cross_entropy: 2.127378463745117 +[2025-04-27 11:49:57,971][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.9944801330566406, cross_entropy: 2.9944801330566406 +[2025-04-27 11:49:59,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 3.586787223815918, cross_entropy: 3.586787223815918 +[2025-04-27 11:50:00,408][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 3.206634998321533, cross_entropy: 3.206634998321533 +[2025-04-27 11:50:02,288][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 3.302452564239502, cross_entropy: 3.302452564239502 +[2025-04-27 11:50:02,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 3.4283485412597656, cross_entropy: 3.4283485412597656 +[2025-04-27 11:50:04,424][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 3.519371509552002, cross_entropy: 3.519371509552002 +[2025-04-27 11:50:04,936][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 2.273958683013916, cross_entropy: 2.273958683013916 +[2025-04-27 11:50:06,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 1.9775733947753906, cross_entropy: 1.9775733947753906 +[2025-04-27 11:50:07,782][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 3.472872734069824, cross_entropy: 3.472872734069824 +[2025-04-27 11:50:08,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 2.56430721282959, cross_entropy: 2.56430721282959 +[2025-04-27 11:50:10,628][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 1.6669679880142212, cross_entropy: 1.6669679880142212 +[2025-04-27 11:50:10,860][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.6014270782470703, cross_entropy: 2.6014270782470703 +[2025-04-27 11:50:12,935][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.8671743869781494, cross_entropy: 1.8671743869781494 +[2025-04-27 11:50:13,039][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 2.3563904762268066, cross_entropy: 2.3563904762268066 +[2025-04-27 11:50:14,762][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 2.289916753768921, cross_entropy: 2.289916753768921 +[2025-04-27 11:50:14,912][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 1.6442344188690186, cross_entropy: 1.6442344188690186 +[2025-04-27 11:50:16,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 2.2523882389068604, cross_entropy: 2.2523882389068604 +[2025-04-27 11:50:16,899][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 3.4878756999969482, cross_entropy: 3.4878756999969482 +[2025-04-27 11:50:19,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 2.340519428253174, cross_entropy: 2.340519428253174 +[2025-04-27 11:50:19,543][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 3.3308145999908447, cross_entropy: 3.3308145999908447 +[2025-04-27 11:50:21,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 2.0032291412353516, cross_entropy: 2.0032291412353516 +[2025-04-27 11:50:21,571][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 2.5026092529296875, cross_entropy: 2.5026092529296875 +[2025-04-27 11:50:23,704][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 3.5353341102600098, cross_entropy: 3.5353341102600098 +[2025-04-27 11:50:23,825][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.9495840072631836, cross_entropy: 2.9495840072631836 +[2025-04-27 11:50:25,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.8641774654388428, cross_entropy: 2.8641774654388428 +[2025-04-27 11:50:25,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 1.8074194192886353, cross_entropy: 1.8074194192886353 +[2025-04-27 11:50:27,931][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 1.6222987174987793, cross_entropy: 1.6222987174987793 +[2025-04-27 11:50:28,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 1.805472493171692, cross_entropy: 1.805472493171692 +[2025-04-27 11:50:29,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.5669667720794678, cross_entropy: 1.5669667720794678 +[2025-04-27 11:50:30,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 2.1277947425842285, cross_entropy: 2.1277947425842285 +[2025-04-27 11:50:32,278][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 3.380178451538086, cross_entropy: 3.380178451538086 +[2025-04-27 11:50:32,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 1.8018372058868408, cross_entropy: 1.8018372058868408 +[2025-04-27 11:50:34,937][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 3.065772771835327, cross_entropy: 3.065772771835327 +[2025-04-27 11:50:35,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.5726282596588135, cross_entropy: 1.5726282596588135 +[2025-04-27 11:50:37,418][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 3.339951753616333, cross_entropy: 3.339951753616333 +[2025-04-27 11:50:37,523][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 1.5389063358306885, cross_entropy: 1.5389063358306885 +[2025-04-27 11:50:39,742][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 3.4654722213745117, cross_entropy: 3.4654722213745117 +[2025-04-27 11:50:39,863][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 3.318593978881836, cross_entropy: 3.318593978881836 +[2025-04-27 11:50:41,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 3.2162442207336426, cross_entropy: 3.2162442207336426 +[2025-04-27 11:50:43,215][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 3.2207999229431152, cross_entropy: 3.2207999229431152 +[2025-04-27 11:50:44,505][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.7885513305664062, cross_entropy: 2.7885513305664062 +[2025-04-27 11:50:45,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 2.9214093685150146, cross_entropy: 2.9214093685150146 +[2025-04-27 11:50:46,424][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.538194179534912, cross_entropy: 2.538194179534912 +[2025-04-27 11:50:48,194][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 2.433210849761963, cross_entropy: 2.433210849761963 +[2025-04-27 11:50:48,522][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 3.085453510284424, cross_entropy: 3.085453510284424 +[2025-04-27 11:50:50,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.2335337400436401, cross_entropy: 1.2335337400436401 +[2025-04-27 11:50:52,059][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.686887264251709, cross_entropy: 2.686887264251709 +[2025-04-27 11:50:52,569][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.6072633266448975, cross_entropy: 1.6072633266448975 +[2025-04-27 11:50:54,335][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.4739503860473633, cross_entropy: 1.4739503860473633 +[2025-04-27 11:50:54,982][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.0800631046295166, cross_entropy: 2.0800631046295166 +[2025-04-27 11:50:56,593][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 2.1130170822143555, cross_entropy: 2.1130170822143555 +[2025-04-27 11:50:57,100][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 3.1954245567321777, cross_entropy: 3.1954245567321777 +[2025-04-27 11:50:58,729][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.6274900436401367, cross_entropy: 1.6274900436401367 +[2025-04-27 11:50:59,056][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 2.7537693977355957, cross_entropy: 2.7537693977355957 +[2025-04-27 11:51:01,026][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 2.0669727325439453, cross_entropy: 2.0669727325439453 +[2025-04-27 11:51:01,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 3.632093906402588, cross_entropy: 3.632093906402588 +[2025-04-27 11:51:04,485][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.2318994998931885, cross_entropy: 2.2318994998931885 +[2025-04-27 11:51:04,698][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.4617764949798584, cross_entropy: 1.4617764949798584 +[2025-04-27 11:51:06,512][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 3.4753665924072266, cross_entropy: 3.4753665924072266 +[2025-04-27 11:51:06,991][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 1.798948049545288, cross_entropy: 1.798948049545288 +[2025-04-27 11:51:08,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 3.5409584045410156, cross_entropy: 3.5409584045410156 +[2025-04-27 11:51:08,824][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 1.2027997970581055, cross_entropy: 1.2027997970581055 +[2025-04-27 11:51:10,158][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.4824891090393066, cross_entropy: 2.4824891090393066 +[2025-04-27 11:51:11,208][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 3.542574405670166, cross_entropy: 3.542574405670166 +[2025-04-27 11:51:11,988][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 1.533869743347168, cross_entropy: 1.533869743347168 +[2025-04-27 11:51:13,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 1.6434086561203003, cross_entropy: 1.6434086561203003 +[2025-04-27 11:51:13,970][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.7387163639068604, cross_entropy: 2.7387163639068604 +[2025-04-27 11:51:16,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 3.0791702270507812, cross_entropy: 3.0791702270507812 +[2025-04-27 11:51:16,675][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.8179854154586792, cross_entropy: 1.8179854154586792 +[2025-04-27 11:51:18,896][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.422511339187622, cross_entropy: 1.422511339187622 +[2025-04-27 11:51:19,018][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.582254409790039, cross_entropy: 2.582254409790039 +[2025-04-27 11:51:20,942][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 1.8098347187042236, cross_entropy: 1.8098347187042236 +[2025-04-27 11:51:21,059][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.7790355682373047, cross_entropy: 1.7790355682373047 +[2025-04-27 11:51:23,197][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 2.5940651893615723, cross_entropy: 2.5940651893615723 +[2025-04-27 11:51:23,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 3.104166030883789, cross_entropy: 3.104166030883789 +[2025-04-27 11:51:26,014][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 3.2376456260681152, cross_entropy: 3.2376456260681152 +[2025-04-27 11:51:26,119][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.519775390625, cross_entropy: 2.519775390625 +[2025-04-27 11:51:28,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 2.0586719512939453, cross_entropy: 2.0586719512939453 +[2025-04-27 11:51:28,609][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 2.1741554737091064, cross_entropy: 2.1741554737091064 +[2025-04-27 11:51:30,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 2.8650400638580322, cross_entropy: 2.8650400638580322 +[2025-04-27 11:51:30,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.8542360067367554, cross_entropy: 1.8542360067367554 +[2025-04-27 11:51:33,106][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 1.6559183597564697, cross_entropy: 1.6559183597564697 +[2025-04-27 11:51:33,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 2.275271415710449, cross_entropy: 2.275271415710449 +[2025-04-27 11:51:35,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 1.8678995370864868, cross_entropy: 1.8678995370864868 +[2025-04-27 11:51:35,689][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 1.3994576930999756, cross_entropy: 1.3994576930999756 +[2025-04-27 11:51:37,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.8592567443847656, cross_entropy: 2.8592567443847656 +[2025-04-27 11:51:38,100][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 1.580008864402771, cross_entropy: 1.580008864402771 +[2025-04-27 11:51:40,370][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 2.048766851425171, cross_entropy: 2.048766851425171 +[2025-04-27 11:51:40,490][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 2.024888038635254, cross_entropy: 2.024888038635254 +[2025-04-27 11:51:42,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 3.1252734661102295, cross_entropy: 3.1252734661102295 +[2025-04-27 11:51:42,674][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 3.173668384552002, cross_entropy: 3.173668384552002 +[2025-04-27 11:51:44,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 1.8670496940612793, cross_entropy: 1.8670496940612793 +[2025-04-27 11:51:44,910][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.684671401977539, cross_entropy: 2.684671401977539 +[2025-04-27 11:51:47,031][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 2.0942702293395996, cross_entropy: 2.0942702293395996 +[2025-04-27 11:51:47,159][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.7803008556365967, cross_entropy: 2.7803008556365967 +[2025-04-27 11:51:49,578][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 3.108375072479248, cross_entropy: 3.108375072479248 +[2025-04-27 11:51:49,688][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.5874496698379517, cross_entropy: 1.5874496698379517 +[2025-04-27 11:51:51,667][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.6459892988204956, cross_entropy: 1.6459892988204956 +[2025-04-27 11:51:51,788][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.4074592590332031, cross_entropy: 1.4074592590332031 +[2025-04-27 11:51:55,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 3.58294677734375, cross_entropy: 3.58294677734375 +[2025-04-27 11:51:55,695][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 1.9604469537734985, cross_entropy: 1.9604469537734985 +[2025-04-27 11:51:57,815][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.6853389739990234, cross_entropy: 2.6853389739990234 +[2025-04-27 11:51:57,938][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 3.178528308868408, cross_entropy: 3.178528308868408 +[2025-04-27 11:52:01,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.936269760131836, cross_entropy: 2.936269760131836 +[2025-04-27 11:52:01,168][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 3.2046236991882324, cross_entropy: 3.2046236991882324 +[2025-04-27 11:52:03,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 1.5950369834899902, cross_entropy: 1.5950369834899902 +[2025-04-27 11:52:03,418][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.322266101837158, cross_entropy: 2.322266101837158 +[2025-04-27 11:52:05,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 3.1576991081237793, cross_entropy: 3.1576991081237793 +[2025-04-27 11:52:05,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.6788403987884521, cross_entropy: 1.6788403987884521 +[2025-04-27 11:52:08,834][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 3.341830253601074, cross_entropy: 3.341830253601074 +[2025-04-27 11:52:08,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.9729766845703125, cross_entropy: 1.9729766845703125 +[2025-04-27 11:52:11,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 2.1238515377044678, cross_entropy: 2.1238515377044678 +[2025-04-27 11:52:11,361][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 3.393430233001709, cross_entropy: 3.393430233001709 +[2025-04-27 11:52:13,361][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.5734632015228271, cross_entropy: 1.5734632015228271 +[2025-04-27 11:52:13,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 3.462254524230957, cross_entropy: 3.462254524230957 +[2025-04-27 11:52:15,879][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 2.697721242904663, cross_entropy: 2.697721242904663 +[2025-04-27 11:52:16,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 1.6055034399032593, cross_entropy: 1.6055034399032593 +[2025-04-27 11:52:18,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 3.6050283908843994, cross_entropy: 3.6050283908843994 +[2025-04-27 11:52:18,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.6361117362976074, cross_entropy: 2.6361117362976074 +[2025-04-27 11:52:20,690][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.9667648077011108, cross_entropy: 1.9667648077011108 +[2025-04-27 11:52:20,814][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 1.7492660284042358, cross_entropy: 1.7492660284042358 +[2025-04-27 11:52:23,254][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 1.9280822277069092, cross_entropy: 1.9280822277069092 +[2025-04-27 11:52:23,360][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 2.140889883041382, cross_entropy: 2.140889883041382 +[2025-04-27 11:52:25,525][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 2.6468429565429688, cross_entropy: 2.6468429565429688 +[2025-04-27 11:52:25,646][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 1.308427333831787, cross_entropy: 1.308427333831787 +[2025-04-27 11:52:27,795][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.882524847984314, cross_entropy: 1.882524847984314 +[2025-04-27 11:52:27,901][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.5371748208999634, cross_entropy: 1.5371748208999634 +[2025-04-27 11:52:29,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.7186541557312012, cross_entropy: 1.7186541557312012 +[2025-04-27 11:52:29,716][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.7719502449035645, cross_entropy: 1.7719502449035645 +[2025-04-27 11:52:31,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.7370604276657104, cross_entropy: 1.7370604276657104 +[2025-04-27 11:52:31,645][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 2.2442963123321533, cross_entropy: 2.2442963123321533 +[2025-04-27 11:52:33,281][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 1.6424856185913086, cross_entropy: 1.6424856185913086 +[2025-04-27 11:52:33,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 1.8868600130081177, cross_entropy: 1.8868600130081177 +[2025-04-27 11:52:35,416][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 2.8168697357177734, cross_entropy: 2.8168697357177734 +[2025-04-27 11:52:35,913][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.9456889629364014, cross_entropy: 1.9456889629364014 +[2025-04-27 11:52:37,551][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 1.9888627529144287, cross_entropy: 1.9888627529144287 +[2025-04-27 11:52:38,153][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.5184736251831055, cross_entropy: 1.5184736251831055 +[2025-04-27 11:52:40,682][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 1.3726953268051147, cross_entropy: 1.3726953268051147 +[2025-04-27 11:52:40,805][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 3.127509593963623, cross_entropy: 3.127509593963623 +[2025-04-27 11:52:43,177][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 3.278362989425659, cross_entropy: 3.278362989425659 +[2025-04-27 11:52:43,301][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 2.358858585357666, cross_entropy: 2.358858585357666 +[2025-04-27 11:52:45,668][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.3909268379211426, cross_entropy: 2.3909268379211426 +[2025-04-27 11:52:45,793][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 1.457831859588623, cross_entropy: 1.457831859588623 +[2025-04-27 11:52:47,767][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.4886106252670288, cross_entropy: 1.4886106252670288 +[2025-04-27 11:52:47,890][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 2.347384452819824, cross_entropy: 2.347384452819824 +[2025-04-27 11:52:50,991][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 2.5372071266174316, cross_entropy: 2.5372071266174316 +[2025-04-27 11:52:51,113][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 3.181396961212158, cross_entropy: 3.181396961212158 +[2025-04-27 11:52:53,240][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 2.5365970134735107, cross_entropy: 2.5365970134735107 +[2025-04-27 11:52:53,345][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 2.157942771911621, cross_entropy: 2.157942771911621 +[2025-04-27 11:52:55,728][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 2.766719341278076, cross_entropy: 2.766719341278076 +[2025-04-27 11:52:55,832][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.7343565225601196, cross_entropy: 1.7343565225601196 +[2025-04-27 11:52:58,073][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 2.638197183609009, cross_entropy: 2.638197183609009 +[2025-04-27 11:52:58,198][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.7333555221557617, cross_entropy: 1.7333555221557617 +[2025-04-27 11:53:00,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 2.3398804664611816, cross_entropy: 2.3398804664611816 +[2025-04-27 11:53:01,019][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.7215209007263184, cross_entropy: 1.7215209007263184 +[2025-04-27 11:53:03,656][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 2.081840991973877, cross_entropy: 2.081840991973877 +[2025-04-27 11:53:03,762][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 1.562058448791504, cross_entropy: 1.562058448791504 +[2025-04-27 11:53:06,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 1.65622079372406, cross_entropy: 1.65622079372406 +[2025-04-27 11:53:06,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 2.014732599258423, cross_entropy: 2.014732599258423 +[2025-04-27 11:53:08,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.8705487251281738, cross_entropy: 1.8705487251281738 +[2025-04-27 11:53:08,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 3.8431615829467773, cross_entropy: 3.8431615829467773 +[2025-04-27 11:53:10,093][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.857853889465332, cross_entropy: 1.857853889465332 +[2025-04-27 11:53:10,214][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 3.114358425140381, cross_entropy: 3.114358425140381 +[2025-04-27 11:53:12,226][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 3.3638906478881836, cross_entropy: 3.3638906478881836 +[2025-04-27 11:53:12,347][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 2.3824498653411865, cross_entropy: 2.3824498653411865 +[2025-04-27 11:53:14,316][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 2.066981792449951, cross_entropy: 2.066981792449951 +[2025-04-27 11:53:14,439][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 3.060789108276367, cross_entropy: 3.060789108276367 +[2025-04-27 11:53:16,454][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 3.4382448196411133, cross_entropy: 3.4382448196411133 +[2025-04-27 11:53:16,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.6686968803405762, cross_entropy: 1.6686968803405762 +[2025-04-27 11:53:18,419][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 1.0419921875, cross_entropy: 1.0419921875 +[2025-04-27 11:53:18,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 2.4758310317993164, cross_entropy: 2.4758310317993164 +[2025-04-27 11:53:20,859][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 2.298584461212158, cross_entropy: 2.298584461212158 +[2025-04-27 11:53:20,989][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 3.3452413082122803, cross_entropy: 3.3452413082122803 +[2025-04-27 11:53:22,997][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 1.64120614528656, cross_entropy: 1.64120614528656 +[2025-04-27 11:53:23,106][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 3.542720317840576, cross_entropy: 3.542720317840576 +[2025-04-27 11:53:24,927][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 3.2183523178100586, cross_entropy: 3.2183523178100586 +[2025-04-27 11:53:25,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 1.4087316989898682, cross_entropy: 1.4087316989898682 +[2025-04-27 11:55:18,214][BaseTrainer][INFO] - [Epoch 8/10] (train) 2.3647844791412354, cross_entropy: 2.3647844791412354 +[2025-04-27 11:55:18,214][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.8098539113998413, cross_entropy: 1.8098539113998413 +[2025-04-27 11:55:18,441][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/best_epoch.pth. +[2025-04-27 11:55:18,604][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch8.pth. +[2025-04-27 11:55:18,814][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 11:55:22,109][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 2.1274237632751465, cross_entropy: 2.1274237632751465 +[2025-04-27 11:55:22,611][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.9185090065002441, cross_entropy: 1.9185090065002441 +[2025-04-27 11:55:24,820][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 3.356630325317383, cross_entropy: 3.356630325317383 +[2025-04-27 11:55:24,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 3.5599005222320557, cross_entropy: 3.5599005222320557 +[2025-04-27 11:55:27,174][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 3.153576374053955, cross_entropy: 3.153576374053955 +[2025-04-27 11:55:27,301][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.1106312274932861, cross_entropy: 1.1106312274932861 +[2025-04-27 11:55:29,474][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.646040916442871, cross_entropy: 2.646040916442871 +[2025-04-27 11:55:29,600][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.873668670654297, cross_entropy: 2.873668670654297 +[2025-04-27 11:55:31,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.761120319366455, cross_entropy: 2.761120319366455 +[2025-04-27 11:55:31,962][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 3.4226064682006836, cross_entropy: 3.4226064682006836 +[2025-04-27 11:55:34,351][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.8119843006134033, cross_entropy: 1.8119843006134033 +[2025-04-27 11:55:35,311][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 1.5107581615447998, cross_entropy: 1.5107581615447998 +[2025-04-27 11:55:37,013][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 3.276141881942749, cross_entropy: 3.276141881942749 +[2025-04-27 11:55:37,418][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 1.513811707496643, cross_entropy: 1.513811707496643 +[2025-04-27 11:55:39,811][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 3.0589797496795654, cross_entropy: 3.0589797496795654 +[2025-04-27 11:55:39,938][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 1.7219129800796509, cross_entropy: 1.7219129800796509 +[2025-04-27 11:55:42,294][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 1.331041693687439, cross_entropy: 1.331041693687439 +[2025-04-27 11:55:42,418][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.3223763704299927, cross_entropy: 1.3223763704299927 +[2025-04-27 11:55:44,125][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.5661814212799072, cross_entropy: 1.5661814212799072 +[2025-04-27 11:55:45,016][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.7579667568206787, cross_entropy: 1.7579667568206787 +[2025-04-27 11:55:47,074][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.7922260761260986, cross_entropy: 1.7922260761260986 +[2025-04-27 11:55:47,200][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 2.0757157802581787, cross_entropy: 2.0757157802581787 +[2025-04-27 11:55:49,801][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.721501111984253, cross_entropy: 2.721501111984253 +[2025-04-27 11:55:49,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.8166253566741943, cross_entropy: 2.8166253566741943 +[2025-04-27 11:55:52,572][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 3.268423318862915, cross_entropy: 3.268423318862915 +[2025-04-27 11:55:52,697][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 2.287480354309082, cross_entropy: 2.287480354309082 +[2025-04-27 11:55:54,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 2.1402649879455566, cross_entropy: 2.1402649879455566 +[2025-04-27 11:55:54,781][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.6070711612701416, cross_entropy: 2.6070711612701416 +[2025-04-27 11:55:56,921][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.7515077590942383, cross_entropy: 2.7515077590942383 +[2025-04-27 11:55:57,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.816192865371704, cross_entropy: 1.816192865371704 +[2025-04-27 11:55:59,562][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 3.4182608127593994, cross_entropy: 3.4182608127593994 +[2025-04-27 11:55:59,685][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 2.2108540534973145, cross_entropy: 2.2108540534973145 +[2025-04-27 11:56:01,980][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 2.1966392993927, cross_entropy: 2.1966392993927 +[2025-04-27 11:56:02,104][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.979811429977417, cross_entropy: 2.979811429977417 +[2025-04-27 11:56:04,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 3.2465438842773438, cross_entropy: 3.2465438842773438 +[2025-04-27 11:56:04,496][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 1.8588930368423462, cross_entropy: 1.8588930368423462 +[2025-04-27 11:56:06,939][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 1.6921004056930542, cross_entropy: 1.6921004056930542 +[2025-04-27 11:56:07,387][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 3.1446964740753174, cross_entropy: 3.1446964740753174 +[2025-04-27 11:56:09,225][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.64027738571167, cross_entropy: 1.64027738571167 +[2025-04-27 11:56:09,615][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 3.440931797027588, cross_entropy: 3.440931797027588 +[2025-04-27 11:56:11,950][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 3.266083240509033, cross_entropy: 3.266083240509033 +[2025-04-27 11:56:12,486][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 3.05975341796875, cross_entropy: 3.05975341796875 +[2025-04-27 11:56:14,421][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.8568005561828613, cross_entropy: 2.8568005561828613 +[2025-04-27 11:56:14,758][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 1.4232120513916016, cross_entropy: 1.4232120513916016 +[2025-04-27 11:56:16,539][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 1.5346301794052124, cross_entropy: 1.5346301794052124 +[2025-04-27 11:56:17,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 2.487086296081543, cross_entropy: 2.487086296081543 +[2025-04-27 11:56:19,492][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.484673500061035, cross_entropy: 3.484673500061035 +[2025-04-27 11:56:19,603][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 3.5894711017608643, cross_entropy: 3.5894711017608643 +[2025-04-27 11:56:21,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 3.295574426651001, cross_entropy: 3.295574426651001 +[2025-04-27 11:56:21,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 1.5090588331222534, cross_entropy: 1.5090588331222534 +[2025-04-27 11:56:24,596][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.8266499042510986, cross_entropy: 1.8266499042510986 +[2025-04-27 11:56:24,744][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.8236708641052246, cross_entropy: 1.8236708641052246 +[2025-04-27 11:56:26,756][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 1.281251072883606, cross_entropy: 1.281251072883606 +[2025-04-27 11:56:27,624][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 2.0585856437683105, cross_entropy: 2.0585856437683105 +[2025-04-27 11:56:28,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 2.0495715141296387, cross_entropy: 2.0495715141296387 +[2025-04-27 11:56:30,703][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 3.4278292655944824, cross_entropy: 3.4278292655944824 +[2025-04-27 11:56:30,828][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.3908634185791016, cross_entropy: 1.3908634185791016 +[2025-04-27 11:56:33,040][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 1.7283803224563599, cross_entropy: 1.7283803224563599 +[2025-04-27 11:56:33,275][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 2.1589207649230957, cross_entropy: 2.1589207649230957 +[2025-04-27 11:56:35,429][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 3.270437240600586, cross_entropy: 3.270437240600586 +[2025-04-27 11:56:35,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.4120826721191406, cross_entropy: 2.4120826721191406 +[2025-04-27 11:56:37,786][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.9482784271240234, cross_entropy: 2.9482784271240234 +[2025-04-27 11:56:38,209][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 1.6553232669830322, cross_entropy: 1.6553232669830322 +[2025-04-27 11:56:39,985][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 2.011849880218506, cross_entropy: 2.011849880218506 +[2025-04-27 11:56:40,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 3.4552440643310547, cross_entropy: 3.4552440643310547 +[2025-04-27 11:56:42,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 1.8651299476623535, cross_entropy: 1.8651299476623535 +[2025-04-27 11:56:43,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 1.192226767539978, cross_entropy: 1.192226767539978 +[2025-04-27 11:56:46,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 1.5112605094909668, cross_entropy: 1.5112605094909668 +[2025-04-27 11:56:46,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 1.490967869758606, cross_entropy: 1.490967869758606 +[2025-04-27 11:56:48,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.7271106243133545, cross_entropy: 1.7271106243133545 +[2025-04-27 11:56:49,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 1.6561998128890991, cross_entropy: 1.6561998128890991 +[2025-04-27 11:56:50,366][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.6548185348510742, cross_entropy: 1.6548185348510742 +[2025-04-27 11:56:51,742][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.6104118824005127, cross_entropy: 1.6104118824005127 +[2025-04-27 11:56:52,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 1.3990278244018555, cross_entropy: 1.3990278244018555 +[2025-04-27 11:56:54,324][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.944634437561035, cross_entropy: 2.944634437561035 +[2025-04-27 11:56:54,451][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 3.2369401454925537, cross_entropy: 3.2369401454925537 +[2025-04-27 11:56:56,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 3.289567232131958, cross_entropy: 3.289567232131958 +[2025-04-27 11:56:56,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 1.4450284242630005, cross_entropy: 1.4450284242630005 +[2025-04-27 11:56:58,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 3.069549560546875, cross_entropy: 3.069549560546875 +[2025-04-27 11:56:59,195][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 1.3001725673675537, cross_entropy: 1.3001725673675537 +[2025-04-27 11:57:00,922][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 2.578317642211914, cross_entropy: 2.578317642211914 +[2025-04-27 11:57:02,060][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 1.6306746006011963, cross_entropy: 1.6306746006011963 +[2025-04-27 11:57:03,592][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.6900248527526855, cross_entropy: 1.6900248527526855 +[2025-04-27 11:57:06,172][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 3.108977794647217, cross_entropy: 3.108977794647217 +[2025-04-27 11:57:06,297][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.8465006351470947, cross_entropy: 1.8465006351470947 +[2025-04-27 11:57:08,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 2.0744285583496094, cross_entropy: 2.0744285583496094 +[2025-04-27 11:57:08,881][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.6895081996917725, cross_entropy: 2.6895081996917725 +[2025-04-27 11:57:11,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 2.252932548522949, cross_entropy: 2.252932548522949 +[2025-04-27 11:57:11,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 1.6808125972747803, cross_entropy: 1.6808125972747803 +[2025-04-27 11:57:13,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.7605624198913574, cross_entropy: 2.7605624198913574 +[2025-04-27 11:57:13,701][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 3.2835283279418945, cross_entropy: 3.2835283279418945 +[2025-04-27 11:57:16,410][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 2.2780590057373047, cross_entropy: 2.2780590057373047 +[2025-04-27 11:57:16,516][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 3.5001237392425537, cross_entropy: 3.5001237392425537 +[2025-04-27 11:57:18,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 1.9291828870773315, cross_entropy: 1.9291828870773315 +[2025-04-27 11:57:18,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.4190831184387207, cross_entropy: 2.4190831184387207 +[2025-04-27 11:57:21,465][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 2.050858736038208, cross_entropy: 2.050858736038208 +[2025-04-27 11:57:21,570][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 3.3438639640808105, cross_entropy: 3.3438639640808105 +[2025-04-27 11:57:24,606][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 2.295344352722168, cross_entropy: 2.295344352722168 +[2025-04-27 11:57:24,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 2.0719428062438965, cross_entropy: 2.0719428062438965 +[2025-04-27 11:57:27,226][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.9156999588012695, cross_entropy: 1.9156999588012695 +[2025-04-27 11:57:27,347][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 3.1777231693267822, cross_entropy: 3.1777231693267822 +[2025-04-27 11:57:29,042][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 3.022153377532959, cross_entropy: 3.022153377532959 +[2025-04-27 11:57:29,147][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 2.176604747772217, cross_entropy: 2.176604747772217 +[2025-04-27 11:57:31,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 3.2989554405212402, cross_entropy: 3.2989554405212402 +[2025-04-27 11:57:31,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 1.584578275680542, cross_entropy: 1.584578275680542 +[2025-04-27 11:57:33,159][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 3.312270402908325, cross_entropy: 3.312270402908325 +[2025-04-27 11:57:33,264][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 3.226435899734497, cross_entropy: 3.226435899734497 +[2025-04-27 11:57:35,356][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 1.3246686458587646, cross_entropy: 1.3246686458587646 +[2025-04-27 11:57:35,460][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 3.271294116973877, cross_entropy: 3.271294116973877 +[2025-04-27 11:57:38,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 1.4808366298675537, cross_entropy: 1.4808366298675537 +[2025-04-27 11:57:38,641][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 3.359421968460083, cross_entropy: 3.359421968460083 +[2025-04-27 11:57:40,475][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.9237141609191895, cross_entropy: 2.9237141609191895 +[2025-04-27 11:57:40,593][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.7202835083007812, cross_entropy: 2.7202835083007812 +[2025-04-27 11:57:42,728][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.9312283992767334, cross_entropy: 1.9312283992767334 +[2025-04-27 11:57:42,854][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 3.1879119873046875, cross_entropy: 3.1879119873046875 +[2025-04-27 11:57:44,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 1.607365369796753, cross_entropy: 1.607365369796753 +[2025-04-27 11:57:44,971][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 1.1251929998397827, cross_entropy: 1.1251929998397827 +[2025-04-27 11:57:47,002][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 2.3528342247009277, cross_entropy: 2.3528342247009277 +[2025-04-27 11:57:47,788][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 3.0041661262512207, cross_entropy: 3.0041661262512207 +[2025-04-27 11:57:49,536][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.392878293991089, cross_entropy: 2.392878293991089 +[2025-04-27 11:57:50,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.9833900928497314, cross_entropy: 2.9833900928497314 +[2025-04-27 11:57:51,818][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.5789546966552734, cross_entropy: 1.5789546966552734 +[2025-04-27 11:57:53,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.0621466636657715, cross_entropy: 2.0621466636657715 +[2025-04-27 11:57:54,464][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 3.0201802253723145, cross_entropy: 3.0201802253723145 +[2025-04-27 11:57:56,429][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.6308783292770386, cross_entropy: 1.6308783292770386 +[2025-04-27 11:57:56,701][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.808987021446228, cross_entropy: 1.808987021446228 +[2025-04-27 11:57:58,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 2.6970996856689453, cross_entropy: 2.6970996856689453 +[2025-04-27 11:57:58,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 2.0419254302978516, cross_entropy: 2.0419254302978516 +[2025-04-27 11:58:01,394][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 3.284710168838501, cross_entropy: 3.284710168838501 +[2025-04-27 11:58:01,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 1.652836561203003, cross_entropy: 1.652836561203003 +[2025-04-27 11:58:03,563][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 1.6061644554138184, cross_entropy: 1.6061644554138184 +[2025-04-27 11:58:03,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 3.109395980834961, cross_entropy: 3.109395980834961 +[2025-04-27 11:58:05,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.8877052068710327, cross_entropy: 1.8877052068710327 +[2025-04-27 11:58:05,841][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.9899141788482666, cross_entropy: 1.9899141788482666 +[2025-04-27 11:58:07,539][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 3.3447985649108887, cross_entropy: 3.3447985649108887 +[2025-04-27 11:58:07,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.9079216718673706, cross_entropy: 1.9079216718673706 +[2025-04-27 11:58:10,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.3540422916412354, cross_entropy: 2.3540422916412354 +[2025-04-27 11:58:10,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 1.7815303802490234, cross_entropy: 1.7815303802490234 +[2025-04-27 11:58:12,671][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.376471757888794, cross_entropy: 2.376471757888794 +[2025-04-27 11:58:12,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 3.1098875999450684, cross_entropy: 3.1098875999450684 +[2025-04-27 11:58:14,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.2438700199127197, cross_entropy: 2.2438700199127197 +[2025-04-27 11:58:14,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 3.168778896331787, cross_entropy: 3.168778896331787 +[2025-04-27 11:58:17,028][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.812480926513672, cross_entropy: 2.812480926513672 +[2025-04-27 11:58:17,134][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.9871344566345215, cross_entropy: 2.9871344566345215 +[2025-04-27 11:58:19,657][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 1.3083761930465698, cross_entropy: 1.3083761930465698 +[2025-04-27 11:58:19,782][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 3.088273048400879, cross_entropy: 3.088273048400879 +[2025-04-27 11:58:22,142][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 2.379084825515747, cross_entropy: 2.379084825515747 +[2025-04-27 11:58:22,248][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.8870720863342285, cross_entropy: 1.8870720863342285 +[2025-04-27 11:58:25,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 3.2279133796691895, cross_entropy: 3.2279133796691895 +[2025-04-27 11:58:25,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 1.1239385604858398, cross_entropy: 1.1239385604858398 +[2025-04-27 11:58:27,783][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 1.70230233669281, cross_entropy: 1.70230233669281 +[2025-04-27 11:58:27,891][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 1.5579859018325806, cross_entropy: 1.5579859018325806 +[2025-04-27 11:58:28,062][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/iteration3000.pth. +[2025-04-27 11:58:30,480][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 3.5133056640625, cross_entropy: 3.5133056640625 +[2025-04-27 11:58:30,603][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.3069076538085938, cross_entropy: 2.3069076538085938 +[2025-04-27 11:58:32,528][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 1.573060154914856, cross_entropy: 1.573060154914856 +[2025-04-27 11:58:32,651][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 1.8413480520248413, cross_entropy: 1.8413480520248413 +[2025-04-27 11:58:35,047][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 2.050635576248169, cross_entropy: 2.050635576248169 +[2025-04-27 11:58:35,183][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 1.8481652736663818, cross_entropy: 1.8481652736663818 +[2025-04-27 11:58:37,156][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 3.077714681625366, cross_entropy: 3.077714681625366 +[2025-04-27 11:58:37,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 1.567680835723877, cross_entropy: 1.567680835723877 +[2025-04-27 11:58:39,609][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 1.5957648754119873, cross_entropy: 1.5957648754119873 +[2025-04-27 11:58:39,732][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 1.22800874710083, cross_entropy: 1.22800874710083 +[2025-04-27 11:58:42,033][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 3.413118839263916, cross_entropy: 3.413118839263916 +[2025-04-27 11:58:42,137][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 1.713280200958252, cross_entropy: 1.713280200958252 +[2025-04-27 11:58:44,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 1.5976333618164062, cross_entropy: 1.5976333618164062 +[2025-04-27 11:58:44,356][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 1.5902612209320068, cross_entropy: 1.5902612209320068 +[2025-04-27 11:58:46,389][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.3087046146392822, cross_entropy: 1.3087046146392822 +[2025-04-27 11:58:46,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 3.232675790786743, cross_entropy: 3.232675790786743 +[2025-04-27 11:58:48,406][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 3.458620071411133, cross_entropy: 3.458620071411133 +[2025-04-27 11:58:48,529][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 1.489984393119812, cross_entropy: 1.489984393119812 +[2025-04-27 11:58:51,051][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 3.2622740268707275, cross_entropy: 3.2622740268707275 +[2025-04-27 11:58:51,168][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.661345362663269, cross_entropy: 1.661345362663269 +[2025-04-27 11:58:53,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 1.378251552581787, cross_entropy: 1.378251552581787 +[2025-04-27 11:58:53,571][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 3.1644301414489746, cross_entropy: 3.1644301414489746 +[2025-04-27 11:58:55,984][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.9013742208480835, cross_entropy: 1.9013742208480835 +[2025-04-27 11:58:56,103][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 3.055616617202759, cross_entropy: 3.055616617202759 +[2025-04-27 11:58:58,910][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 3.1394824981689453, cross_entropy: 3.1394824981689453 +[2025-04-27 11:58:59,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.5907453298568726, cross_entropy: 1.5907453298568726 +[2025-04-27 11:59:01,957][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.7266321182250977, cross_entropy: 1.7266321182250977 +[2025-04-27 11:59:02,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.846972942352295, cross_entropy: 2.846972942352295 +[2025-04-27 11:59:04,459][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.0961406230926514, cross_entropy: 2.0961406230926514 +[2025-04-27 11:59:04,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 3.2446446418762207, cross_entropy: 3.2446446418762207 +[2025-04-27 11:59:06,822][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.116127610206604, cross_entropy: 1.116127610206604 +[2025-04-27 11:59:06,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 2.5146820545196533, cross_entropy: 2.5146820545196533 +[2025-04-27 11:59:08,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 1.5639855861663818, cross_entropy: 1.5639855861663818 +[2025-04-27 11:59:09,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 3.041627883911133, cross_entropy: 3.041627883911133 +[2025-04-27 11:59:11,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.818352222442627, cross_entropy: 2.818352222442627 +[2025-04-27 11:59:11,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 3.2282209396362305, cross_entropy: 3.2282209396362305 +[2025-04-27 11:59:13,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.9459251165390015, cross_entropy: 1.9459251165390015 +[2025-04-27 11:59:13,664][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.7766656875610352, cross_entropy: 1.7766656875610352 +[2025-04-27 11:59:16,016][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 2.762233018875122, cross_entropy: 2.762233018875122 +[2025-04-27 11:59:16,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.9541864395141602, cross_entropy: 1.9541864395141602 +[2025-04-27 11:59:17,977][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.2934017181396484, cross_entropy: 2.2934017181396484 +[2025-04-27 11:59:18,082][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 2.877779722213745, cross_entropy: 2.877779722213745 +[2025-04-27 11:59:20,482][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 1.8249660730361938, cross_entropy: 1.8249660730361938 +[2025-04-27 11:59:20,605][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.4917516708374023, cross_entropy: 3.4917516708374023 +[2025-04-27 11:59:22,923][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 2.8569252490997314, cross_entropy: 2.8569252490997314 +[2025-04-27 11:59:23,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 2.3805575370788574, cross_entropy: 2.3805575370788574 +[2025-04-27 11:59:25,754][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 1.7093110084533691, cross_entropy: 1.7093110084533691 +[2025-04-27 11:59:25,878][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 2.0025835037231445, cross_entropy: 2.0025835037231445 +[2025-04-27 11:59:27,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 3.267460823059082, cross_entropy: 3.267460823059082 +[2025-04-27 11:59:27,759][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.3042433261871338, cross_entropy: 1.3042433261871338 +[2025-04-27 11:59:30,029][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 2.66574764251709, cross_entropy: 2.66574764251709 +[2025-04-27 11:59:30,159][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 3.7349588871002197, cross_entropy: 3.7349588871002197 +[2025-04-27 11:59:32,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.9645278453826904, cross_entropy: 1.9645278453826904 +[2025-04-27 11:59:32,175][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 1.6309187412261963, cross_entropy: 1.6309187412261963 +[2025-04-27 11:59:34,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 1.6682229042053223, cross_entropy: 1.6682229042053223 +[2025-04-27 11:59:34,747][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 2.36323881149292, cross_entropy: 2.36323881149292 +[2025-04-27 11:59:36,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 2.649756669998169, cross_entropy: 2.649756669998169 +[2025-04-27 11:59:36,944][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 3.446958065032959, cross_entropy: 3.446958065032959 +[2025-04-27 11:59:39,064][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 1.604691743850708, cross_entropy: 1.604691743850708 +[2025-04-27 11:59:39,189][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 1.698279857635498, cross_entropy: 1.698279857635498 +[2025-04-27 11:59:41,678][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 1.784356713294983, cross_entropy: 1.784356713294983 +[2025-04-27 11:59:41,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 1.7236664295196533, cross_entropy: 1.7236664295196533 +[2025-04-27 11:59:44,908][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.6166085004806519, cross_entropy: 1.6166085004806519 +[2025-04-27 11:59:45,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 2.6233105659484863, cross_entropy: 2.6233105659484863 +[2025-04-27 11:59:47,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 1.411238193511963, cross_entropy: 1.411238193511963 +[2025-04-27 11:59:47,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 1.8127537965774536, cross_entropy: 1.8127537965774536 +[2025-04-27 11:59:49,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 3.5431017875671387, cross_entropy: 3.5431017875671387 +[2025-04-27 11:59:49,383][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.152657985687256, cross_entropy: 2.152657985687256 +[2025-04-27 11:59:51,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.766105890274048, cross_entropy: 2.766105890274048 +[2025-04-27 11:59:51,683][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 2.6053824424743652, cross_entropy: 2.6053824424743652 +[2025-04-27 11:59:53,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.1870174407958984, cross_entropy: 2.1870174407958984 +[2025-04-27 11:59:53,574][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 1.3805015087127686, cross_entropy: 1.3805015087127686 +[2025-04-27 11:59:56,064][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 3.374321222305298, cross_entropy: 3.374321222305298 +[2025-04-27 11:59:56,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 2.4527502059936523, cross_entropy: 2.4527502059936523 +[2025-04-27 11:59:58,289][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 3.066239356994629, cross_entropy: 3.066239356994629 +[2025-04-27 11:59:58,414][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 3.474748134613037, cross_entropy: 3.474748134613037 +[2025-04-27 12:00:00,332][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.6710726022720337, cross_entropy: 1.6710726022720337 +[2025-04-27 12:00:00,455][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 3.2870097160339355, cross_entropy: 3.2870097160339355 +[2025-04-27 12:00:02,198][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 1.221930980682373, cross_entropy: 1.221930980682373 +[2025-04-27 12:00:02,324][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 1.7398104667663574, cross_entropy: 1.7398104667663574 +[2025-04-27 12:00:04,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 2.9432950019836426, cross_entropy: 2.9432950019836426 +[2025-04-27 12:00:04,536][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 3.3413782119750977, cross_entropy: 3.3413782119750977 +[2025-04-27 12:00:06,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 3.3914527893066406, cross_entropy: 3.3914527893066406 +[2025-04-27 12:00:07,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 3.399287223815918, cross_entropy: 3.399287223815918 +[2025-04-27 12:00:09,074][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 2.036921262741089, cross_entropy: 2.036921262741089 +[2025-04-27 12:00:09,247][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.958481550216675, cross_entropy: 2.958481550216675 +[2025-04-27 12:00:12,215][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 3.3607711791992188, cross_entropy: 3.3607711791992188 +[2025-04-27 12:00:12,339][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 3.3137834072113037, cross_entropy: 3.3137834072113037 +[2025-04-27 12:00:14,644][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.963058590888977, cross_entropy: 1.963058590888977 +[2025-04-27 12:00:14,777][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 2.5642547607421875, cross_entropy: 2.5642547607421875 +[2025-04-27 12:00:16,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 3.2534267902374268, cross_entropy: 3.2534267902374268 +[2025-04-27 12:00:17,098][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 2.3817217350006104, cross_entropy: 2.3817217350006104 +[2025-04-27 12:00:19,348][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.414564609527588, cross_entropy: 2.414564609527588 +[2025-04-27 12:00:19,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 1.4561582803726196, cross_entropy: 1.4561582803726196 +[2025-04-27 12:00:21,660][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 3.1564340591430664, cross_entropy: 3.1564340591430664 +[2025-04-27 12:00:21,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 2.0651979446411133, cross_entropy: 2.0651979446411133 +[2025-04-27 12:00:23,656][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.5559971332550049, cross_entropy: 1.5559971332550049 +[2025-04-27 12:00:24,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 3.3472399711608887, cross_entropy: 3.3472399711608887 +[2025-04-27 12:00:26,693][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 3.032701015472412, cross_entropy: 3.032701015472412 +[2025-04-27 12:00:26,963][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.857891082763672, cross_entropy: 2.857891082763672 +[2025-04-27 12:00:29,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.714451551437378, cross_entropy: 1.714451551437378 +[2025-04-27 12:00:29,698][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.0192947387695312, cross_entropy: 2.0192947387695312 +[2025-04-27 12:00:31,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 1.226597785949707, cross_entropy: 1.226597785949707 +[2025-04-27 12:00:32,184][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 1.3964495658874512, cross_entropy: 1.3964495658874512 +[2025-04-27 12:00:33,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 2.916767120361328, cross_entropy: 2.916767120361328 +[2025-04-27 12:00:34,633][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.9813792705535889, cross_entropy: 1.9813792705535889 +[2025-04-27 12:00:36,352][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 1.6482301950454712, cross_entropy: 1.6482301950454712 +[2025-04-27 12:00:37,310][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 3.307663917541504, cross_entropy: 3.307663917541504 +[2025-04-27 12:00:39,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 1.866949200630188, cross_entropy: 1.866949200630188 +[2025-04-27 12:00:39,843][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 0.9637676477432251, cross_entropy: 0.9637676477432251 +[2025-04-27 12:00:41,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 1.9599120616912842, cross_entropy: 1.9599120616912842 +[2025-04-27 12:00:41,977][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 1.9110859632492065, cross_entropy: 1.9110859632492065 +[2025-04-27 12:00:44,113][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.4603729248046875, cross_entropy: 1.4603729248046875 +[2025-04-27 12:00:44,647][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 1.4696881771087646, cross_entropy: 1.4696881771087646 +[2025-04-27 12:00:46,367][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.897847294807434, cross_entropy: 1.897847294807434 +[2025-04-27 12:00:47,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.4945127964019775, cross_entropy: 2.4945127964019775 +[2025-04-27 12:00:48,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.413494825363159, cross_entropy: 2.413494825363159 +[2025-04-27 12:00:49,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 3.336728811264038, cross_entropy: 3.336728811264038 +[2025-04-27 12:00:51,211][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 1.2810393571853638, cross_entropy: 1.2810393571853638 +[2025-04-27 12:00:52,349][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 3.7231369018554688, cross_entropy: 3.7231369018554688 +[2025-04-27 12:00:53,794][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.0503664016723633, cross_entropy: 2.0503664016723633 +[2025-04-27 12:00:54,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 1.2887152433395386, cross_entropy: 1.2887152433395386 +[2025-04-27 12:00:56,327][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.239938735961914, cross_entropy: 2.239938735961914 +[2025-04-27 12:00:57,095][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 1.4163992404937744, cross_entropy: 1.4163992404937744 +[2025-04-27 12:00:58,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.9795576333999634, cross_entropy: 1.9795576333999634 +[2025-04-27 12:01:00,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.779466152191162, cross_entropy: 1.779466152191162 +[2025-04-27 12:01:01,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.6151251792907715, cross_entropy: 2.6151251792907715 +[2025-04-27 12:01:02,935][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.8933305740356445, cross_entropy: 1.8933305740356445 +[2025-04-27 12:01:03,616][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.3085373640060425, cross_entropy: 1.3085373640060425 +[2025-04-27 12:01:05,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 1.8171672821044922, cross_entropy: 1.8171672821044922 +[2025-04-27 12:01:05,741][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 1.7475244998931885, cross_entropy: 1.7475244998931885 +[2025-04-27 12:01:07,881][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 3.296104907989502, cross_entropy: 3.296104907989502 +[2025-04-27 12:01:08,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 3.077394962310791, cross_entropy: 3.077394962310791 +[2025-04-27 12:01:10,444][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.735417366027832, cross_entropy: 1.735417366027832 +[2025-04-27 12:01:10,552][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 3.154223680496216, cross_entropy: 3.154223680496216 +[2025-04-27 12:01:12,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 1.5001940727233887, cross_entropy: 1.5001940727233887 +[2025-04-27 12:01:13,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 2.6188275814056396, cross_entropy: 2.6188275814056396 +[2025-04-27 12:01:15,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.2671841382980347, cross_entropy: 1.2671841382980347 +[2025-04-27 12:01:15,419][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 3.4161744117736816, cross_entropy: 3.4161744117736816 +[2025-04-27 12:01:17,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.4077608585357666, cross_entropy: 1.4077608585357666 +[2025-04-27 12:01:18,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.8202860355377197, cross_entropy: 1.8202860355377197 +[2025-04-27 12:01:20,065][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 1.7623062133789062, cross_entropy: 1.7623062133789062 +[2025-04-27 12:01:20,187][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 1.6856744289398193, cross_entropy: 1.6856744289398193 +[2025-04-27 12:01:22,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.1179941892623901, cross_entropy: 1.1179941892623901 +[2025-04-27 12:01:22,568][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.9711978435516357, cross_entropy: 1.9711978435516357 +[2025-04-27 12:01:24,598][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 3.0549490451812744, cross_entropy: 3.0549490451812744 +[2025-04-27 12:01:24,721][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 3.105526924133301, cross_entropy: 3.105526924133301 +[2025-04-27 12:01:28,079][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 2.80470871925354, cross_entropy: 2.80470871925354 +[2025-04-27 12:01:28,203][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.470571279525757, cross_entropy: 2.470571279525757 +[2025-04-27 12:01:31,157][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 3.3358042240142822, cross_entropy: 3.3358042240142822 +[2025-04-27 12:01:31,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 1.4889183044433594, cross_entropy: 1.4889183044433594 +[2025-04-27 12:01:34,207][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 3.3588531017303467, cross_entropy: 3.3588531017303467 +[2025-04-27 12:01:34,313][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 3.0424604415893555, cross_entropy: 3.0424604415893555 +[2025-04-27 12:01:36,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 3.255342960357666, cross_entropy: 3.255342960357666 +[2025-04-27 12:01:36,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 1.4748992919921875, cross_entropy: 1.4748992919921875 +[2025-04-27 12:01:38,723][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 1.895148515701294, cross_entropy: 1.895148515701294 +[2025-04-27 12:01:38,843][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 1.922109603881836, cross_entropy: 1.922109603881836 +[2025-04-27 12:01:41,344][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 3.6799473762512207, cross_entropy: 3.6799473762512207 +[2025-04-27 12:01:41,450][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 1.999499797821045, cross_entropy: 1.999499797821045 +[2025-04-27 12:01:43,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 3.571509838104248, cross_entropy: 3.571509838104248 +[2025-04-27 12:01:43,563][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 2.342759370803833, cross_entropy: 2.342759370803833 +[2025-04-27 12:01:45,457][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.963196873664856, cross_entropy: 1.963196873664856 +[2025-04-27 12:01:45,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.8758366107940674, cross_entropy: 1.8758366107940674 +[2025-04-27 12:01:47,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.0832154750823975, cross_entropy: 2.0832154750823975 +[2025-04-27 12:01:47,744][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 1.6278287172317505, cross_entropy: 1.6278287172317505 +[2025-04-27 12:01:50,762][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 1.6642457246780396, cross_entropy: 1.6642457246780396 +[2025-04-27 12:01:50,891][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.0242233276367188, cross_entropy: 2.0242233276367188 +[2025-04-27 12:01:53,653][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 2.9341671466827393, cross_entropy: 2.9341671466827393 +[2025-04-27 12:01:53,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.4190503358840942, cross_entropy: 1.4190503358840942 +[2025-04-27 12:01:56,009][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 2.9725453853607178, cross_entropy: 2.9725453853607178 +[2025-04-27 12:01:56,132][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 1.2726202011108398, cross_entropy: 1.2726202011108398 +[2025-04-27 12:01:58,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 1.6962171792984009, cross_entropy: 1.6962171792984009 +[2025-04-27 12:01:58,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 1.8720695972442627, cross_entropy: 1.8720695972442627 +[2025-04-27 12:02:00,371][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 1.6795645952224731, cross_entropy: 1.6795645952224731 +[2025-04-27 12:02:00,494][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 1.695385456085205, cross_entropy: 1.695385456085205 +[2025-04-27 12:02:02,728][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.9561011791229248, cross_entropy: 1.9561011791229248 +[2025-04-27 12:02:02,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 3.4496583938598633, cross_entropy: 3.4496583938598633 +[2025-04-27 12:02:05,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 2.2851386070251465, cross_entropy: 2.2851386070251465 +[2025-04-27 12:02:05,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 1.726941704750061, cross_entropy: 1.726941704750061 +[2025-04-27 12:02:07,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 1.956697702407837, cross_entropy: 1.956697702407837 +[2025-04-27 12:02:08,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 1.9019535779953003, cross_entropy: 1.9019535779953003 +[2025-04-27 12:02:10,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 2.092054843902588, cross_entropy: 2.092054843902588 +[2025-04-27 12:02:10,658][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 1.7312544584274292, cross_entropy: 1.7312544584274292 +[2025-04-27 12:02:12,542][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 3.0092058181762695, cross_entropy: 3.0092058181762695 +[2025-04-27 12:02:12,665][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.496764063835144, cross_entropy: 1.496764063835144 +[2025-04-27 12:02:14,906][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.9928555488586426, cross_entropy: 2.9928555488586426 +[2025-04-27 12:02:15,070][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 2.5572900772094727, cross_entropy: 2.5572900772094727 +[2025-04-27 12:02:17,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 2.6730992794036865, cross_entropy: 2.6730992794036865 +[2025-04-27 12:02:17,748][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 3.5167369842529297, cross_entropy: 3.5167369842529297 +[2025-04-27 12:02:20,720][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 1.9992057085037231, cross_entropy: 1.9992057085037231 +[2025-04-27 12:02:20,841][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 2.8523097038269043, cross_entropy: 2.8523097038269043 +[2025-04-27 12:02:23,433][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 2.049273729324341, cross_entropy: 2.049273729324341 +[2025-04-27 12:02:23,555][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 1.4457871913909912, cross_entropy: 1.4457871913909912 +[2025-04-27 12:02:25,932][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.4984664916992188, cross_entropy: 2.4984664916992188 +[2025-04-27 12:02:26,058][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.492659091949463, cross_entropy: 1.492659091949463 +[2025-04-27 12:02:28,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.307295322418213, cross_entropy: 2.307295322418213 +[2025-04-27 12:02:28,425][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 2.0336437225341797, cross_entropy: 2.0336437225341797 +[2025-04-27 12:02:30,570][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.924335241317749, cross_entropy: 2.924335241317749 +[2025-04-27 12:02:30,674][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.7858245372772217, cross_entropy: 2.7858245372772217 +[2025-04-27 12:02:33,366][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 2.996203660964966, cross_entropy: 2.996203660964966 +[2025-04-27 12:02:33,470][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 2.375148296356201, cross_entropy: 2.375148296356201 +[2025-04-27 12:02:35,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 1.3809188604354858, cross_entropy: 1.3809188604354858 +[2025-04-27 12:02:35,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 1.5599936246871948, cross_entropy: 1.5599936246871948 +[2025-04-27 12:02:37,682][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 1.9872080087661743, cross_entropy: 1.9872080087661743 +[2025-04-27 12:04:34,349][BaseTrainer][INFO] - [Epoch 9/10] (train) 2.3084208965301514, cross_entropy: 2.3084208965301514 +[2025-04-27 12:04:34,349][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.8180829286575317, cross_entropy: 1.8180829286575317 +[2025-04-27 12:04:34,515][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch9.pth. +[2025-04-27 12:04:34,763][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. +[2025-04-27 12:04:37,444][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.835964322090149, cross_entropy: 1.835964322090149 +[2025-04-27 12:04:37,733][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 2.2213308811187744, cross_entropy: 2.2213308811187744 +[2025-04-27 12:04:39,464][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 1.0320169925689697, cross_entropy: 1.0320169925689697 +[2025-04-27 12:04:41,784][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 3.2631735801696777, cross_entropy: 3.2631735801696777 +[2025-04-27 12:04:41,907][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.8111491203308105, cross_entropy: 2.8111491203308105 +[2025-04-27 12:04:44,036][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 2.2675743103027344, cross_entropy: 2.2675743103027344 +[2025-04-27 12:04:44,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 3.2289342880249023, cross_entropy: 3.2289342880249023 +[2025-04-27 12:04:46,716][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 1.9219691753387451, cross_entropy: 1.9219691753387451 +[2025-04-27 12:04:46,841][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.9118762016296387, cross_entropy: 2.9118762016296387 +[2025-04-27 12:04:49,239][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.8538556098937988, cross_entropy: 1.8538556098937988 +[2025-04-27 12:04:49,363][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.779637575149536, cross_entropy: 2.779637575149536 +[2025-04-27 12:04:51,937][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 2.879521369934082, cross_entropy: 2.879521369934082 +[2025-04-27 12:04:52,062][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.7960951328277588, cross_entropy: 1.7960951328277588 +[2025-04-27 12:04:54,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 2.786618709564209, cross_entropy: 2.786618709564209 +[2025-04-27 12:04:54,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 3.196125030517578, cross_entropy: 3.196125030517578 +[2025-04-27 12:04:56,008][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 1.7921791076660156, cross_entropy: 1.7921791076660156 +[2025-04-27 12:04:56,635][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 1.7821779251098633, cross_entropy: 1.7821779251098633 +[2025-04-27 12:04:58,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.726034641265869, cross_entropy: 2.726034641265869 +[2025-04-27 12:04:59,478][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.0495033264160156, cross_entropy: 2.0495033264160156 +[2025-04-27 12:05:00,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.2951757907867432, cross_entropy: 1.2951757907867432 +[2025-04-27 12:05:01,659][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 2.216376304626465, cross_entropy: 2.216376304626465 +[2025-04-27 12:05:03,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 3.5910444259643555, cross_entropy: 3.5910444259643555 +[2025-04-27 12:05:04,918][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 1.235403299331665, cross_entropy: 1.235403299331665 +[2025-04-27 12:05:05,755][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 1.763834834098816, cross_entropy: 1.763834834098816 +[2025-04-27 12:05:07,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.684636116027832, cross_entropy: 2.684636116027832 +[2025-04-27 12:05:07,960][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 3.079814910888672, cross_entropy: 3.079814910888672 +[2025-04-27 12:05:10,511][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 1.8378424644470215, cross_entropy: 1.8378424644470215 +[2025-04-27 12:05:10,633][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.5861873626708984, cross_entropy: 2.5861873626708984 +[2025-04-27 12:05:12,782][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 3.27547550201416, cross_entropy: 3.27547550201416 +[2025-04-27 12:05:12,887][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.7904568910598755, cross_entropy: 1.7904568910598755 +[2025-04-27 12:05:15,724][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.8380088806152344, cross_entropy: 2.8380088806152344 +[2025-04-27 12:05:15,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 1.2831482887268066, cross_entropy: 1.2831482887268066 +[2025-04-27 12:05:18,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 1.2102357149124146, cross_entropy: 1.2102357149124146 +[2025-04-27 12:05:18,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.6621947288513184, cross_entropy: 2.6621947288513184 +[2025-04-27 12:05:20,909][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.6523268222808838, cross_entropy: 1.6523268222808838 +[2025-04-27 12:05:21,036][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.9840977191925049, cross_entropy: 1.9840977191925049 +[2025-04-27 12:05:23,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.879220485687256, cross_entropy: 2.879220485687256 +[2025-04-27 12:05:23,335][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 1.3192670345306396, cross_entropy: 1.3192670345306396 +[2025-04-27 12:05:26,195][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 2.9438953399658203, cross_entropy: 2.9438953399658203 +[2025-04-27 12:05:26,319][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 1.6422486305236816, cross_entropy: 1.6422486305236816 +[2025-04-27 12:05:28,471][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 2.4171924591064453, cross_entropy: 2.4171924591064453 +[2025-04-27 12:05:28,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.5999748706817627, cross_entropy: 2.5999748706817627 +[2025-04-27 12:05:30,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 1.3996548652648926, cross_entropy: 1.3996548652648926 +[2025-04-27 12:05:30,744][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 3.096933364868164, cross_entropy: 3.096933364868164 +[2025-04-27 12:05:33,872][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.697533369064331, cross_entropy: 1.697533369064331 +[2025-04-27 12:05:33,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 3.1744751930236816, cross_entropy: 3.1744751930236816 +[2025-04-27 12:05:36,459][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 2.4314427375793457, cross_entropy: 2.4314427375793457 +[2025-04-27 12:05:36,584][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 3.047694206237793, cross_entropy: 3.047694206237793 +[2025-04-27 12:05:38,284][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.8029325008392334, cross_entropy: 1.8029325008392334 +[2025-04-27 12:05:38,410][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 3.323413372039795, cross_entropy: 3.323413372039795 +[2025-04-27 12:05:40,272][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.6903843879699707, cross_entropy: 2.6903843879699707 +[2025-04-27 12:05:40,376][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 2.4604763984680176, cross_entropy: 2.4604763984680176 +[2025-04-27 12:05:42,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.8308775424957275, cross_entropy: 1.8308775424957275 +[2025-04-27 12:05:42,307][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 1.2564839124679565, cross_entropy: 1.2564839124679565 +[2025-04-27 12:05:44,678][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.6253647804260254, cross_entropy: 1.6253647804260254 +[2025-04-27 12:05:44,815][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 1.9442545175552368, cross_entropy: 1.9442545175552368 +[2025-04-27 12:05:47,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.4218084812164307, cross_entropy: 1.4218084812164307 +[2025-04-27 12:05:47,296][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 2.0667672157287598, cross_entropy: 2.0667672157287598 +[2025-04-27 12:05:50,065][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 2.6175942420959473, cross_entropy: 2.6175942420959473 +[2025-04-27 12:05:50,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 1.5584626197814941, cross_entropy: 1.5584626197814941 +[2025-04-27 12:05:52,637][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 2.7106409072875977, cross_entropy: 2.7106409072875977 +[2025-04-27 12:05:53,301][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.2342499494552612, cross_entropy: 1.2342499494552612 +[2025-04-27 12:05:55,777][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 2.8889174461364746, cross_entropy: 2.8889174461364746 +[2025-04-27 12:05:56,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 3.4401681423187256, cross_entropy: 3.4401681423187256 +[2025-04-27 12:05:58,342][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 2.6114072799682617, cross_entropy: 2.6114072799682617 +[2025-04-27 12:05:58,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 3.2852087020874023, cross_entropy: 3.2852087020874023 +[2025-04-27 12:06:00,542][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 3.529503345489502, cross_entropy: 3.529503345489502 +[2025-04-27 12:06:00,758][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 1.2658272981643677, cross_entropy: 1.2658272981643677 +[2025-04-27 12:06:03,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 1.5153383016586304, cross_entropy: 1.5153383016586304 +[2025-04-27 12:06:03,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 1.7542515993118286, cross_entropy: 1.7542515993118286 +[2025-04-27 12:06:06,678][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 1.603718876838684, cross_entropy: 1.603718876838684 +[2025-04-27 12:06:06,800][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 3.365464687347412, cross_entropy: 3.365464687347412 +[2025-04-27 12:06:08,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.6174802780151367, cross_entropy: 1.6174802780151367 +[2025-04-27 12:06:08,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 3.3456759452819824, cross_entropy: 3.3456759452819824 +[2025-04-27 12:06:10,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 1.5903260707855225, cross_entropy: 1.5903260707855225 +[2025-04-27 12:06:10,925][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 3.1677846908569336, cross_entropy: 3.1677846908569336 +[2025-04-27 12:06:13,896][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.7384830713272095, cross_entropy: 1.7384830713272095 +[2025-04-27 12:06:14,002][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.8915629386901855, cross_entropy: 1.8915629386901855 +[2025-04-27 12:06:16,625][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.4503810405731201, cross_entropy: 1.4503810405731201 +[2025-04-27 12:06:16,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 2.863069772720337, cross_entropy: 2.863069772720337 +[2025-04-27 12:06:18,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 2.2777504920959473, cross_entropy: 2.2777504920959473 +[2025-04-27 12:06:18,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 1.5221316814422607, cross_entropy: 1.5221316814422607 +[2025-04-27 12:06:21,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 3.233449935913086, cross_entropy: 3.233449935913086 +[2025-04-27 12:06:21,501][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 3.0828325748443604, cross_entropy: 3.0828325748443604 +[2025-04-27 12:06:23,597][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 1.9400575160980225, cross_entropy: 1.9400575160980225 +[2025-04-27 12:06:23,722][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 2.2459654808044434, cross_entropy: 2.2459654808044434 +[2025-04-27 12:06:25,855][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 3.3485569953918457, cross_entropy: 3.3485569953918457 +[2025-04-27 12:06:25,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 1.6897375583648682, cross_entropy: 1.6897375583648682 +[2025-04-27 12:06:28,009][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 3.3263862133026123, cross_entropy: 3.3263862133026123 +[2025-04-27 12:06:28,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.5599313974380493, cross_entropy: 1.5599313974380493 +[2025-04-27 12:06:30,423][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.5895271301269531, cross_entropy: 1.5895271301269531 +[2025-04-27 12:06:30,529][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.2859594821929932, cross_entropy: 1.2859594821929932 +[2025-04-27 12:06:32,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.475724935531616, cross_entropy: 2.475724935531616 +[2025-04-27 12:06:33,092][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 1.7444939613342285, cross_entropy: 1.7444939613342285 +[2025-04-27 12:06:34,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.3426213264465332, cross_entropy: 1.3426213264465332 +[2025-04-27 12:06:35,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 2.0213491916656494, cross_entropy: 2.0213491916656494 +[2025-04-27 12:06:36,474][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 3.1238088607788086, cross_entropy: 3.1238088607788086 +[2025-04-27 12:06:37,888][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 3.5278432369232178, cross_entropy: 3.5278432369232178 +[2025-04-27 12:06:38,318][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.5641642808914185, cross_entropy: 1.5641642808914185 +[2025-04-27 12:06:39,957][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 1.576358437538147, cross_entropy: 1.576358437538147 +[2025-04-27 12:06:40,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 1.5107213258743286, cross_entropy: 1.5107213258743286 +[2025-04-27 12:06:41,970][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 2.122844934463501, cross_entropy: 2.122844934463501 +[2025-04-27 12:06:42,748][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 1.8684041500091553, cross_entropy: 1.8684041500091553 +[2025-04-27 12:06:44,625][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.4137685298919678, cross_entropy: 2.4137685298919678 +[2025-04-27 12:06:45,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 3.1190080642700195, cross_entropy: 3.1190080642700195 +[2025-04-27 12:06:46,671][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 1.458280086517334, cross_entropy: 1.458280086517334 +[2025-04-27 12:06:47,758][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.6879242658615112, cross_entropy: 1.6879242658615112 +[2025-04-27 12:06:48,614][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 2.4202675819396973, cross_entropy: 2.4202675819396973 +[2025-04-27 12:06:49,785][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 3.116680145263672, cross_entropy: 3.116680145263672 +[2025-04-27 12:06:50,808][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 3.025498390197754, cross_entropy: 3.025498390197754 +[2025-04-27 12:06:51,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 3.199812889099121, cross_entropy: 3.199812889099121 +[2025-04-27 12:06:54,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.7663171291351318, cross_entropy: 1.7663171291351318 +[2025-04-27 12:06:54,569][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 1.2714109420776367, cross_entropy: 1.2714109420776367 +[2025-04-27 12:06:56,483][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 1.6903841495513916, cross_entropy: 1.6903841495513916 +[2025-04-27 12:06:56,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.476238250732422, cross_entropy: 2.476238250732422 +[2025-04-27 12:06:58,300][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.0815391540527344, cross_entropy: 2.0815391540527344 +[2025-04-27 12:06:59,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 2.003246307373047, cross_entropy: 2.003246307373047 +[2025-04-27 12:07:01,394][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 1.499528408050537, cross_entropy: 1.499528408050537 +[2025-04-27 12:07:01,514][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.2256958484649658, cross_entropy: 1.2256958484649658 +[2025-04-27 12:07:03,409][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.139815092086792, cross_entropy: 2.139815092086792 +[2025-04-27 12:07:03,594][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 2.0728230476379395, cross_entropy: 2.0728230476379395 +[2025-04-27 12:07:05,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.793508529663086, cross_entropy: 1.793508529663086 +[2025-04-27 12:07:05,747][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.5433592796325684, cross_entropy: 1.5433592796325684 +[2025-04-27 12:07:08,207][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.4319660663604736, cross_entropy: 2.4319660663604736 +[2025-04-27 12:07:08,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 2.5269365310668945, cross_entropy: 2.5269365310668945 +[2025-04-27 12:07:10,888][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 3.078247547149658, cross_entropy: 3.078247547149658 +[2025-04-27 12:07:11,009][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 2.936396598815918, cross_entropy: 2.936396598815918 +[2025-04-27 12:07:13,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 3.2677485942840576, cross_entropy: 3.2677485942840576 +[2025-04-27 12:07:13,260][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 3.291691303253174, cross_entropy: 3.291691303253174 +[2025-04-27 12:07:15,706][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 2.7406890392303467, cross_entropy: 2.7406890392303467 +[2025-04-27 12:07:15,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.443655014038086, cross_entropy: 2.443655014038086 +[2025-04-27 12:07:17,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 1.6380209922790527, cross_entropy: 1.6380209922790527 +[2025-04-27 12:07:18,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 2.086261749267578, cross_entropy: 2.086261749267578 +[2025-04-27 12:07:20,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 1.3522440195083618, cross_entropy: 1.3522440195083618 +[2025-04-27 12:07:20,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 1.6217286586761475, cross_entropy: 1.6217286586761475 +[2025-04-27 12:07:22,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.5626296997070312, cross_entropy: 1.5626296997070312 +[2025-04-27 12:07:23,090][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 3.1881232261657715, cross_entropy: 3.1881232261657715 +[2025-04-27 12:07:25,345][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 2.9439382553100586, cross_entropy: 2.9439382553100586 +[2025-04-27 12:07:25,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 3.0840048789978027, cross_entropy: 3.0840048789978027 +[2025-04-27 12:07:28,200][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.397525429725647, cross_entropy: 1.397525429725647 +[2025-04-27 12:07:28,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.7831501960754395, cross_entropy: 2.7831501960754395 +[2025-04-27 12:07:31,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.734506130218506, cross_entropy: 2.734506130218506 +[2025-04-27 12:07:31,995][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 3.376026153564453, cross_entropy: 3.376026153564453 +[2025-04-27 12:07:34,299][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 3.225754499435425, cross_entropy: 3.225754499435425 +[2025-04-27 12:07:34,403][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.8229031562805176, cross_entropy: 2.8229031562805176 +[2025-04-27 12:07:37,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 1.2406647205352783, cross_entropy: 1.2406647205352783 +[2025-04-27 12:07:37,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 1.533888339996338, cross_entropy: 1.533888339996338 +[2025-04-27 12:07:39,958][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 2.289926052093506, cross_entropy: 2.289926052093506 +[2025-04-27 12:07:40,062][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.5804908275604248, cross_entropy: 1.5804908275604248 +[2025-04-27 12:07:42,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 3.016953229904175, cross_entropy: 3.016953229904175 +[2025-04-27 12:07:42,325][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.518827438354492, cross_entropy: 2.518827438354492 +[2025-04-27 12:07:44,110][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.8833255767822266, cross_entropy: 2.8833255767822266 +[2025-04-27 12:07:44,239][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 1.3766837120056152, cross_entropy: 1.3766837120056152 +[2025-04-27 12:07:46,296][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 1.6548259258270264, cross_entropy: 1.6548259258270264 +[2025-04-27 12:07:46,420][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 1.5609217882156372, cross_entropy: 1.5609217882156372 +[2025-04-27 12:07:48,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 1.080711007118225, cross_entropy: 1.080711007118225 +[2025-04-27 12:07:48,618][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.4617482423782349, cross_entropy: 1.4617482423782349 +[2025-04-27 12:07:50,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.973724842071533, cross_entropy: 2.973724842071533 +[2025-04-27 12:07:50,650][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 2.1181674003601074, cross_entropy: 2.1181674003601074 +[2025-04-27 12:07:52,971][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.7696282863616943, cross_entropy: 2.7696282863616943 +[2025-04-27 12:07:53,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 1.5708363056182861, cross_entropy: 1.5708363056182861 +[2025-04-27 12:07:55,271][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 3.3655314445495605, cross_entropy: 3.3655314445495605 +[2025-04-27 12:07:55,375][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 3.413947820663452, cross_entropy: 3.413947820663452 +[2025-04-27 12:07:57,734][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.90682315826416, cross_entropy: 2.90682315826416 +[2025-04-27 12:07:57,859][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 1.6260948181152344, cross_entropy: 1.6260948181152344 +[2025-04-27 12:08:00,853][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.772242307662964, cross_entropy: 2.772242307662964 +[2025-04-27 12:08:00,980][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 3.290914297103882, cross_entropy: 3.290914297103882 +[2025-04-27 12:08:03,535][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 2.978231430053711, cross_entropy: 2.978231430053711 +[2025-04-27 12:08:03,659][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.8300657272338867, cross_entropy: 2.8300657272338867 +[2025-04-27 12:08:07,224][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 1.3809195756912231, cross_entropy: 1.3809195756912231 +[2025-04-27 12:08:07,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 3.115894079208374, cross_entropy: 3.115894079208374 +[2025-04-27 12:08:09,344][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 2.6407413482666016, cross_entropy: 2.6407413482666016 +[2025-04-27 12:08:09,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 2.0103793144226074, cross_entropy: 2.0103793144226074 +[2025-04-27 12:08:11,611][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 1.502678394317627, cross_entropy: 1.502678394317627 +[2025-04-27 12:08:11,741][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.5894436836242676, cross_entropy: 1.5894436836242676 +[2025-04-27 12:08:14,213][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.1279045343399048, cross_entropy: 1.1279045343399048 +[2025-04-27 12:08:14,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 3.1988744735717773, cross_entropy: 3.1988744735717773 +[2025-04-27 12:08:16,523][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 1.745969533920288, cross_entropy: 1.745969533920288 +[2025-04-27 12:08:16,627][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.4858267307281494, cross_entropy: 1.4858267307281494 +[2025-04-27 12:08:19,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 3.1670918464660645, cross_entropy: 3.1670918464660645 +[2025-04-27 12:08:19,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 1.6100196838378906, cross_entropy: 1.6100196838378906 +[2025-04-27 12:08:21,609][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 2.850860595703125, cross_entropy: 2.850860595703125 +[2025-04-27 12:08:21,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.6594287157058716, cross_entropy: 1.6594287157058716 +[2025-04-27 12:08:23,555][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 1.558606505393982, cross_entropy: 1.558606505393982 +[2025-04-27 12:08:23,677][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.3014707565307617, cross_entropy: 1.3014707565307617 +[2025-04-27 12:08:25,886][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.6656718254089355, cross_entropy: 1.6656718254089355 +[2025-04-27 12:08:26,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.413083076477051, cross_entropy: 2.413083076477051 +[2025-04-27 12:08:29,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 3.1286234855651855, cross_entropy: 3.1286234855651855 +[2025-04-27 12:08:29,276][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 3.6231019496917725, cross_entropy: 3.6231019496917725 +[2025-04-27 12:08:31,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 2.367729902267456, cross_entropy: 2.367729902267456 +[2025-04-27 12:08:31,978][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 3.3203983306884766, cross_entropy: 3.3203983306884766 +[2025-04-27 12:08:34,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 1.4744758605957031, cross_entropy: 1.4744758605957031 +[2025-04-27 12:08:34,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.379734754562378, cross_entropy: 1.379734754562378 +[2025-04-27 12:08:37,031][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.731403112411499, cross_entropy: 2.731403112411499 +[2025-04-27 12:08:37,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 1.5777320861816406, cross_entropy: 1.5777320861816406 +[2025-04-27 12:08:39,387][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 1.8484618663787842, cross_entropy: 1.8484618663787842 +[2025-04-27 12:08:39,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 1.7189936637878418, cross_entropy: 1.7189936637878418 +[2025-04-27 12:08:41,494][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.8173450231552124, cross_entropy: 1.8173450231552124 +[2025-04-27 12:08:41,616][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 1.6004050970077515, cross_entropy: 1.6004050970077515 +[2025-04-27 12:08:44,430][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.97460675239563, cross_entropy: 2.97460675239563 +[2025-04-27 12:08:44,551][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 2.0083839893341064, cross_entropy: 2.0083839893341064 +[2025-04-27 12:08:46,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.821481466293335, cross_entropy: 2.821481466293335 +[2025-04-27 12:08:46,555][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 2.1078054904937744, cross_entropy: 2.1078054904937744 +[2025-04-27 12:08:48,841][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.0261878967285156, cross_entropy: 2.0261878967285156 +[2025-04-27 12:08:48,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 1.5062412023544312, cross_entropy: 1.5062412023544312 +[2025-04-27 12:08:51,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 1.4692085981369019, cross_entropy: 1.4692085981369019 +[2025-04-27 12:08:51,305][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 3.213839054107666, cross_entropy: 3.213839054107666 +[2025-04-27 12:08:52,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 1.3555021286010742, cross_entropy: 1.3555021286010742 +[2025-04-27 12:08:53,109][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 1.7440745830535889, cross_entropy: 1.7440745830535889 +[2025-04-27 12:08:55,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 3.150275707244873, cross_entropy: 3.150275707244873 +[2025-04-27 12:08:55,771][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 2.7126691341400146, cross_entropy: 2.7126691341400146 +[2025-04-27 12:08:57,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 3.067613363265991, cross_entropy: 3.067613363265991 +[2025-04-27 12:08:57,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 3.299405336380005, cross_entropy: 3.299405336380005 +[2025-04-27 12:09:00,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.7907772064208984, cross_entropy: 2.7907772064208984 +[2025-04-27 12:09:00,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 1.7429732084274292, cross_entropy: 1.7429732084274292 +[2025-04-27 12:09:02,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 3.573136329650879, cross_entropy: 3.573136329650879 +[2025-04-27 12:09:03,115][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 1.7608397006988525, cross_entropy: 1.7608397006988525 +[2025-04-27 12:09:05,401][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 1.5096023082733154, cross_entropy: 1.5096023082733154 +[2025-04-27 12:09:05,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 1.6985318660736084, cross_entropy: 1.6985318660736084 +[2025-04-27 12:09:07,929][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.4705801010131836, cross_entropy: 2.4705801010131836 +[2025-04-27 12:09:08,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 3.232750654220581, cross_entropy: 3.232750654220581 +[2025-04-27 12:09:09,866][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 2.180297374725342, cross_entropy: 2.180297374725342 +[2025-04-27 12:09:09,969][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.955193042755127, cross_entropy: 1.955193042755127 +[2025-04-27 12:09:12,346][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.4350377321243286, cross_entropy: 1.4350377321243286 +[2025-04-27 12:09:12,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 3.3031885623931885, cross_entropy: 3.3031885623931885 +[2025-04-27 12:09:15,019][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.597871780395508, cross_entropy: 2.597871780395508 +[2025-04-27 12:09:15,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.4871160984039307, cross_entropy: 1.4871160984039307 +[2025-04-27 12:09:17,686][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 3.376143455505371, cross_entropy: 3.376143455505371 +[2025-04-27 12:09:17,789][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 3.6850857734680176, cross_entropy: 3.6850857734680176 +[2025-04-27 12:09:20,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.346554160118103, cross_entropy: 1.346554160118103 +[2025-04-27 12:09:20,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 3.418318271636963, cross_entropy: 3.418318271636963 +[2025-04-27 12:09:22,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 3.3863179683685303, cross_entropy: 3.3863179683685303 +[2025-04-27 12:09:22,825][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.9988325834274292, cross_entropy: 1.9988325834274292 +[2025-04-27 12:09:24,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 1.7344411611557007, cross_entropy: 1.7344411611557007 +[2025-04-27 12:09:25,043][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 1.7698299884796143, cross_entropy: 1.7698299884796143 +[2025-04-27 12:09:26,956][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 2.3046250343322754, cross_entropy: 2.3046250343322754 +[2025-04-27 12:09:27,060][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 3.259826898574829, cross_entropy: 3.259826898574829 +[2025-04-27 12:09:29,466][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.8694907426834106, cross_entropy: 1.8694907426834106 +[2025-04-27 12:09:29,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.5791313648223877, cross_entropy: 1.5791313648223877 +[2025-04-27 12:09:31,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.7204575538635254, cross_entropy: 1.7204575538635254 +[2025-04-27 12:09:31,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 2.235607147216797, cross_entropy: 2.235607147216797 +[2025-04-27 12:09:34,055][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.37802791595459, cross_entropy: 2.37802791595459 +[2025-04-27 12:09:34,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.924581527709961, cross_entropy: 2.924581527709961 +[2025-04-27 12:09:36,966][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 3.168595790863037, cross_entropy: 3.168595790863037 +[2025-04-27 12:09:37,072][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 1.5729243755340576, cross_entropy: 1.5729243755340576 +[2025-04-27 12:09:39,159][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 3.1178462505340576, cross_entropy: 3.1178462505340576 +[2025-04-27 12:09:39,283][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 2.513333320617676, cross_entropy: 2.513333320617676 +[2025-04-27 12:09:41,483][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.302063465118408, cross_entropy: 2.302063465118408 +[2025-04-27 12:09:41,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 2.2439279556274414, cross_entropy: 2.2439279556274414 +[2025-04-27 12:09:43,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 3.312549591064453, cross_entropy: 3.312549591064453 +[2025-04-27 12:09:43,900][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.5894384384155273, cross_entropy: 1.5894384384155273 +[2025-04-27 12:09:45,853][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 1.145963430404663, cross_entropy: 1.145963430404663 +[2025-04-27 12:09:46,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 3.0174646377563477, cross_entropy: 3.0174646377563477 +[2025-04-27 12:09:48,327][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 2.140998601913452, cross_entropy: 2.140998601913452 +[2025-04-27 12:09:48,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.7656736373901367, cross_entropy: 1.7656736373901367 +[2025-04-27 12:09:50,935][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 1.9933555126190186, cross_entropy: 1.9933555126190186 +[2025-04-27 12:09:51,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 3.405240297317505, cross_entropy: 3.405240297317505 +[2025-04-27 12:09:53,403][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 1.139209270477295, cross_entropy: 1.139209270477295 +[2025-04-27 12:09:53,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 2.929655075073242, cross_entropy: 2.929655075073242 +[2025-04-27 12:09:55,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 3.3367433547973633, cross_entropy: 3.3367433547973633 +[2025-04-27 12:09:56,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 3.37811017036438, cross_entropy: 3.37811017036438 +[2025-04-27 12:09:58,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 1.823254108428955, cross_entropy: 1.823254108428955 +[2025-04-27 12:09:59,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.146016836166382, cross_entropy: 2.146016836166382 +[2025-04-27 12:10:01,428][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.512657642364502, cross_entropy: 2.512657642364502 +[2025-04-27 12:10:01,573][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 1.7776638269424438, cross_entropy: 1.7776638269424438 +[2025-04-27 12:10:03,901][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 2.930087089538574, cross_entropy: 2.930087089538574 +[2025-04-27 12:10:04,005][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 3.157803535461426, cross_entropy: 3.157803535461426 +[2025-04-27 12:10:06,131][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.476293921470642, cross_entropy: 1.476293921470642 +[2025-04-27 12:10:06,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.4894778728485107, cross_entropy: 2.4894778728485107 +[2025-04-27 12:10:08,114][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 2.369990348815918, cross_entropy: 2.369990348815918 +[2025-04-27 12:10:08,611][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 1.666499376296997, cross_entropy: 1.666499376296997 +[2025-04-27 12:10:10,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 3.5253829956054688, cross_entropy: 3.5253829956054688 +[2025-04-27 12:10:11,243][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 1.426880121231079, cross_entropy: 1.426880121231079 +[2025-04-27 12:10:12,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 2.0979230403900146, cross_entropy: 2.0979230403900146 +[2025-04-27 12:10:13,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 3.525813341140747, cross_entropy: 3.525813341140747 +[2025-04-27 12:10:14,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 3.26554012298584, cross_entropy: 3.26554012298584 +[2025-04-27 12:10:15,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.423637866973877, cross_entropy: 2.423637866973877 +[2025-04-27 12:10:16,326][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.1313486099243164, cross_entropy: 2.1313486099243164 +[2025-04-27 12:10:18,459][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 3.638263702392578, cross_entropy: 3.638263702392578 +[2025-04-27 12:10:18,585][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 2.173004627227783, cross_entropy: 2.173004627227783 +[2025-04-27 12:10:20,414][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 1.8063275814056396, cross_entropy: 1.8063275814056396 +[2025-04-27 12:10:20,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 2.4157886505126953, cross_entropy: 2.4157886505126953 +[2025-04-27 12:10:23,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 1.552804708480835, cross_entropy: 1.552804708480835 +[2025-04-27 12:10:23,221][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 1.7234632968902588, cross_entropy: 1.7234632968902588 +[2025-04-27 12:10:25,405][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.131730079650879, cross_entropy: 2.131730079650879 +[2025-04-27 12:10:25,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 1.877685546875, cross_entropy: 1.877685546875 +[2025-04-27 12:10:28,204][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 3.05444598197937, cross_entropy: 3.05444598197937 +[2025-04-27 12:10:28,335][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 3.021512508392334, cross_entropy: 3.021512508392334 +[2025-04-27 12:10:30,475][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.843027114868164, cross_entropy: 2.843027114868164 +[2025-04-27 12:10:30,632][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 2.080678939819336, cross_entropy: 2.080678939819336 +[2025-04-27 12:10:33,121][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 1.506065845489502, cross_entropy: 1.506065845489502 +[2025-04-27 12:10:33,271][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 3.380182981491089, cross_entropy: 3.380182981491089 +[2025-04-27 12:10:35,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 1.4749815464019775, cross_entropy: 1.4749815464019775 +[2025-04-27 12:10:35,581][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 3.3537838459014893, cross_entropy: 3.3537838459014893 +[2025-04-27 12:10:37,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 3.498438835144043, cross_entropy: 3.498438835144043 +[2025-04-27 12:10:37,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 1.3968024253845215, cross_entropy: 1.3968024253845215 +[2025-04-27 12:10:40,768][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 1.5129730701446533, cross_entropy: 1.5129730701446533 +[2025-04-27 12:10:40,893][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 2.809798002243042, cross_entropy: 2.809798002243042 +[2025-04-27 12:10:42,916][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.542907476425171, cross_entropy: 1.542907476425171 +[2025-04-27 12:10:43,041][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 2.2128472328186035, cross_entropy: 2.2128472328186035 +[2025-04-27 12:10:44,594][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 2.643878698348999, cross_entropy: 2.643878698348999 +[2025-04-27 12:10:44,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.8215405941009521, cross_entropy: 1.8215405941009521 +[2025-04-27 12:10:46,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 3.315185070037842, cross_entropy: 3.315185070037842 +[2025-04-27 12:10:46,573][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 1.0500636100769043, cross_entropy: 1.0500636100769043 +[2025-04-27 12:10:49,280][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 1.8367539644241333, cross_entropy: 1.8367539644241333 +[2025-04-27 12:10:49,385][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 3.3991150856018066, cross_entropy: 3.3991150856018066 +[2025-04-27 12:10:51,517][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 1.5196008682250977, cross_entropy: 1.5196008682250977 +[2025-04-27 12:10:51,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 2.416006088256836, cross_entropy: 2.416006088256836 +[2025-04-27 12:10:54,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 1.9213109016418457, cross_entropy: 1.9213109016418457 +[2025-04-27 12:10:54,383][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.453779697418213, cross_entropy: 2.453779697418213 +[2025-04-27 12:10:56,460][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.3339215517044067, cross_entropy: 1.3339215517044067 +[2025-04-27 12:10:56,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 2.2021324634552, cross_entropy: 2.2021324634552 +[2025-04-27 12:10:58,900][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 3.480358600616455, cross_entropy: 3.480358600616455 +[2025-04-27 12:10:59,005][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 2.1973626613616943, cross_entropy: 2.1973626613616943 +[2025-04-27 12:11:01,471][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 3.347295045852661, cross_entropy: 3.347295045852661 +[2025-04-27 12:11:01,592][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.738525390625, cross_entropy: 2.738525390625 +[2025-04-27 12:11:04,119][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 1.571462869644165, cross_entropy: 1.571462869644165 +[2025-04-27 12:11:04,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 2.593064308166504, cross_entropy: 2.593064308166504 +[2025-04-27 12:11:06,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 2.760247230529785, cross_entropy: 2.760247230529785 +[2025-04-27 12:11:06,133][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 2.7765612602233887, cross_entropy: 2.7765612602233887 +[2025-04-27 12:11:08,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 3.1464123725891113, cross_entropy: 3.1464123725891113 +[2025-04-27 12:11:08,421][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.294719934463501, cross_entropy: 1.294719934463501 +[2025-04-27 12:11:11,147][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 1.5438954830169678, cross_entropy: 1.5438954830169678 +[2025-04-27 12:11:11,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 3.195971965789795, cross_entropy: 3.195971965789795 +[2025-04-27 12:11:13,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.8326308727264404, cross_entropy: 2.8326308727264404 +[2025-04-27 12:11:13,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 2.3698325157165527, cross_entropy: 2.3698325157165527 +[2025-04-27 12:11:15,671][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 1.3424882888793945, cross_entropy: 1.3424882888793945 +[2025-04-27 12:11:15,791][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 2.1916663646698, cross_entropy: 2.1916663646698 +[2025-04-27 12:11:17,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.3312537670135498, cross_entropy: 1.3312537670135498 +[2025-04-27 12:11:17,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 2.1590969562530518, cross_entropy: 2.1590969562530518 +[2025-04-27 12:11:19,630][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 1.9886033535003662, cross_entropy: 1.9886033535003662 +[2025-04-27 12:11:19,751][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 3.3854990005493164, cross_entropy: 3.3854990005493164 +[2025-04-27 12:11:21,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 2.7434310913085938, cross_entropy: 2.7434310913085938 +[2025-04-27 12:11:21,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 2.0400326251983643, cross_entropy: 2.0400326251983643 +[2025-04-27 12:11:23,228][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 3.3581721782684326, cross_entropy: 3.3581721782684326 +[2025-04-27 12:11:23,442][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 3.5432653427124023, cross_entropy: 3.5432653427124023 +[2025-04-27 12:11:25,320][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 2.730734348297119, cross_entropy: 2.730734348297119 +[2025-04-27 12:11:26,353][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 3.0228404998779297, cross_entropy: 3.0228404998779297 +[2025-04-27 12:11:28,041][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.577109694480896, cross_entropy: 1.577109694480896 +[2025-04-27 12:11:28,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.9681024551391602, cross_entropy: 1.9681024551391602 +[2025-04-27 12:11:30,372][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 3.280144691467285, cross_entropy: 3.280144691467285 +[2025-04-27 12:11:30,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 1.9481651782989502, cross_entropy: 1.9481651782989502 +[2025-04-27 12:11:33,062][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 3.1243538856506348, cross_entropy: 3.1243538856506348 +[2025-04-27 12:11:33,170][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 1.4552884101867676, cross_entropy: 1.4552884101867676 +[2025-04-27 12:11:35,014][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 3.065833568572998, cross_entropy: 3.065833568572998 +[2025-04-27 12:11:35,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 1.601181983947754, cross_entropy: 1.601181983947754 +[2025-04-27 12:11:37,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 3.269641876220703, cross_entropy: 3.269641876220703 +[2025-04-27 12:11:37,765][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 2.8334124088287354, cross_entropy: 2.8334124088287354 +[2025-04-27 12:11:39,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 1.7517259120941162, cross_entropy: 1.7517259120941162 +[2025-04-27 12:11:40,104][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 3.2346253395080566, cross_entropy: 3.2346253395080566 +[2025-04-27 12:11:41,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 3.199730396270752, cross_entropy: 3.199730396270752 +[2025-04-27 12:11:42,919][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 1.3898203372955322, cross_entropy: 1.3898203372955322 +[2025-04-27 12:11:44,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 1.6592905521392822, cross_entropy: 1.6592905521392822 +[2025-04-27 12:11:45,200][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 2.056877851486206, cross_entropy: 2.056877851486206 +[2025-04-27 12:11:46,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.5388840436935425, cross_entropy: 1.5388840436935425 +[2025-04-27 12:11:46,796][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.8452215194702148, cross_entropy: 1.8452215194702148 +[2025-04-27 12:13:32,611][BaseTrainer][INFO] - [Epoch 10/10] (train) 2.3050436973571777, cross_entropy: 2.3050436973571777 +[2025-04-27 12:13:32,612][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.82505202293396, cross_entropy: 1.82505202293396 +[2025-04-27 12:13:32,775][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/epoch10.pth. +[2025-04-27 12:13:32,987][BaseTrainer][INFO] - Save model: ./exp/20250427-104215/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a6b7b99cafb6bec5c4d70b5a08c5d5c527dc413 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb7d8a078a4012e5dbad69974508f0e16913dddec612232a155ee5790805be2 +size 51764901 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..8fd7607028a5baa16f3934d9a9489fd3d10b38cd --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-104215/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415711e50672e84febe12d7b656dd86d47ef46da0e9670c05bcab58a4e3b9a0d +size 51716259 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6477dc421a56c8fb2e70812c40490823421cc571 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/README.md @@ -0,0 +1,7 @@ +system=default_seed-0 +data=birdclef2025_15s +train=birdclef2025_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.476 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..db3e22633265bfae193ef4fdce7734725a1c0e3d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/config.yaml @@ -0,0 +1,219 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250427-115144 + tensorboard_dir: ./tensorboard/20250427-115144 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ef2006e28f428ed3b9262f6c0e83f736393f82a4 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250427-115144/log/20250427-115147 + sweep: + dir: multirun/${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/20250427-115144/log/20250427-115147 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_15s + - train=birdclef2025_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=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/20250427-115144 + - train.output.tensorboard_dir=./tensorboard/20250427-115144 + job: + name: train + chdir: false + override_dirname: 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/20250427-115144,train.output.tensorboard_dir=./tensorboard/20250427-115144,train.resume.continue_from=,train=birdclef2025_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/20250427-115144/log/20250427-115147 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2fc38bfb34600dea35e50decb0de4866c528647b --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_15s +- train=birdclef2025_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=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/20250427-115144 +- train.output.tensorboard_dir=./tensorboard/20250427-115144 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0caae1e6756986dddc4f8b49feb6ccca234422df --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/.hydra/resolved_config.yaml @@ -0,0 +1,278 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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: true + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2024BaselineMelSpectrogram + 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/20250427-115144 + tensorboard_dir: ./tensorboard/20250427-115144 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250427-115144/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250427-115144/model/epoch{epoch}.pth + last: + path: ./exp/20250427-115144/model/last.pth + best_epoch: + path: ./exp/20250427-115144/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/train.log new file mode 100644 index 0000000000000000000000000000000000000000..80f465fa736d2b324882eed45d1b4ef31a1e3361 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/log/20250427-115147/train.log @@ -0,0 +1,4279 @@ +[2025-04-27 11:52:14,814][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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250427-115144 + tensorboard_dir: ./tensorboard/20250427-115144 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-27 11:52:14,814][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) + ) +) +[2025-04-27 11:52:14,819][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-27 11:52:23,655][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.30259895324707, cross_entropy: 5.30259895324707 +[2025-04-27 11:52:23,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.335302352905273, cross_entropy: 5.335302352905273 +[2025-04-27 11:52:24,297][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.295900821685791, cross_entropy: 5.295900821685791 +[2025-04-27 11:52:24,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.2178144454956055, cross_entropy: 5.2178144454956055 +[2025-04-27 11:52:25,223][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.11585807800293, cross_entropy: 5.11585807800293 +[2025-04-27 11:52:27,624][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.102458953857422, cross_entropy: 5.102458953857422 +[2025-04-27 11:52:28,205][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.973531723022461, cross_entropy: 4.973531723022461 +[2025-04-27 11:52:30,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.030025959014893, cross_entropy: 5.030025959014893 +[2025-04-27 11:52:30,881][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.8077802658081055, cross_entropy: 4.8077802658081055 +[2025-04-27 11:52:33,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.920794486999512, cross_entropy: 4.920794486999512 +[2025-04-27 11:52:34,139][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.983854293823242, cross_entropy: 4.983854293823242 +[2025-04-27 11:52:36,748][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.779067516326904, cross_entropy: 4.779067516326904 +[2025-04-27 11:52:37,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.902193069458008, cross_entropy: 4.902193069458008 +[2025-04-27 11:52:40,805][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.784266471862793, cross_entropy: 4.784266471862793 +[2025-04-27 11:52:41,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.833295822143555, cross_entropy: 4.833295822143555 +[2025-04-27 11:52:43,612][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.754114151000977, cross_entropy: 4.754114151000977 +[2025-04-27 11:52:43,897][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.034990310668945, cross_entropy: 5.034990310668945 +[2025-04-27 11:52:47,168][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.152438640594482, cross_entropy: 5.152438640594482 +[2025-04-27 11:52:47,675][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.738556861877441, cross_entropy: 4.738556861877441 +[2025-04-27 11:52:50,064][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.821481704711914, cross_entropy: 4.821481704711914 +[2025-04-27 11:52:51,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.662850379943848, cross_entropy: 4.662850379943848 +[2025-04-27 11:52:52,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.801815032958984, cross_entropy: 4.801815032958984 +[2025-04-27 11:52:54,224][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.74875545501709, cross_entropy: 4.74875545501709 +[2025-04-27 11:52:55,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.787607192993164, cross_entropy: 4.787607192993164 +[2025-04-27 11:52:57,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.580771446228027, cross_entropy: 4.580771446228027 +[2025-04-27 11:52:59,577][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.823015213012695, cross_entropy: 4.823015213012695 +[2025-04-27 11:52:59,921][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.676060199737549, cross_entropy: 4.676060199737549 +[2025-04-27 11:53:02,778][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.575323581695557, cross_entropy: 4.575323581695557 +[2025-04-27 11:53:03,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.578214645385742, cross_entropy: 4.578214645385742 +[2025-04-27 11:53:06,049][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.699378967285156, cross_entropy: 4.699378967285156 +[2025-04-27 11:53:06,315][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.312051773071289, cross_entropy: 4.312051773071289 +[2025-04-27 11:53:09,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.886200904846191, cross_entropy: 4.886200904846191 +[2025-04-27 11:53:09,518][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.7994608879089355, cross_entropy: 4.7994608879089355 +[2025-04-27 11:53:12,548][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.761910915374756, cross_entropy: 4.761910915374756 +[2025-04-27 11:53:12,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.558674335479736, cross_entropy: 4.558674335479736 +[2025-04-27 11:53:15,750][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.378215789794922, cross_entropy: 4.378215789794922 +[2025-04-27 11:53:16,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.33476448059082, cross_entropy: 4.33476448059082 +[2025-04-27 11:53:18,705][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.315987586975098, cross_entropy: 4.315987586975098 +[2025-04-27 11:53:18,992][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.840209007263184, cross_entropy: 4.840209007263184 +[2025-04-27 11:53:22,832][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.7222795486450195, cross_entropy: 4.7222795486450195 +[2025-04-27 11:53:23,101][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.617287635803223, cross_entropy: 4.617287635803223 +[2025-04-27 11:53:25,984][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.476132392883301, cross_entropy: 4.476132392883301 +[2025-04-27 11:53:26,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.123262882232666, cross_entropy: 4.123262882232666 +[2025-04-27 11:53:28,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.458603858947754, cross_entropy: 4.458603858947754 +[2025-04-27 11:53:29,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.392025947570801, cross_entropy: 4.392025947570801 +[2025-04-27 11:53:32,009][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.104022026062012, cross_entropy: 4.104022026062012 +[2025-04-27 11:53:32,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.705638885498047, cross_entropy: 4.705638885498047 +[2025-04-27 11:53:35,198][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.398877143859863, cross_entropy: 4.398877143859863 +[2025-04-27 11:53:36,100][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.499863624572754, cross_entropy: 4.499863624572754 +[2025-04-27 11:53:38,119][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.442831039428711, cross_entropy: 4.442831039428711 +[2025-04-27 11:53:39,114][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 3.991183280944824, cross_entropy: 3.991183280944824 +[2025-04-27 11:53:41,351][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.091524124145508, cross_entropy: 4.091524124145508 +[2025-04-27 11:53:42,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.291799545288086, cross_entropy: 4.291799545288086 +[2025-04-27 11:53:45,200][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.393045425415039, cross_entropy: 4.393045425415039 +[2025-04-27 11:53:45,485][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.205494403839111, cross_entropy: 4.205494403839111 +[2025-04-27 11:53:48,189][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.394018650054932, cross_entropy: 4.394018650054932 +[2025-04-27 11:53:48,486][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 3.9876956939697266, cross_entropy: 3.9876956939697266 +[2025-04-27 11:53:51,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 3.935225486755371, cross_entropy: 3.935225486755371 +[2025-04-27 11:53:51,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 3.9447715282440186, cross_entropy: 3.9447715282440186 +[2025-04-27 11:53:55,288][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.073084831237793, cross_entropy: 4.073084831237793 +[2025-04-27 11:53:55,570][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.257057189941406, cross_entropy: 4.257057189941406 +[2025-04-27 11:53:58,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.154435157775879, cross_entropy: 4.154435157775879 +[2025-04-27 11:53:58,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.3230695724487305, cross_entropy: 4.3230695724487305 +[2025-04-27 11:54:01,771][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.072064399719238, cross_entropy: 4.072064399719238 +[2025-04-27 11:54:02,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.131603717803955, cross_entropy: 4.131603717803955 +[2025-04-27 11:54:04,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.04857873916626, cross_entropy: 4.04857873916626 +[2025-04-27 11:54:05,042][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 3.9428677558898926, cross_entropy: 3.9428677558898926 +[2025-04-27 11:54:08,338][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.308647155761719, cross_entropy: 4.308647155761719 +[2025-04-27 11:54:08,607][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.482831001281738, cross_entropy: 4.482831001281738 +[2025-04-27 11:54:10,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.143677711486816, cross_entropy: 4.143677711486816 +[2025-04-27 11:54:11,126][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.542884826660156, cross_entropy: 4.542884826660156 +[2025-04-27 11:54:14,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.032710552215576, cross_entropy: 4.032710552215576 +[2025-04-27 11:54:14,364][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.690429210662842, cross_entropy: 3.690429210662842 +[2025-04-27 11:54:17,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.322957992553711, cross_entropy: 4.322957992553711 +[2025-04-27 11:54:17,506][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 3.473031520843506, cross_entropy: 3.473031520843506 +[2025-04-27 11:54:20,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 3.6341121196746826, cross_entropy: 3.6341121196746826 +[2025-04-27 11:54:21,179][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 3.7611641883850098, cross_entropy: 3.7611641883850098 +[2025-04-27 11:54:24,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.284689903259277, cross_entropy: 4.284689903259277 +[2025-04-27 11:54:24,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.43070650100708, cross_entropy: 4.43070650100708 +[2025-04-27 11:54:27,217][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.049274921417236, cross_entropy: 4.049274921417236 +[2025-04-27 11:54:27,639][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.216605186462402, cross_entropy: 4.216605186462402 +[2025-04-27 11:54:30,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 3.340785026550293, cross_entropy: 3.340785026550293 +[2025-04-27 11:54:31,404][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.436174392700195, cross_entropy: 4.436174392700195 +[2025-04-27 11:54:33,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 3.6566877365112305, cross_entropy: 3.6566877365112305 +[2025-04-27 11:54:34,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 3.8520123958587646, cross_entropy: 3.8520123958587646 +[2025-04-27 11:54:37,097][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.6100172996520996, cross_entropy: 3.6100172996520996 +[2025-04-27 11:54:38,671][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 3.573709011077881, cross_entropy: 3.573709011077881 +[2025-04-27 11:54:40,794][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.053647041320801, cross_entropy: 4.053647041320801 +[2025-04-27 11:54:41,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.258758544921875, cross_entropy: 4.258758544921875 +[2025-04-27 11:54:44,256][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.891019821166992, cross_entropy: 3.891019821166992 +[2025-04-27 11:54:44,592][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.0498247146606445, cross_entropy: 4.0498247146606445 +[2025-04-27 11:54:46,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.676077365875244, cross_entropy: 3.676077365875244 +[2025-04-27 11:54:47,705][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.5732154846191406, cross_entropy: 3.5732154846191406 +[2025-04-27 11:54:50,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.074612617492676, cross_entropy: 4.074612617492676 +[2025-04-27 11:54:51,454][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.354798793792725, cross_entropy: 4.354798793792725 +[2025-04-27 11:54:53,996][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.5127484798431396, cross_entropy: 3.5127484798431396 +[2025-04-27 11:54:54,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.3596625328063965, cross_entropy: 4.3596625328063965 +[2025-04-27 11:54:57,601][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.062668561935425, cross_entropy: 3.062668561935425 +[2025-04-27 11:54:58,116][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 3.9000630378723145, cross_entropy: 3.9000630378723145 +[2025-04-27 11:55:01,348][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.3554952144622803, cross_entropy: 3.3554952144622803 +[2025-04-27 11:55:01,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.034019470214844, cross_entropy: 4.034019470214844 +[2025-04-27 11:55:04,883][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.3690097332000732, cross_entropy: 3.3690097332000732 +[2025-04-27 11:55:05,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.5790247917175293, cross_entropy: 3.5790247917175293 +[2025-04-27 11:55:08,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.1831536293029785, cross_entropy: 3.1831536293029785 +[2025-04-27 11:55:08,555][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.1169545650482178, cross_entropy: 3.1169545650482178 +[2025-04-27 11:55:11,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 3.5921835899353027, cross_entropy: 3.5921835899353027 +[2025-04-27 11:55:11,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.1176986694335938, cross_entropy: 3.1176986694335938 +[2025-04-27 11:55:14,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.449270248413086, cross_entropy: 4.449270248413086 +[2025-04-27 11:55:14,727][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.9350955486297607, cross_entropy: 3.9350955486297607 +[2025-04-27 11:55:17,723][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 3.8220362663269043, cross_entropy: 3.8220362663269043 +[2025-04-27 11:55:17,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.1211113929748535, cross_entropy: 3.1211113929748535 +[2025-04-27 11:55:20,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.5811541080474854, cross_entropy: 3.5811541080474854 +[2025-04-27 11:55:21,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.016876697540283, cross_entropy: 4.016876697540283 +[2025-04-27 11:55:23,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 3.6044464111328125, cross_entropy: 3.6044464111328125 +[2025-04-27 11:55:24,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 3.9545626640319824, cross_entropy: 3.9545626640319824 +[2025-04-27 11:55:26,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.061211585998535, cross_entropy: 3.061211585998535 +[2025-04-27 11:55:27,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.152615785598755, cross_entropy: 3.152615785598755 +[2025-04-27 11:55:30,438][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.422101020812988, cross_entropy: 4.422101020812988 +[2025-04-27 11:55:31,307][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.1260576248168945, cross_entropy: 4.1260576248168945 +[2025-04-27 11:55:33,260][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.323721408843994, cross_entropy: 4.323721408843994 +[2025-04-27 11:55:34,403][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.273928165435791, cross_entropy: 4.273928165435791 +[2025-04-27 11:55:36,829][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 2.8719024658203125, cross_entropy: 2.8719024658203125 +[2025-04-27 11:55:37,519][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.5431690216064453, cross_entropy: 3.5431690216064453 +[2025-04-27 11:55:39,692][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.081897497177124, cross_entropy: 3.081897497177124 +[2025-04-27 11:55:40,019][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.241296768188477, cross_entropy: 4.241296768188477 +[2025-04-27 11:55:42,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 3.012881278991699, cross_entropy: 3.012881278991699 +[2025-04-27 11:55:43,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.4407293796539307, cross_entropy: 3.4407293796539307 +[2025-04-27 11:55:45,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.160731792449951, cross_entropy: 4.160731792449951 +[2025-04-27 11:55:47,809][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 3.1910958290100098, cross_entropy: 3.1910958290100098 +[2025-04-27 11:55:48,272][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.9790854454040527, cross_entropy: 3.9790854454040527 +[2025-04-27 11:55:50,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.122958183288574, cross_entropy: 4.122958183288574 +[2025-04-27 11:55:51,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 3.6682868003845215, cross_entropy: 3.6682868003845215 +[2025-04-27 11:55:53,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.413390636444092, cross_entropy: 4.413390636444092 +[2025-04-27 11:55:54,197][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 3.972393274307251, cross_entropy: 3.972393274307251 +[2025-04-27 11:55:57,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 2.9164600372314453, cross_entropy: 2.9164600372314453 +[2025-04-27 11:55:57,494][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.628617525100708, cross_entropy: 3.628617525100708 +[2025-04-27 11:56:00,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.924879550933838, cross_entropy: 3.924879550933838 +[2025-04-27 11:56:00,394][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.187247276306152, cross_entropy: 4.187247276306152 +[2025-04-27 11:56:03,433][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 3.097148895263672, cross_entropy: 3.097148895263672 +[2025-04-27 11:56:03,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.230076789855957, cross_entropy: 3.230076789855957 +[2025-04-27 11:56:06,147][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 3.7397427558898926, cross_entropy: 3.7397427558898926 +[2025-04-27 11:56:06,417][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.463444709777832, cross_entropy: 3.463444709777832 +[2025-04-27 11:56:09,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.942300796508789, cross_entropy: 3.942300796508789 +[2025-04-27 11:56:09,650][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.20503044128418, cross_entropy: 4.20503044128418 +[2025-04-27 11:56:12,704][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 3.3317112922668457, cross_entropy: 3.3317112922668457 +[2025-04-27 11:56:12,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.4498867988586426, cross_entropy: 3.4498867988586426 +[2025-04-27 11:56:16,055][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 3.676582098007202, cross_entropy: 3.676582098007202 +[2025-04-27 11:56:16,324][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.731654405593872, cross_entropy: 3.731654405593872 +[2025-04-27 11:56:19,848][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 3.265476703643799, cross_entropy: 3.265476703643799 +[2025-04-27 11:56:20,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.168787002563477, cross_entropy: 4.168787002563477 +[2025-04-27 11:56:22,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 2.9647717475891113, cross_entropy: 2.9647717475891113 +[2025-04-27 11:56:23,189][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.2279767990112305, cross_entropy: 3.2279767990112305 +[2025-04-27 11:56:26,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 3.5065040588378906, cross_entropy: 3.5065040588378906 +[2025-04-27 11:56:26,676][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 2.643258571624756, cross_entropy: 2.643258571624756 +[2025-04-27 11:56:30,000][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.9761085510253906, cross_entropy: 3.9761085510253906 +[2025-04-27 11:56:30,267][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.431082010269165, cross_entropy: 3.431082010269165 +[2025-04-27 11:56:33,076][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.223459243774414, cross_entropy: 4.223459243774414 +[2025-04-27 11:56:33,343][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.5542447566986084, cross_entropy: 3.5542447566986084 +[2025-04-27 11:56:37,154][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 2.9074108600616455, cross_entropy: 2.9074108600616455 +[2025-04-27 11:56:37,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.6735177040100098, cross_entropy: 3.6735177040100098 +[2025-04-27 11:56:40,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 4.103069305419922, cross_entropy: 4.103069305419922 +[2025-04-27 11:56:40,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.087183952331543, cross_entropy: 3.087183952331543 +[2025-04-27 11:56:43,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.140608787536621, cross_entropy: 4.140608787536621 +[2025-04-27 11:56:43,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.0808279514312744, cross_entropy: 3.0808279514312744 +[2025-04-27 11:56:46,981][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.2579269409179688, cross_entropy: 3.2579269409179688 +[2025-04-27 11:56:47,270][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 3.3898916244506836, cross_entropy: 3.3898916244506836 +[2025-04-27 11:56:50,399][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.5755667686462402, cross_entropy: 3.5755667686462402 +[2025-04-27 11:56:50,685][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.585390329360962, cross_entropy: 3.585390329360962 +[2025-04-27 11:56:53,358][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.279821395874023, cross_entropy: 4.279821395874023 +[2025-04-27 11:56:53,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.878873348236084, cross_entropy: 3.878873348236084 +[2025-04-27 11:56:56,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 2.808468818664551, cross_entropy: 2.808468818664551 +[2025-04-27 11:56:57,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 2.9781012535095215, cross_entropy: 2.9781012535095215 +[2025-04-27 11:57:00,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.860006332397461, cross_entropy: 3.860006332397461 +[2025-04-27 11:57:01,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 3.8409883975982666, cross_entropy: 3.8409883975982666 +[2025-04-27 11:57:03,631][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.269227981567383, cross_entropy: 4.269227981567383 +[2025-04-27 11:57:03,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.9459400177001953, cross_entropy: 3.9459400177001953 +[2025-04-27 11:57:07,058][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.9723501205444336, cross_entropy: 3.9723501205444336 +[2025-04-27 11:57:07,345][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 4.0879106521606445, cross_entropy: 4.0879106521606445 +[2025-04-27 11:57:10,605][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.355496883392334, cross_entropy: 3.355496883392334 +[2025-04-27 11:57:10,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.557607650756836, cross_entropy: 3.557607650756836 +[2025-04-27 11:57:14,090][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 3.4781689643859863, cross_entropy: 3.4781689643859863 +[2025-04-27 11:57:14,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.9077630043029785, cross_entropy: 3.9077630043029785 +[2025-04-27 11:57:18,223][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 2.88018536567688, cross_entropy: 2.88018536567688 +[2025-04-27 11:57:18,489][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.093825340270996, cross_entropy: 4.093825340270996 +[2025-04-27 11:57:21,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.350343704223633, cross_entropy: 3.350343704223633 +[2025-04-27 11:57:22,260][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 2.9700019359588623, cross_entropy: 2.9700019359588623 +[2025-04-27 11:57:25,186][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.3938660621643066, cross_entropy: 3.3938660621643066 +[2025-04-27 11:57:25,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.121997833251953, cross_entropy: 3.121997833251953 +[2025-04-27 11:57:28,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 2.4580445289611816, cross_entropy: 2.4580445289611816 +[2025-04-27 11:57:28,788][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.80318546295166, cross_entropy: 3.80318546295166 +[2025-04-27 11:57:32,227][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 2.59833025932312, cross_entropy: 2.59833025932312 +[2025-04-27 11:57:32,519][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.3324971199035645, cross_entropy: 3.3324971199035645 +[2025-04-27 11:57:36,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 3.113781452178955, cross_entropy: 3.113781452178955 +[2025-04-27 11:57:36,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 4.198464870452881, cross_entropy: 4.198464870452881 +[2025-04-27 11:57:39,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 2.709207773208618, cross_entropy: 2.709207773208618 +[2025-04-27 11:57:40,220][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.327573776245117, cross_entropy: 3.327573776245117 +[2025-04-27 11:57:43,062][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.9238741397857666, cross_entropy: 3.9238741397857666 +[2025-04-27 11:57:43,342][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 2.496067523956299, cross_entropy: 2.496067523956299 +[2025-04-27 11:57:46,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.503255844116211, cross_entropy: 3.503255844116211 +[2025-04-27 11:57:46,387][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.3081576824188232, cross_entropy: 3.3081576824188232 +[2025-04-27 11:57:49,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 2.6447038650512695, cross_entropy: 2.6447038650512695 +[2025-04-27 11:57:49,311][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 3.040128231048584, cross_entropy: 3.040128231048584 +[2025-04-27 11:57:52,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.6688575744628906, cross_entropy: 3.6688575744628906 +[2025-04-27 11:57:52,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 2.6963305473327637, cross_entropy: 2.6963305473327637 +[2025-04-27 11:57:55,802][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 3.8829236030578613, cross_entropy: 3.8829236030578613 +[2025-04-27 11:57:56,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 2.937809944152832, cross_entropy: 2.937809944152832 +[2025-04-27 11:57:58,992][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 2.8391880989074707, cross_entropy: 2.8391880989074707 +[2025-04-27 11:57:59,291][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.7236328125, cross_entropy: 3.7236328125 +[2025-04-27 11:58:02,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 2.40743088722229, cross_entropy: 2.40743088722229 +[2025-04-27 11:58:03,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.8627023696899414, cross_entropy: 3.8627023696899414 +[2025-04-27 11:58:07,005][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.7938435077667236, cross_entropy: 3.7938435077667236 +[2025-04-27 11:58:07,289][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.7486886978149414, cross_entropy: 3.7486886978149414 +[2025-04-27 11:58:10,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.797421932220459, cross_entropy: 3.797421932220459 +[2025-04-27 11:58:11,023][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 2.602921724319458, cross_entropy: 2.602921724319458 +[2025-04-27 11:58:14,738][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.0843210220336914, cross_entropy: 3.0843210220336914 +[2025-04-27 11:58:15,028][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 2.7664542198181152, cross_entropy: 2.7664542198181152 +[2025-04-27 11:58:18,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.7010862827301025, cross_entropy: 3.7010862827301025 +[2025-04-27 11:58:18,362][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 2.9968156814575195, cross_entropy: 2.9968156814575195 +[2025-04-27 11:58:21,121][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.3375964164733887, cross_entropy: 3.3375964164733887 +[2025-04-27 11:58:21,386][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.8481786251068115, cross_entropy: 3.8481786251068115 +[2025-04-27 11:58:24,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 2.713207483291626, cross_entropy: 2.713207483291626 +[2025-04-27 11:58:24,817][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.053750991821289, cross_entropy: 4.053750991821289 +[2025-04-27 11:58:27,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.310927629470825, cross_entropy: 3.310927629470825 +[2025-04-27 11:58:28,184][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 2.841041088104248, cross_entropy: 2.841041088104248 +[2025-04-27 11:58:31,267][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 2.7707254886627197, cross_entropy: 2.7707254886627197 +[2025-04-27 11:58:31,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.3679752349853516, cross_entropy: 3.3679752349853516 +[2025-04-27 11:58:34,254][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 2.9660868644714355, cross_entropy: 2.9660868644714355 +[2025-04-27 11:58:34,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 2.1746253967285156, cross_entropy: 2.1746253967285156 +[2025-04-27 11:58:38,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 2.4802358150482178, cross_entropy: 2.4802358150482178 +[2025-04-27 11:58:38,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 2.8707115650177, cross_entropy: 2.8707115650177 +[2025-04-27 11:58:42,467][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 2.3176050186157227, cross_entropy: 2.3176050186157227 +[2025-04-27 11:58:42,746][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 2.814990520477295, cross_entropy: 2.814990520477295 +[2025-04-27 11:58:46,817][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.62748646736145, cross_entropy: 2.62748646736145 +[2025-04-27 11:58:47,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 2.5843710899353027, cross_entropy: 2.5843710899353027 +[2025-04-27 11:58:51,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.01778507232666, cross_entropy: 3.01778507232666 +[2025-04-27 11:58:51,605][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.3410732746124268, cross_entropy: 3.3410732746124268 +[2025-04-27 11:58:54,596][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 2.1443283557891846, cross_entropy: 2.1443283557891846 +[2025-04-27 11:58:54,865][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.5112411975860596, cross_entropy: 2.5112411975860596 +[2025-04-27 11:58:59,370][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.9032785892486572, cross_entropy: 3.9032785892486572 +[2025-04-27 11:58:59,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 2.4980030059814453, cross_entropy: 2.4980030059814453 +[2025-04-27 11:59:02,798][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.1406185626983643, cross_entropy: 3.1406185626983643 +[2025-04-27 11:59:03,064][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.904465675354004, cross_entropy: 2.904465675354004 +[2025-04-27 11:59:05,647][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 2.905829429626465, cross_entropy: 2.905829429626465 +[2025-04-27 11:59:05,931][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 2.5008487701416016, cross_entropy: 2.5008487701416016 +[2025-04-27 11:59:09,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 2.9839608669281006, cross_entropy: 2.9839608669281006 +[2025-04-27 11:59:09,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 4.091558456420898, cross_entropy: 4.091558456420898 +[2025-04-27 11:59:12,734][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 2.4916114807128906, cross_entropy: 2.4916114807128906 +[2025-04-27 11:59:13,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 3.977799892425537, cross_entropy: 3.977799892425537 +[2025-04-27 11:59:15,331][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.9696550369262695, cross_entropy: 3.9696550369262695 +[2025-04-27 11:59:15,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 3.8596057891845703, cross_entropy: 3.8596057891845703 +[2025-04-27 11:59:18,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.259669780731201, cross_entropy: 3.259669780731201 +[2025-04-27 11:59:18,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 2.7516815662384033, cross_entropy: 2.7516815662384033 +[2025-04-27 11:59:21,275][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.7599775791168213, cross_entropy: 3.7599775791168213 +[2025-04-27 11:59:21,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.768667459487915, cross_entropy: 2.768667459487915 +[2025-04-27 11:59:25,292][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.8927063941955566, cross_entropy: 3.8927063941955566 +[2025-04-27 11:59:25,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.302414894104004, cross_entropy: 3.302414894104004 +[2025-04-27 11:59:28,844][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 3.4879860877990723, cross_entropy: 3.4879860877990723 +[2025-04-27 11:59:29,133][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 2.6154086589813232, cross_entropy: 2.6154086589813232 +[2025-04-27 11:59:32,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 3.011561632156372, cross_entropy: 3.011561632156372 +[2025-04-27 11:59:33,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 2.416914463043213, cross_entropy: 2.416914463043213 +[2025-04-27 11:59:35,760][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.7394931316375732, cross_entropy: 2.7394931316375732 +[2025-04-27 11:59:36,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.8005530834198, cross_entropy: 2.8005530834198 +[2025-04-27 11:59:39,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 2.574918746948242, cross_entropy: 2.574918746948242 +[2025-04-27 11:59:40,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.656128168106079, cross_entropy: 3.656128168106079 +[2025-04-27 11:59:43,979][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 2.473602294921875, cross_entropy: 2.473602294921875 +[2025-04-27 11:59:44,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.420334815979004, cross_entropy: 3.420334815979004 +[2025-04-27 11:59:46,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 4.132350921630859, cross_entropy: 4.132350921630859 +[2025-04-27 11:59:47,212][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.96069598197937, cross_entropy: 2.96069598197937 +[2025-04-27 11:59:49,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 2.39794921875, cross_entropy: 2.39794921875 +[2025-04-27 11:59:50,240][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.434523582458496, cross_entropy: 3.434523582458496 +[2025-04-27 11:59:52,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.725898027420044, cross_entropy: 3.725898027420044 +[2025-04-27 11:59:52,963][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.8917534351348877, cross_entropy: 2.8917534351348877 +[2025-04-27 11:59:56,439][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.058781623840332, cross_entropy: 3.058781623840332 +[2025-04-27 11:59:56,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.6174144744873047, cross_entropy: 3.6174144744873047 +[2025-04-27 11:59:59,929][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.7987608909606934, cross_entropy: 2.7987608909606934 +[2025-04-27 12:00:00,215][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 2.7479116916656494, cross_entropy: 2.7479116916656494 +[2025-04-27 12:00:03,734][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 2.726278781890869, cross_entropy: 2.726278781890869 +[2025-04-27 12:00:04,005][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 3.313689708709717, cross_entropy: 3.313689708709717 +[2025-04-27 12:00:07,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.530409574508667, cross_entropy: 2.530409574508667 +[2025-04-27 12:00:08,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 4.2321319580078125, cross_entropy: 4.2321319580078125 +[2025-04-27 12:00:11,763][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.403181791305542, cross_entropy: 2.403181791305542 +[2025-04-27 12:00:12,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 2.6476917266845703, cross_entropy: 2.6476917266845703 +[2025-04-27 12:00:15,093][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.3872649669647217, cross_entropy: 3.3872649669647217 +[2025-04-27 12:00:15,369][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.3897032737731934, cross_entropy: 2.3897032737731934 +[2025-04-27 12:00:18,537][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.2813472747802734, cross_entropy: 2.2813472747802734 +[2025-04-27 12:00:18,831][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.8657350540161133, cross_entropy: 3.8657350540161133 +[2025-04-27 12:00:21,653][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 2.32952618598938, cross_entropy: 2.32952618598938 +[2025-04-27 12:00:21,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.1464850902557373, cross_entropy: 3.1464850902557373 +[2025-04-27 12:00:24,813][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 2.5276360511779785, cross_entropy: 2.5276360511779785 +[2025-04-27 12:00:25,080][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.8723573684692383, cross_entropy: 2.8723573684692383 +[2025-04-27 12:00:28,175][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.5970592498779297, cross_entropy: 3.5970592498779297 +[2025-04-27 12:00:28,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.6308631896972656, cross_entropy: 3.6308631896972656 +[2025-04-27 12:00:31,848][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 1.994511365890503, cross_entropy: 1.994511365890503 +[2025-04-27 12:00:32,115][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.7357821464538574, cross_entropy: 2.7357821464538574 +[2025-04-27 12:00:35,799][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.8776516914367676, cross_entropy: 2.8776516914367676 +[2025-04-27 12:00:36,098][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.067014694213867, cross_entropy: 3.067014694213867 +[2025-04-27 12:00:39,032][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 2.3307414054870605, cross_entropy: 2.3307414054870605 +[2025-04-27 12:00:39,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.663071393966675, cross_entropy: 3.663071393966675 +[2025-04-27 12:00:42,626][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.9780473709106445, cross_entropy: 2.9780473709106445 +[2025-04-27 12:00:42,915][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.41583251953125, cross_entropy: 3.41583251953125 +[2025-04-27 12:00:46,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.750896453857422, cross_entropy: 2.750896453857422 +[2025-04-27 12:00:46,906][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.019935131072998, cross_entropy: 3.019935131072998 +[2025-04-27 12:00:49,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.3148488998413086, cross_entropy: 2.3148488998413086 +[2025-04-27 12:00:49,857][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 2.9821057319641113, cross_entropy: 2.9821057319641113 +[2025-04-27 12:00:52,898][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 1.6960923671722412, cross_entropy: 1.6960923671722412 +[2025-04-27 12:00:53,163][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 4.093993186950684, cross_entropy: 4.093993186950684 +[2025-04-27 12:00:55,776][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 2.402597427368164, cross_entropy: 2.402597427368164 +[2025-04-27 12:00:56,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.714189052581787, cross_entropy: 3.714189052581787 +[2025-04-27 12:00:59,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.462320566177368, cross_entropy: 3.462320566177368 +[2025-04-27 12:00:59,611][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.0397050380706787, cross_entropy: 2.0397050380706787 +[2025-04-27 12:01:02,090][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.3056516647338867, cross_entropy: 2.3056516647338867 +[2025-04-27 12:01:02,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.0579090118408203, cross_entropy: 3.0579090118408203 +[2025-04-27 12:01:05,221][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.760010004043579, cross_entropy: 3.760010004043579 +[2025-04-27 12:01:05,506][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 2.06296443939209, cross_entropy: 2.06296443939209 +[2025-04-27 12:01:08,906][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.8673174381256104, cross_entropy: 2.8673174381256104 +[2025-04-27 12:01:09,190][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.5390515327453613, cross_entropy: 3.5390515327453613 +[2025-04-27 12:01:12,271][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.750429391860962, cross_entropy: 2.750429391860962 +[2025-04-27 12:01:12,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.5534634590148926, cross_entropy: 3.5534634590148926 +[2025-04-27 12:01:16,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 1.6029467582702637, cross_entropy: 1.6029467582702637 +[2025-04-27 12:01:16,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 1.9439043998718262, cross_entropy: 1.9439043998718262 +[2025-04-27 12:01:19,696][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 2.1504456996917725, cross_entropy: 2.1504456996917725 +[2025-04-27 12:01:19,978][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 2.716017246246338, cross_entropy: 2.716017246246338 +[2025-04-27 12:01:22,702][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.6016762256622314, cross_entropy: 3.6016762256622314 +[2025-04-27 12:01:22,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 1.8630807399749756, cross_entropy: 1.8630807399749756 +[2025-04-27 12:01:26,539][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.5848376750946045, cross_entropy: 3.5848376750946045 +[2025-04-27 12:01:26,813][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.039363384246826, cross_entropy: 3.039363384246826 +[2025-04-27 12:01:29,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.7110300064086914, cross_entropy: 2.7110300064086914 +[2025-04-27 12:01:30,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 1.8401247262954712, cross_entropy: 1.8401247262954712 +[2025-04-27 12:01:33,080][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 2.7287847995758057, cross_entropy: 2.7287847995758057 +[2025-04-27 12:01:33,365][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 2.2614383697509766, cross_entropy: 2.2614383697509766 +[2025-04-27 12:01:36,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 2.3198370933532715, cross_entropy: 2.3198370933532715 +[2025-04-27 12:01:36,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.6960294246673584, cross_entropy: 3.6960294246673584 +[2025-04-27 12:01:39,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 2.748000144958496, cross_entropy: 2.748000144958496 +[2025-04-27 12:01:40,245][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.4037978649139404, cross_entropy: 3.4037978649139404 +[2025-04-27 12:01:43,721][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.1822433471679688, cross_entropy: 2.1822433471679688 +[2025-04-27 12:01:43,986][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.103562831878662, cross_entropy: 2.103562831878662 +[2025-04-27 12:01:47,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 2.511356830596924, cross_entropy: 2.511356830596924 +[2025-04-27 12:01:47,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 3.948098659515381, cross_entropy: 3.948098659515381 +[2025-04-27 12:01:50,389][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.2913169860839844, cross_entropy: 2.2913169860839844 +[2025-04-27 12:01:50,684][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.1341562271118164, cross_entropy: 3.1341562271118164 +[2025-04-27 12:01:53,682][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.284052610397339, cross_entropy: 2.284052610397339 +[2025-04-27 12:01:53,975][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.719916343688965, cross_entropy: 3.719916343688965 +[2025-04-27 12:01:57,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 4.015273094177246, cross_entropy: 4.015273094177246 +[2025-04-27 12:01:57,502][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.6044909954071045, cross_entropy: 2.6044909954071045 +[2025-04-27 12:02:00,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 2.7451961040496826, cross_entropy: 2.7451961040496826 +[2025-04-27 12:02:00,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.968221664428711, cross_entropy: 3.968221664428711 +[2025-04-27 12:02:03,995][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.7341132164001465, cross_entropy: 2.7341132164001465 +[2025-04-27 12:02:04,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.8994197845458984, cross_entropy: 2.8994197845458984 +[2025-04-27 12:02:08,178][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 3.4122066497802734, cross_entropy: 3.4122066497802734 +[2025-04-27 12:02:08,457][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.089258909225464, cross_entropy: 2.089258909225464 +[2025-04-27 12:02:11,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 3.2268521785736084, cross_entropy: 3.2268521785736084 +[2025-04-27 12:02:11,416][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.6548235416412354, cross_entropy: 2.6548235416412354 +[2025-04-27 12:02:14,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.5188441276550293, cross_entropy: 3.5188441276550293 +[2025-04-27 12:02:14,269][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 3.3385682106018066, cross_entropy: 3.3385682106018066 +[2025-04-27 12:02:16,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 2.048081874847412, cross_entropy: 2.048081874847412 +[2025-04-27 12:02:19,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 2.0149691104888916, cross_entropy: 2.0149691104888916 +[2025-04-27 12:05:21,990][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.5364248752593994, cross_entropy: 3.5364248752593994 +[2025-04-27 12:05:21,991][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.11875057220459, cross_entropy: 2.11875057220459 +[2025-04-27 12:05:22,161][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:05:22,318][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch1.pth. +[2025-04-27 12:05:22,478][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:05:26,135][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.705164909362793, cross_entropy: 3.705164909362793 +[2025-04-27 12:05:26,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.0729548931121826, cross_entropy: 2.0729548931121826 +[2025-04-27 12:05:29,250][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.688843011856079, cross_entropy: 3.688843011856079 +[2025-04-27 12:05:29,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 1.8894703388214111, cross_entropy: 1.8894703388214111 +[2025-04-27 12:05:31,700][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.1585206985473633, cross_entropy: 2.1585206985473633 +[2025-04-27 12:05:31,969][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 3.8489274978637695, cross_entropy: 3.8489274978637695 +[2025-04-27 12:05:34,354][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.2381093502044678, cross_entropy: 2.2381093502044678 +[2025-04-27 12:05:34,643][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 1.8300256729125977, cross_entropy: 1.8300256729125977 +[2025-04-27 12:05:36,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.3402090072631836, cross_entropy: 2.3402090072631836 +[2025-04-27 12:05:37,063][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.0648374557495117, cross_entropy: 2.0648374557495117 +[2025-04-27 12:05:39,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.1715519428253174, cross_entropy: 2.1715519428253174 +[2025-04-27 12:05:39,704][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.5414395332336426, cross_entropy: 3.5414395332336426 +[2025-04-27 12:05:42,373][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.5136821269989014, cross_entropy: 3.5136821269989014 +[2025-04-27 12:05:42,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.2355406284332275, cross_entropy: 2.2355406284332275 +[2025-04-27 12:05:45,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 2.7154500484466553, cross_entropy: 2.7154500484466553 +[2025-04-27 12:05:45,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 3.4568605422973633, cross_entropy: 3.4568605422973633 +[2025-04-27 12:05:48,289][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.6534008979797363, cross_entropy: 2.6534008979797363 +[2025-04-27 12:05:48,582][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.292368173599243, cross_entropy: 2.292368173599243 +[2025-04-27 12:05:50,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.6295979022979736, cross_entropy: 3.6295979022979736 +[2025-04-27 12:05:50,923][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 1.7397403717041016, cross_entropy: 1.7397403717041016 +[2025-04-27 12:05:53,034][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.0729732513427734, cross_entropy: 3.0729732513427734 +[2025-04-27 12:05:53,324][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 1.9529073238372803, cross_entropy: 1.9529073238372803 +[2025-04-27 12:05:55,818][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.174421787261963, cross_entropy: 3.174421787261963 +[2025-04-27 12:05:56,117][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.4672093391418457, cross_entropy: 3.4672093391418457 +[2025-04-27 12:05:58,278][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.6305227279663086, cross_entropy: 3.6305227279663086 +[2025-04-27 12:05:58,574][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.1189980506896973, cross_entropy: 2.1189980506896973 +[2025-04-27 12:06:01,462][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.4819388389587402, cross_entropy: 3.4819388389587402 +[2025-04-27 12:06:01,750][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.9999706745147705, cross_entropy: 2.9999706745147705 +[2025-04-27 12:06:03,820][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 3.5225067138671875, cross_entropy: 3.5225067138671875 +[2025-04-27 12:06:04,243][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 1.950031042098999, cross_entropy: 1.950031042098999 +[2025-04-27 12:06:06,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.1453256607055664, cross_entropy: 2.1453256607055664 +[2025-04-27 12:06:06,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.5549232959747314, cross_entropy: 2.5549232959747314 +[2025-04-27 12:06:08,727][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.1347646713256836, cross_entropy: 2.1347646713256836 +[2025-04-27 12:06:09,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 2.510120153427124, cross_entropy: 2.510120153427124 +[2025-04-27 12:06:11,275][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 1.8518667221069336, cross_entropy: 1.8518667221069336 +[2025-04-27 12:06:11,552][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.7032761573791504, cross_entropy: 3.7032761573791504 +[2025-04-27 12:06:14,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.5906476974487305, cross_entropy: 3.5906476974487305 +[2025-04-27 12:06:14,814][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 1.8234121799468994, cross_entropy: 1.8234121799468994 +[2025-04-27 12:06:18,421][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 2.828115940093994, cross_entropy: 2.828115940093994 +[2025-04-27 12:06:18,708][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.0574798583984375, cross_entropy: 2.0574798583984375 +[2025-04-27 12:06:21,018][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.2010912895202637, cross_entropy: 3.2010912895202637 +[2025-04-27 12:06:21,310][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.0657811164855957, cross_entropy: 2.0657811164855957 +[2025-04-27 12:06:23,217][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 2.975682258605957, cross_entropy: 2.975682258605957 +[2025-04-27 12:06:23,504][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.397643566131592, cross_entropy: 2.397643566131592 +[2025-04-27 12:06:25,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.8033082485198975, cross_entropy: 3.8033082485198975 +[2025-04-27 12:06:26,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.189847469329834, cross_entropy: 3.189847469329834 +[2025-04-27 12:06:29,076][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 2.2662978172302246, cross_entropy: 2.2662978172302246 +[2025-04-27 12:06:29,472][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 2.168456792831421, cross_entropy: 2.168456792831421 +[2025-04-27 12:06:31,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.4304730892181396, cross_entropy: 3.4304730892181396 +[2025-04-27 12:06:32,470][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 3.0691847801208496, cross_entropy: 3.0691847801208496 +[2025-04-27 12:06:35,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.3033881187438965, cross_entropy: 3.3033881187438965 +[2025-04-27 12:06:35,439][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 2.4476494789123535, cross_entropy: 2.4476494789123535 +[2025-04-27 12:06:38,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 2.3341917991638184, cross_entropy: 2.3341917991638184 +[2025-04-27 12:06:38,515][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.617478609085083, cross_entropy: 3.617478609085083 +[2025-04-27 12:06:40,986][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 2.0832486152648926, cross_entropy: 2.0832486152648926 +[2025-04-27 12:06:41,280][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 1.7803467512130737, cross_entropy: 1.7803467512130737 +[2025-04-27 12:06:43,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 3.2598748207092285, cross_entropy: 3.2598748207092285 +[2025-04-27 12:06:43,916][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.6585586071014404, cross_entropy: 2.6585586071014404 +[2025-04-27 12:06:46,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.4363925457000732, cross_entropy: 3.4363925457000732 +[2025-04-27 12:06:46,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.3239338397979736, cross_entropy: 3.3239338397979736 +[2025-04-27 12:06:49,275][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.413922071456909, cross_entropy: 3.413922071456909 +[2025-04-27 12:06:49,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.6257224082946777, cross_entropy: 3.6257224082946777 +[2025-04-27 12:06:52,288][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.167764663696289, cross_entropy: 2.167764663696289 +[2025-04-27 12:06:52,575][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 1.565669298171997, cross_entropy: 1.565669298171997 +[2025-04-27 12:06:55,052][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 2.4629411697387695, cross_entropy: 2.4629411697387695 +[2025-04-27 12:06:55,344][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.763669967651367, cross_entropy: 3.763669967651367 +[2025-04-27 12:06:57,862][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 3.6852993965148926, cross_entropy: 3.6852993965148926 +[2025-04-27 12:06:58,147][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 1.8215867280960083, cross_entropy: 1.8215867280960083 +[2025-04-27 12:07:00,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.989757776260376, cross_entropy: 2.989757776260376 +[2025-04-27 12:07:00,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.6589550971984863, cross_entropy: 3.6589550971984863 +[2025-04-27 12:07:02,815][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.1134824752807617, cross_entropy: 3.1134824752807617 +[2025-04-27 12:07:03,108][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.0670857429504395, cross_entropy: 2.0670857429504395 +[2025-04-27 12:07:05,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.460223436355591, cross_entropy: 3.460223436355591 +[2025-04-27 12:07:05,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 1.7909685373306274, cross_entropy: 1.7909685373306274 +[2025-04-27 12:07:08,942][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.633483409881592, cross_entropy: 2.633483409881592 +[2025-04-27 12:07:09,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 3.701587200164795, cross_entropy: 3.701587200164795 +[2025-04-27 12:07:11,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 2.0509040355682373, cross_entropy: 2.0509040355682373 +[2025-04-27 12:07:11,717][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 1.7369356155395508, cross_entropy: 1.7369356155395508 +[2025-04-27 12:07:14,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.6494081020355225, cross_entropy: 3.6494081020355225 +[2025-04-27 12:07:14,502][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 2.333648681640625, cross_entropy: 2.333648681640625 +[2025-04-27 12:07:17,177][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 3.1004598140716553, cross_entropy: 3.1004598140716553 +[2025-04-27 12:07:17,466][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.2881155014038086, cross_entropy: 3.2881155014038086 +[2025-04-27 12:07:20,164][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.2627780437469482, cross_entropy: 2.2627780437469482 +[2025-04-27 12:07:20,431][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.1950578689575195, cross_entropy: 3.1950578689575195 +[2025-04-27 12:07:23,511][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.3452961444854736, cross_entropy: 3.3452961444854736 +[2025-04-27 12:07:23,799][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 3.543593168258667, cross_entropy: 3.543593168258667 +[2025-04-27 12:07:26,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.6765213012695312, cross_entropy: 3.6765213012695312 +[2025-04-27 12:07:26,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.3805809020996094, cross_entropy: 3.3805809020996094 +[2025-04-27 12:07:29,288][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.3364808559417725, cross_entropy: 3.3364808559417725 +[2025-04-27 12:07:29,571][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 3.5193793773651123, cross_entropy: 3.5193793773651123 +[2025-04-27 12:07:32,353][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.78360652923584, cross_entropy: 3.78360652923584 +[2025-04-27 12:07:32,642][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.5015406608581543, cross_entropy: 3.5015406608581543 +[2025-04-27 12:07:35,427][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 2.136801242828369, cross_entropy: 2.136801242828369 +[2025-04-27 12:07:35,715][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 3.18044114112854, cross_entropy: 3.18044114112854 +[2025-04-27 12:07:37,633][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.772413492202759, cross_entropy: 2.772413492202759 +[2025-04-27 12:07:37,899][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.3698318004608154, cross_entropy: 2.3698318004608154 +[2025-04-27 12:07:40,504][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.4753732681274414, cross_entropy: 3.4753732681274414 +[2025-04-27 12:07:40,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.0762534141540527, cross_entropy: 2.0762534141540527 +[2025-04-27 12:07:42,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 2.34348726272583, cross_entropy: 2.34348726272583 +[2025-04-27 12:07:43,198][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 2.609736442565918, cross_entropy: 2.609736442565918 +[2025-04-27 12:07:45,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 2.981156826019287, cross_entropy: 2.981156826019287 +[2025-04-27 12:07:45,499][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.5233757495880127, cross_entropy: 3.5233757495880127 +[2025-04-27 12:07:47,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 1.815042495727539, cross_entropy: 1.815042495727539 +[2025-04-27 12:07:47,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.838038444519043, cross_entropy: 2.838038444519043 +[2025-04-27 12:07:50,264][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 2.027008056640625, cross_entropy: 2.027008056640625 +[2025-04-27 12:07:50,562][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 2.962606191635132, cross_entropy: 2.962606191635132 +[2025-04-27 12:07:54,107][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.4940085411071777, cross_entropy: 2.4940085411071777 +[2025-04-27 12:07:54,394][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.107048511505127, cross_entropy: 3.107048511505127 +[2025-04-27 12:07:56,459][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.516200304031372, cross_entropy: 3.516200304031372 +[2025-04-27 12:07:56,724][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 1.7105964422225952, cross_entropy: 1.7105964422225952 +[2025-04-27 12:07:59,144][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.6601455211639404, cross_entropy: 2.6601455211639404 +[2025-04-27 12:07:59,430][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.2271857261657715, cross_entropy: 3.2271857261657715 +[2025-04-27 12:08:02,187][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 3.463240146636963, cross_entropy: 3.463240146636963 +[2025-04-27 12:08:02,475][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.030424118041992, cross_entropy: 3.030424118041992 +[2025-04-27 12:08:04,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.883310317993164, cross_entropy: 3.883310317993164 +[2025-04-27 12:08:04,814][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.155374526977539, cross_entropy: 3.155374526977539 +[2025-04-27 12:08:08,028][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.101144790649414, cross_entropy: 2.101144790649414 +[2025-04-27 12:08:08,313][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.2048468589782715, cross_entropy: 3.2048468589782715 +[2025-04-27 12:08:10,492][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 1.548011302947998, cross_entropy: 1.548011302947998 +[2025-04-27 12:08:10,784][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 2.407514810562134, cross_entropy: 2.407514810562134 +[2025-04-27 12:08:13,122][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 1.7815667390823364, cross_entropy: 1.7815667390823364 +[2025-04-27 12:08:13,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.078676700592041, cross_entropy: 2.078676700592041 +[2025-04-27 12:08:15,760][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 1.9011030197143555, cross_entropy: 1.9011030197143555 +[2025-04-27 12:08:16,047][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 1.5842578411102295, cross_entropy: 1.5842578411102295 +[2025-04-27 12:08:18,137][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 1.5161097049713135, cross_entropy: 1.5161097049713135 +[2025-04-27 12:08:18,425][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.5596871376037598, cross_entropy: 2.5596871376037598 +[2025-04-27 12:08:20,992][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.2683374881744385, cross_entropy: 3.2683374881744385 +[2025-04-27 12:08:21,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 1.8540444374084473, cross_entropy: 1.8540444374084473 +[2025-04-27 12:08:23,916][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 1.9640865325927734, cross_entropy: 1.9640865325927734 +[2025-04-27 12:08:24,199][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.482285499572754, cross_entropy: 2.482285499572754 +[2025-04-27 12:08:26,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.2022008895874023, cross_entropy: 2.2022008895874023 +[2025-04-27 12:08:26,803][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.8547515869140625, cross_entropy: 2.8547515869140625 +[2025-04-27 12:08:29,087][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.7716658115386963, cross_entropy: 2.7716658115386963 +[2025-04-27 12:08:29,352][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.998368263244629, cross_entropy: 2.998368263244629 +[2025-04-27 12:08:31,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 4.028746128082275, cross_entropy: 4.028746128082275 +[2025-04-27 12:08:31,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.542645215988159, cross_entropy: 3.542645215988159 +[2025-04-27 12:08:34,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 1.4361646175384521, cross_entropy: 1.4361646175384521 +[2025-04-27 12:08:34,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 3.406367063522339, cross_entropy: 3.406367063522339 +[2025-04-27 12:08:36,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.411916494369507, cross_entropy: 3.411916494369507 +[2025-04-27 12:08:37,253][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 1.6756782531738281, cross_entropy: 1.6756782531738281 +[2025-04-27 12:08:40,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 1.8872114419937134, cross_entropy: 1.8872114419937134 +[2025-04-27 12:08:40,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.8207814693450928, cross_entropy: 2.8207814693450928 +[2025-04-27 12:08:43,082][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 1.773176908493042, cross_entropy: 1.773176908493042 +[2025-04-27 12:08:43,348][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.1182022094726562, cross_entropy: 2.1182022094726562 +[2025-04-27 12:08:45,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 1.920076608657837, cross_entropy: 1.920076608657837 +[2025-04-27 12:08:45,516][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 4.0019636154174805, cross_entropy: 4.0019636154174805 +[2025-04-27 12:08:47,592][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.4275567531585693, cross_entropy: 2.4275567531585693 +[2025-04-27 12:08:47,856][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.0880703926086426, cross_entropy: 2.0880703926086426 +[2025-04-27 12:08:50,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.516984224319458, cross_entropy: 2.516984224319458 +[2025-04-27 12:08:50,638][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.353276014328003, cross_entropy: 3.353276014328003 +[2025-04-27 12:08:52,946][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.2339377403259277, cross_entropy: 2.2339377403259277 +[2025-04-27 12:08:53,234][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.1538803577423096, cross_entropy: 3.1538803577423096 +[2025-04-27 12:08:55,465][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 1.90366530418396, cross_entropy: 1.90366530418396 +[2025-04-27 12:08:55,754][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 1.8768420219421387, cross_entropy: 1.8768420219421387 +[2025-04-27 12:08:59,231][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.1834585666656494, cross_entropy: 3.1834585666656494 +[2025-04-27 12:08:59,495][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.046480178833008, cross_entropy: 2.046480178833008 +[2025-04-27 12:09:01,747][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 1.5185586214065552, cross_entropy: 1.5185586214065552 +[2025-04-27 12:09:02,036][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 2.865510940551758, cross_entropy: 2.865510940551758 +[2025-04-27 12:09:05,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 1.7335654497146606, cross_entropy: 1.7335654497146606 +[2025-04-27 12:09:05,938][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.529714584350586, cross_entropy: 2.529714584350586 +[2025-04-27 12:09:08,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 1.7605235576629639, cross_entropy: 1.7605235576629639 +[2025-04-27 12:09:08,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.0921897888183594, cross_entropy: 3.0921897888183594 +[2025-04-27 12:09:11,966][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.9046974182128906, cross_entropy: 2.9046974182128906 +[2025-04-27 12:09:12,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 3.502974510192871, cross_entropy: 3.502974510192871 +[2025-04-27 12:09:14,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 1.9707238674163818, cross_entropy: 1.9707238674163818 +[2025-04-27 12:09:14,643][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.7369775772094727, cross_entropy: 2.7369775772094727 +[2025-04-27 12:09:16,930][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 1.9782363176345825, cross_entropy: 1.9782363176345825 +[2025-04-27 12:09:17,219][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.0399861335754395, cross_entropy: 2.0399861335754395 +[2025-04-27 12:09:19,956][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.216930389404297, cross_entropy: 2.216930389404297 +[2025-04-27 12:09:20,222][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 3.3841516971588135, cross_entropy: 3.3841516971588135 +[2025-04-27 12:09:22,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.3273189067840576, cross_entropy: 3.3273189067840576 +[2025-04-27 12:09:22,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.0936875343322754, cross_entropy: 2.0936875343322754 +[2025-04-27 12:09:24,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.111274242401123, cross_entropy: 2.111274242401123 +[2025-04-27 12:09:25,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.4955451488494873, cross_entropy: 2.4955451488494873 +[2025-04-27 12:09:27,673][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.740212917327881, cross_entropy: 2.740212917327881 +[2025-04-27 12:09:27,944][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 2.228532075881958, cross_entropy: 2.228532075881958 +[2025-04-27 12:09:30,282][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 1.5221900939941406, cross_entropy: 1.5221900939941406 +[2025-04-27 12:09:30,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.723802089691162, cross_entropy: 2.723802089691162 +[2025-04-27 12:09:33,073][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 1.7376246452331543, cross_entropy: 1.7376246452331543 +[2025-04-27 12:09:33,368][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.8910350799560547, cross_entropy: 3.8910350799560547 +[2025-04-27 12:09:35,478][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 3.0109682083129883, cross_entropy: 3.0109682083129883 +[2025-04-27 12:09:35,771][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 1.3675823211669922, cross_entropy: 1.3675823211669922 +[2025-04-27 12:09:38,359][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 1.4706734418869019, cross_entropy: 1.4706734418869019 +[2025-04-27 12:09:38,648][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 1.7105915546417236, cross_entropy: 1.7105915546417236 +[2025-04-27 12:09:41,612][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.240105628967285, cross_entropy: 2.240105628967285 +[2025-04-27 12:09:41,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 1.8236284255981445, cross_entropy: 1.8236284255981445 +[2025-04-27 12:09:45,160][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 1.8595584630966187, cross_entropy: 1.8595584630966187 +[2025-04-27 12:09:45,426][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.145296096801758, cross_entropy: 3.145296096801758 +[2025-04-27 12:09:47,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.5958638191223145, cross_entropy: 3.5958638191223145 +[2025-04-27 12:09:48,092][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 1.8888828754425049, cross_entropy: 1.8888828754425049 +[2025-04-27 12:09:50,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.2115345001220703, cross_entropy: 3.2115345001220703 +[2025-04-27 12:09:51,027][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 2.130392551422119, cross_entropy: 2.130392551422119 +[2025-04-27 12:09:53,773][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 1.8335204124450684, cross_entropy: 1.8335204124450684 +[2025-04-27 12:09:54,061][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 2.085693359375, cross_entropy: 2.085693359375 +[2025-04-27 12:09:56,294][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 3.149008274078369, cross_entropy: 3.149008274078369 +[2025-04-27 12:09:56,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.5658187866210938, cross_entropy: 2.5658187866210938 +[2025-04-27 12:09:59,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 2.2113375663757324, cross_entropy: 2.2113375663757324 +[2025-04-27 12:09:59,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.2647452354431152, cross_entropy: 3.2647452354431152 +[2025-04-27 12:10:01,615][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.5683176517486572, cross_entropy: 3.5683176517486572 +[2025-04-27 12:10:01,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 1.6365312337875366, cross_entropy: 1.6365312337875366 +[2025-04-27 12:10:04,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 1.7561091184616089, cross_entropy: 1.7561091184616089 +[2025-04-27 12:10:04,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 2.8336586952209473, cross_entropy: 2.8336586952209473 +[2025-04-27 12:10:06,759][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.805797576904297, cross_entropy: 3.805797576904297 +[2025-04-27 12:10:07,236][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.0986671447753906, cross_entropy: 2.0986671447753906 +[2025-04-27 12:10:09,221][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.947786569595337, cross_entropy: 2.947786569595337 +[2025-04-27 12:10:09,895][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 3.5069308280944824, cross_entropy: 3.5069308280944824 +[2025-04-27 12:10:11,641][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.0823721885681152, cross_entropy: 2.0823721885681152 +[2025-04-27 12:10:13,335][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 2.1718790531158447, cross_entropy: 2.1718790531158447 +[2025-04-27 12:10:14,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.3978939056396484, cross_entropy: 3.3978939056396484 +[2025-04-27 12:10:16,254][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 1.496720314025879, cross_entropy: 1.496720314025879 +[2025-04-27 12:10:17,021][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.388272762298584, cross_entropy: 3.388272762298584 +[2025-04-27 12:10:18,994][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 1.9497029781341553, cross_entropy: 1.9497029781341553 +[2025-04-27 12:10:19,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.7357430458068848, cross_entropy: 2.7357430458068848 +[2025-04-27 12:10:21,640][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.6419804096221924, cross_entropy: 2.6419804096221924 +[2025-04-27 12:10:22,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.6606407165527344, cross_entropy: 2.6606407165527344 +[2025-04-27 12:10:23,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 1.5460638999938965, cross_entropy: 1.5460638999938965 +[2025-04-27 12:10:24,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 2.006315231323242, cross_entropy: 2.006315231323242 +[2025-04-27 12:10:25,852][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.5269205570220947, cross_entropy: 2.5269205570220947 +[2025-04-27 12:10:26,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.1885128021240234, cross_entropy: 2.1885128021240234 +[2025-04-27 12:10:28,753][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 3.8309390544891357, cross_entropy: 3.8309390544891357 +[2025-04-27 12:10:29,060][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.128328323364258, cross_entropy: 3.128328323364258 +[2025-04-27 12:10:31,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.3474478721618652, cross_entropy: 2.3474478721618652 +[2025-04-27 12:10:31,832][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.784931182861328, cross_entropy: 2.784931182861328 +[2025-04-27 12:10:34,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 3.9262633323669434, cross_entropy: 3.9262633323669434 +[2025-04-27 12:10:34,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.923975944519043, cross_entropy: 2.923975944519043 +[2025-04-27 12:10:37,902][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.283151388168335, cross_entropy: 2.283151388168335 +[2025-04-27 12:10:38,191][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 2.2137224674224854, cross_entropy: 2.2137224674224854 +[2025-04-27 12:10:40,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 1.8760287761688232, cross_entropy: 1.8760287761688232 +[2025-04-27 12:10:41,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.6277360916137695, cross_entropy: 3.6277360916137695 +[2025-04-27 12:10:43,988][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.695258140563965, cross_entropy: 2.695258140563965 +[2025-04-27 12:10:44,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 1.7474501132965088, cross_entropy: 1.7474501132965088 +[2025-04-27 12:10:46,760][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.1417489051818848, cross_entropy: 2.1417489051818848 +[2025-04-27 12:10:47,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 3.5041096210479736, cross_entropy: 3.5041096210479736 +[2025-04-27 12:10:49,125][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.782402515411377, cross_entropy: 1.782402515411377 +[2025-04-27 12:10:49,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 1.3932015895843506, cross_entropy: 1.3932015895843506 +[2025-04-27 12:10:51,358][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 1.8676397800445557, cross_entropy: 1.8676397800445557 +[2025-04-27 12:10:51,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 3.1724791526794434, cross_entropy: 3.1724791526794434 +[2025-04-27 12:10:53,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 1.9271066188812256, cross_entropy: 1.9271066188812256 +[2025-04-27 12:10:54,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 2.008240222930908, cross_entropy: 2.008240222930908 +[2025-04-27 12:10:56,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 3.5246174335479736, cross_entropy: 3.5246174335479736 +[2025-04-27 12:10:56,919][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 1.894940733909607, cross_entropy: 1.894940733909607 +[2025-04-27 12:10:59,391][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 2.020268201828003, cross_entropy: 2.020268201828003 +[2025-04-27 12:10:59,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 1.6776821613311768, cross_entropy: 1.6776821613311768 +[2025-04-27 12:11:02,226][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.8677995204925537, cross_entropy: 2.8677995204925537 +[2025-04-27 12:11:02,516][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 3.5128097534179688, cross_entropy: 3.5128097534179688 +[2025-04-27 12:11:04,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 1.6979091167449951, cross_entropy: 1.6979091167449951 +[2025-04-27 12:11:05,084][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 1.2973902225494385, cross_entropy: 1.2973902225494385 +[2025-04-27 12:11:08,573][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 2.8909339904785156, cross_entropy: 2.8909339904785156 +[2025-04-27 12:11:08,838][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 1.7953896522521973, cross_entropy: 1.7953896522521973 +[2025-04-27 12:11:10,945][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 1.667073369026184, cross_entropy: 1.667073369026184 +[2025-04-27 12:11:11,233][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.198935031890869, cross_entropy: 3.198935031890869 +[2025-04-27 12:11:13,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 1.7732834815979004, cross_entropy: 1.7732834815979004 +[2025-04-27 12:11:14,120][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.2601125240325928, cross_entropy: 3.2601125240325928 +[2025-04-27 12:11:16,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 2.286015033721924, cross_entropy: 2.286015033721924 +[2025-04-27 12:11:17,032][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.631338596343994, cross_entropy: 2.631338596343994 +[2025-04-27 12:11:20,008][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 1.7927534580230713, cross_entropy: 1.7927534580230713 +[2025-04-27 12:11:20,297][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 1.329777479171753, cross_entropy: 1.329777479171753 +[2025-04-27 12:11:22,861][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.5857386589050293, cross_entropy: 2.5857386589050293 +[2025-04-27 12:11:23,148][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.3823702335357666, cross_entropy: 2.3823702335357666 +[2025-04-27 12:11:25,481][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.2475814819335938, cross_entropy: 2.2475814819335938 +[2025-04-27 12:11:25,769][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.6985628604888916, cross_entropy: 2.6985628604888916 +[2025-04-27 12:11:27,783][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.379958391189575, cross_entropy: 2.379958391189575 +[2025-04-27 12:11:28,088][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 3.546299934387207, cross_entropy: 3.546299934387207 +[2025-04-27 12:11:30,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.6006979942321777, cross_entropy: 2.6006979942321777 +[2025-04-27 12:11:30,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.565361738204956, cross_entropy: 2.565361738204956 +[2025-04-27 12:11:32,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.136323928833008, cross_entropy: 2.136323928833008 +[2025-04-27 12:11:33,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 2.040161609649658, cross_entropy: 2.040161609649658 +[2025-04-27 12:11:35,233][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 2.251664876937866, cross_entropy: 2.251664876937866 +[2025-04-27 12:11:35,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 2.975369930267334, cross_entropy: 2.975369930267334 +[2025-04-27 12:11:37,841][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 2.2518272399902344, cross_entropy: 2.2518272399902344 +[2025-04-27 12:11:38,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 3.424985885620117, cross_entropy: 3.424985885620117 +[2025-04-27 12:11:39,948][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 1.666666030883789, cross_entropy: 1.666666030883789 +[2025-04-27 12:11:40,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.2541840076446533, cross_entropy: 3.2541840076446533 +[2025-04-27 12:11:42,534][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 3.207601308822632, cross_entropy: 3.207601308822632 +[2025-04-27 12:11:42,918][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 1.709248423576355, cross_entropy: 1.709248423576355 +[2025-04-27 12:11:44,989][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 1.78359055519104, cross_entropy: 1.78359055519104 +[2025-04-27 12:11:45,492][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 3.611143112182617, cross_entropy: 3.611143112182617 +[2025-04-27 12:11:47,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 1.630235195159912, cross_entropy: 1.630235195159912 +[2025-04-27 12:11:47,586][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 3.584076166152954, cross_entropy: 3.584076166152954 +[2025-04-27 12:11:50,015][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.166445016860962, cross_entropy: 2.166445016860962 +[2025-04-27 12:11:50,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.130805492401123, cross_entropy: 3.130805492401123 +[2025-04-27 12:11:52,568][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 1.7466082572937012, cross_entropy: 1.7466082572937012 +[2025-04-27 12:11:52,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 3.274570941925049, cross_entropy: 3.274570941925049 +[2025-04-27 12:11:54,945][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 1.8941657543182373, cross_entropy: 1.8941657543182373 +[2025-04-27 12:11:55,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.524390935897827, cross_entropy: 2.524390935897827 +[2025-04-27 12:11:57,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.212289333343506, cross_entropy: 2.212289333343506 +[2025-04-27 12:11:57,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 1.5424401760101318, cross_entropy: 1.5424401760101318 +[2025-04-27 12:11:59,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 3.0961790084838867, cross_entropy: 3.0961790084838867 +[2025-04-27 12:12:00,736][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 1.5154807567596436, cross_entropy: 1.5154807567596436 +[2025-04-27 12:12:02,582][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.5638222694396973, cross_entropy: 3.5638222694396973 +[2025-04-27 12:12:02,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 1.8488006591796875, cross_entropy: 1.8488006591796875 +[2025-04-27 12:12:05,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.839320659637451, cross_entropy: 2.839320659637451 +[2025-04-27 12:12:06,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 2.4470741748809814, cross_entropy: 2.4470741748809814 +[2025-04-27 12:12:08,476][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 2.5515923500061035, cross_entropy: 2.5515923500061035 +[2025-04-27 12:12:08,765][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.1172966957092285, cross_entropy: 2.1172966957092285 +[2025-04-27 12:12:11,125][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.0251083374023438, cross_entropy: 2.0251083374023438 +[2025-04-27 12:12:11,415][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 1.4048994779586792, cross_entropy: 1.4048994779586792 +[2025-04-27 12:12:13,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.7184560298919678, cross_entropy: 1.7184560298919678 +[2025-04-27 12:12:14,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.501206159591675, cross_entropy: 3.501206159591675 +[2025-04-27 12:12:16,613][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 1.6884266138076782, cross_entropy: 1.6884266138076782 +[2025-04-27 12:12:16,906][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 1.5467555522918701, cross_entropy: 1.5467555522918701 +[2025-04-27 12:12:19,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 3.5595903396606445, cross_entropy: 3.5595903396606445 +[2025-04-27 12:12:19,672][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 3.7527031898498535, cross_entropy: 3.7527031898498535 +[2025-04-27 12:12:21,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 1.748096227645874, cross_entropy: 1.748096227645874 +[2025-04-27 12:12:21,953][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 1.4325246810913086, cross_entropy: 1.4325246810913086 +[2025-04-27 12:12:24,251][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.3864212036132812, cross_entropy: 3.3864212036132812 +[2025-04-27 12:12:24,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.4541101455688477, cross_entropy: 3.4541101455688477 +[2025-04-27 12:12:27,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 1.7812530994415283, cross_entropy: 1.7812530994415283 +[2025-04-27 12:12:27,384][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 1.929389238357544, cross_entropy: 1.929389238357544 +[2025-04-27 12:12:30,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.905583381652832, cross_entropy: 1.905583381652832 +[2025-04-27 12:12:30,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 3.210540294647217, cross_entropy: 3.210540294647217 +[2025-04-27 12:12:32,682][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.4935660362243652, cross_entropy: 2.4935660362243652 +[2025-04-27 12:12:32,971][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.4289684295654297, cross_entropy: 3.4289684295654297 +[2025-04-27 12:12:35,346][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 1.8853999376296997, cross_entropy: 1.8853999376296997 +[2025-04-27 12:12:35,634][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 3.164722204208374, cross_entropy: 3.164722204208374 +[2025-04-27 12:12:37,912][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.926133155822754, cross_entropy: 2.926133155822754 +[2025-04-27 12:12:38,178][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 3.172485589981079, cross_entropy: 3.172485589981079 +[2025-04-27 12:12:41,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.39382266998291, cross_entropy: 2.39382266998291 +[2025-04-27 12:12:41,408][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.142603874206543, cross_entropy: 3.142603874206543 +[2025-04-27 12:12:43,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 1.565107822418213, cross_entropy: 1.565107822418213 +[2025-04-27 12:12:44,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 1.8354527950286865, cross_entropy: 1.8354527950286865 +[2025-04-27 12:12:46,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.6492483615875244, cross_entropy: 2.6492483615875244 +[2025-04-27 12:12:46,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 3.1059083938598633, cross_entropy: 3.1059083938598633 +[2025-04-27 12:12:49,066][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.4328861236572266, cross_entropy: 2.4328861236572266 +[2025-04-27 12:12:49,331][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 1.6494784355163574, cross_entropy: 1.6494784355163574 +[2025-04-27 12:12:51,576][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 3.302492141723633, cross_entropy: 3.302492141723633 +[2025-04-27 12:12:51,843][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.658541202545166, cross_entropy: 2.658541202545166 +[2025-04-27 12:12:54,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 2.686413288116455, cross_entropy: 2.686413288116455 +[2025-04-27 12:12:54,396][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.7435632944107056, cross_entropy: 1.7435632944107056 +[2025-04-27 12:12:56,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.701348304748535, cross_entropy: 2.701348304748535 +[2025-04-27 12:12:56,953][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 2.3638222217559814, cross_entropy: 2.3638222217559814 +[2025-04-27 12:12:58,928][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.047909736633301, cross_entropy: 3.047909736633301 +[2025-04-27 12:12:59,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.0514843463897705, cross_entropy: 3.0514843463897705 +[2025-04-27 12:13:01,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 1.613529920578003, cross_entropy: 1.613529920578003 +[2025-04-27 12:13:02,073][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 1.870262622833252, cross_entropy: 1.870262622833252 +[2025-04-27 12:13:04,204][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 1.8059463500976562, cross_entropy: 1.8059463500976562 +[2025-04-27 12:13:04,549][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.2646384239196777, cross_entropy: 3.2646384239196777 +[2025-04-27 12:13:07,273][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.912060260772705, cross_entropy: 2.912060260772705 +[2025-04-27 12:13:07,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 1.7547017335891724, cross_entropy: 1.7547017335891724 +[2025-04-27 12:13:09,968][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.946030616760254, cross_entropy: 2.946030616760254 +[2025-04-27 12:13:10,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 2.115142345428467, cross_entropy: 2.115142345428467 +[2025-04-27 12:13:12,761][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 3.0282750129699707, cross_entropy: 3.0282750129699707 +[2025-04-27 12:13:13,108][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 2.021301746368408, cross_entropy: 2.021301746368408 +[2025-04-27 12:13:16,024][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.3516769409179688, cross_entropy: 3.3516769409179688 +[2025-04-27 12:13:17,238][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 1.8010053634643555, cross_entropy: 1.8010053634643555 +[2025-04-27 12:13:18,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.2221484184265137, cross_entropy: 3.2221484184265137 +[2025-04-27 12:13:19,903][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.5755562782287598, cross_entropy: 3.5755562782287598 +[2025-04-27 12:13:21,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 1.5386700630187988, cross_entropy: 1.5386700630187988 +[2025-04-27 12:13:22,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 1.8979923725128174, cross_entropy: 1.8979923725128174 +[2025-04-27 12:13:24,076][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.3303945064544678, cross_entropy: 2.3303945064544678 +[2025-04-27 12:13:25,481][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 1.5069818496704102, cross_entropy: 1.5069818496704102 +[2025-04-27 12:13:27,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 2.0226566791534424, cross_entropy: 2.0226566791534424 +[2025-04-27 12:13:28,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.5347779989242554, cross_entropy: 1.5347779989242554 +[2025-04-27 12:13:29,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.496570110321045, cross_entropy: 3.496570110321045 +[2025-04-27 12:13:31,319][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 2.056947708129883, cross_entropy: 2.056947708129883 +[2025-04-27 12:13:32,810][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 2.935342311859131, cross_entropy: 2.935342311859131 +[2025-04-27 12:15:43,887][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.5786948204040527, cross_entropy: 2.5786948204040527 +[2025-04-27 12:15:43,887][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.6092123985290527, cross_entropy: 1.6092123985290527 +[2025-04-27 12:15:44,121][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:15:44,295][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch2.pth. +[2025-04-27 12:15:44,487][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:15:48,735][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 3.1033682823181152, cross_entropy: 3.1033682823181152 +[2025-04-27 12:15:49,000][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.240166425704956, cross_entropy: 1.240166425704956 +[2025-04-27 12:15:52,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 1.8334646224975586, cross_entropy: 1.8334646224975586 +[2025-04-27 12:15:52,411][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 2.7327628135681152, cross_entropy: 2.7327628135681152 +[2025-04-27 12:15:55,045][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.4902985095977783, cross_entropy: 1.4902985095977783 +[2025-04-27 12:15:55,331][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.227741241455078, cross_entropy: 2.227741241455078 +[2025-04-27 12:15:57,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.5323294401168823, cross_entropy: 1.5323294401168823 +[2025-04-27 12:15:58,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 2.362715721130371, cross_entropy: 2.362715721130371 +[2025-04-27 12:16:00,624][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.115026593208313, cross_entropy: 1.115026593208313 +[2025-04-27 12:16:00,915][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 2.3416006565093994, cross_entropy: 2.3416006565093994 +[2025-04-27 12:16:02,876][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.449694871902466, cross_entropy: 2.449694871902466 +[2025-04-27 12:16:03,166][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 1.7006008625030518, cross_entropy: 1.7006008625030518 +[2025-04-27 12:16:05,304][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.9471163749694824, cross_entropy: 1.9471163749694824 +[2025-04-27 12:16:05,594][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.2971153259277344, cross_entropy: 2.2971153259277344 +[2025-04-27 12:16:07,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 1.9448256492614746, cross_entropy: 1.9448256492614746 +[2025-04-27 12:16:08,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 1.946984052658081, cross_entropy: 1.946984052658081 +[2025-04-27 12:16:10,658][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.365691661834717, cross_entropy: 3.365691661834717 +[2025-04-27 12:16:11,961][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 1.9873898029327393, cross_entropy: 1.9873898029327393 +[2025-04-27 12:16:13,510][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.2361170053482056, cross_entropy: 1.2361170053482056 +[2025-04-27 12:16:15,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.7417773008346558, cross_entropy: 1.7417773008346558 +[2025-04-27 12:16:16,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 3.196155548095703, cross_entropy: 3.196155548095703 +[2025-04-27 12:16:17,672][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.4950084686279297, cross_entropy: 1.4950084686279297 +[2025-04-27 12:16:18,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.4793429374694824, cross_entropy: 3.4793429374694824 +[2025-04-27 12:16:20,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 2.718205451965332, cross_entropy: 2.718205451965332 +[2025-04-27 12:16:21,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.278146982192993, cross_entropy: 3.278146982192993 +[2025-04-27 12:16:24,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 2.240365982055664, cross_entropy: 2.240365982055664 +[2025-04-27 12:16:24,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 1.3063722848892212, cross_entropy: 1.3063722848892212 +[2025-04-27 12:16:28,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 1.9122532606124878, cross_entropy: 1.9122532606124878 +[2025-04-27 12:16:28,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.208220958709717, cross_entropy: 3.208220958709717 +[2025-04-27 12:16:31,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.804572582244873, cross_entropy: 2.804572582244873 +[2025-04-27 12:16:31,291][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.5396862030029297, cross_entropy: 1.5396862030029297 +[2025-04-27 12:16:33,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 3.1585206985473633, cross_entropy: 3.1585206985473633 +[2025-04-27 12:16:33,509][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.0773866176605225, cross_entropy: 3.0773866176605225 +[2025-04-27 12:16:35,980][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 1.9572734832763672, cross_entropy: 1.9572734832763672 +[2025-04-27 12:16:36,268][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 3.297801971435547, cross_entropy: 3.297801971435547 +[2025-04-27 12:16:39,143][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.126265525817871, cross_entropy: 3.126265525817871 +[2025-04-27 12:16:39,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 1.9784202575683594, cross_entropy: 1.9784202575683594 +[2025-04-27 12:16:42,085][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.9707610607147217, cross_entropy: 1.9707610607147217 +[2025-04-27 12:16:42,387][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 1.164817214012146, cross_entropy: 1.164817214012146 +[2025-04-27 12:16:45,210][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 1.791969656944275, cross_entropy: 1.791969656944275 +[2025-04-27 12:16:45,492][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.632817268371582, cross_entropy: 1.632817268371582 +[2025-04-27 12:16:48,158][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 2.5830297470092773, cross_entropy: 2.5830297470092773 +[2025-04-27 12:16:48,421][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 1.3889923095703125, cross_entropy: 1.3889923095703125 +[2025-04-27 12:16:51,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.342052936553955, cross_entropy: 2.342052936553955 +[2025-04-27 12:16:51,585][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.6925830841064453, cross_entropy: 2.6925830841064453 +[2025-04-27 12:16:54,405][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 3.1930768489837646, cross_entropy: 3.1930768489837646 +[2025-04-27 12:16:54,699][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.3736317157745361, cross_entropy: 1.3736317157745361 +[2025-04-27 12:16:57,901][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 3.5238213539123535, cross_entropy: 3.5238213539123535 +[2025-04-27 12:16:58,167][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.9688377380371094, cross_entropy: 2.9688377380371094 +[2025-04-27 12:17:00,978][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 1.4794485569000244, cross_entropy: 1.4794485569000244 +[2025-04-27 12:17:01,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 1.5484747886657715, cross_entropy: 1.5484747886657715 +[2025-04-27 12:17:03,232][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 1.8711752891540527, cross_entropy: 1.8711752891540527 +[2025-04-27 12:17:03,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.920753240585327, cross_entropy: 2.920753240585327 +[2025-04-27 12:17:06,763][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.0091073513031006, cross_entropy: 3.0091073513031006 +[2025-04-27 12:17:07,029][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.0258326530456543, cross_entropy: 3.0258326530456543 +[2025-04-27 12:17:10,550][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.8502719402313232, cross_entropy: 2.8502719402313232 +[2025-04-27 12:17:10,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.071988582611084, cross_entropy: 3.071988582611084 +[2025-04-27 12:17:13,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.4169745445251465, cross_entropy: 2.4169745445251465 +[2025-04-27 12:17:13,327][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.0832037925720215, cross_entropy: 3.0832037925720215 +[2025-04-27 12:17:16,554][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 3.600200653076172, cross_entropy: 3.600200653076172 +[2025-04-27 12:17:16,818][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.6237001419067383, cross_entropy: 2.6237001419067383 +[2025-04-27 12:17:19,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.483633518218994, cross_entropy: 2.483633518218994 +[2025-04-27 12:17:19,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.0642740726470947, cross_entropy: 3.0642740726470947 +[2025-04-27 12:17:22,584][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 1.6696747541427612, cross_entropy: 1.6696747541427612 +[2025-04-27 12:17:22,871][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.511488676071167, cross_entropy: 3.511488676071167 +[2025-04-27 12:17:26,189][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.9629979133605957, cross_entropy: 2.9629979133605957 +[2025-04-27 12:17:26,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.7231768369674683, cross_entropy: 1.7231768369674683 +[2025-04-27 12:17:28,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.333366870880127, cross_entropy: 3.333366870880127 +[2025-04-27 12:17:28,944][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.2302918434143066, cross_entropy: 2.2302918434143066 +[2025-04-27 12:17:31,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 2.4853978157043457, cross_entropy: 2.4853978157043457 +[2025-04-27 12:17:31,733][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.4527411460876465, cross_entropy: 2.4527411460876465 +[2025-04-27 12:17:34,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.3721351623535156, cross_entropy: 2.3721351623535156 +[2025-04-27 12:17:34,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 1.9452993869781494, cross_entropy: 1.9452993869781494 +[2025-04-27 12:17:37,637][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.5752875804901123, cross_entropy: 2.5752875804901123 +[2025-04-27 12:17:37,902][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.364503860473633, cross_entropy: 3.364503860473633 +[2025-04-27 12:17:41,127][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 1.4876673221588135, cross_entropy: 1.4876673221588135 +[2025-04-27 12:17:41,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 2.643421173095703, cross_entropy: 2.643421173095703 +[2025-04-27 12:17:44,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 1.7734664678573608, cross_entropy: 1.7734664678573608 +[2025-04-27 12:17:44,682][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 2.8515825271606445, cross_entropy: 2.8515825271606445 +[2025-04-27 12:17:47,190][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 1.3644222021102905, cross_entropy: 1.3644222021102905 +[2025-04-27 12:17:47,490][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.1849374771118164, cross_entropy: 3.1849374771118164 +[2025-04-27 12:17:49,697][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.7830052375793457, cross_entropy: 1.7830052375793457 +[2025-04-27 12:17:49,994][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 2.8281631469726562, cross_entropy: 2.8281631469726562 +[2025-04-27 12:17:52,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 1.614903450012207, cross_entropy: 1.614903450012207 +[2025-04-27 12:17:52,806][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 1.6928868293762207, cross_entropy: 1.6928868293762207 +[2025-04-27 12:17:55,287][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 1.8815088272094727, cross_entropy: 1.8815088272094727 +[2025-04-27 12:17:55,588][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 2.1519229412078857, cross_entropy: 2.1519229412078857 +[2025-04-27 12:17:58,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.185670852661133, cross_entropy: 3.185670852661133 +[2025-04-27 12:17:58,952][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.2524170875549316, cross_entropy: 3.2524170875549316 +[2025-04-27 12:18:01,816][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 3.3527870178222656, cross_entropy: 3.3527870178222656 +[2025-04-27 12:18:02,082][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 3.2920660972595215, cross_entropy: 3.2920660972595215 +[2025-04-27 12:18:04,465][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.4403650760650635, cross_entropy: 1.4403650760650635 +[2025-04-27 12:18:04,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.3992551565170288, cross_entropy: 1.3992551565170288 +[2025-04-27 12:18:07,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.6908950805664062, cross_entropy: 2.6908950805664062 +[2025-04-27 12:18:07,634][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.2288482189178467, cross_entropy: 3.2288482189178467 +[2025-04-27 12:18:10,374][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.177879810333252, cross_entropy: 1.177879810333252 +[2025-04-27 12:18:10,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.2617435455322266, cross_entropy: 3.2617435455322266 +[2025-04-27 12:18:13,212][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.287349224090576, cross_entropy: 2.287349224090576 +[2025-04-27 12:18:13,517][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.32072114944458, cross_entropy: 2.32072114944458 +[2025-04-27 12:18:16,006][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 1.9914761781692505, cross_entropy: 1.9914761781692505 +[2025-04-27 12:18:16,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.057244300842285, cross_entropy: 2.057244300842285 +[2025-04-27 12:18:18,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 2.03422474861145, cross_entropy: 2.03422474861145 +[2025-04-27 12:18:18,516][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.4130823612213135, cross_entropy: 2.4130823612213135 +[2025-04-27 12:18:21,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.8494683504104614, cross_entropy: 1.8494683504104614 +[2025-04-27 12:18:21,650][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 1.8852276802062988, cross_entropy: 1.8852276802062988 +[2025-04-27 12:18:24,310][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 1.5644595623016357, cross_entropy: 1.5644595623016357 +[2025-04-27 12:18:24,606][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 1.8472797870635986, cross_entropy: 1.8472797870635986 +[2025-04-27 12:18:26,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 1.4388877153396606, cross_entropy: 1.4388877153396606 +[2025-04-27 12:18:27,143][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 2.321484088897705, cross_entropy: 2.321484088897705 +[2025-04-27 12:18:29,741][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 1.413935661315918, cross_entropy: 1.413935661315918 +[2025-04-27 12:18:30,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.2875194549560547, cross_entropy: 2.2875194549560547 +[2025-04-27 12:18:32,920][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.548580288887024, cross_entropy: 1.548580288887024 +[2025-04-27 12:18:33,184][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 1.7402710914611816, cross_entropy: 1.7402710914611816 +[2025-04-27 12:18:36,118][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 3.1644415855407715, cross_entropy: 3.1644415855407715 +[2025-04-27 12:18:36,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 2.875563383102417, cross_entropy: 2.875563383102417 +[2025-04-27 12:18:38,749][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.521995186805725, cross_entropy: 1.521995186805725 +[2025-04-27 12:18:39,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.1775875091552734, cross_entropy: 2.1775875091552734 +[2025-04-27 12:18:40,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.292976140975952, cross_entropy: 2.292976140975952 +[2025-04-27 12:18:41,133][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.4479897022247314, cross_entropy: 3.4479897022247314 +[2025-04-27 12:18:43,677][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.5653905868530273, cross_entropy: 2.5653905868530273 +[2025-04-27 12:18:43,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 1.3809821605682373, cross_entropy: 1.3809821605682373 +[2025-04-27 12:18:47,505][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 1.612738847732544, cross_entropy: 1.612738847732544 +[2025-04-27 12:18:47,796][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.4035756587982178, cross_entropy: 2.4035756587982178 +[2025-04-27 12:18:50,205][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 1.6069755554199219, cross_entropy: 1.6069755554199219 +[2025-04-27 12:18:50,502][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.274559497833252, cross_entropy: 3.274559497833252 +[2025-04-27 12:18:52,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.492280960083008, cross_entropy: 2.492280960083008 +[2025-04-27 12:18:53,150][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.4380972385406494, cross_entropy: 1.4380972385406494 +[2025-04-27 12:18:55,743][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 1.8755388259887695, cross_entropy: 1.8755388259887695 +[2025-04-27 12:18:56,040][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.0395684242248535, cross_entropy: 3.0395684242248535 +[2025-04-27 12:18:58,591][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.1682941913604736, cross_entropy: 2.1682941913604736 +[2025-04-27 12:18:58,855][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 1.89479660987854, cross_entropy: 1.89479660987854 +[2025-04-27 12:19:01,217][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 1.511618971824646, cross_entropy: 1.511618971824646 +[2025-04-27 12:19:01,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.2851333618164062, cross_entropy: 2.2851333618164062 +[2025-04-27 12:19:03,849][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.6653692722320557, cross_entropy: 2.6653692722320557 +[2025-04-27 12:19:04,115][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.2169177532196045, cross_entropy: 2.2169177532196045 +[2025-04-27 12:19:06,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.731501579284668, cross_entropy: 1.731501579284668 +[2025-04-27 12:19:06,684][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.3190319538116455, cross_entropy: 2.3190319538116455 +[2025-04-27 12:19:09,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.5764002799987793, cross_entropy: 1.5764002799987793 +[2025-04-27 12:19:09,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.875234365463257, cross_entropy: 2.875234365463257 +[2025-04-27 12:19:12,553][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 1.7652130126953125, cross_entropy: 1.7652130126953125 +[2025-04-27 12:19:12,820][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.321167469024658, cross_entropy: 2.321167469024658 +[2025-04-27 12:19:15,561][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.2746236324310303, cross_entropy: 1.2746236324310303 +[2025-04-27 12:19:15,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.6913905143737793, cross_entropy: 2.6913905143737793 +[2025-04-27 12:19:19,109][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 1.8088594675064087, cross_entropy: 1.8088594675064087 +[2025-04-27 12:19:19,387][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.0727248191833496, cross_entropy: 2.0727248191833496 +[2025-04-27 12:19:21,978][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.4341492652893066, cross_entropy: 2.4341492652893066 +[2025-04-27 12:19:22,270][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.3118950128555298, cross_entropy: 1.3118950128555298 +[2025-04-27 12:19:24,979][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.1792654991149902, cross_entropy: 3.1792654991149902 +[2025-04-27 12:19:25,270][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 1.406625509262085, cross_entropy: 1.406625509262085 +[2025-04-27 12:19:27,693][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 1.4540246725082397, cross_entropy: 1.4540246725082397 +[2025-04-27 12:19:27,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.257952332496643, cross_entropy: 1.257952332496643 +[2025-04-27 12:19:30,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 1.5093261003494263, cross_entropy: 1.5093261003494263 +[2025-04-27 12:19:30,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 1.960265040397644, cross_entropy: 1.960265040397644 +[2025-04-27 12:19:33,037][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 2.075585126876831, cross_entropy: 2.075585126876831 +[2025-04-27 12:19:33,302][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.4347589015960693, cross_entropy: 2.4347589015960693 +[2025-04-27 12:19:36,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 1.765167236328125, cross_entropy: 1.765167236328125 +[2025-04-27 12:19:36,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.5714890956878662, cross_entropy: 1.5714890956878662 +[2025-04-27 12:19:38,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 1.3642148971557617, cross_entropy: 1.3642148971557617 +[2025-04-27 12:19:38,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 1.7619171142578125, cross_entropy: 1.7619171142578125 +[2025-04-27 12:19:41,121][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 1.0582821369171143, cross_entropy: 1.0582821369171143 +[2025-04-27 12:19:41,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.307466983795166, cross_entropy: 3.307466983795166 +[2025-04-27 12:19:44,034][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.2751524448394775, cross_entropy: 3.2751524448394775 +[2025-04-27 12:19:44,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.3413171768188477, cross_entropy: 3.3413171768188477 +[2025-04-27 12:19:47,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 1.6927504539489746, cross_entropy: 1.6927504539489746 +[2025-04-27 12:19:47,326][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 2.791494369506836, cross_entropy: 2.791494369506836 +[2025-04-27 12:19:50,629][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.6443803310394287, cross_entropy: 1.6443803310394287 +[2025-04-27 12:19:50,931][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 1.3788152933120728, cross_entropy: 1.3788152933120728 +[2025-04-27 12:19:53,857][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 3.0136494636535645, cross_entropy: 3.0136494636535645 +[2025-04-27 12:19:54,123][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.3504605293273926, cross_entropy: 1.3504605293273926 +[2025-04-27 12:19:56,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.094451904296875, cross_entropy: 3.094451904296875 +[2025-04-27 12:19:56,837][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 1.9233555793762207, cross_entropy: 1.9233555793762207 +[2025-04-27 12:19:59,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.4222333431243896, cross_entropy: 2.4222333431243896 +[2025-04-27 12:19:59,804][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.057344436645508, cross_entropy: 3.057344436645508 +[2025-04-27 12:20:02,111][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 1.6747069358825684, cross_entropy: 1.6747069358825684 +[2025-04-27 12:20:02,403][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.2419629096984863, cross_entropy: 2.2419629096984863 +[2025-04-27 12:20:04,574][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.6641998291015625, cross_entropy: 2.6641998291015625 +[2025-04-27 12:20:04,865][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.244464635848999, cross_entropy: 2.244464635848999 +[2025-04-27 12:20:07,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 3.0935792922973633, cross_entropy: 3.0935792922973633 +[2025-04-27 12:20:08,222][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.494492530822754, cross_entropy: 1.494492530822754 +[2025-04-27 12:20:10,088][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.552551507949829, cross_entropy: 2.552551507949829 +[2025-04-27 12:20:10,378][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.3572168350219727, cross_entropy: 1.3572168350219727 +[2025-04-27 12:20:12,585][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.8319497108459473, cross_entropy: 2.8319497108459473 +[2025-04-27 12:20:12,874][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.153109073638916, cross_entropy: 2.153109073638916 +[2025-04-27 12:20:15,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.469494342803955, cross_entropy: 2.469494342803955 +[2025-04-27 12:20:15,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 2.7065012454986572, cross_entropy: 2.7065012454986572 +[2025-04-27 12:20:17,937][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 3.3158135414123535, cross_entropy: 3.3158135414123535 +[2025-04-27 12:20:18,201][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.1814348697662354, cross_entropy: 2.1814348697662354 +[2025-04-27 12:20:21,024][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.4706218242645264, cross_entropy: 2.4706218242645264 +[2025-04-27 12:20:21,288][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.0463404655456543, cross_entropy: 3.0463404655456543 +[2025-04-27 12:20:24,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.265756845474243, cross_entropy: 3.265756845474243 +[2025-04-27 12:20:24,456][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.2101614475250244, cross_entropy: 2.2101614475250244 +[2025-04-27 12:20:26,898][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 1.7606308460235596, cross_entropy: 1.7606308460235596 +[2025-04-27 12:20:27,178][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.7838473320007324, cross_entropy: 2.7838473320007324 +[2025-04-27 12:20:29,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 1.3627511262893677, cross_entropy: 1.3627511262893677 +[2025-04-27 12:20:29,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 2.8538856506347656, cross_entropy: 2.8538856506347656 +[2025-04-27 12:20:31,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.468841314315796, cross_entropy: 2.468841314315796 +[2025-04-27 12:20:32,267][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 1.3986382484436035, cross_entropy: 1.3986382484436035 +[2025-04-27 12:20:34,831][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 2.29414963722229, cross_entropy: 2.29414963722229 +[2025-04-27 12:20:35,096][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.3803553581237793, cross_entropy: 1.3803553581237793 +[2025-04-27 12:20:37,516][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 2.7197513580322266, cross_entropy: 2.7197513580322266 +[2025-04-27 12:20:37,806][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 1.5629645586013794, cross_entropy: 1.5629645586013794 +[2025-04-27 12:20:40,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.5875425338745117, cross_entropy: 2.5875425338745117 +[2025-04-27 12:20:40,809][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.1069512367248535, cross_entropy: 3.1069512367248535 +[2025-04-27 12:20:43,646][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.929947853088379, cross_entropy: 2.929947853088379 +[2025-04-27 12:20:43,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.240788459777832, cross_entropy: 3.240788459777832 +[2025-04-27 12:20:46,638][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 3.058622121810913, cross_entropy: 3.058622121810913 +[2025-04-27 12:20:46,930][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.5196404457092285, cross_entropy: 2.5196404457092285 +[2025-04-27 12:20:48,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.26669979095459, cross_entropy: 2.26669979095459 +[2025-04-27 12:20:49,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 1.4904286861419678, cross_entropy: 1.4904286861419678 +[2025-04-27 12:20:50,951][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.6839590072631836, cross_entropy: 2.6839590072631836 +[2025-04-27 12:20:51,255][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 2.5516748428344727, cross_entropy: 2.5516748428344727 +[2025-04-27 12:20:53,724][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.6472079753875732, cross_entropy: 1.6472079753875732 +[2025-04-27 12:20:54,011][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 1.4567968845367432, cross_entropy: 1.4567968845367432 +[2025-04-27 12:20:56,704][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.0300064086914062, cross_entropy: 2.0300064086914062 +[2025-04-27 12:20:56,992][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.38352632522583, cross_entropy: 1.38352632522583 +[2025-04-27 12:20:59,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 1.6753178834915161, cross_entropy: 1.6753178834915161 +[2025-04-27 12:20:59,623][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.1318511962890625, cross_entropy: 2.1318511962890625 +[2025-04-27 12:21:01,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 2.2505667209625244, cross_entropy: 2.2505667209625244 +[2025-04-27 12:21:02,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.770993232727051, cross_entropy: 2.770993232727051 +[2025-04-27 12:21:04,631][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 1.7207741737365723, cross_entropy: 1.7207741737365723 +[2025-04-27 12:21:04,919][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.7252429723739624, cross_entropy: 1.7252429723739624 +[2025-04-27 12:21:07,374][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 3.539299726486206, cross_entropy: 3.539299726486206 +[2025-04-27 12:21:07,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.20204496383667, cross_entropy: 3.20204496383667 +[2025-04-27 12:21:09,998][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 2.874635696411133, cross_entropy: 2.874635696411133 +[2025-04-27 12:21:10,289][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.344808340072632, cross_entropy: 3.344808340072632 +[2025-04-27 12:21:12,616][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.6192176342010498, cross_entropy: 1.6192176342010498 +[2025-04-27 12:21:12,912][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.0650408267974854, cross_entropy: 1.0650408267974854 +[2025-04-27 12:21:15,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.3396615982055664, cross_entropy: 3.3396615982055664 +[2025-04-27 12:21:15,682][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.4980716705322266, cross_entropy: 1.4980716705322266 +[2025-04-27 12:21:18,048][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.1917998790740967, cross_entropy: 3.1917998790740967 +[2025-04-27 12:21:18,341][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.1625380516052246, cross_entropy: 2.1625380516052246 +[2025-04-27 12:21:20,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.0030603408813477, cross_entropy: 3.0030603408813477 +[2025-04-27 12:21:20,998][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 1.6138529777526855, cross_entropy: 1.6138529777526855 +[2025-04-27 12:21:23,191][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 1.707202434539795, cross_entropy: 1.707202434539795 +[2025-04-27 12:21:23,571][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 2.938354015350342, cross_entropy: 2.938354015350342 +[2025-04-27 12:21:26,189][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 1.5992746353149414, cross_entropy: 1.5992746353149414 +[2025-04-27 12:21:26,455][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.268242597579956, cross_entropy: 3.268242597579956 +[2025-04-27 12:21:29,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 2.8291916847229004, cross_entropy: 2.8291916847229004 +[2025-04-27 12:21:29,536][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.4426960945129395, cross_entropy: 2.4426960945129395 +[2025-04-27 12:21:32,073][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 1.9705926179885864, cross_entropy: 1.9705926179885864 +[2025-04-27 12:21:32,338][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 3.045207977294922, cross_entropy: 3.045207977294922 +[2025-04-27 12:21:35,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 2.7324776649475098, cross_entropy: 2.7324776649475098 +[2025-04-27 12:21:36,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 3.2925655841827393, cross_entropy: 3.2925655841827393 +[2025-04-27 12:21:38,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 1.065420150756836, cross_entropy: 1.065420150756836 +[2025-04-27 12:21:38,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.1279256343841553, cross_entropy: 1.1279256343841553 +[2025-04-27 12:21:41,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.8132848739624023, cross_entropy: 2.8132848739624023 +[2025-04-27 12:21:41,414][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.0533885955810547, cross_entropy: 3.0533885955810547 +[2025-04-27 12:21:44,260][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.8155925273895264, cross_entropy: 1.8155925273895264 +[2025-04-27 12:21:44,527][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.7457056045532227, cross_entropy: 2.7457056045532227 +[2025-04-27 12:21:47,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.6198441982269287, cross_entropy: 2.6198441982269287 +[2025-04-27 12:21:47,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.1924796104431152, cross_entropy: 2.1924796104431152 +[2025-04-27 12:21:49,799][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.021805763244629, cross_entropy: 1.021805763244629 +[2025-04-27 12:21:50,088][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 1.7648437023162842, cross_entropy: 1.7648437023162842 +[2025-04-27 12:21:52,714][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 1.804628849029541, cross_entropy: 1.804628849029541 +[2025-04-27 12:21:53,003][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.198113441467285, cross_entropy: 3.198113441467285 +[2025-04-27 12:21:55,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 2.620626211166382, cross_entropy: 2.620626211166382 +[2025-04-27 12:21:55,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.1497989892959595, cross_entropy: 1.1497989892959595 +[2025-04-27 12:21:57,868][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.2399187088012695, cross_entropy: 3.2399187088012695 +[2025-04-27 12:21:58,158][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.3112802505493164, cross_entropy: 1.3112802505493164 +[2025-04-27 12:22:00,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.1629104614257812, cross_entropy: 2.1629104614257812 +[2025-04-27 12:22:00,680][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 1.8525670766830444, cross_entropy: 1.8525670766830444 +[2025-04-27 12:22:03,217][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.509101390838623, cross_entropy: 1.509101390838623 +[2025-04-27 12:22:03,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 2.4750030040740967, cross_entropy: 2.4750030040740967 +[2025-04-27 12:22:06,329][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.5113903284072876, cross_entropy: 1.5113903284072876 +[2025-04-27 12:22:06,618][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.2038512229919434, cross_entropy: 3.2038512229919434 +[2025-04-27 12:22:09,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 1.1601195335388184, cross_entropy: 1.1601195335388184 +[2025-04-27 12:22:09,573][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.1785709857940674, cross_entropy: 3.1785709857940674 +[2025-04-27 12:22:12,404][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.623917818069458, cross_entropy: 1.623917818069458 +[2025-04-27 12:22:12,694][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.0514891147613525, cross_entropy: 3.0514891147613525 +[2025-04-27 12:22:15,241][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 1.6608200073242188, cross_entropy: 1.6608200073242188 +[2025-04-27 12:22:15,517][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.1672122478485107, cross_entropy: 3.1672122478485107 +[2025-04-27 12:22:17,550][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.3938233852386475, cross_entropy: 1.3938233852386475 +[2025-04-27 12:22:17,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.2194747924804688, cross_entropy: 3.2194747924804688 +[2025-04-27 12:22:20,504][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 1.991901159286499, cross_entropy: 1.991901159286499 +[2025-04-27 12:22:20,791][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 2.9708170890808105, cross_entropy: 2.9708170890808105 +[2025-04-27 12:22:23,570][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 3.386052131652832, cross_entropy: 3.386052131652832 +[2025-04-27 12:22:23,857][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 2.5001072883605957, cross_entropy: 2.5001072883605957 +[2025-04-27 12:22:26,067][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 1.462892770767212, cross_entropy: 1.462892770767212 +[2025-04-27 12:22:26,358][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 2.259629964828491, cross_entropy: 2.259629964828491 +[2025-04-27 12:22:29,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.585474967956543, cross_entropy: 2.585474967956543 +[2025-04-27 12:22:29,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.2167695760726929, cross_entropy: 1.2167695760726929 +[2025-04-27 12:22:32,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.11228084564209, cross_entropy: 3.11228084564209 +[2025-04-27 12:22:32,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.697340488433838, cross_entropy: 1.697340488433838 +[2025-04-27 12:22:34,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 2.653317928314209, cross_entropy: 2.653317928314209 +[2025-04-27 12:22:34,833][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.552383303642273, cross_entropy: 1.552383303642273 +[2025-04-27 12:22:37,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 1.9358562231063843, cross_entropy: 1.9358562231063843 +[2025-04-27 12:22:37,758][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 1.9896265268325806, cross_entropy: 1.9896265268325806 +[2025-04-27 12:22:39,598][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.6088972091674805, cross_entropy: 1.6088972091674805 +[2025-04-27 12:22:39,779][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/iteration1000.pth. +[2025-04-27 12:22:40,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.692129611968994, cross_entropy: 2.692129611968994 +[2025-04-27 12:22:42,370][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.7710305452346802, cross_entropy: 1.7710305452346802 +[2025-04-27 12:22:42,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.048910617828369, cross_entropy: 3.048910617828369 +[2025-04-27 12:22:45,311][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 3.406820058822632, cross_entropy: 3.406820058822632 +[2025-04-27 12:22:45,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.5217169523239136, cross_entropy: 1.5217169523239136 +[2025-04-27 12:22:48,528][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.7840967178344727, cross_entropy: 2.7840967178344727 +[2025-04-27 12:22:48,817][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 1.8713115453720093, cross_entropy: 1.8713115453720093 +[2025-04-27 12:22:51,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 3.0216307640075684, cross_entropy: 3.0216307640075684 +[2025-04-27 12:22:51,726][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.83380126953125, cross_entropy: 2.83380126953125 +[2025-04-27 12:22:53,908][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.7291603088378906, cross_entropy: 2.7291603088378906 +[2025-04-27 12:22:54,174][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.026758909225464, cross_entropy: 3.026758909225464 +[2025-04-27 12:22:57,578][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.3824691772460938, cross_entropy: 2.3824691772460938 +[2025-04-27 12:22:57,871][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 1.5654675960540771, cross_entropy: 1.5654675960540771 +[2025-04-27 12:23:00,431][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 1.9724488258361816, cross_entropy: 1.9724488258361816 +[2025-04-27 12:23:00,725][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.6583383083343506, cross_entropy: 1.6583383083343506 +[2025-04-27 12:23:03,545][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 2.333446502685547, cross_entropy: 2.333446502685547 +[2025-04-27 12:23:03,833][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.8370161056518555, cross_entropy: 2.8370161056518555 +[2025-04-27 12:23:06,142][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.7238166332244873, cross_entropy: 2.7238166332244873 +[2025-04-27 12:23:06,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 1.4584711790084839, cross_entropy: 1.4584711790084839 +[2025-04-27 12:23:08,621][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 2.0585005283355713, cross_entropy: 2.0585005283355713 +[2025-04-27 12:23:08,908][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.281862258911133, cross_entropy: 3.281862258911133 +[2025-04-27 12:23:11,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.3996195793151855, cross_entropy: 2.3996195793151855 +[2025-04-27 12:23:11,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.530341386795044, cross_entropy: 1.530341386795044 +[2025-04-27 12:23:13,774][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 1.4714484214782715, cross_entropy: 1.4714484214782715 +[2025-04-27 12:23:14,065][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.3717460632324219, cross_entropy: 1.3717460632324219 +[2025-04-27 12:23:16,631][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 3.1809327602386475, cross_entropy: 3.1809327602386475 +[2025-04-27 12:23:16,920][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 3.1740317344665527, cross_entropy: 3.1740317344665527 +[2025-04-27 12:23:19,411][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.8239645957946777, cross_entropy: 2.8239645957946777 +[2025-04-27 12:23:19,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.4052724838256836, cross_entropy: 2.4052724838256836 +[2025-04-27 12:23:22,639][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.8071448802947998, cross_entropy: 1.8071448802947998 +[2025-04-27 12:23:22,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.630516767501831, cross_entropy: 1.630516767501831 +[2025-04-27 12:23:25,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.364332437515259, cross_entropy: 3.364332437515259 +[2025-04-27 12:23:25,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 1.6392967700958252, cross_entropy: 1.6392967700958252 +[2025-04-27 12:23:27,577][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 1.529124140739441, cross_entropy: 1.529124140739441 +[2025-04-27 12:23:27,843][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.4584460258483887, cross_entropy: 1.4584460258483887 +[2025-04-27 12:23:30,737][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 2.1243085861206055, cross_entropy: 2.1243085861206055 +[2025-04-27 12:23:31,034][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 2.7007710933685303, cross_entropy: 2.7007710933685303 +[2025-04-27 12:23:34,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.4829553365707397, cross_entropy: 1.4829553365707397 +[2025-04-27 12:23:34,286][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.761931896209717, cross_entropy: 3.761931896209717 +[2025-04-27 12:23:36,562][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.329031467437744, cross_entropy: 3.329031467437744 +[2025-04-27 12:23:36,828][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 1.7606184482574463, cross_entropy: 1.7606184482574463 +[2025-04-27 12:23:39,510][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 1.6923456192016602, cross_entropy: 1.6923456192016602 +[2025-04-27 12:23:39,793][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.3132565021514893, cross_entropy: 3.3132565021514893 +[2025-04-27 12:23:42,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.290714979171753, cross_entropy: 2.290714979171753 +[2025-04-27 12:23:42,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 3.0281777381896973, cross_entropy: 3.0281777381896973 +[2025-04-27 12:23:45,435][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 1.8538663387298584, cross_entropy: 1.8538663387298584 +[2025-04-27 12:23:45,700][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.1856369972229004, cross_entropy: 1.1856369972229004 +[2025-04-27 12:23:47,885][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.3520660400390625, cross_entropy: 2.3520660400390625 +[2025-04-27 12:23:48,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 2.922902822494507, cross_entropy: 2.922902822494507 +[2025-04-27 12:23:50,747][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.9067891836166382, cross_entropy: 1.9067891836166382 +[2025-04-27 12:23:51,036][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 3.0511698722839355, cross_entropy: 3.0511698722839355 +[2025-04-27 12:23:53,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.913898229598999, cross_entropy: 2.913898229598999 +[2025-04-27 12:23:53,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.309063196182251, cross_entropy: 1.309063196182251 +[2025-04-27 12:23:56,618][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.2458882331848145, cross_entropy: 2.2458882331848145 +[2025-04-27 12:23:56,883][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.7208284139633179, cross_entropy: 1.7208284139633179 +[2025-04-27 12:23:59,521][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.3801536560058594, cross_entropy: 3.3801536560058594 +[2025-04-27 12:23:59,811][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 3.109924077987671, cross_entropy: 3.109924077987671 +[2025-04-27 12:24:02,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.658110499382019, cross_entropy: 1.658110499382019 +[2025-04-27 12:24:02,651][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.3872032165527344, cross_entropy: 1.3872032165527344 +[2025-04-27 12:24:05,407][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.736605167388916, cross_entropy: 1.736605167388916 +[2025-04-27 12:24:05,671][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.6795878410339355, cross_entropy: 1.6795878410339355 +[2025-04-27 12:24:07,869][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 1.614533543586731, cross_entropy: 1.614533543586731 +[2025-04-27 12:24:08,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 1.4528909921646118, cross_entropy: 1.4528909921646118 +[2025-04-27 12:24:10,485][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.958804130554199, cross_entropy: 2.958804130554199 +[2025-04-27 12:24:10,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.0172948837280273, cross_entropy: 3.0172948837280273 +[2025-04-27 12:24:13,030][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.5593606233596802, cross_entropy: 1.5593606233596802 +[2025-04-27 12:24:13,292][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.7448084354400635, cross_entropy: 1.7448084354400635 +[2025-04-27 12:24:15,670][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.3789520263671875, cross_entropy: 2.3789520263671875 +[2025-04-27 12:26:25,498][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.273866891860962, cross_entropy: 2.273866891860962 +[2025-04-27 12:26:25,499][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.3832811117172241, cross_entropy: 1.3832811117172241 +[2025-04-27 12:26:25,711][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:26:25,908][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch3.pth. +[2025-04-27 12:26:26,101][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:26:29,243][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.1526011228561401, cross_entropy: 1.1526011228561401 +[2025-04-27 12:26:29,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 1.4233925342559814, cross_entropy: 1.4233925342559814 +[2025-04-27 12:26:31,865][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.5555773973464966, cross_entropy: 1.5555773973464966 +[2025-04-27 12:26:32,134][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.1387243270874023, cross_entropy: 1.1387243270874023 +[2025-04-27 12:26:34,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 1.611630916595459, cross_entropy: 1.611630916595459 +[2025-04-27 12:26:34,822][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.4234782457351685, cross_entropy: 1.4234782457351685 +[2025-04-27 12:26:37,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.2515549659729004, cross_entropy: 1.2515549659729004 +[2025-04-27 12:26:37,386][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 2.8493268489837646, cross_entropy: 2.8493268489837646 +[2025-04-27 12:26:39,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.4589115381240845, cross_entropy: 1.4589115381240845 +[2025-04-27 12:26:39,916][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.3527320623397827, cross_entropy: 1.3527320623397827 +[2025-04-27 12:26:41,909][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.1454741954803467, cross_entropy: 3.1454741954803467 +[2025-04-27 12:26:42,900][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.2217416763305664, cross_entropy: 2.2217416763305664 +[2025-04-27 12:26:44,670][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 1.5881245136260986, cross_entropy: 1.5881245136260986 +[2025-04-27 12:26:45,740][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.9891514778137207, cross_entropy: 2.9891514778137207 +[2025-04-27 12:26:46,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 1.3646397590637207, cross_entropy: 1.3646397590637207 +[2025-04-27 12:26:48,180][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.4394221305847168, cross_entropy: 1.4394221305847168 +[2025-04-27 12:26:49,650][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.1921441555023193, cross_entropy: 2.1921441555023193 +[2025-04-27 12:26:50,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 3.4087202548980713, cross_entropy: 3.4087202548980713 +[2025-04-27 12:26:53,234][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.4374916553497314, cross_entropy: 3.4374916553497314 +[2025-04-27 12:26:53,501][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.3417575359344482, cross_entropy: 2.3417575359344482 +[2025-04-27 12:26:55,912][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 1.3646056652069092, cross_entropy: 1.3646056652069092 +[2025-04-27 12:26:56,203][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.7095909118652344, cross_entropy: 1.7095909118652344 +[2025-04-27 12:26:58,649][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.6174793243408203, cross_entropy: 2.6174793243408203 +[2025-04-27 12:26:58,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 2.9470596313476562, cross_entropy: 2.9470596313476562 +[2025-04-27 12:27:01,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.4422926902770996, cross_entropy: 2.4422926902770996 +[2025-04-27 12:27:01,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.3823574781417847, cross_entropy: 1.3823574781417847 +[2025-04-27 12:27:04,897][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.3494722843170166, cross_entropy: 2.3494722843170166 +[2025-04-27 12:27:05,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.1158316135406494, cross_entropy: 3.1158316135406494 +[2025-04-27 12:27:07,595][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 1.8568005561828613, cross_entropy: 1.8568005561828613 +[2025-04-27 12:27:07,860][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.509582757949829, cross_entropy: 2.509582757949829 +[2025-04-27 12:27:09,974][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 2.6393489837646484, cross_entropy: 2.6393489837646484 +[2025-04-27 12:27:10,240][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.2724337577819824, cross_entropy: 1.2724337577819824 +[2025-04-27 12:27:12,609][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 1.5893244743347168, cross_entropy: 1.5893244743347168 +[2025-04-27 12:27:12,896][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 3.349548816680908, cross_entropy: 3.349548816680908 +[2025-04-27 12:27:15,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.907773017883301, cross_entropy: 2.907773017883301 +[2025-04-27 12:27:15,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 0.9948832988739014, cross_entropy: 0.9948832988739014 +[2025-04-27 12:27:18,168][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.2800345420837402, cross_entropy: 1.2800345420837402 +[2025-04-27 12:27:18,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 1.646299958229065, cross_entropy: 1.646299958229065 +[2025-04-27 12:27:20,381][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.5211777687072754, cross_entropy: 3.5211777687072754 +[2025-04-27 12:27:20,646][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 2.5780959129333496, cross_entropy: 2.5780959129333496 +[2025-04-27 12:27:24,073][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 1.4019081592559814, cross_entropy: 1.4019081592559814 +[2025-04-27 12:27:24,338][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 1.5498665571212769, cross_entropy: 1.5498665571212769 +[2025-04-27 12:27:26,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.102080821990967, cross_entropy: 2.102080821990967 +[2025-04-27 12:27:27,099][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.490035057067871, cross_entropy: 2.490035057067871 +[2025-04-27 12:27:29,253][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 2.327302932739258, cross_entropy: 2.327302932739258 +[2025-04-27 12:27:29,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.32910418510437, cross_entropy: 2.32910418510437 +[2025-04-27 12:27:32,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.0572702884674072, cross_entropy: 2.0572702884674072 +[2025-04-27 12:27:32,586][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 2.0822792053222656, cross_entropy: 2.0822792053222656 +[2025-04-27 12:27:35,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.1151041984558105, cross_entropy: 1.1151041984558105 +[2025-04-27 12:27:35,516][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.7021305561065674, cross_entropy: 2.7021305561065674 +[2025-04-27 12:27:37,702][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.457572340965271, cross_entropy: 1.457572340965271 +[2025-04-27 12:27:37,965][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.331228256225586, cross_entropy: 1.331228256225586 +[2025-04-27 12:27:40,760][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 1.7633378505706787, cross_entropy: 1.7633378505706787 +[2025-04-27 12:27:41,049][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.385836362838745, cross_entropy: 2.385836362838745 +[2025-04-27 12:27:43,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 3.1025969982147217, cross_entropy: 3.1025969982147217 +[2025-04-27 12:27:43,556][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.8418530225753784, cross_entropy: 1.8418530225753784 +[2025-04-27 12:27:45,563][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 1.5498881340026855, cross_entropy: 1.5498881340026855 +[2025-04-27 12:27:45,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 3.2004904747009277, cross_entropy: 3.2004904747009277 +[2025-04-27 12:27:49,288][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 1.663149356842041, cross_entropy: 1.663149356842041 +[2025-04-27 12:27:49,554][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 3.063429117202759, cross_entropy: 3.063429117202759 +[2025-04-27 12:27:51,210][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.5878608226776123, cross_entropy: 1.5878608226776123 +[2025-04-27 12:27:51,500][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.0643882751464844, cross_entropy: 2.0643882751464844 +[2025-04-27 12:27:54,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 2.6663570404052734, cross_entropy: 2.6663570404052734 +[2025-04-27 12:27:54,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 2.1736299991607666, cross_entropy: 2.1736299991607666 +[2025-04-27 12:27:56,740][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.691995620727539, cross_entropy: 2.691995620727539 +[2025-04-27 12:27:57,028][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.525092363357544, cross_entropy: 1.525092363357544 +[2025-04-27 12:27:59,589][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.744940757751465, cross_entropy: 2.744940757751465 +[2025-04-27 12:27:59,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 1.6695911884307861, cross_entropy: 1.6695911884307861 +[2025-04-27 12:28:02,851][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 1.8725471496582031, cross_entropy: 1.8725471496582031 +[2025-04-27 12:28:03,143][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.561556577682495, cross_entropy: 2.561556577682495 +[2025-04-27 12:28:05,286][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.131694793701172, cross_entropy: 2.131694793701172 +[2025-04-27 12:28:05,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.653045654296875, cross_entropy: 1.653045654296875 +[2025-04-27 12:28:07,834][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.3845646381378174, cross_entropy: 1.3845646381378174 +[2025-04-27 12:28:08,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.3457075357437134, cross_entropy: 1.3457075357437134 +[2025-04-27 12:28:10,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 2.1941823959350586, cross_entropy: 2.1941823959350586 +[2025-04-27 12:28:10,331][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 1.2772505283355713, cross_entropy: 1.2772505283355713 +[2025-04-27 12:28:12,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 0.8576180934906006, cross_entropy: 0.8576180934906006 +[2025-04-27 12:28:12,466][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 1.2933753728866577, cross_entropy: 1.2933753728866577 +[2025-04-27 12:28:14,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 3.4593307971954346, cross_entropy: 3.4593307971954346 +[2025-04-27 12:28:14,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.2740380764007568, cross_entropy: 1.2740380764007568 +[2025-04-27 12:28:16,737][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 1.8979408740997314, cross_entropy: 1.8979408740997314 +[2025-04-27 12:28:17,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.646587610244751, cross_entropy: 2.646587610244751 +[2025-04-27 12:28:19,458][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 0.9635157585144043, cross_entropy: 0.9635157585144043 +[2025-04-27 12:28:19,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.3755089044570923, cross_entropy: 1.3755089044570923 +[2025-04-27 12:28:22,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.7334132194519043, cross_entropy: 1.7334132194519043 +[2025-04-27 12:28:22,281][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 3.338076591491699, cross_entropy: 3.338076591491699 +[2025-04-27 12:28:25,338][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.0975978374481201, cross_entropy: 1.0975978374481201 +[2025-04-27 12:28:25,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 0.8667877912521362, cross_entropy: 0.8667877912521362 +[2025-04-27 12:28:28,125][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 1.0149106979370117, cross_entropy: 1.0149106979370117 +[2025-04-27 12:28:28,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 2.311723232269287, cross_entropy: 2.311723232269287 +[2025-04-27 12:28:30,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.1602821350097656, cross_entropy: 3.1602821350097656 +[2025-04-27 12:28:31,320][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.6427538394927979, cross_entropy: 1.6427538394927979 +[2025-04-27 12:28:33,234][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.2102711200714111, cross_entropy: 1.2102711200714111 +[2025-04-27 12:28:33,564][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.040555953979492, cross_entropy: 2.040555953979492 +[2025-04-27 12:28:36,144][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 3.549436092376709, cross_entropy: 3.549436092376709 +[2025-04-27 12:28:36,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.5628411769866943, cross_entropy: 1.5628411769866943 +[2025-04-27 12:28:38,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 3.0270466804504395, cross_entropy: 3.0270466804504395 +[2025-04-27 12:28:38,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.4264678955078125, cross_entropy: 1.4264678955078125 +[2025-04-27 12:28:41,366][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 2.6329634189605713, cross_entropy: 2.6329634189605713 +[2025-04-27 12:28:41,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.0832464694976807, cross_entropy: 1.0832464694976807 +[2025-04-27 12:28:44,189][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 2.044219970703125, cross_entropy: 2.044219970703125 +[2025-04-27 12:28:44,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.457662582397461, cross_entropy: 2.457662582397461 +[2025-04-27 12:28:46,605][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.633694648742676, cross_entropy: 2.633694648742676 +[2025-04-27 12:28:47,458][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 1.4608323574066162, cross_entropy: 1.4608323574066162 +[2025-04-27 12:28:48,879][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.269439935684204, cross_entropy: 2.269439935684204 +[2025-04-27 12:28:51,365][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.2417197227478027, cross_entropy: 1.2417197227478027 +[2025-04-27 12:28:52,153][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.3883557319641113, cross_entropy: 3.3883557319641113 +[2025-04-27 12:28:54,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 1.6672905683517456, cross_entropy: 1.6672905683517456 +[2025-04-27 12:28:54,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 3.352776050567627, cross_entropy: 3.352776050567627 +[2025-04-27 12:28:57,035][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 2.6985676288604736, cross_entropy: 2.6985676288604736 +[2025-04-27 12:28:57,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.491623878479004, cross_entropy: 2.491623878479004 +[2025-04-27 12:29:00,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 2.1008245944976807, cross_entropy: 2.1008245944976807 +[2025-04-27 12:29:00,516][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 2.709434986114502, cross_entropy: 2.709434986114502 +[2025-04-27 12:29:03,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.301844358444214, cross_entropy: 2.301844358444214 +[2025-04-27 12:29:03,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 0.8644324541091919, cross_entropy: 0.8644324541091919 +[2025-04-27 12:29:05,547][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.580512046813965, cross_entropy: 2.580512046813965 +[2025-04-27 12:29:06,209][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.9031500816345215, cross_entropy: 2.9031500816345215 +[2025-04-27 12:29:09,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.2922182083129883, cross_entropy: 1.2922182083129883 +[2025-04-27 12:29:09,791][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.0082542896270752, cross_entropy: 1.0082542896270752 +[2025-04-27 12:29:11,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 1.7347617149353027, cross_entropy: 1.7347617149353027 +[2025-04-27 12:29:12,293][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.448709011077881, cross_entropy: 3.448709011077881 +[2025-04-27 12:29:14,071][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 3.5722036361694336, cross_entropy: 3.5722036361694336 +[2025-04-27 12:29:15,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.936394214630127, cross_entropy: 2.936394214630127 +[2025-04-27 12:29:16,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 2.886625051498413, cross_entropy: 2.886625051498413 +[2025-04-27 12:29:18,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.3036701679229736, cross_entropy: 1.3036701679229736 +[2025-04-27 12:29:19,341][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.256805419921875, cross_entropy: 1.256805419921875 +[2025-04-27 12:29:20,810][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 1.6578617095947266, cross_entropy: 1.6578617095947266 +[2025-04-27 12:29:21,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.8882696628570557, cross_entropy: 2.8882696628570557 +[2025-04-27 12:29:24,184][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.9713045358657837, cross_entropy: 1.9713045358657837 +[2025-04-27 12:29:24,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 0.924954891204834, cross_entropy: 0.924954891204834 +[2025-04-27 12:29:26,851][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 1.4394057989120483, cross_entropy: 1.4394057989120483 +[2025-04-27 12:29:27,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 3.0404279232025146, cross_entropy: 3.0404279232025146 +[2025-04-27 12:29:30,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.780202865600586, cross_entropy: 2.780202865600586 +[2025-04-27 12:29:30,782][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.8091144561767578, cross_entropy: 1.8091144561767578 +[2025-04-27 12:29:33,240][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.4740355014801025, cross_entropy: 1.4740355014801025 +[2025-04-27 12:29:33,529][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.799473762512207, cross_entropy: 2.799473762512207 +[2025-04-27 12:29:35,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 1.220115065574646, cross_entropy: 1.220115065574646 +[2025-04-27 12:29:35,679][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 1.222653865814209, cross_entropy: 1.222653865814209 +[2025-04-27 12:29:38,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.301895260810852, cross_entropy: 1.301895260810852 +[2025-04-27 12:29:38,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.49312686920166, cross_entropy: 2.49312686920166 +[2025-04-27 12:29:41,143][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.10325288772583, cross_entropy: 3.10325288772583 +[2025-04-27 12:29:41,426][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 3.2743260860443115, cross_entropy: 3.2743260860443115 +[2025-04-27 12:29:44,416][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 1.3283324241638184, cross_entropy: 1.3283324241638184 +[2025-04-27 12:29:44,681][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.563199520111084, cross_entropy: 2.563199520111084 +[2025-04-27 12:29:46,897][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 1.4318453073501587, cross_entropy: 1.4318453073501587 +[2025-04-27 12:29:47,189][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.1498939990997314, cross_entropy: 1.1498939990997314 +[2025-04-27 12:29:49,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 3.378788948059082, cross_entropy: 3.378788948059082 +[2025-04-27 12:29:49,874][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 1.2575407028198242, cross_entropy: 1.2575407028198242 +[2025-04-27 12:29:51,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 2.578044891357422, cross_entropy: 2.578044891357422 +[2025-04-27 12:29:51,949][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 1.4905784130096436, cross_entropy: 1.4905784130096436 +[2025-04-27 12:29:54,349][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.5995702743530273, cross_entropy: 1.5995702743530273 +[2025-04-27 12:29:54,639][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 1.7253443002700806, cross_entropy: 1.7253443002700806 +[2025-04-27 12:29:56,852][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.0876796245574951, cross_entropy: 1.0876796245574951 +[2025-04-27 12:29:57,382][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.3597221374511719, cross_entropy: 1.3597221374511719 +[2025-04-27 12:29:59,193][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.3229131698608398, cross_entropy: 1.3229131698608398 +[2025-04-27 12:29:59,801][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.867398500442505, cross_entropy: 2.867398500442505 +[2025-04-27 12:30:01,886][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 1.4248701333999634, cross_entropy: 1.4248701333999634 +[2025-04-27 12:30:02,598][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 1.3357404470443726, cross_entropy: 1.3357404470443726 +[2025-04-27 12:30:04,448][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.363771915435791, cross_entropy: 3.363771915435791 +[2025-04-27 12:30:05,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 2.892045259475708, cross_entropy: 2.892045259475708 +[2025-04-27 12:30:07,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.9364991188049316, cross_entropy: 2.9364991188049316 +[2025-04-27 12:30:07,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 2.5378665924072266, cross_entropy: 2.5378665924072266 +[2025-04-27 12:30:10,088][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 0.9038986563682556, cross_entropy: 0.9038986563682556 +[2025-04-27 12:30:10,421][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.6885008811950684, cross_entropy: 2.6885008811950684 +[2025-04-27 12:30:12,772][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.4977407455444336, cross_entropy: 1.4977407455444336 +[2025-04-27 12:30:13,362][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.7111479043960571, cross_entropy: 1.7111479043960571 +[2025-04-27 12:30:15,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.1515254974365234, cross_entropy: 1.1515254974365234 +[2025-04-27 12:30:15,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.0871284008026123, cross_entropy: 1.0871284008026123 +[2025-04-27 12:30:18,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.164423942565918, cross_entropy: 1.164423942565918 +[2025-04-27 12:30:18,698][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 0.8594931960105896, cross_entropy: 0.8594931960105896 +[2025-04-27 12:30:20,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 2.8644163608551025, cross_entropy: 2.8644163608551025 +[2025-04-27 12:30:21,167][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 2.818721055984497, cross_entropy: 2.818721055984497 +[2025-04-27 12:30:23,501][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 3.373220920562744, cross_entropy: 3.373220920562744 +[2025-04-27 12:30:23,788][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 2.9314069747924805, cross_entropy: 2.9314069747924805 +[2025-04-27 12:30:26,857][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 1.3382960557937622, cross_entropy: 1.3382960557937622 +[2025-04-27 12:30:27,159][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 1.148116111755371, cross_entropy: 1.148116111755371 +[2025-04-27 12:30:29,767][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 3.277926445007324, cross_entropy: 3.277926445007324 +[2025-04-27 12:30:30,053][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 2.7411208152770996, cross_entropy: 2.7411208152770996 +[2025-04-27 12:30:32,359][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 2.705488920211792, cross_entropy: 2.705488920211792 +[2025-04-27 12:30:32,686][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.7247062921524048, cross_entropy: 1.7247062921524048 +[2025-04-27 12:30:35,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 1.1693010330200195, cross_entropy: 1.1693010330200195 +[2025-04-27 12:30:35,418][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.5393915176391602, cross_entropy: 1.5393915176391602 +[2025-04-27 12:30:37,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.2903456687927246, cross_entropy: 1.2903456687927246 +[2025-04-27 12:30:38,035][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 2.7772903442382812, cross_entropy: 2.7772903442382812 +[2025-04-27 12:30:40,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.612682819366455, cross_entropy: 2.612682819366455 +[2025-04-27 12:30:40,751][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 1.5584046840667725, cross_entropy: 1.5584046840667725 +[2025-04-27 12:30:43,934][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.442292332649231, cross_entropy: 1.442292332649231 +[2025-04-27 12:30:44,222][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.4718599319458008, cross_entropy: 1.4718599319458008 +[2025-04-27 12:30:46,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.9043629169464111, cross_entropy: 1.9043629169464111 +[2025-04-27 12:30:47,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 2.537626266479492, cross_entropy: 2.537626266479492 +[2025-04-27 12:30:49,859][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 1.3386194705963135, cross_entropy: 1.3386194705963135 +[2025-04-27 12:30:50,125][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 3.017103433609009, cross_entropy: 3.017103433609009 +[2025-04-27 12:30:52,631][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 1.3113021850585938, cross_entropy: 1.3113021850585938 +[2025-04-27 12:30:52,895][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 0.9861574172973633, cross_entropy: 0.9861574172973633 +[2025-04-27 12:30:55,784][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.1725143194198608, cross_entropy: 1.1725143194198608 +[2025-04-27 12:30:56,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 3.064919948577881, cross_entropy: 3.064919948577881 +[2025-04-27 12:30:58,230][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 1.5852456092834473, cross_entropy: 1.5852456092834473 +[2025-04-27 12:30:58,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 3.3235318660736084, cross_entropy: 3.3235318660736084 +[2025-04-27 12:31:00,887][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 2.2267627716064453, cross_entropy: 2.2267627716064453 +[2025-04-27 12:31:01,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 2.910024404525757, cross_entropy: 2.910024404525757 +[2025-04-27 12:31:03,148][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.9732933044433594, cross_entropy: 1.9732933044433594 +[2025-04-27 12:31:03,499][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 1.6503522396087646, cross_entropy: 1.6503522396087646 +[2025-04-27 12:31:05,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.846794366836548, cross_entropy: 2.846794366836548 +[2025-04-27 12:31:06,055][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.3509128093719482, cross_entropy: 1.3509128093719482 +[2025-04-27 12:31:08,639][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 1.8634120225906372, cross_entropy: 1.8634120225906372 +[2025-04-27 12:31:08,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 1.386385440826416, cross_entropy: 1.386385440826416 +[2025-04-27 12:31:11,344][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 2.209968090057373, cross_entropy: 2.209968090057373 +[2025-04-27 12:31:11,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 1.6886138916015625, cross_entropy: 1.6886138916015625 +[2025-04-27 12:31:13,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 3.300199508666992, cross_entropy: 3.300199508666992 +[2025-04-27 12:31:14,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 1.261620283126831, cross_entropy: 1.261620283126831 +[2025-04-27 12:31:16,336][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.3516020774841309, cross_entropy: 1.3516020774841309 +[2025-04-27 12:31:16,600][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 1.5440630912780762, cross_entropy: 1.5440630912780762 +[2025-04-27 12:31:18,807][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 1.0650417804718018, cross_entropy: 1.0650417804718018 +[2025-04-27 12:31:19,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 2.003209114074707, cross_entropy: 2.003209114074707 +[2025-04-27 12:31:21,853][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.3954174518585205, cross_entropy: 2.3954174518585205 +[2025-04-27 12:31:22,119][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.0589969158172607, cross_entropy: 2.0589969158172607 +[2025-04-27 12:31:24,340][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 2.0547633171081543, cross_entropy: 2.0547633171081543 +[2025-04-27 12:31:24,604][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.428222417831421, cross_entropy: 2.428222417831421 +[2025-04-27 12:31:26,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.4700589179992676, cross_entropy: 1.4700589179992676 +[2025-04-27 12:31:27,145][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.211306095123291, cross_entropy: 2.211306095123291 +[2025-04-27 12:31:29,304][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 3.1571826934814453, cross_entropy: 3.1571826934814453 +[2025-04-27 12:31:29,593][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 1.767317533493042, cross_entropy: 1.767317533493042 +[2025-04-27 12:31:32,133][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 3.3022685050964355, cross_entropy: 3.3022685050964355 +[2025-04-27 12:31:32,449][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.471189022064209, cross_entropy: 2.471189022064209 +[2025-04-27 12:31:35,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 2.0712523460388184, cross_entropy: 2.0712523460388184 +[2025-04-27 12:31:35,730][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.0297107696533203, cross_entropy: 3.0297107696533203 +[2025-04-27 12:31:38,752][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 2.962524175643921, cross_entropy: 2.962524175643921 +[2025-04-27 12:31:39,040][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 2.9420504570007324, cross_entropy: 2.9420504570007324 +[2025-04-27 12:31:40,811][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.2196245193481445, cross_entropy: 3.2196245193481445 +[2025-04-27 12:31:41,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.2950588464736938, cross_entropy: 1.2950588464736938 +[2025-04-27 12:31:43,611][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.6458640098571777, cross_entropy: 2.6458640098571777 +[2025-04-27 12:31:43,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.0776078701019287, cross_entropy: 2.0776078701019287 +[2025-04-27 12:31:46,178][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.8687288761138916, cross_entropy: 2.8687288761138916 +[2025-04-27 12:31:46,508][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.2405847311019897, cross_entropy: 1.2405847311019897 +[2025-04-27 12:31:49,560][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.650718092918396, cross_entropy: 1.650718092918396 +[2025-04-27 12:31:49,851][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.3621296882629395, cross_entropy: 2.3621296882629395 +[2025-04-27 12:31:52,326][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 3.1054861545562744, cross_entropy: 3.1054861545562744 +[2025-04-27 12:31:52,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.3491222858428955, cross_entropy: 2.3491222858428955 +[2025-04-27 12:31:54,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.0964179039001465, cross_entropy: 3.0964179039001465 +[2025-04-27 12:31:55,159][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 2.9935755729675293, cross_entropy: 2.9935755729675293 +[2025-04-27 12:31:58,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 1.4076428413391113, cross_entropy: 1.4076428413391113 +[2025-04-27 12:31:58,453][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.952772617340088, cross_entropy: 2.952772617340088 +[2025-04-27 12:32:00,572][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 1.3171542882919312, cross_entropy: 1.3171542882919312 +[2025-04-27 12:32:00,864][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 1.5504112243652344, cross_entropy: 1.5504112243652344 +[2025-04-27 12:32:03,188][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.3473637104034424, cross_entropy: 1.3473637104034424 +[2025-04-27 12:32:03,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 1.6226876974105835, cross_entropy: 1.6226876974105835 +[2025-04-27 12:32:06,072][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.1792376041412354, cross_entropy: 2.1792376041412354 +[2025-04-27 12:32:06,363][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 3.1019670963287354, cross_entropy: 3.1019670963287354 +[2025-04-27 12:32:08,883][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.599262237548828, cross_entropy: 2.599262237548828 +[2025-04-27 12:32:09,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.3192195892333984, cross_entropy: 1.3192195892333984 +[2025-04-27 12:32:10,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 3.3038625717163086, cross_entropy: 3.3038625717163086 +[2025-04-27 12:32:11,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 2.2232890129089355, cross_entropy: 2.2232890129089355 +[2025-04-27 12:32:14,079][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 3.098888397216797, cross_entropy: 3.098888397216797 +[2025-04-27 12:32:14,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 3.017798900604248, cross_entropy: 3.017798900604248 +[2025-04-27 12:32:16,866][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.8755266666412354, cross_entropy: 2.8755266666412354 +[2025-04-27 12:32:17,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 3.17941951751709, cross_entropy: 3.17941951751709 +[2025-04-27 12:32:19,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 1.248568058013916, cross_entropy: 1.248568058013916 +[2025-04-27 12:32:19,814][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.183060646057129, cross_entropy: 1.183060646057129 +[2025-04-27 12:32:22,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 2.479775905609131, cross_entropy: 2.479775905609131 +[2025-04-27 12:32:22,832][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.0850145816802979, cross_entropy: 1.0850145816802979 +[2025-04-27 12:32:25,572][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 2.540189266204834, cross_entropy: 2.540189266204834 +[2025-04-27 12:32:26,334][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 1.5872304439544678, cross_entropy: 1.5872304439544678 +[2025-04-27 12:32:28,061][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 2.994187831878662, cross_entropy: 2.994187831878662 +[2025-04-27 12:32:29,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 1.0650856494903564, cross_entropy: 1.0650856494903564 +[2025-04-27 12:32:30,559][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 1.4213436841964722, cross_entropy: 1.4213436841964722 +[2025-04-27 12:32:32,716][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.1717288494110107, cross_entropy: 2.1717288494110107 +[2025-04-27 12:32:34,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 1.2211861610412598, cross_entropy: 1.2211861610412598 +[2025-04-27 12:32:35,530][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.942619800567627, cross_entropy: 2.942619800567627 +[2025-04-27 12:32:37,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 2.9983925819396973, cross_entropy: 2.9983925819396973 +[2025-04-27 12:32:39,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.681550145149231, cross_entropy: 1.681550145149231 +[2025-04-27 12:32:39,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.6936206817626953, cross_entropy: 2.6936206817626953 +[2025-04-27 12:32:41,887][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.1446707248687744, cross_entropy: 1.1446707248687744 +[2025-04-27 12:32:42,525][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 1.5441162586212158, cross_entropy: 1.5441162586212158 +[2025-04-27 12:32:44,868][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.151259422302246, cross_entropy: 2.151259422302246 +[2025-04-27 12:32:45,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 2.1360700130462646, cross_entropy: 2.1360700130462646 +[2025-04-27 12:32:47,038][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 1.5329599380493164, cross_entropy: 1.5329599380493164 +[2025-04-27 12:32:48,517][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 1.8605751991271973, cross_entropy: 1.8605751991271973 +[2025-04-27 12:32:49,812][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 1.500255823135376, cross_entropy: 1.500255823135376 +[2025-04-27 12:32:51,285][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 1.9043822288513184, cross_entropy: 1.9043822288513184 +[2025-04-27 12:32:52,950][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 1.5096802711486816, cross_entropy: 1.5096802711486816 +[2025-04-27 12:32:54,164][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 1.9750545024871826, cross_entropy: 1.9750545024871826 +[2025-04-27 12:32:55,139][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 2.6811113357543945, cross_entropy: 2.6811113357543945 +[2025-04-27 12:32:57,517][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 2.09490966796875, cross_entropy: 2.09490966796875 +[2025-04-27 12:32:57,840][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 1.4380733966827393, cross_entropy: 1.4380733966827393 +[2025-04-27 12:32:59,962][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 1.0294206142425537, cross_entropy: 1.0294206142425537 +[2025-04-27 12:33:00,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.814723014831543, cross_entropy: 2.814723014831543 +[2025-04-27 12:33:02,966][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 2.8342747688293457, cross_entropy: 2.8342747688293457 +[2025-04-27 12:33:03,257][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 3.2110280990600586, cross_entropy: 3.2110280990600586 +[2025-04-27 12:33:05,554][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4847676753997803, cross_entropy: 1.4847676753997803 +[2025-04-27 12:33:05,817][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 0.893360435962677, cross_entropy: 0.893360435962677 +[2025-04-27 12:33:08,268][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 1.5934622287750244, cross_entropy: 1.5934622287750244 +[2025-04-27 12:33:08,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 2.4111475944519043, cross_entropy: 2.4111475944519043 +[2025-04-27 12:33:11,129][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.5402289628982544, cross_entropy: 1.5402289628982544 +[2025-04-27 12:33:11,397][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 1.6456615924835205, cross_entropy: 1.6456615924835205 +[2025-04-27 12:33:13,538][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 1.2708630561828613, cross_entropy: 1.2708630561828613 +[2025-04-27 12:33:13,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 1.2688565254211426, cross_entropy: 1.2688565254211426 +[2025-04-27 12:33:17,333][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.4496560096740723, cross_entropy: 2.4496560096740723 +[2025-04-27 12:33:17,621][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.6501319408416748, cross_entropy: 1.6501319408416748 +[2025-04-27 12:33:19,950][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.831820487976074, cross_entropy: 2.831820487976074 +[2025-04-27 12:33:20,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 1.466871976852417, cross_entropy: 1.466871976852417 +[2025-04-27 12:33:22,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 3.184631586074829, cross_entropy: 3.184631586074829 +[2025-04-27 12:33:22,770][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.740452289581299, cross_entropy: 2.740452289581299 +[2025-04-27 12:33:24,830][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.5486347675323486, cross_entropy: 1.5486347675323486 +[2025-04-27 12:33:25,116][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.5951273441314697, cross_entropy: 1.5951273441314697 +[2025-04-27 12:33:27,406][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 2.9146485328674316, cross_entropy: 2.9146485328674316 +[2025-04-27 12:33:27,673][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.367671489715576, cross_entropy: 2.367671489715576 +[2025-04-27 12:33:29,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.9994258880615234, cross_entropy: 1.9994258880615234 +[2025-04-27 12:33:30,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 2.1793534755706787, cross_entropy: 2.1793534755706787 +[2025-04-27 12:33:32,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.7487916946411133, cross_entropy: 2.7487916946411133 +[2025-04-27 12:33:32,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.2056169509887695, cross_entropy: 2.2056169509887695 +[2025-04-27 12:33:34,522][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.893056869506836, cross_entropy: 2.893056869506836 +[2025-04-27 12:33:35,063][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.2494277954101562, cross_entropy: 1.2494277954101562 +[2025-04-27 12:33:38,261][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.2756184339523315, cross_entropy: 1.2756184339523315 +[2025-04-27 12:33:38,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.107328414916992, cross_entropy: 2.107328414916992 +[2025-04-27 12:33:40,972][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 1.9555611610412598, cross_entropy: 1.9555611610412598 +[2025-04-27 12:33:41,261][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.3520982265472412, cross_entropy: 1.3520982265472412 +[2025-04-27 12:33:43,527][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 1.2578721046447754, cross_entropy: 1.2578721046447754 +[2025-04-27 12:33:43,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.8365201950073242, cross_entropy: 1.8365201950073242 +[2025-04-27 12:33:46,013][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 1.7911666631698608, cross_entropy: 1.7911666631698608 +[2025-04-27 12:33:46,463][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 3.0194993019104004, cross_entropy: 3.0194993019104004 +[2025-04-27 12:33:49,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.2599209547042847, cross_entropy: 1.2599209547042847 +[2025-04-27 12:33:49,691][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.360215187072754, cross_entropy: 1.360215187072754 +[2025-04-27 12:33:51,998][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.506467819213867, cross_entropy: 2.506467819213867 +[2025-04-27 12:33:52,287][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 0.8808891773223877, cross_entropy: 0.8808891773223877 +[2025-04-27 12:33:54,513][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 3.0601248741149902, cross_entropy: 3.0601248741149902 +[2025-04-27 12:33:54,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.7926077842712402, cross_entropy: 2.7926077842712402 +[2025-04-27 12:33:57,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 2.9205398559570312, cross_entropy: 2.9205398559570312 +[2025-04-27 12:33:58,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 1.4672915935516357, cross_entropy: 1.4672915935516357 +[2025-04-27 12:34:00,715][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 1.9088475704193115, cross_entropy: 1.9088475704193115 +[2025-04-27 12:34:01,046][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.3131999969482422, cross_entropy: 1.3131999969482422 +[2025-04-27 12:34:03,580][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.48274564743042, cross_entropy: 1.48274564743042 +[2025-04-27 12:34:03,898][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.3701379299163818, cross_entropy: 1.3701379299163818 +[2025-04-27 12:34:06,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 2.5154635906219482, cross_entropy: 2.5154635906219482 +[2025-04-27 12:34:06,600][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 2.9416935443878174, cross_entropy: 2.9416935443878174 +[2025-04-27 12:34:09,593][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.556997299194336, cross_entropy: 1.556997299194336 +[2025-04-27 12:34:09,882][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.679992198944092, cross_entropy: 2.679992198944092 +[2025-04-27 12:34:11,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.7911691665649414, cross_entropy: 1.7911691665649414 +[2025-04-27 12:34:12,183][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 1.9921560287475586, cross_entropy: 1.9921560287475586 +[2025-04-27 12:34:14,439][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 3.0905208587646484, cross_entropy: 3.0905208587646484 +[2025-04-27 12:34:15,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.2510793209075928, cross_entropy: 1.2510793209075928 +[2025-04-27 12:34:16,671][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.6792502403259277, cross_entropy: 2.6792502403259277 +[2025-04-27 12:34:18,252][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.180427074432373, cross_entropy: 3.180427074432373 +[2025-04-27 12:34:19,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 1.4273455142974854, cross_entropy: 1.4273455142974854 +[2025-04-27 12:34:20,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 2.8182079792022705, cross_entropy: 2.8182079792022705 +[2025-04-27 12:34:21,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.1752638816833496, cross_entropy: 2.1752638816833496 +[2025-04-27 12:34:23,369][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 2.9319095611572266, cross_entropy: 2.9319095611572266 +[2025-04-27 12:34:25,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.6322823762893677, cross_entropy: 1.6322823762893677 +[2025-04-27 12:34:26,178][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.913961410522461, cross_entropy: 2.913961410522461 +[2025-04-27 12:34:27,734][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.9473540782928467, cross_entropy: 1.9473540782928467 +[2025-04-27 12:34:28,798][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 0.9365749359130859, cross_entropy: 0.9365749359130859 +[2025-04-27 12:34:31,010][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.325082778930664, cross_entropy: 1.325082778930664 +[2025-04-27 12:34:31,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 2.9056477546691895, cross_entropy: 2.9056477546691895 +[2025-04-27 12:34:33,784][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 1.6151753664016724, cross_entropy: 1.6151753664016724 +[2025-04-27 12:34:34,112][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 1.413648009300232, cross_entropy: 1.413648009300232 +[2025-04-27 12:34:36,297][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 1.0234549045562744, cross_entropy: 1.0234549045562744 +[2025-04-27 12:34:36,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.191620349884033, cross_entropy: 3.191620349884033 +[2025-04-27 12:36:45,801][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.062631368637085, cross_entropy: 2.062631368637085 +[2025-04-27 12:36:45,802][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.3307931423187256, cross_entropy: 1.3307931423187256 +[2025-04-27 12:36:46,044][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:36:46,201][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch4.pth. +[2025-04-27 12:36:46,380][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:36:50,425][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.279013156890869, cross_entropy: 2.279013156890869 +[2025-04-27 12:36:50,952][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.1379356384277344, cross_entropy: 1.1379356384277344 +[2025-04-27 12:36:53,160][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.6958554983139038, cross_entropy: 1.6958554983139038 +[2025-04-27 12:36:53,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.2218420505523682, cross_entropy: 1.2218420505523682 +[2025-04-27 12:36:56,017][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.0020992755889893, cross_entropy: 1.0020992755889893 +[2025-04-27 12:36:56,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.371746778488159, cross_entropy: 2.371746778488159 +[2025-04-27 12:36:58,422][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.057995080947876, cross_entropy: 2.057995080947876 +[2025-04-27 12:36:59,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.165402889251709, cross_entropy: 2.165402889251709 +[2025-04-27 12:37:01,043][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 2.5284600257873535, cross_entropy: 2.5284600257873535 +[2025-04-27 12:37:02,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.0531623363494873, cross_entropy: 1.0531623363494873 +[2025-04-27 12:37:03,524][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 2.968620777130127, cross_entropy: 2.968620777130127 +[2025-04-27 12:37:04,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 2.0634665489196777, cross_entropy: 2.0634665489196777 +[2025-04-27 12:37:06,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.7517518997192383, cross_entropy: 2.7517518997192383 +[2025-04-27 12:37:07,179][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 1.9494702816009521, cross_entropy: 1.9494702816009521 +[2025-04-27 12:37:08,757][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 2.923055410385132, cross_entropy: 2.923055410385132 +[2025-04-27 12:37:10,415][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.4969561100006104, cross_entropy: 2.4969561100006104 +[2025-04-27 12:37:11,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 2.589076519012451, cross_entropy: 2.589076519012451 +[2025-04-27 12:37:13,084][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 2.981416940689087, cross_entropy: 2.981416940689087 +[2025-04-27 12:37:14,004][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.3217520713806152, cross_entropy: 2.3217520713806152 +[2025-04-27 12:37:15,610][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 0.9619680643081665, cross_entropy: 0.9619680643081665 +[2025-04-27 12:37:16,356][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.4941833019256592, cross_entropy: 1.4941833019256592 +[2025-04-27 12:37:18,970][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 1.7991013526916504, cross_entropy: 1.7991013526916504 +[2025-04-27 12:37:20,144][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.573864459991455, cross_entropy: 1.573864459991455 +[2025-04-27 12:37:22,220][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.3258628845214844, cross_entropy: 1.3258628845214844 +[2025-04-27 12:37:22,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.1962348222732544, cross_entropy: 1.1962348222732544 +[2025-04-27 12:37:24,982][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.2049281597137451, cross_entropy: 1.2049281597137451 +[2025-04-27 12:37:25,569][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 0.8984580636024475, cross_entropy: 0.8984580636024475 +[2025-04-27 12:37:27,719][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.1143187284469604, cross_entropy: 1.1143187284469604 +[2025-04-27 12:37:28,146][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.8495376110076904, cross_entropy: 2.8495376110076904 +[2025-04-27 12:37:30,174][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 2.4733123779296875, cross_entropy: 2.4733123779296875 +[2025-04-27 12:37:30,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.3102374076843262, cross_entropy: 1.3102374076843262 +[2025-04-27 12:37:33,245][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 0.9303253889083862, cross_entropy: 0.9303253889083862 +[2025-04-27 12:37:33,812][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.3983159065246582, cross_entropy: 1.3983159065246582 +[2025-04-27 12:37:36,245][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 1.9152354001998901, cross_entropy: 1.9152354001998901 +[2025-04-27 12:37:36,937][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 1.710094690322876, cross_entropy: 1.710094690322876 +[2025-04-27 12:37:39,970][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.257187843322754, cross_entropy: 1.257187843322754 +[2025-04-27 12:37:40,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.206564426422119, cross_entropy: 3.206564426422119 +[2025-04-27 12:37:42,807][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 1.1425180435180664, cross_entropy: 1.1425180435180664 +[2025-04-27 12:37:43,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 2.825239658355713, cross_entropy: 2.825239658355713 +[2025-04-27 12:37:45,803][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.163811445236206, cross_entropy: 1.163811445236206 +[2025-04-27 12:37:46,257][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 2.026601791381836, cross_entropy: 2.026601791381836 +[2025-04-27 12:37:48,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.2095847129821777, cross_entropy: 1.2095847129821777 +[2025-04-27 12:37:49,306][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.5605273246765137, cross_entropy: 1.5605273246765137 +[2025-04-27 12:37:51,452][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.2713204622268677, cross_entropy: 1.2713204622268677 +[2025-04-27 12:37:52,904][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 1.7383086681365967, cross_entropy: 1.7383086681365967 +[2025-04-27 12:37:54,864][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.4355838298797607, cross_entropy: 1.4355838298797607 +[2025-04-27 12:37:55,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.6634609699249268, cross_entropy: 1.6634609699249268 +[2025-04-27 12:37:57,586][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.2431355714797974, cross_entropy: 1.2431355714797974 +[2025-04-27 12:37:58,369][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 3.2635788917541504, cross_entropy: 3.2635788917541504 +[2025-04-27 12:38:01,316][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.133549690246582, cross_entropy: 1.133549690246582 +[2025-04-27 12:38:01,595][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.511094570159912, cross_entropy: 2.511094570159912 +[2025-04-27 12:38:04,756][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.0805965662002563, cross_entropy: 1.0805965662002563 +[2025-04-27 12:38:05,041][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.360064148902893, cross_entropy: 1.360064148902893 +[2025-04-27 12:38:07,526][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.5734941959381104, cross_entropy: 2.5734941959381104 +[2025-04-27 12:38:07,816][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.8274033069610596, cross_entropy: 2.8274033069610596 +[2025-04-27 12:38:10,258][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.5025899410247803, cross_entropy: 2.5025899410247803 +[2025-04-27 12:38:10,549][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 3.3096017837524414, cross_entropy: 3.3096017837524414 +[2025-04-27 12:38:13,420][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.926448345184326, cross_entropy: 2.926448345184326 +[2025-04-27 12:38:13,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 0.9976446032524109, cross_entropy: 0.9976446032524109 +[2025-04-27 12:38:15,964][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 0.9775298833847046, cross_entropy: 0.9775298833847046 +[2025-04-27 12:38:16,234][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 0.954825758934021, cross_entropy: 0.954825758934021 +[2025-04-27 12:38:18,899][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.579298734664917, cross_entropy: 2.579298734664917 +[2025-04-27 12:38:19,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 1.9410892724990845, cross_entropy: 1.9410892724990845 +[2025-04-27 12:38:21,978][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.5393731594085693, cross_entropy: 1.5393731594085693 +[2025-04-27 12:38:22,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 1.2144734859466553, cross_entropy: 1.2144734859466553 +[2025-04-27 12:38:24,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 2.2973413467407227, cross_entropy: 2.2973413467407227 +[2025-04-27 12:38:25,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 2.803779125213623, cross_entropy: 2.803779125213623 +[2025-04-27 12:38:27,636][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 2.498800277709961, cross_entropy: 2.498800277709961 +[2025-04-27 12:38:27,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 1.173437476158142, cross_entropy: 1.173437476158142 +[2025-04-27 12:38:30,532][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 3.00101637840271, cross_entropy: 3.00101637840271 +[2025-04-27 12:38:30,798][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.10195255279541, cross_entropy: 3.10195255279541 +[2025-04-27 12:38:33,372][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.045257329940796, cross_entropy: 2.045257329940796 +[2025-04-27 12:38:33,662][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 0.9941324591636658, cross_entropy: 0.9941324591636658 +[2025-04-27 12:38:35,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 3.1009976863861084, cross_entropy: 3.1009976863861084 +[2025-04-27 12:38:36,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.2159624099731445, cross_entropy: 2.2159624099731445 +[2025-04-27 12:38:38,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 3.2072036266326904, cross_entropy: 3.2072036266326904 +[2025-04-27 12:38:39,722][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 2.936202049255371, cross_entropy: 2.936202049255371 +[2025-04-27 12:38:41,168][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.2605643272399902, cross_entropy: 1.2605643272399902 +[2025-04-27 12:38:42,295][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.3370249271392822, cross_entropy: 1.3370249271392822 +[2025-04-27 12:38:44,104][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 2.0946054458618164, cross_entropy: 2.0946054458618164 +[2025-04-27 12:38:45,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 1.9461088180541992, cross_entropy: 1.9461088180541992 +[2025-04-27 12:38:46,590][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.9155945777893066, cross_entropy: 2.9155945777893066 +[2025-04-27 12:38:48,370][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.1452059745788574, cross_entropy: 2.1452059745788574 +[2025-04-27 12:38:49,054][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 0.913371741771698, cross_entropy: 0.913371741771698 +[2025-04-27 12:38:52,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.094170093536377, cross_entropy: 2.094170093536377 +[2025-04-27 12:38:52,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.038133144378662, cross_entropy: 1.038133144378662 +[2025-04-27 12:38:54,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.2433419227600098, cross_entropy: 2.2433419227600098 +[2025-04-27 12:38:54,953][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.08249032497406, cross_entropy: 1.08249032497406 +[2025-04-27 12:38:57,489][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.6988680362701416, cross_entropy: 1.6988680362701416 +[2025-04-27 12:38:57,779][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.7218506336212158, cross_entropy: 1.7218506336212158 +[2025-04-27 12:39:00,059][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 1.8530038595199585, cross_entropy: 1.8530038595199585 +[2025-04-27 12:39:00,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.092215061187744, cross_entropy: 3.092215061187744 +[2025-04-27 12:39:02,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 1.6577365398406982, cross_entropy: 1.6577365398406982 +[2025-04-27 12:39:02,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 0.7634326219558716, cross_entropy: 0.7634326219558716 +[2025-04-27 12:39:04,917][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.023144006729126, cross_entropy: 1.023144006729126 +[2025-04-27 12:39:05,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.2208216190338135, cross_entropy: 1.2208216190338135 +[2025-04-27 12:39:07,373][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.5277175903320312, cross_entropy: 2.5277175903320312 +[2025-04-27 12:39:07,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 1.6076831817626953, cross_entropy: 1.6076831817626953 +[2025-04-27 12:39:09,821][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 2.7780776023864746, cross_entropy: 2.7780776023864746 +[2025-04-27 12:39:10,114][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3246616125106812, cross_entropy: 1.3246616125106812 +[2025-04-27 12:39:12,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 1.2583990097045898, cross_entropy: 1.2583990097045898 +[2025-04-27 12:39:12,509][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.3460936546325684, cross_entropy: 2.3460936546325684 +[2025-04-27 12:39:14,732][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.309248924255371, cross_entropy: 1.309248924255371 +[2025-04-27 12:39:15,038][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.418025016784668, cross_entropy: 2.418025016784668 +[2025-04-27 12:39:17,578][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 2.7898478507995605, cross_entropy: 2.7898478507995605 +[2025-04-27 12:39:17,843][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.1175000667572021, cross_entropy: 1.1175000667572021 +[2025-04-27 12:39:19,667][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 3.020934581756592, cross_entropy: 3.020934581756592 +[2025-04-27 12:39:20,266][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.499820590019226, cross_entropy: 1.499820590019226 +[2025-04-27 12:39:22,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.6055541038513184, cross_entropy: 1.6055541038513184 +[2025-04-27 12:39:22,643][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.2526941299438477, cross_entropy: 1.2526941299438477 +[2025-04-27 12:39:24,751][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 3.0752925872802734, cross_entropy: 3.0752925872802734 +[2025-04-27 12:39:25,169][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 2.1543519496917725, cross_entropy: 2.1543519496917725 +[2025-04-27 12:39:27,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.7451993227005005, cross_entropy: 1.7451993227005005 +[2025-04-27 12:39:29,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 1.2546534538269043, cross_entropy: 1.2546534538269043 +[2025-04-27 12:39:30,749][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.0070538520812988, cross_entropy: 1.0070538520812988 +[2025-04-27 12:39:31,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.8801424503326416, cross_entropy: 2.8801424503326416 +[2025-04-27 12:39:33,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 1.8744165897369385, cross_entropy: 1.8744165897369385 +[2025-04-27 12:39:33,933][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 2.3893837928771973, cross_entropy: 2.3893837928771973 +[2025-04-27 12:39:36,037][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 3.0358238220214844, cross_entropy: 3.0358238220214844 +[2025-04-27 12:39:36,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.676801919937134, cross_entropy: 2.676801919937134 +[2025-04-27 12:39:38,366][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 1.8481756448745728, cross_entropy: 1.8481756448745728 +[2025-04-27 12:39:39,291][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 3.0701792240142822, cross_entropy: 3.0701792240142822 +[2025-04-27 12:39:40,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.3892550468444824, cross_entropy: 3.3892550468444824 +[2025-04-27 12:39:42,316][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.2514824867248535, cross_entropy: 2.2514824867248535 +[2025-04-27 12:39:43,749][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.476485252380371, cross_entropy: 2.476485252380371 +[2025-04-27 12:39:45,063][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 2.220465660095215, cross_entropy: 2.220465660095215 +[2025-04-27 12:39:46,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.2931302785873413, cross_entropy: 1.2931302785873413 +[2025-04-27 12:39:47,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 1.9622502326965332, cross_entropy: 1.9622502326965332 +[2025-04-27 12:39:49,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.0344934463500977, cross_entropy: 1.0344934463500977 +[2025-04-27 12:39:50,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.315455198287964, cross_entropy: 2.315455198287964 +[2025-04-27 12:39:52,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.2030384540557861, cross_entropy: 1.2030384540557861 +[2025-04-27 12:39:52,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.6127911806106567, cross_entropy: 1.6127911806106567 +[2025-04-27 12:39:54,647][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.445678234100342, cross_entropy: 2.445678234100342 +[2025-04-27 12:39:55,419][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.82513689994812, cross_entropy: 2.82513689994812 +[2025-04-27 12:39:57,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.2359521389007568, cross_entropy: 1.2359521389007568 +[2025-04-27 12:39:58,023][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 0.9860349297523499, cross_entropy: 0.9860349297523499 +[2025-04-27 12:40:00,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 3.0084328651428223, cross_entropy: 3.0084328651428223 +[2025-04-27 12:40:00,634][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 0.8567103147506714, cross_entropy: 0.8567103147506714 +[2025-04-27 12:40:03,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 0.8079124689102173, cross_entropy: 0.8079124689102173 +[2025-04-27 12:40:03,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 0.7965730428695679, cross_entropy: 0.7965730428695679 +[2025-04-27 12:40:06,258][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.8004707098007202, cross_entropy: 1.8004707098007202 +[2025-04-27 12:40:06,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 3.1684205532073975, cross_entropy: 3.1684205532073975 +[2025-04-27 12:40:08,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 3.2091264724731445, cross_entropy: 3.2091264724731445 +[2025-04-27 12:40:09,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.3445706367492676, cross_entropy: 1.3445706367492676 +[2025-04-27 12:40:11,387][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.0275733470916748, cross_entropy: 1.0275733470916748 +[2025-04-27 12:40:11,677][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 0.9989528059959412, cross_entropy: 0.9989528059959412 +[2025-04-27 12:40:13,951][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.3289835453033447, cross_entropy: 2.3289835453033447 +[2025-04-27 12:40:14,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.0724711418151855, cross_entropy: 2.0724711418151855 +[2025-04-27 12:40:17,675][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.6102632284164429, cross_entropy: 1.6102632284164429 +[2025-04-27 12:40:17,966][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.3613120317459106, cross_entropy: 1.3613120317459106 +[2025-04-27 12:40:20,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.1017398834228516, cross_entropy: 3.1017398834228516 +[2025-04-27 12:40:20,742][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.3498239517211914, cross_entropy: 1.3498239517211914 +[2025-04-27 12:40:23,056][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.3064429759979248, cross_entropy: 1.3064429759979248 +[2025-04-27 12:40:23,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 1.3795695304870605, cross_entropy: 1.3795695304870605 +[2025-04-27 12:40:26,521][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 2.971580982208252, cross_entropy: 2.971580982208252 +[2025-04-27 12:40:26,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.1544620990753174, cross_entropy: 2.1544620990753174 +[2025-04-27 12:40:29,070][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 1.0711379051208496, cross_entropy: 1.0711379051208496 +[2025-04-27 12:40:29,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.208052396774292, cross_entropy: 1.208052396774292 +[2025-04-27 12:40:31,326][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 2.7808260917663574, cross_entropy: 2.7808260917663574 +[2025-04-27 12:40:31,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 3.018406391143799, cross_entropy: 3.018406391143799 +[2025-04-27 12:40:33,952][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.3597049713134766, cross_entropy: 2.3597049713134766 +[2025-04-27 12:40:34,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 3.1860666275024414, cross_entropy: 3.1860666275024414 +[2025-04-27 12:40:36,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 2.860909938812256, cross_entropy: 2.860909938812256 +[2025-04-27 12:40:36,763][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 2.900125503540039, cross_entropy: 2.900125503540039 +[2025-04-27 12:40:38,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 3.3578505516052246, cross_entropy: 3.3578505516052246 +[2025-04-27 12:40:39,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 1.6388680934906006, cross_entropy: 1.6388680934906006 +[2025-04-27 12:40:41,616][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 2.9051108360290527, cross_entropy: 2.9051108360290527 +[2025-04-27 12:40:41,883][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.180177092552185, cross_entropy: 1.180177092552185 +[2025-04-27 12:40:43,883][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.2923004627227783, cross_entropy: 1.2923004627227783 +[2025-04-27 12:40:44,172][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 1.4227062463760376, cross_entropy: 1.4227062463760376 +[2025-04-27 12:40:46,396][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.573598027229309, cross_entropy: 1.573598027229309 +[2025-04-27 12:40:46,663][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 1.1440151929855347, cross_entropy: 1.1440151929855347 +[2025-04-27 12:40:49,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 2.734055995941162, cross_entropy: 2.734055995941162 +[2025-04-27 12:40:49,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 2.470158576965332, cross_entropy: 2.470158576965332 +[2025-04-27 12:40:51,915][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.149786114692688, cross_entropy: 1.149786114692688 +[2025-04-27 12:40:52,204][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 0.8944926261901855, cross_entropy: 0.8944926261901855 +[2025-04-27 12:40:54,779][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.706416606903076, cross_entropy: 2.706416606903076 +[2025-04-27 12:40:55,067][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 1.2314645051956177, cross_entropy: 1.2314645051956177 +[2025-04-27 12:40:57,474][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.1883440017700195, cross_entropy: 1.1883440017700195 +[2025-04-27 12:40:57,738][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 1.6694602966308594, cross_entropy: 1.6694602966308594 +[2025-04-27 12:41:00,336][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 2.842526435852051, cross_entropy: 2.842526435852051 +[2025-04-27 12:41:00,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 2.037578821182251, cross_entropy: 2.037578821182251 +[2025-04-27 12:41:02,526][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 1.5205897092819214, cross_entropy: 1.5205897092819214 +[2025-04-27 12:41:02,794][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 1.365781307220459, cross_entropy: 1.365781307220459 +[2025-04-27 12:41:05,715][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.060356616973877, cross_entropy: 2.060356616973877 +[2025-04-27 12:41:06,009][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.500124454498291, cross_entropy: 2.500124454498291 +[2025-04-27 12:41:08,574][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.0224955081939697, cross_entropy: 2.0224955081939697 +[2025-04-27 12:41:08,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 3.0295662879943848, cross_entropy: 3.0295662879943848 +[2025-04-27 12:41:11,506][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 3.0058021545410156, cross_entropy: 3.0058021545410156 +[2025-04-27 12:41:11,794][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.82753849029541, cross_entropy: 2.82753849029541 +[2025-04-27 12:41:14,262][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.0622673034667969, cross_entropy: 1.0622673034667969 +[2025-04-27 12:41:14,528][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 0.9658145308494568, cross_entropy: 0.9658145308494568 +[2025-04-27 12:41:16,609][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.2895439863204956, cross_entropy: 1.2895439863204956 +[2025-04-27 12:41:16,874][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.955681562423706, cross_entropy: 2.955681562423706 +[2025-04-27 12:41:19,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.9498260021209717, cross_entropy: 2.9498260021209717 +[2025-04-27 12:41:19,850][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 3.193416118621826, cross_entropy: 3.193416118621826 +[2025-04-27 12:41:23,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.4657175540924072, cross_entropy: 1.4657175540924072 +[2025-04-27 12:41:23,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.625807523727417, cross_entropy: 1.625807523727417 +[2025-04-27 12:41:25,712][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 2.229766368865967, cross_entropy: 2.229766368865967 +[2025-04-27 12:41:26,001][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 1.8404889106750488, cross_entropy: 1.8404889106750488 +[2025-04-27 12:41:28,620][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 0.9780163764953613, cross_entropy: 0.9780163764953613 +[2025-04-27 12:41:28,910][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 1.4179954528808594, cross_entropy: 1.4179954528808594 +[2025-04-27 12:41:31,491][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.584994316101074, cross_entropy: 2.584994316101074 +[2025-04-27 12:41:31,758][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 3.1872811317443848, cross_entropy: 3.1872811317443848 +[2025-04-27 12:41:34,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.2529001235961914, cross_entropy: 2.2529001235961914 +[2025-04-27 12:41:34,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.5643761157989502, cross_entropy: 1.5643761157989502 +[2025-04-27 12:41:37,403][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.7311320304870605, cross_entropy: 1.7311320304870605 +[2025-04-27 12:41:37,695][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.1942048072814941, cross_entropy: 1.1942048072814941 +[2025-04-27 12:41:40,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.110183835029602, cross_entropy: 1.110183835029602 +[2025-04-27 12:41:40,385][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.708589553833008, cross_entropy: 2.708589553833008 +[2025-04-27 12:41:42,751][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 0.9975408315658569, cross_entropy: 0.9975408315658569 +[2025-04-27 12:41:43,018][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.066601276397705, cross_entropy: 2.066601276397705 +[2025-04-27 12:41:45,676][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 0.798595130443573, cross_entropy: 0.798595130443573 +[2025-04-27 12:41:45,941][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.6616129875183105, cross_entropy: 1.6616129875183105 +[2025-04-27 12:41:48,095][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 3.488532066345215, cross_entropy: 3.488532066345215 +[2025-04-27 12:41:48,385][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.0892497301101685, cross_entropy: 1.0892497301101685 +[2025-04-27 12:41:50,464][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 3.1790506839752197, cross_entropy: 3.1790506839752197 +[2025-04-27 12:41:50,752][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 1.5710123777389526, cross_entropy: 1.5710123777389526 +[2025-04-27 12:41:53,048][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.5776801109313965, cross_entropy: 2.5776801109313965 +[2025-04-27 12:41:53,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.1116952896118164, cross_entropy: 2.1116952896118164 +[2025-04-27 12:41:55,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.6177815198898315, cross_entropy: 1.6177815198898315 +[2025-04-27 12:41:55,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.2132768630981445, cross_entropy: 3.2132768630981445 +[2025-04-27 12:41:58,079][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.762603759765625, cross_entropy: 2.762603759765625 +[2025-04-27 12:41:58,367][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 1.1525694131851196, cross_entropy: 1.1525694131851196 +[2025-04-27 12:42:00,695][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.4482262134552002, cross_entropy: 1.4482262134552002 +[2025-04-27 12:42:00,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.6615064144134521, cross_entropy: 1.6615064144134521 +[2025-04-27 12:42:03,262][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.4075839519500732, cross_entropy: 1.4075839519500732 +[2025-04-27 12:42:03,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 1.8638778924942017, cross_entropy: 1.8638778924942017 +[2025-04-27 12:42:05,615][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 1.1383779048919678, cross_entropy: 1.1383779048919678 +[2025-04-27 12:42:06,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.4916257858276367, cross_entropy: 2.4916257858276367 +[2025-04-27 12:42:08,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.468975305557251, cross_entropy: 1.468975305557251 +[2025-04-27 12:42:09,314][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.9821014404296875, cross_entropy: 1.9821014404296875 +[2025-04-27 12:42:11,313][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.5007405281066895, cross_entropy: 2.5007405281066895 +[2025-04-27 12:42:12,108][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 3.011037826538086, cross_entropy: 3.011037826538086 +[2025-04-27 12:42:13,301][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 1.55733323097229, cross_entropy: 1.55733323097229 +[2025-04-27 12:42:14,722][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 2.2635607719421387, cross_entropy: 2.2635607719421387 +[2025-04-27 12:42:15,815][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 3.0540192127227783, cross_entropy: 3.0540192127227783 +[2025-04-27 12:42:17,029][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 1.691056489944458, cross_entropy: 1.691056489944458 +[2025-04-27 12:42:18,855][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.354742169380188, cross_entropy: 1.354742169380188 +[2025-04-27 12:42:19,984][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.4268836975097656, cross_entropy: 1.4268836975097656 +[2025-04-27 12:42:21,879][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.886658191680908, cross_entropy: 2.886658191680908 +[2025-04-27 12:42:22,371][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.0597128868103027, cross_entropy: 1.0597128868103027 +[2025-04-27 12:42:25,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.0819225311279297, cross_entropy: 2.0819225311279297 +[2025-04-27 12:42:25,824][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 2.7257914543151855, cross_entropy: 2.7257914543151855 +[2025-04-27 12:42:27,793][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 0.914725661277771, cross_entropy: 0.914725661277771 +[2025-04-27 12:42:28,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 2.0383777618408203, cross_entropy: 2.0383777618408203 +[2025-04-27 12:42:30,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.0454204082489014, cross_entropy: 1.0454204082489014 +[2025-04-27 12:42:30,599][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.2507240772247314, cross_entropy: 1.2507240772247314 +[2025-04-27 12:42:32,565][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 3.2845606803894043, cross_entropy: 3.2845606803894043 +[2025-04-27 12:42:33,374][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 1.3247339725494385, cross_entropy: 1.3247339725494385 +[2025-04-27 12:42:34,979][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 1.008992314338684, cross_entropy: 1.008992314338684 +[2025-04-27 12:42:35,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.200338363647461, cross_entropy: 3.200338363647461 +[2025-04-27 12:42:37,503][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.8127762079238892, cross_entropy: 1.8127762079238892 +[2025-04-27 12:42:38,286][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.878206729888916, cross_entropy: 2.878206729888916 +[2025-04-27 12:42:40,030][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.40848708152771, cross_entropy: 2.40848708152771 +[2025-04-27 12:42:41,218][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 1.6521003246307373, cross_entropy: 1.6521003246307373 +[2025-04-27 12:42:42,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.2419794797897339, cross_entropy: 1.2419794797897339 +[2025-04-27 12:42:43,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.4580113887786865, cross_entropy: 1.4580113887786865 +[2025-04-27 12:42:45,605][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 0.8112795352935791, cross_entropy: 0.8112795352935791 +[2025-04-27 12:42:46,457][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.1265618801116943, cross_entropy: 1.1265618801116943 +[2025-04-27 12:42:48,433][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 0.9249447584152222, cross_entropy: 0.9249447584152222 +[2025-04-27 12:42:48,943][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 2.983091354370117, cross_entropy: 2.983091354370117 +[2025-04-27 12:42:51,458][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 3.0457053184509277, cross_entropy: 3.0457053184509277 +[2025-04-27 12:42:51,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 1.8550517559051514, cross_entropy: 1.8550517559051514 +[2025-04-27 12:42:54,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.340890407562256, cross_entropy: 3.340890407562256 +[2025-04-27 12:42:55,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.9604718685150146, cross_entropy: 2.9604718685150146 +[2025-04-27 12:42:57,732][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.764127731323242, cross_entropy: 2.764127731323242 +[2025-04-27 12:42:58,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.192686080932617, cross_entropy: 3.192686080932617 +[2025-04-27 12:43:01,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.3079586029052734, cross_entropy: 2.3079586029052734 +[2025-04-27 12:43:01,381][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.0853828191757202, cross_entropy: 1.0853828191757202 +[2025-04-27 12:43:04,152][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 0.6409429311752319, cross_entropy: 0.6409429311752319 +[2025-04-27 12:43:04,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.3724365234375, cross_entropy: 1.3724365234375 +[2025-04-27 12:43:06,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 1.1885316371917725, cross_entropy: 1.1885316371917725 +[2025-04-27 12:43:06,969][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 2.937941789627075, cross_entropy: 2.937941789627075 +[2025-04-27 12:43:09,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.654749870300293, cross_entropy: 2.654749870300293 +[2025-04-27 12:43:09,800][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.7193043231964111, cross_entropy: 1.7193043231964111 +[2025-04-27 12:43:13,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.112485647201538, cross_entropy: 2.112485647201538 +[2025-04-27 12:43:13,780][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.575378894805908, cross_entropy: 2.575378894805908 +[2025-04-27 12:43:16,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.4006489515304565, cross_entropy: 1.4006489515304565 +[2025-04-27 12:43:16,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.6915351152420044, cross_entropy: 1.6915351152420044 +[2025-04-27 12:43:18,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 3.024892807006836, cross_entropy: 3.024892807006836 +[2025-04-27 12:43:18,773][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 2.5475873947143555, cross_entropy: 2.5475873947143555 +[2025-04-27 12:43:20,439][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.2628064155578613, cross_entropy: 1.2628064155578613 +[2025-04-27 12:43:20,730][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 1.8558179140090942, cross_entropy: 1.8558179140090942 +[2025-04-27 12:43:23,249][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 2.629075765609741, cross_entropy: 2.629075765609741 +[2025-04-27 12:43:23,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 3.229116439819336, cross_entropy: 3.229116439819336 +[2025-04-27 12:43:25,898][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 2.9588229656219482, cross_entropy: 2.9588229656219482 +[2025-04-27 12:43:26,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 2.991698741912842, cross_entropy: 2.991698741912842 +[2025-04-27 12:43:28,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.051086187362671, cross_entropy: 1.051086187362671 +[2025-04-27 12:43:28,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 0.746680498123169, cross_entropy: 0.746680498123169 +[2025-04-27 12:43:31,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 1.0251201391220093, cross_entropy: 1.0251201391220093 +[2025-04-27 12:43:31,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.328396201133728, cross_entropy: 1.328396201133728 +[2025-04-27 12:43:34,412][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.9558377265930176, cross_entropy: 1.9558377265930176 +[2025-04-27 12:43:34,700][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.2455419301986694, cross_entropy: 1.2455419301986694 +[2025-04-27 12:43:37,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 0.9003611207008362, cross_entropy: 0.9003611207008362 +[2025-04-27 12:43:38,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 2.618725299835205, cross_entropy: 2.618725299835205 +[2025-04-27 12:43:40,017][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 2.0359277725219727, cross_entropy: 2.0359277725219727 +[2025-04-27 12:43:40,306][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.5063525438308716, cross_entropy: 1.5063525438308716 +[2025-04-27 12:43:42,546][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 1.7952606678009033, cross_entropy: 1.7952606678009033 +[2025-04-27 12:43:42,835][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.161940336227417, cross_entropy: 2.161940336227417 +[2025-04-27 12:43:45,265][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 1.8368101119995117, cross_entropy: 1.8368101119995117 +[2025-04-27 12:43:45,739][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.196232318878174, cross_entropy: 3.196232318878174 +[2025-04-27 12:43:47,629][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 1.1532161235809326, cross_entropy: 1.1532161235809326 +[2025-04-27 12:43:48,329][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 1.2960340976715088, cross_entropy: 1.2960340976715088 +[2025-04-27 12:43:50,085][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.631113052368164, cross_entropy: 2.631113052368164 +[2025-04-27 12:43:50,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.2410351037979126, cross_entropy: 1.2410351037979126 +[2025-04-27 12:43:52,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 2.4824256896972656, cross_entropy: 2.4824256896972656 +[2025-04-27 12:43:53,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.6957777738571167, cross_entropy: 1.6957777738571167 +[2025-04-27 12:43:55,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.1740503311157227, cross_entropy: 1.1740503311157227 +[2025-04-27 12:43:55,798][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 3.069905996322632, cross_entropy: 3.069905996322632 +[2025-04-27 12:43:57,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 2.6830692291259766, cross_entropy: 2.6830692291259766 +[2025-04-27 12:43:58,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.7704248428344727, cross_entropy: 2.7704248428344727 +[2025-04-27 12:44:00,604][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.3376805782318115, cross_entropy: 1.3376805782318115 +[2025-04-27 12:44:01,769][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 0.9884141683578491, cross_entropy: 0.9884141683578491 +[2025-04-27 12:44:02,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.2755870819091797, cross_entropy: 1.2755870819091797 +[2025-04-27 12:44:04,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.8223347663879395, cross_entropy: 2.8223347663879395 +[2025-04-27 12:44:05,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 3.308948040008545, cross_entropy: 3.308948040008545 +[2025-04-27 12:44:07,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.3093128204345703, cross_entropy: 1.3093128204345703 +[2025-04-27 12:44:08,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 1.2382149696350098, cross_entropy: 1.2382149696350098 +[2025-04-27 12:44:10,127][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 1.9733495712280273, cross_entropy: 1.9733495712280273 +[2025-04-27 12:44:10,610][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.0922893285751343, cross_entropy: 1.0922893285751343 +[2025-04-27 12:44:12,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.3372323513031006, cross_entropy: 1.3372323513031006 +[2025-04-27 12:44:13,223][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.5745041370391846, cross_entropy: 1.5745041370391846 +[2025-04-27 12:44:14,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 2.0188331604003906, cross_entropy: 2.0188331604003906 +[2025-04-27 12:44:16,163][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.2414467334747314, cross_entropy: 1.2414467334747314 +[2025-04-27 12:44:17,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.2359628677368164, cross_entropy: 2.2359628677368164 +[2025-04-27 12:44:19,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 1.6156002283096313, cross_entropy: 1.6156002283096313 +[2025-04-27 12:44:19,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.1944305896759033, cross_entropy: 2.1944305896759033 +[2025-04-27 12:44:22,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.2005257606506348, cross_entropy: 3.2005257606506348 +[2025-04-27 12:44:22,518][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 3.177522659301758, cross_entropy: 3.177522659301758 +[2025-04-27 12:44:24,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 1.3542892932891846, cross_entropy: 1.3542892932891846 +[2025-04-27 12:44:25,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.08209228515625, cross_entropy: 2.08209228515625 +[2025-04-27 12:44:27,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.7610249519348145, cross_entropy: 1.7610249519348145 +[2025-04-27 12:44:27,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 1.8902091979980469, cross_entropy: 1.8902091979980469 +[2025-04-27 12:44:29,513][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.5366756916046143, cross_entropy: 1.5366756916046143 +[2025-04-27 12:44:29,799][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 3.003572463989258, cross_entropy: 3.003572463989258 +[2025-04-27 12:44:31,960][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.9376626014709473, cross_entropy: 2.9376626014709473 +[2025-04-27 12:44:32,242][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.612093925476074, cross_entropy: 2.612093925476074 +[2025-04-27 12:44:34,657][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 2.231995105743408, cross_entropy: 2.231995105743408 +[2025-04-27 12:44:35,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 1.1668109893798828, cross_entropy: 1.1668109893798828 +[2025-04-27 12:44:37,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.3865418434143066, cross_entropy: 2.3865418434143066 +[2025-04-27 12:44:39,422][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 1.2876924276351929, cross_entropy: 1.2876924276351929 +[2025-04-27 12:44:39,995][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.268449068069458, cross_entropy: 3.268449068069458 +[2025-04-27 12:44:42,104][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.0742195844650269, cross_entropy: 1.0742195844650269 +[2025-04-27 12:44:42,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.1397671699523926, cross_entropy: 2.1397671699523926 +[2025-04-27 12:44:44,847][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.4269170761108398, cross_entropy: 1.4269170761108398 +[2025-04-27 12:44:45,156][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 0.9820336699485779, cross_entropy: 0.9820336699485779 +[2025-04-27 12:44:47,608][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.042719841003418, cross_entropy: 2.042719841003418 +[2025-04-27 12:44:48,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.4052485227584839, cross_entropy: 1.4052485227584839 +[2025-04-27 12:44:50,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.5155179500579834, cross_entropy: 1.5155179500579834 +[2025-04-27 12:44:50,958][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.425858736038208, cross_entropy: 2.425858736038208 +[2025-04-27 12:44:52,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.32765793800354, cross_entropy: 1.32765793800354 +[2025-04-27 12:44:54,188][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 0.8577020764350891, cross_entropy: 0.8577020764350891 +[2025-04-27 12:44:55,286][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 1.5511245727539062, cross_entropy: 1.5511245727539062 +[2025-04-27 12:44:56,679][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 1.1136987209320068, cross_entropy: 1.1136987209320068 +[2025-04-27 12:44:57,192][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.1635586023330688, cross_entropy: 1.1635586023330688 +[2025-04-27 12:47:01,698][BaseTrainer][INFO] - [Epoch 5/10] (train) 1.9411011934280396, cross_entropy: 1.9411011934280396 +[2025-04-27 12:47:01,698][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.2401303052902222, cross_entropy: 1.2401303052902222 +[2025-04-27 12:47:01,920][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:47:02,089][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch5.pth. +[2025-04-27 12:47:02,291][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:47:05,768][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 0.5747247934341431, cross_entropy: 0.5747247934341431 +[2025-04-27 12:47:06,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.533820629119873, cross_entropy: 1.533820629119873 +[2025-04-27 12:47:07,811][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 2.8542022705078125, cross_entropy: 2.8542022705078125 +[2025-04-27 12:47:08,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 2.6070284843444824, cross_entropy: 2.6070284843444824 +[2025-04-27 12:47:10,392][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 1.9859131574630737, cross_entropy: 1.9859131574630737 +[2025-04-27 12:47:10,686][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 2.8717727661132812, cross_entropy: 2.8717727661132812 +[2025-04-27 12:47:12,696][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 2.58427095413208, cross_entropy: 2.58427095413208 +[2025-04-27 12:47:13,686][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.087540626525879, cross_entropy: 1.087540626525879 +[2025-04-27 12:47:15,682][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.4890882968902588, cross_entropy: 1.4890882968902588 +[2025-04-27 12:47:16,156][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 1.9521960020065308, cross_entropy: 1.9521960020065308 +[2025-04-27 12:47:18,406][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.438068389892578, cross_entropy: 2.438068389892578 +[2025-04-27 12:47:19,021][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 1.9044408798217773, cross_entropy: 1.9044408798217773 +[2025-04-27 12:47:20,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 3.1912810802459717, cross_entropy: 3.1912810802459717 +[2025-04-27 12:47:22,081][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.7252695560455322, cross_entropy: 1.7252695560455322 +[2025-04-27 12:47:22,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 0.7646137475967407, cross_entropy: 0.7646137475967407 +[2025-04-27 12:47:24,826][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.2705180644989014, cross_entropy: 2.2705180644989014 +[2025-04-27 12:47:25,585][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.1033847332000732, cross_entropy: 1.1033847332000732 +[2025-04-27 12:47:28,301][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.025763988494873, cross_entropy: 3.025763988494873 +[2025-04-27 12:47:28,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 0.9285112023353577, cross_entropy: 0.9285112023353577 +[2025-04-27 12:47:30,849][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 3.0836870670318604, cross_entropy: 3.0836870670318604 +[2025-04-27 12:47:31,200][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 1.8660255670547485, cross_entropy: 1.8660255670547485 +[2025-04-27 12:47:33,368][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.298346996307373, cross_entropy: 1.298346996307373 +[2025-04-27 12:47:33,933][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 0.934635579586029, cross_entropy: 0.934635579586029 +[2025-04-27 12:47:35,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.315197467803955, cross_entropy: 2.315197467803955 +[2025-04-27 12:47:36,579][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 0.8564279079437256, cross_entropy: 0.8564279079437256 +[2025-04-27 12:47:38,349][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.161832094192505, cross_entropy: 2.161832094192505 +[2025-04-27 12:47:39,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 0.9810093641281128, cross_entropy: 0.9810093641281128 +[2025-04-27 12:47:41,481][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.191765069961548, cross_entropy: 2.191765069961548 +[2025-04-27 12:47:41,768][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.5435714721679688, cross_entropy: 1.5435714721679688 +[2025-04-27 12:47:44,174][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 0.9126121401786804, cross_entropy: 0.9126121401786804 +[2025-04-27 12:47:44,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.1149598360061646, cross_entropy: 1.1149598360061646 +[2025-04-27 12:47:47,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.731797695159912, cross_entropy: 2.731797695159912 +[2025-04-27 12:47:47,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 1.6812981367111206, cross_entropy: 1.6812981367111206 +[2025-04-27 12:47:50,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 2.90266752243042, cross_entropy: 2.90266752243042 +[2025-04-27 12:47:50,351][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.7989883422851562, cross_entropy: 2.7989883422851562 +[2025-04-27 12:47:53,179][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 0.9113034605979919, cross_entropy: 0.9113034605979919 +[2025-04-27 12:47:53,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 0.9802311062812805, cross_entropy: 0.9802311062812805 +[2025-04-27 12:47:55,538][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 2.6838457584381104, cross_entropy: 2.6838457584381104 +[2025-04-27 12:47:55,826][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.4670357704162598, cross_entropy: 2.4670357704162598 +[2025-04-27 12:47:58,981][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.5279463529586792, cross_entropy: 1.5279463529586792 +[2025-04-27 12:47:59,269][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 3.2504751682281494, cross_entropy: 3.2504751682281494 +[2025-04-27 12:48:02,054][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.725095510482788, cross_entropy: 2.725095510482788 +[2025-04-27 12:48:02,341][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.1140851974487305, cross_entropy: 1.1140851974487305 +[2025-04-27 12:48:04,248][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 2.827130079269409, cross_entropy: 2.827130079269409 +[2025-04-27 12:48:04,535][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 0.9553675651550293, cross_entropy: 0.9553675651550293 +[2025-04-27 12:48:07,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.0267419815063477, cross_entropy: 2.0267419815063477 +[2025-04-27 12:48:07,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.9134483337402344, cross_entropy: 2.9134483337402344 +[2025-04-27 12:48:09,657][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 3.2045485973358154, cross_entropy: 3.2045485973358154 +[2025-04-27 12:48:09,943][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.5237858295440674, cross_entropy: 1.5237858295440674 +[2025-04-27 12:48:12,339][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.6752312183380127, cross_entropy: 1.6752312183380127 +[2025-04-27 12:48:12,602][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 3.0301477909088135, cross_entropy: 3.0301477909088135 +[2025-04-27 12:48:15,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 2.984853506088257, cross_entropy: 2.984853506088257 +[2025-04-27 12:48:15,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.5595040321350098, cross_entropy: 2.5595040321350098 +[2025-04-27 12:48:18,705][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 0.9385337829589844, cross_entropy: 0.9385337829589844 +[2025-04-27 12:48:18,986][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 0.9012696743011475, cross_entropy: 0.9012696743011475 +[2025-04-27 12:48:21,435][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 0.703384280204773, cross_entropy: 0.703384280204773 +[2025-04-27 12:48:21,725][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 2.3076601028442383, cross_entropy: 2.3076601028442383 +[2025-04-27 12:48:24,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.2422263622283936, cross_entropy: 1.2422263622283936 +[2025-04-27 12:48:24,581][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.0844831466674805, cross_entropy: 2.0844831466674805 +[2025-04-27 12:48:26,793][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.150050640106201, cross_entropy: 2.150050640106201 +[2025-04-27 12:48:27,079][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 2.0066006183624268, cross_entropy: 2.0066006183624268 +[2025-04-27 12:48:29,758][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.3066627979278564, cross_entropy: 2.3066627979278564 +[2025-04-27 12:48:30,041][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.3882290124893188, cross_entropy: 1.3882290124893188 +[2025-04-27 12:48:32,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.5488016605377197, cross_entropy: 1.5488016605377197 +[2025-04-27 12:48:32,745][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 1.0952290296554565, cross_entropy: 1.0952290296554565 +[2025-04-27 12:48:35,026][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.7440764904022217, cross_entropy: 2.7440764904022217 +[2025-04-27 12:48:35,321][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 0.9620102643966675, cross_entropy: 0.9620102643966675 +[2025-04-27 12:48:37,518][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.0369681119918823, cross_entropy: 1.0369681119918823 +[2025-04-27 12:48:37,807][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 1.0503084659576416, cross_entropy: 1.0503084659576416 +[2025-04-27 12:48:39,684][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.2585291862487793, cross_entropy: 1.2585291862487793 +[2025-04-27 12:48:39,975][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 0.6141486167907715, cross_entropy: 0.6141486167907715 +[2025-04-27 12:48:41,977][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.3577394485473633, cross_entropy: 1.3577394485473633 +[2025-04-27 12:48:42,902][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 2.8832898139953613, cross_entropy: 2.8832898139953613 +[2025-04-27 12:48:44,304][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 0.7524471282958984, cross_entropy: 0.7524471282958984 +[2025-04-27 12:48:46,358][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 0.853488564491272, cross_entropy: 0.853488564491272 +[2025-04-27 12:48:46,939][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.3737245798110962, cross_entropy: 1.3737245798110962 +[2025-04-27 12:48:48,918][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 1.4555727243423462, cross_entropy: 1.4555727243423462 +[2025-04-27 12:48:49,630][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.4692578315734863, cross_entropy: 2.4692578315734863 +[2025-04-27 12:48:51,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.0608811378479004, cross_entropy: 2.0608811378479004 +[2025-04-27 12:48:52,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 3.0443100929260254, cross_entropy: 3.0443100929260254 +[2025-04-27 12:48:54,547][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 2.64453125, cross_entropy: 2.64453125 +[2025-04-27 12:48:54,820][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 2.140558958053589, cross_entropy: 2.140558958053589 +[2025-04-27 12:48:56,960][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.9838836193084717, cross_entropy: 2.9838836193084717 +[2025-04-27 12:48:57,285][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.4510146379470825, cross_entropy: 1.4510146379470825 +[2025-04-27 12:48:59,686][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.3319165706634521, cross_entropy: 1.3319165706634521 +[2025-04-27 12:48:59,949][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 1.5528663396835327, cross_entropy: 1.5528663396835327 +[2025-04-27 12:49:02,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 1.0688886642456055, cross_entropy: 1.0688886642456055 +[2025-04-27 12:49:02,447][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 2.1774659156799316, cross_entropy: 2.1774659156799316 +[2025-04-27 12:49:05,209][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 0.9770448207855225, cross_entropy: 0.9770448207855225 +[2025-04-27 12:49:05,501][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 0.7553766965866089, cross_entropy: 0.7553766965866089 +[2025-04-27 12:49:08,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.6894900798797607, cross_entropy: 2.6894900798797607 +[2025-04-27 12:49:08,691][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.0903589725494385, cross_entropy: 1.0903589725494385 +[2025-04-27 12:49:11,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.5467801094055176, cross_entropy: 1.5467801094055176 +[2025-04-27 12:49:12,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.0801029205322266, cross_entropy: 2.0801029205322266 +[2025-04-27 12:49:14,234][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 1.64701247215271, cross_entropy: 1.64701247215271 +[2025-04-27 12:49:14,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 0.7542815804481506, cross_entropy: 0.7542815804481506 +[2025-04-27 12:49:16,678][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.896962881088257, cross_entropy: 2.896962881088257 +[2025-04-27 12:49:16,972][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.7247787714004517, cross_entropy: 1.7247787714004517 +[2025-04-27 12:49:18,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.6242384910583496, cross_entropy: 1.6242384910583496 +[2025-04-27 12:49:18,913][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.0817097425460815, cross_entropy: 1.0817097425460815 +[2025-04-27 12:49:21,330][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.0895681381225586, cross_entropy: 1.0895681381225586 +[2025-04-27 12:49:21,624][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.102440118789673, cross_entropy: 2.102440118789673 +[2025-04-27 12:49:23,665][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 2.908836841583252, cross_entropy: 2.908836841583252 +[2025-04-27 12:49:23,952][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.8006702661514282, cross_entropy: 0.8006702661514282 +[2025-04-27 12:49:26,051][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.2074148654937744, cross_entropy: 1.2074148654937744 +[2025-04-27 12:49:26,805][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.261939525604248, cross_entropy: 2.261939525604248 +[2025-04-27 12:49:29,604][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.940608263015747, cross_entropy: 2.940608263015747 +[2025-04-27 12:49:29,871][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.732974648475647, cross_entropy: 1.732974648475647 +[2025-04-27 12:49:32,533][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.8533134460449219, cross_entropy: 1.8533134460449219 +[2025-04-27 12:49:32,823][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.5278549194335938, cross_entropy: 1.5278549194335938 +[2025-04-27 12:49:35,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.1165128946304321, cross_entropy: 1.1165128946304321 +[2025-04-27 12:49:35,819][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.287880539894104, cross_entropy: 1.287880539894104 +[2025-04-27 12:49:38,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 1.4668933153152466, cross_entropy: 1.4668933153152466 +[2025-04-27 12:49:38,670][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.433788776397705, cross_entropy: 1.433788776397705 +[2025-04-27 12:49:41,397][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.7359323501586914, cross_entropy: 2.7359323501586914 +[2025-04-27 12:49:41,693][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 1.7616794109344482, cross_entropy: 1.7616794109344482 +[2025-04-27 12:49:43,974][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.8326029777526855, cross_entropy: 1.8326029777526855 +[2025-04-27 12:49:44,275][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 2.855158805847168, cross_entropy: 2.855158805847168 +[2025-04-27 12:49:46,306][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.0900979042053223, cross_entropy: 3.0900979042053223 +[2025-04-27 12:49:46,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.1001657247543335, cross_entropy: 1.1001657247543335 +[2025-04-27 12:49:48,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.678740978240967, cross_entropy: 2.678740978240967 +[2025-04-27 12:49:49,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 2.054567337036133, cross_entropy: 2.054567337036133 +[2025-04-27 12:49:51,086][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.1470413208007812, cross_entropy: 1.1470413208007812 +[2025-04-27 12:49:51,374][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 1.711215853691101, cross_entropy: 1.711215853691101 +[2025-04-27 12:49:53,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.4834953546524048, cross_entropy: 1.4834953546524048 +[2025-04-27 12:49:54,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.00284481048584, cross_entropy: 2.00284481048584 +[2025-04-27 12:49:56,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.5946241617202759, cross_entropy: 1.5946241617202759 +[2025-04-27 12:49:56,955][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 2.8536672592163086, cross_entropy: 2.8536672592163086 +[2025-04-27 12:49:59,176][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 0.8753975033760071, cross_entropy: 0.8753975033760071 +[2025-04-27 12:49:59,498][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 2.9966301918029785, cross_entropy: 2.9966301918029785 +[2025-04-27 12:50:01,421][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 3.031804084777832, cross_entropy: 3.031804084777832 +[2025-04-27 12:50:01,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.8563271760940552, cross_entropy: 1.8563271760940552 +[2025-04-27 12:50:03,567][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 3.1386804580688477, cross_entropy: 3.1386804580688477 +[2025-04-27 12:50:04,145][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.168823003768921, cross_entropy: 3.168823003768921 +[2025-04-27 12:50:06,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 3.285642147064209, cross_entropy: 3.285642147064209 +[2025-04-27 12:50:06,827][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 2.898690700531006, cross_entropy: 2.898690700531006 +[2025-04-27 12:50:08,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 1.3076324462890625, cross_entropy: 1.3076324462890625 +[2025-04-27 12:50:10,913][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.3096474409103394, cross_entropy: 1.3096474409103394 +[2025-04-27 12:50:11,613][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.7615422010421753, cross_entropy: 1.7615422010421753 +[2025-04-27 12:50:13,725][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.81787109375, cross_entropy: 2.81787109375 +[2025-04-27 12:50:14,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.3953808546066284, cross_entropy: 1.3953808546066284 +[2025-04-27 12:50:16,414][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.02383553981781, cross_entropy: 1.02383553981781 +[2025-04-27 12:50:17,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 0.9927630424499512, cross_entropy: 0.9927630424499512 +[2025-04-27 12:50:18,979][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 3.1445698738098145, cross_entropy: 3.1445698738098145 +[2025-04-27 12:50:19,442][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.611296534538269, cross_entropy: 1.611296534538269 +[2025-04-27 12:50:21,452][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.3627729415893555, cross_entropy: 1.3627729415893555 +[2025-04-27 12:50:21,735][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 1.6617934703826904, cross_entropy: 1.6617934703826904 +[2025-04-27 12:50:24,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.0041522979736328, cross_entropy: 1.0041522979736328 +[2025-04-27 12:50:24,515][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 3.1846821308135986, cross_entropy: 3.1846821308135986 +[2025-04-27 12:50:26,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.816441297531128, cross_entropy: 2.816441297531128 +[2025-04-27 12:50:27,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 1.285538911819458, cross_entropy: 1.285538911819458 +[2025-04-27 12:50:29,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.666006565093994, cross_entropy: 2.666006565093994 +[2025-04-27 12:50:29,726][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 0.9250638484954834, cross_entropy: 0.9250638484954834 +[2025-04-27 12:50:31,818][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.4555996656417847, cross_entropy: 1.4555996656417847 +[2025-04-27 12:50:32,117][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.16225266456604, cross_entropy: 1.16225266456604 +[2025-04-27 12:50:34,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.101062297821045, cross_entropy: 1.101062297821045 +[2025-04-27 12:50:34,805][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.084930658340454, cross_entropy: 2.084930658340454 +[2025-04-27 12:50:36,655][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.5673508644104004, cross_entropy: 2.5673508644104004 +[2025-04-27 12:50:37,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.2153712511062622, cross_entropy: 1.2153712511062622 +[2025-04-27 12:50:39,153][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.4936792850494385, cross_entropy: 1.4936792850494385 +[2025-04-27 12:50:40,224][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.0630226135253906, cross_entropy: 1.0630226135253906 +[2025-04-27 12:50:42,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.1699233055114746, cross_entropy: 1.1699233055114746 +[2025-04-27 12:50:43,196][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 2.599576234817505, cross_entropy: 2.599576234817505 +[2025-04-27 12:50:45,146][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 1.0848777294158936, cross_entropy: 1.0848777294158936 +[2025-04-27 12:50:45,480][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 1.2900789976119995, cross_entropy: 1.2900789976119995 +[2025-04-27 12:50:47,170][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 1.8389381170272827, cross_entropy: 1.8389381170272827 +[2025-04-27 12:50:48,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 2.8501505851745605, cross_entropy: 2.8501505851745605 +[2025-04-27 12:50:49,715][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.7399654388427734, cross_entropy: 1.7399654388427734 +[2025-04-27 12:50:50,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 2.778090476989746, cross_entropy: 2.778090476989746 +[2025-04-27 12:50:52,087][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.438779354095459, cross_entropy: 2.438779354095459 +[2025-04-27 12:50:52,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 2.612656593322754, cross_entropy: 2.612656593322754 +[2025-04-27 12:50:54,498][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.1895034313201904, cross_entropy: 1.1895034313201904 +[2025-04-27 12:50:55,041][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 2.189065456390381, cross_entropy: 2.189065456390381 +[2025-04-27 12:50:57,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.9334371089935303, cross_entropy: 1.9334371089935303 +[2025-04-27 12:50:57,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 1.1369210481643677, cross_entropy: 1.1369210481643677 +[2025-04-27 12:50:59,685][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.0306214094161987, cross_entropy: 1.0306214094161987 +[2025-04-27 12:51:00,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.6449806690216064, cross_entropy: 1.6449806690216064 +[2025-04-27 12:51:02,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.2907474040985107, cross_entropy: 1.2907474040985107 +[2025-04-27 12:51:03,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.5235939025878906, cross_entropy: 2.5235939025878906 +[2025-04-27 12:51:04,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.3282701969146729, cross_entropy: 1.3282701969146729 +[2025-04-27 12:51:05,912][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.0992792844772339, cross_entropy: 1.0992792844772339 +[2025-04-27 12:51:07,114][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 2.4329264163970947, cross_entropy: 2.4329264163970947 +[2025-04-27 12:51:08,775][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.1960527896881104, cross_entropy: 1.1960527896881104 +[2025-04-27 12:51:09,393][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.1232948303222656, cross_entropy: 2.1232948303222656 +[2025-04-27 12:51:11,362][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 2.9495952129364014, cross_entropy: 2.9495952129364014 +[2025-04-27 12:51:12,918][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.5176299810409546, cross_entropy: 1.5176299810409546 +[2025-04-27 12:51:14,157][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.2608299255371094, cross_entropy: 2.2608299255371094 +[2025-04-27 12:51:15,320][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 2.3477747440338135, cross_entropy: 2.3477747440338135 +[2025-04-27 12:51:16,496][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.052323341369629, cross_entropy: 1.052323341369629 +[2025-04-27 12:51:17,831][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.981640338897705, cross_entropy: 2.981640338897705 +[2025-04-27 12:51:19,273][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 3.1732444763183594, cross_entropy: 3.1732444763183594 +[2025-04-27 12:51:20,522][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 1.574944019317627, cross_entropy: 1.574944019317627 +[2025-04-27 12:51:21,723][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 2.981876850128174, cross_entropy: 2.981876850128174 +[2025-04-27 12:51:23,148][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 2.977081537246704, cross_entropy: 2.977081537246704 +[2025-04-27 12:51:24,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 2.045797348022461, cross_entropy: 2.045797348022461 +[2025-04-27 12:51:25,638][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.196437358856201, cross_entropy: 3.196437358856201 +[2025-04-27 12:51:27,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.875213861465454, cross_entropy: 2.875213861465454 +[2025-04-27 12:51:28,074][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.701866626739502, cross_entropy: 2.701866626739502 +[2025-04-27 12:51:30,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.02280592918396, cross_entropy: 1.02280592918396 +[2025-04-27 12:51:31,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.6345431804656982, cross_entropy: 1.6345431804656982 +[2025-04-27 12:51:32,958][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.579704761505127, cross_entropy: 2.579704761505127 +[2025-04-27 12:51:33,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 2.7433431148529053, cross_entropy: 2.7433431148529053 +[2025-04-27 12:51:35,748][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 2.4623193740844727, cross_entropy: 2.4623193740844727 +[2025-04-27 12:51:36,024][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 1.692084550857544, cross_entropy: 1.692084550857544 +[2025-04-27 12:51:37,974][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.41534423828125, cross_entropy: 2.41534423828125 +[2025-04-27 12:51:38,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.44324791431427, cross_entropy: 1.44324791431427 +[2025-04-27 12:51:41,046][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.1821608543395996, cross_entropy: 1.1821608543395996 +[2025-04-27 12:51:41,313][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 2.7398788928985596, cross_entropy: 2.7398788928985596 +[2025-04-27 12:51:44,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 0.9361953139305115, cross_entropy: 0.9361953139305115 +[2025-04-27 12:51:44,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.0165705680847168, cross_entropy: 1.0165705680847168 +[2025-04-27 12:51:47,876][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 0.8930995464324951, cross_entropy: 0.8930995464324951 +[2025-04-27 12:51:48,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 2.9079480171203613, cross_entropy: 2.9079480171203613 +[2025-04-27 12:51:50,910][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.2558670043945312, cross_entropy: 2.2558670043945312 +[2025-04-27 12:51:51,176][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.4354236125946045, cross_entropy: 1.4354236125946045 +[2025-04-27 12:51:53,850][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.404618263244629, cross_entropy: 2.404618263244629 +[2025-04-27 12:51:54,115][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.8905224800109863, cross_entropy: 2.8905224800109863 +[2025-04-27 12:51:56,713][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 2.8196256160736084, cross_entropy: 2.8196256160736084 +[2025-04-27 12:51:57,018][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 1.6667290925979614, cross_entropy: 1.6667290925979614 +[2025-04-27 12:51:59,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.9335460662841797, cross_entropy: 2.9335460662841797 +[2025-04-27 12:51:59,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 2.8374533653259277, cross_entropy: 2.8374533653259277 +[2025-04-27 12:51:59,733][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/iteration2000.pth. +[2025-04-27 12:52:02,200][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 0.7005205154418945, cross_entropy: 0.7005205154418945 +[2025-04-27 12:52:02,466][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.7261438369750977, cross_entropy: 2.7261438369750977 +[2025-04-27 12:52:04,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.2687859535217285, cross_entropy: 2.2687859535217285 +[2025-04-27 12:52:04,963][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 0.8679219484329224, cross_entropy: 0.8679219484329224 +[2025-04-27 12:52:08,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 2.7809925079345703, cross_entropy: 2.7809925079345703 +[2025-04-27 12:52:08,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.340513229370117, cross_entropy: 2.340513229370117 +[2025-04-27 12:52:11,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 3.353954315185547, cross_entropy: 3.353954315185547 +[2025-04-27 12:52:11,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.287825107574463, cross_entropy: 2.287825107574463 +[2025-04-27 12:52:13,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.917433500289917, cross_entropy: 1.917433500289917 +[2025-04-27 12:52:14,178][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.5721458196640015, cross_entropy: 1.5721458196640015 +[2025-04-27 12:52:17,550][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 2.9669461250305176, cross_entropy: 2.9669461250305176 +[2025-04-27 12:52:17,839][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.9123055934906006, cross_entropy: 1.9123055934906006 +[2025-04-27 12:52:20,325][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.108473777770996, cross_entropy: 1.108473777770996 +[2025-04-27 12:52:20,594][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 1.0216028690338135, cross_entropy: 1.0216028690338135 +[2025-04-27 12:52:22,981][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.123295783996582, cross_entropy: 1.123295783996582 +[2025-04-27 12:52:23,247][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.5165762901306152, cross_entropy: 2.5165762901306152 +[2025-04-27 12:52:26,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.160116195678711, cross_entropy: 1.160116195678711 +[2025-04-27 12:52:26,595][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.166471242904663, cross_entropy: 1.166471242904663 +[2025-04-27 12:52:28,355][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.1952013969421387, cross_entropy: 2.1952013969421387 +[2025-04-27 12:52:28,619][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.450702667236328, cross_entropy: 2.450702667236328 +[2025-04-27 12:52:31,533][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 2.279139995574951, cross_entropy: 2.279139995574951 +[2025-04-27 12:52:31,798][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.029697895050049, cross_entropy: 2.029697895050049 +[2025-04-27 12:52:34,287][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.9570196866989136, cross_entropy: 1.9570196866989136 +[2025-04-27 12:52:34,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 3.0742766857147217, cross_entropy: 3.0742766857147217 +[2025-04-27 12:52:36,774][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 0.8696107268333435, cross_entropy: 0.8696107268333435 +[2025-04-27 12:52:37,038][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 2.0980167388916016, cross_entropy: 2.0980167388916016 +[2025-04-27 12:52:39,167][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 0.708764374256134, cross_entropy: 0.708764374256134 +[2025-04-27 12:52:39,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.4064182043075562, cross_entropy: 1.4064182043075562 +[2025-04-27 12:52:41,541][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.551107168197632, cross_entropy: 2.551107168197632 +[2025-04-27 12:52:41,805][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.302079200744629, cross_entropy: 1.302079200744629 +[2025-04-27 12:52:44,381][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.4828081130981445, cross_entropy: 2.4828081130981445 +[2025-04-27 12:52:44,668][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 1.9744081497192383, cross_entropy: 1.9744081497192383 +[2025-04-27 12:52:47,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.1050310134887695, cross_entropy: 1.1050310134887695 +[2025-04-27 12:52:47,554][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.2486315965652466, cross_entropy: 1.2486315965652466 +[2025-04-27 12:52:49,999][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 1.8616141080856323, cross_entropy: 1.8616141080856323 +[2025-04-27 12:52:50,285][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 2.038269519805908, cross_entropy: 2.038269519805908 +[2025-04-27 12:52:52,502][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.3444039821624756, cross_entropy: 1.3444039821624756 +[2025-04-27 12:52:52,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.774545669555664, cross_entropy: 1.774545669555664 +[2025-04-27 12:52:55,029][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 3.1172008514404297, cross_entropy: 3.1172008514404297 +[2025-04-27 12:52:55,617][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 1.9893265962600708, cross_entropy: 1.9893265962600708 +[2025-04-27 12:52:57,464][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 0.9878190159797668, cross_entropy: 0.9878190159797668 +[2025-04-27 12:52:58,333][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.5921508073806763, cross_entropy: 1.5921508073806763 +[2025-04-27 12:52:59,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.858281135559082, cross_entropy: 2.858281135559082 +[2025-04-27 12:53:01,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 1.1793385744094849, cross_entropy: 1.1793385744094849 +[2025-04-27 12:53:02,235][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.535367965698242, cross_entropy: 2.535367965698242 +[2025-04-27 12:53:03,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 0.897977352142334, cross_entropy: 0.897977352142334 +[2025-04-27 12:53:05,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.2359631061553955, cross_entropy: 1.2359631061553955 +[2025-04-27 12:53:06,855][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.711336135864258, cross_entropy: 2.711336135864258 +[2025-04-27 12:53:07,876][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 0.797478437423706, cross_entropy: 0.797478437423706 +[2025-04-27 12:53:09,631][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 1.16068434715271, cross_entropy: 1.16068434715271 +[2025-04-27 12:53:10,618][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.1050453186035156, cross_entropy: 1.1050453186035156 +[2025-04-27 12:53:12,254][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.3776161670684814, cross_entropy: 2.3776161670684814 +[2025-04-27 12:53:14,510][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.3016135692596436, cross_entropy: 1.3016135692596436 +[2025-04-27 12:53:15,287][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.7115840911865234, cross_entropy: 1.7115840911865234 +[2025-04-27 12:53:17,134][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.6978912353515625, cross_entropy: 1.6978912353515625 +[2025-04-27 12:53:18,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.5516998767852783, cross_entropy: 2.5516998767852783 +[2025-04-27 12:53:20,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.2839317321777344, cross_entropy: 1.2839317321777344 +[2025-04-27 12:53:21,588][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 1.4948089122772217, cross_entropy: 1.4948089122772217 +[2025-04-27 12:53:22,513][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 2.881441116333008, cross_entropy: 2.881441116333008 +[2025-04-27 12:53:24,305][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 0.9183657169342041, cross_entropy: 0.9183657169342041 +[2025-04-27 12:53:25,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.3545949459075928, cross_entropy: 1.3545949459075928 +[2025-04-27 12:53:26,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.002943754196167, cross_entropy: 1.002943754196167 +[2025-04-27 12:53:28,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.193601369857788, cross_entropy: 2.193601369857788 +[2025-04-27 12:53:29,527][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 1.7048921585083008, cross_entropy: 1.7048921585083008 +[2025-04-27 12:53:30,827][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 1.9680590629577637, cross_entropy: 1.9680590629577637 +[2025-04-27 12:53:31,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 2.305189371109009, cross_entropy: 2.305189371109009 +[2025-04-27 12:53:33,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 2.944582462310791, cross_entropy: 2.944582462310791 +[2025-04-27 12:53:33,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 2.2472307682037354, cross_entropy: 2.2472307682037354 +[2025-04-27 12:53:35,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 1.283393144607544, cross_entropy: 1.283393144607544 +[2025-04-27 12:53:36,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.648282527923584, cross_entropy: 1.648282527923584 +[2025-04-27 12:53:39,304][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.2977014780044556, cross_entropy: 1.2977014780044556 +[2025-04-27 12:53:39,591][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.0584180355072021, cross_entropy: 1.0584180355072021 +[2025-04-27 12:53:41,931][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.804408311843872, cross_entropy: 2.804408311843872 +[2025-04-27 12:53:42,197][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.639469861984253, cross_entropy: 1.639469861984253 +[2025-04-27 12:53:44,875][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.1358730792999268, cross_entropy: 2.1358730792999268 +[2025-04-27 12:53:45,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 2.3372998237609863, cross_entropy: 2.3372998237609863 +[2025-04-27 12:53:46,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 0.9658507108688354, cross_entropy: 0.9658507108688354 +[2025-04-27 12:53:47,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.1803417205810547, cross_entropy: 2.1803417205810547 +[2025-04-27 12:53:49,535][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.1004359722137451, cross_entropy: 1.1004359722137451 +[2025-04-27 12:53:49,823][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 1.9400222301483154, cross_entropy: 1.9400222301483154 +[2025-04-27 12:53:52,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 1.1638801097869873, cross_entropy: 1.1638801097869873 +[2025-04-27 12:53:52,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 1.1703146696090698, cross_entropy: 1.1703146696090698 +[2025-04-27 12:53:55,186][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.0701265335083008, cross_entropy: 1.0701265335083008 +[2025-04-27 12:53:55,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 1.9699229001998901, cross_entropy: 1.9699229001998901 +[2025-04-27 12:53:57,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.1538219451904297, cross_entropy: 1.1538219451904297 +[2025-04-27 12:53:57,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 0.7821720838546753, cross_entropy: 0.7821720838546753 +[2025-04-27 12:54:00,296][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.1096704006195068, cross_entropy: 1.1096704006195068 +[2025-04-27 12:54:00,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.867979645729065, cross_entropy: 1.867979645729065 +[2025-04-27 12:54:03,005][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.003528356552124, cross_entropy: 1.003528356552124 +[2025-04-27 12:54:03,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 3.0159969329833984, cross_entropy: 3.0159969329833984 +[2025-04-27 12:54:05,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.610091209411621, cross_entropy: 2.610091209411621 +[2025-04-27 12:54:05,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.7578119039535522, cross_entropy: 1.7578119039535522 +[2025-04-27 12:54:08,034][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.3258483409881592, cross_entropy: 1.3258483409881592 +[2025-04-27 12:54:09,364][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 0.9489867687225342, cross_entropy: 0.9489867687225342 +[2025-04-27 12:54:10,715][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 0.6350099444389343, cross_entropy: 0.6350099444389343 +[2025-04-27 12:54:12,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.3167448043823242, cross_entropy: 1.3167448043823242 +[2025-04-27 12:54:14,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 1.6229100227355957, cross_entropy: 1.6229100227355957 +[2025-04-27 12:54:15,968][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 0.9149441719055176, cross_entropy: 0.9149441719055176 +[2025-04-27 12:54:16,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.1641758680343628, cross_entropy: 1.1641758680343628 +[2025-04-27 12:54:19,776][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.410033941268921, cross_entropy: 1.410033941268921 +[2025-04-27 12:54:20,053][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.1167289018630981, cross_entropy: 1.1167289018630981 +[2025-04-27 12:54:22,724][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 2.15248703956604, cross_entropy: 2.15248703956604 +[2025-04-27 12:54:23,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.1820054054260254, cross_entropy: 1.1820054054260254 +[2025-04-27 12:54:25,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.6895408630371094, cross_entropy: 2.6895408630371094 +[2025-04-27 12:54:25,940][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.2420594692230225, cross_entropy: 1.2420594692230225 +[2025-04-27 12:54:28,761][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.5505852699279785, cross_entropy: 2.5505852699279785 +[2025-04-27 12:54:29,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.1348249912261963, cross_entropy: 1.1348249912261963 +[2025-04-27 12:54:31,450][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 3.0487403869628906, cross_entropy: 3.0487403869628906 +[2025-04-27 12:54:31,744][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 2.7068123817443848, cross_entropy: 2.7068123817443848 +[2025-04-27 12:54:33,887][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.426579236984253, cross_entropy: 1.426579236984253 +[2025-04-27 12:54:34,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.1027183532714844, cross_entropy: 1.1027183532714844 +[2025-04-27 12:54:36,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.3975553512573242, cross_entropy: 1.3975553512573242 +[2025-04-27 12:54:37,281][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.912071943283081, cross_entropy: 1.912071943283081 +[2025-04-27 12:54:39,436][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 0.9203723669052124, cross_entropy: 0.9203723669052124 +[2025-04-27 12:54:39,724][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.9010484218597412, cross_entropy: 1.9010484218597412 +[2025-04-27 12:54:42,331][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 2.6863012313842773, cross_entropy: 2.6863012313842773 +[2025-04-27 12:54:42,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 3.018871784210205, cross_entropy: 3.018871784210205 +[2025-04-27 12:54:45,556][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 2.9781057834625244, cross_entropy: 2.9781057834625244 +[2025-04-27 12:54:45,848][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.2410459518432617, cross_entropy: 3.2410459518432617 +[2025-04-27 12:54:48,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.247913360595703, cross_entropy: 2.247913360595703 +[2025-04-27 12:54:48,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 2.8383493423461914, cross_entropy: 2.8383493423461914 +[2025-04-27 12:54:51,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 0.9559348821640015, cross_entropy: 0.9559348821640015 +[2025-04-27 12:54:51,316][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.8189468383789062, cross_entropy: 1.8189468383789062 +[2025-04-27 12:54:53,301][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 2.187350034713745, cross_entropy: 2.187350034713745 +[2025-04-27 12:54:53,590][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.246063470840454, cross_entropy: 1.246063470840454 +[2025-04-27 12:54:56,584][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.024837613105774, cross_entropy: 1.024837613105774 +[2025-04-27 12:54:56,849][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 0.9752071499824524, cross_entropy: 0.9752071499824524 +[2025-04-27 12:54:59,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 1.1995762586593628, cross_entropy: 1.1995762586593628 +[2025-04-27 12:54:59,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 3.4293041229248047, cross_entropy: 3.4293041229248047 +[2025-04-27 12:55:02,088][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 3.155219554901123, cross_entropy: 3.155219554901123 +[2025-04-27 12:55:02,376][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 1.3165665864944458, cross_entropy: 1.3165665864944458 +[2025-04-27 12:55:04,389][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.682997465133667, cross_entropy: 1.682997465133667 +[2025-04-27 12:55:04,654][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.0988619327545166, cross_entropy: 1.0988619327545166 +[2025-04-27 12:55:07,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 2.818324089050293, cross_entropy: 2.818324089050293 +[2025-04-27 12:55:07,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.310126304626465, cross_entropy: 2.310126304626465 +[2025-04-27 12:55:09,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 3.2535314559936523, cross_entropy: 3.2535314559936523 +[2025-04-27 12:57:15,352][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.8675049543380737, cross_entropy: 1.8675049543380737 +[2025-04-27 12:57:15,352][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.227215051651001, cross_entropy: 1.227215051651001 +[2025-04-27 12:57:15,563][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 12:57:15,741][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch6.pth. +[2025-04-27 12:57:15,971][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 12:57:19,719][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.319075107574463, cross_entropy: 2.319075107574463 +[2025-04-27 12:57:20,009][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.497281551361084, cross_entropy: 2.497281551361084 +[2025-04-27 12:57:22,290][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 1.2358840703964233, cross_entropy: 1.2358840703964233 +[2025-04-27 12:57:22,560][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 0.7669757008552551, cross_entropy: 0.7669757008552551 +[2025-04-27 12:57:24,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 0.8661073446273804, cross_entropy: 0.8661073446273804 +[2025-04-27 12:57:25,500][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.0059292316436768, cross_entropy: 1.0059292316436768 +[2025-04-27 12:57:27,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.7167844772338867, cross_entropy: 2.7167844772338867 +[2025-04-27 12:57:28,066][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.236236572265625, cross_entropy: 1.236236572265625 +[2025-04-27 12:57:30,122][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.3711671829223633, cross_entropy: 1.3711671829223633 +[2025-04-27 12:57:30,458][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.3660697937011719, cross_entropy: 1.3660697937011719 +[2025-04-27 12:57:33,318][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 2.627331256866455, cross_entropy: 2.627331256866455 +[2025-04-27 12:57:33,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.9857518672943115, cross_entropy: 1.9857518672943115 +[2025-04-27 12:57:35,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.7399280071258545, cross_entropy: 2.7399280071258545 +[2025-04-27 12:57:36,150][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 2.9203662872314453, cross_entropy: 2.9203662872314453 +[2025-04-27 12:57:38,403][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.568052291870117, cross_entropy: 2.568052291870117 +[2025-04-27 12:57:38,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.4122252464294434, cross_entropy: 2.4122252464294434 +[2025-04-27 12:57:40,950][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.026200771331787, cross_entropy: 2.026200771331787 +[2025-04-27 12:57:41,263][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.1739320755004883, cross_entropy: 3.1739320755004883 +[2025-04-27 12:57:43,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 3.0011372566223145, cross_entropy: 3.0011372566223145 +[2025-04-27 12:57:43,686][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 0.8438774347305298, cross_entropy: 0.8438774347305298 +[2025-04-27 12:57:45,587][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.0596506595611572, cross_entropy: 1.0596506595611572 +[2025-04-27 12:57:46,266][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.376737594604492, cross_entropy: 2.376737594604492 +[2025-04-27 12:57:49,005][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 1.8470189571380615, cross_entropy: 1.8470189571380615 +[2025-04-27 12:57:49,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.273111343383789, cross_entropy: 2.273111343383789 +[2025-04-27 12:57:51,985][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.861796498298645, cross_entropy: 1.861796498298645 +[2025-04-27 12:57:52,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.403904438018799, cross_entropy: 2.403904438018799 +[2025-04-27 12:57:54,480][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.5633115768432617, cross_entropy: 2.5633115768432617 +[2025-04-27 12:57:55,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 2.854201316833496, cross_entropy: 2.854201316833496 +[2025-04-27 12:57:56,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 0.9805613160133362, cross_entropy: 0.9805613160133362 +[2025-04-27 12:57:57,714][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.0509616136550903, cross_entropy: 1.0509616136550903 +[2025-04-27 12:57:59,982][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 1.822347640991211, cross_entropy: 1.822347640991211 +[2025-04-27 12:58:00,646][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.200887441635132, cross_entropy: 2.200887441635132 +[2025-04-27 12:58:02,488][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.4513440132141113, cross_entropy: 2.4513440132141113 +[2025-04-27 12:58:03,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.109163761138916, cross_entropy: 1.109163761138916 +[2025-04-27 12:58:05,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.5800063610076904, cross_entropy: 2.5800063610076904 +[2025-04-27 12:58:06,266][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.5068283081054688, cross_entropy: 1.5068283081054688 +[2025-04-27 12:58:09,353][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.9192137718200684, cross_entropy: 2.9192137718200684 +[2025-04-27 12:58:09,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.1592068672180176, cross_entropy: 1.1592068672180176 +[2025-04-27 12:58:11,943][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 0.668768048286438, cross_entropy: 0.668768048286438 +[2025-04-27 12:58:12,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.321656584739685, cross_entropy: 1.321656584739685 +[2025-04-27 12:58:14,300][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.0174415111541748, cross_entropy: 1.0174415111541748 +[2025-04-27 12:58:14,600][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 1.9192967414855957, cross_entropy: 1.9192967414855957 +[2025-04-27 12:58:16,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.418548107147217, cross_entropy: 2.418548107147217 +[2025-04-27 12:58:17,185][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 2.8718955516815186, cross_entropy: 2.8718955516815186 +[2025-04-27 12:58:19,498][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.262575626373291, cross_entropy: 2.262575626373291 +[2025-04-27 12:58:19,787][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.5643343925476074, cross_entropy: 1.5643343925476074 +[2025-04-27 12:58:21,958][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 0.6340632438659668, cross_entropy: 0.6340632438659668 +[2025-04-27 12:58:22,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 0.7226892113685608, cross_entropy: 0.7226892113685608 +[2025-04-27 12:58:24,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.5266261100769043, cross_entropy: 2.5266261100769043 +[2025-04-27 12:58:24,975][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.0388245582580566, cross_entropy: 1.0388245582580566 +[2025-04-27 12:58:27,152][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.711671829223633, cross_entropy: 2.711671829223633 +[2025-04-27 12:58:27,439][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 3.0614824295043945, cross_entropy: 3.0614824295043945 +[2025-04-27 12:58:30,471][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 2.2775917053222656, cross_entropy: 2.2775917053222656 +[2025-04-27 12:58:30,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.860029458999634, cross_entropy: 2.860029458999634 +[2025-04-27 12:58:33,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 1.977553367614746, cross_entropy: 1.977553367614746 +[2025-04-27 12:58:33,344][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.630066394805908, cross_entropy: 2.630066394805908 +[2025-04-27 12:58:35,792][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.4358079433441162, cross_entropy: 1.4358079433441162 +[2025-04-27 12:58:36,111][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.0630322694778442, cross_entropy: 1.0630322694778442 +[2025-04-27 12:58:40,008][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 2.835806369781494, cross_entropy: 2.835806369781494 +[2025-04-27 12:58:40,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 2.7147183418273926, cross_entropy: 2.7147183418273926 +[2025-04-27 12:58:42,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 1.5528148412704468, cross_entropy: 1.5528148412704468 +[2025-04-27 12:58:42,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.971168041229248, cross_entropy: 1.971168041229248 +[2025-04-27 12:58:45,088][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.4496550559997559, cross_entropy: 1.4496550559997559 +[2025-04-27 12:58:45,355][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 1.0116827487945557, cross_entropy: 1.0116827487945557 +[2025-04-27 12:58:47,460][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.163142442703247, cross_entropy: 2.163142442703247 +[2025-04-27 12:58:47,756][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.0534812211990356, cross_entropy: 1.0534812211990356 +[2025-04-27 12:58:50,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 0.9370604157447815, cross_entropy: 0.9370604157447815 +[2025-04-27 12:58:50,541][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.7164387702941895, cross_entropy: 2.7164387702941895 +[2025-04-27 12:58:53,082][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 0.8351777791976929, cross_entropy: 0.8351777791976929 +[2025-04-27 12:58:53,372][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 0.7380433082580566, cross_entropy: 0.7380433082580566 +[2025-04-27 12:58:56,360][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.829469919204712, cross_entropy: 2.829469919204712 +[2025-04-27 12:58:56,632][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 0.9325892925262451, cross_entropy: 0.9325892925262451 +[2025-04-27 12:58:58,875][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 2.0624747276306152, cross_entropy: 2.0624747276306152 +[2025-04-27 12:58:59,140][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 2.635953903198242, cross_entropy: 2.635953903198242 +[2025-04-27 12:59:01,087][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 1.0323541164398193, cross_entropy: 1.0323541164398193 +[2025-04-27 12:59:01,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.5853517055511475, cross_entropy: 1.5853517055511475 +[2025-04-27 12:59:03,430][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.1098551750183105, cross_entropy: 2.1098551750183105 +[2025-04-27 12:59:03,724][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 2.3987960815429688, cross_entropy: 2.3987960815429688 +[2025-04-27 12:59:06,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.333047389984131, cross_entropy: 2.333047389984131 +[2025-04-27 12:59:06,370][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 1.7244610786437988, cross_entropy: 1.7244610786437988 +[2025-04-27 12:59:08,430][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 0.9607930779457092, cross_entropy: 0.9607930779457092 +[2025-04-27 12:59:08,720][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 1.7191746234893799, cross_entropy: 1.7191746234893799 +[2025-04-27 12:59:11,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.5299062728881836, cross_entropy: 2.5299062728881836 +[2025-04-27 12:59:11,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 2.7283551692962646, cross_entropy: 2.7283551692962646 +[2025-04-27 12:59:14,273][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 0.8793688416481018, cross_entropy: 0.8793688416481018 +[2025-04-27 12:59:14,563][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 2.0697851181030273, cross_entropy: 2.0697851181030273 +[2025-04-27 12:59:16,660][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 0.8408426642417908, cross_entropy: 0.8408426642417908 +[2025-04-27 12:59:16,953][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 1.217297077178955, cross_entropy: 1.217297077178955 +[2025-04-27 12:59:18,893][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 2.72482967376709, cross_entropy: 2.72482967376709 +[2025-04-27 12:59:19,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 0.7713598608970642, cross_entropy: 0.7713598608970642 +[2025-04-27 12:59:22,053][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 2.83705735206604, cross_entropy: 2.83705735206604 +[2025-04-27 12:59:22,379][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 0.7577285766601562, cross_entropy: 0.7577285766601562 +[2025-04-27 12:59:24,737][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.1019437313079834, cross_entropy: 1.1019437313079834 +[2025-04-27 12:59:25,073][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.0859421491622925, cross_entropy: 1.0859421491622925 +[2025-04-27 12:59:27,194][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.7858638763427734, cross_entropy: 2.7858638763427734 +[2025-04-27 12:59:27,529][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.4231092929840088, cross_entropy: 1.4231092929840088 +[2025-04-27 12:59:29,509][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.0162572860717773, cross_entropy: 1.0162572860717773 +[2025-04-27 12:59:30,228][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 1.2886278629302979, cross_entropy: 1.2886278629302979 +[2025-04-27 12:59:32,737][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.6839509010314941, cross_entropy: 1.6839509010314941 +[2025-04-27 12:59:33,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.679864525794983, cross_entropy: 1.679864525794983 +[2025-04-27 12:59:35,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 1.093154788017273, cross_entropy: 1.093154788017273 +[2025-04-27 12:59:36,171][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 0.8048779964447021, cross_entropy: 0.8048779964447021 +[2025-04-27 12:59:39,087][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 1.949906826019287, cross_entropy: 1.949906826019287 +[2025-04-27 12:59:39,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.2330530881881714, cross_entropy: 1.2330530881881714 +[2025-04-27 12:59:42,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.084909200668335, cross_entropy: 1.084909200668335 +[2025-04-27 12:59:42,541][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.2089624404907227, cross_entropy: 1.2089624404907227 +[2025-04-27 12:59:44,828][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.9665008783340454, cross_entropy: 1.9665008783340454 +[2025-04-27 12:59:45,119][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.4356753826141357, cross_entropy: 1.4356753826141357 +[2025-04-27 12:59:47,850][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 0.9339319467544556, cross_entropy: 0.9339319467544556 +[2025-04-27 12:59:48,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 0.9024097919464111, cross_entropy: 0.9024097919464111 +[2025-04-27 12:59:50,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 0.67616868019104, cross_entropy: 0.67616868019104 +[2025-04-27 12:59:50,609][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 0.9563065767288208, cross_entropy: 0.9563065767288208 +[2025-04-27 12:59:52,578][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.2971477508544922, cross_entropy: 1.2971477508544922 +[2025-04-27 12:59:52,857][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 0.6874604225158691, cross_entropy: 0.6874604225158691 +[2025-04-27 12:59:55,325][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.1047049760818481, cross_entropy: 1.1047049760818481 +[2025-04-27 12:59:55,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 0.7163808345794678, cross_entropy: 0.7163808345794678 +[2025-04-27 12:59:58,124][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 0.8536974191665649, cross_entropy: 0.8536974191665649 +[2025-04-27 12:59:58,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.5805838108062744, cross_entropy: 2.5805838108062744 +[2025-04-27 13:00:01,392][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.212493896484375, cross_entropy: 2.212493896484375 +[2025-04-27 13:00:01,683][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 1.1491388082504272, cross_entropy: 1.1491388082504272 +[2025-04-27 13:00:03,570][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.1442198753356934, cross_entropy: 1.1442198753356934 +[2025-04-27 13:00:03,860][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 1.250859260559082, cross_entropy: 1.250859260559082 +[2025-04-27 13:00:07,045][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.0652387142181396, cross_entropy: 2.0652387142181396 +[2025-04-27 13:00:07,309][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 2.353893280029297, cross_entropy: 2.353893280029297 +[2025-04-27 13:00:10,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 0.8043786287307739, cross_entropy: 0.8043786287307739 +[2025-04-27 13:00:10,518][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.035348653793335, cross_entropy: 1.035348653793335 +[2025-04-27 13:00:14,542][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.1363415718078613, cross_entropy: 3.1363415718078613 +[2025-04-27 13:00:14,824][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 0.968445897102356, cross_entropy: 0.968445897102356 +[2025-04-27 13:00:16,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 0.8500373363494873, cross_entropy: 0.8500373363494873 +[2025-04-27 13:00:17,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 0.8354477882385254, cross_entropy: 0.8354477882385254 +[2025-04-27 13:00:19,803][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 0.8681453466415405, cross_entropy: 0.8681453466415405 +[2025-04-27 13:00:20,069][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.036520004272461, cross_entropy: 2.036520004272461 +[2025-04-27 13:00:22,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 2.723707675933838, cross_entropy: 2.723707675933838 +[2025-04-27 13:00:22,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.6103556156158447, cross_entropy: 1.6103556156158447 +[2025-04-27 13:00:25,005][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 3.2953171730041504, cross_entropy: 3.2953171730041504 +[2025-04-27 13:00:25,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.4154443740844727, cross_entropy: 2.4154443740844727 +[2025-04-27 13:00:27,926][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 2.929335117340088, cross_entropy: 2.929335117340088 +[2025-04-27 13:00:28,194][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.2706891298294067, cross_entropy: 1.2706891298294067 +[2025-04-27 13:00:30,727][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.1498886346817017, cross_entropy: 1.1498886346817017 +[2025-04-27 13:00:31,016][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.31913423538208, cross_entropy: 2.31913423538208 +[2025-04-27 13:00:33,461][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 0.9104582071304321, cross_entropy: 0.9104582071304321 +[2025-04-27 13:00:33,748][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.314845085144043, cross_entropy: 1.314845085144043 +[2025-04-27 13:00:35,696][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 2.672635316848755, cross_entropy: 2.672635316848755 +[2025-04-27 13:00:35,987][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 0.7949981093406677, cross_entropy: 0.7949981093406677 +[2025-04-27 13:00:38,767][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.087433099746704, cross_entropy: 1.087433099746704 +[2025-04-27 13:00:39,054][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.2047650814056396, cross_entropy: 1.2047650814056396 +[2025-04-27 13:00:41,163][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 2.5071496963500977, cross_entropy: 2.5071496963500977 +[2025-04-27 13:00:41,455][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 0.757421612739563, cross_entropy: 0.757421612739563 +[2025-04-27 13:00:43,936][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.607985258102417, cross_entropy: 2.607985258102417 +[2025-04-27 13:00:44,224][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 0.9705498218536377, cross_entropy: 0.9705498218536377 +[2025-04-27 13:00:46,830][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.1084489822387695, cross_entropy: 2.1084489822387695 +[2025-04-27 13:00:47,119][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 2.7776153087615967, cross_entropy: 2.7776153087615967 +[2025-04-27 13:00:49,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 1.974826455116272, cross_entropy: 1.974826455116272 +[2025-04-27 13:00:49,761][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 2.2822608947753906, cross_entropy: 2.2822608947753906 +[2025-04-27 13:00:51,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 1.854140043258667, cross_entropy: 1.854140043258667 +[2025-04-27 13:00:52,252][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 0.8059628009796143, cross_entropy: 0.8059628009796143 +[2025-04-27 13:00:54,555][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.9308706521987915, cross_entropy: 1.9308706521987915 +[2025-04-27 13:00:54,837][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 2.8678810596466064, cross_entropy: 2.8678810596466064 +[2025-04-27 13:00:57,458][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.3048067092895508, cross_entropy: 1.3048067092895508 +[2025-04-27 13:00:57,732][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 1.1110657453536987, cross_entropy: 1.1110657453536987 +[2025-04-27 13:00:59,831][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 2.9337778091430664, cross_entropy: 2.9337778091430664 +[2025-04-27 13:01:00,123][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.3060829639434814, cross_entropy: 1.3060829639434814 +[2025-04-27 13:01:02,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.0377023220062256, cross_entropy: 1.0377023220062256 +[2025-04-27 13:01:02,485][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 2.15928316116333, cross_entropy: 2.15928316116333 +[2025-04-27 13:01:04,436][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 0.846704363822937, cross_entropy: 0.846704363822937 +[2025-04-27 13:01:04,703][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.0391924381256104, cross_entropy: 1.0391924381256104 +[2025-04-27 13:01:06,693][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 2.7347707748413086, cross_entropy: 2.7347707748413086 +[2025-04-27 13:01:06,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 2.740443229675293, cross_entropy: 2.740443229675293 +[2025-04-27 13:01:09,850][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.1513041257858276, cross_entropy: 1.1513041257858276 +[2025-04-27 13:01:10,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 3.2447800636291504, cross_entropy: 3.2447800636291504 +[2025-04-27 13:01:12,395][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.5841405391693115, cross_entropy: 1.5841405391693115 +[2025-04-27 13:01:12,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 2.5912322998046875, cross_entropy: 2.5912322998046875 +[2025-04-27 13:01:14,662][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 2.7527308464050293, cross_entropy: 2.7527308464050293 +[2025-04-27 13:01:14,961][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 2.0167245864868164, cross_entropy: 2.0167245864868164 +[2025-04-27 13:01:17,494][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 3.2388367652893066, cross_entropy: 3.2388367652893066 +[2025-04-27 13:01:17,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.863405466079712, cross_entropy: 1.863405466079712 +[2025-04-27 13:01:20,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 2.8458614349365234, cross_entropy: 2.8458614349365234 +[2025-04-27 13:01:20,536][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.8414736986160278, cross_entropy: 1.8414736986160278 +[2025-04-27 13:01:23,157][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 2.8743295669555664, cross_entropy: 2.8743295669555664 +[2025-04-27 13:01:23,445][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.5184272527694702, cross_entropy: 1.5184272527694702 +[2025-04-27 13:01:25,771][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 1.3365633487701416, cross_entropy: 1.3365633487701416 +[2025-04-27 13:01:26,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 1.9993610382080078, cross_entropy: 1.9993610382080078 +[2025-04-27 13:01:28,714][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 2.281256675720215, cross_entropy: 2.281256675720215 +[2025-04-27 13:01:28,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 1.5159497261047363, cross_entropy: 1.5159497261047363 +[2025-04-27 13:01:31,471][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.105130672454834, cross_entropy: 1.105130672454834 +[2025-04-27 13:01:31,736][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.4712934494018555, cross_entropy: 2.4712934494018555 +[2025-04-27 13:01:34,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 2.5833382606506348, cross_entropy: 2.5833382606506348 +[2025-04-27 13:01:34,944][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 3.1305596828460693, cross_entropy: 3.1305596828460693 +[2025-04-27 13:01:38,151][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.179071307182312, cross_entropy: 1.179071307182312 +[2025-04-27 13:01:38,436][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 1.9333198070526123, cross_entropy: 1.9333198070526123 +[2025-04-27 13:01:40,669][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 1.6490755081176758, cross_entropy: 1.6490755081176758 +[2025-04-27 13:01:40,956][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.7289185523986816, cross_entropy: 1.7289185523986816 +[2025-04-27 13:01:43,414][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 2.9971771240234375, cross_entropy: 2.9971771240234375 +[2025-04-27 13:01:43,699][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.5989856719970703, cross_entropy: 2.5989856719970703 +[2025-04-27 13:01:45,909][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.8985493183135986, cross_entropy: 1.8985493183135986 +[2025-04-27 13:01:46,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.3242143392562866, cross_entropy: 1.3242143392562866 +[2025-04-27 13:01:49,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 2.8779544830322266, cross_entropy: 2.8779544830322266 +[2025-04-27 13:01:49,720][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 0.9828271865844727, cross_entropy: 0.9828271865844727 +[2025-04-27 13:01:52,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.069410800933838, cross_entropy: 3.069410800933838 +[2025-04-27 13:01:52,346][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.4649715423583984, cross_entropy: 1.4649715423583984 +[2025-04-27 13:01:54,362][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.905777931213379, cross_entropy: 2.905777931213379 +[2025-04-27 13:01:54,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.5788872241973877, cross_entropy: 2.5788872241973877 +[2025-04-27 13:01:56,974][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 0.8878679275512695, cross_entropy: 0.8878679275512695 +[2025-04-27 13:01:57,241][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.038454532623291, cross_entropy: 2.038454532623291 +[2025-04-27 13:02:00,939][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.0796775817871094, cross_entropy: 3.0796775817871094 +[2025-04-27 13:02:01,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 2.7164812088012695, cross_entropy: 2.7164812088012695 +[2025-04-27 13:02:03,241][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 0.8721082210540771, cross_entropy: 0.8721082210540771 +[2025-04-27 13:02:03,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.3468254804611206, cross_entropy: 1.3468254804611206 +[2025-04-27 13:02:05,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 0.5212776064872742, cross_entropy: 0.5212776064872742 +[2025-04-27 13:02:06,121][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 2.9467456340789795, cross_entropy: 2.9467456340789795 +[2025-04-27 13:02:08,700][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 3.093315362930298, cross_entropy: 3.093315362930298 +[2025-04-27 13:02:08,985][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.61257004737854, cross_entropy: 1.61257004737854 +[2025-04-27 13:02:11,596][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 2.6221890449523926, cross_entropy: 2.6221890449523926 +[2025-04-27 13:02:11,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.458143949508667, cross_entropy: 1.458143949508667 +[2025-04-27 13:02:14,251][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.028786301612854, cross_entropy: 1.028786301612854 +[2025-04-27 13:02:14,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 3.181840658187866, cross_entropy: 3.181840658187866 +[2025-04-27 13:02:17,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.94289493560791, cross_entropy: 2.94289493560791 +[2025-04-27 13:02:17,354][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 0.7709404230117798, cross_entropy: 0.7709404230117798 +[2025-04-27 13:02:20,091][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.1251251697540283, cross_entropy: 1.1251251697540283 +[2025-04-27 13:02:20,376][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.629894733428955, cross_entropy: 2.629894733428955 +[2025-04-27 13:02:23,290][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 2.6637446880340576, cross_entropy: 2.6637446880340576 +[2025-04-27 13:02:23,554][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 0.7471956610679626, cross_entropy: 0.7471956610679626 +[2025-04-27 13:02:25,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.7506818771362305, cross_entropy: 2.7506818771362305 +[2025-04-27 13:02:25,554][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 3.033169746398926, cross_entropy: 3.033169746398926 +[2025-04-27 13:02:27,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.5615239143371582, cross_entropy: 1.5615239143371582 +[2025-04-27 13:02:28,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 2.804536819458008, cross_entropy: 2.804536819458008 +[2025-04-27 13:02:30,028][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 1.131072998046875, cross_entropy: 1.131072998046875 +[2025-04-27 13:02:30,300][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.6565933227539062, cross_entropy: 1.6565933227539062 +[2025-04-27 13:02:32,184][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.4295141696929932, cross_entropy: 1.4295141696929932 +[2025-04-27 13:02:32,473][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 2.6761794090270996, cross_entropy: 2.6761794090270996 +[2025-04-27 13:02:34,401][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.7695350646972656, cross_entropy: 2.7695350646972656 +[2025-04-27 13:02:35,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 0.8960592746734619, cross_entropy: 0.8960592746734619 +[2025-04-27 13:02:37,306][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 1.73330819606781, cross_entropy: 1.73330819606781 +[2025-04-27 13:02:37,593][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.179966926574707, cross_entropy: 2.179966926574707 +[2025-04-27 13:02:39,853][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.8914525508880615, cross_entropy: 1.8914525508880615 +[2025-04-27 13:02:40,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 1.0813099145889282, cross_entropy: 1.0813099145889282 +[2025-04-27 13:02:42,820][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 1.432600736618042, cross_entropy: 1.432600736618042 +[2025-04-27 13:02:43,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 3.1583261489868164, cross_entropy: 3.1583261489868164 +[2025-04-27 13:02:46,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 0.8853623867034912, cross_entropy: 0.8853623867034912 +[2025-04-27 13:02:46,395][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.3670387268066406, cross_entropy: 2.3670387268066406 +[2025-04-27 13:02:49,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 1.797349452972412, cross_entropy: 1.797349452972412 +[2025-04-27 13:02:49,383][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 0.7874158620834351, cross_entropy: 0.7874158620834351 +[2025-04-27 13:02:51,939][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.5858546495437622, cross_entropy: 1.5858546495437622 +[2025-04-27 13:02:52,240][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 2.6057331562042236, cross_entropy: 2.6057331562042236 +[2025-04-27 13:02:55,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 2.7066378593444824, cross_entropy: 2.7066378593444824 +[2025-04-27 13:02:55,801][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 1.9541782140731812, cross_entropy: 1.9541782140731812 +[2025-04-27 13:02:57,964][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 0.8034395575523376, cross_entropy: 0.8034395575523376 +[2025-04-27 13:02:58,251][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 2.1888861656188965, cross_entropy: 2.1888861656188965 +[2025-04-27 13:03:01,182][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 0.7459562420845032, cross_entropy: 0.7459562420845032 +[2025-04-27 13:03:01,448][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 0.8011429309844971, cross_entropy: 0.8011429309844971 +[2025-04-27 13:03:04,036][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.1288933753967285, cross_entropy: 1.1288933753967285 +[2025-04-27 13:03:04,299][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 1.3974242210388184, cross_entropy: 1.3974242210388184 +[2025-04-27 13:03:06,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 0.98915696144104, cross_entropy: 0.98915696144104 +[2025-04-27 13:03:06,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.1940233707427979, cross_entropy: 1.1940233707427979 +[2025-04-27 13:03:08,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 2.899736166000366, cross_entropy: 2.899736166000366 +[2025-04-27 13:03:09,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 0.8647496104240417, cross_entropy: 0.8647496104240417 +[2025-04-27 13:03:11,405][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.746005058288574, cross_entropy: 2.746005058288574 +[2025-04-27 13:03:11,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 1.6564861536026, cross_entropy: 1.6564861536026 +[2025-04-27 13:03:13,857][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.947678804397583, cross_entropy: 1.947678804397583 +[2025-04-27 13:03:14,148][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.9405627250671387, cross_entropy: 2.9405627250671387 +[2025-04-27 13:03:16,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 1.7958317995071411, cross_entropy: 1.7958317995071411 +[2025-04-27 13:03:16,786][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 2.9790894985198975, cross_entropy: 2.9790894985198975 +[2025-04-27 13:03:19,362][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.138106346130371, cross_entropy: 1.138106346130371 +[2025-04-27 13:03:19,651][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.703458309173584, cross_entropy: 1.703458309173584 +[2025-04-27 13:03:21,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.8237109184265137, cross_entropy: 2.8237109184265137 +[2025-04-27 13:03:22,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.4666848182678223, cross_entropy: 1.4666848182678223 +[2025-04-27 13:03:24,669][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.2722561359405518, cross_entropy: 3.2722561359405518 +[2025-04-27 13:03:24,941][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.0527431964874268, cross_entropy: 2.0527431964874268 +[2025-04-27 13:03:27,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 0.7053090333938599, cross_entropy: 0.7053090333938599 +[2025-04-27 13:03:27,767][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 0.8304293155670166, cross_entropy: 0.8304293155670166 +[2025-04-27 13:03:30,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 1.0311768054962158, cross_entropy: 1.0311768054962158 +[2025-04-27 13:03:30,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 0.7559895515441895, cross_entropy: 0.7559895515441895 +[2025-04-27 13:03:33,609][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.1814370155334473, cross_entropy: 2.1814370155334473 +[2025-04-27 13:03:33,898][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 0.6461584568023682, cross_entropy: 0.6461584568023682 +[2025-04-27 13:03:35,955][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.6407833099365234, cross_entropy: 2.6407833099365234 +[2025-04-27 13:03:36,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 1.6116411685943604, cross_entropy: 1.6116411685943604 +[2025-04-27 13:03:38,337][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.4452664852142334, cross_entropy: 1.4452664852142334 +[2025-04-27 13:03:38,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 0.8742589950561523, cross_entropy: 0.8742589950561523 +[2025-04-27 13:03:41,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 0.8688310384750366, cross_entropy: 0.8688310384750366 +[2025-04-27 13:03:41,937][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.7030117511749268, cross_entropy: 1.7030117511749268 +[2025-04-27 13:03:44,451][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.230243444442749, cross_entropy: 1.230243444442749 +[2025-04-27 13:03:44,717][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 0.9116564393043518, cross_entropy: 0.9116564393043518 +[2025-04-27 13:03:46,906][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.717393636703491, cross_entropy: 2.717393636703491 +[2025-04-27 13:03:47,201][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.2532556056976318, cross_entropy: 1.2532556056976318 +[2025-04-27 13:03:49,707][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 1.9522666931152344, cross_entropy: 1.9522666931152344 +[2025-04-27 13:03:49,994][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 1.1014059782028198, cross_entropy: 1.1014059782028198 +[2025-04-27 13:03:51,901][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.9615037441253662, cross_entropy: 1.9615037441253662 +[2025-04-27 13:03:52,191][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 3.0156197547912598, cross_entropy: 3.0156197547912598 +[2025-04-27 13:03:54,831][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 0.9284246563911438, cross_entropy: 0.9284246563911438 +[2025-04-27 13:03:55,119][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 0.9621241688728333, cross_entropy: 0.9621241688728333 +[2025-04-27 13:03:59,279][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 2.0714643001556396, cross_entropy: 2.0714643001556396 +[2025-04-27 13:03:59,570][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 2.3231048583984375, cross_entropy: 2.3231048583984375 +[2025-04-27 13:04:02,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 3.0958685874938965, cross_entropy: 3.0958685874938965 +[2025-04-27 13:04:02,720][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 2.843181610107422, cross_entropy: 2.843181610107422 +[2025-04-27 13:04:04,890][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 2.698063373565674, cross_entropy: 2.698063373565674 +[2025-04-27 13:04:05,157][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 2.728813648223877, cross_entropy: 2.728813648223877 +[2025-04-27 13:04:07,746][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.2524845600128174, cross_entropy: 2.2524845600128174 +[2025-04-27 13:04:08,033][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 2.0687177181243896, cross_entropy: 2.0687177181243896 +[2025-04-27 13:04:10,147][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.9481124877929688, cross_entropy: 2.9481124877929688 +[2025-04-27 13:04:10,411][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 0.8589938879013062, cross_entropy: 0.8589938879013062 +[2025-04-27 13:04:12,857][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.841386318206787, cross_entropy: 2.841386318206787 +[2025-04-27 13:04:13,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 2.3058340549468994, cross_entropy: 2.3058340549468994 +[2025-04-27 13:04:15,967][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.1277815103530884, cross_entropy: 1.1277815103530884 +[2025-04-27 13:04:16,256][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.4316035509109497, cross_entropy: 1.4316035509109497 +[2025-04-27 13:04:18,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.4656167030334473, cross_entropy: 1.4656167030334473 +[2025-04-27 13:04:18,661][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 0.9509751796722412, cross_entropy: 0.9509751796722412 +[2025-04-27 13:04:20,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.2502212524414062, cross_entropy: 1.2502212524414062 +[2025-04-27 13:04:21,046][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.1371822357177734, cross_entropy: 2.1371822357177734 +[2025-04-27 13:04:24,378][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 2.940819501876831, cross_entropy: 2.940819501876831 +[2025-04-27 13:04:24,644][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.9874095916748047, cross_entropy: 2.9874095916748047 +[2025-04-27 13:04:26,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.3207110166549683, cross_entropy: 1.3207110166549683 +[2025-04-27 13:04:26,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.1490994691848755, cross_entropy: 1.1490994691848755 +[2025-04-27 13:04:29,353][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.2512558698654175, cross_entropy: 1.2512558698654175 +[2025-04-27 13:04:29,619][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.281646490097046, cross_entropy: 1.281646490097046 +[2025-04-27 13:04:31,771][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.1996140480041504, cross_entropy: 1.1996140480041504 +[2025-04-27 13:04:32,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.7183716297149658, cross_entropy: 1.7183716297149658 +[2025-04-27 13:04:34,143][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.2233562469482422, cross_entropy: 1.2233562469482422 +[2025-04-27 13:04:34,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 2.7527689933776855, cross_entropy: 2.7527689933776855 +[2025-04-27 13:04:37,710][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 3.132990837097168, cross_entropy: 3.132990837097168 +[2025-04-27 13:04:37,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.5612032413482666, cross_entropy: 2.5612032413482666 +[2025-04-27 13:04:39,733][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 1.4895997047424316, cross_entropy: 1.4895997047424316 +[2025-04-27 13:04:40,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 0.8305448293685913, cross_entropy: 0.8305448293685913 +[2025-04-27 13:04:42,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.1922602653503418, cross_entropy: 1.1922602653503418 +[2025-04-27 13:04:42,847][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.3516921997070312, cross_entropy: 2.3516921997070312 +[2025-04-27 13:04:45,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 2.895878314971924, cross_entropy: 2.895878314971924 +[2025-04-27 13:04:45,323][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 0.7253991365432739, cross_entropy: 0.7253991365432739 +[2025-04-27 13:04:47,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.096095323562622, cross_entropy: 1.096095323562622 +[2025-04-27 13:04:48,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 3.050776958465576, cross_entropy: 3.050776958465576 +[2025-04-27 13:04:50,202][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.1286327838897705, cross_entropy: 1.1286327838897705 +[2025-04-27 13:04:50,491][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 2.34433650970459, cross_entropy: 2.34433650970459 +[2025-04-27 13:04:52,929][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 0.7431930303573608, cross_entropy: 0.7431930303573608 +[2025-04-27 13:04:53,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.3007323741912842, cross_entropy: 1.3007323741912842 +[2025-04-27 13:04:55,138][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.621894359588623, cross_entropy: 2.621894359588623 +[2025-04-27 13:04:55,415][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.2743091583251953, cross_entropy: 1.2743091583251953 +[2025-04-27 13:04:58,121][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 0.6656575798988342, cross_entropy: 0.6656575798988342 +[2025-04-27 13:04:58,387][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 2.6953659057617188, cross_entropy: 2.6953659057617188 +[2025-04-27 13:05:01,426][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.1131768226623535, cross_entropy: 1.1131768226623535 +[2025-04-27 13:05:01,716][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.4740896224975586, cross_entropy: 1.4740896224975586 +[2025-04-27 13:05:04,068][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.7664101123809814, cross_entropy: 2.7664101123809814 +[2025-04-27 13:05:04,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.0937376022338867, cross_entropy: 2.0937376022338867 +[2025-04-27 13:05:06,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 0.8420397043228149, cross_entropy: 0.8420397043228149 +[2025-04-27 13:05:06,627][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.2478110790252686, cross_entropy: 1.2478110790252686 +[2025-04-27 13:05:08,475][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 0.9938397407531738, cross_entropy: 0.9938397407531738 +[2025-04-27 13:05:08,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.7685953378677368, cross_entropy: 0.7685953378677368 +[2025-04-27 13:05:11,194][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.6268043518066406, cross_entropy: 1.6268043518066406 +[2025-04-27 13:05:11,481][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.6789283752441406, cross_entropy: 1.6789283752441406 +[2025-04-27 13:05:13,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 0.7593778967857361, cross_entropy: 0.7593778967857361 +[2025-04-27 13:05:14,184][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 1.9623959064483643, cross_entropy: 1.9623959064483643 +[2025-04-27 13:05:16,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.0633013248443604, cross_entropy: 1.0633013248443604 +[2025-04-27 13:05:16,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.4581414461135864, cross_entropy: 1.4581414461135864 +[2025-04-27 13:05:18,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 2.1508474349975586, cross_entropy: 2.1508474349975586 +[2025-04-27 13:05:19,062][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.722517490386963, cross_entropy: 1.722517490386963 +[2025-04-27 13:05:21,869][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.5868548154830933, cross_entropy: 1.5868548154830933 +[2025-04-27 13:05:22,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 3.0527138710021973, cross_entropy: 3.0527138710021973 +[2025-04-27 13:05:24,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.1752986907958984, cross_entropy: 1.1752986907958984 +[2025-04-27 13:05:24,835][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.0651803016662598, cross_entropy: 2.0651803016662598 +[2025-04-27 13:07:30,745][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.7979017496109009, cross_entropy: 1.7979017496109009 +[2025-04-27 13:07:30,745][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.1959129571914673, cross_entropy: 1.1959129571914673 +[2025-04-27 13:07:30,957][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 13:07:31,119][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch7.pth. +[2025-04-27 13:07:31,326][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 13:07:35,054][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.1737229824066162, cross_entropy: 1.1737229824066162 +[2025-04-27 13:07:35,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 1.9054877758026123, cross_entropy: 1.9054877758026123 +[2025-04-27 13:07:38,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 0.950044572353363, cross_entropy: 0.950044572353363 +[2025-04-27 13:07:38,612][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 3.102402687072754, cross_entropy: 3.102402687072754 +[2025-04-27 13:07:41,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 2.505699634552002, cross_entropy: 2.505699634552002 +[2025-04-27 13:07:41,837][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.341325044631958, cross_entropy: 1.341325044631958 +[2025-04-27 13:07:44,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.8428491950035095, cross_entropy: 0.8428491950035095 +[2025-04-27 13:07:44,523][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.6657440662384033, cross_entropy: 2.6657440662384033 +[2025-04-27 13:07:46,616][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 0.6285760998725891, cross_entropy: 0.6285760998725891 +[2025-04-27 13:07:46,882][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.5362485647201538, cross_entropy: 1.5362485647201538 +[2025-04-27 13:07:49,656][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 2.70255708694458, cross_entropy: 2.70255708694458 +[2025-04-27 13:07:49,944][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.6610719561576843, cross_entropy: 0.6610719561576843 +[2025-04-27 13:07:52,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 0.8761113882064819, cross_entropy: 0.8761113882064819 +[2025-04-27 13:07:52,839][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.4141416549682617, cross_entropy: 2.4141416549682617 +[2025-04-27 13:07:55,011][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 0.6163991689682007, cross_entropy: 0.6163991689682007 +[2025-04-27 13:07:55,303][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 0.4787496030330658, cross_entropy: 0.4787496030330658 +[2025-04-27 13:07:57,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 1.8909108638763428, cross_entropy: 1.8909108638763428 +[2025-04-27 13:07:57,833][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.184617280960083, cross_entropy: 2.184617280960083 +[2025-04-27 13:08:00,269][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 2.7930996417999268, cross_entropy: 2.7930996417999268 +[2025-04-27 13:08:00,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 0.5916718244552612, cross_entropy: 0.5916718244552612 +[2025-04-27 13:08:02,834][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.6411818265914917, cross_entropy: 1.6411818265914917 +[2025-04-27 13:08:03,130][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 2.6783111095428467, cross_entropy: 2.6783111095428467 +[2025-04-27 13:08:05,587][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.2455377578735352, cross_entropy: 1.2455377578735352 +[2025-04-27 13:08:05,862][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.43938148021698, cross_entropy: 1.43938148021698 +[2025-04-27 13:08:07,902][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 2.8583898544311523, cross_entropy: 2.8583898544311523 +[2025-04-27 13:08:08,428][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 2.0969762802124023, cross_entropy: 2.0969762802124023 +[2025-04-27 13:08:10,889][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.8413960933685303, cross_entropy: 0.8413960933685303 +[2025-04-27 13:08:11,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.015275478363037, cross_entropy: 3.015275478363037 +[2025-04-27 13:08:13,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.2015665769577026, cross_entropy: 1.2015665769577026 +[2025-04-27 13:08:14,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.2909060716629028, cross_entropy: 1.2909060716629028 +[2025-04-27 13:08:16,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.8815191388130188, cross_entropy: 0.8815191388130188 +[2025-04-27 13:08:17,212][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.1155521869659424, cross_entropy: 2.1155521869659424 +[2025-04-27 13:08:19,757][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 0.9028319120407104, cross_entropy: 0.9028319120407104 +[2025-04-27 13:08:20,045][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 3.0372724533081055, cross_entropy: 3.0372724533081055 +[2025-04-27 13:08:22,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 2.7046518325805664, cross_entropy: 2.7046518325805664 +[2025-04-27 13:08:22,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.1357815265655518, cross_entropy: 1.1357815265655518 +[2025-04-27 13:08:25,088][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 1.6617326736450195, cross_entropy: 1.6617326736450195 +[2025-04-27 13:08:25,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.8396854400634766, cross_entropy: 2.8396854400634766 +[2025-04-27 13:08:27,746][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.711688756942749, cross_entropy: 1.711688756942749 +[2025-04-27 13:08:28,012][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.5658032894134521, cross_entropy: 1.5658032894134521 +[2025-04-27 13:08:30,234][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 2.9300003051757812, cross_entropy: 2.9300003051757812 +[2025-04-27 13:08:30,504][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.3524786233901978, cross_entropy: 1.3524786233901978 +[2025-04-27 13:08:32,863][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.6666103601455688, cross_entropy: 1.6666103601455688 +[2025-04-27 13:08:33,181][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.0000579357147217, cross_entropy: 1.0000579357147217 +[2025-04-27 13:08:35,266][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 1.0255317687988281, cross_entropy: 1.0255317687988281 +[2025-04-27 13:08:35,617][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.8304309844970703, cross_entropy: 2.8304309844970703 +[2025-04-27 13:08:37,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.0490386486053467, cross_entropy: 1.0490386486053467 +[2025-04-27 13:08:38,651][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 2.799943208694458, cross_entropy: 2.799943208694458 +[2025-04-27 13:08:40,829][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.604473829269409, cross_entropy: 2.604473829269409 +[2025-04-27 13:08:41,162][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.4327619075775146, cross_entropy: 2.4327619075775146 +[2025-04-27 13:08:43,408][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 1.8186900615692139, cross_entropy: 1.8186900615692139 +[2025-04-27 13:08:43,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.6178635358810425, cross_entropy: 1.6178635358810425 +[2025-04-27 13:08:45,888][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.6522067189216614, cross_entropy: 0.6522067189216614 +[2025-04-27 13:08:46,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.6011143922805786, cross_entropy: 1.6011143922805786 +[2025-04-27 13:08:48,270][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.659862518310547, cross_entropy: 2.659862518310547 +[2025-04-27 13:08:49,013][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 0.9769594669342041, cross_entropy: 0.9769594669342041 +[2025-04-27 13:08:50,680][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.123096466064453, cross_entropy: 2.123096466064453 +[2025-04-27 13:08:51,832][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 0.9814275503158569, cross_entropy: 0.9814275503158569 +[2025-04-27 13:08:53,058][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 1.8758492469787598, cross_entropy: 1.8758492469787598 +[2025-04-27 13:08:54,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.6441539525985718, cross_entropy: 0.6441539525985718 +[2025-04-27 13:08:56,305][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 1.9455926418304443, cross_entropy: 1.9455926418304443 +[2025-04-27 13:08:56,615][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.3546621799468994, cross_entropy: 1.3546621799468994 +[2025-04-27 13:08:58,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.8346619606018066, cross_entropy: 2.8346619606018066 +[2025-04-27 13:08:59,407][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 2.766362190246582, cross_entropy: 2.766362190246582 +[2025-04-27 13:09:01,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.646433115005493, cross_entropy: 2.646433115005493 +[2025-04-27 13:09:01,713][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 0.677859902381897, cross_entropy: 0.677859902381897 +[2025-04-27 13:09:05,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.408221960067749, cross_entropy: 2.408221960067749 +[2025-04-27 13:09:05,294][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.8958220481872559, cross_entropy: 1.8958220481872559 +[2025-04-27 13:09:07,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 1.057854413986206, cross_entropy: 1.057854413986206 +[2025-04-27 13:09:08,161][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.7732977867126465, cross_entropy: 2.7732977867126465 +[2025-04-27 13:09:10,928][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.0296685695648193, cross_entropy: 1.0296685695648193 +[2025-04-27 13:09:11,213][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 2.498844623565674, cross_entropy: 2.498844623565674 +[2025-04-27 13:09:13,953][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 0.9901964068412781, cross_entropy: 0.9901964068412781 +[2025-04-27 13:09:14,241][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.2344807386398315, cross_entropy: 1.2344807386398315 +[2025-04-27 13:09:17,314][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.1906394958496094, cross_entropy: 1.1906394958496094 +[2025-04-27 13:09:17,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.8745930194854736, cross_entropy: 2.8745930194854736 +[2025-04-27 13:09:20,321][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 0.8168887495994568, cross_entropy: 0.8168887495994568 +[2025-04-27 13:09:20,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 0.7479287385940552, cross_entropy: 0.7479287385940552 +[2025-04-27 13:09:22,383][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 2.6973533630371094, cross_entropy: 2.6973533630371094 +[2025-04-27 13:09:22,648][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.61763334274292, cross_entropy: 2.61763334274292 +[2025-04-27 13:09:24,862][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 1.2924344539642334, cross_entropy: 1.2924344539642334 +[2025-04-27 13:09:25,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.0552133321762085, cross_entropy: 1.0552133321762085 +[2025-04-27 13:09:27,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.144871711730957, cross_entropy: 2.144871711730957 +[2025-04-27 13:09:27,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.1874020099639893, cross_entropy: 1.1874020099639893 +[2025-04-27 13:09:30,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 2.0230801105499268, cross_entropy: 2.0230801105499268 +[2025-04-27 13:09:30,973][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 0.9304500818252563, cross_entropy: 0.9304500818252563 +[2025-04-27 13:09:33,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 1.7739448547363281, cross_entropy: 1.7739448547363281 +[2025-04-27 13:09:33,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.7583274841308594, cross_entropy: 2.7583274841308594 +[2025-04-27 13:09:36,594][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 0.8907129168510437, cross_entropy: 0.8907129168510437 +[2025-04-27 13:09:36,882][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 1.0168688297271729, cross_entropy: 1.0168688297271729 +[2025-04-27 13:09:39,212][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.545372724533081, cross_entropy: 2.545372724533081 +[2025-04-27 13:09:39,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 0.9786731004714966, cross_entropy: 0.9786731004714966 +[2025-04-27 13:09:42,788][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.1053426265716553, cross_entropy: 1.1053426265716553 +[2025-04-27 13:09:43,075][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 0.779072105884552, cross_entropy: 0.779072105884552 +[2025-04-27 13:09:45,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.340722918510437, cross_entropy: 1.340722918510437 +[2025-04-27 13:09:45,761][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.3033781051635742, cross_entropy: 1.3033781051635742 +[2025-04-27 13:09:47,966][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.587026596069336, cross_entropy: 2.587026596069336 +[2025-04-27 13:09:48,256][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 0.8348875045776367, cross_entropy: 0.8348875045776367 +[2025-04-27 13:09:50,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.3789643049240112, cross_entropy: 1.3789643049240112 +[2025-04-27 13:09:50,740][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.2003145217895508, cross_entropy: 1.2003145217895508 +[2025-04-27 13:09:53,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.514026641845703, cross_entropy: 2.514026641845703 +[2025-04-27 13:09:53,815][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.245177745819092, cross_entropy: 2.245177745819092 +[2025-04-27 13:09:56,167][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.1200337409973145, cross_entropy: 2.1200337409973145 +[2025-04-27 13:09:56,456][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 0.9557381868362427, cross_entropy: 0.9557381868362427 +[2025-04-27 13:09:58,632][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 3.046290397644043, cross_entropy: 3.046290397644043 +[2025-04-27 13:09:58,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 2.450399160385132, cross_entropy: 2.450399160385132 +[2025-04-27 13:10:01,304][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.5494420528411865, cross_entropy: 1.5494420528411865 +[2025-04-27 13:10:01,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 3.025542736053467, cross_entropy: 3.025542736053467 +[2025-04-27 13:10:03,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 0.7657857537269592, cross_entropy: 0.7657857537269592 +[2025-04-27 13:10:03,951][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.478623628616333, cross_entropy: 2.478623628616333 +[2025-04-27 13:10:06,137][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 2.1120035648345947, cross_entropy: 2.1120035648345947 +[2025-04-27 13:10:06,428][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.921764612197876, cross_entropy: 1.921764612197876 +[2025-04-27 13:10:08,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 1.8829739093780518, cross_entropy: 1.8829739093780518 +[2025-04-27 13:10:08,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 0.8740441799163818, cross_entropy: 0.8740441799163818 +[2025-04-27 13:10:10,646][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 1.9882408380508423, cross_entropy: 1.9882408380508423 +[2025-04-27 13:10:10,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.4538121223449707, cross_entropy: 1.4538121223449707 +[2025-04-27 13:10:13,260][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 1.9639891386032104, cross_entropy: 1.9639891386032104 +[2025-04-27 13:10:13,548][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.1916215419769287, cross_entropy: 1.1916215419769287 +[2025-04-27 13:10:15,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 2.556057929992676, cross_entropy: 2.556057929992676 +[2025-04-27 13:10:16,227][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 1.6825902462005615, cross_entropy: 1.6825902462005615 +[2025-04-27 13:10:18,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 2.604170322418213, cross_entropy: 2.604170322418213 +[2025-04-27 13:10:18,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 0.6541566848754883, cross_entropy: 0.6541566848754883 +[2025-04-27 13:10:20,910][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.7999677658081055, cross_entropy: 2.7999677658081055 +[2025-04-27 13:10:21,198][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.4531869888305664, cross_entropy: 1.4531869888305664 +[2025-04-27 13:10:24,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 0.9496524333953857, cross_entropy: 0.9496524333953857 +[2025-04-27 13:10:24,734][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 0.7136574387550354, cross_entropy: 0.7136574387550354 +[2025-04-27 13:10:27,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 2.733799934387207, cross_entropy: 2.733799934387207 +[2025-04-27 13:10:27,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.9056257009506226, cross_entropy: 1.9056257009506226 +[2025-04-27 13:10:30,105][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 0.9683713912963867, cross_entropy: 0.9683713912963867 +[2025-04-27 13:10:30,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 0.5664889216423035, cross_entropy: 0.5664889216423035 +[2025-04-27 13:10:32,535][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 2.82212495803833, cross_entropy: 2.82212495803833 +[2025-04-27 13:10:32,808][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 1.9709153175354004, cross_entropy: 1.9709153175354004 +[2025-04-27 13:10:35,579][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 2.370901584625244, cross_entropy: 2.370901584625244 +[2025-04-27 13:10:35,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.2606079578399658, cross_entropy: 1.2606079578399658 +[2025-04-27 13:10:37,965][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.264591693878174, cross_entropy: 2.264591693878174 +[2025-04-27 13:10:38,254][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 2.642794132232666, cross_entropy: 2.642794132232666 +[2025-04-27 13:10:40,723][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 2.909008264541626, cross_entropy: 2.909008264541626 +[2025-04-27 13:10:41,013][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 2.7690234184265137, cross_entropy: 2.7690234184265137 +[2025-04-27 13:10:44,020][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 1.8957221508026123, cross_entropy: 1.8957221508026123 +[2025-04-27 13:10:44,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 0.8996248245239258, cross_entropy: 0.8996248245239258 +[2025-04-27 13:10:46,512][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 0.7647864818572998, cross_entropy: 0.7647864818572998 +[2025-04-27 13:10:46,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.5110878944396973, cross_entropy: 2.5110878944396973 +[2025-04-27 13:10:48,942][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.0216164588928223, cross_entropy: 1.0216164588928223 +[2025-04-27 13:10:49,244][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.6331892013549805, cross_entropy: 2.6331892013549805 +[2025-04-27 13:10:51,793][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 3.012784481048584, cross_entropy: 3.012784481048584 +[2025-04-27 13:10:52,080][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.5498037338256836, cross_entropy: 2.5498037338256836 +[2025-04-27 13:10:54,211][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.2444608211517334, cross_entropy: 1.2444608211517334 +[2025-04-27 13:10:54,503][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 0.8100970983505249, cross_entropy: 0.8100970983505249 +[2025-04-27 13:10:57,106][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 0.821994423866272, cross_entropy: 0.821994423866272 +[2025-04-27 13:10:57,396][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.1413781642913818, cross_entropy: 1.1413781642913818 +[2025-04-27 13:10:59,567][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.157104253768921, cross_entropy: 2.157104253768921 +[2025-04-27 13:10:59,867][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.4064459800720215, cross_entropy: 1.4064459800720215 +[2025-04-27 13:11:02,205][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.559166669845581, cross_entropy: 1.559166669845581 +[2025-04-27 13:11:02,494][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 0.9070099592208862, cross_entropy: 0.9070099592208862 +[2025-04-27 13:11:04,979][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.984654188156128, cross_entropy: 1.984654188156128 +[2025-04-27 13:11:05,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.2965404987335205, cross_entropy: 1.2965404987335205 +[2025-04-27 13:11:07,505][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 1.201459527015686, cross_entropy: 1.201459527015686 +[2025-04-27 13:11:07,794][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 0.439651757478714, cross_entropy: 0.439651757478714 +[2025-04-27 13:11:10,373][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.2751388549804688, cross_entropy: 2.2751388549804688 +[2025-04-27 13:11:10,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 2.7237071990966797, cross_entropy: 2.7237071990966797 +[2025-04-27 13:11:13,105][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.5836272239685059, cross_entropy: 1.5836272239685059 +[2025-04-27 13:11:13,369][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 3.0952320098876953, cross_entropy: 3.0952320098876953 +[2025-04-27 13:11:15,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 2.698537588119507, cross_entropy: 2.698537588119507 +[2025-04-27 13:11:16,159][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 1.3162074089050293, cross_entropy: 1.3162074089050293 +[2025-04-27 13:11:17,991][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.61266827583313, cross_entropy: 2.61266827583313 +[2025-04-27 13:11:18,275][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 0.9813162684440613, cross_entropy: 0.9813162684440613 +[2025-04-27 13:11:20,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.8203039169311523, cross_entropy: 2.8203039169311523 +[2025-04-27 13:11:20,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 0.6676183938980103, cross_entropy: 0.6676183938980103 +[2025-04-27 13:11:22,951][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 1.9228453636169434, cross_entropy: 1.9228453636169434 +[2025-04-27 13:11:23,284][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.034812331199646, cross_entropy: 1.034812331199646 +[2025-04-27 13:11:25,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 0.7417137622833252, cross_entropy: 0.7417137622833252 +[2025-04-27 13:11:25,746][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.1794558763504028, cross_entropy: 1.1794558763504028 +[2025-04-27 13:11:28,754][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 1.2393813133239746, cross_entropy: 1.2393813133239746 +[2025-04-27 13:11:29,043][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.9419819116592407, cross_entropy: 1.9419819116592407 +[2025-04-27 13:11:31,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 0.8513181209564209, cross_entropy: 0.8513181209564209 +[2025-04-27 13:11:31,849][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.6169754266738892, cross_entropy: 0.6169754266738892 +[2025-04-27 13:11:33,671][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 0.9180108308792114, cross_entropy: 0.9180108308792114 +[2025-04-27 13:11:34,142][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.0017144680023193, cross_entropy: 2.0017144680023193 +[2025-04-27 13:11:36,603][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.0358929634094238, cross_entropy: 1.0358929634094238 +[2025-04-27 13:11:36,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.4553561210632324, cross_entropy: 2.4553561210632324 +[2025-04-27 13:11:39,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.78971529006958, cross_entropy: 2.78971529006958 +[2025-04-27 13:11:39,587][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 2.9233546257019043, cross_entropy: 2.9233546257019043 +[2025-04-27 13:11:42,392][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 2.817261219024658, cross_entropy: 2.817261219024658 +[2025-04-27 13:11:42,681][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 2.8162364959716797, cross_entropy: 2.8162364959716797 +[2025-04-27 13:11:44,898][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.671149253845215, cross_entropy: 2.671149253845215 +[2025-04-27 13:11:45,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 1.7272847890853882, cross_entropy: 1.7272847890853882 +[2025-04-27 13:11:47,169][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 1.2033843994140625, cross_entropy: 1.2033843994140625 +[2025-04-27 13:11:47,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 2.684349536895752, cross_entropy: 2.684349536895752 +[2025-04-27 13:11:49,731][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 1.799919843673706, cross_entropy: 1.799919843673706 +[2025-04-27 13:11:50,844][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 0.8967012763023376, cross_entropy: 0.8967012763023376 +[2025-04-27 13:11:52,315][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 1.916743278503418, cross_entropy: 1.916743278503418 +[2025-04-27 13:11:53,281][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.2983338832855225, cross_entropy: 1.2983338832855225 +[2025-04-27 13:11:54,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 1.7589149475097656, cross_entropy: 1.7589149475097656 +[2025-04-27 13:11:55,891][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.7069693803787231, cross_entropy: 1.7069693803787231 +[2025-04-27 13:11:57,417][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 0.686387300491333, cross_entropy: 0.686387300491333 +[2025-04-27 13:11:58,129][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 1.880059838294983, cross_entropy: 1.880059838294983 +[2025-04-27 13:11:59,624][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 2.7846431732177734, cross_entropy: 2.7846431732177734 +[2025-04-27 13:12:00,676][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 1.791906714439392, cross_entropy: 1.791906714439392 +[2025-04-27 13:12:02,352][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 2.830643653869629, cross_entropy: 2.830643653869629 +[2025-04-27 13:12:02,934][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.4518316984176636, cross_entropy: 1.4518316984176636 +[2025-04-27 13:12:04,925][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 2.1631996631622314, cross_entropy: 2.1631996631622314 +[2025-04-27 13:12:05,297][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 2.953888416290283, cross_entropy: 2.953888416290283 +[2025-04-27 13:12:07,195][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.166494131088257, cross_entropy: 2.166494131088257 +[2025-04-27 13:12:07,718][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.575963020324707, cross_entropy: 2.575963020324707 +[2025-04-27 13:12:09,663][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 0.783338189125061, cross_entropy: 0.783338189125061 +[2025-04-27 13:12:10,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 0.7472144961357117, cross_entropy: 0.7472144961357117 +[2025-04-27 13:12:12,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 1.0346492528915405, cross_entropy: 1.0346492528915405 +[2025-04-27 13:12:12,584][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 0.8950982093811035, cross_entropy: 0.8950982093811035 +[2025-04-27 13:12:15,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 2.632840156555176, cross_entropy: 2.632840156555176 +[2025-04-27 13:12:15,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 2.6580233573913574, cross_entropy: 2.6580233573913574 +[2025-04-27 13:12:17,805][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 2.689781665802002, cross_entropy: 2.689781665802002 +[2025-04-27 13:12:18,172][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.7116012573242188, cross_entropy: 2.7116012573242188 +[2025-04-27 13:12:20,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.1161186695098877, cross_entropy: 1.1161186695098877 +[2025-04-27 13:12:20,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.8883562088012695, cross_entropy: 2.8883562088012695 +[2025-04-27 13:12:23,194][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.575401782989502, cross_entropy: 2.575401782989502 +[2025-04-27 13:12:23,534][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 2.7874670028686523, cross_entropy: 2.7874670028686523 +[2025-04-27 13:12:25,637][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.4530582427978516, cross_entropy: 2.4530582427978516 +[2025-04-27 13:12:26,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 2.9498767852783203, cross_entropy: 2.9498767852783203 +[2025-04-27 13:12:29,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 0.6372033357620239, cross_entropy: 0.6372033357620239 +[2025-04-27 13:12:30,097][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.2999961376190186, cross_entropy: 2.2999961376190186 +[2025-04-27 13:12:32,689][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 0.7158004641532898, cross_entropy: 0.7158004641532898 +[2025-04-27 13:12:32,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.040816307067871, cross_entropy: 2.040816307067871 +[2025-04-27 13:12:35,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 2.5563788414001465, cross_entropy: 2.5563788414001465 +[2025-04-27 13:12:35,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 2.506579875946045, cross_entropy: 2.506579875946045 +[2025-04-27 13:12:37,775][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.3561451435089111, cross_entropy: 1.3561451435089111 +[2025-04-27 13:12:38,066][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.1486475467681885, cross_entropy: 2.1486475467681885 +[2025-04-27 13:12:40,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.4894130229949951, cross_entropy: 1.4894130229949951 +[2025-04-27 13:12:40,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 0.9810341000556946, cross_entropy: 0.9810341000556946 +[2025-04-27 13:12:43,258][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.249328136444092, cross_entropy: 2.249328136444092 +[2025-04-27 13:12:43,547][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.6078317165374756, cross_entropy: 1.6078317165374756 +[2025-04-27 13:12:45,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 1.2172870635986328, cross_entropy: 1.2172870635986328 +[2025-04-27 13:12:45,897][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.2766525745391846, cross_entropy: 1.2766525745391846 +[2025-04-27 13:12:48,529][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 0.6937693357467651, cross_entropy: 0.6937693357467651 +[2025-04-27 13:12:48,795][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 0.9613908529281616, cross_entropy: 0.9613908529281616 +[2025-04-27 13:12:51,220][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.7065379619598389, cross_entropy: 1.7065379619598389 +[2025-04-27 13:12:51,887][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 1.6462384462356567, cross_entropy: 1.6462384462356567 +[2025-04-27 13:12:54,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 2.517076015472412, cross_entropy: 2.517076015472412 +[2025-04-27 13:12:54,625][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 2.9059300422668457, cross_entropy: 2.9059300422668457 +[2025-04-27 13:12:57,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 0.6907999515533447, cross_entropy: 0.6907999515533447 +[2025-04-27 13:12:57,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 3.054641008377075, cross_entropy: 3.054641008377075 +[2025-04-27 13:12:59,906][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 1.8806614875793457, cross_entropy: 1.8806614875793457 +[2025-04-27 13:13:00,197][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.028653144836426, cross_entropy: 2.028653144836426 +[2025-04-27 13:13:02,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 1.3622002601623535, cross_entropy: 1.3622002601623535 +[2025-04-27 13:13:02,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 1.1889855861663818, cross_entropy: 1.1889855861663818 +[2025-04-27 13:13:05,350][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.3303420543670654, cross_entropy: 2.3303420543670654 +[2025-04-27 13:13:05,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 1.9983588457107544, cross_entropy: 1.9983588457107544 +[2025-04-27 13:13:08,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.524291753768921, cross_entropy: 1.524291753768921 +[2025-04-27 13:13:08,763][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.1888539791107178, cross_entropy: 1.1888539791107178 +[2025-04-27 13:13:11,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 2.828343629837036, cross_entropy: 2.828343629837036 +[2025-04-27 13:13:11,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 1.8438856601715088, cross_entropy: 1.8438856601715088 +[2025-04-27 13:13:13,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.7260682582855225, cross_entropy: 2.7260682582855225 +[2025-04-27 13:13:13,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 0.9867500066757202, cross_entropy: 0.9867500066757202 +[2025-04-27 13:13:15,919][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.287201166152954, cross_entropy: 1.287201166152954 +[2025-04-27 13:13:16,204][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.338768482208252, cross_entropy: 2.338768482208252 +[2025-04-27 13:13:19,145][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.983814239501953, cross_entropy: 2.983814239501953 +[2025-04-27 13:13:19,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.0517330169677734, cross_entropy: 2.0517330169677734 +[2025-04-27 13:13:21,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 1.0934374332427979, cross_entropy: 1.0934374332427979 +[2025-04-27 13:13:22,134][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.6940449476242065, cross_entropy: 1.6940449476242065 +[2025-04-27 13:13:24,797][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.024608850479126, cross_entropy: 1.024608850479126 +[2025-04-27 13:13:25,061][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.1945968866348267, cross_entropy: 1.1945968866348267 +[2025-04-27 13:13:27,242][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 2.7116549015045166, cross_entropy: 2.7116549015045166 +[2025-04-27 13:13:27,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.2353562116622925, cross_entropy: 1.2353562116622925 +[2025-04-27 13:13:30,294][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 3.0888495445251465, cross_entropy: 3.0888495445251465 +[2025-04-27 13:13:30,590][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 0.5298193097114563, cross_entropy: 0.5298193097114563 +[2025-04-27 13:13:33,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 1.3391485214233398, cross_entropy: 1.3391485214233398 +[2025-04-27 13:13:33,463][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 0.765885591506958, cross_entropy: 0.765885591506958 +[2025-04-27 13:13:35,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 2.569085121154785, cross_entropy: 2.569085121154785 +[2025-04-27 13:13:36,202][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 1.02467679977417, cross_entropy: 1.02467679977417 +[2025-04-27 13:13:38,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 2.600287437438965, cross_entropy: 2.600287437438965 +[2025-04-27 13:13:38,894][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.526214122772217, cross_entropy: 2.526214122772217 +[2025-04-27 13:13:41,223][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 3.179676055908203, cross_entropy: 3.179676055908203 +[2025-04-27 13:13:41,489][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.377901077270508, cross_entropy: 2.377901077270508 +[2025-04-27 13:13:43,971][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 2.9161853790283203, cross_entropy: 2.9161853790283203 +[2025-04-27 13:13:44,263][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.132877826690674, cross_entropy: 2.132877826690674 +[2025-04-27 13:13:47,012][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 3.2625393867492676, cross_entropy: 3.2625393867492676 +[2025-04-27 13:13:47,318][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.388928771018982, cross_entropy: 1.388928771018982 +[2025-04-27 13:13:49,432][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 2.639518976211548, cross_entropy: 2.639518976211548 +[2025-04-27 13:13:49,724][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.0976388454437256, cross_entropy: 1.0976388454437256 +[2025-04-27 13:13:53,158][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 1.122780442237854, cross_entropy: 1.122780442237854 +[2025-04-27 13:13:53,448][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 1.0731381177902222, cross_entropy: 1.0731381177902222 +[2025-04-27 13:13:55,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.157244920730591, cross_entropy: 2.157244920730591 +[2025-04-27 13:13:56,083][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.6605184078216553, cross_entropy: 2.6605184078216553 +[2025-04-27 13:13:59,409][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.627129077911377, cross_entropy: 2.627129077911377 +[2025-04-27 13:13:59,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.7897789478302, cross_entropy: 2.7897789478302 +[2025-04-27 13:14:02,123][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 0.8142938613891602, cross_entropy: 0.8142938613891602 +[2025-04-27 13:14:02,417][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 1.8272132873535156, cross_entropy: 1.8272132873535156 +[2025-04-27 13:14:04,421][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 0.9214144349098206, cross_entropy: 0.9214144349098206 +[2025-04-27 13:14:04,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.027908444404602, cross_entropy: 1.027908444404602 +[2025-04-27 13:14:08,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 1.3536208868026733, cross_entropy: 1.3536208868026733 +[2025-04-27 13:14:08,919][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.268425464630127, cross_entropy: 1.268425464630127 +[2025-04-27 13:14:11,178][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.474280595779419, cross_entropy: 1.474280595779419 +[2025-04-27 13:14:11,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 2.77628755569458, cross_entropy: 2.77628755569458 +[2025-04-27 13:14:13,574][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 2.712827205657959, cross_entropy: 2.712827205657959 +[2025-04-27 13:14:13,841][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 3.0803472995758057, cross_entropy: 3.0803472995758057 +[2025-04-27 13:14:16,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.9905365705490112, cross_entropy: 1.9905365705490112 +[2025-04-27 13:14:16,713][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 0.9082976579666138, cross_entropy: 0.9082976579666138 +[2025-04-27 13:14:19,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.1742939949035645, cross_entropy: 2.1742939949035645 +[2025-04-27 13:14:19,775][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 1.9473695755004883, cross_entropy: 1.9473695755004883 +[2025-04-27 13:14:22,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 2.9156546592712402, cross_entropy: 2.9156546592712402 +[2025-04-27 13:14:22,344][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 0.9801077842712402, cross_entropy: 0.9801077842712402 +[2025-04-27 13:14:24,948][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.720909595489502, cross_entropy: 2.720909595489502 +[2025-04-27 13:14:25,234][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.5436367988586426, cross_entropy: 1.5436367988586426 +[2025-04-27 13:14:27,402][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 1.9697344303131104, cross_entropy: 1.9697344303131104 +[2025-04-27 13:14:27,700][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.7620174884796143, cross_entropy: 0.7620174884796143 +[2025-04-27 13:14:29,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.1340304613113403, cross_entropy: 1.1340304613113403 +[2025-04-27 13:14:30,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.2628881931304932, cross_entropy: 1.2628881931304932 +[2025-04-27 13:14:32,214][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.084776520729065, cross_entropy: 1.084776520729065 +[2025-04-27 13:14:32,502][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.0769240856170654, cross_entropy: 1.0769240856170654 +[2025-04-27 13:14:34,460][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.0305832624435425, cross_entropy: 1.0305832624435425 +[2025-04-27 13:14:34,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.782174825668335, cross_entropy: 1.782174825668335 +[2025-04-27 13:14:37,010][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 2.673159122467041, cross_entropy: 2.673159122467041 +[2025-04-27 13:14:37,275][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 1.5164918899536133, cross_entropy: 1.5164918899536133 +[2025-04-27 13:14:39,379][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 0.6634215116500854, cross_entropy: 0.6634215116500854 +[2025-04-27 13:14:39,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.508643388748169, cross_entropy: 1.508643388748169 +[2025-04-27 13:14:42,075][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.9391302466392517, cross_entropy: 0.9391302466392517 +[2025-04-27 13:14:42,428][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 0.8607887625694275, cross_entropy: 0.8607887625694275 +[2025-04-27 13:14:45,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.38374143838882446, cross_entropy: 0.38374143838882446 +[2025-04-27 13:14:45,759][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.6552631855010986, cross_entropy: 2.6552631855010986 +[2025-04-27 13:14:48,217][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.3524668216705322, cross_entropy: 1.3524668216705322 +[2025-04-27 13:14:48,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.3436527252197266, cross_entropy: 1.3436527252197266 +[2025-04-27 13:14:50,966][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.690039873123169, cross_entropy: 2.690039873123169 +[2025-04-27 13:14:51,237][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 0.8602774739265442, cross_entropy: 0.8602774739265442 +[2025-04-27 13:14:53,537][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.557756781578064, cross_entropy: 1.557756781578064 +[2025-04-27 13:14:53,831][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.871719241142273, cross_entropy: 1.871719241142273 +[2025-04-27 13:14:57,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.054546594619751, cross_entropy: 1.054546594619751 +[2025-04-27 13:14:57,374][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 2.6022720336914062, cross_entropy: 2.6022720336914062 +[2025-04-27 13:14:59,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 2.973863124847412, cross_entropy: 2.973863124847412 +[2025-04-27 13:14:59,717][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.874435305595398, cross_entropy: 1.874435305595398 +[2025-04-27 13:15:02,069][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.3289408683776855, cross_entropy: 1.3289408683776855 +[2025-04-27 13:15:02,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 0.8299369215965271, cross_entropy: 0.8299369215965271 +[2025-04-27 13:15:04,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 0.9959574341773987, cross_entropy: 0.9959574341773987 +[2025-04-27 13:15:04,945][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.1313809156417847, cross_entropy: 1.1313809156417847 +[2025-04-27 13:15:08,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.1420637369155884, cross_entropy: 1.1420637369155884 +[2025-04-27 13:15:08,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.167017936706543, cross_entropy: 1.167017936706543 +[2025-04-27 13:15:11,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 2.8862884044647217, cross_entropy: 2.8862884044647217 +[2025-04-27 13:15:11,598][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.8321073651313782, cross_entropy: 0.8321073651313782 +[2025-04-27 13:15:14,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 1.6073452234268188, cross_entropy: 1.6073452234268188 +[2025-04-27 13:15:14,630][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.1995725631713867, cross_entropy: 1.1995725631713867 +[2025-04-27 13:15:16,605][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.8877887725830078, cross_entropy: 1.8877887725830078 +[2025-04-27 13:15:16,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 3.0749571323394775, cross_entropy: 3.0749571323394775 +[2025-04-27 13:15:19,091][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.2466362714767456, cross_entropy: 1.2466362714767456 +[2025-04-27 13:15:19,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.6106536388397217, cross_entropy: 2.6106536388397217 +[2025-04-27 13:15:21,603][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.64310359954834, cross_entropy: 2.64310359954834 +[2025-04-27 13:15:21,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.919165015220642, cross_entropy: 1.919165015220642 +[2025-04-27 13:15:24,195][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.5465378761291504, cross_entropy: 1.5465378761291504 +[2025-04-27 13:15:24,460][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 2.460528612136841, cross_entropy: 2.460528612136841 +[2025-04-27 13:15:26,743][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.2983946800231934, cross_entropy: 2.2983946800231934 +[2025-04-27 13:15:27,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.0722012519836426, cross_entropy: 1.0722012519836426 +[2025-04-27 13:15:29,315][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.6252360343933105, cross_entropy: 2.6252360343933105 +[2025-04-27 13:15:29,605][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 1.4749807119369507, cross_entropy: 1.4749807119369507 +[2025-04-27 13:15:32,092][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.2787492275238037, cross_entropy: 1.2787492275238037 +[2025-04-27 13:15:32,361][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 3.0146446228027344, cross_entropy: 3.0146446228027344 +[2025-04-27 13:15:34,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 2.6833066940307617, cross_entropy: 2.6833066940307617 +[2025-04-27 13:15:35,130][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.876514434814453, cross_entropy: 2.876514434814453 +[2025-04-27 13:15:37,054][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 2.5149147510528564, cross_entropy: 2.5149147510528564 +[2025-04-27 13:15:37,291][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 0.9531663060188293, cross_entropy: 0.9531663060188293 +[2025-04-27 13:17:45,609][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.7829760313034058, cross_entropy: 1.7829760313034058 +[2025-04-27 13:17:45,610][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.221924066543579, cross_entropy: 1.221924066543579 +[2025-04-27 13:17:45,782][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch8.pth. +[2025-04-27 13:17:46,036][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 13:17:49,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.4864790439605713, cross_entropy: 1.4864790439605713 +[2025-04-27 13:17:50,258][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.0687098503112793, cross_entropy: 1.0687098503112793 +[2025-04-27 13:17:52,925][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 2.7229979038238525, cross_entropy: 2.7229979038238525 +[2025-04-27 13:17:53,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 2.7846386432647705, cross_entropy: 2.7846386432647705 +[2025-04-27 13:17:55,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 2.6035988330841064, cross_entropy: 2.6035988330841064 +[2025-04-27 13:17:55,660][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 0.9271876811981201, cross_entropy: 0.9271876811981201 +[2025-04-27 13:17:58,113][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.2693400382995605, cross_entropy: 2.2693400382995605 +[2025-04-27 13:17:58,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.263477325439453, cross_entropy: 2.263477325439453 +[2025-04-27 13:18:00,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.031621217727661, cross_entropy: 2.031621217727661 +[2025-04-27 13:18:00,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 2.7674360275268555, cross_entropy: 2.7674360275268555 +[2025-04-27 13:18:03,434][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.2797574996948242, cross_entropy: 1.2797574996948242 +[2025-04-27 13:18:03,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.6209825277328491, cross_entropy: 0.6209825277328491 +[2025-04-27 13:18:06,341][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.8223793506622314, cross_entropy: 2.8223793506622314 +[2025-04-27 13:18:06,606][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 0.8611797094345093, cross_entropy: 0.8611797094345093 +[2025-04-27 13:18:09,286][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.6256535053253174, cross_entropy: 2.6256535053253174 +[2025-04-27 13:18:09,582][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 1.0501230955123901, cross_entropy: 1.0501230955123901 +[2025-04-27 13:18:11,752][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 0.8348982334136963, cross_entropy: 0.8348982334136963 +[2025-04-27 13:18:12,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 0.9985209107398987, cross_entropy: 0.9985209107398987 +[2025-04-27 13:18:13,962][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 0.7493183612823486, cross_entropy: 0.7493183612823486 +[2025-04-27 13:18:14,250][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.491368293762207, cross_entropy: 1.491368293762207 +[2025-04-27 13:18:17,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.5601638555526733, cross_entropy: 1.5601638555526733 +[2025-04-27 13:18:17,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 1.3615186214447021, cross_entropy: 1.3615186214447021 +[2025-04-27 13:18:20,478][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.284000873565674, cross_entropy: 2.284000873565674 +[2025-04-27 13:18:20,765][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.3112339973449707, cross_entropy: 2.3112339973449707 +[2025-04-27 13:18:23,465][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 2.612056016921997, cross_entropy: 2.612056016921997 +[2025-04-27 13:18:23,761][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 1.4895098209381104, cross_entropy: 1.4895098209381104 +[2025-04-27 13:18:25,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.7412750720977783, cross_entropy: 1.7412750720977783 +[2025-04-27 13:18:25,945][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.009847402572632, cross_entropy: 2.009847402572632 +[2025-04-27 13:18:28,168][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.173152446746826, cross_entropy: 2.173152446746826 +[2025-04-27 13:18:28,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.2873482704162598, cross_entropy: 1.2873482704162598 +[2025-04-27 13:18:31,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.663912773132324, cross_entropy: 2.663912773132324 +[2025-04-27 13:18:31,269][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.467282772064209, cross_entropy: 1.467282772064209 +[2025-04-27 13:18:33,750][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.5391416549682617, cross_entropy: 1.5391416549682617 +[2025-04-27 13:18:34,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.3907697200775146, cross_entropy: 2.3907697200775146 +[2025-04-27 13:18:36,717][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 2.8055620193481445, cross_entropy: 2.8055620193481445 +[2025-04-27 13:18:36,990][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 0.6686007976531982, cross_entropy: 0.6686007976531982 +[2025-04-27 13:18:39,405][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 0.7646166682243347, cross_entropy: 0.7646166682243347 +[2025-04-27 13:18:39,671][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 2.697675943374634, cross_entropy: 2.697675943374634 +[2025-04-27 13:18:41,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 0.9526325464248657, cross_entropy: 0.9526325464248657 +[2025-04-27 13:18:42,260][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.9311375617980957, cross_entropy: 2.9311375617980957 +[2025-04-27 13:18:44,552][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 2.679457664489746, cross_entropy: 2.679457664489746 +[2025-04-27 13:18:44,816][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.5643982887268066, cross_entropy: 2.5643982887268066 +[2025-04-27 13:18:47,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.2147982120513916, cross_entropy: 2.2147982120513916 +[2025-04-27 13:18:47,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 0.5199247598648071, cross_entropy: 0.5199247598648071 +[2025-04-27 13:18:50,202][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.7393763065338135, cross_entropy: 0.7393763065338135 +[2025-04-27 13:18:50,492][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 1.7818173170089722, cross_entropy: 1.7818173170089722 +[2025-04-27 13:18:53,260][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.007817506790161, cross_entropy: 3.007817506790161 +[2025-04-27 13:18:53,525][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 2.8547558784484863, cross_entropy: 2.8547558784484863 +[2025-04-27 13:18:55,979][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 3.054856777191162, cross_entropy: 3.054856777191162 +[2025-04-27 13:18:56,246][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 0.7853356003761292, cross_entropy: 0.7853356003761292 +[2025-04-27 13:18:58,990][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.356083631515503, cross_entropy: 1.356083631515503 +[2025-04-27 13:18:59,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 0.9223016500473022, cross_entropy: 0.9223016500473022 +[2025-04-27 13:19:01,650][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 0.4149959683418274, cross_entropy: 0.4149959683418274 +[2025-04-27 13:19:01,937][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.2349185943603516, cross_entropy: 1.2349185943603516 +[2025-04-27 13:19:03,662][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 1.2867305278778076, cross_entropy: 1.2867305278778076 +[2025-04-27 13:19:04,314][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 3.1483254432678223, cross_entropy: 3.1483254432678223 +[2025-04-27 13:19:05,962][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 0.641471266746521, cross_entropy: 0.641471266746521 +[2025-04-27 13:19:07,035][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 1.0855129957199097, cross_entropy: 1.0855129957199097 +[2025-04-27 13:19:08,902][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.540290355682373, cross_entropy: 1.540290355682373 +[2025-04-27 13:19:09,710][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 2.940061092376709, cross_entropy: 2.940061092376709 +[2025-04-27 13:19:11,330][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 1.956561803817749, cross_entropy: 1.956561803817749 +[2025-04-27 13:19:12,170][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.16792631149292, cross_entropy: 2.16792631149292 +[2025-04-27 13:19:14,088][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 0.8602330088615417, cross_entropy: 0.8602330088615417 +[2025-04-27 13:19:14,460][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.2179979085922241, cross_entropy: 1.2179979085922241 +[2025-04-27 13:19:16,477][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.768113613128662, cross_entropy: 2.768113613128662 +[2025-04-27 13:19:17,158][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.9362495541572571, cross_entropy: 0.9362495541572571 +[2025-04-27 13:19:19,699][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.5264067649841309, cross_entropy: 0.5264067649841309 +[2025-04-27 13:19:20,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.6777243614196777, cross_entropy: 0.6777243614196777 +[2025-04-27 13:19:22,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 0.9053884744644165, cross_entropy: 0.9053884744644165 +[2025-04-27 13:19:23,238][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.0844266414642334, cross_entropy: 1.0844266414642334 +[2025-04-27 13:19:26,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 0.6936741471290588, cross_entropy: 0.6936741471290588 +[2025-04-27 13:19:26,596][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.093271255493164, cross_entropy: 1.093271255493164 +[2025-04-27 13:19:28,716][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.0208953619003296, cross_entropy: 1.0208953619003296 +[2025-04-27 13:19:29,009][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 0.6735200881958008, cross_entropy: 0.6735200881958008 +[2025-04-27 13:19:31,287][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.0290439128875732, cross_entropy: 2.0290439128875732 +[2025-04-27 13:19:31,576][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.5926170349121094, cross_entropy: 2.5926170349121094 +[2025-04-27 13:19:33,594][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 2.3637044429779053, cross_entropy: 2.3637044429779053 +[2025-04-27 13:19:33,884][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.5706825256347656, cross_entropy: 0.5706825256347656 +[2025-04-27 13:19:35,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 2.6876838207244873, cross_entropy: 2.6876838207244873 +[2025-04-27 13:19:36,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 1.1126158237457275, cross_entropy: 1.1126158237457275 +[2025-04-27 13:19:38,322][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.9570894241333008, cross_entropy: 1.9570894241333008 +[2025-04-27 13:19:38,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.9065518379211426, cross_entropy: 0.9065518379211426 +[2025-04-27 13:19:41,173][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.0919779539108276, cross_entropy: 1.0919779539108276 +[2025-04-27 13:19:42,161][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 2.895118236541748, cross_entropy: 2.895118236541748 +[2025-04-27 13:19:43,438][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.0519317388534546, cross_entropy: 1.0519317388534546 +[2025-04-27 13:19:45,070][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.3558534383773804, cross_entropy: 1.3558534383773804 +[2025-04-27 13:19:45,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.2801709175109863, cross_entropy: 2.2801709175109863 +[2025-04-27 13:19:48,038][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.6062898635864258, cross_entropy: 1.6062898635864258 +[2025-04-27 13:19:48,376][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 0.5089194774627686, cross_entropy: 0.5089194774627686 +[2025-04-27 13:19:50,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.3476476669311523, cross_entropy: 2.3476476669311523 +[2025-04-27 13:19:51,269][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.899686574935913, cross_entropy: 2.899686574935913 +[2025-04-27 13:19:53,426][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 1.556986927986145, cross_entropy: 1.556986927986145 +[2025-04-27 13:19:54,135][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.6868014335632324, cross_entropy: 2.6868014335632324 +[2025-04-27 13:19:56,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.8273743987083435, cross_entropy: 0.8273743987083435 +[2025-04-27 13:19:56,472][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 1.8682570457458496, cross_entropy: 1.8682570457458496 +[2025-04-27 13:19:59,173][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.1481692790985107, cross_entropy: 1.1481692790985107 +[2025-04-27 13:19:59,442][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 2.693997383117676, cross_entropy: 2.693997383117676 +[2025-04-27 13:20:02,547][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 1.1939024925231934, cross_entropy: 1.1939024925231934 +[2025-04-27 13:20:02,835][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.549090027809143, cross_entropy: 1.549090027809143 +[2025-04-27 13:20:05,624][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.1979515552520752, cross_entropy: 1.1979515552520752 +[2025-04-27 13:20:05,919][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.970384359359741, cross_entropy: 2.970384359359741 +[2025-04-27 13:20:07,780][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 2.5839831829071045, cross_entropy: 2.5839831829071045 +[2025-04-27 13:20:08,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.2017111778259277, cross_entropy: 1.2017111778259277 +[2025-04-27 13:20:10,352][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.831935405731201, cross_entropy: 2.831935405731201 +[2025-04-27 13:20:10,620][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 0.8934503197669983, cross_entropy: 0.8934503197669983 +[2025-04-27 13:20:12,839][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 2.8869268894195557, cross_entropy: 2.8869268894195557 +[2025-04-27 13:20:13,104][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.720829486846924, cross_entropy: 2.720829486846924 +[2025-04-27 13:20:15,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.7495713233947754, cross_entropy: 0.7495713233947754 +[2025-04-27 13:20:15,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 2.819870710372925, cross_entropy: 2.819870710372925 +[2025-04-27 13:20:18,670][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.8357335329055786, cross_entropy: 0.8357335329055786 +[2025-04-27 13:20:18,961][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 2.6755099296569824, cross_entropy: 2.6755099296569824 +[2025-04-27 13:20:20,854][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.4278030395507812, cross_entropy: 2.4278030395507812 +[2025-04-27 13:20:21,124][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.5601282119750977, cross_entropy: 2.5601282119750977 +[2025-04-27 13:20:23,422][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.4771885871887207, cross_entropy: 1.4771885871887207 +[2025-04-27 13:20:23,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.48990535736084, cross_entropy: 2.48990535736084 +[2025-04-27 13:20:25,822][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 0.9772384762763977, cross_entropy: 0.9772384762763977 +[2025-04-27 13:20:26,124][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 0.9674557447433472, cross_entropy: 0.9674557447433472 +[2025-04-27 13:20:28,271][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 1.963744878768921, cross_entropy: 1.963744878768921 +[2025-04-27 13:20:29,164][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.491431713104248, cross_entropy: 2.491431713104248 +[2025-04-27 13:20:30,679][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.0977888107299805, cross_entropy: 2.0977888107299805 +[2025-04-27 13:20:31,720][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.2287890911102295, cross_entropy: 2.2287890911102295 +[2025-04-27 13:20:33,222][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 0.7834338545799255, cross_entropy: 0.7834338545799255 +[2025-04-27 13:20:35,331][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 1.382824420928955, cross_entropy: 1.382824420928955 +[2025-04-27 13:20:35,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.6637372970581055, cross_entropy: 2.6637372970581055 +[2025-04-27 13:20:38,554][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 0.72812420129776, cross_entropy: 0.72812420129776 +[2025-04-27 13:20:38,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.1888291835784912, cross_entropy: 1.1888291835784912 +[2025-04-27 13:20:41,040][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 1.9087165594100952, cross_entropy: 1.9087165594100952 +[2025-04-27 13:20:41,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.3767414093017578, cross_entropy: 1.3767414093017578 +[2025-04-27 13:20:44,287][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 2.8330740928649902, cross_entropy: 2.8330740928649902 +[2025-04-27 13:20:44,574][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 0.8524064421653748, cross_entropy: 0.8524064421653748 +[2025-04-27 13:20:46,669][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 0.7313806414604187, cross_entropy: 0.7313806414604187 +[2025-04-27 13:20:46,956][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.5955071449279785, cross_entropy: 2.5955071449279785 +[2025-04-27 13:20:49,082][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 0.7771981954574585, cross_entropy: 0.7771981954574585 +[2025-04-27 13:20:49,369][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.3313285112380981, cross_entropy: 1.3313285112380981 +[2025-04-27 13:20:51,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.3437631130218506, cross_entropy: 1.3437631130218506 +[2025-04-27 13:20:51,561][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.3330000638961792, cross_entropy: 1.3330000638961792 +[2025-04-27 13:20:54,348][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.7367782592773438, cross_entropy: 2.7367782592773438 +[2025-04-27 13:20:54,635][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 0.7134534120559692, cross_entropy: 0.7134534120559692 +[2025-04-27 13:20:57,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.8473310470581055, cross_entropy: 2.8473310470581055 +[2025-04-27 13:20:57,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.493910074234009, cross_entropy: 2.493910074234009 +[2025-04-27 13:20:59,602][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.4853553771972656, cross_entropy: 2.4853553771972656 +[2025-04-27 13:20:59,895][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.5501065254211426, cross_entropy: 2.5501065254211426 +[2025-04-27 13:21:01,965][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.2664175033569336, cross_entropy: 2.2664175033569336 +[2025-04-27 13:21:02,253][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.2417495250701904, cross_entropy: 2.2417495250701904 +[2025-04-27 13:21:04,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 0.8172390460968018, cross_entropy: 0.8172390460968018 +[2025-04-27 13:21:04,930][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 2.4172706604003906, cross_entropy: 2.4172706604003906 +[2025-04-27 13:21:07,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 0.8023471832275391, cross_entropy: 0.8023471832275391 +[2025-04-27 13:21:07,328][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.461881160736084, cross_entropy: 1.461881160736084 +[2025-04-27 13:21:10,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.7983289957046509, cross_entropy: 0.7983289957046509 +[2025-04-27 13:21:10,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.059810161590576, cross_entropy: 2.059810161590576 +[2025-04-27 13:21:13,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 2.5708324909210205, cross_entropy: 2.5708324909210205 +[2025-04-27 13:21:13,297][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 2.7772703170776367, cross_entropy: 2.7772703170776367 +[2025-04-27 13:21:13,466][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/iteration3000.pth. +[2025-04-27 13:21:16,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 1.7032363414764404, cross_entropy: 1.7032363414764404 +[2025-04-27 13:21:16,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.0331106185913086, cross_entropy: 2.0331106185913086 +[2025-04-27 13:21:18,367][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 2.8290748596191406, cross_entropy: 2.8290748596191406 +[2025-04-27 13:21:18,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 2.823122978210449, cross_entropy: 2.823122978210449 +[2025-04-27 13:21:21,034][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.072041630744934, cross_entropy: 1.072041630744934 +[2025-04-27 13:21:21,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 0.9940934777259827, cross_entropy: 0.9940934777259827 +[2025-04-27 13:21:23,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 3.046098232269287, cross_entropy: 3.046098232269287 +[2025-04-27 13:21:23,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 0.7632088661193848, cross_entropy: 0.7632088661193848 +[2025-04-27 13:21:26,600][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 2.978710412979126, cross_entropy: 2.978710412979126 +[2025-04-27 13:21:26,893][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 2.6805295944213867, cross_entropy: 2.6805295944213867 +[2025-04-27 13:21:29,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 0.923114538192749, cross_entropy: 0.923114538192749 +[2025-04-27 13:21:29,360][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 2.7281835079193115, cross_entropy: 2.7281835079193115 +[2025-04-27 13:21:31,767][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.3301422595977783, cross_entropy: 2.3301422595977783 +[2025-04-27 13:21:32,030][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 0.597238302230835, cross_entropy: 0.597238302230835 +[2025-04-27 13:21:34,402][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 0.578567624092102, cross_entropy: 0.578567624092102 +[2025-04-27 13:21:34,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.843778133392334, cross_entropy: 2.843778133392334 +[2025-04-27 13:21:36,604][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.8266552686691284, cross_entropy: 0.8266552686691284 +[2025-04-27 13:21:36,892][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 2.245695114135742, cross_entropy: 2.245695114135742 +[2025-04-27 13:21:39,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 1.607177734375, cross_entropy: 1.607177734375 +[2025-04-27 13:21:39,838][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.7660731077194214, cross_entropy: 1.7660731077194214 +[2025-04-27 13:21:41,906][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.759244918823242, cross_entropy: 2.759244918823242 +[2025-04-27 13:21:42,194][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 0.5901758074760437, cross_entropy: 0.5901758074760437 +[2025-04-27 13:21:44,496][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.618604063987732, cross_entropy: 1.618604063987732 +[2025-04-27 13:21:44,807][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 0.8903106451034546, cross_entropy: 0.8903106451034546 +[2025-04-27 13:21:47,794][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 0.9936040639877319, cross_entropy: 0.9936040639877319 +[2025-04-27 13:21:48,084][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.7134833335876465, cross_entropy: 1.7134833335876465 +[2025-04-27 13:21:50,968][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.420859456062317, cross_entropy: 1.420859456062317 +[2025-04-27 13:21:51,263][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.534954071044922, cross_entropy: 2.534954071044922 +[2025-04-27 13:21:53,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.9500856399536133, cross_entropy: 2.9500856399536133 +[2025-04-27 13:21:53,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 1.3036412000656128, cross_entropy: 1.3036412000656128 +[2025-04-27 13:21:56,248][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.3960726261138916, cross_entropy: 1.3960726261138916 +[2025-04-27 13:21:56,513][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 1.260190725326538, cross_entropy: 1.260190725326538 +[2025-04-27 13:21:58,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 2.5276448726654053, cross_entropy: 2.5276448726654053 +[2025-04-27 13:21:59,013][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.401189088821411, cross_entropy: 2.401189088821411 +[2025-04-27 13:22:01,976][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.6114673614501953, cross_entropy: 2.6114673614501953 +[2025-04-27 13:22:02,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 1.1695154905319214, cross_entropy: 1.1695154905319214 +[2025-04-27 13:22:04,393][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.8588210344314575, cross_entropy: 1.8588210344314575 +[2025-04-27 13:22:04,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.1864169836044312, cross_entropy: 1.1864169836044312 +[2025-04-27 13:22:07,007][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 1.0501892566680908, cross_entropy: 1.0501892566680908 +[2025-04-27 13:22:07,297][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.131274938583374, cross_entropy: 1.131274938583374 +[2025-04-27 13:22:09,210][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.7369747161865234, cross_entropy: 2.7369747161865234 +[2025-04-27 13:22:09,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 0.7038990259170532, cross_entropy: 0.7038990259170532 +[2025-04-27 13:22:12,316][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 2.875842809677124, cross_entropy: 2.875842809677124 +[2025-04-27 13:22:12,606][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.0558395385742188, cross_entropy: 3.0558395385742188 +[2025-04-27 13:22:14,710][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 1.9725178480148315, cross_entropy: 1.9725178480148315 +[2025-04-27 13:22:14,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.87630295753479, cross_entropy: 1.87630295753479 +[2025-04-27 13:22:17,498][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 2.9263434410095215, cross_entropy: 2.9263434410095215 +[2025-04-27 13:22:17,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.3409079313278198, cross_entropy: 1.3409079313278198 +[2025-04-27 13:22:19,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.8580601215362549, cross_entropy: 0.8580601215362549 +[2025-04-27 13:22:19,924][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.115228295326233, cross_entropy: 1.115228295326233 +[2025-04-27 13:22:22,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.8585186004638672, cross_entropy: 0.8585186004638672 +[2025-04-27 13:22:22,462][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.090484857559204, cross_entropy: 2.090484857559204 +[2025-04-27 13:22:24,473][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.0389981269836426, cross_entropy: 1.0389981269836426 +[2025-04-27 13:22:24,738][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 1.8204457759857178, cross_entropy: 1.8204457759857178 +[2025-04-27 13:22:27,269][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.6263904571533203, cross_entropy: 2.6263904571533203 +[2025-04-27 13:22:27,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 0.9903196096420288, cross_entropy: 0.9903196096420288 +[2025-04-27 13:22:29,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 1.2588061094284058, cross_entropy: 1.2588061094284058 +[2025-04-27 13:22:30,008][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 1.689100742340088, cross_entropy: 1.689100742340088 +[2025-04-27 13:22:32,270][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 0.7934210300445557, cross_entropy: 0.7934210300445557 +[2025-04-27 13:22:32,560][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 0.7292367815971375, cross_entropy: 0.7292367815971375 +[2025-04-27 13:22:35,248][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 0.8111719489097595, cross_entropy: 0.8111719489097595 +[2025-04-27 13:22:35,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 2.2403955459594727, cross_entropy: 2.2403955459594727 +[2025-04-27 13:22:38,672][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 0.8884475827217102, cross_entropy: 0.8884475827217102 +[2025-04-27 13:22:38,965][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.774944543838501, cross_entropy: 1.774944543838501 +[2025-04-27 13:22:41,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 0.9564141035079956, cross_entropy: 0.9564141035079956 +[2025-04-27 13:22:41,824][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 2.7874085903167725, cross_entropy: 2.7874085903167725 +[2025-04-27 13:22:43,736][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 1.402647614479065, cross_entropy: 1.402647614479065 +[2025-04-27 13:22:44,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 1.4853718280792236, cross_entropy: 1.4853718280792236 +[2025-04-27 13:22:46,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.7167413234710693, cross_entropy: 2.7167413234710693 +[2025-04-27 13:22:46,522][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 1.264862060546875, cross_entropy: 1.264862060546875 +[2025-04-27 13:22:48,479][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.788846969604492, cross_entropy: 2.788846969604492 +[2025-04-27 13:22:48,767][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 1.645544171333313, cross_entropy: 1.645544171333313 +[2025-04-27 13:22:50,996][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 2.7536206245422363, cross_entropy: 2.7536206245422363 +[2025-04-27 13:22:51,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 0.8821207284927368, cross_entropy: 0.8821207284927368 +[2025-04-27 13:22:53,415][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 1.1850159168243408, cross_entropy: 1.1850159168243408 +[2025-04-27 13:22:53,697][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.194253921508789, cross_entropy: 2.194253921508789 +[2025-04-27 13:22:55,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.984041452407837, cross_entropy: 1.984041452407837 +[2025-04-27 13:22:56,016][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.2506439685821533, cross_entropy: 2.2506439685821533 +[2025-04-27 13:22:57,995][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 0.7764852046966553, cross_entropy: 0.7764852046966553 +[2025-04-27 13:22:58,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 2.285914421081543, cross_entropy: 2.285914421081543 +[2025-04-27 13:23:00,147][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 1.0031800270080566, cross_entropy: 1.0031800270080566 +[2025-04-27 13:23:01,065][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 2.692483425140381, cross_entropy: 2.692483425140381 +[2025-04-27 13:23:02,796][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.7469753623008728, cross_entropy: 0.7469753623008728 +[2025-04-27 13:23:03,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 2.4213099479675293, cross_entropy: 2.4213099479675293 +[2025-04-27 13:23:06,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.0771307945251465, cross_entropy: 1.0771307945251465 +[2025-04-27 13:23:06,899][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.8588309288024902, cross_entropy: 2.8588309288024902 +[2025-04-27 13:23:09,513][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 2.930649757385254, cross_entropy: 2.930649757385254 +[2025-04-27 13:23:09,857][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 0.5383591055870056, cross_entropy: 0.5383591055870056 +[2025-04-27 13:23:12,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 0.9457141160964966, cross_entropy: 0.9457141160964966 +[2025-04-27 13:23:12,584][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.1534948348999023, cross_entropy: 1.1534948348999023 +[2025-04-27 13:23:14,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 2.040393352508545, cross_entropy: 2.040393352508545 +[2025-04-27 13:23:15,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 1.1543378829956055, cross_entropy: 1.1543378829956055 +[2025-04-27 13:23:17,470][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.248666286468506, cross_entropy: 2.248666286468506 +[2025-04-27 13:23:17,734][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 1.0758203268051147, cross_entropy: 1.0758203268051147 +[2025-04-27 13:23:20,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 1.187781810760498, cross_entropy: 1.187781810760498 +[2025-04-27 13:23:20,343][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 0.6100679636001587, cross_entropy: 0.6100679636001587 +[2025-04-27 13:23:22,317][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.1467022895812988, cross_entropy: 1.1467022895812988 +[2025-04-27 13:23:23,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.158078670501709, cross_entropy: 1.158078670501709 +[2025-04-27 13:23:25,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 0.826276957988739, cross_entropy: 0.826276957988739 +[2025-04-27 13:23:25,901][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.5234313011169434, cross_entropy: 2.5234313011169434 +[2025-04-27 13:23:28,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 0.788837730884552, cross_entropy: 0.788837730884552 +[2025-04-27 13:23:28,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.6698014736175537, cross_entropy: 2.6698014736175537 +[2025-04-27 13:23:31,057][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 0.815316379070282, cross_entropy: 0.815316379070282 +[2025-04-27 13:23:32,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 0.7467938661575317, cross_entropy: 0.7467938661575317 +[2025-04-27 13:23:33,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.3442513942718506, cross_entropy: 1.3442513942718506 +[2025-04-27 13:23:35,881][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.0100888013839722, cross_entropy: 1.0100888013839722 +[2025-04-27 13:23:37,333][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.6046035289764404, cross_entropy: 2.6046035289764404 +[2025-04-27 13:23:39,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.962597608566284, cross_entropy: 2.962597608566284 +[2025-04-27 13:23:41,091][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 2.60847806930542, cross_entropy: 2.60847806930542 +[2025-04-27 13:23:42,195][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 0.8836366534233093, cross_entropy: 0.8836366534233093 +[2025-04-27 13:23:43,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 0.9365048408508301, cross_entropy: 0.9365048408508301 +[2025-04-27 13:23:44,561][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 1.1194288730621338, cross_entropy: 1.1194288730621338 +[2025-04-27 13:23:46,831][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.002699375152588, cross_entropy: 1.002699375152588 +[2025-04-27 13:23:47,681][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 2.1990859508514404, cross_entropy: 2.1990859508514404 +[2025-04-27 13:23:49,663][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.3299341201782227, cross_entropy: 1.3299341201782227 +[2025-04-27 13:23:50,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.102175235748291, cross_entropy: 2.102175235748291 +[2025-04-27 13:23:52,608][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.299323081970215, cross_entropy: 2.299323081970215 +[2025-04-27 13:23:53,981][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 1.4152002334594727, cross_entropy: 1.4152002334594727 +[2025-04-27 13:23:55,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 2.4864063262939453, cross_entropy: 2.4864063262939453 +[2025-04-27 13:23:56,754][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 0.9570492506027222, cross_entropy: 0.9570492506027222 +[2025-04-27 13:23:58,090][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.5920472145080566, cross_entropy: 2.5920472145080566 +[2025-04-27 13:23:58,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 0.6255354881286621, cross_entropy: 0.6255354881286621 +[2025-04-27 13:24:00,820][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.55173659324646, cross_entropy: 2.55173659324646 +[2025-04-27 13:24:01,678][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 0.6033400297164917, cross_entropy: 0.6033400297164917 +[2025-04-27 13:24:03,331][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.1258223056793213, cross_entropy: 1.1258223056793213 +[2025-04-27 13:24:04,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.9849249124526978, cross_entropy: 1.9849249124526978 +[2025-04-27 13:24:05,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.6435351371765137, cross_entropy: 2.6435351371765137 +[2025-04-27 13:24:07,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.5451780557632446, cross_entropy: 1.5451780557632446 +[2025-04-27 13:24:09,061][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 2.5067405700683594, cross_entropy: 2.5067405700683594 +[2025-04-27 13:24:09,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 0.798628568649292, cross_entropy: 0.798628568649292 +[2025-04-27 13:24:11,246][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 0.8080400228500366, cross_entropy: 0.8080400228500366 +[2025-04-27 13:24:12,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 0.8024953603744507, cross_entropy: 0.8024953603744507 +[2025-04-27 13:24:14,052][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 0.9256075024604797, cross_entropy: 0.9256075024604797 +[2025-04-27 13:24:15,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.266371726989746, cross_entropy: 1.266371726989746 +[2025-04-27 13:24:16,491][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 2.018826961517334, cross_entropy: 2.018826961517334 +[2025-04-27 13:24:17,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 2.6106574535369873, cross_entropy: 2.6106574535369873 +[2025-04-27 13:24:19,294][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 0.7226613163948059, cross_entropy: 0.7226613163948059 +[2025-04-27 13:24:20,533][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.6290686130523682, cross_entropy: 1.6290686130523682 +[2025-04-27 13:24:22,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 0.8956789970397949, cross_entropy: 0.8956789970397949 +[2025-04-27 13:24:23,316][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.6763678789138794, cross_entropy: 1.6763678789138794 +[2025-04-27 13:24:24,633][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.2565281391143799, cross_entropy: 1.2565281391143799 +[2025-04-27 13:24:25,721][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 2.6092894077301025, cross_entropy: 2.6092894077301025 +[2025-04-27 13:24:27,313][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 2.85931396484375, cross_entropy: 2.85931396484375 +[2025-04-27 13:24:28,560][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.9938379526138306, cross_entropy: 1.9938379526138306 +[2025-04-27 13:24:29,507][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.3216677904129028, cross_entropy: 1.3216677904129028 +[2025-04-27 13:24:30,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 1.2051122188568115, cross_entropy: 1.2051122188568115 +[2025-04-27 13:24:31,473][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 2.865861415863037, cross_entropy: 2.865861415863037 +[2025-04-27 13:24:34,349][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.355413794517517, cross_entropy: 1.355413794517517 +[2025-04-27 13:24:34,638][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.021423101425171, cross_entropy: 2.021423101425171 +[2025-04-27 13:24:37,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 0.7015500068664551, cross_entropy: 0.7015500068664551 +[2025-04-27 13:24:37,885][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 2.025780439376831, cross_entropy: 2.025780439376831 +[2025-04-27 13:24:41,090][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 2.3855361938476562, cross_entropy: 2.3855361938476562 +[2025-04-27 13:24:41,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.1735315322875977, cross_entropy: 2.1735315322875977 +[2025-04-27 13:24:43,991][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.7367953062057495, cross_entropy: 0.7367953062057495 +[2025-04-27 13:24:44,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 0.6376467347145081, cross_entropy: 0.6376467347145081 +[2025-04-27 13:24:46,497][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 2.88417387008667, cross_entropy: 2.88417387008667 +[2025-04-27 13:24:46,784][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 2.6816349029541016, cross_entropy: 2.6816349029541016 +[2025-04-27 13:24:49,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 0.7946610450744629, cross_entropy: 0.7946610450744629 +[2025-04-27 13:24:49,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 1.0238882303237915, cross_entropy: 1.0238882303237915 +[2025-04-27 13:24:51,641][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 2.407163619995117, cross_entropy: 2.407163619995117 +[2025-04-27 13:24:51,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 1.397686243057251, cross_entropy: 1.397686243057251 +[2025-04-27 13:24:53,848][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 2.955042839050293, cross_entropy: 2.955042839050293 +[2025-04-27 13:24:54,113][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.0739027261734009, cross_entropy: 1.0739027261734009 +[2025-04-27 13:24:56,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.449657917022705, cross_entropy: 2.449657917022705 +[2025-04-27 13:24:56,666][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 0.8841774463653564, cross_entropy: 0.8841774463653564 +[2025-04-27 13:24:59,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 0.9420072436332703, cross_entropy: 0.9420072436332703 +[2025-04-27 13:24:59,777][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.4499239921569824, cross_entropy: 2.4499239921569824 +[2025-04-27 13:25:02,863][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 1.8906276226043701, cross_entropy: 1.8906276226043701 +[2025-04-27 13:25:03,127][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 2.8271658420562744, cross_entropy: 2.8271658420562744 +[2025-04-27 13:25:05,446][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 0.9171671271324158, cross_entropy: 0.9171671271324158 +[2025-04-27 13:25:05,720][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.541412115097046, cross_entropy: 2.541412115097046 +[2025-04-27 13:25:08,091][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 2.582453727722168, cross_entropy: 2.582453727722168 +[2025-04-27 13:25:08,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 2.7262563705444336, cross_entropy: 2.7262563705444336 +[2025-04-27 13:25:10,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.191436290740967, cross_entropy: 2.191436290740967 +[2025-04-27 13:25:10,561][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 0.6914048790931702, cross_entropy: 0.6914048790931702 +[2025-04-27 13:25:13,361][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.5155038833618164, cross_entropy: 1.5155038833618164 +[2025-04-27 13:25:13,625][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.9047186374664307, cross_entropy: 1.9047186374664307 +[2025-04-27 13:25:16,000][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 2.105062484741211, cross_entropy: 2.105062484741211 +[2025-04-27 13:25:16,289][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 2.4326624870300293, cross_entropy: 2.4326624870300293 +[2025-04-27 13:25:18,710][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 2.4270706176757812, cross_entropy: 2.4270706176757812 +[2025-04-27 13:25:19,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 0.8001102209091187, cross_entropy: 0.8001102209091187 +[2025-04-27 13:25:21,383][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.6839101314544678, cross_entropy: 1.6839101314544678 +[2025-04-27 13:25:21,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 0.8955497145652771, cross_entropy: 0.8955497145652771 +[2025-04-27 13:25:23,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.511942148208618, cross_entropy: 2.511942148208618 +[2025-04-27 13:25:24,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.1035162210464478, cross_entropy: 1.1035162210464478 +[2025-04-27 13:25:26,631][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.6086349487304688, cross_entropy: 2.6086349487304688 +[2025-04-27 13:25:26,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 0.941146969795227, cross_entropy: 0.941146969795227 +[2025-04-27 13:25:29,479][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 0.9793692827224731, cross_entropy: 0.9793692827224731 +[2025-04-27 13:25:29,742][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 0.9125493168830872, cross_entropy: 0.9125493168830872 +[2025-04-27 13:25:33,019][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 2.26729154586792, cross_entropy: 2.26729154586792 +[2025-04-27 13:25:33,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 3.0022518634796143, cross_entropy: 3.0022518634796143 +[2025-04-27 13:25:35,825][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.4787051677703857, cross_entropy: 1.4787051677703857 +[2025-04-27 13:25:36,133][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 1.7345290184020996, cross_entropy: 1.7345290184020996 +[2025-04-27 13:25:38,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.07188081741333, cross_entropy: 2.07188081741333 +[2025-04-27 13:25:38,932][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.4084994792938232, cross_entropy: 1.4084994792938232 +[2025-04-27 13:25:41,277][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 1.787360668182373, cross_entropy: 1.787360668182373 +[2025-04-27 13:25:41,568][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 2.828082323074341, cross_entropy: 2.828082323074341 +[2025-04-27 13:25:44,112][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.809286117553711, cross_entropy: 2.809286117553711 +[2025-04-27 13:25:44,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.296074628829956, cross_entropy: 2.296074628829956 +[2025-04-27 13:25:46,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 1.9638361930847168, cross_entropy: 1.9638361930847168 +[2025-04-27 13:25:47,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 0.700846791267395, cross_entropy: 0.700846791267395 +[2025-04-27 13:25:49,270][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.223665714263916, cross_entropy: 2.223665714263916 +[2025-04-27 13:25:49,536][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 0.8245657682418823, cross_entropy: 0.8245657682418823 +[2025-04-27 13:25:51,481][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.0167367458343506, cross_entropy: 2.0167367458343506 +[2025-04-27 13:27:56,648][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.7242982387542725, cross_entropy: 1.7242982387542725 +[2025-04-27 13:27:56,648][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.181909441947937, cross_entropy: 1.181909441947937 +[2025-04-27 13:27:56,871][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 13:27:57,030][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch9.pth. +[2025-04-27 13:27:57,243][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. +[2025-04-27 13:28:00,357][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 0.9560669660568237, cross_entropy: 0.9560669660568237 +[2025-04-27 13:28:00,686][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.620661735534668, cross_entropy: 1.620661735534668 +[2025-04-27 13:28:02,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.654045581817627, cross_entropy: 0.654045581817627 +[2025-04-27 13:28:05,076][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 2.607558488845825, cross_entropy: 2.607558488845825 +[2025-04-27 13:28:05,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.4241464138031006, cross_entropy: 2.4241464138031006 +[2025-04-27 13:28:07,248][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.765310525894165, cross_entropy: 1.765310525894165 +[2025-04-27 13:28:07,880][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.5535035133361816, cross_entropy: 2.5535035133361816 +[2025-04-27 13:28:10,175][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.9218619465827942, cross_entropy: 0.9218619465827942 +[2025-04-27 13:28:10,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.419543743133545, cross_entropy: 2.419543743133545 +[2025-04-27 13:28:12,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.1098519563674927, cross_entropy: 1.1098519563674927 +[2025-04-27 13:28:13,286][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.3984663486480713, cross_entropy: 2.3984663486480713 +[2025-04-27 13:28:16,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 2.0696990489959717, cross_entropy: 2.0696990489959717 +[2025-04-27 13:28:16,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.1332430839538574, cross_entropy: 1.1332430839538574 +[2025-04-27 13:28:18,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.8966968059539795, cross_entropy: 1.8966968059539795 +[2025-04-27 13:28:18,790][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.5103330612182617, cross_entropy: 2.5103330612182617 +[2025-04-27 13:28:20,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 0.8896931409835815, cross_entropy: 0.8896931409835815 +[2025-04-27 13:28:21,055][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 0.9615368843078613, cross_entropy: 0.9615368843078613 +[2025-04-27 13:28:23,525][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.0656771659851074, cross_entropy: 2.0656771659851074 +[2025-04-27 13:28:24,552][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 1.294682502746582, cross_entropy: 1.294682502746582 +[2025-04-27 13:28:26,109][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 0.5489689111709595, cross_entropy: 0.5489689111709595 +[2025-04-27 13:28:27,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 1.4053843021392822, cross_entropy: 1.4053843021392822 +[2025-04-27 13:28:28,722][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 3.103649139404297, cross_entropy: 3.103649139404297 +[2025-04-27 13:28:30,596][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.6567119359970093, cross_entropy: 0.6567119359970093 +[2025-04-27 13:28:31,725][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 0.8691025972366333, cross_entropy: 0.8691025972366333 +[2025-04-27 13:28:33,578][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.004868745803833, cross_entropy: 2.004868745803833 +[2025-04-27 13:28:34,243][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 2.6048645973205566, cross_entropy: 2.6048645973205566 +[2025-04-27 13:28:36,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 0.9148551821708679, cross_entropy: 0.9148551821708679 +[2025-04-27 13:28:37,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 1.7038416862487793, cross_entropy: 1.7038416862487793 +[2025-04-27 13:28:39,407][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.6572647094726562, cross_entropy: 2.6572647094726562 +[2025-04-27 13:28:39,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.403818130493164, cross_entropy: 1.403818130493164 +[2025-04-27 13:28:42,083][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.3779187202453613, cross_entropy: 2.3779187202453613 +[2025-04-27 13:28:42,371][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 0.6997674703598022, cross_entropy: 0.6997674703598022 +[2025-04-27 13:28:44,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 0.8352269530296326, cross_entropy: 0.8352269530296326 +[2025-04-27 13:28:44,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.111572742462158, cross_entropy: 2.111572742462158 +[2025-04-27 13:28:47,831][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.5266166925430298, cross_entropy: 1.5266166925430298 +[2025-04-27 13:28:48,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.3121470212936401, cross_entropy: 1.3121470212936401 +[2025-04-27 13:28:50,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.4348578453063965, cross_entropy: 2.4348578453063965 +[2025-04-27 13:28:51,142][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 0.8015638589859009, cross_entropy: 0.8015638589859009 +[2025-04-27 13:28:54,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 2.287260055541992, cross_entropy: 2.287260055541992 +[2025-04-27 13:28:54,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 0.9142976999282837, cross_entropy: 0.9142976999282837 +[2025-04-27 13:28:56,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 1.760725975036621, cross_entropy: 1.760725975036621 +[2025-04-27 13:28:56,878][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.2304482460021973, cross_entropy: 2.2304482460021973 +[2025-04-27 13:28:59,192][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 0.6476006507873535, cross_entropy: 0.6476006507873535 +[2025-04-27 13:28:59,481][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.712181806564331, cross_entropy: 2.712181806564331 +[2025-04-27 13:29:02,523][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.0988242626190186, cross_entropy: 1.0988242626190186 +[2025-04-27 13:29:02,812][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 2.8400425910949707, cross_entropy: 2.8400425910949707 +[2025-04-27 13:29:05,470][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.9616990089416504, cross_entropy: 1.9616990089416504 +[2025-04-27 13:29:05,761][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 2.6305580139160156, cross_entropy: 2.6305580139160156 +[2025-04-27 13:29:07,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.3837316036224365, cross_entropy: 1.3837316036224365 +[2025-04-27 13:29:07,882][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 2.7624969482421875, cross_entropy: 2.7624969482421875 +[2025-04-27 13:29:10,130][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.039283037185669, cross_entropy: 2.039283037185669 +[2025-04-27 13:29:10,418][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 1.6917309761047363, cross_entropy: 1.6917309761047363 +[2025-04-27 13:29:12,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.3923989534378052, cross_entropy: 1.3923989534378052 +[2025-04-27 13:29:12,467][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 0.5906453132629395, cross_entropy: 0.5906453132629395 +[2025-04-27 13:29:14,941][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 0.6918759346008301, cross_entropy: 0.6918759346008301 +[2025-04-27 13:29:15,229][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 2.534903049468994, cross_entropy: 2.534903049468994 +[2025-04-27 13:29:17,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.1790704727172852, cross_entropy: 1.1790704727172852 +[2025-04-27 13:29:18,096][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.9086016416549683, cross_entropy: 0.9086016416549683 +[2025-04-27 13:29:20,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.8687946796417236, cross_entropy: 1.8687946796417236 +[2025-04-27 13:29:20,648][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 0.7898173332214355, cross_entropy: 0.7898173332214355 +[2025-04-27 13:29:22,934][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 2.254063844680786, cross_entropy: 2.254063844680786 +[2025-04-27 13:29:24,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.7507412433624268, cross_entropy: 1.7507412433624268 +[2025-04-27 13:29:26,572][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 2.455618381500244, cross_entropy: 2.455618381500244 +[2025-04-27 13:29:27,922][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 0.6668006181716919, cross_entropy: 0.6668006181716919 +[2025-04-27 13:29:29,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 1.8939310312271118, cross_entropy: 1.8939310312271118 +[2025-04-27 13:29:30,701][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 1.5454365015029907, cross_entropy: 1.5454365015029907 +[2025-04-27 13:29:31,988][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 2.7571916580200195, cross_entropy: 2.7571916580200195 +[2025-04-27 13:29:32,895][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 1.8895065784454346, cross_entropy: 1.8895065784454346 +[2025-04-27 13:29:35,280][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 0.6434918642044067, cross_entropy: 0.6434918642044067 +[2025-04-27 13:29:35,568][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 3.017503499984741, cross_entropy: 3.017503499984741 +[2025-04-27 13:29:38,577][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 0.7366877794265747, cross_entropy: 0.7366877794265747 +[2025-04-27 13:29:38,843][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 0.8043541312217712, cross_entropy: 0.8043541312217712 +[2025-04-27 13:29:41,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 0.7268158793449402, cross_entropy: 0.7268158793449402 +[2025-04-27 13:29:41,318][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 0.6748764514923096, cross_entropy: 0.6748764514923096 +[2025-04-27 13:29:43,250][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 0.766088604927063, cross_entropy: 0.766088604927063 +[2025-04-27 13:29:43,544][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.2052569389343262, cross_entropy: 1.2052569389343262 +[2025-04-27 13:29:46,517][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 0.8017874360084534, cross_entropy: 0.8017874360084534 +[2025-04-27 13:29:46,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.381761908531189, cross_entropy: 1.381761908531189 +[2025-04-27 13:29:49,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 0.810462236404419, cross_entropy: 0.810462236404419 +[2025-04-27 13:29:49,559][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.810643196105957, cross_entropy: 0.810643196105957 +[2025-04-27 13:29:51,759][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.6307201385498047, cross_entropy: 1.6307201385498047 +[2025-04-27 13:29:52,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 0.47713324427604675, cross_entropy: 0.47713324427604675 +[2025-04-27 13:29:54,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 2.8382015228271484, cross_entropy: 2.8382015228271484 +[2025-04-27 13:29:54,822][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.453073024749756, cross_entropy: 2.453073024749756 +[2025-04-27 13:29:57,502][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 1.0226982831954956, cross_entropy: 1.0226982831954956 +[2025-04-27 13:29:57,790][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 0.9750317335128784, cross_entropy: 0.9750317335128784 +[2025-04-27 13:30:00,326][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 2.7063984870910645, cross_entropy: 2.7063984870910645 +[2025-04-27 13:30:00,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 0.4001524746417999, cross_entropy: 0.4001524746417999 +[2025-04-27 13:30:02,801][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.7968332767486572, cross_entropy: 2.7968332767486572 +[2025-04-27 13:30:03,088][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.8265525102615356, cross_entropy: 1.8265525102615356 +[2025-04-27 13:30:05,507][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 0.9588363170623779, cross_entropy: 0.9588363170623779 +[2025-04-27 13:30:05,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 2.29463791847229, cross_entropy: 2.29463791847229 +[2025-04-27 13:30:07,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 1.7903705835342407, cross_entropy: 1.7903705835342407 +[2025-04-27 13:30:08,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 2.3735146522521973, cross_entropy: 2.3735146522521973 +[2025-04-27 13:30:10,386][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 0.6475566625595093, cross_entropy: 0.6475566625595093 +[2025-04-27 13:30:11,899][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.822340726852417, cross_entropy: 1.822340726852417 +[2025-04-27 13:30:12,459][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 2.581266403198242, cross_entropy: 2.581266403198242 +[2025-04-27 13:30:14,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 0.7797808051109314, cross_entropy: 0.7797808051109314 +[2025-04-27 13:30:14,729][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.3424098491668701, cross_entropy: 1.3424098491668701 +[2025-04-27 13:30:16,741][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 2.0532851219177246, cross_entropy: 2.0532851219177246 +[2025-04-27 13:30:17,066][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 0.6156553030014038, cross_entropy: 0.6156553030014038 +[2025-04-27 13:30:18,781][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.5135539770126343, cross_entropy: 1.5135539770126343 +[2025-04-27 13:30:19,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 1.3401129245758057, cross_entropy: 1.3401129245758057 +[2025-04-27 13:30:21,783][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.0883216857910156, cross_entropy: 2.0883216857910156 +[2025-04-27 13:30:22,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 2.5650906562805176, cross_entropy: 2.5650906562805176 +[2025-04-27 13:30:23,990][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.2651937007904053, cross_entropy: 2.2651937007904053 +[2025-04-27 13:30:24,941][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.3830533027648926, cross_entropy: 1.3830533027648926 +[2025-04-27 13:30:26,319][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.8195540904998779, cross_entropy: 0.8195540904998779 +[2025-04-27 13:30:27,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.604311466217041, cross_entropy: 2.604311466217041 +[2025-04-27 13:30:29,069][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.538187265396118, cross_entropy: 2.538187265396118 +[2025-04-27 13:30:30,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 2.763068437576294, cross_entropy: 2.763068437576294 +[2025-04-27 13:30:32,118][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.0267441272735596, cross_entropy: 1.0267441272735596 +[2025-04-27 13:30:32,701][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 0.7115676403045654, cross_entropy: 0.7115676403045654 +[2025-04-27 13:30:34,808][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 2.7776401042938232, cross_entropy: 2.7776401042938232 +[2025-04-27 13:30:35,196][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.0469887256622314, cross_entropy: 2.0469887256622314 +[2025-04-27 13:30:37,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.77285099029541, cross_entropy: 2.77285099029541 +[2025-04-27 13:30:38,009][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.1402230262756348, cross_entropy: 1.1402230262756348 +[2025-04-27 13:30:40,280][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 0.48500320315361023, cross_entropy: 0.48500320315361023 +[2025-04-27 13:30:40,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 0.6283509135246277, cross_entropy: 0.6283509135246277 +[2025-04-27 13:30:42,684][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.0618948936462402, cross_entropy: 2.0618948936462402 +[2025-04-27 13:30:43,012][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 1.3830541372299194, cross_entropy: 1.3830541372299194 +[2025-04-27 13:30:45,210][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.8991820812225342, cross_entropy: 1.8991820812225342 +[2025-04-27 13:30:45,487][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.0174226760864258, cross_entropy: 1.0174226760864258 +[2025-04-27 13:30:48,131][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.6270108222961426, cross_entropy: 2.6270108222961426 +[2025-04-27 13:30:48,421][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 1.9082164764404297, cross_entropy: 1.9082164764404297 +[2025-04-27 13:30:50,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 0.6957924962043762, cross_entropy: 0.6957924962043762 +[2025-04-27 13:30:51,254][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 2.4118220806121826, cross_entropy: 2.4118220806121826 +[2025-04-27 13:30:53,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 2.8951845169067383, cross_entropy: 2.8951845169067383 +[2025-04-27 13:30:53,872][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 2.441103219985962, cross_entropy: 2.441103219985962 +[2025-04-27 13:30:56,218][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 0.7791360020637512, cross_entropy: 0.7791360020637512 +[2025-04-27 13:30:56,483][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 1.7482984066009521, cross_entropy: 1.7482984066009521 +[2025-04-27 13:30:58,972][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 2.1287918090820312, cross_entropy: 2.1287918090820312 +[2025-04-27 13:30:59,292][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.8806638717651367, cross_entropy: 1.8806638717651367 +[2025-04-27 13:31:02,495][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 1.9875690937042236, cross_entropy: 1.9875690937042236 +[2025-04-27 13:31:02,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 0.6147232055664062, cross_entropy: 0.6147232055664062 +[2025-04-27 13:31:05,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.46861732006073, cross_entropy: 1.46861732006073 +[2025-04-27 13:31:05,406][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 2.8654439449310303, cross_entropy: 2.8654439449310303 +[2025-04-27 13:31:07,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 1.405042052268982, cross_entropy: 1.405042052268982 +[2025-04-27 13:31:07,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.7056636810302734, cross_entropy: 2.7056636810302734 +[2025-04-27 13:31:10,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.5455108880996704, cross_entropy: 1.5455108880996704 +[2025-04-27 13:31:11,330][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.369168758392334, cross_entropy: 2.369168758392334 +[2025-04-27 13:31:14,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.1428074836730957, cross_entropy: 2.1428074836730957 +[2025-04-27 13:31:14,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.483959674835205, cross_entropy: 2.483959674835205 +[2025-04-27 13:31:17,441][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.5697021484375, cross_entropy: 2.5697021484375 +[2025-04-27 13:31:17,705][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.2319278717041016, cross_entropy: 2.2319278717041016 +[2025-04-27 13:31:20,573][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 0.7838265895843506, cross_entropy: 0.7838265895843506 +[2025-04-27 13:31:20,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 0.7425346374511719, cross_entropy: 0.7425346374511719 +[2025-04-27 13:31:23,463][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 2.518752336502075, cross_entropy: 2.518752336502075 +[2025-04-27 13:31:23,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.149104356765747, cross_entropy: 1.149104356765747 +[2025-04-27 13:31:25,899][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.1025400161743164, cross_entropy: 2.1025400161743164 +[2025-04-27 13:31:26,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.252774477005005, cross_entropy: 2.252774477005005 +[2025-04-27 13:31:28,092][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.459700107574463, cross_entropy: 2.459700107574463 +[2025-04-27 13:31:28,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 0.7356560230255127, cross_entropy: 0.7356560230255127 +[2025-04-27 13:31:30,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.743873357772827, cross_entropy: 2.743873357772827 +[2025-04-27 13:31:30,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 0.93820720911026, cross_entropy: 0.93820720911026 +[2025-04-27 13:31:33,163][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 2.7083702087402344, cross_entropy: 2.7083702087402344 +[2025-04-27 13:31:33,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.1745507717132568, cross_entropy: 1.1745507717132568 +[2025-04-27 13:31:35,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.6288392543792725, cross_entropy: 2.6288392543792725 +[2025-04-27 13:31:35,899][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 0.9900709986686707, cross_entropy: 0.9900709986686707 +[2025-04-27 13:31:38,260][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.416095018386841, cross_entropy: 2.416095018386841 +[2025-04-27 13:31:38,588][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 0.8140188455581665, cross_entropy: 0.8140188455581665 +[2025-04-27 13:31:40,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 2.6236369609832764, cross_entropy: 2.6236369609832764 +[2025-04-27 13:31:41,107][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 2.7034060955047607, cross_entropy: 2.7034060955047607 +[2025-04-27 13:31:43,305][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.377686023712158, cross_entropy: 2.377686023712158 +[2025-04-27 13:31:43,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 0.668511152267456, cross_entropy: 0.668511152267456 +[2025-04-27 13:31:46,549][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.585906982421875, cross_entropy: 2.585906982421875 +[2025-04-27 13:31:46,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.6496193408966064, cross_entropy: 2.6496193408966064 +[2025-04-27 13:31:49,364][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.8554683327674866, cross_entropy: 0.8554683327674866 +[2025-04-27 13:31:49,628][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.302407741546631, cross_entropy: 2.302407741546631 +[2025-04-27 13:31:53,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.5476794242858887, cross_entropy: 2.5476794242858887 +[2025-04-27 13:31:53,526][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 2.7038097381591797, cross_entropy: 2.7038097381591797 +[2025-04-27 13:31:55,825][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.5358148217201233, cross_entropy: 0.5358148217201233 +[2025-04-27 13:31:56,121][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 1.3932828903198242, cross_entropy: 1.3932828903198242 +[2025-04-27 13:31:58,364][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.9987136721611023, cross_entropy: 0.9987136721611023 +[2025-04-27 13:31:58,636][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.0620243549346924, cross_entropy: 1.0620243549346924 +[2025-04-27 13:32:01,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 2.497605085372925, cross_entropy: 2.497605085372925 +[2025-04-27 13:32:01,657][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 2.714019536972046, cross_entropy: 2.714019536972046 +[2025-04-27 13:32:04,026][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 2.457017183303833, cross_entropy: 2.457017183303833 +[2025-04-27 13:32:04,316][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 0.7267080545425415, cross_entropy: 0.7267080545425415 +[2025-04-27 13:32:07,503][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 2.2989327907562256, cross_entropy: 2.2989327907562256 +[2025-04-27 13:32:07,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 0.6115003228187561, cross_entropy: 0.6115003228187561 +[2025-04-27 13:32:09,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.7110534906387329, cross_entropy: 0.7110534906387329 +[2025-04-27 13:32:09,959][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 0.9454554319381714, cross_entropy: 0.9454554319381714 +[2025-04-27 13:32:12,072][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.794616222381592, cross_entropy: 2.794616222381592 +[2025-04-27 13:32:12,337][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 0.5488721132278442, cross_entropy: 0.5488721132278442 +[2025-04-27 13:32:14,638][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.7878973484039307, cross_entropy: 1.7878973484039307 +[2025-04-27 13:32:14,918][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.12465763092041, cross_entropy: 2.12465763092041 +[2025-04-27 13:32:18,156][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 0.7816736698150635, cross_entropy: 0.7816736698150635 +[2025-04-27 13:32:18,446][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 2.338369369506836, cross_entropy: 2.338369369506836 +[2025-04-27 13:32:20,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 0.42959192395210266, cross_entropy: 0.42959192395210266 +[2025-04-27 13:32:21,038][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 2.5672123432159424, cross_entropy: 2.5672123432159424 +[2025-04-27 13:32:24,000][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 2.3330183029174805, cross_entropy: 2.3330183029174805 +[2025-04-27 13:32:24,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.8119711875915527, cross_entropy: 1.8119711875915527 +[2025-04-27 13:32:26,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 1.1875296831130981, cross_entropy: 1.1875296831130981 +[2025-04-27 13:32:26,998][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.7564096450805664, cross_entropy: 2.7564096450805664 +[2025-04-27 13:32:29,177][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.8875322341918945, cross_entropy: 2.8875322341918945 +[2025-04-27 13:32:29,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 0.5294746160507202, cross_entropy: 0.5294746160507202 +[2025-04-27 13:32:31,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.251208782196045, cross_entropy: 1.251208782196045 +[2025-04-27 13:32:31,751][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 2.7754063606262207, cross_entropy: 2.7754063606262207 +[2025-04-27 13:32:34,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 1.6334662437438965, cross_entropy: 1.6334662437438965 +[2025-04-27 13:32:35,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 3.035400390625, cross_entropy: 3.035400390625 +[2025-04-27 13:32:37,331][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 0.7611726522445679, cross_entropy: 0.7611726522445679 +[2025-04-27 13:32:37,627][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.8538516759872437, cross_entropy: 1.8538516759872437 +[2025-04-27 13:32:40,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.2652783393859863, cross_entropy: 2.2652783393859863 +[2025-04-27 13:32:40,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 0.6474482417106628, cross_entropy: 0.6474482417106628 +[2025-04-27 13:32:42,905][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 0.5987938642501831, cross_entropy: 0.5987938642501831 +[2025-04-27 13:32:43,192][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 2.5863640308380127, cross_entropy: 2.5863640308380127 +[2025-04-27 13:32:45,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 2.3054261207580566, cross_entropy: 2.3054261207580566 +[2025-04-27 13:32:45,344][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 1.4422048330307007, cross_entropy: 1.4422048330307007 +[2025-04-27 13:32:47,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.7020025253295898, cross_entropy: 1.7020025253295898 +[2025-04-27 13:32:48,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 0.5324316024780273, cross_entropy: 0.5324316024780273 +[2025-04-27 13:32:50,019][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.3898868560791016, cross_entropy: 2.3898868560791016 +[2025-04-27 13:32:50,368][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 2.378890037536621, cross_entropy: 2.378890037536621 +[2025-04-27 13:32:52,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.4658432006835938, cross_entropy: 2.4658432006835938 +[2025-04-27 13:32:52,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 2.483248233795166, cross_entropy: 2.483248233795166 +[2025-04-27 13:32:55,957][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 1.9150872230529785, cross_entropy: 1.9150872230529785 +[2025-04-27 13:32:56,246][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 2.5607199668884277, cross_entropy: 2.5607199668884277 +[2025-04-27 13:32:58,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 2.5220627784729004, cross_entropy: 2.5220627784729004 +[2025-04-27 13:32:58,882][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.6294057369232178, cross_entropy: 2.6294057369232178 +[2025-04-27 13:33:01,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.3333446979522705, cross_entropy: 2.3333446979522705 +[2025-04-27 13:33:01,524][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 1.0707813501358032, cross_entropy: 1.0707813501358032 +[2025-04-27 13:33:03,508][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.286205530166626, cross_entropy: 1.286205530166626 +[2025-04-27 13:33:03,976][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.552544116973877, cross_entropy: 1.552544116973877 +[2025-04-27 13:33:06,449][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.2327543497085571, cross_entropy: 1.2327543497085571 +[2025-04-27 13:33:06,841][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 2.424769401550293, cross_entropy: 2.424769401550293 +[2025-04-27 13:33:09,979][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.578329563140869, cross_entropy: 2.578329563140869 +[2025-04-27 13:33:10,383][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 2.2507057189941406, cross_entropy: 2.2507057189941406 +[2025-04-27 13:33:13,173][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 2.960575819015503, cross_entropy: 2.960575819015503 +[2025-04-27 13:33:13,463][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 0.9525172710418701, cross_entropy: 0.9525172710418701 +[2025-04-27 13:33:16,061][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.8443158864974976, cross_entropy: 1.8443158864974976 +[2025-04-27 13:33:16,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.6460027694702148, cross_entropy: 1.6460027694702148 +[2025-04-27 13:33:18,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 1.3054203987121582, cross_entropy: 1.3054203987121582 +[2025-04-27 13:33:18,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.2181622982025146, cross_entropy: 1.2181622982025146 +[2025-04-27 13:33:21,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 2.4789836406707764, cross_entropy: 2.4789836406707764 +[2025-04-27 13:33:21,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 2.6477301120758057, cross_entropy: 2.6477301120758057 +[2025-04-27 13:33:23,903][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 1.6608322858810425, cross_entropy: 1.6608322858810425 +[2025-04-27 13:33:24,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 2.743077516555786, cross_entropy: 2.743077516555786 +[2025-04-27 13:33:26,650][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.8789513111114502, cross_entropy: 1.8789513111114502 +[2025-04-27 13:33:26,932][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 2.7996177673339844, cross_entropy: 2.7996177673339844 +[2025-04-27 13:33:29,170][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.0495787858963013, cross_entropy: 1.0495787858963013 +[2025-04-27 13:33:29,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 1.987037181854248, cross_entropy: 1.987037181854248 +[2025-04-27 13:33:31,578][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.9958748817443848, cross_entropy: 2.9958748817443848 +[2025-04-27 13:33:32,378][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.8842153549194336, cross_entropy: 2.8842153549194336 +[2025-04-27 13:33:34,690][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.5587947368621826, cross_entropy: 0.5587947368621826 +[2025-04-27 13:33:35,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.594515323638916, cross_entropy: 2.594515323638916 +[2025-04-27 13:33:37,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 0.659783661365509, cross_entropy: 0.659783661365509 +[2025-04-27 13:33:38,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 1.57766854763031, cross_entropy: 1.57766854763031 +[2025-04-27 13:33:40,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 0.9604662656784058, cross_entropy: 0.9604662656784058 +[2025-04-27 13:33:41,948][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 1.9074296951293945, cross_entropy: 1.9074296951293945 +[2025-04-27 13:33:43,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 0.8324639201164246, cross_entropy: 0.8324639201164246 +[2025-04-27 13:33:44,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.4330252408981323, cross_entropy: 1.4330252408981323 +[2025-04-27 13:33:45,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.409233570098877, cross_entropy: 2.409233570098877 +[2025-04-27 13:33:47,207][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 2.098896026611328, cross_entropy: 2.098896026611328 +[2025-04-27 13:33:48,346][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 1.625830054283142, cross_entropy: 1.625830054283142 +[2025-04-27 13:33:50,061][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.2207249402999878, cross_entropy: 1.2207249402999878 +[2025-04-27 13:33:51,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 0.48549413681030273, cross_entropy: 0.48549413681030273 +[2025-04-27 13:33:52,751][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 0.4643445611000061, cross_entropy: 0.4643445611000061 +[2025-04-27 13:33:54,140][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 1.0563468933105469, cross_entropy: 1.0563468933105469 +[2025-04-27 13:33:55,518][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 1.6380047798156738, cross_entropy: 1.6380047798156738 +[2025-04-27 13:33:56,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.5830068588256836, cross_entropy: 1.5830068588256836 +[2025-04-27 13:33:58,559][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 2.729860782623291, cross_entropy: 2.729860782623291 +[2025-04-27 13:34:00,175][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 1.452906608581543, cross_entropy: 1.452906608581543 +[2025-04-27 13:34:00,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.427180051803589, cross_entropy: 2.427180051803589 +[2025-04-27 13:34:02,975][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.2942752838134766, cross_entropy: 2.2942752838134766 +[2025-04-27 13:34:04,289][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.1180481910705566, cross_entropy: 2.1180481910705566 +[2025-04-27 13:34:05,505][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.6229720711708069, cross_entropy: 0.6229720711708069 +[2025-04-27 13:34:06,716][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 0.9841554760932922, cross_entropy: 0.9841554760932922 +[2025-04-27 13:34:07,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.8021371364593506, cross_entropy: 1.8021371364593506 +[2025-04-27 13:34:09,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.8417134284973145, cross_entropy: 2.8417134284973145 +[2025-04-27 13:34:10,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.8303815722465515, cross_entropy: 0.8303815722465515 +[2025-04-27 13:34:12,000][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.7817928791046143, cross_entropy: 2.7817928791046143 +[2025-04-27 13:34:13,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 2.3539795875549316, cross_entropy: 2.3539795875549316 +[2025-04-27 13:34:15,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.6579220294952393, cross_entropy: 0.6579220294952393 +[2025-04-27 13:34:15,500][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 1.8004282712936401, cross_entropy: 1.8004282712936401 +[2025-04-27 13:34:17,757][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.7400174140930176, cross_entropy: 2.7400174140930176 +[2025-04-27 13:34:18,046][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 1.11720871925354, cross_entropy: 1.11720871925354 +[2025-04-27 13:34:20,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 1.8411585092544556, cross_entropy: 1.8411585092544556 +[2025-04-27 13:34:20,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.755321741104126, cross_entropy: 2.755321741104126 +[2025-04-27 13:34:23,185][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 1.133141279220581, cross_entropy: 1.133141279220581 +[2025-04-27 13:34:23,471][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 0.9425253868103027, cross_entropy: 0.9425253868103027 +[2025-04-27 13:34:25,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 0.984407901763916, cross_entropy: 0.984407901763916 +[2025-04-27 13:34:26,040][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.5425951480865479, cross_entropy: 0.5425951480865479 +[2025-04-27 13:34:28,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 0.611443281173706, cross_entropy: 0.611443281173706 +[2025-04-27 13:34:29,063][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 1.9269670248031616, cross_entropy: 1.9269670248031616 +[2025-04-27 13:34:31,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.7796127796173096, cross_entropy: 2.7796127796173096 +[2025-04-27 13:34:31,632][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 2.253606081008911, cross_entropy: 2.253606081008911 +[2025-04-27 13:34:34,454][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.452636241912842, cross_entropy: 2.452636241912842 +[2025-04-27 13:34:34,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 0.7118961811065674, cross_entropy: 0.7118961811065674 +[2025-04-27 13:34:37,023][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 0.7939227223396301, cross_entropy: 0.7939227223396301 +[2025-04-27 13:34:37,290][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 1.4361867904663086, cross_entropy: 1.4361867904663086 +[2025-04-27 13:34:40,063][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 1.1325277090072632, cross_entropy: 1.1325277090072632 +[2025-04-27 13:34:40,349][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.6426146030426025, cross_entropy: 2.6426146030426025 +[2025-04-27 13:34:42,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 0.7353674173355103, cross_entropy: 0.7353674173355103 +[2025-04-27 13:34:42,945][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 2.7211501598358154, cross_entropy: 2.7211501598358154 +[2025-04-27 13:34:45,151][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 1.1172086000442505, cross_entropy: 1.1172086000442505 +[2025-04-27 13:34:45,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 2.946589946746826, cross_entropy: 2.946589946746826 +[2025-04-27 13:34:48,112][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 0.8425688743591309, cross_entropy: 0.8425688743591309 +[2025-04-27 13:34:48,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.009626865386963, cross_entropy: 1.009626865386963 +[2025-04-27 13:34:50,566][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.9174683094024658, cross_entropy: 1.9174683094024658 +[2025-04-27 13:34:50,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 2.4289169311523438, cross_entropy: 2.4289169311523438 +[2025-04-27 13:34:52,438][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 0.881136417388916, cross_entropy: 0.881136417388916 +[2025-04-27 13:34:52,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.1695177555084229, cross_entropy: 1.1695177555084229 +[2025-04-27 13:34:54,591][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 2.1072959899902344, cross_entropy: 2.1072959899902344 +[2025-04-27 13:34:54,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.5752809047698975, cross_entropy: 2.5752809047698975 +[2025-04-27 13:34:57,723][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.6847357749938965, cross_entropy: 2.6847357749938965 +[2025-04-27 13:34:58,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 0.7000147700309753, cross_entropy: 0.7000147700309753 +[2025-04-27 13:35:00,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 0.8968621492385864, cross_entropy: 0.8968621492385864 +[2025-04-27 13:35:00,526][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 2.423672676086426, cross_entropy: 2.423672676086426 +[2025-04-27 13:35:03,446][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.5333048701286316, cross_entropy: 0.5333048701286316 +[2025-04-27 13:35:03,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.682827949523926, cross_entropy: 2.682827949523926 +[2025-04-27 13:35:05,923][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.0073201656341553, cross_entropy: 1.0073201656341553 +[2025-04-27 13:35:06,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.4511945247650146, cross_entropy: 1.4511945247650146 +[2025-04-27 13:35:08,626][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.6757822036743164, cross_entropy: 1.6757822036743164 +[2025-04-27 13:35:08,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.1119606494903564, cross_entropy: 1.1119606494903564 +[2025-04-27 13:35:11,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 2.781769275665283, cross_entropy: 2.781769275665283 +[2025-04-27 13:35:11,845][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.1991865634918213, cross_entropy: 2.1991865634918213 +[2025-04-27 13:35:14,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 0.6121879816055298, cross_entropy: 0.6121879816055298 +[2025-04-27 13:35:14,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 1.124961018562317, cross_entropy: 1.124961018562317 +[2025-04-27 13:35:16,952][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 1.8657622337341309, cross_entropy: 1.8657622337341309 +[2025-04-27 13:35:17,248][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.7458841800689697, cross_entropy: 1.7458841800689697 +[2025-04-27 13:35:19,813][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.1726317405700684, cross_entropy: 2.1726317405700684 +[2025-04-27 13:35:20,091][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 2.7127292156219482, cross_entropy: 2.7127292156219482 +[2025-04-27 13:35:22,698][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 0.6681642532348633, cross_entropy: 0.6681642532348633 +[2025-04-27 13:35:22,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 0.7550905346870422, cross_entropy: 0.7550905346870422 +[2025-04-27 13:35:25,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.560300588607788, cross_entropy: 2.560300588607788 +[2025-04-27 13:35:25,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 1.99832284450531, cross_entropy: 1.99832284450531 +[2025-04-27 13:35:27,987][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.6484720706939697, cross_entropy: 2.6484720706939697 +[2025-04-27 13:35:28,254][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 2.042890787124634, cross_entropy: 2.042890787124634 +[2025-04-27 13:35:30,472][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.5092482566833496, cross_entropy: 1.5092482566833496 +[2025-04-27 13:35:30,763][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.5746228098869324, cross_entropy: 0.5746228098869324 +[2025-04-27 13:35:33,073][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.6894679069519043, cross_entropy: 2.6894679069519043 +[2025-04-27 13:35:33,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 1.3887438774108887, cross_entropy: 1.3887438774108887 +[2025-04-27 13:35:35,508][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 0.8925367593765259, cross_entropy: 0.8925367593765259 +[2025-04-27 13:35:35,797][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.3871276378631592, cross_entropy: 1.3871276378631592 +[2025-04-27 13:35:37,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 2.752195358276367, cross_entropy: 2.752195358276367 +[2025-04-27 13:35:38,169][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.0925724506378174, cross_entropy: 1.0925724506378174 +[2025-04-27 13:35:40,441][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 0.6433685421943665, cross_entropy: 0.6433685421943665 +[2025-04-27 13:35:40,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.119471549987793, cross_entropy: 2.119471549987793 +[2025-04-27 13:35:43,473][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.3721245527267456, cross_entropy: 1.3721245527267456 +[2025-04-27 13:35:43,759][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 2.8222246170043945, cross_entropy: 2.8222246170043945 +[2025-04-27 13:35:45,900][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.7490639686584473, cross_entropy: 2.7490639686584473 +[2025-04-27 13:35:46,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 2.717179536819458, cross_entropy: 2.717179536819458 +[2025-04-27 13:35:49,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 0.5672408938407898, cross_entropy: 0.5672408938407898 +[2025-04-27 13:35:49,732][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.7741124629974365, cross_entropy: 2.7741124629974365 +[2025-04-27 13:35:51,869][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 1.7543895244598389, cross_entropy: 1.7543895244598389 +[2025-04-27 13:35:52,156][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.519498586654663, cross_entropy: 2.519498586654663 +[2025-04-27 13:35:54,870][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 1.0392932891845703, cross_entropy: 1.0392932891845703 +[2025-04-27 13:35:55,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.4707072973251343, cross_entropy: 1.4707072973251343 +[2025-04-27 13:35:57,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 2.329220771789551, cross_entropy: 2.329220771789551 +[2025-04-27 13:35:57,433][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 2.675725221633911, cross_entropy: 2.675725221633911 +[2025-04-27 13:36:00,087][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 1.506244421005249, cross_entropy: 1.506244421005249 +[2025-04-27 13:36:00,356][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.6210870742797852, cross_entropy: 0.6210870742797852 +[2025-04-27 13:36:03,038][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 2.810513734817505, cross_entropy: 2.810513734817505 +[2025-04-27 13:36:03,314][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 2.3082759380340576, cross_entropy: 2.3082759380340576 +[2025-04-27 13:36:05,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 2.701789140701294, cross_entropy: 2.701789140701294 +[2025-04-27 13:36:05,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.345608115196228, cross_entropy: 1.345608115196228 +[2025-04-27 13:38:13,044][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.7264856100082397, cross_entropy: 1.7264856100082397 +[2025-04-27 13:38:13,045][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.1605579853057861, cross_entropy: 1.1605579853057861 +[2025-04-27 13:38:13,270][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/best_epoch.pth. +[2025-04-27 13:38:13,437][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/epoch10.pth. +[2025-04-27 13:38:13,643][BaseTrainer][INFO] - Save model: ./exp/20250427-115144/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e3aa9ae65e64ba27bda09a5b2a0622d02cfd93c --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887a11993732bc610e1fe1aba1f139ce608e5989ddba7e63575376045cab0511 +size 51764901 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..3986f9375928343644be443edae60ff9cb56cf6d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-115144/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4362e841a15c2fb999d73eb4ff6e50b84e2f5ea8822fa594771eab4043fa1d4 +size 51716259 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/README.md new file mode 100644 index 0000000000000000000000000000000000000000..089d89fc9bcee94557900e81516ad6d950dba3c4 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/README.md @@ -0,0 +1,7 @@ +system=default_seed-0 +data=birdclef2025_reshape_15s +train=birdclef2025_reshape_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.519 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..29a470b406dad7302c8520d4156724cdea562ec7 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/config.yaml @@ -0,0 +1,221 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250427-133045 + tensorboard_dir: ./tensorboard/20250427-133045 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4ec1d68c347b14637f216ddf12a134808b3831b1 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250427-133045/log/20250427-133047 + sweep: + dir: multirun/${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/20250427-133045/log/20250427-133047 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250427-133045 + - train.output.tensorboard_dir=./tensorboard/20250427-133045 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_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_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250427-133045,train.output.tensorboard_dir=./tensorboard/20250427-133045,train.resume.continue_from=,train=birdclef2025_reshape_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/20250427-133045/log/20250427-133047 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f89d5564b33d69ecd792dd441c91141e56f7f281 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250427-133045 +- train.output.tensorboard_dir=./tensorboard/20250427-133045 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..54fd890887e0c391954e65f7c48b9ae469309d4b --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/.hydra/resolved_config.yaml @@ -0,0 +1,280 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250427-133045 + tensorboard_dir: ./tensorboard/20250427-133045 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250427-133045/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250427-133045/model/epoch{epoch}.pth + last: + path: ./exp/20250427-133045/model/last.pth + best_epoch: + path: ./exp/20250427-133045/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/train.log new file mode 100644 index 0000000000000000000000000000000000000000..6ef14e4220267a9f799b99d603ee3a3065ea032e --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/log/20250427-133047/train.log @@ -0,0 +1,4280 @@ +[2025-04-27 13:31:15,196][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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250427-133045 + tensorboard_dir: ./tensorboard/20250427-133045 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-27 13:31:15,196][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) + ) +) +[2025-04-27 13:31:15,201][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-27 13:31:24,706][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.302931308746338, cross_entropy: 5.302931308746338 +[2025-04-27 13:31:25,046][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.283402442932129, cross_entropy: 5.283402442932129 +[2025-04-27 13:31:25,439][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.221212387084961, cross_entropy: 5.221212387084961 +[2025-04-27 13:31:26,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.243991851806641, cross_entropy: 5.243991851806641 +[2025-04-27 13:31:29,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.10880184173584, cross_entropy: 5.10880184173584 +[2025-04-27 13:31:30,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.089111804962158, cross_entropy: 5.089111804962158 +[2025-04-27 13:31:33,570][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.964911460876465, cross_entropy: 4.964911460876465 +[2025-04-27 13:31:34,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.069977760314941, cross_entropy: 5.069977760314941 +[2025-04-27 13:31:37,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.879222869873047, cross_entropy: 4.879222869873047 +[2025-04-27 13:31:39,175][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.800053596496582, cross_entropy: 4.800053596496582 +[2025-04-27 13:31:42,279][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.915602684020996, cross_entropy: 4.915602684020996 +[2025-04-27 13:31:43,380][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.777493953704834, cross_entropy: 4.777493953704834 +[2025-04-27 13:31:46,785][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.924043655395508, cross_entropy: 4.924043655395508 +[2025-04-27 13:31:48,636][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.761261463165283, cross_entropy: 4.761261463165283 +[2025-04-27 13:31:51,095][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.828377723693848, cross_entropy: 4.828377723693848 +[2025-04-27 13:31:52,808][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.675986289978027, cross_entropy: 4.675986289978027 +[2025-04-27 13:31:55,955][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.08528995513916, cross_entropy: 5.08528995513916 +[2025-04-27 13:31:57,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.194815635681152, cross_entropy: 5.194815635681152 +[2025-04-27 13:32:01,297][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.641742706298828, cross_entropy: 4.641742706298828 +[2025-04-27 13:32:01,946][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.871272087097168, cross_entropy: 4.871272087097168 +[2025-04-27 13:32:06,037][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.608515739440918, cross_entropy: 4.608515739440918 +[2025-04-27 13:32:06,354][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.8985066413879395, cross_entropy: 4.8985066413879395 +[2025-04-27 13:32:10,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.690770149230957, cross_entropy: 4.690770149230957 +[2025-04-27 13:32:10,798][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.739781379699707, cross_entropy: 4.739781379699707 +[2025-04-27 13:32:14,207][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.609663963317871, cross_entropy: 4.609663963317871 +[2025-04-27 13:32:14,846][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.753392696380615, cross_entropy: 4.753392696380615 +[2025-04-27 13:32:18,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.6416521072387695, cross_entropy: 4.6416521072387695 +[2025-04-27 13:32:19,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.561655044555664, cross_entropy: 4.561655044555664 +[2025-04-27 13:32:22,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.544796943664551, cross_entropy: 4.544796943664551 +[2025-04-27 13:32:24,451][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.615713119506836, cross_entropy: 4.615713119506836 +[2025-04-27 13:32:27,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.4137420654296875, cross_entropy: 4.4137420654296875 +[2025-04-27 13:32:29,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.862668514251709, cross_entropy: 4.862668514251709 +[2025-04-27 13:32:32,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.769651412963867, cross_entropy: 4.769651412963867 +[2025-04-27 13:32:34,064][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.665360927581787, cross_entropy: 4.665360927581787 +[2025-04-27 13:32:36,872][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.424201488494873, cross_entropy: 4.424201488494873 +[2025-04-27 13:32:38,806][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.285747528076172, cross_entropy: 4.285747528076172 +[2025-04-27 13:32:41,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.430129528045654, cross_entropy: 4.430129528045654 +[2025-04-27 13:32:43,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.288839340209961, cross_entropy: 4.288839340209961 +[2025-04-27 13:32:46,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.798823356628418, cross_entropy: 4.798823356628418 +[2025-04-27 13:32:48,950][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.75117826461792, cross_entropy: 4.75117826461792 +[2025-04-27 13:32:50,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.5886030197143555, cross_entropy: 4.5886030197143555 +[2025-04-27 13:32:53,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.310768127441406, cross_entropy: 4.310768127441406 +[2025-04-27 13:32:54,489][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.330470085144043, cross_entropy: 4.330470085144043 +[2025-04-27 13:32:56,798][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.540019512176514, cross_entropy: 4.540019512176514 +[2025-04-27 13:32:58,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.387624263763428, cross_entropy: 4.387624263763428 +[2025-04-27 13:33:01,924][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.100510597229004, cross_entropy: 4.100510597229004 +[2025-04-27 13:33:03,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.558426856994629, cross_entropy: 4.558426856994629 +[2025-04-27 13:33:06,718][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.289536476135254, cross_entropy: 4.289536476135254 +[2025-04-27 13:33:09,186][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.50651216506958, cross_entropy: 4.50651216506958 +[2025-04-27 13:33:10,471][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.345376491546631, cross_entropy: 4.345376491546631 +[2025-04-27 13:33:13,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.000014305114746, cross_entropy: 4.000014305114746 +[2025-04-27 13:33:14,667][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.172469139099121, cross_entropy: 4.172469139099121 +[2025-04-27 13:33:18,251][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.190013408660889, cross_entropy: 4.190013408660889 +[2025-04-27 13:33:19,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.274273872375488, cross_entropy: 4.274273872375488 +[2025-04-27 13:33:22,824][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.157064437866211, cross_entropy: 4.157064437866211 +[2025-04-27 13:33:24,317][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.283334732055664, cross_entropy: 4.283334732055664 +[2025-04-27 13:33:27,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.025481224060059, cross_entropy: 4.025481224060059 +[2025-04-27 13:33:28,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.088432312011719, cross_entropy: 4.088432312011719 +[2025-04-27 13:33:31,182][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.104621410369873, cross_entropy: 4.104621410369873 +[2025-04-27 13:33:33,077][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.049325942993164, cross_entropy: 4.049325942993164 +[2025-04-27 13:33:35,927][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.38128662109375, cross_entropy: 4.38128662109375 +[2025-04-27 13:33:37,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.2026872634887695, cross_entropy: 4.2026872634887695 +[2025-04-27 13:33:40,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.224373817443848, cross_entropy: 4.224373817443848 +[2025-04-27 13:33:41,771][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.0732927322387695, cross_entropy: 4.0732927322387695 +[2025-04-27 13:33:44,881][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.149435043334961, cross_entropy: 4.149435043334961 +[2025-04-27 13:33:45,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 3.9818854331970215, cross_entropy: 3.9818854331970215 +[2025-04-27 13:33:49,316][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 3.9844717979431152, cross_entropy: 3.9844717979431152 +[2025-04-27 13:33:51,049][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.327176094055176, cross_entropy: 4.327176094055176 +[2025-04-27 13:33:54,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.462091445922852, cross_entropy: 4.462091445922852 +[2025-04-27 13:33:55,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.099120140075684, cross_entropy: 4.099120140075684 +[2025-04-27 13:33:59,048][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.644721984863281, cross_entropy: 4.644721984863281 +[2025-04-27 13:33:59,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.091098785400391, cross_entropy: 4.091098785400391 +[2025-04-27 13:34:03,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.76473069190979, cross_entropy: 3.76473069190979 +[2025-04-27 13:34:04,110][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.380372047424316, cross_entropy: 4.380372047424316 +[2025-04-27 13:34:07,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 3.5999701023101807, cross_entropy: 3.5999701023101807 +[2025-04-27 13:34:09,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 3.6470947265625, cross_entropy: 3.6470947265625 +[2025-04-27 13:34:12,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 3.8324832916259766, cross_entropy: 3.8324832916259766 +[2025-04-27 13:34:13,727][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.318678855895996, cross_entropy: 4.318678855895996 +[2025-04-27 13:34:16,475][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.356441497802734, cross_entropy: 4.356441497802734 +[2025-04-27 13:34:17,246][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.1028900146484375, cross_entropy: 4.1028900146484375 +[2025-04-27 13:34:22,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.34660005569458, cross_entropy: 4.34660005569458 +[2025-04-27 13:34:22,688][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 3.3686270713806152, cross_entropy: 3.3686270713806152 +[2025-04-27 13:34:28,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.451018333435059, cross_entropy: 4.451018333435059 +[2025-04-27 13:34:28,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 3.8567142486572266, cross_entropy: 3.8567142486572266 +[2025-04-27 13:34:33,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 3.839803695678711, cross_entropy: 3.839803695678711 +[2025-04-27 13:34:34,137][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.577127695083618, cross_entropy: 3.577127695083618 +[2025-04-27 13:34:40,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 3.4620795249938965, cross_entropy: 3.4620795249938965 +[2025-04-27 13:34:40,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.14961051940918, cross_entropy: 4.14961051940918 +[2025-04-27 13:34:45,190][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.23989725112915, cross_entropy: 4.23989725112915 +[2025-04-27 13:34:45,503][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.7943663597106934, cross_entropy: 3.7943663597106934 +[2025-04-27 13:34:49,733][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.107390880584717, cross_entropy: 4.107390880584717 +[2025-04-27 13:34:50,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.9039788246154785, cross_entropy: 3.9039788246154785 +[2025-04-27 13:34:54,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.631485939025879, cross_entropy: 3.631485939025879 +[2025-04-27 13:34:55,256][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.1652960777282715, cross_entropy: 4.1652960777282715 +[2025-04-27 13:34:59,259][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.365070819854736, cross_entropy: 4.365070819854736 +[2025-04-27 13:34:59,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.4858217239379883, cross_entropy: 3.4858217239379883 +[2025-04-27 13:35:03,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.3240485191345215, cross_entropy: 4.3240485191345215 +[2025-04-27 13:35:04,210][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.0961170196533203, cross_entropy: 3.0961170196533203 +[2025-04-27 13:35:09,480][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 3.7768473625183105, cross_entropy: 3.7768473625183105 +[2025-04-27 13:35:09,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.433485269546509, cross_entropy: 3.433485269546509 +[2025-04-27 13:35:13,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.14349365234375, cross_entropy: 4.14349365234375 +[2025-04-27 13:35:14,120][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.504457712173462, cross_entropy: 3.504457712173462 +[2025-04-27 13:35:18,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.63169527053833, cross_entropy: 3.63169527053833 +[2025-04-27 13:35:18,772][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.234910488128662, cross_entropy: 3.234910488128662 +[2025-04-27 13:35:23,720][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.195126533508301, cross_entropy: 3.195126533508301 +[2025-04-27 13:35:24,036][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 3.727355718612671, cross_entropy: 3.727355718612671 +[2025-04-27 13:35:27,585][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.4129366874694824, cross_entropy: 3.4129366874694824 +[2025-04-27 13:35:28,044][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.31835412979126, cross_entropy: 4.31835412979126 +[2025-04-27 13:35:31,719][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.8704068660736084, cross_entropy: 3.8704068660736084 +[2025-04-27 13:35:32,164][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 3.8631432056427, cross_entropy: 3.8631432056427 +[2025-04-27 13:35:36,068][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.0261921882629395, cross_entropy: 3.0261921882629395 +[2025-04-27 13:35:36,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.486961841583252, cross_entropy: 3.486961841583252 +[2025-04-27 13:35:40,597][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 3.854468822479248, cross_entropy: 3.854468822479248 +[2025-04-27 13:35:40,910][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 3.6776695251464844, cross_entropy: 3.6776695251464844 +[2025-04-27 13:35:45,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.14103364944458, cross_entropy: 4.14103364944458 +[2025-04-27 13:35:46,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.241851806640625, cross_entropy: 3.241851806640625 +[2025-04-27 13:35:49,795][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.2585573196411133, cross_entropy: 3.2585573196411133 +[2025-04-27 13:35:50,119][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.451346397399902, cross_entropy: 4.451346397399902 +[2025-04-27 13:35:55,019][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.150120735168457, cross_entropy: 4.150120735168457 +[2025-04-27 13:35:55,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.394496917724609, cross_entropy: 4.394496917724609 +[2025-04-27 13:35:59,419][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.356297969818115, cross_entropy: 4.356297969818115 +[2025-04-27 13:35:59,751][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 3.0200815200805664, cross_entropy: 3.0200815200805664 +[2025-04-27 13:36:03,694][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.590644121170044, cross_entropy: 3.590644121170044 +[2025-04-27 13:36:04,006][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.255758285522461, cross_entropy: 3.255758285522461 +[2025-04-27 13:36:07,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.222378253936768, cross_entropy: 4.222378253936768 +[2025-04-27 13:36:07,856][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 2.9953160285949707, cross_entropy: 2.9953160285949707 +[2025-04-27 13:36:12,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.504301071166992, cross_entropy: 3.504301071166992 +[2025-04-27 13:36:12,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.182595729827881, cross_entropy: 4.182595729827881 +[2025-04-27 13:36:18,048][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 3.269897937774658, cross_entropy: 3.269897937774658 +[2025-04-27 13:36:18,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.988203525543213, cross_entropy: 3.988203525543213 +[2025-04-27 13:36:21,946][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.174319744110107, cross_entropy: 4.174319744110107 +[2025-04-27 13:36:22,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 3.7844350337982178, cross_entropy: 3.7844350337982178 +[2025-04-27 13:36:26,423][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.406554698944092, cross_entropy: 4.406554698944092 +[2025-04-27 13:36:26,753][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.066558361053467, cross_entropy: 4.066558361053467 +[2025-04-27 13:36:31,040][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 3.0299463272094727, cross_entropy: 3.0299463272094727 +[2025-04-27 13:36:31,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.5690371990203857, cross_entropy: 3.5690371990203857 +[2025-04-27 13:36:34,978][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.866461992263794, cross_entropy: 3.866461992263794 +[2025-04-27 13:36:35,295][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.191862106323242, cross_entropy: 4.191862106323242 +[2025-04-27 13:36:39,638][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 3.2020998001098633, cross_entropy: 3.2020998001098633 +[2025-04-27 13:36:39,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.330078363418579, cross_entropy: 3.330078363418579 +[2025-04-27 13:36:44,014][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 3.8242087364196777, cross_entropy: 3.8242087364196777 +[2025-04-27 13:36:44,329][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.4601993560791016, cross_entropy: 3.4601993560791016 +[2025-04-27 13:36:48,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.952100992202759, cross_entropy: 3.952100992202759 +[2025-04-27 13:36:48,698][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.140044689178467, cross_entropy: 4.140044689178467 +[2025-04-27 13:36:52,711][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 3.5021398067474365, cross_entropy: 3.5021398067474365 +[2025-04-27 13:36:53,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.4082179069519043, cross_entropy: 3.4082179069519043 +[2025-04-27 13:36:57,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 3.6237268447875977, cross_entropy: 3.6237268447875977 +[2025-04-27 13:36:57,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.6807031631469727, cross_entropy: 3.6807031631469727 +[2025-04-27 13:37:02,549][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 3.286173105239868, cross_entropy: 3.286173105239868 +[2025-04-27 13:37:02,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.210806846618652, cross_entropy: 4.210806846618652 +[2025-04-27 13:37:06,758][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.0363659858703613, cross_entropy: 3.0363659858703613 +[2025-04-27 13:37:07,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.1836955547332764, cross_entropy: 3.1836955547332764 +[2025-04-27 13:37:11,466][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 3.6962227821350098, cross_entropy: 3.6962227821350098 +[2025-04-27 13:37:11,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 2.9343979358673096, cross_entropy: 2.9343979358673096 +[2025-04-27 13:37:16,016][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.9315946102142334, cross_entropy: 3.9315946102142334 +[2025-04-27 13:37:16,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.6357526779174805, cross_entropy: 3.6357526779174805 +[2025-04-27 13:37:20,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 3.9967551231384277, cross_entropy: 3.9967551231384277 +[2025-04-27 13:37:20,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.6386170387268066, cross_entropy: 3.6386170387268066 +[2025-04-27 13:37:25,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 2.9218380451202393, cross_entropy: 2.9218380451202393 +[2025-04-27 13:37:25,826][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.6538476943969727, cross_entropy: 3.6538476943969727 +[2025-04-27 13:37:29,945][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 4.166767120361328, cross_entropy: 4.166767120361328 +[2025-04-27 13:37:30,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.0885367393493652, cross_entropy: 3.0885367393493652 +[2025-04-27 13:37:34,203][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.2577290534973145, cross_entropy: 4.2577290534973145 +[2025-04-27 13:37:34,530][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.1575088500976562, cross_entropy: 3.1575088500976562 +[2025-04-27 13:37:38,977][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.1490318775177, cross_entropy: 3.1490318775177 +[2025-04-27 13:37:39,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 3.3846259117126465, cross_entropy: 3.3846259117126465 +[2025-04-27 13:37:44,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.6239516735076904, cross_entropy: 3.6239516735076904 +[2025-04-27 13:37:44,718][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.5485081672668457, cross_entropy: 3.5485081672668457 +[2025-04-27 13:37:48,209][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.186252593994141, cross_entropy: 4.186252593994141 +[2025-04-27 13:37:48,539][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.9444823265075684, cross_entropy: 3.9444823265075684 +[2025-04-27 13:37:52,525][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 2.857171058654785, cross_entropy: 2.857171058654785 +[2025-04-27 13:37:52,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.123795747756958, cross_entropy: 3.123795747756958 +[2025-04-27 13:37:57,866][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.749697685241699, cross_entropy: 3.749697685241699 +[2025-04-27 13:37:58,180][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 3.774538516998291, cross_entropy: 3.774538516998291 +[2025-04-27 13:38:01,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.195093631744385, cross_entropy: 4.195093631744385 +[2025-04-27 13:38:02,187][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.908020496368408, cross_entropy: 3.908020496368408 +[2025-04-27 13:38:06,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 4.01859712600708, cross_entropy: 4.01859712600708 +[2025-04-27 13:38:06,759][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.9926297664642334, cross_entropy: 3.9926297664642334 +[2025-04-27 13:38:11,151][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.4543890953063965, cross_entropy: 3.4543890953063965 +[2025-04-27 13:38:11,465][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.6206986904144287, cross_entropy: 3.6206986904144287 +[2025-04-27 13:38:16,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 3.426746368408203, cross_entropy: 3.426746368408203 +[2025-04-27 13:38:16,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.8681933879852295, cross_entropy: 3.8681933879852295 +[2025-04-27 13:38:20,901][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 2.9703829288482666, cross_entropy: 2.9703829288482666 +[2025-04-27 13:38:21,213][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.0720367431640625, cross_entropy: 4.0720367431640625 +[2025-04-27 13:38:25,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.554257392883301, cross_entropy: 3.554257392883301 +[2025-04-27 13:38:26,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.0502634048461914, cross_entropy: 3.0502634048461914 +[2025-04-27 13:38:30,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.284721612930298, cross_entropy: 3.284721612930298 +[2025-04-27 13:38:31,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.2976393699645996, cross_entropy: 3.2976393699645996 +[2025-04-27 13:38:36,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 2.8157851696014404, cross_entropy: 2.8157851696014404 +[2025-04-27 13:38:36,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.851520538330078, cross_entropy: 3.851520538330078 +[2025-04-27 13:38:41,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 2.561863899230957, cross_entropy: 2.561863899230957 +[2025-04-27 13:38:41,386][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.1880524158477783, cross_entropy: 3.1880524158477783 +[2025-04-27 13:38:46,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 3.236023187637329, cross_entropy: 3.236023187637329 +[2025-04-27 13:38:46,428][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 4.054065704345703, cross_entropy: 4.054065704345703 +[2025-04-27 13:38:51,884][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 2.68894100189209, cross_entropy: 2.68894100189209 +[2025-04-27 13:38:52,196][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.2490968704223633, cross_entropy: 3.2490968704223633 +[2025-04-27 13:38:56,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.938523292541504, cross_entropy: 3.938523292541504 +[2025-04-27 13:38:56,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 2.4491915702819824, cross_entropy: 2.4491915702819824 +[2025-04-27 13:38:59,660][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.538424491882324, cross_entropy: 3.538424491882324 +[2025-04-27 13:38:59,987][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.1531171798706055, cross_entropy: 3.1531171798706055 +[2025-04-27 13:39:03,469][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 2.8006176948547363, cross_entropy: 2.8006176948547363 +[2025-04-27 13:39:03,797][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 2.9584906101226807, cross_entropy: 2.9584906101226807 +[2025-04-27 13:39:07,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.6414737701416016, cross_entropy: 3.6414737701416016 +[2025-04-27 13:39:07,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 2.708704710006714, cross_entropy: 2.708704710006714 +[2025-04-27 13:39:12,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.0371012687683105, cross_entropy: 4.0371012687683105 +[2025-04-27 13:39:12,762][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.0148472785949707, cross_entropy: 3.0148472785949707 +[2025-04-27 13:39:16,248][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 2.8751754760742188, cross_entropy: 2.8751754760742188 +[2025-04-27 13:39:16,572][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.776231050491333, cross_entropy: 3.776231050491333 +[2025-04-27 13:39:21,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 2.4097533226013184, cross_entropy: 2.4097533226013184 +[2025-04-27 13:39:21,994][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.7515032291412354, cross_entropy: 3.7515032291412354 +[2025-04-27 13:39:25,477][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.766310453414917, cross_entropy: 3.766310453414917 +[2025-04-27 13:39:25,818][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.7402267456054688, cross_entropy: 3.7402267456054688 +[2025-04-27 13:39:29,000][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.8562827110290527, cross_entropy: 3.8562827110290527 +[2025-04-27 13:39:29,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 2.471611976623535, cross_entropy: 2.471611976623535 +[2025-04-27 13:39:33,517][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.0853254795074463, cross_entropy: 3.0853254795074463 +[2025-04-27 13:39:33,830][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 2.8965299129486084, cross_entropy: 2.8965299129486084 +[2025-04-27 13:39:37,733][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.890556812286377, cross_entropy: 3.890556812286377 +[2025-04-27 13:39:38,048][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 2.954820156097412, cross_entropy: 2.954820156097412 +[2025-04-27 13:39:42,197][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.3400120735168457, cross_entropy: 3.3400120735168457 +[2025-04-27 13:39:42,516][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.811772346496582, cross_entropy: 3.811772346496582 +[2025-04-27 13:39:46,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 2.9315245151519775, cross_entropy: 2.9315245151519775 +[2025-04-27 13:39:47,194][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.085028171539307, cross_entropy: 4.085028171539307 +[2025-04-27 13:39:51,772][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.5042264461517334, cross_entropy: 3.5042264461517334 +[2025-04-27 13:39:52,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 2.845919370651245, cross_entropy: 2.845919370651245 +[2025-04-27 13:39:56,981][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 2.7260866165161133, cross_entropy: 2.7260866165161133 +[2025-04-27 13:39:57,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.4992313385009766, cross_entropy: 3.4992313385009766 +[2025-04-27 13:40:01,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 2.9832119941711426, cross_entropy: 2.9832119941711426 +[2025-04-27 13:40:02,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 2.2603745460510254, cross_entropy: 2.2603745460510254 +[2025-04-27 13:40:05,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 2.574458599090576, cross_entropy: 2.574458599090576 +[2025-04-27 13:40:06,229][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 2.957221031188965, cross_entropy: 2.957221031188965 +[2025-04-27 13:40:11,285][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 2.5116748809814453, cross_entropy: 2.5116748809814453 +[2025-04-27 13:40:11,602][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 2.9445133209228516, cross_entropy: 2.9445133209228516 +[2025-04-27 13:40:16,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.752735137939453, cross_entropy: 2.752735137939453 +[2025-04-27 13:40:16,677][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 2.84263277053833, cross_entropy: 2.84263277053833 +[2025-04-27 13:40:21,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.1305596828460693, cross_entropy: 3.1305596828460693 +[2025-04-27 13:40:21,608][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.2944185733795166, cross_entropy: 3.2944185733795166 +[2025-04-27 13:40:26,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 2.1324806213378906, cross_entropy: 2.1324806213378906 +[2025-04-27 13:40:26,946][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.581841468811035, cross_entropy: 2.581841468811035 +[2025-04-27 13:40:32,554][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 4.046961307525635, cross_entropy: 4.046961307525635 +[2025-04-27 13:40:32,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 2.477193593978882, cross_entropy: 2.477193593978882 +[2025-04-27 13:40:37,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.303337335586548, cross_entropy: 3.303337335586548 +[2025-04-27 13:40:38,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.821089267730713, cross_entropy: 2.821089267730713 +[2025-04-27 13:40:42,442][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 2.879788398742676, cross_entropy: 2.879788398742676 +[2025-04-27 13:40:42,774][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 2.757972240447998, cross_entropy: 2.757972240447998 +[2025-04-27 13:40:47,566][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 2.8622636795043945, cross_entropy: 2.8622636795043945 +[2025-04-27 13:40:47,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 4.172891616821289, cross_entropy: 4.172891616821289 +[2025-04-27 13:40:52,526][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 2.530501365661621, cross_entropy: 2.530501365661621 +[2025-04-27 13:40:52,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 4.133098602294922, cross_entropy: 4.133098602294922 +[2025-04-27 13:40:56,739][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.9907257556915283, cross_entropy: 3.9907257556915283 +[2025-04-27 13:40:57,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 4.005460739135742, cross_entropy: 4.005460739135742 +[2025-04-27 13:41:01,336][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.296095848083496, cross_entropy: 3.296095848083496 +[2025-04-27 13:41:01,654][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 2.9710428714752197, cross_entropy: 2.9710428714752197 +[2025-04-27 13:41:05,743][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.69443941116333, cross_entropy: 3.69443941116333 +[2025-04-27 13:41:06,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.7821264266967773, cross_entropy: 2.7821264266967773 +[2025-04-27 13:41:11,069][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.683189630508423, cross_entropy: 3.683189630508423 +[2025-04-27 13:41:11,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.109163284301758, cross_entropy: 3.109163284301758 +[2025-04-27 13:41:16,294][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 3.4964070320129395, cross_entropy: 3.4964070320129395 +[2025-04-27 13:41:16,610][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 2.572505235671997, cross_entropy: 2.572505235671997 +[2025-04-27 13:41:21,307][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 2.969285011291504, cross_entropy: 2.969285011291504 +[2025-04-27 13:41:21,618][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 2.394414186477661, cross_entropy: 2.394414186477661 +[2025-04-27 13:41:26,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.693692207336426, cross_entropy: 2.693692207336426 +[2025-04-27 13:41:26,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.9232892990112305, cross_entropy: 2.9232892990112305 +[2025-04-27 13:41:30,762][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 2.635817527770996, cross_entropy: 2.635817527770996 +[2025-04-27 13:41:31,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.6626534461975098, cross_entropy: 3.6626534461975098 +[2025-04-27 13:41:35,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 2.495910167694092, cross_entropy: 2.495910167694092 +[2025-04-27 13:41:35,985][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.466029644012451, cross_entropy: 3.466029644012451 +[2025-04-27 13:41:39,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 4.165258884429932, cross_entropy: 4.165258884429932 +[2025-04-27 13:41:39,656][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 3.0778186321258545, cross_entropy: 3.0778186321258545 +[2025-04-27 13:41:43,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 2.4327468872070312, cross_entropy: 2.4327468872070312 +[2025-04-27 13:41:44,128][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.6094045639038086, cross_entropy: 3.6094045639038086 +[2025-04-27 13:41:47,859][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.7327911853790283, cross_entropy: 3.7327911853790283 +[2025-04-27 13:41:48,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.921938896179199, cross_entropy: 2.921938896179199 +[2025-04-27 13:41:53,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.0603747367858887, cross_entropy: 3.0603747367858887 +[2025-04-27 13:41:53,918][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.717038631439209, cross_entropy: 3.717038631439209 +[2025-04-27 13:41:58,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.8165926933288574, cross_entropy: 2.8165926933288574 +[2025-04-27 13:41:58,772][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 2.864665985107422, cross_entropy: 2.864665985107422 +[2025-04-27 13:42:03,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 2.8568646907806396, cross_entropy: 2.8568646907806396 +[2025-04-27 13:42:03,399][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 3.3993113040924072, cross_entropy: 3.3993113040924072 +[2025-04-27 13:42:07,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.613560676574707, cross_entropy: 2.613560676574707 +[2025-04-27 13:42:07,740][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 4.305577278137207, cross_entropy: 4.305577278137207 +[2025-04-27 13:42:11,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.468280076980591, cross_entropy: 2.468280076980591 +[2025-04-27 13:42:11,799][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 2.8367767333984375, cross_entropy: 2.8367767333984375 +[2025-04-27 13:42:15,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.375152587890625, cross_entropy: 3.375152587890625 +[2025-04-27 13:42:16,062][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.320272207260132, cross_entropy: 2.320272207260132 +[2025-04-27 13:42:19,748][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.19746732711792, cross_entropy: 2.19746732711792 +[2025-04-27 13:42:20,059][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.775486469268799, cross_entropy: 3.775486469268799 +[2025-04-27 13:42:24,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 2.450624704360962, cross_entropy: 2.450624704360962 +[2025-04-27 13:42:24,792][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.09464693069458, cross_entropy: 3.09464693069458 +[2025-04-27 13:42:29,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 2.610835552215576, cross_entropy: 2.610835552215576 +[2025-04-27 13:42:29,728][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.7327260971069336, cross_entropy: 2.7327260971069336 +[2025-04-27 13:42:33,766][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.6818904876708984, cross_entropy: 3.6818904876708984 +[2025-04-27 13:42:34,093][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.7756619453430176, cross_entropy: 3.7756619453430176 +[2025-04-27 13:42:37,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 2.3401196002960205, cross_entropy: 2.3401196002960205 +[2025-04-27 13:42:37,800][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.875964879989624, cross_entropy: 2.875964879989624 +[2025-04-27 13:42:43,041][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.900951385498047, cross_entropy: 2.900951385498047 +[2025-04-27 13:42:43,355][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.035515785217285, cross_entropy: 3.035515785217285 +[2025-04-27 13:42:48,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 2.406815528869629, cross_entropy: 2.406815528869629 +[2025-04-27 13:42:48,389][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.6424636840820312, cross_entropy: 3.6424636840820312 +[2025-04-27 13:42:53,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.972475290298462, cross_entropy: 2.972475290298462 +[2025-04-27 13:42:53,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.4414467811584473, cross_entropy: 3.4414467811584473 +[2025-04-27 13:42:59,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.9037859439849854, cross_entropy: 2.9037859439849854 +[2025-04-27 13:42:59,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 2.9887654781341553, cross_entropy: 2.9887654781341553 +[2025-04-27 13:43:04,044][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.4128098487854004, cross_entropy: 2.4128098487854004 +[2025-04-27 13:43:04,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 3.0167465209960938, cross_entropy: 3.0167465209960938 +[2025-04-27 13:43:08,968][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 1.8123023509979248, cross_entropy: 1.8123023509979248 +[2025-04-27 13:43:09,302][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 4.11610746383667, cross_entropy: 4.11610746383667 +[2025-04-27 13:43:13,241][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 2.3858814239501953, cross_entropy: 2.3858814239501953 +[2025-04-27 13:43:13,565][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.6910970211029053, cross_entropy: 3.6910970211029053 +[2025-04-27 13:43:18,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.3642234802246094, cross_entropy: 3.3642234802246094 +[2025-04-27 13:43:18,492][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.1600327491760254, cross_entropy: 2.1600327491760254 +[2025-04-27 13:43:22,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.5141079425811768, cross_entropy: 2.5141079425811768 +[2025-04-27 13:43:23,208][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.1289286613464355, cross_entropy: 3.1289286613464355 +[2025-04-27 13:43:27,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 4.016108989715576, cross_entropy: 4.016108989715576 +[2025-04-27 13:43:27,928][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 2.1184840202331543, cross_entropy: 2.1184840202331543 +[2025-04-27 13:43:32,798][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.989598512649536, cross_entropy: 2.989598512649536 +[2025-04-27 13:43:33,129][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.649752616882324, cross_entropy: 3.649752616882324 +[2025-04-27 13:43:38,011][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.8157217502593994, cross_entropy: 2.8157217502593994 +[2025-04-27 13:43:38,325][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.6002745628356934, cross_entropy: 3.6002745628356934 +[2025-04-27 13:43:43,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 1.9127132892608643, cross_entropy: 1.9127132892608643 +[2025-04-27 13:43:43,389][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.0803117752075195, cross_entropy: 2.0803117752075195 +[2025-04-27 13:43:48,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 2.2029688358306885, cross_entropy: 2.2029688358306885 +[2025-04-27 13:43:48,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 2.801661968231201, cross_entropy: 2.801661968231201 +[2025-04-27 13:43:53,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.633535385131836, cross_entropy: 3.633535385131836 +[2025-04-27 13:43:53,350][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 1.9984526634216309, cross_entropy: 1.9984526634216309 +[2025-04-27 13:43:58,130][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.7817721366882324, cross_entropy: 3.7817721366882324 +[2025-04-27 13:43:58,442][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.086183547973633, cross_entropy: 3.086183547973633 +[2025-04-27 13:44:03,032][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.558668613433838, cross_entropy: 2.558668613433838 +[2025-04-27 13:44:03,358][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 1.8958349227905273, cross_entropy: 1.8958349227905273 +[2025-04-27 13:44:07,589][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 2.7740187644958496, cross_entropy: 2.7740187644958496 +[2025-04-27 13:44:07,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 2.536965847015381, cross_entropy: 2.536965847015381 +[2025-04-27 13:44:11,671][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 2.548593044281006, cross_entropy: 2.548593044281006 +[2025-04-27 13:44:11,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.744377613067627, cross_entropy: 3.744377613067627 +[2025-04-27 13:44:15,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 2.8832297325134277, cross_entropy: 2.8832297325134277 +[2025-04-27 13:44:16,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.284987688064575, cross_entropy: 3.284987688064575 +[2025-04-27 13:44:20,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.208160877227783, cross_entropy: 2.208160877227783 +[2025-04-27 13:44:20,938][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.1357226371765137, cross_entropy: 2.1357226371765137 +[2025-04-27 13:44:25,522][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 2.471238613128662, cross_entropy: 2.471238613128662 +[2025-04-27 13:44:25,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 3.77980375289917, cross_entropy: 3.77980375289917 +[2025-04-27 13:44:29,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.2792015075683594, cross_entropy: 2.2792015075683594 +[2025-04-27 13:44:30,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.1489951610565186, cross_entropy: 3.1489951610565186 +[2025-04-27 13:44:34,338][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.4329891204833984, cross_entropy: 2.4329891204833984 +[2025-04-27 13:44:34,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.7362427711486816, cross_entropy: 3.7362427711486816 +[2025-04-27 13:44:39,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 4.157189846038818, cross_entropy: 4.157189846038818 +[2025-04-27 13:44:39,828][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.363091468811035, cross_entropy: 2.363091468811035 +[2025-04-27 13:44:42,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 2.602386951446533, cross_entropy: 2.602386951446533 +[2025-04-27 13:44:43,229][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 4.057103633880615, cross_entropy: 4.057103633880615 +[2025-04-27 13:44:46,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.8995959758758545, cross_entropy: 2.8995959758758545 +[2025-04-27 13:44:46,867][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.8866758346557617, cross_entropy: 2.8866758346557617 +[2025-04-27 13:44:50,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 3.3928427696228027, cross_entropy: 3.3928427696228027 +[2025-04-27 13:44:51,189][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.0262529850006104, cross_entropy: 2.0262529850006104 +[2025-04-27 13:44:54,732][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 3.28285551071167, cross_entropy: 3.28285551071167 +[2025-04-27 13:44:55,061][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.5666537284851074, cross_entropy: 2.5666537284851074 +[2025-04-27 13:44:59,039][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.551514148712158, cross_entropy: 3.551514148712158 +[2025-04-27 13:44:59,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 3.2891433238983154, cross_entropy: 3.2891433238983154 +[2025-04-27 13:45:03,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 2.097123146057129, cross_entropy: 2.097123146057129 +[2025-04-27 13:45:06,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 2.25830340385437, cross_entropy: 2.25830340385437 +[2025-04-27 13:48:45,451][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.5667724609375, cross_entropy: 3.5667724609375 +[2025-04-27 13:48:45,451][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.2269914150238037, cross_entropy: 2.2269914150238037 +[2025-04-27 13:48:45,616][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 13:48:45,773][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch1.pth. +[2025-04-27 13:48:45,935][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 13:48:50,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.6913833618164062, cross_entropy: 3.6913833618164062 +[2025-04-27 13:48:50,841][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.1574649810791016, cross_entropy: 2.1574649810791016 +[2025-04-27 13:48:54,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 4.002132892608643, cross_entropy: 4.002132892608643 +[2025-04-27 13:48:54,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 1.9596394300460815, cross_entropy: 1.9596394300460815 +[2025-04-27 13:48:57,595][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.2493207454681396, cross_entropy: 2.2493207454681396 +[2025-04-27 13:48:57,910][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 4.016110420227051, cross_entropy: 4.016110420227051 +[2025-04-27 13:49:01,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.492263078689575, cross_entropy: 2.492263078689575 +[2025-04-27 13:49:01,413][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 1.9091796875, cross_entropy: 1.9091796875 +[2025-04-27 13:49:04,173][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.4481115341186523, cross_entropy: 2.4481115341186523 +[2025-04-27 13:49:04,485][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.2620441913604736, cross_entropy: 2.2620441913604736 +[2025-04-27 13:49:07,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.095193862915039, cross_entropy: 2.095193862915039 +[2025-04-27 13:49:07,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.643486499786377, cross_entropy: 3.643486499786377 +[2025-04-27 13:49:11,231][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.5530834197998047, cross_entropy: 3.5530834197998047 +[2025-04-27 13:49:11,566][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.026899814605713, cross_entropy: 2.026899814605713 +[2025-04-27 13:49:15,318][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 2.6595897674560547, cross_entropy: 2.6595897674560547 +[2025-04-27 13:49:15,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 3.536377191543579, cross_entropy: 3.536377191543579 +[2025-04-27 13:49:19,018][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.686699867248535, cross_entropy: 2.686699867248535 +[2025-04-27 13:49:19,354][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.2666733264923096, cross_entropy: 2.2666733264923096 +[2025-04-27 13:49:22,990][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.832547187805176, cross_entropy: 3.832547187805176 +[2025-04-27 13:49:23,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 1.757941722869873, cross_entropy: 1.757941722869873 +[2025-04-27 13:49:26,076][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.0374910831451416, cross_entropy: 3.0374910831451416 +[2025-04-27 13:49:26,387][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 2.1273884773254395, cross_entropy: 2.1273884773254395 +[2025-04-27 13:49:29,654][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.1990816593170166, cross_entropy: 3.1990816593170166 +[2025-04-27 13:49:29,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.526038646697998, cross_entropy: 3.526038646697998 +[2025-04-27 13:49:32,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.7373857498168945, cross_entropy: 3.7373857498168945 +[2025-04-27 13:49:33,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.0720667839050293, cross_entropy: 2.0720667839050293 +[2025-04-27 13:49:36,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.585465431213379, cross_entropy: 3.585465431213379 +[2025-04-27 13:49:36,691][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 3.1658926010131836, cross_entropy: 3.1658926010131836 +[2025-04-27 13:49:39,801][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 3.6182827949523926, cross_entropy: 3.6182827949523926 +[2025-04-27 13:49:40,131][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 2.162109851837158, cross_entropy: 2.162109851837158 +[2025-04-27 13:49:43,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.34106707572937, cross_entropy: 2.34106707572937 +[2025-04-27 13:49:43,476][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.438049793243408, cross_entropy: 2.438049793243408 +[2025-04-27 13:49:46,464][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.242140293121338, cross_entropy: 2.242140293121338 +[2025-04-27 13:49:46,796][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 2.5990066528320312, cross_entropy: 2.5990066528320312 +[2025-04-27 13:49:49,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.0887069702148438, cross_entropy: 2.0887069702148438 +[2025-04-27 13:49:50,299][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.5885508060455322, cross_entropy: 3.5885508060455322 +[2025-04-27 13:49:54,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.5748229026794434, cross_entropy: 3.5748229026794434 +[2025-04-27 13:49:54,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 1.7926709651947021, cross_entropy: 1.7926709651947021 +[2025-04-27 13:49:59,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 2.826517105102539, cross_entropy: 2.826517105102539 +[2025-04-27 13:49:59,653][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 1.98903226852417, cross_entropy: 1.98903226852417 +[2025-04-27 13:50:02,788][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.428896427154541, cross_entropy: 3.428896427154541 +[2025-04-27 13:50:03,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.0400750637054443, cross_entropy: 2.0400750637054443 +[2025-04-27 13:50:05,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.0901103019714355, cross_entropy: 3.0901103019714355 +[2025-04-27 13:50:06,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.567861557006836, cross_entropy: 2.567861557006836 +[2025-04-27 13:50:09,743][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.837740182876587, cross_entropy: 3.837740182876587 +[2025-04-27 13:50:10,073][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.039372682571411, cross_entropy: 3.039372682571411 +[2025-04-27 13:50:13,702][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 2.1591978073120117, cross_entropy: 2.1591978073120117 +[2025-04-27 13:50:14,038][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 2.199124813079834, cross_entropy: 2.199124813079834 +[2025-04-27 13:50:17,261][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.407444953918457, cross_entropy: 3.407444953918457 +[2025-04-27 13:50:17,594][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 3.223141670227051, cross_entropy: 3.223141670227051 +[2025-04-27 13:50:20,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.539238214492798, cross_entropy: 3.539238214492798 +[2025-04-27 13:50:21,146][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 2.6287851333618164, cross_entropy: 2.6287851333618164 +[2025-04-27 13:50:24,917][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 2.3661723136901855, cross_entropy: 2.3661723136901855 +[2025-04-27 13:50:25,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.534130573272705, cross_entropy: 3.534130573272705 +[2025-04-27 13:50:28,716][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 2.2812998294830322, cross_entropy: 2.2812998294830322 +[2025-04-27 13:50:29,047][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 1.913400411605835, cross_entropy: 1.913400411605835 +[2025-04-27 13:50:32,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 3.2776169776916504, cross_entropy: 3.2776169776916504 +[2025-04-27 13:50:32,458][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.688197612762451, cross_entropy: 2.688197612762451 +[2025-04-27 13:50:35,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.449347972869873, cross_entropy: 3.449347972869873 +[2025-04-27 13:50:36,220][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.4173901081085205, cross_entropy: 3.4173901081085205 +[2025-04-27 13:50:39,362][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.4263198375701904, cross_entropy: 3.4263198375701904 +[2025-04-27 13:50:39,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.7972218990325928, cross_entropy: 3.7972218990325928 +[2025-04-27 13:50:43,097][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.315703868865967, cross_entropy: 2.315703868865967 +[2025-04-27 13:50:43,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 1.7098979949951172, cross_entropy: 1.7098979949951172 +[2025-04-27 13:50:46,588][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 2.464414119720459, cross_entropy: 2.464414119720459 +[2025-04-27 13:50:46,919][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.7455408573150635, cross_entropy: 3.7455408573150635 +[2025-04-27 13:50:50,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 3.732555866241455, cross_entropy: 3.732555866241455 +[2025-04-27 13:50:50,974][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 1.9313273429870605, cross_entropy: 1.9313273429870605 +[2025-04-27 13:50:53,816][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.9739251136779785, cross_entropy: 2.9739251136779785 +[2025-04-27 13:50:54,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.6298530101776123, cross_entropy: 3.6298530101776123 +[2025-04-27 13:50:57,189][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.0224404335021973, cross_entropy: 3.0224404335021973 +[2025-04-27 13:50:57,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.1463677883148193, cross_entropy: 2.1463677883148193 +[2025-04-27 13:51:00,717][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.669999122619629, cross_entropy: 3.669999122619629 +[2025-04-27 13:51:01,062][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 1.88394033908844, cross_entropy: 1.88394033908844 +[2025-04-27 13:51:04,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.5235066413879395, cross_entropy: 2.5235066413879395 +[2025-04-27 13:51:05,230][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 3.592940092086792, cross_entropy: 3.592940092086792 +[2025-04-27 13:51:07,966][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 1.997096061706543, cross_entropy: 1.997096061706543 +[2025-04-27 13:51:08,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 1.8696975708007812, cross_entropy: 1.8696975708007812 +[2025-04-27 13:51:11,566][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.7344226837158203, cross_entropy: 3.7344226837158203 +[2025-04-27 13:51:11,903][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 2.341013193130493, cross_entropy: 2.341013193130493 +[2025-04-27 13:51:15,340][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 3.246805191040039, cross_entropy: 3.246805191040039 +[2025-04-27 13:51:15,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.416625738143921, cross_entropy: 3.416625738143921 +[2025-04-27 13:51:19,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.3608269691467285, cross_entropy: 2.3608269691467285 +[2025-04-27 13:51:19,931][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.297693967819214, cross_entropy: 3.297693967819214 +[2025-04-27 13:51:24,366][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.366934061050415, cross_entropy: 3.366934061050415 +[2025-04-27 13:51:24,704][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 3.644087791442871, cross_entropy: 3.644087791442871 +[2025-04-27 13:51:28,564][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.647210121154785, cross_entropy: 3.647210121154785 +[2025-04-27 13:51:28,878][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.4748122692108154, cross_entropy: 3.4748122692108154 +[2025-04-27 13:51:32,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.2388081550598145, cross_entropy: 3.2388081550598145 +[2025-04-27 13:51:32,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 3.543205499649048, cross_entropy: 3.543205499649048 +[2025-04-27 13:51:35,828][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.7561309337615967, cross_entropy: 3.7561309337615967 +[2025-04-27 13:51:36,163][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.5544958114624023, cross_entropy: 3.5544958114624023 +[2025-04-27 13:51:39,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 2.2193121910095215, cross_entropy: 2.2193121910095215 +[2025-04-27 13:51:39,994][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 3.1163926124572754, cross_entropy: 3.1163926124572754 +[2025-04-27 13:51:42,651][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.606673002243042, cross_entropy: 2.606673002243042 +[2025-04-27 13:51:42,991][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.268153429031372, cross_entropy: 2.268153429031372 +[2025-04-27 13:51:46,293][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.3393208980560303, cross_entropy: 3.3393208980560303 +[2025-04-27 13:51:46,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.211576461791992, cross_entropy: 2.211576461791992 +[2025-04-27 13:51:49,416][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 2.291261672973633, cross_entropy: 2.291261672973633 +[2025-04-27 13:51:49,753][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 2.5733840465545654, cross_entropy: 2.5733840465545654 +[2025-04-27 13:51:52,814][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.0445094108581543, cross_entropy: 3.0445094108581543 +[2025-04-27 13:51:53,153][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.452699661254883, cross_entropy: 3.452699661254883 +[2025-04-27 13:51:56,150][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.0702223777770996, cross_entropy: 2.0702223777770996 +[2025-04-27 13:51:56,491][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.954163074493408, cross_entropy: 2.954163074493408 +[2025-04-27 13:51:59,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 2.069674491882324, cross_entropy: 2.069674491882324 +[2025-04-27 13:51:59,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 2.94399356842041, cross_entropy: 2.94399356842041 +[2025-04-27 13:52:04,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.536397933959961, cross_entropy: 2.536397933959961 +[2025-04-27 13:52:04,706][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.136662483215332, cross_entropy: 3.136662483215332 +[2025-04-27 13:52:07,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.4908125400543213, cross_entropy: 3.4908125400543213 +[2025-04-27 13:52:08,153][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 1.9879318475723267, cross_entropy: 1.9879318475723267 +[2025-04-27 13:52:11,099][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.8323912620544434, cross_entropy: 2.8323912620544434 +[2025-04-27 13:52:11,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.2120819091796875, cross_entropy: 3.2120819091796875 +[2025-04-27 13:52:14,755][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 3.4816784858703613, cross_entropy: 3.4816784858703613 +[2025-04-27 13:52:15,066][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.1481106281280518, cross_entropy: 3.1481106281280518 +[2025-04-27 13:52:18,063][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.682542562484741, cross_entropy: 3.682542562484741 +[2025-04-27 13:52:18,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.330256700515747, cross_entropy: 3.330256700515747 +[2025-04-27 13:52:21,576][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.0903563499450684, cross_entropy: 2.0903563499450684 +[2025-04-27 13:52:21,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.254662036895752, cross_entropy: 3.254662036895752 +[2025-04-27 13:52:25,218][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 1.7261810302734375, cross_entropy: 1.7261810302734375 +[2025-04-27 13:52:25,531][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 2.438932180404663, cross_entropy: 2.438932180404663 +[2025-04-27 13:52:28,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 1.8850338459014893, cross_entropy: 1.8850338459014893 +[2025-04-27 13:52:29,225][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.0515120029449463, cross_entropy: 2.0515120029449463 +[2025-04-27 13:52:32,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 1.979254961013794, cross_entropy: 1.979254961013794 +[2025-04-27 13:52:32,342][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 1.809574007987976, cross_entropy: 1.809574007987976 +[2025-04-27 13:52:35,401][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 1.5840305089950562, cross_entropy: 1.5840305089950562 +[2025-04-27 13:52:35,735][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.4012985229492188, cross_entropy: 2.4012985229492188 +[2025-04-27 13:52:39,412][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.364748954772949, cross_entropy: 3.364748954772949 +[2025-04-27 13:52:39,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 1.9425033330917358, cross_entropy: 1.9425033330917358 +[2025-04-27 13:52:42,599][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 1.892237901687622, cross_entropy: 1.892237901687622 +[2025-04-27 13:52:42,937][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.5422143936157227, cross_entropy: 2.5422143936157227 +[2025-04-27 13:52:45,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.236131191253662, cross_entropy: 2.236131191253662 +[2025-04-27 13:52:46,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.8829989433288574, cross_entropy: 2.8829989433288574 +[2025-04-27 13:52:49,240][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.820279836654663, cross_entropy: 2.820279836654663 +[2025-04-27 13:52:49,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.9904513359069824, cross_entropy: 2.9904513359069824 +[2025-04-27 13:52:52,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 3.993659019470215, cross_entropy: 3.993659019470215 +[2025-04-27 13:52:52,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.544725179672241, cross_entropy: 3.544725179672241 +[2025-04-27 13:52:55,839][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 1.6683428287506104, cross_entropy: 1.6683428287506104 +[2025-04-27 13:52:56,151][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 3.4111571311950684, cross_entropy: 3.4111571311950684 +[2025-04-27 13:52:59,374][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.478740930557251, cross_entropy: 3.478740930557251 +[2025-04-27 13:52:59,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 1.8277370929718018, cross_entropy: 1.8277370929718018 +[2025-04-27 13:53:03,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 2.1053576469421387, cross_entropy: 2.1053576469421387 +[2025-04-27 13:53:03,443][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.865720748901367, cross_entropy: 2.865720748901367 +[2025-04-27 13:53:06,705][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 1.770481824874878, cross_entropy: 1.770481824874878 +[2025-04-27 13:53:07,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.2923808097839355, cross_entropy: 2.2923808097839355 +[2025-04-27 13:53:09,547][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 1.9987187385559082, cross_entropy: 1.9987187385559082 +[2025-04-27 13:53:09,858][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 4.02450704574585, cross_entropy: 4.02450704574585 +[2025-04-27 13:53:12,692][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.6961708068847656, cross_entropy: 2.6961708068847656 +[2025-04-27 13:53:13,005][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.2379984855651855, cross_entropy: 2.2379984855651855 +[2025-04-27 13:53:16,308][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.655245780944824, cross_entropy: 2.655245780944824 +[2025-04-27 13:53:16,643][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.3905839920043945, cross_entropy: 3.3905839920043945 +[2025-04-27 13:53:19,578][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.3078370094299316, cross_entropy: 2.3078370094299316 +[2025-04-27 13:53:19,893][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.164520740509033, cross_entropy: 3.164520740509033 +[2025-04-27 13:53:22,883][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 1.9077106714248657, cross_entropy: 1.9077106714248657 +[2025-04-27 13:53:23,220][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 1.9590563774108887, cross_entropy: 1.9590563774108887 +[2025-04-27 13:53:27,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.214472770690918, cross_entropy: 3.214472770690918 +[2025-04-27 13:53:28,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.1653974056243896, cross_entropy: 2.1653974056243896 +[2025-04-27 13:53:30,834][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 1.5298259258270264, cross_entropy: 1.5298259258270264 +[2025-04-27 13:53:31,170][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.048147201538086, cross_entropy: 3.048147201538086 +[2025-04-27 13:53:36,017][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 1.705351710319519, cross_entropy: 1.705351710319519 +[2025-04-27 13:53:36,358][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.539313316345215, cross_entropy: 2.539313316345215 +[2025-04-27 13:53:39,613][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 1.715306043624878, cross_entropy: 1.715306043624878 +[2025-04-27 13:53:39,953][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.086884021759033, cross_entropy: 3.086884021759033 +[2025-04-27 13:53:43,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.9346179962158203, cross_entropy: 2.9346179962158203 +[2025-04-27 13:53:44,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 3.4635190963745117, cross_entropy: 3.4635190963745117 +[2025-04-27 13:53:46,820][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 2.0002105236053467, cross_entropy: 2.0002105236053467 +[2025-04-27 13:53:47,159][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.7278711795806885, cross_entropy: 2.7278711795806885 +[2025-04-27 13:53:50,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 1.7490020990371704, cross_entropy: 1.7490020990371704 +[2025-04-27 13:53:50,469][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.1331658363342285, cross_entropy: 2.1331658363342285 +[2025-04-27 13:53:54,029][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.2127366065979004, cross_entropy: 2.2127366065979004 +[2025-04-27 13:53:54,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 3.487874984741211, cross_entropy: 3.487874984741211 +[2025-04-27 13:53:56,933][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.2690343856811523, cross_entropy: 3.2690343856811523 +[2025-04-27 13:53:57,269][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 1.970201849937439, cross_entropy: 1.970201849937439 +[2025-04-27 13:54:00,183][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.2961173057556152, cross_entropy: 2.2961173057556152 +[2025-04-27 13:54:00,495][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.4472110271453857, cross_entropy: 2.4472110271453857 +[2025-04-27 13:54:03,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.8499770164489746, cross_entropy: 2.8499770164489746 +[2025-04-27 13:54:03,883][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 2.2725727558135986, cross_entropy: 2.2725727558135986 +[2025-04-27 13:54:06,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 1.7076327800750732, cross_entropy: 1.7076327800750732 +[2025-04-27 13:54:07,201][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.820943832397461, cross_entropy: 2.820943832397461 +[2025-04-27 13:54:10,571][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 1.8100154399871826, cross_entropy: 1.8100154399871826 +[2025-04-27 13:54:10,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.958554267883301, cross_entropy: 3.958554267883301 +[2025-04-27 13:54:13,651][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 3.1799325942993164, cross_entropy: 3.1799325942993164 +[2025-04-27 13:54:13,973][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 1.4084471464157104, cross_entropy: 1.4084471464157104 +[2025-04-27 13:54:17,270][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 1.5671255588531494, cross_entropy: 1.5671255588531494 +[2025-04-27 13:54:17,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 1.6902458667755127, cross_entropy: 1.6902458667755127 +[2025-04-27 13:54:20,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.3427672386169434, cross_entropy: 2.3427672386169434 +[2025-04-27 13:54:21,169][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 1.994882345199585, cross_entropy: 1.994882345199585 +[2025-04-27 13:54:25,053][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 1.8558845520019531, cross_entropy: 1.8558845520019531 +[2025-04-27 13:54:25,390][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.26182222366333, cross_entropy: 3.26182222366333 +[2025-04-27 13:54:28,431][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.5879390239715576, cross_entropy: 3.5879390239715576 +[2025-04-27 13:54:28,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 1.6728079319000244, cross_entropy: 1.6728079319000244 +[2025-04-27 13:54:32,330][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.23309326171875, cross_entropy: 3.23309326171875 +[2025-04-27 13:54:32,665][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 2.1891424655914307, cross_entropy: 2.1891424655914307 +[2025-04-27 13:54:36,160][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 1.797317624092102, cross_entropy: 1.797317624092102 +[2025-04-27 13:54:36,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 2.0416834354400635, cross_entropy: 2.0416834354400635 +[2025-04-27 13:54:39,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 3.4546804428100586, cross_entropy: 3.4546804428100586 +[2025-04-27 13:54:39,647][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.6530954837799072, cross_entropy: 2.6530954837799072 +[2025-04-27 13:54:42,994][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 2.161083221435547, cross_entropy: 2.161083221435547 +[2025-04-27 13:54:43,334][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.3268749713897705, cross_entropy: 3.3268749713897705 +[2025-04-27 13:54:46,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.538912773132324, cross_entropy: 3.538912773132324 +[2025-04-27 13:54:46,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 1.694307804107666, cross_entropy: 1.694307804107666 +[2025-04-27 13:54:49,358][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 1.9140986204147339, cross_entropy: 1.9140986204147339 +[2025-04-27 13:54:49,669][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 2.7163000106811523, cross_entropy: 2.7163000106811523 +[2025-04-27 13:54:52,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.7708756923675537, cross_entropy: 3.7708756923675537 +[2025-04-27 13:54:53,278][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.25978422164917, cross_entropy: 2.25978422164917 +[2025-04-27 13:54:56,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.985276699066162, cross_entropy: 2.985276699066162 +[2025-04-27 13:54:56,542][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 3.526183605194092, cross_entropy: 3.526183605194092 +[2025-04-27 13:54:59,423][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.0003585815429688, cross_entropy: 2.0003585815429688 +[2025-04-27 13:55:00,363][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 2.2777791023254395, cross_entropy: 2.2777791023254395 +[2025-04-27 13:55:02,710][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.351323127746582, cross_entropy: 3.351323127746582 +[2025-04-27 13:55:03,816][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 1.6479898691177368, cross_entropy: 1.6479898691177368 +[2025-04-27 13:55:05,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.4707682132720947, cross_entropy: 3.4707682132720947 +[2025-04-27 13:55:06,958][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 1.9500586986541748, cross_entropy: 1.9500586986541748 +[2025-04-27 13:55:09,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.690135955810547, cross_entropy: 2.690135955810547 +[2025-04-27 13:55:10,323][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.5976898670196533, cross_entropy: 2.5976898670196533 +[2025-04-27 13:55:12,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.6610679626464844, cross_entropy: 2.6610679626464844 +[2025-04-27 13:55:12,976][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 1.5961408615112305, cross_entropy: 1.5961408615112305 +[2025-04-27 13:55:15,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 1.8866891860961914, cross_entropy: 1.8866891860961914 +[2025-04-27 13:55:16,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.4189236164093018, cross_entropy: 2.4189236164093018 +[2025-04-27 13:55:18,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.203677177429199, cross_entropy: 2.203677177429199 +[2025-04-27 13:55:19,163][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 3.7615017890930176, cross_entropy: 3.7615017890930176 +[2025-04-27 13:55:21,615][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.2892985343933105, cross_entropy: 3.2892985343933105 +[2025-04-27 13:55:22,493][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.489931106567383, cross_entropy: 2.489931106567383 +[2025-04-27 13:55:24,567][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.8036623001098633, cross_entropy: 2.8036623001098633 +[2025-04-27 13:55:25,992][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 3.89186954498291, cross_entropy: 3.89186954498291 +[2025-04-27 13:55:27,809][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 3.06973934173584, cross_entropy: 3.06973934173584 +[2025-04-27 13:55:29,737][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.469210624694824, cross_entropy: 2.469210624694824 +[2025-04-27 13:55:30,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 2.2264246940612793, cross_entropy: 2.2264246940612793 +[2025-04-27 13:55:33,796][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 1.9235899448394775, cross_entropy: 1.9235899448394775 +[2025-04-27 13:55:34,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.6074812412261963, cross_entropy: 3.6074812412261963 +[2025-04-27 13:55:37,611][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.7288284301757812, cross_entropy: 2.7288284301757812 +[2025-04-27 13:55:37,926][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 1.7883919477462769, cross_entropy: 1.7883919477462769 +[2025-04-27 13:55:40,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.07087779045105, cross_entropy: 2.07087779045105 +[2025-04-27 13:55:41,069][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 3.5535004138946533, cross_entropy: 3.5535004138946533 +[2025-04-27 13:55:44,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.8569813966751099, cross_entropy: 1.8569813966751099 +[2025-04-27 13:55:44,680][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 1.4204777479171753, cross_entropy: 1.4204777479171753 +[2025-04-27 13:55:47,419][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 1.8954092264175415, cross_entropy: 1.8954092264175415 +[2025-04-27 13:55:47,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 2.9502434730529785, cross_entropy: 2.9502434730529785 +[2025-04-27 13:55:50,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 1.790168046951294, cross_entropy: 1.790168046951294 +[2025-04-27 13:55:51,026][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 1.9997382164001465, cross_entropy: 1.9997382164001465 +[2025-04-27 13:55:54,325][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 3.7691431045532227, cross_entropy: 3.7691431045532227 +[2025-04-27 13:55:54,635][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 1.9557983875274658, cross_entropy: 1.9557983875274658 +[2025-04-27 13:55:58,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 2.1699559688568115, cross_entropy: 2.1699559688568115 +[2025-04-27 13:55:58,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 1.7895686626434326, cross_entropy: 1.7895686626434326 +[2025-04-27 13:56:01,607][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.943802833557129, cross_entropy: 2.943802833557129 +[2025-04-27 13:56:01,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 3.5943078994750977, cross_entropy: 3.5943078994750977 +[2025-04-27 13:56:04,827][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 1.937284231185913, cross_entropy: 1.937284231185913 +[2025-04-27 13:56:05,454][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 1.4393668174743652, cross_entropy: 1.4393668174743652 +[2025-04-27 13:56:09,605][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 2.7019214630126953, cross_entropy: 2.7019214630126953 +[2025-04-27 13:56:09,921][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 1.8052856922149658, cross_entropy: 1.8052856922149658 +[2025-04-27 13:56:12,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 1.7734229564666748, cross_entropy: 1.7734229564666748 +[2025-04-27 13:56:12,997][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.095031261444092, cross_entropy: 3.095031261444092 +[2025-04-27 13:56:16,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 1.953641653060913, cross_entropy: 1.953641653060913 +[2025-04-27 13:56:17,047][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.469269275665283, cross_entropy: 3.469269275665283 +[2025-04-27 13:56:20,098][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 2.4320456981658936, cross_entropy: 2.4320456981658936 +[2025-04-27 13:56:20,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.654550790786743, cross_entropy: 2.654550790786743 +[2025-04-27 13:56:23,829][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 1.745408296585083, cross_entropy: 1.745408296585083 +[2025-04-27 13:56:24,171][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 1.6989424228668213, cross_entropy: 1.6989424228668213 +[2025-04-27 13:56:27,469][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.515048027038574, cross_entropy: 2.515048027038574 +[2025-04-27 13:56:27,805][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.5032386779785156, cross_entropy: 2.5032386779785156 +[2025-04-27 13:56:31,024][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.2829840183258057, cross_entropy: 2.2829840183258057 +[2025-04-27 13:56:31,335][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.7721352577209473, cross_entropy: 2.7721352577209473 +[2025-04-27 13:56:34,198][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.360917568206787, cross_entropy: 2.360917568206787 +[2025-04-27 13:56:34,509][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 3.589622974395752, cross_entropy: 3.589622974395752 +[2025-04-27 13:56:37,316][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.511664867401123, cross_entropy: 2.511664867401123 +[2025-04-27 13:56:37,651][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.748182773590088, cross_entropy: 2.748182773590088 +[2025-04-27 13:56:40,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.003980875015259, cross_entropy: 2.003980875015259 +[2025-04-27 13:56:40,784][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 1.8506150245666504, cross_entropy: 1.8506150245666504 +[2025-04-27 13:56:43,757][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 2.3464553356170654, cross_entropy: 2.3464553356170654 +[2025-04-27 13:56:44,082][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 3.0793063640594482, cross_entropy: 3.0793063640594482 +[2025-04-27 13:56:47,441][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 2.4047539234161377, cross_entropy: 2.4047539234161377 +[2025-04-27 13:56:47,783][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 3.4427337646484375, cross_entropy: 3.4427337646484375 +[2025-04-27 13:56:50,225][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 1.6937280893325806, cross_entropy: 1.6937280893325806 +[2025-04-27 13:56:51,597][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.1942577362060547, cross_entropy: 3.1942577362060547 +[2025-04-27 13:56:53,270][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 3.4606356620788574, cross_entropy: 3.4606356620788574 +[2025-04-27 13:56:55,015][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 1.902173638343811, cross_entropy: 1.902173638343811 +[2025-04-27 13:56:56,582][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 1.7250865697860718, cross_entropy: 1.7250865697860718 +[2025-04-27 13:56:58,313][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 3.6213603019714355, cross_entropy: 3.6213603019714355 +[2025-04-27 13:56:59,366][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 1.6327052116394043, cross_entropy: 1.6327052116394043 +[2025-04-27 13:57:00,971][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 3.6429734230041504, cross_entropy: 3.6429734230041504 +[2025-04-27 13:57:02,801][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.086371421813965, cross_entropy: 2.086371421813965 +[2025-04-27 13:57:03,456][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.266380548477173, cross_entropy: 3.266380548477173 +[2025-04-27 13:57:05,955][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.048189163208008, cross_entropy: 2.048189163208008 +[2025-04-27 13:57:06,951][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 3.253772258758545, cross_entropy: 3.253772258758545 +[2025-04-27 13:57:09,012][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 1.8568429946899414, cross_entropy: 1.8568429946899414 +[2025-04-27 13:57:10,239][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.708951473236084, cross_entropy: 2.708951473236084 +[2025-04-27 13:57:11,962][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.1462154388427734, cross_entropy: 2.1462154388427734 +[2025-04-27 13:57:13,567][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 1.7071630954742432, cross_entropy: 1.7071630954742432 +[2025-04-27 13:57:15,108][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 3.3765668869018555, cross_entropy: 3.3765668869018555 +[2025-04-27 13:57:17,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 1.5076627731323242, cross_entropy: 1.5076627731323242 +[2025-04-27 13:57:18,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.695798635482788, cross_entropy: 3.695798635482788 +[2025-04-27 13:57:20,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 1.9486424922943115, cross_entropy: 1.9486424922943115 +[2025-04-27 13:57:22,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.945498466491699, cross_entropy: 2.945498466491699 +[2025-04-27 13:57:23,419][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 2.6708781719207764, cross_entropy: 2.6708781719207764 +[2025-04-27 13:57:26,041][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 2.5480856895446777, cross_entropy: 2.5480856895446777 +[2025-04-27 13:57:26,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.25539231300354, cross_entropy: 2.25539231300354 +[2025-04-27 13:57:29,425][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.2047338485717773, cross_entropy: 2.2047338485717773 +[2025-04-27 13:57:29,941][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 1.5882031917572021, cross_entropy: 1.5882031917572021 +[2025-04-27 13:57:33,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.978987693786621, cross_entropy: 1.978987693786621 +[2025-04-27 13:57:33,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.6124541759490967, cross_entropy: 3.6124541759490967 +[2025-04-27 13:57:36,435][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 1.7583950757980347, cross_entropy: 1.7583950757980347 +[2025-04-27 13:57:36,803][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 1.6479318141937256, cross_entropy: 1.6479318141937256 +[2025-04-27 13:57:39,963][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 3.5202383995056152, cross_entropy: 3.5202383995056152 +[2025-04-27 13:57:40,310][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 3.772075891494751, cross_entropy: 3.772075891494751 +[2025-04-27 13:57:42,804][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 1.9370237588882446, cross_entropy: 1.9370237588882446 +[2025-04-27 13:57:43,238][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 1.5209455490112305, cross_entropy: 1.5209455490112305 +[2025-04-27 13:57:45,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.3941192626953125, cross_entropy: 3.3941192626953125 +[2025-04-27 13:57:46,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.4206786155700684, cross_entropy: 3.4206786155700684 +[2025-04-27 13:57:49,432][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 1.795249581336975, cross_entropy: 1.795249581336975 +[2025-04-27 13:57:50,598][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 2.030231475830078, cross_entropy: 2.030231475830078 +[2025-04-27 13:57:53,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.8884891271591187, cross_entropy: 1.8884891271591187 +[2025-04-27 13:57:54,443][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 3.342557907104492, cross_entropy: 3.342557907104492 +[2025-04-27 13:57:56,788][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.5065419673919678, cross_entropy: 2.5065419673919678 +[2025-04-27 13:57:57,195][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.357149124145508, cross_entropy: 3.357149124145508 +[2025-04-27 13:58:00,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 1.9541771411895752, cross_entropy: 1.9541771411895752 +[2025-04-27 13:58:01,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 3.2576866149902344, cross_entropy: 3.2576866149902344 +[2025-04-27 13:58:04,302][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.8299241065979004, cross_entropy: 2.8299241065979004 +[2025-04-27 13:58:04,978][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 3.1661014556884766, cross_entropy: 3.1661014556884766 +[2025-04-27 13:58:08,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.3304202556610107, cross_entropy: 2.3304202556610107 +[2025-04-27 13:58:08,642][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.350578784942627, cross_entropy: 3.350578784942627 +[2025-04-27 13:58:11,700][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 1.608709454536438, cross_entropy: 1.608709454536438 +[2025-04-27 13:58:12,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 1.5905461311340332, cross_entropy: 1.5905461311340332 +[2025-04-27 13:58:15,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.6702675819396973, cross_entropy: 2.6702675819396973 +[2025-04-27 13:58:15,658][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 3.1116247177124023, cross_entropy: 3.1116247177124023 +[2025-04-27 13:58:18,580][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.5389647483825684, cross_entropy: 2.5389647483825684 +[2025-04-27 13:58:18,893][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 1.721893548965454, cross_entropy: 1.721893548965454 +[2025-04-27 13:58:22,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 3.2754359245300293, cross_entropy: 3.2754359245300293 +[2025-04-27 13:58:22,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.722695827484131, cross_entropy: 2.722695827484131 +[2025-04-27 13:58:25,183][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 2.6175644397735596, cross_entropy: 2.6175644397735596 +[2025-04-27 13:58:25,517][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.7608058452606201, cross_entropy: 1.7608058452606201 +[2025-04-27 13:58:28,346][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.599013328552246, cross_entropy: 2.599013328552246 +[2025-04-27 13:58:28,686][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 2.4377057552337646, cross_entropy: 2.4377057552337646 +[2025-04-27 13:58:31,673][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.0307929515838623, cross_entropy: 3.0307929515838623 +[2025-04-27 13:58:32,081][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.0712857246398926, cross_entropy: 3.0712857246398926 +[2025-04-27 13:58:35,612][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 1.598191499710083, cross_entropy: 1.598191499710083 +[2025-04-27 13:58:35,949][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 1.8459913730621338, cross_entropy: 1.8459913730621338 +[2025-04-27 13:58:38,721][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 1.8131790161132812, cross_entropy: 1.8131790161132812 +[2025-04-27 13:58:39,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.2230947017669678, cross_entropy: 3.2230947017669678 +[2025-04-27 13:58:42,166][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.9403538703918457, cross_entropy: 2.9403538703918457 +[2025-04-27 13:58:42,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 1.9132970571517944, cross_entropy: 1.9132970571517944 +[2025-04-27 13:58:45,682][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 3.2469496726989746, cross_entropy: 3.2469496726989746 +[2025-04-27 13:58:46,017][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 1.9837374687194824, cross_entropy: 1.9837374687194824 +[2025-04-27 13:58:49,062][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 2.891822338104248, cross_entropy: 2.891822338104248 +[2025-04-27 13:58:49,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 2.268831491470337, cross_entropy: 2.268831491470337 +[2025-04-27 13:58:53,414][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.4898221492767334, cross_entropy: 3.4898221492767334 +[2025-04-27 13:58:55,102][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 1.7770988941192627, cross_entropy: 1.7770988941192627 +[2025-04-27 13:58:56,299][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.3118364810943604, cross_entropy: 3.3118364810943604 +[2025-04-27 13:58:58,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.399202585220337, cross_entropy: 3.399202585220337 +[2025-04-27 13:59:00,102][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 1.6327879428863525, cross_entropy: 1.6327879428863525 +[2025-04-27 13:59:02,143][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 1.814684510231018, cross_entropy: 1.814684510231018 +[2025-04-27 13:59:03,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.467470169067383, cross_entropy: 2.467470169067383 +[2025-04-27 13:59:05,821][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 1.8246536254882812, cross_entropy: 1.8246536254882812 +[2025-04-27 13:59:07,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 2.0150017738342285, cross_entropy: 2.0150017738342285 +[2025-04-27 13:59:08,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.6411880254745483, cross_entropy: 1.6411880254745483 +[2025-04-27 13:59:10,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.61845326423645, cross_entropy: 3.61845326423645 +[2025-04-27 13:59:12,354][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 2.0631630420684814, cross_entropy: 2.0631630420684814 +[2025-04-27 13:59:14,102][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 3.1206977367401123, cross_entropy: 3.1206977367401123 +[2025-04-27 14:01:55,539][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.6281893253326416, cross_entropy: 2.6281893253326416 +[2025-04-27 14:01:55,539][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.6534242630004883, cross_entropy: 1.6534242630004883 +[2025-04-27 14:01:55,761][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 14:01:55,923][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch2.pth. +[2025-04-27 14:01:56,133][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 14:02:00,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 3.145601272583008, cross_entropy: 3.145601272583008 +[2025-04-27 14:02:01,136][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.4077833890914917, cross_entropy: 1.4077833890914917 +[2025-04-27 14:02:04,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 1.8627541065216064, cross_entropy: 1.8627541065216064 +[2025-04-27 14:02:04,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 2.839751720428467, cross_entropy: 2.839751720428467 +[2025-04-27 14:02:08,645][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.767504334449768, cross_entropy: 1.767504334449768 +[2025-04-27 14:02:08,983][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.180609703063965, cross_entropy: 2.180609703063965 +[2025-04-27 14:02:11,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.5209649801254272, cross_entropy: 1.5209649801254272 +[2025-04-27 14:02:12,260][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 2.3157548904418945, cross_entropy: 2.3157548904418945 +[2025-04-27 14:02:15,323][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.3001036643981934, cross_entropy: 1.3001036643981934 +[2025-04-27 14:02:15,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 2.189859390258789, cross_entropy: 2.189859390258789 +[2025-04-27 14:02:18,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.5882294178009033, cross_entropy: 2.5882294178009033 +[2025-04-27 14:02:18,741][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 1.8321419954299927, cross_entropy: 1.8321419954299927 +[2025-04-27 14:02:21,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.9534116983413696, cross_entropy: 1.9534116983413696 +[2025-04-27 14:02:21,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.468139171600342, cross_entropy: 2.468139171600342 +[2025-04-27 14:02:24,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.079035520553589, cross_entropy: 2.079035520553589 +[2025-04-27 14:02:24,705][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 1.989637851715088, cross_entropy: 1.989637851715088 +[2025-04-27 14:02:28,125][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.481952428817749, cross_entropy: 3.481952428817749 +[2025-04-27 14:02:28,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.2123446464538574, cross_entropy: 2.2123446464538574 +[2025-04-27 14:02:31,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.477843999862671, cross_entropy: 1.477843999862671 +[2025-04-27 14:02:32,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.7224981784820557, cross_entropy: 1.7224981784820557 +[2025-04-27 14:02:34,779][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 3.2166271209716797, cross_entropy: 3.2166271209716797 +[2025-04-27 14:02:35,331][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.5154261589050293, cross_entropy: 1.5154261589050293 +[2025-04-27 14:02:38,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.5164432525634766, cross_entropy: 3.5164432525634766 +[2025-04-27 14:02:39,251][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 2.718888759613037, cross_entropy: 2.718888759613037 +[2025-04-27 14:02:41,466][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.491123676300049, cross_entropy: 3.491123676300049 +[2025-04-27 14:02:43,381][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 2.356029987335205, cross_entropy: 2.356029987335205 +[2025-04-27 14:02:44,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 1.4039226770401, cross_entropy: 1.4039226770401 +[2025-04-27 14:02:48,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 1.9095827341079712, cross_entropy: 1.9095827341079712 +[2025-04-27 14:02:48,354][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.255963087081909, cross_entropy: 3.255963087081909 +[2025-04-27 14:02:51,211][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.83233642578125, cross_entropy: 2.83233642578125 +[2025-04-27 14:02:51,523][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.6662688255310059, cross_entropy: 1.6662688255310059 +[2025-04-27 14:02:54,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 3.2853503227233887, cross_entropy: 3.2853503227233887 +[2025-04-27 14:02:54,543][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.082085132598877, cross_entropy: 3.082085132598877 +[2025-04-27 14:02:57,359][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 1.7530272006988525, cross_entropy: 1.7530272006988525 +[2025-04-27 14:02:57,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 3.5023579597473145, cross_entropy: 3.5023579597473145 +[2025-04-27 14:03:00,942][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.189427614212036, cross_entropy: 3.189427614212036 +[2025-04-27 14:03:01,309][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.2029402256011963, cross_entropy: 2.2029402256011963 +[2025-04-27 14:03:04,572][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 2.107434034347534, cross_entropy: 2.107434034347534 +[2025-04-27 14:03:04,927][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 1.152260422706604, cross_entropy: 1.152260422706604 +[2025-04-27 14:03:08,038][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 1.8346304893493652, cross_entropy: 1.8346304893493652 +[2025-04-27 14:03:08,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.8160345554351807, cross_entropy: 1.8160345554351807 +[2025-04-27 14:03:11,893][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 2.724876880645752, cross_entropy: 2.724876880645752 +[2025-04-27 14:03:12,204][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 1.649819254875183, cross_entropy: 1.649819254875183 +[2025-04-27 14:03:15,148][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.319577932357788, cross_entropy: 2.319577932357788 +[2025-04-27 14:03:15,482][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.8069074153900146, cross_entropy: 2.8069074153900146 +[2025-04-27 14:03:18,662][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 3.2189674377441406, cross_entropy: 3.2189674377441406 +[2025-04-27 14:03:18,998][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.494997501373291, cross_entropy: 1.494997501373291 +[2025-04-27 14:03:22,787][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 3.5628466606140137, cross_entropy: 3.5628466606140137 +[2025-04-27 14:03:23,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 3.0712101459503174, cross_entropy: 3.0712101459503174 +[2025-04-27 14:03:26,993][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 1.48638916015625, cross_entropy: 1.48638916015625 +[2025-04-27 14:03:27,331][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 1.6726945638656616, cross_entropy: 1.6726945638656616 +[2025-04-27 14:03:30,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 1.7990100383758545, cross_entropy: 1.7990100383758545 +[2025-04-27 14:03:30,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.9464526176452637, cross_entropy: 2.9464526176452637 +[2025-04-27 14:03:34,161][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.1707799434661865, cross_entropy: 3.1707799434661865 +[2025-04-27 14:03:34,473][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.007192611694336, cross_entropy: 3.007192611694336 +[2025-04-27 14:03:38,477][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 3.003075122833252, cross_entropy: 3.003075122833252 +[2025-04-27 14:03:38,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.2968194484710693, cross_entropy: 3.2968194484710693 +[2025-04-27 14:03:42,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.404204845428467, cross_entropy: 2.404204845428467 +[2025-04-27 14:03:42,436][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.173516035079956, cross_entropy: 3.173516035079956 +[2025-04-27 14:03:46,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 3.5827245712280273, cross_entropy: 3.5827245712280273 +[2025-04-27 14:03:46,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.5291576385498047, cross_entropy: 2.5291576385498047 +[2025-04-27 14:03:49,121][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.433483123779297, cross_entropy: 2.433483123779297 +[2025-04-27 14:03:49,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.062239170074463, cross_entropy: 3.062239170074463 +[2025-04-27 14:03:52,948][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 1.6602859497070312, cross_entropy: 1.6602859497070312 +[2025-04-27 14:03:53,284][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.4785680770874023, cross_entropy: 3.4785680770874023 +[2025-04-27 14:03:57,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.7787814140319824, cross_entropy: 2.7787814140319824 +[2025-04-27 14:03:57,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.9217274188995361, cross_entropy: 1.9217274188995361 +[2025-04-27 14:04:00,769][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.4956729412078857, cross_entropy: 3.4956729412078857 +[2025-04-27 14:04:01,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.071439266204834, cross_entropy: 2.071439266204834 +[2025-04-27 14:04:04,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 2.4981722831726074, cross_entropy: 2.4981722831726074 +[2025-04-27 14:04:04,358][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.363034725189209, cross_entropy: 2.363034725189209 +[2025-04-27 14:04:07,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.489234209060669, cross_entropy: 2.489234209060669 +[2025-04-27 14:04:08,061][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 2.104255437850952, cross_entropy: 2.104255437850952 +[2025-04-27 14:04:11,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.752354145050049, cross_entropy: 2.752354145050049 +[2025-04-27 14:04:11,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.3142690658569336, cross_entropy: 3.3142690658569336 +[2025-04-27 14:04:15,591][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 1.5750455856323242, cross_entropy: 1.5750455856323242 +[2025-04-27 14:04:15,906][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 2.7237768173217773, cross_entropy: 2.7237768173217773 +[2025-04-27 14:04:19,269][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 1.7921109199523926, cross_entropy: 1.7921109199523926 +[2025-04-27 14:04:19,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.014141082763672, cross_entropy: 3.014141082763672 +[2025-04-27 14:04:22,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 1.340032935142517, cross_entropy: 1.340032935142517 +[2025-04-27 14:04:22,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.1902952194213867, cross_entropy: 3.1902952194213867 +[2025-04-27 14:04:25,742][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.8651542663574219, cross_entropy: 1.8651542663574219 +[2025-04-27 14:04:26,057][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.045559883117676, cross_entropy: 3.045559883117676 +[2025-04-27 14:04:29,191][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 1.6729109287261963, cross_entropy: 1.6729109287261963 +[2025-04-27 14:04:29,524][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 1.8354172706604004, cross_entropy: 1.8354172706604004 +[2025-04-27 14:04:32,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 1.8867145776748657, cross_entropy: 1.8867145776748657 +[2025-04-27 14:04:32,747][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 2.206962823867798, cross_entropy: 2.206962823867798 +[2025-04-27 14:04:36,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.3237671852111816, cross_entropy: 3.3237671852111816 +[2025-04-27 14:04:36,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.2353339195251465, cross_entropy: 3.2353339195251465 +[2025-04-27 14:04:39,876][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 3.3836112022399902, cross_entropy: 3.3836112022399902 +[2025-04-27 14:04:40,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 3.2692179679870605, cross_entropy: 3.2692179679870605 +[2025-04-27 14:04:43,109][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.6117844581604004, cross_entropy: 1.6117844581604004 +[2025-04-27 14:04:43,447][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.5038700103759766, cross_entropy: 1.5038700103759766 +[2025-04-27 14:04:46,765][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.853285312652588, cross_entropy: 2.853285312652588 +[2025-04-27 14:04:47,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.2851178646087646, cross_entropy: 3.2851178646087646 +[2025-04-27 14:04:50,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.3673834800720215, cross_entropy: 1.3673834800720215 +[2025-04-27 14:04:50,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.392446756362915, cross_entropy: 3.392446756362915 +[2025-04-27 14:04:53,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.284694194793701, cross_entropy: 2.284694194793701 +[2025-04-27 14:04:54,274][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.5060884952545166, cross_entropy: 2.5060884952545166 +[2025-04-27 14:04:57,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.1092491149902344, cross_entropy: 2.1092491149902344 +[2025-04-27 14:04:57,563][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 1.9356073141098022, cross_entropy: 1.9356073141098022 +[2025-04-27 14:05:00,258][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 2.1736836433410645, cross_entropy: 2.1736836433410645 +[2025-04-27 14:05:00,595][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.552532196044922, cross_entropy: 2.552532196044922 +[2025-04-27 14:05:04,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.8761439323425293, cross_entropy: 1.8761439323425293 +[2025-04-27 14:05:04,485][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 2.073617458343506, cross_entropy: 2.073617458343506 +[2025-04-27 14:05:07,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 1.6205570697784424, cross_entropy: 1.6205570697784424 +[2025-04-27 14:05:07,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 1.7309998273849487, cross_entropy: 1.7309998273849487 +[2025-04-27 14:05:10,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 1.8308184146881104, cross_entropy: 1.8308184146881104 +[2025-04-27 14:05:11,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 2.4494032859802246, cross_entropy: 2.4494032859802246 +[2025-04-27 14:05:14,084][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 1.4322082996368408, cross_entropy: 1.4322082996368408 +[2025-04-27 14:05:14,422][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.2098593711853027, cross_entropy: 2.2098593711853027 +[2025-04-27 14:05:18,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.6900615692138672, cross_entropy: 1.6900615692138672 +[2025-04-27 14:05:18,414][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 1.9519505500793457, cross_entropy: 1.9519505500793457 +[2025-04-27 14:05:22,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 3.114025831222534, cross_entropy: 3.114025831222534 +[2025-04-27 14:05:22,458][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 2.9104955196380615, cross_entropy: 2.9104955196380615 +[2025-04-27 14:05:25,466][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.4275587797164917, cross_entropy: 1.4275587797164917 +[2025-04-27 14:05:25,793][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.4965529441833496, cross_entropy: 2.4965529441833496 +[2025-04-27 14:05:28,535][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.3794970512390137, cross_entropy: 2.3794970512390137 +[2025-04-27 14:05:28,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.4941420555114746, cross_entropy: 3.4941420555114746 +[2025-04-27 14:05:32,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.5676538944244385, cross_entropy: 2.5676538944244385 +[2025-04-27 14:05:32,360][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 1.5341829061508179, cross_entropy: 1.5341829061508179 +[2025-04-27 14:05:36,304][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 1.6596629619598389, cross_entropy: 1.6596629619598389 +[2025-04-27 14:05:36,636][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.396214008331299, cross_entropy: 2.396214008331299 +[2025-04-27 14:05:39,774][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 1.6482582092285156, cross_entropy: 1.6482582092285156 +[2025-04-27 14:05:40,118][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.2065982818603516, cross_entropy: 3.2065982818603516 +[2025-04-27 14:05:43,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.643979787826538, cross_entropy: 2.643979787826538 +[2025-04-27 14:05:43,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.2563730478286743, cross_entropy: 1.2563730478286743 +[2025-04-27 14:05:47,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 2.0732648372650146, cross_entropy: 2.0732648372650146 +[2025-04-27 14:05:47,382][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.0972843170166016, cross_entropy: 3.0972843170166016 +[2025-04-27 14:05:51,052][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.080242872238159, cross_entropy: 2.080242872238159 +[2025-04-27 14:05:51,387][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 1.780249834060669, cross_entropy: 1.780249834060669 +[2025-04-27 14:05:54,207][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 1.584995985031128, cross_entropy: 1.584995985031128 +[2025-04-27 14:05:54,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.3744349479675293, cross_entropy: 2.3744349479675293 +[2025-04-27 14:05:57,657][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.983736038208008, cross_entropy: 2.983736038208008 +[2025-04-27 14:05:57,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.1681716442108154, cross_entropy: 2.1681716442108154 +[2025-04-27 14:06:00,798][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.6607681512832642, cross_entropy: 1.6607681512832642 +[2025-04-27 14:06:01,140][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.4397666454315186, cross_entropy: 2.4397666454315186 +[2025-04-27 14:06:04,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.4461040496826172, cross_entropy: 1.4461040496826172 +[2025-04-27 14:06:04,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.8477420806884766, cross_entropy: 2.8477420806884766 +[2025-04-27 14:06:08,163][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 1.841499924659729, cross_entropy: 1.841499924659729 +[2025-04-27 14:06:08,497][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.30680251121521, cross_entropy: 2.30680251121521 +[2025-04-27 14:06:11,765][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.2719494104385376, cross_entropy: 1.2719494104385376 +[2025-04-27 14:06:12,101][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.655747413635254, cross_entropy: 2.655747413635254 +[2025-04-27 14:06:15,274][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 1.82505202293396, cross_entropy: 1.82505202293396 +[2025-04-27 14:06:15,593][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.208508014678955, cross_entropy: 2.208508014678955 +[2025-04-27 14:06:19,013][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.467575788497925, cross_entropy: 2.467575788497925 +[2025-04-27 14:06:19,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.6137115955352783, cross_entropy: 1.6137115955352783 +[2025-04-27 14:06:22,972][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.3062591552734375, cross_entropy: 3.3062591552734375 +[2025-04-27 14:06:23,306][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 1.3560764789581299, cross_entropy: 1.3560764789581299 +[2025-04-27 14:06:26,250][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 1.497520923614502, cross_entropy: 1.497520923614502 +[2025-04-27 14:06:26,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.5205069780349731, cross_entropy: 1.5205069780349731 +[2025-04-27 14:06:29,492][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 1.4866024255752563, cross_entropy: 1.4866024255752563 +[2025-04-27 14:06:29,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.0418214797973633, cross_entropy: 2.0418214797973633 +[2025-04-27 14:06:32,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 1.9778409004211426, cross_entropy: 1.9778409004211426 +[2025-04-27 14:06:33,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.3412978649139404, cross_entropy: 2.3412978649139404 +[2025-04-27 14:06:36,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 1.7307559251785278, cross_entropy: 1.7307559251785278 +[2025-04-27 14:06:36,727][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.5522217750549316, cross_entropy: 1.5522217750549316 +[2025-04-27 14:06:39,636][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 1.3550875186920166, cross_entropy: 1.3550875186920166 +[2025-04-27 14:06:39,948][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 1.9452446699142456, cross_entropy: 1.9452446699142456 +[2025-04-27 14:06:43,184][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 1.4176583290100098, cross_entropy: 1.4176583290100098 +[2025-04-27 14:06:43,518][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.3749799728393555, cross_entropy: 3.3749799728393555 +[2025-04-27 14:06:46,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.150531530380249, cross_entropy: 3.150531530380249 +[2025-04-27 14:06:47,056][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.4657204151153564, cross_entropy: 3.4657204151153564 +[2025-04-27 14:06:50,424][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 1.8627533912658691, cross_entropy: 1.8627533912658691 +[2025-04-27 14:06:50,735][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 2.8377857208251953, cross_entropy: 2.8377857208251953 +[2025-04-27 14:06:55,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.7588682174682617, cross_entropy: 1.7588682174682617 +[2025-04-27 14:06:55,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 1.4845144748687744, cross_entropy: 1.4845144748687744 +[2025-04-27 14:06:59,013][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 3.22346830368042, cross_entropy: 3.22346830368042 +[2025-04-27 14:06:59,339][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.5850330591201782, cross_entropy: 1.5850330591201782 +[2025-04-27 14:07:02,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.138995409011841, cross_entropy: 3.138995409011841 +[2025-04-27 14:07:02,705][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 1.9520363807678223, cross_entropy: 1.9520363807678223 +[2025-04-27 14:07:06,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.3968708515167236, cross_entropy: 2.3968708515167236 +[2025-04-27 14:07:06,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.1521964073181152, cross_entropy: 3.1521964073181152 +[2025-04-27 14:07:09,283][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.0085952281951904, cross_entropy: 2.0085952281951904 +[2025-04-27 14:07:09,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.281026840209961, cross_entropy: 2.281026840209961 +[2025-04-27 14:07:12,614][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.718143939971924, cross_entropy: 2.718143939971924 +[2025-04-27 14:07:12,961][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.3069257736206055, cross_entropy: 2.3069257736206055 +[2025-04-27 14:07:16,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 3.0468950271606445, cross_entropy: 3.0468950271606445 +[2025-04-27 14:07:16,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.6536850929260254, cross_entropy: 1.6536850929260254 +[2025-04-27 14:07:19,214][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.743408203125, cross_entropy: 2.743408203125 +[2025-04-27 14:07:19,529][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.5946036577224731, cross_entropy: 1.5946036577224731 +[2025-04-27 14:07:22,762][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.918924331665039, cross_entropy: 2.918924331665039 +[2025-04-27 14:07:23,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.2176389694213867, cross_entropy: 2.2176389694213867 +[2025-04-27 14:07:26,517][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.6469130516052246, cross_entropy: 2.6469130516052246 +[2025-04-27 14:07:26,859][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 2.723844528198242, cross_entropy: 2.723844528198242 +[2025-04-27 14:07:29,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 3.4220147132873535, cross_entropy: 3.4220147132873535 +[2025-04-27 14:07:30,260][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.244174003601074, cross_entropy: 2.244174003601074 +[2025-04-27 14:07:33,606][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.525214910507202, cross_entropy: 2.525214910507202 +[2025-04-27 14:07:33,921][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.035860538482666, cross_entropy: 3.035860538482666 +[2025-04-27 14:07:37,551][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.2174510955810547, cross_entropy: 3.2174510955810547 +[2025-04-27 14:07:37,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.187880754470825, cross_entropy: 2.187880754470825 +[2025-04-27 14:07:41,291][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 1.653907060623169, cross_entropy: 1.653907060623169 +[2025-04-27 14:07:41,620][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.8251123428344727, cross_entropy: 2.8251123428344727 +[2025-04-27 14:07:44,443][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 1.353437900543213, cross_entropy: 1.353437900543213 +[2025-04-27 14:07:44,782][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 3.0205764770507812, cross_entropy: 3.0205764770507812 +[2025-04-27 14:07:47,856][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.372142791748047, cross_entropy: 2.372142791748047 +[2025-04-27 14:07:48,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 1.685654878616333, cross_entropy: 1.685654878616333 +[2025-04-27 14:07:51,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 2.284853458404541, cross_entropy: 2.284853458404541 +[2025-04-27 14:07:51,974][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.3876053094863892, cross_entropy: 1.3876053094863892 +[2025-04-27 14:07:55,371][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 2.7653398513793945, cross_entropy: 2.7653398513793945 +[2025-04-27 14:07:55,720][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 1.6722328662872314, cross_entropy: 1.6722328662872314 +[2025-04-27 14:07:59,734][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.5653176307678223, cross_entropy: 2.5653176307678223 +[2025-04-27 14:08:00,065][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.0551352500915527, cross_entropy: 3.0551352500915527 +[2025-04-27 14:08:03,662][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.9337072372436523, cross_entropy: 2.9337072372436523 +[2025-04-27 14:08:03,995][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.2680435180664062, cross_entropy: 3.2680435180664062 +[2025-04-27 14:08:07,550][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 3.044471025466919, cross_entropy: 3.044471025466919 +[2025-04-27 14:08:07,861][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.5736136436462402, cross_entropy: 2.5736136436462402 +[2025-04-27 14:08:10,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.2493104934692383, cross_entropy: 2.2493104934692383 +[2025-04-27 14:08:10,857][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 1.6257879734039307, cross_entropy: 1.6257879734039307 +[2025-04-27 14:08:13,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.729351758956909, cross_entropy: 2.729351758956909 +[2025-04-27 14:08:13,929][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 2.551894187927246, cross_entropy: 2.551894187927246 +[2025-04-27 14:08:17,137][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.894066572189331, cross_entropy: 1.894066572189331 +[2025-04-27 14:08:17,450][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 1.5663565397262573, cross_entropy: 1.5663565397262573 +[2025-04-27 14:08:21,161][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.034317970275879, cross_entropy: 2.034317970275879 +[2025-04-27 14:08:21,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.4005403518676758, cross_entropy: 1.4005403518676758 +[2025-04-27 14:08:24,529][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 1.7522780895233154, cross_entropy: 1.7522780895233154 +[2025-04-27 14:08:24,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.134948253631592, cross_entropy: 2.134948253631592 +[2025-04-27 14:08:28,070][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 2.196629762649536, cross_entropy: 2.196629762649536 +[2025-04-27 14:08:28,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.7795987129211426, cross_entropy: 2.7795987129211426 +[2025-04-27 14:08:31,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 1.7181718349456787, cross_entropy: 1.7181718349456787 +[2025-04-27 14:08:31,806][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.6356319189071655, cross_entropy: 1.6356319189071655 +[2025-04-27 14:08:35,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 3.591846466064453, cross_entropy: 3.591846466064453 +[2025-04-27 14:08:35,386][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.2009010314941406, cross_entropy: 3.2009010314941406 +[2025-04-27 14:08:38,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 2.9873204231262207, cross_entropy: 2.9873204231262207 +[2025-04-27 14:08:38,619][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.3302459716796875, cross_entropy: 3.3302459716796875 +[2025-04-27 14:08:41,623][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.6068150997161865, cross_entropy: 1.6068150997161865 +[2025-04-27 14:08:41,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.103276014328003, cross_entropy: 1.103276014328003 +[2025-04-27 14:08:45,068][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.42703914642334, cross_entropy: 3.42703914642334 +[2025-04-27 14:08:45,398][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.5607671737670898, cross_entropy: 1.5607671737670898 +[2025-04-27 14:08:48,559][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.3782429695129395, cross_entropy: 3.3782429695129395 +[2025-04-27 14:08:48,871][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.1220850944519043, cross_entropy: 2.1220850944519043 +[2025-04-27 14:08:52,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.194478988647461, cross_entropy: 3.194478988647461 +[2025-04-27 14:08:52,433][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 1.6848714351654053, cross_entropy: 1.6848714351654053 +[2025-04-27 14:08:55,313][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 1.7488657236099243, cross_entropy: 1.7488657236099243 +[2025-04-27 14:08:55,649][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.180614948272705, cross_entropy: 3.180614948272705 +[2025-04-27 14:08:58,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 1.8076636791229248, cross_entropy: 1.8076636791229248 +[2025-04-27 14:08:59,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.213517189025879, cross_entropy: 3.213517189025879 +[2025-04-27 14:09:03,015][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 2.9042632579803467, cross_entropy: 2.9042632579803467 +[2025-04-27 14:09:03,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.5069785118103027, cross_entropy: 2.5069785118103027 +[2025-04-27 14:09:06,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 2.040607452392578, cross_entropy: 2.040607452392578 +[2025-04-27 14:09:06,783][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.8669636249542236, cross_entropy: 2.8669636249542236 +[2025-04-27 14:09:11,134][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 2.7806038856506348, cross_entropy: 2.7806038856506348 +[2025-04-27 14:09:11,444][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 3.404737949371338, cross_entropy: 3.404737949371338 +[2025-04-27 14:09:14,058][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 1.266108512878418, cross_entropy: 1.266108512878418 +[2025-04-27 14:09:14,372][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.251197099685669, cross_entropy: 1.251197099685669 +[2025-04-27 14:09:18,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.8784422874450684, cross_entropy: 2.8784422874450684 +[2025-04-27 14:09:18,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.107725143432617, cross_entropy: 3.107725143432617 +[2025-04-27 14:09:22,228][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.925954818725586, cross_entropy: 1.925954818725586 +[2025-04-27 14:09:22,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.7055716514587402, cross_entropy: 2.7055716514587402 +[2025-04-27 14:09:25,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.6187400817871094, cross_entropy: 2.6187400817871094 +[2025-04-27 14:09:26,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.3456850051879883, cross_entropy: 2.3456850051879883 +[2025-04-27 14:09:29,229][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.0081533193588257, cross_entropy: 1.0081533193588257 +[2025-04-27 14:09:29,566][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 1.684074878692627, cross_entropy: 1.684074878692627 +[2025-04-27 14:09:33,336][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 1.6542792320251465, cross_entropy: 1.6542792320251465 +[2025-04-27 14:09:33,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.1139750480651855, cross_entropy: 3.1139750480651855 +[2025-04-27 14:09:36,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 2.677332878112793, cross_entropy: 2.677332878112793 +[2025-04-27 14:09:36,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.1923761367797852, cross_entropy: 1.1923761367797852 +[2025-04-27 14:09:39,766][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.2446818351745605, cross_entropy: 3.2446818351745605 +[2025-04-27 14:09:40,106][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.529547929763794, cross_entropy: 1.529547929763794 +[2025-04-27 14:09:43,078][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.111363172531128, cross_entropy: 2.111363172531128 +[2025-04-27 14:09:43,390][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 1.803053617477417, cross_entropy: 1.803053617477417 +[2025-04-27 14:09:47,052][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.4151651859283447, cross_entropy: 1.4151651859283447 +[2025-04-27 14:09:47,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 2.6093947887420654, cross_entropy: 2.6093947887420654 +[2025-04-27 14:09:50,726][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.5407524108886719, cross_entropy: 1.5407524108886719 +[2025-04-27 14:09:51,052][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.1652731895446777, cross_entropy: 3.1652731895446777 +[2025-04-27 14:09:54,339][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 1.2890565395355225, cross_entropy: 1.2890565395355225 +[2025-04-27 14:09:54,652][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.270275592803955, cross_entropy: 3.270275592803955 +[2025-04-27 14:09:58,534][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.5993446111679077, cross_entropy: 1.5993446111679077 +[2025-04-27 14:09:58,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 2.9851508140563965, cross_entropy: 2.9851508140563965 +[2025-04-27 14:10:02,016][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 1.6932737827301025, cross_entropy: 1.6932737827301025 +[2025-04-27 14:10:02,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.278231143951416, cross_entropy: 3.278231143951416 +[2025-04-27 14:10:05,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.6073286533355713, cross_entropy: 1.6073286533355713 +[2025-04-27 14:10:05,685][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.2844715118408203, cross_entropy: 3.2844715118408203 +[2025-04-27 14:10:09,082][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 1.7643015384674072, cross_entropy: 1.7643015384674072 +[2025-04-27 14:10:09,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 3.1639270782470703, cross_entropy: 3.1639270782470703 +[2025-04-27 14:10:12,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 3.4108004570007324, cross_entropy: 3.4108004570007324 +[2025-04-27 14:10:13,071][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 2.493257522583008, cross_entropy: 2.493257522583008 +[2025-04-27 14:10:16,181][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 1.4425342082977295, cross_entropy: 1.4425342082977295 +[2025-04-27 14:10:16,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 2.338144302368164, cross_entropy: 2.338144302368164 +[2025-04-27 14:10:19,549][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.5272319316864014, cross_entropy: 2.5272319316864014 +[2025-04-27 14:10:19,884][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.2348830699920654, cross_entropy: 1.2348830699920654 +[2025-04-27 14:10:23,521][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.031294107437134, cross_entropy: 3.031294107437134 +[2025-04-27 14:10:23,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.6977022886276245, cross_entropy: 1.6977022886276245 +[2025-04-27 14:10:26,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 2.689929485321045, cross_entropy: 2.689929485321045 +[2025-04-27 14:10:26,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.3342950344085693, cross_entropy: 1.3342950344085693 +[2025-04-27 14:10:30,252][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 2.0790820121765137, cross_entropy: 2.0790820121765137 +[2025-04-27 14:10:30,592][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 1.8513492345809937, cross_entropy: 1.8513492345809937 +[2025-04-27 14:10:33,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.4546124935150146, cross_entropy: 1.4546124935150146 +[2025-04-27 14:10:33,385][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/iteration1000.pth. +[2025-04-27 14:10:33,719][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.703308343887329, cross_entropy: 2.703308343887329 +[2025-04-27 14:10:37,348][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.8881170749664307, cross_entropy: 1.8881170749664307 +[2025-04-27 14:10:37,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.0501348972320557, cross_entropy: 3.0501348972320557 +[2025-04-27 14:10:40,735][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 3.4013941287994385, cross_entropy: 3.4013941287994385 +[2025-04-27 14:10:41,063][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.5536327362060547, cross_entropy: 1.5536327362060547 +[2025-04-27 14:10:44,773][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.8478264808654785, cross_entropy: 2.8478264808654785 +[2025-04-27 14:10:45,107][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 1.776896595954895, cross_entropy: 1.776896595954895 +[2025-04-27 14:10:48,391][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 3.0773046016693115, cross_entropy: 3.0773046016693115 +[2025-04-27 14:10:48,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.8073744773864746, cross_entropy: 2.8073744773864746 +[2025-04-27 14:10:51,867][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.865386962890625, cross_entropy: 2.865386962890625 +[2025-04-27 14:10:52,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.0157599449157715, cross_entropy: 3.0157599449157715 +[2025-04-27 14:10:56,076][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.623340606689453, cross_entropy: 2.623340606689453 +[2025-04-27 14:10:56,390][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 1.5343866348266602, cross_entropy: 1.5343866348266602 +[2025-04-27 14:10:59,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 2.086407423019409, cross_entropy: 2.086407423019409 +[2025-04-27 14:11:00,007][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.4886208772659302, cross_entropy: 1.4886208772659302 +[2025-04-27 14:11:03,628][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 2.341043472290039, cross_entropy: 2.341043472290039 +[2025-04-27 14:11:03,962][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.7579381465911865, cross_entropy: 2.7579381465911865 +[2025-04-27 14:11:07,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.9109086990356445, cross_entropy: 2.9109086990356445 +[2025-04-27 14:11:07,680][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 1.6073133945465088, cross_entropy: 1.6073133945465088 +[2025-04-27 14:11:10,709][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 2.0340237617492676, cross_entropy: 2.0340237617492676 +[2025-04-27 14:11:11,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.3285465240478516, cross_entropy: 3.3285465240478516 +[2025-04-27 14:11:14,004][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.549436092376709, cross_entropy: 2.549436092376709 +[2025-04-27 14:11:14,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.8287676572799683, cross_entropy: 1.8287676572799683 +[2025-04-27 14:11:17,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 1.5570135116577148, cross_entropy: 1.5570135116577148 +[2025-04-27 14:11:18,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.3504207134246826, cross_entropy: 1.3504207134246826 +[2025-04-27 14:11:21,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 3.3174946308135986, cross_entropy: 3.3174946308135986 +[2025-04-27 14:11:21,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 3.1486992835998535, cross_entropy: 3.1486992835998535 +[2025-04-27 14:11:25,248][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.764218330383301, cross_entropy: 2.764218330383301 +[2025-04-27 14:11:25,594][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.4499499797821045, cross_entropy: 2.4499499797821045 +[2025-04-27 14:11:29,117][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.8948097229003906, cross_entropy: 1.8948097229003906 +[2025-04-27 14:11:29,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.5471723079681396, cross_entropy: 1.5471723079681396 +[2025-04-27 14:11:32,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.406686782836914, cross_entropy: 3.406686782836914 +[2025-04-27 14:11:32,705][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 1.6566352844238281, cross_entropy: 1.6566352844238281 +[2025-04-27 14:11:35,570][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 1.7190077304840088, cross_entropy: 1.7190077304840088 +[2025-04-27 14:11:35,883][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.5317881107330322, cross_entropy: 1.5317881107330322 +[2025-04-27 14:11:39,913][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 2.1161904335021973, cross_entropy: 2.1161904335021973 +[2025-04-27 14:11:40,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 2.7055416107177734, cross_entropy: 2.7055416107177734 +[2025-04-27 14:11:43,716][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.583678126335144, cross_entropy: 1.583678126335144 +[2025-04-27 14:11:44,048][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.5851876735687256, cross_entropy: 3.5851876735687256 +[2025-04-27 14:11:46,763][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.239729881286621, cross_entropy: 3.239729881286621 +[2025-04-27 14:11:47,081][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 1.8646953105926514, cross_entropy: 1.8646953105926514 +[2025-04-27 14:11:50,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 1.747787356376648, cross_entropy: 1.747787356376648 +[2025-04-27 14:11:50,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.3887767791748047, cross_entropy: 3.3887767791748047 +[2025-04-27 14:11:54,558][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.274643898010254, cross_entropy: 2.274643898010254 +[2025-04-27 14:11:54,893][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 2.913651704788208, cross_entropy: 2.913651704788208 +[2025-04-27 14:11:58,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 1.822069525718689, cross_entropy: 1.822069525718689 +[2025-04-27 14:11:58,551][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.3105851411819458, cross_entropy: 1.3105851411819458 +[2025-04-27 14:12:01,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.5022079944610596, cross_entropy: 2.5022079944610596 +[2025-04-27 14:12:01,873][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 3.0024819374084473, cross_entropy: 3.0024819374084473 +[2025-04-27 14:12:05,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.941360354423523, cross_entropy: 1.941360354423523 +[2025-04-27 14:12:05,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 2.993410348892212, cross_entropy: 2.993410348892212 +[2025-04-27 14:12:08,911][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.900707483291626, cross_entropy: 2.900707483291626 +[2025-04-27 14:12:09,245][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.3068649768829346, cross_entropy: 1.3068649768829346 +[2025-04-27 14:12:13,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.1814749240875244, cross_entropy: 2.1814749240875244 +[2025-04-27 14:12:13,355][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.767004370689392, cross_entropy: 1.767004370689392 +[2025-04-27 14:12:16,587][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.462139368057251, cross_entropy: 3.462139368057251 +[2025-04-27 14:12:16,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 3.122711181640625, cross_entropy: 3.122711181640625 +[2025-04-27 14:12:20,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.572759985923767, cross_entropy: 1.572759985923767 +[2025-04-27 14:12:20,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.4994330406188965, cross_entropy: 1.4994330406188965 +[2025-04-27 14:12:23,872][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.764793872833252, cross_entropy: 1.764793872833252 +[2025-04-27 14:12:24,188][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.8633626699447632, cross_entropy: 1.8633626699447632 +[2025-04-27 14:12:27,003][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 1.544801950454712, cross_entropy: 1.544801950454712 +[2025-04-27 14:12:27,348][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 1.6112151145935059, cross_entropy: 1.6112151145935059 +[2025-04-27 14:12:30,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 3.0099148750305176, cross_entropy: 3.0099148750305176 +[2025-04-27 14:12:30,849][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.1292762756347656, cross_entropy: 3.1292762756347656 +[2025-04-27 14:12:33,581][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.6694250106811523, cross_entropy: 1.6694250106811523 +[2025-04-27 14:12:33,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.8643381595611572, cross_entropy: 1.8643381595611572 +[2025-04-27 14:12:36,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.4425532817840576, cross_entropy: 2.4425532817840576 +[2025-04-27 14:15:18,079][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.3259198665618896, cross_entropy: 2.3259198665618896 +[2025-04-27 14:15:18,079][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.538265585899353, cross_entropy: 1.538265585899353 +[2025-04-27 14:15:18,292][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 14:15:18,452][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch3.pth. +[2025-04-27 14:15:18,658][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 14:15:23,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.1974177360534668, cross_entropy: 1.1974177360534668 +[2025-04-27 14:15:23,398][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 1.4482501745224, cross_entropy: 1.4482501745224 +[2025-04-27 14:15:26,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.587324619293213, cross_entropy: 1.587324619293213 +[2025-04-27 14:15:26,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.302783727645874, cross_entropy: 1.302783727645874 +[2025-04-27 14:15:30,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 1.6828672885894775, cross_entropy: 1.6828672885894775 +[2025-04-27 14:15:30,437][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.6465678215026855, cross_entropy: 1.6465678215026855 +[2025-04-27 14:15:33,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.3380788564682007, cross_entropy: 1.3380788564682007 +[2025-04-27 14:15:33,782][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 3.0638298988342285, cross_entropy: 3.0638298988342285 +[2025-04-27 14:15:36,837][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.8224736452102661, cross_entropy: 1.8224736452102661 +[2025-04-27 14:15:37,152][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.530969262123108, cross_entropy: 1.530969262123108 +[2025-04-27 14:15:40,171][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.2201778888702393, cross_entropy: 3.2201778888702393 +[2025-04-27 14:15:40,756][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.308359146118164, cross_entropy: 2.308359146118164 +[2025-04-27 14:15:43,330][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 1.5968149900436401, cross_entropy: 1.5968149900436401 +[2025-04-27 14:15:44,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.90164852142334, cross_entropy: 2.90164852142334 +[2025-04-27 14:15:46,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 1.301255702972412, cross_entropy: 1.301255702972412 +[2025-04-27 14:15:47,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.5700695514678955, cross_entropy: 1.5700695514678955 +[2025-04-27 14:15:49,446][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.2226576805114746, cross_entropy: 2.2226576805114746 +[2025-04-27 14:15:50,262][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 3.4201316833496094, cross_entropy: 3.4201316833496094 +[2025-04-27 14:15:53,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.3356475830078125, cross_entropy: 3.3356475830078125 +[2025-04-27 14:15:54,299][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.366476535797119, cross_entropy: 2.366476535797119 +[2025-04-27 14:15:57,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 1.5784417390823364, cross_entropy: 1.5784417390823364 +[2025-04-27 14:15:57,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.6742416620254517, cross_entropy: 1.6742416620254517 +[2025-04-27 14:16:00,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.750897169113159, cross_entropy: 2.750897169113159 +[2025-04-27 14:16:01,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 3.021979808807373, cross_entropy: 3.021979808807373 +[2025-04-27 14:16:04,459][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.6063525676727295, cross_entropy: 2.6063525676727295 +[2025-04-27 14:16:04,773][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.4027576446533203, cross_entropy: 1.4027576446533203 +[2025-04-27 14:16:08,929][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.164494037628174, cross_entropy: 2.164494037628174 +[2025-04-27 14:16:09,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.096252918243408, cross_entropy: 3.096252918243408 +[2025-04-27 14:16:12,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 1.88823664188385, cross_entropy: 1.88823664188385 +[2025-04-27 14:16:12,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.3756649494171143, cross_entropy: 2.3756649494171143 +[2025-04-27 14:16:15,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 2.7148611545562744, cross_entropy: 2.7148611545562744 +[2025-04-27 14:16:16,021][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.3278604745864868, cross_entropy: 1.3278604745864868 +[2025-04-27 14:16:19,318][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 1.7083218097686768, cross_entropy: 1.7083218097686768 +[2025-04-27 14:16:19,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 3.3712754249572754, cross_entropy: 3.3712754249572754 +[2025-04-27 14:16:22,522][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.93881893157959, cross_entropy: 2.93881893157959 +[2025-04-27 14:16:22,856][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 1.2541718482971191, cross_entropy: 1.2541718482971191 +[2025-04-27 14:16:26,329][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.4662710428237915, cross_entropy: 1.4662710428237915 +[2025-04-27 14:16:26,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 1.6697980165481567, cross_entropy: 1.6697980165481567 +[2025-04-27 14:16:29,604][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.564190626144409, cross_entropy: 3.564190626144409 +[2025-04-27 14:16:29,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 2.644670009613037, cross_entropy: 2.644670009613037 +[2025-04-27 14:16:33,657][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 1.4553020000457764, cross_entropy: 1.4553020000457764 +[2025-04-27 14:16:33,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 1.7249237298965454, cross_entropy: 1.7249237298965454 +[2025-04-27 14:16:36,982][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.0562729835510254, cross_entropy: 2.0562729835510254 +[2025-04-27 14:16:37,294][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.4326114654541016, cross_entropy: 2.4326114654541016 +[2025-04-27 14:16:40,756][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 2.357154369354248, cross_entropy: 2.357154369354248 +[2025-04-27 14:16:41,093][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.4304800033569336, cross_entropy: 2.4304800033569336 +[2025-04-27 14:16:43,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 1.9361436367034912, cross_entropy: 1.9361436367034912 +[2025-04-27 14:16:43,990][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 2.1427555084228516, cross_entropy: 2.1427555084228516 +[2025-04-27 14:16:47,345][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.2224911451339722, cross_entropy: 1.2224911451339722 +[2025-04-27 14:16:47,680][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.757138252258301, cross_entropy: 2.757138252258301 +[2025-04-27 14:16:50,790][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.5117274522781372, cross_entropy: 1.5117274522781372 +[2025-04-27 14:16:51,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.2527105808258057, cross_entropy: 1.2527105808258057 +[2025-04-27 14:16:54,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 1.6591535806655884, cross_entropy: 1.6591535806655884 +[2025-04-27 14:16:54,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.1978917121887207, cross_entropy: 2.1978917121887207 +[2025-04-27 14:16:57,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 3.14878511428833, cross_entropy: 3.14878511428833 +[2025-04-27 14:16:58,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.9043874740600586, cross_entropy: 1.9043874740600586 +[2025-04-27 14:17:00,916][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 1.5512614250183105, cross_entropy: 1.5512614250183105 +[2025-04-27 14:17:01,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 3.113640069961548, cross_entropy: 3.113640069961548 +[2025-04-27 14:17:04,915][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 1.6683003902435303, cross_entropy: 1.6683003902435303 +[2025-04-27 14:17:05,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.9878008365631104, cross_entropy: 2.9878008365631104 +[2025-04-27 14:17:07,478][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.6725175380706787, cross_entropy: 1.6725175380706787 +[2025-04-27 14:17:07,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.0586023330688477, cross_entropy: 2.0586023330688477 +[2025-04-27 14:17:10,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 2.7931647300720215, cross_entropy: 2.7931647300720215 +[2025-04-27 14:17:11,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 2.313889503479004, cross_entropy: 2.313889503479004 +[2025-04-27 14:17:14,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.6129603385925293, cross_entropy: 2.6129603385925293 +[2025-04-27 14:17:14,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.584500789642334, cross_entropy: 1.584500789642334 +[2025-04-27 14:17:17,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.7582545280456543, cross_entropy: 2.7582545280456543 +[2025-04-27 14:17:18,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 1.612165927886963, cross_entropy: 1.612165927886963 +[2025-04-27 14:17:22,009][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 1.987478494644165, cross_entropy: 1.987478494644165 +[2025-04-27 14:17:22,321][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.6002204418182373, cross_entropy: 2.6002204418182373 +[2025-04-27 14:17:25,217][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.325556993484497, cross_entropy: 2.325556993484497 +[2025-04-27 14:17:25,554][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.6530449390411377, cross_entropy: 1.6530449390411377 +[2025-04-27 14:17:28,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.3768470287322998, cross_entropy: 1.3768470287322998 +[2025-04-27 14:17:28,845][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.5425965785980225, cross_entropy: 1.5425965785980225 +[2025-04-27 14:17:31,565][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 2.3348617553710938, cross_entropy: 2.3348617553710938 +[2025-04-27 14:17:31,908][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 1.4277889728546143, cross_entropy: 1.4277889728546143 +[2025-04-27 14:17:34,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.0863884687423706, cross_entropy: 1.0863884687423706 +[2025-04-27 14:17:34,647][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 1.309791088104248, cross_entropy: 1.309791088104248 +[2025-04-27 14:17:37,322][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 3.4585609436035156, cross_entropy: 3.4585609436035156 +[2025-04-27 14:17:37,658][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.3962644338607788, cross_entropy: 1.3962644338607788 +[2025-04-27 14:17:40,356][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 1.9754716157913208, cross_entropy: 1.9754716157913208 +[2025-04-27 14:17:40,670][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.812889575958252, cross_entropy: 2.812889575958252 +[2025-04-27 14:17:43,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 1.2020487785339355, cross_entropy: 1.2020487785339355 +[2025-04-27 14:17:44,105][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.3158124685287476, cross_entropy: 1.3158124685287476 +[2025-04-27 14:17:46,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.7884318828582764, cross_entropy: 1.7884318828582764 +[2025-04-27 14:17:47,289][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 3.4911861419677734, cross_entropy: 3.4911861419677734 +[2025-04-27 14:17:51,046][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.1411373615264893, cross_entropy: 1.1411373615264893 +[2025-04-27 14:17:51,382][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 0.9401970505714417, cross_entropy: 0.9401970505714417 +[2025-04-27 14:17:54,594][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 0.9717867970466614, cross_entropy: 0.9717867970466614 +[2025-04-27 14:17:54,931][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 2.271986484527588, cross_entropy: 2.271986484527588 +[2025-04-27 14:17:57,848][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.174062967300415, cross_entropy: 3.174062967300415 +[2025-04-27 14:17:58,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.6421115398406982, cross_entropy: 1.6421115398406982 +[2025-04-27 14:18:01,471][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.2116392850875854, cross_entropy: 1.2116392850875854 +[2025-04-27 14:18:01,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 1.9144312143325806, cross_entropy: 1.9144312143325806 +[2025-04-27 14:18:05,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 3.494847536087036, cross_entropy: 3.494847536087036 +[2025-04-27 14:18:05,718][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.6902202367782593, cross_entropy: 1.6902202367782593 +[2025-04-27 14:18:08,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 3.129349708557129, cross_entropy: 3.129349708557129 +[2025-04-27 14:18:08,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.6445937156677246, cross_entropy: 1.6445937156677246 +[2025-04-27 14:18:12,178][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 2.603820323944092, cross_entropy: 2.603820323944092 +[2025-04-27 14:18:12,493][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.0184824466705322, cross_entropy: 1.0184824466705322 +[2025-04-27 14:18:15,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 2.040426015853882, cross_entropy: 2.040426015853882 +[2025-04-27 14:18:16,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.7142157554626465, cross_entropy: 2.7142157554626465 +[2025-04-27 14:18:19,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.714961051940918, cross_entropy: 2.714961051940918 +[2025-04-27 14:18:19,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 1.559309482574463, cross_entropy: 1.559309482574463 +[2025-04-27 14:18:22,263][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.205166816711426, cross_entropy: 2.205166816711426 +[2025-04-27 14:18:23,376][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.281646966934204, cross_entropy: 1.281646966934204 +[2025-04-27 14:18:25,953][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.5220870971679688, cross_entropy: 3.5220870971679688 +[2025-04-27 14:18:27,328][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 1.7019199132919312, cross_entropy: 1.7019199132919312 +[2025-04-27 14:18:28,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 3.342803716659546, cross_entropy: 3.342803716659546 +[2025-04-27 14:18:30,559][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 2.758789539337158, cross_entropy: 2.758789539337158 +[2025-04-27 14:18:32,626][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.4345765113830566, cross_entropy: 2.4345765113830566 +[2025-04-27 14:18:34,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 2.1463241577148438, cross_entropy: 2.1463241577148438 +[2025-04-27 14:18:36,651][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 2.75807523727417, cross_entropy: 2.75807523727417 +[2025-04-27 14:18:38,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.3031861782073975, cross_entropy: 2.3031861782073975 +[2025-04-27 14:18:40,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 0.9181036949157715, cross_entropy: 0.9181036949157715 +[2025-04-27 14:18:41,355][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.5480096340179443, cross_entropy: 2.5480096340179443 +[2025-04-27 14:18:43,839][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.8310909271240234, cross_entropy: 2.8310909271240234 +[2025-04-27 14:18:45,851][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.4596333503723145, cross_entropy: 1.4596333503723145 +[2025-04-27 14:18:47,604][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.2367342710494995, cross_entropy: 1.2367342710494995 +[2025-04-27 14:18:49,239][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 1.7555192708969116, cross_entropy: 1.7555192708969116 +[2025-04-27 14:18:50,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.56305193901062, cross_entropy: 3.56305193901062 +[2025-04-27 14:18:52,439][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 3.424823760986328, cross_entropy: 3.424823760986328 +[2025-04-27 14:18:55,285][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.9653565883636475, cross_entropy: 2.9653565883636475 +[2025-04-27 14:18:55,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 3.052658796310425, cross_entropy: 3.052658796310425 +[2025-04-27 14:18:59,243][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.3374240398406982, cross_entropy: 1.3374240398406982 +[2025-04-27 14:18:59,581][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.2502301931381226, cross_entropy: 1.2502301931381226 +[2025-04-27 14:19:02,392][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 1.7421903610229492, cross_entropy: 1.7421903610229492 +[2025-04-27 14:19:02,734][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.8942601680755615, cross_entropy: 2.8942601680755615 +[2025-04-27 14:19:06,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 2.0630805492401123, cross_entropy: 2.0630805492401123 +[2025-04-27 14:19:06,789][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 1.010462760925293, cross_entropy: 1.010462760925293 +[2025-04-27 14:19:09,681][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 1.3926610946655273, cross_entropy: 1.3926610946655273 +[2025-04-27 14:19:10,033][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.979410171508789, cross_entropy: 2.979410171508789 +[2025-04-27 14:19:13,938][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.905280113220215, cross_entropy: 2.905280113220215 +[2025-04-27 14:19:14,258][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.7377235889434814, cross_entropy: 1.7377235889434814 +[2025-04-27 14:19:17,504][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.4508137702941895, cross_entropy: 1.4508137702941895 +[2025-04-27 14:19:17,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.874807357788086, cross_entropy: 2.874807357788086 +[2025-04-27 14:19:20,388][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 1.3377764225006104, cross_entropy: 1.3377764225006104 +[2025-04-27 14:19:20,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 1.15248703956604, cross_entropy: 1.15248703956604 +[2025-04-27 14:19:24,179][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.3338801860809326, cross_entropy: 1.3338801860809326 +[2025-04-27 14:19:24,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.4009430408477783, cross_entropy: 2.4009430408477783 +[2025-04-27 14:19:27,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.0601894855499268, cross_entropy: 3.0601894855499268 +[2025-04-27 14:19:27,706][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 3.209181785583496, cross_entropy: 3.209181785583496 +[2025-04-27 14:19:31,446][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 1.3532873392105103, cross_entropy: 1.3532873392105103 +[2025-04-27 14:19:31,777][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.693544387817383, cross_entropy: 2.693544387817383 +[2025-04-27 14:19:34,762][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 1.504037618637085, cross_entropy: 1.504037618637085 +[2025-04-27 14:19:35,073][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.276715636253357, cross_entropy: 1.276715636253357 +[2025-04-27 14:19:38,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 3.2488322257995605, cross_entropy: 3.2488322257995605 +[2025-04-27 14:19:39,063][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 1.5541865825653076, cross_entropy: 1.5541865825653076 +[2025-04-27 14:19:41,718][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 2.552647113800049, cross_entropy: 2.552647113800049 +[2025-04-27 14:19:42,060][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 1.695651888847351, cross_entropy: 1.695651888847351 +[2025-04-27 14:19:44,697][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.6085090637207031, cross_entropy: 1.6085090637207031 +[2025-04-27 14:19:45,031][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 1.5704200267791748, cross_entropy: 1.5704200267791748 +[2025-04-27 14:19:47,666][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.2228515148162842, cross_entropy: 1.2228515148162842 +[2025-04-27 14:19:47,993][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.484431266784668, cross_entropy: 1.484431266784668 +[2025-04-27 14:19:50,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.3446896076202393, cross_entropy: 1.3446896076202393 +[2025-04-27 14:19:51,296][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.851375102996826, cross_entropy: 2.851375102996826 +[2025-04-27 14:19:54,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 1.640357255935669, cross_entropy: 1.640357255935669 +[2025-04-27 14:19:54,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 1.3802225589752197, cross_entropy: 1.3802225589752197 +[2025-04-27 14:19:57,461][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.3841793537139893, cross_entropy: 3.3841793537139893 +[2025-04-27 14:19:57,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 3.021681308746338, cross_entropy: 3.021681308746338 +[2025-04-27 14:20:00,920][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 3.054713010787964, cross_entropy: 3.054713010787964 +[2025-04-27 14:20:01,237][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 2.6767609119415283, cross_entropy: 2.6767609119415283 +[2025-04-27 14:20:04,615][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 0.7902114987373352, cross_entropy: 0.7902114987373352 +[2025-04-27 14:20:04,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.7753312587738037, cross_entropy: 2.7753312587738037 +[2025-04-27 14:20:08,115][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.6154632568359375, cross_entropy: 1.6154632568359375 +[2025-04-27 14:20:08,449][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.782461404800415, cross_entropy: 1.782461404800415 +[2025-04-27 14:20:11,808][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.3529175519943237, cross_entropy: 1.3529175519943237 +[2025-04-27 14:20:12,120][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.171730637550354, cross_entropy: 1.171730637550354 +[2025-04-27 14:20:15,445][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.5056214332580566, cross_entropy: 1.5056214332580566 +[2025-04-27 14:20:15,780][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 0.8759779334068298, cross_entropy: 0.8759779334068298 +[2025-04-27 14:20:18,794][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 2.9341158866882324, cross_entropy: 2.9341158866882324 +[2025-04-27 14:20:19,108][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 2.8185067176818848, cross_entropy: 2.8185067176818848 +[2025-04-27 14:20:22,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 3.475558042526245, cross_entropy: 3.475558042526245 +[2025-04-27 14:20:22,408][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 3.1114416122436523, cross_entropy: 3.1114416122436523 +[2025-04-27 14:20:25,905][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 1.412128210067749, cross_entropy: 1.412128210067749 +[2025-04-27 14:20:26,216][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 1.3268728256225586, cross_entropy: 1.3268728256225586 +[2025-04-27 14:20:29,703][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 3.4377083778381348, cross_entropy: 3.4377083778381348 +[2025-04-27 14:20:30,017][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 2.8518617153167725, cross_entropy: 2.8518617153167725 +[2025-04-27 14:20:33,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 2.6344499588012695, cross_entropy: 2.6344499588012695 +[2025-04-27 14:20:33,730][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.891861915588379, cross_entropy: 1.891861915588379 +[2025-04-27 14:20:37,107][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 1.3148603439331055, cross_entropy: 1.3148603439331055 +[2025-04-27 14:20:37,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.6320877075195312, cross_entropy: 1.6320877075195312 +[2025-04-27 14:20:40,580][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.4903004169464111, cross_entropy: 1.4903004169464111 +[2025-04-27 14:20:40,921][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 2.8771352767944336, cross_entropy: 2.8771352767944336 +[2025-04-27 14:20:44,339][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.4648842811584473, cross_entropy: 2.4648842811584473 +[2025-04-27 14:20:44,674][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 1.688126564025879, cross_entropy: 1.688126564025879 +[2025-04-27 14:20:48,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.568234920501709, cross_entropy: 1.568234920501709 +[2025-04-27 14:20:49,134][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.5222967863082886, cross_entropy: 1.5222967863082886 +[2025-04-27 14:20:52,189][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.8904190063476562, cross_entropy: 1.8904190063476562 +[2025-04-27 14:20:52,543][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 2.5658745765686035, cross_entropy: 2.5658745765686035 +[2025-04-27 14:20:55,896][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 1.40068519115448, cross_entropy: 1.40068519115448 +[2025-04-27 14:20:56,229][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 3.1116256713867188, cross_entropy: 3.1116256713867188 +[2025-04-27 14:20:59,339][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 1.5697999000549316, cross_entropy: 1.5697999000549316 +[2025-04-27 14:20:59,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 0.955759584903717, cross_entropy: 0.955759584903717 +[2025-04-27 14:21:03,050][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.3364752531051636, cross_entropy: 1.3364752531051636 +[2025-04-27 14:21:03,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 3.115878105163574, cross_entropy: 3.115878105163574 +[2025-04-27 14:21:06,132][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 1.4751172065734863, cross_entropy: 1.4751172065734863 +[2025-04-27 14:21:06,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 3.3579206466674805, cross_entropy: 3.3579206466674805 +[2025-04-27 14:21:09,432][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 2.529646635055542, cross_entropy: 2.529646635055542 +[2025-04-27 14:21:09,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 2.957043170928955, cross_entropy: 2.957043170928955 +[2025-04-27 14:21:12,754][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 2.0000529289245605, cross_entropy: 2.0000529289245605 +[2025-04-27 14:21:13,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 1.8506107330322266, cross_entropy: 1.8506107330322266 +[2025-04-27 14:21:16,049][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.9115872383117676, cross_entropy: 2.9115872383117676 +[2025-04-27 14:21:16,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.487821102142334, cross_entropy: 1.487821102142334 +[2025-04-27 14:21:19,475][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 2.1217870712280273, cross_entropy: 2.1217870712280273 +[2025-04-27 14:21:19,786][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 1.3437962532043457, cross_entropy: 1.3437962532043457 +[2025-04-27 14:21:23,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 2.323991298675537, cross_entropy: 2.323991298675537 +[2025-04-27 14:21:23,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 1.8818345069885254, cross_entropy: 1.8818345069885254 +[2025-04-27 14:21:26,606][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 3.2706003189086914, cross_entropy: 3.2706003189086914 +[2025-04-27 14:21:26,941][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 1.3664088249206543, cross_entropy: 1.3664088249206543 +[2025-04-27 14:21:29,756][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.1403915882110596, cross_entropy: 1.1403915882110596 +[2025-04-27 14:21:30,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 1.6036022901535034, cross_entropy: 1.6036022901535034 +[2025-04-27 14:21:33,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 1.2684850692749023, cross_entropy: 1.2684850692749023 +[2025-04-27 14:21:33,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 2.23836612701416, cross_entropy: 2.23836612701416 +[2025-04-27 14:21:36,764][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.4781439304351807, cross_entropy: 2.4781439304351807 +[2025-04-27 14:21:37,077][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.0424787998199463, cross_entropy: 2.0424787998199463 +[2025-04-27 14:21:39,796][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 2.0523338317871094, cross_entropy: 2.0523338317871094 +[2025-04-27 14:21:40,133][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.53008770942688, cross_entropy: 2.53008770942688 +[2025-04-27 14:21:42,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.5170953273773193, cross_entropy: 1.5170953273773193 +[2025-04-27 14:21:43,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.204838752746582, cross_entropy: 2.204838752746582 +[2025-04-27 14:21:46,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 3.1070938110351562, cross_entropy: 3.1070938110351562 +[2025-04-27 14:21:46,574][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 1.891633152961731, cross_entropy: 1.891633152961731 +[2025-04-27 14:21:49,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 3.387052297592163, cross_entropy: 3.387052297592163 +[2025-04-27 14:21:49,663][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.4028220176696777, cross_entropy: 2.4028220176696777 +[2025-04-27 14:21:53,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 2.128230094909668, cross_entropy: 2.128230094909668 +[2025-04-27 14:21:53,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.064568042755127, cross_entropy: 3.064568042755127 +[2025-04-27 14:21:57,609][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 3.0792760848999023, cross_entropy: 3.0792760848999023 +[2025-04-27 14:21:57,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 3.1016836166381836, cross_entropy: 3.1016836166381836 +[2025-04-27 14:22:00,692][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.22819185256958, cross_entropy: 3.22819185256958 +[2025-04-27 14:22:01,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.2229629755020142, cross_entropy: 1.2229629755020142 +[2025-04-27 14:22:04,296][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.6250240802764893, cross_entropy: 2.6250240802764893 +[2025-04-27 14:22:04,633][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.280529022216797, cross_entropy: 2.280529022216797 +[2025-04-27 14:22:07,071][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.8801989555358887, cross_entropy: 2.8801989555358887 +[2025-04-27 14:22:07,383][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.3289107084274292, cross_entropy: 1.3289107084274292 +[2025-04-27 14:22:11,381][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.6849844455718994, cross_entropy: 1.6849844455718994 +[2025-04-27 14:22:11,717][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.229499340057373, cross_entropy: 2.229499340057373 +[2025-04-27 14:22:14,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 3.111818790435791, cross_entropy: 3.111818790435791 +[2025-04-27 14:22:14,907][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.430824041366577, cross_entropy: 2.430824041366577 +[2025-04-27 14:22:18,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.137408971786499, cross_entropy: 3.137408971786499 +[2025-04-27 14:22:18,544][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 2.9817733764648438, cross_entropy: 2.9817733764648438 +[2025-04-27 14:22:21,945][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 1.5163507461547852, cross_entropy: 1.5163507461547852 +[2025-04-27 14:22:22,275][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.9901413917541504, cross_entropy: 2.9901413917541504 +[2025-04-27 14:22:25,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 1.2955645322799683, cross_entropy: 1.2955645322799683 +[2025-04-27 14:22:25,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 1.6032816171646118, cross_entropy: 1.6032816171646118 +[2025-04-27 14:22:28,232][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.3915599584579468, cross_entropy: 1.3915599584579468 +[2025-04-27 14:22:28,569][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 1.5754735469818115, cross_entropy: 1.5754735469818115 +[2025-04-27 14:22:31,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.3208601474761963, cross_entropy: 2.3208601474761963 +[2025-04-27 14:22:32,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.850971221923828, cross_entropy: 2.850971221923828 +[2025-04-27 14:22:35,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.5955891609191895, cross_entropy: 2.5955891609191895 +[2025-04-27 14:22:36,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.3880847692489624, cross_entropy: 1.3880847692489624 +[2025-04-27 14:22:38,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 3.2322933673858643, cross_entropy: 3.2322933673858643 +[2025-04-27 14:22:38,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 2.2860355377197266, cross_entropy: 2.2860355377197266 +[2025-04-27 14:22:42,266][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 3.189697265625, cross_entropy: 3.189697265625 +[2025-04-27 14:22:42,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 3.1115474700927734, cross_entropy: 3.1115474700927734 +[2025-04-27 14:22:45,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.821206569671631, cross_entropy: 2.821206569671631 +[2025-04-27 14:22:46,058][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 3.242426633834839, cross_entropy: 3.242426633834839 +[2025-04-27 14:22:49,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 1.20771324634552, cross_entropy: 1.20771324634552 +[2025-04-27 14:22:49,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.1549696922302246, cross_entropy: 1.1549696922302246 +[2025-04-27 14:22:53,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 2.5535922050476074, cross_entropy: 2.5535922050476074 +[2025-04-27 14:22:53,481][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.1849408149719238, cross_entropy: 1.1849408149719238 +[2025-04-27 14:22:57,132][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 2.5753095149993896, cross_entropy: 2.5753095149993896 +[2025-04-27 14:22:57,446][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 1.6003135442733765, cross_entropy: 1.6003135442733765 +[2025-04-27 14:23:00,335][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 3.038944959640503, cross_entropy: 3.038944959640503 +[2025-04-27 14:23:00,716][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 1.3026686906814575, cross_entropy: 1.3026686906814575 +[2025-04-27 14:23:03,430][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 1.3379348516464233, cross_entropy: 1.3379348516464233 +[2025-04-27 14:23:04,593][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.0590200424194336, cross_entropy: 2.0590200424194336 +[2025-04-27 14:23:07,376][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 1.1925582885742188, cross_entropy: 1.1925582885742188 +[2025-04-27 14:23:07,770][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 3.0887856483459473, cross_entropy: 3.0887856483459473 +[2025-04-27 14:23:10,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 3.139843702316284, cross_entropy: 3.139843702316284 +[2025-04-27 14:23:11,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.734032392501831, cross_entropy: 1.734032392501831 +[2025-04-27 14:23:14,587][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.5826845169067383, cross_entropy: 2.5826845169067383 +[2025-04-27 14:23:15,046][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 0.9737714529037476, cross_entropy: 0.9737714529037476 +[2025-04-27 14:23:17,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 1.490187406539917, cross_entropy: 1.490187406539917 +[2025-04-27 14:23:18,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 1.9933838844299316, cross_entropy: 1.9933838844299316 +[2025-04-27 14:23:21,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 2.0899031162261963, cross_entropy: 2.0899031162261963 +[2025-04-27 14:23:22,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 1.4565016031265259, cross_entropy: 1.4565016031265259 +[2025-04-27 14:23:25,888][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 1.98346745967865, cross_entropy: 1.98346745967865 +[2025-04-27 14:23:26,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 1.4785128831863403, cross_entropy: 1.4785128831863403 +[2025-04-27 14:23:29,137][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 2.0140380859375, cross_entropy: 2.0140380859375 +[2025-04-27 14:23:29,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 1.634514570236206, cross_entropy: 1.634514570236206 +[2025-04-27 14:23:32,946][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 2.0952465534210205, cross_entropy: 2.0952465534210205 +[2025-04-27 14:23:33,259][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 2.878452777862549, cross_entropy: 2.878452777862549 +[2025-04-27 14:23:36,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 2.1734185218811035, cross_entropy: 2.1734185218811035 +[2025-04-27 14:23:37,280][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 1.5930202007293701, cross_entropy: 1.5930202007293701 +[2025-04-27 14:23:40,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 1.086615800857544, cross_entropy: 1.086615800857544 +[2025-04-27 14:23:40,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.8159642219543457, cross_entropy: 2.8159642219543457 +[2025-04-27 14:23:43,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.0079445838928223, cross_entropy: 3.0079445838928223 +[2025-04-27 14:23:44,157][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 3.055000066757202, cross_entropy: 3.055000066757202 +[2025-04-27 14:23:46,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4484879970550537, cross_entropy: 1.4484879970550537 +[2025-04-27 14:23:47,243][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 0.9797121286392212, cross_entropy: 0.9797121286392212 +[2025-04-27 14:23:50,194][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 1.537489891052246, cross_entropy: 1.537489891052246 +[2025-04-27 14:23:50,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 2.5020601749420166, cross_entropy: 2.5020601749420166 +[2025-04-27 14:23:54,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.5904409885406494, cross_entropy: 1.5904409885406494 +[2025-04-27 14:23:54,432][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 1.5738883018493652, cross_entropy: 1.5738883018493652 +[2025-04-27 14:23:57,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 1.5742404460906982, cross_entropy: 1.5742404460906982 +[2025-04-27 14:23:57,631][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 1.1947119235992432, cross_entropy: 1.1947119235992432 +[2025-04-27 14:24:02,008][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.3845202922821045, cross_entropy: 2.3845202922821045 +[2025-04-27 14:24:02,343][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.4712703227996826, cross_entropy: 1.4712703227996826 +[2025-04-27 14:24:05,288][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.878657341003418, cross_entropy: 2.878657341003418 +[2025-04-27 14:24:05,630][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 1.4228804111480713, cross_entropy: 1.4228804111480713 +[2025-04-27 14:24:08,296][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 3.1625778675079346, cross_entropy: 3.1625778675079346 +[2025-04-27 14:24:08,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.826289176940918, cross_entropy: 2.826289176940918 +[2025-04-27 14:24:11,462][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.8875863552093506, cross_entropy: 1.8875863552093506 +[2025-04-27 14:24:11,796][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.7726197242736816, cross_entropy: 1.7726197242736816 +[2025-04-27 14:24:14,770][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 2.8758010864257812, cross_entropy: 2.8758010864257812 +[2025-04-27 14:24:15,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.3342785835266113, cross_entropy: 2.3342785835266113 +[2025-04-27 14:24:17,883][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.9339241981506348, cross_entropy: 1.9339241981506348 +[2025-04-27 14:24:18,221][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 2.445132255554199, cross_entropy: 2.445132255554199 +[2025-04-27 14:24:21,244][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.679462194442749, cross_entropy: 2.679462194442749 +[2025-04-27 14:24:21,581][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.2740895748138428, cross_entropy: 2.2740895748138428 +[2025-04-27 14:24:24,687][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.966613292694092, cross_entropy: 2.966613292694092 +[2025-04-27 14:24:25,041][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.5115386247634888, cross_entropy: 1.5115386247634888 +[2025-04-27 14:24:28,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.440502405166626, cross_entropy: 1.440502405166626 +[2025-04-27 14:24:28,945][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.1646313667297363, cross_entropy: 2.1646313667297363 +[2025-04-27 14:24:31,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 1.9182783365249634, cross_entropy: 1.9182783365249634 +[2025-04-27 14:24:32,141][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.2951676845550537, cross_entropy: 1.2951676845550537 +[2025-04-27 14:24:35,178][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 1.491276741027832, cross_entropy: 1.491276741027832 +[2025-04-27 14:24:35,513][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.980290412902832, cross_entropy: 1.980290412902832 +[2025-04-27 14:24:38,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 1.8095741271972656, cross_entropy: 1.8095741271972656 +[2025-04-27 14:24:39,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 3.2412710189819336, cross_entropy: 3.2412710189819336 +[2025-04-27 14:24:42,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.3811988830566406, cross_entropy: 1.3811988830566406 +[2025-04-27 14:24:42,866][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.4612714052200317, cross_entropy: 1.4612714052200317 +[2025-04-27 14:24:45,581][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.367354393005371, cross_entropy: 2.367354393005371 +[2025-04-27 14:24:45,894][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 0.7936038970947266, cross_entropy: 0.7936038970947266 +[2025-04-27 14:24:48,953][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 3.257502317428589, cross_entropy: 3.257502317428589 +[2025-04-27 14:24:49,289][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.784780502319336, cross_entropy: 2.784780502319336 +[2025-04-27 14:24:52,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 3.072420597076416, cross_entropy: 3.072420597076416 +[2025-04-27 14:24:53,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 1.6147267818450928, cross_entropy: 1.6147267818450928 +[2025-04-27 14:24:56,868][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 1.913598656654358, cross_entropy: 1.913598656654358 +[2025-04-27 14:24:57,205][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.1611055135726929, cross_entropy: 1.1611055135726929 +[2025-04-27 14:25:00,325][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.5163967609405518, cross_entropy: 1.5163967609405518 +[2025-04-27 14:25:00,670][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.3636513948440552, cross_entropy: 1.3636513948440552 +[2025-04-27 14:25:03,702][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 2.4272327423095703, cross_entropy: 2.4272327423095703 +[2025-04-27 14:25:04,014][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 3.100551128387451, cross_entropy: 3.100551128387451 +[2025-04-27 14:25:07,411][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.601790428161621, cross_entropy: 1.601790428161621 +[2025-04-27 14:25:07,749][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.778594970703125, cross_entropy: 2.778594970703125 +[2025-04-27 14:25:10,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 2.150024175643921, cross_entropy: 2.150024175643921 +[2025-04-27 14:25:10,740][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.0767853260040283, cross_entropy: 2.0767853260040283 +[2025-04-27 14:25:13,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 3.101101875305176, cross_entropy: 3.101101875305176 +[2025-04-27 14:25:13,831][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.1547685861587524, cross_entropy: 1.1547685861587524 +[2025-04-27 14:25:16,499][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.777073383331299, cross_entropy: 2.777073383331299 +[2025-04-27 14:25:16,836][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.314786434173584, cross_entropy: 3.314786434173584 +[2025-04-27 14:25:19,568][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 1.282810091972351, cross_entropy: 1.282810091972351 +[2025-04-27 14:25:19,934][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 2.7918002605438232, cross_entropy: 2.7918002605438232 +[2025-04-27 14:25:22,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.1207430362701416, cross_entropy: 2.1207430362701416 +[2025-04-27 14:25:23,040][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 2.9544925689697266, cross_entropy: 2.9544925689697266 +[2025-04-27 14:25:27,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.5003530979156494, cross_entropy: 1.5003530979156494 +[2025-04-27 14:25:27,648][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.9078500270843506, cross_entropy: 2.9078500270843506 +[2025-04-27 14:25:30,565][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.9877889156341553, cross_entropy: 1.9877889156341553 +[2025-04-27 14:25:30,899][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.0073583126068115, cross_entropy: 1.0073583126068115 +[2025-04-27 14:25:34,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.405487298965454, cross_entropy: 1.405487298965454 +[2025-04-27 14:25:34,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 3.1200757026672363, cross_entropy: 3.1200757026672363 +[2025-04-27 14:25:37,638][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 1.7081525325775146, cross_entropy: 1.7081525325775146 +[2025-04-27 14:25:37,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 1.579368233680725, cross_entropy: 1.579368233680725 +[2025-04-27 14:25:40,982][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 1.1016335487365723, cross_entropy: 1.1016335487365723 +[2025-04-27 14:25:41,262][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.3065361976623535, cross_entropy: 3.3065361976623535 +[2025-04-27 14:28:20,045][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.113624095916748, cross_entropy: 2.113624095916748 +[2025-04-27 14:28:20,046][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.3937504291534424, cross_entropy: 1.3937504291534424 +[2025-04-27 14:28:20,270][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 14:28:20,430][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch4.pth. +[2025-04-27 14:28:20,638][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 14:28:25,057][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.3067259788513184, cross_entropy: 2.3067259788513184 +[2025-04-27 14:28:25,489][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.4134488105773926, cross_entropy: 1.4134488105773926 +[2025-04-27 14:28:28,125][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.7338087558746338, cross_entropy: 1.7338087558746338 +[2025-04-27 14:28:28,640][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.3268063068389893, cross_entropy: 1.3268063068389893 +[2025-04-27 14:28:31,494][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.198509693145752, cross_entropy: 1.198509693145752 +[2025-04-27 14:28:32,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.436756134033203, cross_entropy: 2.436756134033203 +[2025-04-27 14:28:34,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.104160785675049, cross_entropy: 2.104160785675049 +[2025-04-27 14:28:35,600][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.0940120220184326, cross_entropy: 2.0940120220184326 +[2025-04-27 14:28:38,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 2.8370840549468994, cross_entropy: 2.8370840549468994 +[2025-04-27 14:28:39,221][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.010321855545044, cross_entropy: 1.010321855545044 +[2025-04-27 14:28:41,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.0067412853240967, cross_entropy: 3.0067412853240967 +[2025-04-27 14:28:43,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.9367287158966064, cross_entropy: 1.9367287158966064 +[2025-04-27 14:28:45,364][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.8576810359954834, cross_entropy: 2.8576810359954834 +[2025-04-27 14:28:46,274][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.140915870666504, cross_entropy: 2.140915870666504 +[2025-04-27 14:28:48,906][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 3.1713714599609375, cross_entropy: 3.1713714599609375 +[2025-04-27 14:28:50,221][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.5822486877441406, cross_entropy: 2.5822486877441406 +[2025-04-27 14:28:52,138][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 2.5851047039031982, cross_entropy: 2.5851047039031982 +[2025-04-27 14:28:53,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 3.0602409839630127, cross_entropy: 3.0602409839630127 +[2025-04-27 14:28:55,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.4640257358551025, cross_entropy: 2.4640257358551025 +[2025-04-27 14:28:57,292][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.2232439517974854, cross_entropy: 1.2232439517974854 +[2025-04-27 14:28:59,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.5080726146697998, cross_entropy: 1.5080726146697998 +[2025-04-27 14:29:01,745][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 1.935289978981018, cross_entropy: 1.935289978981018 +[2025-04-27 14:29:03,996][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.3555517196655273, cross_entropy: 1.3555517196655273 +[2025-04-27 14:29:05,477][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.355591058731079, cross_entropy: 1.355591058731079 +[2025-04-27 14:29:07,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.378991723060608, cross_entropy: 1.378991723060608 +[2025-04-27 14:29:09,341][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.217038631439209, cross_entropy: 1.217038631439209 +[2025-04-27 14:29:11,318][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 0.9085538387298584, cross_entropy: 0.9085538387298584 +[2025-04-27 14:29:12,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.0275118350982666, cross_entropy: 1.0275118350982666 +[2025-04-27 14:29:15,098][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.8253917694091797, cross_entropy: 2.8253917694091797 +[2025-04-27 14:29:16,341][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 2.6317853927612305, cross_entropy: 2.6317853927612305 +[2025-04-27 14:29:18,545][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.4040807485580444, cross_entropy: 1.4040807485580444 +[2025-04-27 14:29:20,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 1.0743677616119385, cross_entropy: 1.0743677616119385 +[2025-04-27 14:29:22,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.542292833328247, cross_entropy: 1.542292833328247 +[2025-04-27 14:29:24,169][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 2.0477795600891113, cross_entropy: 2.0477795600891113 +[2025-04-27 14:29:26,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 1.7930803298950195, cross_entropy: 1.7930803298950195 +[2025-04-27 14:29:28,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.3408548831939697, cross_entropy: 1.3408548831939697 +[2025-04-27 14:29:30,329][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.2040677070617676, cross_entropy: 3.2040677070617676 +[2025-04-27 14:29:31,980][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 1.1523241996765137, cross_entropy: 1.1523241996765137 +[2025-04-27 14:29:34,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 2.826578378677368, cross_entropy: 2.826578378677368 +[2025-04-27 14:29:36,077][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.1688936948776245, cross_entropy: 1.1688936948776245 +[2025-04-27 14:29:38,432][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 2.160991668701172, cross_entropy: 2.160991668701172 +[2025-04-27 14:29:39,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.253049373626709, cross_entropy: 1.253049373626709 +[2025-04-27 14:29:42,624][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.547810673713684, cross_entropy: 1.547810673713684 +[2025-04-27 14:29:43,791][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.131899356842041, cross_entropy: 1.131899356842041 +[2025-04-27 14:29:47,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 1.8360843658447266, cross_entropy: 1.8360843658447266 +[2025-04-27 14:29:47,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.450032353401184, cross_entropy: 1.450032353401184 +[2025-04-27 14:29:50,409][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.7383249998092651, cross_entropy: 1.7383249998092651 +[2025-04-27 14:29:51,029][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.354278802871704, cross_entropy: 1.354278802871704 +[2025-04-27 14:29:54,548][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 3.2637577056884766, cross_entropy: 3.2637577056884766 +[2025-04-27 14:29:55,630][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.382024884223938, cross_entropy: 1.382024884223938 +[2025-04-27 14:29:57,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.5512466430664062, cross_entropy: 2.5512466430664062 +[2025-04-27 14:29:59,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.0317679643630981, cross_entropy: 1.0317679643630981 +[2025-04-27 14:30:01,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.4160325527191162, cross_entropy: 1.4160325527191162 +[2025-04-27 14:30:03,477][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.5495028495788574, cross_entropy: 2.5495028495788574 +[2025-04-27 14:30:05,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.889528751373291, cross_entropy: 2.889528751373291 +[2025-04-27 14:30:07,012][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.390899896621704, cross_entropy: 2.390899896621704 +[2025-04-27 14:30:08,154][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 3.272916316986084, cross_entropy: 3.272916316986084 +[2025-04-27 14:30:10,713][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.811734676361084, cross_entropy: 2.811734676361084 +[2025-04-27 14:30:12,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 1.1105051040649414, cross_entropy: 1.1105051040649414 +[2025-04-27 14:30:13,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 1.06441330909729, cross_entropy: 1.06441330909729 +[2025-04-27 14:30:15,376][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 0.9476073980331421, cross_entropy: 0.9476073980331421 +[2025-04-27 14:30:17,904][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.642120599746704, cross_entropy: 2.642120599746704 +[2025-04-27 14:30:18,831][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 1.9834654331207275, cross_entropy: 1.9834654331207275 +[2025-04-27 14:30:21,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.6464992761611938, cross_entropy: 1.6464992761611938 +[2025-04-27 14:30:22,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 1.5132226943969727, cross_entropy: 1.5132226943969727 +[2025-04-27 14:30:25,398][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 2.1257293224334717, cross_entropy: 2.1257293224334717 +[2025-04-27 14:30:26,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 3.0216195583343506, cross_entropy: 3.0216195583343506 +[2025-04-27 14:30:29,258][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 2.5459444522857666, cross_entropy: 2.5459444522857666 +[2025-04-27 14:30:29,625][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 1.3156729936599731, cross_entropy: 1.3156729936599731 +[2025-04-27 14:30:33,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 3.0184311866760254, cross_entropy: 3.0184311866760254 +[2025-04-27 14:30:33,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.349256992340088, cross_entropy: 3.349256992340088 +[2025-04-27 14:30:36,645][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.2130632400512695, cross_entropy: 2.2130632400512695 +[2025-04-27 14:30:37,861][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.1124714612960815, cross_entropy: 1.1124714612960815 +[2025-04-27 14:30:40,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 2.9485836029052734, cross_entropy: 2.9485836029052734 +[2025-04-27 14:30:41,841][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.1439855098724365, cross_entropy: 2.1439855098724365 +[2025-04-27 14:30:43,812][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 3.1472325325012207, cross_entropy: 3.1472325325012207 +[2025-04-27 14:30:47,415][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 3.0487313270568848, cross_entropy: 3.0487313270568848 +[2025-04-27 14:30:47,757][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.435030460357666, cross_entropy: 1.435030460357666 +[2025-04-27 14:30:51,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.3702921867370605, cross_entropy: 1.3702921867370605 +[2025-04-27 14:30:51,519][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 2.0711669921875, cross_entropy: 2.0711669921875 +[2025-04-27 14:30:54,785][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 1.8042361736297607, cross_entropy: 1.8042361736297607 +[2025-04-27 14:30:55,098][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.9382758140563965, cross_entropy: 2.9382758140563965 +[2025-04-27 14:30:58,957][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.2425522804260254, cross_entropy: 2.2425522804260254 +[2025-04-27 14:30:59,293][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 0.8750919103622437, cross_entropy: 0.8750919103622437 +[2025-04-27 14:31:03,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.083767890930176, cross_entropy: 2.083767890930176 +[2025-04-27 14:31:03,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.321437120437622, cross_entropy: 1.321437120437622 +[2025-04-27 14:31:06,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.110192060470581, cross_entropy: 2.110192060470581 +[2025-04-27 14:31:07,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.1514651775360107, cross_entropy: 1.1514651775360107 +[2025-04-27 14:31:10,034][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.5243170261383057, cross_entropy: 1.5243170261383057 +[2025-04-27 14:31:10,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.8382165431976318, cross_entropy: 1.8382165431976318 +[2025-04-27 14:31:13,371][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 1.846010684967041, cross_entropy: 1.846010684967041 +[2025-04-27 14:31:13,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.266256809234619, cross_entropy: 3.266256809234619 +[2025-04-27 14:31:16,994][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 1.6243475675582886, cross_entropy: 1.6243475675582886 +[2025-04-27 14:31:17,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 0.7569611668586731, cross_entropy: 0.7569611668586731 +[2025-04-27 14:31:20,806][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.077423334121704, cross_entropy: 1.077423334121704 +[2025-04-27 14:31:21,148][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.449923038482666, cross_entropy: 1.449923038482666 +[2025-04-27 14:31:24,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.6911017894744873, cross_entropy: 2.6911017894744873 +[2025-04-27 14:31:24,594][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 1.7877684831619263, cross_entropy: 1.7877684831619263 +[2025-04-27 14:31:27,680][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 2.9835219383239746, cross_entropy: 2.9835219383239746 +[2025-04-27 14:31:28,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3464782238006592, cross_entropy: 1.3464782238006592 +[2025-04-27 14:31:30,914][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 1.2761147022247314, cross_entropy: 1.2761147022247314 +[2025-04-27 14:31:31,250][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.1363110542297363, cross_entropy: 2.1363110542297363 +[2025-04-27 14:31:34,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.2523250579833984, cross_entropy: 1.2523250579833984 +[2025-04-27 14:31:34,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.381620168685913, cross_entropy: 2.381620168685913 +[2025-04-27 14:31:38,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 2.8783743381500244, cross_entropy: 2.8783743381500244 +[2025-04-27 14:31:38,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.1941887140274048, cross_entropy: 1.1941887140274048 +[2025-04-27 14:31:41,182][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 3.019718885421753, cross_entropy: 3.019718885421753 +[2025-04-27 14:31:41,494][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.6207619905471802, cross_entropy: 1.6207619905471802 +[2025-04-27 14:31:44,857][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.6268538236618042, cross_entropy: 1.6268538236618042 +[2025-04-27 14:31:45,171][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.4342787265777588, cross_entropy: 1.4342787265777588 +[2025-04-27 14:31:47,955][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 3.1221537590026855, cross_entropy: 3.1221537590026855 +[2025-04-27 14:31:48,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 2.027742862701416, cross_entropy: 2.027742862701416 +[2025-04-27 14:31:51,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.6842321157455444, cross_entropy: 1.6842321157455444 +[2025-04-27 14:31:52,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 1.1911875009536743, cross_entropy: 1.1911875009536743 +[2025-04-27 14:31:55,617][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.1309893131256104, cross_entropy: 1.1309893131256104 +[2025-04-27 14:31:55,929][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.9467153549194336, cross_entropy: 2.9467153549194336 +[2025-04-27 14:31:59,355][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 1.8525829315185547, cross_entropy: 1.8525829315185547 +[2025-04-27 14:31:59,675][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 2.2786149978637695, cross_entropy: 2.2786149978637695 +[2025-04-27 14:32:02,371][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 2.8622779846191406, cross_entropy: 2.8622779846191406 +[2025-04-27 14:32:02,717][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.813718795776367, cross_entropy: 2.813718795776367 +[2025-04-27 14:32:05,413][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 1.6703053712844849, cross_entropy: 1.6703053712844849 +[2025-04-27 14:32:05,727][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 3.0325939655303955, cross_entropy: 3.0325939655303955 +[2025-04-27 14:32:08,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.3558759689331055, cross_entropy: 3.3558759689331055 +[2025-04-27 14:32:09,014][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.172144889831543, cross_entropy: 2.172144889831543 +[2025-04-27 14:32:11,848][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.468820095062256, cross_entropy: 2.468820095062256 +[2025-04-27 14:32:12,184][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 2.4421496391296387, cross_entropy: 2.4421496391296387 +[2025-04-27 14:32:14,919][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.3509702682495117, cross_entropy: 1.3509702682495117 +[2025-04-27 14:32:15,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 1.9869508743286133, cross_entropy: 1.9869508743286133 +[2025-04-27 14:32:18,298][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.0634164810180664, cross_entropy: 1.0634164810180664 +[2025-04-27 14:32:18,635][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.2000861167907715, cross_entropy: 2.2000861167907715 +[2025-04-27 14:32:21,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.2768224477767944, cross_entropy: 1.2768224477767944 +[2025-04-27 14:32:21,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.8065764904022217, cross_entropy: 1.8065764904022217 +[2025-04-27 14:32:25,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.266911029815674, cross_entropy: 2.266911029815674 +[2025-04-27 14:32:25,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.7886791229248047, cross_entropy: 2.7886791229248047 +[2025-04-27 14:32:28,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.3692537546157837, cross_entropy: 1.3692537546157837 +[2025-04-27 14:32:29,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 1.0973479747772217, cross_entropy: 1.0973479747772217 +[2025-04-27 14:32:32,219][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 3.069758653640747, cross_entropy: 3.069758653640747 +[2025-04-27 14:32:32,556][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 0.7909342050552368, cross_entropy: 0.7909342050552368 +[2025-04-27 14:32:35,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 0.7835155725479126, cross_entropy: 0.7835155725479126 +[2025-04-27 14:32:35,878][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 0.6791166067123413, cross_entropy: 0.6791166067123413 +[2025-04-27 14:32:39,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.662890076637268, cross_entropy: 1.662890076637268 +[2025-04-27 14:32:39,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 3.1216039657592773, cross_entropy: 3.1216039657592773 +[2025-04-27 14:32:42,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 3.1275441646575928, cross_entropy: 3.1275441646575928 +[2025-04-27 14:32:43,025][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.5696780681610107, cross_entropy: 1.5696780681610107 +[2025-04-27 14:32:45,885][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.1089932918548584, cross_entropy: 1.1089932918548584 +[2025-04-27 14:32:46,221][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 0.9885162115097046, cross_entropy: 0.9885162115097046 +[2025-04-27 14:32:49,283][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.364461898803711, cross_entropy: 2.364461898803711 +[2025-04-27 14:32:49,621][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.016226291656494, cross_entropy: 2.016226291656494 +[2025-04-27 14:32:53,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.467935562133789, cross_entropy: 1.467935562133789 +[2025-04-27 14:32:53,811][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.1561534404754639, cross_entropy: 1.1561534404754639 +[2025-04-27 14:32:57,612][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.2871928215026855, cross_entropy: 3.2871928215026855 +[2025-04-27 14:32:57,949][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.4807296991348267, cross_entropy: 1.4807296991348267 +[2025-04-27 14:33:00,914][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.299211025238037, cross_entropy: 1.299211025238037 +[2025-04-27 14:33:01,249][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 1.4324605464935303, cross_entropy: 1.4324605464935303 +[2025-04-27 14:33:05,013][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 2.916004180908203, cross_entropy: 2.916004180908203 +[2025-04-27 14:33:05,326][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.4419240951538086, cross_entropy: 2.4419240951538086 +[2025-04-27 14:33:08,247][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 1.001615047454834, cross_entropy: 1.001615047454834 +[2025-04-27 14:33:08,579][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.477783441543579, cross_entropy: 1.477783441543579 +[2025-04-27 14:33:11,185][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 2.7306809425354004, cross_entropy: 2.7306809425354004 +[2025-04-27 14:33:11,497][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 2.9083237648010254, cross_entropy: 2.9083237648010254 +[2025-04-27 14:33:14,406][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.2704968452453613, cross_entropy: 2.2704968452453613 +[2025-04-27 14:33:14,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 3.161816358566284, cross_entropy: 3.161816358566284 +[2025-04-27 14:33:17,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 2.9890873432159424, cross_entropy: 2.9890873432159424 +[2025-04-27 14:33:17,918][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 2.878605604171753, cross_entropy: 2.878605604171753 +[2025-04-27 14:33:20,415][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 3.213634490966797, cross_entropy: 3.213634490966797 +[2025-04-27 14:33:20,728][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 1.6079964637756348, cross_entropy: 1.6079964637756348 +[2025-04-27 14:33:23,908][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 3.012913703918457, cross_entropy: 3.012913703918457 +[2025-04-27 14:33:24,232][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.3564245700836182, cross_entropy: 1.3564245700836182 +[2025-04-27 14:33:27,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.3521921634674072, cross_entropy: 1.3521921634674072 +[2025-04-27 14:33:27,428][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 1.5231611728668213, cross_entropy: 1.5231611728668213 +[2025-04-27 14:33:30,470][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.568070411682129, cross_entropy: 1.568070411682129 +[2025-04-27 14:33:30,809][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 1.1869566440582275, cross_entropy: 1.1869566440582275 +[2025-04-27 14:33:34,248][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 2.9228594303131104, cross_entropy: 2.9228594303131104 +[2025-04-27 14:33:34,595][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 2.448579788208008, cross_entropy: 2.448579788208008 +[2025-04-27 14:33:37,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.2250837087631226, cross_entropy: 1.2250837087631226 +[2025-04-27 14:33:37,675][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 0.9115889072418213, cross_entropy: 0.9115889072418213 +[2025-04-27 14:33:40,806][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.752504587173462, cross_entropy: 2.752504587173462 +[2025-04-27 14:33:41,146][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 1.1754050254821777, cross_entropy: 1.1754050254821777 +[2025-04-27 14:33:44,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.0770833492279053, cross_entropy: 1.0770833492279053 +[2025-04-27 14:33:44,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 1.7518048286437988, cross_entropy: 1.7518048286437988 +[2025-04-27 14:33:47,505][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 2.864537239074707, cross_entropy: 2.864537239074707 +[2025-04-27 14:33:47,841][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 2.185523271560669, cross_entropy: 2.185523271560669 +[2025-04-27 14:33:50,412][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 1.648207187652588, cross_entropy: 1.648207187652588 +[2025-04-27 14:33:50,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 1.3553701639175415, cross_entropy: 1.3553701639175415 +[2025-04-27 14:33:53,741][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 1.9147617816925049, cross_entropy: 1.9147617816925049 +[2025-04-27 14:33:54,081][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.51652193069458, cross_entropy: 2.51652193069458 +[2025-04-27 14:33:57,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.1129512786865234, cross_entropy: 2.1129512786865234 +[2025-04-27 14:33:57,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 3.1503138542175293, cross_entropy: 3.1503138542175293 +[2025-04-27 14:34:00,835][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.942279577255249, cross_entropy: 2.942279577255249 +[2025-04-27 14:34:01,150][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.868955135345459, cross_entropy: 2.868955135345459 +[2025-04-27 14:34:04,270][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 0.9955123066902161, cross_entropy: 0.9955123066902161 +[2025-04-27 14:34:04,613][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 0.9217021465301514, cross_entropy: 0.9217021465301514 +[2025-04-27 14:34:07,024][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.3406682014465332, cross_entropy: 1.3406682014465332 +[2025-04-27 14:34:07,367][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 3.0112407207489014, cross_entropy: 3.0112407207489014 +[2025-04-27 14:34:10,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.865342617034912, cross_entropy: 2.865342617034912 +[2025-04-27 14:34:10,548][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 3.295534610748291, cross_entropy: 3.295534610748291 +[2025-04-27 14:34:14,351][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.4995074272155762, cross_entropy: 1.4995074272155762 +[2025-04-27 14:34:14,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.7458579540252686, cross_entropy: 1.7458579540252686 +[2025-04-27 14:34:17,218][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 2.247614622116089, cross_entropy: 2.247614622116089 +[2025-04-27 14:34:17,556][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 1.9104185104370117, cross_entropy: 1.9104185104370117 +[2025-04-27 14:34:20,335][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.0772193670272827, cross_entropy: 1.0772193670272827 +[2025-04-27 14:34:20,671][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 1.7619503736495972, cross_entropy: 1.7619503736495972 +[2025-04-27 14:34:23,896][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.880974292755127, cross_entropy: 2.880974292755127 +[2025-04-27 14:34:24,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 3.3612890243530273, cross_entropy: 3.3612890243530273 +[2025-04-27 14:34:27,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.2315173149108887, cross_entropy: 2.2315173149108887 +[2025-04-27 14:34:27,633][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.7271687984466553, cross_entropy: 1.7271687984466553 +[2025-04-27 14:34:30,678][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.9578264951705933, cross_entropy: 1.9578264951705933 +[2025-04-27 14:34:31,023][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.1503148078918457, cross_entropy: 1.1503148078918457 +[2025-04-27 14:34:34,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.1605161428451538, cross_entropy: 1.1605161428451538 +[2025-04-27 14:34:34,961][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.8929758071899414, cross_entropy: 2.8929758071899414 +[2025-04-27 14:34:37,945][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.197967767715454, cross_entropy: 1.197967767715454 +[2025-04-27 14:34:38,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.10036039352417, cross_entropy: 2.10036039352417 +[2025-04-27 14:34:41,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 0.9435861110687256, cross_entropy: 0.9435861110687256 +[2025-04-27 14:34:41,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.801738977432251, cross_entropy: 1.801738977432251 +[2025-04-27 14:34:44,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 3.403366804122925, cross_entropy: 3.403366804122925 +[2025-04-27 14:34:44,965][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.0407733917236328, cross_entropy: 1.0407733917236328 +[2025-04-27 14:34:47,948][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 3.083977699279785, cross_entropy: 3.083977699279785 +[2025-04-27 14:34:48,260][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 1.4848614931106567, cross_entropy: 1.4848614931106567 +[2025-04-27 14:34:51,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.607546806335449, cross_entropy: 2.607546806335449 +[2025-04-27 14:34:51,511][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.2896270751953125, cross_entropy: 2.2896270751953125 +[2025-04-27 14:34:54,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.5010998249053955, cross_entropy: 1.5010998249053955 +[2025-04-27 14:34:54,907][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.20475435256958, cross_entropy: 3.20475435256958 +[2025-04-27 14:34:57,749][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.674992561340332, cross_entropy: 2.674992561340332 +[2025-04-27 14:34:58,061][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 1.311929702758789, cross_entropy: 1.311929702758789 +[2025-04-27 14:35:01,247][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.3996665477752686, cross_entropy: 1.3996665477752686 +[2025-04-27 14:35:01,559][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.7299104928970337, cross_entropy: 1.7299104928970337 +[2025-04-27 14:35:04,750][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.502708911895752, cross_entropy: 1.502708911895752 +[2025-04-27 14:35:05,080][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 1.7763407230377197, cross_entropy: 1.7763407230377197 +[2025-04-27 14:35:07,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 1.385849952697754, cross_entropy: 1.385849952697754 +[2025-04-27 14:35:08,907][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.5970253944396973, cross_entropy: 2.5970253944396973 +[2025-04-27 14:35:11,240][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.5182042121887207, cross_entropy: 1.5182042121887207 +[2025-04-27 14:35:11,907][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 2.0711159706115723, cross_entropy: 2.0711159706115723 +[2025-04-27 14:35:14,465][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.4997127056121826, cross_entropy: 2.4997127056121826 +[2025-04-27 14:35:15,376][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 3.0306780338287354, cross_entropy: 3.0306780338287354 +[2025-04-27 14:35:17,366][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 1.580634355545044, cross_entropy: 1.580634355545044 +[2025-04-27 14:35:18,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 2.345750570297241, cross_entropy: 2.345750570297241 +[2025-04-27 14:35:20,648][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 3.1147706508636475, cross_entropy: 3.1147706508636475 +[2025-04-27 14:35:21,730][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 1.5567140579223633, cross_entropy: 1.5567140579223633 +[2025-04-27 14:35:24,393][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.4819270372390747, cross_entropy: 1.4819270372390747 +[2025-04-27 14:35:25,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.5138301849365234, cross_entropy: 1.5138301849365234 +[2025-04-27 14:35:28,277][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.8720664978027344, cross_entropy: 2.8720664978027344 +[2025-04-27 14:35:28,798][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.093278169631958, cross_entropy: 1.093278169631958 +[2025-04-27 14:35:32,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.148623466491699, cross_entropy: 2.148623466491699 +[2025-04-27 14:35:33,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 2.891068935394287, cross_entropy: 2.891068935394287 +[2025-04-27 14:35:36,210][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 0.9928885698318481, cross_entropy: 0.9928885698318481 +[2025-04-27 14:35:36,523][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 2.044198989868164, cross_entropy: 2.044198989868164 +[2025-04-27 14:35:39,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.09244966506958, cross_entropy: 1.09244966506958 +[2025-04-27 14:35:39,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.4483706951141357, cross_entropy: 1.4483706951141357 +[2025-04-27 14:35:42,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 3.3839221000671387, cross_entropy: 3.3839221000671387 +[2025-04-27 14:35:43,018][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 1.494354486465454, cross_entropy: 1.494354486465454 +[2025-04-27 14:35:45,847][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 1.010094165802002, cross_entropy: 1.010094165802002 +[2025-04-27 14:35:46,179][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.370358943939209, cross_entropy: 3.370358943939209 +[2025-04-27 14:35:49,166][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.88882315158844, cross_entropy: 1.88882315158844 +[2025-04-27 14:35:49,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.84080171585083, cross_entropy: 2.84080171585083 +[2025-04-27 14:35:52,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.422226905822754, cross_entropy: 2.422226905822754 +[2025-04-27 14:35:52,457][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 1.8286868333816528, cross_entropy: 1.8286868333816528 +[2025-04-27 14:35:55,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.2764253616333008, cross_entropy: 1.2764253616333008 +[2025-04-27 14:35:55,889][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.5386712551116943, cross_entropy: 1.5386712551116943 +[2025-04-27 14:35:58,847][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 0.8715041875839233, cross_entropy: 0.8715041875839233 +[2025-04-27 14:35:59,159][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.2494145631790161, cross_entropy: 1.2494145631790161 +[2025-04-27 14:36:02,232][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.0146620273590088, cross_entropy: 1.0146620273590088 +[2025-04-27 14:36:02,546][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 3.171074390411377, cross_entropy: 3.171074390411377 +[2025-04-27 14:36:06,117][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 3.1244821548461914, cross_entropy: 3.1244821548461914 +[2025-04-27 14:36:06,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 1.8005790710449219, cross_entropy: 1.8005790710449219 +[2025-04-27 14:36:10,503][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.4150686264038086, cross_entropy: 3.4150686264038086 +[2025-04-27 14:36:10,815][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.898674726486206, cross_entropy: 2.898674726486206 +[2025-04-27 14:36:14,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.7496161460876465, cross_entropy: 2.7496161460876465 +[2025-04-27 14:36:15,051][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.314126491546631, cross_entropy: 3.314126491546631 +[2025-04-27 14:36:18,886][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.3045578002929688, cross_entropy: 2.3045578002929688 +[2025-04-27 14:36:19,223][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.1209001541137695, cross_entropy: 1.1209001541137695 +[2025-04-27 14:36:22,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 0.6518336534500122, cross_entropy: 0.6518336534500122 +[2025-04-27 14:36:23,174][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.5822842121124268, cross_entropy: 1.5822842121124268 +[2025-04-27 14:36:26,123][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 1.0912498235702515, cross_entropy: 1.0912498235702515 +[2025-04-27 14:36:26,434][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 2.90476393699646, cross_entropy: 2.90476393699646 +[2025-04-27 14:36:29,702][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.822331428527832, cross_entropy: 2.822331428527832 +[2025-04-27 14:36:30,037][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.8290256261825562, cross_entropy: 1.8290256261825562 +[2025-04-27 14:36:33,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.157489776611328, cross_entropy: 2.157489776611328 +[2025-04-27 14:36:34,189][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.7457780838012695, cross_entropy: 2.7457780838012695 +[2025-04-27 14:36:37,426][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.5983198881149292, cross_entropy: 1.5983198881149292 +[2025-04-27 14:36:37,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.7622218132019043, cross_entropy: 1.7622218132019043 +[2025-04-27 14:36:40,915][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 2.988091468811035, cross_entropy: 2.988091468811035 +[2025-04-27 14:36:41,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 2.5520033836364746, cross_entropy: 2.5520033836364746 +[2025-04-27 14:36:43,764][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.4218302965164185, cross_entropy: 1.4218302965164185 +[2025-04-27 14:36:44,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 1.9038561582565308, cross_entropy: 1.9038561582565308 +[2025-04-27 14:36:47,243][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 2.731844663619995, cross_entropy: 2.731844663619995 +[2025-04-27 14:36:47,603][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 3.160872459411621, cross_entropy: 3.160872459411621 +[2025-04-27 14:36:50,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 3.144782543182373, cross_entropy: 3.144782543182373 +[2025-04-27 14:36:50,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 3.035684585571289, cross_entropy: 3.035684585571289 +[2025-04-27 14:36:54,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.033730387687683, cross_entropy: 1.033730387687683 +[2025-04-27 14:36:54,398][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 1.0962824821472168, cross_entropy: 1.0962824821472168 +[2025-04-27 14:36:57,282][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 1.0155329704284668, cross_entropy: 1.0155329704284668 +[2025-04-27 14:36:57,624][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.434847354888916, cross_entropy: 1.434847354888916 +[2025-04-27 14:37:00,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.8167479038238525, cross_entropy: 1.8167479038238525 +[2025-04-27 14:37:01,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.4353725910186768, cross_entropy: 1.4353725910186768 +[2025-04-27 14:37:05,123][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 1.2114711999893188, cross_entropy: 1.2114711999893188 +[2025-04-27 14:37:05,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 2.7559146881103516, cross_entropy: 2.7559146881103516 +[2025-04-27 14:37:08,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 2.1962790489196777, cross_entropy: 2.1962790489196777 +[2025-04-27 14:37:08,400][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.5656609535217285, cross_entropy: 1.5656609535217285 +[2025-04-27 14:37:11,349][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 2.0520663261413574, cross_entropy: 2.0520663261413574 +[2025-04-27 14:37:11,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.269031524658203, cross_entropy: 2.269031524658203 +[2025-04-27 14:37:14,374][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 2.077455759048462, cross_entropy: 2.077455759048462 +[2025-04-27 14:37:14,711][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.1657493114471436, cross_entropy: 3.1657493114471436 +[2025-04-27 14:37:17,356][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 1.0452425479888916, cross_entropy: 1.0452425479888916 +[2025-04-27 14:37:17,695][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 1.2756785154342651, cross_entropy: 1.2756785154342651 +[2025-04-27 14:37:20,596][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.8296077251434326, cross_entropy: 2.8296077251434326 +[2025-04-27 14:37:20,907][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.148435354232788, cross_entropy: 1.148435354232788 +[2025-04-27 14:37:23,810][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 2.569228172302246, cross_entropy: 2.569228172302246 +[2025-04-27 14:37:24,148][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.7638437747955322, cross_entropy: 1.7638437747955322 +[2025-04-27 14:37:27,179][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.2456624507904053, cross_entropy: 1.2456624507904053 +[2025-04-27 14:37:27,515][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 3.046830415725708, cross_entropy: 3.046830415725708 +[2025-04-27 14:37:30,356][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 2.7576375007629395, cross_entropy: 2.7576375007629395 +[2025-04-27 14:37:30,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.6453120708465576, cross_entropy: 2.6453120708465576 +[2025-04-27 14:37:33,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.3928378820419312, cross_entropy: 1.3928378820419312 +[2025-04-27 14:37:34,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.1144962310791016, cross_entropy: 1.1144962310791016 +[2025-04-27 14:37:36,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.3634697198867798, cross_entropy: 1.3634697198867798 +[2025-04-27 14:37:37,052][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.800182580947876, cross_entropy: 2.800182580947876 +[2025-04-27 14:37:39,981][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 3.1649980545043945, cross_entropy: 3.1649980545043945 +[2025-04-27 14:37:40,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.2315025329589844, cross_entropy: 1.2315025329589844 +[2025-04-27 14:37:43,088][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 1.1401902437210083, cross_entropy: 1.1401902437210083 +[2025-04-27 14:37:44,364][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.012333869934082, cross_entropy: 2.012333869934082 +[2025-04-27 14:37:46,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.1453680992126465, cross_entropy: 1.1453680992126465 +[2025-04-27 14:37:47,624][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.4655036926269531, cross_entropy: 1.4655036926269531 +[2025-04-27 14:37:50,175][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.2982020378112793, cross_entropy: 1.2982020378112793 +[2025-04-27 14:37:50,592][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 1.9058245420455933, cross_entropy: 1.9058245420455933 +[2025-04-27 14:37:53,517][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.2327746152877808, cross_entropy: 1.2327746152877808 +[2025-04-27 14:37:53,897][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.2364444732666016, cross_entropy: 2.2364444732666016 +[2025-04-27 14:37:57,097][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 1.765911340713501, cross_entropy: 1.765911340713501 +[2025-04-27 14:37:57,434][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.0838751792907715, cross_entropy: 2.0838751792907715 +[2025-04-27 14:38:00,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.399827003479004, cross_entropy: 3.399827003479004 +[2025-04-27 14:38:01,327][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 3.320591926574707, cross_entropy: 3.320591926574707 +[2025-04-27 14:38:04,030][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 1.635430097579956, cross_entropy: 1.635430097579956 +[2025-04-27 14:38:04,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.1978349685668945, cross_entropy: 2.1978349685668945 +[2025-04-27 14:38:06,754][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.9938435554504395, cross_entropy: 1.9938435554504395 +[2025-04-27 14:38:07,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 2.073884963989258, cross_entropy: 2.073884963989258 +[2025-04-27 14:38:09,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.6092805862426758, cross_entropy: 1.6092805862426758 +[2025-04-27 14:38:10,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 3.085704803466797, cross_entropy: 3.085704803466797 +[2025-04-27 14:38:13,206][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.877796173095703, cross_entropy: 2.877796173095703 +[2025-04-27 14:38:13,517][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.6531732082366943, cross_entropy: 2.6531732082366943 +[2025-04-27 14:38:17,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 2.303253650665283, cross_entropy: 2.303253650665283 +[2025-04-27 14:38:17,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 1.2081594467163086, cross_entropy: 1.2081594467163086 +[2025-04-27 14:38:20,686][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.405498504638672, cross_entropy: 2.405498504638672 +[2025-04-27 14:38:21,822][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 1.3504266738891602, cross_entropy: 1.3504266738891602 +[2025-04-27 14:38:23,857][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.437370777130127, cross_entropy: 3.437370777130127 +[2025-04-27 14:38:25,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.2106163501739502, cross_entropy: 1.2106163501739502 +[2025-04-27 14:38:27,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.2775866985321045, cross_entropy: 2.2775866985321045 +[2025-04-27 14:38:28,921][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.6221413612365723, cross_entropy: 1.6221413612365723 +[2025-04-27 14:38:30,642][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 0.9237850904464722, cross_entropy: 0.9237850904464722 +[2025-04-27 14:38:32,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.006993293762207, cross_entropy: 2.006993293762207 +[2025-04-27 14:38:34,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.4053447246551514, cross_entropy: 1.4053447246551514 +[2025-04-27 14:38:35,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.5566496849060059, cross_entropy: 1.5566496849060059 +[2025-04-27 14:38:37,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.5230767726898193, cross_entropy: 2.5230767726898193 +[2025-04-27 14:38:38,921][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.3265411853790283, cross_entropy: 1.3265411853790283 +[2025-04-27 14:38:41,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 0.9587422013282776, cross_entropy: 0.9587422013282776 +[2025-04-27 14:38:42,152][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 1.3708218336105347, cross_entropy: 1.3708218336105347 +[2025-04-27 14:38:45,031][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 1.0801448822021484, cross_entropy: 1.0801448822021484 +[2025-04-27 14:38:45,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.3904304504394531, cross_entropy: 1.3904304504394531 +[2025-04-27 14:41:24,063][BaseTrainer][INFO] - [Epoch 5/10] (train) 1.9892646074295044, cross_entropy: 1.9892646074295044 +[2025-04-27 14:41:24,063][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.3350955247879028, cross_entropy: 1.3350955247879028 +[2025-04-27 14:41:24,286][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 14:41:24,446][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch5.pth. +[2025-04-27 14:41:24,648][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 14:41:29,201][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 0.7087098360061646, cross_entropy: 0.7087098360061646 +[2025-04-27 14:41:29,515][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.5188283920288086, cross_entropy: 1.5188283920288086 +[2025-04-27 14:41:32,127][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 2.884495735168457, cross_entropy: 2.884495735168457 +[2025-04-27 14:41:32,522][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 2.659696578979492, cross_entropy: 2.659696578979492 +[2025-04-27 14:41:35,144][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.010165214538574, cross_entropy: 2.010165214538574 +[2025-04-27 14:41:35,583][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 2.8844563961029053, cross_entropy: 2.8844563961029053 +[2025-04-27 14:41:38,348][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 2.6084530353546143, cross_entropy: 2.6084530353546143 +[2025-04-27 14:41:39,350][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.2405949831008911, cross_entropy: 1.2405949831008911 +[2025-04-27 14:41:41,726][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.5316531658172607, cross_entropy: 1.5316531658172607 +[2025-04-27 14:41:42,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.0705089569091797, cross_entropy: 2.0705089569091797 +[2025-04-27 14:41:45,302][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.437316417694092, cross_entropy: 2.437316417694092 +[2025-04-27 14:41:46,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 2.0444393157958984, cross_entropy: 2.0444393157958984 +[2025-04-27 14:41:47,843][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 3.1657357215881348, cross_entropy: 3.1657357215881348 +[2025-04-27 14:41:49,680][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.6481305360794067, cross_entropy: 1.6481305360794067 +[2025-04-27 14:41:50,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 0.8654798269271851, cross_entropy: 0.8654798269271851 +[2025-04-27 14:41:53,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.3394579887390137, cross_entropy: 2.3394579887390137 +[2025-04-27 14:41:54,448][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.0334181785583496, cross_entropy: 1.0334181785583496 +[2025-04-27 14:41:56,980][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.184032678604126, cross_entropy: 3.184032678604126 +[2025-04-27 14:41:57,549][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.0603021383285522, cross_entropy: 1.0603021383285522 +[2025-04-27 14:42:00,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 3.1760411262512207, cross_entropy: 3.1760411262512207 +[2025-04-27 14:42:01,385][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 1.742889642715454, cross_entropy: 1.742889642715454 +[2025-04-27 14:42:03,816][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.0805128812789917, cross_entropy: 1.0805128812789917 +[2025-04-27 14:42:05,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 1.0557215213775635, cross_entropy: 1.0557215213775635 +[2025-04-27 14:42:06,809][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.3578245639801025, cross_entropy: 2.3578245639801025 +[2025-04-27 14:42:08,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 1.0030090808868408, cross_entropy: 1.0030090808868408 +[2025-04-27 14:42:09,601][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.0749809741973877, cross_entropy: 2.0749809741973877 +[2025-04-27 14:42:11,453][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 1.0279279947280884, cross_entropy: 1.0279279947280884 +[2025-04-27 14:42:13,121][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.2617409229278564, cross_entropy: 2.2617409229278564 +[2025-04-27 14:42:14,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.6183624267578125, cross_entropy: 1.6183624267578125 +[2025-04-27 14:42:16,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 0.9654910564422607, cross_entropy: 0.9654910564422607 +[2025-04-27 14:42:17,429][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 0.9613469243049622, cross_entropy: 0.9613469243049622 +[2025-04-27 14:42:20,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.6753382682800293, cross_entropy: 2.6753382682800293 +[2025-04-27 14:42:20,989][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 1.7010188102722168, cross_entropy: 1.7010188102722168 +[2025-04-27 14:42:23,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 2.8476884365081787, cross_entropy: 2.8476884365081787 +[2025-04-27 14:42:24,232][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.88556170463562, cross_entropy: 2.88556170463562 +[2025-04-27 14:42:27,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 1.2009027004241943, cross_entropy: 1.2009027004241943 +[2025-04-27 14:42:28,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.0489938259124756, cross_entropy: 1.0489938259124756 +[2025-04-27 14:42:30,919][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 2.7465126514434814, cross_entropy: 2.7465126514434814 +[2025-04-27 14:42:31,306][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.408909559249878, cross_entropy: 2.408909559249878 +[2025-04-27 14:42:35,175][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.5298748016357422, cross_entropy: 1.5298748016357422 +[2025-04-27 14:42:35,507][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 3.363957405090332, cross_entropy: 3.363957405090332 +[2025-04-27 14:42:38,274][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.707852840423584, cross_entropy: 2.707852840423584 +[2025-04-27 14:42:38,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.2294986248016357, cross_entropy: 1.2294986248016357 +[2025-04-27 14:42:41,411][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 2.6253647804260254, cross_entropy: 2.6253647804260254 +[2025-04-27 14:42:41,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 0.9616349935531616, cross_entropy: 0.9616349935531616 +[2025-04-27 14:42:44,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.196519136428833, cross_entropy: 2.196519136428833 +[2025-04-27 14:42:45,054][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.956482410430908, cross_entropy: 2.956482410430908 +[2025-04-27 14:42:47,866][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 3.252340316772461, cross_entropy: 3.252340316772461 +[2025-04-27 14:42:48,177][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.3830196857452393, cross_entropy: 1.3830196857452393 +[2025-04-27 14:42:51,410][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.826169490814209, cross_entropy: 1.826169490814209 +[2025-04-27 14:42:51,744][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 3.1424896717071533, cross_entropy: 3.1424896717071533 +[2025-04-27 14:42:54,762][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 2.926719903945923, cross_entropy: 2.926719903945923 +[2025-04-27 14:42:55,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.5136525630950928, cross_entropy: 2.5136525630950928 +[2025-04-27 14:42:58,362][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 0.9713728427886963, cross_entropy: 0.9713728427886963 +[2025-04-27 14:42:58,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.1975138187408447, cross_entropy: 1.1975138187408447 +[2025-04-27 14:43:01,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 0.8218040466308594, cross_entropy: 0.8218040466308594 +[2025-04-27 14:43:01,865][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 2.3491525650024414, cross_entropy: 2.3491525650024414 +[2025-04-27 14:43:05,291][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.355634093284607, cross_entropy: 1.355634093284607 +[2025-04-27 14:43:05,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 1.9647953510284424, cross_entropy: 1.9647953510284424 +[2025-04-27 14:43:08,143][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.280282497406006, cross_entropy: 2.280282497406006 +[2025-04-27 14:43:08,478][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 2.01834774017334, cross_entropy: 2.01834774017334 +[2025-04-27 14:43:11,772][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.3799571990966797, cross_entropy: 2.3799571990966797 +[2025-04-27 14:43:12,084][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.5464494228363037, cross_entropy: 1.5464494228363037 +[2025-04-27 14:43:15,302][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.7222058773040771, cross_entropy: 1.7222058773040771 +[2025-04-27 14:43:15,635][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 0.9824988842010498, cross_entropy: 0.9824988842010498 +[2025-04-27 14:43:18,583][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.6410622596740723, cross_entropy: 2.6410622596740723 +[2025-04-27 14:43:18,893][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 0.8927441239356995, cross_entropy: 0.8927441239356995 +[2025-04-27 14:43:21,622][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 0.9983267188072205, cross_entropy: 0.9983267188072205 +[2025-04-27 14:43:21,934][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 1.026827096939087, cross_entropy: 1.026827096939087 +[2025-04-27 14:43:24,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.2045037746429443, cross_entropy: 1.2045037746429443 +[2025-04-27 14:43:25,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 0.8535113334655762, cross_entropy: 0.8535113334655762 +[2025-04-27 14:43:27,958][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.315671682357788, cross_entropy: 1.315671682357788 +[2025-04-27 14:43:28,743][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 2.7569754123687744, cross_entropy: 2.7569754123687744 +[2025-04-27 14:43:30,885][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 0.776357889175415, cross_entropy: 0.776357889175415 +[2025-04-27 14:43:32,786][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 0.955223798751831, cross_entropy: 0.955223798751831 +[2025-04-27 14:43:34,646][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.4802799224853516, cross_entropy: 1.4802799224853516 +[2025-04-27 14:43:36,841][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 1.657989740371704, cross_entropy: 1.657989740371704 +[2025-04-27 14:43:38,189][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.6950690746307373, cross_entropy: 2.6950690746307373 +[2025-04-27 14:43:40,074][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.0632238388061523, cross_entropy: 2.0632238388061523 +[2025-04-27 14:43:41,485][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 3.006730794906616, cross_entropy: 3.006730794906616 +[2025-04-27 14:43:43,795][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 2.5721569061279297, cross_entropy: 2.5721569061279297 +[2025-04-27 14:43:44,890][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 2.078683376312256, cross_entropy: 2.078683376312256 +[2025-04-27 14:43:46,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 3.090010643005371, cross_entropy: 3.090010643005371 +[2025-04-27 14:43:48,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.331116795539856, cross_entropy: 1.331116795539856 +[2025-04-27 14:43:50,350][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.5556151866912842, cross_entropy: 1.5556151866912842 +[2025-04-27 14:43:50,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 1.8126354217529297, cross_entropy: 1.8126354217529297 +[2025-04-27 14:43:53,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 1.1202328205108643, cross_entropy: 1.1202328205108643 +[2025-04-27 14:43:54,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 2.3029730319976807, cross_entropy: 2.3029730319976807 +[2025-04-27 14:43:57,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.2624543905258179, cross_entropy: 1.2624543905258179 +[2025-04-27 14:43:57,654][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 0.9223007559776306, cross_entropy: 0.9223007559776306 +[2025-04-27 14:44:01,633][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.873793125152588, cross_entropy: 2.873793125152588 +[2025-04-27 14:44:01,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.1505069732666016, cross_entropy: 1.1505069732666016 +[2025-04-27 14:44:04,854][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.5304241180419922, cross_entropy: 1.5304241180419922 +[2025-04-27 14:44:05,189][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.149050712585449, cross_entropy: 2.149050712585449 +[2025-04-27 14:44:08,048][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 1.7414848804473877, cross_entropy: 1.7414848804473877 +[2025-04-27 14:44:08,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 0.9646730422973633, cross_entropy: 0.9646730422973633 +[2025-04-27 14:44:10,905][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.8887929916381836, cross_entropy: 2.8887929916381836 +[2025-04-27 14:44:11,628][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.8514283895492554, cross_entropy: 1.8514283895492554 +[2025-04-27 14:44:13,883][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.5826530456542969, cross_entropy: 1.5826530456542969 +[2025-04-27 14:44:14,436][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.0582507848739624, cross_entropy: 1.0582507848739624 +[2025-04-27 14:44:17,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.255474328994751, cross_entropy: 1.255474328994751 +[2025-04-27 14:44:17,650][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.0221848487854004, cross_entropy: 2.0221848487854004 +[2025-04-27 14:44:20,277][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 3.1543965339660645, cross_entropy: 3.1543965339660645 +[2025-04-27 14:44:21,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.8739943504333496, cross_entropy: 0.8739943504333496 +[2025-04-27 14:44:23,302][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.0173792839050293, cross_entropy: 1.0173792839050293 +[2025-04-27 14:44:24,707][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.151463031768799, cross_entropy: 2.151463031768799 +[2025-04-27 14:44:27,392][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.8948276042938232, cross_entropy: 2.8948276042938232 +[2025-04-27 14:44:27,777][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.8590223789215088, cross_entropy: 1.8590223789215088 +[2025-04-27 14:44:30,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 2.068347454071045, cross_entropy: 2.068347454071045 +[2025-04-27 14:44:31,338][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.7765967845916748, cross_entropy: 1.7765967845916748 +[2025-04-27 14:44:34,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.0687875747680664, cross_entropy: 1.0687875747680664 +[2025-04-27 14:44:34,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.1972670555114746, cross_entropy: 1.1972670555114746 +[2025-04-27 14:44:37,778][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 1.4620544910430908, cross_entropy: 1.4620544910430908 +[2025-04-27 14:44:38,183][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.4786311388015747, cross_entropy: 1.4786311388015747 +[2025-04-27 14:44:41,834][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.603480339050293, cross_entropy: 2.603480339050293 +[2025-04-27 14:44:42,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 1.765695571899414, cross_entropy: 1.765695571899414 +[2025-04-27 14:44:44,942][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.7703754901885986, cross_entropy: 1.7703754901885986 +[2025-04-27 14:44:45,277][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 2.9402785301208496, cross_entropy: 2.9402785301208496 +[2025-04-27 14:44:47,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.1160101890563965, cross_entropy: 3.1160101890563965 +[2025-04-27 14:44:48,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.2638288736343384, cross_entropy: 1.2638288736343384 +[2025-04-27 14:44:51,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.6364943981170654, cross_entropy: 2.6364943981170654 +[2025-04-27 14:44:51,414][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 2.165010452270508, cross_entropy: 2.165010452270508 +[2025-04-27 14:44:53,978][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.0727577209472656, cross_entropy: 1.0727577209472656 +[2025-04-27 14:44:54,383][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 1.5302255153656006, cross_entropy: 1.5302255153656006 +[2025-04-27 14:44:57,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.4890751838684082, cross_entropy: 1.4890751838684082 +[2025-04-27 14:44:59,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.162808656692505, cross_entropy: 2.162808656692505 +[2025-04-27 14:45:00,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.6367881298065186, cross_entropy: 1.6367881298065186 +[2025-04-27 14:45:02,887][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 2.956868886947632, cross_entropy: 2.956868886947632 +[2025-04-27 14:45:04,190][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 0.9226981997489929, cross_entropy: 0.9226981997489929 +[2025-04-27 14:45:06,112][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 2.8464441299438477, cross_entropy: 2.8464441299438477 +[2025-04-27 14:45:07,097][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.9932079315185547, cross_entropy: 2.9932079315185547 +[2025-04-27 14:45:09,332][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.7773816585540771, cross_entropy: 1.7773816585540771 +[2025-04-27 14:45:09,702][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 2.9703314304351807, cross_entropy: 2.9703314304351807 +[2025-04-27 14:45:12,877][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.199648857116699, cross_entropy: 3.199648857116699 +[2025-04-27 14:45:13,409][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 3.326836347579956, cross_entropy: 3.326836347579956 +[2025-04-27 14:45:16,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 3.0773873329162598, cross_entropy: 3.0773873329162598 +[2025-04-27 14:45:16,811][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 1.3586559295654297, cross_entropy: 1.3586559295654297 +[2025-04-27 14:45:20,372][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.5547313690185547, cross_entropy: 1.5547313690185547 +[2025-04-27 14:45:20,688][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.6957441568374634, cross_entropy: 1.6957441568374634 +[2025-04-27 14:45:23,873][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.9557173252105713, cross_entropy: 2.9557173252105713 +[2025-04-27 14:45:24,210][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.38046133518219, cross_entropy: 1.38046133518219 +[2025-04-27 14:45:27,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.2244153022766113, cross_entropy: 1.2244153022766113 +[2025-04-27 14:45:27,389][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 1.1330554485321045, cross_entropy: 1.1330554485321045 +[2025-04-27 14:45:30,263][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 3.0987048149108887, cross_entropy: 3.0987048149108887 +[2025-04-27 14:45:30,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.677804946899414, cross_entropy: 1.677804946899414 +[2025-04-27 14:45:33,452][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.3397834300994873, cross_entropy: 1.3397834300994873 +[2025-04-27 14:45:33,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 1.8757777214050293, cross_entropy: 1.8757777214050293 +[2025-04-27 14:45:36,462][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.1092177629470825, cross_entropy: 1.1092177629470825 +[2025-04-27 14:45:36,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 3.2304742336273193, cross_entropy: 3.2304742336273193 +[2025-04-27 14:45:39,934][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.7645716667175293, cross_entropy: 2.7645716667175293 +[2025-04-27 14:45:40,267][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 1.3923403024673462, cross_entropy: 1.3923403024673462 +[2025-04-27 14:45:43,460][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.805255889892578, cross_entropy: 2.805255889892578 +[2025-04-27 14:45:43,787][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 0.9583914279937744, cross_entropy: 0.9583914279937744 +[2025-04-27 14:45:46,611][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.4361056089401245, cross_entropy: 1.4361056089401245 +[2025-04-27 14:45:46,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.5340466499328613, cross_entropy: 1.5340466499328613 +[2025-04-27 14:45:49,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.2740650177001953, cross_entropy: 1.2740650177001953 +[2025-04-27 14:45:50,170][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.12876296043396, cross_entropy: 2.12876296043396 +[2025-04-27 14:45:53,268][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.669586181640625, cross_entropy: 2.669586181640625 +[2025-04-27 14:45:53,580][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.3555339574813843, cross_entropy: 1.3555339574813843 +[2025-04-27 14:45:56,584][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.4140372276306152, cross_entropy: 1.4140372276306152 +[2025-04-27 14:45:57,073][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 0.9693750143051147, cross_entropy: 0.9693750143051147 +[2025-04-27 14:46:00,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.1111719608306885, cross_entropy: 1.1111719608306885 +[2025-04-27 14:46:00,604][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 2.470393180847168, cross_entropy: 2.470393180847168 +[2025-04-27 14:46:03,258][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 0.8479645252227783, cross_entropy: 0.8479645252227783 +[2025-04-27 14:46:03,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 1.4173548221588135, cross_entropy: 1.4173548221588135 +[2025-04-27 14:46:06,213][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 1.8748276233673096, cross_entropy: 1.8748276233673096 +[2025-04-27 14:46:06,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 2.9603662490844727, cross_entropy: 2.9603662490844727 +[2025-04-27 14:46:09,244][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.8275253772735596, cross_entropy: 1.8275253772735596 +[2025-04-27 14:46:09,612][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 2.816041946411133, cross_entropy: 2.816041946411133 +[2025-04-27 14:46:12,521][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.4968879222869873, cross_entropy: 2.4968879222869873 +[2025-04-27 14:46:12,844][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 2.5374252796173096, cross_entropy: 2.5374252796173096 +[2025-04-27 14:46:16,462][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.4572335481643677, cross_entropy: 1.4572335481643677 +[2025-04-27 14:46:16,820][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 1.999572992324829, cross_entropy: 1.999572992324829 +[2025-04-27 14:46:20,364][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.8225823640823364, cross_entropy: 1.8225823640823364 +[2025-04-27 14:46:20,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 1.3225163221359253, cross_entropy: 1.3225163221359253 +[2025-04-27 14:46:23,112][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.103217363357544, cross_entropy: 1.103217363357544 +[2025-04-27 14:46:23,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.5990759134292603, cross_entropy: 1.5990759134292603 +[2025-04-27 14:46:26,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.429074764251709, cross_entropy: 1.429074764251709 +[2025-04-27 14:46:26,980][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.6303257942199707, cross_entropy: 2.6303257942199707 +[2025-04-27 14:46:29,749][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.3030908107757568, cross_entropy: 1.3030908107757568 +[2025-04-27 14:46:30,059][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.1697101593017578, cross_entropy: 1.1697101593017578 +[2025-04-27 14:46:32,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 2.516982078552246, cross_entropy: 2.516982078552246 +[2025-04-27 14:46:33,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.2392246723175049, cross_entropy: 1.2392246723175049 +[2025-04-27 14:46:36,014][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.189591646194458, cross_entropy: 2.189591646194458 +[2025-04-27 14:46:36,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 3.2167673110961914, cross_entropy: 3.2167673110961914 +[2025-04-27 14:46:39,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.6101933717727661, cross_entropy: 1.6101933717727661 +[2025-04-27 14:46:39,974][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.3022141456604004, cross_entropy: 2.3022141456604004 +[2025-04-27 14:46:42,652][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 2.5775270462036133, cross_entropy: 2.5775270462036133 +[2025-04-27 14:46:42,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.0453003644943237, cross_entropy: 1.0453003644943237 +[2025-04-27 14:46:45,721][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.885570526123047, cross_entropy: 2.885570526123047 +[2025-04-27 14:46:46,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 3.1593637466430664, cross_entropy: 3.1593637466430664 +[2025-04-27 14:46:49,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 1.5939369201660156, cross_entropy: 1.5939369201660156 +[2025-04-27 14:46:49,437][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 3.134953498840332, cross_entropy: 3.134953498840332 +[2025-04-27 14:46:52,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 2.9025630950927734, cross_entropy: 2.9025630950927734 +[2025-04-27 14:46:52,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 2.13379168510437, cross_entropy: 2.13379168510437 +[2025-04-27 14:46:55,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.1490511894226074, cross_entropy: 3.1490511894226074 +[2025-04-27 14:46:56,333][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 3.0401411056518555, cross_entropy: 3.0401411056518555 +[2025-04-27 14:46:59,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.7699007987976074, cross_entropy: 2.7699007987976074 +[2025-04-27 14:47:00,506][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 0.951555609703064, cross_entropy: 0.951555609703064 +[2025-04-27 14:47:02,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.6509242057800293, cross_entropy: 1.6509242057800293 +[2025-04-27 14:47:03,921][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.6194753646850586, cross_entropy: 2.6194753646850586 +[2025-04-27 14:47:06,276][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 2.7399444580078125, cross_entropy: 2.7399444580078125 +[2025-04-27 14:47:07,674][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 2.5199718475341797, cross_entropy: 2.5199718475341797 +[2025-04-27 14:47:10,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 1.6775062084197998, cross_entropy: 1.6775062084197998 +[2025-04-27 14:47:10,912][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.4623398780822754, cross_entropy: 2.4623398780822754 +[2025-04-27 14:47:13,762][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.3594646453857422, cross_entropy: 1.3594646453857422 +[2025-04-27 14:47:14,875][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.1894001960754395, cross_entropy: 1.1894001960754395 +[2025-04-27 14:47:17,207][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 2.8304054737091064, cross_entropy: 2.8304054737091064 +[2025-04-27 14:47:18,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 1.1052346229553223, cross_entropy: 1.1052346229553223 +[2025-04-27 14:47:20,635][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.0654770135879517, cross_entropy: 1.0654770135879517 +[2025-04-27 14:47:22,210][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.0097236633300781, cross_entropy: 1.0097236633300781 +[2025-04-27 14:47:24,065][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 2.9274919033050537, cross_entropy: 2.9274919033050537 +[2025-04-27 14:47:25,696][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.2580647468566895, cross_entropy: 2.2580647468566895 +[2025-04-27 14:47:26,898][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.4045056104660034, cross_entropy: 1.4045056104660034 +[2025-04-27 14:47:29,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.5416488647460938, cross_entropy: 2.5416488647460938 +[2025-04-27 14:47:29,944][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.908114433288574, cross_entropy: 2.908114433288574 +[2025-04-27 14:47:32,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 2.8393375873565674, cross_entropy: 2.8393375873565674 +[2025-04-27 14:47:33,218][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 1.957749366760254, cross_entropy: 1.957749366760254 +[2025-04-27 14:47:35,584][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.98978328704834, cross_entropy: 2.98978328704834 +[2025-04-27 14:47:36,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 2.871919631958008, cross_entropy: 2.871919631958008 +[2025-04-27 14:47:37,124][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/iteration2000.pth. +[2025-04-27 14:47:39,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 0.6550711393356323, cross_entropy: 0.6550711393356323 +[2025-04-27 14:47:40,391][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.7882864475250244, cross_entropy: 2.7882864475250244 +[2025-04-27 14:47:42,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.352051258087158, cross_entropy: 2.352051258087158 +[2025-04-27 14:47:43,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 0.970569372177124, cross_entropy: 0.970569372177124 +[2025-04-27 14:47:46,413][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 2.8771655559539795, cross_entropy: 2.8771655559539795 +[2025-04-27 14:47:47,257][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.2313270568847656, cross_entropy: 2.2313270568847656 +[2025-04-27 14:47:50,040][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 3.3125433921813965, cross_entropy: 3.3125433921813965 +[2025-04-27 14:47:50,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.386202335357666, cross_entropy: 2.386202335357666 +[2025-04-27 14:47:53,638][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.9270472526550293, cross_entropy: 1.9270472526550293 +[2025-04-27 14:47:54,270][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.6180219650268555, cross_entropy: 1.6180219650268555 +[2025-04-27 14:47:57,218][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 3.0628697872161865, cross_entropy: 3.0628697872161865 +[2025-04-27 14:47:58,223][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.9079740047454834, cross_entropy: 1.9079740047454834 +[2025-04-27 14:48:00,330][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.3450437784194946, cross_entropy: 1.3450437784194946 +[2025-04-27 14:48:02,099][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 0.8378814458847046, cross_entropy: 0.8378814458847046 +[2025-04-27 14:48:03,574][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.1039681434631348, cross_entropy: 1.1039681434631348 +[2025-04-27 14:48:05,554][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.535846471786499, cross_entropy: 2.535846471786499 +[2025-04-27 14:48:07,128][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.1731879711151123, cross_entropy: 1.1731879711151123 +[2025-04-27 14:48:08,695][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.322904109954834, cross_entropy: 1.322904109954834 +[2025-04-27 14:48:09,756][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.245807409286499, cross_entropy: 2.245807409286499 +[2025-04-27 14:48:11,526][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.411832332611084, cross_entropy: 2.411832332611084 +[2025-04-27 14:48:13,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 2.2501256465911865, cross_entropy: 2.2501256465911865 +[2025-04-27 14:48:14,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.1175711154937744, cross_entropy: 2.1175711154937744 +[2025-04-27 14:48:16,869][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 2.03136944770813, cross_entropy: 2.03136944770813 +[2025-04-27 14:48:18,504][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 3.193934917449951, cross_entropy: 3.193934917449951 +[2025-04-27 14:48:20,177][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 0.7991721630096436, cross_entropy: 0.7991721630096436 +[2025-04-27 14:48:21,633][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 2.229457378387451, cross_entropy: 2.229457378387451 +[2025-04-27 14:48:23,605][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 0.8942898511886597, cross_entropy: 0.8942898511886597 +[2025-04-27 14:48:25,025][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.3615905046463013, cross_entropy: 1.3615905046463013 +[2025-04-27 14:48:26,636][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.636826992034912, cross_entropy: 2.636826992034912 +[2025-04-27 14:48:28,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.3109381198883057, cross_entropy: 1.3109381198883057 +[2025-04-27 14:48:29,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.4287092685699463, cross_entropy: 2.4287092685699463 +[2025-04-27 14:48:31,178][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 1.9116301536560059, cross_entropy: 1.9116301536560059 +[2025-04-27 14:48:32,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.2023776769638062, cross_entropy: 1.2023776769638062 +[2025-04-27 14:48:34,843][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.2239325046539307, cross_entropy: 1.2239325046539307 +[2025-04-27 14:48:35,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 2.164518117904663, cross_entropy: 2.164518117904663 +[2025-04-27 14:48:38,024][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 1.6181824207305908, cross_entropy: 1.6181824207305908 +[2025-04-27 14:48:38,882][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.2287534475326538, cross_entropy: 1.2287534475326538 +[2025-04-27 14:48:40,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.892585039138794, cross_entropy: 1.892585039138794 +[2025-04-27 14:48:42,115][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 3.0274386405944824, cross_entropy: 3.0274386405944824 +[2025-04-27 14:48:45,298][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 2.082315683364868, cross_entropy: 2.082315683364868 +[2025-04-27 14:48:45,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 0.8426042795181274, cross_entropy: 0.8426042795181274 +[2025-04-27 14:48:48,705][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.5855259895324707, cross_entropy: 1.5855259895324707 +[2025-04-27 14:48:49,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.905457019805908, cross_entropy: 2.905457019805908 +[2025-04-27 14:48:51,758][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 1.1310259103775024, cross_entropy: 1.1310259103775024 +[2025-04-27 14:48:52,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.5458390712738037, cross_entropy: 2.5458390712738037 +[2025-04-27 14:48:55,772][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 1.071813702583313, cross_entropy: 1.071813702583313 +[2025-04-27 14:48:56,107][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.2089991569519043, cross_entropy: 1.2089991569519043 +[2025-04-27 14:48:59,270][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.652186870574951, cross_entropy: 2.652186870574951 +[2025-04-27 14:48:59,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 0.7530230283737183, cross_entropy: 0.7530230283737183 +[2025-04-27 14:49:02,702][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 1.3336601257324219, cross_entropy: 1.3336601257324219 +[2025-04-27 14:49:03,014][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.3697329759597778, cross_entropy: 1.3697329759597778 +[2025-04-27 14:49:06,591][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.3430001735687256, cross_entropy: 2.3430001735687256 +[2025-04-27 14:49:06,904][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.3439399003982544, cross_entropy: 1.3439399003982544 +[2025-04-27 14:49:09,777][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.8975144624710083, cross_entropy: 1.8975144624710083 +[2025-04-27 14:49:10,140][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.6036969423294067, cross_entropy: 1.6036969423294067 +[2025-04-27 14:49:13,613][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.5944957733154297, cross_entropy: 2.5944957733154297 +[2025-04-27 14:49:13,949][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.4064052104949951, cross_entropy: 1.4064052104949951 +[2025-04-27 14:49:16,671][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 1.6477785110473633, cross_entropy: 1.6477785110473633 +[2025-04-27 14:49:17,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 2.825644016265869, cross_entropy: 2.825644016265869 +[2025-04-27 14:49:20,071][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 0.9305593967437744, cross_entropy: 0.9305593967437744 +[2025-04-27 14:49:20,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.5631744861602783, cross_entropy: 1.5631744861602783 +[2025-04-27 14:49:22,986][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.1219890117645264, cross_entropy: 1.1219890117645264 +[2025-04-27 14:49:23,617][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.331432819366455, cross_entropy: 2.331432819366455 +[2025-04-27 14:49:26,558][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 1.7170324325561523, cross_entropy: 1.7170324325561523 +[2025-04-27 14:49:26,926][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 1.9749107360839844, cross_entropy: 1.9749107360839844 +[2025-04-27 14:49:29,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 2.3920631408691406, cross_entropy: 2.3920631408691406 +[2025-04-27 14:49:29,954][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 3.0302770137786865, cross_entropy: 3.0302770137786865 +[2025-04-27 14:49:32,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 2.3353686332702637, cross_entropy: 2.3353686332702637 +[2025-04-27 14:49:32,853][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 1.2661402225494385, cross_entropy: 1.2661402225494385 +[2025-04-27 14:49:35,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.755030870437622, cross_entropy: 1.755030870437622 +[2025-04-27 14:49:36,895][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.25094473361969, cross_entropy: 1.25094473361969 +[2025-04-27 14:49:38,849][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.1536976099014282, cross_entropy: 1.1536976099014282 +[2025-04-27 14:49:40,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.7217516899108887, cross_entropy: 2.7217516899108887 +[2025-04-27 14:49:42,547][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.6594327688217163, cross_entropy: 1.6594327688217163 +[2025-04-27 14:49:43,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.1415047645568848, cross_entropy: 2.1415047645568848 +[2025-04-27 14:49:45,701][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 2.362412452697754, cross_entropy: 2.362412452697754 +[2025-04-27 14:49:46,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 1.20465087890625, cross_entropy: 1.20465087890625 +[2025-04-27 14:49:48,828][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.0371060371398926, cross_entropy: 2.0371060371398926 +[2025-04-27 14:49:49,854][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.1961302757263184, cross_entropy: 1.1961302757263184 +[2025-04-27 14:49:51,842][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.0144999027252197, cross_entropy: 2.0144999027252197 +[2025-04-27 14:49:53,209][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 1.3378899097442627, cross_entropy: 1.3378899097442627 +[2025-04-27 14:49:54,665][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 1.1261167526245117, cross_entropy: 1.1261167526245117 +[2025-04-27 14:49:56,292][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.295068383216858, cross_entropy: 1.295068383216858 +[2025-04-27 14:49:57,653][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 2.0376925468444824, cross_entropy: 2.0376925468444824 +[2025-04-27 14:49:59,363][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.0614057779312134, cross_entropy: 1.0614057779312134 +[2025-04-27 14:50:01,744][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 0.7866573929786682, cross_entropy: 0.7866573929786682 +[2025-04-27 14:50:02,655][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 0.9891939163208008, cross_entropy: 0.9891939163208008 +[2025-04-27 14:50:05,001][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 2.0247116088867188, cross_entropy: 2.0247116088867188 +[2025-04-27 14:50:06,371][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.1771461963653564, cross_entropy: 1.1771461963653564 +[2025-04-27 14:50:08,677][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 3.0603179931640625, cross_entropy: 3.0603179931640625 +[2025-04-27 14:50:09,589][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.6425366401672363, cross_entropy: 2.6425366401672363 +[2025-04-27 14:50:12,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.8567116260528564, cross_entropy: 1.8567116260528564 +[2025-04-27 14:50:12,679][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.4188534021377563, cross_entropy: 1.4188534021377563 +[2025-04-27 14:50:16,828][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 0.738991916179657, cross_entropy: 0.738991916179657 +[2025-04-27 14:50:17,168][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 0.7607951164245605, cross_entropy: 0.7607951164245605 +[2025-04-27 14:50:20,304][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.4850889444351196, cross_entropy: 1.4850889444351196 +[2025-04-27 14:50:20,644][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 1.7314285039901733, cross_entropy: 1.7314285039901733 +[2025-04-27 14:50:24,537][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.105299711227417, cross_entropy: 1.105299711227417 +[2025-04-27 14:50:24,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.1210540533065796, cross_entropy: 1.1210540533065796 +[2025-04-27 14:50:28,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.494886040687561, cross_entropy: 1.494886040687561 +[2025-04-27 14:50:28,793][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.1894993782043457, cross_entropy: 1.1894993782043457 +[2025-04-27 14:50:31,862][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 2.280820846557617, cross_entropy: 2.280820846557617 +[2025-04-27 14:50:32,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.304384708404541, cross_entropy: 1.304384708404541 +[2025-04-27 14:50:35,796][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.9250783920288086, cross_entropy: 2.9250783920288086 +[2025-04-27 14:50:36,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.5269381999969482, cross_entropy: 1.5269381999969482 +[2025-04-27 14:50:39,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.548839569091797, cross_entropy: 2.548839569091797 +[2025-04-27 14:50:39,617][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.3088557720184326, cross_entropy: 1.3088557720184326 +[2025-04-27 14:50:42,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 3.1263298988342285, cross_entropy: 3.1263298988342285 +[2025-04-27 14:50:43,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 2.8707046508789062, cross_entropy: 2.8707046508789062 +[2025-04-27 14:50:45,971][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.540344476699829, cross_entropy: 1.540344476699829 +[2025-04-27 14:50:46,310][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.1505179405212402, cross_entropy: 1.1505179405212402 +[2025-04-27 14:50:49,841][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.545224905014038, cross_entropy: 1.545224905014038 +[2025-04-27 14:50:50,189][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.9846316576004028, cross_entropy: 1.9846316576004028 +[2025-04-27 14:50:53,222][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 0.9945546388626099, cross_entropy: 0.9945546388626099 +[2025-04-27 14:50:53,567][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.9642914533615112, cross_entropy: 1.9642914533615112 +[2025-04-27 14:50:56,683][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 2.6916987895965576, cross_entropy: 2.6916987895965576 +[2025-04-27 14:50:57,018][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 3.006598949432373, cross_entropy: 3.006598949432373 +[2025-04-27 14:51:00,665][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 3.1212337017059326, cross_entropy: 3.1212337017059326 +[2025-04-27 14:51:00,979][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.3605611324310303, cross_entropy: 3.3605611324310303 +[2025-04-27 14:51:05,184][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.2436728477478027, cross_entropy: 2.2436728477478027 +[2025-04-27 14:51:05,494][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 2.864298105239868, cross_entropy: 2.864298105239868 +[2025-04-27 14:51:08,887][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 0.980810284614563, cross_entropy: 0.980810284614563 +[2025-04-27 14:51:09,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.7852076292037964, cross_entropy: 1.7852076292037964 +[2025-04-27 14:51:12,210][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 2.3116393089294434, cross_entropy: 2.3116393089294434 +[2025-04-27 14:51:12,556][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.3014320135116577, cross_entropy: 1.3014320135116577 +[2025-04-27 14:51:16,154][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 0.956609845161438, cross_entropy: 0.956609845161438 +[2025-04-27 14:51:16,492][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 1.1160286664962769, cross_entropy: 1.1160286664962769 +[2025-04-27 14:51:19,565][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 1.2837921380996704, cross_entropy: 1.2837921380996704 +[2025-04-27 14:51:19,877][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 3.275315523147583, cross_entropy: 3.275315523147583 +[2025-04-27 14:51:22,982][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 3.3558521270751953, cross_entropy: 3.3558521270751953 +[2025-04-27 14:51:23,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 1.13417649269104, cross_entropy: 1.13417649269104 +[2025-04-27 14:51:26,021][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.6570931673049927, cross_entropy: 1.6570931673049927 +[2025-04-27 14:51:26,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.343226671218872, cross_entropy: 1.343226671218872 +[2025-04-27 14:51:29,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 2.9178152084350586, cross_entropy: 2.9178152084350586 +[2025-04-27 14:51:29,853][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.3714523315429688, cross_entropy: 2.3714523315429688 +[2025-04-27 14:51:32,669][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 3.5374412536621094, cross_entropy: 3.5374412536621094 +[2025-04-27 14:54:16,517][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.914361596107483, cross_entropy: 1.914361596107483 +[2025-04-27 14:54:16,517][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.2608625888824463, cross_entropy: 1.2608625888824463 +[2025-04-27 14:54:16,731][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 14:54:16,890][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch6.pth. +[2025-04-27 14:54:17,093][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 14:54:21,793][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.5138561725616455, cross_entropy: 2.5138561725616455 +[2025-04-27 14:54:22,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.6287920475006104, cross_entropy: 2.6287920475006104 +[2025-04-27 14:54:25,467][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 1.212480068206787, cross_entropy: 1.212480068206787 +[2025-04-27 14:54:25,809][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 0.6493011116981506, cross_entropy: 0.6493011116981506 +[2025-04-27 14:54:28,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 1.0130395889282227, cross_entropy: 1.0130395889282227 +[2025-04-27 14:54:29,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.0148061513900757, cross_entropy: 1.0148061513900757 +[2025-04-27 14:54:31,911][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.664320945739746, cross_entropy: 2.664320945739746 +[2025-04-27 14:54:32,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.2180659770965576, cross_entropy: 1.2180659770965576 +[2025-04-27 14:54:35,911][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.534379005432129, cross_entropy: 1.534379005432129 +[2025-04-27 14:54:36,247][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.3592326641082764, cross_entropy: 1.3592326641082764 +[2025-04-27 14:54:39,222][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 2.7264790534973145, cross_entropy: 2.7264790534973145 +[2025-04-27 14:54:39,535][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.9592344760894775, cross_entropy: 1.9592344760894775 +[2025-04-27 14:54:42,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.7604660987854004, cross_entropy: 2.7604660987854004 +[2025-04-27 14:54:42,678][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 3.0983214378356934, cross_entropy: 3.0983214378356934 +[2025-04-27 14:54:45,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.582894802093506, cross_entropy: 2.582894802093506 +[2025-04-27 14:54:46,045][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.5052919387817383, cross_entropy: 2.5052919387817383 +[2025-04-27 14:54:49,161][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 1.94437575340271, cross_entropy: 1.94437575340271 +[2025-04-27 14:54:49,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.1940529346466064, cross_entropy: 3.1940529346466064 +[2025-04-27 14:54:52,297][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.9570810794830322, cross_entropy: 2.9570810794830322 +[2025-04-27 14:54:52,611][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 0.9806957840919495, cross_entropy: 0.9806957840919495 +[2025-04-27 14:54:55,557][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.1353671550750732, cross_entropy: 1.1353671550750732 +[2025-04-27 14:54:55,893][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.3660690784454346, cross_entropy: 2.3660690784454346 +[2025-04-27 14:54:59,214][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 1.7980296611785889, cross_entropy: 1.7980296611785889 +[2025-04-27 14:54:59,553][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.485732078552246, cross_entropy: 2.485732078552246 +[2025-04-27 14:55:02,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.7765291929244995, cross_entropy: 1.7765291929244995 +[2025-04-27 14:55:02,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.422196626663208, cross_entropy: 2.422196626663208 +[2025-04-27 14:55:05,619][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.7004785537719727, cross_entropy: 2.7004785537719727 +[2025-04-27 14:55:06,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 2.876883029937744, cross_entropy: 2.876883029937744 +[2025-04-27 14:55:08,909][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.0196759700775146, cross_entropy: 1.0196759700775146 +[2025-04-27 14:55:09,700][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.034595012664795, cross_entropy: 1.034595012664795 +[2025-04-27 14:55:12,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.000333547592163, cross_entropy: 2.000333547592163 +[2025-04-27 14:55:13,355][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.2073748111724854, cross_entropy: 2.2073748111724854 +[2025-04-27 14:55:15,766][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.39704966545105, cross_entropy: 2.39704966545105 +[2025-04-27 14:55:16,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.0812206268310547, cross_entropy: 1.0812206268310547 +[2025-04-27 14:55:19,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.477891445159912, cross_entropy: 2.477891445159912 +[2025-04-27 14:55:20,558][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.6164600849151611, cross_entropy: 1.6164600849151611 +[2025-04-27 14:55:24,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.9636597633361816, cross_entropy: 2.9636597633361816 +[2025-04-27 14:55:24,679][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.0998809337615967, cross_entropy: 1.0998809337615967 +[2025-04-27 14:55:27,576][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 0.6870150566101074, cross_entropy: 0.6870150566101074 +[2025-04-27 14:55:27,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.3626078367233276, cross_entropy: 1.3626078367233276 +[2025-04-27 14:55:30,742][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.1332648992538452, cross_entropy: 1.1332648992538452 +[2025-04-27 14:55:31,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.193483829498291, cross_entropy: 2.193483829498291 +[2025-04-27 14:55:34,197][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.3811275959014893, cross_entropy: 2.3811275959014893 +[2025-04-27 14:55:34,509][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 2.913085460662842, cross_entropy: 2.913085460662842 +[2025-04-27 14:55:37,459][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.428709030151367, cross_entropy: 2.428709030151367 +[2025-04-27 14:55:37,776][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.6131665706634521, cross_entropy: 1.6131665706634521 +[2025-04-27 14:55:40,570][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 0.802948534488678, cross_entropy: 0.802948534488678 +[2025-04-27 14:55:40,907][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 0.9702610373497009, cross_entropy: 0.9702610373497009 +[2025-04-27 14:55:44,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.4945175647735596, cross_entropy: 2.4945175647735596 +[2025-04-27 14:55:44,436][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.0770068168640137, cross_entropy: 1.0770068168640137 +[2025-04-27 14:55:47,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.6506171226501465, cross_entropy: 2.6506171226501465 +[2025-04-27 14:55:47,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 3.1488704681396484, cross_entropy: 3.1488704681396484 +[2025-04-27 14:55:51,314][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 2.1472725868225098, cross_entropy: 2.1472725868225098 +[2025-04-27 14:55:51,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.716057777404785, cross_entropy: 2.716057777404785 +[2025-04-27 14:55:54,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 1.94099760055542, cross_entropy: 1.94099760055542 +[2025-04-27 14:55:54,981][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.7090494632720947, cross_entropy: 2.7090494632720947 +[2025-04-27 14:55:57,939][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.4787570238113403, cross_entropy: 1.4787570238113403 +[2025-04-27 14:55:58,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.2314649820327759, cross_entropy: 1.2314649820327759 +[2025-04-27 14:56:02,100][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 2.8608345985412598, cross_entropy: 2.8608345985412598 +[2025-04-27 14:56:02,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 2.87703275680542, cross_entropy: 2.87703275680542 +[2025-04-27 14:56:05,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 1.6853750944137573, cross_entropy: 1.6853750944137573 +[2025-04-27 14:56:05,603][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 2.045314073562622, cross_entropy: 2.045314073562622 +[2025-04-27 14:56:08,722][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.499683141708374, cross_entropy: 1.499683141708374 +[2025-04-27 14:56:09,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 1.032926082611084, cross_entropy: 1.032926082611084 +[2025-04-27 14:56:11,878][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.235584259033203, cross_entropy: 2.235584259033203 +[2025-04-27 14:56:12,222][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.1710662841796875, cross_entropy: 1.1710662841796875 +[2025-04-27 14:56:15,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.0868457555770874, cross_entropy: 1.0868457555770874 +[2025-04-27 14:56:15,505][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.7987380027770996, cross_entropy: 2.7987380027770996 +[2025-04-27 14:56:18,912][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 0.7925165295600891, cross_entropy: 0.7925165295600891 +[2025-04-27 14:56:19,226][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 0.8492417335510254, cross_entropy: 0.8492417335510254 +[2025-04-27 14:56:23,456][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.8501105308532715, cross_entropy: 2.8501105308532715 +[2025-04-27 14:56:23,794][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 1.2121800184249878, cross_entropy: 1.2121800184249878 +[2025-04-27 14:56:26,672][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 2.1396327018737793, cross_entropy: 2.1396327018737793 +[2025-04-27 14:56:27,008][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 2.7914974689483643, cross_entropy: 2.7914974689483643 +[2025-04-27 14:56:29,328][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 1.0798516273498535, cross_entropy: 1.0798516273498535 +[2025-04-27 14:56:29,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.722090244293213, cross_entropy: 1.722090244293213 +[2025-04-27 14:56:32,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.1894242763519287, cross_entropy: 2.1894242763519287 +[2025-04-27 14:56:32,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 2.4564623832702637, cross_entropy: 2.4564623832702637 +[2025-04-27 14:56:36,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.4110939502716064, cross_entropy: 2.4110939502716064 +[2025-04-27 14:56:36,394][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 1.7822685241699219, cross_entropy: 1.7822685241699219 +[2025-04-27 14:56:38,901][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 0.828388512134552, cross_entropy: 0.828388512134552 +[2025-04-27 14:56:39,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 1.690070629119873, cross_entropy: 1.690070629119873 +[2025-04-27 14:56:42,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.6606476306915283, cross_entropy: 2.6606476306915283 +[2025-04-27 14:56:42,396][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 2.7287986278533936, cross_entropy: 2.7287986278533936 +[2025-04-27 14:56:45,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.0899105072021484, cross_entropy: 1.0899105072021484 +[2025-04-27 14:56:45,667][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 2.0959486961364746, cross_entropy: 2.0959486961364746 +[2025-04-27 14:56:48,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 0.8562013506889343, cross_entropy: 0.8562013506889343 +[2025-04-27 14:56:49,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 1.4047356843948364, cross_entropy: 1.4047356843948364 +[2025-04-27 14:56:52,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 2.7270166873931885, cross_entropy: 2.7270166873931885 +[2025-04-27 14:56:52,393][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.0389703512191772, cross_entropy: 1.0389703512191772 +[2025-04-27 14:56:56,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 2.8880789279937744, cross_entropy: 2.8880789279937744 +[2025-04-27 14:56:56,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 0.7493010759353638, cross_entropy: 0.7493010759353638 +[2025-04-27 14:56:59,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.1183269023895264, cross_entropy: 1.1183269023895264 +[2025-04-27 14:57:00,148][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.1028380393981934, cross_entropy: 1.1028380393981934 +[2025-04-27 14:57:02,994][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.7994682788848877, cross_entropy: 2.7994682788848877 +[2025-04-27 14:57:03,306][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.5934598445892334, cross_entropy: 1.5934598445892334 +[2025-04-27 14:57:06,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.0587751865386963, cross_entropy: 1.0587751865386963 +[2025-04-27 14:57:06,737][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 1.0166347026824951, cross_entropy: 1.0166347026824951 +[2025-04-27 14:57:10,762][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.7035834789276123, cross_entropy: 1.7035834789276123 +[2025-04-27 14:57:11,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.7393429279327393, cross_entropy: 1.7393429279327393 +[2025-04-27 14:57:14,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 1.0680429935455322, cross_entropy: 1.0680429935455322 +[2025-04-27 14:57:14,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 0.7807340025901794, cross_entropy: 0.7807340025901794 +[2025-04-27 14:57:18,380][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.055832624435425, cross_entropy: 2.055832624435425 +[2025-04-27 14:57:18,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.2939692735671997, cross_entropy: 1.2939692735671997 +[2025-04-27 14:57:21,571][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.0040329694747925, cross_entropy: 1.0040329694747925 +[2025-04-27 14:57:21,905][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.2182040214538574, cross_entropy: 1.2182040214538574 +[2025-04-27 14:57:24,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.868494987487793, cross_entropy: 1.868494987487793 +[2025-04-27 14:57:25,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.210726022720337, cross_entropy: 1.210726022720337 +[2025-04-27 14:57:28,561][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 0.9001051783561707, cross_entropy: 0.9001051783561707 +[2025-04-27 14:57:28,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 0.8876677751541138, cross_entropy: 0.8876677751541138 +[2025-04-27 14:57:31,846][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 0.7614165544509888, cross_entropy: 0.7614165544509888 +[2025-04-27 14:57:32,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 0.878835916519165, cross_entropy: 0.878835916519165 +[2025-04-27 14:57:34,910][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.275977611541748, cross_entropy: 1.275977611541748 +[2025-04-27 14:57:35,248][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 0.7643886804580688, cross_entropy: 0.7643886804580688 +[2025-04-27 14:57:38,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.2049765586853027, cross_entropy: 1.2049765586853027 +[2025-04-27 14:57:38,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 0.7888831496238708, cross_entropy: 0.7888831496238708 +[2025-04-27 14:57:41,621][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 0.8519081473350525, cross_entropy: 0.8519081473350525 +[2025-04-27 14:57:41,961][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.580202579498291, cross_entropy: 2.580202579498291 +[2025-04-27 14:57:45,105][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.344254493713379, cross_entropy: 2.344254493713379 +[2025-04-27 14:57:45,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 1.1262140274047852, cross_entropy: 1.1262140274047852 +[2025-04-27 14:57:48,075][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.1879115104675293, cross_entropy: 1.1879115104675293 +[2025-04-27 14:57:48,414][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 1.2412725687026978, cross_entropy: 1.2412725687026978 +[2025-04-27 14:57:52,445][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.0032382011413574, cross_entropy: 2.0032382011413574 +[2025-04-27 14:57:52,780][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 2.4018335342407227, cross_entropy: 2.4018335342407227 +[2025-04-27 14:57:56,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 0.8958446979522705, cross_entropy: 0.8958446979522705 +[2025-04-27 14:57:56,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 0.9929777979850769, cross_entropy: 0.9929777979850769 +[2025-04-27 14:58:01,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.1636345386505127, cross_entropy: 3.1636345386505127 +[2025-04-27 14:58:01,744][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 0.9583320617675781, cross_entropy: 0.9583320617675781 +[2025-04-27 14:58:04,556][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 1.0283026695251465, cross_entropy: 1.0283026695251465 +[2025-04-27 14:58:04,867][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 0.9883643388748169, cross_entropy: 0.9883643388748169 +[2025-04-27 14:58:08,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 0.8871515989303589, cross_entropy: 0.8871515989303589 +[2025-04-27 14:58:08,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.1280527114868164, cross_entropy: 2.1280527114868164 +[2025-04-27 14:58:10,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 2.7221202850341797, cross_entropy: 2.7221202850341797 +[2025-04-27 14:58:11,321][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.553109884262085, cross_entropy: 1.553109884262085 +[2025-04-27 14:58:14,349][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 3.295703172683716, cross_entropy: 3.295703172683716 +[2025-04-27 14:58:14,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.5645689964294434, cross_entropy: 2.5645689964294434 +[2025-04-27 14:58:18,001][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 3.0528712272644043, cross_entropy: 3.0528712272644043 +[2025-04-27 14:58:18,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.2037123441696167, cross_entropy: 1.2037123441696167 +[2025-04-27 14:58:21,525][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.0724735260009766, cross_entropy: 1.0724735260009766 +[2025-04-27 14:58:21,835][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.423544406890869, cross_entropy: 2.423544406890869 +[2025-04-27 14:58:25,030][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 0.8462530970573425, cross_entropy: 0.8462530970573425 +[2025-04-27 14:58:25,816][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.5153248310089111, cross_entropy: 1.5153248310089111 +[2025-04-27 14:58:28,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 2.721951961517334, cross_entropy: 2.721951961517334 +[2025-04-27 14:58:28,683][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 1.0732237100601196, cross_entropy: 1.0732237100601196 +[2025-04-27 14:58:32,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.1997864246368408, cross_entropy: 1.1997864246368408 +[2025-04-27 14:58:32,677][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.216489315032959, cross_entropy: 1.216489315032959 +[2025-04-27 14:58:35,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 2.6092610359191895, cross_entropy: 2.6092610359191895 +[2025-04-27 14:58:35,760][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 0.7772137522697449, cross_entropy: 0.7772137522697449 +[2025-04-27 14:58:39,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.5499320030212402, cross_entropy: 2.5499320030212402 +[2025-04-27 14:58:39,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 0.9267371296882629, cross_entropy: 0.9267371296882629 +[2025-04-27 14:58:42,207][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.2441296577453613, cross_entropy: 2.2441296577453613 +[2025-04-27 14:58:42,544][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 2.9618377685546875, cross_entropy: 2.9618377685546875 +[2025-04-27 14:58:45,462][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.0800561904907227, cross_entropy: 2.0800561904907227 +[2025-04-27 14:58:45,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 2.205544948577881, cross_entropy: 2.205544948577881 +[2025-04-27 14:58:48,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 2.1753673553466797, cross_entropy: 2.1753673553466797 +[2025-04-27 14:58:49,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 0.9150387048721313, cross_entropy: 0.9150387048721313 +[2025-04-27 14:58:52,199][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.870336890220642, cross_entropy: 1.870336890220642 +[2025-04-27 14:58:52,535][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 2.9221601486206055, cross_entropy: 2.9221601486206055 +[2025-04-27 14:58:55,817][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.4169247150421143, cross_entropy: 1.4169247150421143 +[2025-04-27 14:58:56,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 1.3089351654052734, cross_entropy: 1.3089351654052734 +[2025-04-27 14:58:58,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 3.0291130542755127, cross_entropy: 3.0291130542755127 +[2025-04-27 14:58:59,088][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.358044147491455, cross_entropy: 1.358044147491455 +[2025-04-27 14:59:02,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.0590153932571411, cross_entropy: 1.0590153932571411 +[2025-04-27 14:59:02,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 2.1569948196411133, cross_entropy: 2.1569948196411133 +[2025-04-27 14:59:05,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 0.7463955283164978, cross_entropy: 0.7463955283164978 +[2025-04-27 14:59:05,639][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.1086077690124512, cross_entropy: 1.1086077690124512 +[2025-04-27 14:59:08,160][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 2.6656394004821777, cross_entropy: 2.6656394004821777 +[2025-04-27 14:59:08,472][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 2.761648654937744, cross_entropy: 2.761648654937744 +[2025-04-27 14:59:12,200][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.225735068321228, cross_entropy: 1.225735068321228 +[2025-04-27 14:59:12,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 3.151791572570801, cross_entropy: 3.151791572570801 +[2025-04-27 14:59:15,686][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.6517308950424194, cross_entropy: 1.6517308950424194 +[2025-04-27 14:59:15,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 2.7133066654205322, cross_entropy: 2.7133066654205322 +[2025-04-27 14:59:18,621][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 2.7172956466674805, cross_entropy: 2.7172956466674805 +[2025-04-27 14:59:18,932][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 2.084141254425049, cross_entropy: 2.084141254425049 +[2025-04-27 14:59:22,024][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 3.3265323638916016, cross_entropy: 3.3265323638916016 +[2025-04-27 14:59:22,361][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 2.01829195022583, cross_entropy: 2.01829195022583 +[2025-04-27 14:59:25,474][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 2.7841312885284424, cross_entropy: 2.7841312885284424 +[2025-04-27 14:59:25,787][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.7556408643722534, cross_entropy: 1.7556408643722534 +[2025-04-27 14:59:28,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 2.7842769622802734, cross_entropy: 2.7842769622802734 +[2025-04-27 14:59:29,336][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.520648717880249, cross_entropy: 1.520648717880249 +[2025-04-27 14:59:32,416][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 1.3562309741973877, cross_entropy: 1.3562309741973877 +[2025-04-27 14:59:32,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 2.2428030967712402, cross_entropy: 2.2428030967712402 +[2025-04-27 14:59:36,437][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 2.2719225883483887, cross_entropy: 2.2719225883483887 +[2025-04-27 14:59:36,771][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 1.3823602199554443, cross_entropy: 1.3823602199554443 +[2025-04-27 14:59:39,680][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.165651559829712, cross_entropy: 1.165651559829712 +[2025-04-27 14:59:39,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.579987049102783, cross_entropy: 2.579987049102783 +[2025-04-27 14:59:43,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 2.7883639335632324, cross_entropy: 2.7883639335632324 +[2025-04-27 14:59:43,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 3.248378276824951, cross_entropy: 3.248378276824951 +[2025-04-27 14:59:47,719][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.2924466133117676, cross_entropy: 1.2924466133117676 +[2025-04-27 14:59:48,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 1.9799869060516357, cross_entropy: 1.9799869060516357 +[2025-04-27 14:59:51,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 1.8478901386260986, cross_entropy: 1.8478901386260986 +[2025-04-27 14:59:51,386][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.854467511177063, cross_entropy: 1.854467511177063 +[2025-04-27 14:59:54,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 3.0252671241760254, cross_entropy: 3.0252671241760254 +[2025-04-27 14:59:54,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.7519166469573975, cross_entropy: 2.7519166469573975 +[2025-04-27 14:59:57,609][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.886736512184143, cross_entropy: 1.886736512184143 +[2025-04-27 14:59:57,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.345907211303711, cross_entropy: 1.345907211303711 +[2025-04-27 15:00:01,320][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 3.00064754486084, cross_entropy: 3.00064754486084 +[2025-04-27 15:00:01,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 0.9375807046890259, cross_entropy: 0.9375807046890259 +[2025-04-27 15:00:04,910][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.1270055770874023, cross_entropy: 3.1270055770874023 +[2025-04-27 15:00:05,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.6069599390029907, cross_entropy: 1.6069599390029907 +[2025-04-27 15:00:08,189][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 3.0020928382873535, cross_entropy: 3.0020928382873535 +[2025-04-27 15:00:08,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.5549285411834717, cross_entropy: 2.5549285411834717 +[2025-04-27 15:00:11,607][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 0.8446742296218872, cross_entropy: 0.8446742296218872 +[2025-04-27 15:00:11,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.0827369689941406, cross_entropy: 2.0827369689941406 +[2025-04-27 15:00:16,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.1096949577331543, cross_entropy: 3.1096949577331543 +[2025-04-27 15:00:16,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 2.838357448577881, cross_entropy: 2.838357448577881 +[2025-04-27 15:00:19,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 0.8213949203491211, cross_entropy: 0.8213949203491211 +[2025-04-27 15:00:19,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.3477725982666016, cross_entropy: 1.3477725982666016 +[2025-04-27 15:00:23,235][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 0.5685825347900391, cross_entropy: 0.5685825347900391 +[2025-04-27 15:00:23,548][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 3.0000410079956055, cross_entropy: 3.0000410079956055 +[2025-04-27 15:00:26,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 3.0387017726898193, cross_entropy: 3.0387017726898193 +[2025-04-27 15:00:27,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.6987910270690918, cross_entropy: 1.6987910270690918 +[2025-04-27 15:00:30,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 2.6518681049346924, cross_entropy: 2.6518681049346924 +[2025-04-27 15:00:30,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.3527581691741943, cross_entropy: 1.3527581691741943 +[2025-04-27 15:00:34,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.250749945640564, cross_entropy: 1.250749945640564 +[2025-04-27 15:00:34,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 2.9860072135925293, cross_entropy: 2.9860072135925293 +[2025-04-27 15:00:38,150][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.922083854675293, cross_entropy: 2.922083854675293 +[2025-04-27 15:00:38,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 1.0317059755325317, cross_entropy: 1.0317059755325317 +[2025-04-27 15:00:41,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.2609374523162842, cross_entropy: 1.2609374523162842 +[2025-04-27 15:00:41,778][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.6806716918945312, cross_entropy: 2.6806716918945312 +[2025-04-27 15:00:45,504][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 2.824436664581299, cross_entropy: 2.824436664581299 +[2025-04-27 15:00:45,824][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 0.8334245681762695, cross_entropy: 0.8334245681762695 +[2025-04-27 15:00:48,698][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.841464042663574, cross_entropy: 2.841464042663574 +[2025-04-27 15:00:49,037][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 3.1590263843536377, cross_entropy: 3.1590263843536377 +[2025-04-27 15:00:51,867][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.4335753917694092, cross_entropy: 1.4335753917694092 +[2025-04-27 15:00:52,179][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 2.9147250652313232, cross_entropy: 2.9147250652313232 +[2025-04-27 15:00:55,202][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 0.9626630544662476, cross_entropy: 0.9626630544662476 +[2025-04-27 15:00:55,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 2.005452871322632, cross_entropy: 2.005452871322632 +[2025-04-27 15:00:58,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.5088350772857666, cross_entropy: 1.5088350772857666 +[2025-04-27 15:00:58,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 2.8411619663238525, cross_entropy: 2.8411619663238525 +[2025-04-27 15:01:01,419][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.915175437927246, cross_entropy: 2.915175437927246 +[2025-04-27 15:01:01,742][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.0068131685256958, cross_entropy: 1.0068131685256958 +[2025-04-27 15:01:05,058][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 1.7858448028564453, cross_entropy: 1.7858448028564453 +[2025-04-27 15:01:05,396][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.2231483459472656, cross_entropy: 2.2231483459472656 +[2025-04-27 15:01:08,669][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.862417459487915, cross_entropy: 1.862417459487915 +[2025-04-27 15:01:09,016][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 0.945083737373352, cross_entropy: 0.945083737373352 +[2025-04-27 15:01:12,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 1.0672463178634644, cross_entropy: 1.0672463178634644 +[2025-04-27 15:01:12,954][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 3.2321243286132812, cross_entropy: 3.2321243286132812 +[2025-04-27 15:01:16,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 1.0729867219924927, cross_entropy: 1.0729867219924927 +[2025-04-27 15:01:16,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.441000461578369, cross_entropy: 2.441000461578369 +[2025-04-27 15:01:20,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 1.7045185565948486, cross_entropy: 1.7045185565948486 +[2025-04-27 15:01:20,468][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 0.8877049088478088, cross_entropy: 0.8877049088478088 +[2025-04-27 15:01:23,691][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.6344995498657227, cross_entropy: 1.6344995498657227 +[2025-04-27 15:01:24,011][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 2.479018211364746, cross_entropy: 2.479018211364746 +[2025-04-27 15:01:28,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 2.795724630355835, cross_entropy: 2.795724630355835 +[2025-04-27 15:01:28,357][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 1.9968061447143555, cross_entropy: 1.9968061447143555 +[2025-04-27 15:01:31,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 1.0165379047393799, cross_entropy: 1.0165379047393799 +[2025-04-27 15:01:31,844][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 2.118206024169922, cross_entropy: 2.118206024169922 +[2025-04-27 15:01:35,466][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 0.7577265501022339, cross_entropy: 0.7577265501022339 +[2025-04-27 15:01:35,803][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 0.9393603205680847, cross_entropy: 0.9393603205680847 +[2025-04-27 15:01:39,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.1348398923873901, cross_entropy: 1.1348398923873901 +[2025-04-27 15:01:39,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 1.3885469436645508, cross_entropy: 1.3885469436645508 +[2025-04-27 15:01:42,913][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 1.12528657913208, cross_entropy: 1.12528657913208 +[2025-04-27 15:01:43,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.3305742740631104, cross_entropy: 1.3305742740631104 +[2025-04-27 15:01:45,841][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 2.956395387649536, cross_entropy: 2.956395387649536 +[2025-04-27 15:01:46,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 0.8148963451385498, cross_entropy: 0.8148963451385498 +[2025-04-27 15:01:49,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.763463258743286, cross_entropy: 2.763463258743286 +[2025-04-27 15:01:49,584][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 1.5098953247070312, cross_entropy: 1.5098953247070312 +[2025-04-27 15:01:52,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.850633978843689, cross_entropy: 1.850633978843689 +[2025-04-27 15:01:52,891][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.995110273361206, cross_entropy: 2.995110273361206 +[2025-04-27 15:01:56,030][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 1.9610425233840942, cross_entropy: 1.9610425233840942 +[2025-04-27 15:01:56,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 3.1005821228027344, cross_entropy: 3.1005821228027344 +[2025-04-27 15:01:59,746][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.357273817062378, cross_entropy: 1.357273817062378 +[2025-04-27 15:02:00,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.725724458694458, cross_entropy: 1.725724458694458 +[2025-04-27 15:02:03,091][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.967405319213867, cross_entropy: 2.967405319213867 +[2025-04-27 15:02:03,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.5401849746704102, cross_entropy: 1.5401849746704102 +[2025-04-27 15:02:06,420][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.289900302886963, cross_entropy: 3.289900302886963 +[2025-04-27 15:02:06,731][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.0943384170532227, cross_entropy: 2.0943384170532227 +[2025-04-27 15:02:09,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 0.6497268676757812, cross_entropy: 0.6497268676757812 +[2025-04-27 15:02:10,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 0.8785901069641113, cross_entropy: 0.8785901069641113 +[2025-04-27 15:02:13,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 0.987322986125946, cross_entropy: 0.987322986125946 +[2025-04-27 15:02:13,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 0.9475167989730835, cross_entropy: 0.9475167989730835 +[2025-04-27 15:02:17,964][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.0843493938446045, cross_entropy: 2.0843493938446045 +[2025-04-27 15:02:18,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 0.7528712153434753, cross_entropy: 0.7528712153434753 +[2025-04-27 15:02:21,320][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.641874313354492, cross_entropy: 2.641874313354492 +[2025-04-27 15:02:21,659][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 1.6461033821105957, cross_entropy: 1.6461033821105957 +[2025-04-27 15:02:24,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.4294177293777466, cross_entropy: 1.4294177293777466 +[2025-04-27 15:02:24,994][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 0.9497816562652588, cross_entropy: 0.9497816562652588 +[2025-04-27 15:02:29,006][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 0.8300336003303528, cross_entropy: 0.8300336003303528 +[2025-04-27 15:02:29,344][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.774524450302124, cross_entropy: 1.774524450302124 +[2025-04-27 15:02:32,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.4446216821670532, cross_entropy: 1.4446216821670532 +[2025-04-27 15:02:32,632][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 0.8769569993019104, cross_entropy: 0.8769569993019104 +[2025-04-27 15:02:35,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.8644931316375732, cross_entropy: 2.8644931316375732 +[2025-04-27 15:02:36,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.414329171180725, cross_entropy: 1.414329171180725 +[2025-04-27 15:02:39,473][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 1.9626408815383911, cross_entropy: 1.9626408815383911 +[2025-04-27 15:02:39,789][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 1.0139648914337158, cross_entropy: 1.0139648914337158 +[2025-04-27 15:02:42,718][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 2.1162614822387695, cross_entropy: 2.1162614822387695 +[2025-04-27 15:02:43,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 3.0538296699523926, cross_entropy: 3.0538296699523926 +[2025-04-27 15:02:46,765][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 0.9504495859146118, cross_entropy: 0.9504495859146118 +[2025-04-27 15:02:47,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 1.021068811416626, cross_entropy: 1.021068811416626 +[2025-04-27 15:02:51,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 2.1127185821533203, cross_entropy: 2.1127185821533203 +[2025-04-27 15:02:51,856][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 2.437479019165039, cross_entropy: 2.437479019165039 +[2025-04-27 15:02:55,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 3.167917490005493, cross_entropy: 3.167917490005493 +[2025-04-27 15:02:55,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 2.885270833969116, cross_entropy: 2.885270833969116 +[2025-04-27 15:02:58,883][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 2.850996494293213, cross_entropy: 2.850996494293213 +[2025-04-27 15:02:59,222][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 2.818182945251465, cross_entropy: 2.818182945251465 +[2025-04-27 15:03:02,384][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.1989312171936035, cross_entropy: 2.1989312171936035 +[2025-04-27 15:03:02,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 2.0888783931732178, cross_entropy: 2.0888783931732178 +[2025-04-27 15:03:05,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 3.015015125274658, cross_entropy: 3.015015125274658 +[2025-04-27 15:03:05,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 1.0695955753326416, cross_entropy: 1.0695955753326416 +[2025-04-27 15:03:09,084][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.9102511405944824, cross_entropy: 2.9102511405944824 +[2025-04-27 15:03:09,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 2.342517375946045, cross_entropy: 2.342517375946045 +[2025-04-27 15:03:12,860][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.0796456336975098, cross_entropy: 1.0796456336975098 +[2025-04-27 15:03:13,203][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.3990648984909058, cross_entropy: 1.3990648984909058 +[2025-04-27 15:03:16,078][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.6332170963287354, cross_entropy: 1.6332170963287354 +[2025-04-27 15:03:16,420][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 1.1139320135116577, cross_entropy: 1.1139320135116577 +[2025-04-27 15:03:19,562][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.3799406290054321, cross_entropy: 1.3799406290054321 +[2025-04-27 15:03:19,901][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.218338966369629, cross_entropy: 2.218338966369629 +[2025-04-27 15:03:24,082][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 3.1037096977233887, cross_entropy: 3.1037096977233887 +[2025-04-27 15:03:24,421][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.8903963565826416, cross_entropy: 2.8903963565826416 +[2025-04-27 15:03:26,738][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.3274524211883545, cross_entropy: 1.3274524211883545 +[2025-04-27 15:03:27,079][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.1046159267425537, cross_entropy: 1.1046159267425537 +[2025-04-27 15:03:29,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.1225886344909668, cross_entropy: 1.1225886344909668 +[2025-04-27 15:03:29,866][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.3813410997390747, cross_entropy: 1.3813410997390747 +[2025-04-27 15:03:32,848][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.2901911735534668, cross_entropy: 1.2901911735534668 +[2025-04-27 15:03:33,189][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.7174313068389893, cross_entropy: 1.7174313068389893 +[2025-04-27 15:03:35,777][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.2026718854904175, cross_entropy: 1.2026718854904175 +[2025-04-27 15:03:36,090][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 2.6396307945251465, cross_entropy: 2.6396307945251465 +[2025-04-27 15:03:40,205][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 3.2475013732910156, cross_entropy: 3.2475013732910156 +[2025-04-27 15:03:40,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.336233615875244, cross_entropy: 2.336233615875244 +[2025-04-27 15:03:42,869][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 1.5694074630737305, cross_entropy: 1.5694074630737305 +[2025-04-27 15:03:43,212][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 0.9215100407600403, cross_entropy: 0.9215100407600403 +[2025-04-27 15:03:46,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.2705106735229492, cross_entropy: 1.2705106735229492 +[2025-04-27 15:03:46,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.363201379776001, cross_entropy: 2.363201379776001 +[2025-04-27 15:03:49,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 3.04386830329895, cross_entropy: 3.04386830329895 +[2025-04-27 15:03:50,314][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 0.5855689644813538, cross_entropy: 0.5855689644813538 +[2025-04-27 15:03:53,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.1776341199874878, cross_entropy: 1.1776341199874878 +[2025-04-27 15:03:53,755][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 2.9258079528808594, cross_entropy: 2.9258079528808594 +[2025-04-27 15:03:56,645][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.0316407680511475, cross_entropy: 1.0316407680511475 +[2025-04-27 15:03:56,978][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 2.5889573097229004, cross_entropy: 2.5889573097229004 +[2025-04-27 15:04:00,012][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 0.8294650316238403, cross_entropy: 0.8294650316238403 +[2025-04-27 15:04:00,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.2562443017959595, cross_entropy: 1.2562443017959595 +[2025-04-27 15:04:03,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.7424466609954834, cross_entropy: 2.7424466609954834 +[2025-04-27 15:04:03,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.2812023162841797, cross_entropy: 1.2812023162841797 +[2025-04-27 15:04:06,542][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 0.7711973786354065, cross_entropy: 0.7711973786354065 +[2025-04-27 15:04:06,877][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 2.6505026817321777, cross_entropy: 2.6505026817321777 +[2025-04-27 15:04:10,276][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.2835073471069336, cross_entropy: 1.2835073471069336 +[2025-04-27 15:04:10,614][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.5487347841262817, cross_entropy: 1.5487347841262817 +[2025-04-27 15:04:13,704][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.814840793609619, cross_entropy: 2.814840793609619 +[2025-04-27 15:04:14,045][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.1832692623138428, cross_entropy: 2.1832692623138428 +[2025-04-27 15:04:16,552][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 0.5677444338798523, cross_entropy: 0.5677444338798523 +[2025-04-27 15:04:16,890][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.3774439096450806, cross_entropy: 1.3774439096450806 +[2025-04-27 15:04:19,635][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 0.9088967442512512, cross_entropy: 0.9088967442512512 +[2025-04-27 15:04:20,184][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.8264064788818359, cross_entropy: 0.8264064788818359 +[2025-04-27 15:04:23,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.520374059677124, cross_entropy: 1.520374059677124 +[2025-04-27 15:04:23,889][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.6847676038742065, cross_entropy: 1.6847676038742065 +[2025-04-27 15:04:27,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 0.8078202605247498, cross_entropy: 0.8078202605247498 +[2025-04-27 15:04:27,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.1414852142333984, cross_entropy: 2.1414852142333984 +[2025-04-27 15:04:30,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.1070191860198975, cross_entropy: 1.1070191860198975 +[2025-04-27 15:04:30,644][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.5579752922058105, cross_entropy: 1.5579752922058105 +[2025-04-27 15:04:33,142][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 2.2207727432250977, cross_entropy: 2.2207727432250977 +[2025-04-27 15:04:33,630][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.6551108360290527, cross_entropy: 1.6551108360290527 +[2025-04-27 15:04:37,242][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.382875919342041, cross_entropy: 1.382875919342041 +[2025-04-27 15:04:37,553][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 3.1655502319335938, cross_entropy: 3.1655502319335938 +[2025-04-27 15:04:40,416][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.2156527042388916, cross_entropy: 1.2156527042388916 +[2025-04-27 15:04:40,696][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.0453851222991943, cross_entropy: 2.0453851222991943 +[2025-04-27 15:07:20,701][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.841442584991455, cross_entropy: 1.841442584991455 +[2025-04-27 15:07:20,702][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.219809889793396, cross_entropy: 1.219809889793396 +[2025-04-27 15:07:20,916][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/best_epoch.pth. +[2025-04-27 15:07:21,080][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch7.pth. +[2025-04-27 15:07:21,287][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 15:07:25,862][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.2999482154846191, cross_entropy: 1.2999482154846191 +[2025-04-27 15:07:26,210][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.0511577129364014, cross_entropy: 2.0511577129364014 +[2025-04-27 15:07:29,985][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 0.9489948153495789, cross_entropy: 0.9489948153495789 +[2025-04-27 15:07:30,301][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.9821226596832275, cross_entropy: 2.9821226596832275 +[2025-04-27 15:07:34,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 2.4809184074401855, cross_entropy: 2.4809184074401855 +[2025-04-27 15:07:34,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.2252049446105957, cross_entropy: 1.2252049446105957 +[2025-04-27 15:07:37,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.7221298217773438, cross_entropy: 0.7221298217773438 +[2025-04-27 15:07:37,979][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.733409881591797, cross_entropy: 2.733409881591797 +[2025-04-27 15:07:40,701][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 0.7802391052246094, cross_entropy: 0.7802391052246094 +[2025-04-27 15:07:41,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.534960150718689, cross_entropy: 1.534960150718689 +[2025-04-27 15:07:44,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 2.815441608428955, cross_entropy: 2.815441608428955 +[2025-04-27 15:07:44,780][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.8303022384643555, cross_entropy: 0.8303022384643555 +[2025-04-27 15:07:48,101][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 0.8640921711921692, cross_entropy: 0.8640921711921692 +[2025-04-27 15:07:48,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.420018196105957, cross_entropy: 2.420018196105957 +[2025-04-27 15:07:51,350][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 0.6876217126846313, cross_entropy: 0.6876217126846313 +[2025-04-27 15:07:51,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 0.6309432983398438, cross_entropy: 0.6309432983398438 +[2025-04-27 15:07:54,651][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 1.9610588550567627, cross_entropy: 1.9610588550567627 +[2025-04-27 15:07:54,992][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.2546632289886475, cross_entropy: 2.2546632289886475 +[2025-04-27 15:07:57,934][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 2.823312759399414, cross_entropy: 2.823312759399414 +[2025-04-27 15:07:58,248][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 0.5933437943458557, cross_entropy: 0.5933437943458557 +[2025-04-27 15:08:01,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.768494725227356, cross_entropy: 1.768494725227356 +[2025-04-27 15:08:01,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 2.743360996246338, cross_entropy: 2.743360996246338 +[2025-04-27 15:08:04,740][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.2466926574707031, cross_entropy: 1.2466926574707031 +[2025-04-27 15:08:05,362][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.4796653985977173, cross_entropy: 1.4796653985977173 +[2025-04-27 15:08:07,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 2.87827730178833, cross_entropy: 2.87827730178833 +[2025-04-27 15:08:08,844][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 2.2464511394500732, cross_entropy: 2.2464511394500732 +[2025-04-27 15:08:11,242][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.8316656947135925, cross_entropy: 0.8316656947135925 +[2025-04-27 15:08:12,230][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.0363078117370605, cross_entropy: 3.0363078117370605 +[2025-04-27 15:08:14,579][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.2141118049621582, cross_entropy: 1.2141118049621582 +[2025-04-27 15:08:15,661][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.1983036994934082, cross_entropy: 1.1983036994934082 +[2025-04-27 15:08:18,277][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.9289544224739075, cross_entropy: 0.9289544224739075 +[2025-04-27 15:08:18,915][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.324310779571533, cross_entropy: 2.324310779571533 +[2025-04-27 15:08:21,901][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 1.0495377779006958, cross_entropy: 1.0495377779006958 +[2025-04-27 15:08:22,304][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 2.9928321838378906, cross_entropy: 2.9928321838378906 +[2025-04-27 15:08:24,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 2.697120428085327, cross_entropy: 2.697120428085327 +[2025-04-27 15:08:25,376][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.3004285097122192, cross_entropy: 1.3004285097122192 +[2025-04-27 15:08:28,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 1.7552495002746582, cross_entropy: 1.7552495002746582 +[2025-04-27 15:08:28,785][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.912212371826172, cross_entropy: 2.912212371826172 +[2025-04-27 15:08:31,690][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.793386697769165, cross_entropy: 1.793386697769165 +[2025-04-27 15:08:32,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.5795670747756958, cross_entropy: 1.5795670747756958 +[2025-04-27 15:08:34,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 3.096925735473633, cross_entropy: 3.096925735473633 +[2025-04-27 15:08:35,233][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.391911268234253, cross_entropy: 1.391911268234253 +[2025-04-27 15:08:38,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.615994930267334, cross_entropy: 1.615994930267334 +[2025-04-27 15:08:38,982][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 0.9643120765686035, cross_entropy: 0.9643120765686035 +[2025-04-27 15:08:41,643][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 0.8924461603164673, cross_entropy: 0.8924461603164673 +[2025-04-27 15:08:42,116][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.887308120727539, cross_entropy: 2.887308120727539 +[2025-04-27 15:08:44,703][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.0473780632019043, cross_entropy: 1.0473780632019043 +[2025-04-27 15:08:45,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 2.7047019004821777, cross_entropy: 2.7047019004821777 +[2025-04-27 15:08:48,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.5878851413726807, cross_entropy: 2.5878851413726807 +[2025-04-27 15:08:48,703][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.5251264572143555, cross_entropy: 2.5251264572143555 +[2025-04-27 15:08:51,328][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 1.7686877250671387, cross_entropy: 1.7686877250671387 +[2025-04-27 15:08:51,672][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.5813831090927124, cross_entropy: 1.5813831090927124 +[2025-04-27 15:08:54,112][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.8626706600189209, cross_entropy: 0.8626706600189209 +[2025-04-27 15:08:54,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.7329806089401245, cross_entropy: 1.7329806089401245 +[2025-04-27 15:08:57,159][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.7603507041931152, cross_entropy: 2.7603507041931152 +[2025-04-27 15:08:57,947][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 1.012132167816162, cross_entropy: 1.012132167816162 +[2025-04-27 15:09:00,013][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.080035924911499, cross_entropy: 2.080035924911499 +[2025-04-27 15:09:01,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 1.0631847381591797, cross_entropy: 1.0631847381591797 +[2025-04-27 15:09:03,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 2.029904365539551, cross_entropy: 2.029904365539551 +[2025-04-27 15:09:03,576][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.6906424164772034, cross_entropy: 0.6906424164772034 +[2025-04-27 15:09:07,014][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 1.9144076108932495, cross_entropy: 1.9144076108932495 +[2025-04-27 15:09:07,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.4419033527374268, cross_entropy: 1.4419033527374268 +[2025-04-27 15:09:10,385][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.888359546661377, cross_entropy: 2.888359546661377 +[2025-04-27 15:09:10,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 2.7192723751068115, cross_entropy: 2.7192723751068115 +[2025-04-27 15:09:13,572][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.746462106704712, cross_entropy: 2.746462106704712 +[2025-04-27 15:09:13,917][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 0.5928285717964172, cross_entropy: 0.5928285717964172 +[2025-04-27 15:09:18,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.2998929023742676, cross_entropy: 2.2998929023742676 +[2025-04-27 15:09:18,356][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.9215493202209473, cross_entropy: 1.9215493202209473 +[2025-04-27 15:09:21,502][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 0.8062912225723267, cross_entropy: 0.8062912225723267 +[2025-04-27 15:09:21,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.8504281044006348, cross_entropy: 2.8504281044006348 +[2025-04-27 15:09:25,236][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.0783640146255493, cross_entropy: 1.0783640146255493 +[2025-04-27 15:09:25,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 2.644688844680786, cross_entropy: 2.644688844680786 +[2025-04-27 15:09:28,735][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.0844244956970215, cross_entropy: 1.0844244956970215 +[2025-04-27 15:09:29,077][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.3465561866760254, cross_entropy: 1.3465561866760254 +[2025-04-27 15:09:32,084][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.1994266510009766, cross_entropy: 1.1994266510009766 +[2025-04-27 15:09:32,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.781151294708252, cross_entropy: 2.781151294708252 +[2025-04-27 15:09:35,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 0.9734470248222351, cross_entropy: 0.9734470248222351 +[2025-04-27 15:09:36,186][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 0.7996819019317627, cross_entropy: 0.7996819019317627 +[2025-04-27 15:09:38,586][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 2.7960896492004395, cross_entropy: 2.7960896492004395 +[2025-04-27 15:09:38,919][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.6044015884399414, cross_entropy: 2.6044015884399414 +[2025-04-27 15:09:42,271][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 0.9573509097099304, cross_entropy: 0.9573509097099304 +[2025-04-27 15:09:42,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.1347625255584717, cross_entropy: 1.1347625255584717 +[2025-04-27 15:09:45,322][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.061915874481201, cross_entropy: 2.061915874481201 +[2025-04-27 15:09:45,633][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.2133965492248535, cross_entropy: 1.2133965492248535 +[2025-04-27 15:09:49,293][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.987212896347046, cross_entropy: 1.987212896347046 +[2025-04-27 15:09:49,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 0.9290137887001038, cross_entropy: 0.9290137887001038 +[2025-04-27 15:09:52,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 1.8800281286239624, cross_entropy: 1.8800281286239624 +[2025-04-27 15:09:53,219][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.9548609256744385, cross_entropy: 2.9548609256744385 +[2025-04-27 15:09:56,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 0.7321265339851379, cross_entropy: 0.7321265339851379 +[2025-04-27 15:09:56,619][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 0.9916605949401855, cross_entropy: 0.9916605949401855 +[2025-04-27 15:09:59,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.586386203765869, cross_entropy: 2.586386203765869 +[2025-04-27 15:10:00,087][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 1.0757455825805664, cross_entropy: 1.0757455825805664 +[2025-04-27 15:10:03,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.0888296365737915, cross_entropy: 1.0888296365737915 +[2025-04-27 15:10:04,203][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 0.8703663349151611, cross_entropy: 0.8703663349151611 +[2025-04-27 15:10:07,480][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.3568410873413086, cross_entropy: 1.3568410873413086 +[2025-04-27 15:10:07,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.3785878419876099, cross_entropy: 1.3785878419876099 +[2025-04-27 15:10:10,181][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.7083935737609863, cross_entropy: 2.7083935737609863 +[2025-04-27 15:10:10,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 0.7864125370979309, cross_entropy: 0.7864125370979309 +[2025-04-27 15:10:13,949][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.4967797994613647, cross_entropy: 1.4967797994613647 +[2025-04-27 15:10:14,263][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.1748759746551514, cross_entropy: 1.1748759746551514 +[2025-04-27 15:10:17,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.399381160736084, cross_entropy: 2.399381160736084 +[2025-04-27 15:10:17,990][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.140467643737793, cross_entropy: 2.140467643737793 +[2025-04-27 15:10:21,043][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.226710557937622, cross_entropy: 2.226710557937622 +[2025-04-27 15:10:21,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.3030139207839966, cross_entropy: 1.3030139207839966 +[2025-04-27 15:10:24,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 3.1590683460235596, cross_entropy: 3.1590683460235596 +[2025-04-27 15:10:24,576][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 2.4401988983154297, cross_entropy: 2.4401988983154297 +[2025-04-27 15:10:27,570][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.5941352844238281, cross_entropy: 1.5941352844238281 +[2025-04-27 15:10:27,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 3.0280909538269043, cross_entropy: 3.0280909538269043 +[2025-04-27 15:10:30,439][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 0.7856898307800293, cross_entropy: 0.7856898307800293 +[2025-04-27 15:10:30,773][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.513475179672241, cross_entropy: 2.513475179672241 +[2025-04-27 15:10:33,728][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 2.1259469985961914, cross_entropy: 2.1259469985961914 +[2025-04-27 15:10:34,088][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.8079861402511597, cross_entropy: 1.8079861402511597 +[2025-04-27 15:10:37,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 1.9855830669403076, cross_entropy: 1.9855830669403076 +[2025-04-27 15:10:37,537][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 0.935003399848938, cross_entropy: 0.935003399848938 +[2025-04-27 15:10:40,492][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 1.9897468090057373, cross_entropy: 1.9897468090057373 +[2025-04-27 15:10:40,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.5111713409423828, cross_entropy: 1.5111713409423828 +[2025-04-27 15:10:44,151][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.1334056854248047, cross_entropy: 2.1334056854248047 +[2025-04-27 15:10:44,494][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.2222416400909424, cross_entropy: 1.2222416400909424 +[2025-04-27 15:10:47,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 2.6563339233398438, cross_entropy: 2.6563339233398438 +[2025-04-27 15:10:47,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 1.6296603679656982, cross_entropy: 1.6296603679656982 +[2025-04-27 15:10:50,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 2.5167782306671143, cross_entropy: 2.5167782306671143 +[2025-04-27 15:10:50,944][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 0.6973133087158203, cross_entropy: 0.6973133087158203 +[2025-04-27 15:10:54,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.8491628170013428, cross_entropy: 2.8491628170013428 +[2025-04-27 15:10:54,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.4778485298156738, cross_entropy: 1.4778485298156738 +[2025-04-27 15:10:58,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.0880786180496216, cross_entropy: 1.0880786180496216 +[2025-04-27 15:10:58,512][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 0.7253109216690063, cross_entropy: 0.7253109216690063 +[2025-04-27 15:11:01,955][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 2.8401081562042236, cross_entropy: 2.8401081562042236 +[2025-04-27 15:11:02,303][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.9251465797424316, cross_entropy: 1.9251465797424316 +[2025-04-27 15:11:05,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 0.9912885427474976, cross_entropy: 0.9912885427474976 +[2025-04-27 15:11:05,867][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 0.6918189525604248, cross_entropy: 0.6918189525604248 +[2025-04-27 15:11:08,825][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 2.7513973712921143, cross_entropy: 2.7513973712921143 +[2025-04-27 15:11:09,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 1.9836479425430298, cross_entropy: 1.9836479425430298 +[2025-04-27 15:11:12,504][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 2.502391815185547, cross_entropy: 2.502391815185547 +[2025-04-27 15:11:12,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.2065266370773315, cross_entropy: 1.2065266370773315 +[2025-04-27 15:11:16,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.3227310180664062, cross_entropy: 2.3227310180664062 +[2025-04-27 15:11:16,371][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 2.620863437652588, cross_entropy: 2.620863437652588 +[2025-04-27 15:11:19,324][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 2.74397349357605, cross_entropy: 2.74397349357605 +[2025-04-27 15:11:19,676][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 2.7734930515289307, cross_entropy: 2.7734930515289307 +[2025-04-27 15:11:23,237][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 2.1894025802612305, cross_entropy: 2.1894025802612305 +[2025-04-27 15:11:23,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 0.963395357131958, cross_entropy: 0.963395357131958 +[2025-04-27 15:11:26,773][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 0.8137775659561157, cross_entropy: 0.8137775659561157 +[2025-04-27 15:11:27,114][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.6678247451782227, cross_entropy: 2.6678247451782227 +[2025-04-27 15:11:30,022][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.0820893049240112, cross_entropy: 1.0820893049240112 +[2025-04-27 15:11:30,368][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.7908811569213867, cross_entropy: 2.7908811569213867 +[2025-04-27 15:11:33,448][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 3.052828550338745, cross_entropy: 3.052828550338745 +[2025-04-27 15:11:33,764][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.7669005393981934, cross_entropy: 2.7669005393981934 +[2025-04-27 15:11:36,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.2694607973098755, cross_entropy: 1.2694607973098755 +[2025-04-27 15:11:37,224][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 0.6764490604400635, cross_entropy: 0.6764490604400635 +[2025-04-27 15:11:40,498][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 0.643427848815918, cross_entropy: 0.643427848815918 +[2025-04-27 15:11:40,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.2069830894470215, cross_entropy: 1.2069830894470215 +[2025-04-27 15:11:43,831][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.1621809005737305, cross_entropy: 2.1621809005737305 +[2025-04-27 15:11:44,145][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.4567759037017822, cross_entropy: 1.4567759037017822 +[2025-04-27 15:11:47,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.6725795269012451, cross_entropy: 1.6725795269012451 +[2025-04-27 15:11:48,119][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.1524354219436646, cross_entropy: 1.1524354219436646 +[2025-04-27 15:11:51,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.938241958618164, cross_entropy: 1.938241958618164 +[2025-04-27 15:11:51,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.2859046459197998, cross_entropy: 1.2859046459197998 +[2025-04-27 15:11:54,449][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 1.3431947231292725, cross_entropy: 1.3431947231292725 +[2025-04-27 15:11:54,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 0.6494960188865662, cross_entropy: 0.6494960188865662 +[2025-04-27 15:11:58,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.3694024085998535, cross_entropy: 2.3694024085998535 +[2025-04-27 15:11:58,435][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 2.8780136108398438, cross_entropy: 2.8780136108398438 +[2025-04-27 15:12:01,650][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.657903790473938, cross_entropy: 1.657903790473938 +[2025-04-27 15:12:01,963][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 3.113607168197632, cross_entropy: 3.113607168197632 +[2025-04-27 15:12:05,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 2.8545196056365967, cross_entropy: 2.8545196056365967 +[2025-04-27 15:12:05,317][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 1.561202049255371, cross_entropy: 1.561202049255371 +[2025-04-27 15:12:08,234][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.7188947200775146, cross_entropy: 2.7188947200775146 +[2025-04-27 15:12:08,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.278281569480896, cross_entropy: 1.278281569480896 +[2025-04-27 15:12:11,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.8924169540405273, cross_entropy: 2.8924169540405273 +[2025-04-27 15:12:11,994][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 0.7533093094825745, cross_entropy: 0.7533093094825745 +[2025-04-27 15:12:14,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 1.9029409885406494, cross_entropy: 1.9029409885406494 +[2025-04-27 15:12:15,220][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.0617291927337646, cross_entropy: 1.0617291927337646 +[2025-04-27 15:12:18,303][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 0.8141680955886841, cross_entropy: 0.8141680955886841 +[2025-04-27 15:12:18,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.2288086414337158, cross_entropy: 1.2288086414337158 +[2025-04-27 15:12:22,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 1.4020203351974487, cross_entropy: 1.4020203351974487 +[2025-04-27 15:12:22,822][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.9699970483779907, cross_entropy: 1.9699970483779907 +[2025-04-27 15:12:25,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 0.8857265710830688, cross_entropy: 0.8857265710830688 +[2025-04-27 15:12:26,331][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.9193633198738098, cross_entropy: 0.9193633198738098 +[2025-04-27 15:12:28,905][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.067081093788147, cross_entropy: 1.067081093788147 +[2025-04-27 15:12:29,878][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 1.9593138694763184, cross_entropy: 1.9593138694763184 +[2025-04-27 15:12:32,472][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.2334492206573486, cross_entropy: 1.2334492206573486 +[2025-04-27 15:12:32,900][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.521369218826294, cross_entropy: 2.521369218826294 +[2025-04-27 15:12:36,145][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.8880057334899902, cross_entropy: 2.8880057334899902 +[2025-04-27 15:12:36,491][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 2.8852171897888184, cross_entropy: 2.8852171897888184 +[2025-04-27 15:12:40,095][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 2.801210403442383, cross_entropy: 2.801210403442383 +[2025-04-27 15:12:40,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 3.041804313659668, cross_entropy: 3.041804313659668 +[2025-04-27 15:12:43,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.7628049850463867, cross_entropy: 2.7628049850463867 +[2025-04-27 15:12:43,659][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 1.6743171215057373, cross_entropy: 1.6743171215057373 +[2025-04-27 15:12:46,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 1.3815109729766846, cross_entropy: 1.3815109729766846 +[2025-04-27 15:12:46,927][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 2.760497808456421, cross_entropy: 2.760497808456421 +[2025-04-27 15:12:49,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 1.846819519996643, cross_entropy: 1.846819519996643 +[2025-04-27 15:12:50,951][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 0.9712976217269897, cross_entropy: 0.9712976217269897 +[2025-04-27 15:12:53,081][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.0785255432128906, cross_entropy: 2.0785255432128906 +[2025-04-27 15:12:54,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.2774608135223389, cross_entropy: 1.2774608135223389 +[2025-04-27 15:12:56,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 1.9451056718826294, cross_entropy: 1.9451056718826294 +[2025-04-27 15:12:57,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.8439664840698242, cross_entropy: 1.8439664840698242 +[2025-04-27 15:12:59,329][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 0.6928528547286987, cross_entropy: 0.6928528547286987 +[2025-04-27 15:12:59,987][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 1.901525855064392, cross_entropy: 1.901525855064392 +[2025-04-27 15:13:02,284][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 2.685349941253662, cross_entropy: 2.685349941253662 +[2025-04-27 15:13:03,270][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 1.9894343614578247, cross_entropy: 1.9894343614578247 +[2025-04-27 15:13:05,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 3.0207858085632324, cross_entropy: 3.0207858085632324 +[2025-04-27 15:13:06,453][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.5119524002075195, cross_entropy: 1.5119524002075195 +[2025-04-27 15:13:09,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 2.2095253467559814, cross_entropy: 2.2095253467559814 +[2025-04-27 15:13:09,571][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 3.171121597290039, cross_entropy: 3.171121597290039 +[2025-04-27 15:13:12,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.500164031982422, cross_entropy: 2.500164031982422 +[2025-04-27 15:13:12,483][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.61763334274292, cross_entropy: 2.61763334274292 +[2025-04-27 15:13:15,453][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 0.7987035512924194, cross_entropy: 0.7987035512924194 +[2025-04-27 15:13:15,791][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 1.0099282264709473, cross_entropy: 1.0099282264709473 +[2025-04-27 15:13:18,500][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 1.0367870330810547, cross_entropy: 1.0367870330810547 +[2025-04-27 15:13:18,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.0054261684417725, cross_entropy: 1.0054261684417725 +[2025-04-27 15:13:22,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 2.828889846801758, cross_entropy: 2.828889846801758 +[2025-04-27 15:13:22,431][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 2.7207274436950684, cross_entropy: 2.7207274436950684 +[2025-04-27 15:13:25,514][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 2.709850311279297, cross_entropy: 2.709850311279297 +[2025-04-27 15:13:26,066][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.7953977584838867, cross_entropy: 2.7953977584838867 +[2025-04-27 15:13:28,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.1311094760894775, cross_entropy: 1.1311094760894775 +[2025-04-27 15:13:29,369][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.9083075523376465, cross_entropy: 2.9083075523376465 +[2025-04-27 15:13:31,919][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.6639580726623535, cross_entropy: 2.6639580726623535 +[2025-04-27 15:13:32,621][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 2.8670101165771484, cross_entropy: 2.8670101165771484 +[2025-04-27 15:13:35,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.5158450603485107, cross_entropy: 2.5158450603485107 +[2025-04-27 15:13:35,781][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 2.842750072479248, cross_entropy: 2.842750072479248 +[2025-04-27 15:13:39,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 0.8229568004608154, cross_entropy: 0.8229568004608154 +[2025-04-27 15:13:39,977][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.198521852493286, cross_entropy: 2.198521852493286 +[2025-04-27 15:13:43,162][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 0.6502045392990112, cross_entropy: 0.6502045392990112 +[2025-04-27 15:13:43,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.081129312515259, cross_entropy: 2.081129312515259 +[2025-04-27 15:13:46,733][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 2.637221336364746, cross_entropy: 2.637221336364746 +[2025-04-27 15:13:47,070][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 2.4468533992767334, cross_entropy: 2.4468533992767334 +[2025-04-27 15:13:49,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.3987897634506226, cross_entropy: 1.3987897634506226 +[2025-04-27 15:13:50,026][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.222007989883423, cross_entropy: 2.222007989883423 +[2025-04-27 15:13:52,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.611211895942688, cross_entropy: 1.611211895942688 +[2025-04-27 15:13:53,163][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.0417675971984863, cross_entropy: 1.0417675971984863 +[2025-04-27 15:13:56,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.4417076110839844, cross_entropy: 2.4417076110839844 +[2025-04-27 15:13:57,149][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.6557469367980957, cross_entropy: 1.6557469367980957 +[2025-04-27 15:14:00,072][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 0.962175726890564, cross_entropy: 0.962175726890564 +[2025-04-27 15:14:00,409][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.3052321672439575, cross_entropy: 1.3052321672439575 +[2025-04-27 15:14:03,537][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 0.7286649346351624, cross_entropy: 0.7286649346351624 +[2025-04-27 15:14:03,878][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 0.993998110294342, cross_entropy: 0.993998110294342 +[2025-04-27 15:14:06,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.7988672256469727, cross_entropy: 1.7988672256469727 +[2025-04-27 15:14:07,891][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 1.7137912511825562, cross_entropy: 1.7137912511825562 +[2025-04-27 15:14:10,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 2.5192596912384033, cross_entropy: 2.5192596912384033 +[2025-04-27 15:14:11,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 3.0017504692077637, cross_entropy: 3.0017504692077637 +[2025-04-27 15:14:14,024][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 0.883287787437439, cross_entropy: 0.883287787437439 +[2025-04-27 15:14:14,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 2.9823403358459473, cross_entropy: 2.9823403358459473 +[2025-04-27 15:14:17,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 1.9302632808685303, cross_entropy: 1.9302632808685303 +[2025-04-27 15:14:17,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.1765079498291016, cross_entropy: 2.1765079498291016 +[2025-04-27 15:14:20,584][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 1.2664284706115723, cross_entropy: 1.2664284706115723 +[2025-04-27 15:14:20,896][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 0.9936314821243286, cross_entropy: 0.9936314821243286 +[2025-04-27 15:14:23,949][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.2380685806274414, cross_entropy: 2.2380685806274414 +[2025-04-27 15:14:24,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.1608340740203857, cross_entropy: 2.1608340740203857 +[2025-04-27 15:14:28,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.5399177074432373, cross_entropy: 1.5399177074432373 +[2025-04-27 15:14:28,503][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 0.9886850714683533, cross_entropy: 0.9886850714683533 +[2025-04-27 15:14:31,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 2.9541406631469727, cross_entropy: 2.9541406631469727 +[2025-04-27 15:14:31,989][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.067929983139038, cross_entropy: 2.067929983139038 +[2025-04-27 15:14:35,022][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.932176113128662, cross_entropy: 2.932176113128662 +[2025-04-27 15:14:35,335][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.1044583320617676, cross_entropy: 1.1044583320617676 +[2025-04-27 15:14:38,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.4425504207611084, cross_entropy: 1.4425504207611084 +[2025-04-27 15:14:38,484][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.464552164077759, cross_entropy: 2.464552164077759 +[2025-04-27 15:14:41,885][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.9255945682525635, cross_entropy: 2.9255945682525635 +[2025-04-27 15:14:42,219][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.0969252586364746, cross_entropy: 2.0969252586364746 +[2025-04-27 15:14:45,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 1.4349591732025146, cross_entropy: 1.4349591732025146 +[2025-04-27 15:14:45,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.958094835281372, cross_entropy: 1.958094835281372 +[2025-04-27 15:14:48,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.1026573181152344, cross_entropy: 1.1026573181152344 +[2025-04-27 15:14:48,628][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.2236889600753784, cross_entropy: 1.2236889600753784 +[2025-04-27 15:14:52,121][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 2.544313669204712, cross_entropy: 2.544313669204712 +[2025-04-27 15:14:52,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.1925573348999023, cross_entropy: 1.1925573348999023 +[2025-04-27 15:14:55,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 3.1315743923187256, cross_entropy: 3.1315743923187256 +[2025-04-27 15:14:55,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 0.619844913482666, cross_entropy: 0.619844913482666 +[2025-04-27 15:14:59,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 1.4205527305603027, cross_entropy: 1.4205527305603027 +[2025-04-27 15:14:59,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 0.9067970514297485, cross_entropy: 0.9067970514297485 +[2025-04-27 15:15:02,702][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 2.667652130126953, cross_entropy: 2.667652130126953 +[2025-04-27 15:15:03,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 1.166421890258789, cross_entropy: 1.166421890258789 +[2025-04-27 15:15:06,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 2.5615434646606445, cross_entropy: 2.5615434646606445 +[2025-04-27 15:15:06,440][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.5248429775238037, cross_entropy: 2.5248429775238037 +[2025-04-27 15:15:09,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 3.122114896774292, cross_entropy: 3.122114896774292 +[2025-04-27 15:15:09,822][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.337238073348999, cross_entropy: 2.337238073348999 +[2025-04-27 15:15:12,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 2.965271472930908, cross_entropy: 2.965271472930908 +[2025-04-27 15:15:12,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.1913156509399414, cross_entropy: 2.1913156509399414 +[2025-04-27 15:15:16,308][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 3.0766758918762207, cross_entropy: 3.0766758918762207 +[2025-04-27 15:15:16,644][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.3849713802337646, cross_entropy: 1.3849713802337646 +[2025-04-27 15:15:19,387][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 2.7148914337158203, cross_entropy: 2.7148914337158203 +[2025-04-27 15:15:19,726][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.053229570388794, cross_entropy: 1.053229570388794 +[2025-04-27 15:15:23,831][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 1.0937979221343994, cross_entropy: 1.0937979221343994 +[2025-04-27 15:15:24,146][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 0.8952876925468445, cross_entropy: 0.8952876925468445 +[2025-04-27 15:15:27,241][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.2546770572662354, cross_entropy: 2.2546770572662354 +[2025-04-27 15:15:27,581][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.5984158515930176, cross_entropy: 2.5984158515930176 +[2025-04-27 15:15:31,674][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.5982627868652344, cross_entropy: 2.5982627868652344 +[2025-04-27 15:15:32,011][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.8024966716766357, cross_entropy: 2.8024966716766357 +[2025-04-27 15:15:34,871][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 0.9181467294692993, cross_entropy: 0.9181467294692993 +[2025-04-27 15:15:35,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 1.7307034730911255, cross_entropy: 1.7307034730911255 +[2025-04-27 15:15:37,678][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 0.8122796416282654, cross_entropy: 0.8122796416282654 +[2025-04-27 15:15:38,018][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 0.8566830158233643, cross_entropy: 0.8566830158233643 +[2025-04-27 15:15:42,644][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 1.4416359663009644, cross_entropy: 1.4416359663009644 +[2025-04-27 15:15:42,967][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.2064311504364014, cross_entropy: 1.2064311504364014 +[2025-04-27 15:15:46,179][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.7270715236663818, cross_entropy: 1.7270715236663818 +[2025-04-27 15:15:46,492][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 2.9496512413024902, cross_entropy: 2.9496512413024902 +[2025-04-27 15:15:49,346][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 2.758096218109131, cross_entropy: 2.758096218109131 +[2025-04-27 15:15:49,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 3.123624324798584, cross_entropy: 3.123624324798584 +[2025-04-27 15:15:52,830][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.9482501745224, cross_entropy: 1.9482501745224 +[2025-04-27 15:15:53,167][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 0.8211593627929688, cross_entropy: 0.8211593627929688 +[2025-04-27 15:15:56,561][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.0023529529571533, cross_entropy: 2.0023529529571533 +[2025-04-27 15:15:56,875][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 1.9703319072723389, cross_entropy: 1.9703319072723389 +[2025-04-27 15:15:59,710][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 2.9543449878692627, cross_entropy: 2.9543449878692627 +[2025-04-27 15:16:00,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 1.1521964073181152, cross_entropy: 1.1521964073181152 +[2025-04-27 15:16:03,990][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.752901792526245, cross_entropy: 2.752901792526245 +[2025-04-27 15:16:04,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.7080786228179932, cross_entropy: 1.7080786228179932 +[2025-04-27 15:16:07,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 1.983412265777588, cross_entropy: 1.983412265777588 +[2025-04-27 15:16:07,725][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.7152743339538574, cross_entropy: 0.7152743339538574 +[2025-04-27 15:16:10,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.164952039718628, cross_entropy: 1.164952039718628 +[2025-04-27 15:16:11,017][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.1820485591888428, cross_entropy: 1.1820485591888428 +[2025-04-27 15:16:13,819][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.0908093452453613, cross_entropy: 1.0908093452453613 +[2025-04-27 15:16:14,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.0584949254989624, cross_entropy: 1.0584949254989624 +[2025-04-27 15:16:16,710][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.1872636079788208, cross_entropy: 1.1872636079788208 +[2025-04-27 15:16:17,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.7041910886764526, cross_entropy: 1.7041910886764526 +[2025-04-27 15:16:19,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 2.749454975128174, cross_entropy: 2.749454975128174 +[2025-04-27 15:16:20,239][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 1.595071792602539, cross_entropy: 1.595071792602539 +[2025-04-27 15:16:22,905][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 0.6726490259170532, cross_entropy: 0.6726490259170532 +[2025-04-27 15:16:23,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.5696773529052734, cross_entropy: 1.5696773529052734 +[2025-04-27 15:16:26,180][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.9299855828285217, cross_entropy: 0.9299855828285217 +[2025-04-27 15:16:26,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 0.7677755951881409, cross_entropy: 0.7677755951881409 +[2025-04-27 15:16:30,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.6340329051017761, cross_entropy: 0.6340329051017761 +[2025-04-27 15:16:30,963][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.6324398517608643, cross_entropy: 2.6324398517608643 +[2025-04-27 15:16:34,672][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.3390840291976929, cross_entropy: 1.3390840291976929 +[2025-04-27 15:16:34,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.4947483539581299, cross_entropy: 1.4947483539581299 +[2025-04-27 15:16:38,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.6877083778381348, cross_entropy: 2.6877083778381348 +[2025-04-27 15:16:38,912][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 0.8865088820457458, cross_entropy: 0.8865088820457458 +[2025-04-27 15:16:42,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.6618287563323975, cross_entropy: 1.6618287563323975 +[2025-04-27 15:16:42,404][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 2.135619640350342, cross_entropy: 2.135619640350342 +[2025-04-27 15:16:46,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.0417311191558838, cross_entropy: 1.0417311191558838 +[2025-04-27 15:16:47,121][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 2.743345260620117, cross_entropy: 2.743345260620117 +[2025-04-27 15:16:50,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 3.0061726570129395, cross_entropy: 3.0061726570129395 +[2025-04-27 15:16:50,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.8955761194229126, cross_entropy: 1.8955761194229126 +[2025-04-27 15:16:54,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.3449790477752686, cross_entropy: 1.3449790477752686 +[2025-04-27 15:16:54,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 0.8710871934890747, cross_entropy: 0.8710871934890747 +[2025-04-27 15:16:57,841][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 1.1727782487869263, cross_entropy: 1.1727782487869263 +[2025-04-27 15:16:58,171][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.3624379634857178, cross_entropy: 1.3624379634857178 +[2025-04-27 15:17:01,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.2697243690490723, cross_entropy: 1.2697243690490723 +[2025-04-27 15:17:02,124][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.3329923152923584, cross_entropy: 1.3329923152923584 +[2025-04-27 15:17:06,413][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 3.1125094890594482, cross_entropy: 3.1125094890594482 +[2025-04-27 15:17:06,725][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.8774956464767456, cross_entropy: 0.8774956464767456 +[2025-04-27 15:17:10,628][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 1.470395803451538, cross_entropy: 1.470395803451538 +[2025-04-27 15:17:10,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.2899856567382812, cross_entropy: 1.2899856567382812 +[2025-04-27 15:17:13,969][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.9589247703552246, cross_entropy: 1.9589247703552246 +[2025-04-27 15:17:14,297][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 3.0392844676971436, cross_entropy: 3.0392844676971436 +[2025-04-27 15:17:17,202][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.1048381328582764, cross_entropy: 1.1048381328582764 +[2025-04-27 15:17:17,515][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.758322238922119, cross_entropy: 2.758322238922119 +[2025-04-27 15:17:21,017][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.7450361251831055, cross_entropy: 2.7450361251831055 +[2025-04-27 15:17:21,356][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.9898918867111206, cross_entropy: 1.9898918867111206 +[2025-04-27 15:17:24,244][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.4938054084777832, cross_entropy: 1.4938054084777832 +[2025-04-27 15:17:24,567][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 2.4467732906341553, cross_entropy: 2.4467732906341553 +[2025-04-27 15:17:28,009][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.479142189025879, cross_entropy: 2.479142189025879 +[2025-04-27 15:17:28,340][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.166314721107483, cross_entropy: 1.166314721107483 +[2025-04-27 15:17:31,423][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.6499080657958984, cross_entropy: 2.6499080657958984 +[2025-04-27 15:17:31,755][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 1.6098583936691284, cross_entropy: 1.6098583936691284 +[2025-04-27 15:17:35,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.1940890550613403, cross_entropy: 1.1940890550613403 +[2025-04-27 15:17:35,700][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 2.980154037475586, cross_entropy: 2.980154037475586 +[2025-04-27 15:17:39,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 2.690809965133667, cross_entropy: 2.690809965133667 +[2025-04-27 15:17:39,631][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.853738307952881, cross_entropy: 2.853738307952881 +[2025-04-27 15:17:42,354][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 2.5831778049468994, cross_entropy: 2.5831778049468994 +[2025-04-27 15:17:42,632][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 0.9336814284324646, cross_entropy: 0.9336814284324646 +[2025-04-27 15:20:30,119][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.8293671607971191, cross_entropy: 1.8293671607971191 +[2025-04-27 15:20:30,119][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.268139123916626, cross_entropy: 1.268139123916626 +[2025-04-27 15:20:30,286][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch8.pth. +[2025-04-27 15:20:30,500][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 15:20:35,312][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.4840586185455322, cross_entropy: 1.4840586185455322 +[2025-04-27 15:20:35,857][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.1440985202789307, cross_entropy: 1.1440985202789307 +[2025-04-27 15:20:39,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 2.8083624839782715, cross_entropy: 2.8083624839782715 +[2025-04-27 15:20:39,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 2.9605154991149902, cross_entropy: 2.9605154991149902 +[2025-04-27 15:20:42,501][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 2.7783119678497314, cross_entropy: 2.7783119678497314 +[2025-04-27 15:20:42,839][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.083264946937561, cross_entropy: 1.083264946937561 +[2025-04-27 15:20:45,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.325878143310547, cross_entropy: 2.325878143310547 +[2025-04-27 15:20:46,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.13284969329834, cross_entropy: 2.13284969329834 +[2025-04-27 15:20:49,383][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.0427517890930176, cross_entropy: 2.0427517890930176 +[2025-04-27 15:20:49,724][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 3.077474355697632, cross_entropy: 3.077474355697632 +[2025-04-27 15:20:53,084][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.3606901168823242, cross_entropy: 1.3606901168823242 +[2025-04-27 15:20:53,908][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.6344369053840637, cross_entropy: 0.6344369053840637 +[2025-04-27 15:20:56,960][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.927300453186035, cross_entropy: 2.927300453186035 +[2025-04-27 15:20:57,298][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 0.8158590793609619, cross_entropy: 0.8158590793609619 +[2025-04-27 15:21:00,597][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.6314916610717773, cross_entropy: 2.6314916610717773 +[2025-04-27 15:21:00,934][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.996894359588623, cross_entropy: 0.996894359588623 +[2025-04-27 15:21:04,119][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 0.8494051694869995, cross_entropy: 0.8494051694869995 +[2025-04-27 15:21:04,455][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 0.8925638198852539, cross_entropy: 0.8925638198852539 +[2025-04-27 15:21:06,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 0.8945043087005615, cross_entropy: 0.8945043087005615 +[2025-04-27 15:21:07,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.541750431060791, cross_entropy: 1.541750431060791 +[2025-04-27 15:21:10,702][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.602266550064087, cross_entropy: 1.602266550064087 +[2025-04-27 15:21:11,014][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 1.5756772756576538, cross_entropy: 1.5756772756576538 +[2025-04-27 15:21:14,483][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.3722376823425293, cross_entropy: 2.3722376823425293 +[2025-04-27 15:21:14,811][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.4342422485351562, cross_entropy: 2.4342422485351562 +[2025-04-27 15:21:18,177][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 2.873278856277466, cross_entropy: 2.873278856277466 +[2025-04-27 15:21:18,519][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 1.576490879058838, cross_entropy: 1.576490879058838 +[2025-04-27 15:21:21,524][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.732107400894165, cross_entropy: 1.732107400894165 +[2025-04-27 15:21:21,861][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.002641201019287, cross_entropy: 2.002641201019287 +[2025-04-27 15:21:24,839][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.3304989337921143, cross_entropy: 2.3304989337921143 +[2025-04-27 15:21:25,176][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.3867247104644775, cross_entropy: 1.3867247104644775 +[2025-04-27 15:21:28,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.7173290252685547, cross_entropy: 2.7173290252685547 +[2025-04-27 15:21:28,640][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.4747940301895142, cross_entropy: 1.4747940301895142 +[2025-04-27 15:21:31,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.5548862218856812, cross_entropy: 1.5548862218856812 +[2025-04-27 15:21:32,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.496026039123535, cross_entropy: 2.496026039123535 +[2025-04-27 15:21:35,457][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 2.7476110458374023, cross_entropy: 2.7476110458374023 +[2025-04-27 15:21:35,780][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 0.7960819602012634, cross_entropy: 0.7960819602012634 +[2025-04-27 15:21:39,018][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 0.9105668663978577, cross_entropy: 0.9105668663978577 +[2025-04-27 15:21:39,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 2.746541976928711, cross_entropy: 2.746541976928711 +[2025-04-27 15:21:42,759][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 0.8064303398132324, cross_entropy: 0.8064303398132324 +[2025-04-27 15:21:43,095][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.914477586746216, cross_entropy: 2.914477586746216 +[2025-04-27 15:21:46,138][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 2.8918914794921875, cross_entropy: 2.8918914794921875 +[2025-04-27 15:21:46,451][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.5410361289978027, cross_entropy: 2.5410361289978027 +[2025-04-27 15:21:49,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.365377426147461, cross_entropy: 2.365377426147461 +[2025-04-27 15:21:49,673][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 0.725371241569519, cross_entropy: 0.725371241569519 +[2025-04-27 15:21:52,597][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.7986074090003967, cross_entropy: 0.7986074090003967 +[2025-04-27 15:21:52,971][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 1.8731951713562012, cross_entropy: 1.8731951713562012 +[2025-04-27 15:21:56,714][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.062330961227417, cross_entropy: 3.062330961227417 +[2025-04-27 15:21:57,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 2.9692137241363525, cross_entropy: 2.9692137241363525 +[2025-04-27 15:21:59,715][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 3.0317070484161377, cross_entropy: 3.0317070484161377 +[2025-04-27 15:22:00,051][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 0.8408392667770386, cross_entropy: 0.8408392667770386 +[2025-04-27 15:22:03,864][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.3742541074752808, cross_entropy: 1.3742541074752808 +[2025-04-27 15:22:04,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.034843921661377, cross_entropy: 1.034843921661377 +[2025-04-27 15:22:07,245][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 0.5358738899230957, cross_entropy: 0.5358738899230957 +[2025-04-27 15:22:07,557][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.4480359554290771, cross_entropy: 1.4480359554290771 +[2025-04-27 15:22:10,471][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 1.3659603595733643, cross_entropy: 1.3659603595733643 +[2025-04-27 15:22:10,973][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 3.1837692260742188, cross_entropy: 3.1837692260742188 +[2025-04-27 15:22:13,360][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 0.6716810464859009, cross_entropy: 0.6716810464859009 +[2025-04-27 15:22:14,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 0.9556173086166382, cross_entropy: 0.9556173086166382 +[2025-04-27 15:22:16,765][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.6200222969055176, cross_entropy: 1.6200222969055176 +[2025-04-27 15:22:17,497][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 3.078137159347534, cross_entropy: 3.078137159347534 +[2025-04-27 15:22:19,758][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.133392333984375, cross_entropy: 2.133392333984375 +[2025-04-27 15:22:20,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.246796131134033, cross_entropy: 2.246796131134033 +[2025-04-27 15:22:23,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 0.91415935754776, cross_entropy: 0.91415935754776 +[2025-04-27 15:22:23,875][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.267757773399353, cross_entropy: 1.267757773399353 +[2025-04-27 15:22:26,682][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.8390469551086426, cross_entropy: 2.8390469551086426 +[2025-04-27 15:22:27,529][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.7990888357162476, cross_entropy: 0.7990888357162476 +[2025-04-27 15:22:30,327][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.4597961902618408, cross_entropy: 0.4597961902618408 +[2025-04-27 15:22:31,648][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.7075825929641724, cross_entropy: 0.7075825929641724 +[2025-04-27 15:22:33,834][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 0.8220068216323853, cross_entropy: 0.8220068216323853 +[2025-04-27 15:22:34,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.1791563034057617, cross_entropy: 1.1791563034057617 +[2025-04-27 15:22:37,667][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 0.8483333587646484, cross_entropy: 0.8483333587646484 +[2025-04-27 15:22:38,003][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.1150016784667969, cross_entropy: 1.1150016784667969 +[2025-04-27 15:22:40,678][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.0746029615402222, cross_entropy: 1.0746029615402222 +[2025-04-27 15:22:40,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 0.7063181400299072, cross_entropy: 0.7063181400299072 +[2025-04-27 15:22:44,207][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 1.9839874505996704, cross_entropy: 1.9839874505996704 +[2025-04-27 15:22:44,544][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.7837772369384766, cross_entropy: 2.7837772369384766 +[2025-04-27 15:22:47,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 2.590033769607544, cross_entropy: 2.590033769607544 +[2025-04-27 15:22:47,715][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.5441460013389587, cross_entropy: 0.5441460013389587 +[2025-04-27 15:22:50,892][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 2.654954433441162, cross_entropy: 2.654954433441162 +[2025-04-27 15:22:51,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 1.0260810852050781, cross_entropy: 1.0260810852050781 +[2025-04-27 15:22:54,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.908457636833191, cross_entropy: 1.908457636833191 +[2025-04-27 15:22:54,864][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.8290809988975525, cross_entropy: 0.8290809988975525 +[2025-04-27 15:22:58,524][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.005772352218628, cross_entropy: 1.005772352218628 +[2025-04-27 15:22:58,889][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 3.005958080291748, cross_entropy: 3.005958080291748 +[2025-04-27 15:23:01,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.1913306713104248, cross_entropy: 1.1913306713104248 +[2025-04-27 15:23:02,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.4564491510391235, cross_entropy: 1.4564491510391235 +[2025-04-27 15:23:04,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.5233895778656006, cross_entropy: 2.5233895778656006 +[2025-04-27 15:23:06,159][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.7453587055206299, cross_entropy: 1.7453587055206299 +[2025-04-27 15:23:07,582][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 0.6820278167724609, cross_entropy: 0.6820278167724609 +[2025-04-27 15:23:09,510][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.36669921875, cross_entropy: 2.36669921875 +[2025-04-27 15:23:11,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.9665470123291016, cross_entropy: 2.9665470123291016 +[2025-04-27 15:23:12,801][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 1.7187455892562866, cross_entropy: 1.7187455892562866 +[2025-04-27 15:23:14,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.8799569606781006, cross_entropy: 2.8799569606781006 +[2025-04-27 15:23:15,994][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.7916330099105835, cross_entropy: 0.7916330099105835 +[2025-04-27 15:23:17,336][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 1.860446572303772, cross_entropy: 1.860446572303772 +[2025-04-27 15:23:19,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.0086462497711182, cross_entropy: 1.0086462497711182 +[2025-04-27 15:23:20,351][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 2.7490766048431396, cross_entropy: 2.7490766048431396 +[2025-04-27 15:23:23,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 1.28005850315094, cross_entropy: 1.28005850315094 +[2025-04-27 15:23:23,902][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.4739677906036377, cross_entropy: 1.4739677906036377 +[2025-04-27 15:23:27,144][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.3522350788116455, cross_entropy: 1.3522350788116455 +[2025-04-27 15:23:27,473][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.965148448944092, cross_entropy: 2.965148448944092 +[2025-04-27 15:23:30,036][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 2.733599901199341, cross_entropy: 2.733599901199341 +[2025-04-27 15:23:31,197][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.3799610137939453, cross_entropy: 1.3799610137939453 +[2025-04-27 15:23:33,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.9462080001831055, cross_entropy: 2.9462080001831055 +[2025-04-27 15:23:34,127][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 0.8359414339065552, cross_entropy: 0.8359414339065552 +[2025-04-27 15:23:36,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 2.925175189971924, cross_entropy: 2.925175189971924 +[2025-04-27 15:23:37,157][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.7368409633636475, cross_entropy: 2.7368409633636475 +[2025-04-27 15:23:39,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.7729748487472534, cross_entropy: 0.7729748487472534 +[2025-04-27 15:23:40,060][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 2.879268169403076, cross_entropy: 2.879268169403076 +[2025-04-27 15:23:43,350][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.8894840478897095, cross_entropy: 0.8894840478897095 +[2025-04-27 15:23:43,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 2.8137598037719727, cross_entropy: 2.8137598037719727 +[2025-04-27 15:23:46,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.2250418663024902, cross_entropy: 2.2250418663024902 +[2025-04-27 15:23:46,614][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.506828546524048, cross_entropy: 2.506828546524048 +[2025-04-27 15:23:49,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.5456123352050781, cross_entropy: 1.5456123352050781 +[2025-04-27 15:23:49,938][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.453901529312134, cross_entropy: 2.453901529312134 +[2025-04-27 15:23:52,674][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 1.1740598678588867, cross_entropy: 1.1740598678588867 +[2025-04-27 15:23:54,123][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 0.9954111576080322, cross_entropy: 0.9954111576080322 +[2025-04-27 15:23:55,704][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 1.9766451120376587, cross_entropy: 1.9766451120376587 +[2025-04-27 15:23:57,805][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.469585418701172, cross_entropy: 2.469585418701172 +[2025-04-27 15:23:58,736][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.154796600341797, cross_entropy: 2.154796600341797 +[2025-04-27 15:24:01,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.389613151550293, cross_entropy: 2.389613151550293 +[2025-04-27 15:24:01,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 0.883185863494873, cross_entropy: 0.883185863494873 +[2025-04-27 15:24:05,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 1.3915770053863525, cross_entropy: 1.3915770053863525 +[2025-04-27 15:24:05,958][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.763540029525757, cross_entropy: 2.763540029525757 +[2025-04-27 15:24:09,661][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 0.7216150760650635, cross_entropy: 0.7216150760650635 +[2025-04-27 15:24:09,974][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.1853609085083008, cross_entropy: 1.1853609085083008 +[2025-04-27 15:24:13,053][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 2.0569236278533936, cross_entropy: 2.0569236278533936 +[2025-04-27 15:24:13,390][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.3668396472930908, cross_entropy: 1.3668396472930908 +[2025-04-27 15:24:16,783][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 2.8322343826293945, cross_entropy: 2.8322343826293945 +[2025-04-27 15:24:17,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 0.8009342551231384, cross_entropy: 0.8009342551231384 +[2025-04-27 15:24:19,999][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 0.8350154757499695, cross_entropy: 0.8350154757499695 +[2025-04-27 15:24:20,312][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.712442398071289, cross_entropy: 2.712442398071289 +[2025-04-27 15:24:23,140][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 0.8452942371368408, cross_entropy: 0.8452942371368408 +[2025-04-27 15:24:23,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.279362678527832, cross_entropy: 1.279362678527832 +[2025-04-27 15:24:26,145][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.4414310455322266, cross_entropy: 1.4414310455322266 +[2025-04-27 15:24:26,495][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.3872382640838623, cross_entropy: 1.3872382640838623 +[2025-04-27 15:24:29,835][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.7629013061523438, cross_entropy: 2.7629013061523438 +[2025-04-27 15:24:30,170][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 0.7427355051040649, cross_entropy: 0.7427355051040649 +[2025-04-27 15:24:33,133][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.8740596771240234, cross_entropy: 2.8740596771240234 +[2025-04-27 15:24:33,480][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.664611577987671, cross_entropy: 2.664611577987671 +[2025-04-27 15:24:36,390][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.5442628860473633, cross_entropy: 2.5442628860473633 +[2025-04-27 15:24:36,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.656832456588745, cross_entropy: 2.656832456588745 +[2025-04-27 15:24:39,478][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.2257120609283447, cross_entropy: 2.2257120609283447 +[2025-04-27 15:24:39,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.313629150390625, cross_entropy: 2.313629150390625 +[2025-04-27 15:24:42,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 0.9460365772247314, cross_entropy: 0.9460365772247314 +[2025-04-27 15:24:43,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 2.44380784034729, cross_entropy: 2.44380784034729 +[2025-04-27 15:24:45,981][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 0.8234825134277344, cross_entropy: 0.8234825134277344 +[2025-04-27 15:24:46,293][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.5115313529968262, cross_entropy: 1.5115313529968262 +[2025-04-27 15:24:49,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.7601896524429321, cross_entropy: 0.7601896524429321 +[2025-04-27 15:24:50,299][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.123086452484131, cross_entropy: 2.123086452484131 +[2025-04-27 15:24:53,131][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 2.769397020339966, cross_entropy: 2.769397020339966 +[2025-04-27 15:24:53,456][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 2.6885790824890137, cross_entropy: 2.6885790824890137 +[2025-04-27 15:24:53,624][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/iteration3000.pth. +[2025-04-27 15:24:56,592][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 1.6650030612945557, cross_entropy: 1.6650030612945557 +[2025-04-27 15:24:56,909][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.1360855102539062, cross_entropy: 2.1360855102539062 +[2025-04-27 15:24:59,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 2.7119791507720947, cross_entropy: 2.7119791507720947 +[2025-04-27 15:25:00,329][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 2.843510150909424, cross_entropy: 2.843510150909424 +[2025-04-27 15:25:03,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.194471001625061, cross_entropy: 1.194471001625061 +[2025-04-27 15:25:03,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 1.0656887292861938, cross_entropy: 1.0656887292861938 +[2025-04-27 15:25:06,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 3.0629491806030273, cross_entropy: 3.0629491806030273 +[2025-04-27 15:25:07,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 0.8460099697113037, cross_entropy: 0.8460099697113037 +[2025-04-27 15:25:10,102][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 2.9602761268615723, cross_entropy: 2.9602761268615723 +[2025-04-27 15:25:10,439][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 2.4799938201904297, cross_entropy: 2.4799938201904297 +[2025-04-27 15:25:13,275][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 0.960484504699707, cross_entropy: 0.960484504699707 +[2025-04-27 15:25:13,586][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 2.8655803203582764, cross_entropy: 2.8655803203582764 +[2025-04-27 15:25:16,533][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.4513049125671387, cross_entropy: 2.4513049125671387 +[2025-04-27 15:25:16,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 0.6820602416992188, cross_entropy: 0.6820602416992188 +[2025-04-27 15:25:19,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 0.5712696313858032, cross_entropy: 0.5712696313858032 +[2025-04-27 15:25:20,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.664161205291748, cross_entropy: 2.664161205291748 +[2025-04-27 15:25:22,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.7002111077308655, cross_entropy: 0.7002111077308655 +[2025-04-27 15:25:23,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 2.181663990020752, cross_entropy: 2.181663990020752 +[2025-04-27 15:25:26,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 1.5267367362976074, cross_entropy: 1.5267367362976074 +[2025-04-27 15:25:26,515][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.569556474685669, cross_entropy: 1.569556474685669 +[2025-04-27 15:25:29,524][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.728282928466797, cross_entropy: 2.728282928466797 +[2025-04-27 15:25:29,861][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 0.7388261556625366, cross_entropy: 0.7388261556625366 +[2025-04-27 15:25:32,828][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.6478346586227417, cross_entropy: 1.6478346586227417 +[2025-04-27 15:25:33,178][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 0.898795485496521, cross_entropy: 0.898795485496521 +[2025-04-27 15:25:37,102][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.037311315536499, cross_entropy: 1.037311315536499 +[2025-04-27 15:25:37,438][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.7088665962219238, cross_entropy: 1.7088665962219238 +[2025-04-27 15:25:40,862][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.523533821105957, cross_entropy: 1.523533821105957 +[2025-04-27 15:25:41,174][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.6198134422302246, cross_entropy: 2.6198134422302246 +[2025-04-27 15:25:44,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.918003559112549, cross_entropy: 2.918003559112549 +[2025-04-27 15:25:44,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 1.418321132659912, cross_entropy: 1.418321132659912 +[2025-04-27 15:25:47,705][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.375967025756836, cross_entropy: 1.375967025756836 +[2025-04-27 15:25:48,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 1.2227479219436646, cross_entropy: 1.2227479219436646 +[2025-04-27 15:25:50,854][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 2.5592386722564697, cross_entropy: 2.5592386722564697 +[2025-04-27 15:25:51,189][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.393815040588379, cross_entropy: 2.393815040588379 +[2025-04-27 15:25:54,200][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.530973196029663, cross_entropy: 2.530973196029663 +[2025-04-27 15:25:54,528][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 1.094098448753357, cross_entropy: 1.094098448753357 +[2025-04-27 15:25:57,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.7970755100250244, cross_entropy: 1.7970755100250244 +[2025-04-27 15:25:57,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.1862061023712158, cross_entropy: 1.1862061023712158 +[2025-04-27 15:26:00,604][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 0.9788294434547424, cross_entropy: 0.9788294434547424 +[2025-04-27 15:26:00,939][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.2284486293792725, cross_entropy: 1.2284486293792725 +[2025-04-27 15:26:03,561][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.835660934448242, cross_entropy: 2.835660934448242 +[2025-04-27 15:26:03,898][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 0.6784056425094604, cross_entropy: 0.6784056425094604 +[2025-04-27 15:26:07,141][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 2.830226421356201, cross_entropy: 2.830226421356201 +[2025-04-27 15:26:07,479][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.2241621017456055, cross_entropy: 3.2241621017456055 +[2025-04-27 15:26:10,811][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 2.1596641540527344, cross_entropy: 2.1596641540527344 +[2025-04-27 15:26:11,147][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.8173621892929077, cross_entropy: 1.8173621892929077 +[2025-04-27 15:26:14,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 2.852745771408081, cross_entropy: 2.852745771408081 +[2025-04-27 15:26:14,579][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.1383715867996216, cross_entropy: 1.1383715867996216 +[2025-04-27 15:26:17,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.7243788242340088, cross_entropy: 0.7243788242340088 +[2025-04-27 15:26:17,358][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.0477828979492188, cross_entropy: 1.0477828979492188 +[2025-04-27 15:26:20,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.9006519913673401, cross_entropy: 0.9006519913673401 +[2025-04-27 15:26:20,610][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.004115581512451, cross_entropy: 2.004115581512451 +[2025-04-27 15:26:23,369][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.2089545726776123, cross_entropy: 1.2089545726776123 +[2025-04-27 15:26:23,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 1.8048813343048096, cross_entropy: 1.8048813343048096 +[2025-04-27 15:26:26,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.6766018867492676, cross_entropy: 2.6766018867492676 +[2025-04-27 15:26:27,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 0.995639443397522, cross_entropy: 0.995639443397522 +[2025-04-27 15:26:30,113][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 1.4400125741958618, cross_entropy: 1.4400125741958618 +[2025-04-27 15:26:30,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 1.753612995147705, cross_entropy: 1.753612995147705 +[2025-04-27 15:26:33,455][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 0.7001090049743652, cross_entropy: 0.7001090049743652 +[2025-04-27 15:26:33,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 0.6848029494285583, cross_entropy: 0.6848029494285583 +[2025-04-27 15:26:36,925][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 0.9560155868530273, cross_entropy: 0.9560155868530273 +[2025-04-27 15:26:37,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 2.1554813385009766, cross_entropy: 2.1554813385009766 +[2025-04-27 15:26:41,088][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 0.9637393951416016, cross_entropy: 0.9637393951416016 +[2025-04-27 15:26:41,425][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.8130196332931519, cross_entropy: 1.8130196332931519 +[2025-04-27 15:26:44,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 1.0191402435302734, cross_entropy: 1.0191402435302734 +[2025-04-27 15:26:45,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 2.7701799869537354, cross_entropy: 2.7701799869537354 +[2025-04-27 15:26:47,544][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 1.2577311992645264, cross_entropy: 1.2577311992645264 +[2025-04-27 15:26:47,884][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 1.3236870765686035, cross_entropy: 1.3236870765686035 +[2025-04-27 15:26:50,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.6479997634887695, cross_entropy: 2.6479997634887695 +[2025-04-27 15:26:51,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 1.2569284439086914, cross_entropy: 1.2569284439086914 +[2025-04-27 15:26:53,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.870300769805908, cross_entropy: 2.870300769805908 +[2025-04-27 15:26:54,228][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 1.6316642761230469, cross_entropy: 1.6316642761230469 +[2025-04-27 15:26:57,161][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 2.915602684020996, cross_entropy: 2.915602684020996 +[2025-04-27 15:26:57,501][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 1.0632045269012451, cross_entropy: 1.0632045269012451 +[2025-04-27 15:27:00,144][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 1.208928108215332, cross_entropy: 1.208928108215332 +[2025-04-27 15:27:00,487][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.066433906555176, cross_entropy: 2.066433906555176 +[2025-04-27 15:27:03,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.9130029678344727, cross_entropy: 1.9130029678344727 +[2025-04-27 15:27:03,461][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.2069101333618164, cross_entropy: 2.2069101333618164 +[2025-04-27 15:27:05,895][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 0.718868613243103, cross_entropy: 0.718868613243103 +[2025-04-27 15:27:06,233][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 2.4615087509155273, cross_entropy: 2.4615087509155273 +[2025-04-27 15:27:08,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.9393181204795837, cross_entropy: 0.9393181204795837 +[2025-04-27 15:27:09,177][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 2.7063674926757812, cross_entropy: 2.7063674926757812 +[2025-04-27 15:27:11,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.6807167530059814, cross_entropy: 0.6807167530059814 +[2025-04-27 15:27:12,268][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 2.4965410232543945, cross_entropy: 2.4965410232543945 +[2025-04-27 15:27:15,745][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.1200389862060547, cross_entropy: 1.1200389862060547 +[2025-04-27 15:27:16,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.8795793056488037, cross_entropy: 2.8795793056488037 +[2025-04-27 15:27:19,924][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 2.936291217803955, cross_entropy: 2.936291217803955 +[2025-04-27 15:27:20,236][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 0.6030083298683167, cross_entropy: 0.6030083298683167 +[2025-04-27 15:27:23,412][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.073803186416626, cross_entropy: 1.073803186416626 +[2025-04-27 15:27:23,747][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.171360731124878, cross_entropy: 1.171360731124878 +[2025-04-27 15:27:26,616][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 2.0061330795288086, cross_entropy: 2.0061330795288086 +[2025-04-27 15:27:26,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 1.1506340503692627, cross_entropy: 1.1506340503692627 +[2025-04-27 15:27:29,937][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.379685640335083, cross_entropy: 2.379685640335083 +[2025-04-27 15:27:30,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 0.8991479277610779, cross_entropy: 0.8991479277610779 +[2025-04-27 15:27:33,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 0.9003028273582458, cross_entropy: 0.9003028273582458 +[2025-04-27 15:27:33,705][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 0.8656811714172363, cross_entropy: 0.8656811714172363 +[2025-04-27 15:27:36,272][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.0070399045944214, cross_entropy: 1.0070399045944214 +[2025-04-27 15:27:36,607][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.1779769659042358, cross_entropy: 1.1779769659042358 +[2025-04-27 15:27:40,303][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 0.9812833070755005, cross_entropy: 0.9812833070755005 +[2025-04-27 15:27:40,638][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.591893196105957, cross_entropy: 2.591893196105957 +[2025-04-27 15:27:43,844][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 0.8499930500984192, cross_entropy: 0.8499930500984192 +[2025-04-27 15:27:44,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.687532424926758, cross_entropy: 2.687532424926758 +[2025-04-27 15:27:47,271][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 0.81876540184021, cross_entropy: 0.81876540184021 +[2025-04-27 15:27:47,584][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 0.8293614387512207, cross_entropy: 0.8293614387512207 +[2025-04-27 15:27:50,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.4900414943695068, cross_entropy: 1.4900414943695068 +[2025-04-27 15:27:51,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.2363182306289673, cross_entropy: 1.2363182306289673 +[2025-04-27 15:27:53,967][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.5736441612243652, cross_entropy: 2.5736441612243652 +[2025-04-27 15:27:54,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.7561511993408203, cross_entropy: 2.7561511993408203 +[2025-04-27 15:27:58,142][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 2.758842945098877, cross_entropy: 2.758842945098877 +[2025-04-27 15:27:58,481][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 0.9725744724273682, cross_entropy: 0.9725744724273682 +[2025-04-27 15:28:01,214][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 0.9846910238265991, cross_entropy: 0.9846910238265991 +[2025-04-27 15:28:01,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 1.137812852859497, cross_entropy: 1.137812852859497 +[2025-04-27 15:28:04,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.0784434080123901, cross_entropy: 1.0784434080123901 +[2025-04-27 15:28:05,002][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 2.287703275680542, cross_entropy: 2.287703275680542 +[2025-04-27 15:28:08,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.3056713342666626, cross_entropy: 1.3056713342666626 +[2025-04-27 15:28:08,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.22835111618042, cross_entropy: 2.22835111618042 +[2025-04-27 15:28:11,311][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.3011269569396973, cross_entropy: 2.3011269569396973 +[2025-04-27 15:28:11,653][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 1.451899528503418, cross_entropy: 1.451899528503418 +[2025-04-27 15:28:14,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 2.4712073802948, cross_entropy: 2.4712073802948 +[2025-04-27 15:28:15,158][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 1.0480138063430786, cross_entropy: 1.0480138063430786 +[2025-04-27 15:28:18,258][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.582918167114258, cross_entropy: 2.582918167114258 +[2025-04-27 15:28:18,593][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 0.6333940625190735, cross_entropy: 0.6333940625190735 +[2025-04-27 15:28:21,617][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.7020509243011475, cross_entropy: 2.7020509243011475 +[2025-04-27 15:28:21,968][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 0.7825272083282471, cross_entropy: 0.7825272083282471 +[2025-04-27 15:28:24,762][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.1033875942230225, cross_entropy: 1.1033875942230225 +[2025-04-27 15:28:25,709][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.9914730787277222, cross_entropy: 1.9914730787277222 +[2025-04-27 15:28:27,994][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.7235493659973145, cross_entropy: 2.7235493659973145 +[2025-04-27 15:28:28,779][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.4996678829193115, cross_entropy: 1.4996678829193115 +[2025-04-27 15:28:31,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 2.583591938018799, cross_entropy: 2.583591938018799 +[2025-04-27 15:28:32,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 0.7153279185295105, cross_entropy: 0.7153279185295105 +[2025-04-27 15:28:34,427][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 0.8622187376022339, cross_entropy: 0.8622187376022339 +[2025-04-27 15:28:35,047][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 0.9231463074684143, cross_entropy: 0.9231463074684143 +[2025-04-27 15:28:37,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 0.8273812532424927, cross_entropy: 0.8273812532424927 +[2025-04-27 15:28:38,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.4892289638519287, cross_entropy: 1.4892289638519287 +[2025-04-27 15:28:40,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 2.1026031970977783, cross_entropy: 2.1026031970977783 +[2025-04-27 15:28:41,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 2.848876953125, cross_entropy: 2.848876953125 +[2025-04-27 15:28:43,900][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 0.9210606217384338, cross_entropy: 0.9210606217384338 +[2025-04-27 15:28:45,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.6861224174499512, cross_entropy: 1.6861224174499512 +[2025-04-27 15:28:47,336][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 0.9887908697128296, cross_entropy: 0.9887908697128296 +[2025-04-27 15:28:48,610][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.6795613765716553, cross_entropy: 1.6795613765716553 +[2025-04-27 15:28:50,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.307429313659668, cross_entropy: 1.307429313659668 +[2025-04-27 15:28:51,915][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 2.5775556564331055, cross_entropy: 2.5775556564331055 +[2025-04-27 15:28:53,945][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 2.908792495727539, cross_entropy: 2.908792495727539 +[2025-04-27 15:28:55,242][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.9839973449707031, cross_entropy: 1.9839973449707031 +[2025-04-27 15:28:56,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.4541118144989014, cross_entropy: 1.4541118144989014 +[2025-04-27 15:28:58,263][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 1.2734698057174683, cross_entropy: 1.2734698057174683 +[2025-04-27 15:28:59,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 2.937957525253296, cross_entropy: 2.937957525253296 +[2025-04-27 15:29:02,386][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.3238908052444458, cross_entropy: 1.3238908052444458 +[2025-04-27 15:29:02,753][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.255040168762207, cross_entropy: 2.255040168762207 +[2025-04-27 15:29:06,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 0.8871703147888184, cross_entropy: 0.8871703147888184 +[2025-04-27 15:29:06,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 1.8813366889953613, cross_entropy: 1.8813366889953613 +[2025-04-27 15:29:09,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 2.4741463661193848, cross_entropy: 2.4741463661193848 +[2025-04-27 15:29:10,309][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.1152241230010986, cross_entropy: 2.1152241230010986 +[2025-04-27 15:29:13,303][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.7421079874038696, cross_entropy: 0.7421079874038696 +[2025-04-27 15:29:13,638][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 0.6405102014541626, cross_entropy: 0.6405102014541626 +[2025-04-27 15:29:16,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 2.895430088043213, cross_entropy: 2.895430088043213 +[2025-04-27 15:29:16,544][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 2.905629873275757, cross_entropy: 2.905629873275757 +[2025-04-27 15:29:19,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 0.7373753190040588, cross_entropy: 0.7373753190040588 +[2025-04-27 15:29:20,327][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 0.8981354236602783, cross_entropy: 0.8981354236602783 +[2025-04-27 15:29:23,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 2.4127564430236816, cross_entropy: 2.4127564430236816 +[2025-04-27 15:29:23,585][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 1.3656306266784668, cross_entropy: 1.3656306266784668 +[2025-04-27 15:29:26,063][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 2.9186930656433105, cross_entropy: 2.9186930656433105 +[2025-04-27 15:29:26,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.0651131868362427, cross_entropy: 1.0651131868362427 +[2025-04-27 15:29:29,319][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.4828717708587646, cross_entropy: 2.4828717708587646 +[2025-04-27 15:29:29,653][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 0.9399915933609009, cross_entropy: 0.9399915933609009 +[2025-04-27 15:29:33,139][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 0.9279053807258606, cross_entropy: 0.9279053807258606 +[2025-04-27 15:29:33,477][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.657155990600586, cross_entropy: 2.657155990600586 +[2025-04-27 15:29:37,225][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 1.7623940706253052, cross_entropy: 1.7623940706253052 +[2025-04-27 15:29:37,565][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 2.707986354827881, cross_entropy: 2.707986354827881 +[2025-04-27 15:29:40,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 0.8711869716644287, cross_entropy: 0.8711869716644287 +[2025-04-27 15:29:40,710][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.480757713317871, cross_entropy: 2.480757713317871 +[2025-04-27 15:29:43,435][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 2.582871913909912, cross_entropy: 2.582871913909912 +[2025-04-27 15:29:43,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 2.759298086166382, cross_entropy: 2.759298086166382 +[2025-04-27 15:29:46,331][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.100308895111084, cross_entropy: 2.100308895111084 +[2025-04-27 15:29:46,667][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 0.8833735585212708, cross_entropy: 0.8833735585212708 +[2025-04-27 15:29:49,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.5665080547332764, cross_entropy: 1.5665080547332764 +[2025-04-27 15:29:49,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.8900785446166992, cross_entropy: 1.8900785446166992 +[2025-04-27 15:29:53,339][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.819955587387085, cross_entropy: 1.819955587387085 +[2025-04-27 15:29:53,679][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 2.460808277130127, cross_entropy: 2.460808277130127 +[2025-04-27 15:29:56,590][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 2.3702805042266846, cross_entropy: 2.3702805042266846 +[2025-04-27 15:29:56,925][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 0.734291672706604, cross_entropy: 0.734291672706604 +[2025-04-27 15:30:00,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.6898216009140015, cross_entropy: 1.6898216009140015 +[2025-04-27 15:30:00,359][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 0.9820438623428345, cross_entropy: 0.9820438623428345 +[2025-04-27 15:30:02,953][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.653564453125, cross_entropy: 2.653564453125 +[2025-04-27 15:30:03,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.181504249572754, cross_entropy: 1.181504249572754 +[2025-04-27 15:30:06,266][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.909553050994873, cross_entropy: 2.909553050994873 +[2025-04-27 15:30:06,667][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 1.03983473777771, cross_entropy: 1.03983473777771 +[2025-04-27 15:30:09,984][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 0.9617933034896851, cross_entropy: 0.9617933034896851 +[2025-04-27 15:30:10,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 0.9461942315101624, cross_entropy: 0.9461942315101624 +[2025-04-27 15:30:14,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 2.3967478275299072, cross_entropy: 2.3967478275299072 +[2025-04-27 15:30:14,433][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 3.0948643684387207, cross_entropy: 3.0948643684387207 +[2025-04-27 15:30:17,457][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.5144150257110596, cross_entropy: 1.5144150257110596 +[2025-04-27 15:30:17,784][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 1.9178998470306396, cross_entropy: 1.9178998470306396 +[2025-04-27 15:30:20,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.0355653762817383, cross_entropy: 2.0355653762817383 +[2025-04-27 15:30:21,286][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.436461329460144, cross_entropy: 1.436461329460144 +[2025-04-27 15:30:24,579][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 1.7479020357131958, cross_entropy: 1.7479020357131958 +[2025-04-27 15:30:24,914][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 2.861968517303467, cross_entropy: 2.861968517303467 +[2025-04-27 15:30:27,885][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.790172576904297, cross_entropy: 2.790172576904297 +[2025-04-27 15:30:28,197][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.534201145172119, cross_entropy: 2.534201145172119 +[2025-04-27 15:30:31,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 1.8952560424804688, cross_entropy: 1.8952560424804688 +[2025-04-27 15:30:32,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 0.8493272066116333, cross_entropy: 0.8493272066116333 +[2025-04-27 15:30:34,861][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.286111831665039, cross_entropy: 2.286111831665039 +[2025-04-27 15:30:35,174][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 0.8119380474090576, cross_entropy: 0.8119380474090576 +[2025-04-27 15:30:37,539][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.0760746002197266, cross_entropy: 2.0760746002197266 +[2025-04-27 15:33:20,310][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.760999321937561, cross_entropy: 1.760999321937561 +[2025-04-27 15:33:20,311][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.2496620416641235, cross_entropy: 1.2496620416641235 +[2025-04-27 15:33:20,475][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch9.pth. +[2025-04-27 15:33:20,698][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 15:33:24,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 0.9361963272094727, cross_entropy: 0.9361963272094727 +[2025-04-27 15:33:25,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.5852696895599365, cross_entropy: 1.5852696895599365 +[2025-04-27 15:33:27,550][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.692527174949646, cross_entropy: 0.692527174949646 +[2025-04-27 15:33:29,533][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 2.716251850128174, cross_entropy: 2.716251850128174 +[2025-04-27 15:33:30,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.539827346801758, cross_entropy: 2.539827346801758 +[2025-04-27 15:33:33,040][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.7966554164886475, cross_entropy: 1.7966554164886475 +[2025-04-27 15:33:34,164][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.698101043701172, cross_entropy: 2.698101043701172 +[2025-04-27 15:33:36,786][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.9748227596282959, cross_entropy: 0.9748227596282959 +[2025-04-27 15:33:37,694][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.440178394317627, cross_entropy: 2.440178394317627 +[2025-04-27 15:33:40,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.0929502248764038, cross_entropy: 1.0929502248764038 +[2025-04-27 15:33:40,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.2825629711151123, cross_entropy: 2.2825629711151123 +[2025-04-27 15:33:44,156][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 2.106210470199585, cross_entropy: 2.106210470199585 +[2025-04-27 15:33:44,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.1776642799377441, cross_entropy: 1.1776642799377441 +[2025-04-27 15:33:47,214][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.8707947731018066, cross_entropy: 1.8707947731018066 +[2025-04-27 15:33:47,615][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.6805076599121094, cross_entropy: 2.6805076599121094 +[2025-04-27 15:33:49,966][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 0.8186822533607483, cross_entropy: 0.8186822533607483 +[2025-04-27 15:33:51,286][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 0.7236226797103882, cross_entropy: 0.7236226797103882 +[2025-04-27 15:33:53,134][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.1080129146575928, cross_entropy: 2.1080129146575928 +[2025-04-27 15:33:55,051][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 1.3078231811523438, cross_entropy: 1.3078231811523438 +[2025-04-27 15:33:56,722][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 0.6314938068389893, cross_entropy: 0.6314938068389893 +[2025-04-27 15:33:58,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 1.41364324092865, cross_entropy: 1.41364324092865 +[2025-04-27 15:33:59,866][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 3.0656402111053467, cross_entropy: 3.0656402111053467 +[2025-04-27 15:34:02,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.5331867337226868, cross_entropy: 0.5331867337226868 +[2025-04-27 15:34:03,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 0.941074550151825, cross_entropy: 0.941074550151825 +[2025-04-27 15:34:05,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.142477035522461, cross_entropy: 2.142477035522461 +[2025-04-27 15:34:06,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 2.6449246406555176, cross_entropy: 2.6449246406555176 +[2025-04-27 15:34:10,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 0.8865148425102234, cross_entropy: 0.8865148425102234 +[2025-04-27 15:34:10,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 1.9704461097717285, cross_entropy: 1.9704461097717285 +[2025-04-27 15:34:13,803][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.790088415145874, cross_entropy: 2.790088415145874 +[2025-04-27 15:34:14,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.5272303819656372, cross_entropy: 1.5272303819656372 +[2025-04-27 15:34:17,249][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.4178695678710938, cross_entropy: 2.4178695678710938 +[2025-04-27 15:34:17,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 0.8047798275947571, cross_entropy: 0.8047798275947571 +[2025-04-27 15:34:20,340][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 0.969488799571991, cross_entropy: 0.969488799571991 +[2025-04-27 15:34:20,657][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.042879343032837, cross_entropy: 2.042879343032837 +[2025-04-27 15:34:24,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.4006099700927734, cross_entropy: 1.4006099700927734 +[2025-04-27 15:34:24,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.4917898178100586, cross_entropy: 1.4917898178100586 +[2025-04-27 15:34:27,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.240323066711426, cross_entropy: 2.240323066711426 +[2025-04-27 15:34:28,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 0.938381552696228, cross_entropy: 0.938381552696228 +[2025-04-27 15:34:31,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 2.3692405223846436, cross_entropy: 2.3692405223846436 +[2025-04-27 15:34:31,752][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 1.004654884338379, cross_entropy: 1.004654884338379 +[2025-04-27 15:34:34,800][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 1.818475365638733, cross_entropy: 1.818475365638733 +[2025-04-27 15:34:35,138][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.210813045501709, cross_entropy: 2.210813045501709 +[2025-04-27 15:34:38,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 0.7490617036819458, cross_entropy: 0.7490617036819458 +[2025-04-27 15:34:38,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.653197765350342, cross_entropy: 2.653197765350342 +[2025-04-27 15:34:42,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.0113508701324463, cross_entropy: 1.0113508701324463 +[2025-04-27 15:34:43,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 2.8513565063476562, cross_entropy: 2.8513565063476562 +[2025-04-27 15:34:46,886][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.9420746564865112, cross_entropy: 1.9420746564865112 +[2025-04-27 15:34:47,223][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 2.5244879722595215, cross_entropy: 2.5244879722595215 +[2025-04-27 15:34:49,967][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.2928622961044312, cross_entropy: 1.2928622961044312 +[2025-04-27 15:34:50,280][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 2.778020143508911, cross_entropy: 2.778020143508911 +[2025-04-27 15:34:53,288][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 1.9954538345336914, cross_entropy: 1.9954538345336914 +[2025-04-27 15:34:53,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 1.7696102857589722, cross_entropy: 1.7696102857589722 +[2025-04-27 15:34:56,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.3012290000915527, cross_entropy: 1.3012290000915527 +[2025-04-27 15:34:57,075][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 0.7284917831420898, cross_entropy: 0.7284917831420898 +[2025-04-27 15:35:00,525][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 0.7652506232261658, cross_entropy: 0.7652506232261658 +[2025-04-27 15:35:00,860][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 2.6714937686920166, cross_entropy: 2.6714937686920166 +[2025-04-27 15:35:04,569][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.032700777053833, cross_entropy: 1.032700777053833 +[2025-04-27 15:35:04,883][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.9232003688812256, cross_entropy: 0.9232003688812256 +[2025-04-27 15:35:08,344][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.9862985610961914, cross_entropy: 1.9862985610961914 +[2025-04-27 15:35:08,676][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 0.9225649237632751, cross_entropy: 0.9225649237632751 +[2025-04-27 15:35:12,274][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 2.25712251663208, cross_entropy: 2.25712251663208 +[2025-04-27 15:35:12,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.905558705329895, cross_entropy: 1.905558705329895 +[2025-04-27 15:35:16,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 2.404668092727661, cross_entropy: 2.404668092727661 +[2025-04-27 15:35:17,019][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 0.6843078136444092, cross_entropy: 0.6843078136444092 +[2025-04-27 15:35:20,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 1.8301055431365967, cross_entropy: 1.8301055431365967 +[2025-04-27 15:35:20,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 1.8108844757080078, cross_entropy: 1.8108844757080078 +[2025-04-27 15:35:24,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 2.6768958568573, cross_entropy: 2.6768958568573 +[2025-04-27 15:35:24,361][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 1.9125077724456787, cross_entropy: 1.9125077724456787 +[2025-04-27 15:35:28,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 0.6083256602287292, cross_entropy: 0.6083256602287292 +[2025-04-27 15:35:28,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 3.029360294342041, cross_entropy: 3.029360294342041 +[2025-04-27 15:35:32,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 0.788644552230835, cross_entropy: 0.788644552230835 +[2025-04-27 15:35:32,745][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 0.8991310000419617, cross_entropy: 0.8991310000419617 +[2025-04-27 15:35:35,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 0.7438396215438843, cross_entropy: 0.7438396215438843 +[2025-04-27 15:35:36,066][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 0.6256945133209229, cross_entropy: 0.6256945133209229 +[2025-04-27 15:35:39,208][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 0.7812197208404541, cross_entropy: 0.7812197208404541 +[2025-04-27 15:35:39,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.1872771978378296, cross_entropy: 1.1872771978378296 +[2025-04-27 15:35:43,837][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 0.8829478025436401, cross_entropy: 0.8829478025436401 +[2025-04-27 15:35:44,176][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.4623794555664062, cross_entropy: 1.4623794555664062 +[2025-04-27 15:35:47,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 0.8097162246704102, cross_entropy: 0.8097162246704102 +[2025-04-27 15:35:48,102][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.7252316474914551, cross_entropy: 0.7252316474914551 +[2025-04-27 15:35:51,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.6560686826705933, cross_entropy: 1.6560686826705933 +[2025-04-27 15:35:51,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 0.5037136077880859, cross_entropy: 0.5037136077880859 +[2025-04-27 15:35:55,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 2.929995536804199, cross_entropy: 2.929995536804199 +[2025-04-27 15:35:55,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.538005828857422, cross_entropy: 2.538005828857422 +[2025-04-27 15:35:58,700][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 0.9923995733261108, cross_entropy: 0.9923995733261108 +[2025-04-27 15:35:59,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 0.9929397106170654, cross_entropy: 0.9929397106170654 +[2025-04-27 15:36:02,433][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 2.6521780490875244, cross_entropy: 2.6521780490875244 +[2025-04-27 15:36:02,767][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 0.5060240626335144, cross_entropy: 0.5060240626335144 +[2025-04-27 15:36:05,907][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.793123245239258, cross_entropy: 2.793123245239258 +[2025-04-27 15:36:06,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.7365961074829102, cross_entropy: 1.7365961074829102 +[2025-04-27 15:36:09,060][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.220663070678711, cross_entropy: 1.220663070678711 +[2025-04-27 15:36:09,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 2.3548481464385986, cross_entropy: 2.3548481464385986 +[2025-04-27 15:36:12,514][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 1.792664885520935, cross_entropy: 1.792664885520935 +[2025-04-27 15:36:12,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 2.376331329345703, cross_entropy: 2.376331329345703 +[2025-04-27 15:36:15,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 0.6412999629974365, cross_entropy: 0.6412999629974365 +[2025-04-27 15:36:16,159][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.9913713932037354, cross_entropy: 1.9913713932037354 +[2025-04-27 15:36:18,666][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 2.77772855758667, cross_entropy: 2.77772855758667 +[2025-04-27 15:36:19,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 0.8501102328300476, cross_entropy: 0.8501102328300476 +[2025-04-27 15:36:21,413][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.4900553226470947, cross_entropy: 1.4900553226470947 +[2025-04-27 15:36:21,770][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 2.074587106704712, cross_entropy: 2.074587106704712 +[2025-04-27 15:36:24,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 0.7854493856430054, cross_entropy: 0.7854493856430054 +[2025-04-27 15:36:25,010][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.4314203262329102, cross_entropy: 1.4314203262329102 +[2025-04-27 15:36:28,020][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 1.392944574356079, cross_entropy: 1.392944574356079 +[2025-04-27 15:36:28,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.0625412464141846, cross_entropy: 2.0625412464141846 +[2025-04-27 15:36:31,639][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 2.716416358947754, cross_entropy: 2.716416358947754 +[2025-04-27 15:36:31,982][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.2805957794189453, cross_entropy: 2.2805957794189453 +[2025-04-27 15:36:35,103][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.3294909000396729, cross_entropy: 1.3294909000396729 +[2025-04-27 15:36:35,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.8709009885787964, cross_entropy: 0.8709009885787964 +[2025-04-27 15:36:38,070][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.5485479831695557, cross_entropy: 2.5485479831695557 +[2025-04-27 15:36:38,405][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.6897616386413574, cross_entropy: 2.6897616386413574 +[2025-04-27 15:36:41,290][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 2.7647252082824707, cross_entropy: 2.7647252082824707 +[2025-04-27 15:36:41,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.1062241792678833, cross_entropy: 1.1062241792678833 +[2025-04-27 15:36:44,714][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 0.5774828791618347, cross_entropy: 0.5774828791618347 +[2025-04-27 15:36:45,069][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 2.8574931621551514, cross_entropy: 2.8574931621551514 +[2025-04-27 15:36:48,027][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.1074578762054443, cross_entropy: 2.1074578762054443 +[2025-04-27 15:36:48,410][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.6930906772613525, cross_entropy: 2.6930906772613525 +[2025-04-27 15:36:51,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.3337016105651855, cross_entropy: 1.3337016105651855 +[2025-04-27 15:36:52,455][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 0.56294184923172, cross_entropy: 0.56294184923172 +[2025-04-27 15:36:54,739][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 0.8166821599006653, cross_entropy: 0.8166821599006653 +[2025-04-27 15:36:55,482][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.2075488567352295, cross_entropy: 2.2075488567352295 +[2025-04-27 15:36:57,933][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 1.405259370803833, cross_entropy: 1.405259370803833 +[2025-04-27 15:36:58,807][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.9623992443084717, cross_entropy: 1.9623992443084717 +[2025-04-27 15:37:01,163][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 0.9795113801956177, cross_entropy: 0.9795113801956177 +[2025-04-27 15:37:02,214][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.5029361248016357, cross_entropy: 2.5029361248016357 +[2025-04-27 15:37:04,330][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 1.888046145439148, cross_entropy: 1.888046145439148 +[2025-04-27 15:37:05,883][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 0.7340874671936035, cross_entropy: 0.7340874671936035 +[2025-04-27 15:37:07,906][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 2.5229711532592773, cross_entropy: 2.5229711532592773 +[2025-04-27 15:37:09,194][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 2.849175214767456, cross_entropy: 2.849175214767456 +[2025-04-27 15:37:11,140][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 2.6345672607421875, cross_entropy: 2.6345672607421875 +[2025-04-27 15:37:12,652][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 1.0288176536560059, cross_entropy: 1.0288176536560059 +[2025-04-27 15:37:14,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 1.8606065511703491, cross_entropy: 1.8606065511703491 +[2025-04-27 15:37:15,954][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 2.2275376319885254, cross_entropy: 2.2275376319885254 +[2025-04-27 15:37:18,180][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.909325361251831, cross_entropy: 1.909325361251831 +[2025-04-27 15:37:19,865][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 1.9562153816223145, cross_entropy: 1.9562153816223145 +[2025-04-27 15:37:21,980][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 0.7085579037666321, cross_entropy: 0.7085579037666321 +[2025-04-27 15:37:23,210][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.4313113689422607, cross_entropy: 1.4313113689422607 +[2025-04-27 15:37:25,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 2.7621092796325684, cross_entropy: 2.7621092796325684 +[2025-04-27 15:37:26,397][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 1.3913606405258179, cross_entropy: 1.3913606405258179 +[2025-04-27 15:37:28,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.5902962684631348, cross_entropy: 2.5902962684631348 +[2025-04-27 15:37:30,048][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.5951223373413086, cross_entropy: 1.5951223373413086 +[2025-04-27 15:37:33,396][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.242502450942993, cross_entropy: 2.242502450942993 +[2025-04-27 15:37:34,775][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.25224232673645, cross_entropy: 2.25224232673645 +[2025-04-27 15:37:36,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.7816643714904785, cross_entropy: 2.7816643714904785 +[2025-04-27 15:37:38,218][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.526798725128174, cross_entropy: 2.526798725128174 +[2025-04-27 15:37:39,463][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.3889589309692383, cross_entropy: 2.3889589309692383 +[2025-04-27 15:37:41,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 0.8109411597251892, cross_entropy: 0.8109411597251892 +[2025-04-27 15:37:42,613][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 0.7713766098022461, cross_entropy: 0.7713766098022461 +[2025-04-27 15:37:45,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 2.471146583557129, cross_entropy: 2.471146583557129 +[2025-04-27 15:37:45,995][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.1865427494049072, cross_entropy: 1.1865427494049072 +[2025-04-27 15:37:48,807][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.2995963096618652, cross_entropy: 2.2995963096618652 +[2025-04-27 15:37:49,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.2004313468933105, cross_entropy: 2.2004313468933105 +[2025-04-27 15:37:52,253][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.472188949584961, cross_entropy: 2.472188949584961 +[2025-04-27 15:37:52,970][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 0.8023250102996826, cross_entropy: 0.8023250102996826 +[2025-04-27 15:37:55,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.7888383865356445, cross_entropy: 2.7888383865356445 +[2025-04-27 15:37:56,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 1.024693489074707, cross_entropy: 1.024693489074707 +[2025-04-27 15:37:58,488][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 2.829763412475586, cross_entropy: 2.829763412475586 +[2025-04-27 15:38:00,072][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.1118524074554443, cross_entropy: 1.1118524074554443 +[2025-04-27 15:38:01,460][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.620786190032959, cross_entropy: 2.620786190032959 +[2025-04-27 15:38:03,501][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.0760364532470703, cross_entropy: 1.0760364532470703 +[2025-04-27 15:38:04,874][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.435852527618408, cross_entropy: 2.435852527618408 +[2025-04-27 15:38:06,572][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 0.9242736101150513, cross_entropy: 0.9242736101150513 +[2025-04-27 15:38:08,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 2.7820849418640137, cross_entropy: 2.7820849418640137 +[2025-04-27 15:38:09,258][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 2.7050375938415527, cross_entropy: 2.7050375938415527 +[2025-04-27 15:38:11,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.4152326583862305, cross_entropy: 2.4152326583862305 +[2025-04-27 15:38:13,023][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 0.6544264554977417, cross_entropy: 0.6544264554977417 +[2025-04-27 15:38:15,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.7127513885498047, cross_entropy: 2.7127513885498047 +[2025-04-27 15:38:16,055][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.732609510421753, cross_entropy: 2.732609510421753 +[2025-04-27 15:38:18,994][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.8632070422172546, cross_entropy: 0.8632070422172546 +[2025-04-27 15:38:19,469][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.4514241218566895, cross_entropy: 2.4514241218566895 +[2025-04-27 15:38:23,885][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.672381639480591, cross_entropy: 2.672381639480591 +[2025-04-27 15:38:24,226][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 2.735941171646118, cross_entropy: 2.735941171646118 +[2025-04-27 15:38:27,063][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.5446687936782837, cross_entropy: 0.5446687936782837 +[2025-04-27 15:38:27,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 1.437704086303711, cross_entropy: 1.437704086303711 +[2025-04-27 15:38:30,351][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.9351822733879089, cross_entropy: 0.9351822733879089 +[2025-04-27 15:38:30,687][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.068303108215332, cross_entropy: 1.068303108215332 +[2025-04-27 15:38:33,981][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 2.444929599761963, cross_entropy: 2.444929599761963 +[2025-04-27 15:38:34,304][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 2.745875120162964, cross_entropy: 2.745875120162964 +[2025-04-27 15:38:37,367][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 2.5255022048950195, cross_entropy: 2.5255022048950195 +[2025-04-27 15:38:37,682][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 0.792289137840271, cross_entropy: 0.792289137840271 +[2025-04-27 15:38:41,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 2.3642683029174805, cross_entropy: 2.3642683029174805 +[2025-04-27 15:38:41,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 0.5177606344223022, cross_entropy: 0.5177606344223022 +[2025-04-27 15:38:44,419][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.6254339814186096, cross_entropy: 0.6254339814186096 +[2025-04-27 15:38:44,755][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.10625422000885, cross_entropy: 1.10625422000885 +[2025-04-27 15:38:47,588][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.8788766860961914, cross_entropy: 2.8788766860961914 +[2025-04-27 15:38:47,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 0.5916950106620789, cross_entropy: 0.5916950106620789 +[2025-04-27 15:38:50,857][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.9327656030654907, cross_entropy: 1.9327656030654907 +[2025-04-27 15:38:51,193][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.1431384086608887, cross_entropy: 2.1431384086608887 +[2025-04-27 15:38:55,248][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 1.122582197189331, cross_entropy: 1.122582197189331 +[2025-04-27 15:38:55,594][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 2.245760679244995, cross_entropy: 2.245760679244995 +[2025-04-27 15:38:58,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 0.5608994960784912, cross_entropy: 0.5608994960784912 +[2025-04-27 15:38:59,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 2.7567834854125977, cross_entropy: 2.7567834854125977 +[2025-04-27 15:39:02,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 2.2880380153656006, cross_entropy: 2.2880380153656006 +[2025-04-27 15:39:02,901][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.6502059698104858, cross_entropy: 1.6502059698104858 +[2025-04-27 15:39:05,870][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 1.526139497756958, cross_entropy: 1.526139497756958 +[2025-04-27 15:39:06,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.875865936279297, cross_entropy: 2.875865936279297 +[2025-04-27 15:39:09,045][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.692934036254883, cross_entropy: 2.692934036254883 +[2025-04-27 15:39:09,358][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 0.5526087284088135, cross_entropy: 0.5526087284088135 +[2025-04-27 15:39:12,244][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.42319917678833, cross_entropy: 1.42319917678833 +[2025-04-27 15:39:12,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 2.8465123176574707, cross_entropy: 2.8465123176574707 +[2025-04-27 15:39:16,043][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 1.737302541732788, cross_entropy: 1.737302541732788 +[2025-04-27 15:39:16,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 3.0868263244628906, cross_entropy: 3.0868263244628906 +[2025-04-27 15:39:19,127][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 0.7803226113319397, cross_entropy: 0.7803226113319397 +[2025-04-27 15:39:19,467][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.805798053741455, cross_entropy: 1.805798053741455 +[2025-04-27 15:39:22,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.4554848670959473, cross_entropy: 2.4554848670959473 +[2025-04-27 15:39:22,735][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 0.7425898909568787, cross_entropy: 0.7425898909568787 +[2025-04-27 15:39:26,048][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 0.696446418762207, cross_entropy: 0.696446418762207 +[2025-04-27 15:39:26,386][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 2.637836456298828, cross_entropy: 2.637836456298828 +[2025-04-27 15:39:29,345][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 2.387566089630127, cross_entropy: 2.387566089630127 +[2025-04-27 15:39:29,679][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 1.6340783834457397, cross_entropy: 1.6340783834457397 +[2025-04-27 15:39:32,788][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.7498626708984375, cross_entropy: 1.7498626708984375 +[2025-04-27 15:39:33,126][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 0.6733118295669556, cross_entropy: 0.6733118295669556 +[2025-04-27 15:39:35,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.4832956790924072, cross_entropy: 2.4832956790924072 +[2025-04-27 15:39:36,115][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 2.5017242431640625, cross_entropy: 2.5017242431640625 +[2025-04-27 15:39:39,376][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.5715513229370117, cross_entropy: 2.5715513229370117 +[2025-04-27 15:39:39,720][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 2.5388669967651367, cross_entropy: 2.5388669967651367 +[2025-04-27 15:39:43,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 1.9064452648162842, cross_entropy: 1.9064452648162842 +[2025-04-27 15:39:43,467][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 2.69919753074646, cross_entropy: 2.69919753074646 +[2025-04-27 15:39:46,466][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 2.634422540664673, cross_entropy: 2.634422540664673 +[2025-04-27 15:39:46,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.45174241065979, cross_entropy: 2.45174241065979 +[2025-04-27 15:39:49,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.3281068801879883, cross_entropy: 2.3281068801879883 +[2025-04-27 15:39:50,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 0.9688076376914978, cross_entropy: 0.9688076376914978 +[2025-04-27 15:39:52,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.2122597694396973, cross_entropy: 1.2122597694396973 +[2025-04-27 15:39:53,093][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.4063584804534912, cross_entropy: 1.4063584804534912 +[2025-04-27 15:39:56,263][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.2260844707489014, cross_entropy: 1.2260844707489014 +[2025-04-27 15:39:56,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 2.5999577045440674, cross_entropy: 2.5999577045440674 +[2025-04-27 15:40:00,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.6038942337036133, cross_entropy: 2.6038942337036133 +[2025-04-27 15:40:00,663][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 2.3435051441192627, cross_entropy: 2.3435051441192627 +[2025-04-27 15:40:03,928][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 2.9988605976104736, cross_entropy: 2.9988605976104736 +[2025-04-27 15:40:04,242][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 1.018065094947815, cross_entropy: 1.018065094947815 +[2025-04-27 15:40:07,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.8543387651443481, cross_entropy: 1.8543387651443481 +[2025-04-27 15:40:07,753][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.7538384199142456, cross_entropy: 1.7538384199142456 +[2025-04-27 15:40:10,773][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 1.38381028175354, cross_entropy: 1.38381028175354 +[2025-04-27 15:40:11,110][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.2083619832992554, cross_entropy: 1.2083619832992554 +[2025-04-27 15:40:14,043][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 2.5230178833007812, cross_entropy: 2.5230178833007812 +[2025-04-27 15:40:14,357][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 2.7786831855773926, cross_entropy: 2.7786831855773926 +[2025-04-27 15:40:17,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 1.665969967842102, cross_entropy: 1.665969967842102 +[2025-04-27 15:40:17,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 2.7397379875183105, cross_entropy: 2.7397379875183105 +[2025-04-27 15:40:20,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.8665202856063843, cross_entropy: 1.8665202856063843 +[2025-04-27 15:40:21,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 2.7370519638061523, cross_entropy: 2.7370519638061523 +[2025-04-27 15:40:24,046][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.0649621486663818, cross_entropy: 1.0649621486663818 +[2025-04-27 15:40:24,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 2.0873687267303467, cross_entropy: 2.0873687267303467 +[2025-04-27 15:40:27,221][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.940788984298706, cross_entropy: 2.940788984298706 +[2025-04-27 15:40:27,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.791653871536255, cross_entropy: 2.791653871536255 +[2025-04-27 15:40:31,135][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.5845353603363037, cross_entropy: 0.5845353603363037 +[2025-04-27 15:40:31,477][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.7606258392333984, cross_entropy: 2.7606258392333984 +[2025-04-27 15:40:34,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 0.6120200753211975, cross_entropy: 0.6120200753211975 +[2025-04-27 15:40:34,891][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 1.661539077758789, cross_entropy: 1.661539077758789 +[2025-04-27 15:40:38,037][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 0.915346086025238, cross_entropy: 0.915346086025238 +[2025-04-27 15:40:38,377][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 2.0594091415405273, cross_entropy: 2.0594091415405273 +[2025-04-27 15:40:41,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 1.0516934394836426, cross_entropy: 1.0516934394836426 +[2025-04-27 15:40:41,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.5100181102752686, cross_entropy: 1.5100181102752686 +[2025-04-27 15:40:44,358][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.4540154933929443, cross_entropy: 2.4540154933929443 +[2025-04-27 15:40:44,671][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 2.10194730758667, cross_entropy: 2.10194730758667 +[2025-04-27 15:40:47,743][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 1.5934102535247803, cross_entropy: 1.5934102535247803 +[2025-04-27 15:40:48,215][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.2070643901824951, cross_entropy: 1.2070643901824951 +[2025-04-27 15:40:51,474][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 0.560280442237854, cross_entropy: 0.560280442237854 +[2025-04-27 15:40:51,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 0.6068097949028015, cross_entropy: 0.6068097949028015 +[2025-04-27 15:40:55,184][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 1.0140111446380615, cross_entropy: 1.0140111446380615 +[2025-04-27 15:40:55,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 1.5847458839416504, cross_entropy: 1.5847458839416504 +[2025-04-27 15:40:58,460][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.807571291923523, cross_entropy: 1.807571291923523 +[2025-04-27 15:40:59,012][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 2.8897390365600586, cross_entropy: 2.8897390365600586 +[2025-04-27 15:41:02,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 1.5060880184173584, cross_entropy: 1.5060880184173584 +[2025-04-27 15:41:02,807][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.355246067047119, cross_entropy: 2.355246067047119 +[2025-04-27 15:41:06,632][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.4836535453796387, cross_entropy: 2.4836535453796387 +[2025-04-27 15:41:06,970][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.0628905296325684, cross_entropy: 2.0628905296325684 +[2025-04-27 15:41:10,089][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.7945123910903931, cross_entropy: 0.7945123910903931 +[2025-04-27 15:41:10,439][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 1.0680142641067505, cross_entropy: 1.0680142641067505 +[2025-04-27 15:41:13,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.9327576160430908, cross_entropy: 1.9327576160430908 +[2025-04-27 15:41:13,487][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.9036612510681152, cross_entropy: 2.9036612510681152 +[2025-04-27 15:41:16,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.9193856120109558, cross_entropy: 0.9193856120109558 +[2025-04-27 15:41:16,622][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.777099132537842, cross_entropy: 2.777099132537842 +[2025-04-27 15:41:19,496][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 2.411261558532715, cross_entropy: 2.411261558532715 +[2025-04-27 15:41:20,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.9066118001937866, cross_entropy: 0.9066118001937866 +[2025-04-27 15:41:22,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 1.7295103073120117, cross_entropy: 1.7295103073120117 +[2025-04-27 15:41:23,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.815316677093506, cross_entropy: 2.815316677093506 +[2025-04-27 15:41:25,571][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 1.032909870147705, cross_entropy: 1.032909870147705 +[2025-04-27 15:41:26,947][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 1.924457311630249, cross_entropy: 1.924457311630249 +[2025-04-27 15:41:28,431][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.8351621627807617, cross_entropy: 2.8351621627807617 +[2025-04-27 15:41:30,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 1.0347200632095337, cross_entropy: 1.0347200632095337 +[2025-04-27 15:41:31,434][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 0.7538319230079651, cross_entropy: 0.7538319230079651 +[2025-04-27 15:41:33,249][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 0.9638163447380066, cross_entropy: 0.9638163447380066 +[2025-04-27 15:41:34,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.6529632210731506, cross_entropy: 0.6529632210731506 +[2025-04-27 15:41:37,190][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 0.6430716514587402, cross_entropy: 0.6430716514587402 +[2025-04-27 15:41:38,190][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 2.072444438934326, cross_entropy: 2.072444438934326 +[2025-04-27 15:41:40,510][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.848989963531494, cross_entropy: 2.848989963531494 +[2025-04-27 15:41:42,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 2.3327856063842773, cross_entropy: 2.3327856063842773 +[2025-04-27 15:41:44,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.7900280952453613, cross_entropy: 2.7900280952453613 +[2025-04-27 15:41:45,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 0.8374172449111938, cross_entropy: 0.8374172449111938 +[2025-04-27 15:41:47,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 0.8036285638809204, cross_entropy: 0.8036285638809204 +[2025-04-27 15:41:49,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 1.6185765266418457, cross_entropy: 1.6185765266418457 +[2025-04-27 15:41:51,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 1.1809251308441162, cross_entropy: 1.1809251308441162 +[2025-04-27 15:41:53,473][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.705578565597534, cross_entropy: 2.705578565597534 +[2025-04-27 15:41:55,159][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 0.6915693283081055, cross_entropy: 0.6915693283081055 +[2025-04-27 15:41:56,186][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 2.7907533645629883, cross_entropy: 2.7907533645629883 +[2025-04-27 15:41:58,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 1.2568607330322266, cross_entropy: 1.2568607330322266 +[2025-04-27 15:41:59,389][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 2.983217716217041, cross_entropy: 2.983217716217041 +[2025-04-27 15:42:02,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 0.6938967108726501, cross_entropy: 0.6938967108726501 +[2025-04-27 15:42:02,835][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.0027227401733398, cross_entropy: 1.0027227401733398 +[2025-04-27 15:42:05,470][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.8726247549057007, cross_entropy: 1.8726247549057007 +[2025-04-27 15:42:06,192][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 2.6215412616729736, cross_entropy: 2.6215412616729736 +[2025-04-27 15:42:08,737][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 0.74135422706604, cross_entropy: 0.74135422706604 +[2025-04-27 15:42:09,401][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.0788075923919678, cross_entropy: 1.0788075923919678 +[2025-04-27 15:42:11,818][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 2.221985101699829, cross_entropy: 2.221985101699829 +[2025-04-27 15:42:12,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.6137003898620605, cross_entropy: 2.6137003898620605 +[2025-04-27 15:42:15,686][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.6997969150543213, cross_entropy: 2.6997969150543213 +[2025-04-27 15:42:16,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 0.7810764312744141, cross_entropy: 0.7810764312744141 +[2025-04-27 15:42:19,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 0.813504159450531, cross_entropy: 0.813504159450531 +[2025-04-27 15:42:19,375][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 2.6185028553009033, cross_entropy: 2.6185028553009033 +[2025-04-27 15:42:23,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.5803231596946716, cross_entropy: 0.5803231596946716 +[2025-04-27 15:42:23,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.8649303913116455, cross_entropy: 2.8649303913116455 +[2025-04-27 15:42:26,704][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.079437017440796, cross_entropy: 1.079437017440796 +[2025-04-27 15:42:27,016][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.3571252822875977, cross_entropy: 1.3571252822875977 +[2025-04-27 15:42:30,409][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.685934066772461, cross_entropy: 1.685934066772461 +[2025-04-27 15:42:30,720][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.1043354272842407, cross_entropy: 1.1043354272842407 +[2025-04-27 15:42:34,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 2.733492374420166, cross_entropy: 2.733492374420166 +[2025-04-27 15:42:34,822][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.3332087993621826, cross_entropy: 2.3332087993621826 +[2025-04-27 15:42:38,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 0.584421694278717, cross_entropy: 0.584421694278717 +[2025-04-27 15:42:38,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 1.1867175102233887, cross_entropy: 1.1867175102233887 +[2025-04-27 15:42:41,702][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 1.9399104118347168, cross_entropy: 1.9399104118347168 +[2025-04-27 15:42:42,039][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.909106731414795, cross_entropy: 1.909106731414795 +[2025-04-27 15:42:44,922][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.3304877281188965, cross_entropy: 2.3304877281188965 +[2025-04-27 15:42:45,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 2.6499087810516357, cross_entropy: 2.6499087810516357 +[2025-04-27 15:42:48,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 0.7603628635406494, cross_entropy: 0.7603628635406494 +[2025-04-27 15:42:49,003][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 0.8114663362503052, cross_entropy: 0.8114663362503052 +[2025-04-27 15:42:52,290][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.5749106407165527, cross_entropy: 2.5749106407165527 +[2025-04-27 15:42:52,632][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 2.0603058338165283, cross_entropy: 2.0603058338165283 +[2025-04-27 15:42:55,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.583277463912964, cross_entropy: 2.583277463912964 +[2025-04-27 15:42:55,732][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 2.049417018890381, cross_entropy: 2.049417018890381 +[2025-04-27 15:42:58,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.7656421661376953, cross_entropy: 1.7656421661376953 +[2025-04-27 15:42:58,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.9479547142982483, cross_entropy: 0.9479547142982483 +[2025-04-27 15:43:01,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.904686450958252, cross_entropy: 2.904686450958252 +[2025-04-27 15:43:02,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 1.3467453718185425, cross_entropy: 1.3467453718185425 +[2025-04-27 15:43:04,784][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 1.003298282623291, cross_entropy: 1.003298282623291 +[2025-04-27 15:43:05,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.4300146102905273, cross_entropy: 1.4300146102905273 +[2025-04-27 15:43:07,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 2.8731515407562256, cross_entropy: 2.8731515407562256 +[2025-04-27 15:43:08,087][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.11199152469635, cross_entropy: 1.11199152469635 +[2025-04-27 15:43:10,897][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 0.5519812107086182, cross_entropy: 0.5519812107086182 +[2025-04-27 15:43:11,238][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.125916004180908, cross_entropy: 2.125916004180908 +[2025-04-27 15:43:15,327][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.177595615386963, cross_entropy: 1.177595615386963 +[2025-04-27 15:43:15,665][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 2.7786855697631836, cross_entropy: 2.7786855697631836 +[2025-04-27 15:43:18,656][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.8080666065216064, cross_entropy: 2.8080666065216064 +[2025-04-27 15:43:18,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 2.728616237640381, cross_entropy: 2.728616237640381 +[2025-04-27 15:43:22,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 0.7223151922225952, cross_entropy: 0.7223151922225952 +[2025-04-27 15:43:22,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.741507053375244, cross_entropy: 2.741507053375244 +[2025-04-27 15:43:25,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 1.6910247802734375, cross_entropy: 1.6910247802734375 +[2025-04-27 15:43:25,750][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.7203145027160645, cross_entropy: 2.7203145027160645 +[2025-04-27 15:43:29,409][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 0.9475976228713989, cross_entropy: 0.9475976228713989 +[2025-04-27 15:43:29,750][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.3452987670898438, cross_entropy: 1.3452987670898438 +[2025-04-27 15:43:32,282][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 2.4676475524902344, cross_entropy: 2.4676475524902344 +[2025-04-27 15:43:32,596][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 2.733248710632324, cross_entropy: 2.733248710632324 +[2025-04-27 15:43:36,089][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 1.5371135473251343, cross_entropy: 1.5371135473251343 +[2025-04-27 15:43:36,429][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.623831033706665, cross_entropy: 0.623831033706665 +[2025-04-27 15:43:39,599][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 2.7895190715789795, cross_entropy: 2.7895190715789795 +[2025-04-27 15:43:39,912][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 2.2889013290405273, cross_entropy: 2.2889013290405273 +[2025-04-27 15:43:42,794][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 2.684323787689209, cross_entropy: 2.684323787689209 +[2025-04-27 15:43:43,079][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.5518592596054077, cross_entropy: 1.5518592596054077 +[2025-04-27 15:46:19,850][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.768607497215271, cross_entropy: 1.768607497215271 +[2025-04-27 15:46:19,851][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.2353873252868652, cross_entropy: 1.2353873252868652 +[2025-04-27 15:46:20,015][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/epoch10.pth. +[2025-04-27 15:46:20,220][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. +[2025-04-27 15:46:20,439][BaseTrainer][INFO] - Save model: ./exp/20250427-133045/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..f88b4c8ee74d88590c58a35599a76f7968b8d6bc --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc01e358d6c9cdfe0d88db0cdef138aca9756e3751f8114a599b1a6f82f8ca3 +size 51764965 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..c5ba43cd00d005fa1b888c042859a1e5c04c4443 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250427-133045/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab04bd9340de85728e8187eb6f92a7cd4fcc59c6492344fd410665968890aa90 +size 51716323 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/README.md new file mode 100644 index 0000000000000000000000000000000000000000..5929269f4119e260fd7358259f547dff010e9ce3 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/README.md @@ -0,0 +1,7 @@ +system=default_seed-0 +data=birdclef2025_reshape_5s +train=birdclef2025_reshape_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.490 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f31471bb083d2655b2257c7031f2b0c85cd24089 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/config.yaml @@ -0,0 +1,221 @@ +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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_5s/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_reshape_5s/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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250428-032422 + tensorboard_dir: ./tensorboard/20250428-032422 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..a1f8a48dc26f49807f450f91988cce026015dfaa --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250428-032422/log/20250428-032425 + sweep: + dir: multirun/${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/20250428-032422/log/20250428-032425 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_reshape_5s + - train=birdclef2025_reshape_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_5s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_5s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250428-032422 + - train.output.tensorboard_dir=./tensorboard/20250428-032422 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_5s,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_reshape_5s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_5s/list/validation.txt,train.output.exp_dir=./exp/20250428-032422,train.output.tensorboard_dir=./tensorboard/20250428-032422,train.resume.continue_from=,train=birdclef2025_reshape_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/20250428-032422/log/20250428-032425 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_5s + 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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0aec635492213e11813a1e0c75e6a73682813320 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_reshape_5s +- train=birdclef2025_reshape_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_5s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_5s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250428-032422 +- train.output.tensorboard_dir=./tensorboard/20250428-032422 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..addacb0bffdcd474ebc2b803a62b92deb90cd873 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/.hydra/resolved_config.yaml @@ -0,0 +1,280 @@ +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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_5s/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_reshape_5s/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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: 5 + decode_audio_as_waveform: true + decode_audio_as_monoral: true + training: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: 5 + decode_audio_as_waveform: true + decode_audio_as_monoral: true + training: false + target_shape: 256 + 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/20250428-032422 + tensorboard_dir: ./tensorboard/20250428-032422 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250428-032422/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250428-032422/model/epoch{epoch}.pth + last: + path: ./exp/20250428-032422/model/last.pth + best_epoch: + path: ./exp/20250428-032422/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/train.log new file mode 100644 index 0000000000000000000000000000000000000000..26e6aee460823deba0e756f2cbd0ce98e1174285 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/log/20250428-032425/train.log @@ -0,0 +1,4282 @@ +[2025-04-28 03:24:53,889][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: 5 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_5s/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_reshape_5s/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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250428-032422 + tensorboard_dir: ./tensorboard/20250428-032422 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-28 03:24:53,889][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) + ) +) +[2025-04-28 03:24:53,893][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-28 03:25:02,199][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.323235511779785, cross_entropy: 5.323235511779785 +[2025-04-28 03:25:02,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.33507776260376, cross_entropy: 5.33507776260376 +[2025-04-28 03:25:02,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.2379913330078125, cross_entropy: 5.2379913330078125 +[2025-04-28 03:25:03,215][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.24312686920166, cross_entropy: 5.24312686920166 +[2025-04-28 03:25:03,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.125740051269531, cross_entropy: 5.125740051269531 +[2025-04-28 03:25:05,938][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.131227016448975, cross_entropy: 5.131227016448975 +[2025-04-28 03:25:06,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.94953727722168, cross_entropy: 4.94953727722168 +[2025-04-28 03:25:08,647][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.049361228942871, cross_entropy: 5.049361228942871 +[2025-04-28 03:25:09,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.806547164916992, cross_entropy: 4.806547164916992 +[2025-04-28 03:25:11,740][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.801175117492676, cross_entropy: 4.801175117492676 +[2025-04-28 03:25:12,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.022723197937012, cross_entropy: 5.022723197937012 +[2025-04-28 03:25:14,911][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.699541091918945, cross_entropy: 4.699541091918945 +[2025-04-28 03:25:15,729][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 5.043684959411621, cross_entropy: 5.043684959411621 +[2025-04-28 03:25:19,129][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.789098739624023, cross_entropy: 4.789098739624023 +[2025-04-28 03:25:19,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.712170124053955, cross_entropy: 4.712170124053955 +[2025-04-28 03:25:22,086][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.651671886444092, cross_entropy: 4.651671886444092 +[2025-04-28 03:25:22,974][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.1654510498046875, cross_entropy: 5.1654510498046875 +[2025-04-28 03:25:25,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.1523027420043945, cross_entropy: 5.1523027420043945 +[2025-04-28 03:25:26,974][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.607272148132324, cross_entropy: 4.607272148132324 +[2025-04-28 03:25:29,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.7935991287231445, cross_entropy: 4.7935991287231445 +[2025-04-28 03:25:30,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.647602081298828, cross_entropy: 4.647602081298828 +[2025-04-28 03:25:31,835][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.87624454498291, cross_entropy: 4.87624454498291 +[2025-04-28 03:25:33,783][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.664105415344238, cross_entropy: 4.664105415344238 +[2025-04-28 03:25:34,996][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.671280860900879, cross_entropy: 4.671280860900879 +[2025-04-28 03:25:36,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.585502624511719, cross_entropy: 4.585502624511719 +[2025-04-28 03:25:39,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.665060997009277, cross_entropy: 4.665060997009277 +[2025-04-28 03:25:39,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.6622467041015625, cross_entropy: 4.6622467041015625 +[2025-04-28 03:25:42,525][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.571554183959961, cross_entropy: 4.571554183959961 +[2025-04-28 03:25:42,798][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.4733123779296875, cross_entropy: 4.4733123779296875 +[2025-04-28 03:25:45,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.663128852844238, cross_entropy: 4.663128852844238 +[2025-04-28 03:25:46,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.484016418457031, cross_entropy: 4.484016418457031 +[2025-04-28 03:25:49,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.784850120544434, cross_entropy: 4.784850120544434 +[2025-04-28 03:25:49,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.8172712326049805, cross_entropy: 4.8172712326049805 +[2025-04-28 03:25:52,652][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.431024551391602, cross_entropy: 4.431024551391602 +[2025-04-28 03:25:52,936][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.324383735656738, cross_entropy: 4.324383735656738 +[2025-04-28 03:25:56,109][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.247826099395752, cross_entropy: 4.247826099395752 +[2025-04-28 03:25:56,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.688880920410156, cross_entropy: 4.688880920410156 +[2025-04-28 03:25:59,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.443848609924316, cross_entropy: 4.443848609924316 +[2025-04-28 03:25:59,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.702905178070068, cross_entropy: 4.702905178070068 +[2025-04-28 03:26:03,276][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.454143524169922, cross_entropy: 4.454143524169922 +[2025-04-28 03:26:03,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.393438339233398, cross_entropy: 4.393438339233398 +[2025-04-28 03:26:06,224][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.251169204711914, cross_entropy: 4.251169204711914 +[2025-04-28 03:26:06,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.240920066833496, cross_entropy: 4.240920066833496 +[2025-04-28 03:26:09,014][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.8105669021606445, cross_entropy: 4.8105669021606445 +[2025-04-28 03:26:09,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.36199951171875, cross_entropy: 4.36199951171875 +[2025-04-28 03:26:12,178][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.391608238220215, cross_entropy: 4.391608238220215 +[2025-04-28 03:26:12,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.238925933837891, cross_entropy: 4.238925933837891 +[2025-04-28 03:26:15,487][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.462242126464844, cross_entropy: 4.462242126464844 +[2025-04-28 03:26:15,824][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 3.9901492595672607, cross_entropy: 3.9901492595672607 +[2025-04-28 03:26:18,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.37969970703125, cross_entropy: 4.37969970703125 +[2025-04-28 03:26:19,064][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.074838638305664, cross_entropy: 4.074838638305664 +[2025-04-28 03:26:21,418][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.526375770568848, cross_entropy: 4.526375770568848 +[2025-04-28 03:26:22,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 3.983253240585327, cross_entropy: 3.983253240585327 +[2025-04-28 03:26:25,220][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.104828357696533, cross_entropy: 4.104828357696533 +[2025-04-28 03:26:25,550][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 3.9924182891845703, cross_entropy: 3.9924182891845703 +[2025-04-28 03:26:28,590][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.24777889251709, cross_entropy: 4.24777889251709 +[2025-04-28 03:26:28,859][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.4157233238220215, cross_entropy: 4.4157233238220215 +[2025-04-28 03:26:31,861][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 3.969787359237671, cross_entropy: 3.969787359237671 +[2025-04-28 03:26:32,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.1447272300720215, cross_entropy: 4.1447272300720215 +[2025-04-28 03:26:35,228][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 3.791494607925415, cross_entropy: 3.791494607925415 +[2025-04-28 03:26:35,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.477959632873535, cross_entropy: 4.477959632873535 +[2025-04-28 03:26:38,449][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.21137809753418, cross_entropy: 4.21137809753418 +[2025-04-28 03:26:38,731][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 3.844666004180908, cross_entropy: 3.844666004180908 +[2025-04-28 03:26:41,597][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 3.730196952819824, cross_entropy: 3.730196952819824 +[2025-04-28 03:26:41,939][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.311429977416992, cross_entropy: 4.311429977416992 +[2025-04-28 03:26:44,777][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.320590496063232, cross_entropy: 4.320590496063232 +[2025-04-28 03:26:45,058][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.063865661621094, cross_entropy: 4.063865661621094 +[2025-04-28 03:26:48,048][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.309268951416016, cross_entropy: 4.309268951416016 +[2025-04-28 03:26:48,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 3.8722944259643555, cross_entropy: 3.8722944259643555 +[2025-04-28 03:26:50,651][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 3.602999448776245, cross_entropy: 3.602999448776245 +[2025-04-28 03:26:51,010][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.447039604187012, cross_entropy: 4.447039604187012 +[2025-04-28 03:26:54,025][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 3.964965343475342, cross_entropy: 3.964965343475342 +[2025-04-28 03:26:54,295][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.732762336730957, cross_entropy: 3.732762336730957 +[2025-04-28 03:26:57,209][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.009190559387207, cross_entropy: 4.009190559387207 +[2025-04-28 03:26:57,493][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.064026355743408, cross_entropy: 4.064026355743408 +[2025-04-28 03:27:01,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.451404571533203, cross_entropy: 4.451404571533203 +[2025-04-28 03:27:01,467][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.5153489112854, cross_entropy: 4.5153489112854 +[2025-04-28 03:27:04,212][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 3.9977614879608154, cross_entropy: 3.9977614879608154 +[2025-04-28 03:27:04,480][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.282196044921875, cross_entropy: 4.282196044921875 +[2025-04-28 03:27:07,175][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.262163162231445, cross_entropy: 4.262163162231445 +[2025-04-28 03:27:07,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 3.8164637088775635, cross_entropy: 3.8164637088775635 +[2025-04-28 03:27:09,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.280523300170898, cross_entropy: 4.280523300170898 +[2025-04-28 03:27:10,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.399767875671387, cross_entropy: 4.399767875671387 +[2025-04-28 03:27:12,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.183468818664551, cross_entropy: 4.183468818664551 +[2025-04-28 03:27:14,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.518575668334961, cross_entropy: 4.518575668334961 +[2025-04-28 03:27:16,218][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.84546160697937, cross_entropy: 3.84546160697937 +[2025-04-28 03:27:17,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.002950668334961, cross_entropy: 4.002950668334961 +[2025-04-28 03:27:19,360][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 3.885909080505371, cross_entropy: 3.885909080505371 +[2025-04-28 03:27:20,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.493653297424316, cross_entropy: 4.493653297424316 +[2025-04-28 03:27:22,900][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.9968931674957275, cross_entropy: 3.9968931674957275 +[2025-04-28 03:27:23,227][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.19166374206543, cross_entropy: 4.19166374206543 +[2025-04-28 03:27:25,464][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.474020481109619, cross_entropy: 3.474020481109619 +[2025-04-28 03:27:26,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.7647266387939453, cross_entropy: 3.7647266387939453 +[2025-04-28 03:27:28,504][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.38749361038208, cross_entropy: 4.38749361038208 +[2025-04-28 03:27:30,013][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 3.930021286010742, cross_entropy: 3.930021286010742 +[2025-04-28 03:27:32,012][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.2397971153259277, cross_entropy: 3.2397971153259277 +[2025-04-28 03:27:33,019][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.507014274597168, cross_entropy: 4.507014274597168 +[2025-04-28 03:27:35,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.3701937198638916, cross_entropy: 3.3701937198638916 +[2025-04-28 03:27:36,401][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 3.98311185836792, cross_entropy: 3.98311185836792 +[2025-04-28 03:27:39,148][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.3312740325927734, cross_entropy: 3.3312740325927734 +[2025-04-28 03:27:39,656][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 3.968860387802124, cross_entropy: 3.968860387802124 +[2025-04-28 03:27:41,999][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.582061290740967, cross_entropy: 3.582061290740967 +[2025-04-28 03:27:42,763][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.9445486068725586, cross_entropy: 3.9445486068725586 +[2025-04-28 03:27:45,449][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.7586283683776855, cross_entropy: 3.7586283683776855 +[2025-04-28 03:27:46,272][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.666971206665039, cross_entropy: 3.666971206665039 +[2025-04-28 03:27:48,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.330748558044434, cross_entropy: 4.330748558044434 +[2025-04-28 03:27:48,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.750467300415039, cross_entropy: 3.750467300415039 +[2025-04-28 03:27:51,770][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.155091285705566, cross_entropy: 4.155091285705566 +[2025-04-28 03:27:52,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.5109376907348633, cross_entropy: 3.5109376907348633 +[2025-04-28 03:27:54,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.397000789642334, cross_entropy: 4.397000789642334 +[2025-04-28 03:27:55,161][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.337404727935791, cross_entropy: 3.337404727935791 +[2025-04-28 03:27:57,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.5538294315338135, cross_entropy: 3.5538294315338135 +[2025-04-28 03:27:58,126][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 3.806344509124756, cross_entropy: 3.806344509124756 +[2025-04-28 03:28:00,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.021790981292725, cross_entropy: 4.021790981292725 +[2025-04-28 03:28:00,913][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 3.239968776702881, cross_entropy: 3.239968776702881 +[2025-04-28 03:28:03,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.1780402660369873, cross_entropy: 3.1780402660369873 +[2025-04-28 03:28:04,056][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.701608180999756, cross_entropy: 3.701608180999756 +[2025-04-28 03:28:06,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 3.7895917892456055, cross_entropy: 3.7895917892456055 +[2025-04-28 03:28:07,441][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.132068157196045, cross_entropy: 4.132068157196045 +[2025-04-28 03:28:09,453][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 3.847874641418457, cross_entropy: 3.847874641418457 +[2025-04-28 03:28:10,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 3.9572300910949707, cross_entropy: 3.9572300910949707 +[2025-04-28 03:28:12,577][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 3.4049887657165527, cross_entropy: 3.4049887657165527 +[2025-04-28 03:28:12,902][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.97528076171875, cross_entropy: 3.97528076171875 +[2025-04-28 03:28:15,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.8701090812683105, cross_entropy: 3.8701090812683105 +[2025-04-28 03:28:15,667][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.107273101806641, cross_entropy: 4.107273101806641 +[2025-04-28 03:28:18,023][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 3.703917980194092, cross_entropy: 3.703917980194092 +[2025-04-28 03:28:18,556][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.4312047958374023, cross_entropy: 3.4312047958374023 +[2025-04-28 03:28:20,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 3.5318288803100586, cross_entropy: 3.5318288803100586 +[2025-04-28 03:28:22,500][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 4.222259521484375, cross_entropy: 4.222259521484375 +[2025-04-28 03:28:23,422][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.4131078720092773, cross_entropy: 3.4131078720092773 +[2025-04-28 03:28:25,079][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 3.3274998664855957, cross_entropy: 3.3274998664855957 +[2025-04-28 03:28:26,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 2.9195003509521484, cross_entropy: 2.9195003509521484 +[2025-04-28 03:28:28,178][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.35030460357666, cross_entropy: 4.35030460357666 +[2025-04-28 03:28:28,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 3.702472686767578, cross_entropy: 3.702472686767578 +[2025-04-28 03:28:31,213][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.291347503662109, cross_entropy: 4.291347503662109 +[2025-04-28 03:28:31,549][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.7184700965881348, cross_entropy: 3.7184700965881348 +[2025-04-28 03:28:33,963][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 2.9138965606689453, cross_entropy: 2.9138965606689453 +[2025-04-28 03:28:34,249][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 3.7251040935516357, cross_entropy: 3.7251040935516357 +[2025-04-28 03:28:37,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.150081634521484, cross_entropy: 4.150081634521484 +[2025-04-28 03:28:38,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.92498779296875, cross_entropy: 3.92498779296875 +[2025-04-28 03:28:39,884][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 3.984335422515869, cross_entropy: 3.984335422515869 +[2025-04-28 03:28:40,615][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.101079225540161, cross_entropy: 3.101079225540161 +[2025-04-28 03:28:42,784][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.331679344177246, cross_entropy: 3.331679344177246 +[2025-04-28 03:28:43,734][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 3.4581823348999023, cross_entropy: 3.4581823348999023 +[2025-04-28 03:28:45,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.075863361358643, cross_entropy: 4.075863361358643 +[2025-04-28 03:28:46,576][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.638388156890869, cross_entropy: 3.638388156890869 +[2025-04-28 03:28:49,112][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.172976493835449, cross_entropy: 4.172976493835449 +[2025-04-28 03:28:49,464][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.34415340423584, cross_entropy: 3.34415340423584 +[2025-04-28 03:28:52,811][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 3.831108570098877, cross_entropy: 3.831108570098877 +[2025-04-28 03:28:53,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 3.22619366645813, cross_entropy: 3.22619366645813 +[2025-04-28 03:28:55,350][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 2.8604559898376465, cross_entropy: 2.8604559898376465 +[2025-04-28 03:28:55,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.9210288524627686, cross_entropy: 3.9210288524627686 +[2025-04-28 03:28:58,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.575926780700684, cross_entropy: 4.575926780700684 +[2025-04-28 03:28:58,885][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 3.0668296813964844, cross_entropy: 3.0668296813964844 +[2025-04-28 03:29:01,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.4843127727508545, cross_entropy: 3.4843127727508545 +[2025-04-28 03:29:01,714][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.267002582550049, cross_entropy: 3.267002582550049 +[2025-04-28 03:29:04,510][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 3.4772207736968994, cross_entropy: 3.4772207736968994 +[2025-04-28 03:29:04,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.044452667236328, cross_entropy: 3.044452667236328 +[2025-04-28 03:29:08,399][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 3.2993035316467285, cross_entropy: 3.2993035316467285 +[2025-04-28 03:29:08,678][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 4.282345771789551, cross_entropy: 4.282345771789551 +[2025-04-28 03:29:11,214][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.079794406890869, cross_entropy: 3.079794406890869 +[2025-04-28 03:29:11,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.6015515327453613, cross_entropy: 3.6015515327453613 +[2025-04-28 03:29:14,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 3.9921443462371826, cross_entropy: 3.9921443462371826 +[2025-04-28 03:29:14,532][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.1185011863708496, cross_entropy: 3.1185011863708496 +[2025-04-28 03:29:17,103][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.993774890899658, cross_entropy: 3.993774890899658 +[2025-04-28 03:29:17,380][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.456592082977295, cross_entropy: 4.456592082977295 +[2025-04-28 03:29:20,018][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.807199478149414, cross_entropy: 3.807199478149414 +[2025-04-28 03:29:20,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.104336738586426, cross_entropy: 3.104336738586426 +[2025-04-28 03:29:22,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 3.292921304702759, cross_entropy: 3.292921304702759 +[2025-04-28 03:29:22,997][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 2.9189586639404297, cross_entropy: 2.9189586639404297 +[2025-04-28 03:29:25,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.2655327320098877, cross_entropy: 3.2655327320098877 +[2025-04-28 03:29:26,228][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.0421152114868164, cross_entropy: 3.0421152114868164 +[2025-04-28 03:29:29,591][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 4.059989929199219, cross_entropy: 4.059989929199219 +[2025-04-28 03:29:29,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.130682468414307, cross_entropy: 4.130682468414307 +[2025-04-28 03:29:32,311][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.093482494354248, cross_entropy: 4.093482494354248 +[2025-04-28 03:29:32,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.756070852279663, cross_entropy: 3.756070852279663 +[2025-04-28 03:29:35,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.2136011123657227, cross_entropy: 3.2136011123657227 +[2025-04-28 03:29:35,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 2.862704277038574, cross_entropy: 2.862704277038574 +[2025-04-28 03:29:38,431][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 2.913821220397949, cross_entropy: 2.913821220397949 +[2025-04-28 03:29:38,713][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 2.872771739959717, cross_entropy: 2.872771739959717 +[2025-04-28 03:29:41,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 4.138181209564209, cross_entropy: 4.138181209564209 +[2025-04-28 03:29:42,021][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.2383251190185547, cross_entropy: 3.2383251190185547 +[2025-04-28 03:29:45,684][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 3.2867352962493896, cross_entropy: 3.2867352962493896 +[2025-04-28 03:29:45,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 3.822843074798584, cross_entropy: 3.822843074798584 +[2025-04-28 03:29:49,049][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.9533958435058594, cross_entropy: 3.9533958435058594 +[2025-04-28 03:29:49,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.2022852897644043, cross_entropy: 3.2022852897644043 +[2025-04-28 03:29:51,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.60416841506958, cross_entropy: 3.60416841506958 +[2025-04-28 03:29:52,223][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.626089096069336, cross_entropy: 3.626089096069336 +[2025-04-28 03:29:54,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 2.794865369796753, cross_entropy: 2.794865369796753 +[2025-04-28 03:29:55,205][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.7751312255859375, cross_entropy: 3.7751312255859375 +[2025-04-28 03:29:57,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 3.91044282913208, cross_entropy: 3.91044282913208 +[2025-04-28 03:29:58,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.0000064373016357, cross_entropy: 3.0000064373016357 +[2025-04-28 03:30:00,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 3.9240307807922363, cross_entropy: 3.9240307807922363 +[2025-04-28 03:30:01,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.2716166973114014, cross_entropy: 3.2716166973114014 +[2025-04-28 03:30:04,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 2.955935001373291, cross_entropy: 2.955935001373291 +[2025-04-28 03:30:04,566][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.6306018829345703, cross_entropy: 3.6306018829345703 +[2025-04-28 03:30:07,184][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.9603090286254883, cross_entropy: 3.9603090286254883 +[2025-04-28 03:30:07,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 3.120792865753174, cross_entropy: 3.120792865753174 +[2025-04-28 03:30:09,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.5682244300842285, cross_entropy: 3.5682244300842285 +[2025-04-28 03:30:10,135][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 2.8323616981506348, cross_entropy: 2.8323616981506348 +[2025-04-28 03:30:12,897][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 3.546861171722412, cross_entropy: 3.546861171722412 +[2025-04-28 03:30:13,166][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 3.887563467025757, cross_entropy: 3.887563467025757 +[2025-04-28 03:30:15,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.741459846496582, cross_entropy: 3.741459846496582 +[2025-04-28 03:30:16,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.1870012283325195, cross_entropy: 3.1870012283325195 +[2025-04-28 03:30:19,040][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 2.7931249141693115, cross_entropy: 2.7931249141693115 +[2025-04-28 03:30:19,322][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 2.8017477989196777, cross_entropy: 2.8017477989196777 +[2025-04-28 03:30:21,978][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 4.182170867919922, cross_entropy: 4.182170867919922 +[2025-04-28 03:30:22,246][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 2.541764259338379, cross_entropy: 2.541764259338379 +[2025-04-28 03:30:25,672][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 2.653968095779419, cross_entropy: 2.653968095779419 +[2025-04-28 03:30:25,942][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.386030673980713, cross_entropy: 3.386030673980713 +[2025-04-28 03:30:28,039][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 4.326705455780029, cross_entropy: 4.326705455780029 +[2025-04-28 03:30:28,316][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.187033176422119, cross_entropy: 3.187033176422119 +[2025-04-28 03:30:30,693][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.3652303218841553, cross_entropy: 3.3652303218841553 +[2025-04-28 03:30:30,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 3.689110517501831, cross_entropy: 3.689110517501831 +[2025-04-28 03:30:33,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 2.977630138397217, cross_entropy: 2.977630138397217 +[2025-04-28 03:30:34,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 3.8478944301605225, cross_entropy: 3.8478944301605225 +[2025-04-28 03:30:36,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.664961576461792, cross_entropy: 3.664961576461792 +[2025-04-28 03:30:36,876][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 3.135373592376709, cross_entropy: 3.135373592376709 +[2025-04-28 03:30:39,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.8180992603302, cross_entropy: 3.8180992603302 +[2025-04-28 03:30:39,838][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 2.798797130584717, cross_entropy: 2.798797130584717 +[2025-04-28 03:30:42,472][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.696876049041748, cross_entropy: 3.696876049041748 +[2025-04-28 03:30:42,747][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 3.7682950496673584, cross_entropy: 3.7682950496673584 +[2025-04-28 03:30:45,744][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.287648916244507, cross_entropy: 3.287648916244507 +[2025-04-28 03:30:46,013][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.259892463684082, cross_entropy: 3.259892463684082 +[2025-04-28 03:30:48,700][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 3.8583459854125977, cross_entropy: 3.8583459854125977 +[2025-04-28 03:30:48,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 2.914849281311035, cross_entropy: 2.914849281311035 +[2025-04-28 03:30:51,637][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.0580639839172363, cross_entropy: 3.0580639839172363 +[2025-04-28 03:30:51,906][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 2.9783692359924316, cross_entropy: 2.9783692359924316 +[2025-04-28 03:30:54,758][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 2.789626121520996, cross_entropy: 2.789626121520996 +[2025-04-28 03:30:55,026][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 3.7759833335876465, cross_entropy: 3.7759833335876465 +[2025-04-28 03:30:58,392][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 2.5194950103759766, cross_entropy: 2.5194950103759766 +[2025-04-28 03:30:58,670][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 3.971066474914551, cross_entropy: 3.971066474914551 +[2025-04-28 03:31:01,463][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.788642168045044, cross_entropy: 2.788642168045044 +[2025-04-28 03:31:01,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 2.8033230304718018, cross_entropy: 2.8033230304718018 +[2025-04-28 03:31:04,607][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.348905086517334, cross_entropy: 3.348905086517334 +[2025-04-28 03:31:04,884][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.1059460639953613, cross_entropy: 3.1059460639953613 +[2025-04-28 03:31:07,731][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 3.2705256938934326, cross_entropy: 3.2705256938934326 +[2025-04-28 03:31:08,009][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 3.8478665351867676, cross_entropy: 3.8478665351867676 +[2025-04-28 03:31:11,662][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 2.780731439590454, cross_entropy: 2.780731439590454 +[2025-04-28 03:31:11,931][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.524700164794922, cross_entropy: 3.524700164794922 +[2025-04-28 03:31:15,477][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.2919178009033203, cross_entropy: 3.2919178009033203 +[2025-04-28 03:31:15,759][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 3.571615219116211, cross_entropy: 3.571615219116211 +[2025-04-28 03:31:18,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 3.5533077716827393, cross_entropy: 3.5533077716827393 +[2025-04-28 03:31:18,792][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 3.060062885284424, cross_entropy: 3.060062885284424 +[2025-04-28 03:31:21,743][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.391744613647461, cross_entropy: 3.391744613647461 +[2025-04-28 03:31:22,013][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 3.532528877258301, cross_entropy: 3.532528877258301 +[2025-04-28 03:31:25,491][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.853976249694824, cross_entropy: 3.853976249694824 +[2025-04-28 03:31:25,760][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 3.0354692935943604, cross_entropy: 3.0354692935943604 +[2025-04-28 03:31:28,028][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.0640342235565186, cross_entropy: 3.0640342235565186 +[2025-04-28 03:31:28,302][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 2.7199008464813232, cross_entropy: 2.7199008464813232 +[2025-04-28 03:31:30,731][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 2.466719627380371, cross_entropy: 2.466719627380371 +[2025-04-28 03:31:31,008][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 2.6959471702575684, cross_entropy: 2.6959471702575684 +[2025-04-28 03:31:33,629][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 2.890336751937866, cross_entropy: 2.890336751937866 +[2025-04-28 03:31:33,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.4417619705200195, cross_entropy: 2.4417619705200195 +[2025-04-28 03:31:37,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.1049084663391113, cross_entropy: 3.1049084663391113 +[2025-04-28 03:31:37,504][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.9799306392669678, cross_entropy: 3.9799306392669678 +[2025-04-28 03:31:40,579][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 3.8944079875946045, cross_entropy: 3.8944079875946045 +[2025-04-28 03:31:40,858][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 2.5341598987579346, cross_entropy: 2.5341598987579346 +[2025-04-28 03:31:44,313][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 4.1588029861450195, cross_entropy: 4.1588029861450195 +[2025-04-28 03:31:44,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 4.043109893798828, cross_entropy: 4.043109893798828 +[2025-04-28 03:31:47,120][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.4756886959075928, cross_entropy: 2.4756886959075928 +[2025-04-28 03:31:47,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 3.6093814373016357, cross_entropy: 3.6093814373016357 +[2025-04-28 03:31:50,733][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 3.9262845516204834, cross_entropy: 3.9262845516204834 +[2025-04-28 03:31:51,009][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 2.661485195159912, cross_entropy: 2.661485195159912 +[2025-04-28 03:31:54,605][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 3.6832334995269775, cross_entropy: 3.6832334995269775 +[2025-04-28 03:31:54,874][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.084989547729492, cross_entropy: 3.084989547729492 +[2025-04-28 03:31:57,336][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 3.9666318893432617, cross_entropy: 3.9666318893432617 +[2025-04-28 03:31:57,622][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 3.253187894821167, cross_entropy: 3.253187894821167 +[2025-04-28 03:32:00,139][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 3.86942982673645, cross_entropy: 3.86942982673645 +[2025-04-28 03:32:00,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.5443148612976074, cross_entropy: 3.5443148612976074 +[2025-04-28 03:32:02,655][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.1773290634155273, cross_entropy: 3.1773290634155273 +[2025-04-28 03:32:02,931][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.9150609970092773, cross_entropy: 2.9150609970092773 +[2025-04-28 03:32:06,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 2.6946592330932617, cross_entropy: 2.6946592330932617 +[2025-04-28 03:32:06,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.576139450073242, cross_entropy: 3.576139450073242 +[2025-04-28 03:32:08,942][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.5091450214385986, cross_entropy: 2.5091450214385986 +[2025-04-28 03:32:09,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 3.063082695007324, cross_entropy: 3.063082695007324 +[2025-04-28 03:32:12,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.572049140930176, cross_entropy: 3.572049140930176 +[2025-04-28 03:32:12,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 2.6132724285125732, cross_entropy: 2.6132724285125732 +[2025-04-28 03:32:15,385][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.101261138916016, cross_entropy: 4.101261138916016 +[2025-04-28 03:32:15,664][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.333923816680908, cross_entropy: 3.333923816680908 +[2025-04-28 03:32:18,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.7024121284484863, cross_entropy: 2.7024121284484863 +[2025-04-28 03:32:18,626][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.985414981842041, cross_entropy: 3.985414981842041 +[2025-04-28 03:32:21,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.138239860534668, cross_entropy: 3.138239860534668 +[2025-04-28 03:32:21,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 3.700913906097412, cross_entropy: 3.700913906097412 +[2025-04-28 03:32:24,192][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.5323145389556885, cross_entropy: 2.5323145389556885 +[2025-04-28 03:32:24,473][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.9947497844696045, cross_entropy: 3.9947497844696045 +[2025-04-28 03:32:27,360][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.3865346908569336, cross_entropy: 3.3865346908569336 +[2025-04-28 03:32:27,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.83469295501709, cross_entropy: 3.83469295501709 +[2025-04-28 03:32:30,419][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 2.988391876220703, cross_entropy: 2.988391876220703 +[2025-04-28 03:32:30,690][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 3.9176785945892334, cross_entropy: 3.9176785945892334 +[2025-04-28 03:32:33,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.4997458457946777, cross_entropy: 2.4997458457946777 +[2025-04-28 03:32:33,791][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 2.638853073120117, cross_entropy: 2.638853073120117 +[2025-04-28 03:32:36,197][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 3.486175775527954, cross_entropy: 3.486175775527954 +[2025-04-28 03:32:36,466][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 3.0624313354492188, cross_entropy: 3.0624313354492188 +[2025-04-28 03:32:39,725][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 3.066995859146118, cross_entropy: 3.066995859146118 +[2025-04-28 03:32:40,007][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.638216733932495, cross_entropy: 3.638216733932495 +[2025-04-28 03:32:42,961][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 2.8038382530212402, cross_entropy: 2.8038382530212402 +[2025-04-28 03:32:43,233][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.719557762145996, cross_entropy: 3.719557762145996 +[2025-04-28 03:32:45,996][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.9845736026763916, cross_entropy: 2.9845736026763916 +[2025-04-28 03:32:46,266][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.736891984939575, cross_entropy: 3.736891984939575 +[2025-04-28 03:32:49,753][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 3.990480422973633, cross_entropy: 3.990480422973633 +[2025-04-28 03:32:50,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.37505841255188, cross_entropy: 3.37505841255188 +[2025-04-28 03:32:53,084][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 3.8779163360595703, cross_entropy: 3.8779163360595703 +[2025-04-28 03:32:53,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 3.0677084922790527, cross_entropy: 3.0677084922790527 +[2025-04-28 03:32:56,569][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 2.786553382873535, cross_entropy: 2.786553382873535 +[2025-04-28 03:32:56,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.9707558155059814, cross_entropy: 2.9707558155059814 +[2025-04-28 03:32:58,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 3.9834909439086914, cross_entropy: 3.9834909439086914 +[2025-04-28 03:32:59,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 2.9760327339172363, cross_entropy: 2.9760327339172363 +[2025-04-28 03:33:02,059][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.5088233947753906, cross_entropy: 3.5088233947753906 +[2025-04-28 03:33:02,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 3.4719789028167725, cross_entropy: 3.4719789028167725 +[2025-04-28 03:33:05,108][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.6486964225769043, cross_entropy: 2.6486964225769043 +[2025-04-28 03:33:05,386][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 2.853447437286377, cross_entropy: 2.853447437286377 +[2025-04-28 03:33:08,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 2.9327802658081055, cross_entropy: 2.9327802658081055 +[2025-04-28 03:33:08,642][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.3429877758026123, cross_entropy: 3.3429877758026123 +[2025-04-28 03:33:12,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.8637356758117676, cross_entropy: 2.8637356758117676 +[2025-04-28 03:33:12,307][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.75738787651062, cross_entropy: 3.75738787651062 +[2025-04-28 03:33:15,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.971377372741699, cross_entropy: 2.971377372741699 +[2025-04-28 03:33:15,729][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.139770984649658, cross_entropy: 3.139770984649658 +[2025-04-28 03:33:18,820][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.470405101776123, cross_entropy: 3.470405101776123 +[2025-04-28 03:33:19,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.2321877479553223, cross_entropy: 2.2321877479553223 +[2025-04-28 03:33:22,160][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 2.6939644813537598, cross_entropy: 2.6939644813537598 +[2025-04-28 03:33:22,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 3.5512871742248535, cross_entropy: 3.5512871742248535 +[2025-04-28 03:33:25,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.857762575149536, cross_entropy: 3.857762575149536 +[2025-04-28 03:33:25,651][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 2.5367560386657715, cross_entropy: 2.5367560386657715 +[2025-04-28 03:33:28,648][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 2.3591818809509277, cross_entropy: 2.3591818809509277 +[2025-04-28 03:33:28,917][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.6580395698547363, cross_entropy: 3.6580395698547363 +[2025-04-28 03:33:31,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 3.6618189811706543, cross_entropy: 3.6618189811706543 +[2025-04-28 03:33:32,090][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 2.4127838611602783, cross_entropy: 2.4127838611602783 +[2025-04-28 03:33:34,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.669173240661621, cross_entropy: 3.669173240661621 +[2025-04-28 03:33:35,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 2.7468247413635254, cross_entropy: 2.7468247413635254 +[2025-04-28 03:33:37,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.1973979473114014, cross_entropy: 3.1973979473114014 +[2025-04-28 03:33:37,900][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 2.906611442565918, cross_entropy: 2.906611442565918 +[2025-04-28 03:33:41,062][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 2.5207643508911133, cross_entropy: 2.5207643508911133 +[2025-04-28 03:33:41,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.966639757156372, cross_entropy: 3.966639757156372 +[2025-04-28 03:33:44,347][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.948615550994873, cross_entropy: 2.948615550994873 +[2025-04-28 03:33:44,616][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 3.6288487911224365, cross_entropy: 3.6288487911224365 +[2025-04-28 03:33:47,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 3.5051584243774414, cross_entropy: 3.5051584243774414 +[2025-04-28 03:33:47,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 2.3932785987854004, cross_entropy: 2.3932785987854004 +[2025-04-28 03:33:50,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.4982855319976807, cross_entropy: 2.4982855319976807 +[2025-04-28 03:33:50,357][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.878188133239746, cross_entropy: 3.878188133239746 +[2025-04-28 03:33:53,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.8166005611419678, cross_entropy: 2.8166005611419678 +[2025-04-28 03:33:53,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.707874298095703, cross_entropy: 3.707874298095703 +[2025-04-28 03:33:56,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 3.208909511566162, cross_entropy: 3.208909511566162 +[2025-04-28 03:33:57,107][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 3.6862893104553223, cross_entropy: 3.6862893104553223 +[2025-04-28 03:33:59,333][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.45524001121521, cross_entropy: 3.45524001121521 +[2025-04-28 03:33:59,603][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 2.652801275253296, cross_entropy: 2.652801275253296 +[2025-04-28 03:34:02,135][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.9263038635253906, cross_entropy: 2.9263038635253906 +[2025-04-28 03:34:02,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 3.066340446472168, cross_entropy: 3.066340446472168 +[2025-04-28 03:34:05,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 2.2613277435302734, cross_entropy: 2.2613277435302734 +[2025-04-28 03:34:05,743][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 3.4718074798583984, cross_entropy: 3.4718074798583984 +[2025-04-28 03:34:08,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.3032872676849365, cross_entropy: 2.3032872676849365 +[2025-04-28 03:34:08,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.405965805053711, cross_entropy: 2.405965805053711 +[2025-04-28 03:34:11,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.5728399753570557, cross_entropy: 2.5728399753570557 +[2025-04-28 03:34:11,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 3.9231762886047363, cross_entropy: 3.9231762886047363 +[2025-04-28 03:34:13,774][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.586045026779175, cross_entropy: 3.586045026779175 +[2025-04-28 03:34:16,713][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.399134397506714, cross_entropy: 3.399134397506714 +[2025-04-28 03:36:46,176][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.6662049293518066, cross_entropy: 3.6662049293518066 +[2025-04-28 03:36:46,176][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.563690185546875, cross_entropy: 2.563690185546875 +[2025-04-28 03:36:46,349][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 03:36:46,513][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch1.pth. +[2025-04-28 03:36:46,683][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 03:36:49,866][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.7203547954559326, cross_entropy: 3.7203547954559326 +[2025-04-28 03:36:50,146][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.3701484203338623, cross_entropy: 2.3701484203338623 +[2025-04-28 03:36:52,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.9284205436706543, cross_entropy: 3.9284205436706543 +[2025-04-28 03:36:53,071][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 1.9923008680343628, cross_entropy: 1.9923008680343628 +[2025-04-28 03:36:55,267][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.3054490089416504, cross_entropy: 2.3054490089416504 +[2025-04-28 03:36:55,535][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 3.8317487239837646, cross_entropy: 3.8317487239837646 +[2025-04-28 03:36:57,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 3.193294048309326, cross_entropy: 3.193294048309326 +[2025-04-28 03:36:58,164][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 2.424178123474121, cross_entropy: 2.424178123474121 +[2025-04-28 03:37:00,265][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.295144557952881, cross_entropy: 2.295144557952881 +[2025-04-28 03:37:00,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.3442273139953613, cross_entropy: 2.3442273139953613 +[2025-04-28 03:37:02,713][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.045166492462158, cross_entropy: 2.045166492462158 +[2025-04-28 03:37:02,996][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.8127777576446533, cross_entropy: 3.8127777576446533 +[2025-04-28 03:37:05,319][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.115046739578247, cross_entropy: 3.115046739578247 +[2025-04-28 03:37:05,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.5454859733581543, cross_entropy: 2.5454859733581543 +[2025-04-28 03:37:09,325][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.5837700366973877, cross_entropy: 3.5837700366973877 +[2025-04-28 03:37:09,595][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 3.6400437355041504, cross_entropy: 3.6400437355041504 +[2025-04-28 03:37:11,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.8299736976623535, cross_entropy: 2.8299736976623535 +[2025-04-28 03:37:12,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.0359973907470703, cross_entropy: 2.0359973907470703 +[2025-04-28 03:37:14,422][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 2.82297420501709, cross_entropy: 2.82297420501709 +[2025-04-28 03:37:14,709][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.3205790519714355, cross_entropy: 2.3205790519714355 +[2025-04-28 03:37:16,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 2.260453701019287, cross_entropy: 2.260453701019287 +[2025-04-28 03:37:16,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 2.498354434967041, cross_entropy: 2.498354434967041 +[2025-04-28 03:37:19,144][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 2.8801259994506836, cross_entropy: 2.8801259994506836 +[2025-04-28 03:37:19,427][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.7087626457214355, cross_entropy: 3.7087626457214355 +[2025-04-28 03:37:21,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 2.8195180892944336, cross_entropy: 2.8195180892944336 +[2025-04-28 03:37:21,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.2522053718566895, cross_entropy: 2.2522053718566895 +[2025-04-28 03:37:24,289][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 2.197082996368408, cross_entropy: 2.197082996368408 +[2025-04-28 03:37:24,557][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.60128116607666, cross_entropy: 2.60128116607666 +[2025-04-28 03:37:26,901][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 2.800663709640503, cross_entropy: 2.800663709640503 +[2025-04-28 03:37:27,184][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 3.39465069770813, cross_entropy: 3.39465069770813 +[2025-04-28 03:37:29,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.18325138092041, cross_entropy: 2.18325138092041 +[2025-04-28 03:37:29,701][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 3.1691665649414062, cross_entropy: 3.1691665649414062 +[2025-04-28 03:37:31,779][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.2927262783050537, cross_entropy: 2.2927262783050537 +[2025-04-28 03:37:32,060][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 3.9432640075683594, cross_entropy: 3.9432640075683594 +[2025-04-28 03:37:34,247][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.1712615489959717, cross_entropy: 2.1712615489959717 +[2025-04-28 03:37:34,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.520737648010254, cross_entropy: 3.520737648010254 +[2025-04-28 03:37:37,417][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.3185441493988037, cross_entropy: 3.3185441493988037 +[2025-04-28 03:37:37,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 3.8759918212890625, cross_entropy: 3.8759918212890625 +[2025-04-28 03:37:41,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 3.461033344268799, cross_entropy: 3.461033344268799 +[2025-04-28 03:37:42,154][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 3.070300817489624, cross_entropy: 3.070300817489624 +[2025-04-28 03:37:44,586][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 2.8174424171447754, cross_entropy: 2.8174424171447754 +[2025-04-28 03:37:44,868][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.668199300765991, cross_entropy: 2.668199300765991 +[2025-04-28 03:37:46,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 2.4640398025512695, cross_entropy: 2.4640398025512695 +[2025-04-28 03:37:47,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.892728328704834, cross_entropy: 2.892728328704834 +[2025-04-28 03:37:49,420][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 2.30127215385437, cross_entropy: 2.30127215385437 +[2025-04-28 03:37:49,703][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.8888087272644043, cross_entropy: 3.8888087272644043 +[2025-04-28 03:37:52,713][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.5347654819488525, cross_entropy: 3.5347654819488525 +[2025-04-28 03:37:52,981][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 4.009282112121582, cross_entropy: 4.009282112121582 +[2025-04-28 03:37:55,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.4634902477264404, cross_entropy: 3.4634902477264404 +[2025-04-28 03:37:55,679][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 2.8343920707702637, cross_entropy: 2.8343920707702637 +[2025-04-28 03:37:58,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.233595848083496, cross_entropy: 3.233595848083496 +[2025-04-28 03:37:58,813][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 3.155219554901123, cross_entropy: 3.155219554901123 +[2025-04-28 03:38:01,348][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.1269025802612305, cross_entropy: 3.1269025802612305 +[2025-04-28 03:38:01,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 2.898503065109253, cross_entropy: 2.898503065109253 +[2025-04-28 03:38:03,899][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 2.634289264678955, cross_entropy: 2.634289264678955 +[2025-04-28 03:38:04,180][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.5139803886413574, cross_entropy: 2.5139803886413574 +[2025-04-28 03:38:06,264][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.480098247528076, cross_entropy: 2.480098247528076 +[2025-04-28 03:38:06,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.661940574645996, cross_entropy: 2.661940574645996 +[2025-04-28 03:38:09,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 2.43621563911438, cross_entropy: 2.43621563911438 +[2025-04-28 03:38:09,546][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 2.1613035202026367, cross_entropy: 2.1613035202026367 +[2025-04-28 03:38:12,243][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 2.1663503646850586, cross_entropy: 2.1663503646850586 +[2025-04-28 03:38:12,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.7927331924438477, cross_entropy: 3.7927331924438477 +[2025-04-28 03:38:14,857][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.1325254440307617, cross_entropy: 2.1325254440307617 +[2025-04-28 03:38:15,138][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 2.173055648803711, cross_entropy: 2.173055648803711 +[2025-04-28 03:38:17,475][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 4.000615119934082, cross_entropy: 4.000615119934082 +[2025-04-28 03:38:17,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 2.969630718231201, cross_entropy: 2.969630718231201 +[2025-04-28 03:38:20,342][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.551339626312256, cross_entropy: 2.551339626312256 +[2025-04-28 03:38:20,613][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 2.279252529144287, cross_entropy: 2.279252529144287 +[2025-04-28 03:38:22,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.616448402404785, cross_entropy: 2.616448402404785 +[2025-04-28 03:38:23,154][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 2.9925026893615723, cross_entropy: 2.9925026893615723 +[2025-04-28 03:38:25,213][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.362710952758789, cross_entropy: 3.362710952758789 +[2025-04-28 03:38:25,493][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.5152266025543213, cross_entropy: 2.5152266025543213 +[2025-04-28 03:38:27,659][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.0886311531066895, cross_entropy: 3.0886311531066895 +[2025-04-28 03:38:27,942][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 2.646120071411133, cross_entropy: 2.646120071411133 +[2025-04-28 03:38:31,058][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.045875310897827, cross_entropy: 2.045875310897827 +[2025-04-28 03:38:31,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 2.6891191005706787, cross_entropy: 2.6891191005706787 +[2025-04-28 03:38:33,456][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 2.6328558921813965, cross_entropy: 2.6328558921813965 +[2025-04-28 03:38:33,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.598167896270752, cross_entropy: 3.598167896270752 +[2025-04-28 03:38:36,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.9846627712249756, cross_entropy: 3.9846627712249756 +[2025-04-28 03:38:36,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.120708465576172, cross_entropy: 3.120708465576172 +[2025-04-28 03:38:38,825][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.4059433937072754, cross_entropy: 2.4059433937072754 +[2025-04-28 03:38:39,105][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.703545570373535, cross_entropy: 3.703545570373535 +[2025-04-28 03:38:41,645][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.5816075801849365, cross_entropy: 2.5816075801849365 +[2025-04-28 03:38:41,930][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 2.7329463958740234, cross_entropy: 2.7329463958740234 +[2025-04-28 03:38:45,367][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.0564193725585938, cross_entropy: 3.0564193725585938 +[2025-04-28 03:38:45,649][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 2.2275261878967285, cross_entropy: 2.2275261878967285 +[2025-04-28 03:38:48,261][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 2.390500068664551, cross_entropy: 2.390500068664551 +[2025-04-28 03:38:48,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 2.361823558807373, cross_entropy: 2.361823558807373 +[2025-04-28 03:38:50,987][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.7163140773773193, cross_entropy: 3.7163140773773193 +[2025-04-28 03:38:51,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.413034677505493, cross_entropy: 2.413034677505493 +[2025-04-28 03:38:53,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.0985255241394043, cross_entropy: 3.0985255241394043 +[2025-04-28 03:38:53,790][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 2.3681118488311768, cross_entropy: 2.3681118488311768 +[2025-04-28 03:38:56,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.442521095275879, cross_entropy: 3.442521095275879 +[2025-04-28 03:38:56,695][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 2.5660696029663086, cross_entropy: 2.5660696029663086 +[2025-04-28 03:38:58,607][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 3.9459073543548584, cross_entropy: 3.9459073543548584 +[2025-04-28 03:38:58,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.93900728225708, cross_entropy: 2.93900728225708 +[2025-04-28 03:39:01,251][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 2.699230194091797, cross_entropy: 2.699230194091797 +[2025-04-28 03:39:01,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 3.48378849029541, cross_entropy: 3.48378849029541 +[2025-04-28 03:39:03,450][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 2.526609182357788, cross_entropy: 2.526609182357788 +[2025-04-28 03:39:03,732][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 2.5290024280548096, cross_entropy: 2.5290024280548096 +[2025-04-28 03:39:05,723][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.8921427726745605, cross_entropy: 3.8921427726745605 +[2025-04-28 03:39:06,005][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 2.6671559810638428, cross_entropy: 2.6671559810638428 +[2025-04-28 03:39:08,092][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 3.654268741607666, cross_entropy: 3.654268741607666 +[2025-04-28 03:39:08,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 1.781447172164917, cross_entropy: 1.781447172164917 +[2025-04-28 03:39:10,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 2.4928195476531982, cross_entropy: 2.4928195476531982 +[2025-04-28 03:39:10,925][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.699889898300171, cross_entropy: 3.699889898300171 +[2025-04-28 03:39:14,535][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.346595287322998, cross_entropy: 2.346595287322998 +[2025-04-28 03:39:14,816][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.376432180404663, cross_entropy: 3.376432180404663 +[2025-04-28 03:39:17,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.6409082412719727, cross_entropy: 3.6409082412719727 +[2025-04-28 03:39:17,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.612694501876831, cross_entropy: 3.612694501876831 +[2025-04-28 03:39:19,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 3.5674333572387695, cross_entropy: 3.5674333572387695 +[2025-04-28 03:39:19,819][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 2.2667148113250732, cross_entropy: 2.2667148113250732 +[2025-04-28 03:39:22,536][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 2.607941150665283, cross_entropy: 2.607941150665283 +[2025-04-28 03:39:22,805][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.1163220405578613, cross_entropy: 3.1163220405578613 +[2025-04-28 03:39:24,982][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 2.5639595985412598, cross_entropy: 2.5639595985412598 +[2025-04-28 03:39:25,264][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 2.9619107246398926, cross_entropy: 2.9619107246398926 +[2025-04-28 03:39:27,811][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.375917911529541, cross_entropy: 2.375917911529541 +[2025-04-28 03:39:28,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.3540167808532715, cross_entropy: 3.3540167808532715 +[2025-04-28 03:39:30,348][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 2.0595576763153076, cross_entropy: 2.0595576763153076 +[2025-04-28 03:39:30,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 3.054417133331299, cross_entropy: 3.054417133331299 +[2025-04-28 03:39:32,777][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.4799957275390625, cross_entropy: 3.4799957275390625 +[2025-04-28 03:39:33,051][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.243986129760742, cross_entropy: 2.243986129760742 +[2025-04-28 03:39:35,372][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 2.476868152618408, cross_entropy: 2.476868152618408 +[2025-04-28 03:39:35,640][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 2.702399969100952, cross_entropy: 2.702399969100952 +[2025-04-28 03:39:37,743][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 2.905198097229004, cross_entropy: 2.905198097229004 +[2025-04-28 03:39:38,011][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.266474723815918, cross_entropy: 2.266474723815918 +[2025-04-28 03:39:40,851][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.7431280612945557, cross_entropy: 3.7431280612945557 +[2025-04-28 03:39:41,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 2.6877591609954834, cross_entropy: 2.6877591609954834 +[2025-04-28 03:39:43,421][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 3.7512593269348145, cross_entropy: 3.7512593269348145 +[2025-04-28 03:39:43,706][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.593656063079834, cross_entropy: 2.593656063079834 +[2025-04-28 03:39:45,828][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.1627254486083984, cross_entropy: 2.1627254486083984 +[2025-04-28 03:39:46,108][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.275416135787964, cross_entropy: 2.275416135787964 +[2025-04-28 03:39:48,596][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 4.002723693847656, cross_entropy: 4.002723693847656 +[2025-04-28 03:39:48,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.4573991298675537, cross_entropy: 2.4573991298675537 +[2025-04-28 03:39:50,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 2.8866353034973145, cross_entropy: 2.8866353034973145 +[2025-04-28 03:39:51,214][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 2.929471015930176, cross_entropy: 2.929471015930176 +[2025-04-28 03:39:53,482][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.043940782546997, cross_entropy: 2.043940782546997 +[2025-04-28 03:39:53,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 2.36846923828125, cross_entropy: 2.36846923828125 +[2025-04-28 03:39:55,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 2.6678662300109863, cross_entropy: 2.6678662300109863 +[2025-04-28 03:39:56,106][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 2.489990472793579, cross_entropy: 2.489990472793579 +[2025-04-28 03:39:58,488][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 2.9399664402008057, cross_entropy: 2.9399664402008057 +[2025-04-28 03:39:58,769][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 4.015720367431641, cross_entropy: 4.015720367431641 +[2025-04-28 03:40:01,109][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.3175199031829834, cross_entropy: 3.3175199031829834 +[2025-04-28 03:40:01,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.2381746768951416, cross_entropy: 2.2381746768951416 +[2025-04-28 03:40:03,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.586172580718994, cross_entropy: 2.586172580718994 +[2025-04-28 03:40:03,455][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 2.513098955154419, cross_entropy: 2.513098955154419 +[2025-04-28 03:40:05,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.5293102264404297, cross_entropy: 2.5293102264404297 +[2025-04-28 03:40:05,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.1879444122314453, cross_entropy: 2.1879444122314453 +[2025-04-28 03:40:08,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 3.606534719467163, cross_entropy: 3.606534719467163 +[2025-04-28 03:40:08,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 2.8471665382385254, cross_entropy: 2.8471665382385254 +[2025-04-28 03:40:10,419][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.6579275131225586, cross_entropy: 2.6579275131225586 +[2025-04-28 03:40:10,797][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 2.250168800354004, cross_entropy: 2.250168800354004 +[2025-04-28 03:40:12,811][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.535229206085205, cross_entropy: 3.535229206085205 +[2025-04-28 03:40:13,122][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 2.7114882469177246, cross_entropy: 2.7114882469177246 +[2025-04-28 03:40:16,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 2.912604570388794, cross_entropy: 2.912604570388794 +[2025-04-28 03:40:16,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 3.0907583236694336, cross_entropy: 3.0907583236694336 +[2025-04-28 03:40:19,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 2.416857957839966, cross_entropy: 2.416857957839966 +[2025-04-28 03:40:19,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 2.9054200649261475, cross_entropy: 2.9054200649261475 +[2025-04-28 03:40:23,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.488773822784424, cross_entropy: 3.488773822784424 +[2025-04-28 03:40:23,505][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.789949417114258, cross_entropy: 2.789949417114258 +[2025-04-28 03:40:25,940][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 2.612344741821289, cross_entropy: 2.612344741821289 +[2025-04-28 03:40:26,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 2.341520071029663, cross_entropy: 2.341520071029663 +[2025-04-28 03:40:29,233][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.636150360107422, cross_entropy: 2.636150360107422 +[2025-04-28 03:40:29,515][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 2.3276822566986084, cross_entropy: 2.3276822566986084 +[2025-04-28 03:40:31,294][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 2.9269986152648926, cross_entropy: 2.9269986152648926 +[2025-04-28 03:40:31,577][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.4043259620666504, cross_entropy: 2.4043259620666504 +[2025-04-28 03:40:33,768][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 2.299436330795288, cross_entropy: 2.299436330795288 +[2025-04-28 03:40:34,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.859523057937622, cross_entropy: 2.859523057937622 +[2025-04-28 03:40:36,601][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.7348766326904297, cross_entropy: 2.7348766326904297 +[2025-04-28 03:40:36,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.2172019481658936, cross_entropy: 2.2172019481658936 +[2025-04-28 03:40:38,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.090949058532715, cross_entropy: 3.090949058532715 +[2025-04-28 03:40:39,121][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 4.072244644165039, cross_entropy: 4.072244644165039 +[2025-04-28 03:40:41,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 3.0355031490325928, cross_entropy: 3.0355031490325928 +[2025-04-28 03:40:41,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 3.3028740882873535, cross_entropy: 3.3028740882873535 +[2025-04-28 03:40:43,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.805471420288086, cross_entropy: 2.805471420288086 +[2025-04-28 03:40:44,107][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 3.889141082763672, cross_entropy: 3.889141082763672 +[2025-04-28 03:40:46,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 2.317667007446289, cross_entropy: 2.317667007446289 +[2025-04-28 03:40:46,403][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.012850761413574, cross_entropy: 2.012850761413574 +[2025-04-28 03:40:49,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 3.2309184074401855, cross_entropy: 3.2309184074401855 +[2025-04-28 03:40:49,323][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 2.685582160949707, cross_entropy: 2.685582160949707 +[2025-04-28 03:40:51,829][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.2791004180908203, cross_entropy: 2.2791004180908203 +[2025-04-28 03:40:52,110][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 2.0069642066955566, cross_entropy: 2.0069642066955566 +[2025-04-28 03:40:54,495][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 2.2581119537353516, cross_entropy: 2.2581119537353516 +[2025-04-28 03:40:54,779][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.155207633972168, cross_entropy: 2.155207633972168 +[2025-04-28 03:40:57,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 3.3979220390319824, cross_entropy: 3.3979220390319824 +[2025-04-28 03:40:57,633][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 3.4156441688537598, cross_entropy: 3.4156441688537598 +[2025-04-28 03:41:00,723][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.3492555618286133, cross_entropy: 2.3492555618286133 +[2025-04-28 03:41:01,003][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.2451486587524414, cross_entropy: 3.2451486587524414 +[2025-04-28 03:41:03,065][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.805537700653076, cross_entropy: 3.805537700653076 +[2025-04-28 03:41:03,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.1594834327697754, cross_entropy: 2.1594834327697754 +[2025-04-28 03:41:06,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 2.2923920154571533, cross_entropy: 2.2923920154571533 +[2025-04-28 03:41:06,333][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 2.1210460662841797, cross_entropy: 2.1210460662841797 +[2025-04-28 03:41:09,195][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.9430527687072754, cross_entropy: 2.9430527687072754 +[2025-04-28 03:41:09,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 4.14581823348999, cross_entropy: 4.14581823348999 +[2025-04-28 03:41:11,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 1.9869385957717896, cross_entropy: 1.9869385957717896 +[2025-04-28 03:41:11,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.560317039489746, cross_entropy: 2.560317039489746 +[2025-04-28 03:41:14,441][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 2.6349740028381348, cross_entropy: 2.6349740028381348 +[2025-04-28 03:41:14,720][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 2.0665361881256104, cross_entropy: 2.0665361881256104 +[2025-04-28 03:41:16,861][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 2.948728561401367, cross_entropy: 2.948728561401367 +[2025-04-28 03:41:17,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 2.9714910984039307, cross_entropy: 2.9714910984039307 +[2025-04-28 03:41:19,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 2.354058265686035, cross_entropy: 2.354058265686035 +[2025-04-28 03:41:19,443][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 3.2507362365722656, cross_entropy: 3.2507362365722656 +[2025-04-28 03:41:21,968][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 2.596524238586426, cross_entropy: 2.596524238586426 +[2025-04-28 03:41:22,248][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.648948907852173, cross_entropy: 2.648948907852173 +[2025-04-28 03:41:24,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.7459096908569336, cross_entropy: 2.7459096908569336 +[2025-04-28 03:41:25,172][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 2.2880148887634277, cross_entropy: 2.2880148887634277 +[2025-04-28 03:41:26,961][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 3.491945743560791, cross_entropy: 3.491945743560791 +[2025-04-28 03:41:28,024][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 3.4921014308929443, cross_entropy: 3.4921014308929443 +[2025-04-28 03:41:29,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.6888208389282227, cross_entropy: 3.6888208389282227 +[2025-04-28 03:41:30,238][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 3.2371373176574707, cross_entropy: 3.2371373176574707 +[2025-04-28 03:41:31,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 2.2961840629577637, cross_entropy: 2.2961840629577637 +[2025-04-28 03:41:32,907][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 2.9513471126556396, cross_entropy: 2.9513471126556396 +[2025-04-28 03:41:34,176][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.7127795219421387, cross_entropy: 2.7127795219421387 +[2025-04-28 03:41:35,059][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 3.6501245498657227, cross_entropy: 3.6501245498657227 +[2025-04-28 03:41:36,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.73498797416687, cross_entropy: 2.73498797416687 +[2025-04-28 03:41:37,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 3.032752513885498, cross_entropy: 3.032752513885498 +[2025-04-28 03:41:38,997][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 3.278716564178467, cross_entropy: 3.278716564178467 +[2025-04-28 03:41:39,318][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.851461887359619, cross_entropy: 2.851461887359619 +[2025-04-28 03:41:41,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.411691188812256, cross_entropy: 2.411691188812256 +[2025-04-28 03:41:41,741][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.7673234939575195, cross_entropy: 2.7673234939575195 +[2025-04-28 03:41:43,276][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 2.2978928089141846, cross_entropy: 2.2978928089141846 +[2025-04-28 03:41:44,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.5159549713134766, cross_entropy: 2.5159549713134766 +[2025-04-28 03:41:45,390][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 3.035156011581421, cross_entropy: 3.035156011581421 +[2025-04-28 03:41:46,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.195159435272217, cross_entropy: 2.195159435272217 +[2025-04-28 03:41:47,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 3.8768930435180664, cross_entropy: 3.8768930435180664 +[2025-04-28 03:41:50,244][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.363858699798584, cross_entropy: 2.363858699798584 +[2025-04-28 03:41:50,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 4.0413947105407715, cross_entropy: 4.0413947105407715 +[2025-04-28 03:41:53,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.5338637828826904, cross_entropy: 3.5338637828826904 +[2025-04-28 03:41:53,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 2.0638885498046875, cross_entropy: 2.0638885498046875 +[2025-04-28 03:41:56,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 1.9625260829925537, cross_entropy: 1.9625260829925537 +[2025-04-28 03:41:56,761][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 1.9906978607177734, cross_entropy: 1.9906978607177734 +[2025-04-28 03:41:58,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.6187729835510254, cross_entropy: 2.6187729835510254 +[2025-04-28 03:41:59,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 3.5759902000427246, cross_entropy: 3.5759902000427246 +[2025-04-28 03:42:01,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 2.6043083667755127, cross_entropy: 2.6043083667755127 +[2025-04-28 03:42:01,333][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.4443728923797607, cross_entropy: 2.4443728923797607 +[2025-04-28 03:42:03,236][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.6991071701049805, cross_entropy: 2.6991071701049805 +[2025-04-28 03:42:03,505][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 2.6341466903686523, cross_entropy: 2.6341466903686523 +[2025-04-28 03:42:05,952][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 2.5701639652252197, cross_entropy: 2.5701639652252197 +[2025-04-28 03:42:06,234][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 2.316093921661377, cross_entropy: 2.316093921661377 +[2025-04-28 03:42:08,527][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.168069362640381, cross_entropy: 2.168069362640381 +[2025-04-28 03:42:08,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 2.874380111694336, cross_entropy: 2.874380111694336 +[2025-04-28 03:42:11,341][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 2.3839831352233887, cross_entropy: 2.3839831352233887 +[2025-04-28 03:42:11,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.617556571960449, cross_entropy: 3.617556571960449 +[2025-04-28 03:42:14,111][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 3.9713799953460693, cross_entropy: 3.9713799953460693 +[2025-04-28 03:42:14,447][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 2.4718594551086426, cross_entropy: 2.4718594551086426 +[2025-04-28 03:42:16,403][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 2.627366781234741, cross_entropy: 2.627366781234741 +[2025-04-28 03:42:16,732][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.011033535003662, cross_entropy: 2.011033535003662 +[2025-04-28 03:42:20,480][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 3.6994941234588623, cross_entropy: 3.6994941234588623 +[2025-04-28 03:42:20,760][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 3.3443491458892822, cross_entropy: 3.3443491458892822 +[2025-04-28 03:42:22,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 3.150749683380127, cross_entropy: 3.150749683380127 +[2025-04-28 03:42:23,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.0900635719299316, cross_entropy: 3.0900635719299316 +[2025-04-28 03:42:25,295][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 2.4744668006896973, cross_entropy: 2.4744668006896973 +[2025-04-28 03:42:25,578][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 2.3881149291992188, cross_entropy: 2.3881149291992188 +[2025-04-28 03:42:28,459][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 2.7367238998413086, cross_entropy: 2.7367238998413086 +[2025-04-28 03:42:28,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.0618672370910645, cross_entropy: 2.0618672370910645 +[2025-04-28 03:42:31,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 2.526008129119873, cross_entropy: 2.526008129119873 +[2025-04-28 03:42:31,589][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 2.82781720161438, cross_entropy: 2.82781720161438 +[2025-04-28 03:42:34,440][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 3.9007928371429443, cross_entropy: 3.9007928371429443 +[2025-04-28 03:42:34,721][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.5224428176879883, cross_entropy: 2.5224428176879883 +[2025-04-28 03:42:37,211][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 3.6392083168029785, cross_entropy: 3.6392083168029785 +[2025-04-28 03:42:37,480][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.5567190647125244, cross_entropy: 2.5567190647125244 +[2025-04-28 03:42:39,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.890458583831787, cross_entropy: 2.890458583831787 +[2025-04-28 03:42:39,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 3.859208106994629, cross_entropy: 3.859208106994629 +[2025-04-28 03:42:41,678][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.7089920043945312, cross_entropy: 2.7089920043945312 +[2025-04-28 03:42:41,946][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.1281795501708984, cross_entropy: 2.1281795501708984 +[2025-04-28 03:42:44,337][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.6760034561157227, cross_entropy: 2.6760034561157227 +[2025-04-28 03:42:44,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 3.4510116577148438, cross_entropy: 3.4510116577148438 +[2025-04-28 03:42:46,639][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.4151859283447266, cross_entropy: 3.4151859283447266 +[2025-04-28 03:42:46,917][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 3.738023281097412, cross_entropy: 3.738023281097412 +[2025-04-28 03:42:49,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 3.4138989448547363, cross_entropy: 3.4138989448547363 +[2025-04-28 03:42:49,599][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 2.188476800918579, cross_entropy: 2.188476800918579 +[2025-04-28 03:42:51,243][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 1.8729636669158936, cross_entropy: 1.8729636669158936 +[2025-04-28 03:42:51,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 1.9482697248458862, cross_entropy: 1.9482697248458862 +[2025-04-28 03:42:53,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 2.641063690185547, cross_entropy: 2.641063690185547 +[2025-04-28 03:42:54,008][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 3.5779523849487305, cross_entropy: 3.5779523849487305 +[2025-04-28 03:42:56,284][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 2.7294535636901855, cross_entropy: 2.7294535636901855 +[2025-04-28 03:42:56,568][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 2.2261617183685303, cross_entropy: 2.2261617183685303 +[2025-04-28 03:42:58,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 2.169099807739258, cross_entropy: 2.169099807739258 +[2025-04-28 03:42:58,437][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.920806884765625, cross_entropy: 2.920806884765625 +[2025-04-28 03:43:00,998][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.9338252544403076, cross_entropy: 2.9338252544403076 +[2025-04-28 03:43:01,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 2.0683796405792236, cross_entropy: 2.0683796405792236 +[2025-04-28 03:43:03,392][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.1563003063201904, cross_entropy: 2.1563003063201904 +[2025-04-28 03:43:03,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 1.967679738998413, cross_entropy: 1.967679738998413 +[2025-04-28 03:43:05,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 1.883540153503418, cross_entropy: 1.883540153503418 +[2025-04-28 03:43:06,055][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.1542129516601562, cross_entropy: 2.1542129516601562 +[2025-04-28 03:43:07,883][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.5446527004241943, cross_entropy: 2.5446527004241943 +[2025-04-28 03:43:08,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.461456537246704, cross_entropy: 3.461456537246704 +[2025-04-28 03:43:10,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 2.3313217163085938, cross_entropy: 2.3313217163085938 +[2025-04-28 03:43:10,852][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 2.858536720275879, cross_entropy: 2.858536720275879 +[2025-04-28 03:43:12,813][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.4556922912597656, cross_entropy: 3.4556922912597656 +[2025-04-28 03:43:13,167][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 1.8160181045532227, cross_entropy: 1.8160181045532227 +[2025-04-28 03:43:16,071][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 3.6919522285461426, cross_entropy: 3.6919522285461426 +[2025-04-28 03:43:16,340][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.39074444770813, cross_entropy: 3.39074444770813 +[2025-04-28 03:43:18,692][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 3.5406737327575684, cross_entropy: 3.5406737327575684 +[2025-04-28 03:43:18,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.0995254516601562, cross_entropy: 2.0995254516601562 +[2025-04-28 03:43:21,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.542250633239746, cross_entropy: 2.542250633239746 +[2025-04-28 03:43:21,424][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 3.20233154296875, cross_entropy: 3.20233154296875 +[2025-04-28 03:43:23,817][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 2.0524702072143555, cross_entropy: 2.0524702072143555 +[2025-04-28 03:43:24,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 2.3255693912506104, cross_entropy: 2.3255693912506104 +[2025-04-28 03:43:26,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.4513206481933594, cross_entropy: 3.4513206481933594 +[2025-04-28 03:43:26,944][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 3.375606060028076, cross_entropy: 3.375606060028076 +[2025-04-28 03:43:29,397][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 1.9866273403167725, cross_entropy: 1.9866273403167725 +[2025-04-28 03:43:29,679][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.394935131072998, cross_entropy: 2.394935131072998 +[2025-04-28 03:43:31,680][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 2.9113426208496094, cross_entropy: 2.9113426208496094 +[2025-04-28 03:43:31,962][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 2.0583410263061523, cross_entropy: 2.0583410263061523 +[2025-04-28 03:43:34,306][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.6030526161193848, cross_entropy: 3.6030526161193848 +[2025-04-28 03:43:34,574][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 2.1775612831115723, cross_entropy: 2.1775612831115723 +[2025-04-28 03:43:37,172][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 2.5601861476898193, cross_entropy: 2.5601861476898193 +[2025-04-28 03:43:37,440][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 2.6640353202819824, cross_entropy: 2.6640353202819824 +[2025-04-28 03:43:40,320][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 2.885930061340332, cross_entropy: 2.885930061340332 +[2025-04-28 03:43:40,589][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 2.6193089485168457, cross_entropy: 2.6193089485168457 +[2025-04-28 03:43:42,639][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 3.1465072631835938, cross_entropy: 3.1465072631835938 +[2025-04-28 03:43:42,921][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.6662464141845703, cross_entropy: 3.6662464141845703 +[2025-04-28 03:43:45,456][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 3.7891509532928467, cross_entropy: 3.7891509532928467 +[2025-04-28 03:43:45,734][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.3867433071136475, cross_entropy: 2.3867433071136475 +[2025-04-28 03:43:47,956][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 3.6673331260681152, cross_entropy: 3.6673331260681152 +[2025-04-28 03:43:48,236][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 3.192446231842041, cross_entropy: 3.192446231842041 +[2025-04-28 03:43:50,844][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.5282039642333984, cross_entropy: 2.5282039642333984 +[2025-04-28 03:43:51,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.087714672088623, cross_entropy: 3.087714672088623 +[2025-04-28 03:43:53,465][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 3.081477642059326, cross_entropy: 3.081477642059326 +[2025-04-28 03:43:53,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.3287696838378906, cross_entropy: 2.3287696838378906 +[2025-04-28 03:43:56,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.8996057510375977, cross_entropy: 2.8996057510375977 +[2025-04-28 03:43:56,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.1429200172424316, cross_entropy: 2.1429200172424316 +[2025-04-28 03:43:58,198][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 3.759121894836426, cross_entropy: 3.759121894836426 +[2025-04-28 03:43:58,479][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 3.1431753635406494, cross_entropy: 3.1431753635406494 +[2025-04-28 03:44:00,556][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 2.1670913696289062, cross_entropy: 2.1670913696289062 +[2025-04-28 03:44:00,836][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 3.972064971923828, cross_entropy: 3.972064971923828 +[2025-04-28 03:44:02,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 2.450312852859497, cross_entropy: 2.450312852859497 +[2025-04-28 03:44:03,045][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 2.0865578651428223, cross_entropy: 2.0865578651428223 +[2025-04-28 03:44:05,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.2375617027282715, cross_entropy: 2.2375617027282715 +[2025-04-28 03:44:05,940][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.664623260498047, cross_entropy: 3.664623260498047 +[2025-04-28 03:44:07,845][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 2.2196624279022217, cross_entropy: 2.2196624279022217 +[2025-04-28 03:44:08,113][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.428952693939209, cross_entropy: 3.428952693939209 +[2025-04-28 03:44:10,651][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 2.314056873321533, cross_entropy: 2.314056873321533 +[2025-04-28 03:44:10,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 3.348111152648926, cross_entropy: 3.348111152648926 +[2025-04-28 03:44:13,080][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 2.0806448459625244, cross_entropy: 2.0806448459625244 +[2025-04-28 03:44:13,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 2.948822021484375, cross_entropy: 2.948822021484375 +[2025-04-28 03:44:15,853][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.5262084007263184, cross_entropy: 2.5262084007263184 +[2025-04-28 03:44:16,135][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 1.983621597290039, cross_entropy: 1.983621597290039 +[2025-04-28 03:44:18,149][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.5285372734069824, cross_entropy: 2.5285372734069824 +[2025-04-28 03:44:18,424][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.1466641426086426, cross_entropy: 3.1466641426086426 +[2025-04-28 03:44:20,967][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 2.9134361743927, cross_entropy: 2.9134361743927 +[2025-04-28 03:44:21,249][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 3.576897621154785, cross_entropy: 3.576897621154785 +[2025-04-28 03:44:24,028][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.7538704872131348, cross_entropy: 3.7538704872131348 +[2025-04-28 03:44:24,729][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 2.4892096519470215, cross_entropy: 2.4892096519470215 +[2025-04-28 03:44:26,155][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.358546733856201, cross_entropy: 3.358546733856201 +[2025-04-28 03:44:27,174][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 2.3585994243621826, cross_entropy: 2.3585994243621826 +[2025-04-28 03:44:29,161][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 2.5168604850769043, cross_entropy: 2.5168604850769043 +[2025-04-28 03:44:30,159][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.2980403900146484, cross_entropy: 2.2980403900146484 +[2025-04-28 03:44:31,718][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.6973302364349365, cross_entropy: 2.6973302364349365 +[2025-04-28 03:44:32,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.4582347869873047, cross_entropy: 2.4582347869873047 +[2025-04-28 03:44:34,402][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 3.867600440979004, cross_entropy: 3.867600440979004 +[2025-04-28 03:44:34,927][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 2.863182544708252, cross_entropy: 2.863182544708252 +[2025-04-28 03:44:37,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.094182014465332, cross_entropy: 3.094182014465332 +[2025-04-28 03:44:38,332][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 2.0662083625793457, cross_entropy: 2.0662083625793457 +[2025-04-28 03:44:40,125][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 2.5787198543548584, cross_entropy: 2.5787198543548584 +[2025-04-28 03:46:40,639][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.8286972045898438, cross_entropy: 2.8286972045898438 +[2025-04-28 03:46:40,640][BaseTrainer][INFO] - [Epoch 2/10] (validation) 2.059156656265259, cross_entropy: 2.059156656265259 +[2025-04-28 03:46:40,869][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 03:46:41,043][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch2.pth. +[2025-04-28 03:46:41,243][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 03:46:45,060][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 3.3423256874084473, cross_entropy: 3.3423256874084473 +[2025-04-28 03:46:45,343][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.6981934309005737, cross_entropy: 1.6981934309005737 +[2025-04-28 03:46:48,197][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 2.0916013717651367, cross_entropy: 2.0916013717651367 +[2025-04-28 03:46:48,481][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 2.9683399200439453, cross_entropy: 2.9683399200439453 +[2025-04-28 03:46:51,254][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 2.1922247409820557, cross_entropy: 2.1922247409820557 +[2025-04-28 03:46:51,535][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.704850196838379, cross_entropy: 2.704850196838379 +[2025-04-28 03:46:53,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.9033758640289307, cross_entropy: 1.9033758640289307 +[2025-04-28 03:46:53,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 2.637251853942871, cross_entropy: 2.637251853942871 +[2025-04-28 03:46:56,277][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.828174114227295, cross_entropy: 1.828174114227295 +[2025-04-28 03:46:56,556][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 2.5293216705322266, cross_entropy: 2.5293216705322266 +[2025-04-28 03:46:58,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.7093119621276855, cross_entropy: 2.7093119621276855 +[2025-04-28 03:46:58,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 2.4610939025878906, cross_entropy: 2.4610939025878906 +[2025-04-28 03:47:00,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.932085394859314, cross_entropy: 1.932085394859314 +[2025-04-28 03:47:00,871][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.61505126953125, cross_entropy: 2.61505126953125 +[2025-04-28 03:47:02,629][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.1636667251586914, cross_entropy: 2.1636667251586914 +[2025-04-28 03:47:02,912][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 2.405923843383789, cross_entropy: 2.405923843383789 +[2025-04-28 03:47:05,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.7849514484405518, cross_entropy: 3.7849514484405518 +[2025-04-28 03:47:05,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.426119327545166, cross_entropy: 2.426119327545166 +[2025-04-28 03:47:07,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.5264650583267212, cross_entropy: 1.5264650583267212 +[2025-04-28 03:47:07,879][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 2.11808705329895, cross_entropy: 2.11808705329895 +[2025-04-28 03:47:10,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 3.4933996200561523, cross_entropy: 3.4933996200561523 +[2025-04-28 03:47:10,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.6759579181671143, cross_entropy: 1.6759579181671143 +[2025-04-28 03:47:12,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.6119091510772705, cross_entropy: 3.6119091510772705 +[2025-04-28 03:47:12,927][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 3.0743672847747803, cross_entropy: 3.0743672847747803 +[2025-04-28 03:47:15,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.376542568206787, cross_entropy: 3.376542568206787 +[2025-04-28 03:47:15,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 3.8110716342926025, cross_entropy: 3.8110716342926025 +[2025-04-28 03:47:17,820][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 2.122288465499878, cross_entropy: 2.122288465499878 +[2025-04-28 03:47:19,449][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.135667085647583, cross_entropy: 2.135667085647583 +[2025-04-28 03:47:20,198][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.354403257369995, cross_entropy: 3.354403257369995 +[2025-04-28 03:47:21,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.1231133937835693, cross_entropy: 2.1231133937835693 +[2025-04-28 03:47:22,866][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 2.2082550525665283, cross_entropy: 2.2082550525665283 +[2025-04-28 03:47:23,722][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 2.706300973892212, cross_entropy: 2.706300973892212 +[2025-04-28 03:47:24,800][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.2770626544952393, cross_entropy: 3.2770626544952393 +[2025-04-28 03:47:26,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 3.567523956298828, cross_entropy: 3.567523956298828 +[2025-04-28 03:47:27,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 3.501535415649414, cross_entropy: 3.501535415649414 +[2025-04-28 03:47:28,541][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.384235382080078, cross_entropy: 3.384235382080078 +[2025-04-28 03:47:29,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.1582186222076416, cross_entropy: 2.1582186222076416 +[2025-04-28 03:47:31,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.833815336227417, cross_entropy: 1.833815336227417 +[2025-04-28 03:47:32,585][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 1.8027782440185547, cross_entropy: 1.8027782440185547 +[2025-04-28 03:47:33,627][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 3.425868511199951, cross_entropy: 3.425868511199951 +[2025-04-28 03:47:35,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 2.0776476860046387, cross_entropy: 2.0776476860046387 +[2025-04-28 03:47:36,125][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 3.5129079818725586, cross_entropy: 3.5129079818725586 +[2025-04-28 03:47:37,300][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 1.9538488388061523, cross_entropy: 1.9538488388061523 +[2025-04-28 03:47:38,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.3448891639709473, cross_entropy: 2.3448891639709473 +[2025-04-28 03:47:40,480][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 3.1326065063476562, cross_entropy: 3.1326065063476562 +[2025-04-28 03:47:41,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 1.8579299449920654, cross_entropy: 1.8579299449920654 +[2025-04-28 03:47:42,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.8241490125656128, cross_entropy: 1.8241490125656128 +[2025-04-28 03:47:44,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.854228973388672, cross_entropy: 2.854228973388672 +[2025-04-28 03:47:45,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 3.067523241043091, cross_entropy: 3.067523241043091 +[2025-04-28 03:47:47,402][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 1.8750364780426025, cross_entropy: 1.8750364780426025 +[2025-04-28 03:47:47,938][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.089418888092041, cross_entropy: 2.089418888092041 +[2025-04-28 03:47:49,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 2.258251905441284, cross_entropy: 2.258251905441284 +[2025-04-28 03:47:50,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.983614444732666, cross_entropy: 2.983614444732666 +[2025-04-28 03:47:52,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 2.285121202468872, cross_entropy: 2.285121202468872 +[2025-04-28 03:47:54,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.3308005332946777, cross_entropy: 3.3308005332946777 +[2025-04-28 03:47:55,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.621890068054199, cross_entropy: 2.621890068054199 +[2025-04-28 03:47:57,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.4934678077697754, cross_entropy: 3.4934678077697754 +[2025-04-28 03:47:58,094][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 1.831192970275879, cross_entropy: 1.831192970275879 +[2025-04-28 03:47:59,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.4489474296569824, cross_entropy: 3.4489474296569824 +[2025-04-28 03:48:00,900][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 2.2033450603485107, cross_entropy: 2.2033450603485107 +[2025-04-28 03:48:01,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.663989543914795, cross_entropy: 2.663989543914795 +[2025-04-28 03:48:03,236][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 3.6334075927734375, cross_entropy: 3.6334075927734375 +[2025-04-28 03:48:04,314][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.351125478744507, cross_entropy: 3.351125478744507 +[2025-04-28 03:48:06,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 1.9029834270477295, cross_entropy: 1.9029834270477295 +[2025-04-28 03:48:06,832][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.8478846549987793, cross_entropy: 3.8478846549987793 +[2025-04-28 03:48:09,602][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 3.188918113708496, cross_entropy: 3.188918113708496 +[2025-04-28 03:48:09,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.9588234424591064, cross_entropy: 1.9588234424591064 +[2025-04-28 03:48:12,071][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 2.5746965408325195, cross_entropy: 2.5746965408325195 +[2025-04-28 03:48:12,351][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.4634900093078613, cross_entropy: 2.4634900093078613 +[2025-04-28 03:48:14,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 3.37164306640625, cross_entropy: 3.37164306640625 +[2025-04-28 03:48:14,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.7916107177734375, cross_entropy: 2.7916107177734375 +[2025-04-28 03:48:17,136][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.159633159637451, cross_entropy: 2.159633159637451 +[2025-04-28 03:48:17,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 2.3465394973754883, cross_entropy: 2.3465394973754883 +[2025-04-28 03:48:20,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 3.2741832733154297, cross_entropy: 3.2741832733154297 +[2025-04-28 03:48:20,593][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.5125837326049805, cross_entropy: 3.5125837326049805 +[2025-04-28 03:48:23,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 2.0198187828063965, cross_entropy: 2.0198187828063965 +[2025-04-28 03:48:23,593][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 2.750227928161621, cross_entropy: 2.750227928161621 +[2025-04-28 03:48:26,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 2.1443920135498047, cross_entropy: 2.1443920135498047 +[2025-04-28 03:48:26,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 2.9780845642089844, cross_entropy: 2.9780845642089844 +[2025-04-28 03:48:28,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 2.98909854888916, cross_entropy: 2.98909854888916 +[2025-04-28 03:48:28,613][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.2940735816955566, cross_entropy: 3.2940735816955566 +[2025-04-28 03:48:30,814][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.8357186317443848, cross_entropy: 1.8357186317443848 +[2025-04-28 03:48:31,083][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.2631633281707764, cross_entropy: 3.2631633281707764 +[2025-04-28 03:48:33,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 2.300532102584839, cross_entropy: 2.300532102584839 +[2025-04-28 03:48:33,555][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 2.4214389324188232, cross_entropy: 2.4214389324188232 +[2025-04-28 03:48:35,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.400650978088379, cross_entropy: 2.400650978088379 +[2025-04-28 03:48:35,888][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 2.4826316833496094, cross_entropy: 2.4826316833496094 +[2025-04-28 03:48:38,078][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.3408126831054688, cross_entropy: 3.3408126831054688 +[2025-04-28 03:48:38,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.400019645690918, cross_entropy: 3.400019645690918 +[2025-04-28 03:48:40,923][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 3.0831260681152344, cross_entropy: 3.0831260681152344 +[2025-04-28 03:48:41,192][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 3.245065689086914, cross_entropy: 3.245065689086914 +[2025-04-28 03:48:43,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 2.532601833343506, cross_entropy: 2.532601833343506 +[2025-04-28 03:48:43,633][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.799039363861084, cross_entropy: 1.799039363861084 +[2025-04-28 03:48:45,690][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 1.8847894668579102, cross_entropy: 1.8847894668579102 +[2025-04-28 03:48:45,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.4157865047454834, cross_entropy: 3.4157865047454834 +[2025-04-28 03:48:48,601][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.7061758041381836, cross_entropy: 1.7061758041381836 +[2025-04-28 03:48:48,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.668593406677246, cross_entropy: 3.668593406677246 +[2025-04-28 03:48:50,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.6640477180480957, cross_entropy: 2.6640477180480957 +[2025-04-28 03:48:51,232][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.472496509552002, cross_entropy: 2.472496509552002 +[2025-04-28 03:48:53,560][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 3.6481447219848633, cross_entropy: 3.6481447219848633 +[2025-04-28 03:48:53,828][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.3838868141174316, cross_entropy: 2.3838868141174316 +[2025-04-28 03:48:55,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 3.9753522872924805, cross_entropy: 3.9753522872924805 +[2025-04-28 03:48:55,945][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.7837252616882324, cross_entropy: 2.7837252616882324 +[2025-04-28 03:48:58,293][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 2.8677730560302734, cross_entropy: 2.8677730560302734 +[2025-04-28 03:48:58,577][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 2.288790702819824, cross_entropy: 2.288790702819824 +[2025-04-28 03:49:00,770][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 3.1218137741088867, cross_entropy: 3.1218137741088867 +[2025-04-28 03:49:01,053][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.1813440322875977, cross_entropy: 2.1813440322875977 +[2025-04-28 03:49:03,158][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 3.515821933746338, cross_entropy: 3.515821933746338 +[2025-04-28 03:49:03,444][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 2.5791373252868652, cross_entropy: 2.5791373252868652 +[2025-04-28 03:49:05,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.661332368850708, cross_entropy: 2.661332368850708 +[2025-04-28 03:49:05,811][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.4774012565612793, cross_entropy: 2.4774012565612793 +[2025-04-28 03:49:08,411][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 2.226454257965088, cross_entropy: 2.226454257965088 +[2025-04-28 03:49:08,690][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 2.326687812805176, cross_entropy: 2.326687812805176 +[2025-04-28 03:49:11,398][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 1.7762994766235352, cross_entropy: 1.7762994766235352 +[2025-04-28 03:49:11,679][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 3.048457145690918, cross_entropy: 3.048457145690918 +[2025-04-28 03:49:13,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.6018624305725098, cross_entropy: 1.6018624305725098 +[2025-04-28 03:49:13,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.522268295288086, cross_entropy: 2.522268295288086 +[2025-04-28 03:49:15,381][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 3.649534225463867, cross_entropy: 3.649534225463867 +[2025-04-28 03:49:15,661][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.5344698429107666, cross_entropy: 3.5344698429107666 +[2025-04-28 03:49:17,996][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.7356374263763428, cross_entropy: 2.7356374263763428 +[2025-04-28 03:49:18,278][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 1.7844088077545166, cross_entropy: 1.7844088077545166 +[2025-04-28 03:49:20,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 2.8696811199188232, cross_entropy: 2.8696811199188232 +[2025-04-28 03:49:21,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.468518018722534, cross_entropy: 2.468518018722534 +[2025-04-28 03:49:23,629][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 3.2124099731445312, cross_entropy: 3.2124099731445312 +[2025-04-28 03:49:23,910][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.3493385314941406, cross_entropy: 3.3493385314941406 +[2025-04-28 03:49:26,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.0968070030212402, cross_entropy: 2.0968070030212402 +[2025-04-28 03:49:26,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.6770834922790527, cross_entropy: 1.6770834922790527 +[2025-04-28 03:49:28,683][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 3.72796368598938, cross_entropy: 3.72796368598938 +[2025-04-28 03:49:28,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.111391067504883, cross_entropy: 3.111391067504883 +[2025-04-28 03:49:31,329][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.2211060523986816, cross_entropy: 2.2211060523986816 +[2025-04-28 03:49:31,598][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.218712329864502, cross_entropy: 2.218712329864502 +[2025-04-28 03:49:33,794][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 3.3162050247192383, cross_entropy: 3.3162050247192383 +[2025-04-28 03:49:34,076][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.70035982131958, cross_entropy: 2.70035982131958 +[2025-04-28 03:49:36,094][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.2497990131378174, cross_entropy: 2.2497990131378174 +[2025-04-28 03:49:36,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.2966742515563965, cross_entropy: 2.2966742515563965 +[2025-04-28 03:49:38,359][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.9535117149353027, cross_entropy: 1.9535117149353027 +[2025-04-28 03:49:38,638][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.661391258239746, cross_entropy: 2.661391258239746 +[2025-04-28 03:49:41,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 2.1761810779571533, cross_entropy: 2.1761810779571533 +[2025-04-28 03:49:41,333][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.9194583892822266, cross_entropy: 2.9194583892822266 +[2025-04-28 03:49:43,725][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 2.9943337440490723, cross_entropy: 2.9943337440490723 +[2025-04-28 03:49:44,035][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.34258770942688, cross_entropy: 2.34258770942688 +[2025-04-28 03:49:46,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.576112985610962, cross_entropy: 1.576112985610962 +[2025-04-28 03:49:46,632][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.7124624252319336, cross_entropy: 2.7124624252319336 +[2025-04-28 03:49:48,989][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 1.6185190677642822, cross_entropy: 1.6185190677642822 +[2025-04-28 03:49:49,273][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.421640634536743, cross_entropy: 2.421640634536743 +[2025-04-28 03:49:51,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.0363545417785645, cross_entropy: 2.0363545417785645 +[2025-04-28 03:49:51,819][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.3388898372650146, cross_entropy: 1.3388898372650146 +[2025-04-28 03:49:54,409][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.415911912918091, cross_entropy: 3.415911912918091 +[2025-04-28 03:49:54,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 1.6496624946594238, cross_entropy: 1.6496624946594238 +[2025-04-28 03:49:57,481][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 2.671428918838501, cross_entropy: 2.671428918838501 +[2025-04-28 03:49:57,762][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.9196903705596924, cross_entropy: 1.9196903705596924 +[2025-04-28 03:49:59,804][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.8368654251098633, cross_entropy: 2.8368654251098633 +[2025-04-28 03:50:00,086][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.2009544372558594, cross_entropy: 2.2009544372558594 +[2025-04-28 03:50:02,252][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 1.8495550155639648, cross_entropy: 1.8495550155639648 +[2025-04-28 03:50:02,534][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.689180374145508, cross_entropy: 2.689180374145508 +[2025-04-28 03:50:04,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 3.122640609741211, cross_entropy: 3.122640609741211 +[2025-04-28 03:50:05,214][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 2.0689024925231934, cross_entropy: 2.0689024925231934 +[2025-04-28 03:50:07,105][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 3.5339696407318115, cross_entropy: 3.5339696407318115 +[2025-04-28 03:50:07,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 2.25323224067688, cross_entropy: 2.25323224067688 +[2025-04-28 03:50:09,552][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 2.074357271194458, cross_entropy: 2.074357271194458 +[2025-04-28 03:50:11,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.406440258026123, cross_entropy: 3.406440258026123 +[2025-04-28 03:50:12,088][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 2.395033359527588, cross_entropy: 2.395033359527588 +[2025-04-28 03:50:13,661][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.599782943725586, cross_entropy: 3.599782943725586 +[2025-04-28 03:50:14,722][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 3.101426124572754, cross_entropy: 3.101426124572754 +[2025-04-28 03:50:15,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 3.120861291885376, cross_entropy: 3.120861291885376 +[2025-04-28 03:50:17,579][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.7887290716171265, cross_entropy: 1.7887290716171265 +[2025-04-28 03:50:18,423][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 1.8475086688995361, cross_entropy: 1.8475086688995361 +[2025-04-28 03:50:20,465][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 2.532869815826416, cross_entropy: 2.532869815826416 +[2025-04-28 03:50:20,778][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.7763590812683105, cross_entropy: 1.7763590812683105 +[2025-04-28 03:50:22,975][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.1283254623413086, cross_entropy: 3.1283254623413086 +[2025-04-28 03:50:23,299][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 2.1533002853393555, cross_entropy: 2.1533002853393555 +[2025-04-28 03:50:25,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.75779390335083, cross_entropy: 2.75779390335083 +[2025-04-28 03:50:26,042][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.1419448852539062, cross_entropy: 3.1419448852539062 +[2025-04-28 03:50:27,968][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.717747211456299, cross_entropy: 2.717747211456299 +[2025-04-28 03:50:28,853][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.479745388031006, cross_entropy: 2.479745388031006 +[2025-04-28 03:50:30,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.5889487266540527, cross_entropy: 2.5889487266540527 +[2025-04-28 03:50:31,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.462416172027588, cross_entropy: 2.462416172027588 +[2025-04-28 03:50:33,657][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 1.8589732646942139, cross_entropy: 1.8589732646942139 +[2025-04-28 03:50:33,942][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.9150080680847168, cross_entropy: 1.9150080680847168 +[2025-04-28 03:50:35,475][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 3.0317840576171875, cross_entropy: 3.0317840576171875 +[2025-04-28 03:50:36,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.871390700340271, cross_entropy: 1.871390700340271 +[2025-04-28 03:50:37,936][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.5572385787963867, cross_entropy: 2.5572385787963867 +[2025-04-28 03:50:39,198][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.487240791320801, cross_entropy: 2.487240791320801 +[2025-04-28 03:50:40,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.001166343688965, cross_entropy: 2.001166343688965 +[2025-04-28 03:50:41,895][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 3.026566505432129, cross_entropy: 3.026566505432129 +[2025-04-28 03:50:42,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 1.9993959665298462, cross_entropy: 1.9993959665298462 +[2025-04-28 03:50:44,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.4584836959838867, cross_entropy: 2.4584836959838867 +[2025-04-28 03:50:45,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 3.736370086669922, cross_entropy: 3.736370086669922 +[2025-04-28 03:50:47,003][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.1474390029907227, cross_entropy: 3.1474390029907227 +[2025-04-28 03:50:47,919][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.2165169715881348, cross_entropy: 3.2165169715881348 +[2025-04-28 03:50:49,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.605527877807617, cross_entropy: 2.605527877807617 +[2025-04-28 03:50:50,590][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 3.2674686908721924, cross_entropy: 3.2674686908721924 +[2025-04-28 03:50:51,746][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.9108762741088867, cross_entropy: 2.9108762741088867 +[2025-04-28 03:50:52,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 3.1938796043395996, cross_entropy: 3.1938796043395996 +[2025-04-28 03:50:53,828][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 3.22724986076355, cross_entropy: 3.22724986076355 +[2025-04-28 03:50:55,135][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 3.492558002471924, cross_entropy: 3.492558002471924 +[2025-04-28 03:50:56,485][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 2.1501262187957764, cross_entropy: 2.1501262187957764 +[2025-04-28 03:50:57,923][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 3.630215644836426, cross_entropy: 3.630215644836426 +[2025-04-28 03:50:59,231][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.9556702375411987, cross_entropy: 1.9556702375411987 +[2025-04-28 03:51:00,507][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 3.557042121887207, cross_entropy: 3.557042121887207 +[2025-04-28 03:51:02,158][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.193424701690674, cross_entropy: 2.193424701690674 +[2025-04-28 03:51:03,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 1.9876452684402466, cross_entropy: 1.9876452684402466 +[2025-04-28 03:51:05,133][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.4512834548950195, cross_entropy: 3.4512834548950195 +[2025-04-28 03:51:06,314][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.179128885269165, cross_entropy: 2.179128885269165 +[2025-04-28 03:51:07,524][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.451129198074341, cross_entropy: 3.451129198074341 +[2025-04-28 03:51:09,266][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 2.61039662361145, cross_entropy: 2.61039662361145 +[2025-04-28 03:51:10,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.709202289581299, cross_entropy: 2.709202289581299 +[2025-04-28 03:51:11,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.844989538192749, cross_entropy: 2.844989538192749 +[2025-04-28 03:51:12,285][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.2399535179138184, cross_entropy: 2.2399535179138184 +[2025-04-28 03:51:13,445][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 1.9571993350982666, cross_entropy: 1.9571993350982666 +[2025-04-28 03:51:14,987][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 2.881186008453369, cross_entropy: 2.881186008453369 +[2025-04-28 03:51:15,890][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 3.109125852584839, cross_entropy: 3.109125852584839 +[2025-04-28 03:51:17,594][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 2.1473889350891113, cross_entropy: 2.1473889350891113 +[2025-04-28 03:51:18,657][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.0347681045532227, cross_entropy: 2.0347681045532227 +[2025-04-28 03:51:19,855][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.8261241912841797, cross_entropy: 1.8261241912841797 +[2025-04-28 03:51:20,985][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 3.829160451889038, cross_entropy: 3.829160451889038 +[2025-04-28 03:51:22,285][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.4532418251037598, cross_entropy: 2.4532418251037598 +[2025-04-28 03:51:23,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.409797430038452, cross_entropy: 3.409797430038452 +[2025-04-28 03:51:24,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.9125378131866455, cross_entropy: 2.9125378131866455 +[2025-04-28 03:51:25,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 1.8113954067230225, cross_entropy: 1.8113954067230225 +[2025-04-28 03:51:27,123][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 2.1135098934173584, cross_entropy: 2.1135098934173584 +[2025-04-28 03:51:28,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 3.2720088958740234, cross_entropy: 3.2720088958740234 +[2025-04-28 03:51:29,244][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.3278656005859375, cross_entropy: 3.3278656005859375 +[2025-04-28 03:51:30,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.206791400909424, cross_entropy: 3.206791400909424 +[2025-04-28 03:51:32,335][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.486624240875244, cross_entropy: 3.486624240875244 +[2025-04-28 03:51:33,938][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 3.4604244232177734, cross_entropy: 3.4604244232177734 +[2025-04-28 03:51:35,338][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.4863476753234863, cross_entropy: 1.4863476753234863 +[2025-04-28 03:51:36,107][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 2.9148998260498047, cross_entropy: 2.9148998260498047 +[2025-04-28 03:51:37,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 2.143092632293701, cross_entropy: 2.143092632293701 +[2025-04-28 03:51:38,653][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.3993916511535645, cross_entropy: 3.3993916511535645 +[2025-04-28 03:51:40,690][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.5655250549316406, cross_entropy: 2.5655250549316406 +[2025-04-28 03:51:41,085][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.3439512252807617, cross_entropy: 3.3439512252807617 +[2025-04-28 03:51:44,429][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 2.1738240718841553, cross_entropy: 2.1738240718841553 +[2025-04-28 03:51:44,709][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 3.2839157581329346, cross_entropy: 3.2839157581329346 +[2025-04-28 03:51:47,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.35894775390625, cross_entropy: 3.35894775390625 +[2025-04-28 03:51:48,034][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.2878332138061523, cross_entropy: 2.2878332138061523 +[2025-04-28 03:51:49,875][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.3137078285217285, cross_entropy: 3.3137078285217285 +[2025-04-28 03:51:50,143][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 3.346893787384033, cross_entropy: 3.346893787384033 +[2025-04-28 03:51:52,171][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.7789947986602783, cross_entropy: 2.7789947986602783 +[2025-04-28 03:51:52,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 1.5968824625015259, cross_entropy: 1.5968824625015259 +[2025-04-28 03:51:54,408][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 3.1081106662750244, cross_entropy: 3.1081106662750244 +[2025-04-28 03:51:54,714][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 3.433553695678711, cross_entropy: 3.433553695678711 +[2025-04-28 03:51:56,641][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 3.5467474460601807, cross_entropy: 3.5467474460601807 +[2025-04-28 03:51:56,923][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 3.3882198333740234, cross_entropy: 3.3882198333740234 +[2025-04-28 03:51:59,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.5228863954544067, cross_entropy: 1.5228863954544067 +[2025-04-28 03:51:59,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.299123764038086, cross_entropy: 2.299123764038086 +[2025-04-28 03:52:01,686][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.4520974159240723, cross_entropy: 3.4520974159240723 +[2025-04-28 03:52:02,433][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 2.451322078704834, cross_entropy: 2.451322078704834 +[2025-04-28 03:52:03,797][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 3.042020797729492, cross_entropy: 3.042020797729492 +[2025-04-28 03:52:05,376][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 1.8735696077346802, cross_entropy: 1.8735696077346802 +[2025-04-28 03:52:06,915][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.545642137527466, cross_entropy: 2.545642137527466 +[2025-04-28 03:52:07,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 2.5790958404541016, cross_entropy: 2.5790958404541016 +[2025-04-28 03:52:09,651][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 2.2448959350585938, cross_entropy: 2.2448959350585938 +[2025-04-28 03:52:10,911][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 2.133627414703369, cross_entropy: 2.133627414703369 +[2025-04-28 03:52:11,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.470261335372925, cross_entropy: 3.470261335372925 +[2025-04-28 03:52:13,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 3.8081626892089844, cross_entropy: 3.8081626892089844 +[2025-04-28 03:52:13,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.3995733261108398, cross_entropy: 1.3995733261108398 +[2025-04-28 03:52:15,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 1.9197759628295898, cross_entropy: 1.9197759628295898 +[2025-04-28 03:52:17,416][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.698773980140686, cross_entropy: 1.698773980140686 +[2025-04-28 03:52:17,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 1.852067232131958, cross_entropy: 1.852067232131958 +[2025-04-28 03:52:19,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 2.552724599838257, cross_entropy: 2.552724599838257 +[2025-04-28 03:52:20,551][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 3.4556190967559814, cross_entropy: 3.4556190967559814 +[2025-04-28 03:52:22,182][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 2.868589401245117, cross_entropy: 2.868589401245117 +[2025-04-28 03:52:23,464][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.846774697303772, cross_entropy: 1.846774697303772 +[2025-04-28 03:52:24,796][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.399270534515381, cross_entropy: 3.399270534515381 +[2025-04-28 03:52:26,116][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 3.1962997913360596, cross_entropy: 3.1962997913360596 +[2025-04-28 03:52:27,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.504228115081787, cross_entropy: 3.504228115081787 +[2025-04-28 03:52:29,183][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 2.3209762573242188, cross_entropy: 2.3209762573242188 +[2025-04-28 03:52:30,685][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.24920654296875, cross_entropy: 3.24920654296875 +[2025-04-28 03:52:31,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 3.1944479942321777, cross_entropy: 3.1944479942321777 +[2025-04-28 03:52:33,138][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.3639791011810303, cross_entropy: 3.3639791011810303 +[2025-04-28 03:52:33,566][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 3.271367311477661, cross_entropy: 3.271367311477661 +[2025-04-28 03:52:35,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.6750330924987793, cross_entropy: 3.6750330924987793 +[2025-04-28 03:52:36,679][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.177321195602417, cross_entropy: 2.177321195602417 +[2025-04-28 03:52:38,194][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 2.9941067695617676, cross_entropy: 2.9941067695617676 +[2025-04-28 03:52:39,680][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 1.979514479637146, cross_entropy: 1.979514479637146 +[2025-04-28 03:52:40,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 2.7214407920837402, cross_entropy: 2.7214407920837402 +[2025-04-28 03:52:41,982][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 2.6544365882873535, cross_entropy: 2.6544365882873535 +[2025-04-28 03:52:43,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 2.595494508743286, cross_entropy: 2.595494508743286 +[2025-04-28 03:52:44,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 3.3232667446136475, cross_entropy: 3.3232667446136475 +[2025-04-28 03:52:45,552][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.714930534362793, cross_entropy: 1.714930534362793 +[2025-04-28 03:52:47,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.001722812652588, cross_entropy: 3.001722812652588 +[2025-04-28 03:52:48,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 2.2944819927215576, cross_entropy: 2.2944819927215576 +[2025-04-28 03:52:49,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 2.85030198097229, cross_entropy: 2.85030198097229 +[2025-04-28 03:52:50,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.6862828731536865, cross_entropy: 1.6862828731536865 +[2025-04-28 03:52:53,002][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 3.4105539321899414, cross_entropy: 3.4105539321899414 +[2025-04-28 03:52:53,286][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.480703115463257, cross_entropy: 2.480703115463257 +[2025-04-28 03:52:54,867][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.6485130786895752, cross_entropy: 1.6485130786895752 +[2025-04-28 03:52:55,159][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/iteration1000.pth. +[2025-04-28 03:52:55,814][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.778663158416748, cross_entropy: 2.778663158416748 +[2025-04-28 03:52:57,292][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 2.3676846027374268, cross_entropy: 2.3676846027374268 +[2025-04-28 03:52:58,129][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.3047525882720947, cross_entropy: 3.3047525882720947 +[2025-04-28 03:53:00,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.9586739540100098, cross_entropy: 1.9586739540100098 +[2025-04-28 03:53:00,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 2.2162089347839355, cross_entropy: 2.2162089347839355 +[2025-04-28 03:53:02,961][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.0323660373687744, cross_entropy: 2.0323660373687744 +[2025-04-28 03:53:03,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.047616958618164, cross_entropy: 2.047616958618164 +[2025-04-28 03:53:05,423][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.024714231491089, cross_entropy: 2.024714231491089 +[2025-04-28 03:53:06,286][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.8848695755004883, cross_entropy: 2.8848695755004883 +[2025-04-28 03:53:08,265][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 1.9677940607070923, cross_entropy: 1.9677940607070923 +[2025-04-28 03:53:09,713][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.3121347427368164, cross_entropy: 3.3121347427368164 +[2025-04-28 03:53:11,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.7751898765563965, cross_entropy: 2.7751898765563965 +[2025-04-28 03:53:13,267][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 1.8226388692855835, cross_entropy: 1.8226388692855835 +[2025-04-28 03:53:14,380][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 3.4534730911254883, cross_entropy: 3.4534730911254883 +[2025-04-28 03:53:15,611][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.9710127115249634, cross_entropy: 1.9710127115249634 +[2025-04-28 03:53:17,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.5365312099456787, cross_entropy: 3.5365312099456787 +[2025-04-28 03:53:18,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.9441466331481934, cross_entropy: 2.9441466331481934 +[2025-04-28 03:53:19,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 3.324460983276367, cross_entropy: 3.324460983276367 +[2025-04-28 03:53:20,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 1.7311748266220093, cross_entropy: 1.7311748266220093 +[2025-04-28 03:53:21,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 3.423712730407715, cross_entropy: 3.423712730407715 +[2025-04-28 03:53:22,899][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.3780508041381836, cross_entropy: 3.3780508041381836 +[2025-04-28 03:53:24,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 1.925662636756897, cross_entropy: 1.925662636756897 +[2025-04-28 03:53:25,273][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 2.298705577850342, cross_entropy: 2.298705577850342 +[2025-04-28 03:53:26,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 3.0893449783325195, cross_entropy: 3.0893449783325195 +[2025-04-28 03:53:28,098][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.8818472623825073, cross_entropy: 1.8818472623825073 +[2025-04-28 03:53:29,436][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.459800958633423, cross_entropy: 2.459800958633423 +[2025-04-28 03:53:32,117][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 3.329379081726074, cross_entropy: 3.329379081726074 +[2025-04-28 03:53:32,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.717275619506836, cross_entropy: 2.717275619506836 +[2025-04-28 03:53:34,432][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.954925060272217, cross_entropy: 2.954925060272217 +[2025-04-28 03:53:35,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 3.268465518951416, cross_entropy: 3.268465518951416 +[2025-04-28 03:53:36,389][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.654329538345337, cross_entropy: 1.654329538345337 +[2025-04-28 03:53:37,549][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.243081569671631, cross_entropy: 3.243081569671631 +[2025-04-28 03:53:38,750][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 1.873684048652649, cross_entropy: 1.873684048652649 +[2025-04-28 03:53:39,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 3.3288726806640625, cross_entropy: 3.3288726806640625 +[2025-04-28 03:53:41,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.607351541519165, cross_entropy: 1.607351541519165 +[2025-04-28 03:53:43,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 3.2962100505828857, cross_entropy: 3.2962100505828857 +[2025-04-28 03:53:44,074][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 2.831721782684326, cross_entropy: 2.831721782684326 +[2025-04-28 03:53:45,593][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 2.9660935401916504, cross_entropy: 2.9660935401916504 +[2025-04-28 03:53:47,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.726781129837036, cross_entropy: 3.726781129837036 +[2025-04-28 03:53:47,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.3259384632110596, cross_entropy: 3.3259384632110596 +[2025-04-28 03:53:49,460][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 2.2729852199554443, cross_entropy: 2.2729852199554443 +[2025-04-28 03:53:50,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 2.645305871963501, cross_entropy: 2.645305871963501 +[2025-04-28 03:53:51,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.7186174392700195, cross_entropy: 3.7186174392700195 +[2025-04-28 03:53:53,470][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.1873106956481934, cross_entropy: 2.1873106956481934 +[2025-04-28 03:53:54,079][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 3.159945011138916, cross_entropy: 3.159945011138916 +[2025-04-28 03:53:56,270][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 3.3407790660858154, cross_entropy: 3.3407790660858154 +[2025-04-28 03:53:56,587][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.6589109897613525, cross_entropy: 1.6589109897613525 +[2025-04-28 03:53:58,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.1842041015625, cross_entropy: 2.1842041015625 +[2025-04-28 03:53:59,086][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 3.3517062664031982, cross_entropy: 3.3517062664031982 +[2025-04-28 03:54:01,247][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 2.14347505569458, cross_entropy: 2.14347505569458 +[2025-04-28 03:54:01,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 3.246155023574829, cross_entropy: 3.246155023574829 +[2025-04-28 03:54:04,246][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 3.1674022674560547, cross_entropy: 3.1674022674560547 +[2025-04-28 03:54:04,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.9239544868469238, cross_entropy: 1.9239544868469238 +[2025-04-28 03:54:07,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.2845563888549805, cross_entropy: 2.2845563888549805 +[2025-04-28 03:54:07,347][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 2.1574912071228027, cross_entropy: 2.1574912071228027 +[2025-04-28 03:54:09,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.417402744293213, cross_entropy: 3.417402744293213 +[2025-04-28 03:54:09,986][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 3.4367318153381348, cross_entropy: 3.4367318153381348 +[2025-04-28 03:54:12,788][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.8301548957824707, cross_entropy: 1.8301548957824707 +[2025-04-28 03:54:13,067][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.661454439163208, cross_entropy: 1.661454439163208 +[2025-04-28 03:54:15,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 2.4391002655029297, cross_entropy: 2.4391002655029297 +[2025-04-28 03:54:15,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 2.094738245010376, cross_entropy: 2.094738245010376 +[2025-04-28 03:54:17,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 3.5330140590667725, cross_entropy: 3.5330140590667725 +[2025-04-28 03:54:17,849][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 3.2937164306640625, cross_entropy: 3.2937164306640625 +[2025-04-28 03:54:20,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.990368366241455, cross_entropy: 2.990368366241455 +[2025-04-28 03:54:20,477][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 2.861875295639038, cross_entropy: 2.861875295639038 +[2025-04-28 03:54:22,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 2.2903785705566406, cross_entropy: 2.2903785705566406 +[2025-04-28 03:54:22,592][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 3.0845999717712402, cross_entropy: 3.0845999717712402 +[2025-04-28 03:54:24,553][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.2198166847229004, cross_entropy: 2.2198166847229004 +[2025-04-28 03:56:26,348][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.66050124168396, cross_entropy: 2.66050124168396 +[2025-04-28 03:56:26,349][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.8654518127441406, cross_entropy: 1.8654518127441406 +[2025-04-28 03:56:26,560][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 03:56:26,724][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch3.pth. +[2025-04-28 03:56:26,932][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 03:56:29,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.4354478120803833, cross_entropy: 1.4354478120803833 +[2025-04-28 03:56:30,033][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 1.7534737586975098, cross_entropy: 1.7534737586975098 +[2025-04-28 03:56:32,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 2.0417675971984863, cross_entropy: 2.0417675971984863 +[2025-04-28 03:56:32,537][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.896987795829773, cross_entropy: 1.896987795829773 +[2025-04-28 03:56:34,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 2.1817467212677, cross_entropy: 2.1817467212677 +[2025-04-28 03:56:34,974][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.729276180267334, cross_entropy: 1.729276180267334 +[2025-04-28 03:56:37,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.9852595329284668, cross_entropy: 1.9852595329284668 +[2025-04-28 03:56:37,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 2.98756742477417, cross_entropy: 2.98756742477417 +[2025-04-28 03:56:39,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 2.2207255363464355, cross_entropy: 2.2207255363464355 +[2025-04-28 03:56:39,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 3.5670313835144043, cross_entropy: 3.5670313835144043 +[2025-04-28 03:56:41,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.5352511405944824, cross_entropy: 3.5352511405944824 +[2025-04-28 03:56:42,756][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.2951345443725586, cross_entropy: 2.2951345443725586 +[2025-04-28 03:56:44,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 2.035083770751953, cross_entropy: 2.035083770751953 +[2025-04-28 03:56:45,164][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 3.452671766281128, cross_entropy: 3.452671766281128 +[2025-04-28 03:56:46,210][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 1.689814805984497, cross_entropy: 1.689814805984497 +[2025-04-28 03:56:47,384][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.2759952545166016, cross_entropy: 1.2759952545166016 +[2025-04-28 03:56:48,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.8226709365844727, cross_entropy: 2.8226709365844727 +[2025-04-28 03:56:49,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 2.0338940620422363, cross_entropy: 2.0338940620422363 +[2025-04-28 03:56:52,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.5481719970703125, cross_entropy: 3.5481719970703125 +[2025-04-28 03:56:52,427][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.323446035385132, cross_entropy: 2.323446035385132 +[2025-04-28 03:56:54,932][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 1.6538634300231934, cross_entropy: 1.6538634300231934 +[2025-04-28 03:56:55,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.8108844757080078, cross_entropy: 1.8108844757080078 +[2025-04-28 03:56:57,570][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.7746455669403076, cross_entropy: 2.7746455669403076 +[2025-04-28 03:56:57,850][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 2.077518939971924, cross_entropy: 2.077518939971924 +[2025-04-28 03:57:00,294][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.6074891090393066, cross_entropy: 2.6074891090393066 +[2025-04-28 03:57:00,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.9146560430526733, cross_entropy: 1.9146560430526733 +[2025-04-28 03:57:03,673][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.652712345123291, cross_entropy: 2.652712345123291 +[2025-04-28 03:57:03,942][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 2.999016284942627, cross_entropy: 2.999016284942627 +[2025-04-28 03:57:06,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.362044334411621, cross_entropy: 2.362044334411621 +[2025-04-28 03:57:06,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 1.7279385328292847, cross_entropy: 1.7279385328292847 +[2025-04-28 03:57:08,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 2.995640277862549, cross_entropy: 2.995640277862549 +[2025-04-28 03:57:08,558][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.8503258228302002, cross_entropy: 1.8503258228302002 +[2025-04-28 03:57:10,897][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 1.7667137384414673, cross_entropy: 1.7667137384414673 +[2025-04-28 03:57:11,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.292764186859131, cross_entropy: 2.292764186859131 +[2025-04-28 03:57:13,249][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 3.0278661251068115, cross_entropy: 3.0278661251068115 +[2025-04-28 03:57:13,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 2.5602073669433594, cross_entropy: 2.5602073669433594 +[2025-04-28 03:57:15,935][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.6707427501678467, cross_entropy: 1.6707427501678467 +[2025-04-28 03:57:16,213][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 2.9164881706237793, cross_entropy: 2.9164881706237793 +[2025-04-28 03:57:18,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.6974496841430664, cross_entropy: 3.6974496841430664 +[2025-04-28 03:57:18,429][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 3.2605814933776855, cross_entropy: 3.2605814933776855 +[2025-04-28 03:57:21,417][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 1.704366683959961, cross_entropy: 1.704366683959961 +[2025-04-28 03:57:21,699][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 2.9951889514923096, cross_entropy: 2.9951889514923096 +[2025-04-28 03:57:23,963][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.2625231742858887, cross_entropy: 2.2625231742858887 +[2025-04-28 03:57:24,243][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 1.870227336883545, cross_entropy: 1.870227336883545 +[2025-04-28 03:57:26,414][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 2.9182519912719727, cross_entropy: 2.9182519912719727 +[2025-04-28 03:57:26,696][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 1.6646137237548828, cross_entropy: 1.6646137237548828 +[2025-04-28 03:57:29,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.004845380783081, cross_entropy: 2.004845380783081 +[2025-04-28 03:57:29,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.5759485960006714, cross_entropy: 1.5759485960006714 +[2025-04-28 03:57:32,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.7018312215805054, cross_entropy: 1.7018312215805054 +[2025-04-28 03:57:32,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.643099784851074, cross_entropy: 2.643099784851074 +[2025-04-28 03:57:34,674][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.6793172359466553, cross_entropy: 1.6793172359466553 +[2025-04-28 03:57:34,956][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 3.1204941272735596, cross_entropy: 3.1204941272735596 +[2025-04-28 03:57:37,426][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.0239522457122803, cross_entropy: 2.0239522457122803 +[2025-04-28 03:57:37,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.863619089126587, cross_entropy: 2.863619089126587 +[2025-04-28 03:57:39,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 3.351508140563965, cross_entropy: 3.351508140563965 +[2025-04-28 03:57:40,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.6621730327606201, cross_entropy: 1.6621730327606201 +[2025-04-28 03:57:41,938][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 1.898127555847168, cross_entropy: 1.898127555847168 +[2025-04-28 03:57:42,221][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 1.8943116664886475, cross_entropy: 1.8943116664886475 +[2025-04-28 03:57:45,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 1.8069323301315308, cross_entropy: 1.8069323301315308 +[2025-04-28 03:57:45,291][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 1.9170783758163452, cross_entropy: 1.9170783758163452 +[2025-04-28 03:57:46,967][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.9019224643707275, cross_entropy: 1.9019224643707275 +[2025-04-28 03:57:47,248][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 1.888455867767334, cross_entropy: 1.888455867767334 +[2025-04-28 03:57:49,808][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 3.098057270050049, cross_entropy: 3.098057270050049 +[2025-04-28 03:57:50,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 1.5117371082305908, cross_entropy: 1.5117371082305908 +[2025-04-28 03:57:52,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.7233870029449463, cross_entropy: 2.7233870029449463 +[2025-04-28 03:57:52,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.6701507568359375, cross_entropy: 1.6701507568359375 +[2025-04-28 03:57:55,305][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 3.129347801208496, cross_entropy: 3.129347801208496 +[2025-04-28 03:57:55,585][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.3130202293395996, cross_entropy: 3.3130202293395996 +[2025-04-28 03:57:58,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.511514186859131, cross_entropy: 2.511514186859131 +[2025-04-28 03:57:58,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 1.5849277973175049, cross_entropy: 1.5849277973175049 +[2025-04-28 03:58:01,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.7079567909240723, cross_entropy: 2.7079567909240723 +[2025-04-28 03:58:01,475][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 3.2021865844726562, cross_entropy: 3.2021865844726562 +[2025-04-28 03:58:03,688][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.6410045623779297, cross_entropy: 1.6410045623779297 +[2025-04-28 03:58:03,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 2.0457026958465576, cross_entropy: 2.0457026958465576 +[2025-04-28 03:58:05,656][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 2.5562186241149902, cross_entropy: 2.5562186241149902 +[2025-04-28 03:58:05,939][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 2.1392650604248047, cross_entropy: 2.1392650604248047 +[2025-04-28 03:58:07,769][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.7025363445281982, cross_entropy: 1.7025363445281982 +[2025-04-28 03:58:08,050][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 3.0181002616882324, cross_entropy: 3.0181002616882324 +[2025-04-28 03:58:09,716][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 3.4711360931396484, cross_entropy: 3.4711360931396484 +[2025-04-28 03:58:09,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 3.0874876976013184, cross_entropy: 3.0874876976013184 +[2025-04-28 03:58:11,822][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.2978193759918213, cross_entropy: 3.2978193759918213 +[2025-04-28 03:58:12,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 3.3073976039886475, cross_entropy: 3.3073976039886475 +[2025-04-28 03:58:14,215][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 2.5572638511657715, cross_entropy: 2.5572638511657715 +[2025-04-28 03:58:14,494][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 2.4085793495178223, cross_entropy: 2.4085793495178223 +[2025-04-28 03:58:16,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.8283436298370361, cross_entropy: 1.8283436298370361 +[2025-04-28 03:58:16,777][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 1.9184250831604004, cross_entropy: 1.9184250831604004 +[2025-04-28 03:58:19,552][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 2.9038448333740234, cross_entropy: 2.9038448333740234 +[2025-04-28 03:58:19,833][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 1.4074610471725464, cross_entropy: 1.4074610471725464 +[2025-04-28 03:58:22,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 2.0009608268737793, cross_entropy: 2.0009608268737793 +[2025-04-28 03:58:22,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 2.0151002407073975, cross_entropy: 2.0151002407073975 +[2025-04-28 03:58:24,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 1.7128479480743408, cross_entropy: 1.7128479480743408 +[2025-04-28 03:58:26,074][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 2.315730094909668, cross_entropy: 2.315730094909668 +[2025-04-28 03:58:27,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 3.4006309509277344, cross_entropy: 3.4006309509277344 +[2025-04-28 03:58:28,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.167879104614258, cross_entropy: 2.167879104614258 +[2025-04-28 03:58:30,351][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 2.885091543197632, cross_entropy: 2.885091543197632 +[2025-04-28 03:58:31,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 3.5028631687164307, cross_entropy: 3.5028631687164307 +[2025-04-28 03:58:32,685][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 3.060797929763794, cross_entropy: 3.060797929763794 +[2025-04-28 03:58:33,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.6468966007232666, cross_entropy: 1.6468966007232666 +[2025-04-28 03:58:35,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 3.392883777618408, cross_entropy: 3.392883777618408 +[2025-04-28 03:58:35,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.5977394580841064, cross_entropy: 1.5977394580841064 +[2025-04-28 03:58:37,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 3.1570425033569336, cross_entropy: 3.1570425033569336 +[2025-04-28 03:58:38,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 3.551213264465332, cross_entropy: 3.551213264465332 +[2025-04-28 03:58:40,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.60953688621521, cross_entropy: 2.60953688621521 +[2025-04-28 03:58:41,717][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 3.599915027618408, cross_entropy: 3.599915027618408 +[2025-04-28 03:58:42,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.015800952911377, cross_entropy: 2.015800952911377 +[2025-04-28 03:58:44,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.867013931274414, cross_entropy: 1.867013931274414 +[2025-04-28 03:58:45,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 1.860321283340454, cross_entropy: 1.860321283340454 +[2025-04-28 03:58:48,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 3.1878678798675537, cross_entropy: 3.1878678798675537 +[2025-04-28 03:58:48,560][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 2.874992847442627, cross_entropy: 2.874992847442627 +[2025-04-28 03:58:50,709][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 1.7668448686599731, cross_entropy: 1.7668448686599731 +[2025-04-28 03:58:50,990][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 1.5555006265640259, cross_entropy: 1.5555006265640259 +[2025-04-28 03:58:53,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 2.175001382827759, cross_entropy: 2.175001382827759 +[2025-04-28 03:58:53,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 1.8112707138061523, cross_entropy: 1.8112707138061523 +[2025-04-28 03:58:55,958][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 3.076164960861206, cross_entropy: 3.076164960861206 +[2025-04-28 03:58:56,362][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 2.8064136505126953, cross_entropy: 2.8064136505126953 +[2025-04-28 03:58:58,656][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.69932222366333, cross_entropy: 2.69932222366333 +[2025-04-28 03:58:59,014][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 1.683292269706726, cross_entropy: 1.683292269706726 +[2025-04-28 03:59:02,260][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.8729770183563232, cross_entropy: 1.8729770183563232 +[2025-04-28 03:59:02,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.7636984586715698, cross_entropy: 1.7636984586715698 +[2025-04-28 03:59:04,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.4632372856140137, cross_entropy: 2.4632372856140137 +[2025-04-28 03:59:05,198][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 2.658761501312256, cross_entropy: 2.658761501312256 +[2025-04-28 03:59:06,887][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 2.6413824558258057, cross_entropy: 2.6413824558258057 +[2025-04-28 03:59:07,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.291482448577881, cross_entropy: 2.291482448577881 +[2025-04-28 03:59:09,305][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 3.4636385440826416, cross_entropy: 3.4636385440826416 +[2025-04-28 03:59:10,711][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.816375494003296, cross_entropy: 1.816375494003296 +[2025-04-28 03:59:12,090][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 2.258358955383301, cross_entropy: 2.258358955383301 +[2025-04-28 03:59:13,388][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 2.2008094787597656, cross_entropy: 2.2008094787597656 +[2025-04-28 03:59:14,373][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 1.8706761598587036, cross_entropy: 1.8706761598587036 +[2025-04-28 03:59:16,161][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 2.2170205116271973, cross_entropy: 2.2170205116271973 +[2025-04-28 03:59:16,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 2.534653425216675, cross_entropy: 2.534653425216675 +[2025-04-28 03:59:18,690][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 2.153074264526367, cross_entropy: 2.153074264526367 +[2025-04-28 03:59:18,969][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.671205997467041, cross_entropy: 2.671205997467041 +[2025-04-28 03:59:22,342][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 1.487577199935913, cross_entropy: 1.487577199935913 +[2025-04-28 03:59:22,622][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 2.6653599739074707, cross_entropy: 2.6653599739074707 +[2025-04-28 03:59:24,941][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 2.6721887588500977, cross_entropy: 2.6721887588500977 +[2025-04-28 03:59:25,222][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.291268825531006, cross_entropy: 2.291268825531006 +[2025-04-28 03:59:27,067][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 3.2754440307617188, cross_entropy: 3.2754440307617188 +[2025-04-28 03:59:27,347][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.4160571098327637, cross_entropy: 2.4160571098327637 +[2025-04-28 03:59:30,095][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.720529317855835, cross_entropy: 1.720529317855835 +[2025-04-28 03:59:30,377][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.3081908226013184, cross_entropy: 2.3081908226013184 +[2025-04-28 03:59:32,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 2.101536512374878, cross_entropy: 2.101536512374878 +[2025-04-28 03:59:32,658][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 1.5202124118804932, cross_entropy: 1.5202124118804932 +[2025-04-28 03:59:35,704][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 2.211106300354004, cross_entropy: 2.211106300354004 +[2025-04-28 03:59:35,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 3.081134796142578, cross_entropy: 3.081134796142578 +[2025-04-28 03:59:38,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 2.4915871620178223, cross_entropy: 2.4915871620178223 +[2025-04-28 03:59:38,400][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 3.461641788482666, cross_entropy: 3.461641788482666 +[2025-04-28 03:59:40,933][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 2.909153938293457, cross_entropy: 2.909153938293457 +[2025-04-28 03:59:41,216][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.5767598152160645, cross_entropy: 3.5767598152160645 +[2025-04-28 03:59:42,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 3.125277280807495, cross_entropy: 3.125277280807495 +[2025-04-28 03:59:43,232][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 3.6246726512908936, cross_entropy: 3.6246726512908936 +[2025-04-28 03:59:45,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 2.053711175918579, cross_entropy: 2.053711175918579 +[2025-04-28 03:59:45,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 3.0781688690185547, cross_entropy: 3.0781688690185547 +[2025-04-28 03:59:47,282][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 3.3215036392211914, cross_entropy: 3.3215036392211914 +[2025-04-28 03:59:47,561][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.7094717025756836, cross_entropy: 1.7094717025756836 +[2025-04-28 03:59:49,617][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.5809407234191895, cross_entropy: 1.5809407234191895 +[2025-04-28 03:59:49,884][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.4813485145568848, cross_entropy: 2.4813485145568848 +[2025-04-28 03:59:51,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.343865156173706, cross_entropy: 2.343865156173706 +[2025-04-28 03:59:52,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 1.8537483215332031, cross_entropy: 1.8537483215332031 +[2025-04-28 03:59:54,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 1.7940469980239868, cross_entropy: 1.7940469980239868 +[2025-04-28 03:59:54,633][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 1.7557792663574219, cross_entropy: 1.7557792663574219 +[2025-04-28 03:59:56,779][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.007580280303955, cross_entropy: 2.007580280303955 +[2025-04-28 03:59:57,061][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 1.4556710720062256, cross_entropy: 1.4556710720062256 +[2025-04-28 03:59:59,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 2.0211803913116455, cross_entropy: 2.0211803913116455 +[2025-04-28 03:59:59,860][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.2851271629333496, cross_entropy: 2.2851271629333496 +[2025-04-28 04:00:02,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.6608166694641113, cross_entropy: 1.6608166694641113 +[2025-04-28 04:00:02,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 3.3459854125976562, cross_entropy: 3.3459854125976562 +[2025-04-28 04:00:04,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 3.021524667739868, cross_entropy: 3.021524667739868 +[2025-04-28 04:00:05,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 2.4891934394836426, cross_entropy: 2.4891934394836426 +[2025-04-28 04:00:07,785][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 2.1635069847106934, cross_entropy: 2.1635069847106934 +[2025-04-28 04:00:08,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 3.2122437953948975, cross_entropy: 3.2122437953948975 +[2025-04-28 04:00:10,291][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 3.085700035095215, cross_entropy: 3.085700035095215 +[2025-04-28 04:00:10,574][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 1.2227630615234375, cross_entropy: 1.2227630615234375 +[2025-04-28 04:00:12,865][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 2.9181103706359863, cross_entropy: 2.9181103706359863 +[2025-04-28 04:00:13,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 3.146057367324829, cross_entropy: 3.146057367324829 +[2025-04-28 04:00:15,719][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 3.0952320098876953, cross_entropy: 3.0952320098876953 +[2025-04-28 04:00:15,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 3.1335484981536865, cross_entropy: 3.1335484981536865 +[2025-04-28 04:00:18,481][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 2.2409541606903076, cross_entropy: 2.2409541606903076 +[2025-04-28 04:00:18,762][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.9154835939407349, cross_entropy: 1.9154835939407349 +[2025-04-28 04:00:20,934][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 3.384373188018799, cross_entropy: 3.384373188018799 +[2025-04-28 04:00:21,236][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 2.1269547939300537, cross_entropy: 2.1269547939300537 +[2025-04-28 04:00:23,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 2.55497670173645, cross_entropy: 2.55497670173645 +[2025-04-28 04:00:23,992][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.4145331382751465, cross_entropy: 1.4145331382751465 +[2025-04-28 04:00:26,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.6014589071273804, cross_entropy: 1.6014589071273804 +[2025-04-28 04:00:26,713][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 3.200320243835449, cross_entropy: 3.200320243835449 +[2025-04-28 04:00:29,063][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 1.762913465499878, cross_entropy: 1.762913465499878 +[2025-04-28 04:00:29,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 2.995265007019043, cross_entropy: 2.995265007019043 +[2025-04-28 04:00:32,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 2.296794891357422, cross_entropy: 2.296794891357422 +[2025-04-28 04:00:32,911][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 2.653017520904541, cross_entropy: 2.653017520904541 +[2025-04-28 04:00:35,302][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 3.3010478019714355, cross_entropy: 3.3010478019714355 +[2025-04-28 04:00:35,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 1.5181281566619873, cross_entropy: 1.5181281566619873 +[2025-04-28 04:00:38,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.0538647174835205, cross_entropy: 2.0538647174835205 +[2025-04-28 04:00:38,680][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 1.9655790328979492, cross_entropy: 1.9655790328979492 +[2025-04-28 04:00:41,347][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 2.0478811264038086, cross_entropy: 2.0478811264038086 +[2025-04-28 04:00:41,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 1.3233301639556885, cross_entropy: 1.3233301639556885 +[2025-04-28 04:00:44,431][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 2.152369976043701, cross_entropy: 2.152369976043701 +[2025-04-28 04:00:44,712][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.7811474800109863, cross_entropy: 2.7811474800109863 +[2025-04-28 04:00:46,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 3.319390058517456, cross_entropy: 3.319390058517456 +[2025-04-28 04:00:46,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.1012802124023438, cross_entropy: 2.1012802124023438 +[2025-04-28 04:00:49,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 3.5229392051696777, cross_entropy: 3.5229392051696777 +[2025-04-28 04:00:49,406][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 3.1697678565979004, cross_entropy: 3.1697678565979004 +[2025-04-28 04:00:51,329][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 3.144667625427246, cross_entropy: 3.144667625427246 +[2025-04-28 04:00:51,597][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 3.3416547775268555, cross_entropy: 3.3416547775268555 +[2025-04-28 04:00:53,710][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.8855104446411133, cross_entropy: 2.8855104446411133 +[2025-04-28 04:00:53,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.5752801895141602, cross_entropy: 1.5752801895141602 +[2025-04-28 04:00:56,341][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 3.4654908180236816, cross_entropy: 3.4654908180236816 +[2025-04-28 04:00:56,622][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.864018201828003, cross_entropy: 2.864018201828003 +[2025-04-28 04:00:58,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 1.6423063278198242, cross_entropy: 1.6423063278198242 +[2025-04-28 04:00:59,066][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 3.4676833152770996, cross_entropy: 3.4676833152770996 +[2025-04-28 04:01:01,376][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 2.7222089767456055, cross_entropy: 2.7222089767456055 +[2025-04-28 04:01:01,659][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 2.9886422157287598, cross_entropy: 2.9886422157287598 +[2025-04-28 04:01:03,543][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.622228980064392, cross_entropy: 1.622228980064392 +[2025-04-28 04:01:03,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 3.5630316734313965, cross_entropy: 3.5630316734313965 +[2025-04-28 04:01:06,033][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 1.9018667936325073, cross_entropy: 1.9018667936325073 +[2025-04-28 04:01:06,301][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 1.747706413269043, cross_entropy: 1.747706413269043 +[2025-04-28 04:01:08,973][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.559453010559082, cross_entropy: 2.559453010559082 +[2025-04-28 04:01:09,253][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.4191713333129883, cross_entropy: 2.4191713333129883 +[2025-04-28 04:01:11,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 2.082641124725342, cross_entropy: 2.082641124725342 +[2025-04-28 04:01:11,581][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.424739360809326, cross_entropy: 2.424739360809326 +[2025-04-28 04:01:13,971][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.8732426166534424, cross_entropy: 1.8732426166534424 +[2025-04-28 04:01:14,251][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 3.231234073638916, cross_entropy: 3.231234073638916 +[2025-04-28 04:01:15,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 2.929243564605713, cross_entropy: 2.929243564605713 +[2025-04-28 04:01:16,277][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.270604133605957, cross_entropy: 2.270604133605957 +[2025-04-28 04:01:18,376][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 3.274610757827759, cross_entropy: 3.274610757827759 +[2025-04-28 04:01:18,643][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.055915117263794, cross_entropy: 2.055915117263794 +[2025-04-28 04:01:21,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 3.060451030731201, cross_entropy: 3.060451030731201 +[2025-04-28 04:01:21,838][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 2.0197441577911377, cross_entropy: 2.0197441577911377 +[2025-04-28 04:01:24,686][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 2.0027894973754883, cross_entropy: 2.0027894973754883 +[2025-04-28 04:01:24,967][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 1.935350775718689, cross_entropy: 1.935350775718689 +[2025-04-28 04:01:26,736][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 1.6796212196350098, cross_entropy: 1.6796212196350098 +[2025-04-28 04:01:27,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 3.0337963104248047, cross_entropy: 3.0337963104248047 +[2025-04-28 04:01:29,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.556589126586914, cross_entropy: 2.556589126586914 +[2025-04-28 04:01:29,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.981325149536133, cross_entropy: 2.981325149536133 +[2025-04-28 04:01:31,923][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 3.446589231491089, cross_entropy: 3.446589231491089 +[2025-04-28 04:01:32,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.7603156566619873, cross_entropy: 1.7603156566619873 +[2025-04-28 04:01:35,230][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 2.6515326499938965, cross_entropy: 2.6515326499938965 +[2025-04-28 04:01:35,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.296950578689575, cross_entropy: 2.296950578689575 +[2025-04-28 04:01:37,717][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 2.411942481994629, cross_entropy: 2.411942481994629 +[2025-04-28 04:01:37,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.9282150268554688, cross_entropy: 2.9282150268554688 +[2025-04-28 04:01:40,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.3400304317474365, cross_entropy: 3.3400304317474365 +[2025-04-28 04:01:40,488][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.838677167892456, cross_entropy: 1.838677167892456 +[2025-04-28 04:01:43,464][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 2.8482680320739746, cross_entropy: 2.8482680320739746 +[2025-04-28 04:01:43,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 1.9549691677093506, cross_entropy: 1.9549691677093506 +[2025-04-28 04:01:46,017][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.6496939659118652, cross_entropy: 2.6496939659118652 +[2025-04-28 04:01:46,298][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 2.4693312644958496, cross_entropy: 2.4693312644958496 +[2025-04-28 04:01:48,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 2.902987480163574, cross_entropy: 2.902987480163574 +[2025-04-28 04:01:48,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 2.6037888526916504, cross_entropy: 2.6037888526916504 +[2025-04-28 04:01:50,974][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 3.565277099609375, cross_entropy: 3.565277099609375 +[2025-04-28 04:01:51,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.1979405879974365, cross_entropy: 2.1979405879974365 +[2025-04-28 04:01:53,635][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.4004011154174805, cross_entropy: 2.4004011154174805 +[2025-04-28 04:01:53,902][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 2.184966564178467, cross_entropy: 2.184966564178467 +[2025-04-28 04:01:55,703][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 1.8402776718139648, cross_entropy: 1.8402776718139648 +[2025-04-28 04:01:55,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 3.0154287815093994, cross_entropy: 3.0154287815093994 +[2025-04-28 04:01:58,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 2.8197755813598633, cross_entropy: 2.8197755813598633 +[2025-04-28 04:01:58,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 1.8882417678833008, cross_entropy: 1.8882417678833008 +[2025-04-28 04:02:01,225][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 1.786691665649414, cross_entropy: 1.786691665649414 +[2025-04-28 04:02:01,504][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 2.545287609100342, cross_entropy: 2.545287609100342 +[2025-04-28 04:02:03,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 3.311842441558838, cross_entropy: 3.311842441558838 +[2025-04-28 04:02:03,754][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 3.254875659942627, cross_entropy: 3.254875659942627 +[2025-04-28 04:02:06,309][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.542160987854004, cross_entropy: 1.542160987854004 +[2025-04-28 04:02:06,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 3.456752300262451, cross_entropy: 3.456752300262451 +[2025-04-28 04:02:09,857][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 3.403877019882202, cross_entropy: 3.403877019882202 +[2025-04-28 04:02:10,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 2.9632174968719482, cross_entropy: 2.9632174968719482 +[2025-04-28 04:02:12,083][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 2.371089220046997, cross_entropy: 2.371089220046997 +[2025-04-28 04:02:12,352][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 3.0439090728759766, cross_entropy: 3.0439090728759766 +[2025-04-28 04:02:14,361][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 1.7231738567352295, cross_entropy: 1.7231738567352295 +[2025-04-28 04:02:14,695][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 3.1288928985595703, cross_entropy: 3.1288928985595703 +[2025-04-28 04:02:17,907][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.7887725830078125, cross_entropy: 2.7887725830078125 +[2025-04-28 04:02:18,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.090604305267334, cross_entropy: 2.090604305267334 +[2025-04-28 04:02:20,689][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 3.2233564853668213, cross_entropy: 3.2233564853668213 +[2025-04-28 04:02:21,401][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 2.9333553314208984, cross_entropy: 2.9333553314208984 +[2025-04-28 04:02:23,353][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 3.4824390411376953, cross_entropy: 3.4824390411376953 +[2025-04-28 04:02:23,697][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 2.1498804092407227, cross_entropy: 2.1498804092407227 +[2025-04-28 04:02:25,786][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 1.9539498090744019, cross_entropy: 1.9539498090744019 +[2025-04-28 04:02:26,347][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.0868520736694336, cross_entropy: 2.0868520736694336 +[2025-04-28 04:02:28,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 3.485548496246338, cross_entropy: 3.485548496246338 +[2025-04-28 04:02:28,589][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 2.075479507446289, cross_entropy: 2.075479507446289 +[2025-04-28 04:02:31,489][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 2.432542324066162, cross_entropy: 2.432542324066162 +[2025-04-28 04:02:31,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 3.7749526500701904, cross_entropy: 3.7749526500701904 +[2025-04-28 04:02:34,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 3.3109281063079834, cross_entropy: 3.3109281063079834 +[2025-04-28 04:02:34,418][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 1.8611721992492676, cross_entropy: 1.8611721992492676 +[2025-04-28 04:02:36,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 1.874091625213623, cross_entropy: 1.874091625213623 +[2025-04-28 04:02:37,260][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 3.5596745014190674, cross_entropy: 3.5596745014190674 +[2025-04-28 04:02:40,270][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 2.258915901184082, cross_entropy: 2.258915901184082 +[2025-04-28 04:02:40,553][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.5876331329345703, cross_entropy: 2.5876331329345703 +[2025-04-28 04:02:42,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 2.5560622215270996, cross_entropy: 2.5560622215270996 +[2025-04-28 04:02:42,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 3.1159098148345947, cross_entropy: 3.1159098148345947 +[2025-04-28 04:02:45,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 2.101351737976074, cross_entropy: 2.101351737976074 +[2025-04-28 04:02:45,511][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 1.8738327026367188, cross_entropy: 1.8738327026367188 +[2025-04-28 04:02:47,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 3.466773509979248, cross_entropy: 3.466773509979248 +[2025-04-28 04:02:47,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 3.2124948501586914, cross_entropy: 3.2124948501586914 +[2025-04-28 04:02:50,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 3.2198801040649414, cross_entropy: 3.2198801040649414 +[2025-04-28 04:02:50,595][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 1.9781471490859985, cross_entropy: 1.9781471490859985 +[2025-04-28 04:02:52,939][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.8776381015777588, cross_entropy: 1.8776381015777588 +[2025-04-28 04:02:53,210][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 2.543750762939453, cross_entropy: 2.543750762939453 +[2025-04-28 04:02:55,185][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 1.9079145193099976, cross_entropy: 1.9079145193099976 +[2025-04-28 04:02:55,466][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 2.3211097717285156, cross_entropy: 2.3211097717285156 +[2025-04-28 04:02:58,923][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 3.3438189029693604, cross_entropy: 3.3438189029693604 +[2025-04-28 04:02:59,194][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 2.1857717037200928, cross_entropy: 2.1857717037200928 +[2025-04-28 04:03:01,311][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.260918140411377, cross_entropy: 2.260918140411377 +[2025-04-28 04:03:01,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 3.4979629516601562, cross_entropy: 3.4979629516601562 +[2025-04-28 04:03:03,662][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 2.7008752822875977, cross_entropy: 2.7008752822875977 +[2025-04-28 04:03:03,932][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.023672342300415, cross_entropy: 2.023672342300415 +[2025-04-28 04:03:05,825][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 3.38812518119812, cross_entropy: 3.38812518119812 +[2025-04-28 04:03:06,102][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.8309276103973389, cross_entropy: 1.8309276103973389 +[2025-04-28 04:03:08,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 3.4096689224243164, cross_entropy: 3.4096689224243164 +[2025-04-28 04:03:08,440][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 3.3703835010528564, cross_entropy: 3.3703835010528564 +[2025-04-28 04:03:10,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 2.9720840454101562, cross_entropy: 2.9720840454101562 +[2025-04-28 04:03:10,640][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 1.8274908065795898, cross_entropy: 1.8274908065795898 +[2025-04-28 04:03:12,741][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.226693630218506, cross_entropy: 2.226693630218506 +[2025-04-28 04:03:13,022][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 1.5433026552200317, cross_entropy: 1.5433026552200317 +[2025-04-28 04:03:14,925][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.4222030639648438, cross_entropy: 2.4222030639648438 +[2025-04-28 04:03:15,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.6903032064437866, cross_entropy: 1.6903032064437866 +[2025-04-28 04:03:17,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.8529751300811768, cross_entropy: 1.8529751300811768 +[2025-04-28 04:03:18,219][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 3.066472053527832, cross_entropy: 3.066472053527832 +[2025-04-28 04:03:20,771][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 3.061282157897949, cross_entropy: 3.061282157897949 +[2025-04-28 04:03:21,053][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.8695679903030396, cross_entropy: 1.8695679903030396 +[2025-04-28 04:03:23,206][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 1.3198868036270142, cross_entropy: 1.3198868036270142 +[2025-04-28 04:03:23,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 2.0917234420776367, cross_entropy: 2.0917234420776367 +[2025-04-28 04:03:26,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.441471576690674, cross_entropy: 2.441471576690674 +[2025-04-28 04:03:26,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 1.84365975856781, cross_entropy: 1.84365975856781 +[2025-04-28 04:03:28,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.6067808866500854, cross_entropy: 1.6067808866500854 +[2025-04-28 04:03:28,958][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.635360836982727, cross_entropy: 1.635360836982727 +[2025-04-28 04:03:30,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.1002228260040283, cross_entropy: 2.1002228260040283 +[2025-04-28 04:03:31,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 2.459470748901367, cross_entropy: 2.459470748901367 +[2025-04-28 04:03:32,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 1.9524190425872803, cross_entropy: 1.9524190425872803 +[2025-04-28 04:03:33,606][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.1754579544067383, cross_entropy: 2.1754579544067383 +[2025-04-28 04:03:36,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 2.794477701187134, cross_entropy: 2.794477701187134 +[2025-04-28 04:03:36,446][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 3.317007064819336, cross_entropy: 3.317007064819336 +[2025-04-28 04:03:39,134][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 1.7764103412628174, cross_entropy: 1.7764103412628174 +[2025-04-28 04:03:39,420][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.8965275287628174, cross_entropy: 1.8965275287628174 +[2025-04-28 04:03:41,587][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.5715014934539795, cross_entropy: 1.5715014934539795 +[2025-04-28 04:03:41,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 3.1679627895355225, cross_entropy: 3.1679627895355225 +[2025-04-28 04:03:44,051][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 2.747236728668213, cross_entropy: 2.747236728668213 +[2025-04-28 04:03:44,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 2.51369047164917, cross_entropy: 2.51369047164917 +[2025-04-28 04:03:46,961][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.5860803127288818, cross_entropy: 1.5860803127288818 +[2025-04-28 04:03:47,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.5956664085388184, cross_entropy: 2.5956664085388184 +[2025-04-28 04:03:49,112][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 2.0908312797546387, cross_entropy: 2.0908312797546387 +[2025-04-28 04:03:49,392][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.3918240070343018, cross_entropy: 2.3918240070343018 +[2025-04-28 04:03:51,422][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 2.627650737762451, cross_entropy: 2.627650737762451 +[2025-04-28 04:03:52,364][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 2.5254440307617188, cross_entropy: 2.5254440307617188 +[2025-04-28 04:03:53,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.9158849716186523, cross_entropy: 2.9158849716186523 +[2025-04-28 04:03:55,179][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.195380210876465, cross_entropy: 3.195380210876465 +[2025-04-28 04:03:56,454][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 3.080845355987549, cross_entropy: 3.080845355987549 +[2025-04-28 04:03:57,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.8091444969177246, cross_entropy: 1.8091444969177246 +[2025-04-28 04:03:58,833][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.5041403770446777, cross_entropy: 2.5041403770446777 +[2025-04-28 04:03:59,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 1.9739482402801514, cross_entropy: 1.9739482402801514 +[2025-04-28 04:04:02,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 3.1704635620117188, cross_entropy: 3.1704635620117188 +[2025-04-28 04:04:02,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.612654209136963, cross_entropy: 2.612654209136963 +[2025-04-28 04:04:04,847][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.575638771057129, cross_entropy: 1.575638771057129 +[2025-04-28 04:04:05,183][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 3.124783515930176, cross_entropy: 3.124783515930176 +[2025-04-28 04:04:07,710][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.8487160205841064, cross_entropy: 1.8487160205841064 +[2025-04-28 04:04:07,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 2.7160515785217285, cross_entropy: 2.7160515785217285 +[2025-04-28 04:04:10,152][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 2.034536838531494, cross_entropy: 2.034536838531494 +[2025-04-28 04:04:10,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 2.281789779663086, cross_entropy: 2.281789779663086 +[2025-04-28 04:04:12,564][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 1.667280673980713, cross_entropy: 1.667280673980713 +[2025-04-28 04:04:12,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 2.3158226013183594, cross_entropy: 2.3158226013183594 +[2025-04-28 04:06:11,620][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.4481818675994873, cross_entropy: 2.4481818675994873 +[2025-04-28 04:06:11,620][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.8221499919891357, cross_entropy: 1.8221499919891357 +[2025-04-28 04:06:11,846][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 04:06:12,008][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch4.pth. +[2025-04-28 04:06:12,219][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:06:15,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.501136302947998, cross_entropy: 2.501136302947998 +[2025-04-28 04:06:16,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.433025598526001, cross_entropy: 1.433025598526001 +[2025-04-28 04:06:17,938][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 2.057771682739258, cross_entropy: 2.057771682739258 +[2025-04-28 04:06:18,392][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.5938602685928345, cross_entropy: 1.5938602685928345 +[2025-04-28 04:06:20,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.4749964475631714, cross_entropy: 1.4749964475631714 +[2025-04-28 04:06:20,644][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.7982845306396484, cross_entropy: 2.7982845306396484 +[2025-04-28 04:06:22,532][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.1559481620788574, cross_entropy: 2.1559481620788574 +[2025-04-28 04:06:23,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.530353546142578, cross_entropy: 2.530353546142578 +[2025-04-28 04:06:24,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 2.8704333305358887, cross_entropy: 2.8704333305358887 +[2025-04-28 04:06:25,906][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.9727224111557007, cross_entropy: 1.9727224111557007 +[2025-04-28 04:06:27,433][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.074385166168213, cross_entropy: 3.074385166168213 +[2025-04-28 04:06:28,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 2.523984432220459, cross_entropy: 2.523984432220459 +[2025-04-28 04:06:29,664][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 3.249913215637207, cross_entropy: 3.249913215637207 +[2025-04-28 04:06:30,908][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.246229648590088, cross_entropy: 2.246229648590088 +[2025-04-28 04:06:32,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 3.2475199699401855, cross_entropy: 3.2475199699401855 +[2025-04-28 04:06:34,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.5911850929260254, cross_entropy: 2.5911850929260254 +[2025-04-28 04:06:34,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 2.7739603519439697, cross_entropy: 2.7739603519439697 +[2025-04-28 04:06:36,995][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 3.184447765350342, cross_entropy: 3.184447765350342 +[2025-04-28 04:06:37,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.83782696723938, cross_entropy: 2.83782696723938 +[2025-04-28 04:06:39,462][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.5102753639221191, cross_entropy: 1.5102753639221191 +[2025-04-28 04:06:39,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.8179848194122314, cross_entropy: 1.8179848194122314 +[2025-04-28 04:06:42,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 2.176055431365967, cross_entropy: 2.176055431365967 +[2025-04-28 04:06:43,080][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 2.119938850402832, cross_entropy: 2.119938850402832 +[2025-04-28 04:06:45,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.9079475402832031, cross_entropy: 1.9079475402832031 +[2025-04-28 04:06:45,575][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.5793195962905884, cross_entropy: 1.5793195962905884 +[2025-04-28 04:06:47,882][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.8215107917785645, cross_entropy: 1.8215107917785645 +[2025-04-28 04:06:48,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 1.5469801425933838, cross_entropy: 1.5469801425933838 +[2025-04-28 04:06:50,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.6052988767623901, cross_entropy: 1.6052988767623901 +[2025-04-28 04:06:50,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 3.1469454765319824, cross_entropy: 3.1469454765319824 +[2025-04-28 04:06:52,538][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 3.1204209327697754, cross_entropy: 3.1204209327697754 +[2025-04-28 04:06:52,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.7825186252593994, cross_entropy: 1.7825186252593994 +[2025-04-28 04:06:55,257][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 1.4466629028320312, cross_entropy: 1.4466629028320312 +[2025-04-28 04:06:55,590][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.9233839511871338, cross_entropy: 1.9233839511871338 +[2025-04-28 04:06:58,026][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 2.4114184379577637, cross_entropy: 2.4114184379577637 +[2025-04-28 04:06:58,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 1.9358601570129395, cross_entropy: 1.9358601570129395 +[2025-04-28 04:07:01,025][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.5943100452423096, cross_entropy: 1.5943100452423096 +[2025-04-28 04:07:01,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.492422580718994, cross_entropy: 3.492422580718994 +[2025-04-28 04:07:03,698][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 1.4060207605361938, cross_entropy: 1.4060207605361938 +[2025-04-28 04:07:04,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 3.115464925765991, cross_entropy: 3.115464925765991 +[2025-04-28 04:07:07,161][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.3209683895111084, cross_entropy: 1.3209683895111084 +[2025-04-28 04:07:07,441][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 2.314457654953003, cross_entropy: 2.314457654953003 +[2025-04-28 04:07:09,528][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.5124192237854004, cross_entropy: 1.5124192237854004 +[2025-04-28 04:07:10,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.9019814729690552, cross_entropy: 1.9019814729690552 +[2025-04-28 04:07:12,547][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.9116135835647583, cross_entropy: 1.9116135835647583 +[2025-04-28 04:07:13,478][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 2.1800317764282227, cross_entropy: 2.1800317764282227 +[2025-04-28 04:07:15,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.990215539932251, cross_entropy: 1.990215539932251 +[2025-04-28 04:07:15,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 2.0591087341308594, cross_entropy: 2.0591087341308594 +[2025-04-28 04:07:17,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.4059922695159912, cross_entropy: 1.4059922695159912 +[2025-04-28 04:07:18,474][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 3.5543577671051025, cross_entropy: 3.5543577671051025 +[2025-04-28 04:07:21,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.8237576484680176, cross_entropy: 1.8237576484680176 +[2025-04-28 04:07:21,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.784398078918457, cross_entropy: 2.784398078918457 +[2025-04-28 04:07:24,318][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.4723128080368042, cross_entropy: 1.4723128080368042 +[2025-04-28 04:07:24,599][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.8182884454727173, cross_entropy: 1.8182884454727173 +[2025-04-28 04:07:26,723][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 3.0306460857391357, cross_entropy: 3.0306460857391357 +[2025-04-28 04:07:27,004][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 3.211699962615967, cross_entropy: 3.211699962615967 +[2025-04-28 04:07:29,099][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.9503397941589355, cross_entropy: 2.9503397941589355 +[2025-04-28 04:07:29,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 3.3726844787597656, cross_entropy: 3.3726844787597656 +[2025-04-28 04:07:31,861][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 3.145545482635498, cross_entropy: 3.145545482635498 +[2025-04-28 04:07:32,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 1.7516553401947021, cross_entropy: 1.7516553401947021 +[2025-04-28 04:07:34,113][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 1.2790776491165161, cross_entropy: 1.2790776491165161 +[2025-04-28 04:07:34,393][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 1.4054797887802124, cross_entropy: 1.4054797887802124 +[2025-04-28 04:07:36,935][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.772395372390747, cross_entropy: 2.772395372390747 +[2025-04-28 04:07:37,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 2.5159590244293213, cross_entropy: 2.5159590244293213 +[2025-04-28 04:07:40,051][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.8945984840393066, cross_entropy: 1.8945984840393066 +[2025-04-28 04:07:40,332][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 1.7634917497634888, cross_entropy: 1.7634917497634888 +[2025-04-28 04:07:42,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 2.597968578338623, cross_entropy: 2.597968578338623 +[2025-04-28 04:07:42,593][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 3.2489500045776367, cross_entropy: 3.2489500045776367 +[2025-04-28 04:07:44,814][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 2.996572732925415, cross_entropy: 2.996572732925415 +[2025-04-28 04:07:45,098][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 1.8894215822219849, cross_entropy: 1.8894215822219849 +[2025-04-28 04:07:47,484][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 3.259650707244873, cross_entropy: 3.259650707244873 +[2025-04-28 04:07:47,760][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.391871929168701, cross_entropy: 3.391871929168701 +[2025-04-28 04:07:49,949][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.3898935317993164, cross_entropy: 2.3898935317993164 +[2025-04-28 04:07:50,229][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.5183161497116089, cross_entropy: 1.5183161497116089 +[2025-04-28 04:07:52,259][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 3.311957836151123, cross_entropy: 3.311957836151123 +[2025-04-28 04:07:52,538][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.4709253311157227, cross_entropy: 2.4709253311157227 +[2025-04-28 04:07:54,756][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 3.6619958877563477, cross_entropy: 3.6619958877563477 +[2025-04-28 04:07:56,274][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 3.222304582595825, cross_entropy: 3.222304582595825 +[2025-04-28 04:07:56,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.928710699081421, cross_entropy: 1.928710699081421 +[2025-04-28 04:07:58,472][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.9444153308868408, cross_entropy: 1.9444153308868408 +[2025-04-28 04:07:59,474][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 2.308389663696289, cross_entropy: 2.308389663696289 +[2025-04-28 04:08:01,256][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 2.1960816383361816, cross_entropy: 2.1960816383361816 +[2025-04-28 04:08:01,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 3.144080638885498, cross_entropy: 3.144080638885498 +[2025-04-28 04:08:04,028][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.4624781608581543, cross_entropy: 2.4624781608581543 +[2025-04-28 04:08:04,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 1.829232931137085, cross_entropy: 1.829232931137085 +[2025-04-28 04:08:07,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.248628854751587, cross_entropy: 2.248628854751587 +[2025-04-28 04:08:08,084][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.3189737796783447, cross_entropy: 1.3189737796783447 +[2025-04-28 04:08:10,528][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.2632789611816406, cross_entropy: 2.2632789611816406 +[2025-04-28 04:08:10,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 2.4048967361450195, cross_entropy: 2.4048967361450195 +[2025-04-28 04:08:12,603][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.8659764528274536, cross_entropy: 1.8659764528274536 +[2025-04-28 04:08:12,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.726418375968933, cross_entropy: 1.726418375968933 +[2025-04-28 04:08:15,051][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.0656633377075195, cross_entropy: 2.0656633377075195 +[2025-04-28 04:08:15,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 1.6707676649093628, cross_entropy: 1.6707676649093628 +[2025-04-28 04:08:17,344][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.052060127258301, cross_entropy: 2.052060127258301 +[2025-04-28 04:08:17,620][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 3.186995029449463, cross_entropy: 3.186995029449463 +[2025-04-28 04:08:19,826][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.405224323272705, cross_entropy: 1.405224323272705 +[2025-04-28 04:08:20,108][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 2.1138062477111816, cross_entropy: 2.1138062477111816 +[2025-04-28 04:08:21,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.7631914615631104, cross_entropy: 2.7631914615631104 +[2025-04-28 04:08:22,126][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 3.0873045921325684, cross_entropy: 3.0873045921325684 +[2025-04-28 04:08:24,108][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 3.0435657501220703, cross_entropy: 3.0435657501220703 +[2025-04-28 04:08:24,386][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 2.095953941345215, cross_entropy: 2.095953941345215 +[2025-04-28 04:08:26,218][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.1404006481170654, cross_entropy: 2.1404006481170654 +[2025-04-28 04:08:26,738][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.2246294021606445, cross_entropy: 2.2246294021606445 +[2025-04-28 04:08:28,689][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.7741892337799072, cross_entropy: 1.7741892337799072 +[2025-04-28 04:08:28,977][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 1.8413026332855225, cross_entropy: 1.8413026332855225 +[2025-04-28 04:08:31,230][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 3.072075843811035, cross_entropy: 3.072075843811035 +[2025-04-28 04:08:31,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.5365904569625854, cross_entropy: 1.5365904569625854 +[2025-04-28 04:08:33,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 3.123957633972168, cross_entropy: 3.123957633972168 +[2025-04-28 04:08:33,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.5036767721176147, cross_entropy: 1.5036767721176147 +[2025-04-28 04:08:35,680][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.954447865486145, cross_entropy: 1.954447865486145 +[2025-04-28 04:08:36,007][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 3.487900733947754, cross_entropy: 3.487900733947754 +[2025-04-28 04:08:37,633][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 3.1921794414520264, cross_entropy: 3.1921794414520264 +[2025-04-28 04:08:38,138][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 3.2432355880737305, cross_entropy: 3.2432355880737305 +[2025-04-28 04:08:40,364][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.8788251876831055, cross_entropy: 1.8788251876831055 +[2025-04-28 04:08:42,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 1.7945514917373657, cross_entropy: 1.7945514917373657 +[2025-04-28 04:08:43,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.743074893951416, cross_entropy: 1.743074893951416 +[2025-04-28 04:08:44,641][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.6323795318603516, cross_entropy: 2.6323795318603516 +[2025-04-28 04:08:45,829][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 1.998989224433899, cross_entropy: 1.998989224433899 +[2025-04-28 04:08:46,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.9767986536026, cross_entropy: 1.9767986536026 +[2025-04-28 04:08:48,133][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 3.022627353668213, cross_entropy: 3.022627353668213 +[2025-04-28 04:08:49,844][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 3.3192005157470703, cross_entropy: 3.3192005157470703 +[2025-04-28 04:08:50,209][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 2.0616908073425293, cross_entropy: 2.0616908073425293 +[2025-04-28 04:08:52,020][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 1.3594664335250854, cross_entropy: 1.3594664335250854 +[2025-04-28 04:08:52,686][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.621476888656616, cross_entropy: 3.621476888656616 +[2025-04-28 04:08:54,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 1.9402353763580322, cross_entropy: 1.9402353763580322 +[2025-04-28 04:08:55,048][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.653829574584961, cross_entropy: 2.653829574584961 +[2025-04-28 04:08:57,180][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 1.2492427825927734, cross_entropy: 1.2492427825927734 +[2025-04-28 04:08:57,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.4082975387573242, cross_entropy: 1.4082975387573242 +[2025-04-28 04:08:59,114][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 2.988492488861084, cross_entropy: 2.988492488861084 +[2025-04-28 04:08:59,863][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.4247968196868896, cross_entropy: 1.4247968196868896 +[2025-04-28 04:09:01,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.4550557136535645, cross_entropy: 2.4550557136535645 +[2025-04-28 04:09:02,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.5420608520507812, cross_entropy: 1.5420608520507812 +[2025-04-28 04:09:04,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.8189113140106201, cross_entropy: 1.8189113140106201 +[2025-04-28 04:09:04,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.757441520690918, cross_entropy: 2.757441520690918 +[2025-04-28 04:09:06,554][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 1.7691781520843506, cross_entropy: 1.7691781520843506 +[2025-04-28 04:09:07,070][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.763538122177124, cross_entropy: 1.763538122177124 +[2025-04-28 04:09:08,982][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 3.304260730743408, cross_entropy: 3.304260730743408 +[2025-04-28 04:09:09,556][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 3.4914746284484863, cross_entropy: 3.4914746284484863 +[2025-04-28 04:09:11,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 3.0598204135894775, cross_entropy: 3.0598204135894775 +[2025-04-28 04:09:12,101][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 1.3382359743118286, cross_entropy: 1.3382359743118286 +[2025-04-28 04:09:14,161][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 2.973573923110962, cross_entropy: 2.973573923110962 +[2025-04-28 04:09:15,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 2.1623048782348633, cross_entropy: 2.1623048782348633 +[2025-04-28 04:09:17,275][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 2.0780234336853027, cross_entropy: 2.0780234336853027 +[2025-04-28 04:09:17,592][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 3.6564135551452637, cross_entropy: 3.6564135551452637 +[2025-04-28 04:09:19,975][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 3.350037097930908, cross_entropy: 3.350037097930908 +[2025-04-28 04:09:20,303][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.3162038326263428, cross_entropy: 1.3162038326263428 +[2025-04-28 04:09:22,011][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 3.0982213020324707, cross_entropy: 3.0982213020324707 +[2025-04-28 04:09:22,723][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.7782979011535645, cross_entropy: 2.7782979011535645 +[2025-04-28 04:09:24,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 1.8826721906661987, cross_entropy: 1.8826721906661987 +[2025-04-28 04:09:26,344][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.907254934310913, cross_entropy: 1.907254934310913 +[2025-04-28 04:09:26,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.6381590366363525, cross_entropy: 1.6381590366363525 +[2025-04-28 04:09:29,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.2220020294189453, cross_entropy: 3.2220020294189453 +[2025-04-28 04:09:29,786][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.701598882675171, cross_entropy: 1.701598882675171 +[2025-04-28 04:09:31,704][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.6580525636672974, cross_entropy: 1.6580525636672974 +[2025-04-28 04:09:32,595][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 3.3371992111206055, cross_entropy: 3.3371992111206055 +[2025-04-28 04:09:35,207][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 3.000993251800537, cross_entropy: 3.000993251800537 +[2025-04-28 04:09:35,518][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.4094901084899902, cross_entropy: 2.4094901084899902 +[2025-04-28 04:09:37,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 1.6559109687805176, cross_entropy: 1.6559109687805176 +[2025-04-28 04:09:37,757][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.3258039951324463, cross_entropy: 1.3258039951324463 +[2025-04-28 04:09:39,678][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 2.7058279514312744, cross_entropy: 2.7058279514312744 +[2025-04-28 04:09:39,960][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 3.0945053100585938, cross_entropy: 3.0945053100585938 +[2025-04-28 04:09:41,935][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.5109410285949707, cross_entropy: 2.5109410285949707 +[2025-04-28 04:09:42,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.5147957801818848, cross_entropy: 1.5147957801818848 +[2025-04-28 04:09:44,396][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 3.283071994781494, cross_entropy: 3.283071994781494 +[2025-04-28 04:09:44,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 1.6688827276229858, cross_entropy: 1.6688827276229858 +[2025-04-28 04:09:46,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 3.5056207180023193, cross_entropy: 3.5056207180023193 +[2025-04-28 04:09:47,150][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 2.5046684741973877, cross_entropy: 2.5046684741973877 +[2025-04-28 04:09:49,488][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 3.458212375640869, cross_entropy: 3.458212375640869 +[2025-04-28 04:09:49,774][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.7632726430892944, cross_entropy: 1.7632726430892944 +[2025-04-28 04:09:51,616][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.7973227500915527, cross_entropy: 1.7973227500915527 +[2025-04-28 04:09:51,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 2.788038969039917, cross_entropy: 2.788038969039917 +[2025-04-28 04:09:53,954][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.93063485622406, cross_entropy: 1.93063485622406 +[2025-04-28 04:09:54,692][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 2.768031120300293, cross_entropy: 2.768031120300293 +[2025-04-28 04:09:57,095][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 3.0164389610290527, cross_entropy: 3.0164389610290527 +[2025-04-28 04:09:57,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 3.6610267162323, cross_entropy: 3.6610267162323 +[2025-04-28 04:09:59,469][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.7401866912841797, cross_entropy: 1.7401866912841797 +[2025-04-28 04:09:59,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 2.8494174480438232, cross_entropy: 2.8494174480438232 +[2025-04-28 04:10:02,226][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 3.0219969749450684, cross_entropy: 3.0219969749450684 +[2025-04-28 04:10:02,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 2.6084184646606445, cross_entropy: 2.6084184646606445 +[2025-04-28 04:10:04,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.590129017829895, cross_entropy: 1.590129017829895 +[2025-04-28 04:10:04,820][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 1.9288384914398193, cross_entropy: 1.9288384914398193 +[2025-04-28 04:10:07,181][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 3.0509681701660156, cross_entropy: 3.0509681701660156 +[2025-04-28 04:10:07,466][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 3.191318988800049, cross_entropy: 3.191318988800049 +[2025-04-28 04:10:09,466][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 3.655491352081299, cross_entropy: 3.655491352081299 +[2025-04-28 04:10:09,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.5362024307250977, cross_entropy: 2.5362024307250977 +[2025-04-28 04:10:11,972][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.2435741424560547, cross_entropy: 2.2435741424560547 +[2025-04-28 04:10:12,280][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.9256114959716797, cross_entropy: 2.9256114959716797 +[2025-04-28 04:10:14,930][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 1.9355628490447998, cross_entropy: 1.9355628490447998 +[2025-04-28 04:10:15,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 1.742794394493103, cross_entropy: 1.742794394493103 +[2025-04-28 04:10:18,046][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.8876895904541016, cross_entropy: 2.8876895904541016 +[2025-04-28 04:10:18,335][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 1.979889154434204, cross_entropy: 1.979889154434204 +[2025-04-28 04:10:20,790][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 2.7389931678771973, cross_entropy: 2.7389931678771973 +[2025-04-28 04:10:21,072][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 1.4632766246795654, cross_entropy: 1.4632766246795654 +[2025-04-28 04:10:22,760][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.6594345569610596, cross_entropy: 1.6594345569610596 +[2025-04-28 04:10:23,487][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 1.4608771800994873, cross_entropy: 1.4608771800994873 +[2025-04-28 04:10:25,496][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.9772942066192627, cross_entropy: 2.9772942066192627 +[2025-04-28 04:10:26,264][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 2.2404680252075195, cross_entropy: 2.2404680252075195 +[2025-04-28 04:10:28,901][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.353318214416504, cross_entropy: 1.353318214416504 +[2025-04-28 04:10:29,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 3.2484006881713867, cross_entropy: 3.2484006881713867 +[2025-04-28 04:10:31,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 3.050632953643799, cross_entropy: 3.050632953643799 +[2025-04-28 04:10:32,077][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.223327875137329, cross_entropy: 2.223327875137329 +[2025-04-28 04:10:33,582][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 2.503603458404541, cross_entropy: 2.503603458404541 +[2025-04-28 04:10:35,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 3.2600975036621094, cross_entropy: 3.2600975036621094 +[2025-04-28 04:10:36,389][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.4108457565307617, cross_entropy: 2.4108457565307617 +[2025-04-28 04:10:37,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 1.4696003198623657, cross_entropy: 1.4696003198623657 +[2025-04-28 04:10:39,074][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 3.2818713188171387, cross_entropy: 3.2818713188171387 +[2025-04-28 04:10:39,733][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.9370759725570679, cross_entropy: 1.9370759725570679 +[2025-04-28 04:10:41,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.7556216716766357, cross_entropy: 1.7556216716766357 +[2025-04-28 04:10:42,793][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.6008477210998535, cross_entropy: 1.6008477210998535 +[2025-04-28 04:10:44,395][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.472771167755127, cross_entropy: 1.472771167755127 +[2025-04-28 04:10:45,050][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.8046813011169434, cross_entropy: 2.8046813011169434 +[2025-04-28 04:10:46,973][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.7714718580245972, cross_entropy: 1.7714718580245972 +[2025-04-28 04:10:47,829][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.9751734733581543, cross_entropy: 2.9751734733581543 +[2025-04-28 04:10:49,917][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 3.1900041103363037, cross_entropy: 3.1900041103363037 +[2025-04-28 04:10:50,915][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.339671015739441, cross_entropy: 1.339671015739441 +[2025-04-28 04:10:52,502][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 1.930562973022461, cross_entropy: 1.930562973022461 +[2025-04-28 04:10:53,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 2.9912679195404053, cross_entropy: 2.9912679195404053 +[2025-04-28 04:10:54,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.531737804412842, cross_entropy: 2.531737804412842 +[2025-04-28 04:10:56,136][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 3.562093734741211, cross_entropy: 3.562093734741211 +[2025-04-28 04:10:57,247][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.812985897064209, cross_entropy: 2.812985897064209 +[2025-04-28 04:10:59,384][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.576688528060913, cross_entropy: 2.576688528060913 +[2025-04-28 04:10:59,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 2.9832277297973633, cross_entropy: 2.9832277297973633 +[2025-04-28 04:11:02,173][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 2.3643221855163574, cross_entropy: 2.3643221855163574 +[2025-04-28 04:11:02,456][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.0640628337860107, cross_entropy: 2.0640628337860107 +[2025-04-28 04:11:05,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 3.2423624992370605, cross_entropy: 3.2423624992370605 +[2025-04-28 04:11:05,414][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.8386152982711792, cross_entropy: 1.8386152982711792 +[2025-04-28 04:11:07,332][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.3310260772705078, cross_entropy: 1.3310260772705078 +[2025-04-28 04:11:07,613][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.2145469188690186, cross_entropy: 1.2145469188690186 +[2025-04-28 04:11:10,001][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 2.7035930156707764, cross_entropy: 2.7035930156707764 +[2025-04-28 04:11:10,270][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 1.925778865814209, cross_entropy: 1.925778865814209 +[2025-04-28 04:11:13,588][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 1.8100035190582275, cross_entropy: 1.8100035190582275 +[2025-04-28 04:11:13,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.6064220666885376, cross_entropy: 1.6064220666885376 +[2025-04-28 04:11:15,994][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.6552143096923828, cross_entropy: 1.6552143096923828 +[2025-04-28 04:11:16,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 3.401301860809326, cross_entropy: 3.401301860809326 +[2025-04-28 04:11:18,760][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 3.046102523803711, cross_entropy: 3.046102523803711 +[2025-04-28 04:11:19,045][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.5013129711151123, cross_entropy: 2.5013129711151123 +[2025-04-28 04:11:21,372][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 3.289931297302246, cross_entropy: 3.289931297302246 +[2025-04-28 04:11:21,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 2.0499091148376465, cross_entropy: 2.0499091148376465 +[2025-04-28 04:11:23,665][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 3.601553440093994, cross_entropy: 3.601553440093994 +[2025-04-28 04:11:23,946][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.7860417366027832, cross_entropy: 1.7860417366027832 +[2025-04-28 04:11:26,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.7491289377212524, cross_entropy: 1.7491289377212524 +[2025-04-28 04:11:26,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 3.3187437057495117, cross_entropy: 3.3187437057495117 +[2025-04-28 04:11:28,539][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.6748676300048828, cross_entropy: 1.6748676300048828 +[2025-04-28 04:11:29,210][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.4784274101257324, cross_entropy: 2.4784274101257324 +[2025-04-28 04:11:31,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 1.4072707891464233, cross_entropy: 1.4072707891464233 +[2025-04-28 04:11:31,725][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 3.139164686203003, cross_entropy: 3.139164686203003 +[2025-04-28 04:11:34,610][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 1.5770089626312256, cross_entropy: 1.5770089626312256 +[2025-04-28 04:11:34,894][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.469029426574707, cross_entropy: 1.469029426574707 +[2025-04-28 04:11:36,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 3.1926023960113525, cross_entropy: 3.1926023960113525 +[2025-04-28 04:11:37,237][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 3.264974594116211, cross_entropy: 3.264974594116211 +[2025-04-28 04:11:40,009][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 2.2015488147735596, cross_entropy: 2.2015488147735596 +[2025-04-28 04:11:40,292][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.2982139587402344, cross_entropy: 2.2982139587402344 +[2025-04-28 04:11:42,320][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 2.2796759605407715, cross_entropy: 2.2796759605407715 +[2025-04-28 04:11:42,589][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.8118507862091064, cross_entropy: 1.8118507862091064 +[2025-04-28 04:11:44,664][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 1.7836182117462158, cross_entropy: 1.7836182117462158 +[2025-04-28 04:11:44,932][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 1.8183188438415527, cross_entropy: 1.8183188438415527 +[2025-04-28 04:11:47,031][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 2.2231063842773438, cross_entropy: 2.2231063842773438 +[2025-04-28 04:11:47,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 3.0341525077819824, cross_entropy: 3.0341525077819824 +[2025-04-28 04:11:49,846][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 3.349445343017578, cross_entropy: 3.349445343017578 +[2025-04-28 04:11:50,124][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 1.787182331085205, cross_entropy: 1.787182331085205 +[2025-04-28 04:11:52,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.7722804546356201, cross_entropy: 1.7722804546356201 +[2025-04-28 04:11:52,520][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.5038567781448364, cross_entropy: 1.5038567781448364 +[2025-04-28 04:11:55,329][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.7508456707000732, cross_entropy: 1.7508456707000732 +[2025-04-28 04:11:55,611][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 1.6295828819274902, cross_entropy: 1.6295828819274902 +[2025-04-28 04:11:57,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 2.361720323562622, cross_entropy: 2.361720323562622 +[2025-04-28 04:11:58,158][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.5294809341430664, cross_entropy: 3.5294809341430664 +[2025-04-28 04:12:00,007][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.7771565914154053, cross_entropy: 2.7771565914154053 +[2025-04-28 04:12:00,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.0148088932037354, cross_entropy: 2.0148088932037354 +[2025-04-28 04:12:02,746][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.5232973098754883, cross_entropy: 3.5232973098754883 +[2025-04-28 04:12:03,668][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 1.7410879135131836, cross_entropy: 1.7410879135131836 +[2025-04-28 04:12:05,610][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.8926472663879395, cross_entropy: 1.8926472663879395 +[2025-04-28 04:12:06,670][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 2.485349178314209, cross_entropy: 2.485349178314209 +[2025-04-28 04:12:08,370][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.9202829599380493, cross_entropy: 1.9202829599380493 +[2025-04-28 04:12:09,200][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 2.1013853549957275, cross_entropy: 2.1013853549957275 +[2025-04-28 04:12:10,792][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 1.7967503070831299, cross_entropy: 1.7967503070831299 +[2025-04-28 04:12:11,999][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.2537686824798584, cross_entropy: 2.2537686824798584 +[2025-04-28 04:12:12,867][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.9197986125946045, cross_entropy: 1.9197986125946045 +[2025-04-28 04:12:15,404][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.7800912857055664, cross_entropy: 2.7800912857055664 +[2025-04-28 04:12:15,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.0736188888549805, cross_entropy: 2.0736188888549805 +[2025-04-28 04:12:18,010][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.9176313877105713, cross_entropy: 1.9176313877105713 +[2025-04-28 04:12:18,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 2.129206418991089, cross_entropy: 2.129206418991089 +[2025-04-28 04:12:20,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 2.334498405456543, cross_entropy: 2.334498405456543 +[2025-04-28 04:12:20,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 3.4765310287475586, cross_entropy: 3.4765310287475586 +[2025-04-28 04:12:22,025][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 3.0724215507507324, cross_entropy: 3.0724215507507324 +[2025-04-28 04:12:23,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 2.6987109184265137, cross_entropy: 2.6987109184265137 +[2025-04-28 04:12:24,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 1.5060898065567017, cross_entropy: 1.5060898065567017 +[2025-04-28 04:12:25,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 2.602022409439087, cross_entropy: 2.602022409439087 +[2025-04-28 04:12:27,616][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 3.119717597961426, cross_entropy: 3.119717597961426 +[2025-04-28 04:12:29,101][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 1.6765356063842773, cross_entropy: 1.6765356063842773 +[2025-04-28 04:12:30,106][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.8632419109344482, cross_entropy: 1.8632419109344482 +[2025-04-28 04:12:31,442][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.5017170906066895, cross_entropy: 2.5017170906066895 +[2025-04-28 04:12:32,473][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 1.8398735523223877, cross_entropy: 1.8398735523223877 +[2025-04-28 04:12:34,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.3389523029327393, cross_entropy: 1.3389523029327393 +[2025-04-28 04:12:35,423][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.6447091102600098, cross_entropy: 1.6447091102600098 +[2025-04-28 04:12:36,510][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.665686845779419, cross_entropy: 1.665686845779419 +[2025-04-28 04:12:38,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 2.3110294342041016, cross_entropy: 2.3110294342041016 +[2025-04-28 04:12:39,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 2.342639446258545, cross_entropy: 2.342639446258545 +[2025-04-28 04:12:40,465][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.3308348655700684, cross_entropy: 1.3308348655700684 +[2025-04-28 04:12:41,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 2.6910061836242676, cross_entropy: 2.6910061836242676 +[2025-04-28 04:12:42,912][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 3.56825590133667, cross_entropy: 3.56825590133667 +[2025-04-28 04:12:44,554][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 3.295827865600586, cross_entropy: 3.295827865600586 +[2025-04-28 04:12:45,073][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 2.5927443504333496, cross_entropy: 2.5927443504333496 +[2025-04-28 04:12:47,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 1.5705736875534058, cross_entropy: 1.5705736875534058 +[2025-04-28 04:12:47,521][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 3.2301106452941895, cross_entropy: 3.2301106452941895 +[2025-04-28 04:12:50,077][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 3.2601256370544434, cross_entropy: 3.2601256370544434 +[2025-04-28 04:12:50,359][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 1.3696331977844238, cross_entropy: 1.3696331977844238 +[2025-04-28 04:12:52,259][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.5862009525299072, cross_entropy: 1.5862009525299072 +[2025-04-28 04:12:52,529][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.7917404174804688, cross_entropy: 1.7917404174804688 +[2025-04-28 04:12:54,719][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 2.668938159942627, cross_entropy: 2.668938159942627 +[2025-04-28 04:12:55,001][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.639034628868103, cross_entropy: 1.639034628868103 +[2025-04-28 04:12:57,208][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 2.8819704055786133, cross_entropy: 2.8819704055786133 +[2025-04-28 04:12:57,488][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.9595274925231934, cross_entropy: 1.9595274925231934 +[2025-04-28 04:13:00,122][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 1.9276952743530273, cross_entropy: 1.9276952743530273 +[2025-04-28 04:13:00,404][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.9105597734451294, cross_entropy: 1.9105597734451294 +[2025-04-28 04:13:03,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.3609278202056885, cross_entropy: 1.3609278202056885 +[2025-04-28 04:13:03,603][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.5466150045394897, cross_entropy: 1.5466150045394897 +[2025-04-28 04:13:05,604][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 3.2521798610687256, cross_entropy: 3.2521798610687256 +[2025-04-28 04:13:05,886][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 1.9127458333969116, cross_entropy: 1.9127458333969116 +[2025-04-28 04:13:08,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 2.154123306274414, cross_entropy: 2.154123306274414 +[2025-04-28 04:13:08,495][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 3.1212520599365234, cross_entropy: 3.1212520599365234 +[2025-04-28 04:13:11,003][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 1.709928035736084, cross_entropy: 1.709928035736084 +[2025-04-28 04:13:11,271][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 3.2295939922332764, cross_entropy: 3.2295939922332764 +[2025-04-28 04:13:13,478][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 3.3629865646362305, cross_entropy: 3.3629865646362305 +[2025-04-28 04:13:13,759][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 2.880866289138794, cross_entropy: 2.880866289138794 +[2025-04-28 04:13:15,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 3.0279135704040527, cross_entropy: 3.0279135704040527 +[2025-04-28 04:13:16,068][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 2.937699556350708, cross_entropy: 2.937699556350708 +[2025-04-28 04:13:18,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 1.492963194847107, cross_entropy: 1.492963194847107 +[2025-04-28 04:13:18,402][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 2.069385528564453, cross_entropy: 2.069385528564453 +[2025-04-28 04:13:20,218][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.729367971420288, cross_entropy: 2.729367971420288 +[2025-04-28 04:13:20,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.1921401023864746, cross_entropy: 3.1921401023864746 +[2025-04-28 04:13:22,667][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 2.5766050815582275, cross_entropy: 2.5766050815582275 +[2025-04-28 04:13:22,995][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 1.9926714897155762, cross_entropy: 1.9926714897155762 +[2025-04-28 04:13:25,097][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 3.346395969390869, cross_entropy: 3.346395969390869 +[2025-04-28 04:13:25,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.4951735734939575, cross_entropy: 1.4951735734939575 +[2025-04-28 04:13:27,523][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 3.0449018478393555, cross_entropy: 3.0449018478393555 +[2025-04-28 04:13:27,804][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 2.9869256019592285, cross_entropy: 2.9869256019592285 +[2025-04-28 04:13:30,197][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 3.4517416954040527, cross_entropy: 3.4517416954040527 +[2025-04-28 04:13:30,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.663292646408081, cross_entropy: 2.663292646408081 +[2025-04-28 04:13:32,918][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.982330799102783, cross_entropy: 2.982330799102783 +[2025-04-28 04:13:33,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 3.3207671642303467, cross_entropy: 3.3207671642303467 +[2025-04-28 04:13:36,886][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.182292938232422, cross_entropy: 3.182292938232422 +[2025-04-28 04:13:37,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.149794816970825, cross_entropy: 2.149794816970825 +[2025-04-28 04:13:39,997][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 3.1699588298797607, cross_entropy: 3.1699588298797607 +[2025-04-28 04:13:40,280][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.2550439834594727, cross_entropy: 3.2550439834594727 +[2025-04-28 04:13:42,745][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.781679391860962, cross_entropy: 1.781679391860962 +[2025-04-28 04:13:43,015][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 3.089794635772705, cross_entropy: 3.089794635772705 +[2025-04-28 04:13:45,598][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 3.254121780395508, cross_entropy: 3.254121780395508 +[2025-04-28 04:13:45,866][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 3.183225631713867, cross_entropy: 3.183225631713867 +[2025-04-28 04:13:48,197][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.554989814758301, cross_entropy: 2.554989814758301 +[2025-04-28 04:13:48,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.6171998977661133, cross_entropy: 1.6171998977661133 +[2025-04-28 04:13:50,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.6328058242797852, cross_entropy: 1.6328058242797852 +[2025-04-28 04:13:50,964][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.417783737182617, cross_entropy: 2.417783737182617 +[2025-04-28 04:13:53,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.9175989627838135, cross_entropy: 1.9175989627838135 +[2025-04-28 04:13:53,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.7942274808883667, cross_entropy: 1.7942274808883667 +[2025-04-28 04:13:55,555][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 2.836801052093506, cross_entropy: 2.836801052093506 +[2025-04-28 04:13:55,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 3.5625216960906982, cross_entropy: 3.5625216960906982 +[2025-04-28 04:13:57,422][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 3.1287434101104736, cross_entropy: 3.1287434101104736 +[2025-04-28 04:15:57,262][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.3642430305480957, cross_entropy: 2.3642430305480957 +[2025-04-28 04:15:57,262][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.7463204860687256, cross_entropy: 1.7463204860687256 +[2025-04-28 04:15:57,486][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 04:15:57,645][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch5.pth. +[2025-04-28 04:15:57,840][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:16:00,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 1.1091176271438599, cross_entropy: 1.1091176271438599 +[2025-04-28 04:16:01,280][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.9094555377960205, cross_entropy: 1.9094555377960205 +[2025-04-28 04:16:02,981][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 2.948455333709717, cross_entropy: 2.948455333709717 +[2025-04-28 04:16:03,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 2.9407966136932373, cross_entropy: 2.9407966136932373 +[2025-04-28 04:16:05,196][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.371730089187622, cross_entropy: 2.371730089187622 +[2025-04-28 04:16:05,659][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 3.096859931945801, cross_entropy: 3.096859931945801 +[2025-04-28 04:16:07,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 2.8372950553894043, cross_entropy: 2.8372950553894043 +[2025-04-28 04:16:09,128][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.370111107826233, cross_entropy: 1.370111107826233 +[2025-04-28 04:16:10,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.7663264274597168, cross_entropy: 1.7663264274597168 +[2025-04-28 04:16:12,068][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.552072763442993, cross_entropy: 2.552072763442993 +[2025-04-28 04:16:13,430][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.7459545135498047, cross_entropy: 2.7459545135498047 +[2025-04-28 04:16:14,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 2.3873789310455322, cross_entropy: 2.3873789310455322 +[2025-04-28 04:16:15,458][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 3.062391996383667, cross_entropy: 3.062391996383667 +[2025-04-28 04:16:17,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 2.028709888458252, cross_entropy: 2.028709888458252 +[2025-04-28 04:16:18,065][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 1.348101258277893, cross_entropy: 1.348101258277893 +[2025-04-28 04:16:20,761][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.5858099460601807, cross_entropy: 2.5858099460601807 +[2025-04-28 04:16:21,029][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.721225619316101, cross_entropy: 1.721225619316101 +[2025-04-28 04:16:23,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.344879627227783, cross_entropy: 3.344879627227783 +[2025-04-28 04:16:23,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.5084028244018555, cross_entropy: 1.5084028244018555 +[2025-04-28 04:16:26,475][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 3.533754348754883, cross_entropy: 3.533754348754883 +[2025-04-28 04:16:26,756][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 2.377272129058838, cross_entropy: 2.377272129058838 +[2025-04-28 04:16:29,077][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.763192892074585, cross_entropy: 1.763192892074585 +[2025-04-28 04:16:29,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 1.2068463563919067, cross_entropy: 1.2068463563919067 +[2025-04-28 04:16:31,741][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.6853675842285156, cross_entropy: 2.6853675842285156 +[2025-04-28 04:16:32,010][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 1.3822152614593506, cross_entropy: 1.3822152614593506 +[2025-04-28 04:16:34,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.3512637615203857, cross_entropy: 2.3512637615203857 +[2025-04-28 04:16:34,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 2.804142951965332, cross_entropy: 2.804142951965332 +[2025-04-28 04:16:36,898][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.3062310218811035, cross_entropy: 2.3062310218811035 +[2025-04-28 04:16:37,166][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.3688971996307373, cross_entropy: 1.3688971996307373 +[2025-04-28 04:16:40,096][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 1.4692456722259521, cross_entropy: 1.4692456722259521 +[2025-04-28 04:16:40,379][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.4303412437438965, cross_entropy: 1.4303412437438965 +[2025-04-28 04:16:43,441][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.830984592437744, cross_entropy: 2.830984592437744 +[2025-04-28 04:16:43,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 3.1539885997772217, cross_entropy: 3.1539885997772217 +[2025-04-28 04:16:46,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 3.212467670440674, cross_entropy: 3.212467670440674 +[2025-04-28 04:16:46,508][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 1.3394253253936768, cross_entropy: 1.3394253253936768 +[2025-04-28 04:16:49,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 1.5356414318084717, cross_entropy: 1.5356414318084717 +[2025-04-28 04:16:49,669][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.1956369876861572, cross_entropy: 1.1956369876861572 +[2025-04-28 04:16:51,627][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 3.0896825790405273, cross_entropy: 3.0896825790405273 +[2025-04-28 04:16:51,898][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.731537342071533, cross_entropy: 2.731537342071533 +[2025-04-28 04:16:55,025][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.4603278636932373, cross_entropy: 1.4603278636932373 +[2025-04-28 04:16:55,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 3.5022668838500977, cross_entropy: 3.5022668838500977 +[2025-04-28 04:16:57,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 3.0847582817077637, cross_entropy: 3.0847582817077637 +[2025-04-28 04:16:57,742][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.7324740886688232, cross_entropy: 1.7324740886688232 +[2025-04-28 04:17:00,041][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 3.0298619270324707, cross_entropy: 3.0298619270324707 +[2025-04-28 04:17:00,319][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 2.3395962715148926, cross_entropy: 2.3395962715148926 +[2025-04-28 04:17:02,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.5903267860412598, cross_entropy: 2.5903267860412598 +[2025-04-28 04:17:03,020][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 3.2238364219665527, cross_entropy: 3.2238364219665527 +[2025-04-28 04:17:05,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 3.297469139099121, cross_entropy: 3.297469139099121 +[2025-04-28 04:17:05,371][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.628321886062622, cross_entropy: 1.628321886062622 +[2025-04-28 04:17:07,782][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 2.119696617126465, cross_entropy: 2.119696617126465 +[2025-04-28 04:17:08,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 2.9126651287078857, cross_entropy: 2.9126651287078857 +[2025-04-28 04:17:10,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 3.304121494293213, cross_entropy: 3.304121494293213 +[2025-04-28 04:17:10,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 3.168278694152832, cross_entropy: 3.168278694152832 +[2025-04-28 04:17:13,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.5530507564544678, cross_entropy: 1.5530507564544678 +[2025-04-28 04:17:13,757][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 2.1598033905029297, cross_entropy: 2.1598033905029297 +[2025-04-28 04:17:16,246][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 1.2177963256835938, cross_entropy: 1.2177963256835938 +[2025-04-28 04:17:16,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 3.339107036590576, cross_entropy: 3.339107036590576 +[2025-04-28 04:17:18,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.5144264698028564, cross_entropy: 1.5144264698028564 +[2025-04-28 04:17:19,203][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.191631317138672, cross_entropy: 2.191631317138672 +[2025-04-28 04:17:21,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.5141618251800537, cross_entropy: 2.5141618251800537 +[2025-04-28 04:17:21,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 2.5708703994750977, cross_entropy: 2.5708703994750977 +[2025-04-28 04:17:24,103][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.5964319705963135, cross_entropy: 2.5964319705963135 +[2025-04-28 04:17:24,385][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 3.2022359371185303, cross_entropy: 3.2022359371185303 +[2025-04-28 04:17:26,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.9028490781784058, cross_entropy: 1.9028490781784058 +[2025-04-28 04:17:27,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.816213607788086, cross_entropy: 2.816213607788086 +[2025-04-28 04:17:29,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.970090389251709, cross_entropy: 2.970090389251709 +[2025-04-28 04:17:29,508][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 1.3225939273834229, cross_entropy: 1.3225939273834229 +[2025-04-28 04:17:31,624][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.3586668968200684, cross_entropy: 1.3586668968200684 +[2025-04-28 04:17:31,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 2.569960832595825, cross_entropy: 2.569960832595825 +[2025-04-28 04:17:33,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.6560698747634888, cross_entropy: 1.6560698747634888 +[2025-04-28 04:17:34,151][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 2.4676756858825684, cross_entropy: 2.4676756858825684 +[2025-04-28 04:17:36,211][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.8571338653564453, cross_entropy: 1.8571338653564453 +[2025-04-28 04:17:36,671][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 1.589216709136963, cross_entropy: 1.589216709136963 +[2025-04-28 04:17:38,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.328383445739746, cross_entropy: 1.328383445739746 +[2025-04-28 04:17:39,883][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 1.4209171533584595, cross_entropy: 1.4209171533584595 +[2025-04-28 04:17:41,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.6574788093566895, cross_entropy: 1.6574788093566895 +[2025-04-28 04:17:42,352][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 1.8637762069702148, cross_entropy: 1.8637762069702148 +[2025-04-28 04:17:43,814][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.7267959117889404, cross_entropy: 2.7267959117889404 +[2025-04-28 04:17:44,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 1.8359713554382324, cross_entropy: 1.8359713554382324 +[2025-04-28 04:17:46,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 3.166109561920166, cross_entropy: 3.166109561920166 +[2025-04-28 04:17:47,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.5997016429901123, cross_entropy: 1.5997016429901123 +[2025-04-28 04:17:49,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 2.5087194442749023, cross_entropy: 2.5087194442749023 +[2025-04-28 04:17:50,395][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 1.6196869611740112, cross_entropy: 1.6196869611740112 +[2025-04-28 04:17:51,930][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.5038410425186157, cross_entropy: 1.5038410425186157 +[2025-04-28 04:17:53,002][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.8021864891052246, cross_entropy: 1.8021864891052246 +[2025-04-28 04:17:54,140][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.0762758255004883, cross_entropy: 2.0762758255004883 +[2025-04-28 04:17:55,573][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 2.7306246757507324, cross_entropy: 2.7306246757507324 +[2025-04-28 04:17:56,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 2.325533151626587, cross_entropy: 2.325533151626587 +[2025-04-28 04:17:57,990][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.140239953994751, cross_entropy: 1.140239953994751 +[2025-04-28 04:17:59,340][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.4299803972244263, cross_entropy: 1.4299803972244263 +[2025-04-28 04:18:00,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.7319071292877197, cross_entropy: 2.7319071292877197 +[2025-04-28 04:18:01,718][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.250993013381958, cross_entropy: 1.250993013381958 +[2025-04-28 04:18:04,074][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 3.1350436210632324, cross_entropy: 3.1350436210632324 +[2025-04-28 04:18:04,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.3324735164642334, cross_entropy: 2.3324735164642334 +[2025-04-28 04:18:06,447][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 2.4267830848693848, cross_entropy: 2.4267830848693848 +[2025-04-28 04:18:07,515][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.5466370582580566, cross_entropy: 1.5466370582580566 +[2025-04-28 04:18:08,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.839529037475586, cross_entropy: 2.839529037475586 +[2025-04-28 04:18:10,019][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 2.3095579147338867, cross_entropy: 2.3095579147338867 +[2025-04-28 04:18:10,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 2.04304838180542, cross_entropy: 2.04304838180542 +[2025-04-28 04:18:12,206][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.6588460206985474, cross_entropy: 1.6588460206985474 +[2025-04-28 04:18:13,124][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.5512633323669434, cross_entropy: 1.5512633323669434 +[2025-04-28 04:18:14,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.3819310665130615, cross_entropy: 2.3819310665130615 +[2025-04-28 04:18:15,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 2.8847835063934326, cross_entropy: 2.8847835063934326 +[2025-04-28 04:18:17,721][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.9281673431396484, cross_entropy: 0.9281673431396484 +[2025-04-28 04:18:18,000][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 2.3305115699768066, cross_entropy: 2.3305115699768066 +[2025-04-28 04:18:21,373][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.4414191246032715, cross_entropy: 2.4414191246032715 +[2025-04-28 04:18:21,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.1191747188568115, cross_entropy: 2.1191747188568115 +[2025-04-28 04:18:23,441][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 2.105792284011841, cross_entropy: 2.105792284011841 +[2025-04-28 04:18:24,305][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 2.9890003204345703, cross_entropy: 2.9890003204345703 +[2025-04-28 04:18:26,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.9113423824310303, cross_entropy: 1.9113423824310303 +[2025-04-28 04:18:26,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.3826628923416138, cross_entropy: 1.3826628923416138 +[2025-04-28 04:18:29,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.4656012058258057, cross_entropy: 1.4656012058258057 +[2025-04-28 04:18:29,745][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.6604843139648438, cross_entropy: 2.6604843139648438 +[2025-04-28 04:18:31,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.9067432880401611, cross_entropy: 1.9067432880401611 +[2025-04-28 04:18:32,624][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.4041588306427, cross_entropy: 2.4041588306427 +[2025-04-28 04:18:34,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 2.055607318878174, cross_entropy: 2.055607318878174 +[2025-04-28 04:18:34,938][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 3.2099251747131348, cross_entropy: 3.2099251747131348 +[2025-04-28 04:18:37,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 3.000427722930908, cross_entropy: 3.000427722930908 +[2025-04-28 04:18:37,429][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.0617823600769043, cross_entropy: 3.0617823600769043 +[2025-04-28 04:18:39,304][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.4052207469940186, cross_entropy: 1.4052207469940186 +[2025-04-28 04:18:39,943][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 1.7739765644073486, cross_entropy: 1.7739765644073486 +[2025-04-28 04:18:42,324][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 2.653862476348877, cross_entropy: 2.653862476348877 +[2025-04-28 04:18:42,592][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.8695454597473145, cross_entropy: 1.8695454597473145 +[2025-04-28 04:18:45,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 1.9162023067474365, cross_entropy: 1.9162023067474365 +[2025-04-28 04:18:45,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 2.1564390659332275, cross_entropy: 2.1564390659332275 +[2025-04-28 04:18:49,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.318319082260132, cross_entropy: 2.318319082260132 +[2025-04-28 04:18:49,637][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 3.418510913848877, cross_entropy: 3.418510913848877 +[2025-04-28 04:18:52,771][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 3.07076096534729, cross_entropy: 3.07076096534729 +[2025-04-28 04:18:53,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 2.2560789585113525, cross_entropy: 2.2560789585113525 +[2025-04-28 04:18:55,251][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 2.9354374408721924, cross_entropy: 2.9354374408721924 +[2025-04-28 04:18:55,518][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.930893898010254, cross_entropy: 2.930893898010254 +[2025-04-28 04:18:57,883][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 2.4788405895233154, cross_entropy: 2.4788405895233154 +[2025-04-28 04:18:58,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 2.9443187713623047, cross_entropy: 2.9443187713623047 +[2025-04-28 04:19:00,660][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.2622125148773193, cross_entropy: 3.2622125148773193 +[2025-04-28 04:19:00,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 2.0803027153015137, cross_entropy: 2.0803027153015137 +[2025-04-28 04:19:03,538][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 3.16139554977417, cross_entropy: 3.16139554977417 +[2025-04-28 04:19:03,821][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 1.7838964462280273, cross_entropy: 1.7838964462280273 +[2025-04-28 04:19:06,775][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.58984375, cross_entropy: 1.58984375 +[2025-04-28 04:19:07,044][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 2.004744291305542, cross_entropy: 2.004744291305542 +[2025-04-28 04:19:09,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 3.1319971084594727, cross_entropy: 3.1319971084594727 +[2025-04-28 04:19:09,903][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 3.169699192047119, cross_entropy: 3.169699192047119 +[2025-04-28 04:19:12,376][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.5385974645614624, cross_entropy: 1.5385974645614624 +[2025-04-28 04:19:12,658][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 2.278719902038574, cross_entropy: 2.278719902038574 +[2025-04-28 04:19:14,909][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 3.1783909797668457, cross_entropy: 3.1783909797668457 +[2025-04-28 04:19:15,178][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.6901819705963135, cross_entropy: 1.6901819705963135 +[2025-04-28 04:19:17,555][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.8660954236984253, cross_entropy: 1.8660954236984253 +[2025-04-28 04:19:17,835][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 2.289285659790039, cross_entropy: 2.289285659790039 +[2025-04-28 04:19:19,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.554091215133667, cross_entropy: 1.554091215133667 +[2025-04-28 04:19:20,201][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 2.0456032752990723, cross_entropy: 2.0456032752990723 +[2025-04-28 04:19:22,894][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 3.2103471755981445, cross_entropy: 3.2103471755981445 +[2025-04-28 04:19:23,175][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 3.2197067737579346, cross_entropy: 3.2197067737579346 +[2025-04-28 04:19:25,939][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 3.2756357192993164, cross_entropy: 3.2756357192993164 +[2025-04-28 04:19:26,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 1.6578752994537354, cross_entropy: 1.6578752994537354 +[2025-04-28 04:19:28,495][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 2.0593647956848145, cross_entropy: 2.0593647956848145 +[2025-04-28 04:19:28,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.2859225273132324, cross_entropy: 1.2859225273132324 +[2025-04-28 04:19:31,248][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.6513843536376953, cross_entropy: 1.6513843536376953 +[2025-04-28 04:19:31,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.8746352195739746, cross_entropy: 2.8746352195739746 +[2025-04-28 04:19:33,572][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.812281608581543, cross_entropy: 2.812281608581543 +[2025-04-28 04:19:33,855][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 3.403193950653076, cross_entropy: 3.403193950653076 +[2025-04-28 04:19:35,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 2.243561029434204, cross_entropy: 2.243561029434204 +[2025-04-28 04:19:36,154][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.671046495437622, cross_entropy: 1.671046495437622 +[2025-04-28 04:19:38,694][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.5001237392425537, cross_entropy: 1.5001237392425537 +[2025-04-28 04:19:38,962][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 2.9049863815307617, cross_entropy: 2.9049863815307617 +[2025-04-28 04:19:41,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 1.747673511505127, cross_entropy: 1.747673511505127 +[2025-04-28 04:19:41,443][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 2.5795366764068604, cross_entropy: 2.5795366764068604 +[2025-04-28 04:19:43,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.1518163681030273, cross_entropy: 2.1518163681030273 +[2025-04-28 04:19:43,730][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 3.099863290786743, cross_entropy: 3.099863290786743 +[2025-04-28 04:19:46,142][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.8795599937438965, cross_entropy: 1.8795599937438965 +[2025-04-28 04:19:46,423][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 3.4477715492248535, cross_entropy: 3.4477715492248535 +[2025-04-28 04:19:48,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.6907410621643066, cross_entropy: 2.6907410621643066 +[2025-04-28 04:19:49,225][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 1.7485690116882324, cross_entropy: 1.7485690116882324 +[2025-04-28 04:19:51,729][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.6024634838104248, cross_entropy: 1.6024634838104248 +[2025-04-28 04:19:52,012][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 3.0418214797973633, cross_entropy: 3.0418214797973633 +[2025-04-28 04:19:54,972][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 2.076467990875244, cross_entropy: 2.076467990875244 +[2025-04-28 04:19:55,246][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 3.4382572174072266, cross_entropy: 3.4382572174072266 +[2025-04-28 04:19:57,602][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.526259183883667, cross_entropy: 1.526259183883667 +[2025-04-28 04:19:57,887][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 2.3597936630249023, cross_entropy: 2.3597936630249023 +[2025-04-28 04:20:00,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.6054723262786865, cross_entropy: 1.6054723262786865 +[2025-04-28 04:20:00,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 1.5642362833023071, cross_entropy: 1.5642362833023071 +[2025-04-28 04:20:03,358][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.6108170747756958, cross_entropy: 1.6108170747756958 +[2025-04-28 04:20:03,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.4114656448364258, cross_entropy: 1.4114656448364258 +[2025-04-28 04:20:05,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 2.86181640625, cross_entropy: 2.86181640625 +[2025-04-28 04:20:06,185][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.6376709938049316, cross_entropy: 1.6376709938049316 +[2025-04-28 04:20:08,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.243791341781616, cross_entropy: 2.243791341781616 +[2025-04-28 04:20:08,686][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.7737727165222168, cross_entropy: 1.7737727165222168 +[2025-04-28 04:20:11,578][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.8412604331970215, cross_entropy: 1.8412604331970215 +[2025-04-28 04:20:11,860][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 1.7663118839263916, cross_entropy: 1.7663118839263916 +[2025-04-28 04:20:14,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 2.7920947074890137, cross_entropy: 2.7920947074890137 +[2025-04-28 04:20:14,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 2.316528797149658, cross_entropy: 2.316528797149658 +[2025-04-28 04:20:16,864][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 3.0646514892578125, cross_entropy: 3.0646514892578125 +[2025-04-28 04:20:17,141][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 2.509463310241699, cross_entropy: 2.509463310241699 +[2025-04-28 04:20:19,821][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 1.8473933935165405, cross_entropy: 1.8473933935165405 +[2025-04-28 04:20:20,104][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 2.081310272216797, cross_entropy: 2.081310272216797 +[2025-04-28 04:20:22,422][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 3.156437635421753, cross_entropy: 3.156437635421753 +[2025-04-28 04:20:22,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.3756165504455566, cross_entropy: 1.3756165504455566 +[2025-04-28 04:20:25,137][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.2030506134033203, cross_entropy: 3.2030506134033203 +[2025-04-28 04:20:25,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.048067808151245, cross_entropy: 2.048067808151245 +[2025-04-28 04:20:27,757][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.9109506607055664, cross_entropy: 2.9109506607055664 +[2025-04-28 04:20:28,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.4543697834014893, cross_entropy: 1.4543697834014893 +[2025-04-28 04:20:30,733][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.9993348121643066, cross_entropy: 1.9993348121643066 +[2025-04-28 04:20:31,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.9848365783691406, cross_entropy: 2.9848365783691406 +[2025-04-28 04:20:33,471][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 3.0734198093414307, cross_entropy: 3.0734198093414307 +[2025-04-28 04:20:33,755][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 2.791841745376587, cross_entropy: 2.791841745376587 +[2025-04-28 04:20:36,198][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 1.7751214504241943, cross_entropy: 1.7751214504241943 +[2025-04-28 04:20:36,479][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.526826858520508, cross_entropy: 2.526826858520508 +[2025-04-28 04:20:39,032][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.505197525024414, cross_entropy: 1.505197525024414 +[2025-04-28 04:20:39,315][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.7129240036010742, cross_entropy: 1.7129240036010742 +[2025-04-28 04:20:41,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 2.852440357208252, cross_entropy: 2.852440357208252 +[2025-04-28 04:20:41,689][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 1.5846999883651733, cross_entropy: 1.5846999883651733 +[2025-04-28 04:20:43,941][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.4756044149398804, cross_entropy: 1.4756044149398804 +[2025-04-28 04:20:44,225][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.4192763566970825, cross_entropy: 1.4192763566970825 +[2025-04-28 04:20:46,516][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 3.1885578632354736, cross_entropy: 3.1885578632354736 +[2025-04-28 04:20:46,797][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.4696779251098633, cross_entropy: 2.4696779251098633 +[2025-04-28 04:20:48,732][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.8126931190490723, cross_entropy: 1.8126931190490723 +[2025-04-28 04:20:49,001][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.6632790565490723, cross_entropy: 2.6632790565490723 +[2025-04-28 04:20:51,455][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 3.2432827949523926, cross_entropy: 3.2432827949523926 +[2025-04-28 04:20:51,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 2.9615092277526855, cross_entropy: 2.9615092277526855 +[2025-04-28 04:20:54,228][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 2.0821754932403564, cross_entropy: 2.0821754932403564 +[2025-04-28 04:20:54,510][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 3.1864211559295654, cross_entropy: 3.1864211559295654 +[2025-04-28 04:20:57,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 3.161741256713867, cross_entropy: 3.161741256713867 +[2025-04-28 04:20:57,432][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/iteration2000.pth. +[2025-04-28 04:20:57,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.2325692176818848, cross_entropy: 1.2325692176818848 +[2025-04-28 04:21:00,327][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 3.0823564529418945, cross_entropy: 3.0823564529418945 +[2025-04-28 04:21:00,612][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.7825775146484375, cross_entropy: 2.7825775146484375 +[2025-04-28 04:21:03,140][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 1.365626335144043, cross_entropy: 1.365626335144043 +[2025-04-28 04:21:03,422][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 2.991870880126953, cross_entropy: 2.991870880126953 +[2025-04-28 04:21:06,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.642366886138916, cross_entropy: 2.642366886138916 +[2025-04-28 04:21:06,386][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 3.4641690254211426, cross_entropy: 3.4641690254211426 +[2025-04-28 04:21:09,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.5240871906280518, cross_entropy: 2.5240871906280518 +[2025-04-28 04:21:09,578][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 2.0415849685668945, cross_entropy: 2.0415849685668945 +[2025-04-28 04:21:11,766][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 2.3050239086151123, cross_entropy: 2.3050239086151123 +[2025-04-28 04:21:12,086][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 3.036438465118408, cross_entropy: 3.036438465118408 +[2025-04-28 04:21:15,299][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 2.213054656982422, cross_entropy: 2.213054656982422 +[2025-04-28 04:21:15,583][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.6294174194335938, cross_entropy: 1.6294174194335938 +[2025-04-28 04:21:18,842][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 1.4289557933807373, cross_entropy: 1.4289557933807373 +[2025-04-28 04:21:19,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.7754572629928589, cross_entropy: 1.7754572629928589 +[2025-04-28 04:21:21,575][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.820079803466797, cross_entropy: 2.820079803466797 +[2025-04-28 04:21:21,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.6084485054016113, cross_entropy: 1.6084485054016113 +[2025-04-28 04:21:24,069][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 3.1925408840179443, cross_entropy: 3.1925408840179443 +[2025-04-28 04:21:24,352][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.512620449066162, cross_entropy: 2.512620449066162 +[2025-04-28 04:21:26,407][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 3.271129846572876, cross_entropy: 3.271129846572876 +[2025-04-28 04:21:26,692][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 2.762651205062866, cross_entropy: 2.762651205062866 +[2025-04-28 04:21:29,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.6007609367370605, cross_entropy: 2.6007609367370605 +[2025-04-28 04:21:29,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 2.3318228721618652, cross_entropy: 2.3318228721618652 +[2025-04-28 04:21:32,532][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 2.5708227157592773, cross_entropy: 2.5708227157592773 +[2025-04-28 04:21:32,814][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 1.4381356239318848, cross_entropy: 1.4381356239318848 +[2025-04-28 04:21:35,204][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 3.4629178047180176, cross_entropy: 3.4629178047180176 +[2025-04-28 04:21:35,484][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 1.5532938241958618, cross_entropy: 1.5532938241958618 +[2025-04-28 04:21:37,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 3.1762306690216064, cross_entropy: 3.1762306690216064 +[2025-04-28 04:21:38,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.9729061126708984, cross_entropy: 2.9729061126708984 +[2025-04-28 04:21:40,565][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 0.9995795488357544, cross_entropy: 0.9995795488357544 +[2025-04-28 04:21:40,833][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.8126893043518066, cross_entropy: 2.8126893043518066 +[2025-04-28 04:21:43,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 2.613795280456543, cross_entropy: 2.613795280456543 +[2025-04-28 04:21:43,345][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.6998534202575684, cross_entropy: 1.6998534202575684 +[2025-04-28 04:21:45,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 3.2688002586364746, cross_entropy: 3.2688002586364746 +[2025-04-28 04:21:46,019][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 2.263643264770508, cross_entropy: 2.263643264770508 +[2025-04-28 04:21:48,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 3.3070614337921143, cross_entropy: 3.3070614337921143 +[2025-04-28 04:21:48,712][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.831506609916687, cross_entropy: 1.831506609916687 +[2025-04-28 04:21:50,535][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.6464680433273315, cross_entropy: 1.6464680433273315 +[2025-04-28 04:21:50,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 3.0208740234375, cross_entropy: 3.0208740234375 +[2025-04-28 04:21:54,366][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 3.1876978874206543, cross_entropy: 3.1876978874206543 +[2025-04-28 04:21:54,645][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 1.4399261474609375, cross_entropy: 1.4399261474609375 +[2025-04-28 04:21:56,934][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 3.0922839641571045, cross_entropy: 3.0922839641571045 +[2025-04-28 04:21:57,216][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 3.175607204437256, cross_entropy: 3.175607204437256 +[2025-04-28 04:21:59,584][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.2141547203063965, cross_entropy: 2.2141547203063965 +[2025-04-28 04:21:59,869][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 3.004612445831299, cross_entropy: 3.004612445831299 +[2025-04-28 04:22:02,521][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 1.2074297666549683, cross_entropy: 1.2074297666549683 +[2025-04-28 04:22:02,801][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.3614585399627686, cross_entropy: 1.3614585399627686 +[2025-04-28 04:22:05,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.32224702835083, cross_entropy: 2.32224702835083 +[2025-04-28 04:22:05,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.155707836151123, cross_entropy: 1.155707836151123 +[2025-04-28 04:22:08,499][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 1.6859301328659058, cross_entropy: 1.6859301328659058 +[2025-04-28 04:22:08,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.3081156015396118, cross_entropy: 1.3081156015396118 +[2025-04-28 04:22:11,247][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 3.3748559951782227, cross_entropy: 3.3748559951782227 +[2025-04-28 04:22:11,516][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.49363374710083, cross_entropy: 1.49363374710083 +[2025-04-28 04:22:14,331][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.3975296020507812, cross_entropy: 1.3975296020507812 +[2025-04-28 04:22:14,611][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 2.253654718399048, cross_entropy: 2.253654718399048 +[2025-04-28 04:22:17,243][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 1.6658294200897217, cross_entropy: 1.6658294200897217 +[2025-04-28 04:22:17,510][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.8229303359985352, cross_entropy: 1.8229303359985352 +[2025-04-28 04:22:19,865][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.3425583839416504, cross_entropy: 2.3425583839416504 +[2025-04-28 04:22:20,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 3.1055197715759277, cross_entropy: 3.1055197715759277 +[2025-04-28 04:22:22,552][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 1.7307614088058472, cross_entropy: 1.7307614088058472 +[2025-04-28 04:22:22,832][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.7276134490966797, cross_entropy: 1.7276134490966797 +[2025-04-28 04:22:25,059][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.1351536512374878, cross_entropy: 1.1351536512374878 +[2025-04-28 04:22:25,326][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.8362114429473877, cross_entropy: 2.8362114429473877 +[2025-04-28 04:22:27,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 2.357179641723633, cross_entropy: 2.357179641723633 +[2025-04-28 04:22:27,960][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.2545313835144043, cross_entropy: 2.2545313835144043 +[2025-04-28 04:22:29,806][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 3.2984256744384766, cross_entropy: 3.2984256744384766 +[2025-04-28 04:22:30,089][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 3.279935836791992, cross_entropy: 3.279935836791992 +[2025-04-28 04:22:32,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 3.275259256362915, cross_entropy: 3.275259256362915 +[2025-04-28 04:22:32,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 1.9554425477981567, cross_entropy: 1.9554425477981567 +[2025-04-28 04:22:34,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.679293155670166, cross_entropy: 1.679293155670166 +[2025-04-28 04:22:35,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.8030765056610107, cross_entropy: 1.8030765056610107 +[2025-04-28 04:22:37,954][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.9872524738311768, cross_entropy: 1.9872524738311768 +[2025-04-28 04:22:38,223][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.958839178085327, cross_entropy: 2.958839178085327 +[2025-04-28 04:22:41,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.6834886074066162, cross_entropy: 1.6834886074066162 +[2025-04-28 04:22:41,384][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.2744131088256836, cross_entropy: 2.2744131088256836 +[2025-04-28 04:22:43,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 1.6685874462127686, cross_entropy: 1.6685874462127686 +[2025-04-28 04:22:43,686][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 1.3514584302902222, cross_entropy: 1.3514584302902222 +[2025-04-28 04:22:46,089][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.7786319255828857, cross_entropy: 2.7786319255828857 +[2025-04-28 04:22:46,370][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.5968291759490967, cross_entropy: 1.5968291759490967 +[2025-04-28 04:22:48,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 1.8461614847183228, cross_entropy: 1.8461614847183228 +[2025-04-28 04:22:48,913][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.0211100578308105, cross_entropy: 2.0211100578308105 +[2025-04-28 04:22:50,593][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 3.178088426589966, cross_entropy: 3.178088426589966 +[2025-04-28 04:22:50,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.447387456893921, cross_entropy: 1.447387456893921 +[2025-04-28 04:22:53,021][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 2.385655403137207, cross_entropy: 2.385655403137207 +[2025-04-28 04:22:53,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.326014757156372, cross_entropy: 1.326014757156372 +[2025-04-28 04:22:56,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 2.936037063598633, cross_entropy: 2.936037063598633 +[2025-04-28 04:22:56,366][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.2453088760375977, cross_entropy: 1.2453088760375977 +[2025-04-28 04:22:58,830][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.4493086338043213, cross_entropy: 1.4493086338043213 +[2025-04-28 04:22:59,098][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.4527397155761719, cross_entropy: 1.4527397155761719 +[2025-04-28 04:23:01,757][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 2.6299917697906494, cross_entropy: 2.6299917697906494 +[2025-04-28 04:23:02,038][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.621253728866577, cross_entropy: 2.621253728866577 +[2025-04-28 04:23:04,588][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 2.045328140258789, cross_entropy: 2.045328140258789 +[2025-04-28 04:23:04,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 2.0010857582092285, cross_entropy: 2.0010857582092285 +[2025-04-28 04:23:08,620][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 1.6648859977722168, cross_entropy: 1.6648859977722168 +[2025-04-28 04:23:08,902][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 1.2895755767822266, cross_entropy: 1.2895755767822266 +[2025-04-28 04:23:11,492][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.6263048648834229, cross_entropy: 1.6263048648834229 +[2025-04-28 04:23:11,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 2.232114315032959, cross_entropy: 2.232114315032959 +[2025-04-28 04:23:15,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.2331538200378418, cross_entropy: 1.2331538200378418 +[2025-04-28 04:23:15,351][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.5254261493682861, cross_entropy: 1.5254261493682861 +[2025-04-28 04:23:18,370][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 2.6924867630004883, cross_entropy: 2.6924867630004883 +[2025-04-28 04:23:18,650][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.325453519821167, cross_entropy: 1.325453519821167 +[2025-04-28 04:23:21,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 3.3755643367767334, cross_entropy: 3.3755643367767334 +[2025-04-28 04:23:21,780][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.5843696594238281, cross_entropy: 1.5843696594238281 +[2025-04-28 04:23:23,919][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.6475863456726074, cross_entropy: 2.6475863456726074 +[2025-04-28 04:23:24,186][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.6617285013198853, cross_entropy: 1.6617285013198853 +[2025-04-28 04:23:26,845][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.8016419410705566, cross_entropy: 2.8016419410705566 +[2025-04-28 04:23:27,126][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.2876050472259521, cross_entropy: 1.2876050472259521 +[2025-04-28 04:23:29,657][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 3.2688117027282715, cross_entropy: 3.2688117027282715 +[2025-04-28 04:23:29,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 3.0993525981903076, cross_entropy: 3.0993525981903076 +[2025-04-28 04:23:32,221][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 3.1507391929626465, cross_entropy: 3.1507391929626465 +[2025-04-28 04:23:32,489][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.6035007238388062, cross_entropy: 1.6035007238388062 +[2025-04-28 04:23:35,470][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 3.1898462772369385, cross_entropy: 3.1898462772369385 +[2025-04-28 04:23:35,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 2.268944263458252, cross_entropy: 2.268944263458252 +[2025-04-28 04:23:37,756][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 3.055551528930664, cross_entropy: 3.055551528930664 +[2025-04-28 04:23:38,040][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 2.4562864303588867, cross_entropy: 2.4562864303588867 +[2025-04-28 04:23:41,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 1.7226017713546753, cross_entropy: 1.7226017713546753 +[2025-04-28 04:23:41,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 3.2969112396240234, cross_entropy: 3.2969112396240234 +[2025-04-28 04:23:44,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.818608045578003, cross_entropy: 1.818608045578003 +[2025-04-28 04:23:44,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.455874443054199, cross_entropy: 3.455874443054199 +[2025-04-28 04:23:47,230][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.310791015625, cross_entropy: 2.310791015625 +[2025-04-28 04:23:47,508][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 3.3240294456481934, cross_entropy: 3.3240294456481934 +[2025-04-28 04:23:50,097][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 2.209290027618408, cross_entropy: 2.209290027618408 +[2025-04-28 04:23:50,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.9181978702545166, cross_entropy: 1.9181978702545166 +[2025-04-28 04:23:52,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.5204858779907227, cross_entropy: 1.5204858779907227 +[2025-04-28 04:23:52,815][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.777476191520691, cross_entropy: 1.777476191520691 +[2025-04-28 04:23:55,464][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.626516580581665, cross_entropy: 1.626516580581665 +[2025-04-28 04:23:55,744][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 1.5488736629486084, cross_entropy: 1.5488736629486084 +[2025-04-28 04:23:58,117][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 2.7073612213134766, cross_entropy: 2.7073612213134766 +[2025-04-28 04:23:58,397][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 3.4822683334350586, cross_entropy: 3.4822683334350586 +[2025-04-28 04:24:00,780][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 2.0334248542785645, cross_entropy: 2.0334248542785645 +[2025-04-28 04:24:01,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 1.76123046875, cross_entropy: 1.76123046875 +[2025-04-28 04:24:03,060][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.1746180057525635, cross_entropy: 1.1746180057525635 +[2025-04-28 04:24:03,343][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.3844237327575684, cross_entropy: 1.3844237327575684 +[2025-04-28 04:24:05,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 3.050785541534424, cross_entropy: 3.050785541534424 +[2025-04-28 04:24:06,049][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.867918014526367, cross_entropy: 2.867918014526367 +[2025-04-28 04:24:08,380][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 2.3103716373443604, cross_entropy: 2.3103716373443604 +[2025-04-28 04:26:09,076][BaseTrainer][INFO] - [Epoch 6/10] (train) 2.2664530277252197, cross_entropy: 2.2664530277252197 +[2025-04-28 04:26:09,077][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.6510937213897705, cross_entropy: 1.6510937213897705 +[2025-04-28 04:26:09,288][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 04:26:09,448][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch6.pth. +[2025-04-28 04:26:09,663][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:26:13,152][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.6858198642730713, cross_entropy: 2.6858198642730713 +[2025-04-28 04:26:13,421][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.970557689666748, cross_entropy: 2.970557689666748 +[2025-04-28 04:26:15,639][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 1.5342923402786255, cross_entropy: 1.5342923402786255 +[2025-04-28 04:26:15,920][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 1.2130084037780762, cross_entropy: 1.2130084037780762 +[2025-04-28 04:26:17,852][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 1.4547345638275146, cross_entropy: 1.4547345638275146 +[2025-04-28 04:26:18,685][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.7923781871795654, cross_entropy: 1.7923781871795654 +[2025-04-28 04:26:20,390][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 3.1476809978485107, cross_entropy: 3.1476809978485107 +[2025-04-28 04:26:21,240][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 2.165733814239502, cross_entropy: 2.165733814239502 +[2025-04-28 04:26:23,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.8845043182373047, cross_entropy: 1.8845043182373047 +[2025-04-28 04:26:24,094][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.8497313261032104, cross_entropy: 1.8497313261032104 +[2025-04-28 04:26:26,331][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 3.186377763748169, cross_entropy: 3.186377763748169 +[2025-04-28 04:26:26,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 2.6383156776428223, cross_entropy: 2.6383156776428223 +[2025-04-28 04:26:28,394][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.935582160949707, cross_entropy: 2.935582160949707 +[2025-04-28 04:26:28,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 3.246978282928467, cross_entropy: 3.246978282928467 +[2025-04-28 04:26:30,817][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.7252588272094727, cross_entropy: 2.7252588272094727 +[2025-04-28 04:26:31,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.5081558227539062, cross_entropy: 2.5081558227539062 +[2025-04-28 04:26:33,340][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.452101230621338, cross_entropy: 2.452101230621338 +[2025-04-28 04:26:33,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.2514801025390625, cross_entropy: 3.2514801025390625 +[2025-04-28 04:26:35,866][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 3.2179689407348633, cross_entropy: 3.2179689407348633 +[2025-04-28 04:26:36,146][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.714271068572998, cross_entropy: 1.714271068572998 +[2025-04-28 04:26:38,066][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.3950703144073486, cross_entropy: 1.3950703144073486 +[2025-04-28 04:26:38,337][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.654527187347412, cross_entropy: 2.654527187347412 +[2025-04-28 04:26:41,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 2.3719735145568848, cross_entropy: 2.3719735145568848 +[2025-04-28 04:26:41,352][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.7345712184906006, cross_entropy: 2.7345712184906006 +[2025-04-28 04:26:43,784][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.936647653579712, cross_entropy: 1.936647653579712 +[2025-04-28 04:26:44,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.616586446762085, cross_entropy: 2.616586446762085 +[2025-04-28 04:26:45,799][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 3.032362461090088, cross_entropy: 3.032362461090088 +[2025-04-28 04:26:46,237][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 2.9609804153442383, cross_entropy: 2.9609804153442383 +[2025-04-28 04:26:48,124][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.5582001209259033, cross_entropy: 1.5582001209259033 +[2025-04-28 04:26:48,671][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.316495656967163, cross_entropy: 1.316495656967163 +[2025-04-28 04:26:50,833][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.2732605934143066, cross_entropy: 2.2732605934143066 +[2025-04-28 04:26:51,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.800398588180542, cross_entropy: 2.800398588180542 +[2025-04-28 04:26:53,378][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.7343196868896484, cross_entropy: 2.7343196868896484 +[2025-04-28 04:26:54,138][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.1704497337341309, cross_entropy: 1.1704497337341309 +[2025-04-28 04:26:56,351][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.933119773864746, cross_entropy: 2.933119773864746 +[2025-04-28 04:26:56,686][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.9106733798980713, cross_entropy: 1.9106733798980713 +[2025-04-28 04:26:59,914][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 3.230701208114624, cross_entropy: 3.230701208114624 +[2025-04-28 04:27:00,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.225698709487915, cross_entropy: 1.225698709487915 +[2025-04-28 04:27:02,188][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 1.3305469751358032, cross_entropy: 1.3305469751358032 +[2025-04-28 04:27:02,469][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.549659013748169, cross_entropy: 1.549659013748169 +[2025-04-28 04:27:04,354][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.4468525648117065, cross_entropy: 1.4468525648117065 +[2025-04-28 04:27:04,623][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.421614646911621, cross_entropy: 2.421614646911621 +[2025-04-28 04:27:06,758][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.981844663619995, cross_entropy: 2.981844663619995 +[2025-04-28 04:27:07,038][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 3.503640651702881, cross_entropy: 3.503640651702881 +[2025-04-28 04:27:09,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.332469940185547, cross_entropy: 2.332469940185547 +[2025-04-28 04:27:09,621][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 2.8117926120758057, cross_entropy: 2.8117926120758057 +[2025-04-28 04:27:11,410][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 1.3214402198791504, cross_entropy: 1.3214402198791504 +[2025-04-28 04:27:11,678][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 2.7694082260131836, cross_entropy: 2.7694082260131836 +[2025-04-28 04:27:14,173][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.65478515625, cross_entropy: 2.65478515625 +[2025-04-28 04:27:14,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.928837537765503, cross_entropy: 1.928837537765503 +[2025-04-28 04:27:16,285][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 3.043942928314209, cross_entropy: 3.043942928314209 +[2025-04-28 04:27:16,568][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 3.3828113079071045, cross_entropy: 3.3828113079071045 +[2025-04-28 04:27:19,618][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 2.566530704498291, cross_entropy: 2.566530704498291 +[2025-04-28 04:27:19,904][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 3.037763833999634, cross_entropy: 3.037763833999634 +[2025-04-28 04:27:22,003][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 2.3487842082977295, cross_entropy: 2.3487842082977295 +[2025-04-28 04:27:22,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 1.5620083808898926, cross_entropy: 1.5620083808898926 +[2025-04-28 04:27:24,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.8042019605636597, cross_entropy: 1.8042019605636597 +[2025-04-28 04:27:24,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.2353684902191162, cross_entropy: 1.2353684902191162 +[2025-04-28 04:27:28,256][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 3.1711864471435547, cross_entropy: 3.1711864471435547 +[2025-04-28 04:27:28,537][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.478048324584961, cross_entropy: 1.478048324584961 +[2025-04-28 04:27:30,624][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 1.9225819110870361, cross_entropy: 1.9225819110870361 +[2025-04-28 04:27:30,892][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.571808934211731, cross_entropy: 1.571808934211731 +[2025-04-28 04:27:33,011][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.7813836336135864, cross_entropy: 1.7813836336135864 +[2025-04-28 04:27:33,280][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 1.2422822713851929, cross_entropy: 1.2422822713851929 +[2025-04-28 04:27:35,193][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.5757126808166504, cross_entropy: 2.5757126808166504 +[2025-04-28 04:27:35,474][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.8510890007019043, cross_entropy: 1.8510890007019043 +[2025-04-28 04:27:37,538][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.491910696029663, cross_entropy: 1.491910696029663 +[2025-04-28 04:27:37,819][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.651383399963379, cross_entropy: 2.651383399963379 +[2025-04-28 04:27:40,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 1.4681529998779297, cross_entropy: 1.4681529998779297 +[2025-04-28 04:27:40,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 2.390385627746582, cross_entropy: 2.390385627746582 +[2025-04-28 04:27:43,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 3.1223318576812744, cross_entropy: 3.1223318576812744 +[2025-04-28 04:27:43,658][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 2.9153995513916016, cross_entropy: 2.9153995513916016 +[2025-04-28 04:27:45,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 2.4869728088378906, cross_entropy: 2.4869728088378906 +[2025-04-28 04:27:46,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 3.295222520828247, cross_entropy: 3.295222520828247 +[2025-04-28 04:27:47,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 1.7201870679855347, cross_entropy: 1.7201870679855347 +[2025-04-28 04:27:47,932][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.5364505052566528, cross_entropy: 1.5364505052566528 +[2025-04-28 04:27:50,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.5624160766601562, cross_entropy: 2.5624160766601562 +[2025-04-28 04:27:50,479][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 2.2470126152038574, cross_entropy: 2.2470126152038574 +[2025-04-28 04:27:52,724][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.7917139530181885, cross_entropy: 2.7917139530181885 +[2025-04-28 04:27:52,993][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 2.686098098754883, cross_entropy: 2.686098098754883 +[2025-04-28 04:27:54,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 1.0481207370758057, cross_entropy: 1.0481207370758057 +[2025-04-28 04:27:55,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 2.7637972831726074, cross_entropy: 2.7637972831726074 +[2025-04-28 04:27:57,651][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.667180061340332, cross_entropy: 2.667180061340332 +[2025-04-28 04:27:57,932][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 1.995837688446045, cross_entropy: 1.995837688446045 +[2025-04-28 04:28:00,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.636475682258606, cross_entropy: 1.636475682258606 +[2025-04-28 04:28:00,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 1.8973544836044312, cross_entropy: 1.8973544836044312 +[2025-04-28 04:28:02,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 1.4093024730682373, cross_entropy: 1.4093024730682373 +[2025-04-28 04:28:03,203][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 2.4436287879943848, cross_entropy: 2.4436287879943848 +[2025-04-28 04:28:04,903][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 3.1049370765686035, cross_entropy: 3.1049370765686035 +[2025-04-28 04:28:05,504][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.7827929258346558, cross_entropy: 1.7827929258346558 +[2025-04-28 04:28:07,906][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 3.0985517501831055, cross_entropy: 3.0985517501831055 +[2025-04-28 04:28:08,405][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 3.081578254699707, cross_entropy: 3.081578254699707 +[2025-04-28 04:28:10,611][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.6438422203063965, cross_entropy: 1.6438422203063965 +[2025-04-28 04:28:11,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.668900489807129, cross_entropy: 1.668900489807129 +[2025-04-28 04:28:12,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 3.088233470916748, cross_entropy: 3.088233470916748 +[2025-04-28 04:28:13,507][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.8453298807144165, cross_entropy: 1.8453298807144165 +[2025-04-28 04:28:15,027][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.2142893075942993, cross_entropy: 1.2142893075942993 +[2025-04-28 04:28:16,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 1.761366605758667, cross_entropy: 1.761366605758667 +[2025-04-28 04:28:18,146][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.980485439300537, cross_entropy: 1.980485439300537 +[2025-04-28 04:28:18,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 2.0233397483825684, cross_entropy: 2.0233397483825684 +[2025-04-28 04:28:21,124][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 1.7598296403884888, cross_entropy: 1.7598296403884888 +[2025-04-28 04:28:21,425][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 1.5189759731292725, cross_entropy: 1.5189759731292725 +[2025-04-28 04:28:24,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.2437777519226074, cross_entropy: 2.2437777519226074 +[2025-04-28 04:28:24,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.851224660873413, cross_entropy: 1.851224660873413 +[2025-04-28 04:28:27,082][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.481014370918274, cross_entropy: 1.481014370918274 +[2025-04-28 04:28:27,365][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 2.942751169204712, cross_entropy: 2.942751169204712 +[2025-04-28 04:28:29,581][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 2.2150254249572754, cross_entropy: 2.2150254249572754 +[2025-04-28 04:28:29,863][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.3812949657440186, cross_entropy: 1.3812949657440186 +[2025-04-28 04:28:32,613][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 1.4754788875579834, cross_entropy: 1.4754788875579834 +[2025-04-28 04:28:32,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 1.6004081964492798, cross_entropy: 1.6004081964492798 +[2025-04-28 04:28:35,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 1.216278076171875, cross_entropy: 1.216278076171875 +[2025-04-28 04:28:35,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 1.381203055381775, cross_entropy: 1.381203055381775 +[2025-04-28 04:28:37,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.4440028667449951, cross_entropy: 1.4440028667449951 +[2025-04-28 04:28:37,643][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 2.1063499450683594, cross_entropy: 2.1063499450683594 +[2025-04-28 04:28:40,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.7121620178222656, cross_entropy: 1.7121620178222656 +[2025-04-28 04:28:40,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 1.4592329263687134, cross_entropy: 1.4592329263687134 +[2025-04-28 04:28:42,693][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.3476489782333374, cross_entropy: 1.3476489782333374 +[2025-04-28 04:28:42,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 1.199529767036438, cross_entropy: 1.199529767036438 +[2025-04-28 04:28:45,481][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.6357531547546387, cross_entropy: 2.6357531547546387 +[2025-04-28 04:28:45,762][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 3.2714877128601074, cross_entropy: 3.2714877128601074 +[2025-04-28 04:28:47,769][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.546725869178772, cross_entropy: 1.546725869178772 +[2025-04-28 04:28:48,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 2.344796657562256, cross_entropy: 2.344796657562256 +[2025-04-28 04:28:51,270][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.4406580924987793, cross_entropy: 2.4406580924987793 +[2025-04-28 04:28:51,553][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.3999807834625244, cross_entropy: 1.3999807834625244 +[2025-04-28 04:28:54,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 1.5834916830062866, cross_entropy: 1.5834916830062866 +[2025-04-28 04:28:54,734][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.5781584978103638, cross_entropy: 1.5781584978103638 +[2025-04-28 04:28:58,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.338808059692383, cross_entropy: 3.338808059692383 +[2025-04-28 04:28:58,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 2.934032917022705, cross_entropy: 2.934032917022705 +[2025-04-28 04:29:01,031][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 1.560065507888794, cross_entropy: 1.560065507888794 +[2025-04-28 04:29:01,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 3.1855549812316895, cross_entropy: 3.1855549812316895 +[2025-04-28 04:29:04,147][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 0.9867386817932129, cross_entropy: 0.9867386817932129 +[2025-04-28 04:29:04,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 1.2685720920562744, cross_entropy: 1.2685720920562744 +[2025-04-28 04:29:06,210][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 2.791900634765625, cross_entropy: 2.791900634765625 +[2025-04-28 04:29:06,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 3.050692558288574, cross_entropy: 3.050692558288574 +[2025-04-28 04:29:08,854][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 3.277249336242676, cross_entropy: 3.277249336242676 +[2025-04-28 04:29:09,135][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.754575252532959, cross_entropy: 2.754575252532959 +[2025-04-28 04:29:11,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 3.210829257965088, cross_entropy: 3.210829257965088 +[2025-04-28 04:29:12,095][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.854914903640747, cross_entropy: 1.854914903640747 +[2025-04-28 04:29:14,688][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.5382089614868164, cross_entropy: 1.5382089614868164 +[2025-04-28 04:29:14,969][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.901294469833374, cross_entropy: 2.901294469833374 +[2025-04-28 04:29:17,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 1.342134714126587, cross_entropy: 1.342134714126587 +[2025-04-28 04:29:17,635][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.551432490348816, cross_entropy: 1.551432490348816 +[2025-04-28 04:29:19,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 3.0870018005371094, cross_entropy: 3.0870018005371094 +[2025-04-28 04:29:19,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.8871541023254395, cross_entropy: 2.8871541023254395 +[2025-04-28 04:29:22,745][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.5395644903182983, cross_entropy: 1.5395644903182983 +[2025-04-28 04:29:23,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 2.2384696006774902, cross_entropy: 2.2384696006774902 +[2025-04-28 04:29:25,077][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 2.5487234592437744, cross_entropy: 2.5487234592437744 +[2025-04-28 04:29:25,359][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 1.9935423135757446, cross_entropy: 1.9935423135757446 +[2025-04-28 04:29:28,091][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.785275936126709, cross_entropy: 2.785275936126709 +[2025-04-28 04:29:28,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 2.802098274230957, cross_entropy: 2.802098274230957 +[2025-04-28 04:29:30,569][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.650993585586548, cross_entropy: 2.650993585586548 +[2025-04-28 04:29:30,851][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 2.8435511589050293, cross_entropy: 2.8435511589050293 +[2025-04-28 04:29:33,354][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.263744354248047, cross_entropy: 2.263744354248047 +[2025-04-28 04:29:33,637][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 3.0712599754333496, cross_entropy: 3.0712599754333496 +[2025-04-28 04:29:35,980][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 2.035194158554077, cross_entropy: 2.035194158554077 +[2025-04-28 04:29:36,262][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 1.5268303155899048, cross_entropy: 1.5268303155899048 +[2025-04-28 04:29:38,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 2.439357280731201, cross_entropy: 2.439357280731201 +[2025-04-28 04:29:38,718][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 1.392087697982788, cross_entropy: 1.392087697982788 +[2025-04-28 04:29:41,490][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.939104437828064, cross_entropy: 1.939104437828064 +[2025-04-28 04:29:41,771][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 2.0736684799194336, cross_entropy: 2.0736684799194336 +[2025-04-28 04:29:43,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 3.3804898262023926, cross_entropy: 3.3804898262023926 +[2025-04-28 04:29:44,064][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 2.4923524856567383, cross_entropy: 2.4923524856567383 +[2025-04-28 04:29:46,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.4730346202850342, cross_entropy: 1.4730346202850342 +[2025-04-28 04:29:46,389][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 2.9394493103027344, cross_entropy: 2.9394493103027344 +[2025-04-28 04:29:48,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.2218084335327148, cross_entropy: 1.2218084335327148 +[2025-04-28 04:29:48,325][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 2.550332546234131, cross_entropy: 2.550332546234131 +[2025-04-28 04:29:50,255][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 3.278898239135742, cross_entropy: 3.278898239135742 +[2025-04-28 04:29:50,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 1.6605465412139893, cross_entropy: 1.6605465412139893 +[2025-04-28 04:29:53,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.763988971710205, cross_entropy: 1.763988971710205 +[2025-04-28 04:29:53,580][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 2.693056106567383, cross_entropy: 2.693056106567383 +[2025-04-28 04:29:56,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.988769769668579, cross_entropy: 1.988769769668579 +[2025-04-28 04:29:56,320][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 3.1002330780029297, cross_entropy: 3.1002330780029297 +[2025-04-28 04:29:58,449][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 2.9890170097351074, cross_entropy: 2.9890170097351074 +[2025-04-28 04:29:58,723][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 3.0354275703430176, cross_entropy: 3.0354275703430176 +[2025-04-28 04:30:01,098][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 3.614511489868164, cross_entropy: 3.614511489868164 +[2025-04-28 04:30:01,366][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 3.1492180824279785, cross_entropy: 3.1492180824279785 +[2025-04-28 04:30:03,861][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 3.0575013160705566, cross_entropy: 3.0575013160705566 +[2025-04-28 04:30:04,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.361775517463684, cross_entropy: 1.361775517463684 +[2025-04-28 04:30:07,134][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 3.3173327445983887, cross_entropy: 3.3173327445983887 +[2025-04-28 04:30:07,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.0700371265411377, cross_entropy: 1.0700371265411377 +[2025-04-28 04:30:09,750][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 1.760340929031372, cross_entropy: 1.760340929031372 +[2025-04-28 04:30:10,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 2.9074106216430664, cross_entropy: 2.9074106216430664 +[2025-04-28 04:30:12,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 2.632535457611084, cross_entropy: 2.632535457611084 +[2025-04-28 04:30:12,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 2.972978353500366, cross_entropy: 2.972978353500366 +[2025-04-28 04:30:15,132][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.879101037979126, cross_entropy: 1.879101037979126 +[2025-04-28 04:30:15,400][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 1.1204866170883179, cross_entropy: 1.1204866170883179 +[2025-04-28 04:30:18,472][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 3.0902647972106934, cross_entropy: 3.0902647972106934 +[2025-04-28 04:30:18,741][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 3.4226131439208984, cross_entropy: 3.4226131439208984 +[2025-04-28 04:30:22,130][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.774378776550293, cross_entropy: 1.774378776550293 +[2025-04-28 04:30:22,398][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 2.3345794677734375, cross_entropy: 2.3345794677734375 +[2025-04-28 04:30:24,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 2.066575527191162, cross_entropy: 2.066575527191162 +[2025-04-28 04:30:25,070][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.2717047929763794, cross_entropy: 1.2717047929763794 +[2025-04-28 04:30:27,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 3.396974802017212, cross_entropy: 3.396974802017212 +[2025-04-28 04:30:27,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 1.855231761932373, cross_entropy: 1.855231761932373 +[2025-04-28 04:30:30,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 2.4399313926696777, cross_entropy: 2.4399313926696777 +[2025-04-28 04:30:30,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 3.0230488777160645, cross_entropy: 3.0230488777160645 +[2025-04-28 04:30:33,297][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 3.2283849716186523, cross_entropy: 3.2283849716186523 +[2025-04-28 04:30:33,580][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 2.822758197784424, cross_entropy: 2.822758197784424 +[2025-04-28 04:30:36,041][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.056648015975952, cross_entropy: 3.056648015975952 +[2025-04-28 04:30:36,322][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 2.350313186645508, cross_entropy: 2.350313186645508 +[2025-04-28 04:30:38,589][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.9891018867492676, cross_entropy: 2.9891018867492676 +[2025-04-28 04:30:38,872][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.4491846561431885, cross_entropy: 2.4491846561431885 +[2025-04-28 04:30:41,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.6984758377075195, cross_entropy: 1.6984758377075195 +[2025-04-28 04:30:41,569][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.6872832775115967, cross_entropy: 2.6872832775115967 +[2025-04-28 04:30:45,417][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.193002223968506, cross_entropy: 3.193002223968506 +[2025-04-28 04:30:45,687][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 1.648477554321289, cross_entropy: 1.648477554321289 +[2025-04-28 04:30:47,891][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 1.3604488372802734, cross_entropy: 1.3604488372802734 +[2025-04-28 04:30:48,173][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 2.815075635910034, cross_entropy: 2.815075635910034 +[2025-04-28 04:30:50,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 1.0333188772201538, cross_entropy: 1.0333188772201538 +[2025-04-28 04:30:50,783][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 3.0388343334198, cross_entropy: 3.0388343334198 +[2025-04-28 04:30:53,128][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 3.3510148525238037, cross_entropy: 3.3510148525238037 +[2025-04-28 04:30:53,412][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 3.3252220153808594, cross_entropy: 3.3252220153808594 +[2025-04-28 04:30:55,875][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 1.889099359512329, cross_entropy: 1.889099359512329 +[2025-04-28 04:30:56,144][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.046238899230957, cross_entropy: 1.046238899230957 +[2025-04-28 04:30:59,127][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.7539252042770386, cross_entropy: 1.7539252042770386 +[2025-04-28 04:30:59,402][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 2.4473977088928223, cross_entropy: 2.4473977088928223 +[2025-04-28 04:31:02,013][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 3.2878823280334473, cross_entropy: 3.2878823280334473 +[2025-04-28 04:31:02,296][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 3.0783987045288086, cross_entropy: 3.0783987045288086 +[2025-04-28 04:31:04,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 2.001311779022217, cross_entropy: 2.001311779022217 +[2025-04-28 04:31:04,803][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 1.643517017364502, cross_entropy: 1.643517017364502 +[2025-04-28 04:31:07,599][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 1.7333767414093018, cross_entropy: 1.7333767414093018 +[2025-04-28 04:31:07,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 1.4672479629516602, cross_entropy: 1.4672479629516602 +[2025-04-28 04:31:09,816][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 1.8455638885498047, cross_entropy: 1.8455638885498047 +[2025-04-28 04:31:10,100][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 3.0546960830688477, cross_entropy: 3.0546960830688477 +[2025-04-28 04:31:12,462][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 2.894578218460083, cross_entropy: 2.894578218460083 +[2025-04-28 04:31:12,744][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 3.201707601547241, cross_entropy: 3.201707601547241 +[2025-04-28 04:31:14,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 3.0001628398895264, cross_entropy: 3.0001628398895264 +[2025-04-28 04:31:14,972][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 2.654789924621582, cross_entropy: 2.654789924621582 +[2025-04-28 04:31:16,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.3416551351547241, cross_entropy: 1.3416551351547241 +[2025-04-28 04:31:17,198][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 1.5583289861679077, cross_entropy: 1.5583289861679077 +[2025-04-28 04:31:19,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 1.9327102899551392, cross_entropy: 1.9327102899551392 +[2025-04-28 04:31:19,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.3971335887908936, cross_entropy: 1.3971335887908936 +[2025-04-28 04:31:22,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 1.7883214950561523, cross_entropy: 1.7883214950561523 +[2025-04-28 04:31:22,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.2226686477661133, cross_entropy: 2.2226686477661133 +[2025-04-28 04:31:25,146][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 1.3985166549682617, cross_entropy: 1.3985166549682617 +[2025-04-28 04:31:25,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 1.9156079292297363, cross_entropy: 1.9156079292297363 +[2025-04-28 04:31:27,880][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 2.741710662841797, cross_entropy: 2.741710662841797 +[2025-04-28 04:31:28,163][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 1.678605556488037, cross_entropy: 1.678605556488037 +[2025-04-28 04:31:30,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.703805923461914, cross_entropy: 2.703805923461914 +[2025-04-28 04:31:31,274][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.822319984436035, cross_entropy: 2.822319984436035 +[2025-04-28 04:31:33,869][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.2437901496887207, cross_entropy: 2.2437901496887207 +[2025-04-28 04:31:34,152][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 1.4960603713989258, cross_entropy: 1.4960603713989258 +[2025-04-28 04:31:36,416][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 2.6983938217163086, cross_entropy: 2.6983938217163086 +[2025-04-28 04:31:36,685][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 3.3452558517456055, cross_entropy: 3.3452558517456055 +[2025-04-28 04:31:39,845][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.5395166873931885, cross_entropy: 1.5395166873931885 +[2025-04-28 04:31:40,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 2.9384665489196777, cross_entropy: 2.9384665489196777 +[2025-04-28 04:31:42,554][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 2.8938117027282715, cross_entropy: 2.8938117027282715 +[2025-04-28 04:31:42,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 3.21356463432312, cross_entropy: 3.21356463432312 +[2025-04-28 04:31:45,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 1.3483418226242065, cross_entropy: 1.3483418226242065 +[2025-04-28 04:31:46,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.6801598072052, cross_entropy: 2.6801598072052 +[2025-04-28 04:31:48,692][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.656287431716919, cross_entropy: 1.656287431716919 +[2025-04-28 04:31:48,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 2.2557435035705566, cross_entropy: 2.2557435035705566 +[2025-04-28 04:31:51,369][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 2.729433536529541, cross_entropy: 2.729433536529541 +[2025-04-28 04:31:51,638][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 3.175323963165283, cross_entropy: 3.175323963165283 +[2025-04-28 04:31:53,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 1.6051311492919922, cross_entropy: 1.6051311492919922 +[2025-04-28 04:31:53,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.8626818656921387, cross_entropy: 2.8626818656921387 +[2025-04-28 04:31:56,265][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 1.5143108367919922, cross_entropy: 1.5143108367919922 +[2025-04-28 04:31:56,548][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 3.271979331970215, cross_entropy: 3.271979331970215 +[2025-04-28 04:31:58,870][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.271071434020996, cross_entropy: 1.271071434020996 +[2025-04-28 04:31:59,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 1.7730908393859863, cross_entropy: 1.7730908393859863 +[2025-04-28 04:32:01,259][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 2.5367753505706787, cross_entropy: 2.5367753505706787 +[2025-04-28 04:32:01,539][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.6582611799240112, cross_entropy: 1.6582611799240112 +[2025-04-28 04:32:04,369][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.6956000328063965, cross_entropy: 1.6956000328063965 +[2025-04-28 04:32:04,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 2.1076488494873047, cross_entropy: 2.1076488494873047 +[2025-04-28 04:32:06,942][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 2.1918764114379883, cross_entropy: 2.1918764114379883 +[2025-04-28 04:32:07,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 2.061331033706665, cross_entropy: 2.061331033706665 +[2025-04-28 04:32:09,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 2.1626086235046387, cross_entropy: 2.1626086235046387 +[2025-04-28 04:32:09,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.290870189666748, cross_entropy: 2.290870189666748 +[2025-04-28 04:32:12,279][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 2.698465347290039, cross_entropy: 2.698465347290039 +[2025-04-28 04:32:12,561][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.944812297821045, cross_entropy: 1.944812297821045 +[2025-04-28 04:32:15,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 2.6689467430114746, cross_entropy: 2.6689467430114746 +[2025-04-28 04:32:15,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 1.7681207656860352, cross_entropy: 1.7681207656860352 +[2025-04-28 04:32:18,813][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 1.9533231258392334, cross_entropy: 1.9533231258392334 +[2025-04-28 04:32:19,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.6693557500839233, cross_entropy: 1.6693557500839233 +[2025-04-28 04:32:21,182][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.7699387073516846, cross_entropy: 2.7699387073516846 +[2025-04-28 04:32:21,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 2.978745698928833, cross_entropy: 2.978745698928833 +[2025-04-28 04:32:23,809][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.5090670585632324, cross_entropy: 1.5090670585632324 +[2025-04-28 04:32:24,089][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 2.919111490249634, cross_entropy: 2.919111490249634 +[2025-04-28 04:32:27,197][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.439812421798706, cross_entropy: 1.439812421798706 +[2025-04-28 04:32:27,479][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.6190685033798218, cross_entropy: 1.6190685033798218 +[2025-04-28 04:32:29,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 2.462923526763916, cross_entropy: 2.462923526763916 +[2025-04-28 04:32:30,141][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 1.5473273992538452, cross_entropy: 1.5473273992538452 +[2025-04-28 04:32:32,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.6213536262512207, cross_entropy: 2.6213536262512207 +[2025-04-28 04:32:32,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 2.148615837097168, cross_entropy: 2.148615837097168 +[2025-04-28 04:32:35,379][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 2.284221649169922, cross_entropy: 2.284221649169922 +[2025-04-28 04:32:35,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 1.9462192058563232, cross_entropy: 1.9462192058563232 +[2025-04-28 04:32:37,644][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.5004383325576782, cross_entropy: 1.5004383325576782 +[2025-04-28 04:32:37,929][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 1.2520259618759155, cross_entropy: 1.2520259618759155 +[2025-04-28 04:32:40,793][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 1.6918116807937622, cross_entropy: 1.6918116807937622 +[2025-04-28 04:32:41,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.433932065963745, cross_entropy: 2.433932065963745 +[2025-04-28 04:32:45,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.6249595880508423, cross_entropy: 1.6249595880508423 +[2025-04-28 04:32:45,297][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 2.1147754192352295, cross_entropy: 2.1147754192352295 +[2025-04-28 04:32:48,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 3.456514835357666, cross_entropy: 3.456514835357666 +[2025-04-28 04:32:49,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.5127511024475098, cross_entropy: 1.5127511024475098 +[2025-04-28 04:32:51,413][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 1.5060511827468872, cross_entropy: 1.5060511827468872 +[2025-04-28 04:32:51,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.4930763244628906, cross_entropy: 1.4930763244628906 +[2025-04-28 04:32:54,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 3.2328286170959473, cross_entropy: 3.2328286170959473 +[2025-04-28 04:32:54,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 2.0009851455688477, cross_entropy: 2.0009851455688477 +[2025-04-28 04:32:56,521][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.5847325325012207, cross_entropy: 2.5847325325012207 +[2025-04-28 04:32:56,802][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 3.069880247116089, cross_entropy: 3.069880247116089 +[2025-04-28 04:32:59,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.747835636138916, cross_entropy: 2.747835636138916 +[2025-04-28 04:32:59,735][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 1.4468235969543457, cross_entropy: 1.4468235969543457 +[2025-04-28 04:33:02,529][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.2324740886688232, cross_entropy: 1.2324740886688232 +[2025-04-28 04:33:02,810][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.8466038703918457, cross_entropy: 1.8466038703918457 +[2025-04-28 04:33:04,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.3815841674804688, cross_entropy: 1.3815841674804688 +[2025-04-28 04:33:05,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.434682846069336, cross_entropy: 2.434682846069336 +[2025-04-28 04:33:07,501][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 2.7314229011535645, cross_entropy: 2.7314229011535645 +[2025-04-28 04:33:07,785][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 3.2020206451416016, cross_entropy: 3.2020206451416016 +[2025-04-28 04:33:11,380][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 1.8607534170150757, cross_entropy: 1.8607534170150757 +[2025-04-28 04:33:11,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 1.3975436687469482, cross_entropy: 1.3975436687469482 +[2025-04-28 04:33:13,514][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.9090509414672852, cross_entropy: 1.9090509414672852 +[2025-04-28 04:33:13,782][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.896960973739624, cross_entropy: 1.896960973739624 +[2025-04-28 04:33:15,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.9580307006835938, cross_entropy: 1.9580307006835938 +[2025-04-28 04:33:15,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.7787330150604248, cross_entropy: 1.7787330150604248 +[2025-04-28 04:33:17,984][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.9109179973602295, cross_entropy: 1.9109179973602295 +[2025-04-28 04:33:18,266][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.792201280593872, cross_entropy: 1.792201280593872 +[2025-04-28 04:33:20,967][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.739914059638977, cross_entropy: 1.739914059638977 +[2025-04-28 04:33:21,249][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.5727221965789795, cross_entropy: 1.5727221965789795 +[2025-04-28 04:33:24,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 1.8169878721237183, cross_entropy: 1.8169878721237183 +[2025-04-28 04:33:24,840][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.9937520027160645, cross_entropy: 2.9937520027160645 +[2025-04-28 04:33:26,599][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.6226954460144043, cross_entropy: 2.6226954460144043 +[2025-04-28 04:33:26,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 1.7764620780944824, cross_entropy: 1.7764620780944824 +[2025-04-28 04:33:29,382][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.5245331525802612, cross_entropy: 1.5245331525802612 +[2025-04-28 04:33:29,664][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.4593820571899414, cross_entropy: 2.4593820571899414 +[2025-04-28 04:33:31,715][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 1.538513422012329, cross_entropy: 1.538513422012329 +[2025-04-28 04:33:31,984][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 3.1192922592163086, cross_entropy: 3.1192922592163086 +[2025-04-28 04:33:34,363][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 2.33298659324646, cross_entropy: 2.33298659324646 +[2025-04-28 04:33:34,631][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.4711723327636719, cross_entropy: 1.4711723327636719 +[2025-04-28 04:33:37,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.607343316078186, cross_entropy: 1.607343316078186 +[2025-04-28 04:33:37,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 1.979931116104126, cross_entropy: 1.979931116104126 +[2025-04-28 04:33:39,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 1.3606321811676025, cross_entropy: 1.3606321811676025 +[2025-04-28 04:33:40,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 2.6307835578918457, cross_entropy: 2.6307835578918457 +[2025-04-28 04:33:41,920][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 3.2766876220703125, cross_entropy: 3.2766876220703125 +[2025-04-28 04:33:42,451][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 2.8717145919799805, cross_entropy: 2.8717145919799805 +[2025-04-28 04:33:44,548][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 1.6679654121398926, cross_entropy: 1.6679654121398926 +[2025-04-28 04:33:44,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.400984764099121, cross_entropy: 1.400984764099121 +[2025-04-28 04:33:47,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.265371322631836, cross_entropy: 1.265371322631836 +[2025-04-28 04:33:47,806][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.7486610412597656, cross_entropy: 1.7486610412597656 +[2025-04-28 04:33:50,031][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 1.2580153942108154, cross_entropy: 1.2580153942108154 +[2025-04-28 04:33:50,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 1.7987184524536133, cross_entropy: 1.7987184524536133 +[2025-04-28 04:33:52,817][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 2.928795337677002, cross_entropy: 2.928795337677002 +[2025-04-28 04:33:53,097][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 2.5300633907318115, cross_entropy: 2.5300633907318115 +[2025-04-28 04:33:54,805][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 3.2300243377685547, cross_entropy: 3.2300243377685547 +[2025-04-28 04:33:55,265][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 1.2846611738204956, cross_entropy: 1.2846611738204956 +[2025-04-28 04:33:57,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.8825538158416748, cross_entropy: 1.8825538158416748 +[2025-04-28 04:33:57,908][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 2.477295160293579, cross_entropy: 2.477295160293579 +[2025-04-28 04:34:00,547][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 2.588744640350342, cross_entropy: 2.588744640350342 +[2025-04-28 04:34:00,817][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.088132381439209, cross_entropy: 2.088132381439209 +[2025-04-28 04:34:03,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 3.1287949085235596, cross_entropy: 3.1287949085235596 +[2025-04-28 04:34:03,514][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 2.0809576511383057, cross_entropy: 2.0809576511383057 +[2025-04-28 04:34:05,539][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 3.053584575653076, cross_entropy: 3.053584575653076 +[2025-04-28 04:34:05,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.676039218902588, cross_entropy: 1.676039218902588 +[2025-04-28 04:34:08,498][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 2.9016201496124268, cross_entropy: 2.9016201496124268 +[2025-04-28 04:34:08,780][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 1.4726982116699219, cross_entropy: 1.4726982116699219 +[2025-04-28 04:34:10,886][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.4984341859817505, cross_entropy: 1.4984341859817505 +[2025-04-28 04:34:11,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.4167566299438477, cross_entropy: 2.4167566299438477 +[2025-04-28 04:36:10,649][BaseTrainer][INFO] - [Epoch 7/10] (train) 2.222641944885254, cross_entropy: 2.222641944885254 +[2025-04-28 04:36:10,649][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.6786919832229614, cross_entropy: 1.6786919832229614 +[2025-04-28 04:36:10,813][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch7.pth. +[2025-04-28 04:36:11,014][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:36:14,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.4241912364959717, cross_entropy: 1.4241912364959717 +[2025-04-28 04:36:14,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.1730213165283203, cross_entropy: 2.1730213165283203 +[2025-04-28 04:36:17,406][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.4220819473266602, cross_entropy: 1.4220819473266602 +[2025-04-28 04:36:17,687][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.9629175662994385, cross_entropy: 2.9629175662994385 +[2025-04-28 04:36:20,077][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 2.771967887878418, cross_entropy: 2.771967887878418 +[2025-04-28 04:36:20,360][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.7130868434906006, cross_entropy: 1.7130868434906006 +[2025-04-28 04:36:22,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 1.2465829849243164, cross_entropy: 1.2465829849243164 +[2025-04-28 04:36:22,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.908618450164795, cross_entropy: 2.908618450164795 +[2025-04-28 04:36:24,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.3577055931091309, cross_entropy: 1.3577055931091309 +[2025-04-28 04:36:25,111][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.7215056419372559, cross_entropy: 1.7215056419372559 +[2025-04-28 04:36:27,421][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 3.0777359008789062, cross_entropy: 3.0777359008789062 +[2025-04-28 04:36:27,688][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.8369561433792114, cross_entropy: 0.8369561433792114 +[2025-04-28 04:36:30,467][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 1.294305443763733, cross_entropy: 1.294305443763733 +[2025-04-28 04:36:30,755][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.672466993331909, cross_entropy: 2.672466993331909 +[2025-04-28 04:36:32,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 1.1681525707244873, cross_entropy: 1.1681525707244873 +[2025-04-28 04:36:33,587][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 1.0881428718566895, cross_entropy: 1.0881428718566895 +[2025-04-28 04:36:35,301][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 2.3346500396728516, cross_entropy: 2.3346500396728516 +[2025-04-28 04:36:36,190][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.576662540435791, cross_entropy: 2.576662540435791 +[2025-04-28 04:36:37,824][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 3.0991575717926025, cross_entropy: 3.0991575717926025 +[2025-04-28 04:36:38,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.0842020511627197, cross_entropy: 1.0842020511627197 +[2025-04-28 04:36:40,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.8792060613632202, cross_entropy: 1.8792060613632202 +[2025-04-28 04:36:41,172][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 3.0387043952941895, cross_entropy: 3.0387043952941895 +[2025-04-28 04:36:42,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.7794251441955566, cross_entropy: 1.7794251441955566 +[2025-04-28 04:36:43,810][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.8632475137710571, cross_entropy: 1.8632475137710571 +[2025-04-28 04:36:45,242][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 3.1870644092559814, cross_entropy: 3.1870644092559814 +[2025-04-28 04:36:46,843][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 2.491204261779785, cross_entropy: 2.491204261779785 +[2025-04-28 04:36:47,777][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 1.4062503576278687, cross_entropy: 1.4062503576278687 +[2025-04-28 04:36:49,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.231645345687866, cross_entropy: 3.231645345687866 +[2025-04-28 04:36:50,251][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.5575687885284424, cross_entropy: 1.5575687885284424 +[2025-04-28 04:36:52,343][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.5151426792144775, cross_entropy: 1.5151426792144775 +[2025-04-28 04:36:52,730][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 1.5228971242904663, cross_entropy: 1.5228971242904663 +[2025-04-28 04:36:54,920][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.334826707839966, cross_entropy: 2.334826707839966 +[2025-04-28 04:36:55,431][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 1.6000957489013672, cross_entropy: 1.6000957489013672 +[2025-04-28 04:36:57,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 3.23931884765625, cross_entropy: 3.23931884765625 +[2025-04-28 04:36:57,991][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 3.3225088119506836, cross_entropy: 3.3225088119506836 +[2025-04-28 04:36:59,659][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.3793296813964844, cross_entropy: 1.3793296813964844 +[2025-04-28 04:37:00,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.2596230506896973, cross_entropy: 2.2596230506896973 +[2025-04-28 04:37:02,415][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.8348019123077393, cross_entropy: 2.8348019123077393 +[2025-04-28 04:37:02,782][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 2.2523281574249268, cross_entropy: 2.2523281574249268 +[2025-04-28 04:37:05,347][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.8034472465515137, cross_entropy: 1.8034472465515137 +[2025-04-28 04:37:05,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 3.359795331954956, cross_entropy: 3.359795331954956 +[2025-04-28 04:37:07,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.6295802593231201, cross_entropy: 1.6295802593231201 +[2025-04-28 04:37:07,943][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.7818223237991333, cross_entropy: 1.7818223237991333 +[2025-04-28 04:37:10,157][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.1917240619659424, cross_entropy: 1.1917240619659424 +[2025-04-28 04:37:10,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 1.007964849472046, cross_entropy: 1.007964849472046 +[2025-04-28 04:37:12,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 3.2402119636535645, cross_entropy: 3.2402119636535645 +[2025-04-28 04:37:12,828][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.8197104930877686, cross_entropy: 1.8197104930877686 +[2025-04-28 04:37:15,712][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 3.2467269897460938, cross_entropy: 3.2467269897460938 +[2025-04-28 04:37:15,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.7255983352661133, cross_entropy: 2.7255983352661133 +[2025-04-28 04:37:17,891][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.6371145248413086, cross_entropy: 2.6371145248413086 +[2025-04-28 04:37:18,172][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.2422091960906982, cross_entropy: 2.2422091960906982 +[2025-04-28 04:37:19,981][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.734032154083252, cross_entropy: 1.734032154083252 +[2025-04-28 04:37:20,263][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 1.2712211608886719, cross_entropy: 1.2712211608886719 +[2025-04-28 04:37:21,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 2.053379774093628, cross_entropy: 2.053379774093628 +[2025-04-28 04:37:22,252][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.9283041954040527, cross_entropy: 2.9283041954040527 +[2025-04-28 04:37:24,740][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 1.4770903587341309, cross_entropy: 1.4770903587341309 +[2025-04-28 04:37:25,012][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.377502679824829, cross_entropy: 2.377502679824829 +[2025-04-28 04:37:27,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 1.5880684852600098, cross_entropy: 1.5880684852600098 +[2025-04-28 04:37:27,599][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 2.434664249420166, cross_entropy: 2.434664249420166 +[2025-04-28 04:37:29,168][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 1.083111047744751, cross_entropy: 1.083111047744751 +[2025-04-28 04:37:29,447][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 2.4142565727233887, cross_entropy: 2.4142565727233887 +[2025-04-28 04:37:31,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.8604552745819092, cross_entropy: 1.8604552745819092 +[2025-04-28 04:37:31,694][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 3.211515188217163, cross_entropy: 3.211515188217163 +[2025-04-28 04:37:34,158][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 3.0300731658935547, cross_entropy: 3.0300731658935547 +[2025-04-28 04:37:34,435][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.939720392227173, cross_entropy: 2.939720392227173 +[2025-04-28 04:37:36,840][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 0.9468909502029419, cross_entropy: 0.9468909502029419 +[2025-04-28 04:37:37,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.6424660682678223, cross_entropy: 2.6424660682678223 +[2025-04-28 04:37:39,239][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 2.200348377227783, cross_entropy: 2.200348377227783 +[2025-04-28 04:37:40,077][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 1.2373237609863281, cross_entropy: 1.2373237609863281 +[2025-04-28 04:37:41,412][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.9793615341186523, cross_entropy: 2.9793615341186523 +[2025-04-28 04:37:42,689][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.2833847999572754, cross_entropy: 1.2833847999572754 +[2025-04-28 04:37:44,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 2.965818405151367, cross_entropy: 2.965818405151367 +[2025-04-28 04:37:45,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.4255900382995605, cross_entropy: 1.4255900382995605 +[2025-04-28 04:37:46,834][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.6861943006515503, cross_entropy: 1.6861943006515503 +[2025-04-28 04:37:48,281][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.7224329710006714, cross_entropy: 1.7224329710006714 +[2025-04-28 04:37:49,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 3.1669116020202637, cross_entropy: 3.1669116020202637 +[2025-04-28 04:37:51,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.5468436479568481, cross_entropy: 1.5468436479568481 +[2025-04-28 04:37:52,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.444330096244812, cross_entropy: 1.444330096244812 +[2025-04-28 04:37:53,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 2.813617706298828, cross_entropy: 2.813617706298828 +[2025-04-28 04:37:54,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.9191412925720215, cross_entropy: 2.9191412925720215 +[2025-04-28 04:37:55,274][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 1.6512291431427002, cross_entropy: 1.6512291431427002 +[2025-04-28 04:37:57,170][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.7351442575454712, cross_entropy: 1.7351442575454712 +[2025-04-28 04:37:57,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.3935933113098145, cross_entropy: 2.3935933113098145 +[2025-04-28 04:37:59,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.5849099159240723, cross_entropy: 1.5849099159240723 +[2025-04-28 04:38:00,779][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 2.444805145263672, cross_entropy: 2.444805145263672 +[2025-04-28 04:38:01,956][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 1.5377753973007202, cross_entropy: 1.5377753973007202 +[2025-04-28 04:38:03,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.0562522411346436, cross_entropy: 2.0562522411346436 +[2025-04-28 04:38:05,066][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 3.3180103302001953, cross_entropy: 3.3180103302001953 +[2025-04-28 04:38:06,120][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 1.4300224781036377, cross_entropy: 1.4300224781036377 +[2025-04-28 04:38:07,861][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 1.6196560859680176, cross_entropy: 1.6196560859680176 +[2025-04-28 04:38:09,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.9627625942230225, cross_entropy: 2.9627625942230225 +[2025-04-28 04:38:10,004][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 1.4638471603393555, cross_entropy: 1.4638471603393555 +[2025-04-28 04:38:12,126][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.4208319187164307, cross_entropy: 1.4208319187164307 +[2025-04-28 04:38:12,816][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 1.735369324684143, cross_entropy: 1.735369324684143 +[2025-04-28 04:38:14,920][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 2.080173969268799, cross_entropy: 2.080173969268799 +[2025-04-28 04:38:15,201][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.8728522062301636, cross_entropy: 1.8728522062301636 +[2025-04-28 04:38:16,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.715857744216919, cross_entropy: 2.715857744216919 +[2025-04-28 04:38:17,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 1.1856613159179688, cross_entropy: 1.1856613159179688 +[2025-04-28 04:38:19,089][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.8854546546936035, cross_entropy: 1.8854546546936035 +[2025-04-28 04:38:19,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.3624606132507324, cross_entropy: 1.3624606132507324 +[2025-04-28 04:38:22,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.5950186252593994, cross_entropy: 2.5950186252593994 +[2025-04-28 04:38:22,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.5186071395874023, cross_entropy: 2.5186071395874023 +[2025-04-28 04:38:24,625][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.505789279937744, cross_entropy: 2.505789279937744 +[2025-04-28 04:38:24,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.189728856086731, cross_entropy: 1.189728856086731 +[2025-04-28 04:38:27,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 3.379180669784546, cross_entropy: 3.379180669784546 +[2025-04-28 04:38:27,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 2.8300113677978516, cross_entropy: 2.8300113677978516 +[2025-04-28 04:38:29,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.7263438701629639, cross_entropy: 1.7263438701629639 +[2025-04-28 04:38:29,967][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 3.362119436264038, cross_entropy: 3.362119436264038 +[2025-04-28 04:38:32,072][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.0145024061203003, cross_entropy: 1.0145024061203003 +[2025-04-28 04:38:32,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.6637256145477295, cross_entropy: 2.6637256145477295 +[2025-04-28 04:38:34,127][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 2.4325499534606934, cross_entropy: 2.4325499534606934 +[2025-04-28 04:38:34,395][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 2.0601165294647217, cross_entropy: 2.0601165294647217 +[2025-04-28 04:38:36,370][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 2.073261260986328, cross_entropy: 2.073261260986328 +[2025-04-28 04:38:36,650][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 1.2923805713653564, cross_entropy: 1.2923805713653564 +[2025-04-28 04:38:38,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.2609589099884033, cross_entropy: 2.2609589099884033 +[2025-04-28 04:38:39,265][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.7152879238128662, cross_entropy: 1.7152879238128662 +[2025-04-28 04:38:41,517][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.2153687477111816, cross_entropy: 2.2153687477111816 +[2025-04-28 04:38:42,954][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.72201406955719, cross_entropy: 1.72201406955719 +[2025-04-28 04:38:43,548][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 2.752737522125244, cross_entropy: 2.752737522125244 +[2025-04-28 04:38:45,483][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 2.152039051055908, cross_entropy: 2.152039051055908 +[2025-04-28 04:38:45,879][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 2.717719554901123, cross_entropy: 2.717719554901123 +[2025-04-28 04:38:47,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 1.3713021278381348, cross_entropy: 1.3713021278381348 +[2025-04-28 04:38:48,136][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.9852991104125977, cross_entropy: 2.9852991104125977 +[2025-04-28 04:38:49,969][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.7973601818084717, cross_entropy: 1.7973601818084717 +[2025-04-28 04:38:51,643][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.7144520282745361, cross_entropy: 1.7144520282745361 +[2025-04-28 04:38:52,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.3433382511138916, cross_entropy: 1.3433382511138916 +[2025-04-28 04:38:54,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 3.0947422981262207, cross_entropy: 3.0947422981262207 +[2025-04-28 04:38:54,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 2.4070889949798584, cross_entropy: 2.4070889949798584 +[2025-04-28 04:38:56,647][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.3225171566009521, cross_entropy: 1.3225171566009521 +[2025-04-28 04:38:57,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 1.5087039470672607, cross_entropy: 1.5087039470672607 +[2025-04-28 04:38:58,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 2.9148073196411133, cross_entropy: 2.9148073196411133 +[2025-04-28 04:39:00,085][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 2.6316094398498535, cross_entropy: 2.6316094398498535 +[2025-04-28 04:39:01,766][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 2.8949437141418457, cross_entropy: 2.8949437141418457 +[2025-04-28 04:39:02,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.8447740077972412, cross_entropy: 1.8447740077972412 +[2025-04-28 04:39:04,080][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.6409361362457275, cross_entropy: 2.6409361362457275 +[2025-04-28 04:39:04,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 2.8811874389648438, cross_entropy: 2.8811874389648438 +[2025-04-28 04:39:06,841][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 3.0380403995513916, cross_entropy: 3.0380403995513916 +[2025-04-28 04:39:07,180][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 3.1032967567443848, cross_entropy: 3.1032967567443848 +[2025-04-28 04:39:09,582][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 2.2544102668762207, cross_entropy: 2.2544102668762207 +[2025-04-28 04:39:09,861][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 1.3563988208770752, cross_entropy: 1.3563988208770752 +[2025-04-28 04:39:12,593][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 1.191895842552185, cross_entropy: 1.191895842552185 +[2025-04-28 04:39:12,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.683377504348755, cross_entropy: 2.683377504348755 +[2025-04-28 04:39:14,720][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.3294745683670044, cross_entropy: 1.3294745683670044 +[2025-04-28 04:39:15,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.7721590995788574, cross_entropy: 2.7721590995788574 +[2025-04-28 04:39:16,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 3.2475204467773438, cross_entropy: 3.2475204467773438 +[2025-04-28 04:39:17,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.713884115219116, cross_entropy: 2.713884115219116 +[2025-04-28 04:39:19,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.4183025360107422, cross_entropy: 1.4183025360107422 +[2025-04-28 04:39:20,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 0.9130573868751526, cross_entropy: 0.9130573868751526 +[2025-04-28 04:39:21,911][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 0.942241907119751, cross_entropy: 0.942241907119751 +[2025-04-28 04:39:22,679][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.695086121559143, cross_entropy: 1.695086121559143 +[2025-04-28 04:39:24,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.478087902069092, cross_entropy: 2.478087902069092 +[2025-04-28 04:39:25,385][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.6706864833831787, cross_entropy: 1.6706864833831787 +[2025-04-28 04:39:27,001][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 2.054215908050537, cross_entropy: 2.054215908050537 +[2025-04-28 04:39:27,964][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.1722514629364014, cross_entropy: 1.1722514629364014 +[2025-04-28 04:39:29,865][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 2.2941527366638184, cross_entropy: 2.2941527366638184 +[2025-04-28 04:39:30,248][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.6108331680297852, cross_entropy: 1.6108331680297852 +[2025-04-28 04:39:32,311][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 1.6565032005310059, cross_entropy: 1.6565032005310059 +[2025-04-28 04:39:33,518][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 1.3344300985336304, cross_entropy: 1.3344300985336304 +[2025-04-28 04:39:35,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.591834545135498, cross_entropy: 2.591834545135498 +[2025-04-28 04:39:36,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 3.089337110519409, cross_entropy: 3.089337110519409 +[2025-04-28 04:39:37,605][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.845700740814209, cross_entropy: 1.845700740814209 +[2025-04-28 04:39:38,719][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 3.172868251800537, cross_entropy: 3.172868251800537 +[2025-04-28 04:39:39,886][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 2.92319393157959, cross_entropy: 2.92319393157959 +[2025-04-28 04:39:41,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 2.0367205142974854, cross_entropy: 2.0367205142974854 +[2025-04-28 04:39:41,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.8556411266326904, cross_entropy: 2.8556411266326904 +[2025-04-28 04:39:44,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.6191471815109253, cross_entropy: 1.6191471815109253 +[2025-04-28 04:39:44,802][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.972684144973755, cross_entropy: 2.972684144973755 +[2025-04-28 04:39:47,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 1.6058008670806885, cross_entropy: 1.6058008670806885 +[2025-04-28 04:39:47,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.413130760192871, cross_entropy: 2.413130760192871 +[2025-04-28 04:39:49,761][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.286264181137085, cross_entropy: 1.286264181137085 +[2025-04-28 04:39:50,044][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.252483606338501, cross_entropy: 1.252483606338501 +[2025-04-28 04:39:52,248][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.7343569993972778, cross_entropy: 1.7343569993972778 +[2025-04-28 04:39:52,569][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 1.7258541584014893, cross_entropy: 1.7258541584014893 +[2025-04-28 04:39:55,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 2.2211382389068604, cross_entropy: 2.2211382389068604 +[2025-04-28 04:39:55,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 0.9585480093955994, cross_entropy: 0.9585480093955994 +[2025-04-28 04:39:58,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 1.145848274230957, cross_entropy: 1.145848274230957 +[2025-04-28 04:39:58,450][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.6114890575408936, cross_entropy: 1.6114890575408936 +[2025-04-28 04:40:00,814][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.567007541656494, cross_entropy: 2.567007541656494 +[2025-04-28 04:40:01,097][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.8865410089492798, cross_entropy: 1.8865410089492798 +[2025-04-28 04:40:02,951][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.7619171142578125, cross_entropy: 2.7619171142578125 +[2025-04-28 04:40:03,233][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 3.3064072132110596, cross_entropy: 3.3064072132110596 +[2025-04-28 04:40:05,615][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 3.012287139892578, cross_entropy: 3.012287139892578 +[2025-04-28 04:40:05,899][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 3.144169569015503, cross_entropy: 3.144169569015503 +[2025-04-28 04:40:08,237][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 3.03682279586792, cross_entropy: 3.03682279586792 +[2025-04-28 04:40:08,520][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 3.191474676132202, cross_entropy: 3.191474676132202 +[2025-04-28 04:40:10,892][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 2.1276111602783203, cross_entropy: 2.1276111602783203 +[2025-04-28 04:40:11,162][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 1.6693284511566162, cross_entropy: 1.6693284511566162 +[2025-04-28 04:40:14,280][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 3.126018762588501, cross_entropy: 3.126018762588501 +[2025-04-28 04:40:14,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 2.4125866889953613, cross_entropy: 2.4125866889953613 +[2025-04-28 04:40:17,533][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 1.4183835983276367, cross_entropy: 1.4183835983276367 +[2025-04-28 04:40:17,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.354916572570801, cross_entropy: 2.354916572570801 +[2025-04-28 04:40:20,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.6919878721237183, cross_entropy: 1.6919878721237183 +[2025-04-28 04:40:20,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 2.24188232421875, cross_entropy: 2.24188232421875 +[2025-04-28 04:40:22,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 2.0546112060546875, cross_entropy: 2.0546112060546875 +[2025-04-28 04:40:22,435][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 1.5165681838989258, cross_entropy: 1.5165681838989258 +[2025-04-28 04:40:24,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 2.2848830223083496, cross_entropy: 2.2848830223083496 +[2025-04-28 04:40:24,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 3.145354747772217, cross_entropy: 3.145354747772217 +[2025-04-28 04:40:26,898][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 2.1053857803344727, cross_entropy: 2.1053857803344727 +[2025-04-28 04:40:27,179][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 3.232297420501709, cross_entropy: 3.232297420501709 +[2025-04-28 04:40:29,180][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.8137123584747314, cross_entropy: 1.8137123584747314 +[2025-04-28 04:40:29,448][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 2.246532440185547, cross_entropy: 2.246532440185547 +[2025-04-28 04:40:31,668][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 3.3691811561584473, cross_entropy: 3.3691811561584473 +[2025-04-28 04:40:31,941][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.663331985473633, cross_entropy: 2.663331985473633 +[2025-04-28 04:40:34,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.6859917640686035, cross_entropy: 2.6859917640686035 +[2025-04-28 04:40:34,315][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 1.5786755084991455, cross_entropy: 1.5786755084991455 +[2025-04-28 04:40:36,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 1.5629370212554932, cross_entropy: 1.5629370212554932 +[2025-04-28 04:40:36,811][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 1.416490077972412, cross_entropy: 1.416490077972412 +[2025-04-28 04:40:38,826][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.339477777481079, cross_entropy: 1.339477777481079 +[2025-04-28 04:40:39,109][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 1.8851027488708496, cross_entropy: 1.8851027488708496 +[2025-04-28 04:40:41,313][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 3.055556297302246, cross_entropy: 3.055556297302246 +[2025-04-28 04:40:41,596][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 1.4967963695526123, cross_entropy: 1.4967963695526123 +[2025-04-28 04:40:44,123][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.9276986122131348, cross_entropy: 2.9276986122131348 +[2025-04-28 04:40:44,405][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.1288880109786987, cross_entropy: 1.1288880109786987 +[2025-04-28 04:40:46,784][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 3.160856246948242, cross_entropy: 3.160856246948242 +[2025-04-28 04:40:47,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 1.2193222045898438, cross_entropy: 1.2193222045898438 +[2025-04-28 04:40:49,733][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 3.1089096069335938, cross_entropy: 3.1089096069335938 +[2025-04-28 04:40:50,014][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 3.1158673763275146, cross_entropy: 3.1158673763275146 +[2025-04-28 04:40:51,998][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 3.0733227729797363, cross_entropy: 3.0733227729797363 +[2025-04-28 04:40:52,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 2.9793128967285156, cross_entropy: 2.9793128967285156 +[2025-04-28 04:40:54,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.621631145477295, cross_entropy: 2.621631145477295 +[2025-04-28 04:40:55,153][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 2.6217875480651855, cross_entropy: 2.6217875480651855 +[2025-04-28 04:40:57,260][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.389984130859375, cross_entropy: 2.389984130859375 +[2025-04-28 04:40:57,539][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 2.13814640045166, cross_entropy: 2.13814640045166 +[2025-04-28 04:40:59,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 2.783000946044922, cross_entropy: 2.783000946044922 +[2025-04-28 04:40:59,990][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 0.9072680473327637, cross_entropy: 0.9072680473327637 +[2025-04-28 04:41:02,972][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.543564796447754, cross_entropy: 2.543564796447754 +[2025-04-28 04:41:03,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.3969990015029907, cross_entropy: 1.3969990015029907 +[2025-04-28 04:41:05,450][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.07674241065979, cross_entropy: 1.07674241065979 +[2025-04-28 04:41:05,734][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 1.9771008491516113, cross_entropy: 1.9771008491516113 +[2025-04-28 04:41:07,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 2.0713624954223633, cross_entropy: 2.0713624954223633 +[2025-04-28 04:41:08,189][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 2.856508731842041, cross_entropy: 2.856508731842041 +[2025-04-28 04:41:10,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.3779466152191162, cross_entropy: 1.3779466152191162 +[2025-04-28 04:41:10,633][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 2.334366798400879, cross_entropy: 2.334366798400879 +[2025-04-28 04:41:12,843][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 1.829270839691162, cross_entropy: 1.829270839691162 +[2025-04-28 04:41:13,124][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 3.044511318206787, cross_entropy: 3.044511318206787 +[2025-04-28 04:41:16,720][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.0558948516845703, cross_entropy: 2.0558948516845703 +[2025-04-28 04:41:17,000][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.2473547458648682, cross_entropy: 1.2473547458648682 +[2025-04-28 04:41:18,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 3.0503528118133545, cross_entropy: 3.0503528118133545 +[2025-04-28 04:41:19,011][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 1.4515173435211182, cross_entropy: 1.4515173435211182 +[2025-04-28 04:41:21,074][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 3.2929847240448, cross_entropy: 3.2929847240448 +[2025-04-28 04:41:21,354][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 1.1888856887817383, cross_entropy: 1.1888856887817383 +[2025-04-28 04:41:23,231][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.207632064819336, cross_entropy: 2.207632064819336 +[2025-04-28 04:41:23,514][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 3.35662841796875, cross_entropy: 3.35662841796875 +[2025-04-28 04:41:25,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 1.4680016040802002, cross_entropy: 1.4680016040802002 +[2025-04-28 04:41:25,451][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 1.3731722831726074, cross_entropy: 1.3731722831726074 +[2025-04-28 04:41:27,514][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.4002108573913574, cross_entropy: 2.4002108573913574 +[2025-04-28 04:41:27,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 2.9381418228149414, cross_entropy: 2.9381418228149414 +[2025-04-28 04:41:30,117][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.2924634218215942, cross_entropy: 1.2924634218215942 +[2025-04-28 04:41:30,458][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.2925639152526855, cross_entropy: 1.2925639152526855 +[2025-04-28 04:41:32,719][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.454594135284424, cross_entropy: 2.454594135284424 +[2025-04-28 04:41:32,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 1.3702045679092407, cross_entropy: 1.3702045679092407 +[2025-04-28 04:41:35,141][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.4799346923828125, cross_entropy: 1.4799346923828125 +[2025-04-28 04:41:35,422][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 2.3378779888153076, cross_entropy: 2.3378779888153076 +[2025-04-28 04:41:37,431][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.8889031410217285, cross_entropy: 2.8889031410217285 +[2025-04-28 04:41:38,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 3.122333526611328, cross_entropy: 3.122333526611328 +[2025-04-28 04:41:39,687][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.2992632389068604, cross_entropy: 2.2992632389068604 +[2025-04-28 04:41:40,766][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 2.0308609008789062, cross_entropy: 2.0308609008789062 +[2025-04-28 04:41:42,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 2.057314157485962, cross_entropy: 2.057314157485962 +[2025-04-28 04:41:42,850][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 2.679288864135742, cross_entropy: 2.679288864135742 +[2025-04-28 04:41:44,743][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.495205283164978, cross_entropy: 1.495205283164978 +[2025-04-28 04:41:45,954][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 1.388155460357666, cross_entropy: 1.388155460357666 +[2025-04-28 04:41:46,947][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 2.1167078018188477, cross_entropy: 2.1167078018188477 +[2025-04-28 04:41:48,482][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 1.5898427963256836, cross_entropy: 1.5898427963256836 +[2025-04-28 04:41:49,125][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 1.135555386543274, cross_entropy: 1.135555386543274 +[2025-04-28 04:41:51,119][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.5226545333862305, cross_entropy: 2.5226545333862305 +[2025-04-28 04:41:52,029][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 1.3046128749847412, cross_entropy: 1.3046128749847412 +[2025-04-28 04:41:53,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.7721613645553589, cross_entropy: 1.7721613645553589 +[2025-04-28 04:41:54,470][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 1.948063611984253, cross_entropy: 1.948063611984253 +[2025-04-28 04:41:56,383][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 3.050558567047119, cross_entropy: 3.050558567047119 +[2025-04-28 04:41:56,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.977895975112915, cross_entropy: 2.977895975112915 +[2025-04-28 04:41:58,736][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 1.7896517515182495, cross_entropy: 1.7896517515182495 +[2025-04-28 04:41:59,228][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.5840091705322266, cross_entropy: 2.5840091705322266 +[2025-04-28 04:42:01,256][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 1.66628098487854, cross_entropy: 1.66628098487854 +[2025-04-28 04:42:01,570][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.6036407947540283, cross_entropy: 2.6036407947540283 +[2025-04-28 04:42:04,075][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.52595853805542, cross_entropy: 2.52595853805542 +[2025-04-28 04:42:04,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.47267484664917, cross_entropy: 1.47267484664917 +[2025-04-28 04:42:06,417][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.5578861236572266, cross_entropy: 1.5578861236572266 +[2025-04-28 04:42:06,791][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.1613496541976929, cross_entropy: 1.1613496541976929 +[2025-04-28 04:42:09,979][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 3.5247802734375, cross_entropy: 3.5247802734375 +[2025-04-28 04:42:10,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 1.4936933517456055, cross_entropy: 1.4936933517456055 +[2025-04-28 04:42:12,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.472033977508545, cross_entropy: 2.472033977508545 +[2025-04-28 04:42:12,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.845736503601074, cross_entropy: 2.845736503601074 +[2025-04-28 04:42:15,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.738966941833496, cross_entropy: 2.738966941833496 +[2025-04-28 04:42:16,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.9652528762817383, cross_entropy: 2.9652528762817383 +[2025-04-28 04:42:18,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 1.4975941181182861, cross_entropy: 1.4975941181182861 +[2025-04-28 04:42:18,372][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.176292896270752, cross_entropy: 2.176292896270752 +[2025-04-28 04:42:19,917][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 3.060856342315674, cross_entropy: 3.060856342315674 +[2025-04-28 04:42:20,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.3854503631591797, cross_entropy: 1.3854503631591797 +[2025-04-28 04:42:24,217][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 3.1461219787597656, cross_entropy: 3.1461219787597656 +[2025-04-28 04:42:24,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.7436997890472412, cross_entropy: 1.7436997890472412 +[2025-04-28 04:42:26,762][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.884300947189331, cross_entropy: 1.884300947189331 +[2025-04-28 04:42:27,091][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 3.142186164855957, cross_entropy: 3.142186164855957 +[2025-04-28 04:42:29,019][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.329270839691162, cross_entropy: 1.329270839691162 +[2025-04-28 04:42:29,327][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 3.1832315921783447, cross_entropy: 3.1832315921783447 +[2025-04-28 04:42:31,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 2.495978832244873, cross_entropy: 2.495978832244873 +[2025-04-28 04:42:31,798][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 1.5075721740722656, cross_entropy: 1.5075721740722656 +[2025-04-28 04:42:34,362][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 3.3562798500061035, cross_entropy: 3.3562798500061035 +[2025-04-28 04:42:34,887][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.480513334274292, cross_entropy: 2.480513334274292 +[2025-04-28 04:42:36,590][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.7422120571136475, cross_entropy: 1.7422120571136475 +[2025-04-28 04:42:37,038][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 1.4588494300842285, cross_entropy: 1.4588494300842285 +[2025-04-28 04:42:39,332][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 1.7242769002914429, cross_entropy: 1.7242769002914429 +[2025-04-28 04:42:39,634][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.946726679801941, cross_entropy: 1.946726679801941 +[2025-04-28 04:42:41,619][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 2.4089877605438232, cross_entropy: 2.4089877605438232 +[2025-04-28 04:42:42,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.9511057138442993, cross_entropy: 0.9511057138442993 +[2025-04-28 04:42:43,894][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.8425519466400146, cross_entropy: 1.8425519466400146 +[2025-04-28 04:42:45,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.4562904834747314, cross_entropy: 1.4562904834747314 +[2025-04-28 04:42:45,819][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.3647329807281494, cross_entropy: 1.3647329807281494 +[2025-04-28 04:42:47,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.4280238151550293, cross_entropy: 1.4280238151550293 +[2025-04-28 04:42:48,054][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.4710453748703003, cross_entropy: 1.4710453748703003 +[2025-04-28 04:42:50,642][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.872705340385437, cross_entropy: 1.872705340385437 +[2025-04-28 04:42:50,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 1.3540221452713013, cross_entropy: 1.3540221452713013 +[2025-04-28 04:42:52,799][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 1.7318991422653198, cross_entropy: 1.7318991422653198 +[2025-04-28 04:42:53,081][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 2.7016549110412598, cross_entropy: 2.7016549110412598 +[2025-04-28 04:42:55,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.661023497581482, cross_entropy: 1.661023497581482 +[2025-04-28 04:42:55,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 1.8610444068908691, cross_entropy: 1.8610444068908691 +[2025-04-28 04:42:58,058][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.2919423580169678, cross_entropy: 1.2919423580169678 +[2025-04-28 04:42:58,353][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 1.2212467193603516, cross_entropy: 1.2212467193603516 +[2025-04-28 04:43:00,106][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.783438205718994, cross_entropy: 2.783438205718994 +[2025-04-28 04:43:01,095][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 3.080906867980957, cross_entropy: 3.080906867980957 +[2025-04-28 04:43:03,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 2.1532211303710938, cross_entropy: 2.1532211303710938 +[2025-04-28 04:43:03,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.267075300216675, cross_entropy: 2.267075300216675 +[2025-04-28 04:43:05,266][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 1.2515532970428467, cross_entropy: 1.2515532970428467 +[2025-04-28 04:43:05,977][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.3282802104949951, cross_entropy: 1.3282802104949951 +[2025-04-28 04:43:07,839][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 2.1062183380126953, cross_entropy: 2.1062183380126953 +[2025-04-28 04:43:09,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 2.5223522186279297, cross_entropy: 2.5223522186279297 +[2025-04-28 04:43:10,061][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 2.8771848678588867, cross_entropy: 2.8771848678588867 +[2025-04-28 04:43:11,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 2.3522465229034424, cross_entropy: 2.3522465229034424 +[2025-04-28 04:43:12,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.9707887172698975, cross_entropy: 1.9707887172698975 +[2025-04-28 04:43:14,289][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 2.592289447784424, cross_entropy: 2.592289447784424 +[2025-04-28 04:43:15,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.2747366428375244, cross_entropy: 1.2747366428375244 +[2025-04-28 04:43:16,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 2.39699649810791, cross_entropy: 2.39699649810791 +[2025-04-28 04:43:18,200][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.6343716382980347, cross_entropy: 1.6343716382980347 +[2025-04-28 04:43:19,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 2.145331382751465, cross_entropy: 2.145331382751465 +[2025-04-28 04:43:20,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.5674817562103271, cross_entropy: 1.5674817562103271 +[2025-04-28 04:43:22,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 1.661778450012207, cross_entropy: 1.661778450012207 +[2025-04-28 04:43:23,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 1.1658682823181152, cross_entropy: 1.1658682823181152 +[2025-04-28 04:43:25,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 1.5093464851379395, cross_entropy: 1.5093464851379395 +[2025-04-28 04:43:25,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.634328842163086, cross_entropy: 1.634328842163086 +[2025-04-28 04:43:27,920][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.7306690216064453, cross_entropy: 1.7306690216064453 +[2025-04-28 04:43:28,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 3.561948299407959, cross_entropy: 3.561948299407959 +[2025-04-28 04:43:30,285][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.6682071685791016, cross_entropy: 1.6682071685791016 +[2025-04-28 04:43:31,112][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.9616951942443848, cross_entropy: 2.9616951942443848 +[2025-04-28 04:43:32,458][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 3.2014122009277344, cross_entropy: 3.2014122009277344 +[2025-04-28 04:43:33,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 2.0585598945617676, cross_entropy: 2.0585598945617676 +[2025-04-28 04:43:34,737][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.8679307699203491, cross_entropy: 1.8679307699203491 +[2025-04-28 04:43:35,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 2.7525248527526855, cross_entropy: 2.7525248527526855 +[2025-04-28 04:43:37,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 3.162503242492676, cross_entropy: 3.162503242492676 +[2025-04-28 04:43:37,795][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.6095901727676392, cross_entropy: 1.6095901727676392 +[2025-04-28 04:43:39,449][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 0.8626112937927246, cross_entropy: 0.8626112937927246 +[2025-04-28 04:43:40,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 2.330612897872925, cross_entropy: 2.330612897872925 +[2025-04-28 04:43:42,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.993591547012329, cross_entropy: 1.993591547012329 +[2025-04-28 04:43:42,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 3.1086153984069824, cross_entropy: 3.1086153984069824 +[2025-04-28 04:43:44,481][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 1.6772633790969849, cross_entropy: 1.6772633790969849 +[2025-04-28 04:43:45,045][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 3.322030544281006, cross_entropy: 3.322030544281006 +[2025-04-28 04:43:46,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 3.019681215286255, cross_entropy: 3.019681215286255 +[2025-04-28 04:43:46,833][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 1.2808623313903809, cross_entropy: 1.2808623313903809 +[2025-04-28 04:45:41,387][BaseTrainer][INFO] - [Epoch 8/10] (train) 2.1267778873443604, cross_entropy: 2.1267778873443604 +[2025-04-28 04:45:41,387][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.6066200733184814, cross_entropy: 1.6066200733184814 +[2025-04-28 04:45:41,608][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 04:45:41,774][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch8.pth. +[2025-04-28 04:45:41,980][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:45:45,469][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.8544803857803345, cross_entropy: 1.8544803857803345 +[2025-04-28 04:45:46,049][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.5256342887878418, cross_entropy: 1.5256342887878418 +[2025-04-28 04:45:48,116][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 3.094752073287964, cross_entropy: 3.094752073287964 +[2025-04-28 04:45:48,438][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 3.3241991996765137, cross_entropy: 3.3241991996765137 +[2025-04-28 04:45:50,451][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 2.811185598373413, cross_entropy: 2.811185598373413 +[2025-04-28 04:45:50,731][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.060815453529358, cross_entropy: 1.060815453529358 +[2025-04-28 04:45:52,696][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.423184394836426, cross_entropy: 2.423184394836426 +[2025-04-28 04:45:52,964][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.614180564880371, cross_entropy: 2.614180564880371 +[2025-04-28 04:45:55,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.537003755569458, cross_entropy: 2.537003755569458 +[2025-04-28 04:45:55,332][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 3.134075164794922, cross_entropy: 3.134075164794922 +[2025-04-28 04:45:57,410][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.4249582290649414, cross_entropy: 1.4249582290649414 +[2025-04-28 04:45:58,494][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 1.3051968812942505, cross_entropy: 1.3051968812942505 +[2025-04-28 04:45:59,985][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.976151466369629, cross_entropy: 2.976151466369629 +[2025-04-28 04:46:00,430][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 1.2208352088928223, cross_entropy: 1.2208352088928223 +[2025-04-28 04:46:02,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.796278476715088, cross_entropy: 2.796278476715088 +[2025-04-28 04:46:03,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 1.2792941331863403, cross_entropy: 1.2792941331863403 +[2025-04-28 04:46:05,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 1.0233078002929688, cross_entropy: 1.0233078002929688 +[2025-04-28 04:46:05,347][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.1127874851226807, cross_entropy: 1.1127874851226807 +[2025-04-28 04:46:06,975][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.1028094291687012, cross_entropy: 1.1028094291687012 +[2025-04-28 04:46:07,270][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.628717303276062, cross_entropy: 1.628717303276062 +[2025-04-28 04:46:10,411][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.532719373703003, cross_entropy: 1.532719373703003 +[2025-04-28 04:46:10,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 1.8271653652191162, cross_entropy: 1.8271653652191162 +[2025-04-28 04:46:13,212][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.5351386070251465, cross_entropy: 2.5351386070251465 +[2025-04-28 04:46:13,490][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.7359747886657715, cross_entropy: 2.7359747886657715 +[2025-04-28 04:46:15,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 3.066824197769165, cross_entropy: 3.066824197769165 +[2025-04-28 04:46:16,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 2.0672049522399902, cross_entropy: 2.0672049522399902 +[2025-04-28 04:46:18,038][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 2.004889965057373, cross_entropy: 2.004889965057373 +[2025-04-28 04:46:18,317][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.2905025482177734, cross_entropy: 2.2905025482177734 +[2025-04-28 04:46:20,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.5847089290618896, cross_entropy: 2.5847089290618896 +[2025-04-28 04:46:20,401][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.7417497634887695, cross_entropy: 1.7417497634887695 +[2025-04-28 04:46:22,755][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 3.091240882873535, cross_entropy: 3.091240882873535 +[2025-04-28 04:46:23,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.841251015663147, cross_entropy: 1.841251015663147 +[2025-04-28 04:46:25,123][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 2.0123119354248047, cross_entropy: 2.0123119354248047 +[2025-04-28 04:46:25,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.656378746032715, cross_entropy: 2.656378746032715 +[2025-04-28 04:46:27,627][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 3.044645071029663, cross_entropy: 3.044645071029663 +[2025-04-28 04:46:27,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 1.6497917175292969, cross_entropy: 1.6497917175292969 +[2025-04-28 04:46:30,175][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 1.4214191436767578, cross_entropy: 1.4214191436767578 +[2025-04-28 04:46:30,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 2.9417717456817627, cross_entropy: 2.9417717456817627 +[2025-04-28 04:46:32,554][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.219214916229248, cross_entropy: 1.219214916229248 +[2025-04-28 04:46:32,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 3.2161223888397217, cross_entropy: 3.2161223888397217 +[2025-04-28 04:46:34,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 2.9949991703033447, cross_entropy: 2.9949991703033447 +[2025-04-28 04:46:35,262][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.9071290493011475, cross_entropy: 2.9071290493011475 +[2025-04-28 04:46:37,269][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.628021717071533, cross_entropy: 2.628021717071533 +[2025-04-28 04:46:37,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 1.184027910232544, cross_entropy: 1.184027910232544 +[2025-04-28 04:46:39,469][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 1.2280889749526978, cross_entropy: 1.2280889749526978 +[2025-04-28 04:46:39,750][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 2.3089311122894287, cross_entropy: 2.3089311122894287 +[2025-04-28 04:46:42,721][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.225980758666992, cross_entropy: 3.225980758666992 +[2025-04-28 04:46:42,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 3.2155685424804688, cross_entropy: 3.2155685424804688 +[2025-04-28 04:46:45,058][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 3.266818046569824, cross_entropy: 3.266818046569824 +[2025-04-28 04:46:45,337][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 1.3043583631515503, cross_entropy: 1.3043583631515503 +[2025-04-28 04:46:47,833][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.5728445053100586, cross_entropy: 1.5728445053100586 +[2025-04-28 04:46:48,101][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.685283899307251, cross_entropy: 1.685283899307251 +[2025-04-28 04:46:50,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 0.9993304014205933, cross_entropy: 0.9993304014205933 +[2025-04-28 04:46:50,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.760195255279541, cross_entropy: 1.760195255279541 +[2025-04-28 04:46:51,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 1.9336984157562256, cross_entropy: 1.9336984157562256 +[2025-04-28 04:46:52,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 3.174264430999756, cross_entropy: 3.174264430999756 +[2025-04-28 04:46:53,941][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.2360105514526367, cross_entropy: 1.2360105514526367 +[2025-04-28 04:46:54,944][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 1.5110868215560913, cross_entropy: 1.5110868215560913 +[2025-04-28 04:46:56,591][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 2.064279556274414, cross_entropy: 2.064279556274414 +[2025-04-28 04:46:57,269][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 2.995148181915283, cross_entropy: 2.995148181915283 +[2025-04-28 04:46:58,927][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.327730417251587, cross_entropy: 2.327730417251587 +[2025-04-28 04:46:59,591][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.6528444290161133, cross_entropy: 2.6528444290161133 +[2025-04-28 04:47:01,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 1.4021295309066772, cross_entropy: 1.4021295309066772 +[2025-04-28 04:47:01,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.903653621673584, cross_entropy: 1.903653621673584 +[2025-04-28 04:47:03,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 3.2118537425994873, cross_entropy: 3.2118537425994873 +[2025-04-28 04:47:03,990][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 1.2277754545211792, cross_entropy: 1.2277754545211792 +[2025-04-28 04:47:06,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.9117462038993835, cross_entropy: 0.9117462038993835 +[2025-04-28 04:47:07,223][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.9882331490516663, cross_entropy: 0.9882331490516663 +[2025-04-28 04:47:09,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 1.3033523559570312, cross_entropy: 1.3033523559570312 +[2025-04-28 04:47:09,484][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.72480046749115, cross_entropy: 1.72480046749115 +[2025-04-28 04:47:12,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 1.2012370824813843, cross_entropy: 1.2012370824813843 +[2025-04-28 04:47:12,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.4190897941589355, cross_entropy: 1.4190897941589355 +[2025-04-28 04:47:14,906][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.4216930866241455, cross_entropy: 1.4216930866241455 +[2025-04-28 04:47:15,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 1.1826282739639282, cross_entropy: 1.1826282739639282 +[2025-04-28 04:47:17,331][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.778547763824463, cross_entropy: 2.778547763824463 +[2025-04-28 04:47:17,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.8369808197021484, cross_entropy: 2.8369808197021484 +[2025-04-28 04:47:19,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 2.9818806648254395, cross_entropy: 2.9818806648254395 +[2025-04-28 04:47:19,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 1.1716737747192383, cross_entropy: 1.1716737747192383 +[2025-04-28 04:47:21,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 2.7758774757385254, cross_entropy: 2.7758774757385254 +[2025-04-28 04:47:22,150][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 1.0900851488113403, cross_entropy: 1.0900851488113403 +[2025-04-28 04:47:24,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 2.5224037170410156, cross_entropy: 2.5224037170410156 +[2025-04-28 04:47:24,389][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 1.451480507850647, cross_entropy: 1.451480507850647 +[2025-04-28 04:47:26,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.415661334991455, cross_entropy: 1.415661334991455 +[2025-04-28 04:47:27,238][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 2.8180742263793945, cross_entropy: 2.8180742263793945 +[2025-04-28 04:47:29,069][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.5198659896850586, cross_entropy: 1.5198659896850586 +[2025-04-28 04:47:30,044][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.7032897472381592, cross_entropy: 1.7032897472381592 +[2025-04-28 04:47:31,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.6893668174743652, cross_entropy: 2.6893668174743652 +[2025-04-28 04:47:32,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 2.0520806312561035, cross_entropy: 2.0520806312561035 +[2025-04-28 04:47:33,430][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 1.4016098976135254, cross_entropy: 1.4016098976135254 +[2025-04-28 04:47:35,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.542421340942383, cross_entropy: 2.542421340942383 +[2025-04-28 04:47:36,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 3.009613513946533, cross_entropy: 3.009613513946533 +[2025-04-28 04:47:37,498][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 2.0437862873077393, cross_entropy: 2.0437862873077393 +[2025-04-28 04:47:38,343][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 3.1776740550994873, cross_entropy: 3.1776740550994873 +[2025-04-28 04:47:39,780][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 1.745190143585205, cross_entropy: 1.745190143585205 +[2025-04-28 04:47:40,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.2346596717834473, cross_entropy: 2.2346596717834473 +[2025-04-28 04:47:42,626][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.8994758129119873, cross_entropy: 1.8994758129119873 +[2025-04-28 04:47:42,905][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 3.058041572570801, cross_entropy: 3.058041572570801 +[2025-04-28 04:47:46,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 1.977432131767273, cross_entropy: 1.977432131767273 +[2025-04-28 04:47:46,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.9645633697509766, cross_entropy: 1.9645633697509766 +[2025-04-28 04:47:48,971][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.7276936769485474, cross_entropy: 1.7276936769485474 +[2025-04-28 04:47:49,254][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 3.054499864578247, cross_entropy: 3.054499864578247 +[2025-04-28 04:47:50,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 2.962876319885254, cross_entropy: 2.962876319885254 +[2025-04-28 04:47:51,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.8961710929870605, cross_entropy: 1.8961710929870605 +[2025-04-28 04:47:53,141][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 3.159583330154419, cross_entropy: 3.159583330154419 +[2025-04-28 04:47:53,424][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 1.3478314876556396, cross_entropy: 1.3478314876556396 +[2025-04-28 04:47:54,950][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 3.0267109870910645, cross_entropy: 3.0267109870910645 +[2025-04-28 04:47:55,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 3.0485618114471436, cross_entropy: 3.0485618114471436 +[2025-04-28 04:47:57,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.8862034678459167, cross_entropy: 0.8862034678459167 +[2025-04-28 04:47:57,474][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 3.1134445667266846, cross_entropy: 3.1134445667266846 +[2025-04-28 04:48:00,448][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 1.5126917362213135, cross_entropy: 1.5126917362213135 +[2025-04-28 04:48:00,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 3.11313533782959, cross_entropy: 3.11313533782959 +[2025-04-28 04:48:02,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.615786075592041, cross_entropy: 2.615786075592041 +[2025-04-28 04:48:02,743][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.577737808227539, cross_entropy: 2.577737808227539 +[2025-04-28 04:48:04,678][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.7498213052749634, cross_entropy: 1.7498213052749634 +[2025-04-28 04:48:05,017][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.9355432987213135, cross_entropy: 2.9355432987213135 +[2025-04-28 04:48:06,734][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 1.3934481143951416, cross_entropy: 1.3934481143951416 +[2025-04-28 04:48:07,916][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 0.867401659488678, cross_entropy: 0.867401659488678 +[2025-04-28 04:48:08,717][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 2.113215684890747, cross_entropy: 2.113215684890747 +[2025-04-28 04:48:10,919][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.870720386505127, cross_entropy: 2.870720386505127 +[2025-04-28 04:48:11,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.140777587890625, cross_entropy: 2.140777587890625 +[2025-04-28 04:48:13,491][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.8180899620056152, cross_entropy: 2.8180899620056152 +[2025-04-28 04:48:13,771][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.4357526302337646, cross_entropy: 1.4357526302337646 +[2025-04-28 04:48:16,882][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 1.8233586549758911, cross_entropy: 1.8233586549758911 +[2025-04-28 04:48:17,165][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.761157751083374, cross_entropy: 2.761157751083374 +[2025-04-28 04:48:20,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.223622441291809, cross_entropy: 1.223622441291809 +[2025-04-28 04:48:20,512][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.7193619012832642, cross_entropy: 1.7193619012832642 +[2025-04-28 04:48:22,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 2.5622715950012207, cross_entropy: 2.5622715950012207 +[2025-04-28 04:48:22,573][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.8632333278656006, cross_entropy: 1.8632333278656006 +[2025-04-28 04:48:25,438][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 3.1143813133239746, cross_entropy: 3.1143813133239746 +[2025-04-28 04:48:25,707][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 1.3631821870803833, cross_entropy: 1.3631821870803833 +[2025-04-28 04:48:27,738][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 1.2771391868591309, cross_entropy: 1.2771391868591309 +[2025-04-28 04:48:28,018][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.8791582584381104, cross_entropy: 2.8791582584381104 +[2025-04-28 04:48:29,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.6979907751083374, cross_entropy: 1.6979907751083374 +[2025-04-28 04:48:30,260][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.6394166946411133, cross_entropy: 1.6394166946411133 +[2025-04-28 04:48:32,022][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 3.246915817260742, cross_entropy: 3.246915817260742 +[2025-04-28 04:48:32,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.6442174911499023, cross_entropy: 1.6442174911499023 +[2025-04-28 04:48:34,836][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.1573617458343506, cross_entropy: 2.1573617458343506 +[2025-04-28 04:48:35,116][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 1.6365370750427246, cross_entropy: 1.6365370750427246 +[2025-04-28 04:48:37,343][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.0932626724243164, cross_entropy: 2.0932626724243164 +[2025-04-28 04:48:37,623][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.844681739807129, cross_entropy: 2.844681739807129 +[2025-04-28 04:48:39,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.141467332839966, cross_entropy: 2.141467332839966 +[2025-04-28 04:48:39,771][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.9150102138519287, cross_entropy: 2.9150102138519287 +[2025-04-28 04:48:41,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.587137460708618, cross_entropy: 2.587137460708618 +[2025-04-28 04:48:42,059][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.6326980590820312, cross_entropy: 2.6326980590820312 +[2025-04-28 04:48:44,236][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 1.2765730619430542, cross_entropy: 1.2765730619430542 +[2025-04-28 04:48:44,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 2.8207874298095703, cross_entropy: 2.8207874298095703 +[2025-04-28 04:48:46,597][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 2.286513090133667, cross_entropy: 2.286513090133667 +[2025-04-28 04:48:46,864][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.6705176830291748, cross_entropy: 1.6705176830291748 +[2025-04-28 04:48:50,372][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 2.967726707458496, cross_entropy: 2.967726707458496 +[2025-04-28 04:48:50,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 1.0307159423828125, cross_entropy: 1.0307159423828125 +[2025-04-28 04:48:52,619][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 1.523990511894226, cross_entropy: 1.523990511894226 +[2025-04-28 04:48:52,901][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 1.4610471725463867, cross_entropy: 1.4610471725463867 +[2025-04-28 04:48:53,156][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/iteration3000.pth. +[2025-04-28 04:48:55,320][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 3.181763172149658, cross_entropy: 3.181763172149658 +[2025-04-28 04:48:55,602][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.0543253421783447, cross_entropy: 2.0543253421783447 +[2025-04-28 04:48:57,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 1.3014906644821167, cross_entropy: 1.3014906644821167 +[2025-04-28 04:48:57,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 1.4880715608596802, cross_entropy: 1.4880715608596802 +[2025-04-28 04:49:00,022][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.795940637588501, cross_entropy: 1.795940637588501 +[2025-04-28 04:49:00,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 1.5169062614440918, cross_entropy: 1.5169062614440918 +[2025-04-28 04:49:02,196][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 2.9097728729248047, cross_entropy: 2.9097728729248047 +[2025-04-28 04:49:02,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 1.2692819833755493, cross_entropy: 1.2692819833755493 +[2025-04-28 04:49:04,862][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 1.4307143688201904, cross_entropy: 1.4307143688201904 +[2025-04-28 04:49:05,129][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 0.8968158960342407, cross_entropy: 0.8968158960342407 +[2025-04-28 04:49:07,311][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 3.1804423332214355, cross_entropy: 3.1804423332214355 +[2025-04-28 04:49:07,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 1.509103775024414, cross_entropy: 1.509103775024414 +[2025-04-28 04:49:09,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 1.405155897140503, cross_entropy: 1.405155897140503 +[2025-04-28 04:49:10,001][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 1.497361183166504, cross_entropy: 1.497361183166504 +[2025-04-28 04:49:11,718][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.1371190547943115, cross_entropy: 1.1371190547943115 +[2025-04-28 04:49:11,999][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.8797738552093506, cross_entropy: 2.8797738552093506 +[2025-04-28 04:49:13,968][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 3.0896003246307373, cross_entropy: 3.0896003246307373 +[2025-04-28 04:49:14,235][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 1.3012582063674927, cross_entropy: 1.3012582063674927 +[2025-04-28 04:49:16,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 3.001019239425659, cross_entropy: 3.001019239425659 +[2025-04-28 04:49:17,071][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.5191043615341187, cross_entropy: 1.5191043615341187 +[2025-04-28 04:49:19,027][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 1.0927445888519287, cross_entropy: 1.0927445888519287 +[2025-04-28 04:49:19,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 2.949450731277466, cross_entropy: 2.949450731277466 +[2025-04-28 04:49:22,026][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.6421380043029785, cross_entropy: 1.6421380043029785 +[2025-04-28 04:49:22,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 2.800095796585083, cross_entropy: 2.800095796585083 +[2025-04-28 04:49:25,071][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 2.9436683654785156, cross_entropy: 2.9436683654785156 +[2025-04-28 04:49:25,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.4613370895385742, cross_entropy: 1.4613370895385742 +[2025-04-28 04:49:28,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.3706110715866089, cross_entropy: 1.3706110715866089 +[2025-04-28 04:49:28,337][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.7235429286956787, cross_entropy: 2.7235429286956787 +[2025-04-28 04:49:30,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 1.6968669891357422, cross_entropy: 1.6968669891357422 +[2025-04-28 04:49:30,844][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 3.04317045211792, cross_entropy: 3.04317045211792 +[2025-04-28 04:49:32,962][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.0166521072387695, cross_entropy: 1.0166521072387695 +[2025-04-28 04:49:33,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 2.361584186553955, cross_entropy: 2.361584186553955 +[2025-04-28 04:49:35,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 1.3885735273361206, cross_entropy: 1.3885735273361206 +[2025-04-28 04:49:35,498][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.791269302368164, cross_entropy: 2.791269302368164 +[2025-04-28 04:49:37,709][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.616229772567749, cross_entropy: 2.616229772567749 +[2025-04-28 04:49:37,977][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 3.0861425399780273, cross_entropy: 3.0861425399780273 +[2025-04-28 04:49:40,116][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.6813113689422607, cross_entropy: 1.6813113689422607 +[2025-04-28 04:49:40,398][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.3891795873641968, cross_entropy: 1.3891795873641968 +[2025-04-28 04:49:42,505][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 2.5505290031433105, cross_entropy: 2.5505290031433105 +[2025-04-28 04:49:42,773][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.6456873416900635, cross_entropy: 1.6456873416900635 +[2025-04-28 04:49:44,654][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.079824209213257, cross_entropy: 2.079824209213257 +[2025-04-28 04:49:44,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 2.4282124042510986, cross_entropy: 2.4282124042510986 +[2025-04-28 04:49:47,309][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 1.8240097761154175, cross_entropy: 1.8240097761154175 +[2025-04-28 04:49:47,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.3610329627990723, cross_entropy: 3.3610329627990723 +[2025-04-28 04:49:49,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 2.564220905303955, cross_entropy: 2.564220905303955 +[2025-04-28 04:49:49,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 2.1188368797302246, cross_entropy: 2.1188368797302246 +[2025-04-28 04:49:52,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 1.302771806716919, cross_entropy: 1.302771806716919 +[2025-04-28 04:49:52,513][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.9249340295791626, cross_entropy: 1.9249340295791626 +[2025-04-28 04:49:54,547][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 3.0789971351623535, cross_entropy: 3.0789971351623535 +[2025-04-28 04:49:54,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.1426496505737305, cross_entropy: 1.1426496505737305 +[2025-04-28 04:49:56,963][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 2.4281787872314453, cross_entropy: 2.4281787872314453 +[2025-04-28 04:49:57,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 3.308811664581299, cross_entropy: 3.308811664581299 +[2025-04-28 04:49:59,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.7441761493682861, cross_entropy: 1.7441761493682861 +[2025-04-28 04:49:59,331][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 1.447749376296997, cross_entropy: 1.447749376296997 +[2025-04-28 04:50:01,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 1.4737716913223267, cross_entropy: 1.4737716913223267 +[2025-04-28 04:50:01,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 2.353095531463623, cross_entropy: 2.353095531463623 +[2025-04-28 04:50:04,164][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 2.449033260345459, cross_entropy: 2.449033260345459 +[2025-04-28 04:50:04,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 3.411897659301758, cross_entropy: 3.411897659301758 +[2025-04-28 04:50:06,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 1.6721036434173584, cross_entropy: 1.6721036434173584 +[2025-04-28 04:50:06,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 1.488490343093872, cross_entropy: 1.488490343093872 +[2025-04-28 04:50:09,357][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 1.5298614501953125, cross_entropy: 1.5298614501953125 +[2025-04-28 04:50:09,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 1.5915822982788086, cross_entropy: 1.5915822982788086 +[2025-04-28 04:50:12,384][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.418508768081665, cross_entropy: 1.418508768081665 +[2025-04-28 04:50:12,666][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 2.403451442718506, cross_entropy: 2.403451442718506 +[2025-04-28 04:50:14,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 1.126286268234253, cross_entropy: 1.126286268234253 +[2025-04-28 04:50:15,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 1.6505721807479858, cross_entropy: 1.6505721807479858 +[2025-04-28 04:50:16,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 3.363734722137451, cross_entropy: 3.363734722137451 +[2025-04-28 04:50:17,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.015740394592285, cross_entropy: 2.015740394592285 +[2025-04-28 04:50:19,129][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.486036777496338, cross_entropy: 2.486036777496338 +[2025-04-28 04:50:19,409][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 2.3445541858673096, cross_entropy: 2.3445541858673096 +[2025-04-28 04:50:21,194][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.0376992225646973, cross_entropy: 2.0376992225646973 +[2025-04-28 04:50:21,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 1.2122225761413574, cross_entropy: 1.2122225761413574 +[2025-04-28 04:50:23,810][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 3.0705726146698, cross_entropy: 3.0705726146698 +[2025-04-28 04:50:24,090][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 2.125624656677246, cross_entropy: 2.125624656677246 +[2025-04-28 04:50:26,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 2.795940399169922, cross_entropy: 2.795940399169922 +[2025-04-28 04:50:26,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 3.3994228839874268, cross_entropy: 3.3994228839874268 +[2025-04-28 04:50:28,689][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.4738905429840088, cross_entropy: 1.4738905429840088 +[2025-04-28 04:50:28,969][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 3.119932174682617, cross_entropy: 3.119932174682617 +[2025-04-28 04:50:30,588][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 0.8261114358901978, cross_entropy: 0.8261114358901978 +[2025-04-28 04:50:30,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 1.3605616092681885, cross_entropy: 1.3605616092681885 +[2025-04-28 04:50:32,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 2.720839500427246, cross_entropy: 2.720839500427246 +[2025-04-28 04:50:33,008][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 3.053060531616211, cross_entropy: 3.053060531616211 +[2025-04-28 04:50:34,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 2.9790823459625244, cross_entropy: 2.9790823459625244 +[2025-04-28 04:50:35,394][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 3.175306558609009, cross_entropy: 3.175306558609009 +[2025-04-28 04:50:37,608][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.8052514791488647, cross_entropy: 1.8052514791488647 +[2025-04-28 04:50:37,887][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.7949671745300293, cross_entropy: 2.7949671745300293 +[2025-04-28 04:50:40,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 3.0030875205993652, cross_entropy: 3.0030875205993652 +[2025-04-28 04:50:41,258][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 2.90228533744812, cross_entropy: 2.90228533744812 +[2025-04-28 04:50:43,583][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.6819562911987305, cross_entropy: 1.6819562911987305 +[2025-04-28 04:50:43,863][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 2.3699536323547363, cross_entropy: 2.3699536323547363 +[2025-04-28 04:50:45,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 3.001237630844116, cross_entropy: 3.001237630844116 +[2025-04-28 04:50:46,154][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 2.1930341720581055, cross_entropy: 2.1930341720581055 +[2025-04-28 04:50:48,437][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.3111085891723633, cross_entropy: 2.3111085891723633 +[2025-04-28 04:50:48,716][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 1.3568693399429321, cross_entropy: 1.3568693399429321 +[2025-04-28 04:50:50,921][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 2.846106767654419, cross_entropy: 2.846106767654419 +[2025-04-28 04:50:51,191][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 1.825840950012207, cross_entropy: 1.825840950012207 +[2025-04-28 04:50:53,123][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.4685770273208618, cross_entropy: 1.4685770273208618 +[2025-04-28 04:50:53,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 3.0998892784118652, cross_entropy: 3.0998892784118652 +[2025-04-28 04:50:56,373][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 2.780090808868408, cross_entropy: 2.780090808868408 +[2025-04-28 04:50:56,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.66013240814209, cross_entropy: 2.66013240814209 +[2025-04-28 04:50:59,128][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.6386967897415161, cross_entropy: 1.6386967897415161 +[2025-04-28 04:50:59,408][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 1.8252519369125366, cross_entropy: 1.8252519369125366 +[2025-04-28 04:51:01,325][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 1.1175408363342285, cross_entropy: 1.1175408363342285 +[2025-04-28 04:51:01,605][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 1.2233335971832275, cross_entropy: 1.2233335971832275 +[2025-04-28 04:51:03,422][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 2.492213010787964, cross_entropy: 2.492213010787964 +[2025-04-28 04:51:03,976][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.9136525392532349, cross_entropy: 1.9136525392532349 +[2025-04-28 04:51:05,849][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 1.4953453540802002, cross_entropy: 1.4953453540802002 +[2025-04-28 04:51:06,326][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 3.0970516204833984, cross_entropy: 3.0970516204833984 +[2025-04-28 04:51:08,961][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 1.8025567531585693, cross_entropy: 1.8025567531585693 +[2025-04-28 04:51:09,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 0.9131800532341003, cross_entropy: 0.9131800532341003 +[2025-04-28 04:51:11,313][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 1.829308032989502, cross_entropy: 1.829308032989502 +[2025-04-28 04:51:11,594][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 1.7534799575805664, cross_entropy: 1.7534799575805664 +[2025-04-28 04:51:13,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.3705735206604004, cross_entropy: 1.3705735206604004 +[2025-04-28 04:51:13,932][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 1.2767751216888428, cross_entropy: 1.2767751216888428 +[2025-04-28 04:51:15,969][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.7899044752120972, cross_entropy: 1.7899044752120972 +[2025-04-28 04:51:16,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.282438278198242, cross_entropy: 2.282438278198242 +[2025-04-28 04:51:18,260][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.160247802734375, cross_entropy: 2.160247802734375 +[2025-04-28 04:51:19,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 2.996272563934326, cross_entropy: 2.996272563934326 +[2025-04-28 04:51:20,693][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 1.166236162185669, cross_entropy: 1.166236162185669 +[2025-04-28 04:51:21,697][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 3.3689093589782715, cross_entropy: 3.3689093589782715 +[2025-04-28 04:51:23,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 1.6299546957015991, cross_entropy: 1.6299546957015991 +[2025-04-28 04:51:23,689][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 1.0800453424453735, cross_entropy: 1.0800453424453735 +[2025-04-28 04:51:25,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 1.998947024345398, cross_entropy: 1.998947024345398 +[2025-04-28 04:51:26,245][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 1.0586929321289062, cross_entropy: 1.0586929321289062 +[2025-04-28 04:51:27,980][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.6664097309112549, cross_entropy: 1.6664097309112549 +[2025-04-28 04:51:29,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.647226095199585, cross_entropy: 1.647226095199585 +[2025-04-28 04:51:30,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.186577320098877, cross_entropy: 2.186577320098877 +[2025-04-28 04:51:31,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.635552167892456, cross_entropy: 1.635552167892456 +[2025-04-28 04:51:33,130][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.2089099884033203, cross_entropy: 1.2089099884033203 +[2025-04-28 04:51:34,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 1.767817735671997, cross_entropy: 1.767817735671997 +[2025-04-28 04:51:35,202][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 1.2628097534179688, cross_entropy: 1.2628097534179688 +[2025-04-28 04:51:36,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 3.0239205360412598, cross_entropy: 3.0239205360412598 +[2025-04-28 04:51:37,781][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 2.912961483001709, cross_entropy: 2.912961483001709 +[2025-04-28 04:51:39,284][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.6719520092010498, cross_entropy: 1.6719520092010498 +[2025-04-28 04:51:39,818][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 2.934299945831299, cross_entropy: 2.934299945831299 +[2025-04-28 04:51:41,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 1.366399884223938, cross_entropy: 1.366399884223938 +[2025-04-28 04:51:42,197][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 2.3965799808502197, cross_entropy: 2.3965799808502197 +[2025-04-28 04:51:44,152][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 0.9378716349601746, cross_entropy: 0.9378716349601746 +[2025-04-28 04:51:44,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 3.1725502014160156, cross_entropy: 3.1725502014160156 +[2025-04-28 04:51:46,608][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.3143072128295898, cross_entropy: 1.3143072128295898 +[2025-04-28 04:51:46,932][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.569091558456421, cross_entropy: 1.569091558456421 +[2025-04-28 04:51:48,951][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 1.6702346801757812, cross_entropy: 1.6702346801757812 +[2025-04-28 04:51:49,387][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 1.5721498727798462, cross_entropy: 1.5721498727798462 +[2025-04-28 04:51:51,345][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.1138606071472168, cross_entropy: 1.1138606071472168 +[2025-04-28 04:51:51,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.8646149635314941, cross_entropy: 1.8646149635314941 +[2025-04-28 04:51:53,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 2.709306240081787, cross_entropy: 2.709306240081787 +[2025-04-28 04:51:53,857][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 2.9079341888427734, cross_entropy: 2.9079341888427734 +[2025-04-28 04:51:56,911][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 2.4313361644744873, cross_entropy: 2.4313361644744873 +[2025-04-28 04:51:57,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.220266103744507, cross_entropy: 2.220266103744507 +[2025-04-28 04:52:00,007][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 3.1123623847961426, cross_entropy: 3.1123623847961426 +[2025-04-28 04:52:00,289][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 1.1111292839050293, cross_entropy: 1.1111292839050293 +[2025-04-28 04:52:03,028][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 3.0806407928466797, cross_entropy: 3.0806407928466797 +[2025-04-28 04:52:03,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.8253469467163086, cross_entropy: 2.8253469467163086 +[2025-04-28 04:52:05,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 3.060232162475586, cross_entropy: 3.060232162475586 +[2025-04-28 04:52:05,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 1.3868277072906494, cross_entropy: 1.3868277072906494 +[2025-04-28 04:52:07,569][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 1.5845228433609009, cross_entropy: 1.5845228433609009 +[2025-04-28 04:52:07,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 1.589785099029541, cross_entropy: 1.589785099029541 +[2025-04-28 04:52:10,299][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 3.299276351928711, cross_entropy: 3.299276351928711 +[2025-04-28 04:52:10,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 1.798580288887024, cross_entropy: 1.798580288887024 +[2025-04-28 04:52:12,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 3.268214702606201, cross_entropy: 3.268214702606201 +[2025-04-28 04:52:12,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 2.2471070289611816, cross_entropy: 2.2471070289611816 +[2025-04-28 04:52:14,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.6141042709350586, cross_entropy: 1.6141042709350586 +[2025-04-28 04:52:14,529][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.790207862854004, cross_entropy: 1.790207862854004 +[2025-04-28 04:52:16,413][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 1.9426451921463013, cross_entropy: 1.9426451921463013 +[2025-04-28 04:52:16,693][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 1.333472728729248, cross_entropy: 1.333472728729248 +[2025-04-28 04:52:19,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 1.4015419483184814, cross_entropy: 1.4015419483184814 +[2025-04-28 04:52:19,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 1.7433979511260986, cross_entropy: 1.7433979511260986 +[2025-04-28 04:52:22,663][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 2.6466474533081055, cross_entropy: 2.6466474533081055 +[2025-04-28 04:52:22,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.161049485206604, cross_entropy: 1.161049485206604 +[2025-04-28 04:52:25,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 2.8725619316101074, cross_entropy: 2.8725619316101074 +[2025-04-28 04:52:25,346][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 1.1189711093902588, cross_entropy: 1.1189711093902588 +[2025-04-28 04:52:27,348][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 1.398223876953125, cross_entropy: 1.398223876953125 +[2025-04-28 04:52:27,627][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 1.7156651020050049, cross_entropy: 1.7156651020050049 +[2025-04-28 04:52:29,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 1.486066222190857, cross_entropy: 1.486066222190857 +[2025-04-28 04:52:29,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 1.6809571981430054, cross_entropy: 1.6809571981430054 +[2025-04-28 04:52:32,047][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.9454448223114014, cross_entropy: 1.9454448223114014 +[2025-04-28 04:52:32,330][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 3.1721272468566895, cross_entropy: 3.1721272468566895 +[2025-04-28 04:52:34,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 2.155966281890869, cross_entropy: 2.155966281890869 +[2025-04-28 04:52:35,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 1.4852056503295898, cross_entropy: 1.4852056503295898 +[2025-04-28 04:52:37,196][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 1.8236432075500488, cross_entropy: 1.8236432075500488 +[2025-04-28 04:52:37,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 1.5064983367919922, cross_entropy: 1.5064983367919922 +[2025-04-28 04:52:39,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 2.010638475418091, cross_entropy: 2.010638475418091 +[2025-04-28 04:52:40,015][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 1.487409234046936, cross_entropy: 1.487409234046936 +[2025-04-28 04:52:41,764][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.843508720397949, cross_entropy: 2.843508720397949 +[2025-04-28 04:52:42,044][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.3632066249847412, cross_entropy: 1.3632066249847412 +[2025-04-28 04:52:44,145][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.753201961517334, cross_entropy: 2.753201961517334 +[2025-04-28 04:52:44,413][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 2.2476017475128174, cross_entropy: 2.2476017475128174 +[2025-04-28 04:52:47,063][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 2.5519423484802246, cross_entropy: 2.5519423484802246 +[2025-04-28 04:52:47,341][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 3.1413722038269043, cross_entropy: 3.1413722038269043 +[2025-04-28 04:52:50,223][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 1.7007616758346558, cross_entropy: 1.7007616758346558 +[2025-04-28 04:52:50,507][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 2.539214611053467, cross_entropy: 2.539214611053467 +[2025-04-28 04:52:52,832][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.7426447868347168, cross_entropy: 1.7426447868347168 +[2025-04-28 04:52:53,115][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 1.1880674362182617, cross_entropy: 1.1880674362182617 +[2025-04-28 04:52:55,262][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.3495254516601562, cross_entropy: 2.3495254516601562 +[2025-04-28 04:52:55,543][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.182429552078247, cross_entropy: 1.182429552078247 +[2025-04-28 04:52:57,570][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.05026912689209, cross_entropy: 2.05026912689209 +[2025-04-28 04:52:57,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 1.762144684791565, cross_entropy: 1.762144684791565 +[2025-04-28 04:52:59,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.7565059661865234, cross_entropy: 2.7565059661865234 +[2025-04-28 04:53:00,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.682788372039795, cross_entropy: 2.682788372039795 +[2025-04-28 04:53:02,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 2.709550380706787, cross_entropy: 2.709550380706787 +[2025-04-28 04:53:02,910][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 2.1744344234466553, cross_entropy: 2.1744344234466553 +[2025-04-28 04:53:04,744][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 1.1732426881790161, cross_entropy: 1.1732426881790161 +[2025-04-28 04:53:05,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 1.1890780925750732, cross_entropy: 1.1890780925750732 +[2025-04-28 04:53:06,829][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 1.8096421957015991, cross_entropy: 1.8096421957015991 +[2025-04-28 04:55:01,343][BaseTrainer][INFO] - [Epoch 9/10] (train) 2.0834531784057617, cross_entropy: 2.0834531784057617 +[2025-04-28 04:55:01,343][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.5796525478363037, cross_entropy: 1.5796525478363037 +[2025-04-28 04:55:01,559][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 04:55:01,724][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch9.pth. +[2025-04-28 04:55:01,938][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 04:55:04,678][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.4126272201538086, cross_entropy: 1.4126272201538086 +[2025-04-28 04:55:05,020][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.926973581314087, cross_entropy: 1.926973581314087 +[2025-04-28 04:55:06,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.8339889049530029, cross_entropy: 0.8339889049530029 +[2025-04-28 04:55:09,045][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 2.9121923446655273, cross_entropy: 2.9121923446655273 +[2025-04-28 04:55:09,325][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.7084269523620605, cross_entropy: 2.7084269523620605 +[2025-04-28 04:55:11,123][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 2.016961097717285, cross_entropy: 2.016961097717285 +[2025-04-28 04:55:11,564][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.925325870513916, cross_entropy: 2.925325870513916 +[2025-04-28 04:55:14,104][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 1.529921054840088, cross_entropy: 1.529921054840088 +[2025-04-28 04:55:14,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.7138826847076416, cross_entropy: 2.7138826847076416 +[2025-04-28 04:55:16,770][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.7223474979400635, cross_entropy: 1.7223474979400635 +[2025-04-28 04:55:17,037][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.6374945640563965, cross_entropy: 2.6374945640563965 +[2025-04-28 04:55:19,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 2.7164676189422607, cross_entropy: 2.7164676189422607 +[2025-04-28 04:55:19,912][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.6023039817810059, cross_entropy: 1.6023039817810059 +[2025-04-28 04:55:21,929][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 2.523242473602295, cross_entropy: 2.523242473602295 +[2025-04-28 04:55:22,212][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.9144809246063232, cross_entropy: 2.9144809246063232 +[2025-04-28 04:55:23,843][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 1.5097650289535522, cross_entropy: 1.5097650289535522 +[2025-04-28 04:55:24,891][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 1.5313597917556763, cross_entropy: 1.5313597917556763 +[2025-04-28 04:55:26,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.4858806133270264, cross_entropy: 2.4858806133270264 +[2025-04-28 04:55:27,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 1.7503466606140137, cross_entropy: 1.7503466606140137 +[2025-04-28 04:55:28,942][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.0828932523727417, cross_entropy: 1.0828932523727417 +[2025-04-28 04:55:30,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 2.0567739009857178, cross_entropy: 2.0567739009857178 +[2025-04-28 04:55:31,304][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 3.3718032836914062, cross_entropy: 3.3718032836914062 +[2025-04-28 04:55:33,550][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.9331268072128296, cross_entropy: 0.9331268072128296 +[2025-04-28 04:55:34,053][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 1.401799201965332, cross_entropy: 1.401799201965332 +[2025-04-28 04:55:36,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.394733428955078, cross_entropy: 2.394733428955078 +[2025-04-28 04:55:36,607][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 2.899726629257202, cross_entropy: 2.899726629257202 +[2025-04-28 04:55:39,322][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 1.5547263622283936, cross_entropy: 1.5547263622283936 +[2025-04-28 04:55:39,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.2087600231170654, cross_entropy: 2.2087600231170654 +[2025-04-28 04:55:41,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.885547399520874, cross_entropy: 2.885547399520874 +[2025-04-28 04:55:41,926][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.5796663761138916, cross_entropy: 1.5796663761138916 +[2025-04-28 04:55:44,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.499025344848633, cross_entropy: 2.499025344848633 +[2025-04-28 04:55:44,926][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 1.2627369165420532, cross_entropy: 1.2627369165420532 +[2025-04-28 04:55:47,263][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 0.9997376203536987, cross_entropy: 0.9997376203536987 +[2025-04-28 04:55:47,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.4759724140167236, cross_entropy: 2.4759724140167236 +[2025-04-28 04:55:50,193][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.4679471254348755, cross_entropy: 1.4679471254348755 +[2025-04-28 04:55:50,472][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.8567328453063965, cross_entropy: 1.8567328453063965 +[2025-04-28 04:55:52,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.666203022003174, cross_entropy: 2.666203022003174 +[2025-04-28 04:55:52,888][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 1.1792891025543213, cross_entropy: 1.1792891025543213 +[2025-04-28 04:55:55,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 2.6090314388275146, cross_entropy: 2.6090314388275146 +[2025-04-28 04:55:55,801][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 1.2960063219070435, cross_entropy: 1.2960063219070435 +[2025-04-28 04:55:57,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 2.297189950942993, cross_entropy: 2.297189950942993 +[2025-04-28 04:55:58,225][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.3654870986938477, cross_entropy: 2.3654870986938477 +[2025-04-28 04:56:00,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 1.202505111694336, cross_entropy: 1.202505111694336 +[2025-04-28 04:56:00,439][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.8551993370056152, cross_entropy: 2.8551993370056152 +[2025-04-28 04:56:03,076][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.4305741786956787, cross_entropy: 1.4305741786956787 +[2025-04-28 04:56:03,356][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 2.928560256958008, cross_entropy: 2.928560256958008 +[2025-04-28 04:56:06,154][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 2.213240146636963, cross_entropy: 2.213240146636963 +[2025-04-28 04:56:06,434][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 2.721818447113037, cross_entropy: 2.721818447113037 +[2025-04-28 04:56:08,252][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.7359273433685303, cross_entropy: 1.7359273433685303 +[2025-04-28 04:56:08,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 3.113752841949463, cross_entropy: 3.113752841949463 +[2025-04-28 04:56:10,327][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.5015740394592285, cross_entropy: 2.5015740394592285 +[2025-04-28 04:56:10,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 2.2558341026306152, cross_entropy: 2.2558341026306152 +[2025-04-28 04:56:12,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.6764276027679443, cross_entropy: 1.6764276027679443 +[2025-04-28 04:56:12,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 1.0792500972747803, cross_entropy: 1.0792500972747803 +[2025-04-28 04:56:14,761][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.4280321598052979, cross_entropy: 1.4280321598052979 +[2025-04-28 04:56:15,041][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 1.6920323371887207, cross_entropy: 1.6920323371887207 +[2025-04-28 04:56:17,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.2457243204116821, cross_entropy: 1.2457243204116821 +[2025-04-28 04:56:18,093][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 1.887526512145996, cross_entropy: 1.887526512145996 +[2025-04-28 04:56:20,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 2.2932143211364746, cross_entropy: 2.2932143211364746 +[2025-04-28 04:56:20,837][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 1.2929240465164185, cross_entropy: 1.2929240465164185 +[2025-04-28 04:56:22,977][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 2.4880905151367188, cross_entropy: 2.4880905151367188 +[2025-04-28 04:56:23,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.1244151592254639, cross_entropy: 1.1244151592254639 +[2025-04-28 04:56:26,433][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 2.6549434661865234, cross_entropy: 2.6549434661865234 +[2025-04-28 04:56:26,784][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 3.076808452606201, cross_entropy: 3.076808452606201 +[2025-04-28 04:56:29,077][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 2.4229161739349365, cross_entropy: 2.4229161739349365 +[2025-04-28 04:56:29,358][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 2.857842206954956, cross_entropy: 2.857842206954956 +[2025-04-28 04:56:31,505][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 3.2144992351531982, cross_entropy: 3.2144992351531982 +[2025-04-28 04:56:31,782][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 0.9387376308441162, cross_entropy: 0.9387376308441162 +[2025-04-28 04:56:34,369][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 1.288907527923584, cross_entropy: 1.288907527923584 +[2025-04-28 04:56:34,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 1.501321792602539, cross_entropy: 1.501321792602539 +[2025-04-28 04:56:37,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 1.379028558731079, cross_entropy: 1.379028558731079 +[2025-04-28 04:56:37,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 3.0186305046081543, cross_entropy: 3.0186305046081543 +[2025-04-28 04:56:39,796][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.3816643953323364, cross_entropy: 1.3816643953323364 +[2025-04-28 04:56:40,063][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.943023204803467, cross_entropy: 2.943023204803467 +[2025-04-28 04:56:42,016][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 1.3565994501113892, cross_entropy: 1.3565994501113892 +[2025-04-28 04:56:42,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 3.01749324798584, cross_entropy: 3.01749324798584 +[2025-04-28 04:56:45,058][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.408124566078186, cross_entropy: 1.408124566078186 +[2025-04-28 04:56:45,337][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.7460453510284424, cross_entropy: 1.7460453510284424 +[2025-04-28 04:56:48,087][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.4023735523223877, cross_entropy: 1.4023735523223877 +[2025-04-28 04:56:48,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 2.6483402252197266, cross_entropy: 2.6483402252197266 +[2025-04-28 04:56:50,648][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.9824577569961548, cross_entropy: 1.9824577569961548 +[2025-04-28 04:56:50,930][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 1.0494472980499268, cross_entropy: 1.0494472980499268 +[2025-04-28 04:56:53,284][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 2.806225061416626, cross_entropy: 2.806225061416626 +[2025-04-28 04:56:53,564][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.788705825805664, cross_entropy: 2.788705825805664 +[2025-04-28 04:56:55,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 1.5821201801300049, cross_entropy: 1.5821201801300049 +[2025-04-28 04:56:55,748][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 1.7905874252319336, cross_entropy: 1.7905874252319336 +[2025-04-28 04:56:57,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 2.9868578910827637, cross_entropy: 2.9868578910827637 +[2025-04-28 04:56:58,057][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 1.55751371383667, cross_entropy: 1.55751371383667 +[2025-04-28 04:57:00,196][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 3.117213726043701, cross_entropy: 3.117213726043701 +[2025-04-28 04:57:00,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.2029283046722412, cross_entropy: 1.2029283046722412 +[2025-04-28 04:57:02,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.3696331977844238, cross_entropy: 1.3696331977844238 +[2025-04-28 04:57:02,880][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.199864387512207, cross_entropy: 1.199864387512207 +[2025-04-28 04:57:04,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.230699062347412, cross_entropy: 2.230699062347412 +[2025-04-28 04:57:05,139][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 1.4252249002456665, cross_entropy: 1.4252249002456665 +[2025-04-28 04:57:07,072][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.156736969947815, cross_entropy: 1.156736969947815 +[2025-04-28 04:57:07,367][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.6910145282745361, cross_entropy: 1.6910145282745361 +[2025-04-28 04:57:09,173][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 2.7203917503356934, cross_entropy: 2.7203917503356934 +[2025-04-28 04:57:09,607][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 3.2209157943725586, cross_entropy: 3.2209157943725586 +[2025-04-28 04:57:11,185][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.3136175870895386, cross_entropy: 1.3136175870895386 +[2025-04-28 04:57:11,563][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 1.3288853168487549, cross_entropy: 1.3288853168487549 +[2025-04-28 04:57:13,316][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 1.2515654563903809, cross_entropy: 1.2515654563903809 +[2025-04-28 04:57:13,784][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.8985390663146973, cross_entropy: 1.8985390663146973 +[2025-04-28 04:57:15,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 1.4720804691314697, cross_entropy: 1.4720804691314697 +[2025-04-28 04:57:16,421][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.3528690338134766, cross_entropy: 2.3528690338134766 +[2025-04-28 04:57:18,431][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 2.8959364891052246, cross_entropy: 2.8959364891052246 +[2025-04-28 04:57:18,709][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 0.8416499495506287, cross_entropy: 0.8416499495506287 +[2025-04-28 04:57:21,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.3844728469848633, cross_entropy: 1.3844728469848633 +[2025-04-28 04:57:21,576][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 2.2441256046295166, cross_entropy: 2.2441256046295166 +[2025-04-28 04:57:23,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.7268028259277344, cross_entropy: 2.7268028259277344 +[2025-04-28 04:57:23,813][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.7311415672302246, cross_entropy: 2.7311415672302246 +[2025-04-28 04:57:25,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 3.0200066566467285, cross_entropy: 3.0200066566467285 +[2025-04-28 04:57:26,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.3739147186279297, cross_entropy: 1.3739147186279297 +[2025-04-28 04:57:28,300][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 0.7697176933288574, cross_entropy: 0.7697176933288574 +[2025-04-28 04:57:28,587][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 1.6454591751098633, cross_entropy: 1.6454591751098633 +[2025-04-28 04:57:30,724][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.286761522293091, cross_entropy: 2.286761522293091 +[2025-04-28 04:57:31,004][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 1.8401501178741455, cross_entropy: 1.8401501178741455 +[2025-04-28 04:57:33,251][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.764115810394287, cross_entropy: 1.764115810394287 +[2025-04-28 04:57:33,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 1.3673176765441895, cross_entropy: 1.3673176765441895 +[2025-04-28 04:57:35,491][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 0.7090409994125366, cross_entropy: 0.7090409994125366 +[2025-04-28 04:57:35,770][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 1.8493751287460327, cross_entropy: 1.8493751287460327 +[2025-04-28 04:57:37,684][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 1.93284273147583, cross_entropy: 1.93284273147583 +[2025-04-28 04:57:37,964][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.684710144996643, cross_entropy: 1.684710144996643 +[2025-04-28 04:57:39,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.2377849817276, cross_entropy: 1.2377849817276 +[2025-04-28 04:57:40,421][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.2144360542297363, cross_entropy: 2.2144360542297363 +[2025-04-28 04:57:42,283][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 2.1753807067871094, cross_entropy: 2.1753807067871094 +[2025-04-28 04:57:43,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 2.9464573860168457, cross_entropy: 2.9464573860168457 +[2025-04-28 04:57:44,858][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 2.828537940979004, cross_entropy: 2.828537940979004 +[2025-04-28 04:57:45,524][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 3.1251444816589355, cross_entropy: 3.1251444816589355 +[2025-04-28 04:57:47,161][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 2.925978183746338, cross_entropy: 2.925978183746338 +[2025-04-28 04:57:48,151][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 2.7254981994628906, cross_entropy: 2.7254981994628906 +[2025-04-28 04:57:49,366][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.278090476989746, cross_entropy: 2.278090476989746 +[2025-04-28 04:57:50,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 1.213910698890686, cross_entropy: 1.213910698890686 +[2025-04-28 04:57:52,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 2.007413148880005, cross_entropy: 2.007413148880005 +[2025-04-28 04:57:53,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 1.1578760147094727, cross_entropy: 1.1578760147094727 +[2025-04-28 04:57:55,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 1.3424285650253296, cross_entropy: 1.3424285650253296 +[2025-04-28 04:57:56,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.5378700494766235, cross_entropy: 1.5378700494766235 +[2025-04-28 04:57:58,085][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 3.103166341781616, cross_entropy: 3.103166341781616 +[2025-04-28 04:57:58,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 2.8151917457580566, cross_entropy: 2.8151917457580566 +[2025-04-28 04:58:00,375][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.9730324745178223, cross_entropy: 2.9730324745178223 +[2025-04-28 04:58:00,998][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.0550563335418701, cross_entropy: 1.0550563335418701 +[2025-04-28 04:58:03,809][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.5694518089294434, cross_entropy: 2.5694518089294434 +[2025-04-28 04:58:04,905][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.4273390769958496, cross_entropy: 2.4273390769958496 +[2025-04-28 04:58:06,309][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 3.128816604614258, cross_entropy: 3.128816604614258 +[2025-04-28 04:58:07,513][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.8395748138427734, cross_entropy: 2.8395748138427734 +[2025-04-28 04:58:08,419][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.6690871715545654, cross_entropy: 2.6690871715545654 +[2025-04-28 04:58:10,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 1.057237148284912, cross_entropy: 1.057237148284912 +[2025-04-28 04:58:10,723][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 1.3589611053466797, cross_entropy: 1.3589611053466797 +[2025-04-28 04:58:13,332][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.9432646036148071, cross_entropy: 1.9432646036148071 +[2025-04-28 04:58:13,611][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.3475403785705566, cross_entropy: 1.3475403785705566 +[2025-04-28 04:58:15,642][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.737513542175293, cross_entropy: 2.737513542175293 +[2025-04-28 04:58:16,013][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.398588180541992, cross_entropy: 2.398588180541992 +[2025-04-28 04:58:17,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.7710776329040527, cross_entropy: 2.7710776329040527 +[2025-04-28 04:58:18,405][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 1.0403327941894531, cross_entropy: 1.0403327941894531 +[2025-04-28 04:58:19,872][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 1.5107035636901855, cross_entropy: 1.5107035636901855 +[2025-04-28 04:58:21,252][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 1.4644923210144043, cross_entropy: 1.4644923210144043 +[2025-04-28 04:58:22,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 0.9424059391021729, cross_entropy: 0.9424059391021729 +[2025-04-28 04:58:23,901][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.2894949913024902, cross_entropy: 1.2894949913024902 +[2025-04-28 04:58:24,245][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.6581764221191406, cross_entropy: 2.6581764221191406 +[2025-04-28 04:58:26,688][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.5497205257415771, cross_entropy: 1.5497205257415771 +[2025-04-28 04:58:27,114][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.652466058731079, cross_entropy: 2.652466058731079 +[2025-04-28 04:58:29,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 1.1310433149337769, cross_entropy: 1.1310433149337769 +[2025-04-28 04:58:29,525][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 3.0529675483703613, cross_entropy: 3.0529675483703613 +[2025-04-28 04:58:30,936][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 3.1403260231018066, cross_entropy: 3.1403260231018066 +[2025-04-28 04:58:32,082][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.780311107635498, cross_entropy: 2.780311107635498 +[2025-04-28 04:58:33,837][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 1.2341047525405884, cross_entropy: 1.2341047525405884 +[2025-04-28 04:58:35,010][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.5541226863861084, cross_entropy: 2.5541226863861084 +[2025-04-28 04:58:36,245][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.9912867546081543, cross_entropy: 2.9912867546081543 +[2025-04-28 04:58:37,639][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 2.7648558616638184, cross_entropy: 2.7648558616638184 +[2025-04-28 04:58:38,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.4833948612213135, cross_entropy: 2.4833948612213135 +[2025-04-28 04:58:41,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 1.1922426223754883, cross_entropy: 1.1922426223754883 +[2025-04-28 04:58:41,627][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 2.8349690437316895, cross_entropy: 2.8349690437316895 +[2025-04-28 04:58:43,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 2.401097297668457, cross_entropy: 2.401097297668457 +[2025-04-28 04:58:43,941][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 1.8711369037628174, cross_entropy: 1.8711369037628174 +[2025-04-28 04:58:45,898][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 1.23135244846344, cross_entropy: 1.23135244846344 +[2025-04-28 04:58:46,293][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.3332749605178833, cross_entropy: 1.3332749605178833 +[2025-04-28 04:58:48,854][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.0946000814437866, cross_entropy: 1.0946000814437866 +[2025-04-28 04:58:49,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 3.008087635040283, cross_entropy: 3.008087635040283 +[2025-04-28 04:58:51,225][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 1.3456047773361206, cross_entropy: 1.3456047773361206 +[2025-04-28 04:58:51,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.2819626331329346, cross_entropy: 1.2819626331329346 +[2025-04-28 04:58:54,058][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 3.0038981437683105, cross_entropy: 3.0038981437683105 +[2025-04-28 04:58:54,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 1.5450005531311035, cross_entropy: 1.5450005531311035 +[2025-04-28 04:58:56,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 2.7980079650878906, cross_entropy: 2.7980079650878906 +[2025-04-28 04:58:56,981][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.3483412265777588, cross_entropy: 1.3483412265777588 +[2025-04-28 04:58:58,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 1.1632413864135742, cross_entropy: 1.1632413864135742 +[2025-04-28 04:58:59,472][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.145787239074707, cross_entropy: 1.145787239074707 +[2025-04-28 04:59:01,170][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.2128283977508545, cross_entropy: 1.2128283977508545 +[2025-04-28 04:59:02,151][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.3339760303497314, cross_entropy: 2.3339760303497314 +[2025-04-28 04:59:04,564][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 2.9558491706848145, cross_entropy: 2.9558491706848145 +[2025-04-28 04:59:04,929][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 3.148259162902832, cross_entropy: 3.148259162902832 +[2025-04-28 04:59:06,935][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 2.1737613677978516, cross_entropy: 2.1737613677978516 +[2025-04-28 04:59:07,251][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 3.0500357151031494, cross_entropy: 3.0500357151031494 +[2025-04-28 04:59:09,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 1.3203425407409668, cross_entropy: 1.3203425407409668 +[2025-04-28 04:59:10,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.1277759075164795, cross_entropy: 1.1277759075164795 +[2025-04-28 04:59:12,194][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.5240824222564697, cross_entropy: 2.5240824222564697 +[2025-04-28 04:59:12,471][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 1.2918745279312134, cross_entropy: 1.2918745279312134 +[2025-04-28 04:59:14,478][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 1.5688047409057617, cross_entropy: 1.5688047409057617 +[2025-04-28 04:59:15,100][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 1.4212040901184082, cross_entropy: 1.4212040901184082 +[2025-04-28 04:59:16,718][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.5723806619644165, cross_entropy: 1.5723806619644165 +[2025-04-28 04:59:17,702][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 1.4223159551620483, cross_entropy: 1.4223159551620483 +[2025-04-28 04:59:19,791][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.66231632232666, cross_entropy: 2.66231632232666 +[2025-04-28 04:59:20,321][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 1.8131380081176758, cross_entropy: 1.8131380081176758 +[2025-04-28 04:59:21,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.5919079780578613, cross_entropy: 2.5919079780578613 +[2025-04-28 04:59:22,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.5365002155303955, cross_entropy: 1.5365002155303955 +[2025-04-28 04:59:24,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 1.7268140316009521, cross_entropy: 1.7268140316009521 +[2025-04-28 04:59:24,745][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 1.253190279006958, cross_entropy: 1.253190279006958 +[2025-04-28 04:59:26,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 1.0178086757659912, cross_entropy: 1.0178086757659912 +[2025-04-28 04:59:27,341][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 2.9498233795166016, cross_entropy: 2.9498233795166016 +[2025-04-28 04:59:28,896][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 0.9523992538452148, cross_entropy: 0.9523992538452148 +[2025-04-28 04:59:29,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 1.459930419921875, cross_entropy: 1.459930419921875 +[2025-04-28 04:59:31,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 3.055208206176758, cross_entropy: 3.055208206176758 +[2025-04-28 04:59:32,160][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 2.394226551055908, cross_entropy: 2.394226551055908 +[2025-04-28 04:59:33,969][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.8802084922790527, cross_entropy: 2.8802084922790527 +[2025-04-28 04:59:34,460][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 3.085117816925049, cross_entropy: 3.085117816925049 +[2025-04-28 04:59:36,488][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.609367609024048, cross_entropy: 2.609367609024048 +[2025-04-28 04:59:36,771][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 1.3897075653076172, cross_entropy: 1.3897075653076172 +[2025-04-28 04:59:39,431][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 3.219747304916382, cross_entropy: 3.219747304916382 +[2025-04-28 04:59:39,759][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 1.3569608926773071, cross_entropy: 1.3569608926773071 +[2025-04-28 04:59:41,922][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 1.2560176849365234, cross_entropy: 1.2560176849365234 +[2025-04-28 04:59:42,204][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 1.3498191833496094, cross_entropy: 1.3498191833496094 +[2025-04-28 04:59:44,580][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.406489849090576, cross_entropy: 2.406489849090576 +[2025-04-28 04:59:44,862][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 3.0105667114257812, cross_entropy: 3.0105667114257812 +[2025-04-28 04:59:46,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 2.028965950012207, cross_entropy: 2.028965950012207 +[2025-04-28 04:59:47,088][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.5073777437210083, cross_entropy: 1.5073777437210083 +[2025-04-28 04:59:49,389][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.4891424179077148, cross_entropy: 1.4891424179077148 +[2025-04-28 04:59:49,781][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 3.1037521362304688, cross_entropy: 3.1037521362304688 +[2025-04-28 04:59:52,175][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.377309799194336, cross_entropy: 2.377309799194336 +[2025-04-28 04:59:52,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.2775537967681885, cross_entropy: 1.2775537967681885 +[2025-04-28 04:59:55,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 3.0622267723083496, cross_entropy: 3.0622267723083496 +[2025-04-28 04:59:55,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 3.3924241065979004, cross_entropy: 3.3924241065979004 +[2025-04-28 04:59:57,800][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.1067099571228027, cross_entropy: 1.1067099571228027 +[2025-04-28 04:59:58,080][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 3.124112367630005, cross_entropy: 3.124112367630005 +[2025-04-28 05:00:00,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 3.0588488578796387, cross_entropy: 3.0588488578796387 +[2025-04-28 05:00:00,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.6376471519470215, cross_entropy: 1.6376471519470215 +[2025-04-28 05:00:02,764][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 1.5469441413879395, cross_entropy: 1.5469441413879395 +[2025-04-28 05:00:03,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 1.492620587348938, cross_entropy: 1.492620587348938 +[2025-04-28 05:00:04,869][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 2.322045087814331, cross_entropy: 2.322045087814331 +[2025-04-28 05:00:05,553][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 3.0151333808898926, cross_entropy: 3.0151333808898926 +[2025-04-28 05:00:07,244][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.5540105104446411, cross_entropy: 1.5540105104446411 +[2025-04-28 05:00:07,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.421738862991333, cross_entropy: 1.421738862991333 +[2025-04-28 05:00:09,804][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.4674149751663208, cross_entropy: 1.4674149751663208 +[2025-04-28 05:00:10,085][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 1.9975647926330566, cross_entropy: 1.9975647926330566 +[2025-04-28 05:00:11,963][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.255265951156616, cross_entropy: 2.255265951156616 +[2025-04-28 05:00:13,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.6300151348114014, cross_entropy: 2.6300151348114014 +[2025-04-28 05:00:14,769][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 3.036017656326294, cross_entropy: 3.036017656326294 +[2025-04-28 05:00:15,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 1.4592458009719849, cross_entropy: 1.4592458009719849 +[2025-04-28 05:00:17,113][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 2.9412760734558105, cross_entropy: 2.9412760734558105 +[2025-04-28 05:00:18,679][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 2.581170082092285, cross_entropy: 2.581170082092285 +[2025-04-28 05:00:19,614][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.047821521759033, cross_entropy: 2.047821521759033 +[2025-04-28 05:00:21,238][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 1.9791396856307983, cross_entropy: 1.9791396856307983 +[2025-04-28 05:00:21,786][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 3.039755344390869, cross_entropy: 3.039755344390869 +[2025-04-28 05:00:23,761][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.4794124364852905, cross_entropy: 1.4794124364852905 +[2025-04-28 05:00:24,070][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 0.995393693447113, cross_entropy: 0.995393693447113 +[2025-04-28 05:00:26,091][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 2.7516629695892334, cross_entropy: 2.7516629695892334 +[2025-04-28 05:00:26,576][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 2.083610773086548, cross_entropy: 2.083610773086548 +[2025-04-28 05:00:28,979][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.293903112411499, cross_entropy: 1.293903112411499 +[2025-04-28 05:00:29,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 1.84879469871521, cross_entropy: 1.84879469871521 +[2025-04-28 05:00:31,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 3.1697757244110107, cross_entropy: 3.1697757244110107 +[2025-04-28 05:00:31,793][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 0.7128228545188904, cross_entropy: 0.7128228545188904 +[2025-04-28 05:00:34,736][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 2.599030017852783, cross_entropy: 2.599030017852783 +[2025-04-28 05:00:35,017][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 2.939591407775879, cross_entropy: 2.939591407775879 +[2025-04-28 05:00:37,511][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 3.1720170974731445, cross_entropy: 3.1720170974731445 +[2025-04-28 05:00:37,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 1.4969868659973145, cross_entropy: 1.4969868659973145 +[2025-04-28 05:00:39,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 1.764725685119629, cross_entropy: 1.764725685119629 +[2025-04-28 05:00:40,397][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.3094544410705566, cross_entropy: 2.3094544410705566 +[2025-04-28 05:00:42,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 1.5702383518218994, cross_entropy: 1.5702383518218994 +[2025-04-28 05:00:43,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 2.612914562225342, cross_entropy: 2.612914562225342 +[2025-04-28 05:00:45,022][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 2.7776060104370117, cross_entropy: 2.7776060104370117 +[2025-04-28 05:00:45,302][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.308759331703186, cross_entropy: 1.308759331703186 +[2025-04-28 05:00:47,315][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.257873058319092, cross_entropy: 2.257873058319092 +[2025-04-28 05:00:47,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 2.2533626556396484, cross_entropy: 2.2533626556396484 +[2025-04-28 05:00:49,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 1.4597609043121338, cross_entropy: 1.4597609043121338 +[2025-04-28 05:00:50,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 3.2129225730895996, cross_entropy: 3.2129225730895996 +[2025-04-28 05:00:52,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 1.0795397758483887, cross_entropy: 1.0795397758483887 +[2025-04-28 05:00:52,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 1.8561652898788452, cross_entropy: 1.8561652898788452 +[2025-04-28 05:00:54,918][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 3.2625293731689453, cross_entropy: 3.2625293731689453 +[2025-04-28 05:00:55,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.9582414627075195, cross_entropy: 2.9582414627075195 +[2025-04-28 05:00:57,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.3752336502075195, cross_entropy: 2.3752336502075195 +[2025-04-28 05:00:57,918][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 1.6717901229858398, cross_entropy: 1.6717901229858398 +[2025-04-28 05:01:00,222][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 3.2989914417266846, cross_entropy: 3.2989914417266846 +[2025-04-28 05:01:00,501][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 2.0210752487182617, cross_entropy: 2.0210752487182617 +[2025-04-28 05:01:02,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 1.3502047061920166, cross_entropy: 1.3502047061920166 +[2025-04-28 05:01:02,628][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 2.0253281593322754, cross_entropy: 2.0253281593322754 +[2025-04-28 05:01:04,990][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 1.3230153322219849, cross_entropy: 1.3230153322219849 +[2025-04-28 05:01:05,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 1.562265396118164, cross_entropy: 1.562265396118164 +[2025-04-28 05:01:07,386][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 1.9260783195495605, cross_entropy: 1.9260783195495605 +[2025-04-28 05:01:07,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 1.6616225242614746, cross_entropy: 1.6616225242614746 +[2025-04-28 05:01:10,405][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.821967840194702, cross_entropy: 2.821967840194702 +[2025-04-28 05:01:10,688][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 2.812732696533203, cross_entropy: 2.812732696533203 +[2025-04-28 05:01:12,831][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.6927709579467773, cross_entropy: 2.6927709579467773 +[2025-04-28 05:01:13,113][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 2.06394362449646, cross_entropy: 2.06394362449646 +[2025-04-28 05:01:15,819][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 1.350837230682373, cross_entropy: 1.350837230682373 +[2025-04-28 05:01:16,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 3.005093574523926, cross_entropy: 3.005093574523926 +[2025-04-28 05:01:18,285][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 1.3529167175292969, cross_entropy: 1.3529167175292969 +[2025-04-28 05:01:18,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 3.0788424015045166, cross_entropy: 3.0788424015045166 +[2025-04-28 05:01:20,762][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 3.2671024799346924, cross_entropy: 3.2671024799346924 +[2025-04-28 05:01:21,042][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 1.2728471755981445, cross_entropy: 1.2728471755981445 +[2025-04-28 05:01:23,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 1.2352707386016846, cross_entropy: 1.2352707386016846 +[2025-04-28 05:01:23,739][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 2.536102294921875, cross_entropy: 2.536102294921875 +[2025-04-28 05:01:25,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.192819356918335, cross_entropy: 1.192819356918335 +[2025-04-28 05:01:25,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 1.992746114730835, cross_entropy: 1.992746114730835 +[2025-04-28 05:01:27,426][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 2.418092966079712, cross_entropy: 2.418092966079712 +[2025-04-28 05:01:27,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.675048589706421, cross_entropy: 1.675048589706421 +[2025-04-28 05:01:29,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 3.064913272857666, cross_entropy: 3.064913272857666 +[2025-04-28 05:01:29,825][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 0.9180608987808228, cross_entropy: 0.9180608987808228 +[2025-04-28 05:01:32,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 1.5489990711212158, cross_entropy: 1.5489990711212158 +[2025-04-28 05:01:32,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 3.0445380210876465, cross_entropy: 3.0445380210876465 +[2025-04-28 05:01:34,946][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 1.1577030420303345, cross_entropy: 1.1577030420303345 +[2025-04-28 05:01:35,227][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 2.2661197185516357, cross_entropy: 2.2661197185516357 +[2025-04-28 05:01:37,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 1.6563640832901, cross_entropy: 1.6563640832901 +[2025-04-28 05:01:38,093][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.2342419624328613, cross_entropy: 2.2342419624328613 +[2025-04-28 05:01:40,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.220184564590454, cross_entropy: 1.220184564590454 +[2025-04-28 05:01:40,706][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 2.010075569152832, cross_entropy: 2.010075569152832 +[2025-04-28 05:01:42,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 3.160252571105957, cross_entropy: 3.160252571105957 +[2025-04-28 05:01:43,245][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.8953715562820435, cross_entropy: 1.8953715562820435 +[2025-04-28 05:01:45,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 3.0862364768981934, cross_entropy: 3.0862364768981934 +[2025-04-28 05:01:45,748][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.614539623260498, cross_entropy: 2.614539623260498 +[2025-04-28 05:01:48,208][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 1.5634396076202393, cross_entropy: 1.5634396076202393 +[2025-04-28 05:01:48,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 2.353532075881958, cross_entropy: 2.353532075881958 +[2025-04-28 05:01:50,229][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 2.5423974990844727, cross_entropy: 2.5423974990844727 +[2025-04-28 05:01:50,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 2.6317105293273926, cross_entropy: 2.6317105293273926 +[2025-04-28 05:01:52,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 3.001811981201172, cross_entropy: 3.001811981201172 +[2025-04-28 05:01:52,937][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.2266631126403809, cross_entropy: 1.2266631126403809 +[2025-04-28 05:01:55,240][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 1.3137211799621582, cross_entropy: 1.3137211799621582 +[2025-04-28 05:01:55,518][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 2.8459558486938477, cross_entropy: 2.8459558486938477 +[2025-04-28 05:01:57,969][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.5865285396575928, cross_entropy: 2.5865285396575928 +[2025-04-28 05:01:58,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 2.113166332244873, cross_entropy: 2.113166332244873 +[2025-04-28 05:02:00,412][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 1.0485938787460327, cross_entropy: 1.0485938787460327 +[2025-04-28 05:02:00,694][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 1.9953707456588745, cross_entropy: 1.9953707456588745 +[2025-04-28 05:02:02,549][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 0.9433363676071167, cross_entropy: 0.9433363676071167 +[2025-04-28 05:02:02,830][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 1.8522930145263672, cross_entropy: 1.8522930145263672 +[2025-04-28 05:02:04,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 1.7616596221923828, cross_entropy: 1.7616596221923828 +[2025-04-28 05:02:05,212][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 3.214634656906128, cross_entropy: 3.214634656906128 +[2025-04-28 05:02:07,021][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 2.599696397781372, cross_entropy: 2.599696397781372 +[2025-04-28 05:02:07,302][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.7717270851135254, cross_entropy: 1.7717270851135254 +[2025-04-28 05:02:09,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 3.088730812072754, cross_entropy: 3.088730812072754 +[2025-04-28 05:02:09,397][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 3.309873342514038, cross_entropy: 3.309873342514038 +[2025-04-28 05:02:11,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 2.5932655334472656, cross_entropy: 2.5932655334472656 +[2025-04-28 05:02:12,229][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.994978427886963, cross_entropy: 2.994978427886963 +[2025-04-28 05:02:14,676][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.3115487098693848, cross_entropy: 1.3115487098693848 +[2025-04-28 05:02:14,955][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.6135687828063965, cross_entropy: 1.6135687828063965 +[2025-04-28 05:02:17,194][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.832519054412842, cross_entropy: 2.832519054412842 +[2025-04-28 05:02:17,461][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 1.8266701698303223, cross_entropy: 1.8266701698303223 +[2025-04-28 05:02:20,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 2.803353786468506, cross_entropy: 2.803353786468506 +[2025-04-28 05:02:20,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 1.2889764308929443, cross_entropy: 1.2889764308929443 +[2025-04-28 05:02:22,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 2.9564456939697266, cross_entropy: 2.9564456939697266 +[2025-04-28 05:02:22,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 1.19722580909729, cross_entropy: 1.19722580909729 +[2025-04-28 05:02:25,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 2.9220852851867676, cross_entropy: 2.9220852851867676 +[2025-04-28 05:02:25,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 2.5335659980773926, cross_entropy: 2.5335659980773926 +[2025-04-28 05:02:27,245][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 1.5096099376678467, cross_entropy: 1.5096099376678467 +[2025-04-28 05:02:27,525][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 3.117115020751953, cross_entropy: 3.117115020751953 +[2025-04-28 05:02:29,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 2.982290744781494, cross_entropy: 2.982290744781494 +[2025-04-28 05:02:29,975][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 1.1386098861694336, cross_entropy: 1.1386098861694336 +[2025-04-28 05:02:32,475][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 1.480936050415039, cross_entropy: 1.480936050415039 +[2025-04-28 05:02:32,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.916669487953186, cross_entropy: 1.916669487953186 +[2025-04-28 05:02:34,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.3565833568572998, cross_entropy: 1.3565833568572998 +[2025-04-28 05:02:34,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.7991883754730225, cross_entropy: 1.7991883754730225 +[2025-04-28 05:04:31,580][BaseTrainer][INFO] - [Epoch 10/10] (train) 2.0633158683776855, cross_entropy: 2.0633158683776855 +[2025-04-28 05:04:31,580][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.5640225410461426, cross_entropy: 1.5640225410461426 +[2025-04-28 05:04:31,790][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/best_epoch.pth. +[2025-04-28 05:04:31,950][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/epoch10.pth. +[2025-04-28 05:04:32,161][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. +[2025-04-28 05:04:32,371][BaseTrainer][INFO] - Save model: ./exp/20250428-032422/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..3f61c1cd01ba7c1991e40e0740e6a051b9a87ab6 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a676b0a4caf0423c81870af00dfc88979e4f52eb499e25bc835d3dcb3ae709 +size 51764965 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..b97ef3283eceae56804c2b4bbde9ab4f8c5d4111 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250428-032422/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cf93364f17ff21617df6fee6c0ae03585377b160ee9e3b2e124ad19c20aef38 +size 51716323 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/README.md new file mode 100644 index 0000000000000000000000000000000000000000..96f2a43acab7f66dc82df51f462a3250f60dbe55 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/README.md @@ -0,0 +1,7 @@ +system=default_seed-1 +data=birdclef2025_reshape_15s +train=birdclef2025_reshape_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.515 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..07735c0da3186d87a73ae27314f3aac494a60ce5 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/config.yaml @@ -0,0 +1,221 @@ +system: + seed: 1 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-075315 + tensorboard_dir: ./tensorboard/20250429-075315 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c16a7e989c4c0782732092db780ac8674bad9f05 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250429-075315/log/20250429-075318 + sweep: + dir: multirun/${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/20250429-075315/log/20250429-075318 + - hydra.mode=RUN + task: + - system=cuda_seed-1 + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250429-075315 + - train.output.tensorboard_dir=./tensorboard/20250429-075315 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_15s,lr_scheduler=none,model=birdclef2025_efficientnet_b0,optimizer=adam,preprocess.dump_format=birdclef2025,preprocess=birdclef2025,system=cuda_seed-1,train.dataset.train.feature_dir=/kaggle/input/birdclef-2025,train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250429-075315,train.output.tensorboard_dir=./tensorboard/20250429-075315,train.resume.continue_from=,train=birdclef2025_reshape_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/20250429-075315/log/20250429-075318 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_15s + preprocess: birdclef2025 + system: cuda_seed-1 + 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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..9202cee1c7a9b69b051b78415bd5b28383dac4f7 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda_seed-1 +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250429-075315 +- train.output.tensorboard_dir=./tensorboard/20250429-075315 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4030023ff66cf93b2df981e206b056f1a5093140 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/.hydra/resolved_config.yaml @@ -0,0 +1,280 @@ +system: + seed: 1 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250429-075315 + tensorboard_dir: ./tensorboard/20250429-075315 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250429-075315/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250429-075315/model/epoch{epoch}.pth + last: + path: ./exp/20250429-075315/model/last.pth + best_epoch: + path: ./exp/20250429-075315/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/train.log new file mode 100644 index 0000000000000000000000000000000000000000..dfe03777f2535c7b191abb8c7e0c6e983d459b15 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/log/20250429-075318/train.log @@ -0,0 +1,4281 @@ +[2025-04-29 07:53:47,037][BaseTrainer][INFO] - system: + seed: 1 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-075315 + tensorboard_dir: ./tensorboard/20250429-075315 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-29 07:53:47,037][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) + ) +) +[2025-04-29 07:53:47,042][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-29 07:53:56,667][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.330094337463379, cross_entropy: 5.330094337463379 +[2025-04-29 07:53:57,017][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.285581588745117, cross_entropy: 5.285581588745117 +[2025-04-29 07:53:57,400][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.185159683227539, cross_entropy: 5.185159683227539 +[2025-04-29 07:53:57,759][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.144158363342285, cross_entropy: 5.144158363342285 +[2025-04-29 07:54:01,929][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.163501739501953, cross_entropy: 5.163501739501953 +[2025-04-29 07:54:02,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.1212873458862305, cross_entropy: 5.1212873458862305 +[2025-04-29 07:54:06,174][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.866813659667969, cross_entropy: 4.866813659667969 +[2025-04-29 07:54:06,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 4.835955619812012, cross_entropy: 4.835955619812012 +[2025-04-29 07:54:10,973][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 5.0944929122924805, cross_entropy: 5.0944929122924805 +[2025-04-29 07:54:11,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.019998550415039, cross_entropy: 5.019998550415039 +[2025-04-29 07:54:15,287][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.941298484802246, cross_entropy: 4.941298484802246 +[2025-04-29 07:54:15,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.982705116271973, cross_entropy: 4.982705116271973 +[2025-04-29 07:54:18,708][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.819875717163086, cross_entropy: 4.819875717163086 +[2025-04-29 07:54:19,059][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.768496513366699, cross_entropy: 4.768496513366699 +[2025-04-29 07:54:22,369][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.811131477355957, cross_entropy: 4.811131477355957 +[2025-04-29 07:54:22,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.863540172576904, cross_entropy: 4.863540172576904 +[2025-04-29 07:54:26,290][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 4.809969902038574, cross_entropy: 4.809969902038574 +[2025-04-29 07:54:26,632][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.111724376678467, cross_entropy: 5.111724376678467 +[2025-04-29 07:54:30,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.8528032302856445, cross_entropy: 4.8528032302856445 +[2025-04-29 07:54:30,569][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.974573135375977, cross_entropy: 4.974573135375977 +[2025-04-29 07:54:33,745][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.688470840454102, cross_entropy: 4.688470840454102 +[2025-04-29 07:54:34,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.8815412521362305, cross_entropy: 4.8815412521362305 +[2025-04-29 07:54:37,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 5.018551826477051, cross_entropy: 5.018551826477051 +[2025-04-29 07:54:38,279][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.759232521057129, cross_entropy: 4.759232521057129 +[2025-04-29 07:54:42,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.495109558105469, cross_entropy: 4.495109558105469 +[2025-04-29 07:54:42,346][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.603681564331055, cross_entropy: 4.603681564331055 +[2025-04-29 07:54:46,046][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.532332420349121, cross_entropy: 4.532332420349121 +[2025-04-29 07:54:46,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.804384231567383, cross_entropy: 4.804384231567383 +[2025-04-29 07:54:49,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.480029106140137, cross_entropy: 4.480029106140137 +[2025-04-29 07:54:50,124][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.42253303527832, cross_entropy: 4.42253303527832 +[2025-04-29 07:54:53,553][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.868350982666016, cross_entropy: 4.868350982666016 +[2025-04-29 07:54:53,910][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.483015060424805, cross_entropy: 4.483015060424805 +[2025-04-29 07:54:57,718][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.791351318359375, cross_entropy: 4.791351318359375 +[2025-04-29 07:54:58,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.549686431884766, cross_entropy: 4.549686431884766 +[2025-04-29 07:55:01,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.254718780517578, cross_entropy: 4.254718780517578 +[2025-04-29 07:55:01,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.4257354736328125, cross_entropy: 4.4257354736328125 +[2025-04-29 07:55:05,256][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.832902431488037, cross_entropy: 4.832902431488037 +[2025-04-29 07:55:05,590][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.578154563903809, cross_entropy: 4.578154563903809 +[2025-04-29 07:55:08,671][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.389163970947266, cross_entropy: 4.389163970947266 +[2025-04-29 07:55:09,010][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.738526344299316, cross_entropy: 4.738526344299316 +[2025-04-29 07:55:13,308][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.724361419677734, cross_entropy: 4.724361419677734 +[2025-04-29 07:55:13,623][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.436849594116211, cross_entropy: 4.436849594116211 +[2025-04-29 07:55:17,662][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.385505199432373, cross_entropy: 4.385505199432373 +[2025-04-29 07:55:18,005][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.3761491775512695, cross_entropy: 4.3761491775512695 +[2025-04-29 07:55:21,607][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.562992572784424, cross_entropy: 4.562992572784424 +[2025-04-29 07:55:21,952][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.118775367736816, cross_entropy: 4.118775367736816 +[2025-04-29 07:55:25,493][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.148153305053711, cross_entropy: 4.148153305053711 +[2025-04-29 07:55:25,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.17064905166626, cross_entropy: 4.17064905166626 +[2025-04-29 07:55:30,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.243927001953125, cross_entropy: 4.243927001953125 +[2025-04-29 07:55:30,478][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.144469261169434, cross_entropy: 4.144469261169434 +[2025-04-29 07:55:34,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.356932640075684, cross_entropy: 4.356932640075684 +[2025-04-29 07:55:34,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.3874359130859375, cross_entropy: 4.3874359130859375 +[2025-04-29 07:55:38,570][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 3.686227560043335, cross_entropy: 3.686227560043335 +[2025-04-29 07:55:38,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.441309452056885, cross_entropy: 4.441309452056885 +[2025-04-29 07:55:43,743][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 3.8147244453430176, cross_entropy: 3.8147244453430176 +[2025-04-29 07:55:44,079][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.41215181350708, cross_entropy: 4.41215181350708 +[2025-04-29 07:55:47,523][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.014870643615723, cross_entropy: 4.014870643615723 +[2025-04-29 07:55:47,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.365689277648926, cross_entropy: 4.365689277648926 +[2025-04-29 07:55:51,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.624693870544434, cross_entropy: 4.624693870544434 +[2025-04-29 07:55:51,918][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 3.6750121116638184, cross_entropy: 3.6750121116638184 +[2025-04-29 07:55:55,430][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.727922439575195, cross_entropy: 4.727922439575195 +[2025-04-29 07:55:55,771][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 3.7279794216156006, cross_entropy: 3.7279794216156006 +[2025-04-29 07:55:59,528][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.101342678070068, cross_entropy: 4.101342678070068 +[2025-04-29 07:55:59,844][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.219757080078125, cross_entropy: 4.219757080078125 +[2025-04-29 07:56:03,939][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 3.990398406982422, cross_entropy: 3.990398406982422 +[2025-04-29 07:56:04,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.214756011962891, cross_entropy: 4.214756011962891 +[2025-04-29 07:56:07,600][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 3.8974084854125977, cross_entropy: 3.8974084854125977 +[2025-04-29 07:56:07,948][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.2825727462768555, cross_entropy: 4.2825727462768555 +[2025-04-29 07:56:11,413][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.553106307983398, cross_entropy: 4.553106307983398 +[2025-04-29 07:56:11,739][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.211662292480469, cross_entropy: 4.211662292480469 +[2025-04-29 07:56:15,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.129402160644531, cross_entropy: 4.129402160644531 +[2025-04-29 07:56:15,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 3.8863353729248047, cross_entropy: 3.8863353729248047 +[2025-04-29 07:56:19,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.7993409633636475, cross_entropy: 3.7993409633636475 +[2025-04-29 07:56:19,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.195134162902832, cross_entropy: 4.195134162902832 +[2025-04-29 07:56:23,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 3.380359172821045, cross_entropy: 3.380359172821045 +[2025-04-29 07:56:24,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.175863265991211, cross_entropy: 4.175863265991211 +[2025-04-29 07:56:27,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 3.584179639816284, cross_entropy: 3.584179639816284 +[2025-04-29 07:56:27,912][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 3.6654014587402344, cross_entropy: 3.6654014587402344 +[2025-04-29 07:56:31,485][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.168704032897949, cross_entropy: 4.168704032897949 +[2025-04-29 07:56:31,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.041088104248047, cross_entropy: 4.041088104248047 +[2025-04-29 07:56:34,999][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 3.822309732437134, cross_entropy: 3.822309732437134 +[2025-04-29 07:56:35,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.354353904724121, cross_entropy: 4.354353904724121 +[2025-04-29 07:56:39,470][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.443896293640137, cross_entropy: 4.443896293640137 +[2025-04-29 07:56:39,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.117497444152832, cross_entropy: 4.117497444152832 +[2025-04-29 07:56:43,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 3.845088481903076, cross_entropy: 3.845088481903076 +[2025-04-29 07:56:43,474][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.583740711212158, cross_entropy: 3.583740711212158 +[2025-04-29 07:56:47,272][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.142887592315674, cross_entropy: 4.142887592315674 +[2025-04-29 07:56:47,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.5168328285217285, cross_entropy: 4.5168328285217285 +[2025-04-29 07:56:51,430][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 3.6281309127807617, cross_entropy: 3.6281309127807617 +[2025-04-29 07:56:51,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.10958194732666, cross_entropy: 4.10958194732666 +[2025-04-29 07:56:56,416][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 3.181684970855713, cross_entropy: 3.181684970855713 +[2025-04-29 07:56:56,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.6589603424072266, cross_entropy: 3.6589603424072266 +[2025-04-29 07:57:00,500][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 4.0493011474609375, cross_entropy: 4.0493011474609375 +[2025-04-29 07:57:00,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.428913116455078, cross_entropy: 4.428913116455078 +[2025-04-29 07:57:04,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 3.767712116241455, cross_entropy: 3.767712116241455 +[2025-04-29 07:57:04,834][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 4.1683478355407715, cross_entropy: 4.1683478355407715 +[2025-04-29 07:57:07,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 3.3828318119049072, cross_entropy: 3.3828318119049072 +[2025-04-29 07:57:08,189][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.549055337905884, cross_entropy: 3.549055337905884 +[2025-04-29 07:57:11,631][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.005125522613525, cross_entropy: 4.005125522613525 +[2025-04-29 07:57:11,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.4244613647460938, cross_entropy: 3.4244613647460938 +[2025-04-29 07:57:15,691][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 3.6323330402374268, cross_entropy: 3.6323330402374268 +[2025-04-29 07:57:16,033][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.9783878326416016, cross_entropy: 3.9783878326416016 +[2025-04-29 07:57:20,201][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.440139055252075, cross_entropy: 3.440139055252075 +[2025-04-29 07:57:20,546][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.480949640274048, cross_entropy: 3.480949640274048 +[2025-04-29 07:57:24,592][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 4.304314613342285, cross_entropy: 4.304314613342285 +[2025-04-29 07:57:24,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 3.7158210277557373, cross_entropy: 3.7158210277557373 +[2025-04-29 07:57:29,254][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.6107778549194336, cross_entropy: 3.6107778549194336 +[2025-04-29 07:57:29,579][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 3.7337632179260254, cross_entropy: 3.7337632179260254 +[2025-04-29 07:57:33,728][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.9990437030792236, cross_entropy: 3.9990437030792236 +[2025-04-29 07:57:34,069][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 3.544586181640625, cross_entropy: 3.544586181640625 +[2025-04-29 07:57:37,601][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.386059284210205, cross_entropy: 3.386059284210205 +[2025-04-29 07:57:37,954][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 4.54888916015625, cross_entropy: 4.54888916015625 +[2025-04-29 07:57:41,853][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 3.100916862487793, cross_entropy: 3.100916862487793 +[2025-04-29 07:57:42,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.297628402709961, cross_entropy: 4.297628402709961 +[2025-04-29 07:57:46,756][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 3.4034531116485596, cross_entropy: 3.4034531116485596 +[2025-04-29 07:57:47,095][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.8586580753326416, cross_entropy: 3.8586580753326416 +[2025-04-29 07:57:50,982][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.579759120941162, cross_entropy: 3.579759120941162 +[2025-04-29 07:57:51,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 2.9225943088531494, cross_entropy: 2.9225943088531494 +[2025-04-29 07:57:55,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 3.7054481506347656, cross_entropy: 3.7054481506347656 +[2025-04-29 07:57:55,797][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.451205253601074, cross_entropy: 4.451205253601074 +[2025-04-29 07:57:59,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.007140159606934, cross_entropy: 4.007140159606934 +[2025-04-29 07:58:00,506][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 4.667177677154541, cross_entropy: 4.667177677154541 +[2025-04-29 07:58:05,149][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.0722110271453857, cross_entropy: 3.0722110271453857 +[2025-04-29 07:58:05,476][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.062767505645752, cross_entropy: 3.062767505645752 +[2025-04-29 07:58:09,123][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 3.7341361045837402, cross_entropy: 3.7341361045837402 +[2025-04-29 07:58:09,589][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 3.3660597801208496, cross_entropy: 3.3660597801208496 +[2025-04-29 07:58:12,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.853304147720337, cross_entropy: 3.853304147720337 +[2025-04-29 07:58:14,031][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 2.688204765319824, cross_entropy: 2.688204765319824 +[2025-04-29 07:58:16,907][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 2.8801486492156982, cross_entropy: 2.8801486492156982 +[2025-04-29 07:58:18,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.3267879486083984, cross_entropy: 3.3267879486083984 +[2025-04-29 07:58:20,711][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 3.703737497329712, cross_entropy: 3.703737497329712 +[2025-04-29 07:58:22,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 3.040203809738159, cross_entropy: 3.040203809738159 +[2025-04-29 07:58:24,762][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 3.939051628112793, cross_entropy: 3.939051628112793 +[2025-04-29 07:58:27,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 3.410964012145996, cross_entropy: 3.410964012145996 +[2025-04-29 07:58:29,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 3.600128173828125, cross_entropy: 3.600128173828125 +[2025-04-29 07:58:31,293][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.396388053894043, cross_entropy: 3.396388053894043 +[2025-04-29 07:58:33,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.095083713531494, cross_entropy: 3.095083713531494 +[2025-04-29 07:58:35,004][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 3.624746322631836, cross_entropy: 3.624746322631836 +[2025-04-29 07:58:37,554][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 3.0923192501068115, cross_entropy: 3.0923192501068115 +[2025-04-29 07:58:39,581][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.0579891204833984, cross_entropy: 3.0579891204833984 +[2025-04-29 07:58:42,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.048975944519043, cross_entropy: 4.048975944519043 +[2025-04-29 07:58:43,643][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.7925078868865967, cross_entropy: 3.7925078868865967 +[2025-04-29 07:58:46,606][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.951892375946045, cross_entropy: 3.951892375946045 +[2025-04-29 07:58:47,980][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 3.301819086074829, cross_entropy: 3.301819086074829 +[2025-04-29 07:58:51,125][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 3.8554153442382812, cross_entropy: 3.8554153442382812 +[2025-04-29 07:58:52,205][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.6173739433288574, cross_entropy: 3.6173739433288574 +[2025-04-29 07:58:55,310][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 3.578479290008545, cross_entropy: 3.578479290008545 +[2025-04-29 07:58:57,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.035447597503662, cross_entropy: 3.035447597503662 +[2025-04-29 07:58:59,351][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.151384353637695, cross_entropy: 4.151384353637695 +[2025-04-29 07:59:01,295][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 3.2755532264709473, cross_entropy: 3.2755532264709473 +[2025-04-29 07:59:03,387][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.0365805625915527, cross_entropy: 3.0365805625915527 +[2025-04-29 07:59:05,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.3837575912475586, cross_entropy: 3.3837575912475586 +[2025-04-29 07:59:07,516][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.3118462562561035, cross_entropy: 4.3118462562561035 +[2025-04-29 07:59:09,729][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 4.048247814178467, cross_entropy: 4.048247814178467 +[2025-04-29 07:59:11,411][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.8516969680786133, cross_entropy: 3.8516969680786133 +[2025-04-29 07:59:14,222][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.320405960083008, cross_entropy: 3.320405960083008 +[2025-04-29 07:59:15,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 3.5349183082580566, cross_entropy: 3.5349183082580566 +[2025-04-29 07:59:18,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.8555243015289307, cross_entropy: 3.8555243015289307 +[2025-04-29 07:59:19,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 2.987494945526123, cross_entropy: 2.987494945526123 +[2025-04-29 07:59:22,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.9313836097717285, cross_entropy: 3.9313836097717285 +[2025-04-29 07:59:23,482][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.719858169555664, cross_entropy: 3.719858169555664 +[2025-04-29 07:59:26,935][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 2.893944263458252, cross_entropy: 2.893944263458252 +[2025-04-29 07:59:27,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 3.1142711639404297, cross_entropy: 3.1142711639404297 +[2025-04-29 07:59:31,178][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.6676130294799805, cross_entropy: 3.6676130294799805 +[2025-04-29 07:59:31,608][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.1938846111297607, cross_entropy: 3.1938846111297607 +[2025-04-29 07:59:34,894][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 3.061553955078125, cross_entropy: 3.061553955078125 +[2025-04-29 07:59:35,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 2.878070592880249, cross_entropy: 2.878070592880249 +[2025-04-29 07:59:38,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.1788761615753174, cross_entropy: 3.1788761615753174 +[2025-04-29 07:59:39,135][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 3.1884043216705322, cross_entropy: 3.1884043216705322 +[2025-04-29 07:59:42,671][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.455700635910034, cross_entropy: 3.455700635910034 +[2025-04-29 07:59:43,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.1651225090026855, cross_entropy: 3.1651225090026855 +[2025-04-29 07:59:47,154][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.157404661178589, cross_entropy: 3.157404661178589 +[2025-04-29 07:59:47,547][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.964313268661499, cross_entropy: 3.964313268661499 +[2025-04-29 07:59:50,824][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.005135536193848, cross_entropy: 4.005135536193848 +[2025-04-29 07:59:51,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.005532741546631, cross_entropy: 4.005532741546631 +[2025-04-29 07:59:54,647][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 4.003510475158691, cross_entropy: 4.003510475158691 +[2025-04-29 07:59:56,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 3.3399810791015625, cross_entropy: 3.3399810791015625 +[2025-04-29 07:59:58,627][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.044379234313965, cross_entropy: 3.044379234313965 +[2025-04-29 08:00:00,900][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 2.954563856124878, cross_entropy: 2.954563856124878 +[2025-04-29 08:00:02,967][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 2.456444501876831, cross_entropy: 2.456444501876831 +[2025-04-29 08:00:04,626][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 2.6607179641723633, cross_entropy: 2.6607179641723633 +[2025-04-29 08:00:06,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 2.9561030864715576, cross_entropy: 2.9561030864715576 +[2025-04-29 08:00:08,749][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 4.020451545715332, cross_entropy: 4.020451545715332 +[2025-04-29 08:00:10,180][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 3.946659564971924, cross_entropy: 3.946659564971924 +[2025-04-29 08:00:12,869][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.865469217300415, cross_entropy: 3.865469217300415 +[2025-04-29 08:00:14,335][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.4806604385375977, cross_entropy: 3.4806604385375977 +[2025-04-29 08:00:16,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.090313673019409, cross_entropy: 3.090313673019409 +[2025-04-29 08:00:18,231][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.8394131660461426, cross_entropy: 3.8394131660461426 +[2025-04-29 08:00:21,023][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 4.03635311126709, cross_entropy: 4.03635311126709 +[2025-04-29 08:00:21,903][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.253011703491211, cross_entropy: 3.253011703491211 +[2025-04-29 08:00:25,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 2.829773187637329, cross_entropy: 2.829773187637329 +[2025-04-29 08:00:25,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.065725803375244, cross_entropy: 3.065725803375244 +[2025-04-29 08:00:29,439][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 3.928835391998291, cross_entropy: 3.928835391998291 +[2025-04-29 08:00:29,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.2278549671173096, cross_entropy: 3.2278549671173096 +[2025-04-29 08:00:33,549][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 3.1941490173339844, cross_entropy: 3.1941490173339844 +[2025-04-29 08:00:33,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 2.8063502311706543, cross_entropy: 2.8063502311706543 +[2025-04-29 08:00:37,844][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.8044533729553223, cross_entropy: 3.8044533729553223 +[2025-04-29 08:00:38,221][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 2.795571804046631, cross_entropy: 2.795571804046631 +[2025-04-29 08:00:41,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 2.8891701698303223, cross_entropy: 2.8891701698303223 +[2025-04-29 08:00:42,988][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 2.734086513519287, cross_entropy: 2.734086513519287 +[2025-04-29 08:00:45,647][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 2.677206516265869, cross_entropy: 2.677206516265869 +[2025-04-29 08:00:47,693][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 3.096096992492676, cross_entropy: 3.096096992492676 +[2025-04-29 08:00:50,255][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 2.7404329776763916, cross_entropy: 2.7404329776763916 +[2025-04-29 08:00:51,425][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.648892402648926, cross_entropy: 3.648892402648926 +[2025-04-29 08:00:54,040][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 2.8039820194244385, cross_entropy: 2.8039820194244385 +[2025-04-29 08:00:55,675][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.1947689056396484, cross_entropy: 3.1947689056396484 +[2025-04-29 08:00:58,591][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 3.0362653732299805, cross_entropy: 3.0362653732299805 +[2025-04-29 08:00:59,728][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 4.370780944824219, cross_entropy: 4.370780944824219 +[2025-04-29 08:01:02,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 3.1913373470306396, cross_entropy: 3.1913373470306396 +[2025-04-29 08:01:05,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 2.6650257110595703, cross_entropy: 2.6650257110595703 +[2025-04-29 08:01:06,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.8157119750976562, cross_entropy: 3.8157119750976562 +[2025-04-29 08:01:09,034][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 4.615835189819336, cross_entropy: 4.615835189819336 +[2025-04-29 08:01:10,497][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 2.827098846435547, cross_entropy: 2.827098846435547 +[2025-04-29 08:01:13,369][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 3.204559087753296, cross_entropy: 3.204559087753296 +[2025-04-29 08:01:14,377][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.971625328063965, cross_entropy: 3.971625328063965 +[2025-04-29 08:01:17,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 2.420057773590088, cross_entropy: 2.420057773590088 +[2025-04-29 08:01:18,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.367262601852417, cross_entropy: 3.367262601852417 +[2025-04-29 08:01:22,070][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 2.7615084648132324, cross_entropy: 2.7615084648132324 +[2025-04-29 08:01:23,395][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 4.183294296264648, cross_entropy: 4.183294296264648 +[2025-04-29 08:01:26,769][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.2272496223449707, cross_entropy: 3.2272496223449707 +[2025-04-29 08:01:27,215][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.5203857421875, cross_entropy: 3.5203857421875 +[2025-04-29 08:01:30,472][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 2.368394374847412, cross_entropy: 2.368394374847412 +[2025-04-29 08:01:31,126][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 2.9049935340881348, cross_entropy: 2.9049935340881348 +[2025-04-29 08:01:35,660][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 2.9498157501220703, cross_entropy: 2.9498157501220703 +[2025-04-29 08:01:36,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 4.3817009925842285, cross_entropy: 4.3817009925842285 +[2025-04-29 08:01:40,176][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 2.4682092666625977, cross_entropy: 2.4682092666625977 +[2025-04-29 08:01:40,516][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.988189935684204, cross_entropy: 3.988189935684204 +[2025-04-29 08:01:44,775][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.7541520595550537, cross_entropy: 3.7541520595550537 +[2025-04-29 08:01:45,682][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 3.242915153503418, cross_entropy: 3.242915153503418 +[2025-04-29 08:01:48,897][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 2.747349262237549, cross_entropy: 2.747349262237549 +[2025-04-29 08:01:49,765][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 3.893000364303589, cross_entropy: 3.893000364303589 +[2025-04-29 08:01:53,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 3.079042434692383, cross_entropy: 3.079042434692383 +[2025-04-29 08:01:53,397][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 3.2066879272460938, cross_entropy: 3.2066879272460938 +[2025-04-29 08:01:57,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 2.8690595626831055, cross_entropy: 2.8690595626831055 +[2025-04-29 08:01:57,979][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 2.848207473754883, cross_entropy: 2.848207473754883 +[2025-04-29 08:02:01,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 2.5468740463256836, cross_entropy: 2.5468740463256836 +[2025-04-29 08:02:02,076][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 3.9597995281219482, cross_entropy: 3.9597995281219482 +[2025-04-29 08:02:05,536][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.0894713401794434, cross_entropy: 2.0894713401794434 +[2025-04-29 08:02:06,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.0494675636291504, cross_entropy: 3.0494675636291504 +[2025-04-29 08:02:09,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 2.6798462867736816, cross_entropy: 2.6798462867736816 +[2025-04-29 08:02:11,406][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 2.4070522785186768, cross_entropy: 2.4070522785186768 +[2025-04-29 08:02:13,610][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.9067134857177734, cross_entropy: 2.9067134857177734 +[2025-04-29 08:02:15,232][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 4.231439590454102, cross_entropy: 4.231439590454102 +[2025-04-29 08:02:17,811][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 2.8925986289978027, cross_entropy: 2.8925986289978027 +[2025-04-29 08:02:19,340][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 2.4752719402313232, cross_entropy: 2.4752719402313232 +[2025-04-29 08:02:22,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 2.7018847465515137, cross_entropy: 2.7018847465515137 +[2025-04-29 08:02:23,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.4601259231567383, cross_entropy: 3.4601259231567383 +[2025-04-29 08:02:25,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 3.3759279251098633, cross_entropy: 3.3759279251098633 +[2025-04-29 08:02:26,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 2.4517204761505127, cross_entropy: 2.4517204761505127 +[2025-04-29 08:02:29,778][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 2.8063125610351562, cross_entropy: 2.8063125610351562 +[2025-04-29 08:02:30,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.104093551635742, cross_entropy: 3.104093551635742 +[2025-04-29 08:02:34,691][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 3.4454479217529297, cross_entropy: 3.4454479217529297 +[2025-04-29 08:02:35,475][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.9418787956237793, cross_entropy: 3.9418787956237793 +[2025-04-29 08:02:38,355][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.715380907058716, cross_entropy: 2.715380907058716 +[2025-04-29 08:02:39,611][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 2.399451732635498, cross_entropy: 2.399451732635498 +[2025-04-29 08:02:42,699][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 2.501417636871338, cross_entropy: 2.501417636871338 +[2025-04-29 08:02:43,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 2.9853761196136475, cross_entropy: 2.9853761196136475 +[2025-04-29 08:02:46,576][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 4.041959762573242, cross_entropy: 4.041959762573242 +[2025-04-29 08:02:48,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 4.172041893005371, cross_entropy: 4.172041893005371 +[2025-04-29 08:02:50,595][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 2.6344125270843506, cross_entropy: 2.6344125270843506 +[2025-04-29 08:02:51,886][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.668457269668579, cross_entropy: 2.668457269668579 +[2025-04-29 08:02:54,592][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.561704397201538, cross_entropy: 2.561704397201538 +[2025-04-29 08:02:56,031][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 2.363050937652588, cross_entropy: 2.363050937652588 +[2025-04-29 08:02:58,574][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.1363565921783447, cross_entropy: 3.1363565921783447 +[2025-04-29 08:02:59,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 2.183556079864502, cross_entropy: 2.183556079864502 +[2025-04-29 08:03:03,325][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 2.760023593902588, cross_entropy: 2.760023593902588 +[2025-04-29 08:03:03,663][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 2.720154047012329, cross_entropy: 2.720154047012329 +[2025-04-29 08:03:06,733][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.4032297134399414, cross_entropy: 2.4032297134399414 +[2025-04-29 08:03:07,141][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 3.4473533630371094, cross_entropy: 3.4473533630371094 +[2025-04-29 08:03:10,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.235562801361084, cross_entropy: 3.235562801361084 +[2025-04-29 08:03:11,316][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 4.177700519561768, cross_entropy: 4.177700519561768 +[2025-04-29 08:03:14,686][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 3.156512975692749, cross_entropy: 3.156512975692749 +[2025-04-29 08:03:15,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 2.702692985534668, cross_entropy: 2.702692985534668 +[2025-04-29 08:03:18,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 2.2046141624450684, cross_entropy: 2.2046141624450684 +[2025-04-29 08:03:20,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 3.096829414367676, cross_entropy: 3.096829414367676 +[2025-04-29 08:03:22,510][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 2.4043283462524414, cross_entropy: 2.4043283462524414 +[2025-04-29 08:03:25,294][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.6935157775878906, cross_entropy: 3.6935157775878906 +[2025-04-29 08:03:26,670][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 2.6738638877868652, cross_entropy: 2.6738638877868652 +[2025-04-29 08:03:29,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.0387277603149414, cross_entropy: 2.0387277603149414 +[2025-04-29 08:03:31,329][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.5186820030212402, cross_entropy: 3.5186820030212402 +[2025-04-29 08:03:33,611][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 3.7778568267822266, cross_entropy: 3.7778568267822266 +[2025-04-29 08:03:35,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 2.494082450866699, cross_entropy: 2.494082450866699 +[2025-04-29 08:03:38,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.83225154876709, cross_entropy: 3.83225154876709 +[2025-04-29 08:03:40,070][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.594792366027832, cross_entropy: 2.594792366027832 +[2025-04-29 08:03:42,082][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.4120969772338867, cross_entropy: 2.4120969772338867 +[2025-04-29 08:03:44,195][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 2.512458324432373, cross_entropy: 2.512458324432373 +[2025-04-29 08:03:47,222][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.1565213203430176, cross_entropy: 3.1565213203430176 +[2025-04-29 08:03:48,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 2.568340539932251, cross_entropy: 2.568340539932251 +[2025-04-29 08:03:51,011][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.9374735355377197, cross_entropy: 3.9374735355377197 +[2025-04-29 08:03:53,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 3.9323110580444336, cross_entropy: 3.9323110580444336 +[2025-04-29 08:03:55,387][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.778778553009033, cross_entropy: 3.778778553009033 +[2025-04-29 08:03:57,558][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 4.020354747772217, cross_entropy: 4.020354747772217 +[2025-04-29 08:03:59,841][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 2.5876190662384033, cross_entropy: 2.5876190662384033 +[2025-04-29 08:04:01,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 3.875908613204956, cross_entropy: 3.875908613204956 +[2025-04-29 08:04:04,069][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.5259532928466797, cross_entropy: 2.5259532928466797 +[2025-04-29 08:04:05,924][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.885551929473877, cross_entropy: 3.885551929473877 +[2025-04-29 08:04:08,153][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 2.450948715209961, cross_entropy: 2.450948715209961 +[2025-04-29 08:04:10,193][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.3773131370544434, cross_entropy: 3.3773131370544434 +[2025-04-29 08:04:12,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.3420908451080322, cross_entropy: 3.3420908451080322 +[2025-04-29 08:04:14,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 2.4304966926574707, cross_entropy: 2.4304966926574707 +[2025-04-29 08:04:17,257][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.504321336746216, cross_entropy: 2.504321336746216 +[2025-04-29 08:04:19,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.4771242141723633, cross_entropy: 3.4771242141723633 +[2025-04-29 08:04:21,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.445643186569214, cross_entropy: 2.445643186569214 +[2025-04-29 08:04:23,162][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 3.634207010269165, cross_entropy: 3.634207010269165 +[2025-04-29 08:04:26,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 2.4410793781280518, cross_entropy: 2.4410793781280518 +[2025-04-29 08:04:27,349][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.6760642528533936, cross_entropy: 2.6760642528533936 +[2025-04-29 08:04:30,407][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 2.5091800689697266, cross_entropy: 2.5091800689697266 +[2025-04-29 08:04:31,249][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 2.5194759368896484, cross_entropy: 2.5194759368896484 +[2025-04-29 08:04:34,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 2.933753490447998, cross_entropy: 2.933753490447998 +[2025-04-29 08:04:34,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 3.464949607849121, cross_entropy: 3.464949607849121 +[2025-04-29 08:04:39,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 1.896543264389038, cross_entropy: 1.896543264389038 +[2025-04-29 08:04:39,775][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 2.278900146484375, cross_entropy: 2.278900146484375 +[2025-04-29 08:04:43,185][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.100867748260498, cross_entropy: 3.100867748260498 +[2025-04-29 08:04:44,528][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.391599655151367, cross_entropy: 3.391599655151367 +[2025-04-29 08:04:48,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 3.399458885192871, cross_entropy: 3.399458885192871 +[2025-04-29 08:04:48,641][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.429504871368408, cross_entropy: 3.429504871368408 +[2025-04-29 08:04:52,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.7782540321350098, cross_entropy: 2.7782540321350098 +[2025-04-29 08:04:52,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.511251449584961, cross_entropy: 3.511251449584961 +[2025-04-29 08:04:55,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 2.312840461730957, cross_entropy: 2.312840461730957 +[2025-04-29 08:04:56,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.5881457328796387, cross_entropy: 2.5881457328796387 +[2025-04-29 08:04:59,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 3.179880142211914, cross_entropy: 3.179880142211914 +[2025-04-29 08:05:00,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 3.323068618774414, cross_entropy: 3.323068618774414 +[2025-04-29 08:05:03,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 2.207292318344116, cross_entropy: 2.207292318344116 +[2025-04-29 08:05:04,405][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 2.2255499362945557, cross_entropy: 2.2255499362945557 +[2025-04-29 08:05:08,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.028441905975342, cross_entropy: 3.028441905975342 +[2025-04-29 08:05:08,389][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.5229623317718506, cross_entropy: 3.5229623317718506 +[2025-04-29 08:05:12,073][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 3.721558094024658, cross_entropy: 3.721558094024658 +[2025-04-29 08:05:13,872][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 2.604055881500244, cross_entropy: 2.604055881500244 +[2025-04-29 08:05:16,108][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 2.411769390106201, cross_entropy: 2.411769390106201 +[2025-04-29 08:05:17,775][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 2.8662610054016113, cross_entropy: 2.8662610054016113 +[2025-04-29 08:05:20,728][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 2.6502537727355957, cross_entropy: 2.6502537727355957 +[2025-04-29 08:05:21,921][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 2.7463302612304688, cross_entropy: 2.7463302612304688 +[2025-04-29 08:05:24,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.4364964962005615, cross_entropy: 3.4364964962005615 +[2025-04-29 08:05:27,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.112138032913208, cross_entropy: 3.112138032913208 +[2025-04-29 08:05:28,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.5035176277160645, cross_entropy: 2.5035176277160645 +[2025-04-29 08:05:31,418][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.2012228965759277, cross_entropy: 2.2012228965759277 +[2025-04-29 08:05:32,624][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 3.1287338733673096, cross_entropy: 3.1287338733673096 +[2025-04-29 08:05:35,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 3.8547699451446533, cross_entropy: 3.8547699451446533 +[2025-04-29 08:05:36,596][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 3.616713047027588, cross_entropy: 3.616713047027588 +[2025-04-29 08:05:39,532][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.7106094360351562, cross_entropy: 3.7106094360351562 +[2025-04-29 08:05:40,403][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.3179168701171875, cross_entropy: 3.3179168701171875 +[2025-04-29 08:05:43,820][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 2.164456844329834, cross_entropy: 2.164456844329834 +[2025-04-29 08:05:44,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 2.4616470336914062, cross_entropy: 2.4616470336914062 +[2025-04-29 08:05:47,603][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.3233871459960938, cross_entropy: 2.3233871459960938 +[2025-04-29 08:05:48,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.485416889190674, cross_entropy: 3.485416889190674 +[2025-04-29 08:05:52,252][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.230703353881836, cross_entropy: 3.230703353881836 +[2025-04-29 08:05:52,713][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.783057689666748, cross_entropy: 2.783057689666748 +[2025-04-29 08:05:56,453][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.1553783416748047, cross_entropy: 2.1553783416748047 +[2025-04-29 08:05:56,777][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 2.9987220764160156, cross_entropy: 2.9987220764160156 +[2025-04-29 08:06:00,545][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 1.9979041814804077, cross_entropy: 1.9979041814804077 +[2025-04-29 08:06:00,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 3.2670955657958984, cross_entropy: 3.2670955657958984 +[2025-04-29 08:06:04,591][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.7529025077819824, cross_entropy: 2.7529025077819824 +[2025-04-29 08:06:04,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.2786755561828613, cross_entropy: 2.2786755561828613 +[2025-04-29 08:06:08,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 2.733835458755493, cross_entropy: 2.733835458755493 +[2025-04-29 08:06:08,666][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.427661895751953, cross_entropy: 3.427661895751953 +[2025-04-29 08:06:13,693][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.831686496734619, cross_entropy: 3.831686496734619 +[2025-04-29 08:09:28,168][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.5367276668548584, cross_entropy: 3.5367276668548584 +[2025-04-29 08:09:28,168][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.204224109649658, cross_entropy: 2.204224109649658 +[2025-04-29 08:09:28,339][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 08:09:28,505][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch1.pth. +[2025-04-29 08:09:28,690][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 08:09:33,106][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 2.3136181831359863, cross_entropy: 2.3136181831359863 +[2025-04-29 08:09:33,517][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 3.007185459136963, cross_entropy: 3.007185459136963 +[2025-04-29 08:09:36,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.5288426876068115, cross_entropy: 3.5288426876068115 +[2025-04-29 08:09:37,309][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 3.699709415435791, cross_entropy: 3.699709415435791 +[2025-04-29 08:09:41,018][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.0331954956054688, cross_entropy: 2.0331954956054688 +[2025-04-29 08:09:41,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 1.7688883543014526, cross_entropy: 1.7688883543014526 +[2025-04-29 08:09:44,569][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 3.6439270973205566, cross_entropy: 3.6439270973205566 +[2025-04-29 08:09:45,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 3.307462215423584, cross_entropy: 3.307462215423584 +[2025-04-29 08:09:48,136][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.282769203186035, cross_entropy: 2.282769203186035 +[2025-04-29 08:09:48,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.5776844024658203, cross_entropy: 2.5776844024658203 +[2025-04-29 08:09:52,413][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 3.777247905731201, cross_entropy: 3.777247905731201 +[2025-04-29 08:09:52,755][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.850003957748413, cross_entropy: 3.850003957748413 +[2025-04-29 08:09:56,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.439155340194702, cross_entropy: 3.439155340194702 +[2025-04-29 08:09:57,056][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.9642465114593506, cross_entropy: 2.9642465114593506 +[2025-04-29 08:10:00,170][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.6136434078216553, cross_entropy: 3.6136434078216553 +[2025-04-29 08:10:00,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 2.7666802406311035, cross_entropy: 2.7666802406311035 +[2025-04-29 08:10:03,588][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 3.482156753540039, cross_entropy: 3.482156753540039 +[2025-04-29 08:10:03,912][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.045588493347168, cross_entropy: 2.045588493347168 +[2025-04-29 08:10:07,041][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.7564399242401123, cross_entropy: 3.7564399242401123 +[2025-04-29 08:10:07,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 3.462573766708374, cross_entropy: 3.462573766708374 +[2025-04-29 08:10:10,635][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 2.3932061195373535, cross_entropy: 2.3932061195373535 +[2025-04-29 08:10:10,981][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 2.312608480453491, cross_entropy: 2.312608480453491 +[2025-04-29 08:10:13,890][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 2.443470001220703, cross_entropy: 2.443470001220703 +[2025-04-29 08:10:14,231][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.0334606170654297, cross_entropy: 3.0334606170654297 +[2025-04-29 08:10:18,204][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 2.972813129425049, cross_entropy: 2.972813129425049 +[2025-04-29 08:10:18,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.0071897506713867, cross_entropy: 2.0071897506713867 +[2025-04-29 08:10:21,481][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.779268503189087, cross_entropy: 3.779268503189087 +[2025-04-29 08:10:21,797][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 3.7275702953338623, cross_entropy: 3.7275702953338623 +[2025-04-29 08:10:25,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 1.8948783874511719, cross_entropy: 1.8948783874511719 +[2025-04-29 08:10:25,892][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 3.576788902282715, cross_entropy: 3.576788902282715 +[2025-04-29 08:10:28,839][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 3.085005283355713, cross_entropy: 3.085005283355713 +[2025-04-29 08:10:29,183][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.3873071670532227, cross_entropy: 2.3873071670532227 +[2025-04-29 08:10:32,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.8938469886779785, cross_entropy: 2.8938469886779785 +[2025-04-29 08:10:32,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 2.199052333831787, cross_entropy: 2.199052333831787 +[2025-04-29 08:10:35,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.6912729740142822, cross_entropy: 2.6912729740142822 +[2025-04-29 08:10:35,975][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 2.3152976036071777, cross_entropy: 2.3152976036071777 +[2025-04-29 08:10:39,427][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 2.366159200668335, cross_entropy: 2.366159200668335 +[2025-04-29 08:10:39,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 1.9462885856628418, cross_entropy: 1.9462885856628418 +[2025-04-29 08:10:44,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 1.6611944437026978, cross_entropy: 1.6611944437026978 +[2025-04-29 08:10:44,648][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.071302890777588, cross_entropy: 2.071302890777588 +[2025-04-29 08:10:48,445][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 2.733811855316162, cross_entropy: 2.733811855316162 +[2025-04-29 08:10:48,790][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.733879327774048, cross_entropy: 2.733879327774048 +[2025-04-29 08:10:51,832][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.4163076877593994, cross_entropy: 3.4163076877593994 +[2025-04-29 08:10:52,176][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.252518653869629, cross_entropy: 2.252518653869629 +[2025-04-29 08:10:55,107][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 1.9816303253173828, cross_entropy: 1.9816303253173828 +[2025-04-29 08:10:55,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.617915153503418, cross_entropy: 3.617915153503418 +[2025-04-29 08:10:59,076][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 2.1695470809936523, cross_entropy: 2.1695470809936523 +[2025-04-29 08:10:59,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 2.0011730194091797, cross_entropy: 2.0011730194091797 +[2025-04-29 08:11:02,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 2.7078890800476074, cross_entropy: 2.7078890800476074 +[2025-04-29 08:11:03,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 2.0223913192749023, cross_entropy: 2.0223913192749023 +[2025-04-29 08:11:06,570][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 2.5415360927581787, cross_entropy: 2.5415360927581787 +[2025-04-29 08:11:06,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 3.7775228023529053, cross_entropy: 3.7775228023529053 +[2025-04-29 08:11:10,341][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.324993133544922, cross_entropy: 3.324993133544922 +[2025-04-29 08:11:10,684][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 2.3063952922821045, cross_entropy: 2.3063952922821045 +[2025-04-29 08:11:14,557][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 2.3228273391723633, cross_entropy: 2.3228273391723633 +[2025-04-29 08:11:14,899][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.1339364051818848, cross_entropy: 2.1339364051818848 +[2025-04-29 08:11:18,257][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.572216033935547, cross_entropy: 2.572216033935547 +[2025-04-29 08:11:18,611][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 1.8180955648422241, cross_entropy: 1.8180955648422241 +[2025-04-29 08:11:22,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 2.5688791275024414, cross_entropy: 2.5688791275024414 +[2025-04-29 08:11:22,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.1161983013153076, cross_entropy: 3.1161983013153076 +[2025-04-29 08:11:25,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 2.826251983642578, cross_entropy: 2.826251983642578 +[2025-04-29 08:11:25,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.02850079536438, cross_entropy: 3.02850079536438 +[2025-04-29 08:11:30,406][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 3.4512486457824707, cross_entropy: 3.4512486457824707 +[2025-04-29 08:11:30,744][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 2.1177985668182373, cross_entropy: 2.1177985668182373 +[2025-04-29 08:11:33,926][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 3.235016345977783, cross_entropy: 3.235016345977783 +[2025-04-29 08:11:34,240][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 2.4793477058410645, cross_entropy: 2.4793477058410645 +[2025-04-29 08:11:37,580][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.0553157329559326, cross_entropy: 2.0553157329559326 +[2025-04-29 08:11:37,929][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 1.8613579273223877, cross_entropy: 1.8613579273223877 +[2025-04-29 08:11:40,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 3.5707969665527344, cross_entropy: 3.5707969665527344 +[2025-04-29 08:11:40,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 2.8768434524536133, cross_entropy: 2.8768434524536133 +[2025-04-29 08:11:43,925][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 1.8100279569625854, cross_entropy: 1.8100279569625854 +[2025-04-29 08:11:44,265][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 1.9804489612579346, cross_entropy: 1.9804489612579346 +[2025-04-29 08:11:47,977][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.02702260017395, cross_entropy: 3.02702260017395 +[2025-04-29 08:11:48,320][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 2.631995677947998, cross_entropy: 2.631995677947998 +[2025-04-29 08:11:51,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.140010356903076, cross_entropy: 2.140010356903076 +[2025-04-29 08:11:51,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 2.220984935760498, cross_entropy: 2.220984935760498 +[2025-04-29 08:11:54,368][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 3.6853880882263184, cross_entropy: 3.6853880882263184 +[2025-04-29 08:11:54,832][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 1.9254337549209595, cross_entropy: 1.9254337549209595 +[2025-04-29 08:11:57,851][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 2.1184566020965576, cross_entropy: 2.1184566020965576 +[2025-04-29 08:11:58,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.4238474369049072, cross_entropy: 3.4238474369049072 +[2025-04-29 08:12:01,079][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.379916191101074, cross_entropy: 2.379916191101074 +[2025-04-29 08:12:02,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.4449477195739746, cross_entropy: 3.4449477195739746 +[2025-04-29 08:12:04,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.4837629795074463, cross_entropy: 2.4837629795074463 +[2025-04-29 08:12:05,522][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 2.8071181774139404, cross_entropy: 2.8071181774139404 +[2025-04-29 08:12:08,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 2.311514377593994, cross_entropy: 2.311514377593994 +[2025-04-29 08:12:09,231][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 3.7936813831329346, cross_entropy: 3.7936813831329346 +[2025-04-29 08:12:12,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 1.85356605052948, cross_entropy: 1.85356605052948 +[2025-04-29 08:12:12,775][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 2.0705294609069824, cross_entropy: 2.0705294609069824 +[2025-04-29 08:12:15,748][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.0382168292999268, cross_entropy: 3.0382168292999268 +[2025-04-29 08:12:16,269][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.7840142250061035, cross_entropy: 2.7840142250061035 +[2025-04-29 08:12:20,316][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 2.241994619369507, cross_entropy: 2.241994619369507 +[2025-04-29 08:12:20,658][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 2.1224870681762695, cross_entropy: 2.1224870681762695 +[2025-04-29 08:12:23,778][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 2.525967597961426, cross_entropy: 2.525967597961426 +[2025-04-29 08:12:24,093][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 2.5423836708068848, cross_entropy: 2.5423836708068848 +[2025-04-29 08:12:27,453][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.783396005630493, cross_entropy: 2.783396005630493 +[2025-04-29 08:12:27,795][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.2244620323181152, cross_entropy: 2.2244620323181152 +[2025-04-29 08:12:30,442][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 2.5056869983673096, cross_entropy: 2.5056869983673096 +[2025-04-29 08:12:30,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 3.2689831256866455, cross_entropy: 3.2689831256866455 +[2025-04-29 08:12:34,381][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 2.09883189201355, cross_entropy: 2.09883189201355 +[2025-04-29 08:12:34,723][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.8786773681640625, cross_entropy: 3.8786773681640625 +[2025-04-29 08:12:37,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.726071834564209, cross_entropy: 3.726071834564209 +[2025-04-29 08:12:38,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 2.232027769088745, cross_entropy: 2.232027769088745 +[2025-04-29 08:12:41,081][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.5448172092437744, cross_entropy: 2.5448172092437744 +[2025-04-29 08:12:42,070][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.2869646549224854, cross_entropy: 2.2869646549224854 +[2025-04-29 08:12:44,249][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.194254159927368, cross_entropy: 3.194254159927368 +[2025-04-29 08:12:45,497][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 2.8050012588500977, cross_entropy: 2.8050012588500977 +[2025-04-29 08:12:47,471][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.117851495742798, cross_entropy: 2.117851495742798 +[2025-04-29 08:12:48,621][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 2.1498682498931885, cross_entropy: 2.1498682498931885 +[2025-04-29 08:12:50,785][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.544316291809082, cross_entropy: 3.544316291809082 +[2025-04-29 08:12:52,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 2.1901164054870605, cross_entropy: 2.1901164054870605 +[2025-04-29 08:12:54,358][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 3.628146171569824, cross_entropy: 3.628146171569824 +[2025-04-29 08:12:56,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 2.317681312561035, cross_entropy: 2.317681312561035 +[2025-04-29 08:12:57,720][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 1.8184540271759033, cross_entropy: 1.8184540271759033 +[2025-04-29 08:13:00,539][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 2.6435837745666504, cross_entropy: 2.6435837745666504 +[2025-04-29 08:13:01,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.61295223236084, cross_entropy: 3.61295223236084 +[2025-04-29 08:13:04,628][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 2.3608572483062744, cross_entropy: 2.3608572483062744 +[2025-04-29 08:13:04,972][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 3.481396198272705, cross_entropy: 3.481396198272705 +[2025-04-29 08:13:07,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 2.004051685333252, cross_entropy: 2.004051685333252 +[2025-04-29 08:13:08,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 1.9231247901916504, cross_entropy: 1.9231247901916504 +[2025-04-29 08:13:10,983][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 3.4734838008880615, cross_entropy: 3.4734838008880615 +[2025-04-29 08:13:12,002][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 1.9026076793670654, cross_entropy: 1.9026076793670654 +[2025-04-29 08:13:14,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.389918327331543, cross_entropy: 2.389918327331543 +[2025-04-29 08:13:15,388][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 2.3808822631835938, cross_entropy: 2.3808822631835938 +[2025-04-29 08:13:18,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 2.028364419937134, cross_entropy: 2.028364419937134 +[2025-04-29 08:13:20,254][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 3.1904854774475098, cross_entropy: 3.1904854774475098 +[2025-04-29 08:13:22,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 1.7481226921081543, cross_entropy: 1.7481226921081543 +[2025-04-29 08:13:23,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.1578166484832764, cross_entropy: 3.1578166484832764 +[2025-04-29 08:13:26,009][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 2.8929500579833984, cross_entropy: 2.8929500579833984 +[2025-04-29 08:13:26,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 3.490903615951538, cross_entropy: 3.490903615951538 +[2025-04-29 08:13:29,475][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 1.8110456466674805, cross_entropy: 1.8110456466674805 +[2025-04-29 08:13:30,149][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.910332679748535, cross_entropy: 2.910332679748535 +[2025-04-29 08:13:32,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 3.551825523376465, cross_entropy: 3.551825523376465 +[2025-04-29 08:13:33,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 3.3792243003845215, cross_entropy: 3.3792243003845215 +[2025-04-29 08:13:36,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 2.23569917678833, cross_entropy: 2.23569917678833 +[2025-04-29 08:13:37,972][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 2.790851354598999, cross_entropy: 2.790851354598999 +[2025-04-29 08:13:40,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.4296162128448486, cross_entropy: 3.4296162128448486 +[2025-04-29 08:13:41,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.3103301525115967, cross_entropy: 2.3103301525115967 +[2025-04-29 08:13:42,978][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 3.563478946685791, cross_entropy: 3.563478946685791 +[2025-04-29 08:13:45,049][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 2.0143842697143555, cross_entropy: 2.0143842697143555 +[2025-04-29 08:13:46,601][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 2.2991528511047363, cross_entropy: 2.2991528511047363 +[2025-04-29 08:13:48,253][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.407559871673584, cross_entropy: 3.407559871673584 +[2025-04-29 08:13:50,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.748652935028076, cross_entropy: 2.748652935028076 +[2025-04-29 08:13:51,856][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 2.1858298778533936, cross_entropy: 2.1858298778533936 +[2025-04-29 08:13:53,394][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 1.9034348726272583, cross_entropy: 1.9034348726272583 +[2025-04-29 08:13:55,233][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 3.451972484588623, cross_entropy: 3.451972484588623 +[2025-04-29 08:13:56,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 3.386486053466797, cross_entropy: 3.386486053466797 +[2025-04-29 08:13:58,336][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 3.1320254802703857, cross_entropy: 3.1320254802703857 +[2025-04-29 08:13:59,991][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.5234670639038086, cross_entropy: 2.5234670639038086 +[2025-04-29 08:14:01,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.921060085296631, cross_entropy: 2.921060085296631 +[2025-04-29 08:14:03,530][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.465745449066162, cross_entropy: 3.465745449066162 +[2025-04-29 08:14:05,587][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.970996379852295, cross_entropy: 2.970996379852295 +[2025-04-29 08:14:07,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.7635626792907715, cross_entropy: 3.7635626792907715 +[2025-04-29 08:14:09,328][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.167358160018921, cross_entropy: 3.167358160018921 +[2025-04-29 08:14:11,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 1.9934463500976562, cross_entropy: 1.9934463500976562 +[2025-04-29 08:14:13,678][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 2.0827929973602295, cross_entropy: 2.0827929973602295 +[2025-04-29 08:14:14,435][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.171067953109741, cross_entropy: 2.171067953109741 +[2025-04-29 08:14:17,042][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 1.874514102935791, cross_entropy: 1.874514102935791 +[2025-04-29 08:14:18,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.003861427307129, cross_entropy: 3.003861427307129 +[2025-04-29 08:14:20,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.213775634765625, cross_entropy: 3.213775634765625 +[2025-04-29 08:14:21,077][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.9224061965942383, cross_entropy: 2.9224061965942383 +[2025-04-29 08:14:23,133][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 3.347980499267578, cross_entropy: 3.347980499267578 +[2025-04-29 08:14:24,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.44760799407959, cross_entropy: 3.44760799407959 +[2025-04-29 08:14:26,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 1.4380052089691162, cross_entropy: 1.4380052089691162 +[2025-04-29 08:14:27,843][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 1.8450913429260254, cross_entropy: 1.8450913429260254 +[2025-04-29 08:14:29,375][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 1.433645486831665, cross_entropy: 1.433645486831665 +[2025-04-29 08:14:32,082][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 3.0690371990203857, cross_entropy: 3.0690371990203857 +[2025-04-29 08:14:33,325][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 2.1892783641815186, cross_entropy: 2.1892783641815186 +[2025-04-29 08:14:34,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 3.542172908782959, cross_entropy: 3.542172908782959 +[2025-04-29 08:14:37,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 3.5191359519958496, cross_entropy: 3.5191359519958496 +[2025-04-29 08:14:38,493][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 3.0711276531219482, cross_entropy: 3.0711276531219482 +[2025-04-29 08:14:40,491][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.289736270904541, cross_entropy: 3.289736270904541 +[2025-04-29 08:14:42,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 3.4330015182495117, cross_entropy: 3.4330015182495117 +[2025-04-29 08:14:43,851][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.926522731781006, cross_entropy: 2.926522731781006 +[2025-04-29 08:14:46,775][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 1.8047382831573486, cross_entropy: 1.8047382831573486 +[2025-04-29 08:14:47,147][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 1.963519811630249, cross_entropy: 1.963519811630249 +[2025-04-29 08:14:50,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 2.8591134548187256, cross_entropy: 2.8591134548187256 +[2025-04-29 08:14:51,031][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 3.791752576828003, cross_entropy: 3.791752576828003 +[2025-04-29 08:14:54,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.82735013961792, cross_entropy: 2.82735013961792 +[2025-04-29 08:14:54,643][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 2.6293535232543945, cross_entropy: 2.6293535232543945 +[2025-04-29 08:14:57,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.425861358642578, cross_entropy: 3.425861358642578 +[2025-04-29 08:14:57,893][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 3.15040922164917, cross_entropy: 3.15040922164917 +[2025-04-29 08:15:00,521][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 2.5405731201171875, cross_entropy: 2.5405731201171875 +[2025-04-29 08:15:00,860][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 3.499478816986084, cross_entropy: 3.499478816986084 +[2025-04-29 08:15:03,809][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.2683725357055664, cross_entropy: 2.2683725357055664 +[2025-04-29 08:15:04,155][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 3.249203681945801, cross_entropy: 3.249203681945801 +[2025-04-29 08:15:06,699][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 2.1093943119049072, cross_entropy: 2.1093943119049072 +[2025-04-29 08:15:07,043][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.060011625289917, cross_entropy: 2.060011625289917 +[2025-04-29 08:15:10,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.1242141723632812, cross_entropy: 3.1242141723632812 +[2025-04-29 08:15:10,876][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 1.8708595037460327, cross_entropy: 1.8708595037460327 +[2025-04-29 08:15:13,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.139392137527466, cross_entropy: 2.139392137527466 +[2025-04-29 08:15:14,130][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 2.261345624923706, cross_entropy: 2.261345624923706 +[2025-04-29 08:15:17,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 1.9576561450958252, cross_entropy: 1.9576561450958252 +[2025-04-29 08:15:17,668][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.7246413230895996, cross_entropy: 2.7246413230895996 +[2025-04-29 08:15:21,104][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 3.273293972015381, cross_entropy: 3.273293972015381 +[2025-04-29 08:15:21,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.6981935501098633, cross_entropy: 2.6981935501098633 +[2025-04-29 08:15:24,382][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 3.1888461112976074, cross_entropy: 3.1888461112976074 +[2025-04-29 08:15:24,718][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 2.1034040451049805, cross_entropy: 2.1034040451049805 +[2025-04-29 08:15:28,070][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.556684970855713, cross_entropy: 3.556684970855713 +[2025-04-29 08:15:28,408][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 1.6228567361831665, cross_entropy: 1.6228567361831665 +[2025-04-29 08:15:31,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 2.3079452514648438, cross_entropy: 2.3079452514648438 +[2025-04-29 08:15:32,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 3.3264975547790527, cross_entropy: 3.3264975547790527 +[2025-04-29 08:15:34,926][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 1.720855474472046, cross_entropy: 1.720855474472046 +[2025-04-29 08:15:35,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 1.8653095960617065, cross_entropy: 1.8653095960617065 +[2025-04-29 08:15:38,214][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 3.7120919227600098, cross_entropy: 3.7120919227600098 +[2025-04-29 08:15:38,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.01069974899292, cross_entropy: 2.01069974899292 +[2025-04-29 08:15:41,170][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 2.5217597484588623, cross_entropy: 2.5217597484588623 +[2025-04-29 08:15:41,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 3.8509860038757324, cross_entropy: 3.8509860038757324 +[2025-04-29 08:15:45,144][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 3.0327959060668945, cross_entropy: 3.0327959060668945 +[2025-04-29 08:15:45,487][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.5744733810424805, cross_entropy: 3.5744733810424805 +[2025-04-29 08:15:48,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 1.856162428855896, cross_entropy: 1.856162428855896 +[2025-04-29 08:15:49,143][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 2.295804977416992, cross_entropy: 2.295804977416992 +[2025-04-29 08:15:52,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 3.237232208251953, cross_entropy: 3.237232208251953 +[2025-04-29 08:15:52,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.1856813430786133, cross_entropy: 2.1856813430786133 +[2025-04-29 08:15:55,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 3.155545473098755, cross_entropy: 3.155545473098755 +[2025-04-29 08:15:55,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.9543633460998535, cross_entropy: 2.9543633460998535 +[2025-04-29 08:15:58,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 3.7722666263580322, cross_entropy: 3.7722666263580322 +[2025-04-29 08:15:58,842][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 2.8751349449157715, cross_entropy: 2.8751349449157715 +[2025-04-29 08:16:02,563][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.047006130218506, cross_entropy: 2.047006130218506 +[2025-04-29 08:16:02,898][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 1.9515711069107056, cross_entropy: 1.9515711069107056 +[2025-04-29 08:16:06,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 3.476743221282959, cross_entropy: 3.476743221282959 +[2025-04-29 08:16:06,794][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.532628059387207, cross_entropy: 3.532628059387207 +[2025-04-29 08:16:10,021][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.5815796852111816, cross_entropy: 2.5815796852111816 +[2025-04-29 08:16:10,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 1.9171607494354248, cross_entropy: 1.9171607494354248 +[2025-04-29 08:16:13,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.0164847373962402, cross_entropy: 2.0164847373962402 +[2025-04-29 08:16:13,655][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.5607240200042725, cross_entropy: 2.5607240200042725 +[2025-04-29 08:16:16,998][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.6813926696777344, cross_entropy: 2.6813926696777344 +[2025-04-29 08:16:17,342][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 1.850306749343872, cross_entropy: 1.850306749343872 +[2025-04-29 08:16:20,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 2.9740872383117676, cross_entropy: 2.9740872383117676 +[2025-04-29 08:16:20,609][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.6669063568115234, cross_entropy: 3.6669063568115234 +[2025-04-29 08:16:23,409][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 3.312051296234131, cross_entropy: 3.312051296234131 +[2025-04-29 08:16:23,725][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 3.3731212615966797, cross_entropy: 3.3731212615966797 +[2025-04-29 08:16:26,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 3.453486919403076, cross_entropy: 3.453486919403076 +[2025-04-29 08:16:27,132][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 2.244774103164673, cross_entropy: 2.244774103164673 +[2025-04-29 08:16:30,250][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 2.2237393856048584, cross_entropy: 2.2237393856048584 +[2025-04-29 08:16:30,593][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.305131673812866, cross_entropy: 2.305131673812866 +[2025-04-29 08:16:34,441][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 3.365722179412842, cross_entropy: 3.365722179412842 +[2025-04-29 08:16:34,784][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 2.8472204208374023, cross_entropy: 2.8472204208374023 +[2025-04-29 08:16:38,129][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 3.6311848163604736, cross_entropy: 3.6311848163604736 +[2025-04-29 08:16:38,442][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 1.6672284603118896, cross_entropy: 1.6672284603118896 +[2025-04-29 08:16:41,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 3.1901965141296387, cross_entropy: 3.1901965141296387 +[2025-04-29 08:16:41,943][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 3.6004865169525146, cross_entropy: 3.6004865169525146 +[2025-04-29 08:16:45,738][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 3.402308464050293, cross_entropy: 3.402308464050293 +[2025-04-29 08:16:46,083][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.4287126064300537, cross_entropy: 3.4287126064300537 +[2025-04-29 08:16:49,573][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 3.6435413360595703, cross_entropy: 3.6435413360595703 +[2025-04-29 08:16:49,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 3.391775608062744, cross_entropy: 3.391775608062744 +[2025-04-29 08:16:53,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 2.1053271293640137, cross_entropy: 2.1053271293640137 +[2025-04-29 08:16:53,490][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.1141111850738525, cross_entropy: 2.1141111850738525 +[2025-04-29 08:16:56,737][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 3.1703238487243652, cross_entropy: 3.1703238487243652 +[2025-04-29 08:16:57,052][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.14689302444458, cross_entropy: 2.14689302444458 +[2025-04-29 08:17:00,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 1.9820342063903809, cross_entropy: 1.9820342063903809 +[2025-04-29 08:17:00,566][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.6532835960388184, cross_entropy: 3.6532835960388184 +[2025-04-29 08:17:04,453][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.6260018348693848, cross_entropy: 3.6260018348693848 +[2025-04-29 08:17:04,768][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 2.1958913803100586, cross_entropy: 2.1958913803100586 +[2025-04-29 08:17:07,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.121920108795166, cross_entropy: 3.121920108795166 +[2025-04-29 08:17:08,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 3.3403754234313965, cross_entropy: 3.3403754234313965 +[2025-04-29 08:17:10,934][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 1.7818539142608643, cross_entropy: 1.7818539142608643 +[2025-04-29 08:17:11,284][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 2.064305543899536, cross_entropy: 2.064305543899536 +[2025-04-29 08:17:14,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 1.9806462526321411, cross_entropy: 1.9806462526321411 +[2025-04-29 08:17:14,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.9320783615112305, cross_entropy: 2.9320783615112305 +[2025-04-29 08:17:18,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 1.8902859687805176, cross_entropy: 1.8902859687805176 +[2025-04-29 08:17:18,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 1.6563193798065186, cross_entropy: 1.6563193798065186 +[2025-04-29 08:17:21,706][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.7808659076690674, cross_entropy: 2.7808659076690674 +[2025-04-29 08:17:22,054][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.844864845275879, cross_entropy: 2.844864845275879 +[2025-04-29 08:17:25,226][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 1.284905195236206, cross_entropy: 1.284905195236206 +[2025-04-29 08:17:25,582][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 1.5766901969909668, cross_entropy: 1.5766901969909668 +[2025-04-29 08:17:29,001][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.4752297401428223, cross_entropy: 2.4752297401428223 +[2025-04-29 08:17:29,342][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 2.9525411128997803, cross_entropy: 2.9525411128997803 +[2025-04-29 08:17:32,188][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.6932246685028076, cross_entropy: 3.6932246685028076 +[2025-04-29 08:17:32,501][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 2.211414337158203, cross_entropy: 2.211414337158203 +[2025-04-29 08:17:36,401][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 2.066190719604492, cross_entropy: 2.066190719604492 +[2025-04-29 08:17:36,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 2.3878440856933594, cross_entropy: 2.3878440856933594 +[2025-04-29 08:17:39,642][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 2.0033254623413086, cross_entropy: 2.0033254623413086 +[2025-04-29 08:17:39,955][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.17730450630188, cross_entropy: 3.17730450630188 +[2025-04-29 08:17:44,028][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 2.0631775856018066, cross_entropy: 2.0631775856018066 +[2025-04-29 08:17:44,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 3.0205178260803223, cross_entropy: 3.0205178260803223 +[2025-04-29 08:17:47,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 1.418096899986267, cross_entropy: 1.418096899986267 +[2025-04-29 08:17:47,718][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 3.2877254486083984, cross_entropy: 3.2877254486083984 +[2025-04-29 08:17:51,649][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 1.7241151332855225, cross_entropy: 1.7241151332855225 +[2025-04-29 08:17:52,001][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.914813995361328, cross_entropy: 2.914813995361328 +[2025-04-29 08:17:54,730][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.302661895751953, cross_entropy: 2.302661895751953 +[2025-04-29 08:17:55,072][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.0830636024475098, cross_entropy: 3.0830636024475098 +[2025-04-29 08:17:57,697][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 3.0709002017974854, cross_entropy: 3.0709002017974854 +[2025-04-29 08:17:58,038][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 2.2675018310546875, cross_entropy: 2.2675018310546875 +[2025-04-29 08:18:01,088][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 2.9242069721221924, cross_entropy: 2.9242069721221924 +[2025-04-29 08:18:01,414][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 3.6979215145111084, cross_entropy: 3.6979215145111084 +[2025-04-29 08:18:04,847][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.348639488220215, cross_entropy: 2.348639488220215 +[2025-04-29 08:18:05,191][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 1.6919389963150024, cross_entropy: 1.6919389963150024 +[2025-04-29 08:18:08,722][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 2.6720499992370605, cross_entropy: 2.6720499992370605 +[2025-04-29 08:18:09,065][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 2.9369759559631348, cross_entropy: 2.9369759559631348 +[2025-04-29 08:18:12,882][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.2107038497924805, cross_entropy: 3.2107038497924805 +[2025-04-29 08:18:13,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 3.479879856109619, cross_entropy: 3.479879856109619 +[2025-04-29 08:18:17,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 3.4645755290985107, cross_entropy: 3.4645755290985107 +[2025-04-29 08:18:17,377][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 2.1904191970825195, cross_entropy: 2.1904191970825195 +[2025-04-29 08:18:20,425][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 1.6491594314575195, cross_entropy: 1.6491594314575195 +[2025-04-29 08:18:20,768][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.1299853324890137, cross_entropy: 2.1299853324890137 +[2025-04-29 08:18:23,660][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.7905492782592773, cross_entropy: 2.7905492782592773 +[2025-04-29 08:18:24,010][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 3.0579166412353516, cross_entropy: 3.0579166412353516 +[2025-04-29 08:18:26,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.6532952785491943, cross_entropy: 1.6532952785491943 +[2025-04-29 08:18:27,231][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 2.067436695098877, cross_entropy: 2.067436695098877 +[2025-04-29 08:18:30,401][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.283815383911133, cross_entropy: 3.283815383911133 +[2025-04-29 08:18:30,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 2.48213529586792, cross_entropy: 2.48213529586792 +[2025-04-29 08:18:34,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 2.8735156059265137, cross_entropy: 2.8735156059265137 +[2025-04-29 08:18:34,613][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 1.9034688472747803, cross_entropy: 1.9034688472747803 +[2025-04-29 08:18:37,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 2.338818311691284, cross_entropy: 2.338818311691284 +[2025-04-29 08:18:38,309][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 3.075178861618042, cross_entropy: 3.075178861618042 +[2025-04-29 08:18:41,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.15775990486145, cross_entropy: 3.15775990486145 +[2025-04-29 08:18:41,697][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.1969451904296875, cross_entropy: 3.1969451904296875 +[2025-04-29 08:18:44,426][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 3.1811914443969727, cross_entropy: 3.1811914443969727 +[2025-04-29 08:18:44,743][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 2.2919392585754395, cross_entropy: 2.2919392585754395 +[2025-04-29 08:18:47,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 3.439793586730957, cross_entropy: 3.439793586730957 +[2025-04-29 08:18:48,002][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 1.78743314743042, cross_entropy: 1.78743314743042 +[2025-04-29 08:18:51,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.481231212615967, cross_entropy: 2.481231212615967 +[2025-04-29 08:18:51,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 2.540184736251831, cross_entropy: 2.540184736251831 +[2025-04-29 08:18:54,903][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 3.3898777961730957, cross_entropy: 3.3898777961730957 +[2025-04-29 08:18:55,244][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 3.3989322185516357, cross_entropy: 3.3989322185516357 +[2025-04-29 08:18:58,091][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.0972189903259277, cross_entropy: 2.0972189903259277 +[2025-04-29 08:18:58,436][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 1.6063604354858398, cross_entropy: 1.6063604354858398 +[2025-04-29 08:19:01,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 3.318258285522461, cross_entropy: 3.318258285522461 +[2025-04-29 08:19:01,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 1.9232765436172485, cross_entropy: 1.9232765436172485 +[2025-04-29 08:19:04,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 3.5264549255371094, cross_entropy: 3.5264549255371094 +[2025-04-29 08:19:04,999][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.5623841285705566, cross_entropy: 2.5623841285705566 +[2025-04-29 08:19:08,113][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 1.692545771598816, cross_entropy: 1.692545771598816 +[2025-04-29 08:19:08,453][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.679269313812256, cross_entropy: 2.679269313812256 +[2025-04-29 08:19:11,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.742135524749756, cross_entropy: 2.742135524749756 +[2025-04-29 08:19:12,054][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 3.456754684448242, cross_entropy: 3.456754684448242 +[2025-04-29 08:19:14,716][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 1.9150207042694092, cross_entropy: 1.9150207042694092 +[2025-04-29 08:19:15,066][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.2425713539123535, cross_entropy: 2.2425713539123535 +[2025-04-29 08:19:19,019][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.519670248031616, cross_entropy: 3.519670248031616 +[2025-04-29 08:19:19,365][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.7685798406600952, cross_entropy: 1.7685798406600952 +[2025-04-29 08:19:22,838][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.4327712059020996, cross_entropy: 2.4327712059020996 +[2025-04-29 08:19:23,381][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 2.118659734725952, cross_entropy: 2.118659734725952 +[2025-04-29 08:19:26,768][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 1.871187448501587, cross_entropy: 1.871187448501587 +[2025-04-29 08:19:27,843][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 1.8249285221099854, cross_entropy: 1.8249285221099854 +[2025-04-29 08:19:30,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 2.0841965675354004, cross_entropy: 2.0841965675354004 +[2025-04-29 08:19:31,031][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 2.0419933795928955, cross_entropy: 2.0419933795928955 +[2025-04-29 08:19:34,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 2.024945020675659, cross_entropy: 2.024945020675659 +[2025-04-29 08:19:34,950][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.1472887992858887, cross_entropy: 3.1472887992858887 +[2025-04-29 08:19:38,641][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.779237985610962, cross_entropy: 2.779237985610962 +[2025-04-29 08:19:38,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 3.1112585067749023, cross_entropy: 3.1112585067749023 +[2025-04-29 08:19:43,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.8840112686157227, cross_entropy: 2.8840112686157227 +[2025-04-29 08:19:43,404][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 2.169461965560913, cross_entropy: 2.169461965560913 +[2025-04-29 08:19:46,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 2.850119113922119, cross_entropy: 2.850119113922119 +[2025-04-29 08:19:47,090][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 1.5588939189910889, cross_entropy: 1.5588939189910889 +[2025-04-29 08:19:51,198][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 2.646315097808838, cross_entropy: 2.646315097808838 +[2025-04-29 08:19:51,545][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 3.2678933143615723, cross_entropy: 3.2678933143615723 +[2025-04-29 08:19:55,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 1.5652542114257812, cross_entropy: 1.5652542114257812 +[2025-04-29 08:19:55,524][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 2.1015429496765137, cross_entropy: 2.1015429496765137 +[2025-04-29 08:19:58,756][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 2.9094057083129883, cross_entropy: 2.9094057083129883 +[2025-04-29 08:19:59,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.9751100540161133, cross_entropy: 2.9751100540161133 +[2025-04-29 08:20:02,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 3.0233263969421387, cross_entropy: 3.0233263969421387 +[2025-04-29 08:20:02,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.020345687866211, cross_entropy: 2.020345687866211 +[2025-04-29 08:20:05,773][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 2.2219324111938477, cross_entropy: 2.2219324111938477 +[2025-04-29 08:20:06,117][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.4237980842590332, cross_entropy: 1.4237980842590332 +[2025-04-29 08:20:08,983][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.3314967155456543, cross_entropy: 3.3314967155456543 +[2025-04-29 08:20:09,297][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 2.139151096343994, cross_entropy: 2.139151096343994 +[2025-04-29 08:20:11,879][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 1.772397518157959, cross_entropy: 1.772397518157959 +[2025-04-29 08:22:58,913][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.67134165763855, cross_entropy: 2.67134165763855 +[2025-04-29 08:22:58,914][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.6357158422470093, cross_entropy: 1.6357158422470093 +[2025-04-29 08:22:59,143][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 08:22:59,318][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch2.pth. +[2025-04-29 08:22:59,517][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 08:23:03,865][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 1.768208384513855, cross_entropy: 1.768208384513855 +[2025-04-29 08:23:04,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.9764020442962646, cross_entropy: 1.9764020442962646 +[2025-04-29 08:23:07,505][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 2.7227611541748047, cross_entropy: 2.7227611541748047 +[2025-04-29 08:23:07,872][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 2.8037004470825195, cross_entropy: 2.8037004470825195 +[2025-04-29 08:23:11,004][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.313366413116455, cross_entropy: 1.313366413116455 +[2025-04-29 08:23:11,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.4779200553894043, cross_entropy: 2.4779200553894043 +[2025-04-29 08:23:15,028][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 3.460193634033203, cross_entropy: 3.460193634033203 +[2025-04-29 08:23:15,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 1.792196273803711, cross_entropy: 1.792196273803711 +[2025-04-29 08:23:18,026][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.9737809896469116, cross_entropy: 1.9737809896469116 +[2025-04-29 08:23:19,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 1.5038644075393677, cross_entropy: 1.5038644075393677 +[2025-04-29 08:23:21,549][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 3.391737461090088, cross_entropy: 3.391737461090088 +[2025-04-29 08:23:22,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 3.1161935329437256, cross_entropy: 3.1161935329437256 +[2025-04-29 08:23:25,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 3.2316949367523193, cross_entropy: 3.2316949367523193 +[2025-04-29 08:23:26,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.5881552696228027, cross_entropy: 2.5881552696228027 +[2025-04-29 08:23:28,462][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 3.2468738555908203, cross_entropy: 3.2468738555908203 +[2025-04-29 08:23:29,865][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 2.940187931060791, cross_entropy: 2.940187931060791 +[2025-04-29 08:23:32,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 1.2099113464355469, cross_entropy: 1.2099113464355469 +[2025-04-29 08:23:33,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 1.6263980865478516, cross_entropy: 1.6263980865478516 +[2025-04-29 08:23:35,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 3.275963306427002, cross_entropy: 3.275963306427002 +[2025-04-29 08:23:36,607][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 2.5557150840759277, cross_entropy: 2.5557150840759277 +[2025-04-29 08:23:38,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 1.8024593591690063, cross_entropy: 1.8024593591690063 +[2025-04-29 08:23:40,316][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 3.1690926551818848, cross_entropy: 3.1690926551818848 +[2025-04-29 08:23:42,554][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 2.1788506507873535, cross_entropy: 2.1788506507873535 +[2025-04-29 08:23:44,305][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 1.7552555799484253, cross_entropy: 1.7552555799484253 +[2025-04-29 08:23:47,041][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 1.698257327079773, cross_entropy: 1.698257327079773 +[2025-04-29 08:23:47,654][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 3.462390899658203, cross_entropy: 3.462390899658203 +[2025-04-29 08:23:50,328][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 2.8806028366088867, cross_entropy: 2.8806028366088867 +[2025-04-29 08:23:50,807][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 1.9808430671691895, cross_entropy: 1.9808430671691895 +[2025-04-29 08:23:53,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 1.55796217918396, cross_entropy: 1.55796217918396 +[2025-04-29 08:23:54,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 1.358443260192871, cross_entropy: 1.358443260192871 +[2025-04-29 08:23:57,390][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.6945154666900635, cross_entropy: 1.6945154666900635 +[2025-04-29 08:23:57,861][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 3.3744866847991943, cross_entropy: 3.3744866847991943 +[2025-04-29 08:24:00,627][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 1.560831069946289, cross_entropy: 1.560831069946289 +[2025-04-29 08:24:01,691][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 1.9175007343292236, cross_entropy: 1.9175007343292236 +[2025-04-29 08:24:03,759][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 2.748806953430176, cross_entropy: 2.748806953430176 +[2025-04-29 08:24:05,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 2.6155591011047363, cross_entropy: 2.6155591011047363 +[2025-04-29 08:24:07,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.0638394355773926, cross_entropy: 2.0638394355773926 +[2025-04-29 08:24:08,480][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 3.3544390201568604, cross_entropy: 3.3544390201568604 +[2025-04-29 08:24:11,317][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 2.0452096462249756, cross_entropy: 2.0452096462249756 +[2025-04-29 08:24:12,297][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 3.173552989959717, cross_entropy: 3.173552989959717 +[2025-04-29 08:24:15,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.9777486324310303, cross_entropy: 1.9777486324310303 +[2025-04-29 08:24:16,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 1.4666668176651, cross_entropy: 1.4666668176651 +[2025-04-29 08:24:19,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 2.9630889892578125, cross_entropy: 2.9630889892578125 +[2025-04-29 08:24:19,874][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 3.036069393157959, cross_entropy: 3.036069393157959 +[2025-04-29 08:24:22,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 1.6779932975769043, cross_entropy: 1.6779932975769043 +[2025-04-29 08:24:22,955][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 2.369656562805176, cross_entropy: 2.369656562805176 +[2025-04-29 08:24:26,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 3.6140031814575195, cross_entropy: 3.6140031814575195 +[2025-04-29 08:24:27,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 1.7269518375396729, cross_entropy: 1.7269518375396729 +[2025-04-29 08:24:30,201][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.3960838317871094, cross_entropy: 2.3960838317871094 +[2025-04-29 08:24:30,519][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 3.0237936973571777, cross_entropy: 3.0237936973571777 +[2025-04-29 08:24:33,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.2731759548187256, cross_entropy: 2.2731759548187256 +[2025-04-29 08:24:33,679][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 2.145585298538208, cross_entropy: 2.145585298538208 +[2025-04-29 08:24:36,786][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.75905442237854, cross_entropy: 2.75905442237854 +[2025-04-29 08:24:37,100][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.6262595653533936, cross_entropy: 3.6262595653533936 +[2025-04-29 08:24:40,765][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 2.059718132019043, cross_entropy: 2.059718132019043 +[2025-04-29 08:24:41,079][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.2959682941436768, cross_entropy: 2.2959682941436768 +[2025-04-29 08:24:44,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.568702459335327, cross_entropy: 3.568702459335327 +[2025-04-29 08:24:44,534][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.0112507343292236, cross_entropy: 2.0112507343292236 +[2025-04-29 08:24:48,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.561873435974121, cross_entropy: 3.561873435974121 +[2025-04-29 08:24:48,524][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 3.2036142349243164, cross_entropy: 3.2036142349243164 +[2025-04-29 08:24:52,502][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 1.6822412014007568, cross_entropy: 1.6822412014007568 +[2025-04-29 08:24:52,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 1.6438837051391602, cross_entropy: 1.6438837051391602 +[2025-04-29 08:24:55,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 2.0651533603668213, cross_entropy: 2.0651533603668213 +[2025-04-29 08:24:56,313][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 3.4468231201171875, cross_entropy: 3.4468231201171875 +[2025-04-29 08:24:59,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.2394094467163086, cross_entropy: 3.2394094467163086 +[2025-04-29 08:24:59,957][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.3370187282562256, cross_entropy: 2.3370187282562256 +[2025-04-29 08:25:03,507][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.3520467281341553, cross_entropy: 1.3520467281341553 +[2025-04-29 08:25:03,898][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 2.2247228622436523, cross_entropy: 2.2247228622436523 +[2025-04-29 08:25:07,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.7904610633850098, cross_entropy: 2.7904610633850098 +[2025-04-29 08:25:08,283][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 1.6216087341308594, cross_entropy: 1.6216087341308594 +[2025-04-29 08:25:11,695][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.011906385421753, cross_entropy: 2.011906385421753 +[2025-04-29 08:25:12,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 1.9615837335586548, cross_entropy: 1.9615837335586548 +[2025-04-29 08:25:15,147][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 1.2659096717834473, cross_entropy: 1.2659096717834473 +[2025-04-29 08:25:15,462][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.8929929733276367, cross_entropy: 2.8929929733276367 +[2025-04-29 08:25:18,407][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 1.6132718324661255, cross_entropy: 1.6132718324661255 +[2025-04-29 08:25:18,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 2.337709903717041, cross_entropy: 2.337709903717041 +[2025-04-29 08:25:22,646][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 3.643125057220459, cross_entropy: 3.643125057220459 +[2025-04-29 08:25:22,992][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 2.788076877593994, cross_entropy: 2.788076877593994 +[2025-04-29 08:25:28,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.277743339538574, cross_entropy: 3.277743339538574 +[2025-04-29 08:25:28,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 1.433563470840454, cross_entropy: 1.433563470840454 +[2025-04-29 08:25:32,184][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.1189894676208496, cross_entropy: 3.1189894676208496 +[2025-04-29 08:25:32,526][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 2.213819742202759, cross_entropy: 2.213819742202759 +[2025-04-29 08:25:35,569][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.314096689224243, cross_entropy: 3.314096689224243 +[2025-04-29 08:25:35,906][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 3.2871599197387695, cross_entropy: 3.2871599197387695 +[2025-04-29 08:25:39,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 3.452951669692993, cross_entropy: 3.452951669692993 +[2025-04-29 08:25:39,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.2780051231384277, cross_entropy: 2.2780051231384277 +[2025-04-29 08:25:42,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 3.152632236480713, cross_entropy: 3.152632236480713 +[2025-04-29 08:25:43,139][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 1.8752317428588867, cross_entropy: 1.8752317428588867 +[2025-04-29 08:25:46,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 1.404496192932129, cross_entropy: 1.404496192932129 +[2025-04-29 08:25:46,560][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 2.01998233795166, cross_entropy: 2.01998233795166 +[2025-04-29 08:25:49,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 1.9068173170089722, cross_entropy: 1.9068173170089722 +[2025-04-29 08:25:50,142][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 3.2642273902893066, cross_entropy: 3.2642273902893066 +[2025-04-29 08:25:53,407][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 2.914484977722168, cross_entropy: 2.914484977722168 +[2025-04-29 08:25:53,722][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 1.4600560665130615, cross_entropy: 1.4600560665130615 +[2025-04-29 08:25:56,911][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 2.3252573013305664, cross_entropy: 2.3252573013305664 +[2025-04-29 08:25:57,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 2.090188503265381, cross_entropy: 2.090188503265381 +[2025-04-29 08:26:00,404][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.2042479515075684, cross_entropy: 3.2042479515075684 +[2025-04-29 08:26:00,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 1.6219630241394043, cross_entropy: 1.6219630241394043 +[2025-04-29 08:26:03,484][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.931124687194824, cross_entropy: 2.931124687194824 +[2025-04-29 08:26:03,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 3.3418068885803223, cross_entropy: 3.3418068885803223 +[2025-04-29 08:26:07,238][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 3.3392891883850098, cross_entropy: 3.3392891883850098 +[2025-04-29 08:26:07,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 1.7357630729675293, cross_entropy: 1.7357630729675293 +[2025-04-29 08:26:10,688][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 3.2485830783843994, cross_entropy: 3.2485830783843994 +[2025-04-29 08:26:11,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.736808180809021, cross_entropy: 1.736808180809021 +[2025-04-29 08:26:15,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 2.0356862545013428, cross_entropy: 2.0356862545013428 +[2025-04-29 08:26:15,497][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.656113386154175, cross_entropy: 2.656113386154175 +[2025-04-29 08:26:18,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 1.6899398565292358, cross_entropy: 1.6899398565292358 +[2025-04-29 08:26:19,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 1.6716065406799316, cross_entropy: 1.6716065406799316 +[2025-04-29 08:26:22,496][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 1.9207394123077393, cross_entropy: 1.9207394123077393 +[2025-04-29 08:26:22,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.653046131134033, cross_entropy: 2.653046131134033 +[2025-04-29 08:26:26,064][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.558730363845825, cross_entropy: 2.558730363845825 +[2025-04-29 08:26:26,408][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 3.2442989349365234, cross_entropy: 3.2442989349365234 +[2025-04-29 08:26:30,155][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 1.603966236114502, cross_entropy: 1.603966236114502 +[2025-04-29 08:26:30,500][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 3.0121917724609375, cross_entropy: 3.0121917724609375 +[2025-04-29 08:26:33,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 3.522923469543457, cross_entropy: 3.522923469543457 +[2025-04-29 08:26:33,848][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.5938405990600586, cross_entropy: 1.5938405990600586 +[2025-04-29 08:26:36,980][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.8689651489257812, cross_entropy: 2.8689651489257812 +[2025-04-29 08:26:37,294][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.7265233993530273, cross_entropy: 2.7265233993530273 +[2025-04-29 08:26:41,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 1.6317882537841797, cross_entropy: 1.6317882537841797 +[2025-04-29 08:26:41,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.3500022888183594, cross_entropy: 2.3500022888183594 +[2025-04-29 08:26:45,006][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 3.187267780303955, cross_entropy: 3.187267780303955 +[2025-04-29 08:26:45,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 1.3933472633361816, cross_entropy: 1.3933472633361816 +[2025-04-29 08:26:48,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.5001070499420166, cross_entropy: 2.5001070499420166 +[2025-04-29 08:26:48,709][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 3.325526475906372, cross_entropy: 3.325526475906372 +[2025-04-29 08:26:52,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 1.5765361785888672, cross_entropy: 1.5765361785888672 +[2025-04-29 08:26:52,503][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.355313777923584, cross_entropy: 2.355313777923584 +[2025-04-29 08:26:55,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.886037826538086, cross_entropy: 1.886037826538086 +[2025-04-29 08:26:55,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 1.4194152355194092, cross_entropy: 1.4194152355194092 +[2025-04-29 08:26:59,005][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 1.3426655530929565, cross_entropy: 1.3426655530929565 +[2025-04-29 08:26:59,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 1.7585008144378662, cross_entropy: 1.7585008144378662 +[2025-04-29 08:27:02,441][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 1.4339197874069214, cross_entropy: 1.4339197874069214 +[2025-04-29 08:27:02,756][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 1.3538074493408203, cross_entropy: 1.3538074493408203 +[2025-04-29 08:27:06,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.7754344940185547, cross_entropy: 2.7754344940185547 +[2025-04-29 08:27:06,857][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 3.379262685775757, cross_entropy: 3.379262685775757 +[2025-04-29 08:27:10,219][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 1.6206457614898682, cross_entropy: 1.6206457614898682 +[2025-04-29 08:27:10,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.956518292427063, cross_entropy: 1.956518292427063 +[2025-04-29 08:27:13,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.1410934925079346, cross_entropy: 2.1410934925079346 +[2025-04-29 08:27:14,008][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.3873472213745117, cross_entropy: 1.3873472213745117 +[2025-04-29 08:27:16,936][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 3.418363571166992, cross_entropy: 3.418363571166992 +[2025-04-29 08:27:17,277][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 3.2086896896362305, cross_entropy: 3.2086896896362305 +[2025-04-29 08:27:20,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 3.5338540077209473, cross_entropy: 3.5338540077209473 +[2025-04-29 08:27:20,464][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 3.447829246520996, cross_entropy: 3.447829246520996 +[2025-04-29 08:27:23,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 1.4657208919525146, cross_entropy: 1.4657208919525146 +[2025-04-29 08:27:24,234][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.0195071697235107, cross_entropy: 2.0195071697235107 +[2025-04-29 08:27:27,224][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 1.977295160293579, cross_entropy: 1.977295160293579 +[2025-04-29 08:27:27,592][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 1.6912388801574707, cross_entropy: 1.6912388801574707 +[2025-04-29 08:27:31,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 3.0093560218811035, cross_entropy: 3.0093560218811035 +[2025-04-29 08:27:32,205][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.3465919494628906, cross_entropy: 3.3465919494628906 +[2025-04-29 08:27:35,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 2.3765621185302734, cross_entropy: 2.3765621185302734 +[2025-04-29 08:27:35,693][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 1.7956411838531494, cross_entropy: 1.7956411838531494 +[2025-04-29 08:27:38,698][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 3.6166796684265137, cross_entropy: 3.6166796684265137 +[2025-04-29 08:27:39,041][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.201383590698242, cross_entropy: 2.201383590698242 +[2025-04-29 08:27:41,740][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.7810559272766113, cross_entropy: 2.7810559272766113 +[2025-04-29 08:27:42,142][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 2.7178003787994385, cross_entropy: 2.7178003787994385 +[2025-04-29 08:27:44,949][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 1.9120584726333618, cross_entropy: 1.9120584726333618 +[2025-04-29 08:27:45,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.7187438011169434, cross_entropy: 2.7187438011169434 +[2025-04-29 08:27:48,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 3.494852066040039, cross_entropy: 3.494852066040039 +[2025-04-29 08:27:49,275][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 2.1164660453796387, cross_entropy: 2.1164660453796387 +[2025-04-29 08:27:51,819][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 3.2218594551086426, cross_entropy: 3.2218594551086426 +[2025-04-29 08:27:52,962][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 3.643646240234375, cross_entropy: 3.643646240234375 +[2025-04-29 08:27:55,136][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 2.8749823570251465, cross_entropy: 2.8749823570251465 +[2025-04-29 08:27:56,134][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 1.4831724166870117, cross_entropy: 1.4831724166870117 +[2025-04-29 08:27:58,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 2.8302841186523438, cross_entropy: 2.8302841186523438 +[2025-04-29 08:27:59,988][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 3.2687366008758545, cross_entropy: 3.2687366008758545 +[2025-04-29 08:28:02,499][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 1.6210341453552246, cross_entropy: 1.6210341453552246 +[2025-04-29 08:28:03,505][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.8264796733856201, cross_entropy: 1.8264796733856201 +[2025-04-29 08:28:06,223][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 2.966733694076538, cross_entropy: 2.966733694076538 +[2025-04-29 08:28:07,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 1.9644527435302734, cross_entropy: 1.9644527435302734 +[2025-04-29 08:28:09,813][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.6740179061889648, cross_entropy: 1.6740179061889648 +[2025-04-29 08:28:10,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 2.1131949424743652, cross_entropy: 2.1131949424743652 +[2025-04-29 08:28:13,980][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 3.19504714012146, cross_entropy: 3.19504714012146 +[2025-04-29 08:28:14,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.2867634296417236, cross_entropy: 2.2867634296417236 +[2025-04-29 08:28:17,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 1.4350528717041016, cross_entropy: 1.4350528717041016 +[2025-04-29 08:28:17,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 1.505897045135498, cross_entropy: 1.505897045135498 +[2025-04-29 08:28:20,634][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 3.0056118965148926, cross_entropy: 3.0056118965148926 +[2025-04-29 08:28:20,972][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 3.429175853729248, cross_entropy: 3.429175853729248 +[2025-04-29 08:28:24,013][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.655973434448242, cross_entropy: 2.655973434448242 +[2025-04-29 08:28:24,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 1.7127516269683838, cross_entropy: 1.7127516269683838 +[2025-04-29 08:28:27,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 3.251739501953125, cross_entropy: 3.251739501953125 +[2025-04-29 08:28:27,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.5588173866271973, cross_entropy: 2.5588173866271973 +[2025-04-29 08:28:30,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.8148490190505981, cross_entropy: 1.8148490190505981 +[2025-04-29 08:28:31,337][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 3.0903944969177246, cross_entropy: 3.0903944969177246 +[2025-04-29 08:28:34,631][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.6176061630249023, cross_entropy: 2.6176061630249023 +[2025-04-29 08:28:34,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 3.1544322967529297, cross_entropy: 3.1544322967529297 +[2025-04-29 08:28:38,083][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 1.5602918863296509, cross_entropy: 1.5602918863296509 +[2025-04-29 08:28:38,396][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 1.5859897136688232, cross_entropy: 1.5859897136688232 +[2025-04-29 08:28:41,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 1.8015174865722656, cross_entropy: 1.8015174865722656 +[2025-04-29 08:28:41,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.4580249786376953, cross_entropy: 2.4580249786376953 +[2025-04-29 08:28:45,174][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 2.130784511566162, cross_entropy: 2.130784511566162 +[2025-04-29 08:28:45,688][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 1.5407719612121582, cross_entropy: 1.5407719612121582 +[2025-04-29 08:28:49,360][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 1.8118312358856201, cross_entropy: 1.8118312358856201 +[2025-04-29 08:28:49,700][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 3.232390880584717, cross_entropy: 3.232390880584717 +[2025-04-29 08:28:52,172][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 3.159355640411377, cross_entropy: 3.159355640411377 +[2025-04-29 08:28:52,486][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 3.2033605575561523, cross_entropy: 3.2033605575561523 +[2025-04-29 08:28:55,603][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 3.0821213722229004, cross_entropy: 3.0821213722229004 +[2025-04-29 08:28:55,942][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.865492343902588, cross_entropy: 2.865492343902588 +[2025-04-29 08:28:58,536][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 2.549966335296631, cross_entropy: 2.549966335296631 +[2025-04-29 08:28:58,946][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 1.785295844078064, cross_entropy: 1.785295844078064 +[2025-04-29 08:29:01,947][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.9295684099197388, cross_entropy: 1.9295684099197388 +[2025-04-29 08:29:02,618][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 1.9332053661346436, cross_entropy: 1.9332053661346436 +[2025-04-29 08:29:05,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.0859484672546387, cross_entropy: 2.0859484672546387 +[2025-04-29 08:29:07,713][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 1.5621393918991089, cross_entropy: 1.5621393918991089 +[2025-04-29 08:29:09,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 1.7015466690063477, cross_entropy: 1.7015466690063477 +[2025-04-29 08:29:11,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.2853944301605225, cross_entropy: 2.2853944301605225 +[2025-04-29 08:29:13,586][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 1.3732646703720093, cross_entropy: 1.3732646703720093 +[2025-04-29 08:29:14,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 3.176374912261963, cross_entropy: 3.176374912261963 +[2025-04-29 08:29:17,299][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 3.0479788780212402, cross_entropy: 3.0479788780212402 +[2025-04-29 08:29:18,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 1.4959994554519653, cross_entropy: 1.4959994554519653 +[2025-04-29 08:29:20,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.0877957344055176, cross_entropy: 2.0877957344055176 +[2025-04-29 08:29:21,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.8684420585632324, cross_entropy: 2.8684420585632324 +[2025-04-29 08:29:24,471][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 3.517615795135498, cross_entropy: 3.517615795135498 +[2025-04-29 08:29:25,930][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.8920867443084717, cross_entropy: 1.8920867443084717 +[2025-04-29 08:29:28,595][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 3.079594373703003, cross_entropy: 3.079594373703003 +[2025-04-29 08:29:29,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 1.7211509943008423, cross_entropy: 1.7211509943008423 +[2025-04-29 08:29:32,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 3.5395874977111816, cross_entropy: 3.5395874977111816 +[2025-04-29 08:29:33,938][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 1.7301697731018066, cross_entropy: 1.7301697731018066 +[2025-04-29 08:29:35,347][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.1110973358154297, cross_entropy: 2.1110973358154297 +[2025-04-29 08:29:38,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.40230131149292, cross_entropy: 3.40230131149292 +[2025-04-29 08:29:39,050][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.43630313873291, cross_entropy: 2.43630313873291 +[2025-04-29 08:29:42,650][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 3.2331442832946777, cross_entropy: 3.2331442832946777 +[2025-04-29 08:29:43,052][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 3.365030288696289, cross_entropy: 3.365030288696289 +[2025-04-29 08:29:45,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 1.776390790939331, cross_entropy: 1.776390790939331 +[2025-04-29 08:29:46,522][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 2.732459783554077, cross_entropy: 2.732459783554077 +[2025-04-29 08:29:49,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.198373556137085, cross_entropy: 3.198373556137085 +[2025-04-29 08:29:50,371][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 2.0326385498046875, cross_entropy: 2.0326385498046875 +[2025-04-29 08:29:52,588][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 3.4882490634918213, cross_entropy: 3.4882490634918213 +[2025-04-29 08:29:54,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 3.3302206993103027, cross_entropy: 3.3302206993103027 +[2025-04-29 08:29:55,601][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.355280637741089, cross_entropy: 3.355280637741089 +[2025-04-29 08:29:57,670][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.3451658487319946, cross_entropy: 1.3451658487319946 +[2025-04-29 08:29:59,468][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 2.8045706748962402, cross_entropy: 2.8045706748962402 +[2025-04-29 08:30:00,987][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.376037120819092, cross_entropy: 2.376037120819092 +[2025-04-29 08:30:03,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.344911813735962, cross_entropy: 3.344911813735962 +[2025-04-29 08:30:04,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 1.7898776531219482, cross_entropy: 1.7898776531219482 +[2025-04-29 08:30:07,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 1.7171348333358765, cross_entropy: 1.7171348333358765 +[2025-04-29 08:30:08,111][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 1.525754690170288, cross_entropy: 1.525754690170288 +[2025-04-29 08:30:12,793][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.996004104614258, cross_entropy: 2.996004104614258 +[2025-04-29 08:30:13,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 1.0259521007537842, cross_entropy: 1.0259521007537842 +[2025-04-29 08:30:16,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 2.796774387359619, cross_entropy: 2.796774387359619 +[2025-04-29 08:30:16,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.856421947479248, cross_entropy: 2.856421947479248 +[2025-04-29 08:30:20,184][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 3.2192888259887695, cross_entropy: 3.2192888259887695 +[2025-04-29 08:30:20,500][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.80625057220459, cross_entropy: 2.80625057220459 +[2025-04-29 08:30:24,030][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 1.948996901512146, cross_entropy: 1.948996901512146 +[2025-04-29 08:30:24,374][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.4485292434692383, cross_entropy: 2.4485292434692383 +[2025-04-29 08:30:27,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 2.1479923725128174, cross_entropy: 2.1479923725128174 +[2025-04-29 08:30:27,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 2.4358339309692383, cross_entropy: 2.4358339309692383 +[2025-04-29 08:30:30,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 1.6760163307189941, cross_entropy: 1.6760163307189941 +[2025-04-29 08:30:30,799][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.027742862701416, cross_entropy: 3.027742862701416 +[2025-04-29 08:30:34,068][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.7783024311065674, cross_entropy: 1.7783024311065674 +[2025-04-29 08:30:34,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 1.7356715202331543, cross_entropy: 1.7356715202331543 +[2025-04-29 08:30:37,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 1.4266390800476074, cross_entropy: 1.4266390800476074 +[2025-04-29 08:30:37,680][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.939896583557129, cross_entropy: 2.939896583557129 +[2025-04-29 08:30:41,144][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.9619125127792358, cross_entropy: 1.9619125127792358 +[2025-04-29 08:30:41,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 2.64933443069458, cross_entropy: 2.64933443069458 +[2025-04-29 08:30:45,401][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 1.9072452783584595, cross_entropy: 1.9072452783584595 +[2025-04-29 08:30:45,744][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 2.39145565032959, cross_entropy: 2.39145565032959 +[2025-04-29 08:30:48,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 1.5559847354888916, cross_entropy: 1.5559847354888916 +[2025-04-29 08:30:48,984][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 2.269042491912842, cross_entropy: 2.269042491912842 +[2025-04-29 08:30:52,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 1.4568748474121094, cross_entropy: 1.4568748474121094 +[2025-04-29 08:30:52,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 3.170762300491333, cross_entropy: 3.170762300491333 +[2025-04-29 08:30:57,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.6063010692596436, cross_entropy: 2.6063010692596436 +[2025-04-29 08:30:57,765][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 3.596525192260742, cross_entropy: 3.596525192260742 +[2025-04-29 08:31:00,371][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 3.0079827308654785, cross_entropy: 3.0079827308654785 +[2025-04-29 08:31:00,715][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 2.1553235054016113, cross_entropy: 2.1553235054016113 +[2025-04-29 08:31:03,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.9178954362869263, cross_entropy: 1.9178954362869263 +[2025-04-29 08:31:04,006][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 1.2181187868118286, cross_entropy: 1.2181187868118286 +[2025-04-29 08:31:07,504][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 1.4904621839523315, cross_entropy: 1.4904621839523315 +[2025-04-29 08:31:07,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.3042209148406982, cross_entropy: 3.3042209148406982 +[2025-04-29 08:31:10,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.8659189939498901, cross_entropy: 1.8659189939498901 +[2025-04-29 08:31:11,061][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 1.4085791110992432, cross_entropy: 1.4085791110992432 +[2025-04-29 08:31:14,112][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 2.43878173828125, cross_entropy: 2.43878173828125 +[2025-04-29 08:31:14,493][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 1.8029309511184692, cross_entropy: 1.8029309511184692 +[2025-04-29 08:31:18,898][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.2110874652862549, cross_entropy: 1.2110874652862549 +[2025-04-29 08:31:19,244][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 2.1391916275024414, cross_entropy: 2.1391916275024414 +[2025-04-29 08:31:22,438][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 3.5470385551452637, cross_entropy: 3.5470385551452637 +[2025-04-29 08:31:22,781][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 1.7749972343444824, cross_entropy: 1.7749972343444824 +[2025-04-29 08:31:25,411][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 3.101551055908203, cross_entropy: 3.101551055908203 +[2025-04-29 08:31:25,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 1.975103497505188, cross_entropy: 1.975103497505188 +[2025-04-29 08:31:29,022][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 2.0380921363830566, cross_entropy: 2.0380921363830566 +[2025-04-29 08:31:29,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.776897668838501, cross_entropy: 1.776897668838501 +[2025-04-29 08:31:32,991][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 3.050661563873291, cross_entropy: 3.050661563873291 +[2025-04-29 08:31:33,339][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.5242736339569092, cross_entropy: 1.5242736339569092 +[2025-04-29 08:31:37,395][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.3838963508605957, cross_entropy: 3.3838963508605957 +[2025-04-29 08:31:37,711][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.5943673849105835, cross_entropy: 1.5943673849105835 +[2025-04-29 08:31:40,791][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 1.855696201324463, cross_entropy: 1.855696201324463 +[2025-04-29 08:31:41,110][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.5883605480194092, cross_entropy: 1.5883605480194092 +[2025-04-29 08:31:44,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 1.4485852718353271, cross_entropy: 1.4485852718353271 +[2025-04-29 08:31:44,684][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 3.6346254348754883, cross_entropy: 3.6346254348754883 +[2025-04-29 08:31:48,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.4696898460388184, cross_entropy: 1.4696898460388184 +[2025-04-29 08:31:48,559][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/iteration1000.pth. +[2025-04-29 08:31:48,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 1.9614536762237549, cross_entropy: 1.9614536762237549 +[2025-04-29 08:31:52,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.0010719299316406, cross_entropy: 1.0010719299316406 +[2025-04-29 08:31:52,626][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.066411018371582, cross_entropy: 3.066411018371582 +[2025-04-29 08:31:55,830][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 3.117741346359253, cross_entropy: 3.117741346359253 +[2025-04-29 08:31:56,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.6288753747940063, cross_entropy: 1.6288753747940063 +[2025-04-29 08:31:59,435][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.0147480964660645, cross_entropy: 2.0147480964660645 +[2025-04-29 08:31:59,787][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.9500598907470703, cross_entropy: 2.9500598907470703 +[2025-04-29 08:32:03,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.349306106567383, cross_entropy: 2.349306106567383 +[2025-04-29 08:32:03,555][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 0.9790459871292114, cross_entropy: 0.9790459871292114 +[2025-04-29 08:32:06,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 1.9051198959350586, cross_entropy: 1.9051198959350586 +[2025-04-29 08:32:06,861][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 2.9764225482940674, cross_entropy: 2.9764225482940674 +[2025-04-29 08:32:09,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 1.6043848991394043, cross_entropy: 1.6043848991394043 +[2025-04-29 08:32:10,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 2.2814812660217285, cross_entropy: 2.2814812660217285 +[2025-04-29 08:32:13,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 3.16776704788208, cross_entropy: 3.16776704788208 +[2025-04-29 08:32:14,010][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.5481019020080566, cross_entropy: 1.5481019020080566 +[2025-04-29 08:32:16,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.226264715194702, cross_entropy: 3.226264715194702 +[2025-04-29 08:32:17,170][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 1.2698519229888916, cross_entropy: 1.2698519229888916 +[2025-04-29 08:32:21,626][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 1.7072839736938477, cross_entropy: 1.7072839736938477 +[2025-04-29 08:32:21,944][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.989105701446533, cross_entropy: 2.989105701446533 +[2025-04-29 08:32:24,556][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 1.655540108680725, cross_entropy: 1.655540108680725 +[2025-04-29 08:32:24,899][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 2.861809253692627, cross_entropy: 2.861809253692627 +[2025-04-29 08:32:28,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 3.0401852130889893, cross_entropy: 3.0401852130889893 +[2025-04-29 08:32:28,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.0222077369689941, cross_entropy: 1.0222077369689941 +[2025-04-29 08:32:31,820][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 2.682342529296875, cross_entropy: 2.682342529296875 +[2025-04-29 08:32:32,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 2.597778797149658, cross_entropy: 2.597778797149658 +[2025-04-29 08:32:35,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 3.155808210372925, cross_entropy: 3.155808210372925 +[2025-04-29 08:32:35,570][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 1.7797513008117676, cross_entropy: 1.7797513008117676 +[2025-04-29 08:32:38,531][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 1.943985939025879, cross_entropy: 1.943985939025879 +[2025-04-29 08:32:38,876][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 3.0469255447387695, cross_entropy: 3.0469255447387695 +[2025-04-29 08:32:43,037][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.745185136795044, cross_entropy: 1.745185136795044 +[2025-04-29 08:32:43,380][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.934995412826538, cross_entropy: 1.934995412826538 +[2025-04-29 08:32:46,162][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 2.3275914192199707, cross_entropy: 2.3275914192199707 +[2025-04-29 08:32:46,497][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 2.1479110717773438, cross_entropy: 2.1479110717773438 +[2025-04-29 08:32:49,937][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 2.788999080657959, cross_entropy: 2.788999080657959 +[2025-04-29 08:32:50,279][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.7674074172973633, cross_entropy: 1.7674074172973633 +[2025-04-29 08:32:53,878][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 2.600961208343506, cross_entropy: 2.600961208343506 +[2025-04-29 08:32:54,193][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 3.2370662689208984, cross_entropy: 3.2370662689208984 +[2025-04-29 08:32:58,206][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.8054214715957642, cross_entropy: 1.8054214715957642 +[2025-04-29 08:32:58,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.364497184753418, cross_entropy: 3.364497184753418 +[2025-04-29 08:33:01,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.0007565021514893, cross_entropy: 3.0007565021514893 +[2025-04-29 08:33:01,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 1.9460585117340088, cross_entropy: 1.9460585117340088 +[2025-04-29 08:33:04,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 2.032536506652832, cross_entropy: 2.032536506652832 +[2025-04-29 08:33:04,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 1.8417960405349731, cross_entropy: 1.8417960405349731 +[2025-04-29 08:33:08,138][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 1.1914293766021729, cross_entropy: 1.1914293766021729 +[2025-04-29 08:33:08,481][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 2.381596088409424, cross_entropy: 2.381596088409424 +[2025-04-29 08:33:11,529][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 2.2300679683685303, cross_entropy: 2.2300679683685303 +[2025-04-29 08:33:11,846][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.867039442062378, cross_entropy: 1.867039442062378 +[2025-04-29 08:33:15,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 1.3539611101150513, cross_entropy: 1.3539611101150513 +[2025-04-29 08:33:15,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 2.6520442962646484, cross_entropy: 2.6520442962646484 +[2025-04-29 08:33:19,287][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.9121607542037964, cross_entropy: 1.9121607542037964 +[2025-04-29 08:33:19,604][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 2.8153629302978516, cross_entropy: 2.8153629302978516 +[2025-04-29 08:33:23,138][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 1.388756513595581, cross_entropy: 1.388756513595581 +[2025-04-29 08:33:23,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 2.9064085483551025, cross_entropy: 2.9064085483551025 +[2025-04-29 08:33:27,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.920029640197754, cross_entropy: 2.920029640197754 +[2025-04-29 08:33:27,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.5822546482086182, cross_entropy: 1.5822546482086182 +[2025-04-29 08:33:31,177][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 1.889365315437317, cross_entropy: 1.889365315437317 +[2025-04-29 08:33:31,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 1.500907063484192, cross_entropy: 1.500907063484192 +[2025-04-29 08:33:34,558][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 2.0349349975585938, cross_entropy: 2.0349349975585938 +[2025-04-29 08:33:34,878][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 2.006463050842285, cross_entropy: 2.006463050842285 +[2025-04-29 08:33:38,207][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.3367526531219482, cross_entropy: 1.3367526531219482 +[2025-04-29 08:33:38,523][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.7637317180633545, cross_entropy: 1.7637317180633545 +[2025-04-29 08:33:41,527][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 2.2476892471313477, cross_entropy: 2.2476892471313477 +[2025-04-29 08:33:41,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 1.9459054470062256, cross_entropy: 1.9459054470062256 +[2025-04-29 08:33:45,349][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.6700448989868164, cross_entropy: 2.6700448989868164 +[2025-04-29 08:33:45,665][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 1.3730549812316895, cross_entropy: 1.3730549812316895 +[2025-04-29 08:33:49,034][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 2.5138802528381348, cross_entropy: 2.5138802528381348 +[2025-04-29 08:33:49,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.8464007377624512, cross_entropy: 1.8464007377624512 +[2025-04-29 08:33:51,975][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 1.7031440734863281, cross_entropy: 1.7031440734863281 +[2025-04-29 08:36:41,276][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.3494369983673096, cross_entropy: 2.3494369983673096 +[2025-04-29 08:36:41,276][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.5565003156661987, cross_entropy: 1.5565003156661987 +[2025-04-29 08:36:41,487][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 08:36:41,647][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch3.pth. +[2025-04-29 08:36:41,859][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 08:36:46,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 3.3247320652008057, cross_entropy: 3.3247320652008057 +[2025-04-29 08:36:47,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 3.2079086303710938, cross_entropy: 3.2079086303710938 +[2025-04-29 08:36:49,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.4903223514556885, cross_entropy: 1.4903223514556885 +[2025-04-29 08:36:50,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.4993839263916016, cross_entropy: 1.4993839263916016 +[2025-04-29 08:36:52,738][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 1.495295763015747, cross_entropy: 1.495295763015747 +[2025-04-29 08:36:54,200][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.0800970792770386, cross_entropy: 1.0800970792770386 +[2025-04-29 08:36:55,433][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.6621150970458984, cross_entropy: 1.6621150970458984 +[2025-04-29 08:36:57,632][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 1.3299974203109741, cross_entropy: 1.3299974203109741 +[2025-04-29 08:36:59,713][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.6212985515594482, cross_entropy: 1.6212985515594482 +[2025-04-29 08:37:00,888][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 2.708566427230835, cross_entropy: 2.708566427230835 +[2025-04-29 08:37:03,045][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.1673059463500977, cross_entropy: 3.1673059463500977 +[2025-04-29 08:37:05,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.7666425704956055, cross_entropy: 2.7666425704956055 +[2025-04-29 08:37:06,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 1.3084163665771484, cross_entropy: 1.3084163665771484 +[2025-04-29 08:37:08,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 1.1943378448486328, cross_entropy: 1.1943378448486328 +[2025-04-29 08:37:10,501][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 2.2588400840759277, cross_entropy: 2.2588400840759277 +[2025-04-29 08:37:12,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 3.3122005462646484, cross_entropy: 3.3122005462646484 +[2025-04-29 08:37:14,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 1.3239092826843262, cross_entropy: 1.3239092826843262 +[2025-04-29 08:37:15,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 3.018516778945923, cross_entropy: 3.018516778945923 +[2025-04-29 08:37:18,035][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 1.6931416988372803, cross_entropy: 1.6931416988372803 +[2025-04-29 08:37:18,552][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 1.9032423496246338, cross_entropy: 1.9032423496246338 +[2025-04-29 08:37:21,483][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 3.1731343269348145, cross_entropy: 3.1731343269348145 +[2025-04-29 08:37:21,920][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 2.739546775817871, cross_entropy: 2.739546775817871 +[2025-04-29 08:37:24,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 3.263674259185791, cross_entropy: 3.263674259185791 +[2025-04-29 08:37:25,980][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 2.9103314876556396, cross_entropy: 2.9103314876556396 +[2025-04-29 08:37:27,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.0709004402160645, cross_entropy: 2.0709004402160645 +[2025-04-29 08:37:28,998][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.566209077835083, cross_entropy: 1.566209077835083 +[2025-04-29 08:37:31,210][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.9283156394958496, cross_entropy: 2.9283156394958496 +[2025-04-29 08:37:32,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 1.4240045547485352, cross_entropy: 1.4240045547485352 +[2025-04-29 08:37:34,373][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 3.06705379486084, cross_entropy: 3.06705379486084 +[2025-04-29 08:37:36,765][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 3.157628297805786, cross_entropy: 3.157628297805786 +[2025-04-29 08:37:37,698][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 1.7754031419754028, cross_entropy: 1.7754031419754028 +[2025-04-29 08:37:40,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 2.2173235416412354, cross_entropy: 2.2173235416412354 +[2025-04-29 08:37:42,116][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 1.3675475120544434, cross_entropy: 1.3675475120544434 +[2025-04-29 08:37:43,601][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.617008686065674, cross_entropy: 2.617008686065674 +[2025-04-29 08:37:45,459][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.7658772468566895, cross_entropy: 2.7658772468566895 +[2025-04-29 08:37:47,576][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 3.032400369644165, cross_entropy: 3.032400369644165 +[2025-04-29 08:37:49,137][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.6889524459838867, cross_entropy: 1.6889524459838867 +[2025-04-29 08:37:50,998][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 2.4492931365966797, cross_entropy: 2.4492931365966797 +[2025-04-29 08:37:52,426][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 2.404717445373535, cross_entropy: 2.404717445373535 +[2025-04-29 08:37:56,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 1.9954211711883545, cross_entropy: 1.9954211711883545 +[2025-04-29 08:37:56,431][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.14776611328125, cross_entropy: 2.14776611328125 +[2025-04-29 08:38:00,062][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 3.0838027000427246, cross_entropy: 3.0838027000427246 +[2025-04-29 08:38:00,405][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 1.3492414951324463, cross_entropy: 1.3492414951324463 +[2025-04-29 08:38:03,095][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.4049956798553467, cross_entropy: 2.4049956798553467 +[2025-04-29 08:38:03,439][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 1.6325823068618774, cross_entropy: 1.6325823068618774 +[2025-04-29 08:38:07,024][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 3.1769156455993652, cross_entropy: 3.1769156455993652 +[2025-04-29 08:38:07,366][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 1.2483266592025757, cross_entropy: 1.2483266592025757 +[2025-04-29 08:38:11,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.2181432247161865, cross_entropy: 1.2181432247161865 +[2025-04-29 08:38:11,430][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.5244343280792236, cross_entropy: 1.5244343280792236 +[2025-04-29 08:38:14,549][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.8869400024414062, cross_entropy: 2.8869400024414062 +[2025-04-29 08:38:14,892][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 2.567723035812378, cross_entropy: 2.567723035812378 +[2025-04-29 08:38:18,744][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 2.452186107635498, cross_entropy: 2.452186107635498 +[2025-04-29 08:38:19,088][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 1.9428256750106812, cross_entropy: 1.9428256750106812 +[2025-04-29 08:38:22,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.202369213104248, cross_entropy: 2.202369213104248 +[2025-04-29 08:38:22,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 1.146824836730957, cross_entropy: 1.146824836730957 +[2025-04-29 08:38:25,979][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.0783321857452393, cross_entropy: 1.0783321857452393 +[2025-04-29 08:38:26,324][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.5295677185058594, cross_entropy: 2.5295677185058594 +[2025-04-29 08:38:29,490][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.58750057220459, cross_entropy: 2.58750057220459 +[2025-04-29 08:38:29,837][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 1.3138761520385742, cross_entropy: 1.3138761520385742 +[2025-04-29 08:38:32,996][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.148226261138916, cross_entropy: 2.148226261138916 +[2025-04-29 08:38:33,338][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 2.955695867538452, cross_entropy: 2.955695867538452 +[2025-04-29 08:38:36,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.0779476165771484, cross_entropy: 2.0779476165771484 +[2025-04-29 08:38:36,788][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 1.3080530166625977, cross_entropy: 1.3080530166625977 +[2025-04-29 08:38:40,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 3.213496208190918, cross_entropy: 3.213496208190918 +[2025-04-29 08:38:40,509][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 1.363932728767395, cross_entropy: 1.363932728767395 +[2025-04-29 08:38:43,781][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.652340292930603, cross_entropy: 1.652340292930603 +[2025-04-29 08:38:44,120][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.594043016433716, cross_entropy: 2.594043016433716 +[2025-04-29 08:38:47,202][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.285036087036133, cross_entropy: 3.285036087036133 +[2025-04-29 08:38:47,545][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 1.8209457397460938, cross_entropy: 1.8209457397460938 +[2025-04-29 08:38:51,120][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 1.4380464553833008, cross_entropy: 1.4380464553833008 +[2025-04-29 08:38:51,464][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.6556878089904785, cross_entropy: 2.6556878089904785 +[2025-04-29 08:38:54,765][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 2.8711373805999756, cross_entropy: 2.8711373805999756 +[2025-04-29 08:38:55,080][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.575736165046692, cross_entropy: 1.575736165046692 +[2025-04-29 08:38:58,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.085395097732544, cross_entropy: 1.085395097732544 +[2025-04-29 08:38:58,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 1.3056398630142212, cross_entropy: 1.3056398630142212 +[2025-04-29 08:39:02,562][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 3.052398681640625, cross_entropy: 3.052398681640625 +[2025-04-29 08:39:02,903][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.166911244392395, cross_entropy: 1.166911244392395 +[2025-04-29 08:39:05,973][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 2.942490577697754, cross_entropy: 2.942490577697754 +[2025-04-29 08:39:06,325][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 1.3879414796829224, cross_entropy: 1.3879414796829224 +[2025-04-29 08:39:09,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 3.0582680702209473, cross_entropy: 3.0582680702209473 +[2025-04-29 08:39:09,742][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 1.1357660293579102, cross_entropy: 1.1357660293579102 +[2025-04-29 08:39:12,954][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.356513500213623, cross_entropy: 2.356513500213623 +[2025-04-29 08:39:13,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 1.0881305932998657, cross_entropy: 1.0881305932998657 +[2025-04-29 08:39:16,825][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 3.1835501194000244, cross_entropy: 3.1835501194000244 +[2025-04-29 08:39:17,165][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 3.2961034774780273, cross_entropy: 3.2961034774780273 +[2025-04-29 08:39:20,983][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 1.586503505706787, cross_entropy: 1.586503505706787 +[2025-04-29 08:39:21,296][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 3.1203880310058594, cross_entropy: 3.1203880310058594 +[2025-04-29 08:39:24,687][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 1.3203620910644531, cross_entropy: 1.3203620910644531 +[2025-04-29 08:39:25,015][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 1.513239860534668, cross_entropy: 1.513239860534668 +[2025-04-29 08:39:28,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 1.8052926063537598, cross_entropy: 1.8052926063537598 +[2025-04-29 08:39:29,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 2.236633539199829, cross_entropy: 2.236633539199829 +[2025-04-29 08:39:32,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 3.488483428955078, cross_entropy: 3.488483428955078 +[2025-04-29 08:39:32,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.7236279249191284, cross_entropy: 1.7236279249191284 +[2025-04-29 08:39:35,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 1.2389165163040161, cross_entropy: 1.2389165163040161 +[2025-04-29 08:39:35,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 3.0553336143493652, cross_entropy: 3.0553336143493652 +[2025-04-29 08:39:39,650][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.8054393529891968, cross_entropy: 1.8054393529891968 +[2025-04-29 08:39:39,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 1.7262500524520874, cross_entropy: 1.7262500524520874 +[2025-04-29 08:39:42,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 2.0994410514831543, cross_entropy: 2.0994410514831543 +[2025-04-29 08:39:43,174][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 1.6713306903839111, cross_entropy: 1.6713306903839111 +[2025-04-29 08:39:46,461][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.3661503791809082, cross_entropy: 1.3661503791809082 +[2025-04-29 08:39:46,804][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 3.1203787326812744, cross_entropy: 3.1203787326812744 +[2025-04-29 08:39:50,050][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.060725688934326, cross_entropy: 2.060725688934326 +[2025-04-29 08:39:50,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.8389506340026855, cross_entropy: 2.8389506340026855 +[2025-04-29 08:39:53,001][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 1.3011677265167236, cross_entropy: 1.3011677265167236 +[2025-04-29 08:39:53,348][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 1.5578752756118774, cross_entropy: 1.5578752756118774 +[2025-04-29 08:39:56,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 2.3033969402313232, cross_entropy: 2.3033969402313232 +[2025-04-29 08:39:56,449][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.272096633911133, cross_entropy: 3.272096633911133 +[2025-04-29 08:39:59,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 3.0521035194396973, cross_entropy: 3.0521035194396973 +[2025-04-29 08:39:59,858][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 1.526167631149292, cross_entropy: 1.526167631149292 +[2025-04-29 08:40:02,961][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 3.1204261779785156, cross_entropy: 3.1204261779785156 +[2025-04-29 08:40:03,278][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 3.581789970397949, cross_entropy: 3.581789970397949 +[2025-04-29 08:40:07,160][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.4493037462234497, cross_entropy: 1.4493037462234497 +[2025-04-29 08:40:07,504][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 1.5343538522720337, cross_entropy: 1.5343538522720337 +[2025-04-29 08:40:10,719][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 1.5613535642623901, cross_entropy: 1.5613535642623901 +[2025-04-29 08:40:11,067][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 3.0556507110595703, cross_entropy: 3.0556507110595703 +[2025-04-29 08:40:14,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.494004249572754, cross_entropy: 2.494004249572754 +[2025-04-29 08:40:14,331][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.85139799118042, cross_entropy: 2.85139799118042 +[2025-04-29 08:40:17,558][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 3.568574905395508, cross_entropy: 3.568574905395508 +[2025-04-29 08:40:17,907][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.4757689237594604, cross_entropy: 1.4757689237594604 +[2025-04-29 08:40:21,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.7701525688171387, cross_entropy: 2.7701525688171387 +[2025-04-29 08:40:21,662][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 1.7172037363052368, cross_entropy: 1.7172037363052368 +[2025-04-29 08:40:25,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 3.254755973815918, cross_entropy: 3.254755973815918 +[2025-04-29 08:40:25,493][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 1.4958434104919434, cross_entropy: 1.4958434104919434 +[2025-04-29 08:40:28,848][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 2.349128007888794, cross_entropy: 2.349128007888794 +[2025-04-29 08:40:29,174][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 3.183021068572998, cross_entropy: 3.183021068572998 +[2025-04-29 08:40:32,553][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 2.5249853134155273, cross_entropy: 2.5249853134155273 +[2025-04-29 08:40:32,898][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 2.4797286987304688, cross_entropy: 2.4797286987304688 +[2025-04-29 08:40:35,894][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 1.6993844509124756, cross_entropy: 1.6993844509124756 +[2025-04-29 08:40:36,252][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 3.062592029571533, cross_entropy: 3.062592029571533 +[2025-04-29 08:40:39,150][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 1.1292914152145386, cross_entropy: 1.1292914152145386 +[2025-04-29 08:40:39,490][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 2.3778235912323, cross_entropy: 2.3778235912323 +[2025-04-29 08:40:42,648][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 1.5561243295669556, cross_entropy: 1.5561243295669556 +[2025-04-29 08:40:42,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 3.1485848426818848, cross_entropy: 3.1485848426818848 +[2025-04-29 08:40:46,029][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.049776315689087, cross_entropy: 1.049776315689087 +[2025-04-29 08:40:46,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.706886649131775, cross_entropy: 1.706886649131775 +[2025-04-29 08:40:49,448][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.6488635540008545, cross_entropy: 2.6488635540008545 +[2025-04-29 08:40:49,789][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 2.8421244621276855, cross_entropy: 2.8421244621276855 +[2025-04-29 08:40:53,495][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.305661201477051, cross_entropy: 2.305661201477051 +[2025-04-29 08:40:53,840][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.153586506843567, cross_entropy: 1.153586506843567 +[2025-04-29 08:40:56,630][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 3.2000231742858887, cross_entropy: 3.2000231742858887 +[2025-04-29 08:40:56,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.4304234981536865, cross_entropy: 3.4304234981536865 +[2025-04-29 08:41:00,260][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 1.3861033916473389, cross_entropy: 1.3861033916473389 +[2025-04-29 08:41:00,574][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 2.5277445316314697, cross_entropy: 2.5277445316314697 +[2025-04-29 08:41:03,266][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 1.7275269031524658, cross_entropy: 1.7275269031524658 +[2025-04-29 08:41:03,657][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 2.45857572555542, cross_entropy: 2.45857572555542 +[2025-04-29 08:41:06,499][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.759179949760437, cross_entropy: 1.759179949760437 +[2025-04-29 08:41:06,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 1.4269275665283203, cross_entropy: 1.4269275665283203 +[2025-04-29 08:41:10,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.0151853561401367, cross_entropy: 3.0151853561401367 +[2025-04-29 08:41:10,579][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 2.5277457237243652, cross_entropy: 2.5277457237243652 +[2025-04-29 08:41:13,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 2.65809965133667, cross_entropy: 2.65809965133667 +[2025-04-29 08:41:13,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 3.3125457763671875, cross_entropy: 3.3125457763671875 +[2025-04-29 08:41:15,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 2.303755760192871, cross_entropy: 2.303755760192871 +[2025-04-29 08:41:17,158][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 3.077714681625366, cross_entropy: 3.077714681625366 +[2025-04-29 08:41:20,791][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 2.6531410217285156, cross_entropy: 2.6531410217285156 +[2025-04-29 08:41:21,103][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.479116439819336, cross_entropy: 1.479116439819336 +[2025-04-29 08:41:24,394][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.252211570739746, cross_entropy: 2.252211570739746 +[2025-04-29 08:41:24,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 3.163240671157837, cross_entropy: 3.163240671157837 +[2025-04-29 08:41:27,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 2.168172836303711, cross_entropy: 2.168172836303711 +[2025-04-29 08:41:27,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.403740406036377, cross_entropy: 3.403740406036377 +[2025-04-29 08:41:31,084][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 1.696265697479248, cross_entropy: 1.696265697479248 +[2025-04-29 08:41:31,440][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.912508964538574, cross_entropy: 2.912508964538574 +[2025-04-29 08:41:34,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 2.6703858375549316, cross_entropy: 2.6703858375549316 +[2025-04-29 08:41:35,392][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 1.4241782426834106, cross_entropy: 1.4241782426834106 +[2025-04-29 08:41:38,093][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 1.008595585823059, cross_entropy: 1.008595585823059 +[2025-04-29 08:41:38,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.2079999446868896, cross_entropy: 1.2079999446868896 +[2025-04-29 08:41:41,888][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 2.90103816986084, cross_entropy: 2.90103816986084 +[2025-04-29 08:41:42,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.7791913747787476, cross_entropy: 1.7791913747787476 +[2025-04-29 08:41:45,070][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.7564555406570435, cross_entropy: 1.7564555406570435 +[2025-04-29 08:41:45,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.3932552337646484, cross_entropy: 1.3932552337646484 +[2025-04-29 08:41:47,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 2.03619122505188, cross_entropy: 2.03619122505188 +[2025-04-29 08:41:48,213][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 1.2604022026062012, cross_entropy: 1.2604022026062012 +[2025-04-29 08:41:50,613][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 3.277822971343994, cross_entropy: 3.277822971343994 +[2025-04-29 08:41:51,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 3.0134897232055664, cross_entropy: 3.0134897232055664 +[2025-04-29 08:41:55,259][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 1.9078834056854248, cross_entropy: 1.9078834056854248 +[2025-04-29 08:41:55,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 3.3777923583984375, cross_entropy: 3.3777923583984375 +[2025-04-29 08:41:59,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 3.1852829456329346, cross_entropy: 3.1852829456329346 +[2025-04-29 08:41:59,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 2.193680763244629, cross_entropy: 2.193680763244629 +[2025-04-29 08:42:02,423][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.289851188659668, cross_entropy: 1.289851188659668 +[2025-04-29 08:42:02,766][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 1.5678606033325195, cross_entropy: 1.5678606033325195 +[2025-04-29 08:42:05,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 3.246225357055664, cross_entropy: 3.246225357055664 +[2025-04-29 08:42:06,159][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 2.956260919570923, cross_entropy: 2.956260919570923 +[2025-04-29 08:42:09,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 2.3032312393188477, cross_entropy: 2.3032312393188477 +[2025-04-29 08:42:09,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.592568039894104, cross_entropy: 1.592568039894104 +[2025-04-29 08:42:12,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 3.0308566093444824, cross_entropy: 3.0308566093444824 +[2025-04-29 08:42:13,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 1.9794285297393799, cross_entropy: 1.9794285297393799 +[2025-04-29 08:42:15,834][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 2.234248638153076, cross_entropy: 2.234248638153076 +[2025-04-29 08:42:16,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.6512342691421509, cross_entropy: 1.6512342691421509 +[2025-04-29 08:42:19,032][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.435327172279358, cross_entropy: 1.435327172279358 +[2025-04-29 08:42:20,851][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 2.3758063316345215, cross_entropy: 2.3758063316345215 +[2025-04-29 08:42:22,730][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 1.6641623973846436, cross_entropy: 1.6641623973846436 +[2025-04-29 08:42:24,798][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.245305061340332, cross_entropy: 2.245305061340332 +[2025-04-29 08:42:26,098][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 1.3543565273284912, cross_entropy: 1.3543565273284912 +[2025-04-29 08:42:28,543][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 1.541063666343689, cross_entropy: 1.541063666343689 +[2025-04-29 08:42:30,263][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 1.2837022542953491, cross_entropy: 1.2837022542953491 +[2025-04-29 08:42:31,506][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.2188642024993896, cross_entropy: 1.2188642024993896 +[2025-04-29 08:42:34,463][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 1.0591644048690796, cross_entropy: 1.0591644048690796 +[2025-04-29 08:42:34,874][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 1.1420950889587402, cross_entropy: 1.1420950889587402 +[2025-04-29 08:42:38,312][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 3.0692896842956543, cross_entropy: 3.0692896842956543 +[2025-04-29 08:42:38,664][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 3.182720422744751, cross_entropy: 3.182720422744751 +[2025-04-29 08:42:42,568][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 2.446094512939453, cross_entropy: 2.446094512939453 +[2025-04-29 08:42:42,912][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.1062283515930176, cross_entropy: 1.1062283515930176 +[2025-04-29 08:42:46,335][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 3.3038089275360107, cross_entropy: 3.3038089275360107 +[2025-04-29 08:42:46,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 1.2211331129074097, cross_entropy: 1.2211331129074097 +[2025-04-29 08:42:51,069][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.4986692667007446, cross_entropy: 1.4986692667007446 +[2025-04-29 08:42:51,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 2.8919577598571777, cross_entropy: 2.8919577598571777 +[2025-04-29 08:42:54,999][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 3.3576531410217285, cross_entropy: 3.3576531410217285 +[2025-04-29 08:42:55,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 2.310319423675537, cross_entropy: 2.310319423675537 +[2025-04-29 08:42:58,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 2.6104533672332764, cross_entropy: 2.6104533672332764 +[2025-04-29 08:42:59,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 3.517831802368164, cross_entropy: 3.517831802368164 +[2025-04-29 08:43:02,917][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 3.246687412261963, cross_entropy: 3.246687412261963 +[2025-04-29 08:43:03,267][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 2.4305617809295654, cross_entropy: 2.4305617809295654 +[2025-04-29 08:43:06,010][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 3.4668996334075928, cross_entropy: 3.4668996334075928 +[2025-04-29 08:43:06,362][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 1.5399043560028076, cross_entropy: 1.5399043560028076 +[2025-04-29 08:43:09,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 3.491786479949951, cross_entropy: 3.491786479949951 +[2025-04-29 08:43:09,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 3.1851067543029785, cross_entropy: 3.1851067543029785 +[2025-04-29 08:43:12,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.507960796356201, cross_entropy: 2.507960796356201 +[2025-04-29 08:43:13,038][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 3.090304374694824, cross_entropy: 3.090304374694824 +[2025-04-29 08:43:16,422][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 1.7695801258087158, cross_entropy: 1.7695801258087158 +[2025-04-29 08:43:16,770][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 2.65407657623291, cross_entropy: 2.65407657623291 +[2025-04-29 08:43:19,770][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.215283155441284, cross_entropy: 2.215283155441284 +[2025-04-29 08:43:20,094][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 3.018095016479492, cross_entropy: 3.018095016479492 +[2025-04-29 08:43:23,063][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 1.4068796634674072, cross_entropy: 1.4068796634674072 +[2025-04-29 08:43:23,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 1.317808985710144, cross_entropy: 1.317808985710144 +[2025-04-29 08:43:27,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 1.8204931020736694, cross_entropy: 1.8204931020736694 +[2025-04-29 08:43:27,384][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 2.5311248302459717, cross_entropy: 2.5311248302459717 +[2025-04-29 08:43:31,383][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.061448574066162, cross_entropy: 3.061448574066162 +[2025-04-29 08:43:31,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 2.8062806129455566, cross_entropy: 2.8062806129455566 +[2025-04-29 08:43:35,424][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 1.005704641342163, cross_entropy: 1.005704641342163 +[2025-04-29 08:43:35,772][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.126070022583008, cross_entropy: 3.126070022583008 +[2025-04-29 08:43:38,521][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.654740333557129, cross_entropy: 1.654740333557129 +[2025-04-29 08:43:38,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.4684994220733643, cross_entropy: 2.4684994220733643 +[2025-04-29 08:43:41,977][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 1.6226189136505127, cross_entropy: 1.6226189136505127 +[2025-04-29 08:43:42,327][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 1.804139256477356, cross_entropy: 1.804139256477356 +[2025-04-29 08:43:45,836][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.830439805984497, cross_entropy: 1.830439805984497 +[2025-04-29 08:43:46,182][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 3.1542015075683594, cross_entropy: 3.1542015075683594 +[2025-04-29 08:43:49,078][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 1.7983371019363403, cross_entropy: 1.7983371019363403 +[2025-04-29 08:43:50,274][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 2.2918949127197266, cross_entropy: 2.2918949127197266 +[2025-04-29 08:43:52,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.2850422859191895, cross_entropy: 2.2850422859191895 +[2025-04-29 08:43:54,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 1.7063989639282227, cross_entropy: 1.7063989639282227 +[2025-04-29 08:43:56,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.322904109954834, cross_entropy: 1.322904109954834 +[2025-04-29 08:43:57,944][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 2.640786647796631, cross_entropy: 2.640786647796631 +[2025-04-29 08:43:59,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 1.2815492153167725, cross_entropy: 1.2815492153167725 +[2025-04-29 08:44:01,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.866482973098755, cross_entropy: 2.866482973098755 +[2025-04-29 08:44:04,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 2.9717674255371094, cross_entropy: 2.9717674255371094 +[2025-04-29 08:44:05,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 3.0409278869628906, cross_entropy: 3.0409278869628906 +[2025-04-29 08:44:07,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 3.2327511310577393, cross_entropy: 3.2327511310577393 +[2025-04-29 08:44:08,633][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 1.2449514865875244, cross_entropy: 1.2449514865875244 +[2025-04-29 08:44:11,200][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 1.6363985538482666, cross_entropy: 1.6363985538482666 +[2025-04-29 08:44:12,441][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 1.2594959735870361, cross_entropy: 1.2594959735870361 +[2025-04-29 08:44:14,779][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.429602861404419, cross_entropy: 1.429602861404419 +[2025-04-29 08:44:16,138][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.4457008838653564, cross_entropy: 2.4457008838653564 +[2025-04-29 08:44:19,014][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 2.2015950679779053, cross_entropy: 2.2015950679779053 +[2025-04-29 08:44:19,602][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 1.3681309223175049, cross_entropy: 1.3681309223175049 +[2025-04-29 08:44:22,522][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 1.3405396938323975, cross_entropy: 1.3405396938323975 +[2025-04-29 08:44:23,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 1.5073859691619873, cross_entropy: 1.5073859691619873 +[2025-04-29 08:44:26,005][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 2.7893872261047363, cross_entropy: 2.7893872261047363 +[2025-04-29 08:44:27,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 2.158036470413208, cross_entropy: 2.158036470413208 +[2025-04-29 08:44:29,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.2203319072723389, cross_entropy: 1.2203319072723389 +[2025-04-29 08:44:32,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 2.357851982116699, cross_entropy: 2.357851982116699 +[2025-04-29 08:44:33,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.651760458946228, cross_entropy: 1.651760458946228 +[2025-04-29 08:44:35,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 0.8276341557502747, cross_entropy: 0.8276341557502747 +[2025-04-29 08:44:36,597][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 1.2480096817016602, cross_entropy: 1.2480096817016602 +[2025-04-29 08:44:39,177][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 2.8425612449645996, cross_entropy: 2.8425612449645996 +[2025-04-29 08:44:39,612][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 1.0218908786773682, cross_entropy: 1.0218908786773682 +[2025-04-29 08:44:43,711][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 2.018719434738159, cross_entropy: 2.018719434738159 +[2025-04-29 08:44:44,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 1.4006539583206177, cross_entropy: 1.4006539583206177 +[2025-04-29 08:44:46,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.6711716651916504, cross_entropy: 2.6711716651916504 +[2025-04-29 08:44:47,064][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 3.0905871391296387, cross_entropy: 3.0905871391296387 +[2025-04-29 08:44:50,508][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 2.1004509925842285, cross_entropy: 2.1004509925842285 +[2025-04-29 08:44:51,380][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.165440320968628, cross_entropy: 1.165440320968628 +[2025-04-29 08:44:54,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 1.2058526277542114, cross_entropy: 1.2058526277542114 +[2025-04-29 08:44:54,865][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.9482004642486572, cross_entropy: 1.9482004642486572 +[2025-04-29 08:44:58,506][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 2.1515045166015625, cross_entropy: 2.1515045166015625 +[2025-04-29 08:44:58,836][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.6449666023254395, cross_entropy: 2.6449666023254395 +[2025-04-29 08:45:01,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 2.8368566036224365, cross_entropy: 2.8368566036224365 +[2025-04-29 08:45:01,950][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 3.0086827278137207, cross_entropy: 3.0086827278137207 +[2025-04-29 08:45:04,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 3.3407175540924072, cross_entropy: 3.3407175540924072 +[2025-04-29 08:45:05,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 1.9176154136657715, cross_entropy: 1.9176154136657715 +[2025-04-29 08:45:08,942][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 2.1012701988220215, cross_entropy: 2.1012701988220215 +[2025-04-29 08:45:09,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 1.132649540901184, cross_entropy: 1.132649540901184 +[2025-04-29 08:45:12,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 0.9881137609481812, cross_entropy: 0.9881137609481812 +[2025-04-29 08:45:13,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 3.217559337615967, cross_entropy: 3.217559337615967 +[2025-04-29 08:45:15,941][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 1.2097935676574707, cross_entropy: 1.2097935676574707 +[2025-04-29 08:45:17,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 3.1536622047424316, cross_entropy: 3.1536622047424316 +[2025-04-29 08:45:19,841][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 1.8926703929901123, cross_entropy: 1.8926703929901123 +[2025-04-29 08:45:20,710][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.8753786087036133, cross_entropy: 2.8753786087036133 +[2025-04-29 08:45:23,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.120682716369629, cross_entropy: 3.120682716369629 +[2025-04-29 08:45:23,745][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 1.5305547714233398, cross_entropy: 1.5305547714233398 +[2025-04-29 08:45:26,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4854601621627808, cross_entropy: 1.4854601621627808 +[2025-04-29 08:45:27,622][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 3.4112792015075684, cross_entropy: 3.4112792015075684 +[2025-04-29 08:45:30,739][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 3.2707314491271973, cross_entropy: 3.2707314491271973 +[2025-04-29 08:45:31,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 1.6258337497711182, cross_entropy: 1.6258337497711182 +[2025-04-29 08:45:34,077][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 2.7876086235046387, cross_entropy: 2.7876086235046387 +[2025-04-29 08:45:34,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 1.4136706590652466, cross_entropy: 1.4136706590652466 +[2025-04-29 08:45:37,621][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 2.8534066677093506, cross_entropy: 2.8534066677093506 +[2025-04-29 08:45:38,105][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 1.415797233581543, cross_entropy: 1.415797233581543 +[2025-04-29 08:45:41,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 1.6601272821426392, cross_entropy: 1.6601272821426392 +[2025-04-29 08:45:42,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 3.4376473426818848, cross_entropy: 3.4376473426818848 +[2025-04-29 08:45:45,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.4389047622680664, cross_entropy: 2.4389047622680664 +[2025-04-29 08:45:45,795][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 1.8460776805877686, cross_entropy: 1.8460776805877686 +[2025-04-29 08:45:48,282][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.5549763441085815, cross_entropy: 1.5549763441085815 +[2025-04-29 08:45:48,760][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 3.0308077335357666, cross_entropy: 3.0308077335357666 +[2025-04-29 08:45:52,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 2.8696939945220947, cross_entropy: 2.8696939945220947 +[2025-04-29 08:45:52,458][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.6410329341888428, cross_entropy: 1.6410329341888428 +[2025-04-29 08:45:56,045][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 2.9464948177337646, cross_entropy: 2.9464948177337646 +[2025-04-29 08:45:56,359][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.938791275024414, cross_entropy: 2.938791275024414 +[2025-04-29 08:45:59,705][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 2.8847906589508057, cross_entropy: 2.8847906589508057 +[2025-04-29 08:46:00,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 2.8153772354125977, cross_entropy: 2.8153772354125977 +[2025-04-29 08:46:03,140][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.721306324005127, cross_entropy: 2.721306324005127 +[2025-04-29 08:46:03,485][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 1.267640233039856, cross_entropy: 1.267640233039856 +[2025-04-29 08:46:07,696][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.2281088829040527, cross_entropy: 2.2281088829040527 +[2025-04-29 08:46:08,043][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.0824438333511353, cross_entropy: 1.0824438333511353 +[2025-04-29 08:46:11,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 3.218233108520508, cross_entropy: 3.218233108520508 +[2025-04-29 08:46:11,600][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.3668227195739746, cross_entropy: 2.3668227195739746 +[2025-04-29 08:46:15,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 2.162889003753662, cross_entropy: 2.162889003753662 +[2025-04-29 08:46:15,363][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 2.8991079330444336, cross_entropy: 2.8991079330444336 +[2025-04-29 08:46:18,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 2.56868577003479, cross_entropy: 2.56868577003479 +[2025-04-29 08:46:18,914][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 2.4037973880767822, cross_entropy: 2.4037973880767822 +[2025-04-29 08:46:22,411][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.878126382827759, cross_entropy: 2.878126382827759 +[2025-04-29 08:46:22,751][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 2.830047369003296, cross_entropy: 2.830047369003296 +[2025-04-29 08:46:25,761][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 2.9272043704986572, cross_entropy: 2.9272043704986572 +[2025-04-29 08:46:26,108][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.8223954439163208, cross_entropy: 1.8223954439163208 +[2025-04-29 08:46:29,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.321805715560913, cross_entropy: 2.321805715560913 +[2025-04-29 08:46:29,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 2.9487781524658203, cross_entropy: 2.9487781524658203 +[2025-04-29 08:46:32,713][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 1.6227598190307617, cross_entropy: 1.6227598190307617 +[2025-04-29 08:46:33,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.060270309448242, cross_entropy: 2.060270309448242 +[2025-04-29 08:46:36,117][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 3.2645483016967773, cross_entropy: 3.2645483016967773 +[2025-04-29 08:46:36,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 3.048877716064453, cross_entropy: 3.048877716064453 +[2025-04-29 08:46:40,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 2.2544755935668945, cross_entropy: 2.2544755935668945 +[2025-04-29 08:46:40,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 2.195819139480591, cross_entropy: 2.195819139480591 +[2025-04-29 08:46:43,535][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.630951166152954, cross_entropy: 1.630951166152954 +[2025-04-29 08:46:43,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 2.848783493041992, cross_entropy: 2.848783493041992 +[2025-04-29 08:46:47,083][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 1.0332062244415283, cross_entropy: 1.0332062244415283 +[2025-04-29 08:46:47,426][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 3.0992374420166016, cross_entropy: 3.0992374420166016 +[2025-04-29 08:46:50,137][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.4529788494110107, cross_entropy: 1.4529788494110107 +[2025-04-29 08:46:50,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 1.3334763050079346, cross_entropy: 1.3334763050079346 +[2025-04-29 08:46:53,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.4639105796813965, cross_entropy: 1.4639105796813965 +[2025-04-29 08:46:53,887][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.919053792953491, cross_entropy: 2.919053792953491 +[2025-04-29 08:46:57,078][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 1.267028570175171, cross_entropy: 1.267028570175171 +[2025-04-29 08:46:57,424][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 2.9117069244384766, cross_entropy: 2.9117069244384766 +[2025-04-29 08:47:00,356][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 1.3931732177734375, cross_entropy: 1.3931732177734375 +[2025-04-29 08:47:00,695][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 1.7102018594741821, cross_entropy: 1.7102018594741821 +[2025-04-29 08:47:04,034][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 2.4167966842651367, cross_entropy: 2.4167966842651367 +[2025-04-29 08:47:04,384][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.1627485752105713, cross_entropy: 1.1627485752105713 +[2025-04-29 08:47:08,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.3361024856567383, cross_entropy: 2.3361024856567383 +[2025-04-29 08:47:09,110][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 1.2109379768371582, cross_entropy: 1.2109379768371582 +[2025-04-29 08:47:11,829][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.5036817789077759, cross_entropy: 1.5036817789077759 +[2025-04-29 08:47:12,168][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 1.6366302967071533, cross_entropy: 1.6366302967071533 +[2025-04-29 08:47:15,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 3.3844258785247803, cross_entropy: 3.3844258785247803 +[2025-04-29 08:47:15,753][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.3629549741744995, cross_entropy: 1.3629549741744995 +[2025-04-29 08:47:18,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.1718502044677734, cross_entropy: 1.1718502044677734 +[2025-04-29 08:47:18,759][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 3.0464184284210205, cross_entropy: 3.0464184284210205 +[2025-04-29 08:47:22,025][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 2.1600165367126465, cross_entropy: 2.1600165367126465 +[2025-04-29 08:47:22,365][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 2.1604793071746826, cross_entropy: 2.1604793071746826 +[2025-04-29 08:47:25,493][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 3.315871000289917, cross_entropy: 3.315871000289917 +[2025-04-29 08:47:25,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.1763916015625, cross_entropy: 3.1763916015625 +[2025-04-29 08:50:09,021][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.2093448638916016, cross_entropy: 2.2093448638916016 +[2025-04-29 08:50:09,022][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.3772354125976562, cross_entropy: 1.3772354125976562 +[2025-04-29 08:50:09,250][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 08:50:09,419][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch4.pth. +[2025-04-29 08:50:09,650][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 08:50:14,248][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.3266327381134033, cross_entropy: 2.3266327381134033 +[2025-04-29 08:50:14,590][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.4029958248138428, cross_entropy: 1.4029958248138428 +[2025-04-29 08:50:17,804][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.7935208082199097, cross_entropy: 1.7935208082199097 +[2025-04-29 08:50:18,141][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.3128256797790527, cross_entropy: 1.3128256797790527 +[2025-04-29 08:50:21,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 2.9219634532928467, cross_entropy: 2.9219634532928467 +[2025-04-29 08:50:21,402][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.9146671295166016, cross_entropy: 2.9146671295166016 +[2025-04-29 08:50:24,646][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.8472821712493896, cross_entropy: 2.8472821712493896 +[2025-04-29 08:50:24,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 1.1074292659759521, cross_entropy: 1.1074292659759521 +[2025-04-29 08:50:27,760][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 0.8941596150398254, cross_entropy: 0.8941596150398254 +[2025-04-29 08:50:28,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 3.061892509460449, cross_entropy: 3.061892509460449 +[2025-04-29 08:50:31,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 1.9563957452774048, cross_entropy: 1.9563957452774048 +[2025-04-29 08:50:31,893][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.1026012897491455, cross_entropy: 1.1026012897491455 +[2025-04-29 08:50:35,404][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.0938165187835693, cross_entropy: 2.0938165187835693 +[2025-04-29 08:50:35,749][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 3.1208982467651367, cross_entropy: 3.1208982467651367 +[2025-04-29 08:50:39,242][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 1.7974591255187988, cross_entropy: 1.7974591255187988 +[2025-04-29 08:50:39,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 0.9597796201705933, cross_entropy: 0.9597796201705933 +[2025-04-29 08:50:42,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 2.3213729858398438, cross_entropy: 2.3213729858398438 +[2025-04-29 08:50:43,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 2.6977810859680176, cross_entropy: 2.6977810859680176 +[2025-04-29 08:50:46,327][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 1.0530835390090942, cross_entropy: 1.0530835390090942 +[2025-04-29 08:50:46,674][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.8620907068252563, cross_entropy: 1.8620907068252563 +[2025-04-29 08:50:50,179][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.3202638626098633, cross_entropy: 1.3202638626098633 +[2025-04-29 08:50:50,522][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 2.995069980621338, cross_entropy: 2.995069980621338 +[2025-04-29 08:50:53,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.070483684539795, cross_entropy: 1.070483684539795 +[2025-04-29 08:50:53,924][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.2096827030181885, cross_entropy: 1.2096827030181885 +[2025-04-29 08:50:56,888][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 0.9915398955345154, cross_entropy: 0.9915398955345154 +[2025-04-29 08:50:57,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.5685269832611084, cross_entropy: 1.5685269832611084 +[2025-04-29 08:51:00,155][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 1.1513144969940186, cross_entropy: 1.1513144969940186 +[2025-04-29 08:51:00,500][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 3.0897092819213867, cross_entropy: 3.0897092819213867 +[2025-04-29 08:51:03,571][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 1.0990360975265503, cross_entropy: 1.0990360975265503 +[2025-04-29 08:51:03,892][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 1.1903669834136963, cross_entropy: 1.1903669834136963 +[2025-04-29 08:51:06,966][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 2.3024539947509766, cross_entropy: 2.3024539947509766 +[2025-04-29 08:51:07,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 2.1925430297851562, cross_entropy: 2.1925430297851562 +[2025-04-29 08:51:09,833][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.1938968896865845, cross_entropy: 1.1938968896865845 +[2025-04-29 08:51:10,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 1.419177532196045, cross_entropy: 1.419177532196045 +[2025-04-29 08:51:13,966][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 2.3921403884887695, cross_entropy: 2.3921403884887695 +[2025-04-29 08:51:14,741][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.1787118911743164, cross_entropy: 1.1787118911743164 +[2025-04-29 08:51:17,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.3734307289123535, cross_entropy: 3.3734307289123535 +[2025-04-29 08:51:18,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 0.9687392115592957, cross_entropy: 0.9687392115592957 +[2025-04-29 08:51:20,934][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 1.0417205095291138, cross_entropy: 1.0417205095291138 +[2025-04-29 08:51:21,276][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 0.9237155914306641, cross_entropy: 0.9237155914306641 +[2025-04-29 08:51:24,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 1.6701202392578125, cross_entropy: 1.6701202392578125 +[2025-04-29 08:51:24,833][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.2516584396362305, cross_entropy: 1.2516584396362305 +[2025-04-29 08:51:28,530][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.417149543762207, cross_entropy: 1.417149543762207 +[2025-04-29 08:51:28,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.1187782287597656, cross_entropy: 1.1187782287597656 +[2025-04-29 08:51:31,795][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 2.986534833908081, cross_entropy: 2.986534833908081 +[2025-04-29 08:51:32,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.3637092113494873, cross_entropy: 1.3637092113494873 +[2025-04-29 08:51:35,320][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.8154518604278564, cross_entropy: 1.8154518604278564 +[2025-04-29 08:51:35,664][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.3187174797058105, cross_entropy: 1.3187174797058105 +[2025-04-29 08:51:39,033][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.9742343425750732, cross_entropy: 2.9742343425750732 +[2025-04-29 08:51:39,616][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.0813713073730469, cross_entropy: 1.0813713073730469 +[2025-04-29 08:51:42,304][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 1.1313011646270752, cross_entropy: 1.1313011646270752 +[2025-04-29 08:51:42,693][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 2.6420459747314453, cross_entropy: 2.6420459747314453 +[2025-04-29 08:51:45,410][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 2.6300365924835205, cross_entropy: 2.6300365924835205 +[2025-04-29 08:51:46,181][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 0.9420547485351562, cross_entropy: 0.9420547485351562 +[2025-04-29 08:51:48,955][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 1.1541353464126587, cross_entropy: 1.1541353464126587 +[2025-04-29 08:51:49,672][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 3.1210451126098633, cross_entropy: 3.1210451126098633 +[2025-04-29 08:51:52,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 1.491652250289917, cross_entropy: 1.491652250289917 +[2025-04-29 08:51:53,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 3.0826239585876465, cross_entropy: 3.0826239585876465 +[2025-04-29 08:51:56,386][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 3.314685821533203, cross_entropy: 3.314685821533203 +[2025-04-29 08:51:57,057][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 2.4795026779174805, cross_entropy: 2.4795026779174805 +[2025-04-29 08:52:00,096][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 2.9360857009887695, cross_entropy: 2.9360857009887695 +[2025-04-29 08:52:00,599][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.4335227012634277, cross_entropy: 2.4335227012634277 +[2025-04-29 08:52:03,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 0.7832712531089783, cross_entropy: 0.7832712531089783 +[2025-04-29 08:52:04,338][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 2.995431423187256, cross_entropy: 2.995431423187256 +[2025-04-29 08:52:07,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.430807590484619, cross_entropy: 2.430807590484619 +[2025-04-29 08:52:08,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 1.234403371810913, cross_entropy: 1.234403371810913 +[2025-04-29 08:52:10,888][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 1.390557050704956, cross_entropy: 1.390557050704956 +[2025-04-29 08:52:12,775][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 1.090285062789917, cross_entropy: 1.090285062789917 +[2025-04-29 08:52:14,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 2.1111795902252197, cross_entropy: 2.1111795902252197 +[2025-04-29 08:52:16,031][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 1.0470342636108398, cross_entropy: 1.0470342636108398 +[2025-04-29 08:52:18,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 2.034273386001587, cross_entropy: 2.034273386001587 +[2025-04-29 08:52:19,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 1.0016682147979736, cross_entropy: 1.0016682147979736 +[2025-04-29 08:52:21,589][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 3.3074581623077393, cross_entropy: 3.3074581623077393 +[2025-04-29 08:52:23,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 2.878850221633911, cross_entropy: 2.878850221633911 +[2025-04-29 08:52:25,005][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 1.3746049404144287, cross_entropy: 1.3746049404144287 +[2025-04-29 08:52:27,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 2.546785354614258, cross_entropy: 2.546785354614258 +[2025-04-29 08:52:28,055][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.3999313116073608, cross_entropy: 1.3999313116073608 +[2025-04-29 08:52:31,427][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 2.829446315765381, cross_entropy: 2.829446315765381 +[2025-04-29 08:52:31,904][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.1561672687530518, cross_entropy: 1.1561672687530518 +[2025-04-29 08:52:35,215][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.5129261016845703, cross_entropy: 1.5129261016845703 +[2025-04-29 08:52:35,618][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 3.4829769134521484, cross_entropy: 3.4829769134521484 +[2025-04-29 08:52:38,626][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 1.2102458477020264, cross_entropy: 1.2102458477020264 +[2025-04-29 08:52:40,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.3616113662719727, cross_entropy: 2.3616113662719727 +[2025-04-29 08:52:42,673][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 1.5509095191955566, cross_entropy: 1.5509095191955566 +[2025-04-29 08:52:43,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 1.421149730682373, cross_entropy: 1.421149730682373 +[2025-04-29 08:52:46,117][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 3.101443290710449, cross_entropy: 3.101443290710449 +[2025-04-29 08:52:46,857][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 1.1120564937591553, cross_entropy: 1.1120564937591553 +[2025-04-29 08:52:50,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.0382649898529053, cross_entropy: 1.0382649898529053 +[2025-04-29 08:52:50,460][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.331924557685852, cross_entropy: 1.331924557685852 +[2025-04-29 08:52:53,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 3.2216811180114746, cross_entropy: 3.2216811180114746 +[2025-04-29 08:52:53,902][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.830995559692383, cross_entropy: 2.830995559692383 +[2025-04-29 08:52:57,073][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 2.442786455154419, cross_entropy: 2.442786455154419 +[2025-04-29 08:52:57,387][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 1.2906818389892578, cross_entropy: 1.2906818389892578 +[2025-04-29 08:53:01,057][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 1.4649543762207031, cross_entropy: 1.4649543762207031 +[2025-04-29 08:53:01,403][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 2.423046112060547, cross_entropy: 2.423046112060547 +[2025-04-29 08:53:04,634][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.6838841438293457, cross_entropy: 1.6838841438293457 +[2025-04-29 08:53:04,977][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 1.5181727409362793, cross_entropy: 1.5181727409362793 +[2025-04-29 08:53:08,488][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 2.3723063468933105, cross_entropy: 2.3723063468933105 +[2025-04-29 08:53:08,825][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 1.3935730457305908, cross_entropy: 1.3935730457305908 +[2025-04-29 08:53:11,960][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 2.826658010482788, cross_entropy: 2.826658010482788 +[2025-04-29 08:53:12,303][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.58351993560791, cross_entropy: 2.58351993560791 +[2025-04-29 08:53:15,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 1.1755175590515137, cross_entropy: 1.1755175590515137 +[2025-04-29 08:53:15,651][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 2.0534164905548096, cross_entropy: 2.0534164905548096 +[2025-04-29 08:53:18,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 1.3514611721038818, cross_entropy: 1.3514611721038818 +[2025-04-29 08:53:18,848][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 2.6368179321289062, cross_entropy: 2.6368179321289062 +[2025-04-29 08:53:22,033][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.1678732633590698, cross_entropy: 1.1678732633590698 +[2025-04-29 08:53:22,347][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 1.4704493284225464, cross_entropy: 1.4704493284225464 +[2025-04-29 08:53:25,819][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.8553060293197632, cross_entropy: 1.8553060293197632 +[2025-04-29 08:53:26,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 2.9657835960388184, cross_entropy: 2.9657835960388184 +[2025-04-29 08:53:30,417][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 2.955517292022705, cross_entropy: 2.955517292022705 +[2025-04-29 08:53:30,746][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 1.2748669385910034, cross_entropy: 1.2748669385910034 +[2025-04-29 08:53:34,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 1.5213578939437866, cross_entropy: 1.5213578939437866 +[2025-04-29 08:53:34,426][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.263559341430664, cross_entropy: 1.263559341430664 +[2025-04-29 08:53:37,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 2.1121695041656494, cross_entropy: 2.1121695041656494 +[2025-04-29 08:53:37,927][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 3.1078038215637207, cross_entropy: 3.1078038215637207 +[2025-04-29 08:53:41,123][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 3.203484058380127, cross_entropy: 3.203484058380127 +[2025-04-29 08:53:41,464][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 1.4118552207946777, cross_entropy: 1.4118552207946777 +[2025-04-29 08:53:45,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.1265618801116943, cross_entropy: 1.1265618801116943 +[2025-04-29 08:53:45,522][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 2.361421585083008, cross_entropy: 2.361421585083008 +[2025-04-29 08:53:48,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.0220096111297607, cross_entropy: 2.0220096111297607 +[2025-04-29 08:53:49,251][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 3.0628342628479004, cross_entropy: 3.0628342628479004 +[2025-04-29 08:53:52,441][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 2.4577255249023438, cross_entropy: 2.4577255249023438 +[2025-04-29 08:53:52,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 1.2494103908538818, cross_entropy: 1.2494103908538818 +[2025-04-29 08:53:56,277][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.7787132263183594, cross_entropy: 2.7787132263183594 +[2025-04-29 08:53:56,622][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 3.016958236694336, cross_entropy: 3.016958236694336 +[2025-04-29 08:53:59,816][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 1.7701821327209473, cross_entropy: 1.7701821327209473 +[2025-04-29 08:54:00,158][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 2.64330792427063, cross_entropy: 2.64330792427063 +[2025-04-29 08:54:03,586][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 2.632946491241455, cross_entropy: 2.632946491241455 +[2025-04-29 08:54:03,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.7446798086166382, cross_entropy: 1.7446798086166382 +[2025-04-29 08:54:07,078][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.9378881454467773, cross_entropy: 2.9378881454467773 +[2025-04-29 08:54:07,421][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.368513584136963, cross_entropy: 1.368513584136963 +[2025-04-29 08:54:11,555][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 2.1010706424713135, cross_entropy: 2.1010706424713135 +[2025-04-29 08:54:11,902][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.515451669692993, cross_entropy: 2.515451669692993 +[2025-04-29 08:54:15,546][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.448516845703125, cross_entropy: 2.448516845703125 +[2025-04-29 08:54:15,864][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 2.2934746742248535, cross_entropy: 2.2934746742248535 +[2025-04-29 08:54:19,107][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 1.86251962184906, cross_entropy: 1.86251962184906 +[2025-04-29 08:54:19,428][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 2.777299404144287, cross_entropy: 2.777299404144287 +[2025-04-29 08:54:22,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 0.9023520946502686, cross_entropy: 0.9023520946502686 +[2025-04-29 08:54:23,185][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 1.5741971731185913, cross_entropy: 1.5741971731185913 +[2025-04-29 08:54:26,663][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 1.542846918106079, cross_entropy: 1.542846918106079 +[2025-04-29 08:54:27,004][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 2.9636738300323486, cross_entropy: 2.9636738300323486 +[2025-04-29 08:54:30,243][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 1.5118740797042847, cross_entropy: 1.5118740797042847 +[2025-04-29 08:54:30,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 1.2762714624404907, cross_entropy: 1.2762714624404907 +[2025-04-29 08:54:34,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.8189283609390259, cross_entropy: 1.8189283609390259 +[2025-04-29 08:54:34,464][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 2.349184513092041, cross_entropy: 2.349184513092041 +[2025-04-29 08:54:38,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 1.5308947563171387, cross_entropy: 1.5308947563171387 +[2025-04-29 08:54:38,405][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.574065685272217, cross_entropy: 2.574065685272217 +[2025-04-29 08:54:41,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 1.5089865922927856, cross_entropy: 1.5089865922927856 +[2025-04-29 08:54:41,972][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 2.420790672302246, cross_entropy: 2.420790672302246 +[2025-04-29 08:54:45,385][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.4224853515625, cross_entropy: 1.4224853515625 +[2025-04-29 08:54:45,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 2.0278940200805664, cross_entropy: 2.0278940200805664 +[2025-04-29 08:54:49,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.3350012302398682, cross_entropy: 1.3350012302398682 +[2025-04-29 08:54:49,406][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.3628408908843994, cross_entropy: 1.3628408908843994 +[2025-04-29 08:54:52,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 2.0407180786132812, cross_entropy: 2.0407180786132812 +[2025-04-29 08:54:52,628][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 3.0684475898742676, cross_entropy: 3.0684475898742676 +[2025-04-29 08:54:55,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 1.6690757274627686, cross_entropy: 1.6690757274627686 +[2025-04-29 08:54:55,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 2.90952730178833, cross_entropy: 2.90952730178833 +[2025-04-29 08:54:58,571][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 2.4354727268218994, cross_entropy: 2.4354727268218994 +[2025-04-29 08:54:58,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.2146188020706177, cross_entropy: 1.2146188020706177 +[2025-04-29 08:55:02,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 1.134340524673462, cross_entropy: 1.134340524673462 +[2025-04-29 08:55:02,626][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 1.1273971796035767, cross_entropy: 1.1273971796035767 +[2025-04-29 08:55:06,022][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.9364475011825562, cross_entropy: 1.9364475011825562 +[2025-04-29 08:55:06,338][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 1.3042569160461426, cross_entropy: 1.3042569160461426 +[2025-04-29 08:55:09,947][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 3.010018825531006, cross_entropy: 3.010018825531006 +[2025-04-29 08:55:10,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 1.5809701681137085, cross_entropy: 1.5809701681137085 +[2025-04-29 08:55:13,600][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 2.1337227821350098, cross_entropy: 2.1337227821350098 +[2025-04-29 08:55:13,940][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 3.1003003120422363, cross_entropy: 3.1003003120422363 +[2025-04-29 08:55:18,129][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.734158992767334, cross_entropy: 1.734158992767334 +[2025-04-29 08:55:18,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.2888271808624268, cross_entropy: 1.2888271808624268 +[2025-04-29 08:55:21,600][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 2.327754497528076, cross_entropy: 2.327754497528076 +[2025-04-29 08:55:21,946][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.2792408466339111, cross_entropy: 1.2792408466339111 +[2025-04-29 08:55:25,274][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 1.3666582107543945, cross_entropy: 1.3666582107543945 +[2025-04-29 08:55:25,621][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 2.9332356452941895, cross_entropy: 2.9332356452941895 +[2025-04-29 08:55:29,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 0.6945275664329529, cross_entropy: 0.6945275664329529 +[2025-04-29 08:55:30,196][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.306236982345581, cross_entropy: 1.306236982345581 +[2025-04-29 08:55:33,229][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.9462488889694214, cross_entropy: 1.9462488889694214 +[2025-04-29 08:55:33,570][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 0.9894881248474121, cross_entropy: 0.9894881248474121 +[2025-04-29 08:55:36,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 2.5881576538085938, cross_entropy: 2.5881576538085938 +[2025-04-29 08:55:36,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 0.867089033126831, cross_entropy: 0.867089033126831 +[2025-04-29 08:55:40,593][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 3.011709690093994, cross_entropy: 3.011709690093994 +[2025-04-29 08:55:40,939][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 1.4179456233978271, cross_entropy: 1.4179456233978271 +[2025-04-29 08:55:44,737][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 2.8114266395568848, cross_entropy: 2.8114266395568848 +[2025-04-29 08:55:45,084][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 2.788663387298584, cross_entropy: 2.788663387298584 +[2025-04-29 08:55:48,159][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.076137065887451, cross_entropy: 2.076137065887451 +[2025-04-29 08:55:48,538][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 1.563570261001587, cross_entropy: 1.563570261001587 +[2025-04-29 08:55:51,913][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.603731155395508, cross_entropy: 2.603731155395508 +[2025-04-29 08:55:52,233][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 0.8411325812339783, cross_entropy: 0.8411325812339783 +[2025-04-29 08:55:55,792][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 1.7761106491088867, cross_entropy: 1.7761106491088867 +[2025-04-29 08:55:56,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 3.2291455268859863, cross_entropy: 3.2291455268859863 +[2025-04-29 08:55:58,845][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 3.1899304389953613, cross_entropy: 3.1899304389953613 +[2025-04-29 08:55:59,190][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.372394323348999, cross_entropy: 1.372394323348999 +[2025-04-29 08:56:02,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 2.6540913581848145, cross_entropy: 2.6540913581848145 +[2025-04-29 08:56:02,632][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 2.355943202972412, cross_entropy: 2.355943202972412 +[2025-04-29 08:56:05,411][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.4170901775360107, cross_entropy: 2.4170901775360107 +[2025-04-29 08:56:05,754][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 3.017263650894165, cross_entropy: 3.017263650894165 +[2025-04-29 08:56:08,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 1.6418988704681396, cross_entropy: 1.6418988704681396 +[2025-04-29 08:56:09,039][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.6000816822052002, cross_entropy: 1.6000816822052002 +[2025-04-29 08:56:12,915][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 3.053095579147339, cross_entropy: 3.053095579147339 +[2025-04-29 08:56:13,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 3.227874517440796, cross_entropy: 3.227874517440796 +[2025-04-29 08:56:16,398][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.7051868438720703, cross_entropy: 2.7051868438720703 +[2025-04-29 08:56:16,898][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.2873752117156982, cross_entropy: 1.2873752117156982 +[2025-04-29 08:56:20,104][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 2.960331678390503, cross_entropy: 2.960331678390503 +[2025-04-29 08:56:20,458][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 1.8850312232971191, cross_entropy: 1.8850312232971191 +[2025-04-29 08:56:23,539][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 1.9085562229156494, cross_entropy: 1.9085562229156494 +[2025-04-29 08:56:24,404][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.018805980682373, cross_entropy: 2.018805980682373 +[2025-04-29 08:56:27,341][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.4905320405960083, cross_entropy: 1.4905320405960083 +[2025-04-29 08:56:27,773][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 2.4867615699768066, cross_entropy: 2.4867615699768066 +[2025-04-29 08:56:31,032][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.999638557434082, cross_entropy: 1.999638557434082 +[2025-04-29 08:56:31,384][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 2.721001148223877, cross_entropy: 2.721001148223877 +[2025-04-29 08:56:34,402][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.0778815746307373, cross_entropy: 2.0778815746307373 +[2025-04-29 08:56:35,302][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 2.8095450401306152, cross_entropy: 2.8095450401306152 +[2025-04-29 08:56:37,545][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.940798282623291, cross_entropy: 2.940798282623291 +[2025-04-29 08:56:39,141][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 2.8147263526916504, cross_entropy: 2.8147263526916504 +[2025-04-29 08:56:41,147][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 0.8609819412231445, cross_entropy: 0.8609819412231445 +[2025-04-29 08:56:43,515][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 1.8004517555236816, cross_entropy: 1.8004517555236816 +[2025-04-29 08:56:44,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.6800600290298462, cross_entropy: 1.6800600290298462 +[2025-04-29 08:56:48,070][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.250864028930664, cross_entropy: 2.250864028930664 +[2025-04-29 08:56:48,388][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 0.9632516503334045, cross_entropy: 0.9632516503334045 +[2025-04-29 08:56:51,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 1.5899600982666016, cross_entropy: 1.5899600982666016 +[2025-04-29 08:56:51,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 1.0857068300247192, cross_entropy: 1.0857068300247192 +[2025-04-29 08:56:54,940][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 2.547269582748413, cross_entropy: 2.547269582748413 +[2025-04-29 08:56:55,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.4260778427124023, cross_entropy: 3.4260778427124023 +[2025-04-29 08:56:58,546][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.5738625526428223, cross_entropy: 2.5738625526428223 +[2025-04-29 08:56:59,225][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 1.797562837600708, cross_entropy: 1.797562837600708 +[2025-04-29 08:57:01,879][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 2.2352042198181152, cross_entropy: 2.2352042198181152 +[2025-04-29 08:57:02,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.6392558813095093, cross_entropy: 1.6392558813095093 +[2025-04-29 08:57:05,625][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 2.5111589431762695, cross_entropy: 2.5111589431762695 +[2025-04-29 08:57:06,100][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 1.4391285181045532, cross_entropy: 1.4391285181045532 +[2025-04-29 08:57:09,256][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 2.6470494270324707, cross_entropy: 2.6470494270324707 +[2025-04-29 08:57:09,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.256943464279175, cross_entropy: 2.256943464279175 +[2025-04-29 08:57:12,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.879331350326538, cross_entropy: 1.879331350326538 +[2025-04-29 08:57:13,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 2.672031879425049, cross_entropy: 2.672031879425049 +[2025-04-29 08:57:16,452][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 1.9609653949737549, cross_entropy: 1.9609653949737549 +[2025-04-29 08:57:16,814][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.3146772384643555, cross_entropy: 2.3146772384643555 +[2025-04-29 08:57:19,382][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.6937355995178223, cross_entropy: 2.6937355995178223 +[2025-04-29 08:57:20,080][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 2.823545217514038, cross_entropy: 2.823545217514038 +[2025-04-29 08:57:22,973][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 2.551690101623535, cross_entropy: 2.551690101623535 +[2025-04-29 08:57:23,440][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 3.332599639892578, cross_entropy: 3.332599639892578 +[2025-04-29 08:57:26,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.8434603214263916, cross_entropy: 1.8434603214263916 +[2025-04-29 08:57:28,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.3916821479797363, cross_entropy: 1.3916821479797363 +[2025-04-29 08:57:30,897][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.594251871109009, cross_entropy: 2.594251871109009 +[2025-04-29 08:57:31,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.4596514701843262, cross_entropy: 1.4596514701843262 +[2025-04-29 08:57:34,941][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 1.9845306873321533, cross_entropy: 1.9845306873321533 +[2025-04-29 08:57:35,313][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 2.7573578357696533, cross_entropy: 2.7573578357696533 +[2025-04-29 08:57:38,921][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 1.2219301462173462, cross_entropy: 1.2219301462173462 +[2025-04-29 08:57:39,261][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 0.8994184732437134, cross_entropy: 0.8994184732437134 +[2025-04-29 08:57:42,955][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 3.036846399307251, cross_entropy: 3.036846399307251 +[2025-04-29 08:57:43,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 0.8573911190032959, cross_entropy: 0.8573911190032959 +[2025-04-29 08:57:46,505][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 2.242898941040039, cross_entropy: 2.242898941040039 +[2025-04-29 08:57:46,850][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 3.116746425628662, cross_entropy: 3.116746425628662 +[2025-04-29 08:57:50,227][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 1.0962460041046143, cross_entropy: 1.0962460041046143 +[2025-04-29 08:57:50,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.158608913421631, cross_entropy: 3.158608913421631 +[2025-04-29 08:57:53,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 3.174739360809326, cross_entropy: 3.174739360809326 +[2025-04-29 08:57:53,548][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.4055416584014893, cross_entropy: 2.4055416584014893 +[2025-04-29 08:57:57,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 1.3338279724121094, cross_entropy: 1.3338279724121094 +[2025-04-29 08:57:58,003][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 2.0521466732025146, cross_entropy: 2.0521466732025146 +[2025-04-29 08:58:01,303][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 0.9841045141220093, cross_entropy: 0.9841045141220093 +[2025-04-29 08:58:01,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.1695010662078857, cross_entropy: 1.1695010662078857 +[2025-04-29 08:58:05,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 3.0490686893463135, cross_entropy: 3.0490686893463135 +[2025-04-29 08:58:05,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.6822028160095215, cross_entropy: 1.6822028160095215 +[2025-04-29 08:58:08,717][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 2.5828590393066406, cross_entropy: 2.5828590393066406 +[2025-04-29 08:58:09,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.4101383686065674, cross_entropy: 1.4101383686065674 +[2025-04-29 08:58:11,764][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 1.1735979318618774, cross_entropy: 1.1735979318618774 +[2025-04-29 08:58:12,880][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 1.0922566652297974, cross_entropy: 1.0922566652297974 +[2025-04-29 08:58:15,069][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.0057694911956787, cross_entropy: 3.0057694911956787 +[2025-04-29 08:58:16,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 1.6677380800247192, cross_entropy: 1.6677380800247192 +[2025-04-29 08:58:18,791][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.9901280403137207, cross_entropy: 2.9901280403137207 +[2025-04-29 08:58:20,641][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 1.1608576774597168, cross_entropy: 1.1608576774597168 +[2025-04-29 08:58:22,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 1.4362783432006836, cross_entropy: 1.4362783432006836 +[2025-04-29 08:58:23,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 2.900146484375, cross_entropy: 2.900146484375 +[2025-04-29 08:58:26,899][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 3.3192734718322754, cross_entropy: 3.3192734718322754 +[2025-04-29 08:58:27,241][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.9118716716766357, cross_entropy: 1.9118716716766357 +[2025-04-29 08:58:30,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 0.9182772636413574, cross_entropy: 0.9182772636413574 +[2025-04-29 08:58:30,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 1.432214617729187, cross_entropy: 1.432214617729187 +[2025-04-29 08:58:33,965][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.9109723567962646, cross_entropy: 2.9109723567962646 +[2025-04-29 08:58:34,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 3.120981216430664, cross_entropy: 3.120981216430664 +[2025-04-29 08:58:38,094][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.2286901473999023, cross_entropy: 2.2286901473999023 +[2025-04-29 08:58:38,439][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 3.0573017597198486, cross_entropy: 3.0573017597198486 +[2025-04-29 08:58:41,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 2.9815802574157715, cross_entropy: 2.9815802574157715 +[2025-04-29 08:58:41,617][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.5196516513824463, cross_entropy: 1.5196516513824463 +[2025-04-29 08:58:45,460][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 0.8631226420402527, cross_entropy: 0.8631226420402527 +[2025-04-29 08:58:45,806][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 0.8197514414787292, cross_entropy: 0.8197514414787292 +[2025-04-29 08:58:48,650][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.4002326726913452, cross_entropy: 1.4002326726913452 +[2025-04-29 08:58:48,991][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 0.8212718963623047, cross_entropy: 0.8212718963623047 +[2025-04-29 08:58:51,702][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 2.960829734802246, cross_entropy: 2.960829734802246 +[2025-04-29 08:58:52,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 0.9591166973114014, cross_entropy: 0.9591166973114014 +[2025-04-29 08:58:54,943][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 2.7322793006896973, cross_entropy: 2.7322793006896973 +[2025-04-29 08:58:55,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 2.2790632247924805, cross_entropy: 2.2790632247924805 +[2025-04-29 08:58:58,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.8671748638153076, cross_entropy: 1.8671748638153076 +[2025-04-29 08:58:59,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.014291763305664, cross_entropy: 2.014291763305664 +[2025-04-29 08:59:02,764][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 2.7922892570495605, cross_entropy: 2.7922892570495605 +[2025-04-29 08:59:03,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.6466513872146606, cross_entropy: 1.6466513872146606 +[2025-04-29 08:59:06,571][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 2.251232624053955, cross_entropy: 2.251232624053955 +[2025-04-29 08:59:07,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 2.9781856536865234, cross_entropy: 2.9781856536865234 +[2025-04-29 08:59:10,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 3.258267402648926, cross_entropy: 3.258267402648926 +[2025-04-29 08:59:10,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.2394053936004639, cross_entropy: 1.2394053936004639 +[2025-04-29 08:59:13,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.6250286102294922, cross_entropy: 1.6250286102294922 +[2025-04-29 08:59:14,292][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.9238255023956299, cross_entropy: 1.9238255023956299 +[2025-04-29 08:59:17,970][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 1.1136806011199951, cross_entropy: 1.1136806011199951 +[2025-04-29 08:59:18,317][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.906196355819702, cross_entropy: 2.906196355819702 +[2025-04-29 08:59:21,409][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 3.2036805152893066, cross_entropy: 3.2036805152893066 +[2025-04-29 08:59:21,755][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 2.526707649230957, cross_entropy: 2.526707649230957 +[2025-04-29 08:59:24,768][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 1.197281002998352, cross_entropy: 1.197281002998352 +[2025-04-29 08:59:25,083][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 1.4475533962249756, cross_entropy: 1.4475533962249756 +[2025-04-29 08:59:29,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 3.111929178237915, cross_entropy: 3.111929178237915 +[2025-04-29 08:59:29,686][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.0278843641281128, cross_entropy: 1.0278843641281128 +[2025-04-29 08:59:32,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 2.2197444438934326, cross_entropy: 2.2197444438934326 +[2025-04-29 08:59:33,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 3.0295603275299072, cross_entropy: 3.0295603275299072 +[2025-04-29 08:59:37,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.2548233270645142, cross_entropy: 1.2548233270645142 +[2025-04-29 08:59:37,480][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 1.0711863040924072, cross_entropy: 1.0711863040924072 +[2025-04-29 08:59:41,707][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.2015446424484253, cross_entropy: 1.2015446424484253 +[2025-04-29 08:59:42,054][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.914313316345215, cross_entropy: 2.914313316345215 +[2025-04-29 08:59:45,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 2.145573616027832, cross_entropy: 2.145573616027832 +[2025-04-29 08:59:45,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 3.031703472137451, cross_entropy: 3.031703472137451 +[2025-04-29 08:59:48,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.5356371402740479, cross_entropy: 1.5356371402740479 +[2025-04-29 08:59:48,631][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.21413516998291, cross_entropy: 2.21413516998291 +[2025-04-29 08:59:51,644][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 1.6313287019729614, cross_entropy: 1.6313287019729614 +[2025-04-29 08:59:51,988][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.7362862825393677, cross_entropy: 1.7362862825393677 +[2025-04-29 08:59:55,125][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 2.2763662338256836, cross_entropy: 2.2763662338256836 +[2025-04-29 08:59:55,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.1697487831115723, cross_entropy: 2.1697487831115723 +[2025-04-29 08:59:58,291][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.2475824356079102, cross_entropy: 1.2475824356079102 +[2025-04-29 08:59:58,671][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 2.512924909591675, cross_entropy: 2.512924909591675 +[2025-04-29 09:00:01,358][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 2.1061644554138184, cross_entropy: 2.1061644554138184 +[2025-04-29 09:00:02,078][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 1.344441533088684, cross_entropy: 1.344441533088684 +[2025-04-29 09:00:04,915][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.681074857711792, cross_entropy: 1.681074857711792 +[2025-04-29 09:00:06,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 1.9204012155532837, cross_entropy: 1.9204012155532837 +[2025-04-29 09:00:08,342][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 0.940571129322052, cross_entropy: 0.940571129322052 +[2025-04-29 09:00:10,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.4953064918518066, cross_entropy: 2.4953064918518066 +[2025-04-29 09:00:11,936][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 1.3669301271438599, cross_entropy: 1.3669301271438599 +[2025-04-29 09:00:14,508][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 1.1551728248596191, cross_entropy: 1.1551728248596191 +[2025-04-29 09:00:15,375][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.833873748779297, cross_entropy: 2.833873748779297 +[2025-04-29 09:00:17,769][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 1.1603851318359375, cross_entropy: 1.1603851318359375 +[2025-04-29 09:00:18,961][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.70783269405365, cross_entropy: 1.70783269405365 +[2025-04-29 09:00:21,780][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 3.2290682792663574, cross_entropy: 3.2290682792663574 +[2025-04-29 09:00:23,056][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.7800194025039673, cross_entropy: 1.7800194025039673 +[2025-04-29 09:00:25,017][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 2.8286540508270264, cross_entropy: 2.8286540508270264 +[2025-04-29 09:00:26,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.3331944942474365, cross_entropy: 2.3331944942474365 +[2025-04-29 09:00:28,252][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.3217082023620605, cross_entropy: 2.3217082023620605 +[2025-04-29 09:00:30,042][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 2.207153558731079, cross_entropy: 2.207153558731079 +[2025-04-29 09:00:31,650][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.0367989540100098, cross_entropy: 3.0367989540100098 +[2025-04-29 09:00:34,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.7444334030151367, cross_entropy: 2.7444334030151367 +[2025-04-29 09:00:35,490][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 0.9545222520828247, cross_entropy: 0.9545222520828247 +[2025-04-29 09:00:38,142][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.249756336212158, cross_entropy: 3.249756336212158 +[2025-04-29 09:00:38,763][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 2.3931360244750977, cross_entropy: 2.3931360244750977 +[2025-04-29 09:00:43,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.42289400100708, cross_entropy: 2.42289400100708 +[2025-04-29 09:00:43,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.5356132984161377, cross_entropy: 1.5356132984161377 +[2025-04-29 09:00:46,364][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 1.3768112659454346, cross_entropy: 1.3768112659454346 +[2025-04-29 09:00:46,689][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.9473512172698975, cross_entropy: 2.9473512172698975 +[2025-04-29 09:00:49,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.7502291202545166, cross_entropy: 1.7502291202545166 +[2025-04-29 09:00:49,828][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 3.085702896118164, cross_entropy: 3.085702896118164 +[2025-04-29 09:00:53,116][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.619290351867676, cross_entropy: 2.619290351867676 +[2025-04-29 09:00:53,458][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.1642390489578247, cross_entropy: 1.1642390489578247 +[2025-04-29 09:00:56,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.5128076076507568, cross_entropy: 1.5128076076507568 +[2025-04-29 09:00:57,373][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 2.612879991531372, cross_entropy: 2.612879991531372 +[2025-04-29 09:00:59,154][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 2.684206008911133, cross_entropy: 2.684206008911133 +[2025-04-29 09:01:00,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.0029412508010864, cross_entropy: 1.0029412508010864 +[2025-04-29 09:03:49,040][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.0153369903564453, cross_entropy: 2.0153369903564453 +[2025-04-29 09:03:49,040][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.3635411262512207, cross_entropy: 1.3635411262512207 +[2025-04-29 09:03:49,267][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 09:03:49,431][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch5.pth. +[2025-04-29 09:03:49,633][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 09:03:53,889][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 2.471857786178589, cross_entropy: 2.471857786178589 +[2025-04-29 09:03:54,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 2.5715978145599365, cross_entropy: 2.5715978145599365 +[2025-04-29 09:03:57,596][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 3.1128182411193848, cross_entropy: 3.1128182411193848 +[2025-04-29 09:03:58,372][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 3.3062169551849365, cross_entropy: 3.3062169551849365 +[2025-04-29 09:04:00,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 1.213781714439392, cross_entropy: 1.213781714439392 +[2025-04-29 09:04:02,128][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 1.4873826503753662, cross_entropy: 1.4873826503753662 +[2025-04-29 09:04:04,371][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 3.0125575065612793, cross_entropy: 3.0125575065612793 +[2025-04-29 09:04:05,690][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 2.6162662506103516, cross_entropy: 2.6162662506103516 +[2025-04-29 09:04:08,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.7913212776184082, cross_entropy: 1.7913212776184082 +[2025-04-29 09:04:09,819][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 1.1814906597137451, cross_entropy: 1.1814906597137451 +[2025-04-29 09:04:11,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.115297317504883, cross_entropy: 2.115297317504883 +[2025-04-29 09:04:13,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 0.9417426586151123, cross_entropy: 0.9417426586151123 +[2025-04-29 09:04:16,061][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 2.5543344020843506, cross_entropy: 2.5543344020843506 +[2025-04-29 09:04:17,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.1651434898376465, cross_entropy: 1.1651434898376465 +[2025-04-29 09:04:19,385][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 1.067680835723877, cross_entropy: 1.067680835723877 +[2025-04-29 09:04:21,081][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.994096279144287, cross_entropy: 2.994096279144287 +[2025-04-29 09:04:22,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.0104197263717651, cross_entropy: 1.0104197263717651 +[2025-04-29 09:04:24,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.1243276596069336, cross_entropy: 3.1243276596069336 +[2025-04-29 09:04:25,903][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.9490195512771606, cross_entropy: 1.9490195512771606 +[2025-04-29 09:04:29,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 2.317610263824463, cross_entropy: 2.317610263824463 +[2025-04-29 09:04:29,685][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 2.6229381561279297, cross_entropy: 2.6229381561279297 +[2025-04-29 09:04:32,560][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 0.9334399104118347, cross_entropy: 0.9334399104118347 +[2025-04-29 09:04:32,909][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 2.3737542629241943, cross_entropy: 2.3737542629241943 +[2025-04-29 09:04:35,758][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 1.1903328895568848, cross_entropy: 1.1903328895568848 +[2025-04-29 09:04:36,134][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 2.1627769470214844, cross_entropy: 2.1627769470214844 +[2025-04-29 09:04:38,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.3049094676971436, cross_entropy: 2.3049094676971436 +[2025-04-29 09:04:39,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 2.861016273498535, cross_entropy: 2.861016273498535 +[2025-04-29 09:04:42,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 1.2876408100128174, cross_entropy: 1.2876408100128174 +[2025-04-29 09:04:42,436][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.7577791213989258, cross_entropy: 1.7577791213989258 +[2025-04-29 09:04:45,107][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 1.3809703588485718, cross_entropy: 1.3809703588485718 +[2025-04-29 09:04:45,772][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 2.9430129528045654, cross_entropy: 2.9430129528045654 +[2025-04-29 09:04:48,382][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.9059596061706543, cross_entropy: 2.9059596061706543 +[2025-04-29 09:04:49,687][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 3.095608949661255, cross_entropy: 3.095608949661255 +[2025-04-29 09:04:51,854][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 3.044243812561035, cross_entropy: 3.044243812561035 +[2025-04-29 09:04:53,196][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.8295509815216064, cross_entropy: 2.8295509815216064 +[2025-04-29 09:04:55,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 2.97841739654541, cross_entropy: 2.97841739654541 +[2025-04-29 09:04:56,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 2.7791013717651367, cross_entropy: 2.7791013717651367 +[2025-04-29 09:05:00,295][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 3.090243339538574, cross_entropy: 3.090243339538574 +[2025-04-29 09:05:01,139][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 1.9150104522705078, cross_entropy: 1.9150104522705078 +[2025-04-29 09:05:03,249][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 2.1430881023406982, cross_entropy: 2.1430881023406982 +[2025-04-29 09:05:04,466][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 0.8213028907775879, cross_entropy: 0.8213028907775879 +[2025-04-29 09:05:06,019][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.857860803604126, cross_entropy: 2.857860803604126 +[2025-04-29 09:05:07,995][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.0447195768356323, cross_entropy: 1.0447195768356323 +[2025-04-29 09:05:09,158][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 1.6318848133087158, cross_entropy: 1.6318848133087158 +[2025-04-29 09:05:11,246][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 1.163161277770996, cross_entropy: 1.163161277770996 +[2025-04-29 09:05:12,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 1.325845718383789, cross_entropy: 1.325845718383789 +[2025-04-29 09:05:14,962][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 1.1780641078948975, cross_entropy: 1.1780641078948975 +[2025-04-29 09:05:16,393][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 2.909776210784912, cross_entropy: 2.909776210784912 +[2025-04-29 09:05:19,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 2.2620413303375244, cross_entropy: 2.2620413303375244 +[2025-04-29 09:05:19,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.9312232732772827, cross_entropy: 1.9312232732772827 +[2025-04-29 09:05:23,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 2.615145683288574, cross_entropy: 2.615145683288574 +[2025-04-29 09:05:23,529][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 1.5182876586914062, cross_entropy: 1.5182876586914062 +[2025-04-29 09:05:26,810][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 1.9858989715576172, cross_entropy: 1.9858989715576172 +[2025-04-29 09:05:27,493][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.2993807792663574, cross_entropy: 1.2993807792663574 +[2025-04-29 09:05:30,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 2.0714807510375977, cross_entropy: 2.0714807510375977 +[2025-04-29 09:05:31,357][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 2.512085437774658, cross_entropy: 2.512085437774658 +[2025-04-29 09:05:34,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 1.2343225479125977, cross_entropy: 1.2343225479125977 +[2025-04-29 09:05:34,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 2.9134793281555176, cross_entropy: 2.9134793281555176 +[2025-04-29 09:05:37,814][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 1.4156863689422607, cross_entropy: 1.4156863689422607 +[2025-04-29 09:05:38,125][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 1.3641421794891357, cross_entropy: 1.3641421794891357 +[2025-04-29 09:05:41,305][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 1.1166422367095947, cross_entropy: 1.1166422367095947 +[2025-04-29 09:05:41,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 3.3699207305908203, cross_entropy: 3.3699207305908203 +[2025-04-29 09:05:44,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 2.7277138233184814, cross_entropy: 2.7277138233184814 +[2025-04-29 09:05:44,747][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 0.8664556741714478, cross_entropy: 0.8664556741714478 +[2025-04-29 09:05:48,098][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 1.0935535430908203, cross_entropy: 1.0935535430908203 +[2025-04-29 09:05:48,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.4804482460021973, cross_entropy: 2.4804482460021973 +[2025-04-29 09:05:50,924][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 3.232548952102661, cross_entropy: 3.232548952102661 +[2025-04-29 09:05:51,450][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 2.1588923931121826, cross_entropy: 2.1588923931121826 +[2025-04-29 09:05:54,210][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 0.946229100227356, cross_entropy: 0.946229100227356 +[2025-04-29 09:05:54,657][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 2.138340950012207, cross_entropy: 2.138340950012207 +[2025-04-29 09:05:58,084][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 1.9604666233062744, cross_entropy: 1.9604666233062744 +[2025-04-29 09:05:58,401][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 2.8552989959716797, cross_entropy: 2.8552989959716797 +[2025-04-29 09:06:01,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 3.0384745597839355, cross_entropy: 3.0384745597839355 +[2025-04-29 09:06:02,099][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.0427110195159912, cross_entropy: 1.0427110195159912 +[2025-04-29 09:06:05,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 2.3454716205596924, cross_entropy: 2.3454716205596924 +[2025-04-29 09:06:05,703][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.463532567024231, cross_entropy: 1.463532567024231 +[2025-04-29 09:06:08,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.0821542739868164, cross_entropy: 2.0821542739868164 +[2025-04-29 09:06:08,952][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.274914264678955, cross_entropy: 2.274914264678955 +[2025-04-29 09:06:11,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 0.8799079656600952, cross_entropy: 0.8799079656600952 +[2025-04-29 09:06:12,305][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 0.9414734244346619, cross_entropy: 0.9414734244346619 +[2025-04-29 09:06:14,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 3.061652183532715, cross_entropy: 3.061652183532715 +[2025-04-29 09:06:15,395][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 0.9317405223846436, cross_entropy: 0.9317405223846436 +[2025-04-29 09:06:18,159][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.525038242340088, cross_entropy: 2.525038242340088 +[2025-04-29 09:06:18,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 0.895711362361908, cross_entropy: 0.895711362361908 +[2025-04-29 09:06:22,044][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 2.5343000888824463, cross_entropy: 2.5343000888824463 +[2025-04-29 09:06:22,383][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.679762363433838, cross_entropy: 2.679762363433838 +[2025-04-29 09:06:27,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 2.9032721519470215, cross_entropy: 2.9032721519470215 +[2025-04-29 09:06:27,446][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.4047795534133911, cross_entropy: 1.4047795534133911 +[2025-04-29 09:06:31,058][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.1035284996032715, cross_entropy: 1.1035284996032715 +[2025-04-29 09:06:31,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.753920078277588, cross_entropy: 1.753920078277588 +[2025-04-29 09:06:34,498][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.876950263977051, cross_entropy: 2.876950263977051 +[2025-04-29 09:06:34,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 3.0084376335144043, cross_entropy: 3.0084376335144043 +[2025-04-29 09:06:37,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 3.073152542114258, cross_entropy: 3.073152542114258 +[2025-04-29 09:06:38,114][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 1.1139776706695557, cross_entropy: 1.1139776706695557 +[2025-04-29 09:06:41,702][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 1.1255724430084229, cross_entropy: 1.1255724430084229 +[2025-04-29 09:06:42,014][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.451453685760498, cross_entropy: 1.451453685760498 +[2025-04-29 09:06:44,762][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 0.890079140663147, cross_entropy: 0.890079140663147 +[2025-04-29 09:06:45,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.0189118385314941, cross_entropy: 1.0189118385314941 +[2025-04-29 09:06:48,299][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.927511215209961, cross_entropy: 1.927511215209961 +[2025-04-29 09:06:48,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 0.9386891722679138, cross_entropy: 0.9386891722679138 +[2025-04-29 09:06:51,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.024158000946045, cross_entropy: 1.024158000946045 +[2025-04-29 09:06:53,572][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.9548048973083496, cross_entropy: 2.9548048973083496 +[2025-04-29 09:06:55,654][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 2.9234964847564697, cross_entropy: 2.9234964847564697 +[2025-04-29 09:06:56,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 2.813997745513916, cross_entropy: 2.813997745513916 +[2025-04-29 09:06:58,978][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.1793410778045654, cross_entropy: 1.1793410778045654 +[2025-04-29 09:07:00,139][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 1.2885949611663818, cross_entropy: 1.2885949611663818 +[2025-04-29 09:07:02,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 1.3228634595870972, cross_entropy: 1.3228634595870972 +[2025-04-29 09:07:03,867][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.6525909900665283, cross_entropy: 1.6525909900665283 +[2025-04-29 09:07:06,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 2.4914305210113525, cross_entropy: 2.4914305210113525 +[2025-04-29 09:07:07,824][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 2.062028646469116, cross_entropy: 2.062028646469116 +[2025-04-29 09:07:11,384][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.2993972301483154, cross_entropy: 1.2993972301483154 +[2025-04-29 09:07:11,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 0.7780797481536865, cross_entropy: 0.7780797481536865 +[2025-04-29 09:07:15,114][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 0.8550974130630493, cross_entropy: 0.8550974130630493 +[2025-04-29 09:07:15,454][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 3.125039577484131, cross_entropy: 3.125039577484131 +[2025-04-29 09:07:18,477][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 1.5902743339538574, cross_entropy: 1.5902743339538574 +[2025-04-29 09:07:18,816][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 2.9348185062408447, cross_entropy: 2.9348185062408447 +[2025-04-29 09:07:22,570][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 0.9059799313545227, cross_entropy: 0.9059799313545227 +[2025-04-29 09:07:22,909][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 1.1417078971862793, cross_entropy: 1.1417078971862793 +[2025-04-29 09:07:25,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 2.3778324127197266, cross_entropy: 2.3778324127197266 +[2025-04-29 09:07:26,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.0012506246566772, cross_entropy: 1.0012506246566772 +[2025-04-29 09:07:28,638][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 3.3096084594726562, cross_entropy: 3.3096084594726562 +[2025-04-29 09:07:28,966][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.2414724826812744, cross_entropy: 1.2414724826812744 +[2025-04-29 09:07:31,752][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.0191130638122559, cross_entropy: 1.0191130638122559 +[2025-04-29 09:07:32,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 0.6910333037376404, cross_entropy: 0.6910333037376404 +[2025-04-29 09:07:34,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.569411277770996, cross_entropy: 1.569411277770996 +[2025-04-29 09:07:35,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 3.3386075496673584, cross_entropy: 3.3386075496673584 +[2025-04-29 09:07:38,177][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.0816102027893066, cross_entropy: 1.0816102027893066 +[2025-04-29 09:07:38,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 0.9024271368980408, cross_entropy: 0.9024271368980408 +[2025-04-29 09:07:41,554][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 2.6271562576293945, cross_entropy: 2.6271562576293945 +[2025-04-29 09:07:41,937][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 0.8469736576080322, cross_entropy: 0.8469736576080322 +[2025-04-29 09:07:44,962][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.562772750854492, cross_entropy: 2.562772750854492 +[2025-04-29 09:07:45,300][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.6488429307937622, cross_entropy: 1.6488429307937622 +[2025-04-29 09:07:48,134][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 2.01065993309021, cross_entropy: 2.01065993309021 +[2025-04-29 09:07:48,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 1.8935377597808838, cross_entropy: 1.8935377597808838 +[2025-04-29 09:07:52,031][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 3.0406265258789062, cross_entropy: 3.0406265258789062 +[2025-04-29 09:07:52,607][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 1.4229528903961182, cross_entropy: 1.4229528903961182 +[2025-04-29 09:07:54,989][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 2.6983160972595215, cross_entropy: 2.6983160972595215 +[2025-04-29 09:07:56,001][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 2.7827041149139404, cross_entropy: 2.7827041149139404 +[2025-04-29 09:07:58,178][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.5606296062469482, cross_entropy: 1.5606296062469482 +[2025-04-29 09:07:59,086][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.8566226959228516, cross_entropy: 2.8566226959228516 +[2025-04-29 09:08:02,208][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.805971622467041, cross_entropy: 1.805971622467041 +[2025-04-29 09:08:02,597][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 2.5633890628814697, cross_entropy: 2.5633890628814697 +[2025-04-29 09:08:05,326][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 1.2617934942245483, cross_entropy: 1.2617934942245483 +[2025-04-29 09:08:05,639][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 2.7010631561279297, cross_entropy: 2.7010631561279297 +[2025-04-29 09:08:08,805][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.7518342733383179, cross_entropy: 1.7518342733383179 +[2025-04-29 09:08:09,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.3585644960403442, cross_entropy: 1.3585644960403442 +[2025-04-29 09:08:12,487][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 2.883082628250122, cross_entropy: 2.883082628250122 +[2025-04-29 09:08:13,599][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.5795294046401978, cross_entropy: 1.5795294046401978 +[2025-04-29 09:08:15,812][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 1.1249597072601318, cross_entropy: 1.1249597072601318 +[2025-04-29 09:08:16,935][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.4093751907348633, cross_entropy: 2.4093751907348633 +[2025-04-29 09:08:19,416][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.9265050888061523, cross_entropy: 2.9265050888061523 +[2025-04-29 09:08:20,322][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.327990770339966, cross_entropy: 2.327990770339966 +[2025-04-29 09:08:22,506][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 0.9698108434677124, cross_entropy: 0.9698108434677124 +[2025-04-29 09:08:23,680][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 2.9966840744018555, cross_entropy: 2.9966840744018555 +[2025-04-29 09:08:25,695][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.3816485404968262, cross_entropy: 1.3816485404968262 +[2025-04-29 09:08:27,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.5527927875518799, cross_entropy: 1.5527927875518799 +[2025-04-29 09:08:29,480][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 1.695635437965393, cross_entropy: 1.695635437965393 +[2025-04-29 09:08:29,942][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 0.991126537322998, cross_entropy: 0.991126537322998 +[2025-04-29 09:08:32,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 2.6318857669830322, cross_entropy: 2.6318857669830322 +[2025-04-29 09:08:33,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 2.868925094604492, cross_entropy: 2.868925094604492 +[2025-04-29 09:08:36,158][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 2.6697216033935547, cross_entropy: 2.6697216033935547 +[2025-04-29 09:08:37,414][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.1060283184051514, cross_entropy: 1.1060283184051514 +[2025-04-29 09:08:39,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 1.0168631076812744, cross_entropy: 1.0168631076812744 +[2025-04-29 09:08:41,031][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 1.7653247117996216, cross_entropy: 1.7653247117996216 +[2025-04-29 09:08:43,290][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 2.041858673095703, cross_entropy: 2.041858673095703 +[2025-04-29 09:08:45,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 1.5107046365737915, cross_entropy: 1.5107046365737915 +[2025-04-29 09:08:47,043][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 1.0859720706939697, cross_entropy: 1.0859720706939697 +[2025-04-29 09:08:49,130][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 2.4062724113464355, cross_entropy: 2.4062724113464355 +[2025-04-29 09:08:49,964][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 1.0837987661361694, cross_entropy: 1.0837987661361694 +[2025-04-29 09:08:52,362][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.55324125289917, cross_entropy: 2.55324125289917 +[2025-04-29 09:08:53,143][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 1.2055423259735107, cross_entropy: 1.2055423259735107 +[2025-04-29 09:08:55,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 2.041046142578125, cross_entropy: 2.041046142578125 +[2025-04-29 09:08:56,368][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 1.0271581411361694, cross_entropy: 1.0271581411361694 +[2025-04-29 09:08:58,864][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 2.80545711517334, cross_entropy: 2.80545711517334 +[2025-04-29 09:09:00,246][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 1.3805902004241943, cross_entropy: 1.3805902004241943 +[2025-04-29 09:09:02,804][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 2.2713112831115723, cross_entropy: 2.2713112831115723 +[2025-04-29 09:09:03,652][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.838403344154358, cross_entropy: 1.838403344154358 +[2025-04-29 09:09:06,407][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.776075839996338, cross_entropy: 1.776075839996338 +[2025-04-29 09:09:06,977][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 3.075023651123047, cross_entropy: 3.075023651123047 +[2025-04-29 09:09:10,077][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 3.079806089401245, cross_entropy: 3.079806089401245 +[2025-04-29 09:09:10,443][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 3.034440517425537, cross_entropy: 3.034440517425537 +[2025-04-29 09:09:13,482][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 1.0286222696304321, cross_entropy: 1.0286222696304321 +[2025-04-29 09:09:14,225][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 2.8588218688964844, cross_entropy: 2.8588218688964844 +[2025-04-29 09:09:17,087][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 1.9056954383850098, cross_entropy: 1.9056954383850098 +[2025-04-29 09:09:17,879][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.0994272232055664, cross_entropy: 1.0994272232055664 +[2025-04-29 09:09:20,146][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 2.8784677982330322, cross_entropy: 2.8784677982330322 +[2025-04-29 09:09:21,512][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 1.305528163909912, cross_entropy: 1.305528163909912 +[2025-04-29 09:09:23,373][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 1.2785828113555908, cross_entropy: 1.2785828113555908 +[2025-04-29 09:09:25,303][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.7111353874206543, cross_entropy: 1.7111353874206543 +[2025-04-29 09:09:27,261][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.5555715560913086, cross_entropy: 2.5555715560913086 +[2025-04-29 09:09:28,487][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 1.8979288339614868, cross_entropy: 1.8979288339614868 +[2025-04-29 09:09:30,625][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 1.1903491020202637, cross_entropy: 1.1903491020202637 +[2025-04-29 09:09:31,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 1.2874202728271484, cross_entropy: 1.2874202728271484 +[2025-04-29 09:09:34,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 2.009187698364258, cross_entropy: 2.009187698364258 +[2025-04-29 09:09:34,855][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 0.7483124732971191, cross_entropy: 0.7483124732971191 +[2025-04-29 09:09:37,163][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 1.1117122173309326, cross_entropy: 1.1117122173309326 +[2025-04-29 09:09:38,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.3024039268493652, cross_entropy: 2.3024039268493652 +[2025-04-29 09:09:40,682][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.293879985809326, cross_entropy: 2.293879985809326 +[2025-04-29 09:09:41,256][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.2974869012832642, cross_entropy: 1.2974869012832642 +[2025-04-29 09:09:44,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 2.0548524856567383, cross_entropy: 2.0548524856567383 +[2025-04-29 09:09:45,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.931720495223999, cross_entropy: 2.931720495223999 +[2025-04-29 09:09:47,761][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 1.0485901832580566, cross_entropy: 1.0485901832580566 +[2025-04-29 09:09:50,590][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 1.4137165546417236, cross_entropy: 1.4137165546417236 +[2025-04-29 09:09:51,155][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 2.4121174812316895, cross_entropy: 2.4121174812316895 +[2025-04-29 09:09:54,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.7008590698242188, cross_entropy: 2.7008590698242188 +[2025-04-29 09:09:54,709][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.46323823928833, cross_entropy: 1.46323823928833 +[2025-04-29 09:09:57,368][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.3475133180618286, cross_entropy: 1.3475133180618286 +[2025-04-29 09:09:57,847][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 1.9354380369186401, cross_entropy: 1.9354380369186401 +[2025-04-29 09:10:01,124][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 2.675039768218994, cross_entropy: 2.675039768218994 +[2025-04-29 09:10:01,693][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.5206009149551392, cross_entropy: 1.5206009149551392 +[2025-04-29 09:10:05,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.713229775428772, cross_entropy: 1.713229775428772 +[2025-04-29 09:10:05,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 1.0346156358718872, cross_entropy: 1.0346156358718872 +[2025-04-29 09:10:08,461][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.203903913497925, cross_entropy: 2.203903913497925 +[2025-04-29 09:10:08,832][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 2.456550359725952, cross_entropy: 2.456550359725952 +[2025-04-29 09:10:12,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.324010133743286, cross_entropy: 2.324010133743286 +[2025-04-29 09:10:12,388][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.9560906887054443, cross_entropy: 2.9560906887054443 +[2025-04-29 09:10:15,927][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 2.2158584594726562, cross_entropy: 2.2158584594726562 +[2025-04-29 09:10:16,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 1.9978199005126953, cross_entropy: 1.9978199005126953 +[2025-04-29 09:10:19,662][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.090665340423584, cross_entropy: 2.090665340423584 +[2025-04-29 09:10:20,004][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 2.6163430213928223, cross_entropy: 2.6163430213928223 +[2025-04-29 09:10:20,285][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/iteration2000.pth. +[2025-04-29 09:10:23,182][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 2.430255889892578, cross_entropy: 2.430255889892578 +[2025-04-29 09:10:23,521][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 1.0676419734954834, cross_entropy: 1.0676419734954834 +[2025-04-29 09:10:26,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.906221628189087, cross_entropy: 2.906221628189087 +[2025-04-29 09:10:26,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 2.7516064643859863, cross_entropy: 2.7516064643859863 +[2025-04-29 09:10:29,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 1.4015393257141113, cross_entropy: 1.4015393257141113 +[2025-04-29 09:10:30,090][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.142364025115967, cross_entropy: 2.142364025115967 +[2025-04-29 09:10:33,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 1.8216586112976074, cross_entropy: 1.8216586112976074 +[2025-04-29 09:10:33,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 1.659482717514038, cross_entropy: 1.659482717514038 +[2025-04-29 09:10:36,990][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.5856812000274658, cross_entropy: 1.5856812000274658 +[2025-04-29 09:10:37,332][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.4456983804702759, cross_entropy: 1.4456983804702759 +[2025-04-29 09:10:40,719][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 3.286600112915039, cross_entropy: 3.286600112915039 +[2025-04-29 09:10:41,064][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.8083405494689941, cross_entropy: 1.8083405494689941 +[2025-04-29 09:10:44,812][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.8347373008728027, cross_entropy: 1.8347373008728027 +[2025-04-29 09:10:45,154][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 0.799248218536377, cross_entropy: 0.799248218536377 +[2025-04-29 09:10:48,093][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.0774340629577637, cross_entropy: 1.0774340629577637 +[2025-04-29 09:10:48,434][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.1373538970947266, cross_entropy: 2.1373538970947266 +[2025-04-29 09:10:51,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.2055079936981201, cross_entropy: 1.2055079936981201 +[2025-04-29 09:10:52,248][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 2.306851863861084, cross_entropy: 2.306851863861084 +[2025-04-29 09:10:55,331][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 1.4045143127441406, cross_entropy: 1.4045143127441406 +[2025-04-29 09:10:55,670][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.3064112663269043, cross_entropy: 2.3064112663269043 +[2025-04-29 09:10:58,477][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 1.3672711849212646, cross_entropy: 1.3672711849212646 +[2025-04-29 09:10:58,820][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 1.1038730144500732, cross_entropy: 1.1038730144500732 +[2025-04-29 09:11:01,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.9508984088897705, cross_entropy: 1.9508984088897705 +[2025-04-29 09:11:02,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 1.3281769752502441, cross_entropy: 1.3281769752502441 +[2025-04-29 09:11:05,166][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 2.0515599250793457, cross_entropy: 2.0515599250793457 +[2025-04-29 09:11:05,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 1.2088210582733154, cross_entropy: 1.2088210582733154 +[2025-04-29 09:11:09,043][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 2.6990582942962646, cross_entropy: 2.6990582942962646 +[2025-04-29 09:11:09,363][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 0.9949671030044556, cross_entropy: 0.9949671030044556 +[2025-04-29 09:11:12,815][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 1.1599452495574951, cross_entropy: 1.1599452495574951 +[2025-04-29 09:11:13,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 2.658212900161743, cross_entropy: 2.658212900161743 +[2025-04-29 09:11:16,679][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 1.7970645427703857, cross_entropy: 1.7970645427703857 +[2025-04-29 09:11:17,021][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 1.1026322841644287, cross_entropy: 1.1026322841644287 +[2025-04-29 09:11:20,324][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 2.9325878620147705, cross_entropy: 2.9325878620147705 +[2025-04-29 09:11:20,669][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.60793137550354, cross_entropy: 1.60793137550354 +[2025-04-29 09:11:24,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 2.8622262477874756, cross_entropy: 2.8622262477874756 +[2025-04-29 09:11:25,255][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 1.2663228511810303, cross_entropy: 1.2663228511810303 +[2025-04-29 09:11:28,693][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.0297045707702637, cross_entropy: 1.0297045707702637 +[2025-04-29 09:11:29,031][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 0.9446521997451782, cross_entropy: 0.9446521997451782 +[2025-04-29 09:11:32,148][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 1.026788592338562, cross_entropy: 1.026788592338562 +[2025-04-29 09:11:32,486][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 2.819092273712158, cross_entropy: 2.819092273712158 +[2025-04-29 09:11:35,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 1.138596773147583, cross_entropy: 1.138596773147583 +[2025-04-29 09:11:35,948][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.091794729232788, cross_entropy: 1.091794729232788 +[2025-04-29 09:11:39,249][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.5610909461975098, cross_entropy: 2.5610909461975098 +[2025-04-29 09:11:39,589][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 1.6563947200775146, cross_entropy: 1.6563947200775146 +[2025-04-29 09:11:42,720][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.4106297492980957, cross_entropy: 2.4106297492980957 +[2025-04-29 09:11:43,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 2.1254961490631104, cross_entropy: 2.1254961490631104 +[2025-04-29 09:11:45,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 3.0051352977752686, cross_entropy: 3.0051352977752686 +[2025-04-29 09:11:46,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 1.025207281112671, cross_entropy: 1.025207281112671 +[2025-04-29 09:11:49,361][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.313768982887268, cross_entropy: 1.313768982887268 +[2025-04-29 09:11:49,704][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 1.3559552431106567, cross_entropy: 1.3559552431106567 +[2025-04-29 09:11:52,805][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 2.134413957595825, cross_entropy: 2.134413957595825 +[2025-04-29 09:11:53,150][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.86362624168396, cross_entropy: 2.86362624168396 +[2025-04-29 09:11:55,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 3.1036486625671387, cross_entropy: 3.1036486625671387 +[2025-04-29 09:11:56,251][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.3611998558044434, cross_entropy: 1.3611998558044434 +[2025-04-29 09:11:59,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 2.371893882751465, cross_entropy: 2.371893882751465 +[2025-04-29 09:12:00,056][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 1.9338123798370361, cross_entropy: 1.9338123798370361 +[2025-04-29 09:12:03,090][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.5442702770233154, cross_entropy: 1.5442702770233154 +[2025-04-29 09:12:03,435][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 1.0139901638031006, cross_entropy: 1.0139901638031006 +[2025-04-29 09:12:06,487][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 1.0446263551712036, cross_entropy: 1.0446263551712036 +[2025-04-29 09:12:06,832][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 3.2047231197357178, cross_entropy: 3.2047231197357178 +[2025-04-29 09:12:10,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 2.983379364013672, cross_entropy: 2.983379364013672 +[2025-04-29 09:12:10,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 2.911715507507324, cross_entropy: 2.911715507507324 +[2025-04-29 09:12:14,088][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.954732894897461, cross_entropy: 2.954732894897461 +[2025-04-29 09:12:14,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 0.9943612813949585, cross_entropy: 0.9943612813949585 +[2025-04-29 09:12:18,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 1.3720848560333252, cross_entropy: 1.3720848560333252 +[2025-04-29 09:12:18,771][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 2.5014004707336426, cross_entropy: 2.5014004707336426 +[2025-04-29 09:12:22,016][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 1.528537392616272, cross_entropy: 1.528537392616272 +[2025-04-29 09:12:22,353][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 1.6609423160552979, cross_entropy: 1.6609423160552979 +[2025-04-29 09:12:25,816][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 3.193777561187744, cross_entropy: 3.193777561187744 +[2025-04-29 09:12:26,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.470826268196106, cross_entropy: 1.470826268196106 +[2025-04-29 09:12:29,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.1620503664016724, cross_entropy: 1.1620503664016724 +[2025-04-29 09:12:30,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.89504075050354, cross_entropy: 1.89504075050354 +[2025-04-29 09:12:33,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 0.8385341167449951, cross_entropy: 0.8385341167449951 +[2025-04-29 09:12:33,508][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.133638858795166, cross_entropy: 1.133638858795166 +[2025-04-29 09:12:36,760][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.847654342651367, cross_entropy: 2.847654342651367 +[2025-04-29 09:12:37,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 1.86995530128479, cross_entropy: 1.86995530128479 +[2025-04-29 09:12:40,273][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 2.940765857696533, cross_entropy: 2.940765857696533 +[2025-04-29 09:12:40,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.329317092895508, cross_entropy: 2.329317092895508 +[2025-04-29 09:12:43,619][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 2.8102002143859863, cross_entropy: 2.8102002143859863 +[2025-04-29 09:12:43,962][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.917668342590332, cross_entropy: 2.917668342590332 +[2025-04-29 09:12:47,044][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 1.5038552284240723, cross_entropy: 1.5038552284240723 +[2025-04-29 09:12:47,387][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 2.75662899017334, cross_entropy: 2.75662899017334 +[2025-04-29 09:12:50,191][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.9167343378067017, cross_entropy: 1.9167343378067017 +[2025-04-29 09:12:50,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 1.8232536315917969, cross_entropy: 1.8232536315917969 +[2025-04-29 09:12:53,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.0523866415023804, cross_entropy: 1.0523866415023804 +[2025-04-29 09:12:53,976][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 2.8248472213745117, cross_entropy: 2.8248472213745117 +[2025-04-29 09:12:56,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.0941503047943115, cross_entropy: 1.0941503047943115 +[2025-04-29 09:12:57,201][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.5135279893875122, cross_entropy: 1.5135279893875122 +[2025-04-29 09:13:01,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 2.8666117191314697, cross_entropy: 2.8666117191314697 +[2025-04-29 09:13:01,438][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 1.5174376964569092, cross_entropy: 1.5174376964569092 +[2025-04-29 09:13:04,804][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.4795751571655273, cross_entropy: 2.4795751571655273 +[2025-04-29 09:13:05,143][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.2749342918395996, cross_entropy: 1.2749342918395996 +[2025-04-29 09:13:07,732][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.0452611446380615, cross_entropy: 1.0452611446380615 +[2025-04-29 09:13:08,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 0.9755692481994629, cross_entropy: 0.9755692481994629 +[2025-04-29 09:13:10,955][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 2.394948720932007, cross_entropy: 2.394948720932007 +[2025-04-29 09:13:11,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 3.1596410274505615, cross_entropy: 3.1596410274505615 +[2025-04-29 09:13:14,680][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 3.094106435775757, cross_entropy: 3.094106435775757 +[2025-04-29 09:13:15,023][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 1.6182693243026733, cross_entropy: 1.6182693243026733 +[2025-04-29 09:13:18,854][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.1291115283966064, cross_entropy: 1.1291115283966064 +[2025-04-29 09:13:19,189][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.294468879699707, cross_entropy: 1.294468879699707 +[2025-04-29 09:13:21,940][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.0037903785705566, cross_entropy: 1.0037903785705566 +[2025-04-29 09:13:22,279][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 2.1727969646453857, cross_entropy: 2.1727969646453857 +[2025-04-29 09:13:25,542][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.2419452667236328, cross_entropy: 1.2419452667236328 +[2025-04-29 09:13:25,860][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.852151393890381, cross_entropy: 2.852151393890381 +[2025-04-29 09:13:29,717][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 2.7877731323242188, cross_entropy: 2.7877731323242188 +[2025-04-29 09:13:30,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.7345550060272217, cross_entropy: 2.7345550060272217 +[2025-04-29 09:13:32,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.6723580360412598, cross_entropy: 1.6723580360412598 +[2025-04-29 09:13:33,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 1.2116930484771729, cross_entropy: 1.2116930484771729 +[2025-04-29 09:13:36,304][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 2.930194854736328, cross_entropy: 2.930194854736328 +[2025-04-29 09:13:36,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.0067479610443115, cross_entropy: 1.0067479610443115 +[2025-04-29 09:13:39,668][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.1801371574401855, cross_entropy: 1.1801371574401855 +[2025-04-29 09:13:40,010][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.314046859741211, cross_entropy: 1.314046859741211 +[2025-04-29 09:13:42,937][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.9362977743148804, cross_entropy: 1.9362977743148804 +[2025-04-29 09:13:43,249][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 1.1491354703903198, cross_entropy: 1.1491354703903198 +[2025-04-29 09:13:46,588][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.3450886011123657, cross_entropy: 1.3450886011123657 +[2025-04-29 09:13:46,987][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 1.9677883386611938, cross_entropy: 1.9677883386611938 +[2025-04-29 09:13:50,036][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 2.2265470027923584, cross_entropy: 2.2265470027923584 +[2025-04-29 09:13:50,409][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 2.521481990814209, cross_entropy: 2.521481990814209 +[2025-04-29 09:13:53,512][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 1.154172420501709, cross_entropy: 1.154172420501709 +[2025-04-29 09:13:53,824][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 1.3157789707183838, cross_entropy: 1.3157789707183838 +[2025-04-29 09:13:56,935][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 2.7638657093048096, cross_entropy: 2.7638657093048096 +[2025-04-29 09:13:57,249][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 2.3381283283233643, cross_entropy: 2.3381283283233643 +[2025-04-29 09:14:00,163][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.2791051864624023, cross_entropy: 1.2791051864624023 +[2025-04-29 09:14:00,507][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.0063297748565674, cross_entropy: 1.0063297748565674 +[2025-04-29 09:14:03,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 2.6074037551879883, cross_entropy: 2.6074037551879883 +[2025-04-29 09:14:03,617][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.470974326133728, cross_entropy: 1.470974326133728 +[2025-04-29 09:14:06,823][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 2.388808250427246, cross_entropy: 2.388808250427246 +[2025-04-29 09:14:07,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 2.14094877243042, cross_entropy: 2.14094877243042 +[2025-04-29 09:14:10,518][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 2.7092881202697754, cross_entropy: 2.7092881202697754 +[2025-04-29 09:14:10,855][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.2010035514831543, cross_entropy: 1.2010035514831543 +[2025-04-29 09:14:13,564][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 1.2917933464050293, cross_entropy: 1.2917933464050293 +[2025-04-29 09:14:13,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 2.772960662841797, cross_entropy: 2.772960662841797 +[2025-04-29 09:14:17,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.0592107772827148, cross_entropy: 1.0592107772827148 +[2025-04-29 09:14:17,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.3079915046691895, cross_entropy: 1.3079915046691895 +[2025-04-29 09:14:20,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.183218002319336, cross_entropy: 2.183218002319336 +[2025-04-29 09:14:20,921][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 1.1054954528808594, cross_entropy: 1.1054954528808594 +[2025-04-29 09:17:03,972][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.9233332872390747, cross_entropy: 1.9233332872390747 +[2025-04-29 09:17:03,973][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.2881404161453247, cross_entropy: 1.2881404161453247 +[2025-04-29 09:17:04,193][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 09:17:04,360][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch6.pth. +[2025-04-29 09:17:04,969][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 09:17:09,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.473724365234375, cross_entropy: 2.473724365234375 +[2025-04-29 09:17:09,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 3.029651641845703, cross_entropy: 3.029651641845703 +[2025-04-29 09:17:12,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 2.4145994186401367, cross_entropy: 2.4145994186401367 +[2025-04-29 09:17:13,318][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 2.7687413692474365, cross_entropy: 2.7687413692474365 +[2025-04-29 09:17:16,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 3.344011068344116, cross_entropy: 3.344011068344116 +[2025-04-29 09:17:17,023][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 2.1429247856140137, cross_entropy: 2.1429247856140137 +[2025-04-29 09:17:19,746][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 3.043320417404175, cross_entropy: 3.043320417404175 +[2025-04-29 09:17:20,167][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 2.7528483867645264, cross_entropy: 2.7528483867645264 +[2025-04-29 09:17:22,916][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.4477803707122803, cross_entropy: 1.4477803707122803 +[2025-04-29 09:17:23,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 0.83629310131073, cross_entropy: 0.83629310131073 +[2025-04-29 09:17:25,927][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 0.8313732147216797, cross_entropy: 0.8313732147216797 +[2025-04-29 09:17:26,767][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 2.747138738632202, cross_entropy: 2.747138738632202 +[2025-04-29 09:17:29,351][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 1.6524114608764648, cross_entropy: 1.6524114608764648 +[2025-04-29 09:17:30,128][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 1.3115155696868896, cross_entropy: 1.3115155696868896 +[2025-04-29 09:17:32,981][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 1.6006388664245605, cross_entropy: 1.6006388664245605 +[2025-04-29 09:17:34,107][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.96521258354187, cross_entropy: 2.96521258354187 +[2025-04-29 09:17:36,272][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 0.9882650375366211, cross_entropy: 0.9882650375366211 +[2025-04-29 09:17:37,344][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 2.5908563137054443, cross_entropy: 2.5908563137054443 +[2025-04-29 09:17:39,873][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.5712294578552246, cross_entropy: 2.5712294578552246 +[2025-04-29 09:17:40,582][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.9288567304611206, cross_entropy: 1.9288567304611206 +[2025-04-29 09:17:43,500][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 3.0671329498291016, cross_entropy: 3.0671329498291016 +[2025-04-29 09:17:43,878][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 1.2965223789215088, cross_entropy: 1.2965223789215088 +[2025-04-29 09:17:47,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 3.084503173828125, cross_entropy: 3.084503173828125 +[2025-04-29 09:17:48,078][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 1.1657817363739014, cross_entropy: 1.1657817363739014 +[2025-04-29 09:17:53,130][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.057928442955017, cross_entropy: 1.057928442955017 +[2025-04-29 09:17:53,478][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 1.6210899353027344, cross_entropy: 1.6210899353027344 +[2025-04-29 09:17:56,730][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 3.147753953933716, cross_entropy: 3.147753953933716 +[2025-04-29 09:17:57,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 2.913227081298828, cross_entropy: 2.913227081298828 +[2025-04-29 09:18:00,003][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.0564296245574951, cross_entropy: 1.0564296245574951 +[2025-04-29 09:18:00,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 2.77541446685791, cross_entropy: 2.77541446685791 +[2025-04-29 09:18:03,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 2.788080930709839, cross_entropy: 2.788080930709839 +[2025-04-29 09:18:03,595][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.028409719467163, cross_entropy: 2.028409719467163 +[2025-04-29 09:18:06,791][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 0.9123697280883789, cross_entropy: 0.9123697280883789 +[2025-04-29 09:18:07,130][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 2.3620986938476562, cross_entropy: 2.3620986938476562 +[2025-04-29 09:18:09,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 1.4772504568099976, cross_entropy: 1.4772504568099976 +[2025-04-29 09:18:10,107][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.0376652479171753, cross_entropy: 1.0376652479171753 +[2025-04-29 09:18:12,719][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.637998580932617, cross_entropy: 2.637998580932617 +[2025-04-29 09:18:13,060][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 2.8083689212799072, cross_entropy: 2.8083689212799072 +[2025-04-29 09:18:15,596][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 1.3097337484359741, cross_entropy: 1.3097337484359741 +[2025-04-29 09:18:15,942][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 2.8631603717803955, cross_entropy: 2.8631603717803955 +[2025-04-29 09:18:19,550][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.532102108001709, cross_entropy: 1.532102108001709 +[2025-04-29 09:18:19,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.7718300819396973, cross_entropy: 2.7718300819396973 +[2025-04-29 09:18:23,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.714160442352295, cross_entropy: 2.714160442352295 +[2025-04-29 09:18:23,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 0.9557385444641113, cross_entropy: 0.9557385444641113 +[2025-04-29 09:18:26,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.76639461517334, cross_entropy: 2.76639461517334 +[2025-04-29 09:18:27,260][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 0.877416729927063, cross_entropy: 0.877416729927063 +[2025-04-29 09:18:30,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 1.773270606994629, cross_entropy: 1.773270606994629 +[2025-04-29 09:18:30,886][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 2.6516406536102295, cross_entropy: 2.6516406536102295 +[2025-04-29 09:18:33,873][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 1.3137074708938599, cross_entropy: 1.3137074708938599 +[2025-04-29 09:18:34,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.4659347534179688, cross_entropy: 1.4659347534179688 +[2025-04-29 09:18:37,592][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.7459933757781982, cross_entropy: 2.7459933757781982 +[2025-04-29 09:18:37,907][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.4491406679153442, cross_entropy: 1.4491406679153442 +[2025-04-29 09:18:41,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 1.7009233236312866, cross_entropy: 1.7009233236312866 +[2025-04-29 09:18:42,142][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.5928704738616943, cross_entropy: 2.5928704738616943 +[2025-04-29 09:18:45,205][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 1.391714334487915, cross_entropy: 1.391714334487915 +[2025-04-29 09:18:45,542][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.9207963943481445, cross_entropy: 2.9207963943481445 +[2025-04-29 09:18:48,592][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.5637056827545166, cross_entropy: 1.5637056827545166 +[2025-04-29 09:18:48,930][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 2.455721855163574, cross_entropy: 2.455721855163574 +[2025-04-29 09:18:51,765][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 2.178401470184326, cross_entropy: 2.178401470184326 +[2025-04-29 09:18:52,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.797654390335083, cross_entropy: 1.797654390335083 +[2025-04-29 09:18:55,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.298793077468872, cross_entropy: 2.298793077468872 +[2025-04-29 09:18:55,522][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 0.5765674114227295, cross_entropy: 0.5765674114227295 +[2025-04-29 09:18:58,820][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.0024371147155762, cross_entropy: 1.0024371147155762 +[2025-04-29 09:18:59,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 2.4524474143981934, cross_entropy: 2.4524474143981934 +[2025-04-29 09:19:02,089][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 0.9479423761367798, cross_entropy: 0.9479423761367798 +[2025-04-29 09:19:02,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 3.046919107437134, cross_entropy: 3.046919107437134 +[2025-04-29 09:19:05,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 2.2864556312561035, cross_entropy: 2.2864556312561035 +[2025-04-29 09:19:06,067][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 1.0656625032424927, cross_entropy: 1.0656625032424927 +[2025-04-29 09:19:08,826][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 2.54642391204834, cross_entropy: 2.54642391204834 +[2025-04-29 09:19:09,150][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 1.3045934438705444, cross_entropy: 1.3045934438705444 +[2025-04-29 09:19:11,993][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.2686166763305664, cross_entropy: 2.2686166763305664 +[2025-04-29 09:19:12,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 1.4402987957000732, cross_entropy: 1.4402987957000732 +[2025-04-29 09:19:15,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 1.0010616779327393, cross_entropy: 1.0010616779327393 +[2025-04-29 09:19:15,943][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 0.9941544532775879, cross_entropy: 0.9941544532775879 +[2025-04-29 09:19:19,221][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 0.869736909866333, cross_entropy: 0.869736909866333 +[2025-04-29 09:19:19,601][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.6593506336212158, cross_entropy: 1.6593506336212158 +[2025-04-29 09:19:22,179][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 1.9813681840896606, cross_entropy: 1.9813681840896606 +[2025-04-29 09:19:22,516][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 0.7105227112770081, cross_entropy: 0.7105227112770081 +[2025-04-29 09:19:25,511][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 3.17850923538208, cross_entropy: 3.17850923538208 +[2025-04-29 09:19:25,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 2.1478219032287598, cross_entropy: 2.1478219032287598 +[2025-04-29 09:19:28,820][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 0.64136803150177, cross_entropy: 0.64136803150177 +[2025-04-29 09:19:29,456][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 1.5318922996520996, cross_entropy: 1.5318922996520996 +[2025-04-29 09:19:32,067][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 1.2229242324829102, cross_entropy: 1.2229242324829102 +[2025-04-29 09:19:32,685][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 1.3514611721038818, cross_entropy: 1.3514611721038818 +[2025-04-29 09:19:35,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.1512811183929443, cross_entropy: 1.1512811183929443 +[2025-04-29 09:19:36,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 1.3156344890594482, cross_entropy: 1.3156344890594482 +[2025-04-29 09:19:38,726][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 2.2130439281463623, cross_entropy: 2.2130439281463623 +[2025-04-29 09:19:39,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 2.398693561553955, cross_entropy: 2.398693561553955 +[2025-04-29 09:19:42,120][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 0.9731450080871582, cross_entropy: 0.9731450080871582 +[2025-04-29 09:19:44,474][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 3.2145276069641113, cross_entropy: 3.2145276069641113 +[2025-04-29 09:19:45,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 0.8400067090988159, cross_entropy: 0.8400067090988159 +[2025-04-29 09:19:48,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 2.81547212600708, cross_entropy: 2.81547212600708 +[2025-04-29 09:19:48,586][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 0.6635984182357788, cross_entropy: 0.6635984182357788 +[2025-04-29 09:19:51,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 2.6142964363098145, cross_entropy: 2.6142964363098145 +[2025-04-29 09:19:52,261][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.880767345428467, cross_entropy: 2.880767345428467 +[2025-04-29 09:19:54,595][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 3.037759304046631, cross_entropy: 3.037759304046631 +[2025-04-29 09:19:55,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 2.49000883102417, cross_entropy: 2.49000883102417 +[2025-04-29 09:19:58,641][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 0.8238327503204346, cross_entropy: 0.8238327503204346 +[2025-04-29 09:19:59,240][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 2.99015474319458, cross_entropy: 2.99015474319458 +[2025-04-29 09:20:01,825][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 2.3475799560546875, cross_entropy: 2.3475799560546875 +[2025-04-29 09:20:02,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 0.8188067078590393, cross_entropy: 0.8188067078590393 +[2025-04-29 09:20:05,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 1.2707948684692383, cross_entropy: 1.2707948684692383 +[2025-04-29 09:20:06,500][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 1.1660162210464478, cross_entropy: 1.1660162210464478 +[2025-04-29 09:20:09,082][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.2246004343032837, cross_entropy: 1.2246004343032837 +[2025-04-29 09:20:09,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.6831035614013672, cross_entropy: 1.6831035614013672 +[2025-04-29 09:20:12,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.1182725429534912, cross_entropy: 1.1182725429534912 +[2025-04-29 09:20:12,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.3162084817886353, cross_entropy: 1.3162084817886353 +[2025-04-29 09:20:15,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.1206862926483154, cross_entropy: 1.1206862926483154 +[2025-04-29 09:20:16,068][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 2.9524941444396973, cross_entropy: 2.9524941444396973 +[2025-04-29 09:20:19,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 2.4873175621032715, cross_entropy: 2.4873175621032715 +[2025-04-29 09:20:19,783][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 2.046924114227295, cross_entropy: 2.046924114227295 +[2025-04-29 09:20:23,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 1.2096059322357178, cross_entropy: 1.2096059322357178 +[2025-04-29 09:20:23,431][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.9729037284851074, cross_entropy: 1.9729037284851074 +[2025-04-29 09:20:26,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 0.9486995935440063, cross_entropy: 0.9486995935440063 +[2025-04-29 09:20:26,937][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 3.099985122680664, cross_entropy: 3.099985122680664 +[2025-04-29 09:20:30,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 2.7693533897399902, cross_entropy: 2.7693533897399902 +[2025-04-29 09:20:31,329][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 3.173537492752075, cross_entropy: 3.173537492752075 +[2025-04-29 09:20:34,033][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 1.1382942199707031, cross_entropy: 1.1382942199707031 +[2025-04-29 09:20:34,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 0.7662549018859863, cross_entropy: 0.7662549018859863 +[2025-04-29 09:20:37,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 3.0123188495635986, cross_entropy: 3.0123188495635986 +[2025-04-29 09:20:38,009][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.4543049335479736, cross_entropy: 1.4543049335479736 +[2025-04-29 09:20:41,916][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 0.8625169396400452, cross_entropy: 0.8625169396400452 +[2025-04-29 09:20:42,229][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 0.9657101035118103, cross_entropy: 0.9657101035118103 +[2025-04-29 09:20:45,812][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 2.5819616317749023, cross_entropy: 2.5819616317749023 +[2025-04-29 09:20:46,127][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 0.9919382333755493, cross_entropy: 0.9919382333755493 +[2025-04-29 09:20:49,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 2.330026149749756, cross_entropy: 2.330026149749756 +[2025-04-29 09:20:49,796][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 2.5051448345184326, cross_entropy: 2.5051448345184326 +[2025-04-29 09:20:54,565][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 2.1487677097320557, cross_entropy: 2.1487677097320557 +[2025-04-29 09:20:54,905][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 0.7889136075973511, cross_entropy: 0.7889136075973511 +[2025-04-29 09:20:57,632][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 2.433730125427246, cross_entropy: 2.433730125427246 +[2025-04-29 09:20:57,978][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 2.1508541107177734, cross_entropy: 2.1508541107177734 +[2025-04-29 09:21:01,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 0.7184348106384277, cross_entropy: 0.7184348106384277 +[2025-04-29 09:21:01,618][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 1.2953261137008667, cross_entropy: 1.2953261137008667 +[2025-04-29 09:21:05,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 2.033653736114502, cross_entropy: 2.033653736114502 +[2025-04-29 09:21:05,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 0.7291826009750366, cross_entropy: 0.7291826009750366 +[2025-04-29 09:21:08,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.0324954986572266, cross_entropy: 2.0324954986572266 +[2025-04-29 09:21:09,013][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 2.980900287628174, cross_entropy: 2.980900287628174 +[2025-04-29 09:21:11,688][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.7048053741455078, cross_entropy: 1.7048053741455078 +[2025-04-29 09:21:12,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 1.7137737274169922, cross_entropy: 1.7137737274169922 +[2025-04-29 09:21:14,762][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.956920862197876, cross_entropy: 2.956920862197876 +[2025-04-29 09:21:15,105][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 2.499880075454712, cross_entropy: 2.499880075454712 +[2025-04-29 09:21:18,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.1285783052444458, cross_entropy: 1.1285783052444458 +[2025-04-29 09:21:18,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 2.870985507965088, cross_entropy: 2.870985507965088 +[2025-04-29 09:21:21,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 0.763408362865448, cross_entropy: 0.763408362865448 +[2025-04-29 09:21:21,920][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.449672818183899, cross_entropy: 1.449672818183899 +[2025-04-29 09:21:24,755][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 2.261807680130005, cross_entropy: 2.261807680130005 +[2025-04-29 09:21:25,103][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 0.8310030102729797, cross_entropy: 0.8310030102729797 +[2025-04-29 09:21:27,794][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 0.769467830657959, cross_entropy: 0.769467830657959 +[2025-04-29 09:21:28,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 1.1800806522369385, cross_entropy: 1.1800806522369385 +[2025-04-29 09:21:31,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 2.589796304702759, cross_entropy: 2.589796304702759 +[2025-04-29 09:21:32,174][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 1.0266340970993042, cross_entropy: 1.0266340970993042 +[2025-04-29 09:21:36,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 0.9927650094032288, cross_entropy: 0.9927650094032288 +[2025-04-29 09:21:36,477][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 3.26157283782959, cross_entropy: 3.26157283782959 +[2025-04-29 09:21:39,520][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 2.7355430126190186, cross_entropy: 2.7355430126190186 +[2025-04-29 09:21:39,836][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 1.0382426977157593, cross_entropy: 1.0382426977157593 +[2025-04-29 09:21:43,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 2.7113661766052246, cross_entropy: 2.7113661766052246 +[2025-04-29 09:21:44,069][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 2.4919042587280273, cross_entropy: 2.4919042587280273 +[2025-04-29 09:21:47,369][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 2.627708911895752, cross_entropy: 2.627708911895752 +[2025-04-29 09:21:47,708][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.068603754043579, cross_entropy: 1.068603754043579 +[2025-04-29 09:21:51,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 0.8908555507659912, cross_entropy: 0.8908555507659912 +[2025-04-29 09:21:51,688][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 0.9893029928207397, cross_entropy: 0.9893029928207397 +[2025-04-29 09:21:55,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.047289252281189, cross_entropy: 1.047289252281189 +[2025-04-29 09:21:55,495][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.706519603729248, cross_entropy: 1.706519603729248 +[2025-04-29 09:21:58,188][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 0.6793401837348938, cross_entropy: 0.6793401837348938 +[2025-04-29 09:21:58,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.083808422088623, cross_entropy: 1.083808422088623 +[2025-04-29 09:22:01,643][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.1794190406799316, cross_entropy: 1.1794190406799316 +[2025-04-29 09:22:01,983][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 3.4091718196868896, cross_entropy: 3.4091718196868896 +[2025-04-29 09:22:04,769][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 2.217953681945801, cross_entropy: 2.217953681945801 +[2025-04-29 09:22:05,105][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 0.9758223295211792, cross_entropy: 0.9758223295211792 +[2025-04-29 09:22:08,918][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 0.9980071783065796, cross_entropy: 0.9980071783065796 +[2025-04-29 09:22:09,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.3571960926055908, cross_entropy: 1.3571960926055908 +[2025-04-29 09:22:12,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 0.8327573537826538, cross_entropy: 0.8327573537826538 +[2025-04-29 09:22:12,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.3641940355300903, cross_entropy: 1.3641940355300903 +[2025-04-29 09:22:15,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 2.833547592163086, cross_entropy: 2.833547592163086 +[2025-04-29 09:22:15,497][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 2.612046718597412, cross_entropy: 2.612046718597412 +[2025-04-29 09:22:18,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 2.951348066329956, cross_entropy: 2.951348066329956 +[2025-04-29 09:22:19,023][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 2.812910318374634, cross_entropy: 2.812910318374634 +[2025-04-29 09:22:22,164][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.8886806964874268, cross_entropy: 1.8886806964874268 +[2025-04-29 09:22:22,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 2.797053813934326, cross_entropy: 2.797053813934326 +[2025-04-29 09:22:25,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.932902216911316, cross_entropy: 1.932902216911316 +[2025-04-29 09:22:26,152][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.5289881229400635, cross_entropy: 2.5289881229400635 +[2025-04-29 09:22:28,669][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 2.8429102897644043, cross_entropy: 2.8429102897644043 +[2025-04-29 09:22:29,011][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.327329397201538, cross_entropy: 1.327329397201538 +[2025-04-29 09:22:31,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 3.148101568222046, cross_entropy: 3.148101568222046 +[2025-04-29 09:22:32,318][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.3114811182022095, cross_entropy: 1.3114811182022095 +[2025-04-29 09:22:35,261][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 1.5336978435516357, cross_entropy: 1.5336978435516357 +[2025-04-29 09:22:35,575][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 0.8255330324172974, cross_entropy: 0.8255330324172974 +[2025-04-29 09:22:39,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 1.7106459140777588, cross_entropy: 1.7106459140777588 +[2025-04-29 09:22:40,111][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 2.312546968460083, cross_entropy: 2.312546968460083 +[2025-04-29 09:22:43,389][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 2.16239070892334, cross_entropy: 2.16239070892334 +[2025-04-29 09:22:43,726][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 1.3637897968292236, cross_entropy: 1.3637897968292236 +[2025-04-29 09:22:47,005][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 2.6719179153442383, cross_entropy: 2.6719179153442383 +[2025-04-29 09:22:47,344][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 2.5053679943084717, cross_entropy: 2.5053679943084717 +[2025-04-29 09:22:51,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 1.1631078720092773, cross_entropy: 1.1631078720092773 +[2025-04-29 09:22:51,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 2.6407699584960938, cross_entropy: 2.6407699584960938 +[2025-04-29 09:22:54,551][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.804604172706604, cross_entropy: 1.804604172706604 +[2025-04-29 09:22:54,902][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 1.5880529880523682, cross_entropy: 1.5880529880523682 +[2025-04-29 09:22:57,849][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 2.205902099609375, cross_entropy: 2.205902099609375 +[2025-04-29 09:22:58,188][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 1.641953468322754, cross_entropy: 1.641953468322754 +[2025-04-29 09:23:01,382][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 2.867230176925659, cross_entropy: 2.867230176925659 +[2025-04-29 09:23:01,724][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.510674476623535, cross_entropy: 2.510674476623535 +[2025-04-29 09:23:05,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 1.0599706172943115, cross_entropy: 1.0599706172943115 +[2025-04-29 09:23:05,938][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 3.496520519256592, cross_entropy: 3.496520519256592 +[2025-04-29 09:23:09,022][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 1.1557247638702393, cross_entropy: 1.1557247638702393 +[2025-04-29 09:23:09,356][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 0.8529469966888428, cross_entropy: 0.8529469966888428 +[2025-04-29 09:23:12,539][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 1.0522820949554443, cross_entropy: 1.0522820949554443 +[2025-04-29 09:23:12,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 1.7989472150802612, cross_entropy: 1.7989472150802612 +[2025-04-29 09:23:15,987][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.9370099306106567, cross_entropy: 1.9370099306106567 +[2025-04-29 09:23:16,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 1.150840401649475, cross_entropy: 1.150840401649475 +[2025-04-29 09:23:19,980][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 2.5892961025238037, cross_entropy: 2.5892961025238037 +[2025-04-29 09:23:20,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 1.132096767425537, cross_entropy: 1.132096767425537 +[2025-04-29 09:23:23,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.1285508871078491, cross_entropy: 1.1285508871078491 +[2025-04-29 09:23:23,801][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 0.8712793588638306, cross_entropy: 0.8712793588638306 +[2025-04-29 09:23:26,837][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.318436622619629, cross_entropy: 1.318436622619629 +[2025-04-29 09:23:27,183][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 2.8097853660583496, cross_entropy: 2.8097853660583496 +[2025-04-29 09:23:30,388][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 2.557551383972168, cross_entropy: 2.557551383972168 +[2025-04-29 09:23:30,733][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 1.1718730926513672, cross_entropy: 1.1718730926513672 +[2025-04-29 09:23:33,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 1.2737102508544922, cross_entropy: 1.2737102508544922 +[2025-04-29 09:23:34,202][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 0.7980660200119019, cross_entropy: 0.7980660200119019 +[2025-04-29 09:23:37,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.3660902976989746, cross_entropy: 2.3660902976989746 +[2025-04-29 09:23:37,399][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 2.4422037601470947, cross_entropy: 2.4422037601470947 +[2025-04-29 09:23:40,320][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 2.9121651649475098, cross_entropy: 2.9121651649475098 +[2025-04-29 09:23:40,697][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.4578893184661865, cross_entropy: 2.4578893184661865 +[2025-04-29 09:23:44,485][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 2.9996776580810547, cross_entropy: 2.9996776580810547 +[2025-04-29 09:23:44,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.8297549486160278, cross_entropy: 1.8297549486160278 +[2025-04-29 09:23:48,023][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 1.2828651666641235, cross_entropy: 1.2828651666641235 +[2025-04-29 09:23:48,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 2.316387414932251, cross_entropy: 2.316387414932251 +[2025-04-29 09:23:51,221][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 2.646907091140747, cross_entropy: 2.646907091140747 +[2025-04-29 09:23:52,020][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.1566376686096191, cross_entropy: 1.1566376686096191 +[2025-04-29 09:23:54,803][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 2.794538974761963, cross_entropy: 2.794538974761963 +[2025-04-29 09:23:55,856][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.538567066192627, cross_entropy: 2.538567066192627 +[2025-04-29 09:24:00,173][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 3.2206387519836426, cross_entropy: 3.2206387519836426 +[2025-04-29 09:24:00,515][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 0.7488045692443848, cross_entropy: 0.7488045692443848 +[2025-04-29 09:24:03,437][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 0.8448890447616577, cross_entropy: 0.8448890447616577 +[2025-04-29 09:24:03,752][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 0.9202972054481506, cross_entropy: 0.9202972054481506 +[2025-04-29 09:24:06,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 0.9758400321006775, cross_entropy: 0.9758400321006775 +[2025-04-29 09:24:07,273][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 2.7467541694641113, cross_entropy: 2.7467541694641113 +[2025-04-29 09:24:10,248][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 1.4597364664077759, cross_entropy: 1.4597364664077759 +[2025-04-29 09:24:10,560][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 1.9100693464279175, cross_entropy: 1.9100693464279175 +[2025-04-29 09:24:14,314][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.120884895324707, cross_entropy: 2.120884895324707 +[2025-04-29 09:24:14,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 1.0706827640533447, cross_entropy: 1.0706827640533447 +[2025-04-29 09:24:17,486][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 2.0569536685943604, cross_entropy: 2.0569536685943604 +[2025-04-29 09:24:17,860][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 2.9683408737182617, cross_entropy: 2.9683408737182617 +[2025-04-29 09:24:20,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 0.9061660766601562, cross_entropy: 0.9061660766601562 +[2025-04-29 09:24:21,521][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 0.9757923483848572, cross_entropy: 0.9757923483848572 +[2025-04-29 09:24:24,244][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 2.8517470359802246, cross_entropy: 2.8517470359802246 +[2025-04-29 09:24:24,859][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 0.7873426079750061, cross_entropy: 0.7873426079750061 +[2025-04-29 09:24:28,080][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 3.0165507793426514, cross_entropy: 3.0165507793426514 +[2025-04-29 09:24:28,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 2.8619484901428223, cross_entropy: 2.8619484901428223 +[2025-04-29 09:24:31,444][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 3.0585808753967285, cross_entropy: 3.0585808753967285 +[2025-04-29 09:24:31,760][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.5941851139068604, cross_entropy: 1.5941851139068604 +[2025-04-29 09:24:35,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 0.9749574661254883, cross_entropy: 0.9749574661254883 +[2025-04-29 09:24:35,419][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 3.044100284576416, cross_entropy: 3.044100284576416 +[2025-04-29 09:24:38,613][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.7508037090301514, cross_entropy: 1.7508037090301514 +[2025-04-29 09:24:38,954][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 1.780339241027832, cross_entropy: 1.780339241027832 +[2025-04-29 09:24:41,889][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.469655752182007, cross_entropy: 2.469655752182007 +[2025-04-29 09:24:42,227][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 1.384190320968628, cross_entropy: 1.384190320968628 +[2025-04-29 09:24:45,624][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 1.192271113395691, cross_entropy: 1.192271113395691 +[2025-04-29 09:24:45,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 3.1011619567871094, cross_entropy: 3.1011619567871094 +[2025-04-29 09:24:49,941][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.5012009143829346, cross_entropy: 2.5012009143829346 +[2025-04-29 09:24:50,279][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 2.3224029541015625, cross_entropy: 2.3224029541015625 +[2025-04-29 09:24:53,269][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.10378098487854, cross_entropy: 1.10378098487854 +[2025-04-29 09:24:53,613][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.0381650924682617, cross_entropy: 1.0381650924682617 +[2025-04-29 09:24:56,293][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.3827297687530518, cross_entropy: 1.3827297687530518 +[2025-04-29 09:24:56,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 1.3786324262619019, cross_entropy: 1.3786324262619019 +[2025-04-29 09:24:59,956][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 0.7672435641288757, cross_entropy: 0.7672435641288757 +[2025-04-29 09:25:00,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 1.6601709127426147, cross_entropy: 1.6601709127426147 +[2025-04-29 09:25:03,477][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 1.2276463508605957, cross_entropy: 1.2276463508605957 +[2025-04-29 09:25:03,824][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 2.2351932525634766, cross_entropy: 2.2351932525634766 +[2025-04-29 09:25:07,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.0653395652770996, cross_entropy: 1.0653395652770996 +[2025-04-29 09:25:07,360][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 1.1430151462554932, cross_entropy: 1.1430151462554932 +[2025-04-29 09:25:11,022][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 2.956080436706543, cross_entropy: 2.956080436706543 +[2025-04-29 09:25:11,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.7028584480285645, cross_entropy: 2.7028584480285645 +[2025-04-29 09:25:14,378][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.6629217863082886, cross_entropy: 1.6629217863082886 +[2025-04-29 09:25:14,692][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 1.4191811084747314, cross_entropy: 1.4191811084747314 +[2025-04-29 09:25:18,232][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 0.9322164058685303, cross_entropy: 0.9322164058685303 +[2025-04-29 09:25:18,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 2.9945850372314453, cross_entropy: 2.9945850372314453 +[2025-04-29 09:25:21,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 1.7627592086791992, cross_entropy: 1.7627592086791992 +[2025-04-29 09:25:22,290][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.2802598476409912, cross_entropy: 1.2802598476409912 +[2025-04-29 09:25:25,405][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 0.6828410029411316, cross_entropy: 0.6828410029411316 +[2025-04-29 09:25:25,720][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.0867708921432495, cross_entropy: 1.0867708921432495 +[2025-04-29 09:25:28,951][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 1.914365291595459, cross_entropy: 1.914365291595459 +[2025-04-29 09:25:29,265][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 1.9626426696777344, cross_entropy: 1.9626426696777344 +[2025-04-29 09:25:32,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.4144333600997925, cross_entropy: 1.4144333600997925 +[2025-04-29 09:25:32,569][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 1.640968918800354, cross_entropy: 1.640968918800354 +[2025-04-29 09:25:35,336][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.786984920501709, cross_entropy: 2.786984920501709 +[2025-04-29 09:25:35,650][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 2.8409512042999268, cross_entropy: 2.8409512042999268 +[2025-04-29 09:25:39,216][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 1.4787641763687134, cross_entropy: 1.4787641763687134 +[2025-04-29 09:25:39,558][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 1.9941152334213257, cross_entropy: 1.9941152334213257 +[2025-04-29 09:25:42,210][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.1601810455322266, cross_entropy: 2.1601810455322266 +[2025-04-29 09:25:42,551][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.3208121061325073, cross_entropy: 1.3208121061325073 +[2025-04-29 09:25:45,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 1.1037904024124146, cross_entropy: 1.1037904024124146 +[2025-04-29 09:25:45,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 2.968506336212158, cross_entropy: 2.968506336212158 +[2025-04-29 09:25:48,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.3021047115325928, cross_entropy: 1.3021047115325928 +[2025-04-29 09:25:49,203][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 0.8405489921569824, cross_entropy: 0.8405489921569824 +[2025-04-29 09:25:52,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.4908058643341064, cross_entropy: 1.4908058643341064 +[2025-04-29 09:25:52,870][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.70001482963562, cross_entropy: 2.70001482963562 +[2025-04-29 09:25:56,095][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 1.0343527793884277, cross_entropy: 1.0343527793884277 +[2025-04-29 09:25:56,432][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.365055799484253, cross_entropy: 2.365055799484253 +[2025-04-29 09:25:59,574][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 1.5095092058181763, cross_entropy: 1.5095092058181763 +[2025-04-29 09:25:59,912][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.1643035411834717, cross_entropy: 2.1643035411834717 +[2025-04-29 09:26:02,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 1.0119094848632812, cross_entropy: 1.0119094848632812 +[2025-04-29 09:26:03,240][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 0.868822455406189, cross_entropy: 0.868822455406189 +[2025-04-29 09:26:06,264][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 2.4371719360351562, cross_entropy: 2.4371719360351562 +[2025-04-29 09:26:06,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 2.5347533226013184, cross_entropy: 2.5347533226013184 +[2025-04-29 09:26:09,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.4251163005828857, cross_entropy: 2.4251163005828857 +[2025-04-29 09:26:10,053][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.5871126651763916, cross_entropy: 1.5871126651763916 +[2025-04-29 09:26:13,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 1.1811779737472534, cross_entropy: 1.1811779737472534 +[2025-04-29 09:26:13,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 0.8925280570983887, cross_entropy: 0.8925280570983887 +[2025-04-29 09:26:17,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 1.1321156024932861, cross_entropy: 1.1321156024932861 +[2025-04-29 09:26:17,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.9298095703125, cross_entropy: 1.9298095703125 +[2025-04-29 09:26:20,520][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.26237154006958, cross_entropy: 1.26237154006958 +[2025-04-29 09:26:20,863][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 3.085569381713867, cross_entropy: 3.085569381713867 +[2025-04-29 09:26:23,918][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 3.0334854125976562, cross_entropy: 3.0334854125976562 +[2025-04-29 09:26:24,264][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.2316367626190186, cross_entropy: 1.2316367626190186 +[2025-04-29 09:26:27,835][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.1077094078063965, cross_entropy: 1.1077094078063965 +[2025-04-29 09:26:28,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.2351611852645874, cross_entropy: 1.2351611852645874 +[2025-04-29 09:26:31,491][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 2.414590358734131, cross_entropy: 2.414590358734131 +[2025-04-29 09:26:31,826][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 1.704993724822998, cross_entropy: 1.704993724822998 +[2025-04-29 09:26:34,494][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.967778205871582, cross_entropy: 2.967778205871582 +[2025-04-29 09:26:34,835][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.240955114364624, cross_entropy: 2.240955114364624 +[2025-04-29 09:26:37,775][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 2.2618746757507324, cross_entropy: 2.2618746757507324 +[2025-04-29 09:26:38,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 2.646165609359741, cross_entropy: 2.646165609359741 +[2025-04-29 09:26:41,103][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.5243186950683594, cross_entropy: 2.5243186950683594 +[2025-04-29 09:26:41,453][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 2.722486972808838, cross_entropy: 2.722486972808838 +[2025-04-29 09:26:44,303][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 2.791299819946289, cross_entropy: 2.791299819946289 +[2025-04-29 09:26:44,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.724905252456665, cross_entropy: 1.724905252456665 +[2025-04-29 09:26:47,676][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 2.569023609161377, cross_entropy: 2.569023609161377 +[2025-04-29 09:26:48,019][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 3.0945777893066406, cross_entropy: 3.0945777893066406 +[2025-04-29 09:26:50,935][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 1.4390532970428467, cross_entropy: 1.4390532970428467 +[2025-04-29 09:26:51,277][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 1.1857231855392456, cross_entropy: 1.1857231855392456 +[2025-04-29 09:26:55,196][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.4354379177093506, cross_entropy: 1.4354379177093506 +[2025-04-29 09:26:55,510][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 1.4114601612091064, cross_entropy: 1.4114601612091064 +[2025-04-29 09:26:58,667][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 2.800248146057129, cross_entropy: 2.800248146057129 +[2025-04-29 09:26:58,982][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 2.353729248046875, cross_entropy: 2.353729248046875 +[2025-04-29 09:27:02,754][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 2.9432766437530518, cross_entropy: 2.9432766437530518 +[2025-04-29 09:27:03,095][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.3018532991409302, cross_entropy: 1.3018532991409302 +[2025-04-29 09:27:06,354][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.5654902458190918, cross_entropy: 1.5654902458190918 +[2025-04-29 09:27:06,669][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.769432544708252, cross_entropy: 2.769432544708252 +[2025-04-29 09:27:09,680][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.7721285820007324, cross_entropy: 2.7721285820007324 +[2025-04-29 09:27:09,992][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 1.0465264320373535, cross_entropy: 1.0465264320373535 +[2025-04-29 09:27:13,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 2.9754559993743896, cross_entropy: 2.9754559993743896 +[2025-04-29 09:27:13,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.0666658878326416, cross_entropy: 2.0666658878326416 +[2025-04-29 09:27:16,136][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 1.168409824371338, cross_entropy: 1.168409824371338 +[2025-04-29 09:27:16,454][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 2.9106359481811523, cross_entropy: 2.9106359481811523 +[2025-04-29 09:27:19,194][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.7978017330169678, cross_entropy: 1.7978017330169678 +[2025-04-29 09:27:19,535][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 0.9481309652328491, cross_entropy: 0.9481309652328491 +[2025-04-29 09:27:22,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 0.760866641998291, cross_entropy: 0.760866641998291 +[2025-04-29 09:27:22,580][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 2.315293312072754, cross_entropy: 2.315293312072754 +[2025-04-29 09:27:26,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 2.9200687408447266, cross_entropy: 2.9200687408447266 +[2025-04-29 09:27:26,495][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 1.2249081134796143, cross_entropy: 1.2249081134796143 +[2025-04-29 09:27:29,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 2.550370693206787, cross_entropy: 2.550370693206787 +[2025-04-29 09:27:29,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 2.276548385620117, cross_entropy: 2.276548385620117 +[2025-04-29 09:27:32,844][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 0.9554430246353149, cross_entropy: 0.9554430246353149 +[2025-04-29 09:27:33,157][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 0.6631096601486206, cross_entropy: 0.6631096601486206 +[2025-04-29 09:27:35,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 1.8063818216323853, cross_entropy: 1.8063818216323853 +[2025-04-29 09:30:17,267][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.8762515783309937, cross_entropy: 1.8762515783309937 +[2025-04-29 09:30:17,267][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.2337839603424072, cross_entropy: 1.2337839603424072 +[2025-04-29 09:30:17,482][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 09:30:17,645][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch7.pth. +[2025-04-29 09:30:17,858][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 09:30:22,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 0.8392073512077332, cross_entropy: 0.8392073512077332 +[2025-04-29 09:30:22,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 1.3549681901931763, cross_entropy: 1.3549681901931763 +[2025-04-29 09:30:25,524][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.6563704013824463, cross_entropy: 1.6563704013824463 +[2025-04-29 09:30:26,001][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.9131734371185303, cross_entropy: 2.9131734371185303 +[2025-04-29 09:30:29,172][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.2663391828536987, cross_entropy: 1.2663391828536987 +[2025-04-29 09:30:30,542][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.2603962421417236, cross_entropy: 1.2603962421417236 +[2025-04-29 09:30:32,318][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 1.757271647453308, cross_entropy: 1.757271647453308 +[2025-04-29 09:30:34,334][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 1.3087279796600342, cross_entropy: 1.3087279796600342 +[2025-04-29 09:30:35,294][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.0290393829345703, cross_entropy: 1.0290393829345703 +[2025-04-29 09:30:37,198][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 0.9859030246734619, cross_entropy: 0.9859030246734619 +[2025-04-29 09:30:39,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 1.7245328426361084, cross_entropy: 1.7245328426361084 +[2025-04-29 09:30:40,942][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 2.7665858268737793, cross_entropy: 2.7665858268737793 +[2025-04-29 09:30:42,326][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 1.169882893562317, cross_entropy: 1.169882893562317 +[2025-04-29 09:30:44,332][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 1.634013295173645, cross_entropy: 1.634013295173645 +[2025-04-29 09:30:45,648][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 2.104952335357666, cross_entropy: 2.104952335357666 +[2025-04-29 09:30:47,601][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 2.8540267944335938, cross_entropy: 2.8540267944335938 +[2025-04-29 09:30:49,016][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 0.829436182975769, cross_entropy: 0.829436182975769 +[2025-04-29 09:30:50,918][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 0.9542533755302429, cross_entropy: 0.9542533755302429 +[2025-04-29 09:30:52,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 1.019079327583313, cross_entropy: 1.019079327583313 +[2025-04-29 09:30:54,117][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.698161005973816, cross_entropy: 1.698161005973816 +[2025-04-29 09:30:55,700][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.622420310974121, cross_entropy: 1.622420310974121 +[2025-04-29 09:30:57,551][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 3.052340507507324, cross_entropy: 3.052340507507324 +[2025-04-29 09:30:58,756][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 3.092073917388916, cross_entropy: 3.092073917388916 +[2025-04-29 09:31:00,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 2.9002065658569336, cross_entropy: 2.9002065658569336 +[2025-04-29 09:31:02,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 1.5265628099441528, cross_entropy: 1.5265628099441528 +[2025-04-29 09:31:04,270][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 0.9939385056495667, cross_entropy: 0.9939385056495667 +[2025-04-29 09:31:05,954][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.9682852625846863, cross_entropy: 0.9682852625846863 +[2025-04-29 09:31:07,947][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 2.2501213550567627, cross_entropy: 2.2501213550567627 +[2025-04-29 09:31:08,891][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.4487420320510864, cross_entropy: 1.4487420320510864 +[2025-04-29 09:31:11,651][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.4364933967590332, cross_entropy: 1.4364933967590332 +[2025-04-29 09:31:12,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.805320143699646, cross_entropy: 0.805320143699646 +[2025-04-29 09:31:16,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.7922475337982178, cross_entropy: 2.7922475337982178 +[2025-04-29 09:31:17,093][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 2.5677545070648193, cross_entropy: 2.5677545070648193 +[2025-04-29 09:31:19,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 1.0041213035583496, cross_entropy: 1.0041213035583496 +[2025-04-29 09:31:20,342][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 2.750669479370117, cross_entropy: 2.750669479370117 +[2025-04-29 09:31:23,236][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 0.9807324409484863, cross_entropy: 0.9807324409484863 +[2025-04-29 09:31:23,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.849071979522705, cross_entropy: 2.849071979522705 +[2025-04-29 09:31:26,228][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 1.1190530061721802, cross_entropy: 1.1190530061721802 +[2025-04-29 09:31:26,667][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.758730411529541, cross_entropy: 1.758730411529541 +[2025-04-29 09:31:30,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.9907772541046143, cross_entropy: 1.9907772541046143 +[2025-04-29 09:31:30,493][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 2.6136157512664795, cross_entropy: 2.6136157512664795 +[2025-04-29 09:31:33,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 2.8716537952423096, cross_entropy: 2.8716537952423096 +[2025-04-29 09:31:33,868][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.9789243936538696, cross_entropy: 1.9789243936538696 +[2025-04-29 09:31:36,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 0.864589273929596, cross_entropy: 0.864589273929596 +[2025-04-29 09:31:37,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 2.2169342041015625, cross_entropy: 2.2169342041015625 +[2025-04-29 09:31:39,956][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 0.8701536655426025, cross_entropy: 0.8701536655426025 +[2025-04-29 09:31:41,080][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 0.9128366708755493, cross_entropy: 0.9128366708755493 +[2025-04-29 09:31:43,513][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 1.4180772304534912, cross_entropy: 1.4180772304534912 +[2025-04-29 09:31:45,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 1.0823605060577393, cross_entropy: 1.0823605060577393 +[2025-04-29 09:31:46,637][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 1.5014927387237549, cross_entropy: 1.5014927387237549 +[2025-04-29 09:31:49,278][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.027989387512207, cross_entropy: 2.027989387512207 +[2025-04-29 09:31:50,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.6567254066467285, cross_entropy: 1.6567254066467285 +[2025-04-29 09:31:52,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.7248107194900513, cross_entropy: 0.7248107194900513 +[2025-04-29 09:31:54,024][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 3.0080463886260986, cross_entropy: 3.0080463886260986 +[2025-04-29 09:31:55,576][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.2289843559265137, cross_entropy: 2.2289843559265137 +[2025-04-29 09:31:57,328][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 0.9433447122573853, cross_entropy: 0.9433447122573853 +[2025-04-29 09:31:59,008][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 1.5610088109970093, cross_entropy: 1.5610088109970093 +[2025-04-29 09:32:00,609][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 2.589205503463745, cross_entropy: 2.589205503463745 +[2025-04-29 09:32:02,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 1.1195646524429321, cross_entropy: 1.1195646524429321 +[2025-04-29 09:32:03,794][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 1.0648431777954102, cross_entropy: 1.0648431777954102 +[2025-04-29 09:32:05,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 1.4383922815322876, cross_entropy: 1.4383922815322876 +[2025-04-29 09:32:06,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 0.7646579742431641, cross_entropy: 0.7646579742431641 +[2025-04-29 09:32:09,162][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.779024124145508, cross_entropy: 2.779024124145508 +[2025-04-29 09:32:09,942][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 2.3645739555358887, cross_entropy: 2.3645739555358887 +[2025-04-29 09:32:12,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.0940327644348145, cross_entropy: 2.0940327644348145 +[2025-04-29 09:32:12,950][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 2.857132911682129, cross_entropy: 2.857132911682129 +[2025-04-29 09:32:15,468][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.6746256351470947, cross_entropy: 2.6746256351470947 +[2025-04-29 09:32:16,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.8096518516540527, cross_entropy: 1.8096518516540527 +[2025-04-29 09:32:19,174][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 1.1270034313201904, cross_entropy: 1.1270034313201904 +[2025-04-29 09:32:19,924][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.4862427711486816, cross_entropy: 2.4862427711486816 +[2025-04-29 09:32:22,491][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 2.7550880908966064, cross_entropy: 2.7550880908966064 +[2025-04-29 09:32:23,220][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 2.5752339363098145, cross_entropy: 2.5752339363098145 +[2025-04-29 09:32:25,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 0.8673228025436401, cross_entropy: 0.8673228025436401 +[2025-04-29 09:32:26,505][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 0.8286517262458801, cross_entropy: 0.8286517262458801 +[2025-04-29 09:32:29,682][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 0.9852684140205383, cross_entropy: 0.9852684140205383 +[2025-04-29 09:32:30,006][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 1.4971427917480469, cross_entropy: 1.4971427917480469 +[2025-04-29 09:32:32,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 0.9735962152481079, cross_entropy: 0.9735962152481079 +[2025-04-29 09:32:32,920][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.034067153930664, cross_entropy: 1.034067153930664 +[2025-04-29 09:32:36,080][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 1.3351225852966309, cross_entropy: 1.3351225852966309 +[2025-04-29 09:32:36,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 0.977145254611969, cross_entropy: 0.977145254611969 +[2025-04-29 09:32:39,590][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 2.9346532821655273, cross_entropy: 2.9346532821655273 +[2025-04-29 09:32:39,903][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 0.7736610174179077, cross_entropy: 0.7736610174179077 +[2025-04-29 09:32:42,376][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.583139419555664, cross_entropy: 2.583139419555664 +[2025-04-29 09:32:42,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 2.384704113006592, cross_entropy: 2.384704113006592 +[2025-04-29 09:32:45,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.135931372642517, cross_entropy: 1.135931372642517 +[2025-04-29 09:32:45,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 0.9529094099998474, cross_entropy: 0.9529094099998474 +[2025-04-29 09:32:49,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.1668825149536133, cross_entropy: 2.1668825149536133 +[2025-04-29 09:32:50,172][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.1693944931030273, cross_entropy: 2.1693944931030273 +[2025-04-29 09:32:52,859][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 1.3718531131744385, cross_entropy: 1.3718531131744385 +[2025-04-29 09:32:53,552][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 2.1835289001464844, cross_entropy: 2.1835289001464844 +[2025-04-29 09:32:57,060][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 1.074716567993164, cross_entropy: 1.074716567993164 +[2025-04-29 09:32:57,432][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 2.3309266567230225, cross_entropy: 2.3309266567230225 +[2025-04-29 09:33:00,360][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.4215619564056396, cross_entropy: 1.4215619564056396 +[2025-04-29 09:33:01,275][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.06130313873291, cross_entropy: 2.06130313873291 +[2025-04-29 09:33:03,492][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 2.7017993927001953, cross_entropy: 2.7017993927001953 +[2025-04-29 09:33:05,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 3.0575690269470215, cross_entropy: 3.0575690269470215 +[2025-04-29 09:33:06,674][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 0.6848691701889038, cross_entropy: 0.6848691701889038 +[2025-04-29 09:33:08,242][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 1.666816234588623, cross_entropy: 1.666816234588623 +[2025-04-29 09:33:09,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.3514220714569092, cross_entropy: 1.3514220714569092 +[2025-04-29 09:33:11,637][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 2.663445472717285, cross_entropy: 2.663445472717285 +[2025-04-29 09:33:12,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.7755203247070312, cross_entropy: 2.7755203247070312 +[2025-04-29 09:33:14,824][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.28499698638916, cross_entropy: 2.28499698638916 +[2025-04-29 09:33:15,861][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 1.4201629161834717, cross_entropy: 1.4201629161834717 +[2025-04-29 09:33:18,401][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 0.773412823677063, cross_entropy: 0.773412823677063 +[2025-04-29 09:33:19,643][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 0.9005213379859924, cross_entropy: 0.9005213379859924 +[2025-04-29 09:33:22,322][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 2.339603900909424, cross_entropy: 2.339603900909424 +[2025-04-29 09:33:23,138][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.059303879737854, cross_entropy: 1.059303879737854 +[2025-04-29 09:33:25,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 2.5443546772003174, cross_entropy: 2.5443546772003174 +[2025-04-29 09:33:26,468][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.592233419418335, cross_entropy: 1.592233419418335 +[2025-04-29 09:33:29,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 0.9954339861869812, cross_entropy: 0.9954339861869812 +[2025-04-29 09:33:29,911][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 0.8256481885910034, cross_entropy: 0.8256481885910034 +[2025-04-29 09:33:32,879][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 2.3028507232666016, cross_entropy: 2.3028507232666016 +[2025-04-29 09:33:33,254][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 1.0105057954788208, cross_entropy: 1.0105057954788208 +[2025-04-29 09:33:35,987][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 2.361806869506836, cross_entropy: 2.361806869506836 +[2025-04-29 09:33:37,139][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 1.01456880569458, cross_entropy: 1.01456880569458 +[2025-04-29 09:33:39,336][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.4426769018173218, cross_entropy: 1.4426769018173218 +[2025-04-29 09:33:40,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.8734562397003174, cross_entropy: 2.8734562397003174 +[2025-04-29 09:33:42,829][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 2.319774627685547, cross_entropy: 2.319774627685547 +[2025-04-29 09:33:44,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 1.3438200950622559, cross_entropy: 1.3438200950622559 +[2025-04-29 09:33:46,346][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 2.468513011932373, cross_entropy: 2.468513011932373 +[2025-04-29 09:33:47,423][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 0.7113193273544312, cross_entropy: 0.7113193273544312 +[2025-04-29 09:33:49,358][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 3.047910213470459, cross_entropy: 3.047910213470459 +[2025-04-29 09:33:50,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.6937592029571533, cross_entropy: 2.6937592029571533 +[2025-04-29 09:33:52,232][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.968440055847168, cross_entropy: 1.968440055847168 +[2025-04-29 09:33:54,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.3288118839263916, cross_entropy: 1.3288118839263916 +[2025-04-29 09:33:55,358][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.6814258098602295, cross_entropy: 1.6814258098602295 +[2025-04-29 09:33:58,204][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 1.5377204418182373, cross_entropy: 1.5377204418182373 +[2025-04-29 09:33:58,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 2.8565101623535156, cross_entropy: 2.8565101623535156 +[2025-04-29 09:34:01,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.9989677667617798, cross_entropy: 1.9989677667617798 +[2025-04-29 09:34:02,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 3.0327467918395996, cross_entropy: 3.0327467918395996 +[2025-04-29 09:34:04,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 1.7031885385513306, cross_entropy: 1.7031885385513306 +[2025-04-29 09:34:05,190][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 1.0864479541778564, cross_entropy: 1.0864479541778564 +[2025-04-29 09:34:07,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 1.0376946926116943, cross_entropy: 1.0376946926116943 +[2025-04-29 09:34:08,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.1118863821029663, cross_entropy: 1.1118863821029663 +[2025-04-29 09:34:12,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 1.1714681386947632, cross_entropy: 1.1714681386947632 +[2025-04-29 09:34:12,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 1.2686930894851685, cross_entropy: 1.2686930894851685 +[2025-04-29 09:34:15,181][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 0.9842953681945801, cross_entropy: 0.9842953681945801 +[2025-04-29 09:34:15,521][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 0.8647026419639587, cross_entropy: 0.8647026419639587 +[2025-04-29 09:34:18,940][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 0.751217782497406, cross_entropy: 0.751217782497406 +[2025-04-29 09:34:19,280][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 2.3034729957580566, cross_entropy: 2.3034729957580566 +[2025-04-29 09:34:22,312][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 2.979684829711914, cross_entropy: 2.979684829711914 +[2025-04-29 09:34:22,651][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.4505562782287598, cross_entropy: 2.4505562782287598 +[2025-04-29 09:34:25,778][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 2.722360849380493, cross_entropy: 2.722360849380493 +[2025-04-29 09:34:26,122][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 0.7492391467094421, cross_entropy: 0.7492391467094421 +[2025-04-29 09:34:28,428][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 0.6255843639373779, cross_entropy: 0.6255843639373779 +[2025-04-29 09:34:29,042][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 1.213552713394165, cross_entropy: 1.213552713394165 +[2025-04-29 09:34:31,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.6634401082992554, cross_entropy: 1.6634401082992554 +[2025-04-29 09:34:32,715][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 1.3113703727722168, cross_entropy: 1.3113703727722168 +[2025-04-29 09:34:35,497][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 1.5784120559692383, cross_entropy: 1.5784120559692383 +[2025-04-29 09:34:36,514][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.7095366716384888, cross_entropy: 1.7095366716384888 +[2025-04-29 09:34:38,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.182689666748047, cross_entropy: 2.182689666748047 +[2025-04-29 09:34:39,531][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.0537446737289429, cross_entropy: 1.0537446737289429 +[2025-04-29 09:34:42,249][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 2.519784927368164, cross_entropy: 2.519784927368164 +[2025-04-29 09:34:43,082][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.0521457195281982, cross_entropy: 1.0521457195281982 +[2025-04-29 09:34:45,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 2.9463820457458496, cross_entropy: 2.9463820457458496 +[2025-04-29 09:34:46,392][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 0.8352838754653931, cross_entropy: 0.8352838754653931 +[2025-04-29 09:34:48,997][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 2.421752452850342, cross_entropy: 2.421752452850342 +[2025-04-29 09:34:50,348][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 1.454713225364685, cross_entropy: 1.454713225364685 +[2025-04-29 09:34:52,208][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 0.7427130937576294, cross_entropy: 0.7427130937576294 +[2025-04-29 09:34:54,199][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 1.8412773609161377, cross_entropy: 1.8412773609161377 +[2025-04-29 09:34:55,769][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 2.772292375564575, cross_entropy: 2.772292375564575 +[2025-04-29 09:34:57,692][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 1.1043775081634521, cross_entropy: 1.1043775081634521 +[2025-04-29 09:34:59,511][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 2.536649465560913, cross_entropy: 2.536649465560913 +[2025-04-29 09:35:01,114][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 2.2083230018615723, cross_entropy: 2.2083230018615723 +[2025-04-29 09:35:03,690][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.0523533821105957, cross_entropy: 2.0523533821105957 +[2025-04-29 09:35:04,395][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 2.8416247367858887, cross_entropy: 2.8416247367858887 +[2025-04-29 09:35:07,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.6716790199279785, cross_entropy: 2.6716790199279785 +[2025-04-29 09:35:07,854][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 2.8689961433410645, cross_entropy: 2.8689961433410645 +[2025-04-29 09:35:10,796][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 1.1224207878112793, cross_entropy: 1.1224207878112793 +[2025-04-29 09:35:11,764][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.3258758783340454, cross_entropy: 1.3258758783340454 +[2025-04-29 09:35:14,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.07033109664917, cross_entropy: 1.07033109664917 +[2025-04-29 09:35:14,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.3062679767608643, cross_entropy: 1.3062679767608643 +[2025-04-29 09:35:16,774][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.1715199947357178, cross_entropy: 2.1715199947357178 +[2025-04-29 09:35:18,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 0.5928058624267578, cross_entropy: 0.5928058624267578 +[2025-04-29 09:35:19,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 2.846871852874756, cross_entropy: 2.846871852874756 +[2025-04-29 09:35:21,411][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 1.2593536376953125, cross_entropy: 1.2593536376953125 +[2025-04-29 09:35:23,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 0.8874156475067139, cross_entropy: 0.8874156475067139 +[2025-04-29 09:35:24,484][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.74828839302063, cross_entropy: 2.74828839302063 +[2025-04-29 09:35:26,856][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.4886486530303955, cross_entropy: 1.4886486530303955 +[2025-04-29 09:35:28,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 1.1312143802642822, cross_entropy: 1.1312143802642822 +[2025-04-29 09:35:30,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 0.9638429284095764, cross_entropy: 0.9638429284095764 +[2025-04-29 09:35:32,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 0.9698507189750671, cross_entropy: 0.9698507189750671 +[2025-04-29 09:35:33,651][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 2.5894250869750977, cross_entropy: 2.5894250869750977 +[2025-04-29 09:35:35,714][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 1.8180108070373535, cross_entropy: 1.8180108070373535 +[2025-04-29 09:35:36,850][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 1.6827754974365234, cross_entropy: 1.6827754974365234 +[2025-04-29 09:35:39,195][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 0.7523576021194458, cross_entropy: 0.7523576021194458 +[2025-04-29 09:35:40,265][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 0.9987187385559082, cross_entropy: 0.9987187385559082 +[2025-04-29 09:35:42,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 2.2617273330688477, cross_entropy: 2.2617273330688477 +[2025-04-29 09:35:43,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 0.9164836406707764, cross_entropy: 0.9164836406707764 +[2025-04-29 09:35:46,314][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 2.7366676330566406, cross_entropy: 2.7366676330566406 +[2025-04-29 09:35:46,765][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 1.784052848815918, cross_entropy: 1.784052848815918 +[2025-04-29 09:35:49,884][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 2.7446417808532715, cross_entropy: 2.7446417808532715 +[2025-04-29 09:35:50,198][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 1.1291065216064453, cross_entropy: 1.1291065216064453 +[2025-04-29 09:35:53,387][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 0.9101085662841797, cross_entropy: 0.9101085662841797 +[2025-04-29 09:35:53,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 2.7866406440734863, cross_entropy: 2.7866406440734863 +[2025-04-29 09:35:56,925][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 1.0353574752807617, cross_entropy: 1.0353574752807617 +[2025-04-29 09:35:57,268][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 0.9529738426208496, cross_entropy: 0.9529738426208496 +[2025-04-29 09:36:00,650][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 1.7089323997497559, cross_entropy: 1.7089323997497559 +[2025-04-29 09:36:00,990][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 2.9308340549468994, cross_entropy: 2.9308340549468994 +[2025-04-29 09:36:04,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 2.361313581466675, cross_entropy: 2.361313581466675 +[2025-04-29 09:36:04,930][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.8964306116104126, cross_entropy: 1.8964306116104126 +[2025-04-29 09:36:08,213][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 1.0250587463378906, cross_entropy: 1.0250587463378906 +[2025-04-29 09:36:08,527][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 1.9966310262680054, cross_entropy: 1.9966310262680054 +[2025-04-29 09:36:11,676][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 1.6179633140563965, cross_entropy: 1.6179633140563965 +[2025-04-29 09:36:12,019][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 2.727130651473999, cross_entropy: 2.727130651473999 +[2025-04-29 09:36:14,934][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 1.676235556602478, cross_entropy: 1.676235556602478 +[2025-04-29 09:36:15,277][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 3.243058204650879, cross_entropy: 3.243058204650879 +[2025-04-29 09:36:17,867][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 1.6321933269500732, cross_entropy: 1.6321933269500732 +[2025-04-29 09:36:18,214][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 0.8693448305130005, cross_entropy: 0.8693448305130005 +[2025-04-29 09:36:20,978][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 0.9094974994659424, cross_entropy: 0.9094974994659424 +[2025-04-29 09:36:21,317][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 2.7330806255340576, cross_entropy: 2.7330806255340576 +[2025-04-29 09:36:24,314][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.6294362545013428, cross_entropy: 2.6294362545013428 +[2025-04-29 09:36:24,627][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 2.377425193786621, cross_entropy: 2.377425193786621 +[2025-04-29 09:36:28,432][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.507387161254883, cross_entropy: 2.507387161254883 +[2025-04-29 09:36:28,769][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.2078442573547363, cross_entropy: 2.2078442573547363 +[2025-04-29 09:36:32,005][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 2.085684299468994, cross_entropy: 2.085684299468994 +[2025-04-29 09:36:32,350][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.8161354064941406, cross_entropy: 2.8161354064941406 +[2025-04-29 09:36:36,113][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 1.0005744695663452, cross_entropy: 1.0005744695663452 +[2025-04-29 09:36:36,455][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 3.0794718265533447, cross_entropy: 3.0794718265533447 +[2025-04-29 09:36:39,129][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 1.7193026542663574, cross_entropy: 1.7193026542663574 +[2025-04-29 09:36:39,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 0.7160004377365112, cross_entropy: 0.7160004377365112 +[2025-04-29 09:36:42,464][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 1.3145976066589355, cross_entropy: 1.3145976066589355 +[2025-04-29 09:36:42,807][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 0.9961091876029968, cross_entropy: 0.9961091876029968 +[2025-04-29 09:36:45,916][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 1.575204849243164, cross_entropy: 1.575204849243164 +[2025-04-29 09:36:46,263][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.0338990688323975, cross_entropy: 1.0338990688323975 +[2025-04-29 09:36:48,967][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.716684341430664, cross_entropy: 2.716684341430664 +[2025-04-29 09:36:49,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 0.6199342012405396, cross_entropy: 0.6199342012405396 +[2025-04-29 09:36:52,984][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 2.9051284790039062, cross_entropy: 2.9051284790039062 +[2025-04-29 09:36:53,327][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 1.1081489324569702, cross_entropy: 1.1081489324569702 +[2025-04-29 09:36:56,194][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.3074158430099487, cross_entropy: 1.3074158430099487 +[2025-04-29 09:36:56,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 2.7877726554870605, cross_entropy: 2.7877726554870605 +[2025-04-29 09:36:59,564][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.7492982149124146, cross_entropy: 1.7492982149124146 +[2025-04-29 09:36:59,909][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 1.217646598815918, cross_entropy: 1.217646598815918 +[2025-04-29 09:37:03,153][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 1.7752732038497925, cross_entropy: 1.7752732038497925 +[2025-04-29 09:37:03,489][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 0.9487940073013306, cross_entropy: 0.9487940073013306 +[2025-04-29 09:37:06,538][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.1854076385498047, cross_entropy: 2.1854076385498047 +[2025-04-29 09:37:06,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 2.4888229370117188, cross_entropy: 2.4888229370117188 +[2025-04-29 09:37:09,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 2.6669580936431885, cross_entropy: 2.6669580936431885 +[2025-04-29 09:37:09,979][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 1.0131791830062866, cross_entropy: 1.0131791830062866 +[2025-04-29 09:37:13,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 1.5619091987609863, cross_entropy: 1.5619091987609863 +[2025-04-29 09:37:13,402][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 3.019470691680908, cross_entropy: 3.019470691680908 +[2025-04-29 09:37:16,533][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 1.2726030349731445, cross_entropy: 1.2726030349731445 +[2025-04-29 09:37:17,396][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 1.5918121337890625, cross_entropy: 1.5918121337890625 +[2025-04-29 09:37:20,440][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 2.3009679317474365, cross_entropy: 2.3009679317474365 +[2025-04-29 09:37:20,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 0.6284034252166748, cross_entropy: 0.6284034252166748 +[2025-04-29 09:37:23,913][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 1.688476800918579, cross_entropy: 1.688476800918579 +[2025-04-29 09:37:24,254][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.2774198055267334, cross_entropy: 1.2774198055267334 +[2025-04-29 09:37:27,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.546690583229065, cross_entropy: 1.546690583229065 +[2025-04-29 09:37:28,073][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.29117751121521, cross_entropy: 1.29117751121521 +[2025-04-29 09:37:31,194][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 0.8328604698181152, cross_entropy: 0.8328604698181152 +[2025-04-29 09:37:31,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 1.837287425994873, cross_entropy: 1.837287425994873 +[2025-04-29 09:37:34,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.5235836505889893, cross_entropy: 1.5235836505889893 +[2025-04-29 09:37:34,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.039394497871399, cross_entropy: 1.039394497871399 +[2025-04-29 09:37:38,110][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.341366767883301, cross_entropy: 2.341366767883301 +[2025-04-29 09:37:38,463][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 3.0529918670654297, cross_entropy: 3.0529918670654297 +[2025-04-29 09:37:41,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.810502529144287, cross_entropy: 2.810502529144287 +[2025-04-29 09:37:41,961][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 0.9096999764442444, cross_entropy: 0.9096999764442444 +[2025-04-29 09:37:44,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 2.240910053253174, cross_entropy: 2.240910053253174 +[2025-04-29 09:37:45,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 0.8357922434806824, cross_entropy: 0.8357922434806824 +[2025-04-29 09:37:47,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 0.9080339074134827, cross_entropy: 0.9080339074134827 +[2025-04-29 09:37:48,949][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 1.5629713535308838, cross_entropy: 1.5629713535308838 +[2025-04-29 09:37:51,586][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.110695481300354, cross_entropy: 1.110695481300354 +[2025-04-29 09:37:52,111][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 3.132920742034912, cross_entropy: 3.132920742034912 +[2025-04-29 09:37:54,873][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 0.9793155193328857, cross_entropy: 0.9793155193328857 +[2025-04-29 09:37:55,304][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.9503579139709473, cross_entropy: 2.9503579139709473 +[2025-04-29 09:37:58,136][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 1.6032114028930664, cross_entropy: 1.6032114028930664 +[2025-04-29 09:37:58,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.41619873046875, cross_entropy: 1.41619873046875 +[2025-04-29 09:38:01,229][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 2.106523036956787, cross_entropy: 2.106523036956787 +[2025-04-29 09:38:01,983][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 2.6714961528778076, cross_entropy: 2.6714961528778076 +[2025-04-29 09:38:04,447][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 1.1688346862792969, cross_entropy: 1.1688346862792969 +[2025-04-29 09:38:06,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 0.9912568926811218, cross_entropy: 0.9912568926811218 +[2025-04-29 09:38:08,071][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 1.2273223400115967, cross_entropy: 1.2273223400115967 +[2025-04-29 09:38:10,277][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 0.8508433699607849, cross_entropy: 0.8508433699607849 +[2025-04-29 09:38:11,633][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.6414899826049805, cross_entropy: 2.6414899826049805 +[2025-04-29 09:38:13,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 1.6045607328414917, cross_entropy: 1.6045607328414917 +[2025-04-29 09:38:15,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 0.6002262830734253, cross_entropy: 0.6002262830734253 +[2025-04-29 09:38:17,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 2.916917324066162, cross_entropy: 2.916917324066162 +[2025-04-29 09:38:18,292][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 0.9094399809837341, cross_entropy: 0.9094399809837341 +[2025-04-29 09:38:21,479][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 1.7443040609359741, cross_entropy: 1.7443040609359741 +[2025-04-29 09:38:21,820][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 2.7494864463806152, cross_entropy: 2.7494864463806152 +[2025-04-29 09:38:24,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 1.9950737953186035, cross_entropy: 1.9950737953186035 +[2025-04-29 09:38:25,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.7971723079681396, cross_entropy: 2.7971723079681396 +[2025-04-29 09:38:27,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 1.9639222621917725, cross_entropy: 1.9639222621917725 +[2025-04-29 09:38:28,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 1.4004740715026855, cross_entropy: 1.4004740715026855 +[2025-04-29 09:38:30,972][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 1.4167909622192383, cross_entropy: 1.4167909622192383 +[2025-04-29 09:38:32,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 1.3308056592941284, cross_entropy: 1.3308056592941284 +[2025-04-29 09:38:34,957][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 0.8243083357810974, cross_entropy: 0.8243083357810974 +[2025-04-29 09:38:36,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 2.8060078620910645, cross_entropy: 2.8060078620910645 +[2025-04-29 09:38:38,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 2.7744717597961426, cross_entropy: 2.7744717597961426 +[2025-04-29 09:38:39,251][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 2.695296049118042, cross_entropy: 2.695296049118042 +[2025-04-29 09:38:42,503][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.2261779308319092, cross_entropy: 1.2261779308319092 +[2025-04-29 09:38:43,009][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 1.4665019512176514, cross_entropy: 1.4665019512176514 +[2025-04-29 09:38:46,085][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.1624219417572021, cross_entropy: 1.1624219417572021 +[2025-04-29 09:38:46,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 1.9849700927734375, cross_entropy: 1.9849700927734375 +[2025-04-29 09:38:50,707][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.2496347427368164, cross_entropy: 1.2496347427368164 +[2025-04-29 09:38:51,050][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 1.02817702293396, cross_entropy: 1.02817702293396 +[2025-04-29 09:38:54,066][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 0.7976090908050537, cross_entropy: 0.7976090908050537 +[2025-04-29 09:38:54,379][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.7669739723205566, cross_entropy: 2.7669739723205566 +[2025-04-29 09:38:57,473][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 0.8114895820617676, cross_entropy: 0.8114895820617676 +[2025-04-29 09:38:57,811][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.6777799129486084, cross_entropy: 2.6777799129486084 +[2025-04-29 09:39:01,074][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.386415481567383, cross_entropy: 2.386415481567383 +[2025-04-29 09:39:01,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.1016111373901367, cross_entropy: 1.1016111373901367 +[2025-04-29 09:39:04,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 2.18829345703125, cross_entropy: 2.18829345703125 +[2025-04-29 09:39:04,535][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 2.3294126987457275, cross_entropy: 2.3294126987457275 +[2025-04-29 09:39:07,236][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.471295952796936, cross_entropy: 1.471295952796936 +[2025-04-29 09:39:07,576][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 2.8590712547302246, cross_entropy: 2.8590712547302246 +[2025-04-29 09:39:10,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 0.8819919228553772, cross_entropy: 0.8819919228553772 +[2025-04-29 09:39:11,044][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.3037548065185547, cross_entropy: 1.3037548065185547 +[2025-04-29 09:39:15,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.330906867980957, cross_entropy: 1.330906867980957 +[2025-04-29 09:39:15,488][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 0.8295150399208069, cross_entropy: 0.8295150399208069 +[2025-04-29 09:39:18,718][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 2.7535505294799805, cross_entropy: 2.7535505294799805 +[2025-04-29 09:39:19,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 0.8459116220474243, cross_entropy: 0.8459116220474243 +[2025-04-29 09:39:22,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 1.3240153789520264, cross_entropy: 1.3240153789520264 +[2025-04-29 09:39:22,758][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.7082395553588867, cross_entropy: 1.7082395553588867 +[2025-04-29 09:39:25,512][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 1.3722755908966064, cross_entropy: 1.3722755908966064 +[2025-04-29 09:39:26,037][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.523985505104065, cross_entropy: 1.523985505104065 +[2025-04-29 09:39:28,932][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 1.9987597465515137, cross_entropy: 1.9987597465515137 +[2025-04-29 09:39:29,301][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 1.6384822130203247, cross_entropy: 1.6384822130203247 +[2025-04-29 09:39:31,932][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.1867215633392334, cross_entropy: 1.1867215633392334 +[2025-04-29 09:39:32,984][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 2.9754717350006104, cross_entropy: 2.9754717350006104 +[2025-04-29 09:39:35,226][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.4790523052215576, cross_entropy: 2.4790523052215576 +[2025-04-29 09:39:35,820][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 0.8235214352607727, cross_entropy: 0.8235214352607727 +[2025-04-29 09:39:38,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 2.7893195152282715, cross_entropy: 2.7893195152282715 +[2025-04-29 09:39:39,343][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.1012331247329712, cross_entropy: 1.1012331247329712 +[2025-04-29 09:39:41,480][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 2.2455124855041504, cross_entropy: 2.2455124855041504 +[2025-04-29 09:39:42,547][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 0.9742763042449951, cross_entropy: 0.9742763042449951 +[2025-04-29 09:39:44,768][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 0.7326717972755432, cross_entropy: 0.7326717972755432 +[2025-04-29 09:39:46,163][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.594658613204956, cross_entropy: 1.594658613204956 +[2025-04-29 09:39:48,185][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.279726266860962, cross_entropy: 1.279726266860962 +[2025-04-29 09:39:49,206][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.4068286418914795, cross_entropy: 1.4068286418914795 +[2025-04-29 09:39:51,410][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 1.2470697164535522, cross_entropy: 1.2470697164535522 +[2025-04-29 09:39:52,712][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 0.9580010771751404, cross_entropy: 0.9580010771751404 +[2025-04-29 09:39:54,486][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 0.8117750883102417, cross_entropy: 0.8117750883102417 +[2025-04-29 09:39:55,871][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 2.117912769317627, cross_entropy: 2.117912769317627 +[2025-04-29 09:39:57,807][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 2.3070430755615234, cross_entropy: 2.3070430755615234 +[2025-04-29 09:40:00,091][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 1.1821820735931396, cross_entropy: 1.1821820735931396 +[2025-04-29 09:40:00,847][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 2.5594887733459473, cross_entropy: 2.5594887733459473 +[2025-04-29 09:40:03,675][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.169461727142334, cross_entropy: 1.169461727142334 +[2025-04-29 09:40:04,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.3432166576385498, cross_entropy: 1.3432166576385498 +[2025-04-29 09:40:07,262][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 1.3473583459854126, cross_entropy: 1.3473583459854126 +[2025-04-29 09:40:07,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.8902227878570557, cross_entropy: 1.8902227878570557 +[2025-04-29 09:40:11,515][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.6919009685516357, cross_entropy: 2.6919009685516357 +[2025-04-29 09:40:11,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.352159023284912, cross_entropy: 2.352159023284912 +[2025-04-29 09:40:15,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.1765751838684082, cross_entropy: 1.1765751838684082 +[2025-04-29 09:40:16,290][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.1292999982833862, cross_entropy: 1.1292999982833862 +[2025-04-29 09:40:19,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 1.3978203535079956, cross_entropy: 1.3978203535079956 +[2025-04-29 09:40:19,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.384228229522705, cross_entropy: 2.384228229522705 +[2025-04-29 09:40:23,083][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.3351500034332275, cross_entropy: 1.3351500034332275 +[2025-04-29 09:40:23,429][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.6949939727783203, cross_entropy: 2.6949939727783203 +[2025-04-29 09:40:26,803][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 2.1620259284973145, cross_entropy: 2.1620259284973145 +[2025-04-29 09:40:27,141][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.3744361400604248, cross_entropy: 1.3744361400604248 +[2025-04-29 09:40:30,212][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 2.4062185287475586, cross_entropy: 2.4062185287475586 +[2025-04-29 09:40:30,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 3.1601929664611816, cross_entropy: 3.1601929664611816 +[2025-04-29 09:40:33,244][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.210280418395996, cross_entropy: 2.210280418395996 +[2025-04-29 09:40:33,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 2.6914987564086914, cross_entropy: 2.6914987564086914 +[2025-04-29 09:40:35,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 2.415684938430786, cross_entropy: 2.415684938430786 +[2025-04-29 09:43:19,076][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.7458596229553223, cross_entropy: 1.7458596229553223 +[2025-04-29 09:43:19,077][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.318480372428894, cross_entropy: 1.318480372428894 +[2025-04-29 09:43:19,241][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch8.pth. +[2025-04-29 09:43:19,458][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 09:43:23,603][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 0.9357752203941345, cross_entropy: 0.9357752203941345 +[2025-04-29 09:43:23,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 2.5287368297576904, cross_entropy: 2.5287368297576904 +[2025-04-29 09:43:27,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 1.8593281507492065, cross_entropy: 1.8593281507492065 +[2025-04-29 09:43:27,664][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 2.003109931945801, cross_entropy: 2.003109931945801 +[2025-04-29 09:43:30,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 0.5909450054168701, cross_entropy: 0.5909450054168701 +[2025-04-29 09:43:31,132][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 0.6655703783035278, cross_entropy: 0.6655703783035278 +[2025-04-29 09:43:34,363][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.8264782428741455, cross_entropy: 2.8264782428741455 +[2025-04-29 09:43:34,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 0.6287156343460083, cross_entropy: 0.6287156343460083 +[2025-04-29 09:43:37,980][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 0.8293671607971191, cross_entropy: 0.8293671607971191 +[2025-04-29 09:43:38,360][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 2.093287467956543, cross_entropy: 2.093287467956543 +[2025-04-29 09:43:41,497][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 0.9505739212036133, cross_entropy: 0.9505739212036133 +[2025-04-29 09:43:41,836][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.9162289500236511, cross_entropy: 0.9162289500236511 +[2025-04-29 09:43:44,608][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.3546066284179688, cross_entropy: 2.3546066284179688 +[2025-04-29 09:43:44,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 0.90740966796875, cross_entropy: 0.90740966796875 +[2025-04-29 09:43:48,442][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 1.4408940076828003, cross_entropy: 1.4408940076828003 +[2025-04-29 09:43:48,754][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.623927116394043, cross_entropy: 0.623927116394043 +[2025-04-29 09:43:51,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 2.738398790359497, cross_entropy: 2.738398790359497 +[2025-04-29 09:43:52,438][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 2.3074536323547363, cross_entropy: 2.3074536323547363 +[2025-04-29 09:43:56,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.9457159042358398, cross_entropy: 1.9457159042358398 +[2025-04-29 09:43:56,634][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 2.7594642639160156, cross_entropy: 2.7594642639160156 +[2025-04-29 09:43:59,728][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 0.7043756246566772, cross_entropy: 0.7043756246566772 +[2025-04-29 09:44:00,088][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 2.607448101043701, cross_entropy: 2.607448101043701 +[2025-04-29 09:44:04,136][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.3107876777648926, cross_entropy: 2.3107876777648926 +[2025-04-29 09:44:04,478][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.8012309074401855, cross_entropy: 2.8012309074401855 +[2025-04-29 09:44:08,253][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 1.917386770248413, cross_entropy: 1.917386770248413 +[2025-04-29 09:44:08,595][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 0.8527907729148865, cross_entropy: 0.8527907729148865 +[2025-04-29 09:44:11,920][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 2.6181271076202393, cross_entropy: 2.6181271076202393 +[2025-04-29 09:44:12,266][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 1.3667868375778198, cross_entropy: 1.3667868375778198 +[2025-04-29 09:44:15,063][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 1.5378024578094482, cross_entropy: 1.5378024578094482 +[2025-04-29 09:44:15,437][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 2.7074313163757324, cross_entropy: 2.7074313163757324 +[2025-04-29 09:44:18,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 0.8399243354797363, cross_entropy: 0.8399243354797363 +[2025-04-29 09:44:19,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 0.7576590776443481, cross_entropy: 0.7576590776443481 +[2025-04-29 09:44:22,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 0.446975976228714, cross_entropy: 0.446975976228714 +[2025-04-29 09:44:22,493][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 1.4238126277923584, cross_entropy: 1.4238126277923584 +[2025-04-29 09:44:26,363][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 0.8785940408706665, cross_entropy: 0.8785940408706665 +[2025-04-29 09:44:26,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 2.7432217597961426, cross_entropy: 2.7432217597961426 +[2025-04-29 09:44:30,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 2.603057861328125, cross_entropy: 2.603057861328125 +[2025-04-29 09:44:30,677][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 2.9412496089935303, cross_entropy: 2.9412496089935303 +[2025-04-29 09:44:33,482][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 2.758155584335327, cross_entropy: 2.758155584335327 +[2025-04-29 09:44:34,049][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 1.087573528289795, cross_entropy: 1.087573528289795 +[2025-04-29 09:44:37,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 0.6818447113037109, cross_entropy: 0.6818447113037109 +[2025-04-29 09:44:37,748][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 1.8892954587936401, cross_entropy: 1.8892954587936401 +[2025-04-29 09:44:41,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 1.0616326332092285, cross_entropy: 1.0616326332092285 +[2025-04-29 09:44:41,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 2.697282075881958, cross_entropy: 2.697282075881958 +[2025-04-29 09:44:44,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.8747224807739258, cross_entropy: 0.8747224807739258 +[2025-04-29 09:44:45,132][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 2.7907466888427734, cross_entropy: 2.7907466888427734 +[2025-04-29 09:44:47,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.003030300140381, cross_entropy: 3.003030300140381 +[2025-04-29 09:44:48,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 0.7909444570541382, cross_entropy: 0.7909444570541382 +[2025-04-29 09:44:51,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 2.5939440727233887, cross_entropy: 2.5939440727233887 +[2025-04-29 09:44:51,783][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 0.9299176931381226, cross_entropy: 0.9299176931381226 +[2025-04-29 09:44:54,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 2.1456263065338135, cross_entropy: 2.1456263065338135 +[2025-04-29 09:44:55,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 2.8075528144836426, cross_entropy: 2.8075528144836426 +[2025-04-29 09:44:58,665][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 1.916318416595459, cross_entropy: 1.916318416595459 +[2025-04-29 09:44:59,008][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.3249173164367676, cross_entropy: 1.3249173164367676 +[2025-04-29 09:45:02,435][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 1.0216257572174072, cross_entropy: 1.0216257572174072 +[2025-04-29 09:45:02,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 2.9532270431518555, cross_entropy: 2.9532270431518555 +[2025-04-29 09:45:06,488][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.455251932144165, cross_entropy: 1.455251932144165 +[2025-04-29 09:45:06,831][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 1.1036112308502197, cross_entropy: 1.1036112308502197 +[2025-04-29 09:45:09,992][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.8821184635162354, cross_entropy: 1.8821184635162354 +[2025-04-29 09:45:10,516][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 1.901298999786377, cross_entropy: 1.901298999786377 +[2025-04-29 09:45:14,049][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.5010859966278076, cross_entropy: 2.5010859966278076 +[2025-04-29 09:45:14,393][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 1.1059495210647583, cross_entropy: 1.1059495210647583 +[2025-04-29 09:45:17,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 1.6165658235549927, cross_entropy: 1.6165658235549927 +[2025-04-29 09:45:17,666][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 2.424893379211426, cross_entropy: 2.424893379211426 +[2025-04-29 09:45:20,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.748574733734131, cross_entropy: 2.748574733734131 +[2025-04-29 09:45:21,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 2.5673751831054688, cross_entropy: 2.5673751831054688 +[2025-04-29 09:45:24,678][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 1.0423434972763062, cross_entropy: 1.0423434972763062 +[2025-04-29 09:45:25,028][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.5845929384231567, cross_entropy: 0.5845929384231567 +[2025-04-29 09:45:27,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 2.2888026237487793, cross_entropy: 2.2888026237487793 +[2025-04-29 09:45:28,813][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 2.5031299591064453, cross_entropy: 2.5031299591064453 +[2025-04-29 09:45:31,798][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 1.5641450881958008, cross_entropy: 1.5641450881958008 +[2025-04-29 09:45:32,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 2.2365150451660156, cross_entropy: 2.2365150451660156 +[2025-04-29 09:45:35,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 2.37262225151062, cross_entropy: 2.37262225151062 +[2025-04-29 09:45:36,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 2.7852659225463867, cross_entropy: 2.7852659225463867 +[2025-04-29 09:45:39,602][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.955400228500366, cross_entropy: 2.955400228500366 +[2025-04-29 09:45:40,131][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 1.633766531944275, cross_entropy: 1.633766531944275 +[2025-04-29 09:45:43,417][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 1.6201002597808838, cross_entropy: 1.6201002597808838 +[2025-04-29 09:45:43,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 2.5641090869903564, cross_entropy: 2.5641090869903564 +[2025-04-29 09:45:46,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 1.929151177406311, cross_entropy: 1.929151177406311 +[2025-04-29 09:45:47,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 1.8061480522155762, cross_entropy: 1.8061480522155762 +[2025-04-29 09:45:50,144][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.1984837055206299, cross_entropy: 1.1984837055206299 +[2025-04-29 09:45:50,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.9949685335159302, cross_entropy: 0.9949685335159302 +[2025-04-29 09:45:53,745][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 3.0116517543792725, cross_entropy: 3.0116517543792725 +[2025-04-29 09:45:54,086][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 1.1549344062805176, cross_entropy: 1.1549344062805176 +[2025-04-29 09:45:56,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 0.814648449420929, cross_entropy: 0.814648449420929 +[2025-04-29 09:45:57,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.142289161682129, cross_entropy: 1.142289161682129 +[2025-04-29 09:46:00,167][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.3741259574890137, cross_entropy: 2.3741259574890137 +[2025-04-29 09:46:00,507][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 2.57724928855896, cross_entropy: 2.57724928855896 +[2025-04-29 09:46:03,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 0.8334982991218567, cross_entropy: 0.8334982991218567 +[2025-04-29 09:46:03,718][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.6554129123687744, cross_entropy: 2.6554129123687744 +[2025-04-29 09:46:06,584][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.1804697513580322, cross_entropy: 2.1804697513580322 +[2025-04-29 09:46:08,007][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 0.92685866355896, cross_entropy: 0.92685866355896 +[2025-04-29 09:46:10,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 1.5159296989440918, cross_entropy: 1.5159296989440918 +[2025-04-29 09:46:12,113][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 2.185774087905884, cross_entropy: 2.185774087905884 +[2025-04-29 09:46:14,039][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 1.7495007514953613, cross_entropy: 1.7495007514953613 +[2025-04-29 09:46:15,747][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.0906708240509033, cross_entropy: 1.0906708240509033 +[2025-04-29 09:46:17,264][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 1.1620142459869385, cross_entropy: 1.1620142459869385 +[2025-04-29 09:46:18,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 1.6080658435821533, cross_entropy: 1.6080658435821533 +[2025-04-29 09:46:20,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.3055219650268555, cross_entropy: 1.3055219650268555 +[2025-04-29 09:46:21,619][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 0.9459915161132812, cross_entropy: 0.9459915161132812 +[2025-04-29 09:46:24,435][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 0.9888553023338318, cross_entropy: 0.9888553023338318 +[2025-04-29 09:46:25,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 1.7729719877243042, cross_entropy: 1.7729719877243042 +[2025-04-29 09:46:27,421][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 0.7955133318901062, cross_entropy: 0.7955133318901062 +[2025-04-29 09:46:29,539][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.0799732208251953, cross_entropy: 2.0799732208251953 +[2025-04-29 09:46:31,293][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 2.6650094985961914, cross_entropy: 2.6650094985961914 +[2025-04-29 09:46:32,480][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 0.7809111475944519, cross_entropy: 0.7809111475944519 +[2025-04-29 09:46:34,911][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.328185558319092, cross_entropy: 2.328185558319092 +[2025-04-29 09:46:35,616][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.804688572883606, cross_entropy: 0.804688572883606 +[2025-04-29 09:46:38,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 0.858474850654602, cross_entropy: 0.858474850654602 +[2025-04-29 09:46:39,173][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 1.0960410833358765, cross_entropy: 1.0960410833358765 +[2025-04-29 09:46:42,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 1.895582914352417, cross_entropy: 1.895582914352417 +[2025-04-29 09:46:42,739][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.704660415649414, cross_entropy: 2.704660415649414 +[2025-04-29 09:46:45,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.653048038482666, cross_entropy: 2.653048038482666 +[2025-04-29 09:46:45,818][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.023306131362915, cross_entropy: 1.023306131362915 +[2025-04-29 09:46:49,179][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.5473785400390625, cross_entropy: 2.5473785400390625 +[2025-04-29 09:46:49,491][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 2.5577733516693115, cross_entropy: 2.5577733516693115 +[2025-04-29 09:46:52,893][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 1.2442231178283691, cross_entropy: 1.2442231178283691 +[2025-04-29 09:46:53,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 2.1729133129119873, cross_entropy: 2.1729133129119873 +[2025-04-29 09:46:55,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 1.1267787218093872, cross_entropy: 1.1267787218093872 +[2025-04-29 09:46:56,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.7819485664367676, cross_entropy: 2.7819485664367676 +[2025-04-29 09:46:59,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 1.2847216129302979, cross_entropy: 1.2847216129302979 +[2025-04-29 09:47:00,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.0003082752227783, cross_entropy: 1.0003082752227783 +[2025-04-29 09:47:03,186][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 0.6302279233932495, cross_entropy: 0.6302279233932495 +[2025-04-29 09:47:03,500][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 0.8416728973388672, cross_entropy: 0.8416728973388672 +[2025-04-29 09:47:06,841][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.7926108837127686, cross_entropy: 1.7926108837127686 +[2025-04-29 09:47:07,179][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.8414256572723389, cross_entropy: 1.8414256572723389 +[2025-04-29 09:47:10,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 0.854366660118103, cross_entropy: 0.854366660118103 +[2025-04-29 09:47:10,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.8046784400939941, cross_entropy: 1.8046784400939941 +[2025-04-29 09:47:13,800][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 2.635619640350342, cross_entropy: 2.635619640350342 +[2025-04-29 09:47:14,114][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 0.8498080372810364, cross_entropy: 0.8498080372810364 +[2025-04-29 09:47:17,600][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 1.3920270204544067, cross_entropy: 1.3920270204544067 +[2025-04-29 09:47:17,943][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 1.3705811500549316, cross_entropy: 1.3705811500549316 +[2025-04-29 09:47:21,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.1913318634033203, cross_entropy: 1.1913318634033203 +[2025-04-29 09:47:21,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.9644449949264526, cross_entropy: 1.9644449949264526 +[2025-04-29 09:47:25,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.3571478128433228, cross_entropy: 1.3571478128433228 +[2025-04-29 09:47:25,362][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.6911845207214355, cross_entropy: 1.6911845207214355 +[2025-04-29 09:47:28,450][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 1.2225695848464966, cross_entropy: 1.2225695848464966 +[2025-04-29 09:47:28,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 2.1113059520721436, cross_entropy: 2.1113059520721436 +[2025-04-29 09:47:32,128][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 1.0533208847045898, cross_entropy: 1.0533208847045898 +[2025-04-29 09:47:32,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.9035592079162598, cross_entropy: 2.9035592079162598 +[2025-04-29 09:47:34,825][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.6761932373046875, cross_entropy: 2.6761932373046875 +[2025-04-29 09:47:35,170][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.113095998764038, cross_entropy: 2.113095998764038 +[2025-04-29 09:47:38,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.746115207672119, cross_entropy: 2.746115207672119 +[2025-04-29 09:47:38,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 1.645557165145874, cross_entropy: 1.645557165145874 +[2025-04-29 09:47:42,187][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 0.7635191679000854, cross_entropy: 0.7635191679000854 +[2025-04-29 09:47:42,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 1.9125336408615112, cross_entropy: 1.9125336408615112 +[2025-04-29 09:47:45,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 1.016875982284546, cross_entropy: 1.016875982284546 +[2025-04-29 09:47:46,313][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 0.9489984512329102, cross_entropy: 0.9489984512329102 +[2025-04-29 09:47:48,917][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.7041395902633667, cross_entropy: 0.7041395902633667 +[2025-04-29 09:47:49,261][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 1.1215214729309082, cross_entropy: 1.1215214729309082 +[2025-04-29 09:47:52,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 1.0573855638504028, cross_entropy: 1.0573855638504028 +[2025-04-29 09:47:52,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 1.8956992626190186, cross_entropy: 1.8956992626190186 +[2025-04-29 09:47:52,846][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/iteration3000.pth. +[2025-04-29 09:47:56,112][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 0.9163246750831604, cross_entropy: 0.9163246750831604 +[2025-04-29 09:47:56,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.6558549404144287, cross_entropy: 2.6558549404144287 +[2025-04-29 09:48:00,362][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 0.8237786293029785, cross_entropy: 0.8237786293029785 +[2025-04-29 09:48:00,676][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 0.7411870360374451, cross_entropy: 0.7411870360374451 +[2025-04-29 09:48:04,109][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 3.1734988689422607, cross_entropy: 3.1734988689422607 +[2025-04-29 09:48:04,456][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 0.931471049785614, cross_entropy: 0.931471049785614 +[2025-04-29 09:48:07,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 2.688021183013916, cross_entropy: 2.688021183013916 +[2025-04-29 09:48:08,092][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 2.883328676223755, cross_entropy: 2.883328676223755 +[2025-04-29 09:48:11,115][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 2.293280839920044, cross_entropy: 2.293280839920044 +[2025-04-29 09:48:11,429][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 0.787888765335083, cross_entropy: 0.787888765335083 +[2025-04-29 09:48:14,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 0.8506959676742554, cross_entropy: 0.8506959676742554 +[2025-04-29 09:48:14,345][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 1.1644670963287354, cross_entropy: 1.1644670963287354 +[2025-04-29 09:48:17,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 3.0556979179382324, cross_entropy: 3.0556979179382324 +[2025-04-29 09:48:18,256][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 0.8562567830085754, cross_entropy: 0.8562567830085754 +[2025-04-29 09:48:21,485][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.2230949401855469, cross_entropy: 1.2230949401855469 +[2025-04-29 09:48:21,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.3544857501983643, cross_entropy: 2.3544857501983643 +[2025-04-29 09:48:25,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.7213888168334961, cross_entropy: 0.7213888168334961 +[2025-04-29 09:48:25,549][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 2.3546531200408936, cross_entropy: 2.3546531200408936 +[2025-04-29 09:48:28,726][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 0.7473567128181458, cross_entropy: 0.7473567128181458 +[2025-04-29 09:48:29,075][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.794224739074707, cross_entropy: 1.794224739074707 +[2025-04-29 09:48:32,772][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 1.247900366783142, cross_entropy: 1.247900366783142 +[2025-04-29 09:48:33,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 2.038634777069092, cross_entropy: 2.038634777069092 +[2025-04-29 09:48:35,996][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 2.145096778869629, cross_entropy: 2.145096778869629 +[2025-04-29 09:48:36,351][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 0.9181333780288696, cross_entropy: 0.9181333780288696 +[2025-04-29 09:48:39,995][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.5153625011444092, cross_entropy: 1.5153625011444092 +[2025-04-29 09:48:40,337][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.6582926511764526, cross_entropy: 1.6582926511764526 +[2025-04-29 09:48:43,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 2.6743130683898926, cross_entropy: 2.6743130683898926 +[2025-04-29 09:48:43,588][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 1.8020333051681519, cross_entropy: 1.8020333051681519 +[2025-04-29 09:48:46,701][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 1.4795372486114502, cross_entropy: 1.4795372486114502 +[2025-04-29 09:48:47,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 0.8918137550354004, cross_entropy: 0.8918137550354004 +[2025-04-29 09:48:50,282][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.4169394969940186, cross_entropy: 1.4169394969940186 +[2025-04-29 09:48:50,624][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 2.063087224960327, cross_entropy: 2.063087224960327 +[2025-04-29 09:48:54,198][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 2.987639904022217, cross_entropy: 2.987639904022217 +[2025-04-29 09:48:54,537][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.468435525894165, cross_entropy: 2.468435525894165 +[2025-04-29 09:48:57,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.794903039932251, cross_entropy: 2.794903039932251 +[2025-04-29 09:48:57,582][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 0.8915613889694214, cross_entropy: 0.8915613889694214 +[2025-04-29 09:49:00,204][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.5681147575378418, cross_entropy: 1.5681147575378418 +[2025-04-29 09:49:00,543][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 2.3110320568084717, cross_entropy: 2.3110320568084717 +[2025-04-29 09:49:03,923][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 0.7318885326385498, cross_entropy: 0.7318885326385498 +[2025-04-29 09:49:04,278][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.2916743755340576, cross_entropy: 1.2916743755340576 +[2025-04-29 09:49:06,940][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 0.9418748617172241, cross_entropy: 0.9418748617172241 +[2025-04-29 09:49:07,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 3.0057575702667236, cross_entropy: 3.0057575702667236 +[2025-04-29 09:49:10,590][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 1.0504536628723145, cross_entropy: 1.0504536628723145 +[2025-04-29 09:49:10,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 1.38154935836792, cross_entropy: 1.38154935836792 +[2025-04-29 09:49:13,676][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 2.7557969093322754, cross_entropy: 2.7557969093322754 +[2025-04-29 09:49:14,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.0570297241210938, cross_entropy: 1.0570297241210938 +[2025-04-29 09:49:16,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 0.8601560592651367, cross_entropy: 0.8601560592651367 +[2025-04-29 09:49:17,312][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.1972739696502686, cross_entropy: 1.1972739696502686 +[2025-04-29 09:49:19,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.8643766641616821, cross_entropy: 0.8643766641616821 +[2025-04-29 09:49:20,935][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 2.505686044692993, cross_entropy: 2.505686044692993 +[2025-04-29 09:49:23,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.9588329792022705, cross_entropy: 0.9588329792022705 +[2025-04-29 09:49:24,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.612929344177246, cross_entropy: 2.612929344177246 +[2025-04-29 09:49:27,117][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 2.4856886863708496, cross_entropy: 2.4856886863708496 +[2025-04-29 09:49:27,813][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 3.0849342346191406, cross_entropy: 3.0849342346191406 +[2025-04-29 09:49:30,889][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 1.1613327264785767, cross_entropy: 1.1613327264785767 +[2025-04-29 09:49:31,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 0.9750063419342041, cross_entropy: 0.9750063419342041 +[2025-04-29 09:49:34,485][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 2.818808078765869, cross_entropy: 2.818808078765869 +[2025-04-29 09:49:34,801][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 0.936866044998169, cross_entropy: 0.936866044998169 +[2025-04-29 09:49:38,344][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.8683600425720215, cross_entropy: 2.8683600425720215 +[2025-04-29 09:49:38,685][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 2.199990749359131, cross_entropy: 2.199990749359131 +[2025-04-29 09:49:41,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 0.7076103091239929, cross_entropy: 0.7076103091239929 +[2025-04-29 09:49:42,089][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 0.7632471323013306, cross_entropy: 0.7632471323013306 +[2025-04-29 09:49:45,224][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.4824055433273315, cross_entropy: 1.4824055433273315 +[2025-04-29 09:49:45,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 0.7214444875717163, cross_entropy: 0.7214444875717163 +[2025-04-29 09:49:48,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.302750825881958, cross_entropy: 2.302750825881958 +[2025-04-29 09:49:49,415][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 1.9561208486557007, cross_entropy: 1.9561208486557007 +[2025-04-29 09:49:52,158][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 0.9852191805839539, cross_entropy: 0.9852191805839539 +[2025-04-29 09:49:53,207][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.636255979537964, cross_entropy: 2.636255979537964 +[2025-04-29 09:49:55,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.2023158073425293, cross_entropy: 2.2023158073425293 +[2025-04-29 09:49:56,701][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 2.7662339210510254, cross_entropy: 2.7662339210510254 +[2025-04-29 09:49:58,896][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.1796021461486816, cross_entropy: 2.1796021461486816 +[2025-04-29 09:50:00,402][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 0.8322184085845947, cross_entropy: 0.8322184085845947 +[2025-04-29 09:50:02,861][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 0.7454494833946228, cross_entropy: 0.7454494833946228 +[2025-04-29 09:50:04,087][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 0.9620363116264343, cross_entropy: 0.9620363116264343 +[2025-04-29 09:50:06,359][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 2.339021921157837, cross_entropy: 2.339021921157837 +[2025-04-29 09:50:08,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.6413445472717285, cross_entropy: 2.6413445472717285 +[2025-04-29 09:50:09,634][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 0.9235680103302002, cross_entropy: 0.9235680103302002 +[2025-04-29 09:50:11,631][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 0.9931346774101257, cross_entropy: 0.9931346774101257 +[2025-04-29 09:50:13,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 2.709839344024658, cross_entropy: 2.709839344024658 +[2025-04-29 09:50:14,710][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 1.933105230331421, cross_entropy: 1.933105230331421 +[2025-04-29 09:50:16,915][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.4843843877315521, cross_entropy: 0.4843843877315521 +[2025-04-29 09:50:18,002][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 3.062936782836914, cross_entropy: 3.062936782836914 +[2025-04-29 09:50:20,138][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.6207621097564697, cross_entropy: 0.6207621097564697 +[2025-04-29 09:50:21,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 1.1273051500320435, cross_entropy: 1.1273051500320435 +[2025-04-29 09:50:23,570][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.13252592086792, cross_entropy: 1.13252592086792 +[2025-04-29 09:50:24,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.824629306793213, cross_entropy: 2.824629306793213 +[2025-04-29 09:50:26,777][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 0.8519973754882812, cross_entropy: 0.8519973754882812 +[2025-04-29 09:50:28,125][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 2.761277437210083, cross_entropy: 2.761277437210083 +[2025-04-29 09:50:30,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 2.3021798133850098, cross_entropy: 2.3021798133850098 +[2025-04-29 09:50:31,188][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 2.8008248805999756, cross_entropy: 2.8008248805999756 +[2025-04-29 09:50:34,119][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 1.3979182243347168, cross_entropy: 1.3979182243347168 +[2025-04-29 09:50:34,482][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 0.9347279667854309, cross_entropy: 0.9347279667854309 +[2025-04-29 09:50:37,366][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.2356491088867188, cross_entropy: 2.2356491088867188 +[2025-04-29 09:50:37,705][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 2.6877617835998535, cross_entropy: 2.6877617835998535 +[2025-04-29 09:50:41,246][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 2.6350185871124268, cross_entropy: 2.6350185871124268 +[2025-04-29 09:50:41,591][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 1.6168276071548462, cross_entropy: 1.6168276071548462 +[2025-04-29 09:50:45,453][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.2617683410644531, cross_entropy: 1.2617683410644531 +[2025-04-29 09:50:45,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.1246085166931152, cross_entropy: 1.1246085166931152 +[2025-04-29 09:50:49,006][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 3.0518908500671387, cross_entropy: 3.0518908500671387 +[2025-04-29 09:50:49,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 1.7275853157043457, cross_entropy: 1.7275853157043457 +[2025-04-29 09:50:52,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.9529742002487183, cross_entropy: 1.9529742002487183 +[2025-04-29 09:50:52,659][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 3.0455496311187744, cross_entropy: 3.0455496311187744 +[2025-04-29 09:50:55,227][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 1.0977143049240112, cross_entropy: 1.0977143049240112 +[2025-04-29 09:50:55,974][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 1.591181755065918, cross_entropy: 1.591181755065918 +[2025-04-29 09:50:58,411][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.3148646354675293, cross_entropy: 1.3148646354675293 +[2025-04-29 09:51:00,556][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 3.0164706707000732, cross_entropy: 3.0164706707000732 +[2025-04-29 09:51:02,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 1.8248151540756226, cross_entropy: 1.8248151540756226 +[2025-04-29 09:51:03,946][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 1.7408342361450195, cross_entropy: 1.7408342361450195 +[2025-04-29 09:51:05,713][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 2.2576396465301514, cross_entropy: 2.2576396465301514 +[2025-04-29 09:51:07,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 2.6523871421813965, cross_entropy: 2.6523871421813965 +[2025-04-29 09:51:08,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 0.7763364315032959, cross_entropy: 0.7763364315032959 +[2025-04-29 09:51:10,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 2.4539849758148193, cross_entropy: 2.4539849758148193 +[2025-04-29 09:51:12,729][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.0459942817687988, cross_entropy: 1.0459942817687988 +[2025-04-29 09:51:13,849][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 2.779218912124634, cross_entropy: 2.779218912124634 +[2025-04-29 09:51:16,085][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 0.8988025784492493, cross_entropy: 0.8988025784492493 +[2025-04-29 09:51:17,253][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.428008556365967, cross_entropy: 2.428008556365967 +[2025-04-29 09:51:19,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.7929229736328125, cross_entropy: 2.7929229736328125 +[2025-04-29 09:51:20,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 0.796561598777771, cross_entropy: 0.796561598777771 +[2025-04-29 09:51:22,629][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 0.9604400396347046, cross_entropy: 0.9604400396347046 +[2025-04-29 09:51:23,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 3.112182378768921, cross_entropy: 3.112182378768921 +[2025-04-29 09:51:27,229][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.659045696258545, cross_entropy: 2.659045696258545 +[2025-04-29 09:51:27,568][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 2.1004934310913086, cross_entropy: 2.1004934310913086 +[2025-04-29 09:51:31,199][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.838775157928467, cross_entropy: 2.838775157928467 +[2025-04-29 09:51:31,538][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 1.1478567123413086, cross_entropy: 1.1478567123413086 +[2025-04-29 09:51:34,106][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 2.5311367511749268, cross_entropy: 2.5311367511749268 +[2025-04-29 09:51:34,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 2.4897608757019043, cross_entropy: 2.4897608757019043 +[2025-04-29 09:51:37,475][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.229487895965576, cross_entropy: 2.229487895965576 +[2025-04-29 09:51:37,811][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 2.5046565532684326, cross_entropy: 2.5046565532684326 +[2025-04-29 09:51:41,053][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 2.5476460456848145, cross_entropy: 2.5476460456848145 +[2025-04-29 09:51:41,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.7114453315734863, cross_entropy: 2.7114453315734863 +[2025-04-29 09:51:44,651][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 1.3012341260910034, cross_entropy: 1.3012341260910034 +[2025-04-29 09:51:44,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 2.7604689598083496, cross_entropy: 2.7604689598083496 +[2025-04-29 09:51:48,386][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 2.4461259841918945, cross_entropy: 2.4461259841918945 +[2025-04-29 09:51:48,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.4081227779388428, cross_entropy: 1.4081227779388428 +[2025-04-29 09:51:51,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 1.117866039276123, cross_entropy: 1.117866039276123 +[2025-04-29 09:51:52,079][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 2.790444850921631, cross_entropy: 2.790444850921631 +[2025-04-29 09:51:56,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 1.1422661542892456, cross_entropy: 1.1422661542892456 +[2025-04-29 09:51:56,385][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.5697499513626099, cross_entropy: 1.5697499513626099 +[2025-04-29 09:51:59,493][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 1.055108666419983, cross_entropy: 1.055108666419983 +[2025-04-29 09:51:59,845][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.4727323055267334, cross_entropy: 1.4727323055267334 +[2025-04-29 09:52:03,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 2.838545560836792, cross_entropy: 2.838545560836792 +[2025-04-29 09:52:03,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 2.0746068954467773, cross_entropy: 2.0746068954467773 +[2025-04-29 09:52:06,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 2.2295079231262207, cross_entropy: 2.2295079231262207 +[2025-04-29 09:52:06,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 3.016934871673584, cross_entropy: 3.016934871673584 +[2025-04-29 09:52:10,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 2.543883800506592, cross_entropy: 2.543883800506592 +[2025-04-29 09:52:10,486][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 2.3617753982543945, cross_entropy: 2.3617753982543945 +[2025-04-29 09:52:12,997][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 0.9929839372634888, cross_entropy: 0.9929839372634888 +[2025-04-29 09:52:13,336][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.084899663925171, cross_entropy: 1.084899663925171 +[2025-04-29 09:52:16,421][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 0.8644890785217285, cross_entropy: 0.8644890785217285 +[2025-04-29 09:52:16,759][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 1.99666428565979, cross_entropy: 1.99666428565979 +[2025-04-29 09:52:19,468][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 2.5556671619415283, cross_entropy: 2.5556671619415283 +[2025-04-29 09:52:19,806][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 1.3878178596496582, cross_entropy: 1.3878178596496582 +[2025-04-29 09:52:22,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 1.7287909984588623, cross_entropy: 1.7287909984588623 +[2025-04-29 09:52:23,278][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.9710267782211304, cross_entropy: 0.9710267782211304 +[2025-04-29 09:52:26,547][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 2.6126668453216553, cross_entropy: 2.6126668453216553 +[2025-04-29 09:52:26,894][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 1.0887477397918701, cross_entropy: 1.0887477397918701 +[2025-04-29 09:52:30,387][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 0.977899432182312, cross_entropy: 0.977899432182312 +[2025-04-29 09:52:30,724][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 2.085960865020752, cross_entropy: 2.085960865020752 +[2025-04-29 09:52:33,910][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 1.3103865385055542, cross_entropy: 1.3103865385055542 +[2025-04-29 09:52:34,247][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 1.7238357067108154, cross_entropy: 1.7238357067108154 +[2025-04-29 09:52:37,317][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 2.5493860244750977, cross_entropy: 2.5493860244750977 +[2025-04-29 09:52:37,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 0.8964035511016846, cross_entropy: 0.8964035511016846 +[2025-04-29 09:52:40,398][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 2.8822250366210938, cross_entropy: 2.8822250366210938 +[2025-04-29 09:52:40,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 1.3497289419174194, cross_entropy: 1.3497289419174194 +[2025-04-29 09:52:44,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 2.5054500102996826, cross_entropy: 2.5054500102996826 +[2025-04-29 09:52:44,503][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 3.2356162071228027, cross_entropy: 3.2356162071228027 +[2025-04-29 09:52:47,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 1.5965096950531006, cross_entropy: 1.5965096950531006 +[2025-04-29 09:52:47,843][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 1.4817132949829102, cross_entropy: 1.4817132949829102 +[2025-04-29 09:52:50,994][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 2.250511884689331, cross_entropy: 2.250511884689331 +[2025-04-29 09:52:51,341][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 1.0982240438461304, cross_entropy: 1.0982240438461304 +[2025-04-29 09:52:54,250][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 1.3410487174987793, cross_entropy: 1.3410487174987793 +[2025-04-29 09:52:54,588][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 1.8254516124725342, cross_entropy: 1.8254516124725342 +[2025-04-29 09:52:57,293][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 0.988667368888855, cross_entropy: 0.988667368888855 +[2025-04-29 09:52:57,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.290585994720459, cross_entropy: 2.290585994720459 +[2025-04-29 09:53:01,068][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 0.7999957799911499, cross_entropy: 0.7999957799911499 +[2025-04-29 09:53:01,386][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.3033032417297363, cross_entropy: 1.3033032417297363 +[2025-04-29 09:53:04,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.5805057287216187, cross_entropy: 1.5805057287216187 +[2025-04-29 09:53:04,847][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.072077751159668, cross_entropy: 1.072077751159668 +[2025-04-29 09:53:08,118][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 0.5940865278244019, cross_entropy: 0.5940865278244019 +[2025-04-29 09:53:08,462][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 1.25996732711792, cross_entropy: 1.25996732711792 +[2025-04-29 09:53:10,805][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 0.9849848747253418, cross_entropy: 0.9849848747253418 +[2025-04-29 09:53:11,146][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.5710883140563965, cross_entropy: 1.5710883140563965 +[2025-04-29 09:53:14,309][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 1.0458652973175049, cross_entropy: 1.0458652973175049 +[2025-04-29 09:53:14,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.2111876010894775, cross_entropy: 2.2111876010894775 +[2025-04-29 09:53:17,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 2.979053258895874, cross_entropy: 2.979053258895874 +[2025-04-29 09:53:18,161][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 0.9022195935249329, cross_entropy: 0.9022195935249329 +[2025-04-29 09:53:20,896][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 1.5080633163452148, cross_entropy: 1.5080633163452148 +[2025-04-29 09:53:21,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 1.051239252090454, cross_entropy: 1.051239252090454 +[2025-04-29 09:53:24,395][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 0.8756721019744873, cross_entropy: 0.8756721019744873 +[2025-04-29 09:53:24,725][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 0.6548910140991211, cross_entropy: 0.6548910140991211 +[2025-04-29 09:53:28,543][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 1.4559407234191895, cross_entropy: 1.4559407234191895 +[2025-04-29 09:53:28,890][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.4470148086547852, cross_entropy: 1.4470148086547852 +[2025-04-29 09:53:31,772][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 2.6783809661865234, cross_entropy: 2.6783809661865234 +[2025-04-29 09:53:32,119][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.755527973175049, cross_entropy: 2.755527973175049 +[2025-04-29 09:53:35,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 3.0555624961853027, cross_entropy: 3.0555624961853027 +[2025-04-29 09:53:35,373][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 0.6163854598999023, cross_entropy: 0.6163854598999023 +[2025-04-29 09:53:38,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 2.706387996673584, cross_entropy: 2.706387996673584 +[2025-04-29 09:53:39,204][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.882864475250244, cross_entropy: 2.882864475250244 +[2025-04-29 09:53:42,679][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 0.719824492931366, cross_entropy: 0.719824492931366 +[2025-04-29 09:53:43,020][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 0.9415874481201172, cross_entropy: 0.9415874481201172 +[2025-04-29 09:53:45,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 0.8482276201248169, cross_entropy: 0.8482276201248169 +[2025-04-29 09:53:45,699][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.2451422214508057, cross_entropy: 2.2451422214508057 +[2025-04-29 09:53:48,372][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 0.882851243019104, cross_entropy: 0.882851243019104 +[2025-04-29 09:53:48,651][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 1.824951171875, cross_entropy: 1.824951171875 +[2025-04-29 09:56:28,776][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.7410253286361694, cross_entropy: 1.7410253286361694 +[2025-04-29 09:56:28,777][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.173197627067566, cross_entropy: 1.173197627067566 +[2025-04-29 09:56:29,025][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/best_epoch.pth. +[2025-04-29 09:56:29,185][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch9.pth. +[2025-04-29 09:56:29,393][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 09:56:33,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 2.9549973011016846, cross_entropy: 2.9549973011016846 +[2025-04-29 09:56:33,979][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.357499122619629, cross_entropy: 1.357499122619629 +[2025-04-29 09:56:37,242][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.3752128481864929, cross_entropy: 0.3752128481864929 +[2025-04-29 09:56:37,554][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 1.6670477390289307, cross_entropy: 1.6670477390289307 +[2025-04-29 09:56:40,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 1.9673912525177002, cross_entropy: 1.9673912525177002 +[2025-04-29 09:56:41,225][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.4408365488052368, cross_entropy: 1.4408365488052368 +[2025-04-29 09:56:44,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.473453998565674, cross_entropy: 2.473453998565674 +[2025-04-29 09:56:44,931][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.721807599067688, cross_entropy: 0.721807599067688 +[2025-04-29 09:56:48,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 1.9691839218139648, cross_entropy: 1.9691839218139648 +[2025-04-29 09:56:48,633][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 2.544541358947754, cross_entropy: 2.544541358947754 +[2025-04-29 09:56:51,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 1.9305102825164795, cross_entropy: 1.9305102825164795 +[2025-04-29 09:56:51,866][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 0.7286999225616455, cross_entropy: 0.7286999225616455 +[2025-04-29 09:56:55,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 0.8364297151565552, cross_entropy: 0.8364297151565552 +[2025-04-29 09:56:55,529][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 0.9626644849777222, cross_entropy: 0.9626644849777222 +[2025-04-29 09:56:58,648][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.8877010345458984, cross_entropy: 2.8877010345458984 +[2025-04-29 09:56:58,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 1.9250174760818481, cross_entropy: 1.9250174760818481 +[2025-04-29 09:57:01,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 0.9600865840911865, cross_entropy: 0.9600865840911865 +[2025-04-29 09:57:02,173][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 0.757103681564331, cross_entropy: 0.757103681564331 +[2025-04-29 09:57:05,107][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.7450640201568604, cross_entropy: 2.7450640201568604 +[2025-04-29 09:57:05,428][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.3375334739685059, cross_entropy: 1.3375334739685059 +[2025-04-29 09:57:08,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 1.337202548980713, cross_entropy: 1.337202548980713 +[2025-04-29 09:57:08,698][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 2.680002212524414, cross_entropy: 2.680002212524414 +[2025-04-29 09:57:11,595][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.4982706904411316, cross_entropy: 0.4982706904411316 +[2025-04-29 09:57:11,935][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 2.0733256340026855, cross_entropy: 2.0733256340026855 +[2025-04-29 09:57:14,816][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.7373721599578857, cross_entropy: 2.7373721599578857 +[2025-04-29 09:57:15,157][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 0.806987464427948, cross_entropy: 0.806987464427948 +[2025-04-29 09:57:18,530][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 0.954840898513794, cross_entropy: 0.954840898513794 +[2025-04-29 09:57:18,869][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 1.4444160461425781, cross_entropy: 1.4444160461425781 +[2025-04-29 09:57:22,212][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.751025915145874, cross_entropy: 2.751025915145874 +[2025-04-29 09:57:22,550][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 2.229485273361206, cross_entropy: 2.229485273361206 +[2025-04-29 09:57:27,175][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 0.6405574679374695, cross_entropy: 0.6405574679374695 +[2025-04-29 09:57:27,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 1.3417683839797974, cross_entropy: 1.3417683839797974 +[2025-04-29 09:57:30,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 2.0310630798339844, cross_entropy: 2.0310630798339844 +[2025-04-29 09:57:30,689][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 1.4805941581726074, cross_entropy: 1.4805941581726074 +[2025-04-29 09:57:33,719][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 0.7217484712600708, cross_entropy: 0.7217484712600708 +[2025-04-29 09:57:34,060][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 2.7007133960723877, cross_entropy: 2.7007133960723877 +[2025-04-29 09:57:37,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.795036792755127, cross_entropy: 2.795036792755127 +[2025-04-29 09:57:37,553][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 1.0804400444030762, cross_entropy: 1.0804400444030762 +[2025-04-29 09:57:40,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 0.962958574295044, cross_entropy: 0.962958574295044 +[2025-04-29 09:57:41,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 0.7405946850776672, cross_entropy: 0.7405946850776672 +[2025-04-29 09:57:43,960][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 2.6441049575805664, cross_entropy: 2.6441049575805664 +[2025-04-29 09:57:44,302][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 1.4440417289733887, cross_entropy: 1.4440417289733887 +[2025-04-29 09:57:47,199][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 0.5654234290122986, cross_entropy: 0.5654234290122986 +[2025-04-29 09:57:47,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 0.7277896404266357, cross_entropy: 0.7277896404266357 +[2025-04-29 09:57:49,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.659510850906372, cross_entropy: 1.659510850906372 +[2025-04-29 09:57:50,336][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 2.9756975173950195, cross_entropy: 2.9756975173950195 +[2025-04-29 09:57:53,616][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 0.8935690522193909, cross_entropy: 0.8935690522193909 +[2025-04-29 09:57:53,955][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 2.5406222343444824, cross_entropy: 2.5406222343444824 +[2025-04-29 09:57:57,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.0618095397949219, cross_entropy: 1.0618095397949219 +[2025-04-29 09:57:57,375][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 1.3283839225769043, cross_entropy: 1.3283839225769043 +[2025-04-29 09:58:00,118][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 0.9530665278434753, cross_entropy: 0.9530665278434753 +[2025-04-29 09:58:00,431][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 0.6411421298980713, cross_entropy: 0.6411421298980713 +[2025-04-29 09:58:03,252][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.1348223686218262, cross_entropy: 1.1348223686218262 +[2025-04-29 09:58:03,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 2.9449501037597656, cross_entropy: 2.9449501037597656 +[2025-04-29 09:58:06,618][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.789345145225525, cross_entropy: 1.789345145225525 +[2025-04-29 09:58:06,955][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 1.7603793144226074, cross_entropy: 1.7603793144226074 +[2025-04-29 09:58:09,640][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.443199872970581, cross_entropy: 1.443199872970581 +[2025-04-29 09:58:09,977][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 1.247826337814331, cross_entropy: 1.247826337814331 +[2025-04-29 09:58:13,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 0.8227370381355286, cross_entropy: 0.8227370381355286 +[2025-04-29 09:58:13,571][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 1.086611270904541, cross_entropy: 1.086611270904541 +[2025-04-29 09:58:17,413][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 1.2757844924926758, cross_entropy: 1.2757844924926758 +[2025-04-29 09:58:17,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 0.8366608619689941, cross_entropy: 0.8366608619689941 +[2025-04-29 09:58:20,893][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 0.80661541223526, cross_entropy: 0.80661541223526 +[2025-04-29 09:58:21,238][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 1.4955682754516602, cross_entropy: 1.4955682754516602 +[2025-04-29 09:58:24,081][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 2.8795974254608154, cross_entropy: 2.8795974254608154 +[2025-04-29 09:58:24,426][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 1.518345832824707, cross_entropy: 1.518345832824707 +[2025-04-29 09:58:28,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 2.6467714309692383, cross_entropy: 2.6467714309692383 +[2025-04-29 09:58:28,344][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 2.7202038764953613, cross_entropy: 2.7202038764953613 +[2025-04-29 09:58:31,449][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 0.7791951298713684, cross_entropy: 0.7791951298713684 +[2025-04-29 09:58:31,794][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 0.9412500858306885, cross_entropy: 0.9412500858306885 +[2025-04-29 09:58:34,792][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 0.8667792081832886, cross_entropy: 0.8667792081832886 +[2025-04-29 09:58:35,110][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 0.5408927202224731, cross_entropy: 0.5408927202224731 +[2025-04-29 09:58:38,335][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 0.603342592716217, cross_entropy: 0.603342592716217 +[2025-04-29 09:58:38,650][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 1.4813551902770996, cross_entropy: 1.4813551902770996 +[2025-04-29 09:58:42,089][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 1.1614367961883545, cross_entropy: 1.1614367961883545 +[2025-04-29 09:58:42,430][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.1374502182006836, cross_entropy: 1.1374502182006836 +[2025-04-29 09:58:45,374][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.0735423564910889, cross_entropy: 1.0735423564910889 +[2025-04-29 09:58:45,715][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 0.8170325756072998, cross_entropy: 0.8170325756072998 +[2025-04-29 09:58:49,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.077173113822937, cross_entropy: 1.077173113822937 +[2025-04-29 09:58:49,436][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.49185529351234436, cross_entropy: 0.49185529351234436 +[2025-04-29 09:58:52,367][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.1926519870758057, cross_entropy: 1.1926519870758057 +[2025-04-29 09:58:52,711][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 2.870657444000244, cross_entropy: 2.870657444000244 +[2025-04-29 09:58:55,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 1.3048958778381348, cross_entropy: 1.3048958778381348 +[2025-04-29 09:58:56,293][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.7524495124816895, cross_entropy: 2.7524495124816895 +[2025-04-29 09:59:00,769][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 1.0025906562805176, cross_entropy: 1.0025906562805176 +[2025-04-29 09:59:01,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 1.809058666229248, cross_entropy: 1.809058666229248 +[2025-04-29 09:59:04,086][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 3.167262077331543, cross_entropy: 3.167262077331543 +[2025-04-29 09:59:04,423][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 0.4826684892177582, cross_entropy: 0.4826684892177582 +[2025-04-29 09:59:07,372][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.5420727729797363, cross_entropy: 2.5420727729797363 +[2025-04-29 09:59:07,688][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 2.6811485290527344, cross_entropy: 2.6811485290527344 +[2025-04-29 09:59:10,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 0.7461481094360352, cross_entropy: 0.7461481094360352 +[2025-04-29 09:59:11,005][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.5798206329345703, cross_entropy: 1.5798206329345703 +[2025-04-29 09:59:14,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 1.95515775680542, cross_entropy: 1.95515775680542 +[2025-04-29 09:59:14,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 3.0884032249450684, cross_entropy: 3.0884032249450684 +[2025-04-29 09:59:17,261][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 2.075653553009033, cross_entropy: 2.075653553009033 +[2025-04-29 09:59:17,607][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 2.6681666374206543, cross_entropy: 2.6681666374206543 +[2025-04-29 09:59:20,331][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 1.9194748401641846, cross_entropy: 1.9194748401641846 +[2025-04-29 09:59:20,669][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 1.8565632104873657, cross_entropy: 1.8565632104873657 +[2025-04-29 09:59:23,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 0.6318309307098389, cross_entropy: 0.6318309307098389 +[2025-04-29 09:59:24,164][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 0.9227341413497925, cross_entropy: 0.9227341413497925 +[2025-04-29 09:59:27,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 2.257324695587158, cross_entropy: 2.257324695587158 +[2025-04-29 09:59:27,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.5285801887512207, cross_entropy: 1.5285801887512207 +[2025-04-29 09:59:30,378][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 2.449619770050049, cross_entropy: 2.449619770050049 +[2025-04-29 09:59:30,715][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.6073508262634277, cross_entropy: 2.6073508262634277 +[2025-04-29 09:59:34,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 0.8624346852302551, cross_entropy: 0.8624346852302551 +[2025-04-29 09:59:34,751][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.9908454418182373, cross_entropy: 2.9908454418182373 +[2025-04-29 09:59:38,014][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 0.8006057143211365, cross_entropy: 0.8006057143211365 +[2025-04-29 09:59:38,358][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 2.3353400230407715, cross_entropy: 2.3353400230407715 +[2025-04-29 09:59:41,954][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 1.1109260320663452, cross_entropy: 1.1109260320663452 +[2025-04-29 09:59:42,292][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 1.1441518068313599, cross_entropy: 1.1441518068313599 +[2025-04-29 09:59:45,070][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 3.1310575008392334, cross_entropy: 3.1310575008392334 +[2025-04-29 09:59:45,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.2885217666625977, cross_entropy: 1.2885217666625977 +[2025-04-29 09:59:48,251][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 2.4522545337677, cross_entropy: 2.4522545337677 +[2025-04-29 09:59:48,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 1.3509632349014282, cross_entropy: 1.3509632349014282 +[2025-04-29 09:59:52,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 0.9904518127441406, cross_entropy: 0.9904518127441406 +[2025-04-29 09:59:52,560][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.2801947593688965, cross_entropy: 2.2801947593688965 +[2025-04-29 09:59:55,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 2.917903423309326, cross_entropy: 2.917903423309326 +[2025-04-29 09:59:55,876][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 2.175485372543335, cross_entropy: 2.175485372543335 +[2025-04-29 09:59:59,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 2.345146894454956, cross_entropy: 2.345146894454956 +[2025-04-29 09:59:59,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 0.7307065725326538, cross_entropy: 0.7307065725326538 +[2025-04-29 10:00:02,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 3.0337815284729004, cross_entropy: 3.0337815284729004 +[2025-04-29 10:00:02,991][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 0.657368540763855, cross_entropy: 0.657368540763855 +[2025-04-29 10:00:06,346][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.1274282932281494, cross_entropy: 1.1274282932281494 +[2025-04-29 10:00:06,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.4405009746551514, cross_entropy: 2.4405009746551514 +[2025-04-29 10:00:09,803][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 0.9991862773895264, cross_entropy: 0.9991862773895264 +[2025-04-29 10:00:10,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 2.5116164684295654, cross_entropy: 2.5116164684295654 +[2025-04-29 10:00:12,865][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 0.9505628347396851, cross_entropy: 0.9505628347396851 +[2025-04-29 10:00:13,204][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 1.1604828834533691, cross_entropy: 1.1604828834533691 +[2025-04-29 10:00:16,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 1.8953633308410645, cross_entropy: 1.8953633308410645 +[2025-04-29 10:00:16,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 2.755643844604492, cross_entropy: 2.755643844604492 +[2025-04-29 10:00:19,814][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.084132194519043, cross_entropy: 2.084132194519043 +[2025-04-29 10:00:20,150][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 0.649852454662323, cross_entropy: 0.649852454662323 +[2025-04-29 10:00:23,258][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 0.47647354006767273, cross_entropy: 0.47647354006767273 +[2025-04-29 10:00:23,596][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 2.5901780128479004, cross_entropy: 2.5901780128479004 +[2025-04-29 10:00:27,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 0.8168014287948608, cross_entropy: 0.8168014287948608 +[2025-04-29 10:00:28,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 0.6098122596740723, cross_entropy: 0.6098122596740723 +[2025-04-29 10:00:30,783][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 2.8852806091308594, cross_entropy: 2.8852806091308594 +[2025-04-29 10:00:31,124][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 0.9725138545036316, cross_entropy: 0.9725138545036316 +[2025-04-29 10:00:34,465][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.3300716876983643, cross_entropy: 2.3300716876983643 +[2025-04-29 10:00:34,779][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.992063283920288, cross_entropy: 1.992063283920288 +[2025-04-29 10:00:38,390][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 0.582114040851593, cross_entropy: 0.582114040851593 +[2025-04-29 10:00:38,726][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.8145251274108887, cross_entropy: 2.8145251274108887 +[2025-04-29 10:00:41,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 0.9413285851478577, cross_entropy: 0.9413285851478577 +[2025-04-29 10:00:41,872][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.548521041870117, cross_entropy: 2.548521041870117 +[2025-04-29 10:00:44,866][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.715330123901367, cross_entropy: 2.715330123901367 +[2025-04-29 10:00:45,204][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 2.7230782508850098, cross_entropy: 2.7230782508850098 +[2025-04-29 10:00:49,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 2.1518173217773438, cross_entropy: 2.1518173217773438 +[2025-04-29 10:00:49,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 2.8461132049560547, cross_entropy: 2.8461132049560547 +[2025-04-29 10:00:52,786][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.452889323234558, cross_entropy: 1.452889323234558 +[2025-04-29 10:00:53,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 0.7408168911933899, cross_entropy: 0.7408168911933899 +[2025-04-29 10:00:56,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 1.181579351425171, cross_entropy: 1.181579351425171 +[2025-04-29 10:00:56,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 1.8253998756408691, cross_entropy: 1.8253998756408691 +[2025-04-29 10:00:59,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 1.2587462663650513, cross_entropy: 1.2587462663650513 +[2025-04-29 10:01:00,226][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 1.0343527793884277, cross_entropy: 1.0343527793884277 +[2025-04-29 10:01:02,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 2.001455307006836, cross_entropy: 2.001455307006836 +[2025-04-29 10:01:03,141][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 0.783650279045105, cross_entropy: 0.783650279045105 +[2025-04-29 10:01:06,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 0.7239658832550049, cross_entropy: 0.7239658832550049 +[2025-04-29 10:01:06,622][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 1.4347015619277954, cross_entropy: 1.4347015619277954 +[2025-04-29 10:01:10,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.1047396659851074, cross_entropy: 1.1047396659851074 +[2025-04-29 10:01:10,372][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 3.0225720405578613, cross_entropy: 3.0225720405578613 +[2025-04-29 10:01:13,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 1.9015754461288452, cross_entropy: 1.9015754461288452 +[2025-04-29 10:01:13,437][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 1.0018072128295898, cross_entropy: 1.0018072128295898 +[2025-04-29 10:01:16,679][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 1.2848196029663086, cross_entropy: 1.2848196029663086 +[2025-04-29 10:01:17,017][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.360823154449463, cross_entropy: 2.360823154449463 +[2025-04-29 10:01:20,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 2.2636876106262207, cross_entropy: 2.2636876106262207 +[2025-04-29 10:01:20,579][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.985703468322754, cross_entropy: 2.985703468322754 +[2025-04-29 10:01:23,827][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.8659873008728027, cross_entropy: 2.8659873008728027 +[2025-04-29 10:01:24,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.610100269317627, cross_entropy: 0.610100269317627 +[2025-04-29 10:01:27,396][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 1.993574619293213, cross_entropy: 1.993574619293213 +[2025-04-29 10:01:27,711][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.2160844802856445, cross_entropy: 2.2160844802856445 +[2025-04-29 10:01:32,315][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 2.568729877471924, cross_entropy: 2.568729877471924 +[2025-04-29 10:01:32,651][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 1.9031705856323242, cross_entropy: 1.9031705856323242 +[2025-04-29 10:01:35,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 0.6622153520584106, cross_entropy: 0.6622153520584106 +[2025-04-29 10:01:35,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.9083139896392822, cross_entropy: 0.9083139896392822 +[2025-04-29 10:01:38,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 2.8673527240753174, cross_entropy: 2.8673527240753174 +[2025-04-29 10:01:39,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 0.7886442542076111, cross_entropy: 0.7886442542076111 +[2025-04-29 10:01:42,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 1.9091296195983887, cross_entropy: 1.9091296195983887 +[2025-04-29 10:01:42,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 2.6034836769104004, cross_entropy: 2.6034836769104004 +[2025-04-29 10:01:45,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 2.8483176231384277, cross_entropy: 2.8483176231384277 +[2025-04-29 10:01:45,836][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 1.4089224338531494, cross_entropy: 1.4089224338531494 +[2025-04-29 10:01:49,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 2.719367027282715, cross_entropy: 2.719367027282715 +[2025-04-29 10:01:49,694][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.8402408957481384, cross_entropy: 0.8402408957481384 +[2025-04-29 10:01:52,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 2.7174072265625, cross_entropy: 2.7174072265625 +[2025-04-29 10:01:52,887][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 1.0350470542907715, cross_entropy: 1.0350470542907715 +[2025-04-29 10:01:56,115][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 0.9022328853607178, cross_entropy: 0.9022328853607178 +[2025-04-29 10:01:56,460][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 2.347404956817627, cross_entropy: 2.347404956817627 +[2025-04-29 10:01:59,994][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.899413824081421, cross_entropy: 2.899413824081421 +[2025-04-29 10:02:00,342][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 2.540140151977539, cross_entropy: 2.540140151977539 +[2025-04-29 10:02:04,027][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 2.3446664810180664, cross_entropy: 2.3446664810180664 +[2025-04-29 10:02:04,370][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 1.717625379562378, cross_entropy: 1.717625379562378 +[2025-04-29 10:02:08,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 1.0661513805389404, cross_entropy: 1.0661513805389404 +[2025-04-29 10:02:08,322][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 1.4703010320663452, cross_entropy: 1.4703010320663452 +[2025-04-29 10:02:12,168][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.7254157066345215, cross_entropy: 1.7254157066345215 +[2025-04-29 10:02:12,513][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.591928482055664, cross_entropy: 2.591928482055664 +[2025-04-29 10:02:15,677][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 1.2087262868881226, cross_entropy: 1.2087262868881226 +[2025-04-29 10:02:15,992][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.804774284362793, cross_entropy: 2.804774284362793 +[2025-04-29 10:02:19,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 1.7945588827133179, cross_entropy: 1.7945588827133179 +[2025-04-29 10:02:20,074][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.4080462455749512, cross_entropy: 1.4080462455749512 +[2025-04-29 10:02:23,518][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 1.3557637929916382, cross_entropy: 1.3557637929916382 +[2025-04-29 10:02:23,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.3346688747406006, cross_entropy: 2.3346688747406006 +[2025-04-29 10:02:27,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 2.432086706161499, cross_entropy: 2.432086706161499 +[2025-04-29 10:02:27,615][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.7546632289886475, cross_entropy: 2.7546632289886475 +[2025-04-29 10:02:30,978][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 0.8757283687591553, cross_entropy: 0.8757283687591553 +[2025-04-29 10:02:31,323][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.0094408988952637, cross_entropy: 2.0094408988952637 +[2025-04-29 10:02:34,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 0.6779663562774658, cross_entropy: 0.6779663562774658 +[2025-04-29 10:02:34,623][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 1.064812183380127, cross_entropy: 1.064812183380127 +[2025-04-29 10:02:37,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 0.7435065507888794, cross_entropy: 0.7435065507888794 +[2025-04-29 10:02:38,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 0.8838571906089783, cross_entropy: 0.8838571906089783 +[2025-04-29 10:02:41,733][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 2.778367042541504, cross_entropy: 2.778367042541504 +[2025-04-29 10:02:42,079][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.7794972658157349, cross_entropy: 1.7794972658157349 +[2025-04-29 10:02:46,112][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 0.9961020946502686, cross_entropy: 0.9961020946502686 +[2025-04-29 10:02:46,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.388096809387207, cross_entropy: 2.388096809387207 +[2025-04-29 10:02:49,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 0.5320802330970764, cross_entropy: 0.5320802330970764 +[2025-04-29 10:02:49,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 1.9600214958190918, cross_entropy: 1.9600214958190918 +[2025-04-29 10:02:52,807][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 2.5286312103271484, cross_entropy: 2.5286312103271484 +[2025-04-29 10:02:53,150][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 2.298552989959717, cross_entropy: 2.298552989959717 +[2025-04-29 10:02:56,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 2.2200350761413574, cross_entropy: 2.2200350761413574 +[2025-04-29 10:02:56,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 0.9787689447402954, cross_entropy: 0.9787689447402954 +[2025-04-29 10:03:00,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 1.488351821899414, cross_entropy: 1.488351821899414 +[2025-04-29 10:03:00,636][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.5071802139282227, cross_entropy: 2.5071802139282227 +[2025-04-29 10:03:03,654][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 1.092162847518921, cross_entropy: 1.092162847518921 +[2025-04-29 10:03:03,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 0.85154789686203, cross_entropy: 0.85154789686203 +[2025-04-29 10:03:06,971][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.3772250413894653, cross_entropy: 1.3772250413894653 +[2025-04-29 10:03:07,286][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.1078667640686035, cross_entropy: 1.1078667640686035 +[2025-04-29 10:03:10,258][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 0.8087940812110901, cross_entropy: 0.8087940812110901 +[2025-04-29 10:03:10,600][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 1.3118810653686523, cross_entropy: 1.3118810653686523 +[2025-04-29 10:03:13,308][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.0085529088974, cross_entropy: 1.0085529088974 +[2025-04-29 10:03:13,624][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 2.1839537620544434, cross_entropy: 2.1839537620544434 +[2025-04-29 10:03:16,874][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 3.114088773727417, cross_entropy: 3.114088773727417 +[2025-04-29 10:03:17,187][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 2.3796019554138184, cross_entropy: 2.3796019554138184 +[2025-04-29 10:03:20,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.7674860954284668, cross_entropy: 1.7674860954284668 +[2025-04-29 10:03:20,857][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 2.2798404693603516, cross_entropy: 2.2798404693603516 +[2025-04-29 10:03:23,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 0.7896138429641724, cross_entropy: 0.7896138429641724 +[2025-04-29 10:03:24,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 0.9862918853759766, cross_entropy: 0.9862918853759766 +[2025-04-29 10:03:27,487][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 1.5716922283172607, cross_entropy: 1.5716922283172607 +[2025-04-29 10:03:27,827][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 0.6275763511657715, cross_entropy: 0.6275763511657715 +[2025-04-29 10:03:30,973][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 0.9961133003234863, cross_entropy: 0.9961133003234863 +[2025-04-29 10:03:31,318][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 2.980809211730957, cross_entropy: 2.980809211730957 +[2025-04-29 10:03:34,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 3.0921077728271484, cross_entropy: 3.0921077728271484 +[2025-04-29 10:03:34,773][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 2.8942437171936035, cross_entropy: 2.8942437171936035 +[2025-04-29 10:03:37,733][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 1.4806369543075562, cross_entropy: 1.4806369543075562 +[2025-04-29 10:03:38,055][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.556140422821045, cross_entropy: 2.556140422821045 +[2025-04-29 10:03:41,860][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 0.7154909372329712, cross_entropy: 0.7154909372329712 +[2025-04-29 10:03:42,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.8484290838241577, cross_entropy: 0.8484290838241577 +[2025-04-29 10:03:45,224][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 1.787539005279541, cross_entropy: 1.787539005279541 +[2025-04-29 10:03:45,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 2.6101839542388916, cross_entropy: 2.6101839542388916 +[2025-04-29 10:03:49,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 0.8447785377502441, cross_entropy: 0.8447785377502441 +[2025-04-29 10:03:49,824][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.224226474761963, cross_entropy: 2.224226474761963 +[2025-04-29 10:03:53,025][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 0.8748721480369568, cross_entropy: 0.8748721480369568 +[2025-04-29 10:03:53,368][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 2.2279419898986816, cross_entropy: 2.2279419898986816 +[2025-04-29 10:03:57,028][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.0408681631088257, cross_entropy: 1.0408681631088257 +[2025-04-29 10:03:57,369][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.816941261291504, cross_entropy: 2.816941261291504 +[2025-04-29 10:04:00,750][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 0.6019001007080078, cross_entropy: 0.6019001007080078 +[2025-04-29 10:04:01,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 0.6776443123817444, cross_entropy: 0.6776443123817444 +[2025-04-29 10:04:03,953][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 2.0037364959716797, cross_entropy: 2.0037364959716797 +[2025-04-29 10:04:04,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 1.7596275806427002, cross_entropy: 1.7596275806427002 +[2025-04-29 10:04:07,325][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 2.053713083267212, cross_entropy: 2.053713083267212 +[2025-04-29 10:04:07,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 1.2507152557373047, cross_entropy: 1.2507152557373047 +[2025-04-29 10:04:10,523][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 3.100450038909912, cross_entropy: 3.100450038909912 +[2025-04-29 10:04:10,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.1572434902191162, cross_entropy: 1.1572434902191162 +[2025-04-29 10:04:13,610][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 0.9386414289474487, cross_entropy: 0.9386414289474487 +[2025-04-29 10:04:14,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 2.5691885948181152, cross_entropy: 2.5691885948181152 +[2025-04-29 10:04:16,507][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.8520562648773193, cross_entropy: 2.8520562648773193 +[2025-04-29 10:04:18,217][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 0.8970228433609009, cross_entropy: 0.8970228433609009 +[2025-04-29 10:04:20,229][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 1.0515525341033936, cross_entropy: 1.0515525341033936 +[2025-04-29 10:04:22,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.9213111400604248, cross_entropy: 0.9213111400604248 +[2025-04-29 10:04:24,613][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 2.61146879196167, cross_entropy: 2.61146879196167 +[2025-04-29 10:04:25,419][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 0.8536253571510315, cross_entropy: 0.8536253571510315 +[2025-04-29 10:04:27,667][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.747282028198242, cross_entropy: 2.747282028198242 +[2025-04-29 10:04:28,863][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 2.801300048828125, cross_entropy: 2.801300048828125 +[2025-04-29 10:04:31,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.8131449222564697, cross_entropy: 2.8131449222564697 +[2025-04-29 10:04:32,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 0.790590226650238, cross_entropy: 0.790590226650238 +[2025-04-29 10:04:34,859][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.8226118087768555, cross_entropy: 0.8226118087768555 +[2025-04-29 10:04:35,623][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 1.0180565118789673, cross_entropy: 1.0180565118789673 +[2025-04-29 10:04:37,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.787752151489258, cross_entropy: 2.787752151489258 +[2025-04-29 10:04:38,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.029923439025879, cross_entropy: 2.029923439025879 +[2025-04-29 10:04:41,288][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.1346616744995117, cross_entropy: 2.1346616744995117 +[2025-04-29 10:04:41,953][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 1.2389012575149536, cross_entropy: 1.2389012575149536 +[2025-04-29 10:04:44,171][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 2.459453582763672, cross_entropy: 2.459453582763672 +[2025-04-29 10:04:45,218][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 2.370673179626465, cross_entropy: 2.370673179626465 +[2025-04-29 10:04:47,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 1.904040813446045, cross_entropy: 1.904040813446045 +[2025-04-29 10:04:48,367][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 1.6275568008422852, cross_entropy: 1.6275568008422852 +[2025-04-29 10:04:51,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 2.3506107330322266, cross_entropy: 2.3506107330322266 +[2025-04-29 10:04:51,767][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 2.795440196990967, cross_entropy: 2.795440196990967 +[2025-04-29 10:04:55,587][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.6206603050231934, cross_entropy: 2.6206603050231934 +[2025-04-29 10:04:55,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 0.9176634550094604, cross_entropy: 0.9176634550094604 +[2025-04-29 10:04:58,442][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 0.8971407413482666, cross_entropy: 0.8971407413482666 +[2025-04-29 10:04:58,779][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 0.6159853339195251, cross_entropy: 0.6159853339195251 +[2025-04-29 10:05:02,490][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.7702791690826416, cross_entropy: 2.7702791690826416 +[2025-04-29 10:05:02,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 3.0196709632873535, cross_entropy: 3.0196709632873535 +[2025-04-29 10:05:06,147][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 0.8569799065589905, cross_entropy: 0.8569799065589905 +[2025-04-29 10:05:06,782][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.6253726482391357, cross_entropy: 2.6253726482391357 +[2025-04-29 10:05:09,437][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 3.1340832710266113, cross_entropy: 3.1340832710266113 +[2025-04-29 10:05:09,782][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 1.2365574836730957, cross_entropy: 1.2365574836730957 +[2025-04-29 10:05:13,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 2.432530403137207, cross_entropy: 2.432530403137207 +[2025-04-29 10:05:13,676][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 2.9633102416992188, cross_entropy: 2.9633102416992188 +[2025-04-29 10:05:16,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 1.3158633708953857, cross_entropy: 1.3158633708953857 +[2025-04-29 10:05:17,428][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 0.6229780912399292, cross_entropy: 0.6229780912399292 +[2025-04-29 10:05:20,139][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 2.390133857727051, cross_entropy: 2.390133857727051 +[2025-04-29 10:05:20,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 0.9711059331893921, cross_entropy: 0.9711059331893921 +[2025-04-29 10:05:23,316][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 0.8468401432037354, cross_entropy: 0.8468401432037354 +[2025-04-29 10:05:24,320][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.35787034034729, cross_entropy: 1.35787034034729 +[2025-04-29 10:05:27,359][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 2.5625479221343994, cross_entropy: 2.5625479221343994 +[2025-04-29 10:05:27,682][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 0.7580796480178833, cross_entropy: 0.7580796480178833 +[2025-04-29 10:05:30,336][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 1.0840740203857422, cross_entropy: 1.0840740203857422 +[2025-04-29 10:05:31,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 1.8690601587295532, cross_entropy: 1.8690601587295532 +[2025-04-29 10:05:34,546][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 2.719151735305786, cross_entropy: 2.719151735305786 +[2025-04-29 10:05:34,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 1.3778197765350342, cross_entropy: 1.3778197765350342 +[2025-04-29 10:05:39,444][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.6318451166152954, cross_entropy: 0.6318451166152954 +[2025-04-29 10:05:39,792][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 0.8632825016975403, cross_entropy: 0.8632825016975403 +[2025-04-29 10:05:43,212][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.5873112678527832, cross_entropy: 1.5873112678527832 +[2025-04-29 10:05:43,527][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.4046357870101929, cross_entropy: 1.4046357870101929 +[2025-04-29 10:05:47,384][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 2.7104458808898926, cross_entropy: 2.7104458808898926 +[2025-04-29 10:05:47,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.3256099224090576, cross_entropy: 1.3256099224090576 +[2025-04-29 10:05:50,964][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 0.5584918856620789, cross_entropy: 0.5584918856620789 +[2025-04-29 10:05:51,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 1.7484354972839355, cross_entropy: 1.7484354972839355 +[2025-04-29 10:05:55,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 2.7800371646881104, cross_entropy: 2.7800371646881104 +[2025-04-29 10:05:55,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 2.514202117919922, cross_entropy: 2.514202117919922 +[2025-04-29 10:05:59,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 1.1405960321426392, cross_entropy: 1.1405960321426392 +[2025-04-29 10:06:00,307][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 2.335394859313965, cross_entropy: 2.335394859313965 +[2025-04-29 10:06:03,501][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.6140687465667725, cross_entropy: 2.6140687465667725 +[2025-04-29 10:06:03,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.1488856077194214, cross_entropy: 1.1488856077194214 +[2025-04-29 10:06:06,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 3.0476152896881104, cross_entropy: 3.0476152896881104 +[2025-04-29 10:06:07,258][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 2.602909564971924, cross_entropy: 2.602909564971924 +[2025-04-29 10:06:09,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 1.01458740234375, cross_entropy: 1.01458740234375 +[2025-04-29 10:06:10,052][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 0.8980573415756226, cross_entropy: 0.8980573415756226 +[2025-04-29 10:06:12,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 1.5739113092422485, cross_entropy: 1.5739113092422485 +[2025-04-29 10:06:13,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 0.9210759401321411, cross_entropy: 0.9210759401321411 +[2025-04-29 10:06:16,269][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 0.8898066282272339, cross_entropy: 0.8898066282272339 +[2025-04-29 10:06:16,581][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 2.686237096786499, cross_entropy: 2.686237096786499 +[2025-04-29 10:06:21,302][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.429758310317993, cross_entropy: 2.429758310317993 +[2025-04-29 10:06:21,651][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 2.391193389892578, cross_entropy: 2.391193389892578 +[2025-04-29 10:06:24,595][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 1.1822869777679443, cross_entropy: 1.1822869777679443 +[2025-04-29 10:06:24,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.05342698097229, cross_entropy: 1.05342698097229 +[2025-04-29 10:06:28,159][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 2.3449227809906006, cross_entropy: 2.3449227809906006 +[2025-04-29 10:06:28,501][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.225478172302246, cross_entropy: 1.225478172302246 +[2025-04-29 10:06:31,813][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 1.7780992984771729, cross_entropy: 1.7780992984771729 +[2025-04-29 10:06:32,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 1.3042092323303223, cross_entropy: 1.3042092323303223 +[2025-04-29 10:06:34,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 2.658607006072998, cross_entropy: 2.658607006072998 +[2025-04-29 10:06:35,217][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 2.6062471866607666, cross_entropy: 2.6062471866607666 +[2025-04-29 10:06:38,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.282280445098877, cross_entropy: 2.282280445098877 +[2025-04-29 10:06:38,537][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 1.2476805448532104, cross_entropy: 1.2476805448532104 +[2025-04-29 10:06:41,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 1.1575214862823486, cross_entropy: 1.1575214862823486 +[2025-04-29 10:06:42,289][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 1.953460454940796, cross_entropy: 1.953460454940796 +[2025-04-29 10:06:45,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 2.7746694087982178, cross_entropy: 2.7746694087982178 +[2025-04-29 10:06:45,857][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.71134614944458, cross_entropy: 2.71134614944458 +[2025-04-29 10:06:49,608][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 2.3922836780548096, cross_entropy: 2.3922836780548096 +[2025-04-29 10:06:49,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.9911081790924072, cross_entropy: 1.9911081790924072 +[2025-04-29 10:06:53,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 2.8972973823547363, cross_entropy: 2.8972973823547363 +[2025-04-29 10:06:53,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 1.412353277206421, cross_entropy: 1.412353277206421 +[2025-04-29 10:06:56,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 2.5396034717559814, cross_entropy: 2.5396034717559814 +[2025-04-29 10:06:57,265][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 1.4628474712371826, cross_entropy: 1.4628474712371826 +[2025-04-29 10:07:00,625][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 1.6492270231246948, cross_entropy: 1.6492270231246948 +[2025-04-29 10:07:00,939][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.3360979557037354, cross_entropy: 1.3360979557037354 +[2025-04-29 10:07:03,364][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.3842213153839111, cross_entropy: 1.3842213153839111 +[2025-04-29 10:07:03,644][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 2.3793253898620605, cross_entropy: 2.3793253898620605 +[2025-04-29 10:09:55,137][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.7180263996124268, cross_entropy: 1.7180263996124268 +[2025-04-29 10:09:55,137][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.2350361347198486, cross_entropy: 1.2350361347198486 +[2025-04-29 10:09:55,306][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/epoch10.pth. +[2025-04-29 10:09:55,524][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. +[2025-04-29 10:09:55,744][BaseTrainer][INFO] - Save model: ./exp/20250429-075315/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..47a710b4baa1905c786e9592e783d3ebcf69cb4a --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83557d691d9dc199355e7b37c3161d735d5ff018fc769757bb51269ca8d157fb +size 51764965 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..8158b639eb534bbd6f5f6e23c66d18efa63e33be --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-075315/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3c395018b2bc137e000ff0afb13de9648f1946f2c9ae55c0ece335e885bc27 +size 51716323 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/README.md b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/README.md new file mode 100644 index 0000000000000000000000000000000000000000..325b42ec1c4f6a80ea6a24320b2f6b3e1de94490 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/README.md @@ -0,0 +1,7 @@ +system=default_seed-2 +data=birdclef2025_reshape_15s +train=birdclef2025_reshape_efficientnet_b0 +model=birdclef2025_efficientnet_b0 +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.517 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c581b2eae3db2cb4ef97c94002e21145cd2388e0 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/config.yaml @@ -0,0 +1,221 @@ +system: + seed: 2 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-174748 + tensorboard_dir: ./tensorboard/20250429-174748 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0a5cd1204ba2f83d0b58ca6b06ddf5d7b8fcb848 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250429-174748/log/20250429-174752 + sweep: + dir: multirun/${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/20250429-174748/log/20250429-174752 + - hydra.mode=RUN + task: + - system=cuda_seed-2 + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_efficientnet_b0 + - model=birdclef2025_efficientnet_b0 + - optimizer=adam + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250429-174748 + - train.output.tensorboard_dir=./tensorboard/20250429-174748 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_15s,lr_scheduler=none,model=birdclef2025_efficientnet_b0,optimizer=adam,preprocess.dump_format=birdclef2025,preprocess=birdclef2025,system=cuda_seed-2,train.dataset.train.feature_dir=/kaggle/input/birdclef-2025,train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250429-174748,train.output.tensorboard_dir=./tensorboard/20250429-174748,train.resume.continue_from=,train=birdclef2025_reshape_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/20250429-174748/log/20250429-174752 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam + model: birdclef2025_efficientnet_b0 + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_15s + preprocess: birdclef2025 + system: cuda_seed-2 + 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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..85323583b915eda2e5006b977d002faf151a3e0e --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda_seed-2 +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_efficientnet_b0 +- model=birdclef2025_efficientnet_b0 +- optimizer=adam +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250429-174748 +- train.output.tensorboard_dir=./tensorboard/20250429-174748 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..997472656fb0b652cdf5afc59604f32112c2307e --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/.hydra/resolved_config.yaml @@ -0,0 +1,280 @@ +system: + seed: 2 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250429-174748 + tensorboard_dir: ./tensorboard/20250429-174748 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250429-174748/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250429-174748/model/epoch{epoch}.pth + last: + path: ./exp/20250429-174748/model/last.pth + best_epoch: + path: ./exp/20250429-174748/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/train.log new file mode 100644 index 0000000000000000000000000000000000000000..16e580b0d94a11872cbfd00f563252336e794209 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/log/20250429-174752/train.log @@ -0,0 +1,4281 @@ +[2025-04-29 17:48:24,079][BaseTrainer][INFO] - system: + seed: 2 + 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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-174748 + tensorboard_dir: ./tensorboard/20250429-174748 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-29 17:48:24,079][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) + ) +) +[2025-04-29 17:48:24,084][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-29 17:48:34,555][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.370720386505127, cross_entropy: 5.370720386505127 +[2025-04-29 17:48:34,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.248135089874268, cross_entropy: 5.248135089874268 +[2025-04-29 17:48:35,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.219254493713379, cross_entropy: 5.219254493713379 +[2025-04-29 17:48:36,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.112503528594971, cross_entropy: 5.112503528594971 +[2025-04-29 17:48:40,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.075361251831055, cross_entropy: 5.075361251831055 +[2025-04-29 17:48:41,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 4.868646621704102, cross_entropy: 4.868646621704102 +[2025-04-29 17:48:44,875][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.951467514038086, cross_entropy: 4.951467514038086 +[2025-04-29 17:48:46,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 4.886526584625244, cross_entropy: 4.886526584625244 +[2025-04-29 17:48:49,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.983381748199463, cross_entropy: 4.983381748199463 +[2025-04-29 17:48:50,868][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.011801719665527, cross_entropy: 5.011801719665527 +[2025-04-29 17:48:53,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.774420261383057, cross_entropy: 4.774420261383057 +[2025-04-29 17:48:55,951][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.866613388061523, cross_entropy: 4.866613388061523 +[2025-04-29 17:48:58,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.634262561798096, cross_entropy: 4.634262561798096 +[2025-04-29 17:49:00,145][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.900954246520996, cross_entropy: 4.900954246520996 +[2025-04-29 17:49:02,766][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.735268592834473, cross_entropy: 4.735268592834473 +[2025-04-29 17:49:04,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 5.127458572387695, cross_entropy: 5.127458572387695 +[2025-04-29 17:49:07,490][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 4.792211055755615, cross_entropy: 4.792211055755615 +[2025-04-29 17:49:09,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 4.995530605316162, cross_entropy: 4.995530605316162 +[2025-04-29 17:49:12,018][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.729854106903076, cross_entropy: 4.729854106903076 +[2025-04-29 17:49:13,907][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.537911891937256, cross_entropy: 4.537911891937256 +[2025-04-29 17:49:16,972][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.699958801269531, cross_entropy: 4.699958801269531 +[2025-04-29 17:49:18,638][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.881274700164795, cross_entropy: 4.881274700164795 +[2025-04-29 17:49:21,732][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.874640464782715, cross_entropy: 4.874640464782715 +[2025-04-29 17:49:22,924][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.849064826965332, cross_entropy: 4.849064826965332 +[2025-04-29 17:49:26,182][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.536708831787109, cross_entropy: 4.536708831787109 +[2025-04-29 17:49:27,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.606867790222168, cross_entropy: 4.606867790222168 +[2025-04-29 17:49:30,942][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.706572532653809, cross_entropy: 4.706572532653809 +[2025-04-29 17:49:32,234][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.678995132446289, cross_entropy: 4.678995132446289 +[2025-04-29 17:49:35,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.740875720977783, cross_entropy: 4.740875720977783 +[2025-04-29 17:49:37,257][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.408588409423828, cross_entropy: 4.408588409423828 +[2025-04-29 17:49:40,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.409946441650391, cross_entropy: 4.409946441650391 +[2025-04-29 17:49:41,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.641819953918457, cross_entropy: 4.641819953918457 +[2025-04-29 17:49:44,973][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.492342948913574, cross_entropy: 4.492342948913574 +[2025-04-29 17:49:46,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.6285400390625, cross_entropy: 4.6285400390625 +[2025-04-29 17:49:50,078][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.334724426269531, cross_entropy: 4.334724426269531 +[2025-04-29 17:49:50,708][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.632599830627441, cross_entropy: 4.632599830627441 +[2025-04-29 17:49:54,007][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.828472137451172, cross_entropy: 4.828472137451172 +[2025-04-29 17:49:55,958][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.689214706420898, cross_entropy: 4.689214706420898 +[2025-04-29 17:49:59,006][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.5238566398620605, cross_entropy: 4.5238566398620605 +[2025-04-29 17:50:00,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.637528419494629, cross_entropy: 4.637528419494629 +[2025-04-29 17:50:03,560][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.6155686378479, cross_entropy: 4.6155686378479 +[2025-04-29 17:50:04,926][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.398857593536377, cross_entropy: 4.398857593536377 +[2025-04-29 17:50:08,324][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.27070426940918, cross_entropy: 4.27070426940918 +[2025-04-29 17:50:09,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.434690475463867, cross_entropy: 4.434690475463867 +[2025-04-29 17:50:13,142][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.6539411544799805, cross_entropy: 4.6539411544799805 +[2025-04-29 17:50:14,419][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.6968278884887695, cross_entropy: 4.6968278884887695 +[2025-04-29 17:50:17,636][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.607226371765137, cross_entropy: 4.607226371765137 +[2025-04-29 17:50:18,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.077602863311768, cross_entropy: 4.077602863311768 +[2025-04-29 17:50:21,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.151134967803955, cross_entropy: 4.151134967803955 +[2025-04-29 17:50:23,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.526429653167725, cross_entropy: 4.526429653167725 +[2025-04-29 17:50:26,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.493753910064697, cross_entropy: 4.493753910064697 +[2025-04-29 17:50:28,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.360426902770996, cross_entropy: 4.360426902770996 +[2025-04-29 17:50:30,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.372464656829834, cross_entropy: 4.372464656829834 +[2025-04-29 17:50:32,604][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.160522937774658, cross_entropy: 4.160522937774658 +[2025-04-29 17:50:35,037][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.5536394119262695, cross_entropy: 4.5536394119262695 +[2025-04-29 17:50:38,114][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.265474319458008, cross_entropy: 4.265474319458008 +[2025-04-29 17:50:40,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.010392189025879, cross_entropy: 4.010392189025879 +[2025-04-29 17:50:43,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.164439678192139, cross_entropy: 4.164439678192139 +[2025-04-29 17:50:45,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.157456398010254, cross_entropy: 4.157456398010254 +[2025-04-29 17:50:48,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.590405464172363, cross_entropy: 4.590405464172363 +[2025-04-29 17:50:50,592][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.418733596801758, cross_entropy: 4.418733596801758 +[2025-04-29 17:50:53,016][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.1277079582214355, cross_entropy: 4.1277079582214355 +[2025-04-29 17:50:54,832][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.209315299987793, cross_entropy: 4.209315299987793 +[2025-04-29 17:50:57,734][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 3.638474702835083, cross_entropy: 3.638474702835083 +[2025-04-29 17:50:59,599][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 3.856978178024292, cross_entropy: 3.856978178024292 +[2025-04-29 17:51:02,244][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.416614055633545, cross_entropy: 4.416614055633545 +[2025-04-29 17:51:03,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.061223030090332, cross_entropy: 4.061223030090332 +[2025-04-29 17:51:07,204][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 3.612600326538086, cross_entropy: 3.612600326538086 +[2025-04-29 17:51:08,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 3.9325146675109863, cross_entropy: 3.9325146675109863 +[2025-04-29 17:51:11,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.351992130279541, cross_entropy: 4.351992130279541 +[2025-04-29 17:51:12,700][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.204993724822998, cross_entropy: 4.204993724822998 +[2025-04-29 17:51:16,936][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 3.836629867553711, cross_entropy: 3.836629867553711 +[2025-04-29 17:51:18,221][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.7105038166046143, cross_entropy: 3.7105038166046143 +[2025-04-29 17:51:21,121][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.159997940063477, cross_entropy: 4.159997940063477 +[2025-04-29 17:51:22,390][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.251653671264648, cross_entropy: 4.251653671264648 +[2025-04-29 17:51:25,645][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.3276567459106445, cross_entropy: 4.3276567459106445 +[2025-04-29 17:51:26,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.351861953735352, cross_entropy: 4.351861953735352 +[2025-04-29 17:51:30,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.46771240234375, cross_entropy: 4.46771240234375 +[2025-04-29 17:51:32,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 3.536856174468994, cross_entropy: 3.536856174468994 +[2025-04-29 17:51:35,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 3.7702043056488037, cross_entropy: 3.7702043056488037 +[2025-04-29 17:51:37,159][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.358906269073486, cross_entropy: 4.358906269073486 +[2025-04-29 17:51:39,851][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.0672760009765625, cross_entropy: 4.0672760009765625 +[2025-04-29 17:51:41,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 3.750098705291748, cross_entropy: 3.750098705291748 +[2025-04-29 17:51:45,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.145288467407227, cross_entropy: 4.145288467407227 +[2025-04-29 17:51:46,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.721959114074707, cross_entropy: 4.721959114074707 +[2025-04-29 17:51:50,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.525437831878662, cross_entropy: 3.525437831878662 +[2025-04-29 17:51:52,733][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 3.6800146102905273, cross_entropy: 3.6800146102905273 +[2025-04-29 17:51:55,462][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.347991943359375, cross_entropy: 4.347991943359375 +[2025-04-29 17:51:57,336][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 3.6076431274414062, cross_entropy: 3.6076431274414062 +[2025-04-29 17:51:59,624][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.841503620147705, cross_entropy: 3.841503620147705 +[2025-04-29 17:52:01,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 3.737199068069458, cross_entropy: 3.737199068069458 +[2025-04-29 17:52:04,607][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.425377368927002, cross_entropy: 3.425377368927002 +[2025-04-29 17:52:06,790][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.968636989593506, cross_entropy: 3.968636989593506 +[2025-04-29 17:52:10,674][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 3.3401947021484375, cross_entropy: 3.3401947021484375 +[2025-04-29 17:52:11,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.134128570556641, cross_entropy: 4.134128570556641 +[2025-04-29 17:52:15,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.972137928009033, cross_entropy: 3.972137928009033 +[2025-04-29 17:52:16,486][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 3.5893640518188477, cross_entropy: 3.5893640518188477 +[2025-04-29 17:52:19,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.835136890411377, cross_entropy: 3.835136890411377 +[2025-04-29 17:52:21,252][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 3.833524227142334, cross_entropy: 3.833524227142334 +[2025-04-29 17:52:23,898][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 4.234801769256592, cross_entropy: 4.234801769256592 +[2025-04-29 17:52:25,627][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 3.884666919708252, cross_entropy: 3.884666919708252 +[2025-04-29 17:52:29,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.39121150970459, cross_entropy: 3.39121150970459 +[2025-04-29 17:52:30,648][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.597296237945557, cross_entropy: 4.597296237945557 +[2025-04-29 17:52:34,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.6450741291046143, cross_entropy: 3.6450741291046143 +[2025-04-29 17:52:34,978][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.964569091796875, cross_entropy: 3.964569091796875 +[2025-04-29 17:52:38,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.64872932434082, cross_entropy: 4.64872932434082 +[2025-04-29 17:52:39,002][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 4.128273010253906, cross_entropy: 4.128273010253906 +[2025-04-29 17:52:43,039][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.1570844650268555, cross_entropy: 4.1570844650268555 +[2025-04-29 17:52:43,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.5114517211914062, cross_entropy: 3.5114517211914062 +[2025-04-29 17:52:47,722][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 3.0940887928009033, cross_entropy: 3.0940887928009033 +[2025-04-29 17:52:48,150][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 4.291410446166992, cross_entropy: 4.291410446166992 +[2025-04-29 17:52:53,543][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.6765382289886475, cross_entropy: 3.6765382289886475 +[2025-04-29 17:52:53,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 3.661576271057129, cross_entropy: 3.661576271057129 +[2025-04-29 17:52:58,129][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.029156684875488, cross_entropy: 4.029156684875488 +[2025-04-29 17:52:58,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.3290696144104, cross_entropy: 4.3290696144104 +[2025-04-29 17:53:03,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 4.208154201507568, cross_entropy: 4.208154201507568 +[2025-04-29 17:53:03,457][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 4.021481990814209, cross_entropy: 4.021481990814209 +[2025-04-29 17:53:07,669][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 3.3839969635009766, cross_entropy: 3.3839969635009766 +[2025-04-29 17:53:08,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.178586006164551, cross_entropy: 4.178586006164551 +[2025-04-29 17:53:12,705][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.487148284912109, cross_entropy: 4.487148284912109 +[2025-04-29 17:53:13,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 3.8898401260375977, cross_entropy: 3.8898401260375977 +[2025-04-29 17:53:17,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 3.143747329711914, cross_entropy: 3.143747329711914 +[2025-04-29 17:53:18,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.4923906326293945, cross_entropy: 3.4923906326293945 +[2025-04-29 17:53:21,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.8133914470672607, cross_entropy: 3.8133914470672607 +[2025-04-29 17:53:21,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 3.001939296722412, cross_entropy: 3.001939296722412 +[2025-04-29 17:53:27,294][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 4.1359100341796875, cross_entropy: 4.1359100341796875 +[2025-04-29 17:53:27,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.435842990875244, cross_entropy: 3.435842990875244 +[2025-04-29 17:53:32,128][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.12479305267334, cross_entropy: 4.12479305267334 +[2025-04-29 17:53:32,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 2.7794666290283203, cross_entropy: 2.7794666290283203 +[2025-04-29 17:53:36,609][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 3.891570568084717, cross_entropy: 3.891570568084717 +[2025-04-29 17:53:36,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 3.914666175842285, cross_entropy: 3.914666175842285 +[2025-04-29 17:53:42,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 4.312994956970215, cross_entropy: 4.312994956970215 +[2025-04-29 17:53:42,499][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 3.5973358154296875, cross_entropy: 3.5973358154296875 +[2025-04-29 17:53:46,937][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 3.037221908569336, cross_entropy: 3.037221908569336 +[2025-04-29 17:53:47,281][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 3.751159906387329, cross_entropy: 3.751159906387329 +[2025-04-29 17:53:51,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.007251262664795, cross_entropy: 3.007251262664795 +[2025-04-29 17:53:51,748][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 4.257142066955566, cross_entropy: 4.257142066955566 +[2025-04-29 17:53:56,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 3.473461151123047, cross_entropy: 3.473461151123047 +[2025-04-29 17:53:56,817][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.017474174499512, cross_entropy: 4.017474174499512 +[2025-04-29 17:54:00,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.4122486114501953, cross_entropy: 3.4122486114501953 +[2025-04-29 17:54:01,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.09777307510376, cross_entropy: 4.09777307510376 +[2025-04-29 17:54:05,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.820303440093994, cross_entropy: 3.820303440093994 +[2025-04-29 17:54:06,142][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.239126682281494, cross_entropy: 3.239126682281494 +[2025-04-29 17:54:10,302][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 3.0873453617095947, cross_entropy: 3.0873453617095947 +[2025-04-29 17:54:10,654][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.218761444091797, cross_entropy: 4.218761444091797 +[2025-04-29 17:54:14,467][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.494140386581421, cross_entropy: 3.494140386581421 +[2025-04-29 17:54:14,789][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 3.4334774017333984, cross_entropy: 3.4334774017333984 +[2025-04-29 17:54:19,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.3977770805358887, cross_entropy: 3.3977770805358887 +[2025-04-29 17:54:19,707][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.047356605529785, cross_entropy: 4.047356605529785 +[2025-04-29 17:54:23,546][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 3.3621628284454346, cross_entropy: 3.3621628284454346 +[2025-04-29 17:54:23,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.7104685306549072, cross_entropy: 3.7104685306549072 +[2025-04-29 17:54:28,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 2.9831433296203613, cross_entropy: 2.9831433296203613 +[2025-04-29 17:54:29,037][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 3.4315261840820312, cross_entropy: 3.4315261840820312 +[2025-04-29 17:54:33,056][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 3.342902183532715, cross_entropy: 3.342902183532715 +[2025-04-29 17:54:33,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.248863458633423, cross_entropy: 3.248863458633423 +[2025-04-29 17:54:37,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 4.367751121520996, cross_entropy: 4.367751121520996 +[2025-04-29 17:54:38,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.1868109703063965, cross_entropy: 4.1868109703063965 +[2025-04-29 17:54:42,966][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.4174182415008545, cross_entropy: 3.4174182415008545 +[2025-04-29 17:54:43,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 3.1065053939819336, cross_entropy: 3.1065053939819336 +[2025-04-29 17:54:47,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 4.0976715087890625, cross_entropy: 4.0976715087890625 +[2025-04-29 17:54:47,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 3.2282299995422363, cross_entropy: 3.2282299995422363 +[2025-04-29 17:54:51,966][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 4.337550640106201, cross_entropy: 4.337550640106201 +[2025-04-29 17:54:52,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 2.8659210205078125, cross_entropy: 2.8659210205078125 +[2025-04-29 17:54:56,482][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 2.9264745712280273, cross_entropy: 2.9264745712280273 +[2025-04-29 17:54:56,830][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.190516948699951, cross_entropy: 3.190516948699951 +[2025-04-29 17:55:00,982][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 3.4950978755950928, cross_entropy: 3.4950978755950928 +[2025-04-29 17:55:01,301][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.326366901397705, cross_entropy: 3.326366901397705 +[2025-04-29 17:55:05,545][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.853125810623169, cross_entropy: 3.853125810623169 +[2025-04-29 17:55:05,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 3.082181453704834, cross_entropy: 3.082181453704834 +[2025-04-29 17:55:10,316][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.1584181785583496, cross_entropy: 3.1584181785583496 +[2025-04-29 17:55:10,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 3.914933681488037, cross_entropy: 3.914933681488037 +[2025-04-29 17:55:14,866][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.3190689086914062, cross_entropy: 3.3190689086914062 +[2025-04-29 17:55:15,231][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.260010242462158, cross_entropy: 3.260010242462158 +[2025-04-29 17:55:19,649][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.032077312469482, cross_entropy: 4.032077312469482 +[2025-04-29 17:55:19,974][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.005321979522705, cross_entropy: 4.005321979522705 +[2025-04-29 17:55:23,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 4.035769462585449, cross_entropy: 4.035769462585449 +[2025-04-29 17:55:24,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 2.769425868988037, cross_entropy: 2.769425868988037 +[2025-04-29 17:55:28,007][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.3119571208953857, cross_entropy: 3.3119571208953857 +[2025-04-29 17:55:28,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 4.208974838256836, cross_entropy: 4.208974838256836 +[2025-04-29 17:55:32,512][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.041027069091797, cross_entropy: 3.041027069091797 +[2025-04-29 17:55:32,848][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 2.8918488025665283, cross_entropy: 2.8918488025665283 +[2025-04-29 17:55:36,785][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 2.9159951210021973, cross_entropy: 2.9159951210021973 +[2025-04-29 17:55:37,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 3.3722071647644043, cross_entropy: 3.3722071647644043 +[2025-04-29 17:55:41,720][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 3.1916849613189697, cross_entropy: 3.1916849613189697 +[2025-04-29 17:55:42,040][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 4.130825042724609, cross_entropy: 4.130825042724609 +[2025-04-29 17:55:46,678][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.2259466648101807, cross_entropy: 3.2259466648101807 +[2025-04-29 17:55:47,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.2417526245117188, cross_entropy: 3.2417526245117188 +[2025-04-29 17:55:50,866][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.2943413257598877, cross_entropy: 3.2943413257598877 +[2025-04-29 17:55:51,193][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 3.53195858001709, cross_entropy: 3.53195858001709 +[2025-04-29 17:55:55,204][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 2.739776134490967, cross_entropy: 2.739776134490967 +[2025-04-29 17:55:56,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 3.3571457862854004, cross_entropy: 3.3571457862854004 +[2025-04-29 17:55:59,585][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.389861583709717, cross_entropy: 3.389861583709717 +[2025-04-29 17:56:00,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.095000743865967, cross_entropy: 4.095000743865967 +[2025-04-29 17:56:04,699][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 3.0426506996154785, cross_entropy: 3.0426506996154785 +[2025-04-29 17:56:05,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 3.8180367946624756, cross_entropy: 3.8180367946624756 +[2025-04-29 17:56:08,483][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.1978766918182373, cross_entropy: 3.1978766918182373 +[2025-04-29 17:56:09,206][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.286276340484619, cross_entropy: 3.286276340484619 +[2025-04-29 17:56:12,569][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 3.2160439491271973, cross_entropy: 3.2160439491271973 +[2025-04-29 17:56:13,989][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 4.039975643157959, cross_entropy: 4.039975643157959 +[2025-04-29 17:56:17,000][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 2.487506866455078, cross_entropy: 2.487506866455078 +[2025-04-29 17:56:18,582][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 4.020524024963379, cross_entropy: 4.020524024963379 +[2025-04-29 17:56:21,528][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 2.6256461143493652, cross_entropy: 2.6256461143493652 +[2025-04-29 17:56:23,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 2.667351722717285, cross_entropy: 2.667351722717285 +[2025-04-29 17:56:26,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 4.226911544799805, cross_entropy: 4.226911544799805 +[2025-04-29 17:56:27,320][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 3.5632567405700684, cross_entropy: 3.5632567405700684 +[2025-04-29 17:56:31,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 2.774374485015869, cross_entropy: 2.774374485015869 +[2025-04-29 17:56:31,920][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 3.4879255294799805, cross_entropy: 3.4879255294799805 +[2025-04-29 17:56:35,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.485037088394165, cross_entropy: 3.485037088394165 +[2025-04-29 17:56:36,518][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 2.8299129009246826, cross_entropy: 2.8299129009246826 +[2025-04-29 17:56:40,449][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 4.075940132141113, cross_entropy: 4.075940132141113 +[2025-04-29 17:56:41,387][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.6228199005126953, cross_entropy: 3.6228199005126953 +[2025-04-29 17:56:45,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 2.87528395652771, cross_entropy: 2.87528395652771 +[2025-04-29 17:56:46,224][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.068840742111206, cross_entropy: 3.068840742111206 +[2025-04-29 17:56:49,084][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 3.9330201148986816, cross_entropy: 3.9330201148986816 +[2025-04-29 17:56:51,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.1696364879608154, cross_entropy: 3.1696364879608154 +[2025-04-29 17:56:53,502][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 3.1659505367279053, cross_entropy: 3.1659505367279053 +[2025-04-29 17:56:56,592][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.924222946166992, cross_entropy: 3.924222946166992 +[2025-04-29 17:56:57,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 3.6363391876220703, cross_entropy: 3.6363391876220703 +[2025-04-29 17:57:01,200][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.533567428588867, cross_entropy: 3.533567428588867 +[2025-04-29 17:57:02,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.3618297576904297, cross_entropy: 3.3618297576904297 +[2025-04-29 17:57:06,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 2.5459630489349365, cross_entropy: 2.5459630489349365 +[2025-04-29 17:57:08,196][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 2.5508313179016113, cross_entropy: 2.5508313179016113 +[2025-04-29 17:57:11,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 2.9234867095947266, cross_entropy: 2.9234867095947266 +[2025-04-29 17:57:13,006][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.0370161533355713, cross_entropy: 3.0370161533355713 +[2025-04-29 17:57:16,802][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 2.701503038406372, cross_entropy: 2.701503038406372 +[2025-04-29 17:57:18,593][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.40218448638916, cross_entropy: 3.40218448638916 +[2025-04-29 17:57:21,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 2.728158950805664, cross_entropy: 2.728158950805664 +[2025-04-29 17:57:23,256][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.6139745712280273, cross_entropy: 3.6139745712280273 +[2025-04-29 17:57:26,936][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 4.076269626617432, cross_entropy: 4.076269626617432 +[2025-04-29 17:57:27,808][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 2.5905399322509766, cross_entropy: 2.5905399322509766 +[2025-04-29 17:57:31,404][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 3.848341941833496, cross_entropy: 3.848341941833496 +[2025-04-29 17:57:32,460][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 2.5814356803894043, cross_entropy: 2.5814356803894043 +[2025-04-29 17:57:36,774][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.0216593742370605, cross_entropy: 2.0216593742370605 +[2025-04-29 17:57:37,248][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 3.8945231437683105, cross_entropy: 3.8945231437683105 +[2025-04-29 17:57:42,197][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.5506999492645264, cross_entropy: 3.5506999492645264 +[2025-04-29 17:57:42,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 2.883009672164917, cross_entropy: 2.883009672164917 +[2025-04-29 17:57:46,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 2.8685028553009033, cross_entropy: 2.8685028553009033 +[2025-04-29 17:57:46,935][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.596585273742676, cross_entropy: 2.596585273742676 +[2025-04-29 17:57:50,714][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 3.692023992538452, cross_entropy: 3.692023992538452 +[2025-04-29 17:57:51,086][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.966172218322754, cross_entropy: 3.966172218322754 +[2025-04-29 17:57:55,269][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 2.5913660526275635, cross_entropy: 2.5913660526275635 +[2025-04-29 17:57:55,735][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.4110288619995117, cross_entropy: 2.4110288619995117 +[2025-04-29 17:57:59,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 2.3906056880950928, cross_entropy: 2.3906056880950928 +[2025-04-29 17:58:00,356][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 3.909674644470215, cross_entropy: 3.909674644470215 +[2025-04-29 17:58:04,048][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.6696929931640625, cross_entropy: 3.6696929931640625 +[2025-04-29 17:58:04,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 2.887533664703369, cross_entropy: 2.887533664703369 +[2025-04-29 17:58:08,631][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.8603713512420654, cross_entropy: 3.8603713512420654 +[2025-04-29 17:58:09,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 2.189697504043579, cross_entropy: 2.189697504043579 +[2025-04-29 17:58:13,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.458526849746704, cross_entropy: 3.458526849746704 +[2025-04-29 17:58:14,244][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 2.6643409729003906, cross_entropy: 2.6643409729003906 +[2025-04-29 17:58:18,486][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.713320016860962, cross_entropy: 3.713320016860962 +[2025-04-29 17:58:18,829][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 3.8166308403015137, cross_entropy: 3.8166308403015137 +[2025-04-29 17:58:23,118][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 2.3576812744140625, cross_entropy: 2.3576812744140625 +[2025-04-29 17:58:24,570][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 3.8307340145111084, cross_entropy: 3.8307340145111084 +[2025-04-29 17:58:27,871][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.2183852195739746, cross_entropy: 3.2183852195739746 +[2025-04-29 17:58:30,241][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.673103094100952, cross_entropy: 3.673103094100952 +[2025-04-29 17:58:32,384][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 2.44337797164917, cross_entropy: 2.44337797164917 +[2025-04-29 17:58:35,068][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 2.909951686859131, cross_entropy: 2.909951686859131 +[2025-04-29 17:58:36,753][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 2.461181163787842, cross_entropy: 2.461181163787842 +[2025-04-29 17:58:39,795][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 2.999459743499756, cross_entropy: 2.999459743499756 +[2025-04-29 17:58:41,596][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.7098031044006348, cross_entropy: 2.7098031044006348 +[2025-04-29 17:58:44,602][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.949233055114746, cross_entropy: 2.949233055114746 +[2025-04-29 17:58:46,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 3.222745895385742, cross_entropy: 3.222745895385742 +[2025-04-29 17:58:50,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 2.5834152698516846, cross_entropy: 2.5834152698516846 +[2025-04-29 17:58:51,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 2.961562156677246, cross_entropy: 2.961562156677246 +[2025-04-29 17:58:54,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.243682861328125, cross_entropy: 3.243682861328125 +[2025-04-29 17:58:56,251][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 3.933295965194702, cross_entropy: 3.933295965194702 +[2025-04-29 17:58:59,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.08164644241333, cross_entropy: 2.08164644241333 +[2025-04-29 17:59:00,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 2.7834601402282715, cross_entropy: 2.7834601402282715 +[2025-04-29 17:59:04,265][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 2.505035877227783, cross_entropy: 2.505035877227783 +[2025-04-29 17:59:06,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 2.105391025543213, cross_entropy: 2.105391025543213 +[2025-04-29 17:59:09,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.8025999069213867, cross_entropy: 2.8025999069213867 +[2025-04-29 17:59:11,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.0057637691497803, cross_entropy: 3.0057637691497803 +[2025-04-29 17:59:13,711][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 2.8755412101745605, cross_entropy: 2.8755412101745605 +[2025-04-29 17:59:16,437][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.379866600036621, cross_entropy: 2.379866600036621 +[2025-04-29 17:59:19,008][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 4.305426120758057, cross_entropy: 4.305426120758057 +[2025-04-29 17:59:22,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 2.6862432956695557, cross_entropy: 2.6862432956695557 +[2025-04-29 17:59:23,690][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 2.4985079765319824, cross_entropy: 2.4985079765319824 +[2025-04-29 17:59:27,462][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.4551234245300293, cross_entropy: 2.4551234245300293 +[2025-04-29 17:59:28,579][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 2.801717758178711, cross_entropy: 2.801717758178711 +[2025-04-29 17:59:32,638][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.6343603134155273, cross_entropy: 2.6343603134155273 +[2025-04-29 17:59:33,192][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.7296266555786133, cross_entropy: 3.7296266555786133 +[2025-04-29 17:59:37,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 2.8054208755493164, cross_entropy: 2.8054208755493164 +[2025-04-29 17:59:38,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.3917837142944336, cross_entropy: 2.3917837142944336 +[2025-04-29 17:59:41,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.950347900390625, cross_entropy: 2.950347900390625 +[2025-04-29 17:59:42,665][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.565101385116577, cross_entropy: 3.565101385116577 +[2025-04-29 17:59:46,768][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.8414244651794434, cross_entropy: 3.8414244651794434 +[2025-04-29 17:59:47,317][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.0315170288085938, cross_entropy: 3.0315170288085938 +[2025-04-29 17:59:51,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 2.4740097522735596, cross_entropy: 2.4740097522735596 +[2025-04-29 17:59:52,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.374148368835449, cross_entropy: 2.374148368835449 +[2025-04-29 17:59:56,759][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.2744877338409424, cross_entropy: 2.2744877338409424 +[2025-04-29 17:59:58,422][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 2.579594135284424, cross_entropy: 2.579594135284424 +[2025-04-29 18:00:01,171][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 2.822277545928955, cross_entropy: 2.822277545928955 +[2025-04-29 18:00:03,945][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.1724002361297607, cross_entropy: 2.1724002361297607 +[2025-04-29 18:00:05,702][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 3.1029539108276367, cross_entropy: 3.1029539108276367 +[2025-04-29 18:00:08,137][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.6257381439208984, cross_entropy: 3.6257381439208984 +[2025-04-29 18:00:10,345][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 3.7648122310638428, cross_entropy: 3.7648122310638428 +[2025-04-29 18:00:12,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.8809428215026855, cross_entropy: 3.8809428215026855 +[2025-04-29 18:00:15,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.982192277908325, cross_entropy: 2.982192277908325 +[2025-04-29 18:00:16,542][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.9349396228790283, cross_entropy: 3.9349396228790283 +[2025-04-29 18:00:19,385][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 3.769198417663574, cross_entropy: 3.769198417663574 +[2025-04-29 18:00:20,914][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 2.872041702270508, cross_entropy: 2.872041702270508 +[2025-04-29 18:00:23,850][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 3.4682483673095703, cross_entropy: 3.4682483673095703 +[2025-04-29 18:00:26,130][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 2.3444533348083496, cross_entropy: 2.3444533348083496 +[2025-04-29 18:00:28,547][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 3.808121919631958, cross_entropy: 3.808121919631958 +[2025-04-29 18:00:30,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 2.409646987915039, cross_entropy: 2.409646987915039 +[2025-04-29 18:00:32,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 1.8721981048583984, cross_entropy: 1.8721981048583984 +[2025-04-29 18:00:34,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 2.6172590255737305, cross_entropy: 2.6172590255737305 +[2025-04-29 18:00:36,760][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 2.6371145248413086, cross_entropy: 2.6371145248413086 +[2025-04-29 18:00:39,083][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.0168323516845703, cross_entropy: 2.0168323516845703 +[2025-04-29 18:00:40,742][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.408797264099121, cross_entropy: 2.408797264099121 +[2025-04-29 18:00:44,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 2.1886610984802246, cross_entropy: 2.1886610984802246 +[2025-04-29 18:00:45,964][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.4442873001098633, cross_entropy: 3.4442873001098633 +[2025-04-29 18:00:49,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.247588634490967, cross_entropy: 3.247588634490967 +[2025-04-29 18:00:51,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.4326467514038086, cross_entropy: 2.4326467514038086 +[2025-04-29 18:00:54,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.6945042610168457, cross_entropy: 3.6945042610168457 +[2025-04-29 18:00:55,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 4.026097774505615, cross_entropy: 4.026097774505615 +[2025-04-29 18:00:58,710][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 2.7416582107543945, cross_entropy: 2.7416582107543945 +[2025-04-29 18:01:00,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.9006917476654053, cross_entropy: 3.9006917476654053 +[2025-04-29 18:01:02,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 3.1678214073181152, cross_entropy: 3.1678214073181152 +[2025-04-29 18:01:05,770][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 3.1946704387664795, cross_entropy: 3.1946704387664795 +[2025-04-29 18:01:07,118][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 2.9082884788513184, cross_entropy: 2.9082884788513184 +[2025-04-29 18:01:10,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.234675884246826, cross_entropy: 3.234675884246826 +[2025-04-29 18:01:11,422][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 3.688429832458496, cross_entropy: 3.688429832458496 +[2025-04-29 18:01:15,436][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.6529088020324707, cross_entropy: 3.6529088020324707 +[2025-04-29 18:01:15,788][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 2.4574992656707764, cross_entropy: 2.4574992656707764 +[2025-04-29 18:01:20,111][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.5375747680664062, cross_entropy: 2.5375747680664062 +[2025-04-29 18:01:20,436][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 3.340519428253174, cross_entropy: 3.340519428253174 +[2025-04-29 18:01:25,388][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.13608717918396, cross_entropy: 3.13608717918396 +[2025-04-29 18:01:25,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.599324941635132, cross_entropy: 3.599324941635132 +[2025-04-29 18:01:31,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 2.5191490650177, cross_entropy: 2.5191490650177 +[2025-04-29 18:01:31,957][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.050062894821167, cross_entropy: 3.050062894821167 +[2025-04-29 18:01:37,706][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.5244266986846924, cross_entropy: 3.5244266986846924 +[2025-04-29 18:01:38,028][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.7255311012268066, cross_entropy: 3.7255311012268066 +[2025-04-29 18:01:42,003][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.590181827545166, cross_entropy: 2.590181827545166 +[2025-04-29 18:01:42,351][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 3.4255828857421875, cross_entropy: 3.4255828857421875 +[2025-04-29 18:01:47,037][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 3.0579562187194824, cross_entropy: 3.0579562187194824 +[2025-04-29 18:01:47,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 3.609612464904785, cross_entropy: 3.609612464904785 +[2025-04-29 18:01:52,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 3.277726650238037, cross_entropy: 3.277726650238037 +[2025-04-29 18:01:52,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 2.766343832015991, cross_entropy: 2.766343832015991 +[2025-04-29 18:01:57,266][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.6632256507873535, cross_entropy: 2.6632256507873535 +[2025-04-29 18:01:57,591][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.5643444061279297, cross_entropy: 3.5643444061279297 +[2025-04-29 18:02:01,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 2.1336584091186523, cross_entropy: 2.1336584091186523 +[2025-04-29 18:02:02,061][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 4.074329853057861, cross_entropy: 4.074329853057861 +[2025-04-29 18:02:06,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.233433246612549, cross_entropy: 3.233433246612549 +[2025-04-29 18:02:06,410][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.810969352722168, cross_entropy: 3.810969352722168 +[2025-04-29 18:02:10,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.7782843112945557, cross_entropy: 2.7782843112945557 +[2025-04-29 18:02:11,080][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 3.8504152297973633, cross_entropy: 3.8504152297973633 +[2025-04-29 18:02:15,277][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 3.243556261062622, cross_entropy: 3.243556261062622 +[2025-04-29 18:02:15,600][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.5832340717315674, cross_entropy: 2.5832340717315674 +[2025-04-29 18:02:20,174][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 2.9908058643341064, cross_entropy: 2.9908058643341064 +[2025-04-29 18:02:20,527][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.051875591278076, cross_entropy: 2.051875591278076 +[2025-04-29 18:02:24,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 2.0756783485412598, cross_entropy: 2.0756783485412598 +[2025-04-29 18:02:24,719][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 2.369302272796631, cross_entropy: 2.369302272796631 +[2025-04-29 18:02:29,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.5425381660461426, cross_entropy: 3.5425381660461426 +[2025-04-29 18:02:32,689][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 2.2635064125061035, cross_entropy: 2.2635064125061035 +[2025-04-29 18:06:17,547][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.587773084640503, cross_entropy: 3.587773084640503 +[2025-04-29 18:06:17,547][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.253652572631836, cross_entropy: 2.253652572631836 +[2025-04-29 18:06:17,751][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 18:06:18,000][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch1.pth. +[2025-04-29 18:06:18,223][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 18:06:23,683][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.3215279579162598, cross_entropy: 3.3215279579162598 +[2025-04-29 18:06:24,043][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.3953592777252197, cross_entropy: 2.3953592777252197 +[2025-04-29 18:06:27,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 2.1859593391418457, cross_entropy: 2.1859593391418457 +[2025-04-29 18:06:28,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 3.168323516845703, cross_entropy: 3.168323516845703 +[2025-04-29 18:06:31,299][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.207179307937622, cross_entropy: 2.207179307937622 +[2025-04-29 18:06:31,683][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 2.0835328102111816, cross_entropy: 2.0835328102111816 +[2025-04-29 18:06:35,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.5441739559173584, cross_entropy: 2.5441739559173584 +[2025-04-29 18:06:36,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 2.3995211124420166, cross_entropy: 2.3995211124420166 +[2025-04-29 18:06:40,728][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.0495808124542236, cross_entropy: 2.0495808124542236 +[2025-04-29 18:06:41,086][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.4451346397399902, cross_entropy: 2.4451346397399902 +[2025-04-29 18:06:45,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.160555839538574, cross_entropy: 2.160555839538574 +[2025-04-29 18:06:45,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 2.0747714042663574, cross_entropy: 2.0747714042663574 +[2025-04-29 18:06:49,096][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.404909372329712, cross_entropy: 3.404909372329712 +[2025-04-29 18:06:49,453][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 3.483757972717285, cross_entropy: 3.483757972717285 +[2025-04-29 18:06:53,918][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.121882915496826, cross_entropy: 3.121882915496826 +[2025-04-29 18:06:54,276][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 1.9878193140029907, cross_entropy: 1.9878193140029907 +[2025-04-29 18:06:58,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.448640823364258, cross_entropy: 2.448640823364258 +[2025-04-29 18:06:58,629][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.6841869354248047, cross_entropy: 2.6841869354248047 +[2025-04-29 18:07:01,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.3273117542266846, cross_entropy: 3.3273117542266846 +[2025-04-29 18:07:02,285][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 3.4478044509887695, cross_entropy: 3.4478044509887695 +[2025-04-29 18:07:06,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 1.8480230569839478, cross_entropy: 1.8480230569839478 +[2025-04-29 18:07:06,531][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 3.8939132690429688, cross_entropy: 3.8939132690429688 +[2025-04-29 18:07:10,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 2.3783483505249023, cross_entropy: 2.3783483505249023 +[2025-04-29 18:07:10,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 2.0395681858062744, cross_entropy: 2.0395681858062744 +[2025-04-29 18:07:14,127][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 2.7257943153381348, cross_entropy: 2.7257943153381348 +[2025-04-29 18:07:14,490][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.665231704711914, cross_entropy: 2.665231704711914 +[2025-04-29 18:07:17,902][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 2.6353464126586914, cross_entropy: 2.6353464126586914 +[2025-04-29 18:07:18,261][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 2.426929473876953, cross_entropy: 2.426929473876953 +[2025-04-29 18:07:22,703][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 3.830449342727661, cross_entropy: 3.830449342727661 +[2025-04-29 18:07:23,063][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 2.403932571411133, cross_entropy: 2.403932571411133 +[2025-04-29 18:07:26,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 3.8828847408294678, cross_entropy: 3.8828847408294678 +[2025-04-29 18:07:27,197][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 3.2579023838043213, cross_entropy: 3.2579023838043213 +[2025-04-29 18:07:30,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.2891809940338135, cross_entropy: 2.2891809940338135 +[2025-04-29 18:07:30,649][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 1.895771861076355, cross_entropy: 1.895771861076355 +[2025-04-29 18:07:34,062][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.5410053730010986, cross_entropy: 2.5410053730010986 +[2025-04-29 18:07:34,421][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.152719020843506, cross_entropy: 3.152719020843506 +[2025-04-29 18:07:38,754][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.3533902168273926, cross_entropy: 3.3533902168273926 +[2025-04-29 18:07:39,113][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 1.9682211875915527, cross_entropy: 1.9682211875915527 +[2025-04-29 18:07:42,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 3.613800525665283, cross_entropy: 3.613800525665283 +[2025-04-29 18:07:42,674][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.4575247764587402, cross_entropy: 2.4575247764587402 +[2025-04-29 18:07:46,715][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 2.3196678161621094, cross_entropy: 2.3196678161621094 +[2025-04-29 18:07:47,037][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.1958179473876953, cross_entropy: 2.1958179473876953 +[2025-04-29 18:07:51,329][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.57265567779541, cross_entropy: 3.57265567779541 +[2025-04-29 18:07:51,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.575411796569824, cross_entropy: 2.575411796569824 +[2025-04-29 18:07:56,382][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.37552809715271, cross_entropy: 3.37552809715271 +[2025-04-29 18:07:56,741][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 2.3644251823425293, cross_entropy: 2.3644251823425293 +[2025-04-29 18:08:00,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 2.3367109298706055, cross_entropy: 2.3367109298706055 +[2025-04-29 18:08:00,633][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 3.5409388542175293, cross_entropy: 3.5409388542175293 +[2025-04-29 18:08:04,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 1.8580149412155151, cross_entropy: 1.8580149412155151 +[2025-04-29 18:08:04,844][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 2.475982189178467, cross_entropy: 2.475982189178467 +[2025-04-29 18:08:08,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.077789545059204, cross_entropy: 3.077789545059204 +[2025-04-29 18:08:08,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 3.5744411945343018, cross_entropy: 3.5744411945343018 +[2025-04-29 18:08:12,608][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 1.9853298664093018, cross_entropy: 1.9853298664093018 +[2025-04-29 18:08:12,971][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 2.5092077255249023, cross_entropy: 2.5092077255249023 +[2025-04-29 18:08:16,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.4734394550323486, cross_entropy: 3.4734394550323486 +[2025-04-29 18:08:17,244][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 2.093355655670166, cross_entropy: 2.093355655670166 +[2025-04-29 18:08:20,970][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 2.0890002250671387, cross_entropy: 2.0890002250671387 +[2025-04-29 18:08:21,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.099454641342163, cross_entropy: 2.099454641342163 +[2025-04-29 18:08:24,802][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 2.9236769676208496, cross_entropy: 2.9236769676208496 +[2025-04-29 18:08:25,158][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.433669090270996, cross_entropy: 3.433669090270996 +[2025-04-29 18:08:29,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.719637155532837, cross_entropy: 3.719637155532837 +[2025-04-29 18:08:29,674][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 2.3680343627929688, cross_entropy: 2.3680343627929688 +[2025-04-29 18:08:33,213][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.3328170776367188, cross_entropy: 2.3328170776367188 +[2025-04-29 18:08:33,571][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 3.359797954559326, cross_entropy: 3.359797954559326 +[2025-04-29 18:08:38,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 2.468384027481079, cross_entropy: 2.468384027481079 +[2025-04-29 18:08:38,487][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 1.6030311584472656, cross_entropy: 1.6030311584472656 +[2025-04-29 18:08:41,722][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 2.2878317832946777, cross_entropy: 2.2878317832946777 +[2025-04-29 18:08:42,082][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 1.6319248676300049, cross_entropy: 1.6319248676300049 +[2025-04-29 18:08:45,740][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 3.423163414001465, cross_entropy: 3.423163414001465 +[2025-04-29 18:08:46,098][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.4351675510406494, cross_entropy: 3.4351675510406494 +[2025-04-29 18:08:49,633][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 1.8042575120925903, cross_entropy: 1.8042575120925903 +[2025-04-29 18:08:49,991][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 3.093441963195801, cross_entropy: 3.093441963195801 +[2025-04-29 18:08:53,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.1164963245391846, cross_entropy: 3.1164963245391846 +[2025-04-29 18:08:54,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 1.8617851734161377, cross_entropy: 1.8617851734161377 +[2025-04-29 18:08:58,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.2894558906555176, cross_entropy: 2.2894558906555176 +[2025-04-29 18:08:59,022][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 3.100680112838745, cross_entropy: 3.100680112838745 +[2025-04-29 18:09:02,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 3.675421714782715, cross_entropy: 3.675421714782715 +[2025-04-29 18:09:02,726][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.8235726356506348, cross_entropy: 3.8235726356506348 +[2025-04-29 18:09:06,527][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 2.5507590770721436, cross_entropy: 2.5507590770721436 +[2025-04-29 18:09:06,889][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.8598103523254395, cross_entropy: 3.8598103523254395 +[2025-04-29 18:09:10,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 2.761491298675537, cross_entropy: 2.761491298675537 +[2025-04-29 18:09:10,954][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 2.9953958988189697, cross_entropy: 2.9953958988189697 +[2025-04-29 18:09:13,793][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 3.2120823860168457, cross_entropy: 3.2120823860168457 +[2025-04-29 18:09:14,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.1127214431762695, cross_entropy: 3.1127214431762695 +[2025-04-29 18:09:19,725][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.300302028656006, cross_entropy: 3.300302028656006 +[2025-04-29 18:09:20,079][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 2.026670455932617, cross_entropy: 2.026670455932617 +[2025-04-29 18:09:23,249][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.6666994094848633, cross_entropy: 3.6666994094848633 +[2025-04-29 18:09:23,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.4886865615844727, cross_entropy: 3.4886865615844727 +[2025-04-29 18:09:26,951][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 2.3763208389282227, cross_entropy: 2.3763208389282227 +[2025-04-29 18:09:28,196][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 2.1142818927764893, cross_entropy: 2.1142818927764893 +[2025-04-29 18:09:31,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 2.9699549674987793, cross_entropy: 2.9699549674987793 +[2025-04-29 18:09:33,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 2.0609583854675293, cross_entropy: 2.0609583854675293 +[2025-04-29 18:09:35,483][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.056957483291626, cross_entropy: 3.056957483291626 +[2025-04-29 18:09:36,426][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 3.1887269020080566, cross_entropy: 3.1887269020080566 +[2025-04-29 18:09:40,285][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.888340711593628, cross_entropy: 2.888340711593628 +[2025-04-29 18:09:40,727][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.4636926651000977, cross_entropy: 2.4636926651000977 +[2025-04-29 18:09:44,362][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 2.110629081726074, cross_entropy: 2.110629081726074 +[2025-04-29 18:09:44,717][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.1436567306518555, cross_entropy: 2.1436567306518555 +[2025-04-29 18:09:47,941][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.119497776031494, cross_entropy: 3.119497776031494 +[2025-04-29 18:09:48,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.5610132217407227, cross_entropy: 3.5610132217407227 +[2025-04-29 18:09:51,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 3.672633171081543, cross_entropy: 3.672633171081543 +[2025-04-29 18:09:53,008][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.2986717224121094, cross_entropy: 3.2986717224121094 +[2025-04-29 18:09:56,482][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.5013418197631836, cross_entropy: 2.5013418197631836 +[2025-04-29 18:09:57,385][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.2017593383789062, cross_entropy: 2.2017593383789062 +[2025-04-29 18:10:01,396][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.5567808151245117, cross_entropy: 3.5567808151245117 +[2025-04-29 18:10:01,751][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 2.0350146293640137, cross_entropy: 2.0350146293640137 +[2025-04-29 18:10:06,915][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 3.763278007507324, cross_entropy: 3.763278007507324 +[2025-04-29 18:10:07,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 2.2984843254089355, cross_entropy: 2.2984843254089355 +[2025-04-29 18:10:11,394][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 1.981477975845337, cross_entropy: 1.981477975845337 +[2025-04-29 18:10:11,756][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 2.7209644317626953, cross_entropy: 2.7209644317626953 +[2025-04-29 18:10:15,111][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 3.8943591117858887, cross_entropy: 3.8943591117858887 +[2025-04-29 18:10:15,432][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 2.2047839164733887, cross_entropy: 2.2047839164733887 +[2025-04-29 18:10:19,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 3.727853298187256, cross_entropy: 3.727853298187256 +[2025-04-29 18:10:19,479][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 2.863105297088623, cross_entropy: 2.863105297088623 +[2025-04-29 18:10:22,867][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.594658851623535, cross_entropy: 3.594658851623535 +[2025-04-29 18:10:23,222][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 2.669987201690674, cross_entropy: 2.669987201690674 +[2025-04-29 18:10:27,806][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.788832664489746, cross_entropy: 2.788832664489746 +[2025-04-29 18:10:28,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 1.9743704795837402, cross_entropy: 1.9743704795837402 +[2025-04-29 18:10:31,818][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 3.753483772277832, cross_entropy: 3.753483772277832 +[2025-04-29 18:10:32,179][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 1.9365276098251343, cross_entropy: 1.9365276098251343 +[2025-04-29 18:10:36,019][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 2.273641586303711, cross_entropy: 2.273641586303711 +[2025-04-29 18:10:36,377][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 3.120028018951416, cross_entropy: 3.120028018951416 +[2025-04-29 18:10:40,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 3.227642059326172, cross_entropy: 3.227642059326172 +[2025-04-29 18:10:40,556][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 1.9018034934997559, cross_entropy: 1.9018034934997559 +[2025-04-29 18:10:45,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 3.1502506732940674, cross_entropy: 3.1502506732940674 +[2025-04-29 18:10:45,412][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.8057775497436523, cross_entropy: 2.8057775497436523 +[2025-04-29 18:10:49,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 2.1095190048217773, cross_entropy: 2.1095190048217773 +[2025-04-29 18:10:49,944][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 3.2169666290283203, cross_entropy: 3.2169666290283203 +[2025-04-29 18:10:53,230][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 3.2568321228027344, cross_entropy: 3.2568321228027344 +[2025-04-29 18:10:53,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.8369245529174805, cross_entropy: 2.8369245529174805 +[2025-04-29 18:10:57,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.7567214965820312, cross_entropy: 2.7567214965820312 +[2025-04-29 18:10:57,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.8588647842407227, cross_entropy: 2.8588647842407227 +[2025-04-29 18:11:01,455][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.1332340240478516, cross_entropy: 2.1332340240478516 +[2025-04-29 18:11:01,811][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 1.8826466798782349, cross_entropy: 1.8826466798782349 +[2025-04-29 18:11:06,009][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 1.7589800357818604, cross_entropy: 1.7589800357818604 +[2025-04-29 18:11:06,363][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 2.319842576980591, cross_entropy: 2.319842576980591 +[2025-04-29 18:11:10,351][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 3.4357614517211914, cross_entropy: 3.4357614517211914 +[2025-04-29 18:11:10,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 2.097419023513794, cross_entropy: 2.097419023513794 +[2025-04-29 18:11:15,139][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.257561683654785, cross_entropy: 3.257561683654785 +[2025-04-29 18:11:15,504][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 3.477602005004883, cross_entropy: 3.477602005004883 +[2025-04-29 18:11:19,010][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 2.446078062057495, cross_entropy: 2.446078062057495 +[2025-04-29 18:11:19,332][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 1.8466770648956299, cross_entropy: 1.8466770648956299 +[2025-04-29 18:11:23,122][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.0328612327575684, cross_entropy: 3.0328612327575684 +[2025-04-29 18:11:23,478][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 3.324951648712158, cross_entropy: 3.324951648712158 +[2025-04-29 18:11:27,168][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 3.6592509746551514, cross_entropy: 3.6592509746551514 +[2025-04-29 18:11:27,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 1.629384994506836, cross_entropy: 1.629384994506836 +[2025-04-29 18:11:32,062][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 1.7416763305664062, cross_entropy: 1.7416763305664062 +[2025-04-29 18:11:32,423][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 1.9360649585723877, cross_entropy: 1.9360649585723877 +[2025-04-29 18:11:35,595][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.060698986053467, cross_entropy: 2.060698986053467 +[2025-04-29 18:11:35,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 1.8732647895812988, cross_entropy: 1.8732647895812988 +[2025-04-29 18:11:39,446][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 1.884185552597046, cross_entropy: 1.884185552597046 +[2025-04-29 18:11:39,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.061805009841919, cross_entropy: 3.061805009841919 +[2025-04-29 18:11:44,134][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.1062207221984863, cross_entropy: 3.1062207221984863 +[2025-04-29 18:11:44,492][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 2.6601717472076416, cross_entropy: 2.6601717472076416 +[2025-04-29 18:11:48,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.5576748847961426, cross_entropy: 3.5576748847961426 +[2025-04-29 18:11:48,676][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.3757224082946777, cross_entropy: 2.3757224082946777 +[2025-04-29 18:11:52,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 1.7765779495239258, cross_entropy: 1.7765779495239258 +[2025-04-29 18:11:52,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 2.613589286804199, cross_entropy: 2.613589286804199 +[2025-04-29 18:11:56,148][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.4567482471466064, cross_entropy: 3.4567482471466064 +[2025-04-29 18:11:56,503][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.8693199157714844, cross_entropy: 2.8693199157714844 +[2025-04-29 18:11:59,865][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 3.581453561782837, cross_entropy: 3.581453561782837 +[2025-04-29 18:12:01,036][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.0548582077026367, cross_entropy: 3.0548582077026367 +[2025-04-29 18:12:05,131][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 1.9508485794067383, cross_entropy: 1.9508485794067383 +[2025-04-29 18:12:05,629][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 2.3739280700683594, cross_entropy: 2.3739280700683594 +[2025-04-29 18:12:09,144][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 2.252363681793213, cross_entropy: 2.252363681793213 +[2025-04-29 18:12:09,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.527522563934326, cross_entropy: 2.527522563934326 +[2025-04-29 18:12:13,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 3.5084710121154785, cross_entropy: 3.5084710121154785 +[2025-04-29 18:12:13,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 3.6341094970703125, cross_entropy: 3.6341094970703125 +[2025-04-29 18:12:17,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.303021192550659, cross_entropy: 2.303021192550659 +[2025-04-29 18:12:18,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.0131406784057617, cross_entropy: 2.0131406784057617 +[2025-04-29 18:12:21,229][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 2.7425384521484375, cross_entropy: 2.7425384521484375 +[2025-04-29 18:12:22,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.1005396842956543, cross_entropy: 2.1005396842956543 +[2025-04-29 18:12:25,218][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 3.3099749088287354, cross_entropy: 3.3099749088287354 +[2025-04-29 18:12:25,628][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 3.4679038524627686, cross_entropy: 3.4679038524627686 +[2025-04-29 18:12:29,087][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 3.3572397232055664, cross_entropy: 3.3572397232055664 +[2025-04-29 18:12:29,439][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 1.587130069732666, cross_entropy: 1.587130069732666 +[2025-04-29 18:12:32,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 1.7941739559173584, cross_entropy: 1.7941739559173584 +[2025-04-29 18:12:33,385][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 1.8317112922668457, cross_entropy: 1.8317112922668457 +[2025-04-29 18:12:36,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 2.063835859298706, cross_entropy: 2.063835859298706 +[2025-04-29 18:12:37,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 2.9228312969207764, cross_entropy: 2.9228312969207764 +[2025-04-29 18:12:40,316][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.015164613723755, cross_entropy: 2.015164613723755 +[2025-04-29 18:12:41,498][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 2.1688737869262695, cross_entropy: 2.1688737869262695 +[2025-04-29 18:12:43,974][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 1.9259955883026123, cross_entropy: 1.9259955883026123 +[2025-04-29 18:12:45,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 2.9375195503234863, cross_entropy: 2.9375195503234863 +[2025-04-29 18:12:48,236][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 3.2961509227752686, cross_entropy: 3.2961509227752686 +[2025-04-29 18:12:49,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 2.7995166778564453, cross_entropy: 2.7995166778564453 +[2025-04-29 18:12:52,290][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.5334720611572266, cross_entropy: 2.5334720611572266 +[2025-04-29 18:12:53,589][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 2.7810349464416504, cross_entropy: 2.7810349464416504 +[2025-04-29 18:12:56,719][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 2.845223903656006, cross_entropy: 2.845223903656006 +[2025-04-29 18:12:58,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.3047633171081543, cross_entropy: 2.3047633171081543 +[2025-04-29 18:13:00,429][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.4029722213745117, cross_entropy: 3.4029722213745117 +[2025-04-29 18:13:01,833][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 3.320018768310547, cross_entropy: 3.320018768310547 +[2025-04-29 18:13:04,124][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.747274160385132, cross_entropy: 2.747274160385132 +[2025-04-29 18:13:05,697][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 3.2712175846099854, cross_entropy: 3.2712175846099854 +[2025-04-29 18:13:07,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.9035167694091797, cross_entropy: 2.9035167694091797 +[2025-04-29 18:13:09,980][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 1.9350292682647705, cross_entropy: 1.9350292682647705 +[2025-04-29 18:13:11,042][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.5218660831451416, cross_entropy: 3.5218660831451416 +[2025-04-29 18:13:14,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.3255419731140137, cross_entropy: 3.3255419731140137 +[2025-04-29 18:13:15,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 2.490199089050293, cross_entropy: 2.490199089050293 +[2025-04-29 18:13:19,161][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 2.2925868034362793, cross_entropy: 2.2925868034362793 +[2025-04-29 18:13:20,067][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 2.301241636276245, cross_entropy: 2.301241636276245 +[2025-04-29 18:13:23,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 3.2344608306884766, cross_entropy: 3.2344608306884766 +[2025-04-29 18:13:24,729][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 2.162065029144287, cross_entropy: 2.162065029144287 +[2025-04-29 18:13:27,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.8208231925964355, cross_entropy: 2.8208231925964355 +[2025-04-29 18:13:28,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.025423526763916, cross_entropy: 2.025423526763916 +[2025-04-29 18:13:31,781][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 1.7926464080810547, cross_entropy: 1.7926464080810547 +[2025-04-29 18:13:32,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.2615838050842285, cross_entropy: 2.2615838050842285 +[2025-04-29 18:13:35,541][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 3.4892923831939697, cross_entropy: 3.4892923831939697 +[2025-04-29 18:13:36,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.082005739212036, cross_entropy: 3.082005739212036 +[2025-04-29 18:13:39,301][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 2.1215548515319824, cross_entropy: 2.1215548515319824 +[2025-04-29 18:13:40,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.304302930831909, cross_entropy: 3.304302930831909 +[2025-04-29 18:13:43,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 3.6981847286224365, cross_entropy: 3.6981847286224365 +[2025-04-29 18:13:44,283][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 3.4874582290649414, cross_entropy: 3.4874582290649414 +[2025-04-29 18:13:46,996][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.615065813064575, cross_entropy: 2.615065813064575 +[2025-04-29 18:13:49,145][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.6551928520202637, cross_entropy: 2.6551928520202637 +[2025-04-29 18:13:51,242][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 1.815159559249878, cross_entropy: 1.815159559249878 +[2025-04-29 18:13:54,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 2.222458839416504, cross_entropy: 2.222458839416504 +[2025-04-29 18:13:55,275][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.50724458694458, cross_entropy: 2.50724458694458 +[2025-04-29 18:13:58,022][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.114931583404541, cross_entropy: 2.114931583404541 +[2025-04-29 18:13:59,193][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.3119800090789795, cross_entropy: 2.3119800090789795 +[2025-04-29 18:14:01,859][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 1.8223127126693726, cross_entropy: 1.8223127126693726 +[2025-04-29 18:14:03,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 1.9882279634475708, cross_entropy: 1.9882279634475708 +[2025-04-29 18:14:06,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.1458773612976074, cross_entropy: 2.1458773612976074 +[2025-04-29 18:14:07,071][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 2.5119738578796387, cross_entropy: 2.5119738578796387 +[2025-04-29 18:14:09,947][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.3466787338256836, cross_entropy: 2.3466787338256836 +[2025-04-29 18:14:11,148][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 3.5012898445129395, cross_entropy: 3.5012898445129395 +[2025-04-29 18:14:13,552][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 1.6991493701934814, cross_entropy: 1.6991493701934814 +[2025-04-29 18:14:14,902][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 1.8214826583862305, cross_entropy: 1.8214826583862305 +[2025-04-29 18:14:17,415][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 1.957167625427246, cross_entropy: 1.957167625427246 +[2025-04-29 18:14:18,579][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.808336019515991, cross_entropy: 2.808336019515991 +[2025-04-29 18:14:20,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 2.2511813640594482, cross_entropy: 2.2511813640594482 +[2025-04-29 18:14:22,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 3.1828155517578125, cross_entropy: 3.1828155517578125 +[2025-04-29 18:14:24,573][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 2.759528875350952, cross_entropy: 2.759528875350952 +[2025-04-29 18:14:26,585][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.5929834842681885, cross_entropy: 1.5929834842681885 +[2025-04-29 18:14:28,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 1.7601765394210815, cross_entropy: 1.7601765394210815 +[2025-04-29 18:14:30,389][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.127392530441284, cross_entropy: 2.127392530441284 +[2025-04-29 18:14:32,653][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 3.640869617462158, cross_entropy: 3.640869617462158 +[2025-04-29 18:14:33,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 3.4344139099121094, cross_entropy: 3.4344139099121094 +[2025-04-29 18:14:36,898][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 2.88019061088562, cross_entropy: 2.88019061088562 +[2025-04-29 18:14:37,965][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.969257116317749, cross_entropy: 2.969257116317749 +[2025-04-29 18:14:41,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 2.708721160888672, cross_entropy: 2.708721160888672 +[2025-04-29 18:14:41,631][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 1.7886779308319092, cross_entropy: 1.7886779308319092 +[2025-04-29 18:14:46,004][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 3.2092466354370117, cross_entropy: 3.2092466354370117 +[2025-04-29 18:14:46,359][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.5604660511016846, cross_entropy: 2.5604660511016846 +[2025-04-29 18:14:50,285][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 2.936147928237915, cross_entropy: 2.936147928237915 +[2025-04-29 18:14:50,605][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 2.183786392211914, cross_entropy: 2.183786392211914 +[2025-04-29 18:14:54,284][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 3.1358394622802734, cross_entropy: 3.1358394622802734 +[2025-04-29 18:14:54,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 2.1731157302856445, cross_entropy: 2.1731157302856445 +[2025-04-29 18:14:58,704][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.074598550796509, cross_entropy: 2.074598550796509 +[2025-04-29 18:14:59,056][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 2.438661575317383, cross_entropy: 2.438661575317383 +[2025-04-29 18:15:02,604][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 2.3530125617980957, cross_entropy: 2.3530125617980957 +[2025-04-29 18:15:02,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.235586643218994, cross_entropy: 3.235586643218994 +[2025-04-29 18:15:06,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 1.8044700622558594, cross_entropy: 1.8044700622558594 +[2025-04-29 18:15:07,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 1.7201792001724243, cross_entropy: 1.7201792001724243 +[2025-04-29 18:15:12,080][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 3.149348735809326, cross_entropy: 3.149348735809326 +[2025-04-29 18:15:12,402][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 2.025841236114502, cross_entropy: 2.025841236114502 +[2025-04-29 18:15:16,820][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 1.7579824924468994, cross_entropy: 1.7579824924468994 +[2025-04-29 18:15:17,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 3.377501964569092, cross_entropy: 3.377501964569092 +[2025-04-29 18:15:20,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 3.6788368225097656, cross_entropy: 3.6788368225097656 +[2025-04-29 18:15:20,982][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 3.500851631164551, cross_entropy: 3.500851631164551 +[2025-04-29 18:15:24,498][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 3.262125015258789, cross_entropy: 3.262125015258789 +[2025-04-29 18:15:24,819][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.6735446453094482, cross_entropy: 2.6735446453094482 +[2025-04-29 18:15:29,180][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.408820152282715, cross_entropy: 2.408820152282715 +[2025-04-29 18:15:29,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.252285957336426, cross_entropy: 2.252285957336426 +[2025-04-29 18:15:33,617][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.863668918609619, cross_entropy: 2.863668918609619 +[2025-04-29 18:15:33,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 3.2469704151153564, cross_entropy: 3.2469704151153564 +[2025-04-29 18:15:37,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 2.2881577014923096, cross_entropy: 2.2881577014923096 +[2025-04-29 18:15:38,161][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.291839361190796, cross_entropy: 3.291839361190796 +[2025-04-29 18:15:41,728][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 3.511493682861328, cross_entropy: 3.511493682861328 +[2025-04-29 18:15:42,050][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 1.7769185304641724, cross_entropy: 1.7769185304641724 +[2025-04-29 18:15:45,190][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 3.099543333053589, cross_entropy: 3.099543333053589 +[2025-04-29 18:15:45,545][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 3.527449131011963, cross_entropy: 3.527449131011963 +[2025-04-29 18:15:49,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 1.8839175701141357, cross_entropy: 1.8839175701141357 +[2025-04-29 18:15:50,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 3.6771492958068848, cross_entropy: 3.6771492958068848 +[2025-04-29 18:15:53,929][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 1.5335835218429565, cross_entropy: 1.5335835218429565 +[2025-04-29 18:15:54,291][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 2.223947286605835, cross_entropy: 2.223947286605835 +[2025-04-29 18:15:57,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 2.2200160026550293, cross_entropy: 2.2200160026550293 +[2025-04-29 18:15:57,834][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 1.676309585571289, cross_entropy: 1.676309585571289 +[2025-04-29 18:16:01,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 3.215381622314453, cross_entropy: 3.215381622314453 +[2025-04-29 18:16:01,664][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 3.363189697265625, cross_entropy: 3.363189697265625 +[2025-04-29 18:16:05,596][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.3709425926208496, cross_entropy: 3.3709425926208496 +[2025-04-29 18:16:05,956][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.1942691802978516, cross_entropy: 2.1942691802978516 +[2025-04-29 18:16:10,286][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 2.1174421310424805, cross_entropy: 2.1174421310424805 +[2025-04-29 18:16:10,647][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 2.1771388053894043, cross_entropy: 2.1771388053894043 +[2025-04-29 18:16:14,273][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 3.396977186203003, cross_entropy: 3.396977186203003 +[2025-04-29 18:16:14,633][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 3.3159286975860596, cross_entropy: 3.3159286975860596 +[2025-04-29 18:16:18,992][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 2.903412342071533, cross_entropy: 2.903412342071533 +[2025-04-29 18:16:19,348][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 1.6213006973266602, cross_entropy: 1.6213006973266602 +[2025-04-29 18:16:23,248][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 1.697288990020752, cross_entropy: 1.697288990020752 +[2025-04-29 18:16:23,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 1.9760392904281616, cross_entropy: 1.9760392904281616 +[2025-04-29 18:16:27,711][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 1.8155162334442139, cross_entropy: 1.8155162334442139 +[2025-04-29 18:16:28,075][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.196035385131836, cross_entropy: 2.196035385131836 +[2025-04-29 18:16:31,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.1468801498413086, cross_entropy: 3.1468801498413086 +[2025-04-29 18:16:32,053][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 1.7921984195709229, cross_entropy: 1.7921984195709229 +[2025-04-29 18:16:35,590][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 3.483733654022217, cross_entropy: 3.483733654022217 +[2025-04-29 18:16:35,948][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.8930563926696777, cross_entropy: 2.8930563926696777 +[2025-04-29 18:16:38,958][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 2.4485087394714355, cross_entropy: 2.4485087394714355 +[2025-04-29 18:16:39,313][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 2.962503433227539, cross_entropy: 2.962503433227539 +[2025-04-29 18:16:42,916][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 2.9252731800079346, cross_entropy: 2.9252731800079346 +[2025-04-29 18:16:43,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 2.08131742477417, cross_entropy: 2.08131742477417 +[2025-04-29 18:16:46,399][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 1.944839358329773, cross_entropy: 1.944839358329773 +[2025-04-29 18:16:46,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 3.072554111480713, cross_entropy: 3.072554111480713 +[2025-04-29 18:16:50,283][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.8419532775878906, cross_entropy: 2.8419532775878906 +[2025-04-29 18:16:50,707][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 2.720902442932129, cross_entropy: 2.720902442932129 +[2025-04-29 18:16:54,555][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 2.5135040283203125, cross_entropy: 2.5135040283203125 +[2025-04-29 18:16:54,913][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 1.9385993480682373, cross_entropy: 1.9385993480682373 +[2025-04-29 18:16:58,261][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.6803693771362305, cross_entropy: 3.6803693771362305 +[2025-04-29 18:16:58,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 3.3704073429107666, cross_entropy: 3.3704073429107666 +[2025-04-29 18:17:02,094][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 1.7756112813949585, cross_entropy: 1.7756112813949585 +[2025-04-29 18:17:02,450][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.4274569749832153, cross_entropy: 1.4274569749832153 +[2025-04-29 18:17:05,698][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 2.1758556365966797, cross_entropy: 2.1758556365966797 +[2025-04-29 18:17:07,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 1.9919103384017944, cross_entropy: 1.9919103384017944 +[2025-04-29 18:17:10,402][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 2.2945668697357178, cross_entropy: 2.2945668697357178 +[2025-04-29 18:17:11,000][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 3.468409538269043, cross_entropy: 3.468409538269043 +[2025-04-29 18:17:15,129][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.540585994720459, cross_entropy: 2.540585994720459 +[2025-04-29 18:17:15,485][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.7847113609313965, cross_entropy: 2.7847113609313965 +[2025-04-29 18:17:19,158][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 2.477726936340332, cross_entropy: 2.477726936340332 +[2025-04-29 18:17:19,509][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 3.1232893466949463, cross_entropy: 3.1232893466949463 +[2025-04-29 18:17:22,647][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.0237228870391846, cross_entropy: 3.0237228870391846 +[2025-04-29 18:17:23,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 3.531238079071045, cross_entropy: 3.531238079071045 +[2025-04-29 18:17:26,931][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.900017023086548, cross_entropy: 2.900017023086548 +[2025-04-29 18:17:27,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 1.4613224267959595, cross_entropy: 1.4613224267959595 +[2025-04-29 18:17:30,662][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.2691731452941895, cross_entropy: 2.2691731452941895 +[2025-04-29 18:17:31,365][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.6057448387145996, cross_entropy: 2.6057448387145996 +[2025-04-29 18:17:34,797][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 3.397874355316162, cross_entropy: 3.397874355316162 +[2025-04-29 18:17:35,295][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 1.824939489364624, cross_entropy: 1.824939489364624 +[2025-04-29 18:17:38,484][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.4950575828552246, cross_entropy: 2.4950575828552246 +[2025-04-29 18:17:40,001][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.4084160327911377, cross_entropy: 3.4084160327911377 +[2025-04-29 18:17:42,637][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 3.3890552520751953, cross_entropy: 3.3890552520751953 +[2025-04-29 18:17:43,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 3.5238118171691895, cross_entropy: 3.5238118171691895 +[2025-04-29 18:17:46,640][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.235649824142456, cross_entropy: 3.235649824142456 +[2025-04-29 18:17:49,209][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 2.8276498317718506, cross_entropy: 2.8276498317718506 +[2025-04-29 18:17:51,227][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 2.6784675121307373, cross_entropy: 2.6784675121307373 +[2025-04-29 18:17:53,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 3.106609344482422, cross_entropy: 3.106609344482422 +[2025-04-29 18:17:55,149][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 2.701556444168091, cross_entropy: 2.701556444168091 +[2025-04-29 18:17:57,165][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 3.143765449523926, cross_entropy: 3.143765449523926 +[2025-04-29 18:17:59,867][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.61513614654541, cross_entropy: 3.61513614654541 +[2025-04-29 18:18:00,710][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.7981162071228027, cross_entropy: 2.7981162071228027 +[2025-04-29 18:18:04,346][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 1.5451204776763916, cross_entropy: 1.5451204776763916 +[2025-04-29 18:18:05,203][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 3.366399049758911, cross_entropy: 3.366399049758911 +[2025-04-29 18:18:08,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 2.6985690593719482, cross_entropy: 2.6985690593719482 +[2025-04-29 18:18:09,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 1.6886787414550781, cross_entropy: 1.6886787414550781 +[2025-04-29 18:18:12,325][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 2.089923858642578, cross_entropy: 2.089923858642578 +[2025-04-29 18:18:13,932][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 1.657172679901123, cross_entropy: 1.657172679901123 +[2025-04-29 18:18:16,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 3.010222911834717, cross_entropy: 3.010222911834717 +[2025-04-29 18:18:17,996][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.7140579223632812, cross_entropy: 3.7140579223632812 +[2025-04-29 18:18:20,883][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 1.689893364906311, cross_entropy: 1.689893364906311 +[2025-04-29 18:18:21,900][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 3.364239454269409, cross_entropy: 3.364239454269409 +[2025-04-29 18:18:24,827][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 1.815604329109192, cross_entropy: 1.815604329109192 +[2025-04-29 18:18:25,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.2294130325317383, cross_entropy: 2.2294130325317383 +[2025-04-29 18:18:28,358][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 3.386101722717285, cross_entropy: 3.386101722717285 +[2025-04-29 18:18:29,591][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 2.0258543491363525, cross_entropy: 2.0258543491363525 +[2025-04-29 18:18:32,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 3.109340190887451, cross_entropy: 3.109340190887451 +[2025-04-29 18:18:34,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 1.5099523067474365, cross_entropy: 1.5099523067474365 +[2025-04-29 18:18:35,381][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 3.561455249786377, cross_entropy: 3.561455249786377 +[2025-04-29 18:18:37,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 2.1283700466156006, cross_entropy: 2.1283700466156006 +[2025-04-29 18:21:55,519][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.6689467430114746, cross_entropy: 2.6689467430114746 +[2025-04-29 18:21:55,519][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.7376036643981934, cross_entropy: 1.7376036643981934 +[2025-04-29 18:21:55,784][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 18:21:55,959][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch2.pth. +[2025-04-29 18:21:56,196][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 18:22:01,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 2.261204242706299, cross_entropy: 2.261204242706299 +[2025-04-29 18:22:02,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.9430463314056396, cross_entropy: 1.9430463314056396 +[2025-04-29 18:22:05,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 1.480285882949829, cross_entropy: 1.480285882949829 +[2025-04-29 18:22:07,178][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 1.5223597288131714, cross_entropy: 1.5223597288131714 +[2025-04-29 18:22:09,846][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 2.837813377380371, cross_entropy: 2.837813377380371 +[2025-04-29 18:22:11,248][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 1.282580852508545, cross_entropy: 1.282580852508545 +[2025-04-29 18:22:13,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.7707676887512207, cross_entropy: 1.7707676887512207 +[2025-04-29 18:22:16,156][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 1.870851755142212, cross_entropy: 1.870851755142212 +[2025-04-29 18:22:17,319][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.594853401184082, cross_entropy: 1.594853401184082 +[2025-04-29 18:22:20,206][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 1.33951997756958, cross_entropy: 1.33951997756958 +[2025-04-29 18:22:21,531][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 1.9625985622406006, cross_entropy: 1.9625985622406006 +[2025-04-29 18:22:24,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 1.741033911705017, cross_entropy: 1.741033911705017 +[2025-04-29 18:22:25,291][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 2.6939892768859863, cross_entropy: 2.6939892768859863 +[2025-04-29 18:22:28,782][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.708303689956665, cross_entropy: 2.708303689956665 +[2025-04-29 18:22:29,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.023679256439209, cross_entropy: 2.023679256439209 +[2025-04-29 18:22:33,479][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 3.750257968902588, cross_entropy: 3.750257968902588 +[2025-04-29 18:22:33,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 2.653714179992676, cross_entropy: 2.653714179992676 +[2025-04-29 18:22:37,574][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 3.184577465057373, cross_entropy: 3.184577465057373 +[2025-04-29 18:22:37,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 3.1055188179016113, cross_entropy: 3.1055188179016113 +[2025-04-29 18:22:42,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.5793594121932983, cross_entropy: 1.5793594121932983 +[2025-04-29 18:22:42,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 2.8006396293640137, cross_entropy: 2.8006396293640137 +[2025-04-29 18:22:46,020][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 2.489461898803711, cross_entropy: 2.489461898803711 +[2025-04-29 18:22:46,503][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.0334484577178955, cross_entropy: 3.0334484577178955 +[2025-04-29 18:22:49,741][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 1.9619545936584473, cross_entropy: 1.9619545936584473 +[2025-04-29 18:22:50,457][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.336793899536133, cross_entropy: 3.336793899536133 +[2025-04-29 18:22:53,576][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 2.958022356033325, cross_entropy: 2.958022356033325 +[2025-04-29 18:22:54,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 2.6922731399536133, cross_entropy: 2.6922731399536133 +[2025-04-29 18:22:57,017][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.0404512882232666, cross_entropy: 2.0404512882232666 +[2025-04-29 18:22:57,737][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 1.2916760444641113, cross_entropy: 1.2916760444641113 +[2025-04-29 18:23:01,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 1.7259671688079834, cross_entropy: 1.7259671688079834 +[2025-04-29 18:23:01,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 3.537639617919922, cross_entropy: 3.537639617919922 +[2025-04-29 18:23:05,001][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 3.3613016605377197, cross_entropy: 3.3613016605377197 +[2025-04-29 18:23:07,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 1.9020934104919434, cross_entropy: 1.9020934104919434 +[2025-04-29 18:23:09,555][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 1.6532443761825562, cross_entropy: 1.6532443761825562 +[2025-04-29 18:23:11,958][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 1.720460295677185, cross_entropy: 1.720460295677185 +[2025-04-29 18:23:13,993][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.571312427520752, cross_entropy: 3.571312427520752 +[2025-04-29 18:23:15,591][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.354241371154785, cross_entropy: 2.354241371154785 +[2025-04-29 18:23:18,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.9220712184906006, cross_entropy: 1.9220712184906006 +[2025-04-29 18:23:20,115][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 2.845515727996826, cross_entropy: 2.845515727996826 +[2025-04-29 18:23:23,674][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 1.9682695865631104, cross_entropy: 1.9682695865631104 +[2025-04-29 18:23:24,880][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.478740930557251, cross_entropy: 1.478740930557251 +[2025-04-29 18:23:27,532][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 3.063385486602783, cross_entropy: 3.063385486602783 +[2025-04-29 18:23:29,141][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 3.248159408569336, cross_entropy: 3.248159408569336 +[2025-04-29 18:23:31,517][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 3.66306209564209, cross_entropy: 3.66306209564209 +[2025-04-29 18:23:33,116][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.507230758666992, cross_entropy: 2.507230758666992 +[2025-04-29 18:23:36,102][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 1.703211784362793, cross_entropy: 1.703211784362793 +[2025-04-29 18:23:37,232][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 3.1130971908569336, cross_entropy: 3.1130971908569336 +[2025-04-29 18:23:40,788][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.073322296142578, cross_entropy: 2.073322296142578 +[2025-04-29 18:23:41,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.3685660362243652, cross_entropy: 2.3685660362243652 +[2025-04-29 18:23:44,408][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 1.6598973274230957, cross_entropy: 1.6598973274230957 +[2025-04-29 18:23:45,794][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.9576525688171387, cross_entropy: 2.9576525688171387 +[2025-04-29 18:23:48,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 3.000944137573242, cross_entropy: 3.000944137573242 +[2025-04-29 18:23:49,378][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.450514316558838, cross_entropy: 2.450514316558838 +[2025-04-29 18:23:53,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 2.8032240867614746, cross_entropy: 2.8032240867614746 +[2025-04-29 18:23:53,807][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.1625328063964844, cross_entropy: 3.1625328063964844 +[2025-04-29 18:23:57,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.24320650100708, cross_entropy: 2.24320650100708 +[2025-04-29 18:23:58,077][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 2.6282105445861816, cross_entropy: 2.6282105445861816 +[2025-04-29 18:24:01,209][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.659806251525879, cross_entropy: 2.659806251525879 +[2025-04-29 18:24:01,563][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.4042611122131348, cross_entropy: 3.4042611122131348 +[2025-04-29 18:24:04,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 2.259037733078003, cross_entropy: 2.259037733078003 +[2025-04-29 18:24:05,188][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 3.241114616394043, cross_entropy: 3.241114616394043 +[2025-04-29 18:24:08,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.9240479469299316, cross_entropy: 2.9240479469299316 +[2025-04-29 18:24:09,283][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 1.8192940950393677, cross_entropy: 1.8192940950393677 +[2025-04-29 18:24:13,004][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 3.2913379669189453, cross_entropy: 3.2913379669189453 +[2025-04-29 18:24:13,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 1.7369823455810547, cross_entropy: 1.7369823455810547 +[2025-04-29 18:24:16,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.1162850856781006, cross_entropy: 2.1162850856781006 +[2025-04-29 18:24:17,117][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.7093946933746338, cross_entropy: 1.7093946933746338 +[2025-04-29 18:24:20,484][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 1.3494484424591064, cross_entropy: 1.3494484424591064 +[2025-04-29 18:24:21,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.351820468902588, cross_entropy: 2.351820468902588 +[2025-04-29 18:24:24,001][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 3.0240020751953125, cross_entropy: 3.0240020751953125 +[2025-04-29 18:24:25,764][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.4768147468566895, cross_entropy: 2.4768147468566895 +[2025-04-29 18:24:27,951][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.3782596588134766, cross_entropy: 2.3782596588134766 +[2025-04-29 18:24:29,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 1.643998622894287, cross_entropy: 1.643998622894287 +[2025-04-29 18:24:32,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 1.6005643606185913, cross_entropy: 1.6005643606185913 +[2025-04-29 18:24:33,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 1.6816980838775635, cross_entropy: 1.6816980838775635 +[2025-04-29 18:24:37,304][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 3.3130950927734375, cross_entropy: 3.3130950927734375 +[2025-04-29 18:24:37,672][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 3.6478676795959473, cross_entropy: 3.6478676795959473 +[2025-04-29 18:24:42,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 3.1746792793273926, cross_entropy: 3.1746792793273926 +[2025-04-29 18:24:43,027][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 1.7205731868743896, cross_entropy: 1.7205731868743896 +[2025-04-29 18:24:46,359][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 1.7646889686584473, cross_entropy: 1.7646889686584473 +[2025-04-29 18:24:47,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 2.283318519592285, cross_entropy: 2.283318519592285 +[2025-04-29 18:24:50,591][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.7261509895324707, cross_entropy: 1.7261509895324707 +[2025-04-29 18:24:51,338][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 1.3335543870925903, cross_entropy: 1.3335543870925903 +[2025-04-29 18:24:54,391][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 1.615161418914795, cross_entropy: 1.615161418914795 +[2025-04-29 18:24:55,160][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 3.747344493865967, cross_entropy: 3.747344493865967 +[2025-04-29 18:24:59,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 3.2815537452697754, cross_entropy: 3.2815537452697754 +[2025-04-29 18:24:59,903][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 1.6207454204559326, cross_entropy: 1.6207454204559326 +[2025-04-29 18:25:03,385][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 2.7890241146087646, cross_entropy: 2.7890241146087646 +[2025-04-29 18:25:03,739][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.093949317932129, cross_entropy: 3.093949317932129 +[2025-04-29 18:25:07,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 1.4012691974639893, cross_entropy: 1.4012691974639893 +[2025-04-29 18:25:08,087][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 1.8330549001693726, cross_entropy: 1.8330549001693726 +[2025-04-29 18:25:12,001][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.4501550197601318, cross_entropy: 1.4501550197601318 +[2025-04-29 18:25:13,496][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.3411083221435547, cross_entropy: 1.3411083221435547 +[2025-04-29 18:25:18,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 1.5069159269332886, cross_entropy: 1.5069159269332886 +[2025-04-29 18:25:18,668][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 1.9357260465621948, cross_entropy: 1.9357260465621948 +[2025-04-29 18:25:22,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.4450443983078003, cross_entropy: 1.4450443983078003 +[2025-04-29 18:25:22,809][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.1481008529663086, cross_entropy: 3.1481008529663086 +[2025-04-29 18:25:25,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.1156444549560547, cross_entropy: 2.1156444549560547 +[2025-04-29 18:25:27,072][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 1.6185592412948608, cross_entropy: 1.6185592412948608 +[2025-04-29 18:25:31,077][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 1.547328233718872, cross_entropy: 1.547328233718872 +[2025-04-29 18:25:31,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 3.6416735649108887, cross_entropy: 3.6416735649108887 +[2025-04-29 18:25:35,230][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 3.9351086616516113, cross_entropy: 3.9351086616516113 +[2025-04-29 18:25:35,667][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.0173985958099365, cross_entropy: 2.0173985958099365 +[2025-04-29 18:25:39,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.7820932865142822, cross_entropy: 1.7820932865142822 +[2025-04-29 18:25:39,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 1.7860503196716309, cross_entropy: 1.7860503196716309 +[2025-04-29 18:25:43,178][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.348506212234497, cross_entropy: 2.348506212234497 +[2025-04-29 18:25:43,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.949871063232422, cross_entropy: 2.949871063232422 +[2025-04-29 18:25:48,336][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 1.792189359664917, cross_entropy: 1.792189359664917 +[2025-04-29 18:25:48,697][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 1.4597175121307373, cross_entropy: 1.4597175121307373 +[2025-04-29 18:25:52,634][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 3.021214008331299, cross_entropy: 3.021214008331299 +[2025-04-29 18:25:52,991][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.119878053665161, cross_entropy: 2.119878053665161 +[2025-04-29 18:25:56,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.1736865043640137, cross_entropy: 1.1736865043640137 +[2025-04-29 18:25:57,324][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 1.2572400569915771, cross_entropy: 1.2572400569915771 +[2025-04-29 18:26:00,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 2.5807743072509766, cross_entropy: 2.5807743072509766 +[2025-04-29 18:26:01,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 2.1285128593444824, cross_entropy: 2.1285128593444824 +[2025-04-29 18:26:04,787][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 3.045961380004883, cross_entropy: 3.045961380004883 +[2025-04-29 18:26:05,115][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 1.233768105506897, cross_entropy: 1.233768105506897 +[2025-04-29 18:26:08,546][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 3.5739645957946777, cross_entropy: 3.5739645957946777 +[2025-04-29 18:26:09,145][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 1.3461276292800903, cross_entropy: 1.3461276292800903 +[2025-04-29 18:26:12,797][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.0193915367126465, cross_entropy: 2.0193915367126465 +[2025-04-29 18:26:13,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 2.3517937660217285, cross_entropy: 2.3517937660217285 +[2025-04-29 18:26:17,773][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 2.7125484943389893, cross_entropy: 2.7125484943389893 +[2025-04-29 18:26:18,132][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 1.4107952117919922, cross_entropy: 1.4107952117919922 +[2025-04-29 18:26:22,724][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 2.2545764446258545, cross_entropy: 2.2545764446258545 +[2025-04-29 18:26:23,086][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 1.9005861282348633, cross_entropy: 1.9005861282348633 +[2025-04-29 18:26:26,830][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 1.4220669269561768, cross_entropy: 1.4220669269561768 +[2025-04-29 18:26:27,191][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 3.194911479949951, cross_entropy: 3.194911479949951 +[2025-04-29 18:26:31,006][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 3.5001516342163086, cross_entropy: 3.5001516342163086 +[2025-04-29 18:26:31,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 1.3095656633377075, cross_entropy: 1.3095656633377075 +[2025-04-29 18:26:35,001][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 3.299957275390625, cross_entropy: 3.299957275390625 +[2025-04-29 18:26:35,541][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 3.3453361988067627, cross_entropy: 3.3453361988067627 +[2025-04-29 18:26:39,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 1.8885681629180908, cross_entropy: 1.8885681629180908 +[2025-04-29 18:26:39,396][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 1.7494639158248901, cross_entropy: 1.7494639158248901 +[2025-04-29 18:26:43,079][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.2189645767211914, cross_entropy: 2.2189645767211914 +[2025-04-29 18:26:43,442][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 1.3308384418487549, cross_entropy: 1.3308384418487549 +[2025-04-29 18:26:47,233][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.4147779941558838, cross_entropy: 1.4147779941558838 +[2025-04-29 18:26:47,591][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 3.425045967102051, cross_entropy: 3.425045967102051 +[2025-04-29 18:26:51,427][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.8637667894363403, cross_entropy: 1.8637667894363403 +[2025-04-29 18:26:51,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.2401657104492188, cross_entropy: 2.2401657104492188 +[2025-04-29 18:26:55,460][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 1.8567652702331543, cross_entropy: 1.8567652702331543 +[2025-04-29 18:26:55,782][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 3.3808374404907227, cross_entropy: 3.3808374404907227 +[2025-04-29 18:26:59,888][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.8101811408996582, cross_entropy: 1.8101811408996582 +[2025-04-29 18:27:00,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.1336328983306885, cross_entropy: 2.1336328983306885 +[2025-04-29 18:27:03,959][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.7488932609558105, cross_entropy: 2.7488932609558105 +[2025-04-29 18:27:04,277][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 1.7390198707580566, cross_entropy: 1.7390198707580566 +[2025-04-29 18:27:08,072][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 3.1171083450317383, cross_entropy: 3.1171083450317383 +[2025-04-29 18:27:08,429][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 2.0956263542175293, cross_entropy: 2.0956263542175293 +[2025-04-29 18:27:11,742][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.1796131134033203, cross_entropy: 3.1796131134033203 +[2025-04-29 18:27:12,095][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 2.622518539428711, cross_entropy: 2.622518539428711 +[2025-04-29 18:27:15,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 1.6940336227416992, cross_entropy: 1.6940336227416992 +[2025-04-29 18:27:15,781][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 2.2715048789978027, cross_entropy: 2.2715048789978027 +[2025-04-29 18:27:19,230][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 1.8182405233383179, cross_entropy: 1.8182405233383179 +[2025-04-29 18:27:19,626][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 1.491788625717163, cross_entropy: 1.491788625717163 +[2025-04-29 18:27:23,574][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 1.3820829391479492, cross_entropy: 1.3820829391479492 +[2025-04-29 18:27:24,008][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 1.4083662033081055, cross_entropy: 1.4083662033081055 +[2025-04-29 18:27:28,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.404923915863037, cross_entropy: 2.404923915863037 +[2025-04-29 18:27:28,975][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.9912512302398682, cross_entropy: 1.9912512302398682 +[2025-04-29 18:27:32,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 1.3930940628051758, cross_entropy: 1.3930940628051758 +[2025-04-29 18:27:32,584][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 2.3540258407592773, cross_entropy: 2.3540258407592773 +[2025-04-29 18:27:35,974][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 1.799656629562378, cross_entropy: 1.799656629562378 +[2025-04-29 18:27:36,298][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 1.689068078994751, cross_entropy: 1.689068078994751 +[2025-04-29 18:27:39,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.319631338119507, cross_entropy: 3.319631338119507 +[2025-04-29 18:27:40,085][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 1.6874079704284668, cross_entropy: 1.6874079704284668 +[2025-04-29 18:27:43,453][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 2.2441108226776123, cross_entropy: 2.2441108226776123 +[2025-04-29 18:27:43,867][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 2.1886138916015625, cross_entropy: 2.1886138916015625 +[2025-04-29 18:27:48,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.5013909339904785, cross_entropy: 1.5013909339904785 +[2025-04-29 18:27:48,897][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 3.6257169246673584, cross_entropy: 3.6257169246673584 +[2025-04-29 18:27:53,015][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 2.27152943611145, cross_entropy: 2.27152943611145 +[2025-04-29 18:27:53,372][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.453831672668457, cross_entropy: 1.453831672668457 +[2025-04-29 18:27:56,893][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.1563732624053955, cross_entropy: 3.1563732624053955 +[2025-04-29 18:27:57,854][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 1.5383764505386353, cross_entropy: 1.5383764505386353 +[2025-04-29 18:28:00,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 1.478431224822998, cross_entropy: 1.478431224822998 +[2025-04-29 18:28:02,122][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.033216953277588, cross_entropy: 3.033216953277588 +[2025-04-29 18:28:04,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 2.932111978530884, cross_entropy: 2.932111978530884 +[2025-04-29 18:28:06,299][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.8177967071533203, cross_entropy: 2.8177967071533203 +[2025-04-29 18:28:07,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 1.7316738367080688, cross_entropy: 1.7316738367080688 +[2025-04-29 18:28:10,647][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 3.3971269130706787, cross_entropy: 3.3971269130706787 +[2025-04-29 18:28:11,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 1.6826958656311035, cross_entropy: 1.6826958656311035 +[2025-04-29 18:28:14,702][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 2.8743536472320557, cross_entropy: 2.8743536472320557 +[2025-04-29 18:28:15,648][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.762732982635498, cross_entropy: 2.762732982635498 +[2025-04-29 18:28:18,562][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 2.150632381439209, cross_entropy: 2.150632381439209 +[2025-04-29 18:28:18,983][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 1.5870532989501953, cross_entropy: 1.5870532989501953 +[2025-04-29 18:28:23,284][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 3.1432039737701416, cross_entropy: 3.1432039737701416 +[2025-04-29 18:28:23,638][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.438676357269287, cross_entropy: 2.438676357269287 +[2025-04-29 18:28:27,415][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 1.5688118934631348, cross_entropy: 1.5688118934631348 +[2025-04-29 18:28:27,774][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 3.5515449047088623, cross_entropy: 3.5515449047088623 +[2025-04-29 18:28:32,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 3.4980053901672363, cross_entropy: 3.4980053901672363 +[2025-04-29 18:28:32,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.2523388862609863, cross_entropy: 2.2523388862609863 +[2025-04-29 18:28:35,607][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 1.3690751791000366, cross_entropy: 1.3690751791000366 +[2025-04-29 18:28:36,010][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.475585460662842, cross_entropy: 3.475585460662842 +[2025-04-29 18:28:40,270][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 1.749863624572754, cross_entropy: 1.749863624572754 +[2025-04-29 18:28:40,594][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 3.4257164001464844, cross_entropy: 3.4257164001464844 +[2025-04-29 18:28:44,211][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 3.239156723022461, cross_entropy: 3.239156723022461 +[2025-04-29 18:28:44,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 2.0686075687408447, cross_entropy: 2.0686075687408447 +[2025-04-29 18:28:48,682][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 1.835904598236084, cross_entropy: 1.835904598236084 +[2025-04-29 18:28:49,042][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.8836007118225098, cross_entropy: 2.8836007118225098 +[2025-04-29 18:28:51,943][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 2.948397636413574, cross_entropy: 2.948397636413574 +[2025-04-29 18:28:52,648][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 1.7282854318618774, cross_entropy: 1.7282854318618774 +[2025-04-29 18:28:55,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.5244665145874023, cross_entropy: 1.5244665145874023 +[2025-04-29 18:28:57,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 2.8269309997558594, cross_entropy: 2.8269309997558594 +[2025-04-29 18:28:59,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 3.3499443531036377, cross_entropy: 3.3499443531036377 +[2025-04-29 18:29:02,542][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 1.9452061653137207, cross_entropy: 1.9452061653137207 +[2025-04-29 18:29:03,959][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.360297918319702, cross_entropy: 3.360297918319702 +[2025-04-29 18:29:06,608][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.96724009513855, cross_entropy: 2.96724009513855 +[2025-04-29 18:29:07,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 1.688826560974121, cross_entropy: 1.688826560974121 +[2025-04-29 18:29:10,260][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 1.9126265048980713, cross_entropy: 1.9126265048980713 +[2025-04-29 18:29:12,851][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.8969602584838867, cross_entropy: 2.8969602584838867 +[2025-04-29 18:29:14,604][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 1.5725035667419434, cross_entropy: 1.5725035667419434 +[2025-04-29 18:29:17,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.322143077850342, cross_entropy: 2.322143077850342 +[2025-04-29 18:29:18,683][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.9494056701660156, cross_entropy: 2.9494056701660156 +[2025-04-29 18:29:23,397][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 3.168541669845581, cross_entropy: 3.168541669845581 +[2025-04-29 18:29:23,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 2.524209499359131, cross_entropy: 2.524209499359131 +[2025-04-29 18:29:26,627][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 2.078803300857544, cross_entropy: 2.078803300857544 +[2025-04-29 18:29:27,385][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 1.798301339149475, cross_entropy: 1.798301339149475 +[2025-04-29 18:29:32,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.927506446838379, cross_entropy: 1.927506446838379 +[2025-04-29 18:29:32,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 3.099231719970703, cross_entropy: 3.099231719970703 +[2025-04-29 18:29:37,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.1558103561401367, cross_entropy: 2.1558103561401367 +[2025-04-29 18:29:37,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 1.768367052078247, cross_entropy: 1.768367052078247 +[2025-04-29 18:29:41,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 1.823364019393921, cross_entropy: 1.823364019393921 +[2025-04-29 18:29:41,402][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 2.424295425415039, cross_entropy: 2.424295425415039 +[2025-04-29 18:29:46,490][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.4998486042022705, cross_entropy: 1.4998486042022705 +[2025-04-29 18:29:46,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 1.1889231204986572, cross_entropy: 1.1889231204986572 +[2025-04-29 18:29:50,636][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.58609676361084, cross_entropy: 3.58609676361084 +[2025-04-29 18:29:51,000][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.638223648071289, cross_entropy: 3.638223648071289 +[2025-04-29 18:29:54,512][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 1.6002683639526367, cross_entropy: 1.6002683639526367 +[2025-04-29 18:29:54,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 2.7679598331451416, cross_entropy: 2.7679598331451416 +[2025-04-29 18:29:58,245][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.5220534801483154, cross_entropy: 1.5220534801483154 +[2025-04-29 18:29:58,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 1.5511455535888672, cross_entropy: 1.5511455535888672 +[2025-04-29 18:30:02,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.0717988014221191, cross_entropy: 1.0717988014221191 +[2025-04-29 18:30:02,550][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 1.536838412284851, cross_entropy: 1.536838412284851 +[2025-04-29 18:30:06,283][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.6417956352233887, cross_entropy: 2.6417956352233887 +[2025-04-29 18:30:06,694][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 2.521620035171509, cross_entropy: 2.521620035171509 +[2025-04-29 18:30:10,003][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 3.262234687805176, cross_entropy: 3.262234687805176 +[2025-04-29 18:30:10,477][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 1.6515178680419922, cross_entropy: 1.6515178680419922 +[2025-04-29 18:30:13,895][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.0669212341308594, cross_entropy: 3.0669212341308594 +[2025-04-29 18:30:14,731][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 1.3509355783462524, cross_entropy: 1.3509355783462524 +[2025-04-29 18:30:18,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 2.030593156814575, cross_entropy: 2.030593156814575 +[2025-04-29 18:30:18,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 1.8782503604888916, cross_entropy: 1.8782503604888916 +[2025-04-29 18:30:22,111][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.4054603576660156, cross_entropy: 2.4054603576660156 +[2025-04-29 18:30:22,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 1.6673176288604736, cross_entropy: 1.6673176288604736 +[2025-04-29 18:30:25,859][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 1.6120988130569458, cross_entropy: 1.6120988130569458 +[2025-04-29 18:30:26,571][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 2.719818115234375, cross_entropy: 2.719818115234375 +[2025-04-29 18:30:30,076][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.2643985748291016, cross_entropy: 2.2643985748291016 +[2025-04-29 18:30:31,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 2.093358039855957, cross_entropy: 2.093358039855957 +[2025-04-29 18:30:34,437][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 2.441420555114746, cross_entropy: 2.441420555114746 +[2025-04-29 18:30:35,383][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 3.65596342086792, cross_entropy: 3.65596342086792 +[2025-04-29 18:30:38,343][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 1.340130090713501, cross_entropy: 1.340130090713501 +[2025-04-29 18:30:39,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 2.520887851715088, cross_entropy: 2.520887851715088 +[2025-04-29 18:30:42,838][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 3.4942479133605957, cross_entropy: 3.4942479133605957 +[2025-04-29 18:30:43,927][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 1.5329492092132568, cross_entropy: 1.5329492092132568 +[2025-04-29 18:30:46,752][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.6943182945251465, cross_entropy: 2.6943182945251465 +[2025-04-29 18:30:47,863][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.6659260988235474, cross_entropy: 1.6659260988235474 +[2025-04-29 18:30:50,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 3.029569625854492, cross_entropy: 3.029569625854492 +[2025-04-29 18:30:51,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 1.8933937549591064, cross_entropy: 1.8933937549591064 +[2025-04-29 18:30:54,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 1.883660078048706, cross_entropy: 1.883660078048706 +[2025-04-29 18:30:56,007][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 2.856238603591919, cross_entropy: 2.856238603591919 +[2025-04-29 18:30:59,367][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 2.836888074874878, cross_entropy: 2.836888074874878 +[2025-04-29 18:30:59,723][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.6345791816711426, cross_entropy: 3.6345791816711426 +[2025-04-29 18:31:03,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.2906978130340576, cross_entropy: 1.2906978130340576 +[2025-04-29 18:31:03,696][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 1.412054419517517, cross_entropy: 1.412054419517517 +[2025-04-29 18:31:07,500][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 1.7325999736785889, cross_entropy: 1.7325999736785889 +[2025-04-29 18:31:07,859][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.7659519910812378, cross_entropy: 1.7659519910812378 +[2025-04-29 18:31:11,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.172657012939453, cross_entropy: 3.172657012939453 +[2025-04-29 18:31:11,777][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 2.8072609901428223, cross_entropy: 2.8072609901428223 +[2025-04-29 18:31:15,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 2.1570136547088623, cross_entropy: 2.1570136547088623 +[2025-04-29 18:31:15,917][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 3.239896774291992, cross_entropy: 3.239896774291992 +[2025-04-29 18:31:19,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.1781487464904785, cross_entropy: 3.1781487464904785 +[2025-04-29 18:31:19,902][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.3762390613555908, cross_entropy: 1.3762390613555908 +[2025-04-29 18:31:23,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 1.3499863147735596, cross_entropy: 1.3499863147735596 +[2025-04-29 18:31:24,106][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 1.3199083805084229, cross_entropy: 1.3199083805084229 +[2025-04-29 18:31:27,458][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 1.522214651107788, cross_entropy: 1.522214651107788 +[2025-04-29 18:31:27,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.4780648946762085, cross_entropy: 1.4780648946762085 +[2025-04-29 18:31:31,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 1.5919876098632812, cross_entropy: 1.5919876098632812 +[2025-04-29 18:31:32,144][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 3.163224220275879, cross_entropy: 3.163224220275879 +[2025-04-29 18:31:35,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 1.4850449562072754, cross_entropy: 1.4850449562072754 +[2025-04-29 18:31:36,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 1.6235392093658447, cross_entropy: 1.6235392093658447 +[2025-04-29 18:31:39,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 3.1514930725097656, cross_entropy: 3.1514930725097656 +[2025-04-29 18:31:40,395][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 3.427371025085449, cross_entropy: 3.427371025085449 +[2025-04-29 18:31:43,180][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.683724045753479, cross_entropy: 1.683724045753479 +[2025-04-29 18:31:44,749][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.6535630226135254, cross_entropy: 2.6535630226135254 +[2025-04-29 18:31:47,568][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 3.458928108215332, cross_entropy: 3.458928108215332 +[2025-04-29 18:31:48,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 2.4208452701568604, cross_entropy: 2.4208452701568604 +[2025-04-29 18:31:51,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.3558497428894043, cross_entropy: 1.3558497428894043 +[2025-04-29 18:31:52,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 1.8708628416061401, cross_entropy: 1.8708628416061401 +[2025-04-29 18:31:56,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.5782952308654785, cross_entropy: 1.5782952308654785 +[2025-04-29 18:31:56,576][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 3.404088258743286, cross_entropy: 3.404088258743286 +[2025-04-29 18:32:00,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 1.5482618808746338, cross_entropy: 1.5482618808746338 +[2025-04-29 18:32:00,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 2.180413246154785, cross_entropy: 2.180413246154785 +[2025-04-29 18:32:00,899][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/iteration1000.pth. +[2025-04-29 18:32:04,831][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 1.6319262981414795, cross_entropy: 1.6319262981414795 +[2025-04-29 18:32:05,658][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 3.4765872955322266, cross_entropy: 3.4765872955322266 +[2025-04-29 18:32:08,769][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.032561779022217, cross_entropy: 3.032561779022217 +[2025-04-29 18:32:09,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.9945389032363892, cross_entropy: 1.9945389032363892 +[2025-04-29 18:32:12,809][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.515419840812683, cross_entropy: 1.515419840812683 +[2025-04-29 18:32:13,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 1.8182076215744019, cross_entropy: 1.8182076215744019 +[2025-04-29 18:32:18,294][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.1537318229675293, cross_entropy: 2.1537318229675293 +[2025-04-29 18:32:18,649][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.252546787261963, cross_entropy: 2.252546787261963 +[2025-04-29 18:32:21,764][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 3.552741527557373, cross_entropy: 3.552741527557373 +[2025-04-29 18:32:22,306][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 3.2357418537139893, cross_entropy: 3.2357418537139893 +[2025-04-29 18:32:25,613][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.1776270866394043, cross_entropy: 3.1776270866394043 +[2025-04-29 18:32:26,479][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.0687639713287354, cross_entropy: 2.0687639713287354 +[2025-04-29 18:32:29,340][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 3.0860466957092285, cross_entropy: 3.0860466957092285 +[2025-04-29 18:32:30,188][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 2.0477726459503174, cross_entropy: 2.0477726459503174 +[2025-04-29 18:32:33,258][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 2.9357857704162598, cross_entropy: 2.9357857704162598 +[2025-04-29 18:32:33,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.1811113357543945, cross_entropy: 3.1811113357543945 +[2025-04-29 18:32:37,088][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 3.416682481765747, cross_entropy: 3.416682481765747 +[2025-04-29 18:32:38,020][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 1.8815702199935913, cross_entropy: 1.8815702199935913 +[2025-04-29 18:32:41,493][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.144442081451416, cross_entropy: 2.144442081451416 +[2025-04-29 18:32:42,248][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 2.1544814109802246, cross_entropy: 2.1544814109802246 +[2025-04-29 18:32:45,466][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 2.4044337272644043, cross_entropy: 2.4044337272644043 +[2025-04-29 18:32:46,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.713876247406006, cross_entropy: 2.713876247406006 +[2025-04-29 18:32:49,808][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 0.9745863080024719, cross_entropy: 0.9745863080024719 +[2025-04-29 18:32:51,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 3.470905303955078, cross_entropy: 3.470905303955078 +[2025-04-29 18:32:54,461][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 2.97037935256958, cross_entropy: 2.97037935256958 +[2025-04-29 18:32:55,917][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 1.841355562210083, cross_entropy: 1.841355562210083 +[2025-04-29 18:32:58,945][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 1.4056854248046875, cross_entropy: 1.4056854248046875 +[2025-04-29 18:32:59,927][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.8588738441467285, cross_entropy: 2.8588738441467285 +[2025-04-29 18:33:02,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 1.679738998413086, cross_entropy: 1.679738998413086 +[2025-04-29 18:33:04,092][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 3.276698589324951, cross_entropy: 3.276698589324951 +[2025-04-29 18:33:07,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 2.276801824569702, cross_entropy: 2.276801824569702 +[2025-04-29 18:33:07,951][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.5363986492156982, cross_entropy: 3.5363986492156982 +[2025-04-29 18:33:11,175][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 1.846892237663269, cross_entropy: 1.846892237663269 +[2025-04-29 18:33:12,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 2.8864917755126953, cross_entropy: 2.8864917755126953 +[2025-04-29 18:33:15,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 2.270796298980713, cross_entropy: 2.270796298980713 +[2025-04-29 18:33:16,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 2.684560775756836, cross_entropy: 2.684560775756836 +[2025-04-29 18:33:19,561][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 1.643777847290039, cross_entropy: 1.643777847290039 +[2025-04-29 18:33:20,311][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.6046326160430908, cross_entropy: 1.6046326160430908 +[2025-04-29 18:33:23,408][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.376751184463501, cross_entropy: 3.376751184463501 +[2025-04-29 18:33:25,351][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 1.872321605682373, cross_entropy: 1.872321605682373 +[2025-04-29 18:33:28,304][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 1.6110742092132568, cross_entropy: 1.6110742092132568 +[2025-04-29 18:33:28,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 3.235778331756592, cross_entropy: 3.235778331756592 +[2025-04-29 18:33:31,864][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 1.393594741821289, cross_entropy: 1.393594741821289 +[2025-04-29 18:33:32,619][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.677854537963867, cross_entropy: 2.677854537963867 +[2025-04-29 18:33:36,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 2.893242835998535, cross_entropy: 2.893242835998535 +[2025-04-29 18:33:36,845][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 2.906890869140625, cross_entropy: 2.906890869140625 +[2025-04-29 18:33:40,440][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 3.4267683029174805, cross_entropy: 3.4267683029174805 +[2025-04-29 18:33:41,000][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.1469309329986572, cross_entropy: 2.1469309329986572 +[2025-04-29 18:33:44,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 3.2785634994506836, cross_entropy: 3.2785634994506836 +[2025-04-29 18:33:44,801][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 3.3712611198425293, cross_entropy: 3.3712611198425293 +[2025-04-29 18:33:48,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 3.332021951675415, cross_entropy: 3.332021951675415 +[2025-04-29 18:33:49,128][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 3.2017500400543213, cross_entropy: 3.2017500400543213 +[2025-04-29 18:33:52,361][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 2.9073262214660645, cross_entropy: 2.9073262214660645 +[2025-04-29 18:33:53,507][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 1.643798589706421, cross_entropy: 1.643798589706421 +[2025-04-29 18:33:57,342][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 2.0842630863189697, cross_entropy: 2.0842630863189697 +[2025-04-29 18:33:57,765][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 2.020859718322754, cross_entropy: 2.020859718322754 +[2025-04-29 18:34:01,801][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 2.6287310123443604, cross_entropy: 2.6287310123443604 +[2025-04-29 18:34:02,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.5182985067367554, cross_entropy: 1.5182985067367554 +[2025-04-29 18:34:06,213][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.2128874063491821, cross_entropy: 1.2128874063491821 +[2025-04-29 18:34:06,568][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.524853229522705, cross_entropy: 1.524853229522705 +[2025-04-29 18:34:09,672][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 2.898225784301758, cross_entropy: 2.898225784301758 +[2025-04-29 18:34:10,036][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 1.618802785873413, cross_entropy: 1.618802785873413 +[2025-04-29 18:34:13,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 3.1626744270324707, cross_entropy: 3.1626744270324707 +[2025-04-29 18:34:13,757][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.6107940673828125, cross_entropy: 2.6107940673828125 +[2025-04-29 18:34:17,677][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.3682594299316406, cross_entropy: 3.3682594299316406 +[2025-04-29 18:34:18,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.7471091747283936, cross_entropy: 1.7471091747283936 +[2025-04-29 18:34:21,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 3.2399497032165527, cross_entropy: 3.2399497032165527 +[2025-04-29 18:34:21,553][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 3.715123176574707, cross_entropy: 3.715123176574707 +[2025-04-29 18:37:41,832][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.333113670349121, cross_entropy: 2.333113670349121 +[2025-04-29 18:37:41,833][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.5132139921188354, cross_entropy: 1.5132139921188354 +[2025-04-29 18:37:42,073][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 18:37:42,257][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch3.pth. +[2025-04-29 18:37:42,507][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 18:37:49,732][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 3.323286533355713, cross_entropy: 3.323286533355713 +[2025-04-29 18:37:50,087][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 3.138064384460449, cross_entropy: 3.138064384460449 +[2025-04-29 18:37:53,145][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.2402448654174805, cross_entropy: 1.2402448654174805 +[2025-04-29 18:37:53,506][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 3.2971231937408447, cross_entropy: 3.2971231937408447 +[2025-04-29 18:37:56,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 1.623806357383728, cross_entropy: 1.623806357383728 +[2025-04-29 18:37:57,261][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 2.1072027683258057, cross_entropy: 2.1072027683258057 +[2025-04-29 18:38:00,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 2.541166305541992, cross_entropy: 2.541166305541992 +[2025-04-29 18:38:01,139][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 2.7221946716308594, cross_entropy: 2.7221946716308594 +[2025-04-29 18:38:05,112][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 2.449348211288452, cross_entropy: 2.449348211288452 +[2025-04-29 18:38:05,471][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.9520227909088135, cross_entropy: 1.9520227909088135 +[2025-04-29 18:38:09,543][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 2.2704973220825195, cross_entropy: 2.2704973220825195 +[2025-04-29 18:38:09,898][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 1.8402910232543945, cross_entropy: 1.8402910232543945 +[2025-04-29 18:38:14,180][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 3.320270538330078, cross_entropy: 3.320270538330078 +[2025-04-29 18:38:14,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 3.4214000701904297, cross_entropy: 3.4214000701904297 +[2025-04-29 18:38:18,293][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 2.5576913356781006, cross_entropy: 2.5576913356781006 +[2025-04-29 18:38:18,651][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.3248673677444458, cross_entropy: 1.3248673677444458 +[2025-04-29 18:38:22,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 1.372626543045044, cross_entropy: 1.372626543045044 +[2025-04-29 18:38:22,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 1.5516201257705688, cross_entropy: 1.5516201257705688 +[2025-04-29 18:38:26,066][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 2.7841386795043945, cross_entropy: 2.7841386795043945 +[2025-04-29 18:38:26,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 1.4570629596710205, cross_entropy: 1.4570629596710205 +[2025-04-29 18:38:30,322][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 2.6574501991271973, cross_entropy: 2.6574501991271973 +[2025-04-29 18:38:30,681][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 3.093702793121338, cross_entropy: 3.093702793121338 +[2025-04-29 18:38:34,467][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 3.168067455291748, cross_entropy: 3.168067455291748 +[2025-04-29 18:38:34,829][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 2.511348009109497, cross_entropy: 2.511348009109497 +[2025-04-29 18:38:39,225][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.0787084102630615, cross_entropy: 2.0787084102630615 +[2025-04-29 18:38:39,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 2.464388847351074, cross_entropy: 2.464388847351074 +[2025-04-29 18:38:43,374][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 3.019636631011963, cross_entropy: 3.019636631011963 +[2025-04-29 18:38:43,696][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 1.61124849319458, cross_entropy: 1.61124849319458 +[2025-04-29 18:38:48,225][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.3361976146698, cross_entropy: 2.3361976146698 +[2025-04-29 18:38:48,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 3.1838326454162598, cross_entropy: 3.1838326454162598 +[2025-04-29 18:38:52,183][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 1.402984380722046, cross_entropy: 1.402984380722046 +[2025-04-29 18:38:52,503][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 2.9676432609558105, cross_entropy: 2.9676432609558105 +[2025-04-29 18:38:56,460][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 2.0006468296051025, cross_entropy: 2.0006468296051025 +[2025-04-29 18:38:56,817][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 3.0819311141967773, cross_entropy: 3.0819311141967773 +[2025-04-29 18:39:00,939][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 1.4404208660125732, cross_entropy: 1.4404208660125732 +[2025-04-29 18:39:01,293][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 1.7026262283325195, cross_entropy: 1.7026262283325195 +[2025-04-29 18:39:04,801][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.6650111675262451, cross_entropy: 1.6650111675262451 +[2025-04-29 18:39:05,158][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 1.815996527671814, cross_entropy: 1.815996527671814 +[2025-04-29 18:39:08,631][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 1.3097848892211914, cross_entropy: 1.3097848892211914 +[2025-04-29 18:39:08,984][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 3.038860321044922, cross_entropy: 3.038860321044922 +[2025-04-29 18:39:12,764][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.461371421813965, cross_entropy: 2.461371421813965 +[2025-04-29 18:39:13,120][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 1.7412943840026855, cross_entropy: 1.7412943840026855 +[2025-04-29 18:39:17,001][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 1.824864387512207, cross_entropy: 1.824864387512207 +[2025-04-29 18:39:17,347][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 1.4095768928527832, cross_entropy: 1.4095768928527832 +[2025-04-29 18:39:21,198][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 1.2357611656188965, cross_entropy: 1.2357611656188965 +[2025-04-29 18:39:21,551][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 1.047414779663086, cross_entropy: 1.047414779663086 +[2025-04-29 18:39:24,963][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 1.8385924100875854, cross_entropy: 1.8385924100875854 +[2025-04-29 18:39:25,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 1.6236119270324707, cross_entropy: 1.6236119270324707 +[2025-04-29 18:39:29,363][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 2.6180338859558105, cross_entropy: 2.6180338859558105 +[2025-04-29 18:39:29,719][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 1.4490339756011963, cross_entropy: 1.4490339756011963 +[2025-04-29 18:39:33,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 2.987401008605957, cross_entropy: 2.987401008605957 +[2025-04-29 18:39:33,458][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.464766263961792, cross_entropy: 1.464766263961792 +[2025-04-29 18:39:37,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.462015151977539, cross_entropy: 2.462015151977539 +[2025-04-29 18:39:38,126][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.2135581970214844, cross_entropy: 2.2135581970214844 +[2025-04-29 18:39:41,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 1.1971321105957031, cross_entropy: 1.1971321105957031 +[2025-04-29 18:39:42,186][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 2.5485708713531494, cross_entropy: 2.5485708713531494 +[2025-04-29 18:39:46,023][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 1.0840330123901367, cross_entropy: 1.0840330123901367 +[2025-04-29 18:39:46,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.9320576190948486, cross_entropy: 2.9320576190948486 +[2025-04-29 18:39:51,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 2.8358523845672607, cross_entropy: 2.8358523845672607 +[2025-04-29 18:39:51,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 1.3483387231826782, cross_entropy: 1.3483387231826782 +[2025-04-29 18:39:54,658][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 2.8563127517700195, cross_entropy: 2.8563127517700195 +[2025-04-29 18:39:55,018][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 2.2572484016418457, cross_entropy: 2.2572484016418457 +[2025-04-29 18:39:58,766][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 3.5224313735961914, cross_entropy: 3.5224313735961914 +[2025-04-29 18:39:59,126][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 3.360976219177246, cross_entropy: 3.360976219177246 +[2025-04-29 18:40:02,828][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 1.631631851196289, cross_entropy: 1.631631851196289 +[2025-04-29 18:40:03,181][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 3.127174139022827, cross_entropy: 3.127174139022827 +[2025-04-29 18:40:07,076][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.4946587085723877, cross_entropy: 2.4946587085723877 +[2025-04-29 18:40:07,434][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.2828760147094727, cross_entropy: 3.2828760147094727 +[2025-04-29 18:40:11,539][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 1.2600288391113281, cross_entropy: 1.2600288391113281 +[2025-04-29 18:40:11,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 1.3900911808013916, cross_entropy: 1.3900911808013916 +[2025-04-29 18:40:15,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 1.8845162391662598, cross_entropy: 1.8845162391662598 +[2025-04-29 18:40:15,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.0726585388183594, cross_entropy: 1.0726585388183594 +[2025-04-29 18:40:19,194][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 2.083757162094116, cross_entropy: 2.083757162094116 +[2025-04-29 18:40:19,550][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.4209541082382202, cross_entropy: 1.4209541082382202 +[2025-04-29 18:40:23,217][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 3.3204121589660645, cross_entropy: 3.3204121589660645 +[2025-04-29 18:40:23,574][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 2.9970405101776123, cross_entropy: 2.9970405101776123 +[2025-04-29 18:40:27,816][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.616329312324524, cross_entropy: 1.616329312324524 +[2025-04-29 18:40:28,175][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 3.4116127490997314, cross_entropy: 3.4116127490997314 +[2025-04-29 18:40:31,667][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 1.2097808122634888, cross_entropy: 1.2097808122634888 +[2025-04-29 18:40:32,030][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.1387535333633423, cross_entropy: 1.1387535333633423 +[2025-04-29 18:40:36,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.142798900604248, cross_entropy: 3.142798900604248 +[2025-04-29 18:40:36,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.4816174507141113, cross_entropy: 2.4816174507141113 +[2025-04-29 18:40:40,616][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 2.4193625450134277, cross_entropy: 2.4193625450134277 +[2025-04-29 18:40:40,976][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.6476860046386719, cross_entropy: 1.6476860046386719 +[2025-04-29 18:40:44,959][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 2.919316291809082, cross_entropy: 2.919316291809082 +[2025-04-29 18:40:45,329][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 1.5601733922958374, cross_entropy: 1.5601733922958374 +[2025-04-29 18:40:48,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.2409789562225342, cross_entropy: 1.2409789562225342 +[2025-04-29 18:40:49,282][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 2.8933820724487305, cross_entropy: 2.8933820724487305 +[2025-04-29 18:40:53,670][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 2.0534753799438477, cross_entropy: 2.0534753799438477 +[2025-04-29 18:40:54,024][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 1.5764198303222656, cross_entropy: 1.5764198303222656 +[2025-04-29 18:40:57,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 2.764496326446533, cross_entropy: 2.764496326446533 +[2025-04-29 18:40:58,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.1100252866744995, cross_entropy: 1.1100252866744995 +[2025-04-29 18:41:01,243][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 2.352531671524048, cross_entropy: 2.352531671524048 +[2025-04-29 18:41:01,608][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 1.308110237121582, cross_entropy: 1.308110237121582 +[2025-04-29 18:41:05,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 1.2518973350524902, cross_entropy: 1.2518973350524902 +[2025-04-29 18:41:05,815][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.6684396266937256, cross_entropy: 1.6684396266937256 +[2025-04-29 18:41:10,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 1.5303053855895996, cross_entropy: 1.5303053855895996 +[2025-04-29 18:41:10,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 2.205296039581299, cross_entropy: 2.205296039581299 +[2025-04-29 18:41:13,932][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 1.4132990837097168, cross_entropy: 1.4132990837097168 +[2025-04-29 18:41:14,251][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 2.9651877880096436, cross_entropy: 2.9651877880096436 +[2025-04-29 18:41:17,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 1.5499296188354492, cross_entropy: 1.5499296188354492 +[2025-04-29 18:41:18,227][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 1.4650681018829346, cross_entropy: 1.4650681018829346 +[2025-04-29 18:41:21,955][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 1.4615592956542969, cross_entropy: 1.4615592956542969 +[2025-04-29 18:41:22,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 1.698617696762085, cross_entropy: 1.698617696762085 +[2025-04-29 18:41:25,905][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.743107318878174, cross_entropy: 2.743107318878174 +[2025-04-29 18:41:26,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 2.9160900115966797, cross_entropy: 2.9160900115966797 +[2025-04-29 18:41:29,532][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 2.1256699562072754, cross_entropy: 2.1256699562072754 +[2025-04-29 18:41:29,891][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 0.9689559936523438, cross_entropy: 0.9689559936523438 +[2025-04-29 18:41:33,278][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 2.4271979331970215, cross_entropy: 2.4271979331970215 +[2025-04-29 18:41:33,666][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 1.4388885498046875, cross_entropy: 1.4388885498046875 +[2025-04-29 18:41:37,333][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.986271858215332, cross_entropy: 2.986271858215332 +[2025-04-29 18:41:37,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.1367294788360596, cross_entropy: 1.1367294788360596 +[2025-04-29 18:41:41,474][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 2.914093255996704, cross_entropy: 2.914093255996704 +[2025-04-29 18:41:41,831][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 1.524410605430603, cross_entropy: 1.524410605430603 +[2025-04-29 18:41:45,606][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 1.4476382732391357, cross_entropy: 1.4476382732391357 +[2025-04-29 18:41:45,963][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 1.3684964179992676, cross_entropy: 1.3684964179992676 +[2025-04-29 18:41:49,448][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.322378635406494, cross_entropy: 2.322378635406494 +[2025-04-29 18:41:49,806][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 3.056088447570801, cross_entropy: 3.056088447570801 +[2025-04-29 18:41:53,400][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 2.0029137134552, cross_entropy: 2.0029137134552 +[2025-04-29 18:41:53,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.6576576232910156, cross_entropy: 2.6576576232910156 +[2025-04-29 18:41:57,949][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 2.882640838623047, cross_entropy: 2.882640838623047 +[2025-04-29 18:41:58,307][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 1.9028934240341187, cross_entropy: 1.9028934240341187 +[2025-04-29 18:42:02,284][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.2952966690063477, cross_entropy: 2.2952966690063477 +[2025-04-29 18:42:02,638][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 1.5303122997283936, cross_entropy: 1.5303122997283936 +[2025-04-29 18:42:06,303][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 3.4879708290100098, cross_entropy: 3.4879708290100098 +[2025-04-29 18:42:06,659][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 3.23410701751709, cross_entropy: 3.23410701751709 +[2025-04-29 18:42:09,759][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 2.088749885559082, cross_entropy: 2.088749885559082 +[2025-04-29 18:42:10,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.0852861404418945, cross_entropy: 2.0852861404418945 +[2025-04-29 18:42:13,992][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 2.313718795776367, cross_entropy: 2.313718795776367 +[2025-04-29 18:42:14,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 3.1299142837524414, cross_entropy: 3.1299142837524414 +[2025-04-29 18:42:17,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 1.3874106407165527, cross_entropy: 1.3874106407165527 +[2025-04-29 18:42:18,080][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.093350887298584, cross_entropy: 2.093350887298584 +[2025-04-29 18:42:22,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.146822690963745, cross_entropy: 2.146822690963745 +[2025-04-29 18:42:22,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 2.2774152755737305, cross_entropy: 2.2774152755737305 +[2025-04-29 18:42:26,787][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 2.405853271484375, cross_entropy: 2.405853271484375 +[2025-04-29 18:42:27,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 1.672156572341919, cross_entropy: 1.672156572341919 +[2025-04-29 18:42:30,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 3.2076315879821777, cross_entropy: 3.2076315879821777 +[2025-04-29 18:42:30,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.3311262130737305, cross_entropy: 2.3311262130737305 +[2025-04-29 18:42:35,040][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.1929296255111694, cross_entropy: 1.1929296255111694 +[2025-04-29 18:42:35,398][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 1.35392165184021, cross_entropy: 1.35392165184021 +[2025-04-29 18:42:39,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.009878158569336, cross_entropy: 3.009878158569336 +[2025-04-29 18:42:39,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 2.286038875579834, cross_entropy: 2.286038875579834 +[2025-04-29 18:42:43,569][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 1.472870945930481, cross_entropy: 1.472870945930481 +[2025-04-29 18:42:43,931][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.6533610820770264, cross_entropy: 2.6533610820770264 +[2025-04-29 18:42:47,517][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 1.2470431327819824, cross_entropy: 1.2470431327819824 +[2025-04-29 18:42:47,873][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 2.9260168075561523, cross_entropy: 2.9260168075561523 +[2025-04-29 18:42:52,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 2.097193956375122, cross_entropy: 2.097193956375122 +[2025-04-29 18:42:52,514][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 1.1455014944076538, cross_entropy: 1.1455014944076538 +[2025-04-29 18:42:56,139][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 3.4042418003082275, cross_entropy: 3.4042418003082275 +[2025-04-29 18:42:56,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 2.1583070755004883, cross_entropy: 2.1583070755004883 +[2025-04-29 18:43:00,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.1472363471984863, cross_entropy: 1.1472363471984863 +[2025-04-29 18:43:00,525][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 1.023297905921936, cross_entropy: 1.023297905921936 +[2025-04-29 18:43:04,602][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.9356091022491455, cross_entropy: 1.9356091022491455 +[2025-04-29 18:43:04,975][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.2136893272399902, cross_entropy: 1.2136893272399902 +[2025-04-29 18:43:09,244][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 2.2129077911376953, cross_entropy: 2.2129077911376953 +[2025-04-29 18:43:09,566][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 3.368278980255127, cross_entropy: 3.368278980255127 +[2025-04-29 18:43:13,784][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.2461414337158203, cross_entropy: 2.2461414337158203 +[2025-04-29 18:43:14,139][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 1.444150447845459, cross_entropy: 1.444150447845459 +[2025-04-29 18:43:17,650][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 1.9265666007995605, cross_entropy: 1.9265666007995605 +[2025-04-29 18:43:18,009][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 3.1403417587280273, cross_entropy: 3.1403417587280273 +[2025-04-29 18:43:21,626][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.7564878463745117, cross_entropy: 2.7564878463745117 +[2025-04-29 18:43:21,986][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 1.781611680984497, cross_entropy: 1.781611680984497 +[2025-04-29 18:43:26,487][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 2.8907439708709717, cross_entropy: 2.8907439708709717 +[2025-04-29 18:43:26,843][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 3.45330548286438, cross_entropy: 3.45330548286438 +[2025-04-29 18:43:30,007][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 3.488529920578003, cross_entropy: 3.488529920578003 +[2025-04-29 18:43:30,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.4306859970092773, cross_entropy: 1.4306859970092773 +[2025-04-29 18:43:34,145][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 2.41597318649292, cross_entropy: 2.41597318649292 +[2025-04-29 18:43:34,466][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.5837750434875488, cross_entropy: 1.5837750434875488 +[2025-04-29 18:43:38,551][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 2.7545671463012695, cross_entropy: 2.7545671463012695 +[2025-04-29 18:43:38,909][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 1.73386812210083, cross_entropy: 1.73386812210083 +[2025-04-29 18:43:42,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 2.718771457672119, cross_entropy: 2.718771457672119 +[2025-04-29 18:43:43,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 1.6263211965560913, cross_entropy: 1.6263211965560913 +[2025-04-29 18:43:46,248][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 1.3288084268569946, cross_entropy: 1.3288084268569946 +[2025-04-29 18:43:48,159][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 1.267835259437561, cross_entropy: 1.267835259437561 +[2025-04-29 18:43:50,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 1.3517124652862549, cross_entropy: 1.3517124652862549 +[2025-04-29 18:43:51,913][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 1.442673921585083, cross_entropy: 1.442673921585083 +[2025-04-29 18:43:54,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 1.7273563146591187, cross_entropy: 1.7273563146591187 +[2025-04-29 18:43:55,811][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.2302992343902588, cross_entropy: 1.2302992343902588 +[2025-04-29 18:43:57,929][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 3.049586534500122, cross_entropy: 3.049586534500122 +[2025-04-29 18:43:59,776][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.202260136604309, cross_entropy: 1.202260136604309 +[2025-04-29 18:44:02,197][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 3.1155824661254883, cross_entropy: 3.1155824661254883 +[2025-04-29 18:44:03,654][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.47621750831604, cross_entropy: 1.47621750831604 +[2025-04-29 18:44:06,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 3.3296871185302734, cross_entropy: 3.3296871185302734 +[2025-04-29 18:44:08,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 1.4333877563476562, cross_entropy: 1.4333877563476562 +[2025-04-29 18:44:10,915][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 1.2995777130126953, cross_entropy: 1.2995777130126953 +[2025-04-29 18:44:12,831][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 2.117000102996826, cross_entropy: 2.117000102996826 +[2025-04-29 18:44:15,570][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 2.4504711627960205, cross_entropy: 2.4504711627960205 +[2025-04-29 18:44:17,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 2.3084945678710938, cross_entropy: 2.3084945678710938 +[2025-04-29 18:44:19,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.6214834451675415, cross_entropy: 1.6214834451675415 +[2025-04-29 18:44:22,117][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 2.327605724334717, cross_entropy: 2.327605724334717 +[2025-04-29 18:44:23,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 1.29056715965271, cross_entropy: 1.29056715965271 +[2025-04-29 18:44:26,072][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 3.168836832046509, cross_entropy: 3.168836832046509 +[2025-04-29 18:44:27,123][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 2.425924062728882, cross_entropy: 2.425924062728882 +[2025-04-29 18:44:30,907][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 1.2609927654266357, cross_entropy: 1.2609927654266357 +[2025-04-29 18:44:31,264][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.3377158641815186, cross_entropy: 1.3377158641815186 +[2025-04-29 18:44:34,395][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 3.283053159713745, cross_entropy: 3.283053159713745 +[2025-04-29 18:44:34,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 2.532898187637329, cross_entropy: 2.532898187637329 +[2025-04-29 18:44:38,891][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.5322890281677246, cross_entropy: 2.5322890281677246 +[2025-04-29 18:44:39,258][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 1.0810301303863525, cross_entropy: 1.0810301303863525 +[2025-04-29 18:44:43,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 2.194906711578369, cross_entropy: 2.194906711578369 +[2025-04-29 18:44:43,886][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.135084629058838, cross_entropy: 1.135084629058838 +[2025-04-29 18:44:47,428][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 3.0872607231140137, cross_entropy: 3.0872607231140137 +[2025-04-29 18:44:47,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.8022360801696777, cross_entropy: 2.8022360801696777 +[2025-04-29 18:44:50,902][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 2.5807385444641113, cross_entropy: 2.5807385444641113 +[2025-04-29 18:44:52,216][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 1.7109873294830322, cross_entropy: 1.7109873294830322 +[2025-04-29 18:44:56,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 1.4460960626602173, cross_entropy: 1.4460960626602173 +[2025-04-29 18:44:57,140][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 1.3536957502365112, cross_entropy: 1.3536957502365112 +[2025-04-29 18:45:01,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 3.1522929668426514, cross_entropy: 3.1522929668426514 +[2025-04-29 18:45:01,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 1.6486470699310303, cross_entropy: 1.6486470699310303 +[2025-04-29 18:45:06,236][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 1.3293628692626953, cross_entropy: 1.3293628692626953 +[2025-04-29 18:45:06,594][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 3.239095687866211, cross_entropy: 3.239095687866211 +[2025-04-29 18:45:09,748][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 1.9469678401947021, cross_entropy: 1.9469678401947021 +[2025-04-29 18:45:10,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 3.0564322471618652, cross_entropy: 3.0564322471618652 +[2025-04-29 18:45:14,134][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 1.437978982925415, cross_entropy: 1.437978982925415 +[2025-04-29 18:45:14,496][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 1.3428314924240112, cross_entropy: 1.3428314924240112 +[2025-04-29 18:45:20,030][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 1.5925804376602173, cross_entropy: 1.5925804376602173 +[2025-04-29 18:45:20,352][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 3.1720805168151855, cross_entropy: 3.1720805168151855 +[2025-04-29 18:45:23,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.6414875984191895, cross_entropy: 2.6414875984191895 +[2025-04-29 18:45:24,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.3035969734191895, cross_entropy: 1.3035969734191895 +[2025-04-29 18:45:27,428][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 3.2950384616851807, cross_entropy: 3.2950384616851807 +[2025-04-29 18:45:27,783][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 1.1295435428619385, cross_entropy: 1.1295435428619385 +[2025-04-29 18:45:31,112][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.6994376182556152, cross_entropy: 2.6994376182556152 +[2025-04-29 18:45:31,471][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 1.75477933883667, cross_entropy: 1.75477933883667 +[2025-04-29 18:45:35,042][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 3.1329140663146973, cross_entropy: 3.1329140663146973 +[2025-04-29 18:45:35,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 1.4760894775390625, cross_entropy: 1.4760894775390625 +[2025-04-29 18:45:39,085][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 1.743009328842163, cross_entropy: 1.743009328842163 +[2025-04-29 18:45:39,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 2.275031089782715, cross_entropy: 2.275031089782715 +[2025-04-29 18:45:43,874][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 1.767643928527832, cross_entropy: 1.767643928527832 +[2025-04-29 18:45:44,198][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 1.359795093536377, cross_entropy: 1.359795093536377 +[2025-04-29 18:45:48,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 2.579116106033325, cross_entropy: 2.579116106033325 +[2025-04-29 18:45:48,448][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 1.9686992168426514, cross_entropy: 1.9686992168426514 +[2025-04-29 18:45:52,252][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 1.9718854427337646, cross_entropy: 1.9718854427337646 +[2025-04-29 18:45:52,575][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 1.8885315656661987, cross_entropy: 1.8885315656661987 +[2025-04-29 18:45:56,206][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 2.418292760848999, cross_entropy: 2.418292760848999 +[2025-04-29 18:45:56,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.361020803451538, cross_entropy: 1.361020803451538 +[2025-04-29 18:45:59,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.87546706199646, cross_entropy: 2.87546706199646 +[2025-04-29 18:46:00,692][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 1.307896614074707, cross_entropy: 1.307896614074707 +[2025-04-29 18:46:03,998][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 3.0814881324768066, cross_entropy: 3.0814881324768066 +[2025-04-29 18:46:04,463][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.0885705947875977, cross_entropy: 3.0885705947875977 +[2025-04-29 18:46:07,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 3.1966552734375, cross_entropy: 3.1966552734375 +[2025-04-29 18:46:08,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 2.997471332550049, cross_entropy: 2.997471332550049 +[2025-04-29 18:46:11,661][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.637852668762207, cross_entropy: 2.637852668762207 +[2025-04-29 18:46:12,135][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.3274831771850586, cross_entropy: 2.3274831771850586 +[2025-04-29 18:46:15,875][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 1.3659868240356445, cross_entropy: 1.3659868240356445 +[2025-04-29 18:46:16,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 3.456165313720703, cross_entropy: 3.456165313720703 +[2025-04-29 18:46:19,948][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 2.213038921356201, cross_entropy: 2.213038921356201 +[2025-04-29 18:46:20,915][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 1.9808018207550049, cross_entropy: 1.9808018207550049 +[2025-04-29 18:46:24,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 1.3653671741485596, cross_entropy: 1.3653671741485596 +[2025-04-29 18:46:24,629][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 1.5418914556503296, cross_entropy: 1.5418914556503296 +[2025-04-29 18:46:29,031][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.6615618467330933, cross_entropy: 1.6615618467330933 +[2025-04-29 18:46:29,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 3.204195261001587, cross_entropy: 3.204195261001587 +[2025-04-29 18:46:32,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 1.6311863660812378, cross_entropy: 1.6311863660812378 +[2025-04-29 18:46:33,176][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 2.273820400238037, cross_entropy: 2.273820400238037 +[2025-04-29 18:46:36,930][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 2.479654550552368, cross_entropy: 2.479654550552368 +[2025-04-29 18:46:37,254][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.044588327407837, cross_entropy: 2.044588327407837 +[2025-04-29 18:46:40,857][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 1.1078228950500488, cross_entropy: 1.1078228950500488 +[2025-04-29 18:46:41,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 1.3264410495758057, cross_entropy: 1.3264410495758057 +[2025-04-29 18:46:44,707][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 2.8141398429870605, cross_entropy: 2.8141398429870605 +[2025-04-29 18:46:45,071][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.509491205215454, cross_entropy: 1.509491205215454 +[2025-04-29 18:46:49,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 3.3861234188079834, cross_entropy: 3.3861234188079834 +[2025-04-29 18:46:49,373][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 2.6665172576904297, cross_entropy: 2.6665172576904297 +[2025-04-29 18:46:53,696][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 2.785346031188965, cross_entropy: 2.785346031188965 +[2025-04-29 18:46:54,051][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 1.6286696195602417, cross_entropy: 1.6286696195602417 +[2025-04-29 18:46:57,868][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 1.436316967010498, cross_entropy: 1.436316967010498 +[2025-04-29 18:46:59,666][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 1.5270130634307861, cross_entropy: 1.5270130634307861 +[2025-04-29 18:47:02,638][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.013537645339966, cross_entropy: 2.013537645339966 +[2025-04-29 18:47:04,141][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 3.3008463382720947, cross_entropy: 3.3008463382720947 +[2025-04-29 18:47:06,494][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 1.734269142150879, cross_entropy: 1.734269142150879 +[2025-04-29 18:47:07,712][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 2.641578435897827, cross_entropy: 2.641578435897827 +[2025-04-29 18:47:10,613][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.1541426181793213, cross_entropy: 1.1541426181793213 +[2025-04-29 18:47:11,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.1721982955932617, cross_entropy: 2.1721982955932617 +[2025-04-29 18:47:15,372][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.4157531261444092, cross_entropy: 1.4157531261444092 +[2025-04-29 18:47:15,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 2.106436014175415, cross_entropy: 2.106436014175415 +[2025-04-29 18:47:19,397][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 1.7139348983764648, cross_entropy: 1.7139348983764648 +[2025-04-29 18:47:19,760][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 1.6443431377410889, cross_entropy: 1.6443431377410889 +[2025-04-29 18:47:23,655][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 3.3334903717041016, cross_entropy: 3.3334903717041016 +[2025-04-29 18:47:24,121][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 2.260650634765625, cross_entropy: 2.260650634765625 +[2025-04-29 18:47:27,729][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 3.1797618865966797, cross_entropy: 3.1797618865966797 +[2025-04-29 18:47:28,372][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 3.0035324096679688, cross_entropy: 3.0035324096679688 +[2025-04-29 18:47:32,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 3.076094627380371, cross_entropy: 3.076094627380371 +[2025-04-29 18:47:33,534][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 1.1895041465759277, cross_entropy: 1.1895041465759277 +[2025-04-29 18:47:36,906][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 1.4507172107696533, cross_entropy: 1.4507172107696533 +[2025-04-29 18:47:37,611][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 1.5973834991455078, cross_entropy: 1.5973834991455078 +[2025-04-29 18:47:40,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 1.5741366147994995, cross_entropy: 1.5741366147994995 +[2025-04-29 18:47:41,187][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 2.9609668254852295, cross_entropy: 2.9609668254852295 +[2025-04-29 18:47:44,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.0755531787872314, cross_entropy: 2.0755531787872314 +[2025-04-29 18:47:45,266][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 2.202678680419922, cross_entropy: 2.202678680419922 +[2025-04-29 18:47:49,139][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 1.5017375946044922, cross_entropy: 1.5017375946044922 +[2025-04-29 18:47:49,726][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.7734261751174927, cross_entropy: 1.7734261751174927 +[2025-04-29 18:47:53,835][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 2.822258949279785, cross_entropy: 2.822258949279785 +[2025-04-29 18:47:54,190][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 0.9793413877487183, cross_entropy: 0.9793413877487183 +[2025-04-29 18:47:57,271][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 2.516012191772461, cross_entropy: 2.516012191772461 +[2025-04-29 18:47:57,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.551828145980835, cross_entropy: 1.551828145980835 +[2025-04-29 18:48:01,793][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 3.2747702598571777, cross_entropy: 3.2747702598571777 +[2025-04-29 18:48:02,212][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 1.5756306648254395, cross_entropy: 1.5756306648254395 +[2025-04-29 18:48:06,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 1.3964859247207642, cross_entropy: 1.3964859247207642 +[2025-04-29 18:48:06,744][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.3069608211517334, cross_entropy: 2.3069608211517334 +[2025-04-29 18:48:10,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.424612283706665, cross_entropy: 1.424612283706665 +[2025-04-29 18:48:11,062][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 1.646956205368042, cross_entropy: 1.646956205368042 +[2025-04-29 18:48:15,082][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 3.190631151199341, cross_entropy: 3.190631151199341 +[2025-04-29 18:48:15,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.291250228881836, cross_entropy: 1.291250228881836 +[2025-04-29 18:48:19,263][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.617220401763916, cross_entropy: 2.617220401763916 +[2025-04-29 18:48:19,621][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.306636095046997, cross_entropy: 1.306636095046997 +[2025-04-29 18:48:23,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 2.2658674716949463, cross_entropy: 2.2658674716949463 +[2025-04-29 18:48:23,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 1.386534333229065, cross_entropy: 1.386534333229065 +[2025-04-29 18:48:27,168][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 3.090700626373291, cross_entropy: 3.090700626373291 +[2025-04-29 18:48:27,529][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.3561725616455078, cross_entropy: 1.3561725616455078 +[2025-04-29 18:48:31,073][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 1.3586300611495972, cross_entropy: 1.3586300611495972 +[2025-04-29 18:48:31,396][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 1.3700358867645264, cross_entropy: 1.3700358867645264 +[2025-04-29 18:48:35,188][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.618481397628784, cross_entropy: 2.618481397628784 +[2025-04-29 18:48:35,547][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 1.5531569719314575, cross_entropy: 1.5531569719314575 +[2025-04-29 18:48:39,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 3.1355233192443848, cross_entropy: 3.1355233192443848 +[2025-04-29 18:48:39,425][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 2.5570998191833496, cross_entropy: 2.5570998191833496 +[2025-04-29 18:48:42,906][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.7530016899108887, cross_entropy: 2.7530016899108887 +[2025-04-29 18:48:43,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 3.1498146057128906, cross_entropy: 3.1498146057128906 +[2025-04-29 18:48:46,898][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.726741909980774, cross_entropy: 1.726741909980774 +[2025-04-29 18:48:47,256][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 3.0185537338256836, cross_entropy: 3.0185537338256836 +[2025-04-29 18:48:50,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.2001829147338867, cross_entropy: 1.2001829147338867 +[2025-04-29 18:48:51,349][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 3.1888022422790527, cross_entropy: 3.1888022422790527 +[2025-04-29 18:48:54,823][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 3.0007195472717285, cross_entropy: 3.0007195472717285 +[2025-04-29 18:48:55,466][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.4718918800354004, cross_entropy: 1.4718918800354004 +[2025-04-29 18:48:59,212][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.329362154006958, cross_entropy: 1.329362154006958 +[2025-04-29 18:48:59,617][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.5093190670013428, cross_entropy: 2.5093190670013428 +[2025-04-29 18:49:03,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 3.1300559043884277, cross_entropy: 3.1300559043884277 +[2025-04-29 18:49:04,494][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 3.4380478858947754, cross_entropy: 3.4380478858947754 +[2025-04-29 18:49:08,237][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.189523220062256, cross_entropy: 2.189523220062256 +[2025-04-29 18:49:08,620][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 1.150943636894226, cross_entropy: 1.150943636894226 +[2025-04-29 18:49:12,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 2.1736931800842285, cross_entropy: 2.1736931800842285 +[2025-04-29 18:49:12,679][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 0.7345585227012634, cross_entropy: 0.7345585227012634 +[2025-04-29 18:49:17,424][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.4090689420700073, cross_entropy: 1.4090689420700073 +[2025-04-29 18:49:17,745][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 3.382734537124634, cross_entropy: 3.382734537124634 +[2025-04-29 18:49:21,281][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.3582745790481567, cross_entropy: 1.3582745790481567 +[2025-04-29 18:49:21,637][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 1.3829143047332764, cross_entropy: 1.3829143047332764 +[2025-04-29 18:49:26,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 3.022636890411377, cross_entropy: 3.022636890411377 +[2025-04-29 18:49:26,566][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.4076201915740967, cross_entropy: 1.4076201915740967 +[2025-04-29 18:49:31,317][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.8753602504730225, cross_entropy: 2.8753602504730225 +[2025-04-29 18:49:31,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.122450590133667, cross_entropy: 1.122450590133667 +[2025-04-29 18:49:35,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 1.616176724433899, cross_entropy: 1.616176724433899 +[2025-04-29 18:49:36,209][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 2.1590723991394043, cross_entropy: 2.1590723991394043 +[2025-04-29 18:49:40,361][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.3892641067504883, cross_entropy: 1.3892641067504883 +[2025-04-29 18:49:40,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.2349066734313965, cross_entropy: 2.2349066734313965 +[2025-04-29 18:49:44,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 1.2964117527008057, cross_entropy: 1.2964117527008057 +[2025-04-29 18:49:44,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 2.01303768157959, cross_entropy: 2.01303768157959 +[2025-04-29 18:49:48,736][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 3.265932083129883, cross_entropy: 3.265932083129883 +[2025-04-29 18:49:49,090][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 1.0774296522140503, cross_entropy: 1.0774296522140503 +[2025-04-29 18:49:53,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 2.2437925338745117, cross_entropy: 2.2437925338745117 +[2025-04-29 18:49:53,388][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.0462647676467896, cross_entropy: 1.0462647676467896 +[2025-04-29 18:49:57,496][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.982184410095215, cross_entropy: 2.982184410095215 +[2025-04-29 18:49:57,818][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.0927987098693848, cross_entropy: 1.0927987098693848 +[2025-04-29 18:50:01,816][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.5516043901443481, cross_entropy: 1.5516043901443481 +[2025-04-29 18:50:02,141][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.566777229309082, cross_entropy: 1.566777229309082 +[2025-04-29 18:50:06,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 3.012394428253174, cross_entropy: 3.012394428253174 +[2025-04-29 18:50:06,329][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 3.3650357723236084, cross_entropy: 3.3650357723236084 +[2025-04-29 18:50:09,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 2.9354097843170166, cross_entropy: 2.9354097843170166 +[2025-04-29 18:50:09,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 3.1392440795898438, cross_entropy: 3.1392440795898438 +[2025-04-29 18:50:14,079][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 1.6703227758407593, cross_entropy: 1.6703227758407593 +[2025-04-29 18:53:28,935][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.132861375808716, cross_entropy: 2.132861375808716 +[2025-04-29 18:53:28,936][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.375071406364441, cross_entropy: 1.375071406364441 +[2025-04-29 18:53:29,186][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 18:53:29,365][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch4.pth. +[2025-04-29 18:53:29,599][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 18:53:35,416][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 1.9847824573516846, cross_entropy: 1.9847824573516846 +[2025-04-29 18:53:35,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.46922767162323, cross_entropy: 1.46922767162323 +[2025-04-29 18:53:38,945][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.5696816444396973, cross_entropy: 1.5696816444396973 +[2025-04-29 18:53:39,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.2873938083648682, cross_entropy: 1.2873938083648682 +[2025-04-29 18:53:43,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.3274099826812744, cross_entropy: 1.3274099826812744 +[2025-04-29 18:53:43,484][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.9312968254089355, cross_entropy: 2.9312968254089355 +[2025-04-29 18:53:47,376][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 1.9719679355621338, cross_entropy: 1.9719679355621338 +[2025-04-29 18:53:47,733][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 1.4739679098129272, cross_entropy: 1.4739679098129272 +[2025-04-29 18:53:51,063][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 2.063371181488037, cross_entropy: 2.063371181488037 +[2025-04-29 18:53:51,543][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.2549604177474976, cross_entropy: 1.2549604177474976 +[2025-04-29 18:53:55,200][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 1.2389025688171387, cross_entropy: 1.2389025688171387 +[2025-04-29 18:53:55,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.7983635663986206, cross_entropy: 1.7983635663986206 +[2025-04-29 18:53:59,404][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 0.9644352793693542, cross_entropy: 0.9644352793693542 +[2025-04-29 18:53:59,785][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.366744041442871, cross_entropy: 2.366744041442871 +[2025-04-29 18:54:03,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 1.4605076313018799, cross_entropy: 1.4605076313018799 +[2025-04-29 18:54:04,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 1.164095163345337, cross_entropy: 1.164095163345337 +[2025-04-29 18:54:07,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 1.0645909309387207, cross_entropy: 1.0645909309387207 +[2025-04-29 18:54:07,786][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 1.2579401731491089, cross_entropy: 1.2579401731491089 +[2025-04-29 18:54:10,477][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 1.1575689315795898, cross_entropy: 1.1575689315795898 +[2025-04-29 18:54:12,504][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 0.9851009845733643, cross_entropy: 0.9851009845733643 +[2025-04-29 18:54:14,182][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.2552518844604492, cross_entropy: 1.2552518844604492 +[2025-04-29 18:54:16,539][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 1.856376051902771, cross_entropy: 1.856376051902771 +[2025-04-29 18:54:18,073][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 2.2806122303009033, cross_entropy: 2.2806122303009033 +[2025-04-29 18:54:20,650][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 2.706134557723999, cross_entropy: 2.706134557723999 +[2025-04-29 18:54:22,279][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.0829862356185913, cross_entropy: 1.0829862356185913 +[2025-04-29 18:54:24,290][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.0598548650741577, cross_entropy: 1.0598548650741577 +[2025-04-29 18:54:26,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 1.0120365619659424, cross_entropy: 1.0120365619659424 +[2025-04-29 18:54:28,951][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 3.0992674827575684, cross_entropy: 3.0992674827575684 +[2025-04-29 18:54:30,379][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 3.1517646312713623, cross_entropy: 3.1517646312713623 +[2025-04-29 18:54:32,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 1.0897197723388672, cross_entropy: 1.0897197723388672 +[2025-04-29 18:54:34,451][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.606673240661621, cross_entropy: 1.606673240661621 +[2025-04-29 18:54:36,704][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 1.927154302597046, cross_entropy: 1.927154302597046 +[2025-04-29 18:54:38,462][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 2.159252166748047, cross_entropy: 2.159252166748047 +[2025-04-29 18:54:40,234][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 2.89103102684021, cross_entropy: 2.89103102684021 +[2025-04-29 18:54:42,295][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 1.299332857131958, cross_entropy: 1.299332857131958 +[2025-04-29 18:54:43,843][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 2.690492868423462, cross_entropy: 2.690492868423462 +[2025-04-29 18:54:46,271][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 1.646037220954895, cross_entropy: 1.646037220954895 +[2025-04-29 18:54:48,704][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 3.15040922164917, cross_entropy: 3.15040922164917 +[2025-04-29 18:54:50,269][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 1.2898874282836914, cross_entropy: 1.2898874282836914 +[2025-04-29 18:54:52,938][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.3573143482208252, cross_entropy: 1.3573143482208252 +[2025-04-29 18:54:54,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 1.2451131343841553, cross_entropy: 1.2451131343841553 +[2025-04-29 18:54:57,519][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 3.061528205871582, cross_entropy: 3.061528205871582 +[2025-04-29 18:54:57,876][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 2.1074059009552, cross_entropy: 2.1074059009552 +[2025-04-29 18:55:02,182][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 2.5123279094696045, cross_entropy: 2.5123279094696045 +[2025-04-29 18:55:02,535][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 1.7989439964294434, cross_entropy: 1.7989439964294434 +[2025-04-29 18:55:06,204][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.5214134454727173, cross_entropy: 1.5214134454727173 +[2025-04-29 18:55:06,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.2206554412841797, cross_entropy: 1.2206554412841797 +[2025-04-29 18:55:09,623][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 2.140251636505127, cross_entropy: 2.140251636505127 +[2025-04-29 18:55:09,945][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.5144290924072266, cross_entropy: 2.5144290924072266 +[2025-04-29 18:55:14,324][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 2.9781301021575928, cross_entropy: 2.9781301021575928 +[2025-04-29 18:55:14,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 1.3283133506774902, cross_entropy: 1.3283133506774902 +[2025-04-29 18:55:18,126][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 3.1526877880096436, cross_entropy: 3.1526877880096436 +[2025-04-29 18:55:18,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 3.4037015438079834, cross_entropy: 3.4037015438079834 +[2025-04-29 18:55:21,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.591820478439331, cross_entropy: 2.591820478439331 +[2025-04-29 18:55:22,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.5897655487060547, cross_entropy: 2.5897655487060547 +[2025-04-29 18:55:27,302][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 1.4696123600006104, cross_entropy: 1.4696123600006104 +[2025-04-29 18:55:27,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 1.1457479000091553, cross_entropy: 1.1457479000091553 +[2025-04-29 18:55:31,317][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.6064300537109375, cross_entropy: 2.6064300537109375 +[2025-04-29 18:55:31,670][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 2.5393683910369873, cross_entropy: 2.5393683910369873 +[2025-04-29 18:55:35,844][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 0.930344820022583, cross_entropy: 0.930344820022583 +[2025-04-29 18:55:36,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 1.270422339439392, cross_entropy: 1.270422339439392 +[2025-04-29 18:55:41,349][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 1.5888097286224365, cross_entropy: 1.5888097286224365 +[2025-04-29 18:55:41,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 2.966928482055664, cross_entropy: 2.966928482055664 +[2025-04-29 18:55:45,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 2.5425362586975098, cross_entropy: 2.5425362586975098 +[2025-04-29 18:55:45,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.1022098064422607, cross_entropy: 2.1022098064422607 +[2025-04-29 18:55:49,413][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 1.3188247680664062, cross_entropy: 1.3188247680664062 +[2025-04-29 18:55:49,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 1.8326828479766846, cross_entropy: 1.8326828479766846 +[2025-04-29 18:55:53,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 2.863935947418213, cross_entropy: 2.863935947418213 +[2025-04-29 18:55:53,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 1.4604711532592773, cross_entropy: 1.4604711532592773 +[2025-04-29 18:55:58,084][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 1.4545421600341797, cross_entropy: 1.4545421600341797 +[2025-04-29 18:55:58,403][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.311636447906494, cross_entropy: 3.311636447906494 +[2025-04-29 18:56:02,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.026205539703369, cross_entropy: 2.026205539703369 +[2025-04-29 18:56:02,568][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 2.7355101108551025, cross_entropy: 2.7355101108551025 +[2025-04-29 18:56:06,647][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 2.0346314907073975, cross_entropy: 2.0346314907073975 +[2025-04-29 18:56:07,005][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.959299087524414, cross_entropy: 2.959299087524414 +[2025-04-29 18:56:11,191][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 2.494935989379883, cross_entropy: 2.494935989379883 +[2025-04-29 18:56:11,554][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.0034222602844238, cross_entropy: 1.0034222602844238 +[2025-04-29 18:56:14,848][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.3505381345748901, cross_entropy: 1.3505381345748901 +[2025-04-29 18:56:15,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.5982710123062134, cross_entropy: 1.5982710123062134 +[2025-04-29 18:56:19,075][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.8967541456222534, cross_entropy: 1.8967541456222534 +[2025-04-29 18:56:19,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 2.144432783126831, cross_entropy: 2.144432783126831 +[2025-04-29 18:56:23,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 1.1818089485168457, cross_entropy: 1.1818089485168457 +[2025-04-29 18:56:23,700][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.8193373680114746, cross_entropy: 2.8193373680114746 +[2025-04-29 18:56:27,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 3.321476936340332, cross_entropy: 3.321476936340332 +[2025-04-29 18:56:27,465][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 1.7981712818145752, cross_entropy: 1.7981712818145752 +[2025-04-29 18:56:30,779][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.7350072860717773, cross_entropy: 1.7350072860717773 +[2025-04-29 18:56:31,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 1.209139347076416, cross_entropy: 1.209139347076416 +[2025-04-29 18:56:34,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.767104148864746, cross_entropy: 1.767104148864746 +[2025-04-29 18:56:35,082][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.3453369140625, cross_entropy: 1.3453369140625 +[2025-04-29 18:56:39,030][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 3.030296802520752, cross_entropy: 3.030296802520752 +[2025-04-29 18:56:39,388][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 3.1476950645446777, cross_entropy: 3.1476950645446777 +[2025-04-29 18:56:42,712][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.4009110927581787, cross_entropy: 3.4009110927581787 +[2025-04-29 18:56:43,066][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.9831480979919434, cross_entropy: 2.9831480979919434 +[2025-04-29 18:56:46,743][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 1.1786115169525146, cross_entropy: 1.1786115169525146 +[2025-04-29 18:56:47,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 2.977248191833496, cross_entropy: 2.977248191833496 +[2025-04-29 18:56:51,298][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 2.193356513977051, cross_entropy: 2.193356513977051 +[2025-04-29 18:56:51,657][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 1.4047263860702515, cross_entropy: 1.4047263860702515 +[2025-04-29 18:56:54,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 2.0285210609436035, cross_entropy: 2.0285210609436035 +[2025-04-29 18:56:55,014][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 1.2175880670547485, cross_entropy: 1.2175880670547485 +[2025-04-29 18:56:59,087][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3348503112792969, cross_entropy: 1.3348503112792969 +[2025-04-29 18:56:59,410][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 0.9523579478263855, cross_entropy: 0.9523579478263855 +[2025-04-29 18:57:04,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 3.131770610809326, cross_entropy: 3.131770610809326 +[2025-04-29 18:57:04,478][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.5528737306594849, cross_entropy: 1.5528737306594849 +[2025-04-29 18:57:08,425][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.0780272483825684, cross_entropy: 2.0780272483825684 +[2025-04-29 18:57:08,787][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 2.316993236541748, cross_entropy: 2.316993236541748 +[2025-04-29 18:57:12,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.360924243927002, cross_entropy: 1.360924243927002 +[2025-04-29 18:57:12,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 1.2800073623657227, cross_entropy: 1.2800073623657227 +[2025-04-29 18:57:16,052][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.3407877683639526, cross_entropy: 1.3407877683639526 +[2025-04-29 18:57:16,416][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 0.8912127017974854, cross_entropy: 0.8912127017974854 +[2025-04-29 18:57:20,498][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.1054785251617432, cross_entropy: 1.1054785251617432 +[2025-04-29 18:57:20,820][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 2.7292017936706543, cross_entropy: 2.7292017936706543 +[2025-04-29 18:57:25,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 1.8292193412780762, cross_entropy: 1.8292193412780762 +[2025-04-29 18:57:25,594][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.277131199836731, cross_entropy: 1.277131199836731 +[2025-04-29 18:57:29,239][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 1.8848851919174194, cross_entropy: 1.8848851919174194 +[2025-04-29 18:57:29,602][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 2.2706570625305176, cross_entropy: 2.2706570625305176 +[2025-04-29 18:57:32,596][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.6658167839050293, cross_entropy: 2.6658167839050293 +[2025-04-29 18:57:32,952][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 2.2042062282562256, cross_entropy: 2.2042062282562256 +[2025-04-29 18:57:36,447][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 2.278265953063965, cross_entropy: 2.278265953063965 +[2025-04-29 18:57:36,806][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 2.0292744636535645, cross_entropy: 2.0292744636535645 +[2025-04-29 18:57:40,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 3.168489933013916, cross_entropy: 3.168489933013916 +[2025-04-29 18:57:40,804][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 2.161006450653076, cross_entropy: 2.161006450653076 +[2025-04-29 18:57:44,709][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 1.6997987031936646, cross_entropy: 1.6997987031936646 +[2025-04-29 18:57:45,066][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 1.6133975982666016, cross_entropy: 1.6133975982666016 +[2025-04-29 18:57:48,975][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.3504562377929688, cross_entropy: 2.3504562377929688 +[2025-04-29 18:57:49,333][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 0.8149372339248657, cross_entropy: 0.8149372339248657 +[2025-04-29 18:57:53,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 2.2412619590759277, cross_entropy: 2.2412619590759277 +[2025-04-29 18:57:53,639][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 0.8906632661819458, cross_entropy: 0.8906632661819458 +[2025-04-29 18:57:57,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 1.382845401763916, cross_entropy: 1.382845401763916 +[2025-04-29 18:57:57,821][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.5360355377197266, cross_entropy: 1.5360355377197266 +[2025-04-29 18:58:01,709][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.2965030670166016, cross_entropy: 2.2965030670166016 +[2025-04-29 18:58:02,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 3.020987033843994, cross_entropy: 3.020987033843994 +[2025-04-29 18:58:05,473][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.3506064414978027, cross_entropy: 1.3506064414978027 +[2025-04-29 18:58:05,909][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.521516799926758, cross_entropy: 2.521516799926758 +[2025-04-29 18:58:09,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 1.9404675960540771, cross_entropy: 1.9404675960540771 +[2025-04-29 18:58:10,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 2.373643398284912, cross_entropy: 2.373643398284912 +[2025-04-29 18:58:13,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 1.533402681350708, cross_entropy: 1.533402681350708 +[2025-04-29 18:58:14,667][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 1.5917249917984009, cross_entropy: 1.5917249917984009 +[2025-04-29 18:58:18,088][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 1.2412158250808716, cross_entropy: 1.2412158250808716 +[2025-04-29 18:58:18,879][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 1.2247424125671387, cross_entropy: 1.2247424125671387 +[2025-04-29 18:58:21,977][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 2.709740161895752, cross_entropy: 2.709740161895752 +[2025-04-29 18:58:23,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.8109909296035767, cross_entropy: 1.8109909296035767 +[2025-04-29 18:58:25,679][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 2.894164800643921, cross_entropy: 2.894164800643921 +[2025-04-29 18:58:27,161][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 1.0916410684585571, cross_entropy: 1.0916410684585571 +[2025-04-29 18:58:29,645][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.5463371276855469, cross_entropy: 1.5463371276855469 +[2025-04-29 18:58:31,588][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.4890563488006592, cross_entropy: 1.4890563488006592 +[2025-04-29 18:58:33,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 2.0394582748413086, cross_entropy: 2.0394582748413086 +[2025-04-29 18:58:35,052][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 1.5162631273269653, cross_entropy: 1.5162631273269653 +[2025-04-29 18:58:37,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 1.689150333404541, cross_entropy: 1.689150333404541 +[2025-04-29 18:58:38,825][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.1425749063491821, cross_entropy: 1.1425749063491821 +[2025-04-29 18:58:41,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 2.9057211875915527, cross_entropy: 2.9057211875915527 +[2025-04-29 18:58:42,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 1.862107753753662, cross_entropy: 1.862107753753662 +[2025-04-29 18:58:46,989][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.0885993242263794, cross_entropy: 1.0885993242263794 +[2025-04-29 18:58:47,524][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.403895616531372, cross_entropy: 1.403895616531372 +[2025-04-29 18:58:51,125][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 1.22967529296875, cross_entropy: 1.22967529296875 +[2025-04-29 18:58:51,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 1.7742362022399902, cross_entropy: 1.7742362022399902 +[2025-04-29 18:58:55,058][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 3.0761361122131348, cross_entropy: 3.0761361122131348 +[2025-04-29 18:58:55,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 1.1230318546295166, cross_entropy: 1.1230318546295166 +[2025-04-29 18:58:58,791][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 3.2111456394195557, cross_entropy: 3.2111456394195557 +[2025-04-29 18:58:59,737][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.4346529245376587, cross_entropy: 1.4346529245376587 +[2025-04-29 18:59:02,418][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 2.456717014312744, cross_entropy: 2.456717014312744 +[2025-04-29 18:59:04,000][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.644318103790283, cross_entropy: 2.644318103790283 +[2025-04-29 18:59:06,015][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.6445509195327759, cross_entropy: 1.6445509195327759 +[2025-04-29 18:59:07,651][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 1.9665777683258057, cross_entropy: 1.9665777683258057 +[2025-04-29 18:59:10,459][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 1.7724448442459106, cross_entropy: 1.7724448442459106 +[2025-04-29 18:59:11,225][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 1.2871050834655762, cross_entropy: 1.2871050834655762 +[2025-04-29 18:59:15,135][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 3.187925338745117, cross_entropy: 3.187925338745117 +[2025-04-29 18:59:15,501][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 2.8969345092773438, cross_entropy: 2.8969345092773438 +[2025-04-29 18:59:19,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.2689045667648315, cross_entropy: 1.2689045667648315 +[2025-04-29 18:59:20,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 3.2419981956481934, cross_entropy: 3.2419981956481934 +[2025-04-29 18:59:24,316][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 0.8878501653671265, cross_entropy: 0.8878501653671265 +[2025-04-29 18:59:24,667][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 2.9149155616760254, cross_entropy: 2.9149155616760254 +[2025-04-29 18:59:28,864][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 1.5711151361465454, cross_entropy: 1.5711151361465454 +[2025-04-29 18:59:29,219][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 3.0548758506774902, cross_entropy: 3.0548758506774902 +[2025-04-29 18:59:33,056][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 1.1718286275863647, cross_entropy: 1.1718286275863647 +[2025-04-29 18:59:33,420][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.364240050315857, cross_entropy: 1.364240050315857 +[2025-04-29 18:59:37,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.773255705833435, cross_entropy: 1.773255705833435 +[2025-04-29 18:59:37,593][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.837134599685669, cross_entropy: 2.837134599685669 +[2025-04-29 18:59:41,397][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 0.9848330020904541, cross_entropy: 0.9848330020904541 +[2025-04-29 18:59:41,720][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.8096742630004883, cross_entropy: 1.8096742630004883 +[2025-04-29 18:59:44,953][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 1.1964263916015625, cross_entropy: 1.1964263916015625 +[2025-04-29 18:59:45,314][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 2.9703259468078613, cross_entropy: 2.9703259468078613 +[2025-04-29 18:59:48,711][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 2.683537006378174, cross_entropy: 2.683537006378174 +[2025-04-29 18:59:49,070][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 2.467961072921753, cross_entropy: 2.467961072921753 +[2025-04-29 18:59:52,746][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 1.524562120437622, cross_entropy: 1.524562120437622 +[2025-04-29 18:59:53,066][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 2.3587489128112793, cross_entropy: 2.3587489128112793 +[2025-04-29 18:59:57,115][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.8647985458374023, cross_entropy: 2.8647985458374023 +[2025-04-29 18:59:57,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.9918041229248047, cross_entropy: 2.9918041229248047 +[2025-04-29 19:00:01,513][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.505910873413086, cross_entropy: 2.505910873413086 +[2025-04-29 19:00:01,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.3933706283569336, cross_entropy: 2.3933706283569336 +[2025-04-29 19:00:06,385][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 1.9661964178085327, cross_entropy: 1.9661964178085327 +[2025-04-29 19:00:06,708][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 3.1093435287475586, cross_entropy: 3.1093435287475586 +[2025-04-29 19:00:11,008][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 2.9166221618652344, cross_entropy: 2.9166221618652344 +[2025-04-29 19:00:11,366][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 2.9809927940368652, cross_entropy: 2.9809927940368652 +[2025-04-29 19:00:14,779][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 3.3566555976867676, cross_entropy: 3.3566555976867676 +[2025-04-29 19:00:15,142][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.8565807342529297, cross_entropy: 2.8565807342529297 +[2025-04-29 19:00:18,677][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 2.4223475456237793, cross_entropy: 2.4223475456237793 +[2025-04-29 19:00:18,997][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 2.012408971786499, cross_entropy: 2.012408971786499 +[2025-04-29 19:00:22,743][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.1800754070281982, cross_entropy: 1.1800754070281982 +[2025-04-29 19:00:23,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 3.0265026092529297, cross_entropy: 3.0265026092529297 +[2025-04-29 19:00:27,465][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 1.8792462348937988, cross_entropy: 1.8792462348937988 +[2025-04-29 19:00:27,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 3.0682616233825684, cross_entropy: 3.0682616233825684 +[2025-04-29 19:00:31,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 3.341427803039551, cross_entropy: 3.341427803039551 +[2025-04-29 19:00:31,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 1.843727946281433, cross_entropy: 1.843727946281433 +[2025-04-29 19:00:35,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 1.5795741081237793, cross_entropy: 1.5795741081237793 +[2025-04-29 19:00:36,150][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 0.9447396397590637, cross_entropy: 0.9447396397590637 +[2025-04-29 19:00:39,781][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 2.6157102584838867, cross_entropy: 2.6157102584838867 +[2025-04-29 19:00:40,106][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 3.235166549682617, cross_entropy: 3.235166549682617 +[2025-04-29 19:00:43,872][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.300673484802246, cross_entropy: 1.300673484802246 +[2025-04-29 19:00:44,230][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 2.6051149368286133, cross_entropy: 2.6051149368286133 +[2025-04-29 19:00:48,487][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.2805216312408447, cross_entropy: 2.2805216312408447 +[2025-04-29 19:00:48,810][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 2.890796661376953, cross_entropy: 2.890796661376953 +[2025-04-29 19:00:52,339][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.600675582885742, cross_entropy: 2.600675582885742 +[2025-04-29 19:00:52,696][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 1.9162936210632324, cross_entropy: 1.9162936210632324 +[2025-04-29 19:00:56,897][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 2.770742416381836, cross_entropy: 2.770742416381836 +[2025-04-29 19:00:57,257][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 2.904430389404297, cross_entropy: 2.904430389404297 +[2025-04-29 19:01:00,262][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 1.800257921218872, cross_entropy: 1.800257921218872 +[2025-04-29 19:01:00,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 2.710702896118164, cross_entropy: 2.710702896118164 +[2025-04-29 19:01:04,015][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 1.4636483192443848, cross_entropy: 1.4636483192443848 +[2025-04-29 19:01:04,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.872814178466797, cross_entropy: 2.872814178466797 +[2025-04-29 19:01:07,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.0791072845458984, cross_entropy: 2.0791072845458984 +[2025-04-29 19:01:07,896][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.5716456174850464, cross_entropy: 1.5716456174850464 +[2025-04-29 19:01:12,601][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.304868459701538, cross_entropy: 3.304868459701538 +[2025-04-29 19:01:12,956][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.553961753845215, cross_entropy: 2.553961753845215 +[2025-04-29 19:01:16,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 2.574002742767334, cross_entropy: 2.574002742767334 +[2025-04-29 19:01:17,002][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 2.10548734664917, cross_entropy: 2.10548734664917 +[2025-04-29 19:01:20,791][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.6234064102172852, cross_entropy: 1.6234064102172852 +[2025-04-29 19:01:21,151][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.7543706893920898, cross_entropy: 1.7543706893920898 +[2025-04-29 19:01:25,034][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 2.050731897354126, cross_entropy: 2.050731897354126 +[2025-04-29 19:01:25,355][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 2.9169182777404785, cross_entropy: 2.9169182777404785 +[2025-04-29 19:01:29,570][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.1442980766296387, cross_entropy: 2.1442980766296387 +[2025-04-29 19:01:29,894][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.8736343383789062, cross_entropy: 1.8736343383789062 +[2025-04-29 19:01:33,824][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 1.7616403102874756, cross_entropy: 1.7616403102874756 +[2025-04-29 19:01:34,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.1632308959960938, cross_entropy: 2.1632308959960938 +[2025-04-29 19:01:38,148][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 3.1061596870422363, cross_entropy: 3.1061596870422363 +[2025-04-29 19:01:38,505][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 1.9096252918243408, cross_entropy: 1.9096252918243408 +[2025-04-29 19:01:42,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 2.053560256958008, cross_entropy: 2.053560256958008 +[2025-04-29 19:01:42,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 1.3771568536758423, cross_entropy: 1.3771568536758423 +[2025-04-29 19:01:45,853][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 2.920121431350708, cross_entropy: 2.920121431350708 +[2025-04-29 19:01:46,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 3.0700442790985107, cross_entropy: 3.0700442790985107 +[2025-04-29 19:01:49,985][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 0.7231584787368774, cross_entropy: 0.7231584787368774 +[2025-04-29 19:01:50,345][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.5684144496917725, cross_entropy: 2.5684144496917725 +[2025-04-29 19:01:53,861][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 2.855240821838379, cross_entropy: 2.855240821838379 +[2025-04-29 19:01:54,220][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.8825345039367676, cross_entropy: 2.8825345039367676 +[2025-04-29 19:01:58,410][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 1.497689127922058, cross_entropy: 1.497689127922058 +[2025-04-29 19:01:58,732][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 2.515261650085449, cross_entropy: 2.515261650085449 +[2025-04-29 19:02:03,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 2.2715938091278076, cross_entropy: 2.2715938091278076 +[2025-04-29 19:02:03,799][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.9224860668182373, cross_entropy: 1.9224860668182373 +[2025-04-29 19:02:07,947][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.762765884399414, cross_entropy: 1.762765884399414 +[2025-04-29 19:02:08,304][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 1.2549421787261963, cross_entropy: 1.2549421787261963 +[2025-04-29 19:02:11,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 1.2090412378311157, cross_entropy: 1.2090412378311157 +[2025-04-29 19:02:12,152][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.9735074043273926, cross_entropy: 2.9735074043273926 +[2025-04-29 19:02:15,812][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 1.4985942840576172, cross_entropy: 1.4985942840576172 +[2025-04-29 19:02:16,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 3.13662052154541, cross_entropy: 3.13662052154541 +[2025-04-29 19:02:20,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 1.3426882028579712, cross_entropy: 1.3426882028579712 +[2025-04-29 19:02:21,239][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 1.2766419649124146, cross_entropy: 1.2766419649124146 +[2025-04-29 19:02:24,744][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 1.14109206199646, cross_entropy: 1.14109206199646 +[2025-04-29 19:02:25,114][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.5063602924346924, cross_entropy: 1.5063602924346924 +[2025-04-29 19:02:28,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 2.204336404800415, cross_entropy: 2.204336404800415 +[2025-04-29 19:02:29,016][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 0.8980185389518738, cross_entropy: 0.8980185389518738 +[2025-04-29 19:02:32,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.5828933715820312, cross_entropy: 1.5828933715820312 +[2025-04-29 19:02:33,170][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.3599460124969482, cross_entropy: 1.3599460124969482 +[2025-04-29 19:02:37,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.3617949485778809, cross_entropy: 1.3617949485778809 +[2025-04-29 19:02:38,218][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 1.4198286533355713, cross_entropy: 1.4198286533355713 +[2025-04-29 19:02:41,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 3.221972703933716, cross_entropy: 3.221972703933716 +[2025-04-29 19:02:42,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 2.599626064300537, cross_entropy: 2.599626064300537 +[2025-04-29 19:02:45,629][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.9255590438842773, cross_entropy: 2.9255590438842773 +[2025-04-29 19:02:45,949][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 1.6094878911972046, cross_entropy: 1.6094878911972046 +[2025-04-29 19:02:49,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.13391375541687, cross_entropy: 3.13391375541687 +[2025-04-29 19:02:50,058][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.353891611099243, cross_entropy: 2.353891611099243 +[2025-04-29 19:02:53,821][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 2.8208389282226562, cross_entropy: 2.8208389282226562 +[2025-04-29 19:02:54,184][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 3.107724189758301, cross_entropy: 3.107724189758301 +[2025-04-29 19:02:58,328][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 3.1329262256622314, cross_entropy: 3.1329262256622314 +[2025-04-29 19:02:58,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 3.165600538253784, cross_entropy: 3.165600538253784 +[2025-04-29 19:03:02,425][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 3.016887664794922, cross_entropy: 3.016887664794922 +[2025-04-29 19:03:02,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.6623404026031494, cross_entropy: 2.6623404026031494 +[2025-04-29 19:03:06,601][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.0088837146759033, cross_entropy: 1.0088837146759033 +[2025-04-29 19:03:06,964][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.7711403369903564, cross_entropy: 2.7711403369903564 +[2025-04-29 19:03:11,251][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.1593143939971924, cross_entropy: 2.1593143939971924 +[2025-04-29 19:03:11,598][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.4098703861236572, cross_entropy: 1.4098703861236572 +[2025-04-29 19:03:15,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.2785362005233765, cross_entropy: 1.2785362005233765 +[2025-04-29 19:03:15,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 2.630086660385132, cross_entropy: 2.630086660385132 +[2025-04-29 19:03:19,274][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 2.869894504547119, cross_entropy: 2.869894504547119 +[2025-04-29 19:03:19,596][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.4366790056228638, cross_entropy: 1.4366790056228638 +[2025-04-29 19:03:23,014][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 2.060770273208618, cross_entropy: 2.060770273208618 +[2025-04-29 19:03:23,361][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 3.0881333351135254, cross_entropy: 3.0881333351135254 +[2025-04-29 19:03:27,280][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 1.2325294017791748, cross_entropy: 1.2325294017791748 +[2025-04-29 19:03:27,645][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 1.392897129058838, cross_entropy: 1.392897129058838 +[2025-04-29 19:03:30,727][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 1.6802235841751099, cross_entropy: 1.6802235841751099 +[2025-04-29 19:03:31,083][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.3271949291229248, cross_entropy: 1.3271949291229248 +[2025-04-29 19:03:34,753][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 2.3409440517425537, cross_entropy: 2.3409440517425537 +[2025-04-29 19:03:35,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 2.961094379425049, cross_entropy: 2.961094379425049 +[2025-04-29 19:03:39,847][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 3.106187343597412, cross_entropy: 3.106187343597412 +[2025-04-29 19:03:40,206][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.652174949645996, cross_entropy: 1.652174949645996 +[2025-04-29 19:03:44,147][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 0.9351195096969604, cross_entropy: 0.9351195096969604 +[2025-04-29 19:03:44,503][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 1.7496815919876099, cross_entropy: 1.7496815919876099 +[2025-04-29 19:03:48,169][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.408279299736023, cross_entropy: 1.408279299736023 +[2025-04-29 19:03:48,522][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.7870491743087769, cross_entropy: 1.7870491743087769 +[2025-04-29 19:03:52,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.1531598567962646, cross_entropy: 1.1531598567962646 +[2025-04-29 19:03:52,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 1.2254245281219482, cross_entropy: 1.2254245281219482 +[2025-04-29 19:03:57,575][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 1.5343340635299683, cross_entropy: 1.5343340635299683 +[2025-04-29 19:03:57,935][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 2.966071367263794, cross_entropy: 2.966071367263794 +[2025-04-29 19:04:02,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.0875256061553955, cross_entropy: 3.0875256061553955 +[2025-04-29 19:04:02,631][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 2.961060047149658, cross_entropy: 2.961060047149658 +[2025-04-29 19:04:06,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 3.2479093074798584, cross_entropy: 3.2479093074798584 +[2025-04-29 19:04:06,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 1.5766080617904663, cross_entropy: 1.5766080617904663 +[2025-04-29 19:04:10,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.6063730716705322, cross_entropy: 1.6063730716705322 +[2025-04-29 19:04:11,038][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.3605493307113647, cross_entropy: 1.3605493307113647 +[2025-04-29 19:04:14,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.1832427978515625, cross_entropy: 1.1832427978515625 +[2025-04-29 19:04:14,923][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 2.8638362884521484, cross_entropy: 2.8638362884521484 +[2025-04-29 19:04:18,284][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 1.6768931150436401, cross_entropy: 1.6768931150436401 +[2025-04-29 19:04:18,648][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.3077894449234009, cross_entropy: 1.3077894449234009 +[2025-04-29 19:04:21,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 3.0118021965026855, cross_entropy: 3.0118021965026855 +[2025-04-29 19:04:22,130][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.9619452953338623, cross_entropy: 1.9619452953338623 +[2025-04-29 19:04:25,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.2595560550689697, cross_entropy: 1.2595560550689697 +[2025-04-29 19:04:26,140][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 2.1122658252716064, cross_entropy: 2.1122658252716064 +[2025-04-29 19:04:29,420][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.6255879402160645, cross_entropy: 2.6255879402160645 +[2025-04-29 19:04:29,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 2.6651153564453125, cross_entropy: 2.6651153564453125 +[2025-04-29 19:04:34,454][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 2.361893892288208, cross_entropy: 2.361893892288208 +[2025-04-29 19:04:34,814][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 1.296254277229309, cross_entropy: 1.296254277229309 +[2025-04-29 19:04:38,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.8782596588134766, cross_entropy: 2.8782596588134766 +[2025-04-29 19:04:39,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 2.955533027648926, cross_entropy: 2.955533027648926 +[2025-04-29 19:04:42,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.1788101196289062, cross_entropy: 1.1788101196289062 +[2025-04-29 19:04:42,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.4562923908233643, cross_entropy: 1.4562923908233643 +[2025-04-29 19:04:46,455][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 1.8723714351654053, cross_entropy: 1.8723714351654053 +[2025-04-29 19:04:47,189][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.2765713930130005, cross_entropy: 1.2765713930130005 +[2025-04-29 19:04:51,163][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 0.8540824055671692, cross_entropy: 0.8540824055671692 +[2025-04-29 19:04:51,559][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 1.9150819778442383, cross_entropy: 1.9150819778442383 +[2025-04-29 19:04:54,756][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 3.0719618797302246, cross_entropy: 3.0719618797302246 +[2025-04-29 19:04:55,204][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 1.40272855758667, cross_entropy: 1.40272855758667 +[2025-04-29 19:04:59,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 2.0316643714904785, cross_entropy: 2.0316643714904785 +[2025-04-29 19:04:59,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.217589855194092, cross_entropy: 2.217589855194092 +[2025-04-29 19:05:03,670][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.6933045387268066, cross_entropy: 2.6933045387268066 +[2025-04-29 19:05:04,024][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 3.1317625045776367, cross_entropy: 3.1317625045776367 +[2025-04-29 19:05:07,067][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 1.4883395433425903, cross_entropy: 1.4883395433425903 +[2025-04-29 19:05:07,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 2.018050193786621, cross_entropy: 2.018050193786621 +[2025-04-29 19:05:10,486][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 2.260131359100342, cross_entropy: 2.260131359100342 +[2025-04-29 19:05:11,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 3.1548986434936523, cross_entropy: 3.1548986434936523 +[2025-04-29 19:05:14,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 1.1903975009918213, cross_entropy: 1.1903975009918213 +[2025-04-29 19:05:15,340][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 3.045344352722168, cross_entropy: 3.045344352722168 +[2025-04-29 19:05:19,733][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.2101845741271973, cross_entropy: 3.2101845741271973 +[2025-04-29 19:05:20,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 1.4659197330474854, cross_entropy: 1.4659197330474854 +[2025-04-29 19:05:24,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 2.1798439025878906, cross_entropy: 2.1798439025878906 +[2025-04-29 19:05:24,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 1.9105195999145508, cross_entropy: 1.9105195999145508 +[2025-04-29 19:05:27,794][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.2372280359268188, cross_entropy: 1.2372280359268188 +[2025-04-29 19:05:28,331][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 0.9068887233734131, cross_entropy: 0.9068887233734131 +[2025-04-29 19:05:31,501][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.3787190914154053, cross_entropy: 1.3787190914154053 +[2025-04-29 19:05:32,017][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 1.9343613386154175, cross_entropy: 1.9343613386154175 +[2025-04-29 19:05:35,255][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 1.1224225759506226, cross_entropy: 1.1224225759506226 +[2025-04-29 19:05:36,320][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.1730518341064453, cross_entropy: 1.1730518341064453 +[2025-04-29 19:05:39,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.7650729417800903, cross_entropy: 1.7650729417800903 +[2025-04-29 19:05:40,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.996894121170044, cross_entropy: 2.996894121170044 +[2025-04-29 19:05:43,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 2.63703989982605, cross_entropy: 2.63703989982605 +[2025-04-29 19:05:44,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 2.2752275466918945, cross_entropy: 2.2752275466918945 +[2025-04-29 19:05:48,069][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 2.9593505859375, cross_entropy: 2.9593505859375 +[2025-04-29 19:05:48,391][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 2.0929787158966064, cross_entropy: 2.0929787158966064 +[2025-04-29 19:05:51,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 3.279215097427368, cross_entropy: 3.279215097427368 +[2025-04-29 19:09:08,880][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.0432350635528564, cross_entropy: 2.0432350635528564 +[2025-04-29 19:09:08,881][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.2964173555374146, cross_entropy: 1.2964173555374146 +[2025-04-29 19:09:09,125][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 19:09:09,317][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch5.pth. +[2025-04-29 19:09:09,541][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 19:09:15,385][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 1.9913870096206665, cross_entropy: 1.9913870096206665 +[2025-04-29 19:09:15,743][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 2.8099968433380127, cross_entropy: 2.8099968433380127 +[2025-04-29 19:09:18,972][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 1.445587396621704, cross_entropy: 1.445587396621704 +[2025-04-29 19:09:19,295][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 1.6565840244293213, cross_entropy: 1.6565840244293213 +[2025-04-29 19:09:22,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.1824703216552734, cross_entropy: 2.1824703216552734 +[2025-04-29 19:09:23,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 1.1004996299743652, cross_entropy: 1.1004996299743652 +[2025-04-29 19:09:27,094][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 1.4661314487457275, cross_entropy: 1.4661314487457275 +[2025-04-29 19:09:27,452][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 2.9208531379699707, cross_entropy: 2.9208531379699707 +[2025-04-29 19:09:31,413][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 2.804715633392334, cross_entropy: 2.804715633392334 +[2025-04-29 19:09:31,940][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 1.9444000720977783, cross_entropy: 1.9444000720977783 +[2025-04-29 19:09:35,933][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.7398056983947754, cross_entropy: 2.7398056983947754 +[2025-04-29 19:09:36,451][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 0.8998712301254272, cross_entropy: 0.8998712301254272 +[2025-04-29 19:09:39,663][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 1.439982295036316, cross_entropy: 1.439982295036316 +[2025-04-29 19:09:40,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 0.99946528673172, cross_entropy: 0.99946528673172 +[2025-04-29 19:09:43,933][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 1.256949543952942, cross_entropy: 1.256949543952942 +[2025-04-29 19:09:45,168][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 0.8922407031059265, cross_entropy: 0.8922407031059265 +[2025-04-29 19:09:47,729][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.1600931882858276, cross_entropy: 1.1600931882858276 +[2025-04-29 19:09:49,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 2.788773775100708, cross_entropy: 2.788773775100708 +[2025-04-29 19:09:51,579][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.229419231414795, cross_entropy: 1.229419231414795 +[2025-04-29 19:09:53,926][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 1.6671581268310547, cross_entropy: 1.6671581268310547 +[2025-04-29 19:09:55,703][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 0.9589422345161438, cross_entropy: 0.9589422345161438 +[2025-04-29 19:09:58,216][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 3.002084732055664, cross_entropy: 3.002084732055664 +[2025-04-29 19:09:59,560][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 2.454042911529541, cross_entropy: 2.454042911529541 +[2025-04-29 19:10:03,112][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 1.044494390487671, cross_entropy: 1.044494390487671 +[2025-04-29 19:10:03,590][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 0.7269744873046875, cross_entropy: 0.7269744873046875 +[2025-04-29 19:10:08,218][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 1.2400076389312744, cross_entropy: 1.2400076389312744 +[2025-04-29 19:10:08,544][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 1.106083631515503, cross_entropy: 1.106083631515503 +[2025-04-29 19:10:12,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 1.2494274377822876, cross_entropy: 1.2494274377822876 +[2025-04-29 19:10:12,507][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 2.339108943939209, cross_entropy: 2.339108943939209 +[2025-04-29 19:10:15,957][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 1.1981399059295654, cross_entropy: 1.1981399059295654 +[2025-04-29 19:10:16,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.419682502746582, cross_entropy: 1.419682502746582 +[2025-04-29 19:10:19,908][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.768156051635742, cross_entropy: 2.768156051635742 +[2025-04-29 19:10:21,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 0.9548099040985107, cross_entropy: 0.9548099040985107 +[2025-04-29 19:10:24,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 1.9478472471237183, cross_entropy: 1.9478472471237183 +[2025-04-29 19:10:26,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 3.2443225383758545, cross_entropy: 3.2443225383758545 +[2025-04-29 19:10:29,516][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 0.9666844010353088, cross_entropy: 0.9666844010353088 +[2025-04-29 19:10:30,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.1262726783752441, cross_entropy: 1.1262726783752441 +[2025-04-29 19:10:33,462][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 1.0427814722061157, cross_entropy: 1.0427814722061157 +[2025-04-29 19:10:34,208][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.7111549377441406, cross_entropy: 2.7111549377441406 +[2025-04-29 19:10:37,219][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 2.549293041229248, cross_entropy: 2.549293041229248 +[2025-04-29 19:10:39,490][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 1.0810058116912842, cross_entropy: 1.0810058116912842 +[2025-04-29 19:10:42,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 1.1485919952392578, cross_entropy: 1.1485919952392578 +[2025-04-29 19:10:43,485][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.8955388069152832, cross_entropy: 1.8955388069152832 +[2025-04-29 19:10:46,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 1.241437315940857, cross_entropy: 1.241437315940857 +[2025-04-29 19:10:47,567][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 3.0465469360351562, cross_entropy: 3.0465469360351562 +[2025-04-29 19:10:50,039][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 1.1706819534301758, cross_entropy: 1.1706819534301758 +[2025-04-29 19:10:52,284][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.716853618621826, cross_entropy: 2.716853618621826 +[2025-04-29 19:10:53,708][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 0.9958876967430115, cross_entropy: 0.9958876967430115 +[2025-04-29 19:10:55,876][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.3681025505065918, cross_entropy: 1.3681025505065918 +[2025-04-29 19:10:57,573][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 2.319641590118408, cross_entropy: 2.319641590118408 +[2025-04-29 19:10:59,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 2.1032233238220215, cross_entropy: 2.1032233238220215 +[2025-04-29 19:11:01,293][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 1.6412229537963867, cross_entropy: 1.6412229537963867 +[2025-04-29 19:11:04,287][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.264838695526123, cross_entropy: 2.264838695526123 +[2025-04-29 19:11:06,161][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 2.510650157928467, cross_entropy: 2.510650157928467 +[2025-04-29 19:11:07,940][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 0.9125300645828247, cross_entropy: 0.9125300645828247 +[2025-04-29 19:11:10,652][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 1.9183356761932373, cross_entropy: 1.9183356761932373 +[2025-04-29 19:11:13,893][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 1.3823649883270264, cross_entropy: 1.3823649883270264 +[2025-04-29 19:11:15,386][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.4639478921890259, cross_entropy: 1.4639478921890259 +[2025-04-29 19:11:18,168][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 1.0519933700561523, cross_entropy: 1.0519933700561523 +[2025-04-29 19:11:19,572][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.18721342086792, cross_entropy: 2.18721342086792 +[2025-04-29 19:11:22,124][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 2.3257923126220703, cross_entropy: 2.3257923126220703 +[2025-04-29 19:11:23,737][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.6321842670440674, cross_entropy: 2.6321842670440674 +[2025-04-29 19:11:26,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.6522555351257324, cross_entropy: 1.6522555351257324 +[2025-04-29 19:11:28,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.763016700744629, cross_entropy: 1.763016700744629 +[2025-04-29 19:11:31,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.8469905853271484, cross_entropy: 2.8469905853271484 +[2025-04-29 19:11:33,253][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 3.213376045227051, cross_entropy: 3.213376045227051 +[2025-04-29 19:11:36,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 1.8169403076171875, cross_entropy: 1.8169403076171875 +[2025-04-29 19:11:37,743][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.4907629489898682, cross_entropy: 1.4907629489898682 +[2025-04-29 19:11:39,834][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 2.6855099201202393, cross_entropy: 2.6855099201202393 +[2025-04-29 19:11:42,634][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.2736825942993164, cross_entropy: 1.2736825942993164 +[2025-04-29 19:11:44,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 3.0805890560150146, cross_entropy: 3.0805890560150146 +[2025-04-29 19:11:47,498][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 2.0877685546875, cross_entropy: 2.0877685546875 +[2025-04-29 19:11:48,434][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 2.974954128265381, cross_entropy: 2.974954128265381 +[2025-04-29 19:11:51,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.1687380075454712, cross_entropy: 1.1687380075454712 +[2025-04-29 19:11:52,272][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 1.3548250198364258, cross_entropy: 1.3548250198364258 +[2025-04-29 19:11:55,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 2.4591002464294434, cross_entropy: 2.4591002464294434 +[2025-04-29 19:11:56,573][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 3.2694411277770996, cross_entropy: 3.2694411277770996 +[2025-04-29 19:11:59,777][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.7595338821411133, cross_entropy: 2.7595338821411133 +[2025-04-29 19:12:00,858][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 0.9403465986251831, cross_entropy: 0.9403465986251831 +[2025-04-29 19:12:04,163][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 1.429049015045166, cross_entropy: 1.429049015045166 +[2025-04-29 19:12:05,415][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.5949318408966064, cross_entropy: 1.5949318408966064 +[2025-04-29 19:12:07,721][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 1.093345046043396, cross_entropy: 1.093345046043396 +[2025-04-29 19:12:09,253][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 1.7706215381622314, cross_entropy: 1.7706215381622314 +[2025-04-29 19:12:11,499][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.2969964742660522, cross_entropy: 1.2969964742660522 +[2025-04-29 19:12:13,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.2967135906219482, cross_entropy: 1.2967135906219482 +[2025-04-29 19:12:16,824][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 2.9747300148010254, cross_entropy: 2.9747300148010254 +[2025-04-29 19:12:18,655][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 2.6602585315704346, cross_entropy: 2.6602585315704346 +[2025-04-29 19:12:20,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.5096220970153809, cross_entropy: 1.5096220970153809 +[2025-04-29 19:12:22,961][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 0.9481878280639648, cross_entropy: 0.9481878280639648 +[2025-04-29 19:12:24,281][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.1215698719024658, cross_entropy: 1.1215698719024658 +[2025-04-29 19:12:27,113][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 1.1501234769821167, cross_entropy: 1.1501234769821167 +[2025-04-29 19:12:27,912][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.9346511363983154, cross_entropy: 1.9346511363983154 +[2025-04-29 19:12:31,232][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 2.681544303894043, cross_entropy: 2.681544303894043 +[2025-04-29 19:12:31,731][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.1262338161468506, cross_entropy: 2.1262338161468506 +[2025-04-29 19:12:35,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 1.2054753303527832, cross_entropy: 1.2054753303527832 +[2025-04-29 19:12:35,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 1.6796756982803345, cross_entropy: 1.6796756982803345 +[2025-04-29 19:12:39,548][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 1.3463530540466309, cross_entropy: 1.3463530540466309 +[2025-04-29 19:12:39,966][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 2.09375, cross_entropy: 2.09375 +[2025-04-29 19:12:43,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 3.235557794570923, cross_entropy: 3.235557794570923 +[2025-04-29 19:12:43,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.5777995586395264, cross_entropy: 1.5777995586395264 +[2025-04-29 19:12:48,336][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.256535291671753, cross_entropy: 1.256535291671753 +[2025-04-29 19:12:48,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 3.0273842811584473, cross_entropy: 3.0273842811584473 +[2025-04-29 19:12:52,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 2.963451385498047, cross_entropy: 2.963451385498047 +[2025-04-29 19:12:53,349][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 1.3601058721542358, cross_entropy: 1.3601058721542358 +[2025-04-29 19:12:57,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.6375528573989868, cross_entropy: 1.6375528573989868 +[2025-04-29 19:12:57,414][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.1434504985809326, cross_entropy: 2.1434504985809326 +[2025-04-29 19:13:00,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.1178765296936035, cross_entropy: 2.1178765296936035 +[2025-04-29 19:13:00,953][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.269660234451294, cross_entropy: 1.269660234451294 +[2025-04-29 19:13:04,895][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.2864502668380737, cross_entropy: 1.2864502668380737 +[2025-04-29 19:13:05,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 2.3077101707458496, cross_entropy: 2.3077101707458496 +[2025-04-29 19:13:08,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 0.9298474788665771, cross_entropy: 0.9298474788665771 +[2025-04-29 19:13:09,344][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.135573148727417, cross_entropy: 1.135573148727417 +[2025-04-29 19:13:12,431][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 1.4370112419128418, cross_entropy: 1.4370112419128418 +[2025-04-29 19:13:13,762][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 3.073136329650879, cross_entropy: 3.073136329650879 +[2025-04-29 19:13:16,557][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 1.7056890726089478, cross_entropy: 1.7056890726089478 +[2025-04-29 19:13:17,794][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 2.4504809379577637, cross_entropy: 2.4504809379577637 +[2025-04-29 19:13:20,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.064391851425171, cross_entropy: 1.064391851425171 +[2025-04-29 19:13:22,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 3.1455817222595215, cross_entropy: 3.1455817222595215 +[2025-04-29 19:13:25,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.169506072998047, cross_entropy: 3.169506072998047 +[2025-04-29 19:13:26,013][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 2.793914794921875, cross_entropy: 2.793914794921875 +[2025-04-29 19:13:29,538][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.368394136428833, cross_entropy: 2.368394136428833 +[2025-04-29 19:13:30,541][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.0937846899032593, cross_entropy: 1.0937846899032593 +[2025-04-29 19:13:33,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.5172230005264282, cross_entropy: 1.5172230005264282 +[2025-04-29 19:13:34,653][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 2.648773670196533, cross_entropy: 2.648773670196533 +[2025-04-29 19:13:38,270][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 2.236508369445801, cross_entropy: 2.236508369445801 +[2025-04-29 19:13:38,759][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.3297371864318848, cross_entropy: 2.3297371864318848 +[2025-04-29 19:13:42,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 2.10868239402771, cross_entropy: 2.10868239402771 +[2025-04-29 19:13:42,754][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 2.859889507293701, cross_entropy: 2.859889507293701 +[2025-04-29 19:13:46,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 1.1482839584350586, cross_entropy: 1.1482839584350586 +[2025-04-29 19:13:47,087][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 1.1542279720306396, cross_entropy: 1.1542279720306396 +[2025-04-29 19:13:50,305][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.6093807220458984, cross_entropy: 2.6093807220458984 +[2025-04-29 19:13:51,407][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 2.1211981773376465, cross_entropy: 2.1211981773376465 +[2025-04-29 19:13:55,245][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 3.039830446243286, cross_entropy: 3.039830446243286 +[2025-04-29 19:13:55,677][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 1.4976139068603516, cross_entropy: 1.4976139068603516 +[2025-04-29 19:13:59,396][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 1.0722392797470093, cross_entropy: 1.0722392797470093 +[2025-04-29 19:13:59,770][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 1.5672919750213623, cross_entropy: 1.5672919750213623 +[2025-04-29 19:14:03,457][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 1.5484479665756226, cross_entropy: 1.5484479665756226 +[2025-04-29 19:14:03,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.4206618070602417, cross_entropy: 1.4206618070602417 +[2025-04-29 19:14:07,126][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.1420750617980957, cross_entropy: 1.1420750617980957 +[2025-04-29 19:14:07,892][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 1.8278794288635254, cross_entropy: 1.8278794288635254 +[2025-04-29 19:14:11,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.5738445520401, cross_entropy: 1.5738445520401 +[2025-04-29 19:14:11,949][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.5682790279388428, cross_entropy: 1.5682790279388428 +[2025-04-29 19:14:15,448][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 2.0285897254943848, cross_entropy: 2.0285897254943848 +[2025-04-29 19:14:15,853][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 1.6496481895446777, cross_entropy: 1.6496481895446777 +[2025-04-29 19:14:19,366][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.378042459487915, cross_entropy: 1.378042459487915 +[2025-04-29 19:14:19,826][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.1006009578704834, cross_entropy: 1.1006009578704834 +[2025-04-29 19:14:23,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 0.8272387385368347, cross_entropy: 0.8272387385368347 +[2025-04-29 19:14:24,148][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 0.8325197696685791, cross_entropy: 0.8325197696685791 +[2025-04-29 19:14:28,182][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 1.3924963474273682, cross_entropy: 1.3924963474273682 +[2025-04-29 19:14:28,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 1.9115664958953857, cross_entropy: 1.9115664958953857 +[2025-04-29 19:14:31,802][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.9286141395568848, cross_entropy: 2.9286141395568848 +[2025-04-29 19:14:32,123][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 1.1774778366088867, cross_entropy: 1.1774778366088867 +[2025-04-29 19:14:35,859][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 0.9727236032485962, cross_entropy: 0.9727236032485962 +[2025-04-29 19:14:36,218][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 2.7967100143432617, cross_entropy: 2.7967100143432617 +[2025-04-29 19:14:39,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 2.553022623062134, cross_entropy: 2.553022623062134 +[2025-04-29 19:14:39,774][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 3.164567708969116, cross_entropy: 3.164567708969116 +[2025-04-29 19:14:43,127][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 1.1211304664611816, cross_entropy: 1.1211304664611816 +[2025-04-29 19:14:43,636][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.550419807434082, cross_entropy: 2.550419807434082 +[2025-04-29 19:14:46,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.1263610124588013, cross_entropy: 1.1263610124588013 +[2025-04-29 19:14:47,485][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.8961066007614136, cross_entropy: 1.8961066007614136 +[2025-04-29 19:14:50,747][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 1.0992968082427979, cross_entropy: 1.0992968082427979 +[2025-04-29 19:14:52,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 2.229107618331909, cross_entropy: 2.229107618331909 +[2025-04-29 19:14:54,497][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 2.119842529296875, cross_entropy: 2.119842529296875 +[2025-04-29 19:14:56,381][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 1.2263479232788086, cross_entropy: 1.2263479232788086 +[2025-04-29 19:14:58,579][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 1.1542564630508423, cross_entropy: 1.1542564630508423 +[2025-04-29 19:15:00,283][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.8295469284057617, cross_entropy: 2.8295469284057617 +[2025-04-29 19:15:02,863][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 1.4869238138198853, cross_entropy: 1.4869238138198853 +[2025-04-29 19:15:04,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 2.1393051147460938, cross_entropy: 2.1393051147460938 +[2025-04-29 19:15:06,631][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 1.3522605895996094, cross_entropy: 1.3522605895996094 +[2025-04-29 19:15:08,935][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 1.3216739892959595, cross_entropy: 1.3216739892959595 +[2025-04-29 19:15:11,280][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 3.087841510772705, cross_entropy: 3.087841510772705 +[2025-04-29 19:15:14,256][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 3.296804428100586, cross_entropy: 3.296804428100586 +[2025-04-29 19:15:15,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 1.0190693140029907, cross_entropy: 1.0190693140029907 +[2025-04-29 19:15:18,824][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 3.0948877334594727, cross_entropy: 3.0948877334594727 +[2025-04-29 19:15:19,527][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 2.636704683303833, cross_entropy: 2.636704683303833 +[2025-04-29 19:15:22,916][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.304762601852417, cross_entropy: 1.304762601852417 +[2025-04-29 19:15:23,273][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 0.9614480137825012, cross_entropy: 0.9614480137825012 +[2025-04-29 19:15:26,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 2.935512065887451, cross_entropy: 2.935512065887451 +[2025-04-29 19:15:27,015][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.6051275730133057, cross_entropy: 2.6051275730133057 +[2025-04-29 19:15:30,320][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.9494853019714355, cross_entropy: 1.9494853019714355 +[2025-04-29 19:15:31,391][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 2.9740686416625977, cross_entropy: 2.9740686416625977 +[2025-04-29 19:15:34,851][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 2.0950701236724854, cross_entropy: 2.0950701236724854 +[2025-04-29 19:15:35,228][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 2.8890953063964844, cross_entropy: 2.8890953063964844 +[2025-04-29 19:15:39,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.593736410140991, cross_entropy: 2.593736410140991 +[2025-04-29 19:15:39,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 2.3223400115966797, cross_entropy: 2.3223400115966797 +[2025-04-29 19:15:42,620][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.7218444347381592, cross_entropy: 1.7218444347381592 +[2025-04-29 19:15:43,257][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 1.3412694931030273, cross_entropy: 1.3412694931030273 +[2025-04-29 19:15:46,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 0.9937231540679932, cross_entropy: 0.9937231540679932 +[2025-04-29 19:15:47,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.554593563079834, cross_entropy: 1.554593563079834 +[2025-04-29 19:15:50,507][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 1.3698058128356934, cross_entropy: 1.3698058128356934 +[2025-04-29 19:15:51,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 1.0991582870483398, cross_entropy: 1.0991582870483398 +[2025-04-29 19:15:54,277][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.8641884326934814, cross_entropy: 2.8641884326934814 +[2025-04-29 19:15:55,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 1.6746227741241455, cross_entropy: 1.6746227741241455 +[2025-04-29 19:15:58,652][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 2.0206921100616455, cross_entropy: 2.0206921100616455 +[2025-04-29 19:15:59,693][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 2.9608864784240723, cross_entropy: 2.9608864784240723 +[2025-04-29 19:16:02,732][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.05241060256958, cross_entropy: 3.05241060256958 +[2025-04-29 19:16:03,665][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 2.247523784637451, cross_entropy: 2.247523784637451 +[2025-04-29 19:16:06,869][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.0098419189453125, cross_entropy: 2.0098419189453125 +[2025-04-29 19:16:07,635][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.908894419670105, cross_entropy: 1.908894419670105 +[2025-04-29 19:16:10,864][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.3378772735595703, cross_entropy: 1.3378772735595703 +[2025-04-29 19:16:11,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 1.027310848236084, cross_entropy: 1.027310848236084 +[2025-04-29 19:16:15,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 1.4625396728515625, cross_entropy: 1.4625396728515625 +[2025-04-29 19:16:15,552][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 2.4181220531463623, cross_entropy: 2.4181220531463623 +[2025-04-29 19:16:19,663][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 3.0067195892333984, cross_entropy: 3.0067195892333984 +[2025-04-29 19:16:20,022][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 1.1961324214935303, cross_entropy: 1.1961324214935303 +[2025-04-29 19:16:22,967][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.67466139793396, cross_entropy: 1.67466139793396 +[2025-04-29 19:16:23,865][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 2.0346412658691406, cross_entropy: 2.0346412658691406 +[2025-04-29 19:16:27,680][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 2.830772876739502, cross_entropy: 2.830772876739502 +[2025-04-29 19:16:28,213][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 2.9099278450012207, cross_entropy: 2.9099278450012207 +[2025-04-29 19:16:31,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.3471671342849731, cross_entropy: 1.3471671342849731 +[2025-04-29 19:16:33,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.1371209621429443, cross_entropy: 1.1371209621429443 +[2025-04-29 19:16:35,760][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 0.853118360042572, cross_entropy: 0.853118360042572 +[2025-04-29 19:16:37,650][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.2724738121032715, cross_entropy: 2.2724738121032715 +[2025-04-29 19:16:39,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 2.8966050148010254, cross_entropy: 2.8966050148010254 +[2025-04-29 19:16:41,582][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.406813144683838, cross_entropy: 2.406813144683838 +[2025-04-29 19:16:44,287][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.7327170372009277, cross_entropy: 2.7327170372009277 +[2025-04-29 19:16:45,641][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 1.4630045890808105, cross_entropy: 1.4630045890808105 +[2025-04-29 19:16:47,970][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 1.7455675601959229, cross_entropy: 1.7455675601959229 +[2025-04-29 19:16:49,603][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.1105167865753174, cross_entropy: 2.1105167865753174 +[2025-04-29 19:16:52,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 2.3576102256774902, cross_entropy: 2.3576102256774902 +[2025-04-29 19:16:53,209][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/iteration2000.pth. +[2025-04-29 19:16:53,620][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.3372145891189575, cross_entropy: 1.3372145891189575 +[2025-04-29 19:16:56,921][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.789276599884033, cross_entropy: 2.789276599884033 +[2025-04-29 19:16:57,450][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 1.4187970161437988, cross_entropy: 1.4187970161437988 +[2025-04-29 19:17:01,351][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 2.959500789642334, cross_entropy: 2.959500789642334 +[2025-04-29 19:17:01,730][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 0.9744551777839661, cross_entropy: 0.9744551777839661 +[2025-04-29 19:17:05,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 1.201997995376587, cross_entropy: 1.201997995376587 +[2025-04-29 19:17:06,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 0.9673366546630859, cross_entropy: 0.9673366546630859 +[2025-04-29 19:17:11,133][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.4601972103118896, cross_entropy: 2.4601972103118896 +[2025-04-29 19:17:11,492][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.6694737672805786, cross_entropy: 1.6694737672805786 +[2025-04-29 19:17:15,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 2.714982032775879, cross_entropy: 2.714982032775879 +[2025-04-29 19:17:15,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 2.9038538932800293, cross_entropy: 2.9038538932800293 +[2025-04-29 19:17:19,255][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.2982735633850098, cross_entropy: 1.2982735633850098 +[2025-04-29 19:17:19,749][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.4467612504959106, cross_entropy: 1.4467612504959106 +[2025-04-29 19:17:23,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 2.896566867828369, cross_entropy: 2.896566867828369 +[2025-04-29 19:17:24,066][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.3972699642181396, cross_entropy: 1.3972699642181396 +[2025-04-29 19:17:27,848][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.557607412338257, cross_entropy: 2.557607412338257 +[2025-04-29 19:17:28,198][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 2.0095489025115967, cross_entropy: 2.0095489025115967 +[2025-04-29 19:17:32,107][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.8815369606018066, cross_entropy: 1.8815369606018066 +[2025-04-29 19:17:32,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.669079303741455, cross_entropy: 2.669079303741455 +[2025-04-29 19:17:36,282][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 1.1635295152664185, cross_entropy: 1.1635295152664185 +[2025-04-29 19:17:36,637][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 0.8026198148727417, cross_entropy: 0.8026198148727417 +[2025-04-29 19:17:40,505][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.031247138977051, cross_entropy: 2.031247138977051 +[2025-04-29 19:17:40,864][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.545365333557129, cross_entropy: 1.545365333557129 +[2025-04-29 19:17:44,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 3.031770944595337, cross_entropy: 3.031770944595337 +[2025-04-29 19:17:45,189][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 2.884737968444824, cross_entropy: 2.884737968444824 +[2025-04-29 19:17:48,861][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 1.3031692504882812, cross_entropy: 1.3031692504882812 +[2025-04-29 19:17:49,219][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 1.094423532485962, cross_entropy: 1.094423532485962 +[2025-04-29 19:17:52,516][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.2826220989227295, cross_entropy: 1.2826220989227295 +[2025-04-29 19:17:52,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 1.0202064514160156, cross_entropy: 1.0202064514160156 +[2025-04-29 19:17:56,683][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 2.83038330078125, cross_entropy: 2.83038330078125 +[2025-04-29 19:17:57,041][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 3.312042713165283, cross_entropy: 3.312042713165283 +[2025-04-29 19:18:00,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 0.8326084613800049, cross_entropy: 0.8326084613800049 +[2025-04-29 19:18:00,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 2.570434808731079, cross_entropy: 2.570434808731079 +[2025-04-29 19:18:05,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.8563865423202515, cross_entropy: 1.8563865423202515 +[2025-04-29 19:18:05,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 1.9714255332946777, cross_entropy: 1.9714255332946777 +[2025-04-29 19:18:08,913][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 2.2947497367858887, cross_entropy: 2.2947497367858887 +[2025-04-29 19:18:09,236][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.878141164779663, cross_entropy: 1.878141164779663 +[2025-04-29 19:18:13,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 2.946560859680176, cross_entropy: 2.946560859680176 +[2025-04-29 19:18:13,426][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 1.6196088790893555, cross_entropy: 1.6196088790893555 +[2025-04-29 19:18:16,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 2.96553373336792, cross_entropy: 2.96553373336792 +[2025-04-29 19:18:17,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 2.056375503540039, cross_entropy: 2.056375503540039 +[2025-04-29 19:18:21,523][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.0992181301116943, cross_entropy: 1.0992181301116943 +[2025-04-29 19:18:21,883][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 1.5784940719604492, cross_entropy: 1.5784940719604492 +[2025-04-29 19:18:25,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.345811367034912, cross_entropy: 2.345811367034912 +[2025-04-29 19:18:26,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.744810104370117, cross_entropy: 2.744810104370117 +[2025-04-29 19:18:29,568][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 1.2675634622573853, cross_entropy: 1.2675634622573853 +[2025-04-29 19:18:29,890][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.0196800231933594, cross_entropy: 1.0196800231933594 +[2025-04-29 19:18:33,568][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 1.9694457054138184, cross_entropy: 1.9694457054138184 +[2025-04-29 19:18:33,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 1.2701841592788696, cross_entropy: 1.2701841592788696 +[2025-04-29 19:18:37,182][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 3.0227596759796143, cross_entropy: 3.0227596759796143 +[2025-04-29 19:18:37,663][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 2.30753231048584, cross_entropy: 2.30753231048584 +[2025-04-29 19:18:41,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.604135513305664, cross_entropy: 2.604135513305664 +[2025-04-29 19:18:41,745][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.629523754119873, cross_entropy: 1.629523754119873 +[2025-04-29 19:18:45,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 2.328202247619629, cross_entropy: 2.328202247619629 +[2025-04-29 19:18:46,345][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.315950870513916, cross_entropy: 1.315950870513916 +[2025-04-29 19:18:49,698][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 3.227179527282715, cross_entropy: 3.227179527282715 +[2025-04-29 19:18:50,052][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 3.1646664142608643, cross_entropy: 3.1646664142608643 +[2025-04-29 19:18:53,638][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 1.4834504127502441, cross_entropy: 1.4834504127502441 +[2025-04-29 19:18:54,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 0.8458473682403564, cross_entropy: 0.8458473682403564 +[2025-04-29 19:18:57,949][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 1.72416090965271, cross_entropy: 1.72416090965271 +[2025-04-29 19:18:58,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.204370141029358, cross_entropy: 1.204370141029358 +[2025-04-29 19:19:02,131][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.223382592201233, cross_entropy: 1.223382592201233 +[2025-04-29 19:19:02,506][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 0.9571730494499207, cross_entropy: 0.9571730494499207 +[2025-04-29 19:19:06,412][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 2.824843406677246, cross_entropy: 2.824843406677246 +[2025-04-29 19:19:06,770][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.461812973022461, cross_entropy: 2.461812973022461 +[2025-04-29 19:19:10,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 2.9458179473876953, cross_entropy: 2.9458179473876953 +[2025-04-29 19:19:11,167][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 1.6681023836135864, cross_entropy: 1.6681023836135864 +[2025-04-29 19:19:15,569][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 1.4164435863494873, cross_entropy: 1.4164435863494873 +[2025-04-29 19:19:15,930][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 3.1394433975219727, cross_entropy: 3.1394433975219727 +[2025-04-29 19:19:20,180][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 2.9482014179229736, cross_entropy: 2.9482014179229736 +[2025-04-29 19:19:20,537][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.2511699199676514, cross_entropy: 1.2511699199676514 +[2025-04-29 19:19:24,983][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.4511384963989258, cross_entropy: 1.4511384963989258 +[2025-04-29 19:19:25,346][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 1.2265000343322754, cross_entropy: 1.2265000343322754 +[2025-04-29 19:19:28,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.4809340238571167, cross_entropy: 1.4809340238571167 +[2025-04-29 19:19:29,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.826023817062378, cross_entropy: 2.826023817062378 +[2025-04-29 19:19:32,645][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 2.493290901184082, cross_entropy: 2.493290901184082 +[2025-04-29 19:19:33,006][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 2.1502294540405273, cross_entropy: 2.1502294540405273 +[2025-04-29 19:19:36,290][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 0.8646267056465149, cross_entropy: 0.8646267056465149 +[2025-04-29 19:19:36,649][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.5604298114776611, cross_entropy: 1.5604298114776611 +[2025-04-29 19:19:40,306][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 2.855318069458008, cross_entropy: 2.855318069458008 +[2025-04-29 19:19:40,667][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 1.198981761932373, cross_entropy: 1.198981761932373 +[2025-04-29 19:19:44,079][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 1.9412786960601807, cross_entropy: 1.9412786960601807 +[2025-04-29 19:19:44,441][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 2.6560556888580322, cross_entropy: 2.6560556888580322 +[2025-04-29 19:19:47,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 1.3413045406341553, cross_entropy: 1.3413045406341553 +[2025-04-29 19:19:47,891][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.0991390943527222, cross_entropy: 1.0991390943527222 +[2025-04-29 19:19:51,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 2.910491943359375, cross_entropy: 2.910491943359375 +[2025-04-29 19:19:52,075][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 2.40779972076416, cross_entropy: 2.40779972076416 +[2025-04-29 19:19:56,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 1.288541555404663, cross_entropy: 1.288541555404663 +[2025-04-29 19:19:56,731][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 2.834713935852051, cross_entropy: 2.834713935852051 +[2025-04-29 19:20:00,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 1.3030052185058594, cross_entropy: 1.3030052185058594 +[2025-04-29 19:20:01,260][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 1.3430826663970947, cross_entropy: 1.3430826663970947 +[2025-04-29 19:20:05,438][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 2.226350784301758, cross_entropy: 2.226350784301758 +[2025-04-29 19:20:05,826][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 3.1704905033111572, cross_entropy: 3.1704905033111572 +[2025-04-29 19:20:09,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 1.9670778512954712, cross_entropy: 1.9670778512954712 +[2025-04-29 19:20:10,038][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 2.6571462154388428, cross_entropy: 2.6571462154388428 +[2025-04-29 19:20:13,351][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.7343354225158691, cross_entropy: 1.7343354225158691 +[2025-04-29 19:20:13,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 1.8003718852996826, cross_entropy: 1.8003718852996826 +[2025-04-29 19:20:17,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 3.109104633331299, cross_entropy: 3.109104633331299 +[2025-04-29 19:20:18,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 2.2113595008850098, cross_entropy: 2.2113595008850098 +[2025-04-29 19:20:22,387][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 2.719143867492676, cross_entropy: 2.719143867492676 +[2025-04-29 19:20:22,791][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.294050931930542, cross_entropy: 1.294050931930542 +[2025-04-29 19:20:26,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 1.2391356229782104, cross_entropy: 1.2391356229782104 +[2025-04-29 19:20:27,320][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.994001865386963, cross_entropy: 1.994001865386963 +[2025-04-29 19:20:31,877][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 3.246750831604004, cross_entropy: 3.246750831604004 +[2025-04-29 19:20:32,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.9336130619049072, cross_entropy: 1.9336130619049072 +[2025-04-29 19:20:35,766][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.7220234870910645, cross_entropy: 2.7220234870910645 +[2025-04-29 19:20:36,121][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.8371968269348145, cross_entropy: 1.8371968269348145 +[2025-04-29 19:20:40,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 2.6542325019836426, cross_entropy: 2.6542325019836426 +[2025-04-29 19:20:40,865][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 2.6817007064819336, cross_entropy: 2.6817007064819336 +[2025-04-29 19:20:44,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.7319087982177734, cross_entropy: 1.7319087982177734 +[2025-04-29 19:20:44,469][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.4897692203521729, cross_entropy: 1.4897692203521729 +[2025-04-29 19:20:47,867][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 3.097736358642578, cross_entropy: 3.097736358642578 +[2025-04-29 19:20:48,226][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.0953994989395142, cross_entropy: 1.0953994989395142 +[2025-04-29 19:20:51,646][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 1.9320406913757324, cross_entropy: 1.9320406913757324 +[2025-04-29 19:20:51,969][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.071781873703003, cross_entropy: 1.071781873703003 +[2025-04-29 19:20:55,296][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 1.5769020318984985, cross_entropy: 1.5769020318984985 +[2025-04-29 19:20:55,618][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 1.6178126335144043, cross_entropy: 1.6178126335144043 +[2025-04-29 19:20:59,148][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.7601909637451172, cross_entropy: 1.7601909637451172 +[2025-04-29 19:20:59,527][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 1.538022756576538, cross_entropy: 1.538022756576538 +[2025-04-29 19:21:03,520][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.8759233951568604, cross_entropy: 2.8759233951568604 +[2025-04-29 19:21:04,695][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 3.1370975971221924, cross_entropy: 3.1370975971221924 +[2025-04-29 19:21:07,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 2.395785093307495, cross_entropy: 2.395785093307495 +[2025-04-29 19:21:08,861][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.6690864562988281, cross_entropy: 1.6690864562988281 +[2025-04-29 19:21:11,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 1.1578325033187866, cross_entropy: 1.1578325033187866 +[2025-04-29 19:21:12,350][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.1813408136367798, cross_entropy: 1.1813408136367798 +[2025-04-29 19:21:15,488][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 0.7255217432975769, cross_entropy: 0.7255217432975769 +[2025-04-29 19:21:16,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 1.5052049160003662, cross_entropy: 1.5052049160003662 +[2025-04-29 19:21:20,183][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 1.4751499891281128, cross_entropy: 1.4751499891281128 +[2025-04-29 19:21:20,540][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 1.4689024686813354, cross_entropy: 1.4689024686813354 +[2025-04-29 19:21:23,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.1221976280212402, cross_entropy: 1.1221976280212402 +[2025-04-29 19:21:24,268][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 3.015385150909424, cross_entropy: 3.015385150909424 +[2025-04-29 19:21:28,047][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 2.9280056953430176, cross_entropy: 2.9280056953430176 +[2025-04-29 19:21:28,412][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.1436423063278198, cross_entropy: 1.1436423063278198 +[2025-04-29 19:21:31,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.505656361579895, cross_entropy: 1.505656361579895 +[2025-04-29 19:21:32,132][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.1856489181518555, cross_entropy: 2.1856489181518555 +[2025-04-29 19:21:35,133][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 2.3965516090393066, cross_entropy: 2.3965516090393066 +[2025-04-29 19:24:51,452][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.9167461395263672, cross_entropy: 1.9167461395263672 +[2025-04-29 19:24:51,453][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.2527697086334229, cross_entropy: 1.2527697086334229 +[2025-04-29 19:24:51,691][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 19:24:51,881][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch6.pth. +[2025-04-29 19:24:52,117][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 19:24:57,037][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 1.1794049739837646, cross_entropy: 1.1794049739837646 +[2025-04-29 19:24:57,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 3.0007026195526123, cross_entropy: 3.0007026195526123 +[2025-04-29 19:25:01,148][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 0.7918719053268433, cross_entropy: 0.7918719053268433 +[2025-04-29 19:25:01,472][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 1.0472359657287598, cross_entropy: 1.0472359657287598 +[2025-04-29 19:25:06,394][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 0.9252774119377136, cross_entropy: 0.9252774119377136 +[2025-04-29 19:25:06,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.7580130100250244, cross_entropy: 1.7580130100250244 +[2025-04-29 19:25:10,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.786409616470337, cross_entropy: 2.786409616470337 +[2025-04-29 19:25:11,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.741634488105774, cross_entropy: 1.741634488105774 +[2025-04-29 19:25:14,322][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 2.8660686016082764, cross_entropy: 2.8660686016082764 +[2025-04-29 19:25:15,862][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.704276442527771, cross_entropy: 1.704276442527771 +[2025-04-29 19:25:19,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 1.2936875820159912, cross_entropy: 1.2936875820159912 +[2025-04-29 19:25:19,594][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 2.3728256225585938, cross_entropy: 2.3728256225585938 +[2025-04-29 19:25:23,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.8891921043395996, cross_entropy: 2.8891921043395996 +[2025-04-29 19:25:24,247][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 0.7766754031181335, cross_entropy: 0.7766754031181335 +[2025-04-29 19:25:27,815][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 0.8259865045547485, cross_entropy: 0.8259865045547485 +[2025-04-29 19:25:28,451][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 1.1432645320892334, cross_entropy: 1.1432645320892334 +[2025-04-29 19:25:32,050][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.5591936111450195, cross_entropy: 2.5591936111450195 +[2025-04-29 19:25:32,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 2.739689350128174, cross_entropy: 2.739689350128174 +[2025-04-29 19:25:36,425][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 1.1934843063354492, cross_entropy: 1.1934843063354492 +[2025-04-29 19:25:37,208][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.2636126279830933, cross_entropy: 1.2636126279830933 +[2025-04-29 19:25:40,205][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.2489745616912842, cross_entropy: 1.2489745616912842 +[2025-04-29 19:25:41,075][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 1.2945420742034912, cross_entropy: 1.2945420742034912 +[2025-04-29 19:25:44,323][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 2.855825424194336, cross_entropy: 2.855825424194336 +[2025-04-29 19:25:45,193][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 1.2686678171157837, cross_entropy: 1.2686678171157837 +[2025-04-29 19:25:48,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.6690908670425415, cross_entropy: 1.6690908670425415 +[2025-04-29 19:25:49,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 1.435161828994751, cross_entropy: 1.435161828994751 +[2025-04-29 19:25:52,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.520524024963379, cross_entropy: 2.520524024963379 +[2025-04-29 19:25:53,622][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 1.0418087244033813, cross_entropy: 1.0418087244033813 +[2025-04-29 19:25:56,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 2.388059616088867, cross_entropy: 2.388059616088867 +[2025-04-29 19:25:58,123][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.0981992483139038, cross_entropy: 1.0981992483139038 +[2025-04-29 19:26:01,155][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 1.3681747913360596, cross_entropy: 1.3681747913360596 +[2025-04-29 19:26:02,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.383190631866455, cross_entropy: 2.383190631866455 +[2025-04-29 19:26:05,056][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.7663261890411377, cross_entropy: 2.7663261890411377 +[2025-04-29 19:26:06,482][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 2.806441307067871, cross_entropy: 2.806441307067871 +[2025-04-29 19:26:09,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 1.9686959981918335, cross_entropy: 1.9686959981918335 +[2025-04-29 19:26:10,500][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.9791059494018555, cross_entropy: 1.9791059494018555 +[2025-04-29 19:26:13,886][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 1.139710783958435, cross_entropy: 1.139710783958435 +[2025-04-29 19:26:15,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.2275431156158447, cross_entropy: 1.2275431156158447 +[2025-04-29 19:26:17,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 2.8316946029663086, cross_entropy: 2.8316946029663086 +[2025-04-29 19:26:19,204][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.6139748096466064, cross_entropy: 1.6139748096466064 +[2025-04-29 19:26:22,141][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 2.8001084327697754, cross_entropy: 2.8001084327697754 +[2025-04-29 19:26:22,983][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.400628089904785, cross_entropy: 2.400628089904785 +[2025-04-29 19:26:26,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.6399693489074707, cross_entropy: 2.6399693489074707 +[2025-04-29 19:26:27,137][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 0.9263607263565063, cross_entropy: 0.9263607263565063 +[2025-04-29 19:26:30,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.7967529296875, cross_entropy: 2.7967529296875 +[2025-04-29 19:26:30,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.300662875175476, cross_entropy: 1.300662875175476 +[2025-04-29 19:26:34,733][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 2.9279680252075195, cross_entropy: 2.9279680252075195 +[2025-04-29 19:26:35,101][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 1.1098012924194336, cross_entropy: 1.1098012924194336 +[2025-04-29 19:26:38,372][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 0.953704297542572, cross_entropy: 0.953704297542572 +[2025-04-29 19:26:39,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.042335033416748, cross_entropy: 1.042335033416748 +[2025-04-29 19:26:42,780][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.604867458343506, cross_entropy: 2.604867458343506 +[2025-04-29 19:26:43,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.113823413848877, cross_entropy: 1.113823413848877 +[2025-04-29 19:26:46,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 0.9379550814628601, cross_entropy: 0.9379550814628601 +[2025-04-29 19:26:47,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.6578588485717773, cross_entropy: 2.6578588485717773 +[2025-04-29 19:26:52,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 0.768567681312561, cross_entropy: 0.768567681312561 +[2025-04-29 19:26:52,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 1.3953405618667603, cross_entropy: 1.3953405618667603 +[2025-04-29 19:26:56,415][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.0586745738983154, cross_entropy: 1.0586745738983154 +[2025-04-29 19:26:56,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.7990626096725464, cross_entropy: 1.7990626096725464 +[2025-04-29 19:27:01,201][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 2.5851006507873535, cross_entropy: 2.5851006507873535 +[2025-04-29 19:27:01,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 1.4595177173614502, cross_entropy: 1.4595177173614502 +[2025-04-29 19:27:05,619][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 1.07358717918396, cross_entropy: 1.07358717918396 +[2025-04-29 19:27:05,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.6404361724853516, cross_entropy: 1.6404361724853516 +[2025-04-29 19:27:09,714][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 2.119938373565674, cross_entropy: 2.119938373565674 +[2025-04-29 19:27:10,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 1.542975664138794, cross_entropy: 1.542975664138794 +[2025-04-29 19:27:14,108][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.7436764240264893, cross_entropy: 2.7436764240264893 +[2025-04-29 19:27:14,475][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 2.670145034790039, cross_entropy: 2.670145034790039 +[2025-04-29 19:27:17,270][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 2.9887444972991943, cross_entropy: 2.9887444972991943 +[2025-04-29 19:27:17,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.3828554153442383, cross_entropy: 2.3828554153442383 +[2025-04-29 19:27:21,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 3.0140652656555176, cross_entropy: 3.0140652656555176 +[2025-04-29 19:27:21,789][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 1.6093769073486328, cross_entropy: 1.6093769073486328 +[2025-04-29 19:27:25,649][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 1.2335500717163086, cross_entropy: 1.2335500717163086 +[2025-04-29 19:27:26,013][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 0.46873846650123596, cross_entropy: 0.46873846650123596 +[2025-04-29 19:27:30,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 1.081403374671936, cross_entropy: 1.081403374671936 +[2025-04-29 19:27:30,416][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 0.9956948161125183, cross_entropy: 0.9956948161125183 +[2025-04-29 19:27:35,567][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 2.946582794189453, cross_entropy: 2.946582794189453 +[2025-04-29 19:27:35,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 2.456022262573242, cross_entropy: 2.456022262573242 +[2025-04-29 19:27:39,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.5575170516967773, cross_entropy: 2.5575170516967773 +[2025-04-29 19:27:39,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 0.968948245048523, cross_entropy: 0.968948245048523 +[2025-04-29 19:27:43,508][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.947435140609741, cross_entropy: 2.947435140609741 +[2025-04-29 19:27:43,869][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 1.2750654220581055, cross_entropy: 1.2750654220581055 +[2025-04-29 19:27:48,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 0.8962780237197876, cross_entropy: 0.8962780237197876 +[2025-04-29 19:27:48,934][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 1.3265411853790283, cross_entropy: 1.3265411853790283 +[2025-04-29 19:27:52,218][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 0.9790359735488892, cross_entropy: 0.9790359735488892 +[2025-04-29 19:27:52,576][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 0.7822263240814209, cross_entropy: 0.7822263240814209 +[2025-04-29 19:27:56,987][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 2.150951862335205, cross_entropy: 2.150951862335205 +[2025-04-29 19:27:57,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 3.3849949836730957, cross_entropy: 3.3849949836730957 +[2025-04-29 19:28:00,931][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 2.7389719486236572, cross_entropy: 2.7389719486236572 +[2025-04-29 19:28:01,291][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 0.6838332414627075, cross_entropy: 0.6838332414627075 +[2025-04-29 19:28:05,732][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 1.6856780052185059, cross_entropy: 1.6856780052185059 +[2025-04-29 19:28:06,056][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.8222246170043945, cross_entropy: 1.8222246170043945 +[2025-04-29 19:28:09,402][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 1.4265344142913818, cross_entropy: 1.4265344142913818 +[2025-04-29 19:28:09,728][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 0.6892744302749634, cross_entropy: 0.6892744302749634 +[2025-04-29 19:28:13,322][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 2.2005016803741455, cross_entropy: 2.2005016803741455 +[2025-04-29 19:28:13,643][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 0.9738062024116516, cross_entropy: 0.9738062024116516 +[2025-04-29 19:28:17,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 1.6072351932525635, cross_entropy: 1.6072351932525635 +[2025-04-29 19:28:18,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.5058863162994385, cross_entropy: 1.5058863162994385 +[2025-04-29 19:28:22,331][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.5760687589645386, cross_entropy: 1.5760687589645386 +[2025-04-29 19:28:22,688][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 3.154688835144043, cross_entropy: 3.154688835144043 +[2025-04-29 19:28:26,970][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.0291650295257568, cross_entropy: 1.0291650295257568 +[2025-04-29 19:28:27,326][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 2.5859289169311523, cross_entropy: 2.5859289169311523 +[2025-04-29 19:28:31,846][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 2.439154624938965, cross_entropy: 2.439154624938965 +[2025-04-29 19:28:32,207][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 2.5450620651245117, cross_entropy: 2.5450620651245117 +[2025-04-29 19:28:35,927][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 1.1782667636871338, cross_entropy: 1.1782667636871338 +[2025-04-29 19:28:36,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 2.36824369430542, cross_entropy: 2.36824369430542 +[2025-04-29 19:28:39,727][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.5750373601913452, cross_entropy: 1.5750373601913452 +[2025-04-29 19:28:40,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 2.2394609451293945, cross_entropy: 2.2394609451293945 +[2025-04-29 19:28:43,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.1680065393447876, cross_entropy: 1.1680065393447876 +[2025-04-29 19:28:44,254][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.9128526449203491, cross_entropy: 1.9128526449203491 +[2025-04-29 19:28:48,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 2.270902156829834, cross_entropy: 2.270902156829834 +[2025-04-29 19:28:48,850][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 0.7936283946037292, cross_entropy: 0.7936283946037292 +[2025-04-29 19:28:52,538][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 1.76649010181427, cross_entropy: 1.76649010181427 +[2025-04-29 19:28:52,898][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 2.4764938354492188, cross_entropy: 2.4764938354492188 +[2025-04-29 19:28:56,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 3.2405922412872314, cross_entropy: 3.2405922412872314 +[2025-04-29 19:28:56,910][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 1.418810486793518, cross_entropy: 1.418810486793518 +[2025-04-29 19:29:00,114][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 2.074917793273926, cross_entropy: 2.074917793273926 +[2025-04-29 19:29:00,444][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 1.3183629512786865, cross_entropy: 1.3183629512786865 +[2025-04-29 19:29:03,829][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.2808914184570312, cross_entropy: 1.2808914184570312 +[2025-04-29 19:29:04,186][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 1.593979835510254, cross_entropy: 1.593979835510254 +[2025-04-29 19:29:07,889][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 1.8974884748458862, cross_entropy: 1.8974884748458862 +[2025-04-29 19:29:08,249][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 1.1728878021240234, cross_entropy: 1.1728878021240234 +[2025-04-29 19:29:14,416][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.5466771125793457, cross_entropy: 1.5466771125793457 +[2025-04-29 19:29:14,775][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 0.9176620244979858, cross_entropy: 0.9176620244979858 +[2025-04-29 19:29:18,334][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.6388871669769287, cross_entropy: 2.6388871669769287 +[2025-04-29 19:29:18,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.6684932708740234, cross_entropy: 1.6684932708740234 +[2025-04-29 19:29:22,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 0.6039671301841736, cross_entropy: 0.6039671301841736 +[2025-04-29 19:29:22,702][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 0.9616135358810425, cross_entropy: 0.9616135358810425 +[2025-04-29 19:29:26,738][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 2.9238812923431396, cross_entropy: 2.9238812923431396 +[2025-04-29 19:29:27,097][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.0250060558319092, cross_entropy: 1.0250060558319092 +[2025-04-29 19:29:31,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 1.0050221681594849, cross_entropy: 1.0050221681594849 +[2025-04-29 19:29:31,385][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 0.9380958080291748, cross_entropy: 0.9380958080291748 +[2025-04-29 19:29:35,004][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 1.643592357635498, cross_entropy: 1.643592357635498 +[2025-04-29 19:29:35,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.169145345687866, cross_entropy: 2.169145345687866 +[2025-04-29 19:29:39,439][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 0.7035104036331177, cross_entropy: 0.7035104036331177 +[2025-04-29 19:29:39,805][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.3279273509979248, cross_entropy: 1.3279273509979248 +[2025-04-29 19:29:43,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 2.155705451965332, cross_entropy: 2.155705451965332 +[2025-04-29 19:29:44,355][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 1.2686583995819092, cross_entropy: 1.2686583995819092 +[2025-04-29 19:29:47,950][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 3.0962772369384766, cross_entropy: 3.0962772369384766 +[2025-04-29 19:29:48,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.6789381504058838, cross_entropy: 1.6789381504058838 +[2025-04-29 19:29:52,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 2.9701552391052246, cross_entropy: 2.9701552391052246 +[2025-04-29 19:29:53,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 1.171941876411438, cross_entropy: 1.171941876411438 +[2025-04-29 19:29:57,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 2.6701183319091797, cross_entropy: 2.6701183319091797 +[2025-04-29 19:29:57,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.6329195499420166, cross_entropy: 1.6329195499420166 +[2025-04-29 19:30:01,437][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 2.865839719772339, cross_entropy: 2.865839719772339 +[2025-04-29 19:30:01,791][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.585414171218872, cross_entropy: 2.585414171218872 +[2025-04-29 19:30:06,618][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 2.4676549434661865, cross_entropy: 2.4676549434661865 +[2025-04-29 19:30:06,939][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.142957329750061, cross_entropy: 1.142957329750061 +[2025-04-29 19:30:10,934][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 0.8868116140365601, cross_entropy: 0.8868116140365601 +[2025-04-29 19:30:11,256][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 0.9766653776168823, cross_entropy: 0.9766653776168823 +[2025-04-29 19:30:15,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 0.824058473110199, cross_entropy: 0.824058473110199 +[2025-04-29 19:30:15,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 1.2698583602905273, cross_entropy: 1.2698583602905273 +[2025-04-29 19:30:19,868][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 3.0022482872009277, cross_entropy: 3.0022482872009277 +[2025-04-29 19:30:20,230][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 2.862384796142578, cross_entropy: 2.862384796142578 +[2025-04-29 19:30:24,084][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.057889938354492, cross_entropy: 2.057889938354492 +[2025-04-29 19:30:24,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 1.7721593379974365, cross_entropy: 1.7721593379974365 +[2025-04-29 19:30:29,166][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 1.1885443925857544, cross_entropy: 1.1885443925857544 +[2025-04-29 19:30:29,516][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 1.5300559997558594, cross_entropy: 1.5300559997558594 +[2025-04-29 19:30:33,396][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.2870218753814697, cross_entropy: 1.2870218753814697 +[2025-04-29 19:30:33,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 2.7361462116241455, cross_entropy: 2.7361462116241455 +[2025-04-29 19:30:37,559][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 2.609773635864258, cross_entropy: 2.609773635864258 +[2025-04-29 19:30:37,910][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 1.49832284450531, cross_entropy: 1.49832284450531 +[2025-04-29 19:30:41,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 2.8912367820739746, cross_entropy: 2.8912367820739746 +[2025-04-29 19:30:41,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 2.947237253189087, cross_entropy: 2.947237253189087 +[2025-04-29 19:30:45,514][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 0.8984209895133972, cross_entropy: 0.8984209895133972 +[2025-04-29 19:30:45,870][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 2.2295420169830322, cross_entropy: 2.2295420169830322 +[2025-04-29 19:30:49,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.9959495067596436, cross_entropy: 1.9959495067596436 +[2025-04-29 19:30:50,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 2.891061544418335, cross_entropy: 2.891061544418335 +[2025-04-29 19:30:53,797][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 1.5337305068969727, cross_entropy: 1.5337305068969727 +[2025-04-29 19:30:54,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 2.7990996837615967, cross_entropy: 2.7990996837615967 +[2025-04-29 19:30:58,143][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 3.26497483253479, cross_entropy: 3.26497483253479 +[2025-04-29 19:30:58,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 1.0270471572875977, cross_entropy: 1.0270471572875977 +[2025-04-29 19:31:02,276][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.7130191326141357, cross_entropy: 1.7130191326141357 +[2025-04-29 19:31:02,637][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 2.9671101570129395, cross_entropy: 2.9671101570129395 +[2025-04-29 19:31:06,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.154226541519165, cross_entropy: 1.154226541519165 +[2025-04-29 19:31:06,554][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 1.2091138362884521, cross_entropy: 1.2091138362884521 +[2025-04-29 19:31:10,277][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 1.3037772178649902, cross_entropy: 1.3037772178649902 +[2025-04-29 19:31:10,632][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 0.9779719114303589, cross_entropy: 0.9779719114303589 +[2025-04-29 19:31:14,757][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 1.0285407304763794, cross_entropy: 1.0285407304763794 +[2025-04-29 19:31:15,121][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 2.5428097248077393, cross_entropy: 2.5428097248077393 +[2025-04-29 19:31:19,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 2.127127170562744, cross_entropy: 2.127127170562744 +[2025-04-29 19:31:19,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 2.4830291271209717, cross_entropy: 2.4830291271209717 +[2025-04-29 19:31:23,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.7773382663726807, cross_entropy: 2.7773382663726807 +[2025-04-29 19:31:23,513][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 1.6822627782821655, cross_entropy: 1.6822627782821655 +[2025-04-29 19:31:27,515][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.106250524520874, cross_entropy: 1.106250524520874 +[2025-04-29 19:31:27,874][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 1.495922565460205, cross_entropy: 1.495922565460205 +[2025-04-29 19:31:31,774][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.5585917234420776, cross_entropy: 1.5585917234420776 +[2025-04-29 19:31:32,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.1355936527252197, cross_entropy: 2.1355936527252197 +[2025-04-29 19:31:35,252][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 2.1806788444519043, cross_entropy: 2.1806788444519043 +[2025-04-29 19:31:35,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 1.1825953722000122, cross_entropy: 1.1825953722000122 +[2025-04-29 19:31:38,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 2.397454261779785, cross_entropy: 2.397454261779785 +[2025-04-29 19:31:39,321][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 1.1313766241073608, cross_entropy: 1.1313766241073608 +[2025-04-29 19:31:43,462][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 2.4172070026397705, cross_entropy: 2.4172070026397705 +[2025-04-29 19:31:43,821][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 2.563992977142334, cross_entropy: 2.563992977142334 +[2025-04-29 19:31:46,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 1.652429223060608, cross_entropy: 1.652429223060608 +[2025-04-29 19:31:47,174][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 1.152362585067749, cross_entropy: 1.152362585067749 +[2025-04-29 19:31:51,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.5750200748443604, cross_entropy: 1.5750200748443604 +[2025-04-29 19:31:51,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.6105525493621826, cross_entropy: 1.6105525493621826 +[2025-04-29 19:31:55,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 1.2012137174606323, cross_entropy: 1.2012137174606323 +[2025-04-29 19:31:55,800][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 1.7109932899475098, cross_entropy: 1.7109932899475098 +[2025-04-29 19:31:59,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 1.0766326189041138, cross_entropy: 1.0766326189041138 +[2025-04-29 19:31:59,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 2.9257419109344482, cross_entropy: 2.9257419109344482 +[2025-04-29 19:32:02,959][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.8219544887542725, cross_entropy: 2.8219544887542725 +[2025-04-29 19:32:03,392][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.6874217987060547, cross_entropy: 2.6874217987060547 +[2025-04-29 19:32:07,431][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 0.9680982232093811, cross_entropy: 0.9680982232093811 +[2025-04-29 19:32:07,786][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 1.4493217468261719, cross_entropy: 1.4493217468261719 +[2025-04-29 19:32:11,129][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.116665840148926, cross_entropy: 3.116665840148926 +[2025-04-29 19:32:11,454][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 0.9586867094039917, cross_entropy: 0.9586867094039917 +[2025-04-29 19:32:14,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 2.035562038421631, cross_entropy: 2.035562038421631 +[2025-04-29 19:32:15,166][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 2.4105114936828613, cross_entropy: 2.4105114936828613 +[2025-04-29 19:32:18,971][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 2.9524266719818115, cross_entropy: 2.9524266719818115 +[2025-04-29 19:32:19,330][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 2.852130651473999, cross_entropy: 2.852130651473999 +[2025-04-29 19:32:23,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 1.4693734645843506, cross_entropy: 1.4693734645843506 +[2025-04-29 19:32:23,608][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.2543962001800537, cross_entropy: 1.2543962001800537 +[2025-04-29 19:32:27,834][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 1.3113999366760254, cross_entropy: 1.3113999366760254 +[2025-04-29 19:32:28,156][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.6181738376617432, cross_entropy: 1.6181738376617432 +[2025-04-29 19:32:32,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.628178596496582, cross_entropy: 1.628178596496582 +[2025-04-29 19:32:32,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 1.1139805316925049, cross_entropy: 1.1139805316925049 +[2025-04-29 19:32:35,954][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 1.1870661973953247, cross_entropy: 1.1870661973953247 +[2025-04-29 19:32:36,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 2.114668846130371, cross_entropy: 2.114668846130371 +[2025-04-29 19:32:40,226][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.5295686721801758, cross_entropy: 1.5295686721801758 +[2025-04-29 19:32:40,581][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.836824893951416, cross_entropy: 2.836824893951416 +[2025-04-29 19:32:45,003][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 3.0566110610961914, cross_entropy: 3.0566110610961914 +[2025-04-29 19:32:45,363][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 2.903538703918457, cross_entropy: 2.903538703918457 +[2025-04-29 19:32:49,161][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 1.44950532913208, cross_entropy: 1.44950532913208 +[2025-04-29 19:32:49,483][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 2.7971277236938477, cross_entropy: 2.7971277236938477 +[2025-04-29 19:32:52,897][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.0868853330612183, cross_entropy: 1.0868853330612183 +[2025-04-29 19:32:53,251][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 2.78835391998291, cross_entropy: 2.78835391998291 +[2025-04-29 19:32:56,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 0.8413870930671692, cross_entropy: 0.8413870930671692 +[2025-04-29 19:32:57,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.4360201358795166, cross_entropy: 1.4360201358795166 +[2025-04-29 19:33:01,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.2944881916046143, cross_entropy: 1.2944881916046143 +[2025-04-29 19:33:01,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 1.0263909101486206, cross_entropy: 1.0263909101486206 +[2025-04-29 19:33:05,209][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.1562132835388184, cross_entropy: 2.1562132835388184 +[2025-04-29 19:33:05,567][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.2043510675430298, cross_entropy: 1.2043510675430298 +[2025-04-29 19:33:08,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 1.294255018234253, cross_entropy: 1.294255018234253 +[2025-04-29 19:33:09,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 1.4409372806549072, cross_entropy: 1.4409372806549072 +[2025-04-29 19:33:13,080][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 0.7863392233848572, cross_entropy: 0.7863392233848572 +[2025-04-29 19:33:13,435][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 0.5521448254585266, cross_entropy: 0.5521448254585266 +[2025-04-29 19:33:17,509][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 2.3997554779052734, cross_entropy: 2.3997554779052734 +[2025-04-29 19:33:17,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 2.8242554664611816, cross_entropy: 2.8242554664611816 +[2025-04-29 19:33:21,046][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 1.6179946660995483, cross_entropy: 1.6179946660995483 +[2025-04-29 19:33:21,406][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.6988024711608887, cross_entropy: 2.6988024711608887 +[2025-04-29 19:33:24,819][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.7836318016052246, cross_entropy: 2.7836318016052246 +[2025-04-29 19:33:25,178][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 2.282392978668213, cross_entropy: 2.282392978668213 +[2025-04-29 19:33:29,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.6551841497421265, cross_entropy: 1.6551841497421265 +[2025-04-29 19:33:29,963][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 0.9322173595428467, cross_entropy: 0.9322173595428467 +[2025-04-29 19:33:33,783][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.1859134435653687, cross_entropy: 1.1859134435653687 +[2025-04-29 19:33:34,142][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 3.2819602489471436, cross_entropy: 3.2819602489471436 +[2025-04-29 19:33:37,080][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 0.8496809005737305, cross_entropy: 0.8496809005737305 +[2025-04-29 19:33:37,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 1.7064427137374878, cross_entropy: 1.7064427137374878 +[2025-04-29 19:33:41,703][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 2.4390597343444824, cross_entropy: 2.4390597343444824 +[2025-04-29 19:33:42,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 3.3640005588531494, cross_entropy: 3.3640005588531494 +[2025-04-29 19:33:45,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 2.4465456008911133, cross_entropy: 2.4465456008911133 +[2025-04-29 19:33:45,773][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 0.5973219275474548, cross_entropy: 0.5973219275474548 +[2025-04-29 19:33:49,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 2.770549774169922, cross_entropy: 2.770549774169922 +[2025-04-29 19:33:49,631][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.527751088142395, cross_entropy: 1.527751088142395 +[2025-04-29 19:33:53,508][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 1.077610969543457, cross_entropy: 1.077610969543457 +[2025-04-29 19:33:53,864][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.875929355621338, cross_entropy: 2.875929355621338 +[2025-04-29 19:33:57,394][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 1.3104183673858643, cross_entropy: 1.3104183673858643 +[2025-04-29 19:33:57,750][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 0.7626445293426514, cross_entropy: 0.7626445293426514 +[2025-04-29 19:34:01,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.198690414428711, cross_entropy: 1.198690414428711 +[2025-04-29 19:34:02,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 1.0092799663543701, cross_entropy: 1.0092799663543701 +[2025-04-29 19:34:06,902][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 1.428126573562622, cross_entropy: 1.428126573562622 +[2025-04-29 19:34:07,261][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.172813892364502, cross_entropy: 1.172813892364502 +[2025-04-29 19:34:11,977][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.1348083019256592, cross_entropy: 1.1348083019256592 +[2025-04-29 19:34:12,335][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 2.087890625, cross_entropy: 2.087890625 +[2025-04-29 19:34:16,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 0.9669689536094666, cross_entropy: 0.9669689536094666 +[2025-04-29 19:34:16,506][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.797781229019165, cross_entropy: 1.797781229019165 +[2025-04-29 19:34:20,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.010395050048828, cross_entropy: 3.010395050048828 +[2025-04-29 19:34:20,774][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 1.9181418418884277, cross_entropy: 1.9181418418884277 +[2025-04-29 19:34:24,190][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 0.9356707334518433, cross_entropy: 0.9356707334518433 +[2025-04-29 19:34:24,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 2.781764030456543, cross_entropy: 2.781764030456543 +[2025-04-29 19:34:28,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 2.715113639831543, cross_entropy: 2.715113639831543 +[2025-04-29 19:34:29,125][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 2.855316638946533, cross_entropy: 2.855316638946533 +[2025-04-29 19:34:33,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 1.1454432010650635, cross_entropy: 1.1454432010650635 +[2025-04-29 19:34:33,674][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 2.0523500442504883, cross_entropy: 2.0523500442504883 +[2025-04-29 19:34:37,566][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.2394073009490967, cross_entropy: 2.2394073009490967 +[2025-04-29 19:34:37,966][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 1.136242151260376, cross_entropy: 1.136242151260376 +[2025-04-29 19:34:41,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.6665829420089722, cross_entropy: 1.6665829420089722 +[2025-04-29 19:34:42,070][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 1.5787184238433838, cross_entropy: 1.5787184238433838 +[2025-04-29 19:34:45,816][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.3601058721542358, cross_entropy: 1.3601058721542358 +[2025-04-29 19:34:46,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 2.921689987182617, cross_entropy: 2.921689987182617 +[2025-04-29 19:34:49,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 2.2278342247009277, cross_entropy: 2.2278342247009277 +[2025-04-29 19:34:50,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 1.0874018669128418, cross_entropy: 1.0874018669128418 +[2025-04-29 19:34:53,402][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.8957765102386475, cross_entropy: 2.8957765102386475 +[2025-04-29 19:34:54,558][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 2.0860280990600586, cross_entropy: 2.0860280990600586 +[2025-04-29 19:34:57,729][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 1.329795002937317, cross_entropy: 1.329795002937317 +[2025-04-29 19:34:59,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.035409688949585, cross_entropy: 2.035409688949585 +[2025-04-29 19:35:02,054][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 2.9069173336029053, cross_entropy: 2.9069173336029053 +[2025-04-29 19:35:02,739][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 2.883632183074951, cross_entropy: 2.883632183074951 +[2025-04-29 19:35:06,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 1.7833399772644043, cross_entropy: 1.7833399772644043 +[2025-04-29 19:35:07,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.9574475288391113, cross_entropy: 2.9574475288391113 +[2025-04-29 19:35:10,796][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 2.311237335205078, cross_entropy: 2.311237335205078 +[2025-04-29 19:35:11,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 0.8926856517791748, cross_entropy: 0.8926856517791748 +[2025-04-29 19:35:14,618][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 2.8590140342712402, cross_entropy: 2.8590140342712402 +[2025-04-29 19:35:16,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 1.0646528005599976, cross_entropy: 1.0646528005599976 +[2025-04-29 19:35:19,230][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 2.835645914077759, cross_entropy: 2.835645914077759 +[2025-04-29 19:35:21,125][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.0392427444458008, cross_entropy: 1.0392427444458008 +[2025-04-29 19:35:23,018][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 1.1539579629898071, cross_entropy: 1.1539579629898071 +[2025-04-29 19:35:25,225][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 1.2931321859359741, cross_entropy: 1.2931321859359741 +[2025-04-29 19:35:26,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 0.8150039911270142, cross_entropy: 0.8150039911270142 +[2025-04-29 19:35:28,799][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 2.9119691848754883, cross_entropy: 2.9119691848754883 +[2025-04-29 19:35:31,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 0.8542804718017578, cross_entropy: 0.8542804718017578 +[2025-04-29 19:35:32,885][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 1.3719346523284912, cross_entropy: 1.3719346523284912 +[2025-04-29 19:35:35,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 0.8445384502410889, cross_entropy: 0.8445384502410889 +[2025-04-29 19:35:37,077][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 2.526972770690918, cross_entropy: 2.526972770690918 +[2025-04-29 19:35:40,020][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.1625683307647705, cross_entropy: 1.1625683307647705 +[2025-04-29 19:35:40,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 1.0117675065994263, cross_entropy: 1.0117675065994263 +[2025-04-29 19:35:44,167][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 0.9870144128799438, cross_entropy: 0.9870144128799438 +[2025-04-29 19:35:45,314][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 1.7312138080596924, cross_entropy: 1.7312138080596924 +[2025-04-29 19:35:48,319][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 2.426781415939331, cross_entropy: 2.426781415939331 +[2025-04-29 19:35:49,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 3.0919761657714844, cross_entropy: 3.0919761657714844 +[2025-04-29 19:35:52,782][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 3.077334403991699, cross_entropy: 3.077334403991699 +[2025-04-29 19:35:53,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 2.976008415222168, cross_entropy: 2.976008415222168 +[2025-04-29 19:35:56,757][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 2.323505401611328, cross_entropy: 2.323505401611328 +[2025-04-29 19:35:57,807][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.5147441625595093, cross_entropy: 1.5147441625595093 +[2025-04-29 19:36:00,810][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 2.8433499336242676, cross_entropy: 2.8433499336242676 +[2025-04-29 19:36:01,237][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 2.173250436782837, cross_entropy: 2.173250436782837 +[2025-04-29 19:36:04,739][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.4316426515579224, cross_entropy: 1.4316426515579224 +[2025-04-29 19:36:05,527][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 2.6457433700561523, cross_entropy: 2.6457433700561523 +[2025-04-29 19:36:08,933][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 1.0627424716949463, cross_entropy: 1.0627424716949463 +[2025-04-29 19:36:09,296][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.7495713233947754, cross_entropy: 2.7495713233947754 +[2025-04-29 19:36:14,134][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 1.3926658630371094, cross_entropy: 1.3926658630371094 +[2025-04-29 19:36:14,488][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 1.382108211517334, cross_entropy: 1.382108211517334 +[2025-04-29 19:36:18,100][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.7257400751113892, cross_entropy: 1.7257400751113892 +[2025-04-29 19:36:18,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 1.0220615863800049, cross_entropy: 1.0220615863800049 +[2025-04-29 19:36:22,257][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 1.474791407585144, cross_entropy: 1.474791407585144 +[2025-04-29 19:36:22,580][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 1.1022312641143799, cross_entropy: 1.1022312641143799 +[2025-04-29 19:36:26,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.7675659656524658, cross_entropy: 1.7675659656524658 +[2025-04-29 19:36:27,033][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.4881609678268433, cross_entropy: 1.4881609678268433 +[2025-04-29 19:36:30,455][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 2.0454678535461426, cross_entropy: 2.0454678535461426 +[2025-04-29 19:36:30,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 1.7187397480010986, cross_entropy: 1.7187397480010986 +[2025-04-29 19:36:35,448][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 1.4384312629699707, cross_entropy: 1.4384312629699707 +[2025-04-29 19:36:35,804][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.157076358795166, cross_entropy: 1.157076358795166 +[2025-04-29 19:36:39,812][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 1.215756893157959, cross_entropy: 1.215756893157959 +[2025-04-29 19:36:40,136][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 2.7950339317321777, cross_entropy: 2.7950339317321777 +[2025-04-29 19:36:44,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 1.208570957183838, cross_entropy: 1.208570957183838 +[2025-04-29 19:36:44,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.3521528244018555, cross_entropy: 1.3521528244018555 +[2025-04-29 19:36:48,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.3447586297988892, cross_entropy: 1.3447586297988892 +[2025-04-29 19:36:49,280][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.2620697021484375, cross_entropy: 1.2620697021484375 +[2025-04-29 19:36:52,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.5814621448516846, cross_entropy: 2.5814621448516846 +[2025-04-29 19:36:53,066][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 0.9593226909637451, cross_entropy: 0.9593226909637451 +[2025-04-29 19:36:57,161][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 1.0014467239379883, cross_entropy: 1.0014467239379883 +[2025-04-29 19:36:57,529][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.2803139686584473, cross_entropy: 1.2803139686584473 +[2025-04-29 19:37:00,710][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.3919057846069336, cross_entropy: 2.3919057846069336 +[2025-04-29 19:37:01,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 2.331820011138916, cross_entropy: 2.331820011138916 +[2025-04-29 19:37:05,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.1185669898986816, cross_entropy: 1.1185669898986816 +[2025-04-29 19:37:05,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.273391842842102, cross_entropy: 1.273391842842102 +[2025-04-29 19:37:09,799][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 1.2688841819763184, cross_entropy: 1.2688841819763184 +[2025-04-29 19:37:10,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.694608211517334, cross_entropy: 2.694608211517334 +[2025-04-29 19:37:13,978][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.356380581855774, cross_entropy: 1.356380581855774 +[2025-04-29 19:37:14,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.057893991470337, cross_entropy: 1.057893991470337 +[2025-04-29 19:37:18,110][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 3.1400928497314453, cross_entropy: 3.1400928497314453 +[2025-04-29 19:37:18,472][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 2.825434446334839, cross_entropy: 2.825434446334839 +[2025-04-29 19:37:21,918][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.7304710149765015, cross_entropy: 1.7304710149765015 +[2025-04-29 19:37:22,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 1.4780333042144775, cross_entropy: 1.4780333042144775 +[2025-04-29 19:37:26,025][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 2.5754945278167725, cross_entropy: 2.5754945278167725 +[2025-04-29 19:37:26,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 1.4685181379318237, cross_entropy: 1.4685181379318237 +[2025-04-29 19:40:40,135][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.814695119857788, cross_entropy: 1.814695119857788 +[2025-04-29 19:40:40,136][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.2410578727722168, cross_entropy: 1.2410578727722168 +[2025-04-29 19:40:40,369][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 19:40:40,560][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch7.pth. +[2025-04-29 19:40:40,809][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 19:40:45,142][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.219637155532837, cross_entropy: 1.219637155532837 +[2025-04-29 19:40:46,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.7303543090820312, cross_entropy: 2.7303543090820312 +[2025-04-29 19:40:49,345][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 0.8472093939781189, cross_entropy: 0.8472093939781189 +[2025-04-29 19:40:50,071][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.4277496337890625, cross_entropy: 2.4277496337890625 +[2025-04-29 19:40:53,610][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.3763201236724854, cross_entropy: 1.3763201236724854 +[2025-04-29 19:40:54,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 2.657273292541504, cross_entropy: 2.657273292541504 +[2025-04-29 19:40:58,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.6298372745513916, cross_entropy: 0.6298372745513916 +[2025-04-29 19:40:59,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.0700366497039795, cross_entropy: 2.0700366497039795 +[2025-04-29 19:41:02,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 0.855039119720459, cross_entropy: 0.855039119720459 +[2025-04-29 19:41:03,383][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.4231288433074951, cross_entropy: 1.4231288433074951 +[2025-04-29 19:41:06,633][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 0.9894929528236389, cross_entropy: 0.9894929528236389 +[2025-04-29 19:41:08,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 1.3188396692276, cross_entropy: 1.3188396692276 +[2025-04-29 19:41:11,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 1.5550010204315186, cross_entropy: 1.5550010204315186 +[2025-04-29 19:41:12,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 0.6408348083496094, cross_entropy: 0.6408348083496094 +[2025-04-29 19:41:15,249][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 2.7998971939086914, cross_entropy: 2.7998971939086914 +[2025-04-29 19:41:16,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 3.1109507083892822, cross_entropy: 3.1109507083892822 +[2025-04-29 19:41:19,315][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 1.263659119606018, cross_entropy: 1.263659119606018 +[2025-04-29 19:41:20,768][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.3344197273254395, cross_entropy: 2.3344197273254395 +[2025-04-29 19:41:23,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 2.4426188468933105, cross_entropy: 2.4426188468933105 +[2025-04-29 19:41:25,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 0.5309534072875977, cross_entropy: 0.5309534072875977 +[2025-04-29 19:41:28,127][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 2.6701364517211914, cross_entropy: 2.6701364517211914 +[2025-04-29 19:41:29,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 2.688183307647705, cross_entropy: 2.688183307647705 +[2025-04-29 19:41:31,749][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 2.9929473400115967, cross_entropy: 2.9929473400115967 +[2025-04-29 19:41:33,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 2.5977559089660645, cross_entropy: 2.5977559089660645 +[2025-04-29 19:41:35,743][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 2.6633434295654297, cross_entropy: 2.6633434295654297 +[2025-04-29 19:41:37,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 1.1093614101409912, cross_entropy: 1.1093614101409912 +[2025-04-29 19:41:39,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.7033460736274719, cross_entropy: 0.7033460736274719 +[2025-04-29 19:41:41,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 1.2719049453735352, cross_entropy: 1.2719049453735352 +[2025-04-29 19:41:44,190][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 0.9421379566192627, cross_entropy: 0.9421379566192627 +[2025-04-29 19:41:44,950][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.0671420097351074, cross_entropy: 1.0671420097351074 +[2025-04-29 19:41:48,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 1.3756769895553589, cross_entropy: 1.3756769895553589 +[2025-04-29 19:41:49,029][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.6060097217559814, cross_entropy: 2.6060097217559814 +[2025-04-29 19:41:52,412][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 1.8442752361297607, cross_entropy: 1.8442752361297607 +[2025-04-29 19:41:53,724][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 2.861359119415283, cross_entropy: 2.861359119415283 +[2025-04-29 19:41:57,047][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 0.8944176435470581, cross_entropy: 0.8944176435470581 +[2025-04-29 19:41:57,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 2.3643131256103516, cross_entropy: 2.3643131256103516 +[2025-04-29 19:42:01,135][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 2.6727380752563477, cross_entropy: 2.6727380752563477 +[2025-04-29 19:42:01,491][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.842101812362671, cross_entropy: 2.842101812362671 +[2025-04-29 19:42:04,480][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.7725169658660889, cross_entropy: 1.7725169658660889 +[2025-04-29 19:42:04,911][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 0.6528815031051636, cross_entropy: 0.6528815031051636 +[2025-04-29 19:42:09,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 1.577053427696228, cross_entropy: 1.577053427696228 +[2025-04-29 19:42:09,663][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.772647738456726, cross_entropy: 1.772647738456726 +[2025-04-29 19:42:14,704][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.9333359003067017, cross_entropy: 1.9333359003067017 +[2025-04-29 19:42:15,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 0.7486740350723267, cross_entropy: 0.7486740350723267 +[2025-04-29 19:42:18,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 0.8043391704559326, cross_entropy: 0.8043391704559326 +[2025-04-29 19:42:18,489][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.7958617210388184, cross_entropy: 2.7958617210388184 +[2025-04-29 19:42:22,430][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 2.7084527015686035, cross_entropy: 2.7084527015686035 +[2025-04-29 19:42:22,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 0.9396668672561646, cross_entropy: 0.9396668672561646 +[2025-04-29 19:42:26,136][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 3.0736141204833984, cross_entropy: 3.0736141204833984 +[2025-04-29 19:42:26,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.880295753479004, cross_entropy: 2.880295753479004 +[2025-04-29 19:42:31,689][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.768974542617798, cross_entropy: 2.768974542617798 +[2025-04-29 19:42:32,051][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 2.5114753246307373, cross_entropy: 2.5114753246307373 +[2025-04-29 19:42:36,084][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.9984928369522095, cross_entropy: 0.9984928369522095 +[2025-04-29 19:42:36,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.4792098999023438, cross_entropy: 1.4792098999023438 +[2025-04-29 19:42:40,681][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.5431342124938965, cross_entropy: 2.5431342124938965 +[2025-04-29 19:42:41,042][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 0.6647255420684814, cross_entropy: 0.6647255420684814 +[2025-04-29 19:42:45,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.160271644592285, cross_entropy: 2.160271644592285 +[2025-04-29 19:42:46,321][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 1.4151291847229004, cross_entropy: 1.4151291847229004 +[2025-04-29 19:42:49,798][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 2.499356269836426, cross_entropy: 2.499356269836426 +[2025-04-29 19:42:50,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.9050990343093872, cross_entropy: 0.9050990343093872 +[2025-04-29 19:42:53,441][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 3.077430248260498, cross_entropy: 3.077430248260498 +[2025-04-29 19:42:53,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.0914726257324219, cross_entropy: 1.0914726257324219 +[2025-04-29 19:42:57,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 1.8850818872451782, cross_entropy: 1.8850818872451782 +[2025-04-29 19:42:57,801][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 2.2526626586914062, cross_entropy: 2.2526626586914062 +[2025-04-29 19:43:01,838][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 1.1456530094146729, cross_entropy: 1.1456530094146729 +[2025-04-29 19:43:02,201][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 2.543848991394043, cross_entropy: 2.543848991394043 +[2025-04-29 19:43:05,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.604475498199463, cross_entropy: 2.604475498199463 +[2025-04-29 19:43:06,163][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 2.8732738494873047, cross_entropy: 2.8732738494873047 +[2025-04-29 19:43:10,113][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 1.3548893928527832, cross_entropy: 1.3548893928527832 +[2025-04-29 19:43:10,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.4833767414093018, cross_entropy: 2.4833767414093018 +[2025-04-29 19:43:14,199][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.0737996101379395, cross_entropy: 1.0737996101379395 +[2025-04-29 19:43:14,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 0.9518198370933533, cross_entropy: 0.9518198370933533 +[2025-04-29 19:43:18,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 2.582972526550293, cross_entropy: 2.582972526550293 +[2025-04-29 19:43:18,760][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.1703598499298096, cross_entropy: 1.1703598499298096 +[2025-04-29 19:43:22,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 2.8145837783813477, cross_entropy: 2.8145837783813477 +[2025-04-29 19:43:23,171][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 0.7419871091842651, cross_entropy: 0.7419871091842651 +[2025-04-29 19:43:27,119][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 2.781062126159668, cross_entropy: 2.781062126159668 +[2025-04-29 19:43:27,474][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 0.8606623411178589, cross_entropy: 0.8606623411178589 +[2025-04-29 19:43:31,240][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 1.5563023090362549, cross_entropy: 1.5563023090362549 +[2025-04-29 19:43:31,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.5935781002044678, cross_entropy: 2.5935781002044678 +[2025-04-29 19:43:35,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 2.0857324600219727, cross_entropy: 2.0857324600219727 +[2025-04-29 19:43:35,567][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.197253704071045, cross_entropy: 1.197253704071045 +[2025-04-29 19:43:39,568][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 1.1181706190109253, cross_entropy: 1.1181706190109253 +[2025-04-29 19:43:39,927][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.1310851573944092, cross_entropy: 1.1310851573944092 +[2025-04-29 19:43:43,272][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.2416985034942627, cross_entropy: 1.2416985034942627 +[2025-04-29 19:43:43,594][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 2.625509738922119, cross_entropy: 2.625509738922119 +[2025-04-29 19:43:47,298][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.421715021133423, cross_entropy: 2.421715021133423 +[2025-04-29 19:43:48,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 0.5905110836029053, cross_entropy: 0.5905110836029053 +[2025-04-29 19:43:51,429][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 1.484424352645874, cross_entropy: 1.484424352645874 +[2025-04-29 19:43:52,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 0.9118928909301758, cross_entropy: 0.9118928909301758 +[2025-04-29 19:43:55,131][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 0.8309175968170166, cross_entropy: 0.8309175968170166 +[2025-04-29 19:43:57,594][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 1.6221868991851807, cross_entropy: 1.6221868991851807 +[2025-04-29 19:44:00,221][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 2.374938488006592, cross_entropy: 2.374938488006592 +[2025-04-29 19:44:01,334][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.941653251647949, cross_entropy: 2.941653251647949 +[2025-04-29 19:44:05,862][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.3810157775878906, cross_entropy: 1.3810157775878906 +[2025-04-29 19:44:06,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 2.635035991668701, cross_entropy: 2.635035991668701 +[2025-04-29 19:44:10,175][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.626345634460449, cross_entropy: 2.626345634460449 +[2025-04-29 19:44:10,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 2.536639451980591, cross_entropy: 2.536639451980591 +[2025-04-29 19:44:13,913][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.721454381942749, cross_entropy: 1.721454381942749 +[2025-04-29 19:44:14,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.549220323562622, cross_entropy: 1.549220323562622 +[2025-04-29 19:44:17,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.016202211380005, cross_entropy: 2.016202211380005 +[2025-04-29 19:44:18,229][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.2950477600097656, cross_entropy: 2.2950477600097656 +[2025-04-29 19:44:21,756][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.011066436767578, cross_entropy: 2.011066436767578 +[2025-04-29 19:44:22,329][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.1249659061431885, cross_entropy: 1.1249659061431885 +[2025-04-29 19:44:26,769][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 1.6997346878051758, cross_entropy: 1.6997346878051758 +[2025-04-29 19:44:27,126][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 0.9964860081672668, cross_entropy: 0.9964860081672668 +[2025-04-29 19:44:30,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.3177173137664795, cross_entropy: 1.3177173137664795 +[2025-04-29 19:44:30,784][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 0.831310510635376, cross_entropy: 0.831310510635376 +[2025-04-29 19:44:34,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.2146131992340088, cross_entropy: 1.2146131992340088 +[2025-04-29 19:44:34,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.8697304725646973, cross_entropy: 2.8697304725646973 +[2025-04-29 19:44:39,116][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 0.8422681093215942, cross_entropy: 0.8422681093215942 +[2025-04-29 19:44:39,473][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.3430774211883545, cross_entropy: 1.3430774211883545 +[2025-04-29 19:44:42,734][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 2.2351584434509277, cross_entropy: 2.2351584434509277 +[2025-04-29 19:44:43,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 1.389043927192688, cross_entropy: 1.389043927192688 +[2025-04-29 19:44:46,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.4618594646453857, cross_entropy: 2.4618594646453857 +[2025-04-29 19:44:46,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.2095180749893188, cross_entropy: 1.2095180749893188 +[2025-04-29 19:44:50,842][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 0.9711298942565918, cross_entropy: 0.9711298942565918 +[2025-04-29 19:44:51,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 0.9669744968414307, cross_entropy: 0.9669744968414307 +[2025-04-29 19:44:55,399][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 1.6699657440185547, cross_entropy: 1.6699657440185547 +[2025-04-29 19:44:56,093][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 0.5142017602920532, cross_entropy: 0.5142017602920532 +[2025-04-29 19:44:59,646][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 1.0380949974060059, cross_entropy: 1.0380949974060059 +[2025-04-29 19:45:00,498][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 2.984069347381592, cross_entropy: 2.984069347381592 +[2025-04-29 19:45:03,561][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 1.048471212387085, cross_entropy: 1.048471212387085 +[2025-04-29 19:45:04,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.1063127517700195, cross_entropy: 1.1063127517700195 +[2025-04-29 19:45:07,134][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.3313597440719604, cross_entropy: 1.3313597440719604 +[2025-04-29 19:45:08,875][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 1.2407740354537964, cross_entropy: 1.2407740354537964 +[2025-04-29 19:45:11,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 1.3021719455718994, cross_entropy: 1.3021719455718994 +[2025-04-29 19:45:13,037][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.2095627784729004, cross_entropy: 1.2095627784729004 +[2025-04-29 19:45:15,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.5919148921966553, cross_entropy: 1.5919148921966553 +[2025-04-29 19:45:17,358][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 2.5809006690979004, cross_entropy: 2.5809006690979004 +[2025-04-29 19:45:19,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 2.2420315742492676, cross_entropy: 2.2420315742492676 +[2025-04-29 19:45:21,615][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 0.6911386251449585, cross_entropy: 0.6911386251449585 +[2025-04-29 19:45:22,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 1.03117036819458, cross_entropy: 1.03117036819458 +[2025-04-29 19:45:26,275][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 3.127983808517456, cross_entropy: 3.127983808517456 +[2025-04-29 19:45:26,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 0.9037122130393982, cross_entropy: 0.9037122130393982 +[2025-04-29 19:45:31,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 0.9087519645690918, cross_entropy: 0.9087519645690918 +[2025-04-29 19:45:31,508][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 1.1486908197402954, cross_entropy: 1.1486908197402954 +[2025-04-29 19:45:36,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 1.9768743515014648, cross_entropy: 1.9768743515014648 +[2025-04-29 19:45:36,418][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 3.0496320724487305, cross_entropy: 3.0496320724487305 +[2025-04-29 19:45:40,477][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 1.8733924627304077, cross_entropy: 1.8733924627304077 +[2025-04-29 19:45:40,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 0.790859043598175, cross_entropy: 0.790859043598175 +[2025-04-29 19:45:44,120][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.0998246669769287, cross_entropy: 2.0998246669769287 +[2025-04-29 19:45:44,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 2.39421010017395, cross_entropy: 2.39421010017395 +[2025-04-29 19:45:48,229][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.9324984550476074, cross_entropy: 2.9324984550476074 +[2025-04-29 19:45:48,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 1.3304805755615234, cross_entropy: 1.3304805755615234 +[2025-04-29 19:45:52,048][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 1.3269555568695068, cross_entropy: 1.3269555568695068 +[2025-04-29 19:45:52,410][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.420604944229126, cross_entropy: 1.420604944229126 +[2025-04-29 19:45:57,078][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 3.0992064476013184, cross_entropy: 3.0992064476013184 +[2025-04-29 19:45:57,402][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 2.340245485305786, cross_entropy: 2.340245485305786 +[2025-04-29 19:46:03,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 0.8687698245048523, cross_entropy: 0.8687698245048523 +[2025-04-29 19:46:03,523][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 1.3349733352661133, cross_entropy: 1.3349733352661133 +[2025-04-29 19:46:07,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.7748311758041382, cross_entropy: 1.7748311758041382 +[2025-04-29 19:46:07,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 2.6070237159729004, cross_entropy: 2.6070237159729004 +[2025-04-29 19:46:11,375][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 2.2671380043029785, cross_entropy: 2.2671380043029785 +[2025-04-29 19:46:11,738][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.0834848880767822, cross_entropy: 1.0834848880767822 +[2025-04-29 19:46:15,603][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 3.0330467224121094, cross_entropy: 3.0330467224121094 +[2025-04-29 19:46:15,968][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 2.352079153060913, cross_entropy: 2.352079153060913 +[2025-04-29 19:46:19,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 0.9424527883529663, cross_entropy: 0.9424527883529663 +[2025-04-29 19:46:19,571][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 1.2551456689834595, cross_entropy: 1.2551456689834595 +[2025-04-29 19:46:23,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 1.6043370962142944, cross_entropy: 1.6043370962142944 +[2025-04-29 19:46:23,770][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 2.659194231033325, cross_entropy: 2.659194231033325 +[2025-04-29 19:46:27,491][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 2.6564383506774902, cross_entropy: 2.6564383506774902 +[2025-04-29 19:46:27,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 0.910752534866333, cross_entropy: 0.910752534866333 +[2025-04-29 19:46:31,424][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 2.7332119941711426, cross_entropy: 2.7332119941711426 +[2025-04-29 19:46:31,786][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 1.5539785623550415, cross_entropy: 1.5539785623550415 +[2025-04-29 19:46:35,962][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 0.7293137311935425, cross_entropy: 0.7293137311935425 +[2025-04-29 19:46:36,319][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 0.9417610168457031, cross_entropy: 0.9417610168457031 +[2025-04-29 19:46:39,577][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 2.0553386211395264, cross_entropy: 2.0553386211395264 +[2025-04-29 19:46:39,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 3.3031201362609863, cross_entropy: 3.3031201362609863 +[2025-04-29 19:46:44,888][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.0902389287948608, cross_entropy: 1.0902389287948608 +[2025-04-29 19:46:45,264][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 2.2124850749969482, cross_entropy: 2.2124850749969482 +[2025-04-29 19:46:49,241][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 2.9957265853881836, cross_entropy: 2.9957265853881836 +[2025-04-29 19:46:49,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 1.733027458190918, cross_entropy: 1.733027458190918 +[2025-04-29 19:46:53,123][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.4974005222320557, cross_entropy: 1.4974005222320557 +[2025-04-29 19:46:53,480][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 2.4024739265441895, cross_entropy: 2.4024739265441895 +[2025-04-29 19:46:57,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 2.7861804962158203, cross_entropy: 2.7861804962158203 +[2025-04-29 19:46:57,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 2.7302608489990234, cross_entropy: 2.7302608489990234 +[2025-04-29 19:47:01,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 2.54140043258667, cross_entropy: 2.54140043258667 +[2025-04-29 19:47:02,232][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 2.7532310485839844, cross_entropy: 2.7532310485839844 +[2025-04-29 19:47:06,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 3.0316362380981445, cross_entropy: 3.0316362380981445 +[2025-04-29 19:47:06,658][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 1.4290459156036377, cross_entropy: 1.4290459156036377 +[2025-04-29 19:47:11,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 1.1457619667053223, cross_entropy: 1.1457619667053223 +[2025-04-29 19:47:11,881][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 1.154050588607788, cross_entropy: 1.154050588607788 +[2025-04-29 19:47:16,152][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 2.943373203277588, cross_entropy: 2.943373203277588 +[2025-04-29 19:47:16,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.9712908267974854, cross_entropy: 2.9712908267974854 +[2025-04-29 19:47:20,309][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 2.5446345806121826, cross_entropy: 2.5446345806121826 +[2025-04-29 19:47:20,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 2.1421751976013184, cross_entropy: 2.1421751976013184 +[2025-04-29 19:47:23,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 1.0595319271087646, cross_entropy: 1.0595319271087646 +[2025-04-29 19:47:24,197][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 2.9884867668151855, cross_entropy: 2.9884867668151855 +[2025-04-29 19:47:27,795][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 0.9489229917526245, cross_entropy: 0.9489229917526245 +[2025-04-29 19:47:28,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 1.4260995388031006, cross_entropy: 1.4260995388031006 +[2025-04-29 19:47:31,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.0715038776397705, cross_entropy: 1.0715038776397705 +[2025-04-29 19:47:31,926][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 2.524404525756836, cross_entropy: 2.524404525756836 +[2025-04-29 19:47:35,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.8871631622314453, cross_entropy: 1.8871631622314453 +[2025-04-29 19:47:36,183][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 1.247102975845337, cross_entropy: 1.247102975845337 +[2025-04-29 19:47:40,118][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 3.0178816318511963, cross_entropy: 3.0178816318511963 +[2025-04-29 19:47:40,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 2.7688755989074707, cross_entropy: 2.7688755989074707 +[2025-04-29 19:47:44,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 1.1001431941986084, cross_entropy: 1.1001431941986084 +[2025-04-29 19:47:44,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 2.0913760662078857, cross_entropy: 2.0913760662078857 +[2025-04-29 19:47:48,616][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.6967540979385376, cross_entropy: 1.6967540979385376 +[2025-04-29 19:47:49,045][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.5945918560028076, cross_entropy: 1.5945918560028076 +[2025-04-29 19:47:54,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 1.8635339736938477, cross_entropy: 1.8635339736938477 +[2025-04-29 19:47:54,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.29988694190979, cross_entropy: 2.29988694190979 +[2025-04-29 19:47:58,130][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 1.3853747844696045, cross_entropy: 1.3853747844696045 +[2025-04-29 19:47:58,490][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 0.8933855891227722, cross_entropy: 0.8933855891227722 +[2025-04-29 19:48:02,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 2.0203750133514404, cross_entropy: 2.0203750133514404 +[2025-04-29 19:48:03,185][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 1.0929204225540161, cross_entropy: 1.0929204225540161 +[2025-04-29 19:48:07,375][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 3.111861228942871, cross_entropy: 3.111861228942871 +[2025-04-29 19:48:07,736][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 0.850247859954834, cross_entropy: 0.850247859954834 +[2025-04-29 19:48:11,374][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 1.2292497158050537, cross_entropy: 1.2292497158050537 +[2025-04-29 19:48:11,736][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 0.9475597143173218, cross_entropy: 0.9475597143173218 +[2025-04-29 19:48:16,315][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 1.4271385669708252, cross_entropy: 1.4271385669708252 +[2025-04-29 19:48:16,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.5980969667434692, cross_entropy: 1.5980969667434692 +[2025-04-29 19:48:20,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 0.8787039518356323, cross_entropy: 0.8787039518356323 +[2025-04-29 19:48:21,216][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.5985937118530273, cross_entropy: 2.5985937118530273 +[2025-04-29 19:48:25,438][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 1.2242375612258911, cross_entropy: 1.2242375612258911 +[2025-04-29 19:48:25,764][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.9474425315856934, cross_entropy: 2.9474425315856934 +[2025-04-29 19:48:29,475][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 1.6885545253753662, cross_entropy: 1.6885545253753662 +[2025-04-29 19:48:29,840][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 1.4699761867523193, cross_entropy: 1.4699761867523193 +[2025-04-29 19:48:33,585][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 1.4755573272705078, cross_entropy: 1.4755573272705078 +[2025-04-29 19:48:33,944][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 3.0627341270446777, cross_entropy: 3.0627341270446777 +[2025-04-29 19:48:37,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 1.1965034008026123, cross_entropy: 1.1965034008026123 +[2025-04-29 19:48:38,335][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 1.470266580581665, cross_entropy: 1.470266580581665 +[2025-04-29 19:48:42,147][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 1.7237414121627808, cross_entropy: 1.7237414121627808 +[2025-04-29 19:48:42,497][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 2.9522221088409424, cross_entropy: 2.9522221088409424 +[2025-04-29 19:48:47,082][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.861295700073242, cross_entropy: 2.861295700073242 +[2025-04-29 19:48:47,444][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 3.1171059608459473, cross_entropy: 3.1171059608459473 +[2025-04-29 19:48:51,036][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 0.8420540690422058, cross_entropy: 0.8420540690422058 +[2025-04-29 19:48:51,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 0.8278967142105103, cross_entropy: 0.8278967142105103 +[2025-04-29 19:48:55,154][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 0.6027771234512329, cross_entropy: 0.6027771234512329 +[2025-04-29 19:48:55,518][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 1.0477509498596191, cross_entropy: 1.0477509498596191 +[2025-04-29 19:48:59,304][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.0320391654968262, cross_entropy: 1.0320391654968262 +[2025-04-29 19:48:59,669][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 0.7335785627365112, cross_entropy: 0.7335785627365112 +[2025-04-29 19:49:02,838][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 1.3969651460647583, cross_entropy: 1.3969651460647583 +[2025-04-29 19:49:03,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.1550651788711548, cross_entropy: 1.1550651788711548 +[2025-04-29 19:49:07,256][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.6204981803894043, cross_entropy: 2.6204981803894043 +[2025-04-29 19:49:07,613][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.4826958179473877, cross_entropy: 1.4826958179473877 +[2025-04-29 19:49:11,518][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 0.7753846645355225, cross_entropy: 0.7753846645355225 +[2025-04-29 19:49:11,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 0.8730543851852417, cross_entropy: 0.8730543851852417 +[2025-04-29 19:49:15,589][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 0.8899717330932617, cross_entropy: 0.8899717330932617 +[2025-04-29 19:49:15,966][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 2.6865615844726562, cross_entropy: 2.6865615844726562 +[2025-04-29 19:49:20,530][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 0.7841485738754272, cross_entropy: 0.7841485738754272 +[2025-04-29 19:49:20,892][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 1.3467612266540527, cross_entropy: 1.3467612266540527 +[2025-04-29 19:49:24,085][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 2.384368896484375, cross_entropy: 2.384368896484375 +[2025-04-29 19:49:24,445][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.9447786808013916, cross_entropy: 2.9447786808013916 +[2025-04-29 19:49:28,079][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.708658456802368, cross_entropy: 2.708658456802368 +[2025-04-29 19:49:28,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 2.480573892593384, cross_entropy: 2.480573892593384 +[2025-04-29 19:49:32,089][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 0.9976973533630371, cross_entropy: 0.9976973533630371 +[2025-04-29 19:49:32,417][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 3.0424304008483887, cross_entropy: 3.0424304008483887 +[2025-04-29 19:49:36,083][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.576132297515869, cross_entropy: 2.576132297515869 +[2025-04-29 19:49:36,441][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.798401355743408, cross_entropy: 2.798401355743408 +[2025-04-29 19:49:40,555][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 2.6195120811462402, cross_entropy: 2.6195120811462402 +[2025-04-29 19:49:40,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 2.515571117401123, cross_entropy: 2.515571117401123 +[2025-04-29 19:49:44,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 0.9335566759109497, cross_entropy: 0.9335566759109497 +[2025-04-29 19:49:45,529][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.972883701324463, cross_entropy: 2.972883701324463 +[2025-04-29 19:49:49,658][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.690031051635742, cross_entropy: 2.690031051635742 +[2025-04-29 19:49:50,047][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 2.4230785369873047, cross_entropy: 2.4230785369873047 +[2025-04-29 19:49:53,913][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 2.2601845264434814, cross_entropy: 2.2601845264434814 +[2025-04-29 19:49:54,274][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.2301784753799438, cross_entropy: 1.2301784753799438 +[2025-04-29 19:49:57,557][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.9813506603240967, cross_entropy: 1.9813506603240967 +[2025-04-29 19:49:58,090][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 3.1105666160583496, cross_entropy: 3.1105666160583496 +[2025-04-29 19:50:02,232][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 0.6233866214752197, cross_entropy: 0.6233866214752197 +[2025-04-29 19:50:03,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 1.5602840185165405, cross_entropy: 1.5602840185165405 +[2025-04-29 19:50:06,504][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 1.498814582824707, cross_entropy: 1.498814582824707 +[2025-04-29 19:50:08,253][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.1458864212036133, cross_entropy: 2.1458864212036133 +[2025-04-29 19:50:10,872][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 2.813763380050659, cross_entropy: 2.813763380050659 +[2025-04-29 19:50:12,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 2.6696109771728516, cross_entropy: 2.6696109771728516 +[2025-04-29 19:50:14,714][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 1.0165081024169922, cross_entropy: 1.0165081024169922 +[2025-04-29 19:50:16,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 1.9664771556854248, cross_entropy: 1.9664771556854248 +[2025-04-29 19:50:19,081][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 1.3195021152496338, cross_entropy: 1.3195021152496338 +[2025-04-29 19:50:20,577][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 1.0685296058654785, cross_entropy: 1.0685296058654785 +[2025-04-29 19:50:23,458][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 1.9460424184799194, cross_entropy: 1.9460424184799194 +[2025-04-29 19:50:25,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 1.2759164571762085, cross_entropy: 1.2759164571762085 +[2025-04-29 19:50:27,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.0719175338745117, cross_entropy: 2.0719175338745117 +[2025-04-29 19:50:30,326][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.0031585693359375, cross_entropy: 2.0031585693359375 +[2025-04-29 19:50:31,758][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 0.893537700176239, cross_entropy: 0.893537700176239 +[2025-04-29 19:50:33,918][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 0.6683905124664307, cross_entropy: 0.6683905124664307 +[2025-04-29 19:50:36,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 2.1627330780029297, cross_entropy: 2.1627330780029297 +[2025-04-29 19:50:37,852][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 1.159703016281128, cross_entropy: 1.159703016281128 +[2025-04-29 19:50:40,058][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 2.3261332511901855, cross_entropy: 2.3261332511901855 +[2025-04-29 19:50:42,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 0.6213421821594238, cross_entropy: 0.6213421821594238 +[2025-04-29 19:50:44,540][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 0.871089518070221, cross_entropy: 0.871089518070221 +[2025-04-29 19:50:46,161][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.7799134254455566, cross_entropy: 2.7799134254455566 +[2025-04-29 19:50:48,683][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.851745128631592, cross_entropy: 2.851745128631592 +[2025-04-29 19:50:50,838][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 0.9272617101669312, cross_entropy: 0.9272617101669312 +[2025-04-29 19:50:53,412][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 1.3588923215866089, cross_entropy: 1.3588923215866089 +[2025-04-29 19:50:55,207][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 1.837538480758667, cross_entropy: 1.837538480758667 +[2025-04-29 19:50:58,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.7615318298339844, cross_entropy: 1.7615318298339844 +[2025-04-29 19:50:59,253][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 2.7465970516204834, cross_entropy: 2.7465970516204834 +[2025-04-29 19:51:02,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 3.0795469284057617, cross_entropy: 3.0795469284057617 +[2025-04-29 19:51:03,470][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.2128653526306152, cross_entropy: 1.2128653526306152 +[2025-04-29 19:51:06,714][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 2.9457056522369385, cross_entropy: 2.9457056522369385 +[2025-04-29 19:51:08,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.5632405281066895, cross_entropy: 1.5632405281066895 +[2025-04-29 19:51:11,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 1.2710039615631104, cross_entropy: 1.2710039615631104 +[2025-04-29 19:51:12,695][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 3.0781898498535156, cross_entropy: 3.0781898498535156 +[2025-04-29 19:51:14,634][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 1.3551051616668701, cross_entropy: 1.3551051616668701 +[2025-04-29 19:51:18,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.57818865776062, cross_entropy: 2.57818865776062 +[2025-04-29 19:51:18,830][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 0.7938547134399414, cross_entropy: 0.7938547134399414 +[2025-04-29 19:51:22,312][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 2.580012798309326, cross_entropy: 2.580012798309326 +[2025-04-29 19:51:22,681][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.717534303665161, cross_entropy: 2.717534303665161 +[2025-04-29 19:51:27,677][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 1.426784634590149, cross_entropy: 1.426784634590149 +[2025-04-29 19:51:28,033][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.2270898818969727, cross_entropy: 1.2270898818969727 +[2025-04-29 19:51:31,557][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 0.9840327501296997, cross_entropy: 0.9840327501296997 +[2025-04-29 19:51:31,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.9816080331802368, cross_entropy: 0.9816080331802368 +[2025-04-29 19:51:35,704][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 2.22385835647583, cross_entropy: 2.22385835647583 +[2025-04-29 19:51:36,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 2.3244128227233887, cross_entropy: 2.3244128227233887 +[2025-04-29 19:51:39,577][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 2.589657783508301, cross_entropy: 2.589657783508301 +[2025-04-29 19:51:39,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.857580542564392, cross_entropy: 1.857580542564392 +[2025-04-29 19:51:43,187][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 2.9143640995025635, cross_entropy: 2.9143640995025635 +[2025-04-29 19:51:43,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 0.9844890832901001, cross_entropy: 0.9844890832901001 +[2025-04-29 19:51:47,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 1.460632562637329, cross_entropy: 1.460632562637329 +[2025-04-29 19:51:47,940][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 0.7940105199813843, cross_entropy: 0.7940105199813843 +[2025-04-29 19:51:52,051][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 2.899916172027588, cross_entropy: 2.899916172027588 +[2025-04-29 19:51:52,552][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 2.2644529342651367, cross_entropy: 2.2644529342651367 +[2025-04-29 19:51:57,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.9313337802886963, cross_entropy: 0.9313337802886963 +[2025-04-29 19:51:57,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 2.1259846687316895, cross_entropy: 2.1259846687316895 +[2025-04-29 19:52:01,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.9570073485374451, cross_entropy: 0.9570073485374451 +[2025-04-29 19:52:01,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 1.6119682788848877, cross_entropy: 1.6119682788848877 +[2025-04-29 19:52:05,589][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.2591201066970825, cross_entropy: 1.2591201066970825 +[2025-04-29 19:52:05,941][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 2.03275728225708, cross_entropy: 2.03275728225708 +[2025-04-29 19:52:09,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 1.3788073062896729, cross_entropy: 1.3788073062896729 +[2025-04-29 19:52:09,368][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 1.9951297044754028, cross_entropy: 1.9951297044754028 +[2025-04-29 19:52:13,269][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 2.895321846008301, cross_entropy: 2.895321846008301 +[2025-04-29 19:52:13,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.6124054193496704, cross_entropy: 1.6124054193496704 +[2025-04-29 19:52:17,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.3978666067123413, cross_entropy: 1.3978666067123413 +[2025-04-29 19:52:17,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 2.2153866291046143, cross_entropy: 2.2153866291046143 +[2025-04-29 19:52:20,554][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 1.0572506189346313, cross_entropy: 1.0572506189346313 +[2025-04-29 19:52:21,711][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.1235822439193726, cross_entropy: 1.1235822439193726 +[2025-04-29 19:52:24,292][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 3.0359177589416504, cross_entropy: 3.0359177589416504 +[2025-04-29 19:52:25,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 0.8541476130485535, cross_entropy: 0.8541476130485535 +[2025-04-29 19:52:28,726][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 2.7444190979003906, cross_entropy: 2.7444190979003906 +[2025-04-29 19:52:29,230][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 0.9318966865539551, cross_entropy: 0.9318966865539551 +[2025-04-29 19:52:34,121][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 3.1547398567199707, cross_entropy: 3.1547398567199707 +[2025-04-29 19:52:34,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.1927483081817627, cross_entropy: 1.1927483081817627 +[2025-04-29 19:52:37,863][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 0.7934877872467041, cross_entropy: 0.7934877872467041 +[2025-04-29 19:52:38,223][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.9738966226577759, cross_entropy: 0.9738966226577759 +[2025-04-29 19:52:42,433][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 0.785700798034668, cross_entropy: 0.785700798034668 +[2025-04-29 19:52:42,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.8722929954528809, cross_entropy: 1.8722929954528809 +[2025-04-29 19:52:46,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 2.686326503753662, cross_entropy: 2.686326503753662 +[2025-04-29 19:52:47,023][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 2.7381811141967773, cross_entropy: 2.7381811141967773 +[2025-04-29 19:52:50,374][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 2.1908037662506104, cross_entropy: 2.1908037662506104 +[2025-04-29 19:52:50,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 1.8960119485855103, cross_entropy: 1.8960119485855103 +[2025-04-29 19:52:54,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.91725492477417, cross_entropy: 2.91725492477417 +[2025-04-29 19:52:55,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.19355046749115, cross_entropy: 1.19355046749115 +[2025-04-29 19:52:59,420][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 2.392285108566284, cross_entropy: 2.392285108566284 +[2025-04-29 19:52:59,818][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 2.6841206550598145, cross_entropy: 2.6841206550598145 +[2025-04-29 19:53:04,088][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 1.4826449155807495, cross_entropy: 1.4826449155807495 +[2025-04-29 19:53:04,447][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.3102099895477295, cross_entropy: 1.3102099895477295 +[2025-04-29 19:53:07,863][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 1.75827956199646, cross_entropy: 1.75827956199646 +[2025-04-29 19:53:08,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 0.8823226690292358, cross_entropy: 0.8823226690292358 +[2025-04-29 19:53:12,000][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.6998045444488525, cross_entropy: 1.6998045444488525 +[2025-04-29 19:53:12,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 0.983739972114563, cross_entropy: 0.983739972114563 +[2025-04-29 19:53:15,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 1.235134243965149, cross_entropy: 1.235134243965149 +[2025-04-29 19:53:16,347][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.3105201721191406, cross_entropy: 2.3105201721191406 +[2025-04-29 19:53:19,938][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 2.0020804405212402, cross_entropy: 2.0020804405212402 +[2025-04-29 19:53:20,226][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 2.4140725135803223, cross_entropy: 2.4140725135803223 +[2025-04-29 19:56:31,377][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.805271029472351, cross_entropy: 1.805271029472351 +[2025-04-29 19:56:31,378][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.2603130340576172, cross_entropy: 1.2603130340576172 +[2025-04-29 19:56:31,563][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch8.pth. +[2025-04-29 19:56:31,809][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 19:56:36,805][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.0544672012329102, cross_entropy: 1.0544672012329102 +[2025-04-29 19:56:37,163][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.6961944103240967, cross_entropy: 1.6961944103240967 +[2025-04-29 19:56:40,787][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 2.877232074737549, cross_entropy: 2.877232074737549 +[2025-04-29 19:56:41,142][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 1.0003390312194824, cross_entropy: 1.0003390312194824 +[2025-04-29 19:56:44,867][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 0.8614007830619812, cross_entropy: 0.8614007830619812 +[2025-04-29 19:56:45,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 0.9866503477096558, cross_entropy: 0.9866503477096558 +[2025-04-29 19:56:48,558][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.8231201171875, cross_entropy: 2.8231201171875 +[2025-04-29 19:56:48,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 1.6330339908599854, cross_entropy: 1.6330339908599854 +[2025-04-29 19:56:52,953][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 1.9914593696594238, cross_entropy: 1.9914593696594238 +[2025-04-29 19:56:53,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 0.819717288017273, cross_entropy: 0.819717288017273 +[2025-04-29 19:56:56,696][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.0175002813339233, cross_entropy: 1.0175002813339233 +[2025-04-29 19:56:57,758][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 1.9491605758666992, cross_entropy: 1.9491605758666992 +[2025-04-29 19:57:01,248][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 0.9052455425262451, cross_entropy: 0.9052455425262451 +[2025-04-29 19:57:01,656][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 1.8687725067138672, cross_entropy: 1.8687725067138672 +[2025-04-29 19:57:05,271][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 0.6724100112915039, cross_entropy: 0.6724100112915039 +[2025-04-29 19:57:05,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.8106868267059326, cross_entropy: 0.8106868267059326 +[2025-04-29 19:57:09,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 2.359339475631714, cross_entropy: 2.359339475631714 +[2025-04-29 19:57:10,173][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.1779916286468506, cross_entropy: 1.1779916286468506 +[2025-04-29 19:57:13,412][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 2.599924087524414, cross_entropy: 2.599924087524414 +[2025-04-29 19:57:13,817][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.094208836555481, cross_entropy: 1.094208836555481 +[2025-04-29 19:57:19,771][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.0503478050231934, cross_entropy: 1.0503478050231934 +[2025-04-29 19:57:20,134][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 0.7646804451942444, cross_entropy: 0.7646804451942444 +[2025-04-29 19:57:23,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 0.9630051255226135, cross_entropy: 0.9630051255226135 +[2025-04-29 19:57:24,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 1.4648596048355103, cross_entropy: 1.4648596048355103 +[2025-04-29 19:57:27,133][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 1.535524845123291, cross_entropy: 1.535524845123291 +[2025-04-29 19:57:27,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 0.9078655242919922, cross_entropy: 0.9078655242919922 +[2025-04-29 19:57:31,669][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 2.6811728477478027, cross_entropy: 2.6811728477478027 +[2025-04-29 19:57:32,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 1.4925129413604736, cross_entropy: 1.4925129413604736 +[2025-04-29 19:57:36,259][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.142594814300537, cross_entropy: 2.142594814300537 +[2025-04-29 19:57:36,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 2.580209255218506, cross_entropy: 2.580209255218506 +[2025-04-29 19:57:39,835][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.737696409225464, cross_entropy: 2.737696409225464 +[2025-04-29 19:57:40,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 2.6760196685791016, cross_entropy: 2.6760196685791016 +[2025-04-29 19:57:43,525][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.278311014175415, cross_entropy: 1.278311014175415 +[2025-04-29 19:57:43,883][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.519841194152832, cross_entropy: 2.519841194152832 +[2025-04-29 19:57:47,455][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 2.93117356300354, cross_entropy: 2.93117356300354 +[2025-04-29 19:57:47,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 2.938403367996216, cross_entropy: 2.938403367996216 +[2025-04-29 19:57:51,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 2.6216535568237305, cross_entropy: 2.6216535568237305 +[2025-04-29 19:57:51,684][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 1.4951695203781128, cross_entropy: 1.4951695203781128 +[2025-04-29 19:57:56,345][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.7559340000152588, cross_entropy: 1.7559340000152588 +[2025-04-29 19:57:56,702][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.4114108085632324, cross_entropy: 2.4114108085632324 +[2025-04-29 19:58:00,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 1.206465482711792, cross_entropy: 1.206465482711792 +[2025-04-29 19:58:00,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 3.1126468181610107, cross_entropy: 3.1126468181610107 +[2025-04-29 19:58:05,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.864959716796875, cross_entropy: 2.864959716796875 +[2025-04-29 19:58:05,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 2.7392396926879883, cross_entropy: 2.7392396926879883 +[2025-04-29 19:58:09,569][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 2.831238031387329, cross_entropy: 2.831238031387329 +[2025-04-29 19:58:09,922][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 0.7640106678009033, cross_entropy: 0.7640106678009033 +[2025-04-29 19:58:14,084][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 2.500274419784546, cross_entropy: 2.500274419784546 +[2025-04-29 19:58:14,443][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 0.9669175148010254, cross_entropy: 0.9669175148010254 +[2025-04-29 19:58:18,381][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 2.5415024757385254, cross_entropy: 2.5415024757385254 +[2025-04-29 19:58:18,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 1.0254204273223877, cross_entropy: 1.0254204273223877 +[2025-04-29 19:58:22,387][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.2227156162261963, cross_entropy: 1.2227156162261963 +[2025-04-29 19:58:22,748][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 0.8124065399169922, cross_entropy: 0.8124065399169922 +[2025-04-29 19:58:26,414][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 1.9900273084640503, cross_entropy: 1.9900273084640503 +[2025-04-29 19:58:26,773][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 2.1730120182037354, cross_entropy: 2.1730120182037354 +[2025-04-29 19:58:30,486][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 2.857386350631714, cross_entropy: 2.857386350631714 +[2025-04-29 19:58:30,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 0.6176844239234924, cross_entropy: 0.6176844239234924 +[2025-04-29 19:58:34,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.5616233348846436, cross_entropy: 1.5616233348846436 +[2025-04-29 19:58:34,938][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 1.5512464046478271, cross_entropy: 1.5512464046478271 +[2025-04-29 19:58:38,427][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 2.773538589477539, cross_entropy: 2.773538589477539 +[2025-04-29 19:58:38,787][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 1.3057280778884888, cross_entropy: 1.3057280778884888 +[2025-04-29 19:58:41,671][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 0.6668903827667236, cross_entropy: 0.6668903827667236 +[2025-04-29 19:58:42,026][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 0.5966335535049438, cross_entropy: 0.5966335535049438 +[2025-04-29 19:58:45,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 2.634761333465576, cross_entropy: 2.634761333465576 +[2025-04-29 19:58:46,095][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.7351347208023071, cross_entropy: 1.7351347208023071 +[2025-04-29 19:58:49,510][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.452622890472412, cross_entropy: 2.452622890472412 +[2025-04-29 19:58:49,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 2.096733570098877, cross_entropy: 2.096733570098877 +[2025-04-29 19:58:53,410][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 1.3704396486282349, cross_entropy: 1.3704396486282349 +[2025-04-29 19:58:53,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 2.661210775375366, cross_entropy: 2.661210775375366 +[2025-04-29 19:58:56,964][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 0.7091244459152222, cross_entropy: 0.7091244459152222 +[2025-04-29 19:58:57,286][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 0.8301049470901489, cross_entropy: 0.8301049470901489 +[2025-04-29 19:59:00,988][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 2.422028064727783, cross_entropy: 2.422028064727783 +[2025-04-29 19:59:01,313][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.1874535083770752, cross_entropy: 1.1874535083770752 +[2025-04-29 19:59:05,985][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.2735228538513184, cross_entropy: 1.2735228538513184 +[2025-04-29 19:59:06,307][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 2.6081626415252686, cross_entropy: 2.6081626415252686 +[2025-04-29 19:59:10,389][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.0319321155548096, cross_entropy: 2.0319321155548096 +[2025-04-29 19:59:10,756][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 1.7361526489257812, cross_entropy: 1.7361526489257812 +[2025-04-29 19:59:14,393][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 2.8733105659484863, cross_entropy: 2.8733105659484863 +[2025-04-29 19:59:14,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.8468717932701111, cross_entropy: 0.8468717932701111 +[2025-04-29 19:59:18,623][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 1.3312575817108154, cross_entropy: 1.3312575817108154 +[2025-04-29 19:59:18,945][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 2.4767370223999023, cross_entropy: 2.4767370223999023 +[2025-04-29 19:59:22,650][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.0161210298538208, cross_entropy: 1.0161210298538208 +[2025-04-29 19:59:23,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 2.7036056518554688, cross_entropy: 2.7036056518554688 +[2025-04-29 19:59:26,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 0.8789598941802979, cross_entropy: 0.8789598941802979 +[2025-04-29 19:59:26,702][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 0.8410902619361877, cross_entropy: 0.8410902619361877 +[2025-04-29 19:59:30,621][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.7837274074554443, cross_entropy: 1.7837274074554443 +[2025-04-29 19:59:30,967][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 0.794934868812561, cross_entropy: 0.794934868812561 +[2025-04-29 19:59:35,877][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 1.3941729068756104, cross_entropy: 1.3941729068756104 +[2025-04-29 19:59:36,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.3599199056625366, cross_entropy: 1.3599199056625366 +[2025-04-29 19:59:40,212][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 1.0138256549835205, cross_entropy: 1.0138256549835205 +[2025-04-29 19:59:40,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 0.7892630100250244, cross_entropy: 0.7892630100250244 +[2025-04-29 19:59:43,821][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 0.99739670753479, cross_entropy: 0.99739670753479 +[2025-04-29 19:59:44,180][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 2.6806857585906982, cross_entropy: 2.6806857585906982 +[2025-04-29 19:59:47,530][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.6905581951141357, cross_entropy: 2.6905581951141357 +[2025-04-29 19:59:47,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.986102283000946, cross_entropy: 0.986102283000946 +[2025-04-29 19:59:51,699][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.7286667823791504, cross_entropy: 2.7286667823791504 +[2025-04-29 19:59:52,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 2.7518372535705566, cross_entropy: 2.7518372535705566 +[2025-04-29 19:59:55,509][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 2.3786780834198, cross_entropy: 2.3786780834198 +[2025-04-29 19:59:55,933][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 0.9209766387939453, cross_entropy: 0.9209766387939453 +[2025-04-29 19:59:59,431][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 2.052216053009033, cross_entropy: 2.052216053009033 +[2025-04-29 19:59:59,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.1371740102767944, cross_entropy: 1.1371740102767944 +[2025-04-29 20:00:04,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.7831811904907227, cross_entropy: 2.7831811904907227 +[2025-04-29 20:00:04,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 0.8067235350608826, cross_entropy: 0.8067235350608826 +[2025-04-29 20:00:08,704][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.5478742122650146, cross_entropy: 1.5478742122650146 +[2025-04-29 20:00:09,026][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.051284074783325, cross_entropy: 2.051284074783325 +[2025-04-29 20:00:12,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 2.304680347442627, cross_entropy: 2.304680347442627 +[2025-04-29 20:00:13,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 0.8806444406509399, cross_entropy: 0.8806444406509399 +[2025-04-29 20:00:17,290][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 1.2773756980895996, cross_entropy: 1.2773756980895996 +[2025-04-29 20:00:17,644][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.8590635061264038, cross_entropy: 0.8590635061264038 +[2025-04-29 20:00:21,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 2.4663186073303223, cross_entropy: 2.4663186073303223 +[2025-04-29 20:00:21,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.6656569242477417, cross_entropy: 0.6656569242477417 +[2025-04-29 20:00:25,813][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 1.0668015480041504, cross_entropy: 1.0668015480041504 +[2025-04-29 20:00:26,168][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 0.8130373358726501, cross_entropy: 0.8130373358726501 +[2025-04-29 20:00:30,773][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 1.7807142734527588, cross_entropy: 1.7807142734527588 +[2025-04-29 20:00:31,131][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.6338789463043213, cross_entropy: 1.6338789463043213 +[2025-04-29 20:00:35,915][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.919177770614624, cross_entropy: 2.919177770614624 +[2025-04-29 20:00:36,381][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 2.3876326084136963, cross_entropy: 2.3876326084136963 +[2025-04-29 20:00:40,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 1.3425652980804443, cross_entropy: 1.3425652980804443 +[2025-04-29 20:00:40,846][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 0.9763678312301636, cross_entropy: 0.9763678312301636 +[2025-04-29 20:00:44,976][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.287508487701416, cross_entropy: 2.287508487701416 +[2025-04-29 20:00:45,320][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.671693801879883, cross_entropy: 2.671693801879883 +[2025-04-29 20:00:49,220][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.7630398273468018, cross_entropy: 2.7630398273468018 +[2025-04-29 20:00:49,572][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 0.7138699889183044, cross_entropy: 0.7138699889183044 +[2025-04-29 20:00:53,696][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.873368740081787, cross_entropy: 2.873368740081787 +[2025-04-29 20:00:54,019][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 1.2197022438049316, cross_entropy: 1.2197022438049316 +[2025-04-29 20:00:57,602][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 2.3544363975524902, cross_entropy: 2.3544363975524902 +[2025-04-29 20:00:57,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 2.706127405166626, cross_entropy: 2.706127405166626 +[2025-04-29 20:01:01,335][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 1.988316297531128, cross_entropy: 1.988316297531128 +[2025-04-29 20:01:01,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 0.7868449687957764, cross_entropy: 0.7868449687957764 +[2025-04-29 20:01:05,130][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 2.731849431991577, cross_entropy: 2.731849431991577 +[2025-04-29 20:01:05,488][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 1.1216022968292236, cross_entropy: 1.1216022968292236 +[2025-04-29 20:01:09,888][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 0.8136438727378845, cross_entropy: 0.8136438727378845 +[2025-04-29 20:01:10,245][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 1.2631019353866577, cross_entropy: 1.2631019353866577 +[2025-04-29 20:01:13,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.1253496408462524, cross_entropy: 1.1253496408462524 +[2025-04-29 20:01:14,151][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 0.7972164154052734, cross_entropy: 0.7972164154052734 +[2025-04-29 20:01:17,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.0764830112457275, cross_entropy: 1.0764830112457275 +[2025-04-29 20:01:17,885][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 0.7930099964141846, cross_entropy: 0.7930099964141846 +[2025-04-29 20:01:21,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.5913870334625244, cross_entropy: 2.5913870334625244 +[2025-04-29 20:01:22,134][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 2.8472509384155273, cross_entropy: 2.8472509384155273 +[2025-04-29 20:01:25,875][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.6521425247192383, cross_entropy: 2.6521425247192383 +[2025-04-29 20:01:26,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.3109920024871826, cross_entropy: 2.3109920024871826 +[2025-04-29 20:01:29,293][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.7639846801757812, cross_entropy: 2.7639846801757812 +[2025-04-29 20:01:29,651][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.518280267715454, cross_entropy: 2.518280267715454 +[2025-04-29 20:01:33,725][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.2228407859802246, cross_entropy: 2.2228407859802246 +[2025-04-29 20:01:34,082][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.076955795288086, cross_entropy: 2.076955795288086 +[2025-04-29 20:01:37,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 2.3533053398132324, cross_entropy: 2.3533053398132324 +[2025-04-29 20:01:38,043][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 0.9419078826904297, cross_entropy: 0.9419078826904297 +[2025-04-29 20:01:41,809][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 0.7609983086585999, cross_entropy: 0.7609983086585999 +[2025-04-29 20:01:42,167][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 2.9244260787963867, cross_entropy: 2.9244260787963867 +[2025-04-29 20:01:46,263][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 2.1823906898498535, cross_entropy: 2.1823906898498535 +[2025-04-29 20:01:46,702][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.304046630859375, cross_entropy: 2.304046630859375 +[2025-04-29 20:01:49,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 1.0690505504608154, cross_entropy: 1.0690505504608154 +[2025-04-29 20:01:50,446][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 0.6535992622375488, cross_entropy: 0.6535992622375488 +[2025-04-29 20:01:50,775][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/iteration3000.pth. +[2025-04-29 20:01:53,506][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 0.7245503664016724, cross_entropy: 0.7245503664016724 +[2025-04-29 20:01:54,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 0.7340757250785828, cross_entropy: 0.7340757250785828 +[2025-04-29 20:01:57,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 2.642059803009033, cross_entropy: 2.642059803009033 +[2025-04-29 20:01:58,008][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 1.797551155090332, cross_entropy: 1.797551155090332 +[2025-04-29 20:02:02,500][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.0107930898666382, cross_entropy: 1.0107930898666382 +[2025-04-29 20:02:02,855][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 2.8553614616394043, cross_entropy: 2.8553614616394043 +[2025-04-29 20:02:05,395][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 2.655294418334961, cross_entropy: 2.655294418334961 +[2025-04-29 20:02:06,895][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 1.277188777923584, cross_entropy: 1.277188777923584 +[2025-04-29 20:02:09,570][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 1.1591360569000244, cross_entropy: 1.1591360569000244 +[2025-04-29 20:02:11,301][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 1.5886356830596924, cross_entropy: 1.5886356830596924 +[2025-04-29 20:02:15,537][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 0.7913877964019775, cross_entropy: 0.7913877964019775 +[2025-04-29 20:02:16,439][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 0.9549731016159058, cross_entropy: 0.9549731016159058 +[2025-04-29 20:02:19,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.815052032470703, cross_entropy: 2.815052032470703 +[2025-04-29 20:02:20,598][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 2.7952980995178223, cross_entropy: 2.7952980995178223 +[2025-04-29 20:02:23,768][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 3.0676651000976562, cross_entropy: 3.0676651000976562 +[2025-04-29 20:02:24,700][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.8961341381073, cross_entropy: 2.8961341381073 +[2025-04-29 20:02:28,514][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 1.133821725845337, cross_entropy: 1.133821725845337 +[2025-04-29 20:02:28,869][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 2.506556987762451, cross_entropy: 2.506556987762451 +[2025-04-29 20:02:32,986][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 1.8925902843475342, cross_entropy: 1.8925902843475342 +[2025-04-29 20:02:33,339][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 0.8022236824035645, cross_entropy: 0.8022236824035645 +[2025-04-29 20:02:37,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.5154666900634766, cross_entropy: 2.5154666900634766 +[2025-04-29 20:02:37,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 1.1296932697296143, cross_entropy: 1.1296932697296143 +[2025-04-29 20:02:41,490][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 0.6466670036315918, cross_entropy: 0.6466670036315918 +[2025-04-29 20:02:41,850][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 1.5708222389221191, cross_entropy: 1.5708222389221191 +[2025-04-29 20:02:45,577][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.6434073448181152, cross_entropy: 1.6434073448181152 +[2025-04-29 20:02:45,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.2056546211242676, cross_entropy: 1.2056546211242676 +[2025-04-29 20:02:50,075][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 2.131965160369873, cross_entropy: 2.131965160369873 +[2025-04-29 20:02:50,398][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.3775994777679443, cross_entropy: 2.3775994777679443 +[2025-04-29 20:02:53,887][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 1.8238636255264282, cross_entropy: 1.8238636255264282 +[2025-04-29 20:02:54,242][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 1.0010263919830322, cross_entropy: 1.0010263919830322 +[2025-04-29 20:02:57,708][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 0.9363685846328735, cross_entropy: 0.9363685846328735 +[2025-04-29 20:02:58,061][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 0.7954171895980835, cross_entropy: 0.7954171895980835 +[2025-04-29 20:03:01,790][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 1.1717641353607178, cross_entropy: 1.1717641353607178 +[2025-04-29 20:03:02,149][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 1.2145261764526367, cross_entropy: 1.2145261764526367 +[2025-04-29 20:03:05,475][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.4672980308532715, cross_entropy: 2.4672980308532715 +[2025-04-29 20:03:05,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 0.923405110836029, cross_entropy: 0.923405110836029 +[2025-04-29 20:03:08,777][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 2.547959804534912, cross_entropy: 2.547959804534912 +[2025-04-29 20:03:09,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 2.7180728912353516, cross_entropy: 2.7180728912353516 +[2025-04-29 20:03:12,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 0.7716144323348999, cross_entropy: 0.7716144323348999 +[2025-04-29 20:03:13,327][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.085519552230835, cross_entropy: 1.085519552230835 +[2025-04-29 20:03:16,679][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 1.6416138410568237, cross_entropy: 1.6416138410568237 +[2025-04-29 20:03:17,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 2.4773662090301514, cross_entropy: 2.4773662090301514 +[2025-04-29 20:03:21,081][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 0.8620169758796692, cross_entropy: 0.8620169758796692 +[2025-04-29 20:03:21,440][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 0.9483380317687988, cross_entropy: 0.9483380317687988 +[2025-04-29 20:03:25,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 0.9727600812911987, cross_entropy: 0.9727600812911987 +[2025-04-29 20:03:25,399][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.3928815126419067, cross_entropy: 1.3928815126419067 +[2025-04-29 20:03:28,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 0.920488178730011, cross_entropy: 0.920488178730011 +[2025-04-29 20:03:29,082][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 2.5592212677001953, cross_entropy: 2.5592212677001953 +[2025-04-29 20:03:33,885][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.9415767788887024, cross_entropy: 0.9415767788887024 +[2025-04-29 20:03:34,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 2.684114933013916, cross_entropy: 2.684114933013916 +[2025-04-29 20:03:37,578][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 2.1190686225891113, cross_entropy: 2.1190686225891113 +[2025-04-29 20:03:37,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 3.0091755390167236, cross_entropy: 3.0091755390167236 +[2025-04-29 20:03:41,508][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 2.795609474182129, cross_entropy: 2.795609474182129 +[2025-04-29 20:03:41,827][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 3.0252366065979004, cross_entropy: 3.0252366065979004 +[2025-04-29 20:03:45,557][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.9236884117126465, cross_entropy: 2.9236884117126465 +[2025-04-29 20:03:45,915][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 2.526089668273926, cross_entropy: 2.526089668273926 +[2025-04-29 20:03:50,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 1.8741304874420166, cross_entropy: 1.8741304874420166 +[2025-04-29 20:03:50,388][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 2.2685060501098633, cross_entropy: 2.2685060501098633 +[2025-04-29 20:03:54,082][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.3157541751861572, cross_entropy: 2.3157541751861572 +[2025-04-29 20:03:54,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 0.6439582109451294, cross_entropy: 0.6439582109451294 +[2025-04-29 20:03:57,880][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 2.4501051902770996, cross_entropy: 2.4501051902770996 +[2025-04-29 20:03:58,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 1.7611918449401855, cross_entropy: 1.7611918449401855 +[2025-04-29 20:04:01,375][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 2.458806276321411, cross_entropy: 2.458806276321411 +[2025-04-29 20:04:02,402][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 2.4379544258117676, cross_entropy: 2.4379544258117676 +[2025-04-29 20:04:05,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.247982978820801, cross_entropy: 2.247982978820801 +[2025-04-29 20:04:06,515][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 1.1027309894561768, cross_entropy: 1.1027309894561768 +[2025-04-29 20:04:09,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 2.7326364517211914, cross_entropy: 2.7326364517211914 +[2025-04-29 20:04:10,595][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.699627637863159, cross_entropy: 2.699627637863159 +[2025-04-29 20:04:13,477][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 1.8977433443069458, cross_entropy: 1.8977433443069458 +[2025-04-29 20:04:14,400][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 0.7491531372070312, cross_entropy: 0.7491531372070312 +[2025-04-29 20:04:18,087][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 1.3838024139404297, cross_entropy: 1.3838024139404297 +[2025-04-29 20:04:18,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 0.839156985282898, cross_entropy: 0.839156985282898 +[2025-04-29 20:04:21,547][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 0.610095202922821, cross_entropy: 0.610095202922821 +[2025-04-29 20:04:22,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 1.5946693420410156, cross_entropy: 1.5946693420410156 +[2025-04-29 20:04:27,261][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 2.4501888751983643, cross_entropy: 2.4501888751983643 +[2025-04-29 20:04:27,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 1.7518415451049805, cross_entropy: 1.7518415451049805 +[2025-04-29 20:04:30,715][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 2.666025161743164, cross_entropy: 2.666025161743164 +[2025-04-29 20:04:31,065][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.925485610961914, cross_entropy: 2.925485610961914 +[2025-04-29 20:04:34,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 2.681057929992676, cross_entropy: 2.681057929992676 +[2025-04-29 20:04:35,156][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 2.5362279415130615, cross_entropy: 2.5362279415130615 +[2025-04-29 20:04:38,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.7260104417800903, cross_entropy: 0.7260104417800903 +[2025-04-29 20:04:39,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 1.6406927108764648, cross_entropy: 1.6406927108764648 +[2025-04-29 20:04:42,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 1.0793635845184326, cross_entropy: 1.0793635845184326 +[2025-04-29 20:04:44,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 2.5281131267547607, cross_entropy: 2.5281131267547607 +[2025-04-29 20:04:48,069][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 2.6636972427368164, cross_entropy: 2.6636972427368164 +[2025-04-29 20:04:48,392][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 1.074278712272644, cross_entropy: 1.074278712272644 +[2025-04-29 20:04:52,028][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 1.3858120441436768, cross_entropy: 1.3858120441436768 +[2025-04-29 20:04:52,347][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 2.496835231781006, cross_entropy: 2.496835231781006 +[2025-04-29 20:04:56,271][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 0.7550417184829712, cross_entropy: 0.7550417184829712 +[2025-04-29 20:04:56,629][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 0.8483927249908447, cross_entropy: 0.8483927249908447 +[2025-04-29 20:05:02,033][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 0.9737602472305298, cross_entropy: 0.9737602472305298 +[2025-04-29 20:05:02,355][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 2.5226070880889893, cross_entropy: 2.5226070880889893 +[2025-04-29 20:05:05,841][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.737030267715454, cross_entropy: 2.737030267715454 +[2025-04-29 20:05:06,202][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 2.576080799102783, cross_entropy: 2.576080799102783 +[2025-04-29 20:05:09,969][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 0.7214174866676331, cross_entropy: 0.7214174866676331 +[2025-04-29 20:05:10,324][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 1.1425464153289795, cross_entropy: 1.1425464153289795 +[2025-04-29 20:05:13,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 3.152517080307007, cross_entropy: 3.152517080307007 +[2025-04-29 20:05:13,788][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 2.8127498626708984, cross_entropy: 2.8127498626708984 +[2025-04-29 20:05:17,457][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 0.7553300857543945, cross_entropy: 0.7553300857543945 +[2025-04-29 20:05:17,804][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 0.6884627938270569, cross_entropy: 0.6884627938270569 +[2025-04-29 20:05:21,903][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.1123948097229004, cross_entropy: 1.1123948097229004 +[2025-04-29 20:05:22,259][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 1.3094112873077393, cross_entropy: 1.3094112873077393 +[2025-04-29 20:05:26,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 3.0513155460357666, cross_entropy: 3.0513155460357666 +[2025-04-29 20:05:27,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 0.8464601039886475, cross_entropy: 0.8464601039886475 +[2025-04-29 20:05:31,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.1452414989471436, cross_entropy: 1.1452414989471436 +[2025-04-29 20:05:31,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 2.6673991680145264, cross_entropy: 2.6673991680145264 +[2025-04-29 20:05:35,041][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.6337060928344727, cross_entropy: 2.6337060928344727 +[2025-04-29 20:05:35,364][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 1.6668014526367188, cross_entropy: 1.6668014526367188 +[2025-04-29 20:05:38,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 0.8452930450439453, cross_entropy: 0.8452930450439453 +[2025-04-29 20:05:39,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 1.3132598400115967, cross_entropy: 1.3132598400115967 +[2025-04-29 20:05:42,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 1.2821425199508667, cross_entropy: 1.2821425199508667 +[2025-04-29 20:05:42,564][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 0.8248718976974487, cross_entropy: 0.8248718976974487 +[2025-04-29 20:05:46,186][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 0.728436291217804, cross_entropy: 0.728436291217804 +[2025-04-29 20:05:46,548][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 1.24679696559906, cross_entropy: 1.24679696559906 +[2025-04-29 20:05:49,677][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 2.983510732650757, cross_entropy: 2.983510732650757 +[2025-04-29 20:05:50,036][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 1.9972285032272339, cross_entropy: 1.9972285032272339 +[2025-04-29 20:05:53,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 0.9435999989509583, cross_entropy: 0.9435999989509583 +[2025-04-29 20:05:53,986][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 2.171121120452881, cross_entropy: 2.171121120452881 +[2025-04-29 20:05:57,850][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 2.2776341438293457, cross_entropy: 2.2776341438293457 +[2025-04-29 20:05:58,171][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 2.8537166118621826, cross_entropy: 2.8537166118621826 +[2025-04-29 20:06:02,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 0.8463173508644104, cross_entropy: 0.8463173508644104 +[2025-04-29 20:06:02,740][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 1.4104963541030884, cross_entropy: 1.4104963541030884 +[2025-04-29 20:06:05,889][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.460449695587158, cross_entropy: 2.460449695587158 +[2025-04-29 20:06:06,242][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 0.7605684399604797, cross_entropy: 0.7605684399604797 +[2025-04-29 20:06:09,106][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 2.7396047115325928, cross_entropy: 2.7396047115325928 +[2025-04-29 20:06:10,127][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.704316258430481, cross_entropy: 1.704316258430481 +[2025-04-29 20:06:13,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 0.9961001873016357, cross_entropy: 0.9961001873016357 +[2025-04-29 20:06:14,181][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.4955130815505981, cross_entropy: 1.4955130815505981 +[2025-04-29 20:06:17,610][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 2.9911227226257324, cross_entropy: 2.9911227226257324 +[2025-04-29 20:06:18,476][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.582883358001709, cross_entropy: 2.582883358001709 +[2025-04-29 20:06:21,639][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 2.4831106662750244, cross_entropy: 2.4831106662750244 +[2025-04-29 20:06:22,275][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 1.8966021537780762, cross_entropy: 1.8966021537780762 +[2025-04-29 20:06:25,979][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 1.5312949419021606, cross_entropy: 1.5312949419021606 +[2025-04-29 20:06:26,332][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.2445034980773926, cross_entropy: 1.2445034980773926 +[2025-04-29 20:06:29,662][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 2.2494282722473145, cross_entropy: 2.2494282722473145 +[2025-04-29 20:06:30,414][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 1.8339818716049194, cross_entropy: 1.8339818716049194 +[2025-04-29 20:06:33,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 2.2172977924346924, cross_entropy: 2.2172977924346924 +[2025-04-29 20:06:34,842][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 0.8992992639541626, cross_entropy: 0.8992992639541626 +[2025-04-29 20:06:37,424][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 0.8601297736167908, cross_entropy: 0.8601297736167908 +[2025-04-29 20:06:39,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 0.6308836936950684, cross_entropy: 0.6308836936950684 +[2025-04-29 20:06:41,021][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.4113872051239014, cross_entropy: 1.4113872051239014 +[2025-04-29 20:06:42,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 1.5835330486297607, cross_entropy: 1.5835330486297607 +[2025-04-29 20:06:45,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 1.0535579919815063, cross_entropy: 1.0535579919815063 +[2025-04-29 20:06:47,333][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 2.3705239295959473, cross_entropy: 2.3705239295959473 +[2025-04-29 20:06:49,759][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.1531299352645874, cross_entropy: 1.1531299352645874 +[2025-04-29 20:06:51,094][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 2.647195816040039, cross_entropy: 2.647195816040039 +[2025-04-29 20:06:54,948][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 1.3242719173431396, cross_entropy: 1.3242719173431396 +[2025-04-29 20:06:55,342][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 2.370450735092163, cross_entropy: 2.370450735092163 +[2025-04-29 20:06:58,831][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.467711925506592, cross_entropy: 2.467711925506592 +[2025-04-29 20:06:59,184][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 1.87748122215271, cross_entropy: 1.87748122215271 +[2025-04-29 20:07:02,864][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 1.8924829959869385, cross_entropy: 1.8924829959869385 +[2025-04-29 20:07:03,222][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 0.8453059196472168, cross_entropy: 0.8453059196472168 +[2025-04-29 20:07:07,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 0.7338760495185852, cross_entropy: 0.7338760495185852 +[2025-04-29 20:07:07,894][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.8198778033256531, cross_entropy: 0.8198778033256531 +[2025-04-29 20:07:11,845][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 1.1666815280914307, cross_entropy: 1.1666815280914307 +[2025-04-29 20:07:12,206][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 0.6097627878189087, cross_entropy: 0.6097627878189087 +[2025-04-29 20:07:15,493][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 0.7358550429344177, cross_entropy: 0.7358550429344177 +[2025-04-29 20:07:18,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 2.5318284034729004, cross_entropy: 2.5318284034729004 +[2025-04-29 20:07:19,939][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 1.068515658378601, cross_entropy: 1.068515658378601 +[2025-04-29 20:07:22,191][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 2.705718517303467, cross_entropy: 2.705718517303467 +[2025-04-29 20:07:24,921][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 1.6131649017333984, cross_entropy: 1.6131649017333984 +[2025-04-29 20:07:26,571][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.3098376989364624, cross_entropy: 1.3098376989364624 +[2025-04-29 20:07:28,922][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.4193861484527588, cross_entropy: 1.4193861484527588 +[2025-04-29 20:07:31,170][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 1.1936981678009033, cross_entropy: 1.1936981678009033 +[2025-04-29 20:07:32,874][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 0.979299783706665, cross_entropy: 0.979299783706665 +[2025-04-29 20:07:35,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 0.8118348717689514, cross_entropy: 0.8118348717689514 +[2025-04-29 20:07:37,594][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 1.1694214344024658, cross_entropy: 1.1694214344024658 +[2025-04-29 20:07:40,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 2.5589640140533447, cross_entropy: 2.5589640140533447 +[2025-04-29 20:07:42,349][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 0.909652590751648, cross_entropy: 0.909652590751648 +[2025-04-29 20:07:44,970][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 2.0519399642944336, cross_entropy: 2.0519399642944336 +[2025-04-29 20:07:47,251][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.424546241760254, cross_entropy: 2.424546241760254 +[2025-04-29 20:07:48,933][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 0.7457931041717529, cross_entropy: 0.7457931041717529 +[2025-04-29 20:07:51,084][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 3.1068673133850098, cross_entropy: 3.1068673133850098 +[2025-04-29 20:07:53,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.5683960914611816, cross_entropy: 2.5683960914611816 +[2025-04-29 20:07:54,891][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 1.159918189048767, cross_entropy: 1.159918189048767 +[2025-04-29 20:07:57,272][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 2.3052115440368652, cross_entropy: 2.3052115440368652 +[2025-04-29 20:07:58,377][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 2.22589373588562, cross_entropy: 2.22589373588562 +[2025-04-29 20:08:01,568][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.7534258365631104, cross_entropy: 1.7534258365631104 +[2025-04-29 20:08:02,715][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 1.8079692125320435, cross_entropy: 1.8079692125320435 +[2025-04-29 20:08:05,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 2.7582311630249023, cross_entropy: 2.7582311630249023 +[2025-04-29 20:08:06,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 2.1367976665496826, cross_entropy: 2.1367976665496826 +[2025-04-29 20:08:10,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 0.7317269444465637, cross_entropy: 0.7317269444465637 +[2025-04-29 20:08:11,115][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 1.6773998737335205, cross_entropy: 1.6773998737335205 +[2025-04-29 20:08:14,820][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 1.8048793077468872, cross_entropy: 1.8048793077468872 +[2025-04-29 20:08:15,739][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.9424679279327393, cross_entropy: 1.9424679279327393 +[2025-04-29 20:08:18,665][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.435971260070801, cross_entropy: 2.435971260070801 +[2025-04-29 20:08:20,105][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 1.745348572731018, cross_entropy: 1.745348572731018 +[2025-04-29 20:08:23,287][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 0.6964612007141113, cross_entropy: 0.6964612007141113 +[2025-04-29 20:08:24,748][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 2.89221453666687, cross_entropy: 2.89221453666687 +[2025-04-29 20:08:27,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 2.791581630706787, cross_entropy: 2.791581630706787 +[2025-04-29 20:08:28,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 2.4413886070251465, cross_entropy: 2.4413886070251465 +[2025-04-29 20:08:31,479][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.1417760848999023, cross_entropy: 1.1417760848999023 +[2025-04-29 20:08:32,462][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 2.450774669647217, cross_entropy: 2.450774669647217 +[2025-04-29 20:08:35,568][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 1.0088577270507812, cross_entropy: 1.0088577270507812 +[2025-04-29 20:08:36,479][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.8655034303665161, cross_entropy: 1.8655034303665161 +[2025-04-29 20:08:39,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.985197067260742, cross_entropy: 2.985197067260742 +[2025-04-29 20:08:40,876][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 0.7163158655166626, cross_entropy: 0.7163158655166626 +[2025-04-29 20:08:44,126][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.4922308921813965, cross_entropy: 2.4922308921813965 +[2025-04-29 20:08:45,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 0.9942348003387451, cross_entropy: 0.9942348003387451 +[2025-04-29 20:08:49,051][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 2.6214818954467773, cross_entropy: 2.6214818954467773 +[2025-04-29 20:08:49,533][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 1.1482365131378174, cross_entropy: 1.1482365131378174 +[2025-04-29 20:08:52,601][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.8530893325805664, cross_entropy: 2.8530893325805664 +[2025-04-29 20:08:53,019][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 2.7193262577056885, cross_entropy: 2.7193262577056885 +[2025-04-29 20:08:57,404][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.2584171295166016, cross_entropy: 2.2584171295166016 +[2025-04-29 20:12:18,926][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.753639817237854, cross_entropy: 1.753639817237854 +[2025-04-29 20:12:18,927][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.2702195644378662, cross_entropy: 1.2702195644378662 +[2025-04-29 20:12:19,117][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch9.pth. +[2025-04-29 20:12:19,370][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 20:12:24,553][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 2.530264377593994, cross_entropy: 2.530264377593994 +[2025-04-29 20:12:24,984][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.344118356704712, cross_entropy: 1.344118356704712 +[2025-04-29 20:12:28,584][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.9689933657646179, cross_entropy: 0.9689933657646179 +[2025-04-29 20:12:28,977][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 1.1900503635406494, cross_entropy: 1.1900503635406494 +[2025-04-29 20:12:32,818][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.088000535964966, cross_entropy: 2.088000535964966 +[2025-04-29 20:12:33,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.4378052949905396, cross_entropy: 1.4378052949905396 +[2025-04-29 20:12:38,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 0.6792981028556824, cross_entropy: 0.6792981028556824 +[2025-04-29 20:12:38,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.634992241859436, cross_entropy: 0.634992241859436 +[2025-04-29 20:12:42,323][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.6225826740264893, cross_entropy: 2.6225826740264893 +[2025-04-29 20:12:42,681][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.0524017810821533, cross_entropy: 1.0524017810821533 +[2025-04-29 20:12:45,967][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 1.5385618209838867, cross_entropy: 1.5385618209838867 +[2025-04-29 20:12:46,323][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 0.796315610408783, cross_entropy: 0.796315610408783 +[2025-04-29 20:12:50,015][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.0323212146759033, cross_entropy: 1.0323212146759033 +[2025-04-29 20:12:50,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.7391606569290161, cross_entropy: 1.7391606569290161 +[2025-04-29 20:12:53,491][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.6358609199523926, cross_entropy: 2.6358609199523926 +[2025-04-29 20:12:53,849][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 2.110426425933838, cross_entropy: 2.110426425933838 +[2025-04-29 20:12:57,274][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 1.363640308380127, cross_entropy: 1.363640308380127 +[2025-04-29 20:12:57,629][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 1.0267733335494995, cross_entropy: 1.0267733335494995 +[2025-04-29 20:13:01,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 0.7654673457145691, cross_entropy: 0.7654673457145691 +[2025-04-29 20:13:02,044][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.2190220355987549, cross_entropy: 1.2190220355987549 +[2025-04-29 20:13:06,340][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 1.192391276359558, cross_entropy: 1.192391276359558 +[2025-04-29 20:13:06,697][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 0.7935584187507629, cross_entropy: 0.7935584187507629 +[2025-04-29 20:13:11,572][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.8133002519607544, cross_entropy: 0.8133002519607544 +[2025-04-29 20:13:11,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 2.8668699264526367, cross_entropy: 2.8668699264526367 +[2025-04-29 20:13:16,765][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.5879831314086914, cross_entropy: 2.5879831314086914 +[2025-04-29 20:13:17,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 0.8312156796455383, cross_entropy: 0.8312156796455383 +[2025-04-29 20:13:21,541][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 0.9290141463279724, cross_entropy: 0.9290141463279724 +[2025-04-29 20:13:21,865][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 0.8477315902709961, cross_entropy: 0.8477315902709961 +[2025-04-29 20:13:25,475][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 1.050137996673584, cross_entropy: 1.050137996673584 +[2025-04-29 20:13:25,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.5419223308563232, cross_entropy: 1.5419223308563232 +[2025-04-29 20:13:30,410][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 1.2466709613800049, cross_entropy: 1.2466709613800049 +[2025-04-29 20:13:30,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 1.9807398319244385, cross_entropy: 1.9807398319244385 +[2025-04-29 20:13:34,152][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 1.1647266149520874, cross_entropy: 1.1647266149520874 +[2025-04-29 20:13:34,516][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 0.7150463461875916, cross_entropy: 0.7150463461875916 +[2025-04-29 20:13:38,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 2.734147548675537, cross_entropy: 2.734147548675537 +[2025-04-29 20:13:38,394][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 2.961853504180908, cross_entropy: 2.961853504180908 +[2025-04-29 20:13:41,758][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 0.9556086659431458, cross_entropy: 0.9556086659431458 +[2025-04-29 20:13:42,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 2.164520263671875, cross_entropy: 2.164520263671875 +[2025-04-29 20:13:46,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 0.7714092135429382, cross_entropy: 0.7714092135429382 +[2025-04-29 20:13:46,391][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 2.0159072875976562, cross_entropy: 2.0159072875976562 +[2025-04-29 20:13:49,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 1.99445641040802, cross_entropy: 1.99445641040802 +[2025-04-29 20:13:50,059][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 0.7312480211257935, cross_entropy: 0.7312480211257935 +[2025-04-29 20:13:53,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 1.7477184534072876, cross_entropy: 1.7477184534072876 +[2025-04-29 20:13:53,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.098970413208008, cross_entropy: 2.098970413208008 +[2025-04-29 20:13:58,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.252187728881836, cross_entropy: 1.252187728881836 +[2025-04-29 20:13:58,398][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 1.4336625337600708, cross_entropy: 1.4336625337600708 +[2025-04-29 20:14:01,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 0.8734159469604492, cross_entropy: 0.8734159469604492 +[2025-04-29 20:14:02,028][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 1.1668418645858765, cross_entropy: 1.1668418645858765 +[2025-04-29 20:14:05,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 0.6681029796600342, cross_entropy: 0.6681029796600342 +[2025-04-29 20:14:05,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 2.5988309383392334, cross_entropy: 2.5988309383392334 +[2025-04-29 20:14:10,040][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 1.4929554462432861, cross_entropy: 1.4929554462432861 +[2025-04-29 20:14:10,387][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 2.7649340629577637, cross_entropy: 2.7649340629577637 +[2025-04-29 20:14:13,702][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 2.0343127250671387, cross_entropy: 2.0343127250671387 +[2025-04-29 20:14:14,057][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 1.0812158584594727, cross_entropy: 1.0812158584594727 +[2025-04-29 20:14:17,960][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.0587095022201538, cross_entropy: 1.0587095022201538 +[2025-04-29 20:14:18,313][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 1.6079410314559937, cross_entropy: 1.6079410314559937 +[2025-04-29 20:14:22,115][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 2.5825467109680176, cross_entropy: 2.5825467109680176 +[2025-04-29 20:14:22,477][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.8831923604011536, cross_entropy: 0.8831923604011536 +[2025-04-29 20:14:26,905][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.326041579246521, cross_entropy: 1.326041579246521 +[2025-04-29 20:14:27,264][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 1.9625805616378784, cross_entropy: 1.9625805616378784 +[2025-04-29 20:14:31,281][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 0.6805432438850403, cross_entropy: 0.6805432438850403 +[2025-04-29 20:14:31,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 0.8994670510292053, cross_entropy: 0.8994670510292053 +[2025-04-29 20:14:35,626][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 0.6679980754852295, cross_entropy: 0.6679980754852295 +[2025-04-29 20:14:35,971][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 1.3076281547546387, cross_entropy: 1.3076281547546387 +[2025-04-29 20:14:39,637][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 0.8461505174636841, cross_entropy: 0.8461505174636841 +[2025-04-29 20:14:39,990][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 1.2699127197265625, cross_entropy: 1.2699127197265625 +[2025-04-29 20:14:43,580][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 1.3991318941116333, cross_entropy: 1.3991318941116333 +[2025-04-29 20:14:43,937][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 1.9361865520477295, cross_entropy: 1.9361865520477295 +[2025-04-29 20:14:47,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 2.6256966590881348, cross_entropy: 2.6256966590881348 +[2025-04-29 20:14:47,741][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 2.4807894229888916, cross_entropy: 2.4807894229888916 +[2025-04-29 20:14:51,623][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 0.7556620240211487, cross_entropy: 0.7556620240211487 +[2025-04-29 20:14:51,982][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 1.6120445728302002, cross_entropy: 1.6120445728302002 +[2025-04-29 20:14:55,612][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 0.7470060586929321, cross_entropy: 0.7470060586929321 +[2025-04-29 20:14:55,975][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.541412353515625, cross_entropy: 2.541412353515625 +[2025-04-29 20:14:59,956][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 2.1404027938842773, cross_entropy: 2.1404027938842773 +[2025-04-29 20:15:00,317][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.3014538288116455, cross_entropy: 1.3014538288116455 +[2025-04-29 20:15:03,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 2.131014347076416, cross_entropy: 2.131014347076416 +[2025-04-29 20:15:04,327][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.1278271675109863, cross_entropy: 1.1278271675109863 +[2025-04-29 20:15:08,112][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.971635341644287, cross_entropy: 1.971635341644287 +[2025-04-29 20:15:08,471][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 1.8626580238342285, cross_entropy: 1.8626580238342285 +[2025-04-29 20:15:12,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.4520957469940186, cross_entropy: 1.4520957469940186 +[2025-04-29 20:15:12,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 2.1921961307525635, cross_entropy: 2.1921961307525635 +[2025-04-29 20:15:16,719][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 0.8340201377868652, cross_entropy: 0.8340201377868652 +[2025-04-29 20:15:17,043][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 0.6488248705863953, cross_entropy: 0.6488248705863953 +[2025-04-29 20:15:21,420][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 0.911332368850708, cross_entropy: 0.911332368850708 +[2025-04-29 20:15:21,777][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 0.8844399452209473, cross_entropy: 0.8844399452209473 +[2025-04-29 20:15:25,473][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 0.5804124474525452, cross_entropy: 0.5804124474525452 +[2025-04-29 20:15:25,837][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 0.898398756980896, cross_entropy: 0.898398756980896 +[2025-04-29 20:15:29,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 0.8642870783805847, cross_entropy: 0.8642870783805847 +[2025-04-29 20:15:29,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.8468753099441528, cross_entropy: 1.8468753099441528 +[2025-04-29 20:15:32,773][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 0.5058243274688721, cross_entropy: 0.5058243274688721 +[2025-04-29 20:15:33,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 1.1760462522506714, cross_entropy: 1.1760462522506714 +[2025-04-29 20:15:36,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.597843885421753, cross_entropy: 2.597843885421753 +[2025-04-29 20:15:36,844][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 1.1098096370697021, cross_entropy: 1.1098096370697021 +[2025-04-29 20:15:40,445][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.7601783275604248, cross_entropy: 1.7601783275604248 +[2025-04-29 20:15:40,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 0.7873663902282715, cross_entropy: 0.7873663902282715 +[2025-04-29 20:15:44,185][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 3.111388921737671, cross_entropy: 3.111388921737671 +[2025-04-29 20:15:44,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 1.741956353187561, cross_entropy: 1.741956353187561 +[2025-04-29 20:15:48,514][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 0.6780935525894165, cross_entropy: 0.6780935525894165 +[2025-04-29 20:15:48,873][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 2.2980024814605713, cross_entropy: 2.2980024814605713 +[2025-04-29 20:15:52,981][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 1.731022596359253, cross_entropy: 1.731022596359253 +[2025-04-29 20:15:53,341][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 0.782171905040741, cross_entropy: 0.782171905040741 +[2025-04-29 20:15:57,156][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 0.7703750133514404, cross_entropy: 0.7703750133514404 +[2025-04-29 20:15:57,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 1.7701747417449951, cross_entropy: 1.7701747417449951 +[2025-04-29 20:16:01,325][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 0.9976759552955627, cross_entropy: 0.9976759552955627 +[2025-04-29 20:16:01,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 0.8021535277366638, cross_entropy: 0.8021535277366638 +[2025-04-29 20:16:05,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.206167221069336, cross_entropy: 1.206167221069336 +[2025-04-29 20:16:05,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.8223522305488586, cross_entropy: 0.8223522305488586 +[2025-04-29 20:16:09,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.890300750732422, cross_entropy: 2.890300750732422 +[2025-04-29 20:16:09,808][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.669189453125, cross_entropy: 2.669189453125 +[2025-04-29 20:16:13,318][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 3.0091707706451416, cross_entropy: 3.0091707706451416 +[2025-04-29 20:16:13,643][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 0.9446610808372498, cross_entropy: 0.9446610808372498 +[2025-04-29 20:16:17,214][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 0.9748483300209045, cross_entropy: 0.9748483300209045 +[2025-04-29 20:16:17,864][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 0.6565061807632446, cross_entropy: 0.6565061807632446 +[2025-04-29 20:16:21,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.0511765480041504, cross_entropy: 2.0511765480041504 +[2025-04-29 20:16:23,263][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.1781728267669678, cross_entropy: 2.1781728267669678 +[2025-04-29 20:16:25,755][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 2.9033901691436768, cross_entropy: 2.9033901691436768 +[2025-04-29 20:16:27,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 2.1570098400115967, cross_entropy: 2.1570098400115967 +[2025-04-29 20:16:29,697][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.1340994834899902, cross_entropy: 1.1340994834899902 +[2025-04-29 20:16:31,956][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 1.465423345565796, cross_entropy: 1.465423345565796 +[2025-04-29 20:16:33,082][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 0.9516531229019165, cross_entropy: 0.9516531229019165 +[2025-04-29 20:16:36,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.1381890773773193, cross_entropy: 1.1381890773773193 +[2025-04-29 20:16:36,908][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.2667779922485352, cross_entropy: 1.2667779922485352 +[2025-04-29 20:16:40,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 1.4861335754394531, cross_entropy: 1.4861335754394531 +[2025-04-29 20:16:41,251][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 2.7351977825164795, cross_entropy: 2.7351977825164795 +[2025-04-29 20:16:44,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 1.8764891624450684, cross_entropy: 1.8764891624450684 +[2025-04-29 20:16:45,030][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 1.2408063411712646, cross_entropy: 1.2408063411712646 +[2025-04-29 20:16:48,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 1.0121808052062988, cross_entropy: 1.0121808052062988 +[2025-04-29 20:16:49,107][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 2.217465877532959, cross_entropy: 2.217465877532959 +[2025-04-29 20:16:52,772][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 0.5612888336181641, cross_entropy: 0.5612888336181641 +[2025-04-29 20:16:53,472][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.8524346351623535, cross_entropy: 2.8524346351623535 +[2025-04-29 20:16:56,647][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 0.9742386341094971, cross_entropy: 0.9742386341094971 +[2025-04-29 20:16:57,558][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.6476478576660156, cross_entropy: 1.6476478576660156 +[2025-04-29 20:17:00,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 2.5952813625335693, cross_entropy: 2.5952813625335693 +[2025-04-29 20:17:01,765][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 0.8416963219642639, cross_entropy: 0.8416963219642639 +[2025-04-29 20:17:04,560][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.2474712133407593, cross_entropy: 1.2474712133407593 +[2025-04-29 20:17:06,069][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 1.6436762809753418, cross_entropy: 1.6436762809753418 +[2025-04-29 20:17:08,383][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 2.762878656387329, cross_entropy: 2.762878656387329 +[2025-04-29 20:17:10,551][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.5529279708862305, cross_entropy: 2.5529279708862305 +[2025-04-29 20:17:12,457][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 3.138636827468872, cross_entropy: 3.138636827468872 +[2025-04-29 20:17:14,218][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 1.250473141670227, cross_entropy: 1.250473141670227 +[2025-04-29 20:17:16,573][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 1.4285118579864502, cross_entropy: 1.4285118579864502 +[2025-04-29 20:17:18,674][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.2312350273132324, cross_entropy: 2.2312350273132324 +[2025-04-29 20:17:20,737][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 0.7143533229827881, cross_entropy: 0.7143533229827881 +[2025-04-29 20:17:22,552][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 1.0459771156311035, cross_entropy: 1.0459771156311035 +[2025-04-29 20:17:25,200][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 1.1398684978485107, cross_entropy: 1.1398684978485107 +[2025-04-29 20:17:26,934][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 2.2917585372924805, cross_entropy: 2.2917585372924805 +[2025-04-29 20:17:29,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.494723916053772, cross_entropy: 1.494723916053772 +[2025-04-29 20:17:30,779][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.9732743501663208, cross_entropy: 1.9732743501663208 +[2025-04-29 20:17:33,428][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 1.4570887088775635, cross_entropy: 1.4570887088775635 +[2025-04-29 20:17:35,547][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 0.7348458170890808, cross_entropy: 0.7348458170890808 +[2025-04-29 20:17:37,633][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 1.9698461294174194, cross_entropy: 1.9698461294174194 +[2025-04-29 20:17:39,415][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 2.8213918209075928, cross_entropy: 2.8213918209075928 +[2025-04-29 20:17:41,698][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.252732515335083, cross_entropy: 2.252732515335083 +[2025-04-29 20:17:42,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 2.1587672233581543, cross_entropy: 2.1587672233581543 +[2025-04-29 20:17:44,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 1.6536438465118408, cross_entropy: 1.6536438465118408 +[2025-04-29 20:17:46,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 0.671052873134613, cross_entropy: 0.671052873134613 +[2025-04-29 20:17:50,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 1.3130724430084229, cross_entropy: 1.3130724430084229 +[2025-04-29 20:17:51,151][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 3.031376838684082, cross_entropy: 3.031376838684082 +[2025-04-29 20:17:54,313][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.6345465183258057, cross_entropy: 2.6345465183258057 +[2025-04-29 20:17:55,457][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 2.857368230819702, cross_entropy: 2.857368230819702 +[2025-04-29 20:17:59,110][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 0.8050158023834229, cross_entropy: 0.8050158023834229 +[2025-04-29 20:17:59,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 0.9783908724784851, cross_entropy: 0.9783908724784851 +[2025-04-29 20:18:03,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 1.5769445896148682, cross_entropy: 1.5769445896148682 +[2025-04-29 20:18:03,696][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 1.9924542903900146, cross_entropy: 1.9924542903900146 +[2025-04-29 20:18:07,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 0.6908650994300842, cross_entropy: 0.6908650994300842 +[2025-04-29 20:18:07,875][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.3994216918945312, cross_entropy: 2.3994216918945312 +[2025-04-29 20:18:11,464][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 1.421567440032959, cross_entropy: 1.421567440032959 +[2025-04-29 20:18:11,888][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.2051234245300293, cross_entropy: 2.2051234245300293 +[2025-04-29 20:18:15,860][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 0.7714851498603821, cross_entropy: 0.7714851498603821 +[2025-04-29 20:18:16,217][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 1.703204870223999, cross_entropy: 1.703204870223999 +[2025-04-29 20:18:20,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.8299938440322876, cross_entropy: 0.8299938440322876 +[2025-04-29 20:18:20,492][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 2.143885374069214, cross_entropy: 2.143885374069214 +[2025-04-29 20:18:24,502][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 2.6883082389831543, cross_entropy: 2.6883082389831543 +[2025-04-29 20:18:24,856][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 2.331050395965576, cross_entropy: 2.331050395965576 +[2025-04-29 20:18:28,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 0.6956374645233154, cross_entropy: 0.6956374645233154 +[2025-04-29 20:18:29,131][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 1.4649823904037476, cross_entropy: 1.4649823904037476 +[2025-04-29 20:18:32,457][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 0.7470790147781372, cross_entropy: 0.7470790147781372 +[2025-04-29 20:18:32,779][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 2.806570529937744, cross_entropy: 2.806570529937744 +[2025-04-29 20:18:36,643][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 3.2419488430023193, cross_entropy: 3.2419488430023193 +[2025-04-29 20:18:37,059][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 2.3174991607666016, cross_entropy: 2.3174991607666016 +[2025-04-29 20:18:41,073][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 1.1682872772216797, cross_entropy: 1.1682872772216797 +[2025-04-29 20:18:41,427][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.0665011405944824, cross_entropy: 1.0665011405944824 +[2025-04-29 20:18:45,040][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.67578387260437, cross_entropy: 2.67578387260437 +[2025-04-29 20:18:45,363][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.0148041248321533, cross_entropy: 1.0148041248321533 +[2025-04-29 20:18:49,361][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 2.843221664428711, cross_entropy: 2.843221664428711 +[2025-04-29 20:18:49,718][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 1.2637906074523926, cross_entropy: 1.2637906074523926 +[2025-04-29 20:18:53,398][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 2.8405351638793945, cross_entropy: 2.8405351638793945 +[2025-04-29 20:18:53,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 2.4958643913269043, cross_entropy: 2.4958643913269043 +[2025-04-29 20:18:57,603][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 0.7027785778045654, cross_entropy: 0.7027785778045654 +[2025-04-29 20:18:57,959][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 2.6940903663635254, cross_entropy: 2.6940903663635254 +[2025-04-29 20:19:02,326][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 2.5379652976989746, cross_entropy: 2.5379652976989746 +[2025-04-29 20:19:02,683][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 0.8013361692428589, cross_entropy: 0.8013361692428589 +[2025-04-29 20:19:06,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.6285557746887207, cross_entropy: 2.6285557746887207 +[2025-04-29 20:19:06,505][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 1.1952934265136719, cross_entropy: 1.1952934265136719 +[2025-04-29 20:19:10,378][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.8538472652435303, cross_entropy: 2.8538472652435303 +[2025-04-29 20:19:10,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 0.7744615077972412, cross_entropy: 0.7744615077972412 +[2025-04-29 20:19:14,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.0506616830825806, cross_entropy: 1.0506616830825806 +[2025-04-29 20:19:14,739][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 1.5998070240020752, cross_entropy: 1.5998070240020752 +[2025-04-29 20:19:18,758][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.889012336730957, cross_entropy: 2.889012336730957 +[2025-04-29 20:19:19,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 2.9548940658569336, cross_entropy: 2.9548940658569336 +[2025-04-29 20:19:22,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 1.1767292022705078, cross_entropy: 1.1767292022705078 +[2025-04-29 20:19:22,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 0.6889216899871826, cross_entropy: 0.6889216899871826 +[2025-04-29 20:19:26,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 1.3703060150146484, cross_entropy: 1.3703060150146484 +[2025-04-29 20:19:26,621][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 2.4991934299468994, cross_entropy: 2.4991934299468994 +[2025-04-29 20:19:30,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 2.6919357776641846, cross_entropy: 2.6919357776641846 +[2025-04-29 20:19:30,978][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 1.5256340503692627, cross_entropy: 1.5256340503692627 +[2025-04-29 20:19:35,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 2.6180574893951416, cross_entropy: 2.6180574893951416 +[2025-04-29 20:19:35,844][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 2.8410086631774902, cross_entropy: 2.8410086631774902 +[2025-04-29 20:19:39,279][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.0216684341430664, cross_entropy: 1.0216684341430664 +[2025-04-29 20:19:39,635][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 2.852320432662964, cross_entropy: 2.852320432662964 +[2025-04-29 20:19:42,997][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.813845634460449, cross_entropy: 2.813845634460449 +[2025-04-29 20:19:43,418][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 0.8805087208747864, cross_entropy: 0.8805087208747864 +[2025-04-29 20:19:47,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 1.136446475982666, cross_entropy: 1.136446475982666 +[2025-04-29 20:19:47,406][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 0.5399755239486694, cross_entropy: 0.5399755239486694 +[2025-04-29 20:19:51,087][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 1.0228676795959473, cross_entropy: 1.0228676795959473 +[2025-04-29 20:19:51,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 0.8788225054740906, cross_entropy: 0.8788225054740906 +[2025-04-29 20:19:55,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 0.996311604976654, cross_entropy: 0.996311604976654 +[2025-04-29 20:19:55,593][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.906489610671997, cross_entropy: 2.906489610671997 +[2025-04-29 20:19:59,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.796051025390625, cross_entropy: 2.796051025390625 +[2025-04-29 20:20:01,765][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 3.1247024536132812, cross_entropy: 3.1247024536132812 +[2025-04-29 20:20:03,897][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 0.5609973669052124, cross_entropy: 0.5609973669052124 +[2025-04-29 20:20:06,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 0.9333701729774475, cross_entropy: 0.9333701729774475 +[2025-04-29 20:20:07,960][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 2.2961835861206055, cross_entropy: 2.2961835861206055 +[2025-04-29 20:20:09,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 1.1642844676971436, cross_entropy: 1.1642844676971436 +[2025-04-29 20:20:11,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 1.080269694328308, cross_entropy: 1.080269694328308 +[2025-04-29 20:20:14,164][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 1.0897963047027588, cross_entropy: 1.0897963047027588 +[2025-04-29 20:20:15,743][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 0.5525315999984741, cross_entropy: 0.5525315999984741 +[2025-04-29 20:20:19,020][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 2.875537633895874, cross_entropy: 2.875537633895874 +[2025-04-29 20:20:19,681][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 0.994533896446228, cross_entropy: 0.994533896446228 +[2025-04-29 20:20:22,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 0.37200403213500977, cross_entropy: 0.37200403213500977 +[2025-04-29 20:20:23,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 2.6670022010803223, cross_entropy: 2.6670022010803223 +[2025-04-29 20:20:26,656][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 0.9542827606201172, cross_entropy: 0.9542827606201172 +[2025-04-29 20:20:28,241][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 0.590424656867981, cross_entropy: 0.590424656867981 +[2025-04-29 20:20:30,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 0.873175323009491, cross_entropy: 0.873175323009491 +[2025-04-29 20:20:31,977][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 2.1340994834899902, cross_entropy: 2.1340994834899902 +[2025-04-29 20:20:34,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 1.0273849964141846, cross_entropy: 1.0273849964141846 +[2025-04-29 20:20:35,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 0.9625654220581055, cross_entropy: 0.9625654220581055 +[2025-04-29 20:20:39,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.9505107402801514, cross_entropy: 1.9505107402801514 +[2025-04-29 20:20:42,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 2.0555953979492188, cross_entropy: 2.0555953979492188 +[2025-04-29 20:20:43,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 0.7482530474662781, cross_entropy: 0.7482530474662781 +[2025-04-29 20:20:46,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 1.4866032600402832, cross_entropy: 1.4866032600402832 +[2025-04-29 20:20:47,315][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.4050676822662354, cross_entropy: 2.4050676822662354 +[2025-04-29 20:20:50,708][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.6786862015724182, cross_entropy: 0.6786862015724182 +[2025-04-29 20:20:51,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 1.42811918258667, cross_entropy: 1.42811918258667 +[2025-04-29 20:20:55,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 1.203484296798706, cross_entropy: 1.203484296798706 +[2025-04-29 20:20:55,862][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 1.3908445835113525, cross_entropy: 1.3908445835113525 +[2025-04-29 20:20:59,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.2279515266418457, cross_entropy: 2.2279515266418457 +[2025-04-29 20:21:00,752][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 0.46481698751449585, cross_entropy: 0.46481698751449585 +[2025-04-29 20:21:03,885][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 2.483212947845459, cross_entropy: 2.483212947845459 +[2025-04-29 20:21:05,166][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 2.953339099884033, cross_entropy: 2.953339099884033 +[2025-04-29 20:21:08,561][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.689584970474243, cross_entropy: 2.689584970474243 +[2025-04-29 20:21:09,639][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 1.4553614854812622, cross_entropy: 1.4553614854812622 +[2025-04-29 20:21:12,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 0.7586435079574585, cross_entropy: 0.7586435079574585 +[2025-04-29 20:21:13,628][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 2.725658416748047, cross_entropy: 2.725658416748047 +[2025-04-29 20:21:16,616][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 0.8937501907348633, cross_entropy: 0.8937501907348633 +[2025-04-29 20:21:18,767][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 2.9242844581604004, cross_entropy: 2.9242844581604004 +[2025-04-29 20:21:20,228][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 0.861777126789093, cross_entropy: 0.861777126789093 +[2025-04-29 20:21:23,222][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 2.4018425941467285, cross_entropy: 2.4018425941467285 +[2025-04-29 20:21:24,349][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 0.7016491889953613, cross_entropy: 0.7016491889953613 +[2025-04-29 20:21:26,935][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 2.322869062423706, cross_entropy: 2.322869062423706 +[2025-04-29 20:21:28,377][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 3.214999198913574, cross_entropy: 3.214999198913574 +[2025-04-29 20:21:31,665][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.0100793838500977, cross_entropy: 2.0100793838500977 +[2025-04-29 20:21:32,006][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.055593490600586, cross_entropy: 2.055593490600586 +[2025-04-29 20:21:35,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 0.7275354862213135, cross_entropy: 0.7275354862213135 +[2025-04-29 20:21:36,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 1.309201717376709, cross_entropy: 1.309201717376709 +[2025-04-29 20:21:40,010][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 3.040128707885742, cross_entropy: 3.040128707885742 +[2025-04-29 20:21:42,201][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 0.6034979820251465, cross_entropy: 0.6034979820251465 +[2025-04-29 20:21:44,215][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.7043614387512207, cross_entropy: 2.7043614387512207 +[2025-04-29 20:21:47,163][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.8958722352981567, cross_entropy: 0.8958722352981567 +[2025-04-29 20:21:48,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 1.0519911050796509, cross_entropy: 1.0519911050796509 +[2025-04-29 20:21:51,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 0.4443252682685852, cross_entropy: 0.4443252682685852 +[2025-04-29 20:21:52,472][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 1.2304672002792358, cross_entropy: 1.2304672002792358 +[2025-04-29 20:21:55,792][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 2.2829294204711914, cross_entropy: 2.2829294204711914 +[2025-04-29 20:21:56,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.1057498455047607, cross_entropy: 2.1057498455047607 +[2025-04-29 20:22:00,115][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 1.3160741329193115, cross_entropy: 1.3160741329193115 +[2025-04-29 20:22:00,533][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 0.8062955141067505, cross_entropy: 0.8062955141067505 +[2025-04-29 20:22:04,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.6908528804779053, cross_entropy: 2.6908528804779053 +[2025-04-29 20:22:05,142][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 3.0256617069244385, cross_entropy: 3.0256617069244385 +[2025-04-29 20:22:08,603][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 1.8969066143035889, cross_entropy: 1.8969066143035889 +[2025-04-29 20:22:08,967][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 2.709991455078125, cross_entropy: 2.709991455078125 +[2025-04-29 20:22:12,547][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.8845244646072388, cross_entropy: 0.8845244646072388 +[2025-04-29 20:22:12,906][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 2.782991409301758, cross_entropy: 2.782991409301758 +[2025-04-29 20:22:17,347][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 1.4962691068649292, cross_entropy: 1.4962691068649292 +[2025-04-29 20:22:17,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 3.0048913955688477, cross_entropy: 3.0048913955688477 +[2025-04-29 20:22:21,626][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 0.915295422077179, cross_entropy: 0.915295422077179 +[2025-04-29 20:22:21,983][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 0.7857559323310852, cross_entropy: 0.7857559323310852 +[2025-04-29 20:22:26,190][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 1.6164222955703735, cross_entropy: 1.6164222955703735 +[2025-04-29 20:22:26,547][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 1.206390142440796, cross_entropy: 1.206390142440796 +[2025-04-29 20:22:29,933][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 2.627655506134033, cross_entropy: 2.627655506134033 +[2025-04-29 20:22:30,260][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 2.084562301635742, cross_entropy: 2.084562301635742 +[2025-04-29 20:22:34,669][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 1.7264337539672852, cross_entropy: 1.7264337539672852 +[2025-04-29 20:22:35,031][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 1.4932481050491333, cross_entropy: 1.4932481050491333 +[2025-04-29 20:22:39,403][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 2.107646942138672, cross_entropy: 2.107646942138672 +[2025-04-29 20:22:39,728][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 1.5700870752334595, cross_entropy: 1.5700870752334595 +[2025-04-29 20:22:43,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 2.1459124088287354, cross_entropy: 2.1459124088287354 +[2025-04-29 20:22:43,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 2.707754611968994, cross_entropy: 2.707754611968994 +[2025-04-29 20:22:47,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 2.8841192722320557, cross_entropy: 2.8841192722320557 +[2025-04-29 20:22:48,321][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 2.3785600662231445, cross_entropy: 2.3785600662231445 +[2025-04-29 20:22:51,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 0.8902109861373901, cross_entropy: 0.8902109861373901 +[2025-04-29 20:22:52,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 1.2926390171051025, cross_entropy: 1.2926390171051025 +[2025-04-29 20:22:55,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 2.5834031105041504, cross_entropy: 2.5834031105041504 +[2025-04-29 20:22:56,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 2.1452865600585938, cross_entropy: 2.1452865600585938 +[2025-04-29 20:22:59,491][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 1.401258945465088, cross_entropy: 1.401258945465088 +[2025-04-29 20:23:00,114][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.006335973739624, cross_entropy: 2.006335973739624 +[2025-04-29 20:23:03,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 1.8877270221710205, cross_entropy: 1.8877270221710205 +[2025-04-29 20:23:04,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 2.6285204887390137, cross_entropy: 2.6285204887390137 +[2025-04-29 20:23:07,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 0.8599736094474792, cross_entropy: 0.8599736094474792 +[2025-04-29 20:23:07,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.6475309133529663, cross_entropy: 0.6475309133529663 +[2025-04-29 20:23:11,236][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 1.785024642944336, cross_entropy: 1.785024642944336 +[2025-04-29 20:23:11,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 2.4675300121307373, cross_entropy: 2.4675300121307373 +[2025-04-29 20:23:15,356][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 2.155094861984253, cross_entropy: 2.155094861984253 +[2025-04-29 20:23:16,215][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 3.121614456176758, cross_entropy: 3.121614456176758 +[2025-04-29 20:23:19,662][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.2453703880310059, cross_entropy: 1.2453703880310059 +[2025-04-29 20:23:20,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 0.7163252234458923, cross_entropy: 0.7163252234458923 +[2025-04-29 20:23:23,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 1.4331809282302856, cross_entropy: 1.4331809282302856 +[2025-04-29 20:23:24,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 0.9210737943649292, cross_entropy: 0.9210737943649292 +[2025-04-29 20:23:27,926][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 0.90827476978302, cross_entropy: 0.90827476978302 +[2025-04-29 20:23:28,597][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 1.0457172393798828, cross_entropy: 1.0457172393798828 +[2025-04-29 20:23:31,777][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.1054506301879883, cross_entropy: 1.1054506301879883 +[2025-04-29 20:23:32,892][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 0.9029106497764587, cross_entropy: 0.9029106497764587 +[2025-04-29 20:23:36,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.9607433080673218, cross_entropy: 1.9607433080673218 +[2025-04-29 20:23:37,614][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 2.614560604095459, cross_entropy: 2.614560604095459 +[2025-04-29 20:23:41,833][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 1.0353100299835205, cross_entropy: 1.0353100299835205 +[2025-04-29 20:23:42,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.6261563301086426, cross_entropy: 2.6261563301086426 +[2025-04-29 20:23:46,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 0.6479660272598267, cross_entropy: 0.6479660272598267 +[2025-04-29 20:23:46,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 0.6841452121734619, cross_entropy: 0.6841452121734619 +[2025-04-29 20:23:51,039][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 2.684108257293701, cross_entropy: 2.684108257293701 +[2025-04-29 20:23:51,385][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 0.9901022911071777, cross_entropy: 0.9901022911071777 +[2025-04-29 20:23:56,209][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.711621880531311, cross_entropy: 0.711621880531311 +[2025-04-29 20:23:56,572][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 1.1626436710357666, cross_entropy: 1.1626436710357666 +[2025-04-29 20:24:00,510][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 0.8726298809051514, cross_entropy: 0.8726298809051514 +[2025-04-29 20:24:00,875][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 1.1289448738098145, cross_entropy: 1.1289448738098145 +[2025-04-29 20:24:04,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.4455831050872803, cross_entropy: 1.4455831050872803 +[2025-04-29 20:24:04,445][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 1.4854302406311035, cross_entropy: 1.4854302406311035 +[2025-04-29 20:24:08,378][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 2.9201292991638184, cross_entropy: 2.9201292991638184 +[2025-04-29 20:24:08,732][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 1.763900637626648, cross_entropy: 1.763900637626648 +[2025-04-29 20:24:12,201][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 0.751450777053833, cross_entropy: 0.751450777053833 +[2025-04-29 20:24:12,528][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 3.136186122894287, cross_entropy: 3.136186122894287 +[2025-04-29 20:24:16,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 0.6825485229492188, cross_entropy: 0.6825485229492188 +[2025-04-29 20:24:16,607][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 0.9427980780601501, cross_entropy: 0.9427980780601501 +[2025-04-29 20:24:20,508][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 2.366230010986328, cross_entropy: 2.366230010986328 +[2025-04-29 20:24:20,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 2.8955612182617188, cross_entropy: 2.8955612182617188 +[2025-04-29 20:24:24,610][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 1.0675287246704102, cross_entropy: 1.0675287246704102 +[2025-04-29 20:24:25,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 1.1265389919281006, cross_entropy: 1.1265389919281006 +[2025-04-29 20:24:28,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 0.5217485427856445, cross_entropy: 0.5217485427856445 +[2025-04-29 20:24:30,187][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 1.8737804889678955, cross_entropy: 1.8737804889678955 +[2025-04-29 20:24:32,994][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 0.6988227367401123, cross_entropy: 0.6988227367401123 +[2025-04-29 20:24:33,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 1.9672795534133911, cross_entropy: 1.9672795534133911 +[2025-04-29 20:24:37,750][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 1.81922447681427, cross_entropy: 1.81922447681427 +[2025-04-29 20:24:38,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 2.3440752029418945, cross_entropy: 2.3440752029418945 +[2025-04-29 20:24:41,919][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.8852454423904419, cross_entropy: 0.8852454423904419 +[2025-04-29 20:24:42,642][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 0.9138060808181763, cross_entropy: 0.9138060808181763 +[2025-04-29 20:24:46,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.575406551361084, cross_entropy: 1.575406551361084 +[2025-04-29 20:24:46,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 2.266282081604004, cross_entropy: 2.266282081604004 +[2025-04-29 20:24:49,528][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.3662476539611816, cross_entropy: 1.3662476539611816 +[2025-04-29 20:28:07,572][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.6249465942382812, cross_entropy: 1.6249465942382812 +[2025-04-29 20:28:07,573][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.1270513534545898, cross_entropy: 1.1270513534545898 +[2025-04-29 20:28:07,826][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/best_epoch.pth. +[2025-04-29 20:28:08,011][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/epoch10.pth. +[2025-04-29 20:28:08,251][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. +[2025-04-29 20:28:08,496][BaseTrainer][INFO] - Save model: ./exp/20250429-174748/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..5aabfa9e91014a5c988ae284486a3c6bf332ec29 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e212846d1bddc31350d1dfeeb900f2851d8d379ed46f30fc1bb256d13c61fd03 +size 51764965 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..afb13944334aaa99551a0f018f069de5f1b5a866 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250429-174748/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622b9ec65a502c7ed2327c2d0ccbc3ec4608dc1f8f675bcfb564cb33ce35bc90 +size 51716323 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f549bedb9b8f3662c713c1c9d71481db7a54b890 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/config.yaml @@ -0,0 +1,231 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250430-132920 + tensorboard_dir: ./tensorboard/20250430-132920 + save_checkpoint: + iteration: + every: 10000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/hydra.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0cf04a96f8b6a456a710238cc1e2fc7972786beb --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/hydra.yaml @@ -0,0 +1,191 @@ +hydra: + run: + dir: ./exp/20250430-132920/log/20250430-132923 + sweep: + dir: multirun/${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/20250430-132920/log/20250430-132923 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_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_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250430-132920 + - train.output.tensorboard_dir=./tensorboard/20250430-132920 + job: + name: train + chdir: false + override_dirname: +metrics=birdclef2025_categorical_cross_entropy,criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_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_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250430-132920,train.output.tensorboard_dir=./tensorboard/20250430-132920,train.resume.continue_from=,train=birdclef2025_reshape_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/20250430-132920/log/20250430-132923 + 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_reshape_efficientnet_b0 + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/overrides.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0f81d1271a3db981fe774dd85c8136e5d7d61a56 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/overrides.yaml @@ -0,0 +1,17 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_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_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250430-132920 +- train.output.tensorboard_dir=./tensorboard/20250430-132920 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..cc42b856c0db8afb8afbe347d3b782156b01f083 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/.hydra/resolved_config.yaml @@ -0,0 +1,290 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250430-132920 + tensorboard_dir: ./tensorboard/20250430-132920 + save_checkpoint: + iteration: + every: 10000 + path: ./exp/20250430-132920/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250430-132920/model/epoch{epoch}.pth + last: + path: ./exp/20250430-132920/model/last.pth + best_epoch: + path: ./exp/20250430-132920/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 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/train.log b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/train.log new file mode 100644 index 0000000000000000000000000000000000000000..3dbf708d6808b43b50bce702224fe906121272b2 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/log/20250430-132923/train.log @@ -0,0 +1,4297 @@ +[2025-04-30 13:29:52,541][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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250430-132920 + tensorboard_dir: ./tensorboard/20250430-132920 + save_checkpoint: + iteration: + every: 10000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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} + +[2025-04-30 13:29:52,541][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) + ) +) +[2025-04-30 13:29:52,546][BaseTrainer][INFO] - # of parameters: 4271434. +[2025-04-30 13:30:02,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.302931308746338, cross_entropy: 5.302931308746338 +[2025-04-30 13:30:02,405][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.283402442932129, cross_entropy: 5.283402442932129 +[2025-04-30 13:30:02,745][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.221212387084961, cross_entropy: 5.221212387084961 +[2025-04-30 13:30:03,118][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.243993759155273, cross_entropy: 5.243993759155273 +[2025-04-30 13:30:05,949][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.108799934387207, cross_entropy: 5.108799934387207 +[2025-04-30 13:30:06,863][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.089110374450684, cross_entropy: 5.089110374450684 +[2025-04-30 13:30:09,620][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 4.964911460876465, cross_entropy: 4.964911460876465 +[2025-04-30 13:30:10,620][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.069982051849365, cross_entropy: 5.069982051849365 +[2025-04-30 13:30:13,005][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 4.879220008850098, cross_entropy: 4.879220008850098 +[2025-04-30 13:30:14,747][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 4.800060272216797, cross_entropy: 4.800060272216797 +[2025-04-30 13:30:16,932][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 4.915607929229736, cross_entropy: 4.915607929229736 +[2025-04-30 13:30:18,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 4.777491569519043, cross_entropy: 4.777491569519043 +[2025-04-30 13:30:21,107][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 4.924041748046875, cross_entropy: 4.924041748046875 +[2025-04-30 13:30:23,348][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 4.76125431060791, cross_entropy: 4.76125431060791 +[2025-04-30 13:30:25,207][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 4.828367710113525, cross_entropy: 4.828367710113525 +[2025-04-30 13:30:26,950][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.676011562347412, cross_entropy: 4.676011562347412 +[2025-04-30 13:30:29,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.085284233093262, cross_entropy: 5.085284233093262 +[2025-04-30 13:30:31,366][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 5.194859504699707, cross_entropy: 5.194859504699707 +[2025-04-30 13:30:34,409][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.641758918762207, cross_entropy: 4.641758918762207 +[2025-04-30 13:30:35,245][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.871301651000977, cross_entropy: 4.871301651000977 +[2025-04-30 13:30:38,715][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.608482360839844, cross_entropy: 4.608482360839844 +[2025-04-30 13:30:39,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 4.898494720458984, cross_entropy: 4.898494720458984 +[2025-04-30 13:30:42,588][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 4.690732002258301, cross_entropy: 4.690732002258301 +[2025-04-30 13:30:42,903][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 4.7397332191467285, cross_entropy: 4.7397332191467285 +[2025-04-30 13:30:46,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.609688758850098, cross_entropy: 4.609688758850098 +[2025-04-30 13:30:47,203][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.753361701965332, cross_entropy: 4.753361701965332 +[2025-04-30 13:30:49,811][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.641672134399414, cross_entropy: 4.641672134399414 +[2025-04-30 13:30:51,154][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.561648368835449, cross_entropy: 4.561648368835449 +[2025-04-30 13:30:53,657][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.544717311859131, cross_entropy: 4.544717311859131 +[2025-04-30 13:30:55,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.615734100341797, cross_entropy: 4.615734100341797 +[2025-04-30 13:30:57,534][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.413717269897461, cross_entropy: 4.413717269897461 +[2025-04-30 13:30:59,271][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 4.862681865692139, cross_entropy: 4.862681865692139 +[2025-04-30 13:31:01,790][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.769654750823975, cross_entropy: 4.769654750823975 +[2025-04-30 13:31:03,645][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 4.665258884429932, cross_entropy: 4.665258884429932 +[2025-04-30 13:31:05,964][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 4.42427921295166, cross_entropy: 4.42427921295166 +[2025-04-30 13:31:07,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.285861492156982, cross_entropy: 4.285861492156982 +[2025-04-30 13:31:09,699][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.430037498474121, cross_entropy: 4.430037498474121 +[2025-04-30 13:31:11,446][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.288614273071289, cross_entropy: 4.288614273071289 +[2025-04-30 13:31:13,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.7988080978393555, cross_entropy: 4.7988080978393555 +[2025-04-30 13:31:16,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.751255989074707, cross_entropy: 4.751255989074707 +[2025-04-30 13:31:17,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.588732719421387, cross_entropy: 4.588732719421387 +[2025-04-30 13:31:20,725][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.3099870681762695, cross_entropy: 4.3099870681762695 +[2025-04-30 13:31:21,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 4.330026626586914, cross_entropy: 4.330026626586914 +[2025-04-30 13:31:24,224][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.5401740074157715, cross_entropy: 4.5401740074157715 +[2025-04-30 13:31:25,807][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.387330055236816, cross_entropy: 4.387330055236816 +[2025-04-30 13:31:28,233][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.101847171783447, cross_entropy: 4.101847171783447 +[2025-04-30 13:31:30,025][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.559490203857422, cross_entropy: 4.559490203857422 +[2025-04-30 13:31:32,097][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.292463302612305, cross_entropy: 4.292463302612305 +[2025-04-30 13:31:35,190][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.50818395614624, cross_entropy: 4.50818395614624 +[2025-04-30 13:31:35,825][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.345264434814453, cross_entropy: 4.345264434814453 +[2025-04-30 13:31:39,243][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.004391670227051, cross_entropy: 4.004391670227051 +[2025-04-30 13:31:39,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.174909591674805, cross_entropy: 4.174909591674805 +[2025-04-30 13:31:43,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.186873912811279, cross_entropy: 4.186873912811279 +[2025-04-30 13:31:44,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 4.276283264160156, cross_entropy: 4.276283264160156 +[2025-04-30 13:31:46,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.142200946807861, cross_entropy: 4.142200946807861 +[2025-04-30 13:31:48,084][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.283634185791016, cross_entropy: 4.283634185791016 +[2025-04-30 13:31:50,695][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.0206074714660645, cross_entropy: 4.0206074714660645 +[2025-04-30 13:31:51,972][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.0944342613220215, cross_entropy: 4.0944342613220215 +[2025-04-30 13:31:54,744][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.105462074279785, cross_entropy: 4.105462074279785 +[2025-04-30 13:31:56,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.049962997436523, cross_entropy: 4.049962997436523 +[2025-04-30 13:31:59,259][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.381836891174316, cross_entropy: 4.381836891174316 +[2025-04-30 13:32:00,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.204795837402344, cross_entropy: 4.204795837402344 +[2025-04-30 13:32:03,186][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.223920822143555, cross_entropy: 4.223920822143555 +[2025-04-30 13:32:04,298][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.071588039398193, cross_entropy: 4.071588039398193 +[2025-04-30 13:32:07,415][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.144485950469971, cross_entropy: 4.144485950469971 +[2025-04-30 13:32:08,226][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 3.9737579822540283, cross_entropy: 3.9737579822540283 +[2025-04-30 13:32:11,259][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 3.969269275665283, cross_entropy: 3.969269275665283 +[2025-04-30 13:32:12,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 4.318899154663086, cross_entropy: 4.318899154663086 +[2025-04-30 13:32:15,353][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.452785491943359, cross_entropy: 4.452785491943359 +[2025-04-30 13:32:15,741][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.099088668823242, cross_entropy: 4.099088668823242 +[2025-04-30 13:32:19,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.643980503082275, cross_entropy: 4.643980503082275 +[2025-04-30 13:32:19,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.077904224395752, cross_entropy: 4.077904224395752 +[2025-04-30 13:32:22,969][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 3.761712074279785, cross_entropy: 3.761712074279785 +[2025-04-30 13:32:23,648][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.379891395568848, cross_entropy: 4.379891395568848 +[2025-04-30 13:32:26,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 3.620786190032959, cross_entropy: 3.620786190032959 +[2025-04-30 13:32:27,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 3.656360149383545, cross_entropy: 3.656360149383545 +[2025-04-30 13:32:30,675][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 3.8206610679626465, cross_entropy: 3.8206610679626465 +[2025-04-30 13:32:31,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.3236517906188965, cross_entropy: 4.3236517906188965 +[2025-04-30 13:32:34,569][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.34844970703125, cross_entropy: 4.34844970703125 +[2025-04-30 13:32:35,153][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.107034683227539, cross_entropy: 4.107034683227539 +[2025-04-30 13:32:39,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.350558280944824, cross_entropy: 4.350558280944824 +[2025-04-30 13:32:40,084][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 3.3671011924743652, cross_entropy: 3.3671011924743652 +[2025-04-30 13:32:44,218][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.458925724029541, cross_entropy: 4.458925724029541 +[2025-04-30 13:32:44,538][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 3.8542251586914062, cross_entropy: 3.8542251586914062 +[2025-04-30 13:32:48,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 3.8513524532318115, cross_entropy: 3.8513524532318115 +[2025-04-30 13:32:48,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 3.579826831817627, cross_entropy: 3.579826831817627 +[2025-04-30 13:32:52,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 3.482017993927002, cross_entropy: 3.482017993927002 +[2025-04-30 13:32:52,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.137218475341797, cross_entropy: 4.137218475341797 +[2025-04-30 13:32:55,478][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.23097038269043, cross_entropy: 4.23097038269043 +[2025-04-30 13:32:55,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 3.80271577835083, cross_entropy: 3.80271577835083 +[2025-04-30 13:32:59,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.114719390869141, cross_entropy: 4.114719390869141 +[2025-04-30 13:32:59,367][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 3.9197323322296143, cross_entropy: 3.9197323322296143 +[2025-04-30 13:33:03,103][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 3.6359338760375977, cross_entropy: 3.6359338760375977 +[2025-04-30 13:33:03,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.160984039306641, cross_entropy: 4.160984039306641 +[2025-04-30 13:33:07,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.3536553382873535, cross_entropy: 4.3536553382873535 +[2025-04-30 13:33:07,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 3.471364974975586, cross_entropy: 3.471364974975586 +[2025-04-30 13:33:10,989][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.301711082458496, cross_entropy: 4.301711082458496 +[2025-04-30 13:33:11,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 3.096679210662842, cross_entropy: 3.096679210662842 +[2025-04-30 13:33:15,454][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 3.7513298988342285, cross_entropy: 3.7513298988342285 +[2025-04-30 13:33:15,787][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 3.4468796253204346, cross_entropy: 3.4468796253204346 +[2025-04-30 13:33:19,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.148987770080566, cross_entropy: 4.148987770080566 +[2025-04-30 13:33:19,395][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 3.5077621936798096, cross_entropy: 3.5077621936798096 +[2025-04-30 13:33:23,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 3.6368212699890137, cross_entropy: 3.6368212699890137 +[2025-04-30 13:33:23,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 3.2628045082092285, cross_entropy: 3.2628045082092285 +[2025-04-30 13:33:27,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 3.1930408477783203, cross_entropy: 3.1930408477783203 +[2025-04-30 13:33:28,092][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 3.7570858001708984, cross_entropy: 3.7570858001708984 +[2025-04-30 13:33:31,445][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 3.399879217147827, cross_entropy: 3.399879217147827 +[2025-04-30 13:33:31,757][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.3135881423950195, cross_entropy: 4.3135881423950195 +[2025-04-30 13:33:35,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 3.8908982276916504, cross_entropy: 3.8908982276916504 +[2025-04-30 13:33:35,350][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 3.8749899864196777, cross_entropy: 3.8749899864196777 +[2025-04-30 13:33:39,142][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 3.059603452682495, cross_entropy: 3.059603452682495 +[2025-04-30 13:33:39,478][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 3.4958810806274414, cross_entropy: 3.4958810806274414 +[2025-04-30 13:33:42,765][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 3.8154966831207275, cross_entropy: 3.8154966831207275 +[2025-04-30 13:33:43,100][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 3.675947666168213, cross_entropy: 3.675947666168213 +[2025-04-30 13:33:47,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.122170448303223, cross_entropy: 4.122170448303223 +[2025-04-30 13:33:47,708][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 3.2716593742370605, cross_entropy: 3.2716593742370605 +[2025-04-30 13:33:50,898][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 3.2426257133483887, cross_entropy: 3.2426257133483887 +[2025-04-30 13:33:51,214][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.463261604309082, cross_entropy: 4.463261604309082 +[2025-04-30 13:33:55,217][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.1430463790893555, cross_entropy: 4.1430463790893555 +[2025-04-30 13:33:55,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.392714023590088, cross_entropy: 4.392714023590088 +[2025-04-30 13:33:58,987][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.350134372711182, cross_entropy: 4.350134372711182 +[2025-04-30 13:33:59,300][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 3.0015218257904053, cross_entropy: 3.0015218257904053 +[2025-04-30 13:34:02,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 3.594817876815796, cross_entropy: 3.594817876815796 +[2025-04-30 13:34:02,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 3.246914863586426, cross_entropy: 3.246914863586426 +[2025-04-30 13:34:05,781][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.219468116760254, cross_entropy: 4.219468116760254 +[2025-04-30 13:34:06,114][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 3.002918243408203, cross_entropy: 3.002918243408203 +[2025-04-30 13:34:09,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 3.4994354248046875, cross_entropy: 3.4994354248046875 +[2025-04-30 13:34:10,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.183218955993652, cross_entropy: 4.183218955993652 +[2025-04-30 13:34:14,637][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 3.2497763633728027, cross_entropy: 3.2497763633728027 +[2025-04-30 13:34:14,973][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 4.0085768699646, cross_entropy: 4.0085768699646 +[2025-04-30 13:34:18,167][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.186661720275879, cross_entropy: 4.186661720275879 +[2025-04-30 13:34:18,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 3.779937744140625, cross_entropy: 3.779937744140625 +[2025-04-30 13:34:22,036][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.41380500793457, cross_entropy: 4.41380500793457 +[2025-04-30 13:34:22,356][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.033576011657715, cross_entropy: 4.033576011657715 +[2025-04-30 13:34:25,637][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 3.035702705383301, cross_entropy: 3.035702705383301 +[2025-04-30 13:34:25,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 3.5619590282440186, cross_entropy: 3.5619590282440186 +[2025-04-30 13:34:29,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 3.870943546295166, cross_entropy: 3.870943546295166 +[2025-04-30 13:34:29,343][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.168976783752441, cross_entropy: 4.168976783752441 +[2025-04-30 13:34:32,751][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 3.201469659805298, cross_entropy: 3.201469659805298 +[2025-04-30 13:34:33,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 3.3327789306640625, cross_entropy: 3.3327789306640625 +[2025-04-30 13:34:36,282][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 3.850144386291504, cross_entropy: 3.850144386291504 +[2025-04-30 13:34:36,595][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 3.4515416622161865, cross_entropy: 3.4515416622161865 +[2025-04-30 13:34:39,939][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 3.957961320877075, cross_entropy: 3.957961320877075 +[2025-04-30 13:34:40,279][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.155576705932617, cross_entropy: 4.155576705932617 +[2025-04-30 13:34:43,877][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 3.5208740234375, cross_entropy: 3.5208740234375 +[2025-04-30 13:34:44,209][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 3.448493003845215, cross_entropy: 3.448493003845215 +[2025-04-30 13:34:47,833][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 3.616997003555298, cross_entropy: 3.616997003555298 +[2025-04-30 13:34:48,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 3.691145896911621, cross_entropy: 3.691145896911621 +[2025-04-30 13:34:52,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 3.286940813064575, cross_entropy: 3.286940813064575 +[2025-04-30 13:34:52,640][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.230721950531006, cross_entropy: 4.230721950531006 +[2025-04-30 13:34:55,892][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 3.051626443862915, cross_entropy: 3.051626443862915 +[2025-04-30 13:34:56,233][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 3.1900811195373535, cross_entropy: 3.1900811195373535 +[2025-04-30 13:34:59,739][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 3.6507859230041504, cross_entropy: 3.6507859230041504 +[2025-04-30 13:35:00,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 2.945143222808838, cross_entropy: 2.945143222808838 +[2025-04-30 13:35:03,397][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 3.9227499961853027, cross_entropy: 3.9227499961853027 +[2025-04-30 13:35:03,729][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 3.6514925956726074, cross_entropy: 3.6514925956726074 +[2025-04-30 13:35:07,249][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.016426086425781, cross_entropy: 4.016426086425781 +[2025-04-30 13:35:07,585][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 3.6548705101013184, cross_entropy: 3.6548705101013184 +[2025-04-30 13:35:11,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 2.9517908096313477, cross_entropy: 2.9517908096313477 +[2025-04-30 13:35:12,078][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 3.6770548820495605, cross_entropy: 3.6770548820495605 +[2025-04-30 13:35:15,143][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 4.1624755859375, cross_entropy: 4.1624755859375 +[2025-04-30 13:35:15,485][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 3.0659337043762207, cross_entropy: 3.0659337043762207 +[2025-04-30 13:35:18,836][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.211574554443359, cross_entropy: 4.211574554443359 +[2025-04-30 13:35:19,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 3.1640212535858154, cross_entropy: 3.1640212535858154 +[2025-04-30 13:35:22,830][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 3.092480182647705, cross_entropy: 3.092480182647705 +[2025-04-30 13:35:23,163][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 3.397177219390869, cross_entropy: 3.397177219390869 +[2025-04-30 13:35:26,350][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 3.637457847595215, cross_entropy: 3.637457847595215 +[2025-04-30 13:35:26,678][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 3.607234001159668, cross_entropy: 3.607234001159668 +[2025-04-30 13:35:29,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.165239334106445, cross_entropy: 4.165239334106445 +[2025-04-30 13:35:30,324][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 3.8935840129852295, cross_entropy: 3.8935840129852295 +[2025-04-30 13:35:33,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 2.840059757232666, cross_entropy: 2.840059757232666 +[2025-04-30 13:35:34,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 3.1522743701934814, cross_entropy: 3.1522743701934814 +[2025-04-30 13:35:37,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 3.754851818084717, cross_entropy: 3.754851818084717 +[2025-04-30 13:35:38,250][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 3.787078857421875, cross_entropy: 3.787078857421875 +[2025-04-30 13:35:41,306][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.161879062652588, cross_entropy: 4.161879062652588 +[2025-04-30 13:35:41,620][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 3.8669419288635254, cross_entropy: 3.8669419288635254 +[2025-04-30 13:35:45,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 4.003451347351074, cross_entropy: 4.003451347351074 +[2025-04-30 13:35:45,553][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 3.956355333328247, cross_entropy: 3.956355333328247 +[2025-04-30 13:35:49,669][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 3.4405412673950195, cross_entropy: 3.4405412673950195 +[2025-04-30 13:35:49,989][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 3.626163959503174, cross_entropy: 3.626163959503174 +[2025-04-30 13:35:53,905][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 3.398662567138672, cross_entropy: 3.398662567138672 +[2025-04-30 13:35:54,243][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 3.9055063724517822, cross_entropy: 3.9055063724517822 +[2025-04-30 13:35:58,683][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 2.9946999549865723, cross_entropy: 2.9946999549865723 +[2025-04-30 13:35:59,013][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.1203532218933105, cross_entropy: 4.1203532218933105 +[2025-04-30 13:36:03,367][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 3.544724941253662, cross_entropy: 3.544724941253662 +[2025-04-30 13:36:03,695][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 3.016667366027832, cross_entropy: 3.016667366027832 +[2025-04-30 13:36:07,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 3.3046774864196777, cross_entropy: 3.3046774864196777 +[2025-04-30 13:36:07,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 3.278528928756714, cross_entropy: 3.278528928756714 +[2025-04-30 13:36:11,112][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 2.8211731910705566, cross_entropy: 2.8211731910705566 +[2025-04-30 13:36:11,447][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.8653101921081543, cross_entropy: 3.8653101921081543 +[2025-04-30 13:36:15,200][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 2.5766289234161377, cross_entropy: 2.5766289234161377 +[2025-04-30 13:36:15,512][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 3.2128164768218994, cross_entropy: 3.2128164768218994 +[2025-04-30 13:36:19,204][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 3.225306510925293, cross_entropy: 3.225306510925293 +[2025-04-30 13:36:19,537][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 4.071686744689941, cross_entropy: 4.071686744689941 +[2025-04-30 13:36:23,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 2.685147762298584, cross_entropy: 2.685147762298584 +[2025-04-30 13:36:23,558][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 3.227982997894287, cross_entropy: 3.227982997894287 +[2025-04-30 13:36:27,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 3.982966423034668, cross_entropy: 3.982966423034668 +[2025-04-30 13:36:27,336][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 2.452263355255127, cross_entropy: 2.452263355255127 +[2025-04-30 13:36:30,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 3.525800943374634, cross_entropy: 3.525800943374634 +[2025-04-30 13:36:30,852][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 3.141958713531494, cross_entropy: 3.141958713531494 +[2025-04-30 13:36:33,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 2.782918930053711, cross_entropy: 2.782918930053711 +[2025-04-30 13:36:34,259][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 2.9780430793762207, cross_entropy: 2.9780430793762207 +[2025-04-30 13:36:37,575][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 3.6213560104370117, cross_entropy: 3.6213560104370117 +[2025-04-30 13:36:37,902][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 2.7180967330932617, cross_entropy: 2.7180967330932617 +[2025-04-30 13:36:41,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.037413597106934, cross_entropy: 4.037413597106934 +[2025-04-30 13:36:41,594][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 3.0354819297790527, cross_entropy: 3.0354819297790527 +[2025-04-30 13:36:44,912][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 2.9262022972106934, cross_entropy: 2.9262022972106934 +[2025-04-30 13:36:45,246][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 3.768404960632324, cross_entropy: 3.768404960632324 +[2025-04-30 13:36:48,937][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 2.4422967433929443, cross_entropy: 2.4422967433929443 +[2025-04-30 13:36:49,252][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.727322578430176, cross_entropy: 3.727322578430176 +[2025-04-30 13:36:52,366][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 3.7625951766967773, cross_entropy: 3.7625951766967773 +[2025-04-30 13:36:52,678][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.749058246612549, cross_entropy: 3.749058246612549 +[2025-04-30 13:36:56,026][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 3.882810115814209, cross_entropy: 3.882810115814209 +[2025-04-30 13:36:56,357][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 2.486722946166992, cross_entropy: 2.486722946166992 +[2025-04-30 13:36:59,993][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 3.093163251876831, cross_entropy: 3.093163251876831 +[2025-04-30 13:37:00,335][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 2.9507641792297363, cross_entropy: 2.9507641792297363 +[2025-04-30 13:37:03,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.929659128189087, cross_entropy: 3.929659128189087 +[2025-04-30 13:37:03,948][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 2.931016445159912, cross_entropy: 2.931016445159912 +[2025-04-30 13:37:07,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.3208234310150146, cross_entropy: 3.3208234310150146 +[2025-04-30 13:37:07,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 3.7943434715270996, cross_entropy: 3.7943434715270996 +[2025-04-30 13:37:11,139][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 2.969756603240967, cross_entropy: 2.969756603240967 +[2025-04-30 13:37:11,466][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.0962815284729, cross_entropy: 4.0962815284729 +[2025-04-30 13:37:15,477][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 3.523001194000244, cross_entropy: 3.523001194000244 +[2025-04-30 13:37:15,789][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 2.829620361328125, cross_entropy: 2.829620361328125 +[2025-04-30 13:37:19,493][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 2.7454752922058105, cross_entropy: 2.7454752922058105 +[2025-04-30 13:37:19,831][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 3.4429945945739746, cross_entropy: 3.4429945945739746 +[2025-04-30 13:37:23,040][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 2.9078776836395264, cross_entropy: 2.9078776836395264 +[2025-04-30 13:37:23,375][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 2.277195930480957, cross_entropy: 2.277195930480957 +[2025-04-30 13:37:26,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 2.559282064437866, cross_entropy: 2.559282064437866 +[2025-04-30 13:37:27,275][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 2.9886560440063477, cross_entropy: 2.9886560440063477 +[2025-04-30 13:37:31,443][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 2.503054141998291, cross_entropy: 2.503054141998291 +[2025-04-30 13:37:31,755][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 2.9514169692993164, cross_entropy: 2.9514169692993164 +[2025-04-30 13:37:35,203][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 2.7517807483673096, cross_entropy: 2.7517807483673096 +[2025-04-30 13:37:35,537][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 2.890855312347412, cross_entropy: 2.890855312347412 +[2025-04-30 13:37:39,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 3.2034659385681152, cross_entropy: 3.2034659385681152 +[2025-04-30 13:37:39,691][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 3.2821779251098633, cross_entropy: 3.2821779251098633 +[2025-04-30 13:37:43,896][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 2.1485729217529297, cross_entropy: 2.1485729217529297 +[2025-04-30 13:37:44,210][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 2.6442222595214844, cross_entropy: 2.6442222595214844 +[2025-04-30 13:37:48,925][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 4.0115814208984375, cross_entropy: 4.0115814208984375 +[2025-04-30 13:37:49,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 2.5031206607818604, cross_entropy: 2.5031206607818604 +[2025-04-30 13:37:52,918][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.317002773284912, cross_entropy: 3.317002773284912 +[2025-04-30 13:37:53,252][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 2.8443994522094727, cross_entropy: 2.8443994522094727 +[2025-04-30 13:37:56,463][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 2.8400204181671143, cross_entropy: 2.8400204181671143 +[2025-04-30 13:37:56,787][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 2.8095030784606934, cross_entropy: 2.8095030784606934 +[2025-04-30 13:38:00,699][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 2.843546152114868, cross_entropy: 2.843546152114868 +[2025-04-30 13:38:01,011][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 4.176444053649902, cross_entropy: 4.176444053649902 +[2025-04-30 13:38:05,117][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 2.6371402740478516, cross_entropy: 2.6371402740478516 +[2025-04-30 13:38:05,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 4.075215816497803, cross_entropy: 4.075215816497803 +[2025-04-30 13:38:08,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.9359042644500732, cross_entropy: 3.9359042644500732 +[2025-04-30 13:38:08,649][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 3.992896795272827, cross_entropy: 3.992896795272827 +[2025-04-30 13:38:12,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.284710645675659, cross_entropy: 3.284710645675659 +[2025-04-30 13:38:12,394][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 2.9761087894439697, cross_entropy: 2.9761087894439697 +[2025-04-30 13:38:16,115][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.7052993774414062, cross_entropy: 3.7052993774414062 +[2025-04-30 13:38:16,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 2.8613767623901367, cross_entropy: 2.8613767623901367 +[2025-04-30 13:38:20,853][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 3.705716609954834, cross_entropy: 3.705716609954834 +[2025-04-30 13:38:21,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 3.09995174407959, cross_entropy: 3.09995174407959 +[2025-04-30 13:38:25,477][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 3.472682237625122, cross_entropy: 3.472682237625122 +[2025-04-30 13:38:25,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 2.5869832038879395, cross_entropy: 2.5869832038879395 +[2025-04-30 13:38:29,940][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 2.9307732582092285, cross_entropy: 2.9307732582092285 +[2025-04-30 13:38:30,254][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 2.3928110599517822, cross_entropy: 2.3928110599517822 +[2025-04-30 13:38:35,012][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 2.6867787837982178, cross_entropy: 2.6867787837982178 +[2025-04-30 13:38:35,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 2.941962480545044, cross_entropy: 2.941962480545044 +[2025-04-30 13:38:41,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 2.6231672763824463, cross_entropy: 2.6231672763824463 +[2025-04-30 13:38:41,393][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 3.6857526302337646, cross_entropy: 3.6857526302337646 +[2025-04-30 13:38:47,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 2.5326685905456543, cross_entropy: 2.5326685905456543 +[2025-04-30 13:38:47,629][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.442378282546997, cross_entropy: 3.442378282546997 +[2025-04-30 13:38:54,479][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 4.197765350341797, cross_entropy: 4.197765350341797 +[2025-04-30 13:38:54,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 2.976480007171631, cross_entropy: 2.976480007171631 +[2025-04-30 13:38:58,563][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 2.4395666122436523, cross_entropy: 2.4395666122436523 +[2025-04-30 13:38:58,883][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 3.590075969696045, cross_entropy: 3.590075969696045 +[2025-04-30 13:39:02,099][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 3.766974925994873, cross_entropy: 3.766974925994873 +[2025-04-30 13:39:02,417][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 2.95552921295166, cross_entropy: 2.95552921295166 +[2025-04-30 13:39:07,007][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.0629172325134277, cross_entropy: 3.0629172325134277 +[2025-04-30 13:39:07,320][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 3.690030574798584, cross_entropy: 3.690030574798584 +[2025-04-30 13:39:10,997][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 2.83134126663208, cross_entropy: 2.83134126663208 +[2025-04-30 13:39:11,313][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 2.8758187294006348, cross_entropy: 2.8758187294006348 +[2025-04-30 13:39:16,392][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 2.9018712043762207, cross_entropy: 2.9018712043762207 +[2025-04-30 13:39:16,723][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 3.4575934410095215, cross_entropy: 3.4575934410095215 +[2025-04-30 13:39:20,498][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 2.649921178817749, cross_entropy: 2.649921178817749 +[2025-04-30 13:39:20,836][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 4.2889251708984375, cross_entropy: 4.2889251708984375 +[2025-04-30 13:39:24,370][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 2.5133633613586426, cross_entropy: 2.5133633613586426 +[2025-04-30 13:39:24,683][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 2.7905611991882324, cross_entropy: 2.7905611991882324 +[2025-04-30 13:39:28,950][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 3.334510326385498, cross_entropy: 3.334510326385498 +[2025-04-30 13:39:29,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 2.313231945037842, cross_entropy: 2.313231945037842 +[2025-04-30 13:39:34,482][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 2.2223758697509766, cross_entropy: 2.2223758697509766 +[2025-04-30 13:39:34,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.7828540802001953, cross_entropy: 3.7828540802001953 +[2025-04-30 13:39:39,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 2.4276645183563232, cross_entropy: 2.4276645183563232 +[2025-04-30 13:39:40,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.091541290283203, cross_entropy: 3.091541290283203 +[2025-04-30 13:39:44,029][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 2.5408806800842285, cross_entropy: 2.5408806800842285 +[2025-04-30 13:39:44,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 2.7039570808410645, cross_entropy: 2.7039570808410645 +[2025-04-30 13:39:47,789][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.671278238296509, cross_entropy: 3.671278238296509 +[2025-04-30 13:39:48,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.7939460277557373, cross_entropy: 3.7939460277557373 +[2025-04-30 13:39:51,643][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 2.2318601608276367, cross_entropy: 2.2318601608276367 +[2025-04-30 13:39:51,973][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 2.88606858253479, cross_entropy: 2.88606858253479 +[2025-04-30 13:39:55,861][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 2.8924970626831055, cross_entropy: 2.8924970626831055 +[2025-04-30 13:39:56,203][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.004028797149658, cross_entropy: 3.004028797149658 +[2025-04-30 13:39:59,870][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 2.415790557861328, cross_entropy: 2.415790557861328 +[2025-04-30 13:40:00,193][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.5812628269195557, cross_entropy: 3.5812628269195557 +[2025-04-30 13:40:04,109][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 2.9772496223449707, cross_entropy: 2.9772496223449707 +[2025-04-30 13:40:04,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.4350242614746094, cross_entropy: 3.4350242614746094 +[2025-04-30 13:40:09,312][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 2.922081470489502, cross_entropy: 2.922081470489502 +[2025-04-30 13:40:09,627][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 3.0176167488098145, cross_entropy: 3.0176167488098145 +[2025-04-30 13:40:12,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 2.428098678588867, cross_entropy: 2.428098678588867 +[2025-04-30 13:40:13,279][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 2.987152338027954, cross_entropy: 2.987152338027954 +[2025-04-30 13:40:17,231][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 1.8152055740356445, cross_entropy: 1.8152055740356445 +[2025-04-30 13:40:17,565][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 4.092784881591797, cross_entropy: 4.092784881591797 +[2025-04-30 13:40:20,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 2.3559553623199463, cross_entropy: 2.3559553623199463 +[2025-04-30 13:40:21,116][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.667755603790283, cross_entropy: 3.667755603790283 +[2025-04-30 13:40:24,332][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.414010524749756, cross_entropy: 3.414010524749756 +[2025-04-30 13:40:24,666][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 2.1897506713867188, cross_entropy: 2.1897506713867188 +[2025-04-30 13:40:28,134][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 2.483783721923828, cross_entropy: 2.483783721923828 +[2025-04-30 13:40:28,450][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.1479053497314453, cross_entropy: 3.1479053497314453 +[2025-04-30 13:40:32,287][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 4.043145179748535, cross_entropy: 4.043145179748535 +[2025-04-30 13:40:32,614][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 2.120187997817993, cross_entropy: 2.120187997817993 +[2025-04-30 13:40:37,116][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 2.9502763748168945, cross_entropy: 2.9502763748168945 +[2025-04-30 13:40:37,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 3.7222824096679688, cross_entropy: 3.7222824096679688 +[2025-04-30 13:40:41,920][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 2.8657073974609375, cross_entropy: 2.8657073974609375 +[2025-04-30 13:40:42,238][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.616147994995117, cross_entropy: 3.616147994995117 +[2025-04-30 13:40:45,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 1.9560275077819824, cross_entropy: 1.9560275077819824 +[2025-04-30 13:40:46,258][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 2.0666303634643555, cross_entropy: 2.0666303634643555 +[2025-04-30 13:40:50,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 2.3038206100463867, cross_entropy: 2.3038206100463867 +[2025-04-30 13:40:50,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 2.816016674041748, cross_entropy: 2.816016674041748 +[2025-04-30 13:40:53,891][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.6287379264831543, cross_entropy: 3.6287379264831543 +[2025-04-30 13:40:54,208][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 2.0760536193847656, cross_entropy: 2.0760536193847656 +[2025-04-30 13:40:57,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.7919390201568604, cross_entropy: 3.7919390201568604 +[2025-04-30 13:40:58,307][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.0864319801330566, cross_entropy: 3.0864319801330566 +[2025-04-30 13:41:01,903][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 2.638457775115967, cross_entropy: 2.638457775115967 +[2025-04-30 13:41:02,222][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 1.935188889503479, cross_entropy: 1.935188889503479 +[2025-04-30 13:41:05,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 2.8161301612854004, cross_entropy: 2.8161301612854004 +[2025-04-30 13:41:05,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 2.5074079036712646, cross_entropy: 2.5074079036712646 +[2025-04-30 13:41:09,242][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 2.4824695587158203, cross_entropy: 2.4824695587158203 +[2025-04-30 13:41:09,573][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.8067128658294678, cross_entropy: 3.8067128658294678 +[2025-04-30 13:41:13,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 2.8762707710266113, cross_entropy: 2.8762707710266113 +[2025-04-30 13:41:14,188][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.285900592803955, cross_entropy: 3.285900592803955 +[2025-04-30 13:41:18,152][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 2.2280402183532715, cross_entropy: 2.2280402183532715 +[2025-04-30 13:41:18,484][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 2.0680341720581055, cross_entropy: 2.0680341720581055 +[2025-04-30 13:41:21,911][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 2.4647769927978516, cross_entropy: 2.4647769927978516 +[2025-04-30 13:41:22,249][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 3.817424774169922, cross_entropy: 3.817424774169922 +[2025-04-30 13:41:25,736][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 2.2890355587005615, cross_entropy: 2.2890355587005615 +[2025-04-30 13:41:26,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.132735252380371, cross_entropy: 3.132735252380371 +[2025-04-30 13:41:29,615][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 2.454860210418701, cross_entropy: 2.454860210418701 +[2025-04-30 13:41:29,930][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.6849656105041504, cross_entropy: 3.6849656105041504 +[2025-04-30 13:41:33,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 4.152278900146484, cross_entropy: 4.152278900146484 +[2025-04-30 13:41:33,874][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 2.3986454010009766, cross_entropy: 2.3986454010009766 +[2025-04-30 13:41:36,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 2.6408071517944336, cross_entropy: 2.6408071517944336 +[2025-04-30 13:41:37,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 4.094295024871826, cross_entropy: 4.094295024871826 +[2025-04-30 13:41:40,620][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.8430848121643066, cross_entropy: 2.8430848121643066 +[2025-04-30 13:41:40,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 2.8999345302581787, cross_entropy: 2.8999345302581787 +[2025-04-30 13:41:45,128][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 3.44175386428833, cross_entropy: 3.44175386428833 +[2025-04-30 13:41:45,467][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 2.061955451965332, cross_entropy: 2.061955451965332 +[2025-04-30 13:41:48,966][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 3.2815914154052734, cross_entropy: 3.2815914154052734 +[2025-04-30 13:41:49,281][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 2.589813709259033, cross_entropy: 2.589813709259033 +[2025-04-30 13:41:52,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.567765951156616, cross_entropy: 3.567765951156616 +[2025-04-30 13:41:53,114][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 3.3298840522766113, cross_entropy: 3.3298840522766113 +[2025-04-30 13:41:56,051][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 2.1471800804138184, cross_entropy: 2.1471800804138184 +[2025-04-30 13:41:59,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 2.2866923809051514, cross_entropy: 2.2866923809051514 +[2025-04-30 13:45:06,510][BaseTrainer][INFO] - [Epoch 1/10] (train) 3.5695853233337402, cross_entropy: 3.5695853233337402 +[2025-04-30 13:45:06,510][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.2386724948883057, cross_entropy: 2.2386724948883057 +[2025-04-30 13:45:06,510][BaseTrainer][INFO] - [Epoch 1/10] (metrics) roc_auc: 0.9480721950531006 +[2025-04-30 13:45:06,683][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 13:45:06,845][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch1.pth. +[2025-04-30 13:45:07,013][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 13:45:11,319][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 3.6262564659118652, cross_entropy: 3.6262564659118652 +[2025-04-30 13:45:11,658][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 2.1901447772979736, cross_entropy: 2.1901447772979736 +[2025-04-30 13:45:14,902][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.9379079341888428, cross_entropy: 3.9379079341888428 +[2025-04-30 13:45:15,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 1.9732924699783325, cross_entropy: 1.9732924699783325 +[2025-04-30 13:45:18,222][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 2.2833523750305176, cross_entropy: 2.2833523750305176 +[2025-04-30 13:45:18,561][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 3.9597408771514893, cross_entropy: 3.9597408771514893 +[2025-04-30 13:45:21,724][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 2.5276150703430176, cross_entropy: 2.5276150703430176 +[2025-04-30 13:45:22,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 1.9680230617523193, cross_entropy: 1.9680230617523193 +[2025-04-30 13:45:24,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 2.4444541931152344, cross_entropy: 2.4444541931152344 +[2025-04-30 13:45:25,268][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 2.307220458984375, cross_entropy: 2.307220458984375 +[2025-04-30 13:45:28,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 2.1184258460998535, cross_entropy: 2.1184258460998535 +[2025-04-30 13:45:28,915][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.7130517959594727, cross_entropy: 3.7130517959594727 +[2025-04-30 13:45:32,209][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.5530624389648438, cross_entropy: 3.5530624389648438 +[2025-04-30 13:45:32,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 2.066974639892578, cross_entropy: 2.066974639892578 +[2025-04-30 13:45:35,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 2.6883745193481445, cross_entropy: 2.6883745193481445 +[2025-04-30 13:45:36,302][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 3.4687514305114746, cross_entropy: 3.4687514305114746 +[2025-04-30 13:45:39,482][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 2.680821418762207, cross_entropy: 2.680821418762207 +[2025-04-30 13:45:39,822][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 2.1706643104553223, cross_entropy: 2.1706643104553223 +[2025-04-30 13:45:42,777][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.8675522804260254, cross_entropy: 3.8675522804260254 +[2025-04-30 13:45:43,115][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 1.7610396146774292, cross_entropy: 1.7610396146774292 +[2025-04-30 13:45:45,995][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.1012470722198486, cross_entropy: 3.1012470722198486 +[2025-04-30 13:45:46,332][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 2.2094998359680176, cross_entropy: 2.2094998359680176 +[2025-04-30 13:45:49,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.1432418823242188, cross_entropy: 3.1432418823242188 +[2025-04-30 13:45:49,702][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 3.4899139404296875, cross_entropy: 3.4899139404296875 +[2025-04-30 13:45:52,372][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.7975618839263916, cross_entropy: 3.7975618839263916 +[2025-04-30 13:45:52,708][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 2.1317217350006104, cross_entropy: 2.1317217350006104 +[2025-04-30 13:45:55,957][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.573720932006836, cross_entropy: 3.573720932006836 +[2025-04-30 13:45:56,293][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 3.1063146591186523, cross_entropy: 3.1063146591186523 +[2025-04-30 13:45:59,347][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 3.602384328842163, cross_entropy: 3.602384328842163 +[2025-04-30 13:45:59,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 2.151401996612549, cross_entropy: 2.151401996612549 +[2025-04-30 13:46:02,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 2.3799731731414795, cross_entropy: 2.3799731731414795 +[2025-04-30 13:46:03,225][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 2.4209141731262207, cross_entropy: 2.4209141731262207 +[2025-04-30 13:46:05,955][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 2.2222530841827393, cross_entropy: 2.2222530841827393 +[2025-04-30 13:46:06,293][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 2.591130495071411, cross_entropy: 2.591130495071411 +[2025-04-30 13:46:09,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 2.0422399044036865, cross_entropy: 2.0422399044036865 +[2025-04-30 13:46:09,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.6831064224243164, cross_entropy: 3.6831064224243164 +[2025-04-30 13:46:13,243][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.5365395545959473, cross_entropy: 3.5365395545959473 +[2025-04-30 13:46:13,581][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 1.8074933290481567, cross_entropy: 1.8074933290481567 +[2025-04-30 13:46:18,006][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 2.796177864074707, cross_entropy: 2.796177864074707 +[2025-04-30 13:46:18,343][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 2.0020155906677246, cross_entropy: 2.0020155906677246 +[2025-04-30 13:46:21,469][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.3616061210632324, cross_entropy: 3.3616061210632324 +[2025-04-30 13:46:21,809][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.1046462059020996, cross_entropy: 2.1046462059020996 +[2025-04-30 13:46:24,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.0232760906219482, cross_entropy: 3.0232760906219482 +[2025-04-30 13:46:24,680][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 2.613835573196411, cross_entropy: 2.613835573196411 +[2025-04-30 13:46:27,662][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.8008909225463867, cross_entropy: 3.8008909225463867 +[2025-04-30 13:46:28,002][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 2.944378137588501, cross_entropy: 2.944378137588501 +[2025-04-30 13:46:31,900][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 2.150573492050171, cross_entropy: 2.150573492050171 +[2025-04-30 13:46:32,213][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 2.2276711463928223, cross_entropy: 2.2276711463928223 +[2025-04-30 13:46:35,467][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 3.3606858253479004, cross_entropy: 3.3606858253479004 +[2025-04-30 13:46:35,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 3.2237870693206787, cross_entropy: 3.2237870693206787 +[2025-04-30 13:46:39,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.5037496089935303, cross_entropy: 3.5037496089935303 +[2025-04-30 13:46:39,491][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 2.605876922607422, cross_entropy: 2.605876922607422 +[2025-04-30 13:46:42,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 2.363649845123291, cross_entropy: 2.363649845123291 +[2025-04-30 13:46:42,993][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.519528865814209, cross_entropy: 3.519528865814209 +[2025-04-30 13:46:45,919][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 2.2817397117614746, cross_entropy: 2.2817397117614746 +[2025-04-30 13:46:46,230][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 1.9019484519958496, cross_entropy: 1.9019484519958496 +[2025-04-30 13:46:49,230][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 3.2836196422576904, cross_entropy: 3.2836196422576904 +[2025-04-30 13:46:49,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 2.662607192993164, cross_entropy: 2.662607192993164 +[2025-04-30 13:46:52,697][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.463927745819092, cross_entropy: 3.463927745819092 +[2025-04-30 13:46:53,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.4029183387756348, cross_entropy: 3.4029183387756348 +[2025-04-30 13:46:56,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.4500222206115723, cross_entropy: 3.4500222206115723 +[2025-04-30 13:46:56,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.820542097091675, cross_entropy: 3.820542097091675 +[2025-04-30 13:46:59,714][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 2.299351215362549, cross_entropy: 2.299351215362549 +[2025-04-30 13:47:00,048][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 1.6796581745147705, cross_entropy: 1.6796581745147705 +[2025-04-30 13:47:03,314][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 2.4804444313049316, cross_entropy: 2.4804444313049316 +[2025-04-30 13:47:03,656][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.73539400100708, cross_entropy: 3.73539400100708 +[2025-04-30 13:47:07,302][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 3.746095657348633, cross_entropy: 3.746095657348633 +[2025-04-30 13:47:07,620][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 2.046065092086792, cross_entropy: 2.046065092086792 +[2025-04-30 13:47:10,677][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 2.96417236328125, cross_entropy: 2.96417236328125 +[2025-04-30 13:47:11,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.65755558013916, cross_entropy: 3.65755558013916 +[2025-04-30 13:47:13,765][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.0693392753601074, cross_entropy: 3.0693392753601074 +[2025-04-30 13:47:14,109][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 2.183450937271118, cross_entropy: 2.183450937271118 +[2025-04-30 13:47:17,226][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.6548304557800293, cross_entropy: 3.6548304557800293 +[2025-04-30 13:47:17,571][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 1.89890718460083, cross_entropy: 1.89890718460083 +[2025-04-30 13:47:21,228][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 2.521305561065674, cross_entropy: 2.521305561065674 +[2025-04-30 13:47:21,568][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 3.509415626525879, cross_entropy: 3.509415626525879 +[2025-04-30 13:47:24,451][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 1.954484462738037, cross_entropy: 1.954484462738037 +[2025-04-30 13:47:24,798][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 1.8740042448043823, cross_entropy: 1.8740042448043823 +[2025-04-30 13:47:28,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.769353151321411, cross_entropy: 3.769353151321411 +[2025-04-30 13:47:28,618][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 2.3153915405273438, cross_entropy: 2.3153915405273438 +[2025-04-30 13:47:31,942][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 3.25423526763916, cross_entropy: 3.25423526763916 +[2025-04-30 13:47:32,282][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.4210939407348633, cross_entropy: 3.4210939407348633 +[2025-04-30 13:47:35,887][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.4499502182006836, cross_entropy: 2.4499502182006836 +[2025-04-30 13:47:36,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.2957122325897217, cross_entropy: 3.2957122325897217 +[2025-04-30 13:47:40,280][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 3.4008336067199707, cross_entropy: 3.4008336067199707 +[2025-04-30 13:47:40,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 3.620211601257324, cross_entropy: 3.620211601257324 +[2025-04-30 13:47:44,203][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.658928871154785, cross_entropy: 3.658928871154785 +[2025-04-30 13:47:44,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.4502663612365723, cross_entropy: 3.4502663612365723 +[2025-04-30 13:47:47,578][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.2056875228881836, cross_entropy: 3.2056875228881836 +[2025-04-30 13:47:47,928][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 3.4590868949890137, cross_entropy: 3.4590868949890137 +[2025-04-30 13:47:50,978][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.7915279865264893, cross_entropy: 3.7915279865264893 +[2025-04-30 13:47:51,321][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.570474147796631, cross_entropy: 3.570474147796631 +[2025-04-30 13:47:54,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 2.1326770782470703, cross_entropy: 2.1326770782470703 +[2025-04-30 13:47:55,175][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 3.15932035446167, cross_entropy: 3.15932035446167 +[2025-04-30 13:47:57,746][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 2.5745742321014404, cross_entropy: 2.5745742321014404 +[2025-04-30 13:47:58,090][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 2.2605674266815186, cross_entropy: 2.2605674266815186 +[2025-04-30 13:48:01,341][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.3908324241638184, cross_entropy: 3.3908324241638184 +[2025-04-30 13:48:01,683][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.2424821853637695, cross_entropy: 2.2424821853637695 +[2025-04-30 13:48:04,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 2.2643074989318848, cross_entropy: 2.2643074989318848 +[2025-04-30 13:48:04,942][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 2.5671353340148926, cross_entropy: 2.5671353340148926 +[2025-04-30 13:48:07,765][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 2.9813039302825928, cross_entropy: 2.9813039302825928 +[2025-04-30 13:48:08,110][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.4991559982299805, cross_entropy: 3.4991559982299805 +[2025-04-30 13:48:11,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 2.0985097885131836, cross_entropy: 2.0985097885131836 +[2025-04-30 13:48:11,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.944467544555664, cross_entropy: 2.944467544555664 +[2025-04-30 13:48:14,347][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 2.0874879360198975, cross_entropy: 2.0874879360198975 +[2025-04-30 13:48:14,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 2.946143865585327, cross_entropy: 2.946143865585327 +[2025-04-30 13:48:19,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.4947800636291504, cross_entropy: 2.4947800636291504 +[2025-04-30 13:48:19,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.1730594635009766, cross_entropy: 3.1730594635009766 +[2025-04-30 13:48:22,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.4916176795959473, cross_entropy: 3.4916176795959473 +[2025-04-30 13:48:22,952][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 1.9750585556030273, cross_entropy: 1.9750585556030273 +[2025-04-30 13:48:25,944][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.866626501083374, cross_entropy: 2.866626501083374 +[2025-04-30 13:48:26,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.1639559268951416, cross_entropy: 3.1639559268951416 +[2025-04-30 13:48:29,535][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 3.4728715419769287, cross_entropy: 3.4728715419769287 +[2025-04-30 13:48:29,870][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.1735777854919434, cross_entropy: 3.1735777854919434 +[2025-04-30 13:48:32,703][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.654022455215454, cross_entropy: 3.654022455215454 +[2025-04-30 13:48:33,041][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.3465280532836914, cross_entropy: 3.3465280532836914 +[2025-04-30 13:48:36,257][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 2.107426166534424, cross_entropy: 2.107426166534424 +[2025-04-30 13:48:36,589][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.2679433822631836, cross_entropy: 3.2679433822631836 +[2025-04-30 13:48:39,558][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 1.7506641149520874, cross_entropy: 1.7506641149520874 +[2025-04-30 13:48:39,895][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 2.4578704833984375, cross_entropy: 2.4578704833984375 +[2025-04-30 13:48:42,895][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 1.8379545211791992, cross_entropy: 1.8379545211791992 +[2025-04-30 13:48:43,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 2.0562026500701904, cross_entropy: 2.0562026500701904 +[2025-04-30 13:48:46,376][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 1.9308185577392578, cross_entropy: 1.9308185577392578 +[2025-04-30 13:48:46,712][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 1.6895674467086792, cross_entropy: 1.6895674467086792 +[2025-04-30 13:48:49,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 1.6275652647018433, cross_entropy: 1.6275652647018433 +[2025-04-30 13:48:49,628][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 2.3533310890197754, cross_entropy: 2.3533310890197754 +[2025-04-30 13:48:52,925][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.3331151008605957, cross_entropy: 3.3331151008605957 +[2025-04-30 13:48:53,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 1.9352034330368042, cross_entropy: 1.9352034330368042 +[2025-04-30 13:48:56,423][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 1.8598358631134033, cross_entropy: 1.8598358631134033 +[2025-04-30 13:48:56,756][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 2.5513997077941895, cross_entropy: 2.5513997077941895 +[2025-04-30 13:48:59,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 2.202425241470337, cross_entropy: 2.202425241470337 +[2025-04-30 13:48:59,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.8809361457824707, cross_entropy: 2.8809361457824707 +[2025-04-30 13:49:03,063][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 2.7840542793273926, cross_entropy: 2.7840542793273926 +[2025-04-30 13:49:03,388][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 3.0879404544830322, cross_entropy: 3.0879404544830322 +[2025-04-30 13:49:05,987][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 3.988607168197632, cross_entropy: 3.988607168197632 +[2025-04-30 13:49:06,326][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.663121223449707, cross_entropy: 3.663121223449707 +[2025-04-30 13:49:09,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 1.722497582435608, cross_entropy: 1.722497582435608 +[2025-04-30 13:49:09,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 3.4568538665771484, cross_entropy: 3.4568538665771484 +[2025-04-30 13:49:12,476][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.544330596923828, cross_entropy: 3.544330596923828 +[2025-04-30 13:49:12,820][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 1.7894775867462158, cross_entropy: 1.7894775867462158 +[2025-04-30 13:49:16,164][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 2.1011545658111572, cross_entropy: 2.1011545658111572 +[2025-04-30 13:49:16,498][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.819199562072754, cross_entropy: 2.819199562072754 +[2025-04-30 13:49:19,539][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 1.7637250423431396, cross_entropy: 1.7637250423431396 +[2025-04-30 13:49:19,880][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.300036668777466, cross_entropy: 2.300036668777466 +[2025-04-30 13:49:22,003][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.0655722618103027, cross_entropy: 2.0655722618103027 +[2025-04-30 13:49:22,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 4.032548427581787, cross_entropy: 4.032548427581787 +[2025-04-30 13:49:25,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 2.69559907913208, cross_entropy: 2.69559907913208 +[2025-04-30 13:49:25,369][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.172706365585327, cross_entropy: 2.172706365585327 +[2025-04-30 13:49:28,656][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 2.6715731620788574, cross_entropy: 2.6715731620788574 +[2025-04-30 13:49:28,993][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 3.3643651008605957, cross_entropy: 3.3643651008605957 +[2025-04-30 13:49:31,758][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 2.342740058898926, cross_entropy: 2.342740058898926 +[2025-04-30 13:49:32,096][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.151205539703369, cross_entropy: 3.151205539703369 +[2025-04-30 13:49:34,930][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 1.939461350440979, cross_entropy: 1.939461350440979 +[2025-04-30 13:49:35,265][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 1.9433965682983398, cross_entropy: 1.9433965682983398 +[2025-04-30 13:49:39,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.269697666168213, cross_entropy: 3.269697666168213 +[2025-04-30 13:49:39,609][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 2.2216343879699707, cross_entropy: 2.2216343879699707 +[2025-04-30 13:49:42,464][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 1.6053130626678467, cross_entropy: 1.6053130626678467 +[2025-04-30 13:49:42,801][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 2.9952759742736816, cross_entropy: 2.9952759742736816 +[2025-04-30 13:49:47,869][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 1.7214303016662598, cross_entropy: 1.7214303016662598 +[2025-04-30 13:49:48,210][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 2.552126884460449, cross_entropy: 2.552126884460449 +[2025-04-30 13:49:51,910][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 1.679547905921936, cross_entropy: 1.679547905921936 +[2025-04-30 13:49:52,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.11971378326416, cross_entropy: 3.11971378326416 +[2025-04-30 13:49:55,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 2.9500608444213867, cross_entropy: 2.9500608444213867 +[2025-04-30 13:49:55,785][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 3.504870891571045, cross_entropy: 3.504870891571045 +[2025-04-30 13:49:58,418][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 1.992896318435669, cross_entropy: 1.992896318435669 +[2025-04-30 13:49:58,731][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.6866626739501953, cross_entropy: 2.6866626739501953 +[2025-04-30 13:50:01,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 1.6988015174865723, cross_entropy: 1.6988015174865723 +[2025-04-30 13:50:02,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 2.134718894958496, cross_entropy: 2.134718894958496 +[2025-04-30 13:50:05,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.2148945331573486, cross_entropy: 2.2148945331573486 +[2025-04-30 13:50:06,098][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 3.5140576362609863, cross_entropy: 3.5140576362609863 +[2025-04-30 13:50:08,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 3.3043646812438965, cross_entropy: 3.3043646812438965 +[2025-04-30 13:50:09,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.026547908782959, cross_entropy: 2.026547908782959 +[2025-04-30 13:50:12,203][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 2.3308911323547363, cross_entropy: 2.3308911323547363 +[2025-04-30 13:50:12,542][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.472405195236206, cross_entropy: 2.472405195236206 +[2025-04-30 13:50:15,332][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 2.7730603218078613, cross_entropy: 2.7730603218078613 +[2025-04-30 13:50:15,674][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 2.271436929702759, cross_entropy: 2.271436929702759 +[2025-04-30 13:50:19,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 1.6916141510009766, cross_entropy: 1.6916141510009766 +[2025-04-30 13:50:19,440][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 2.778857707977295, cross_entropy: 2.778857707977295 +[2025-04-30 13:50:22,599][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 1.8445879220962524, cross_entropy: 1.8445879220962524 +[2025-04-30 13:50:22,935][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.93676495552063, cross_entropy: 3.93676495552063 +[2025-04-30 13:50:25,802][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 3.1323161125183105, cross_entropy: 3.1323161125183105 +[2025-04-30 13:50:26,137][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 1.3537580966949463, cross_entropy: 1.3537580966949463 +[2025-04-30 13:50:29,422][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 1.6711119413375854, cross_entropy: 1.6711119413375854 +[2025-04-30 13:50:29,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 1.7796200513839722, cross_entropy: 1.7796200513839722 +[2025-04-30 13:50:32,986][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.301063060760498, cross_entropy: 2.301063060760498 +[2025-04-30 13:50:33,322][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 2.0091848373413086, cross_entropy: 2.0091848373413086 +[2025-04-30 13:50:37,201][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 1.8278452157974243, cross_entropy: 1.8278452157974243 +[2025-04-30 13:50:37,513][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.2520291805267334, cross_entropy: 3.2520291805267334 +[2025-04-30 13:50:40,430][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.5248022079467773, cross_entropy: 3.5248022079467773 +[2025-04-30 13:50:40,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 1.729586124420166, cross_entropy: 1.729586124420166 +[2025-04-30 13:50:44,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.205387592315674, cross_entropy: 3.205387592315674 +[2025-04-30 13:50:44,656][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 2.1887476444244385, cross_entropy: 2.1887476444244385 +[2025-04-30 13:50:48,182][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 1.7914708852767944, cross_entropy: 1.7914708852767944 +[2025-04-30 13:50:48,526][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 2.0716631412506104, cross_entropy: 2.0716631412506104 +[2025-04-30 13:50:52,019][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 3.484285354614258, cross_entropy: 3.484285354614258 +[2025-04-30 13:50:52,355][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 2.609081268310547, cross_entropy: 2.609081268310547 +[2025-04-30 13:50:55,575][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 2.073317527770996, cross_entropy: 2.073317527770996 +[2025-04-30 13:50:55,910][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.2646584510803223, cross_entropy: 3.2646584510803223 +[2025-04-30 13:50:58,605][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.5461459159851074, cross_entropy: 3.5461459159851074 +[2025-04-30 13:50:58,940][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 1.7078454494476318, cross_entropy: 1.7078454494476318 +[2025-04-30 13:51:01,650][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 1.9677438735961914, cross_entropy: 1.9677438735961914 +[2025-04-30 13:51:01,988][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 2.753995656967163, cross_entropy: 2.753995656967163 +[2025-04-30 13:51:05,071][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.8115804195404053, cross_entropy: 3.8115804195404053 +[2025-04-30 13:51:05,406][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 2.2873120307922363, cross_entropy: 2.2873120307922363 +[2025-04-30 13:51:08,195][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 2.986142158508301, cross_entropy: 2.986142158508301 +[2025-04-30 13:51:08,507][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 3.4659690856933594, cross_entropy: 3.4659690856933594 +[2025-04-30 13:51:11,210][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.0304441452026367, cross_entropy: 2.0304441452026367 +[2025-04-30 13:51:11,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 2.2917842864990234, cross_entropy: 2.2917842864990234 +[2025-04-30 13:51:14,724][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 3.48195481300354, cross_entropy: 3.48195481300354 +[2025-04-30 13:51:15,197][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 1.6893121004104614, cross_entropy: 1.6893121004104614 +[2025-04-30 13:51:17,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.535606622695923, cross_entropy: 3.535606622695923 +[2025-04-30 13:51:18,672][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 1.9775447845458984, cross_entropy: 1.9775447845458984 +[2025-04-30 13:51:21,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 2.8003811836242676, cross_entropy: 2.8003811836242676 +[2025-04-30 13:51:22,193][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 2.659485340118408, cross_entropy: 2.659485340118408 +[2025-04-30 13:51:24,652][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 2.640230178833008, cross_entropy: 2.640230178833008 +[2025-04-30 13:51:25,022][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 1.6888638734817505, cross_entropy: 1.6888638734817505 +[2025-04-30 13:51:28,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 1.8919888734817505, cross_entropy: 1.8919888734817505 +[2025-04-30 13:51:28,702][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.4186978340148926, cross_entropy: 2.4186978340148926 +[2025-04-30 13:51:31,846][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.2082324028015137, cross_entropy: 2.2082324028015137 +[2025-04-30 13:51:32,678][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 3.7908730506896973, cross_entropy: 3.7908730506896973 +[2025-04-30 13:51:35,077][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 3.306671619415283, cross_entropy: 3.306671619415283 +[2025-04-30 13:51:36,195][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 2.4624216556549072, cross_entropy: 2.4624216556549072 +[2025-04-30 13:51:38,372][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.9021496772766113, cross_entropy: 2.9021496772766113 +[2025-04-30 13:51:39,924][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 4.013803482055664, cross_entropy: 4.013803482055664 +[2025-04-30 13:51:41,680][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 2.967278242111206, cross_entropy: 2.967278242111206 +[2025-04-30 13:51:44,267][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 2.441589832305908, cross_entropy: 2.441589832305908 +[2025-04-30 13:51:44,902][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 2.2872154712677, cross_entropy: 2.2872154712677 +[2025-04-30 13:51:48,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 1.9264960289001465, cross_entropy: 1.9264960289001465 +[2025-04-30 13:51:48,642][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.555544853210449, cross_entropy: 3.555544853210449 +[2025-04-30 13:51:52,400][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.7277441024780273, cross_entropy: 2.7277441024780273 +[2025-04-30 13:51:52,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 1.7654247283935547, cross_entropy: 1.7654247283935547 +[2025-04-30 13:51:56,750][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.1043176651000977, cross_entropy: 2.1043176651000977 +[2025-04-30 13:51:57,079][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 3.5974459648132324, cross_entropy: 3.5974459648132324 +[2025-04-30 13:52:00,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 1.8395565748214722, cross_entropy: 1.8395565748214722 +[2025-04-30 13:52:00,832][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 1.3989861011505127, cross_entropy: 1.3989861011505127 +[2025-04-30 13:52:04,012][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 1.916334629058838, cross_entropy: 1.916334629058838 +[2025-04-30 13:52:04,795][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 2.9470529556274414, cross_entropy: 2.9470529556274414 +[2025-04-30 13:52:07,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 1.8242024183273315, cross_entropy: 1.8242024183273315 +[2025-04-30 13:52:08,295][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 1.9009215831756592, cross_entropy: 1.9009215831756592 +[2025-04-30 13:52:10,783][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 3.819946050643921, cross_entropy: 3.819946050643921 +[2025-04-30 13:52:11,272][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 1.9022482633590698, cross_entropy: 1.9022482633590698 +[2025-04-30 13:52:14,905][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 2.1959075927734375, cross_entropy: 2.1959075927734375 +[2025-04-30 13:52:16,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 1.7684519290924072, cross_entropy: 1.7684519290924072 +[2025-04-30 13:52:19,080][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.9734506607055664, cross_entropy: 2.9734506607055664 +[2025-04-30 13:52:20,534][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 3.6178925037384033, cross_entropy: 3.6178925037384033 +[2025-04-30 13:52:22,536][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 1.949907660484314, cross_entropy: 1.949907660484314 +[2025-04-30 13:52:24,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 1.3530199527740479, cross_entropy: 1.3530199527740479 +[2025-04-30 13:52:27,969][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 2.781376361846924, cross_entropy: 2.781376361846924 +[2025-04-30 13:52:28,364][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 1.8432059288024902, cross_entropy: 1.8432059288024902 +[2025-04-30 13:52:31,412][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 1.7411593198776245, cross_entropy: 1.7411593198776245 +[2025-04-30 13:52:32,114][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 3.0223631858825684, cross_entropy: 3.0223631858825684 +[2025-04-30 13:52:35,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 1.913982629776001, cross_entropy: 1.913982629776001 +[2025-04-30 13:52:35,859][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.4067935943603516, cross_entropy: 3.4067935943603516 +[2025-04-30 13:52:38,627][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 2.3613710403442383, cross_entropy: 2.3613710403442383 +[2025-04-30 13:52:39,603][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.6218104362487793, cross_entropy: 2.6218104362487793 +[2025-04-30 13:52:42,765][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 1.7199093103408813, cross_entropy: 1.7199093103408813 +[2025-04-30 13:52:43,462][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 1.7445154190063477, cross_entropy: 1.7445154190063477 +[2025-04-30 13:52:46,585][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.6679601669311523, cross_entropy: 2.6679601669311523 +[2025-04-30 13:52:47,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.5092051029205322, cross_entropy: 2.5092051029205322 +[2025-04-30 13:52:50,453][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.2788760662078857, cross_entropy: 2.2788760662078857 +[2025-04-30 13:52:50,841][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 2.777096748352051, cross_entropy: 2.777096748352051 +[2025-04-30 13:52:53,761][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 2.41426682472229, cross_entropy: 2.41426682472229 +[2025-04-30 13:52:54,098][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 3.5591020584106445, cross_entropy: 3.5591020584106445 +[2025-04-30 13:52:56,930][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.57918381690979, cross_entropy: 2.57918381690979 +[2025-04-30 13:52:57,273][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.730830669403076, cross_entropy: 2.730830669403076 +[2025-04-30 13:53:00,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 1.9738800525665283, cross_entropy: 1.9738800525665283 +[2025-04-30 13:53:01,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 1.848571538925171, cross_entropy: 1.848571538925171 +[2025-04-30 13:53:04,141][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 2.20176362991333, cross_entropy: 2.20176362991333 +[2025-04-30 13:53:04,878][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 3.0768697261810303, cross_entropy: 3.0768697261810303 +[2025-04-30 13:53:07,776][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 2.3780837059020996, cross_entropy: 2.3780837059020996 +[2025-04-30 13:53:08,404][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 3.4325382709503174, cross_entropy: 3.4325382709503174 +[2025-04-30 13:53:10,815][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 1.645064353942871, cross_entropy: 1.645064353942871 +[2025-04-30 13:53:12,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.1764016151428223, cross_entropy: 3.1764016151428223 +[2025-04-30 13:53:13,904][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 3.4044032096862793, cross_entropy: 3.4044032096862793 +[2025-04-30 13:53:15,735][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 1.9485167264938354, cross_entropy: 1.9485167264938354 +[2025-04-30 13:53:17,719][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 1.7364776134490967, cross_entropy: 1.7364776134490967 +[2025-04-30 13:53:19,155][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 3.6564481258392334, cross_entropy: 3.6564481258392334 +[2025-04-30 13:53:20,458][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 1.6993746757507324, cross_entropy: 1.6993746757507324 +[2025-04-30 13:53:22,196][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 3.5386600494384766, cross_entropy: 3.5386600494384766 +[2025-04-30 13:53:24,124][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.176215887069702, cross_entropy: 2.176215887069702 +[2025-04-30 13:53:24,915][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 3.2147250175476074, cross_entropy: 3.2147250175476074 +[2025-04-30 13:53:27,499][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.0567078590393066, cross_entropy: 2.0567078590393066 +[2025-04-30 13:53:28,727][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 3.3593645095825195, cross_entropy: 3.3593645095825195 +[2025-04-30 13:53:31,120][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 1.848423957824707, cross_entropy: 1.848423957824707 +[2025-04-30 13:53:32,676][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.6853561401367188, cross_entropy: 2.6853561401367188 +[2025-04-30 13:53:34,121][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.1849842071533203, cross_entropy: 2.1849842071533203 +[2025-04-30 13:53:36,146][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 1.8618789911270142, cross_entropy: 1.8618789911270142 +[2025-04-30 13:53:37,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 3.3090152740478516, cross_entropy: 3.3090152740478516 +[2025-04-30 13:53:39,861][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 1.5182759761810303, cross_entropy: 1.5182759761810303 +[2025-04-30 13:53:40,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 3.656212329864502, cross_entropy: 3.656212329864502 +[2025-04-30 13:53:42,917][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 1.9736825227737427, cross_entropy: 1.9736825227737427 +[2025-04-30 13:53:44,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.9497995376586914, cross_entropy: 2.9497995376586914 +[2025-04-30 13:53:46,575][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 2.6393933296203613, cross_entropy: 2.6393933296203613 +[2025-04-30 13:53:48,146][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 2.4882664680480957, cross_entropy: 2.4882664680480957 +[2025-04-30 13:53:49,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 2.2204885482788086, cross_entropy: 2.2204885482788086 +[2025-04-30 13:53:51,387][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 2.209303855895996, cross_entropy: 2.209303855895996 +[2025-04-30 13:53:53,055][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 1.6459616422653198, cross_entropy: 1.6459616422653198 +[2025-04-30 13:53:55,017][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 1.9907686710357666, cross_entropy: 1.9907686710357666 +[2025-04-30 13:53:56,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.6215996742248535, cross_entropy: 3.6215996742248535 +[2025-04-30 13:53:58,598][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 1.7967902421951294, cross_entropy: 1.7967902421951294 +[2025-04-30 13:53:59,589][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 1.6523056030273438, cross_entropy: 1.6523056030273438 +[2025-04-30 13:54:02,584][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 3.586276054382324, cross_entropy: 3.586276054382324 +[2025-04-30 13:54:03,374][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 3.801474094390869, cross_entropy: 3.801474094390869 +[2025-04-30 13:54:05,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 1.9848779439926147, cross_entropy: 1.9848779439926147 +[2025-04-30 13:54:06,216][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 1.5679161548614502, cross_entropy: 1.5679161548614502 +[2025-04-30 13:54:09,173][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.417872190475464, cross_entropy: 3.417872190475464 +[2025-04-30 13:54:09,528][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.452232599258423, cross_entropy: 3.452232599258423 +[2025-04-30 13:54:12,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 1.7984066009521484, cross_entropy: 1.7984066009521484 +[2025-04-30 13:54:13,560][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 1.9617674350738525, cross_entropy: 1.9617674350738525 +[2025-04-30 13:54:15,987][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 1.9308750629425049, cross_entropy: 1.9308750629425049 +[2025-04-30 13:54:17,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 3.3743438720703125, cross_entropy: 3.3743438720703125 +[2025-04-30 13:54:19,288][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.473116397857666, cross_entropy: 2.473116397857666 +[2025-04-30 13:54:19,868][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 3.320103645324707, cross_entropy: 3.320103645324707 +[2025-04-30 13:54:22,841][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 1.863173007965088, cross_entropy: 1.863173007965088 +[2025-04-30 13:54:23,735][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 3.2771193981170654, cross_entropy: 3.2771193981170654 +[2025-04-30 13:54:25,948][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 2.8204329013824463, cross_entropy: 2.8204329013824463 +[2025-04-30 13:54:27,374][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 3.1257293224334717, cross_entropy: 3.1257293224334717 +[2025-04-30 13:54:29,907][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.337378740310669, cross_entropy: 2.337378740310669 +[2025-04-30 13:54:30,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 3.313636302947998, cross_entropy: 3.313636302947998 +[2025-04-30 13:54:33,525][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 1.5937016010284424, cross_entropy: 1.5937016010284424 +[2025-04-30 13:54:34,390][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 1.6125679016113281, cross_entropy: 1.6125679016113281 +[2025-04-30 13:54:37,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.6182949542999268, cross_entropy: 2.6182949542999268 +[2025-04-30 13:54:37,806][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 3.1545422077178955, cross_entropy: 3.1545422077178955 +[2025-04-30 13:54:40,515][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.5597400665283203, cross_entropy: 2.5597400665283203 +[2025-04-30 13:54:40,893][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 1.6951792240142822, cross_entropy: 1.6951792240142822 +[2025-04-30 13:54:43,878][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 3.323204278945923, cross_entropy: 3.323204278945923 +[2025-04-30 13:54:44,536][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.7266712188720703, cross_entropy: 2.7266712188720703 +[2025-04-30 13:54:47,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 2.5789222717285156, cross_entropy: 2.5789222717285156 +[2025-04-30 13:54:47,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 1.8709384202957153, cross_entropy: 1.8709384202957153 +[2025-04-30 13:54:49,996][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 2.5789475440979004, cross_entropy: 2.5789475440979004 +[2025-04-30 13:54:50,755][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 2.434933662414551, cross_entropy: 2.434933662414551 +[2025-04-30 13:54:53,162][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.0227303504943848, cross_entropy: 3.0227303504943848 +[2025-04-30 13:54:53,518][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.046712875366211, cross_entropy: 3.046712875366211 +[2025-04-30 13:54:56,648][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 1.4871952533721924, cross_entropy: 1.4871952533721924 +[2025-04-30 13:54:57,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 1.9031094312667847, cross_entropy: 1.9031094312667847 +[2025-04-30 13:54:59,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 1.7770512104034424, cross_entropy: 1.7770512104034424 +[2025-04-30 13:55:00,299][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.201418399810791, cross_entropy: 3.201418399810791 +[2025-04-30 13:55:03,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 2.9444684982299805, cross_entropy: 2.9444684982299805 +[2025-04-30 13:55:03,715][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 1.9035742282867432, cross_entropy: 1.9035742282867432 +[2025-04-30 13:55:06,997][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 3.1743826866149902, cross_entropy: 3.1743826866149902 +[2025-04-30 13:55:07,337][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 2.1417174339294434, cross_entropy: 2.1417174339294434 +[2025-04-30 13:55:10,338][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 2.9135494232177734, cross_entropy: 2.9135494232177734 +[2025-04-30 13:55:10,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 2.1823017597198486, cross_entropy: 2.1823017597198486 +[2025-04-30 13:55:14,204][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.4806032180786133, cross_entropy: 3.4806032180786133 +[2025-04-30 13:55:16,010][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 1.8946311473846436, cross_entropy: 1.8946311473846436 +[2025-04-30 13:55:17,105][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 3.3018381595611572, cross_entropy: 3.3018381595611572 +[2025-04-30 13:55:19,259][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.4205973148345947, cross_entropy: 3.4205973148345947 +[2025-04-30 13:55:20,946][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 1.6424201726913452, cross_entropy: 1.6424201726913452 +[2025-04-30 13:55:22,958][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 1.8045785427093506, cross_entropy: 1.8045785427093506 +[2025-04-30 13:55:24,162][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 2.4190635681152344, cross_entropy: 2.4190635681152344 +[2025-04-30 13:55:26,194][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 1.8722933530807495, cross_entropy: 1.8722933530807495 +[2025-04-30 13:55:27,688][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 2.034868001937866, cross_entropy: 2.034868001937866 +[2025-04-30 13:55:29,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 1.6628119945526123, cross_entropy: 1.6628119945526123 +[2025-04-30 13:55:31,291][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.6151530742645264, cross_entropy: 3.6151530742645264 +[2025-04-30 13:55:32,854][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 1.9939637184143066, cross_entropy: 1.9939637184143066 +[2025-04-30 13:55:34,545][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 3.1943507194519043, cross_entropy: 3.1943507194519043 +[2025-04-30 13:58:23,559][BaseTrainer][INFO] - [Epoch 2/10] (train) 2.6309196949005127, cross_entropy: 2.6309196949005127 +[2025-04-30 13:58:23,559][BaseTrainer][INFO] - [Epoch 2/10] (validation) 1.687761902809143, cross_entropy: 1.687761902809143 +[2025-04-30 13:58:23,560][BaseTrainer][INFO] - [Epoch 2/10] (metrics) roc_auc: 0.9681202173233032 +[2025-04-30 13:58:23,794][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 13:58:23,972][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch2.pth. +[2025-04-30 13:58:24,193][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 13:58:28,839][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 3.1938438415527344, cross_entropy: 3.1938438415527344 +[2025-04-30 13:58:29,554][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 1.3633966445922852, cross_entropy: 1.3633966445922852 +[2025-04-30 13:58:33,389][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 1.903594970703125, cross_entropy: 1.903594970703125 +[2025-04-30 13:58:33,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 2.8215599060058594, cross_entropy: 2.8215599060058594 +[2025-04-30 13:58:37,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 1.721657395362854, cross_entropy: 1.721657395362854 +[2025-04-30 13:58:37,529][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.331214666366577, cross_entropy: 2.331214666366577 +[2025-04-30 13:58:40,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 1.530568242073059, cross_entropy: 1.530568242073059 +[2025-04-30 13:58:41,015][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 2.255742073059082, cross_entropy: 2.255742073059082 +[2025-04-30 13:58:44,433][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 1.2313110828399658, cross_entropy: 1.2313110828399658 +[2025-04-30 13:58:44,748][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 2.1996536254882812, cross_entropy: 2.1996536254882812 +[2025-04-30 13:58:47,798][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.6185340881347656, cross_entropy: 2.6185340881347656 +[2025-04-30 13:58:48,144][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 1.7772568464279175, cross_entropy: 1.7772568464279175 +[2025-04-30 13:58:51,348][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 1.9919288158416748, cross_entropy: 1.9919288158416748 +[2025-04-30 13:58:51,793][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 2.406562566757202, cross_entropy: 2.406562566757202 +[2025-04-30 13:58:54,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.207202911376953, cross_entropy: 2.207202911376953 +[2025-04-30 13:58:55,335][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 2.058321952819824, cross_entropy: 2.058321952819824 +[2025-04-30 13:58:58,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.473212957382202, cross_entropy: 3.473212957382202 +[2025-04-30 13:58:59,766][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 2.144658088684082, cross_entropy: 2.144658088684082 +[2025-04-30 13:59:01,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 1.4533562660217285, cross_entropy: 1.4533562660217285 +[2025-04-30 13:59:03,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 1.730310082435608, cross_entropy: 1.730310082435608 +[2025-04-30 13:59:04,996][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 3.174283742904663, cross_entropy: 3.174283742904663 +[2025-04-30 13:59:07,071][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 1.4179288148880005, cross_entropy: 1.4179288148880005 +[2025-04-30 13:59:08,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.59401273727417, cross_entropy: 3.59401273727417 +[2025-04-30 13:59:10,734][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 2.756211519241333, cross_entropy: 2.756211519241333 +[2025-04-30 13:59:11,785][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.5653140544891357, cross_entropy: 3.5653140544891357 +[2025-04-30 13:59:15,145][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 2.3450517654418945, cross_entropy: 2.3450517654418945 +[2025-04-30 13:59:15,456][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 1.4937366247177124, cross_entropy: 1.4937366247177124 +[2025-04-30 13:59:19,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 1.9334754943847656, cross_entropy: 1.9334754943847656 +[2025-04-30 13:59:20,221][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.2027931213378906, cross_entropy: 3.2027931213378906 +[2025-04-30 13:59:23,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.8507869243621826, cross_entropy: 2.8507869243621826 +[2025-04-30 13:59:23,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 1.6491649150848389, cross_entropy: 1.6491649150848389 +[2025-04-30 13:59:26,497][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 3.2688865661621094, cross_entropy: 3.2688865661621094 +[2025-04-30 13:59:26,835][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 3.089411497116089, cross_entropy: 3.089411497116089 +[2025-04-30 13:59:29,992][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 1.765543818473816, cross_entropy: 1.765543818473816 +[2025-04-30 13:59:30,333][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 3.421121120452881, cross_entropy: 3.421121120452881 +[2025-04-30 13:59:33,424][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 3.192959785461426, cross_entropy: 3.192959785461426 +[2025-04-30 13:59:33,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 2.1795191764831543, cross_entropy: 2.1795191764831543 +[2025-04-30 13:59:36,615][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 2.08774995803833, cross_entropy: 2.08774995803833 +[2025-04-30 13:59:36,952][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 1.1721733808517456, cross_entropy: 1.1721733808517456 +[2025-04-30 13:59:40,286][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 1.8867472410202026, cross_entropy: 1.8867472410202026 +[2025-04-30 13:59:40,622][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 1.9055495262145996, cross_entropy: 1.9055495262145996 +[2025-04-30 13:59:43,788][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 2.773123264312744, cross_entropy: 2.773123264312744 +[2025-04-30 13:59:44,128][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 1.472153663635254, cross_entropy: 1.472153663635254 +[2025-04-30 13:59:47,124][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.3793351650238037, cross_entropy: 2.3793351650238037 +[2025-04-30 13:59:47,453][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.8560028076171875, cross_entropy: 2.8560028076171875 +[2025-04-30 13:59:50,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 3.25246524810791, cross_entropy: 3.25246524810791 +[2025-04-30 13:59:50,978][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 1.4617972373962402, cross_entropy: 1.4617972373962402 +[2025-04-30 13:59:54,876][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 3.6184439659118652, cross_entropy: 3.6184439659118652 +[2025-04-30 13:59:55,213][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 3.079324245452881, cross_entropy: 3.079324245452881 +[2025-04-30 13:59:58,934][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 1.5795159339904785, cross_entropy: 1.5795159339904785 +[2025-04-30 13:59:59,248][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 1.5974416732788086, cross_entropy: 1.5974416732788086 +[2025-04-30 14:00:02,032][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 1.9515951871871948, cross_entropy: 1.9515951871871948 +[2025-04-30 14:00:02,370][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.966356039047241, cross_entropy: 2.966356039047241 +[2025-04-30 14:00:06,030][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 3.1189370155334473, cross_entropy: 3.1189370155334473 +[2025-04-30 14:00:06,372][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 3.036539316177368, cross_entropy: 3.036539316177368 +[2025-04-30 14:00:10,117][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.989788055419922, cross_entropy: 2.989788055419922 +[2025-04-30 14:00:10,468][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.3254568576812744, cross_entropy: 3.3254568576812744 +[2025-04-30 14:00:13,329][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.358189582824707, cross_entropy: 2.358189582824707 +[2025-04-30 14:00:13,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 3.184366226196289, cross_entropy: 3.184366226196289 +[2025-04-30 14:00:17,109][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 3.6017403602600098, cross_entropy: 3.6017403602600098 +[2025-04-30 14:00:17,422][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.534310817718506, cross_entropy: 2.534310817718506 +[2025-04-30 14:00:20,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.454866409301758, cross_entropy: 2.454866409301758 +[2025-04-30 14:00:20,894][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.126863956451416, cross_entropy: 3.126863956451416 +[2025-04-30 14:00:24,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 1.7705706357955933, cross_entropy: 1.7705706357955933 +[2025-04-30 14:00:24,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.432591676712036, cross_entropy: 3.432591676712036 +[2025-04-30 14:00:28,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 2.819761276245117, cross_entropy: 2.819761276245117 +[2025-04-30 14:00:29,255][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 1.8532317876815796, cross_entropy: 1.8532317876815796 +[2025-04-30 14:00:32,343][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.497556686401367, cross_entropy: 3.497556686401367 +[2025-04-30 14:00:32,679][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 2.046673059463501, cross_entropy: 2.046673059463501 +[2025-04-30 14:00:35,649][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 2.5047714710235596, cross_entropy: 2.5047714710235596 +[2025-04-30 14:00:35,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.4070212841033936, cross_entropy: 2.4070212841033936 +[2025-04-30 14:00:39,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.479064464569092, cross_entropy: 2.479064464569092 +[2025-04-30 14:00:39,678][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 2.0829219818115234, cross_entropy: 2.0829219818115234 +[2025-04-30 14:00:43,168][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.7680416107177734, cross_entropy: 2.7680416107177734 +[2025-04-30 14:00:43,511][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.2934393882751465, cross_entropy: 3.2934393882751465 +[2025-04-30 14:00:47,193][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 1.5810730457305908, cross_entropy: 1.5810730457305908 +[2025-04-30 14:00:47,532][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 2.777379035949707, cross_entropy: 2.777379035949707 +[2025-04-30 14:00:50,903][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 1.8183162212371826, cross_entropy: 1.8183162212371826 +[2025-04-30 14:00:51,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.0329697132110596, cross_entropy: 3.0329697132110596 +[2025-04-30 14:00:54,230][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 1.3966659307479858, cross_entropy: 1.3966659307479858 +[2025-04-30 14:00:54,573][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.1031699180603027, cross_entropy: 3.1031699180603027 +[2025-04-30 14:00:57,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 1.8643834590911865, cross_entropy: 1.8643834590911865 +[2025-04-30 14:00:58,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.0451607704162598, cross_entropy: 3.0451607704162598 +[2025-04-30 14:01:01,634][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 1.803067922592163, cross_entropy: 1.803067922592163 +[2025-04-30 14:01:01,973][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 1.8285294771194458, cross_entropy: 1.8285294771194458 +[2025-04-30 14:01:05,252][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 1.8135066032409668, cross_entropy: 1.8135066032409668 +[2025-04-30 14:01:05,565][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 2.1388890743255615, cross_entropy: 2.1388890743255615 +[2025-04-30 14:01:08,632][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.2981114387512207, cross_entropy: 3.2981114387512207 +[2025-04-30 14:01:08,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.082308292388916, cross_entropy: 3.082308292388916 +[2025-04-30 14:01:12,437][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 3.3985297679901123, cross_entropy: 3.3985297679901123 +[2025-04-30 14:01:12,774][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 3.301382064819336, cross_entropy: 3.301382064819336 +[2025-04-30 14:01:15,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 1.5735464096069336, cross_entropy: 1.5735464096069336 +[2025-04-30 14:01:16,155][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 1.510510802268982, cross_entropy: 1.510510802268982 +[2025-04-30 14:01:19,250][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.835131883621216, cross_entropy: 2.835131883621216 +[2025-04-30 14:01:19,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.304433584213257, cross_entropy: 3.304433584213257 +[2025-04-30 14:01:23,166][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.4350850582122803, cross_entropy: 1.4350850582122803 +[2025-04-30 14:01:23,477][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 3.399801254272461, cross_entropy: 3.399801254272461 +[2025-04-30 14:01:26,413][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 2.294602870941162, cross_entropy: 2.294602870941162 +[2025-04-30 14:01:26,762][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 2.4802064895629883, cross_entropy: 2.4802064895629883 +[2025-04-30 14:01:29,683][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.0635998249053955, cross_entropy: 2.0635998249053955 +[2025-04-30 14:01:29,999][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 1.9411081075668335, cross_entropy: 1.9411081075668335 +[2025-04-30 14:01:32,961][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 2.163686990737915, cross_entropy: 2.163686990737915 +[2025-04-30 14:01:33,303][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.5962586402893066, cross_entropy: 2.5962586402893066 +[2025-04-30 14:01:36,718][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 1.9040465354919434, cross_entropy: 1.9040465354919434 +[2025-04-30 14:01:37,064][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 2.0203020572662354, cross_entropy: 2.0203020572662354 +[2025-04-30 14:01:40,346][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 1.6247785091400146, cross_entropy: 1.6247785091400146 +[2025-04-30 14:01:40,663][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 1.713680386543274, cross_entropy: 1.713680386543274 +[2025-04-30 14:01:44,120][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 1.730418086051941, cross_entropy: 1.730418086051941 +[2025-04-30 14:01:44,462][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 2.4760942459106445, cross_entropy: 2.4760942459106445 +[2025-04-30 14:01:47,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 1.481261968612671, cross_entropy: 1.481261968612671 +[2025-04-30 14:01:47,799][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 2.1621170043945312, cross_entropy: 2.1621170043945312 +[2025-04-30 14:01:51,486][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 1.593061089515686, cross_entropy: 1.593061089515686 +[2025-04-30 14:01:51,826][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 1.8762524127960205, cross_entropy: 1.8762524127960205 +[2025-04-30 14:01:55,255][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 3.0893614292144775, cross_entropy: 3.0893614292144775 +[2025-04-30 14:01:55,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 2.9154462814331055, cross_entropy: 2.9154462814331055 +[2025-04-30 14:01:58,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 1.4238982200622559, cross_entropy: 1.4238982200622559 +[2025-04-30 14:01:58,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.416182041168213, cross_entropy: 2.416182041168213 +[2025-04-30 14:02:01,504][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.4544692039489746, cross_entropy: 2.4544692039489746 +[2025-04-30 14:02:01,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.511324167251587, cross_entropy: 3.511324167251587 +[2025-04-30 14:02:05,024][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.573962450027466, cross_entropy: 2.573962450027466 +[2025-04-30 14:02:05,365][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 1.5616652965545654, cross_entropy: 1.5616652965545654 +[2025-04-30 14:02:08,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 1.581067681312561, cross_entropy: 1.581067681312561 +[2025-04-30 14:02:09,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 2.3827757835388184, cross_entropy: 2.3827757835388184 +[2025-04-30 14:02:12,317][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 1.6968960762023926, cross_entropy: 1.6968960762023926 +[2025-04-30 14:02:12,656][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.2748239040374756, cross_entropy: 3.2748239040374756 +[2025-04-30 14:02:15,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.62851619720459, cross_entropy: 2.62851619720459 +[2025-04-30 14:02:16,202][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 1.3438358306884766, cross_entropy: 1.3438358306884766 +[2025-04-30 14:02:19,483][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 2.0300700664520264, cross_entropy: 2.0300700664520264 +[2025-04-30 14:02:19,825][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.0530848503112793, cross_entropy: 3.0530848503112793 +[2025-04-30 14:02:22,884][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.1481776237487793, cross_entropy: 2.1481776237487793 +[2025-04-30 14:02:23,197][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 1.8630585670471191, cross_entropy: 1.8630585670471191 +[2025-04-30 14:02:26,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 1.600252389907837, cross_entropy: 1.600252389907837 +[2025-04-30 14:02:26,556][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.4448201656341553, cross_entropy: 2.4448201656341553 +[2025-04-30 14:02:29,456][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.953941822052002, cross_entropy: 2.953941822052002 +[2025-04-30 14:02:29,769][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.264188766479492, cross_entropy: 2.264188766479492 +[2025-04-30 14:02:32,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 1.7223155498504639, cross_entropy: 1.7223155498504639 +[2025-04-30 14:02:33,057][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.3790032863616943, cross_entropy: 2.3790032863616943 +[2025-04-30 14:02:36,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 1.4073808193206787, cross_entropy: 1.4073808193206787 +[2025-04-30 14:02:37,057][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.831625461578369, cross_entropy: 2.831625461578369 +[2025-04-30 14:02:40,518][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 1.8337197303771973, cross_entropy: 1.8337197303771973 +[2025-04-30 14:02:40,838][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 2.3098297119140625, cross_entropy: 2.3098297119140625 +[2025-04-30 14:02:44,275][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 1.219010591506958, cross_entropy: 1.219010591506958 +[2025-04-30 14:02:44,588][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.6022491455078125, cross_entropy: 2.6022491455078125 +[2025-04-30 14:02:48,141][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 1.884415626525879, cross_entropy: 1.884415626525879 +[2025-04-30 14:02:48,453][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.188497543334961, cross_entropy: 2.188497543334961 +[2025-04-30 14:02:51,647][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.5244598388671875, cross_entropy: 2.5244598388671875 +[2025-04-30 14:02:51,966][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 1.606896996498108, cross_entropy: 1.606896996498108 +[2025-04-30 14:02:55,450][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 3.28471302986145, cross_entropy: 3.28471302986145 +[2025-04-30 14:02:55,764][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 1.4254345893859863, cross_entropy: 1.4254345893859863 +[2025-04-30 14:02:58,838][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 1.4677209854125977, cross_entropy: 1.4677209854125977 +[2025-04-30 14:02:59,176][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 1.5913922786712646, cross_entropy: 1.5913922786712646 +[2025-04-30 14:03:02,167][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 1.5915193557739258, cross_entropy: 1.5915193557739258 +[2025-04-30 14:03:02,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 2.0214200019836426, cross_entropy: 2.0214200019836426 +[2025-04-30 14:03:05,786][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 1.9760034084320068, cross_entropy: 1.9760034084320068 +[2025-04-30 14:03:06,124][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.4532132148742676, cross_entropy: 2.4532132148742676 +[2025-04-30 14:03:09,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 1.7894399166107178, cross_entropy: 1.7894399166107178 +[2025-04-30 14:03:10,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 1.638102412223816, cross_entropy: 1.638102412223816 +[2025-04-30 14:03:13,261][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 1.3007487058639526, cross_entropy: 1.3007487058639526 +[2025-04-30 14:03:13,608][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 1.8898770809173584, cross_entropy: 1.8898770809173584 +[2025-04-30 14:03:16,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 1.3759541511535645, cross_entropy: 1.3759541511535645 +[2025-04-30 14:03:17,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.431515693664551, cross_entropy: 3.431515693664551 +[2025-04-30 14:03:20,137][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.237168312072754, cross_entropy: 3.237168312072754 +[2025-04-30 14:03:20,471][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 3.415281057357788, cross_entropy: 3.415281057357788 +[2025-04-30 14:03:24,120][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 1.757049560546875, cross_entropy: 1.757049560546875 +[2025-04-30 14:03:24,459][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 2.8442494869232178, cross_entropy: 2.8442494869232178 +[2025-04-30 14:03:28,482][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 1.7699122428894043, cross_entropy: 1.7699122428894043 +[2025-04-30 14:03:28,815][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 1.4061272144317627, cross_entropy: 1.4061272144317627 +[2025-04-30 14:03:32,577][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 3.2480480670928955, cross_entropy: 3.2480480670928955 +[2025-04-30 14:03:32,890][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 1.6526753902435303, cross_entropy: 1.6526753902435303 +[2025-04-30 14:03:36,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 3.184730052947998, cross_entropy: 3.184730052947998 +[2025-04-30 14:03:36,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 1.939544916152954, cross_entropy: 1.939544916152954 +[2025-04-30 14:03:40,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 2.400484085083008, cross_entropy: 2.400484085083008 +[2025-04-30 14:03:40,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.124948740005493, cross_entropy: 3.124948740005493 +[2025-04-30 14:03:44,261][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 1.9513788223266602, cross_entropy: 1.9513788223266602 +[2025-04-30 14:03:44,574][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 2.2279467582702637, cross_entropy: 2.2279467582702637 +[2025-04-30 14:03:47,725][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 2.7013587951660156, cross_entropy: 2.7013587951660156 +[2025-04-30 14:03:48,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.273627758026123, cross_entropy: 2.273627758026123 +[2025-04-30 14:03:51,941][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 3.0897555351257324, cross_entropy: 3.0897555351257324 +[2025-04-30 14:03:52,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 1.6605224609375, cross_entropy: 1.6605224609375 +[2025-04-30 14:03:55,240][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.683727979660034, cross_entropy: 2.683727979660034 +[2025-04-30 14:03:55,553][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.670653223991394, cross_entropy: 1.670653223991394 +[2025-04-30 14:03:59,062][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.9584107398986816, cross_entropy: 2.9584107398986816 +[2025-04-30 14:03:59,404][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 2.2355613708496094, cross_entropy: 2.2355613708496094 +[2025-04-30 14:04:02,631][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 2.579535484313965, cross_entropy: 2.579535484313965 +[2025-04-30 14:04:02,976][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 2.733152151107788, cross_entropy: 2.733152151107788 +[2025-04-30 14:04:06,008][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 3.4175491333007812, cross_entropy: 3.4175491333007812 +[2025-04-30 14:04:06,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 2.2121262550354004, cross_entropy: 2.2121262550354004 +[2025-04-30 14:04:09,478][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.5416312217712402, cross_entropy: 2.5416312217712402 +[2025-04-30 14:04:09,821][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.052905797958374, cross_entropy: 3.052905797958374 +[2025-04-30 14:04:13,525][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.1732540130615234, cross_entropy: 3.1732540130615234 +[2025-04-30 14:04:13,863][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.1211066246032715, cross_entropy: 2.1211066246032715 +[2025-04-30 14:04:17,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 1.6234550476074219, cross_entropy: 1.6234550476074219 +[2025-04-30 14:04:17,454][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.8467202186584473, cross_entropy: 2.8467202186584473 +[2025-04-30 14:04:20,316][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 1.3807966709136963, cross_entropy: 1.3807966709136963 +[2025-04-30 14:04:20,664][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 3.025700330734253, cross_entropy: 3.025700330734253 +[2025-04-30 14:04:23,918][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.4054172039031982, cross_entropy: 2.4054172039031982 +[2025-04-30 14:04:24,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 1.6552081108093262, cross_entropy: 1.6552081108093262 +[2025-04-30 14:04:27,861][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 2.330883741378784, cross_entropy: 2.330883741378784 +[2025-04-30 14:04:28,201][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 1.4378876686096191, cross_entropy: 1.4378876686096191 +[2025-04-30 14:04:31,234][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 2.7516422271728516, cross_entropy: 2.7516422271728516 +[2025-04-30 14:04:31,577][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 1.710071086883545, cross_entropy: 1.710071086883545 +[2025-04-30 14:04:35,123][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.4925432205200195, cross_entropy: 2.4925432205200195 +[2025-04-30 14:04:35,461][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.068894863128662, cross_entropy: 3.068894863128662 +[2025-04-30 14:04:38,871][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.955669641494751, cross_entropy: 2.955669641494751 +[2025-04-30 14:04:39,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.2805862426757812, cross_entropy: 3.2805862426757812 +[2025-04-30 14:04:42,666][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 3.028792381286621, cross_entropy: 3.028792381286621 +[2025-04-30 14:04:42,982][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 2.542998790740967, cross_entropy: 2.542998790740967 +[2025-04-30 14:04:46,135][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.1238365173339844, cross_entropy: 2.1238365173339844 +[2025-04-30 14:04:46,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 1.5941731929779053, cross_entropy: 1.5941731929779053 +[2025-04-30 14:04:49,400][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 2.649519920349121, cross_entropy: 2.649519920349121 +[2025-04-30 14:04:49,741][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 2.545753002166748, cross_entropy: 2.545753002166748 +[2025-04-30 14:04:52,965][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 1.7912333011627197, cross_entropy: 1.7912333011627197 +[2025-04-30 14:04:53,305][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 1.5358550548553467, cross_entropy: 1.5358550548553467 +[2025-04-30 14:04:56,710][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 1.9892901182174683, cross_entropy: 1.9892901182174683 +[2025-04-30 14:04:57,050][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 1.4805099964141846, cross_entropy: 1.4805099964141846 +[2025-04-30 14:05:00,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 1.7074439525604248, cross_entropy: 1.7074439525604248 +[2025-04-30 14:05:00,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.1754395961761475, cross_entropy: 2.1754395961761475 +[2025-04-30 14:05:03,382][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 2.089261054992676, cross_entropy: 2.089261054992676 +[2025-04-30 14:05:03,716][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.7221903800964355, cross_entropy: 2.7221903800964355 +[2025-04-30 14:05:06,718][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 1.669656753540039, cross_entropy: 1.669656753540039 +[2025-04-30 14:05:07,030][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.6408119201660156, cross_entropy: 1.6408119201660156 +[2025-04-30 14:05:10,287][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 3.495252847671509, cross_entropy: 3.495252847671509 +[2025-04-30 14:05:10,598][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 3.1927053928375244, cross_entropy: 3.1927053928375244 +[2025-04-30 14:05:13,792][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 2.930612564086914, cross_entropy: 2.930612564086914 +[2025-04-30 14:05:14,143][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.323551893234253, cross_entropy: 3.323551893234253 +[2025-04-30 14:05:17,502][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.6413993835449219, cross_entropy: 1.6413993835449219 +[2025-04-30 14:05:17,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 1.1749768257141113, cross_entropy: 1.1749768257141113 +[2025-04-30 14:05:21,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.457296848297119, cross_entropy: 3.457296848297119 +[2025-04-30 14:05:21,662][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 1.5740547180175781, cross_entropy: 1.5740547180175781 +[2025-04-30 14:05:25,183][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.337547540664673, cross_entropy: 3.337547540664673 +[2025-04-30 14:05:25,525][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.1033825874328613, cross_entropy: 2.1033825874328613 +[2025-04-30 14:05:28,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.117959976196289, cross_entropy: 3.117959976196289 +[2025-04-30 14:05:29,015][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 1.8219982385635376, cross_entropy: 1.8219982385635376 +[2025-04-30 14:05:31,940][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 1.6805622577667236, cross_entropy: 1.6805622577667236 +[2025-04-30 14:05:32,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.185586929321289, cross_entropy: 3.185586929321289 +[2025-04-30 14:05:35,348][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 1.740382432937622, cross_entropy: 1.740382432937622 +[2025-04-30 14:05:35,658][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 3.162656307220459, cross_entropy: 3.162656307220459 +[2025-04-30 14:05:39,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 2.9310097694396973, cross_entropy: 2.9310097694396973 +[2025-04-30 14:05:39,609][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 2.4840776920318604, cross_entropy: 2.4840776920318604 +[2025-04-30 14:05:42,859][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 2.059997797012329, cross_entropy: 2.059997797012329 +[2025-04-30 14:05:43,212][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.808140277862549, cross_entropy: 2.808140277862549 +[2025-04-30 14:05:47,653][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 2.7382514476776123, cross_entropy: 2.7382514476776123 +[2025-04-30 14:05:47,994][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 3.357252836227417, cross_entropy: 3.357252836227417 +[2025-04-30 14:05:50,970][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 1.209411382675171, cross_entropy: 1.209411382675171 +[2025-04-30 14:05:51,317][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 1.271368384361267, cross_entropy: 1.271368384361267 +[2025-04-30 14:05:55,049][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.839478015899658, cross_entropy: 2.839478015899658 +[2025-04-30 14:05:55,389][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 2.9959561824798584, cross_entropy: 2.9959561824798584 +[2025-04-30 14:05:58,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.9567983150482178, cross_entropy: 1.9567983150482178 +[2025-04-30 14:05:59,116][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.7376163005828857, cross_entropy: 2.7376163005828857 +[2025-04-30 14:06:02,778][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.661778450012207, cross_entropy: 2.661778450012207 +[2025-04-30 14:06:03,096][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 2.431363105773926, cross_entropy: 2.431363105773926 +[2025-04-30 14:06:06,320][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 0.9744830131530762, cross_entropy: 0.9744830131530762 +[2025-04-30 14:06:06,660][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 1.768013596534729, cross_entropy: 1.768013596534729 +[2025-04-30 14:06:10,264][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 1.7188029289245605, cross_entropy: 1.7188029289245605 +[2025-04-30 14:06:10,577][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.0786728858947754, cross_entropy: 3.0786728858947754 +[2025-04-30 14:06:13,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 2.715879440307617, cross_entropy: 2.715879440307617 +[2025-04-30 14:06:14,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 1.357370138168335, cross_entropy: 1.357370138168335 +[2025-04-30 14:06:17,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.271754503250122, cross_entropy: 3.271754503250122 +[2025-04-30 14:06:17,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 1.4252841472625732, cross_entropy: 1.4252841472625732 +[2025-04-30 14:06:20,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 2.0890753269195557, cross_entropy: 2.0890753269195557 +[2025-04-30 14:06:20,872][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 1.859512448310852, cross_entropy: 1.859512448310852 +[2025-04-30 14:06:25,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 1.393805742263794, cross_entropy: 1.393805742263794 +[2025-04-30 14:06:25,603][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 2.5699806213378906, cross_entropy: 2.5699806213378906 +[2025-04-30 14:06:28,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 1.4431045055389404, cross_entropy: 1.4431045055389404 +[2025-04-30 14:06:29,233][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.221088409423828, cross_entropy: 3.221088409423828 +[2025-04-30 14:06:32,774][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 1.2365264892578125, cross_entropy: 1.2365264892578125 +[2025-04-30 14:06:33,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 3.24708890914917, cross_entropy: 3.24708890914917 +[2025-04-30 14:06:37,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 1.5751577615737915, cross_entropy: 1.5751577615737915 +[2025-04-30 14:06:37,436][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.058324098587036, cross_entropy: 3.058324098587036 +[2025-04-30 14:06:40,778][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 1.676642656326294, cross_entropy: 1.676642656326294 +[2025-04-30 14:06:41,114][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 3.248932123184204, cross_entropy: 3.248932123184204 +[2025-04-30 14:06:43,984][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 1.5255881547927856, cross_entropy: 1.5255881547927856 +[2025-04-30 14:06:44,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.2419347763061523, cross_entropy: 3.2419347763061523 +[2025-04-30 14:06:48,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 1.7634172439575195, cross_entropy: 1.7634172439575195 +[2025-04-30 14:06:48,391][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 3.1628546714782715, cross_entropy: 3.1628546714782715 +[2025-04-30 14:06:51,987][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 3.40509295463562, cross_entropy: 3.40509295463562 +[2025-04-30 14:06:52,307][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 2.5240018367767334, cross_entropy: 2.5240018367767334 +[2025-04-30 14:06:56,202][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 1.4167628288269043, cross_entropy: 1.4167628288269043 +[2025-04-30 14:06:56,516][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 2.3854827880859375, cross_entropy: 2.3854827880859375 +[2025-04-30 14:06:59,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.5323128700256348, cross_entropy: 2.5323128700256348 +[2025-04-30 14:07:00,066][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 1.2593719959259033, cross_entropy: 1.2593719959259033 +[2025-04-30 14:07:04,029][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 3.063441038131714, cross_entropy: 3.063441038131714 +[2025-04-30 14:07:04,341][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 1.7311930656433105, cross_entropy: 1.7311930656433105 +[2025-04-30 14:07:07,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 2.691387414932251, cross_entropy: 2.691387414932251 +[2025-04-30 14:07:07,392][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 1.3955931663513184, cross_entropy: 1.3955931663513184 +[2025-04-30 14:07:11,063][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 2.110968589782715, cross_entropy: 2.110968589782715 +[2025-04-30 14:07:11,410][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 1.8946551084518433, cross_entropy: 1.8946551084518433 +[2025-04-30 14:07:13,912][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 1.440659999847412, cross_entropy: 1.440659999847412 +[2025-04-30 14:07:14,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 2.7156448364257812, cross_entropy: 2.7156448364257812 +[2025-04-30 14:07:17,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 1.8980273008346558, cross_entropy: 1.8980273008346558 +[2025-04-30 14:07:17,846][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 3.043233871459961, cross_entropy: 3.043233871459961 +[2025-04-30 14:07:21,460][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 3.4705793857574463, cross_entropy: 3.4705793857574463 +[2025-04-30 14:07:21,780][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 1.5924590826034546, cross_entropy: 1.5924590826034546 +[2025-04-30 14:07:25,651][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 2.861032724380493, cross_entropy: 2.861032724380493 +[2025-04-30 14:07:25,993][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 1.8156976699829102, cross_entropy: 1.8156976699829102 +[2025-04-30 14:07:29,736][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 3.1054091453552246, cross_entropy: 3.1054091453552246 +[2025-04-30 14:07:30,071][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.8173770904541016, cross_entropy: 2.8173770904541016 +[2025-04-30 14:07:33,468][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 2.8633298873901367, cross_entropy: 2.8633298873901367 +[2025-04-30 14:07:33,815][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 3.026581287384033, cross_entropy: 3.026581287384033 +[2025-04-30 14:07:37,731][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.516477108001709, cross_entropy: 2.516477108001709 +[2025-04-30 14:07:38,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 1.533070683479309, cross_entropy: 1.533070683479309 +[2025-04-30 14:07:41,278][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 2.058460235595703, cross_entropy: 2.058460235595703 +[2025-04-30 14:07:41,628][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 1.4809589385986328, cross_entropy: 1.4809589385986328 +[2025-04-30 14:07:45,042][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 2.3675830364227295, cross_entropy: 2.3675830364227295 +[2025-04-30 14:07:45,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.764772891998291, cross_entropy: 2.764772891998291 +[2025-04-30 14:07:48,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.8976948261260986, cross_entropy: 2.8976948261260986 +[2025-04-30 14:07:48,932][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 1.5466015338897705, cross_entropy: 1.5466015338897705 +[2025-04-30 14:07:51,978][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 1.9765266180038452, cross_entropy: 1.9765266180038452 +[2025-04-30 14:07:52,292][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.362605094909668, cross_entropy: 3.362605094909668 +[2025-04-30 14:07:55,695][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.603119373321533, cross_entropy: 2.603119373321533 +[2025-04-30 14:07:56,043][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.7427947521209717, cross_entropy: 1.7427947521209717 +[2025-04-30 14:07:59,875][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 1.598083734512329, cross_entropy: 1.598083734512329 +[2025-04-30 14:08:00,198][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 1.4287487268447876, cross_entropy: 1.4287487268447876 +[2025-04-30 14:08:03,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 3.3342084884643555, cross_entropy: 3.3342084884643555 +[2025-04-30 14:08:03,961][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 3.1475110054016113, cross_entropy: 3.1475110054016113 +[2025-04-30 14:08:07,514][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 2.8092944622039795, cross_entropy: 2.8092944622039795 +[2025-04-30 14:08:07,855][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 2.5216922760009766, cross_entropy: 2.5216922760009766 +[2025-04-30 14:08:11,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 1.9606114625930786, cross_entropy: 1.9606114625930786 +[2025-04-30 14:08:11,852][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 1.5860158205032349, cross_entropy: 1.5860158205032349 +[2025-04-30 14:08:14,995][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.4488136768341064, cross_entropy: 3.4488136768341064 +[2025-04-30 14:08:15,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 1.6478854417800903, cross_entropy: 1.6478854417800903 +[2025-04-30 14:08:18,073][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 1.652363657951355, cross_entropy: 1.652363657951355 +[2025-04-30 14:08:18,422][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.6492383480072021, cross_entropy: 1.6492383480072021 +[2025-04-30 14:08:22,104][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 2.1682910919189453, cross_entropy: 2.1682910919189453 +[2025-04-30 14:08:22,418][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 2.743504047393799, cross_entropy: 2.743504047393799 +[2025-04-30 14:08:25,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 1.6383790969848633, cross_entropy: 1.6383790969848633 +[2025-04-30 14:08:26,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 3.533824920654297, cross_entropy: 3.533824920654297 +[2025-04-30 14:08:29,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.368593692779541, cross_entropy: 3.368593692779541 +[2025-04-30 14:08:29,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 1.7233175039291382, cross_entropy: 1.7233175039291382 +[2025-04-30 14:08:33,541][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 1.6941392421722412, cross_entropy: 1.6941392421722412 +[2025-04-30 14:08:33,884][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.3376264572143555, cross_entropy: 3.3376264572143555 +[2025-04-30 14:08:37,256][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 2.2412965297698975, cross_entropy: 2.2412965297698975 +[2025-04-30 14:08:37,566][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 2.9051027297973633, cross_entropy: 2.9051027297973633 +[2025-04-30 14:08:41,176][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 1.7896523475646973, cross_entropy: 1.7896523475646973 +[2025-04-30 14:08:41,488][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 1.3099719285964966, cross_entropy: 1.3099719285964966 +[2025-04-30 14:08:44,449][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 2.549069881439209, cross_entropy: 2.549069881439209 +[2025-04-30 14:08:44,795][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 3.07258939743042, cross_entropy: 3.07258939743042 +[2025-04-30 14:08:48,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 1.9792238473892212, cross_entropy: 1.9792238473892212 +[2025-04-30 14:08:48,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 2.9782848358154297, cross_entropy: 2.9782848358154297 +[2025-04-30 14:08:52,214][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.937993049621582, cross_entropy: 2.937993049621582 +[2025-04-30 14:08:52,527][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 1.281707763671875, cross_entropy: 1.281707763671875 +[2025-04-30 14:08:56,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.2021100521087646, cross_entropy: 2.2021100521087646 +[2025-04-30 14:08:56,490][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 1.7859904766082764, cross_entropy: 1.7859904766082764 +[2025-04-30 14:08:59,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 3.4332435131073, cross_entropy: 3.4332435131073 +[2025-04-30 14:08:59,989][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 3.096519708633423, cross_entropy: 3.096519708633423 +[2025-04-30 14:09:03,803][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 1.5266969203948975, cross_entropy: 1.5266969203948975 +[2025-04-30 14:09:04,115][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 1.5421209335327148, cross_entropy: 1.5421209335327148 +[2025-04-30 14:09:07,441][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.7436127662658691, cross_entropy: 1.7436127662658691 +[2025-04-30 14:09:07,776][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.8353357315063477, cross_entropy: 1.8353357315063477 +[2025-04-30 14:09:10,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 1.4698190689086914, cross_entropy: 1.4698190689086914 +[2025-04-30 14:09:11,033][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 1.6083929538726807, cross_entropy: 1.6083929538726807 +[2025-04-30 14:09:14,320][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 2.962686777114868, cross_entropy: 2.962686777114868 +[2025-04-30 14:09:14,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.0936970710754395, cross_entropy: 3.0936970710754395 +[2025-04-30 14:09:17,314][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.626323938369751, cross_entropy: 1.626323938369751 +[2025-04-30 14:09:17,627][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.8580594062805176, cross_entropy: 1.8580594062805176 +[2025-04-30 14:09:20,348][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.5183603763580322, cross_entropy: 2.5183603763580322 +[2025-04-30 14:12:03,837][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.3266170024871826, cross_entropy: 2.3266170024871826 +[2025-04-30 14:12:03,838][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.5009828805923462, cross_entropy: 1.5009828805923462 +[2025-04-30 14:12:03,838][BaseTrainer][INFO] - [Epoch 3/10] (metrics) roc_auc: 0.97477787733078 +[2025-04-30 14:12:04,052][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 14:12:04,218][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch3.pth. +[2025-04-30 14:12:04,417][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 14:12:08,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 1.2269984483718872, cross_entropy: 1.2269984483718872 +[2025-04-30 14:12:08,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 1.4987194538116455, cross_entropy: 1.4987194538116455 +[2025-04-30 14:12:11,862][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.5435967445373535, cross_entropy: 1.5435967445373535 +[2025-04-30 14:12:12,183][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.351269006729126, cross_entropy: 1.351269006729126 +[2025-04-30 14:12:15,431][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 1.730481743812561, cross_entropy: 1.730481743812561 +[2025-04-30 14:12:15,768][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.6558854579925537, cross_entropy: 1.6558854579925537 +[2025-04-30 14:12:18,896][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 1.3548812866210938, cross_entropy: 1.3548812866210938 +[2025-04-30 14:12:19,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 3.065182685852051, cross_entropy: 3.065182685852051 +[2025-04-30 14:12:22,228][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 1.941401481628418, cross_entropy: 1.941401481628418 +[2025-04-30 14:12:22,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 1.5292320251464844, cross_entropy: 1.5292320251464844 +[2025-04-30 14:12:25,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 3.2059719562530518, cross_entropy: 3.2059719562530518 +[2025-04-30 14:12:26,095][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.321207284927368, cross_entropy: 2.321207284927368 +[2025-04-30 14:12:28,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 1.7191158533096313, cross_entropy: 1.7191158533096313 +[2025-04-30 14:12:29,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.874086856842041, cross_entropy: 2.874086856842041 +[2025-04-30 14:12:31,236][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 1.3642268180847168, cross_entropy: 1.3642268180847168 +[2025-04-30 14:12:32,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.5258384943008423, cross_entropy: 1.5258384943008423 +[2025-04-30 14:12:34,604][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.293229579925537, cross_entropy: 2.293229579925537 +[2025-04-30 14:12:35,827][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 3.4297420978546143, cross_entropy: 3.4297420978546143 +[2025-04-30 14:12:38,864][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.326594114303589, cross_entropy: 3.326594114303589 +[2025-04-30 14:12:39,191][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.3265089988708496, cross_entropy: 2.3265089988708496 +[2025-04-30 14:12:42,146][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 1.5522596836090088, cross_entropy: 1.5522596836090088 +[2025-04-30 14:12:42,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 1.6543047428131104, cross_entropy: 1.6543047428131104 +[2025-04-30 14:12:45,579][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.7361106872558594, cross_entropy: 2.7361106872558594 +[2025-04-30 14:12:45,890][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 3.061271905899048, cross_entropy: 3.061271905899048 +[2025-04-30 14:12:49,690][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 2.579176902770996, cross_entropy: 2.579176902770996 +[2025-04-30 14:12:50,004][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.4060187339782715, cross_entropy: 1.4060187339782715 +[2025-04-30 14:12:54,219][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.153524160385132, cross_entropy: 2.153524160385132 +[2025-04-30 14:12:54,532][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.1130597591400146, cross_entropy: 3.1130597591400146 +[2025-04-30 14:12:57,709][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 1.928668737411499, cross_entropy: 1.928668737411499 +[2025-04-30 14:12:58,023][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.3980917930603027, cross_entropy: 2.3980917930603027 +[2025-04-30 14:13:00,854][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 2.6896679401397705, cross_entropy: 2.6896679401397705 +[2025-04-30 14:13:01,165][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 1.4331345558166504, cross_entropy: 1.4331345558166504 +[2025-04-30 14:13:04,500][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 1.6897943019866943, cross_entropy: 1.6897943019866943 +[2025-04-30 14:13:04,814][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 3.385773181915283, cross_entropy: 3.385773181915283 +[2025-04-30 14:13:07,785][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.9119105339050293, cross_entropy: 2.9119105339050293 +[2025-04-30 14:13:08,097][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 1.2806310653686523, cross_entropy: 1.2806310653686523 +[2025-04-30 14:13:11,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 1.6129653453826904, cross_entropy: 1.6129653453826904 +[2025-04-30 14:13:11,729][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 1.6808966398239136, cross_entropy: 1.6808966398239136 +[2025-04-30 14:13:14,421][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.6110172271728516, cross_entropy: 3.6110172271728516 +[2025-04-30 14:13:14,762][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 2.6680445671081543, cross_entropy: 2.6680445671081543 +[2025-04-30 14:13:18,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 1.4413564205169678, cross_entropy: 1.4413564205169678 +[2025-04-30 14:13:18,651][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 1.7714905738830566, cross_entropy: 1.7714905738830566 +[2025-04-30 14:13:22,088][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.158191680908203, cross_entropy: 2.158191680908203 +[2025-04-30 14:13:22,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.4338998794555664, cross_entropy: 2.4338998794555664 +[2025-04-30 14:13:25,216][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 2.4325690269470215, cross_entropy: 2.4325690269470215 +[2025-04-30 14:13:25,529][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.3944711685180664, cross_entropy: 2.3944711685180664 +[2025-04-30 14:13:29,004][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 1.9864866733551025, cross_entropy: 1.9864866733551025 +[2025-04-30 14:13:29,342][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 2.1338629722595215, cross_entropy: 2.1338629722595215 +[2025-04-30 14:13:32,462][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 1.2467029094696045, cross_entropy: 1.2467029094696045 +[2025-04-30 14:13:32,775][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.7595434188842773, cross_entropy: 2.7595434188842773 +[2025-04-30 14:13:35,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 1.475811243057251, cross_entropy: 1.475811243057251 +[2025-04-30 14:13:36,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 1.2430496215820312, cross_entropy: 1.2430496215820312 +[2025-04-30 14:13:39,672][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 1.6890263557434082, cross_entropy: 1.6890263557434082 +[2025-04-30 14:13:40,016][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 2.1957266330718994, cross_entropy: 2.1957266330718994 +[2025-04-30 14:13:42,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 3.2183103561401367, cross_entropy: 3.2183103561401367 +[2025-04-30 14:13:43,005][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 1.8869166374206543, cross_entropy: 1.8869166374206543 +[2025-04-30 14:13:45,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 1.4981944561004639, cross_entropy: 1.4981944561004639 +[2025-04-30 14:13:46,061][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 3.09455943107605, cross_entropy: 3.09455943107605 +[2025-04-30 14:13:49,664][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 1.7588675022125244, cross_entropy: 1.7588675022125244 +[2025-04-30 14:13:49,975][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 3.054123640060425, cross_entropy: 3.054123640060425 +[2025-04-30 14:13:52,707][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.5531057119369507, cross_entropy: 1.5531057119369507 +[2025-04-30 14:13:53,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 1.9867517948150635, cross_entropy: 1.9867517948150635 +[2025-04-30 14:13:56,510][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 2.834440231323242, cross_entropy: 2.834440231323242 +[2025-04-30 14:13:56,847][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 2.284810781478882, cross_entropy: 2.284810781478882 +[2025-04-30 14:13:59,848][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.6791305541992188, cross_entropy: 2.6791305541992188 +[2025-04-30 14:14:00,196][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 1.5876575708389282, cross_entropy: 1.5876575708389282 +[2025-04-30 14:14:03,539][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.7632856369018555, cross_entropy: 2.7632856369018555 +[2025-04-30 14:14:03,886][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 1.6072090864181519, cross_entropy: 1.6072090864181519 +[2025-04-30 14:14:07,460][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.067409038543701, cross_entropy: 2.067409038543701 +[2025-04-30 14:14:07,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.6492743492126465, cross_entropy: 2.6492743492126465 +[2025-04-30 14:14:10,663][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 2.2910335063934326, cross_entropy: 2.2910335063934326 +[2025-04-30 14:14:10,996][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 1.720523476600647, cross_entropy: 1.720523476600647 +[2025-04-30 14:14:13,925][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.3638978004455566, cross_entropy: 1.3638978004455566 +[2025-04-30 14:14:14,278][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 1.4794557094573975, cross_entropy: 1.4794557094573975 +[2025-04-30 14:14:16,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 2.3726134300231934, cross_entropy: 2.3726134300231934 +[2025-04-30 14:14:17,041][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 1.4742538928985596, cross_entropy: 1.4742538928985596 +[2025-04-30 14:14:19,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 1.0663009881973267, cross_entropy: 1.0663009881973267 +[2025-04-30 14:14:19,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 1.3921524286270142, cross_entropy: 1.3921524286270142 +[2025-04-30 14:14:22,551][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 3.504533290863037, cross_entropy: 3.504533290863037 +[2025-04-30 14:14:22,894][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 1.4071955680847168, cross_entropy: 1.4071955680847168 +[2025-04-30 14:14:25,882][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 2.01812481880188, cross_entropy: 2.01812481880188 +[2025-04-30 14:14:26,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.775904893875122, cross_entropy: 2.775904893875122 +[2025-04-30 14:14:29,175][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 1.2759671211242676, cross_entropy: 1.2759671211242676 +[2025-04-30 14:14:29,487][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.411298155784607, cross_entropy: 1.411298155784607 +[2025-04-30 14:14:32,751][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 1.8668532371520996, cross_entropy: 1.8668532371520996 +[2025-04-30 14:14:33,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 3.4593441486358643, cross_entropy: 3.4593441486358643 +[2025-04-30 14:14:36,601][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 1.1662861108779907, cross_entropy: 1.1662861108779907 +[2025-04-30 14:14:36,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 0.943763256072998, cross_entropy: 0.943763256072998 +[2025-04-30 14:14:40,080][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 0.9762654900550842, cross_entropy: 0.9762654900550842 +[2025-04-30 14:14:40,421][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 2.3910927772521973, cross_entropy: 2.3910927772521973 +[2025-04-30 14:14:43,244][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.211477756500244, cross_entropy: 3.211477756500244 +[2025-04-30 14:14:43,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.629306674003601, cross_entropy: 1.629306674003601 +[2025-04-30 14:14:46,478][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 1.1134241819381714, cross_entropy: 1.1134241819381714 +[2025-04-30 14:14:46,814][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 1.9799100160598755, cross_entropy: 1.9799100160598755 +[2025-04-30 14:14:50,207][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 3.499011278152466, cross_entropy: 3.499011278152466 +[2025-04-30 14:14:50,520][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 1.6664878129959106, cross_entropy: 1.6664878129959106 +[2025-04-30 14:14:53,669][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 3.1141648292541504, cross_entropy: 3.1141648292541504 +[2025-04-30 14:14:53,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 1.5384867191314697, cross_entropy: 1.5384867191314697 +[2025-04-30 14:14:58,007][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 2.7008557319641113, cross_entropy: 2.7008557319641113 +[2025-04-30 14:14:58,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 1.0512943267822266, cross_entropy: 1.0512943267822266 +[2025-04-30 14:15:01,884][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 2.056598663330078, cross_entropy: 2.056598663330078 +[2025-04-30 14:15:02,195][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.635582685470581, cross_entropy: 2.635582685470581 +[2025-04-30 14:15:05,137][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 2.632197618484497, cross_entropy: 2.632197618484497 +[2025-04-30 14:15:05,477][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 1.4767141342163086, cross_entropy: 1.4767141342163086 +[2025-04-30 14:15:08,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.2230658531188965, cross_entropy: 2.2230658531188965 +[2025-04-30 14:15:09,566][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 1.3155145645141602, cross_entropy: 1.3155145645141602 +[2025-04-30 14:15:12,055][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 3.4804086685180664, cross_entropy: 3.4804086685180664 +[2025-04-30 14:15:13,687][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 1.682340383529663, cross_entropy: 1.682340383529663 +[2025-04-30 14:15:15,356][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 3.3434479236602783, cross_entropy: 3.3434479236602783 +[2025-04-30 14:15:16,947][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 2.7918930053710938, cross_entropy: 2.7918930053710938 +[2025-04-30 14:15:19,051][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.5172219276428223, cross_entropy: 2.5172219276428223 +[2025-04-30 14:15:20,688][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 2.1983184814453125, cross_entropy: 2.1983184814453125 +[2025-04-30 14:15:22,634][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 2.7276246547698975, cross_entropy: 2.7276246547698975 +[2025-04-30 14:15:24,324][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.231524705886841, cross_entropy: 2.231524705886841 +[2025-04-30 14:15:26,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 0.8988350033760071, cross_entropy: 0.8988350033760071 +[2025-04-30 14:15:28,377][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 2.5286777019500732, cross_entropy: 2.5286777019500732 +[2025-04-30 14:15:30,531][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.833987236022949, cross_entropy: 2.833987236022949 +[2025-04-30 14:15:33,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.4584174156188965, cross_entropy: 1.4584174156188965 +[2025-04-30 14:15:34,286][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 1.1687272787094116, cross_entropy: 1.1687272787094116 +[2025-04-30 14:15:36,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 1.773903727531433, cross_entropy: 1.773903727531433 +[2025-04-30 14:15:37,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.6254777908325195, cross_entropy: 3.6254777908325195 +[2025-04-30 14:15:40,224][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 3.394076347351074, cross_entropy: 3.394076347351074 +[2025-04-30 14:15:42,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 2.9356136322021484, cross_entropy: 2.9356136322021484 +[2025-04-30 14:15:43,842][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 3.075310230255127, cross_entropy: 3.075310230255127 +[2025-04-30 14:15:46,122][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.2880547046661377, cross_entropy: 1.2880547046661377 +[2025-04-30 14:15:48,031][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.2455382347106934, cross_entropy: 1.2455382347106934 +[2025-04-30 14:15:50,236][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 1.7027180194854736, cross_entropy: 1.7027180194854736 +[2025-04-30 14:15:52,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.8819684982299805, cross_entropy: 2.8819684982299805 +[2025-04-30 14:15:54,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.9592680931091309, cross_entropy: 1.9592680931091309 +[2025-04-30 14:15:55,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 0.9967945218086243, cross_entropy: 0.9967945218086243 +[2025-04-30 14:15:57,595][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 1.4262588024139404, cross_entropy: 1.4262588024139404 +[2025-04-30 14:15:57,948][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 3.0281906127929688, cross_entropy: 3.0281906127929688 +[2025-04-30 14:16:02,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.8953936100006104, cross_entropy: 2.8953936100006104 +[2025-04-30 14:16:03,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 1.7870445251464844, cross_entropy: 1.7870445251464844 +[2025-04-30 14:16:06,515][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 1.4729375839233398, cross_entropy: 1.4729375839233398 +[2025-04-30 14:16:06,829][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 2.831390857696533, cross_entropy: 2.831390857696533 +[2025-04-30 14:16:09,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 1.2808730602264404, cross_entropy: 1.2808730602264404 +[2025-04-30 14:16:10,009][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 1.1000043153762817, cross_entropy: 1.1000043153762817 +[2025-04-30 14:16:13,648][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 1.4011313915252686, cross_entropy: 1.4011313915252686 +[2025-04-30 14:16:13,986][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 2.3039939403533936, cross_entropy: 2.3039939403533936 +[2025-04-30 14:16:17,125][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.1014606952667236, cross_entropy: 3.1014606952667236 +[2025-04-30 14:16:17,460][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 3.2793288230895996, cross_entropy: 3.2793288230895996 +[2025-04-30 14:16:21,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 1.4014770984649658, cross_entropy: 1.4014770984649658 +[2025-04-30 14:16:21,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.588399648666382, cross_entropy: 2.588399648666382 +[2025-04-30 14:16:24,718][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 1.578771948814392, cross_entropy: 1.578771948814392 +[2025-04-30 14:16:25,057][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 1.3053436279296875, cross_entropy: 1.3053436279296875 +[2025-04-30 14:16:28,358][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 3.2794337272644043, cross_entropy: 3.2794337272644043 +[2025-04-30 14:16:28,671][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 1.4883980751037598, cross_entropy: 1.4883980751037598 +[2025-04-30 14:16:31,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 2.520472764968872, cross_entropy: 2.520472764968872 +[2025-04-30 14:16:31,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 1.5574920177459717, cross_entropy: 1.5574920177459717 +[2025-04-30 14:16:35,054][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 1.7035514116287231, cross_entropy: 1.7035514116287231 +[2025-04-30 14:16:35,638][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 1.6605077981948853, cross_entropy: 1.6605077981948853 +[2025-04-30 14:16:38,379][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.2108882665634155, cross_entropy: 1.2108882665634155 +[2025-04-30 14:16:39,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 1.4391489028930664, cross_entropy: 1.4391489028930664 +[2025-04-30 14:16:41,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 1.3873754739761353, cross_entropy: 1.3873754739761353 +[2025-04-30 14:16:42,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 2.877739667892456, cross_entropy: 2.877739667892456 +[2025-04-30 14:16:45,499][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 1.5943652391433716, cross_entropy: 1.5943652391433716 +[2025-04-30 14:16:47,181][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 1.3917357921600342, cross_entropy: 1.3917357921600342 +[2025-04-30 14:16:49,103][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 3.4174861907958984, cross_entropy: 3.4174861907958984 +[2025-04-30 14:16:50,644][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 3.0861587524414062, cross_entropy: 3.0861587524414062 +[2025-04-30 14:16:52,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 3.067343235015869, cross_entropy: 3.067343235015869 +[2025-04-30 14:16:53,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 2.6407575607299805, cross_entropy: 2.6407575607299805 +[2025-04-30 14:16:56,824][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 0.8174911737442017, cross_entropy: 0.8174911737442017 +[2025-04-30 14:16:57,597][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.653141975402832, cross_entropy: 2.653141975402832 +[2025-04-30 14:17:00,277][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.6323859691619873, cross_entropy: 1.6323859691619873 +[2025-04-30 14:17:01,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 1.7617809772491455, cross_entropy: 1.7617809772491455 +[2025-04-30 14:17:03,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.3142720460891724, cross_entropy: 1.3142720460891724 +[2025-04-30 14:17:04,994][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 1.1013107299804688, cross_entropy: 1.1013107299804688 +[2025-04-30 14:17:07,733][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.4141426086425781, cross_entropy: 1.4141426086425781 +[2025-04-30 14:17:08,542][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 0.853394091129303, cross_entropy: 0.853394091129303 +[2025-04-30 14:17:11,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 2.922178268432617, cross_entropy: 2.922178268432617 +[2025-04-30 14:17:11,690][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 2.8541746139526367, cross_entropy: 2.8541746139526367 +[2025-04-30 14:17:14,521][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 3.529151439666748, cross_entropy: 3.529151439666748 +[2025-04-30 14:17:15,398][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 3.1544814109802246, cross_entropy: 3.1544814109802246 +[2025-04-30 14:17:18,171][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 1.43402898311615, cross_entropy: 1.43402898311615 +[2025-04-30 14:17:18,864][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 1.3333542346954346, cross_entropy: 1.3333542346954346 +[2025-04-30 14:17:21,801][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 3.4419479370117188, cross_entropy: 3.4419479370117188 +[2025-04-30 14:17:22,262][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 2.8787970542907715, cross_entropy: 2.8787970542907715 +[2025-04-30 14:17:25,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 2.6524040699005127, cross_entropy: 2.6524040699005127 +[2025-04-30 14:17:26,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.8755908012390137, cross_entropy: 1.8755908012390137 +[2025-04-30 14:17:28,788][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 1.3865289688110352, cross_entropy: 1.3865289688110352 +[2025-04-30 14:17:29,168][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 1.693166971206665, cross_entropy: 1.693166971206665 +[2025-04-30 14:17:32,274][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 1.439077377319336, cross_entropy: 1.439077377319336 +[2025-04-30 14:17:32,637][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 2.941030502319336, cross_entropy: 2.941030502319336 +[2025-04-30 14:17:35,765][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.468172550201416, cross_entropy: 2.468172550201416 +[2025-04-30 14:17:36,102][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 1.6741573810577393, cross_entropy: 1.6741573810577393 +[2025-04-30 14:17:40,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 1.5230638980865479, cross_entropy: 1.5230638980865479 +[2025-04-30 14:17:40,901][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.5121322870254517, cross_entropy: 1.5121322870254517 +[2025-04-30 14:17:44,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.860825538635254, cross_entropy: 1.860825538635254 +[2025-04-30 14:17:44,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 2.515305995941162, cross_entropy: 2.515305995941162 +[2025-04-30 14:17:48,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 1.4370265007019043, cross_entropy: 1.4370265007019043 +[2025-04-30 14:17:48,463][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 3.1472740173339844, cross_entropy: 3.1472740173339844 +[2025-04-30 14:17:52,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 1.6563993692398071, cross_entropy: 1.6563993692398071 +[2025-04-30 14:17:52,441][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 0.9252285957336426, cross_entropy: 0.9252285957336426 +[2025-04-30 14:17:56,142][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 1.229074478149414, cross_entropy: 1.229074478149414 +[2025-04-30 14:17:56,456][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 3.1069984436035156, cross_entropy: 3.1069984436035156 +[2025-04-30 14:17:59,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 1.620192289352417, cross_entropy: 1.620192289352417 +[2025-04-30 14:18:00,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 3.38397216796875, cross_entropy: 3.38397216796875 +[2025-04-30 14:18:03,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 2.475351572036743, cross_entropy: 2.475351572036743 +[2025-04-30 14:18:04,342][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 2.9942541122436523, cross_entropy: 2.9942541122436523 +[2025-04-30 14:18:06,759][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 1.9773386716842651, cross_entropy: 1.9773386716842651 +[2025-04-30 14:18:08,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 1.7811657190322876, cross_entropy: 1.7811657190322876 +[2025-04-30 14:18:10,819][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 2.864130973815918, cross_entropy: 2.864130973815918 +[2025-04-30 14:18:12,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 1.5584843158721924, cross_entropy: 1.5584843158721924 +[2025-04-30 14:18:14,839][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 2.08251953125, cross_entropy: 2.08251953125 +[2025-04-30 14:18:15,438][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 1.4584225416183472, cross_entropy: 1.4584225416183472 +[2025-04-30 14:18:18,893][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 2.224024772644043, cross_entropy: 2.224024772644043 +[2025-04-30 14:18:19,233][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 1.785427451133728, cross_entropy: 1.785427451133728 +[2025-04-30 14:18:22,532][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 3.222527503967285, cross_entropy: 3.222527503967285 +[2025-04-30 14:18:22,865][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 1.4035639762878418, cross_entropy: 1.4035639762878418 +[2025-04-30 14:18:26,116][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.1062676906585693, cross_entropy: 1.1062676906585693 +[2025-04-30 14:18:26,451][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 1.6208006143569946, cross_entropy: 1.6208006143569946 +[2025-04-30 14:18:29,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 1.1678701639175415, cross_entropy: 1.1678701639175415 +[2025-04-30 14:18:30,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 2.157723903656006, cross_entropy: 2.157723903656006 +[2025-04-30 14:18:33,996][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.4002685546875, cross_entropy: 2.4002685546875 +[2025-04-30 14:18:34,339][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.019927740097046, cross_entropy: 2.019927740097046 +[2025-04-30 14:18:37,437][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 1.9369120597839355, cross_entropy: 1.9369120597839355 +[2025-04-30 14:18:37,773][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 2.4558839797973633, cross_entropy: 2.4558839797973633 +[2025-04-30 14:18:41,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 1.5107965469360352, cross_entropy: 1.5107965469360352 +[2025-04-30 14:18:41,577][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 2.278804063796997, cross_entropy: 2.278804063796997 +[2025-04-30 14:18:44,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 3.1405913829803467, cross_entropy: 3.1405913829803467 +[2025-04-30 14:18:44,979][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 1.9523866176605225, cross_entropy: 1.9523866176605225 +[2025-04-30 14:18:48,351][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 3.427318572998047, cross_entropy: 3.427318572998047 +[2025-04-30 14:18:49,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.3358726501464844, cross_entropy: 2.3358726501464844 +[2025-04-30 14:18:52,418][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 2.2044336795806885, cross_entropy: 2.2044336795806885 +[2025-04-30 14:18:54,000][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.09436297416687, cross_entropy: 3.09436297416687 +[2025-04-30 14:18:56,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 3.006350040435791, cross_entropy: 3.006350040435791 +[2025-04-30 14:18:57,864][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 3.0651159286499023, cross_entropy: 3.0651159286499023 +[2025-04-30 14:19:00,453][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.081493854522705, cross_entropy: 3.081493854522705 +[2025-04-30 14:19:01,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.3518335819244385, cross_entropy: 1.3518335819244385 +[2025-04-30 14:19:04,380][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 2.5962281227111816, cross_entropy: 2.5962281227111816 +[2025-04-30 14:19:05,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.187180519104004, cross_entropy: 2.187180519104004 +[2025-04-30 14:19:07,688][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.8985931873321533, cross_entropy: 2.8985931873321533 +[2025-04-30 14:19:08,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 1.312550663948059, cross_entropy: 1.312550663948059 +[2025-04-30 14:19:12,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 1.703329086303711, cross_entropy: 1.703329086303711 +[2025-04-30 14:19:13,417][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 2.274954319000244, cross_entropy: 2.274954319000244 +[2025-04-30 14:19:16,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 3.1385607719421387, cross_entropy: 3.1385607719421387 +[2025-04-30 14:19:17,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.3843560218811035, cross_entropy: 2.3843560218811035 +[2025-04-30 14:19:20,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.129798650741577, cross_entropy: 3.129798650741577 +[2025-04-30 14:19:21,133][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 2.906514883041382, cross_entropy: 2.906514883041382 +[2025-04-30 14:19:24,713][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 1.4676581621170044, cross_entropy: 1.4676581621170044 +[2025-04-30 14:19:25,103][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.998579978942871, cross_entropy: 2.998579978942871 +[2025-04-30 14:19:28,107][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 1.3188600540161133, cross_entropy: 1.3188600540161133 +[2025-04-30 14:19:28,445][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 1.7369134426116943, cross_entropy: 1.7369134426116943 +[2025-04-30 14:19:31,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.371819257736206, cross_entropy: 1.371819257736206 +[2025-04-30 14:19:32,445][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 1.4817101955413818, cross_entropy: 1.4817101955413818 +[2025-04-30 14:19:35,626][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.339871644973755, cross_entropy: 2.339871644973755 +[2025-04-30 14:19:36,001][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.860076427459717, cross_entropy: 2.860076427459717 +[2025-04-30 14:19:39,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.6638782024383545, cross_entropy: 2.6638782024383545 +[2025-04-30 14:19:39,803][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.4626975059509277, cross_entropy: 1.4626975059509277 +[2025-04-30 14:19:42,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 3.1883199214935303, cross_entropy: 3.1883199214935303 +[2025-04-30 14:19:43,098][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 2.230602264404297, cross_entropy: 2.230602264404297 +[2025-04-30 14:19:47,242][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 3.2575907707214355, cross_entropy: 3.2575907707214355 +[2025-04-30 14:19:47,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 3.119335651397705, cross_entropy: 3.119335651397705 +[2025-04-30 14:19:51,098][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 2.787477493286133, cross_entropy: 2.787477493286133 +[2025-04-30 14:19:51,421][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 3.2258498668670654, cross_entropy: 3.2258498668670654 +[2025-04-30 14:19:54,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 1.2100660800933838, cross_entropy: 1.2100660800933838 +[2025-04-30 14:19:55,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.2056571245193481, cross_entropy: 1.2056571245193481 +[2025-04-30 14:19:58,637][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 2.537698745727539, cross_entropy: 2.537698745727539 +[2025-04-30 14:19:59,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 1.1858406066894531, cross_entropy: 1.1858406066894531 +[2025-04-30 14:20:03,482][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 2.6384754180908203, cross_entropy: 2.6384754180908203 +[2025-04-30 14:20:03,807][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 1.6521153450012207, cross_entropy: 1.6521153450012207 +[2025-04-30 14:20:06,902][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 3.0279407501220703, cross_entropy: 3.0279407501220703 +[2025-04-30 14:20:07,970][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 1.3722645044326782, cross_entropy: 1.3722645044326782 +[2025-04-30 14:20:10,424][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 1.3535170555114746, cross_entropy: 1.3535170555114746 +[2025-04-30 14:20:12,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 2.177309989929199, cross_entropy: 2.177309989929199 +[2025-04-30 14:20:15,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 1.2457573413848877, cross_entropy: 1.2457573413848877 +[2025-04-30 14:20:15,878][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 3.0309672355651855, cross_entropy: 3.0309672355651855 +[2025-04-30 14:20:18,777][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 3.0908334255218506, cross_entropy: 3.0908334255218506 +[2025-04-30 14:20:21,122][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.771342396736145, cross_entropy: 1.771342396736145 +[2025-04-30 14:20:22,536][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 2.624265193939209, cross_entropy: 2.624265193939209 +[2025-04-30 14:20:24,360][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 0.9686957597732544, cross_entropy: 0.9686957597732544 +[2025-04-30 14:20:26,181][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 1.5119240283966064, cross_entropy: 1.5119240283966064 +[2025-04-30 14:20:28,389][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 1.9743324518203735, cross_entropy: 1.9743324518203735 +[2025-04-30 14:20:30,039][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 2.1505508422851562, cross_entropy: 2.1505508422851562 +[2025-04-30 14:20:31,568][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 1.6371346712112427, cross_entropy: 1.6371346712112427 +[2025-04-30 14:20:34,379][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 1.9504847526550293, cross_entropy: 1.9504847526550293 +[2025-04-30 14:20:35,732][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 1.447084665298462, cross_entropy: 1.447084665298462 +[2025-04-30 14:20:38,292][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 2.0785861015319824, cross_entropy: 2.0785861015319824 +[2025-04-30 14:20:39,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 1.6199840307235718, cross_entropy: 1.6199840307235718 +[2025-04-30 14:20:42,161][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 2.1002378463745117, cross_entropy: 2.1002378463745117 +[2025-04-30 14:20:42,538][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 2.920473098754883, cross_entropy: 2.920473098754883 +[2025-04-30 14:20:46,479][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 2.2253522872924805, cross_entropy: 2.2253522872924805 +[2025-04-30 14:20:46,816][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 1.5010716915130615, cross_entropy: 1.5010716915130615 +[2025-04-30 14:20:50,082][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 1.0512235164642334, cross_entropy: 1.0512235164642334 +[2025-04-30 14:20:50,423][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.7836525440216064, cross_entropy: 2.7836525440216064 +[2025-04-30 14:20:54,095][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 2.92095947265625, cross_entropy: 2.92095947265625 +[2025-04-30 14:20:54,434][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 3.1409411430358887, cross_entropy: 3.1409411430358887 +[2025-04-30 14:20:57,552][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 1.4983034133911133, cross_entropy: 1.4983034133911133 +[2025-04-30 14:20:57,891][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 1.025478482246399, cross_entropy: 1.025478482246399 +[2025-04-30 14:21:01,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 1.6386535167694092, cross_entropy: 1.6386535167694092 +[2025-04-30 14:21:01,474][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 2.480947732925415, cross_entropy: 2.480947732925415 +[2025-04-30 14:21:05,100][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.6351759433746338, cross_entropy: 1.6351759433746338 +[2025-04-30 14:21:05,413][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 1.5432634353637695, cross_entropy: 1.5432634353637695 +[2025-04-30 14:21:08,678][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 1.4856641292572021, cross_entropy: 1.4856641292572021 +[2025-04-30 14:21:09,020][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 1.2595055103302002, cross_entropy: 1.2595055103302002 +[2025-04-30 14:21:13,690][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.3788986206054688, cross_entropy: 2.3788986206054688 +[2025-04-30 14:21:14,025][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.478795051574707, cross_entropy: 1.478795051574707 +[2025-04-30 14:21:17,585][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.885324478149414, cross_entropy: 2.885324478149414 +[2025-04-30 14:21:17,899][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 1.4371463060379028, cross_entropy: 1.4371463060379028 +[2025-04-30 14:21:21,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 3.1140174865722656, cross_entropy: 3.1140174865722656 +[2025-04-30 14:21:21,509][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.920379638671875, cross_entropy: 2.920379638671875 +[2025-04-30 14:21:24,800][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.8749363422393799, cross_entropy: 1.8749363422393799 +[2025-04-30 14:21:25,113][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.7422640323638916, cross_entropy: 1.7422640323638916 +[2025-04-30 14:21:28,355][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 2.961015224456787, cross_entropy: 2.961015224456787 +[2025-04-30 14:21:28,671][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.2808284759521484, cross_entropy: 2.2808284759521484 +[2025-04-30 14:21:31,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.9552457332611084, cross_entropy: 1.9552457332611084 +[2025-04-30 14:21:32,196][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 2.4453089237213135, cross_entropy: 2.4453089237213135 +[2025-04-30 14:21:35,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 2.652686595916748, cross_entropy: 2.652686595916748 +[2025-04-30 14:21:35,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.344350814819336, cross_entropy: 2.344350814819336 +[2025-04-30 14:21:38,925][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 2.9815807342529297, cross_entropy: 2.9815807342529297 +[2025-04-30 14:21:39,258][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 1.5171191692352295, cross_entropy: 1.5171191692352295 +[2025-04-30 14:21:43,385][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 1.6071760654449463, cross_entropy: 1.6071760654449463 +[2025-04-30 14:21:43,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.125361919403076, cross_entropy: 2.125361919403076 +[2025-04-30 14:21:46,838][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 1.9752713441848755, cross_entropy: 1.9752713441848755 +[2025-04-30 14:21:47,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 1.4654262065887451, cross_entropy: 1.4654262065887451 +[2025-04-30 14:21:50,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 1.4562493562698364, cross_entropy: 1.4562493562698364 +[2025-04-30 14:21:51,013][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.91640305519104, cross_entropy: 1.91640305519104 +[2025-04-30 14:21:54,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 1.8410091400146484, cross_entropy: 1.8410091400146484 +[2025-04-30 14:21:55,015][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 3.1682114601135254, cross_entropy: 3.1682114601135254 +[2025-04-30 14:21:59,252][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.333181619644165, cross_entropy: 1.333181619644165 +[2025-04-30 14:21:59,596][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.3542555570602417, cross_entropy: 1.3542555570602417 +[2025-04-30 14:22:03,013][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 2.400460720062256, cross_entropy: 2.400460720062256 +[2025-04-30 14:22:03,327][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 0.8720741868019104, cross_entropy: 0.8720741868019104 +[2025-04-30 14:22:06,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 3.259338855743408, cross_entropy: 3.259338855743408 +[2025-04-30 14:22:07,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 2.7844932079315186, cross_entropy: 2.7844932079315186 +[2025-04-30 14:22:11,335][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 3.1133198738098145, cross_entropy: 3.1133198738098145 +[2025-04-30 14:22:11,677][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 1.6028822660446167, cross_entropy: 1.6028822660446167 +[2025-04-30 14:22:15,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 2.005096197128296, cross_entropy: 2.005096197128296 +[2025-04-30 14:22:15,855][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.192262053489685, cross_entropy: 1.192262053489685 +[2025-04-30 14:22:19,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.4626281261444092, cross_entropy: 1.4626281261444092 +[2025-04-30 14:22:19,860][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.3719792366027832, cross_entropy: 1.3719792366027832 +[2025-04-30 14:22:23,434][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 2.546088933944702, cross_entropy: 2.546088933944702 +[2025-04-30 14:22:23,772][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 3.102433204650879, cross_entropy: 3.102433204650879 +[2025-04-30 14:22:27,800][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 1.6722112894058228, cross_entropy: 1.6722112894058228 +[2025-04-30 14:22:28,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 2.7625575065612793, cross_entropy: 2.7625575065612793 +[2025-04-30 14:22:31,347][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 2.186892032623291, cross_entropy: 2.186892032623291 +[2025-04-30 14:22:31,689][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.1040053367614746, cross_entropy: 2.1040053367614746 +[2025-04-30 14:22:35,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 3.1091694831848145, cross_entropy: 3.1091694831848145 +[2025-04-30 14:22:35,520][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.2867968082427979, cross_entropy: 1.2867968082427979 +[2025-04-30 14:22:38,573][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.7569539546966553, cross_entropy: 2.7569539546966553 +[2025-04-30 14:22:39,195][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.391091823577881, cross_entropy: 3.391091823577881 +[2025-04-30 14:22:42,425][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 1.3032870292663574, cross_entropy: 1.3032870292663574 +[2025-04-30 14:22:43,319][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 2.8811287879943848, cross_entropy: 2.8811287879943848 +[2025-04-30 14:22:46,126][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 2.162721633911133, cross_entropy: 2.162721633911133 +[2025-04-30 14:22:46,928][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 2.962224245071411, cross_entropy: 2.962224245071411 +[2025-04-30 14:22:51,192][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 1.475419044494629, cross_entropy: 1.475419044494629 +[2025-04-30 14:22:51,538][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.8731954097747803, cross_entropy: 2.8731954097747803 +[2025-04-30 14:22:54,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 1.9544004201889038, cross_entropy: 1.9544004201889038 +[2025-04-30 14:22:55,058][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.0990232229232788, cross_entropy: 1.0990232229232788 +[2025-04-30 14:22:59,066][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 1.4118592739105225, cross_entropy: 1.4118592739105225 +[2025-04-30 14:22:59,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 3.1249008178710938, cross_entropy: 3.1249008178710938 +[2025-04-30 14:23:03,001][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 1.6763993501663208, cross_entropy: 1.6763993501663208 +[2025-04-30 14:23:03,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 1.4880216121673584, cross_entropy: 1.4880216121673584 +[2025-04-30 14:23:06,767][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 1.061978816986084, cross_entropy: 1.061978816986084 +[2025-04-30 14:23:07,048][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.3516950607299805, cross_entropy: 3.3516950607299805 +[2025-04-30 14:26:04,847][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.1201882362365723, cross_entropy: 2.1201882362365723 +[2025-04-30 14:26:04,847][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.394229531288147, cross_entropy: 1.394229531288147 +[2025-04-30 14:26:04,847][BaseTrainer][INFO] - [Epoch 4/10] (metrics) roc_auc: 0.9764987826347351 +[2025-04-30 14:26:05,073][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 14:26:05,237][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch4.pth. +[2025-04-30 14:26:05,444][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 14:26:10,354][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.2978835105895996, cross_entropy: 2.2978835105895996 +[2025-04-30 14:26:10,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 1.4121501445770264, cross_entropy: 1.4121501445770264 +[2025-04-30 14:26:14,185][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.7732007503509521, cross_entropy: 1.7732007503509521 +[2025-04-30 14:26:14,529][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 1.3739650249481201, cross_entropy: 1.3739650249481201 +[2025-04-30 14:26:17,555][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.148137092590332, cross_entropy: 1.148137092590332 +[2025-04-30 14:26:17,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 2.4711270332336426, cross_entropy: 2.4711270332336426 +[2025-04-30 14:26:20,888][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.081587314605713, cross_entropy: 2.081587314605713 +[2025-04-30 14:26:21,238][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.1783528327941895, cross_entropy: 2.1783528327941895 +[2025-04-30 14:26:24,337][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 2.897536516189575, cross_entropy: 2.897536516189575 +[2025-04-30 14:26:24,769][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.064631700515747, cross_entropy: 1.064631700515747 +[2025-04-30 14:26:27,793][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.019026756286621, cross_entropy: 3.019026756286621 +[2025-04-30 14:26:28,557][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.993298888206482, cross_entropy: 1.993298888206482 +[2025-04-30 14:26:31,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 2.858560800552368, cross_entropy: 2.858560800552368 +[2025-04-30 14:26:31,857][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.1537411212921143, cross_entropy: 2.1537411212921143 +[2025-04-30 14:26:34,958][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 3.1171422004699707, cross_entropy: 3.1171422004699707 +[2025-04-30 14:26:36,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.598451614379883, cross_entropy: 2.598451614379883 +[2025-04-30 14:26:38,278][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 2.621624708175659, cross_entropy: 2.621624708175659 +[2025-04-30 14:26:39,828][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 3.0775694847106934, cross_entropy: 3.0775694847106934 +[2025-04-30 14:26:42,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.484358310699463, cross_entropy: 2.484358310699463 +[2025-04-30 14:26:43,531][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 1.1829922199249268, cross_entropy: 1.1829922199249268 +[2025-04-30 14:26:46,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 1.457885503768921, cross_entropy: 1.457885503768921 +[2025-04-30 14:26:47,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 1.9962384700775146, cross_entropy: 1.9962384700775146 +[2025-04-30 14:26:51,002][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.3325252532958984, cross_entropy: 1.3325252532958984 +[2025-04-30 14:26:51,508][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.359300136566162, cross_entropy: 1.359300136566162 +[2025-04-30 14:26:54,375][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 1.3727327585220337, cross_entropy: 1.3727327585220337 +[2025-04-30 14:26:55,050][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.2144787311553955, cross_entropy: 1.2144787311553955 +[2025-04-30 14:26:58,146][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 0.8766571283340454, cross_entropy: 0.8766571283340454 +[2025-04-30 14:26:58,511][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.0451977252960205, cross_entropy: 1.0451977252960205 +[2025-04-30 14:27:01,792][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.882232666015625, cross_entropy: 2.882232666015625 +[2025-04-30 14:27:02,107][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 2.626857042312622, cross_entropy: 2.626857042312622 +[2025-04-30 14:27:05,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 1.4082937240600586, cross_entropy: 1.4082937240600586 +[2025-04-30 14:27:05,878][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 1.074114441871643, cross_entropy: 1.074114441871643 +[2025-04-30 14:27:09,535][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 1.4747648239135742, cross_entropy: 1.4747648239135742 +[2025-04-30 14:27:09,856][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 2.064696788787842, cross_entropy: 2.064696788787842 +[2025-04-30 14:27:13,355][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 1.8362709283828735, cross_entropy: 1.8362709283828735 +[2025-04-30 14:27:13,717][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 1.390267252922058, cross_entropy: 1.390267252922058 +[2025-04-30 14:27:17,812][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 3.3069331645965576, cross_entropy: 3.3069331645965576 +[2025-04-30 14:27:18,124][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 1.1203491687774658, cross_entropy: 1.1203491687774658 +[2025-04-30 14:27:21,627][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 2.7671189308166504, cross_entropy: 2.7671189308166504 +[2025-04-30 14:27:21,939][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.2774617671966553, cross_entropy: 1.2774617671966553 +[2025-04-30 14:27:25,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 2.174945831298828, cross_entropy: 2.174945831298828 +[2025-04-30 14:27:25,636][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 1.1706838607788086, cross_entropy: 1.1706838607788086 +[2025-04-30 14:27:29,165][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 1.4818174839019775, cross_entropy: 1.4818174839019775 +[2025-04-30 14:27:29,502][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 1.0683741569519043, cross_entropy: 1.0683741569519043 +[2025-04-30 14:27:33,234][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 1.8508638143539429, cross_entropy: 1.8508638143539429 +[2025-04-30 14:27:33,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.499700903892517, cross_entropy: 1.499700903892517 +[2025-04-30 14:27:36,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 1.833314061164856, cross_entropy: 1.833314061164856 +[2025-04-30 14:27:36,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 1.4446613788604736, cross_entropy: 1.4446613788604736 +[2025-04-30 14:27:40,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 3.3308212757110596, cross_entropy: 3.3308212757110596 +[2025-04-30 14:27:41,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 1.4020349979400635, cross_entropy: 1.4020349979400635 +[2025-04-30 14:27:43,898][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.552215576171875, cross_entropy: 2.552215576171875 +[2025-04-30 14:27:45,185][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 0.9914044141769409, cross_entropy: 0.9914044141769409 +[2025-04-30 14:27:47,290][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.4496338367462158, cross_entropy: 1.4496338367462158 +[2025-04-30 14:27:48,679][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 2.5292344093322754, cross_entropy: 2.5292344093322754 +[2025-04-30 14:27:51,925][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.902738332748413, cross_entropy: 2.902738332748413 +[2025-04-30 14:27:52,449][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 2.4858922958374023, cross_entropy: 2.4858922958374023 +[2025-04-30 14:27:54,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 3.292656421661377, cross_entropy: 3.292656421661377 +[2025-04-30 14:27:56,214][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 2.8025026321411133, cross_entropy: 2.8025026321411133 +[2025-04-30 14:27:58,657][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 1.0196239948272705, cross_entropy: 1.0196239948272705 +[2025-04-30 14:27:59,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 1.0206482410430908, cross_entropy: 1.0206482410430908 +[2025-04-30 14:28:01,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 0.962559700012207, cross_entropy: 0.962559700012207 +[2025-04-30 14:28:03,148][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.632570743560791, cross_entropy: 2.632570743560791 +[2025-04-30 14:28:05,438][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 2.018326759338379, cross_entropy: 2.018326759338379 +[2025-04-30 14:28:07,687][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.5168240070343018, cross_entropy: 1.5168240070343018 +[2025-04-30 14:28:08,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 1.5608899593353271, cross_entropy: 1.5608899593353271 +[2025-04-30 14:28:10,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 2.102783679962158, cross_entropy: 2.102783679962158 +[2025-04-30 14:28:12,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 2.9804253578186035, cross_entropy: 2.9804253578186035 +[2025-04-30 14:28:14,349][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 2.5560872554779053, cross_entropy: 2.5560872554779053 +[2025-04-30 14:28:15,728][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 1.2240753173828125, cross_entropy: 1.2240753173828125 +[2025-04-30 14:28:18,209][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 3.1028523445129395, cross_entropy: 3.1028523445129395 +[2025-04-30 14:28:20,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.306802272796631, cross_entropy: 3.306802272796631 +[2025-04-30 14:28:22,166][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 2.244037628173828, cross_entropy: 2.244037628173828 +[2025-04-30 14:28:24,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 1.1207311153411865, cross_entropy: 1.1207311153411865 +[2025-04-30 14:28:25,653][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 3.0134658813476562, cross_entropy: 3.0134658813476562 +[2025-04-30 14:28:28,999][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 2.174072742462158, cross_entropy: 2.174072742462158 +[2025-04-30 14:28:29,585][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 3.109764575958252, cross_entropy: 3.109764575958252 +[2025-04-30 14:28:34,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 3.0068881511688232, cross_entropy: 3.0068881511688232 +[2025-04-30 14:28:35,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.4365203380584717, cross_entropy: 1.4365203380584717 +[2025-04-30 14:28:38,225][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 1.438133955001831, cross_entropy: 1.438133955001831 +[2025-04-30 14:28:38,557][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 2.1005077362060547, cross_entropy: 2.1005077362060547 +[2025-04-30 14:28:42,217][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 1.797956109046936, cross_entropy: 1.797956109046936 +[2025-04-30 14:28:42,560][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.8903651237487793, cross_entropy: 2.8903651237487793 +[2025-04-30 14:28:46,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 2.218341112136841, cross_entropy: 2.218341112136841 +[2025-04-30 14:28:46,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 0.9629303812980652, cross_entropy: 0.9629303812980652 +[2025-04-30 14:28:51,576][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 2.0624685287475586, cross_entropy: 2.0624685287475586 +[2025-04-30 14:28:51,923][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.2348881959915161, cross_entropy: 1.2348881959915161 +[2025-04-30 14:28:55,439][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 2.246267795562744, cross_entropy: 2.246267795562744 +[2025-04-30 14:28:55,771][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 1.1218781471252441, cross_entropy: 1.1218781471252441 +[2025-04-30 14:28:58,892][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 1.5525637865066528, cross_entropy: 1.5525637865066528 +[2025-04-30 14:28:59,234][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 1.8129910230636597, cross_entropy: 1.8129910230636597 +[2025-04-30 14:29:02,904][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 1.8209319114685059, cross_entropy: 1.8209319114685059 +[2025-04-30 14:29:03,221][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 3.2999513149261475, cross_entropy: 3.2999513149261475 +[2025-04-30 14:29:06,465][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 1.6772651672363281, cross_entropy: 1.6772651672363281 +[2025-04-30 14:29:06,807][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 0.7190722227096558, cross_entropy: 0.7190722227096558 +[2025-04-30 14:29:10,239][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.0382695198059082, cross_entropy: 1.0382695198059082 +[2025-04-30 14:29:10,553][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 1.3573529720306396, cross_entropy: 1.3573529720306396 +[2025-04-30 14:29:13,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.6843101978302, cross_entropy: 2.6843101978302 +[2025-04-30 14:29:14,180][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 1.7389161586761475, cross_entropy: 1.7389161586761475 +[2025-04-30 14:29:17,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 3.0176544189453125, cross_entropy: 3.0176544189453125 +[2025-04-30 14:29:17,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3632913827896118, cross_entropy: 1.3632913827896118 +[2025-04-30 14:29:20,739][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 1.2628629207611084, cross_entropy: 1.2628629207611084 +[2025-04-30 14:29:21,054][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.171565532684326, cross_entropy: 2.171565532684326 +[2025-04-30 14:29:24,654][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 1.3357279300689697, cross_entropy: 1.3357279300689697 +[2025-04-30 14:29:24,990][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 2.35522723197937, cross_entropy: 2.35522723197937 +[2025-04-30 14:29:28,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 2.796837329864502, cross_entropy: 2.796837329864502 +[2025-04-30 14:29:28,898][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.1412873268127441, cross_entropy: 1.1412873268127441 +[2025-04-30 14:29:31,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 2.9256091117858887, cross_entropy: 2.9256091117858887 +[2025-04-30 14:29:32,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.538194179534912, cross_entropy: 1.538194179534912 +[2025-04-30 14:29:35,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 1.6375768184661865, cross_entropy: 1.6375768184661865 +[2025-04-30 14:29:36,087][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 1.417816400527954, cross_entropy: 1.417816400527954 +[2025-04-30 14:29:39,036][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 3.1269173622131348, cross_entropy: 3.1269173622131348 +[2025-04-30 14:29:39,373][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 1.9896451234817505, cross_entropy: 1.9896451234817505 +[2025-04-30 14:29:42,812][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 1.6694952249526978, cross_entropy: 1.6694952249526978 +[2025-04-30 14:29:43,192][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 1.220630407333374, cross_entropy: 1.220630407333374 +[2025-04-30 14:29:46,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 1.1185948848724365, cross_entropy: 1.1185948848724365 +[2025-04-30 14:29:47,020][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 2.907766342163086, cross_entropy: 2.907766342163086 +[2025-04-30 14:29:50,646][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 1.8174577951431274, cross_entropy: 1.8174577951431274 +[2025-04-30 14:29:50,962][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 2.380199432373047, cross_entropy: 2.380199432373047 +[2025-04-30 14:29:54,190][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 2.86368989944458, cross_entropy: 2.86368989944458 +[2025-04-30 14:29:54,505][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.8800103664398193, cross_entropy: 2.8800103664398193 +[2025-04-30 14:29:58,194][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 1.641495704650879, cross_entropy: 1.641495704650879 +[2025-04-30 14:29:58,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 3.095175266265869, cross_entropy: 3.095175266265869 +[2025-04-30 14:30:01,831][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.289175033569336, cross_entropy: 3.289175033569336 +[2025-04-30 14:30:02,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 2.1507763862609863, cross_entropy: 2.1507763862609863 +[2025-04-30 14:30:05,405][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.441171169281006, cross_entropy: 2.441171169281006 +[2025-04-30 14:30:05,784][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 2.4733498096466064, cross_entropy: 2.4733498096466064 +[2025-04-30 14:30:08,753][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.3258205652236938, cross_entropy: 1.3258205652236938 +[2025-04-30 14:30:09,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 2.0713839530944824, cross_entropy: 2.0713839530944824 +[2025-04-30 14:30:12,680][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 1.0930187702178955, cross_entropy: 1.0930187702178955 +[2025-04-30 14:30:12,993][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.1643433570861816, cross_entropy: 2.1643433570861816 +[2025-04-30 14:30:16,486][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.3589739799499512, cross_entropy: 1.3589739799499512 +[2025-04-30 14:30:16,818][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.680309772491455, cross_entropy: 1.680309772491455 +[2025-04-30 14:30:19,770][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 2.298255443572998, cross_entropy: 2.298255443572998 +[2025-04-30 14:30:20,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 2.818387031555176, cross_entropy: 2.818387031555176 +[2025-04-30 14:30:23,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.305262565612793, cross_entropy: 1.305262565612793 +[2025-04-30 14:30:23,886][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 0.957383394241333, cross_entropy: 0.957383394241333 +[2025-04-30 14:30:27,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 3.0775485038757324, cross_entropy: 3.0775485038757324 +[2025-04-30 14:30:27,645][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 0.8600053787231445, cross_entropy: 0.8600053787231445 +[2025-04-30 14:30:31,252][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 0.7820488214492798, cross_entropy: 0.7820488214492798 +[2025-04-30 14:30:31,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 0.675697386264801, cross_entropy: 0.675697386264801 +[2025-04-30 14:30:35,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 1.7239294052124023, cross_entropy: 1.7239294052124023 +[2025-04-30 14:30:35,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 3.049513101577759, cross_entropy: 3.049513101577759 +[2025-04-30 14:30:38,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 3.1128859519958496, cross_entropy: 3.1128859519958496 +[2025-04-30 14:30:38,918][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.550929069519043, cross_entropy: 1.550929069519043 +[2025-04-30 14:30:41,984][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.1587531566619873, cross_entropy: 1.1587531566619873 +[2025-04-30 14:30:42,323][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 0.901343584060669, cross_entropy: 0.901343584060669 +[2025-04-30 14:30:45,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.4775588512420654, cross_entropy: 2.4775588512420654 +[2025-04-30 14:30:45,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 2.0425219535827637, cross_entropy: 2.0425219535827637 +[2025-04-30 14:30:49,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.4940130710601807, cross_entropy: 1.4940130710601807 +[2025-04-30 14:30:50,230][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 1.4140996932983398, cross_entropy: 1.4140996932983398 +[2025-04-30 14:30:53,881][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.2284035682678223, cross_entropy: 3.2284035682678223 +[2025-04-30 14:30:54,226][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 1.4363596439361572, cross_entropy: 1.4363596439361572 +[2025-04-30 14:30:57,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 1.3921786546707153, cross_entropy: 1.3921786546707153 +[2025-04-30 14:30:57,700][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 1.4213213920593262, cross_entropy: 1.4213213920593262 +[2025-04-30 14:31:01,942][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 2.851106643676758, cross_entropy: 2.851106643676758 +[2025-04-30 14:31:02,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.3903567790985107, cross_entropy: 2.3903567790985107 +[2025-04-30 14:31:05,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 0.9463182687759399, cross_entropy: 0.9463182687759399 +[2025-04-30 14:31:05,782][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.3609527349472046, cross_entropy: 1.3609527349472046 +[2025-04-30 14:31:08,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 2.7741036415100098, cross_entropy: 2.7741036415100098 +[2025-04-30 14:31:09,041][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 2.885894775390625, cross_entropy: 2.885894775390625 +[2025-04-30 14:31:12,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 2.2115092277526855, cross_entropy: 2.2115092277526855 +[2025-04-30 14:31:12,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 3.190190315246582, cross_entropy: 3.190190315246582 +[2025-04-30 14:31:15,646][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 2.9990594387054443, cross_entropy: 2.9990594387054443 +[2025-04-30 14:31:15,959][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 2.903188943862915, cross_entropy: 2.903188943862915 +[2025-04-30 14:31:19,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 3.3165009021759033, cross_entropy: 3.3165009021759033 +[2025-04-30 14:31:19,436][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 1.5893473625183105, cross_entropy: 1.5893473625183105 +[2025-04-30 14:31:22,805][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 2.985874891281128, cross_entropy: 2.985874891281128 +[2025-04-30 14:31:23,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 1.3765639066696167, cross_entropy: 1.3765639066696167 +[2025-04-30 14:31:25,951][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 1.5013351440429688, cross_entropy: 1.5013351440429688 +[2025-04-30 14:31:26,265][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 1.5184509754180908, cross_entropy: 1.5184509754180908 +[2025-04-30 14:31:29,659][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 1.5836009979248047, cross_entropy: 1.5836009979248047 +[2025-04-30 14:31:29,993][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 1.1473240852355957, cross_entropy: 1.1473240852355957 +[2025-04-30 14:31:34,015][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 2.8190219402313232, cross_entropy: 2.8190219402313232 +[2025-04-30 14:31:34,368][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 2.340336322784424, cross_entropy: 2.340336322784424 +[2025-04-30 14:31:37,508][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 1.2111585140228271, cross_entropy: 1.2111585140228271 +[2025-04-30 14:31:37,852][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 0.9946301579475403, cross_entropy: 0.9946301579475403 +[2025-04-30 14:31:41,449][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 2.822396993637085, cross_entropy: 2.822396993637085 +[2025-04-30 14:31:41,798][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 1.1049067974090576, cross_entropy: 1.1049067974090576 +[2025-04-30 14:31:45,142][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.162812352180481, cross_entropy: 1.162812352180481 +[2025-04-30 14:31:45,493][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 1.8004584312438965, cross_entropy: 1.8004584312438965 +[2025-04-30 14:31:48,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 2.95589017868042, cross_entropy: 2.95589017868042 +[2025-04-30 14:31:49,225][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 2.3025689125061035, cross_entropy: 2.3025689125061035 +[2025-04-30 14:31:52,266][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 1.654427409172058, cross_entropy: 1.654427409172058 +[2025-04-30 14:31:52,580][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 1.3901731967926025, cross_entropy: 1.3901731967926025 +[2025-04-30 14:31:55,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 1.9314994812011719, cross_entropy: 1.9314994812011719 +[2025-04-30 14:31:56,174][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 2.5208632946014404, cross_entropy: 2.5208632946014404 +[2025-04-30 14:31:59,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.131953239440918, cross_entropy: 2.131953239440918 +[2025-04-30 14:31:59,887][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 3.1698522567749023, cross_entropy: 3.1698522567749023 +[2025-04-30 14:32:03,432][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 2.9542765617370605, cross_entropy: 2.9542765617370605 +[2025-04-30 14:32:03,774][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.962008476257324, cross_entropy: 2.962008476257324 +[2025-04-30 14:32:07,337][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.0431987047195435, cross_entropy: 1.0431987047195435 +[2025-04-30 14:32:07,673][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 0.8818690776824951, cross_entropy: 0.8818690776824951 +[2025-04-30 14:32:10,390][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 1.3744654655456543, cross_entropy: 1.3744654655456543 +[2025-04-30 14:32:10,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.9842565059661865, cross_entropy: 2.9842565059661865 +[2025-04-30 14:32:14,184][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 2.841648578643799, cross_entropy: 2.841648578643799 +[2025-04-30 14:32:14,524][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 3.2748284339904785, cross_entropy: 3.2748284339904785 +[2025-04-30 14:32:18,515][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.425969123840332, cross_entropy: 1.425969123840332 +[2025-04-30 14:32:18,851][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.7754031419754028, cross_entropy: 1.7754031419754028 +[2025-04-30 14:32:21,647][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 2.2912518978118896, cross_entropy: 2.2912518978118896 +[2025-04-30 14:32:21,960][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 1.9229952096939087, cross_entropy: 1.9229952096939087 +[2025-04-30 14:32:25,012][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.0904135704040527, cross_entropy: 1.0904135704040527 +[2025-04-30 14:32:25,350][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 1.7581963539123535, cross_entropy: 1.7581963539123535 +[2025-04-30 14:32:28,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.8236098289489746, cross_entropy: 2.8236098289489746 +[2025-04-30 14:32:29,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 3.3652424812316895, cross_entropy: 3.3652424812316895 +[2025-04-30 14:32:32,470][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.246192455291748, cross_entropy: 2.246192455291748 +[2025-04-30 14:32:32,783][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 1.817354679107666, cross_entropy: 1.817354679107666 +[2025-04-30 14:32:36,074][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 1.9552470445632935, cross_entropy: 1.9552470445632935 +[2025-04-30 14:32:36,413][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 1.1366865634918213, cross_entropy: 1.1366865634918213 +[2025-04-30 14:32:40,137][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 1.126502275466919, cross_entropy: 1.126502275466919 +[2025-04-30 14:32:40,478][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 2.86897611618042, cross_entropy: 2.86897611618042 +[2025-04-30 14:32:43,747][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.1538152694702148, cross_entropy: 1.1538152694702148 +[2025-04-30 14:32:44,080][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 2.075910806655884, cross_entropy: 2.075910806655884 +[2025-04-30 14:32:47,451][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 0.9130983352661133, cross_entropy: 0.9130983352661133 +[2025-04-30 14:32:47,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.7862964868545532, cross_entropy: 1.7862964868545532 +[2025-04-30 14:32:51,236][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 3.530482769012451, cross_entropy: 3.530482769012451 +[2025-04-30 14:32:51,582][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 0.9903450608253479, cross_entropy: 0.9903450608253479 +[2025-04-30 14:32:54,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 3.142590045928955, cross_entropy: 3.142590045928955 +[2025-04-30 14:32:55,038][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 1.605393409729004, cross_entropy: 1.605393409729004 +[2025-04-30 14:32:58,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.58107590675354, cross_entropy: 2.58107590675354 +[2025-04-30 14:32:58,479][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 2.1848347187042236, cross_entropy: 2.1848347187042236 +[2025-04-30 14:33:01,979][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 1.39118230342865, cross_entropy: 1.39118230342865 +[2025-04-30 14:33:02,291][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.2296512126922607, cross_entropy: 3.2296512126922607 +[2025-04-30 14:33:05,584][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.690598964691162, cross_entropy: 2.690598964691162 +[2025-04-30 14:33:05,923][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 1.2854433059692383, cross_entropy: 1.2854433059692383 +[2025-04-30 14:33:09,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 1.355818510055542, cross_entropy: 1.355818510055542 +[2025-04-30 14:33:09,786][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 1.731619119644165, cross_entropy: 1.731619119644165 +[2025-04-30 14:33:13,191][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 1.394660234451294, cross_entropy: 1.394660234451294 +[2025-04-30 14:33:13,521][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 1.7722556591033936, cross_entropy: 1.7722556591033936 +[2025-04-30 14:33:16,804][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 1.3452011346817017, cross_entropy: 1.3452011346817017 +[2025-04-30 14:33:17,117][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.5319695472717285, cross_entropy: 2.5319695472717285 +[2025-04-30 14:33:20,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.5442755222320557, cross_entropy: 1.5442755222320557 +[2025-04-30 14:33:20,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 2.1510937213897705, cross_entropy: 2.1510937213897705 +[2025-04-30 14:33:24,247][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 2.417530059814453, cross_entropy: 2.417530059814453 +[2025-04-30 14:33:24,584][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.993359088897705, cross_entropy: 2.993359088897705 +[2025-04-30 14:33:27,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 1.5995811223983765, cross_entropy: 1.5995811223983765 +[2025-04-30 14:33:27,837][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 2.3318381309509277, cross_entropy: 2.3318381309509277 +[2025-04-30 14:33:31,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 3.0494699478149414, cross_entropy: 3.0494699478149414 +[2025-04-30 14:33:31,461][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 1.7172918319702148, cross_entropy: 1.7172918319702148 +[2025-04-30 14:33:34,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.4485303163528442, cross_entropy: 1.4485303163528442 +[2025-04-30 14:33:35,383][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 1.5088245868682861, cross_entropy: 1.5088245868682861 +[2025-04-30 14:33:38,746][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 2.835123300552368, cross_entropy: 2.835123300552368 +[2025-04-30 14:33:39,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 1.0043599605560303, cross_entropy: 1.0043599605560303 +[2025-04-30 14:33:44,043][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 2.158008575439453, cross_entropy: 2.158008575439453 +[2025-04-30 14:33:44,381][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 3.0290136337280273, cross_entropy: 3.0290136337280273 +[2025-04-30 14:33:47,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 0.8926262855529785, cross_entropy: 0.8926262855529785 +[2025-04-30 14:33:47,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 1.983721137046814, cross_entropy: 1.983721137046814 +[2025-04-30 14:33:51,030][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 1.1096891164779663, cross_entropy: 1.1096891164779663 +[2025-04-30 14:33:51,345][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.3322428464889526, cross_entropy: 1.3322428464889526 +[2025-04-30 14:33:54,578][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 3.354292869567871, cross_entropy: 3.354292869567871 +[2025-04-30 14:33:54,899][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 1.5343915224075317, cross_entropy: 1.5343915224075317 +[2025-04-30 14:33:57,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 1.0876860618591309, cross_entropy: 1.0876860618591309 +[2025-04-30 14:33:58,279][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.331101179122925, cross_entropy: 3.331101179122925 +[2025-04-30 14:34:01,909][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.821306586265564, cross_entropy: 1.821306586265564 +[2025-04-30 14:34:02,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.8536972999572754, cross_entropy: 2.8536972999572754 +[2025-04-30 14:34:05,306][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 2.4669504165649414, cross_entropy: 2.4669504165649414 +[2025-04-30 14:34:05,647][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 1.9186562299728394, cross_entropy: 1.9186562299728394 +[2025-04-30 14:34:08,874][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 1.3675609827041626, cross_entropy: 1.3675609827041626 +[2025-04-30 14:34:09,213][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 1.5915374755859375, cross_entropy: 1.5915374755859375 +[2025-04-30 14:34:12,571][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 0.9250578880310059, cross_entropy: 0.9250578880310059 +[2025-04-30 14:34:12,907][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 1.145709753036499, cross_entropy: 1.145709753036499 +[2025-04-30 14:34:16,734][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.1048367023468018, cross_entropy: 1.1048367023468018 +[2025-04-30 14:34:17,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 3.1721384525299072, cross_entropy: 3.1721384525299072 +[2025-04-30 14:34:21,018][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 3.0289082527160645, cross_entropy: 3.0289082527160645 +[2025-04-30 14:34:21,359][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 1.852418303489685, cross_entropy: 1.852418303489685 +[2025-04-30 14:34:25,192][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.363255262374878, cross_entropy: 3.363255262374878 +[2025-04-30 14:34:25,514][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 2.971900701522827, cross_entropy: 2.971900701522827 +[2025-04-30 14:34:29,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 2.7708687782287598, cross_entropy: 2.7708687782287598 +[2025-04-30 14:34:29,449][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.3874359130859375, cross_entropy: 3.3874359130859375 +[2025-04-30 14:34:33,529][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 2.3423211574554443, cross_entropy: 2.3423211574554443 +[2025-04-30 14:34:33,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.2539634704589844, cross_entropy: 1.2539634704589844 +[2025-04-30 14:34:37,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 0.6850122213363647, cross_entropy: 0.6850122213363647 +[2025-04-30 14:34:37,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 1.6405236721038818, cross_entropy: 1.6405236721038818 +[2025-04-30 14:34:40,981][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 1.1328904628753662, cross_entropy: 1.1328904628753662 +[2025-04-30 14:34:41,295][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 2.918084144592285, cross_entropy: 2.918084144592285 +[2025-04-30 14:34:44,783][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 2.7793092727661133, cross_entropy: 2.7793092727661133 +[2025-04-30 14:34:45,126][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.851763367652893, cross_entropy: 1.851763367652893 +[2025-04-30 14:34:49,459][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 2.16886830329895, cross_entropy: 2.16886830329895 +[2025-04-30 14:34:49,783][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.719963550567627, cross_entropy: 2.719963550567627 +[2025-04-30 14:34:53,168][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 1.4570256471633911, cross_entropy: 1.4570256471633911 +[2025-04-30 14:34:53,484][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 1.6952548027038574, cross_entropy: 1.6952548027038574 +[2025-04-30 14:34:56,440][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 2.9067816734313965, cross_entropy: 2.9067816734313965 +[2025-04-30 14:34:56,752][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 2.5340893268585205, cross_entropy: 2.5340893268585205 +[2025-04-30 14:34:59,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 1.466991662979126, cross_entropy: 1.466991662979126 +[2025-04-30 14:34:59,876][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 1.8617945909500122, cross_entropy: 1.8617945909500122 +[2025-04-30 14:35:03,536][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 2.7057580947875977, cross_entropy: 2.7057580947875977 +[2025-04-30 14:35:03,866][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 3.2005529403686523, cross_entropy: 3.2005529403686523 +[2025-04-30 14:35:07,074][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 3.135222911834717, cross_entropy: 3.135222911834717 +[2025-04-30 14:35:07,412][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 3.0498805046081543, cross_entropy: 3.0498805046081543 +[2025-04-30 14:35:10,482][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 1.0022947788238525, cross_entropy: 1.0022947788238525 +[2025-04-30 14:35:10,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 1.0245976448059082, cross_entropy: 1.0245976448059082 +[2025-04-30 14:35:13,912][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 1.055251121520996, cross_entropy: 1.055251121520996 +[2025-04-30 14:35:14,225][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 1.5014398097991943, cross_entropy: 1.5014398097991943 +[2025-04-30 14:35:18,557][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 1.8444409370422363, cross_entropy: 1.8444409370422363 +[2025-04-30 14:35:18,871][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 1.4218858480453491, cross_entropy: 1.4218858480453491 +[2025-04-30 14:35:22,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 1.1276800632476807, cross_entropy: 1.1276800632476807 +[2025-04-30 14:35:23,011][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 2.799265146255493, cross_entropy: 2.799265146255493 +[2025-04-30 14:35:25,817][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 2.2260522842407227, cross_entropy: 2.2260522842407227 +[2025-04-30 14:35:26,132][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.573338508605957, cross_entropy: 1.573338508605957 +[2025-04-30 14:35:29,475][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 2.047114849090576, cross_entropy: 2.047114849090576 +[2025-04-30 14:35:29,789][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.280698299407959, cross_entropy: 2.280698299407959 +[2025-04-30 14:35:32,795][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 2.070309638977051, cross_entropy: 2.070309638977051 +[2025-04-30 14:35:33,128][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.092991352081299, cross_entropy: 3.092991352081299 +[2025-04-30 14:35:36,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 1.129936933517456, cross_entropy: 1.129936933517456 +[2025-04-30 14:35:37,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 1.2805674076080322, cross_entropy: 1.2805674076080322 +[2025-04-30 14:35:39,642][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.7909862995147705, cross_entropy: 2.7909862995147705 +[2025-04-30 14:35:40,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.2133557796478271, cross_entropy: 1.2133557796478271 +[2025-04-30 14:35:43,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 2.4742074012756348, cross_entropy: 2.4742074012756348 +[2025-04-30 14:35:44,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.8155698776245117, cross_entropy: 1.8155698776245117 +[2025-04-30 14:35:47,083][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 1.3706556558609009, cross_entropy: 1.3706556558609009 +[2025-04-30 14:35:47,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 3.116872787475586, cross_entropy: 3.116872787475586 +[2025-04-30 14:35:51,181][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 2.726253032684326, cross_entropy: 2.726253032684326 +[2025-04-30 14:35:51,911][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 2.6880226135253906, cross_entropy: 2.6880226135253906 +[2025-04-30 14:35:54,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.470561146736145, cross_entropy: 1.470561146736145 +[2025-04-30 14:35:56,172][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 1.0531525611877441, cross_entropy: 1.0531525611877441 +[2025-04-30 14:35:58,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.3120157718658447, cross_entropy: 1.3120157718658447 +[2025-04-30 14:35:59,416][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.780172348022461, cross_entropy: 2.780172348022461 +[2025-04-30 14:36:01,902][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 3.189624309539795, cross_entropy: 3.189624309539795 +[2025-04-30 14:36:03,309][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.2610371112823486, cross_entropy: 1.2610371112823486 +[2025-04-30 14:36:05,433][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 1.1986006498336792, cross_entropy: 1.1986006498336792 +[2025-04-30 14:36:07,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 2.0354628562927246, cross_entropy: 2.0354628562927246 +[2025-04-30 14:36:09,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.108464241027832, cross_entropy: 1.108464241027832 +[2025-04-30 14:36:10,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 1.4508869647979736, cross_entropy: 1.4508869647979736 +[2025-04-30 14:36:13,199][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.3534270524978638, cross_entropy: 1.3534270524978638 +[2025-04-30 14:36:13,752][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 2.0184237957000732, cross_entropy: 2.0184237957000732 +[2025-04-30 14:36:16,974][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 1.172642469406128, cross_entropy: 1.172642469406128 +[2025-04-30 14:36:17,311][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.2308707237243652, cross_entropy: 2.2308707237243652 +[2025-04-30 14:36:20,906][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 1.789899230003357, cross_entropy: 1.789899230003357 +[2025-04-30 14:36:21,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 2.157425880432129, cross_entropy: 2.157425880432129 +[2025-04-30 14:36:25,071][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.419698715209961, cross_entropy: 3.419698715209961 +[2025-04-30 14:36:25,407][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 3.3667707443237305, cross_entropy: 3.3667707443237305 +[2025-04-30 14:36:28,853][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 1.579695463180542, cross_entropy: 1.579695463180542 +[2025-04-30 14:36:29,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.1282005310058594, cross_entropy: 2.1282005310058594 +[2025-04-30 14:36:32,206][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.9261775016784668, cross_entropy: 1.9261775016784668 +[2025-04-30 14:36:32,548][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 2.0534400939941406, cross_entropy: 2.0534400939941406 +[2025-04-30 14:36:35,482][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.710988163948059, cross_entropy: 1.710988163948059 +[2025-04-30 14:36:35,796][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 3.0288033485412598, cross_entropy: 3.0288033485412598 +[2025-04-30 14:36:38,894][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 2.926168918609619, cross_entropy: 2.926168918609619 +[2025-04-30 14:36:39,231][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.677135944366455, cross_entropy: 2.677135944366455 +[2025-04-30 14:36:42,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 2.3209900856018066, cross_entropy: 2.3209900856018066 +[2025-04-30 14:36:43,375][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 1.215147614479065, cross_entropy: 1.215147614479065 +[2025-04-30 14:36:46,654][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.4239511489868164, cross_entropy: 2.4239511489868164 +[2025-04-30 14:36:47,696][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 1.348356008529663, cross_entropy: 1.348356008529663 +[2025-04-30 14:36:50,356][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 3.3712775707244873, cross_entropy: 3.3712775707244873 +[2025-04-30 14:36:51,322][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 1.063414454460144, cross_entropy: 1.063414454460144 +[2025-04-30 14:36:54,236][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 2.2871975898742676, cross_entropy: 2.2871975898742676 +[2025-04-30 14:36:55,882][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.5493345260620117, cross_entropy: 1.5493345260620117 +[2025-04-30 14:36:58,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 1.0054471492767334, cross_entropy: 1.0054471492767334 +[2025-04-30 14:36:59,734][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 2.001026153564453, cross_entropy: 2.001026153564453 +[2025-04-30 14:37:02,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.3350427150726318, cross_entropy: 1.3350427150726318 +[2025-04-30 14:37:03,122][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 1.5269145965576172, cross_entropy: 1.5269145965576172 +[2025-04-30 14:37:06,281][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 2.496877670288086, cross_entropy: 2.496877670288086 +[2025-04-30 14:37:06,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 1.3211214542388916, cross_entropy: 1.3211214542388916 +[2025-04-30 14:37:10,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.0773143768310547, cross_entropy: 1.0773143768310547 +[2025-04-30 14:37:10,881][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 1.33766508102417, cross_entropy: 1.33766508102417 +[2025-04-30 14:37:13,825][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 1.1082870960235596, cross_entropy: 1.1082870960235596 +[2025-04-30 14:37:14,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.3910152912139893, cross_entropy: 1.3910152912139893 +[2025-04-30 14:40:03,345][BaseTrainer][INFO] - [Epoch 5/10] (train) 1.9918923377990723, cross_entropy: 1.9918923377990723 +[2025-04-30 14:40:03,346][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.2519006729125977, cross_entropy: 1.2519006729125977 +[2025-04-30 14:40:03,346][BaseTrainer][INFO] - [Epoch 5/10] (metrics) roc_auc: 0.9783334732055664 +[2025-04-30 14:40:03,568][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 14:40:03,794][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch5.pth. +[2025-04-30 14:40:04,037][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 14:40:08,550][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 0.6802226305007935, cross_entropy: 0.6802226305007935 +[2025-04-30 14:40:08,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.4145392179489136, cross_entropy: 1.4145392179489136 +[2025-04-30 14:40:11,742][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 2.892350435256958, cross_entropy: 2.892350435256958 +[2025-04-30 14:40:12,103][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 2.7142350673675537, cross_entropy: 2.7142350673675537 +[2025-04-30 14:40:14,961][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 2.0293941497802734, cross_entropy: 2.0293941497802734 +[2025-04-30 14:40:15,301][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 2.91865873336792, cross_entropy: 2.91865873336792 +[2025-04-30 14:40:18,379][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 2.5970866680145264, cross_entropy: 2.5970866680145264 +[2025-04-30 14:40:19,601][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 1.220081090927124, cross_entropy: 1.220081090927124 +[2025-04-30 14:40:22,217][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.5958900451660156, cross_entropy: 1.5958900451660156 +[2025-04-30 14:40:22,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 2.0885214805603027, cross_entropy: 2.0885214805603027 +[2025-04-30 14:40:26,093][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.3813140392303467, cross_entropy: 2.3813140392303467 +[2025-04-30 14:40:26,659][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 2.049924612045288, cross_entropy: 2.049924612045288 +[2025-04-30 14:40:28,884][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 3.1087646484375, cross_entropy: 3.1087646484375 +[2025-04-30 14:40:30,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 1.6928396224975586, cross_entropy: 1.6928396224975586 +[2025-04-30 14:40:32,166][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 0.871188759803772, cross_entropy: 0.871188759803772 +[2025-04-30 14:40:33,981][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 2.3415627479553223, cross_entropy: 2.3415627479553223 +[2025-04-30 14:40:35,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 1.0439037084579468, cross_entropy: 1.0439037084579468 +[2025-04-30 14:40:37,979][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 3.1258702278137207, cross_entropy: 3.1258702278137207 +[2025-04-30 14:40:39,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.0027968883514404, cross_entropy: 1.0027968883514404 +[2025-04-30 14:40:41,407][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 3.135105609893799, cross_entropy: 3.135105609893799 +[2025-04-30 14:40:43,493][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 1.7883570194244385, cross_entropy: 1.7883570194244385 +[2025-04-30 14:40:44,865][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.1766053438186646, cross_entropy: 1.1766053438186646 +[2025-04-30 14:40:47,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 1.0689094066619873, cross_entropy: 1.0689094066619873 +[2025-04-30 14:40:48,275][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.389528751373291, cross_entropy: 2.389528751373291 +[2025-04-30 14:40:50,757][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 0.9951426982879639, cross_entropy: 0.9951426982879639 +[2025-04-30 14:40:51,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 2.0156869888305664, cross_entropy: 2.0156869888305664 +[2025-04-30 14:40:54,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 0.9644707441329956, cross_entropy: 0.9644707441329956 +[2025-04-30 14:40:55,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.209587812423706, cross_entropy: 2.209587812423706 +[2025-04-30 14:40:57,299][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 1.639564037322998, cross_entropy: 1.639564037322998 +[2025-04-30 14:40:58,909][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 0.9832007884979248, cross_entropy: 0.9832007884979248 +[2025-04-30 14:41:00,727][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 0.9635220766067505, cross_entropy: 0.9635220766067505 +[2025-04-30 14:41:02,901][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.6374778747558594, cross_entropy: 2.6374778747558594 +[2025-04-30 14:41:04,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 1.6764938831329346, cross_entropy: 1.6764938831329346 +[2025-04-30 14:41:06,564][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 2.809281826019287, cross_entropy: 2.809281826019287 +[2025-04-30 14:41:07,898][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 2.956230640411377, cross_entropy: 2.956230640411377 +[2025-04-30 14:41:10,948][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 1.166056752204895, cross_entropy: 1.166056752204895 +[2025-04-30 14:41:12,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.0592559576034546, cross_entropy: 1.0592559576034546 +[2025-04-30 14:41:14,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 2.7705297470092773, cross_entropy: 2.7705297470092773 +[2025-04-30 14:41:15,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 2.47469425201416, cross_entropy: 2.47469425201416 +[2025-04-30 14:41:18,246][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.498168706893921, cross_entropy: 1.498168706893921 +[2025-04-30 14:41:18,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 3.3227128982543945, cross_entropy: 3.3227128982543945 +[2025-04-30 14:41:21,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.657897710800171, cross_entropy: 2.657897710800171 +[2025-04-30 14:41:22,593][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.1672545671463013, cross_entropy: 1.1672545671463013 +[2025-04-30 14:41:25,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 2.630983829498291, cross_entropy: 2.630983829498291 +[2025-04-30 14:41:26,339][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 1.0469211339950562, cross_entropy: 1.0469211339950562 +[2025-04-30 14:41:28,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.2234885692596436, cross_entropy: 2.2234885692596436 +[2025-04-30 14:41:29,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.913649320602417, cross_entropy: 2.913649320602417 +[2025-04-30 14:41:32,241][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 3.298471212387085, cross_entropy: 3.298471212387085 +[2025-04-30 14:41:33,106][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 1.4272462129592896, cross_entropy: 1.4272462129592896 +[2025-04-30 14:41:35,935][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 1.7620041370391846, cross_entropy: 1.7620041370391846 +[2025-04-30 14:41:36,377][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 3.1775453090667725, cross_entropy: 3.1775453090667725 +[2025-04-30 14:41:39,525][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 2.9464731216430664, cross_entropy: 2.9464731216430664 +[2025-04-30 14:41:39,920][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 2.486671209335327, cross_entropy: 2.486671209335327 +[2025-04-30 14:41:43,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 0.8808041214942932, cross_entropy: 0.8808041214942932 +[2025-04-30 14:41:44,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.2337250709533691, cross_entropy: 1.2337250709533691 +[2025-04-30 14:41:47,099][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 0.7677634954452515, cross_entropy: 0.7677634954452515 +[2025-04-30 14:41:47,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 2.3490710258483887, cross_entropy: 2.3490710258483887 +[2025-04-30 14:41:50,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.3656176328659058, cross_entropy: 1.3656176328659058 +[2025-04-30 14:41:50,973][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 2.033414602279663, cross_entropy: 2.033414602279663 +[2025-04-30 14:41:53,823][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.289670705795288, cross_entropy: 2.289670705795288 +[2025-04-30 14:41:54,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 1.9294896125793457, cross_entropy: 1.9294896125793457 +[2025-04-30 14:41:57,979][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 2.3249270915985107, cross_entropy: 2.3249270915985107 +[2025-04-30 14:41:58,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 1.459876298904419, cross_entropy: 1.459876298904419 +[2025-04-30 14:42:01,165][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 1.6829286813735962, cross_entropy: 1.6829286813735962 +[2025-04-30 14:42:01,501][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 1.0395675897598267, cross_entropy: 1.0395675897598267 +[2025-04-30 14:42:04,809][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.6488518714904785, cross_entropy: 2.6488518714904785 +[2025-04-30 14:42:05,142][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 0.9444396495819092, cross_entropy: 0.9444396495819092 +[2025-04-30 14:42:08,025][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.054755687713623, cross_entropy: 1.054755687713623 +[2025-04-30 14:42:08,354][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 1.0169525146484375, cross_entropy: 1.0169525146484375 +[2025-04-30 14:42:11,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.3351716995239258, cross_entropy: 1.3351716995239258 +[2025-04-30 14:42:12,644][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 0.9365753531455994, cross_entropy: 0.9365753531455994 +[2025-04-30 14:42:14,963][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.3457460403442383, cross_entropy: 1.3457460403442383 +[2025-04-30 14:42:17,410][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 2.857013702392578, cross_entropy: 2.857013702392578 +[2025-04-30 14:42:18,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 0.8509974479675293, cross_entropy: 0.8509974479675293 +[2025-04-30 14:42:22,080][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 1.003985047340393, cross_entropy: 1.003985047340393 +[2025-04-30 14:42:22,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.3385140895843506, cross_entropy: 1.3385140895843506 +[2025-04-30 14:42:25,504][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 1.5979583263397217, cross_entropy: 1.5979583263397217 +[2025-04-30 14:42:25,923][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 2.7602663040161133, cross_entropy: 2.7602663040161133 +[2025-04-30 14:42:29,235][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 2.011650323867798, cross_entropy: 2.011650323867798 +[2025-04-30 14:42:29,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 3.0269176959991455, cross_entropy: 3.0269176959991455 +[2025-04-30 14:42:33,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 2.57073974609375, cross_entropy: 2.57073974609375 +[2025-04-30 14:42:33,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 2.1002016067504883, cross_entropy: 2.1002016067504883 +[2025-04-30 14:42:36,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 3.1023921966552734, cross_entropy: 3.1023921966552734 +[2025-04-30 14:42:37,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.391311764717102, cross_entropy: 1.391311764717102 +[2025-04-30 14:42:40,453][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 1.7287100553512573, cross_entropy: 1.7287100553512573 +[2025-04-30 14:42:40,790][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 1.8415117263793945, cross_entropy: 1.8415117263793945 +[2025-04-30 14:42:43,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 1.1483845710754395, cross_entropy: 1.1483845710754395 +[2025-04-30 14:42:44,235][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 2.2522025108337402, cross_entropy: 2.2522025108337402 +[2025-04-30 14:42:47,835][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.1362907886505127, cross_entropy: 1.1362907886505127 +[2025-04-30 14:42:48,167][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 0.8691796064376831, cross_entropy: 0.8691796064376831 +[2025-04-30 14:42:51,970][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 2.8005337715148926, cross_entropy: 2.8005337715148926 +[2025-04-30 14:42:52,307][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.199059247970581, cross_entropy: 1.199059247970581 +[2025-04-30 14:42:56,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.5579469203948975, cross_entropy: 1.5579469203948975 +[2025-04-30 14:42:56,533][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.1701371669769287, cross_entropy: 2.1701371669769287 +[2025-04-30 14:42:59,754][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 1.7885408401489258, cross_entropy: 1.7885408401489258 +[2025-04-30 14:43:00,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 0.9919620752334595, cross_entropy: 0.9919620752334595 +[2025-04-30 14:43:03,110][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 2.877012252807617, cross_entropy: 2.877012252807617 +[2025-04-30 14:43:03,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 1.9106523990631104, cross_entropy: 1.9106523990631104 +[2025-04-30 14:43:06,156][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.565201759338379, cross_entropy: 1.565201759338379 +[2025-04-30 14:43:06,485][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.0546408891677856, cross_entropy: 1.0546408891677856 +[2025-04-30 14:43:09,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.264890193939209, cross_entropy: 1.264890193939209 +[2025-04-30 14:43:09,926][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 2.0797553062438965, cross_entropy: 2.0797553062438965 +[2025-04-30 14:43:13,066][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 3.091121196746826, cross_entropy: 3.091121196746826 +[2025-04-30 14:43:13,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 0.9690629243850708, cross_entropy: 0.9690629243850708 +[2025-04-30 14:43:16,315][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 0.961578369140625, cross_entropy: 0.961578369140625 +[2025-04-30 14:43:16,651][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 2.115239143371582, cross_entropy: 2.115239143371582 +[2025-04-30 14:43:20,842][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.978484630584717, cross_entropy: 2.978484630584717 +[2025-04-30 14:43:21,155][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.7845180034637451, cross_entropy: 1.7845180034637451 +[2025-04-30 14:43:24,836][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.8941237926483154, cross_entropy: 1.8941237926483154 +[2025-04-30 14:43:25,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.7117094993591309, cross_entropy: 1.7117094993591309 +[2025-04-30 14:43:28,547][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.026339054107666, cross_entropy: 1.026339054107666 +[2025-04-30 14:43:28,885][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.2155609130859375, cross_entropy: 1.2155609130859375 +[2025-04-30 14:43:32,448][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 1.5224907398223877, cross_entropy: 1.5224907398223877 +[2025-04-30 14:43:32,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 1.3906561136245728, cross_entropy: 1.3906561136245728 +[2025-04-30 14:43:36,263][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.6965246200561523, cross_entropy: 2.6965246200561523 +[2025-04-30 14:43:36,600][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 1.7048258781433105, cross_entropy: 1.7048258781433105 +[2025-04-30 14:43:39,677][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.8081505298614502, cross_entropy: 1.8081505298614502 +[2025-04-30 14:43:39,989][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 2.9241347312927246, cross_entropy: 2.9241347312927246 +[2025-04-30 14:43:42,985][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 3.2833633422851562, cross_entropy: 3.2833633422851562 +[2025-04-30 14:43:43,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.1546739339828491, cross_entropy: 1.1546739339828491 +[2025-04-30 14:43:46,623][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 2.723874568939209, cross_entropy: 2.723874568939209 +[2025-04-30 14:43:46,937][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 2.1171607971191406, cross_entropy: 2.1171607971191406 +[2025-04-30 14:43:50,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.0845701694488525, cross_entropy: 1.0845701694488525 +[2025-04-30 14:43:50,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 1.5178710222244263, cross_entropy: 1.5178710222244263 +[2025-04-30 14:43:53,477][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.4119625091552734, cross_entropy: 1.4119625091552734 +[2025-04-30 14:43:53,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 2.1105618476867676, cross_entropy: 2.1105618476867676 +[2025-04-30 14:43:57,446][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 1.6876879930496216, cross_entropy: 1.6876879930496216 +[2025-04-30 14:43:57,775][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 2.9634451866149902, cross_entropy: 2.9634451866149902 +[2025-04-30 14:44:01,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 0.9323910474777222, cross_entropy: 0.9323910474777222 +[2025-04-30 14:44:01,724][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 2.9329028129577637, cross_entropy: 2.9329028129577637 +[2025-04-30 14:44:04,479][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.9730446338653564, cross_entropy: 2.9730446338653564 +[2025-04-30 14:44:04,809][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.846203327178955, cross_entropy: 1.846203327178955 +[2025-04-30 14:44:07,381][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 3.000217914581299, cross_entropy: 3.000217914581299 +[2025-04-30 14:44:07,742][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.2068746089935303, cross_entropy: 3.2068746089935303 +[2025-04-30 14:44:10,902][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 3.3596394062042236, cross_entropy: 3.3596394062042236 +[2025-04-30 14:44:11,402][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 3.1168594360351562, cross_entropy: 3.1168594360351562 +[2025-04-30 14:44:14,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 1.3340089321136475, cross_entropy: 1.3340089321136475 +[2025-04-30 14:44:15,617][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.529981255531311, cross_entropy: 1.529981255531311 +[2025-04-30 14:44:18,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 1.7526590824127197, cross_entropy: 1.7526590824127197 +[2025-04-30 14:44:19,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 2.9063057899475098, cross_entropy: 2.9063057899475098 +[2025-04-30 14:44:22,603][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 1.3955118656158447, cross_entropy: 1.3955118656158447 +[2025-04-30 14:44:23,475][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 1.1871755123138428, cross_entropy: 1.1871755123138428 +[2025-04-30 14:44:26,563][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 1.1196045875549316, cross_entropy: 1.1196045875549316 +[2025-04-30 14:44:27,065][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 3.2179765701293945, cross_entropy: 3.2179765701293945 +[2025-04-30 14:44:29,868][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.571101427078247, cross_entropy: 1.571101427078247 +[2025-04-30 14:44:30,227][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.2961649894714355, cross_entropy: 1.2961649894714355 +[2025-04-30 14:44:33,379][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 1.9915428161621094, cross_entropy: 1.9915428161621094 +[2025-04-30 14:44:33,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 1.0460184812545776, cross_entropy: 1.0460184812545776 +[2025-04-30 14:44:36,923][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 3.1550381183624268, cross_entropy: 3.1550381183624268 +[2025-04-30 14:44:37,254][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 2.7910008430480957, cross_entropy: 2.7910008430480957 +[2025-04-30 14:44:40,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 1.4852490425109863, cross_entropy: 1.4852490425109863 +[2025-04-30 14:44:40,633][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.8453826904296875, cross_entropy: 2.8453826904296875 +[2025-04-30 14:44:44,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 0.8841338157653809, cross_entropy: 0.8841338157653809 +[2025-04-30 14:44:44,345][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.4433616399765015, cross_entropy: 1.4433616399765015 +[2025-04-30 14:44:47,327][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.4088077545166016, cross_entropy: 1.4088077545166016 +[2025-04-30 14:44:47,705][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.2991552352905273, cross_entropy: 1.2991552352905273 +[2025-04-30 14:44:51,041][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 2.041992664337158, cross_entropy: 2.041992664337158 +[2025-04-30 14:44:51,381][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.6140365600585938, cross_entropy: 2.6140365600585938 +[2025-04-30 14:44:54,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.4151694774627686, cross_entropy: 1.4151694774627686 +[2025-04-30 14:44:54,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.3377655744552612, cross_entropy: 1.3377655744552612 +[2025-04-30 14:44:58,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 0.9052122831344604, cross_entropy: 0.9052122831344604 +[2025-04-30 14:44:58,843][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 1.1160385608673096, cross_entropy: 1.1160385608673096 +[2025-04-30 14:45:02,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 2.4467852115631104, cross_entropy: 2.4467852115631104 +[2025-04-30 14:45:02,600][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 1.015160083770752, cross_entropy: 1.015160083770752 +[2025-04-30 14:45:05,557][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 1.3148765563964844, cross_entropy: 1.3148765563964844 +[2025-04-30 14:45:05,893][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 1.8714017868041992, cross_entropy: 1.8714017868041992 +[2025-04-30 14:45:08,999][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 2.8643016815185547, cross_entropy: 2.8643016815185547 +[2025-04-30 14:45:09,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.8790804147720337, cross_entropy: 1.8790804147720337 +[2025-04-30 14:45:12,448][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 2.7978575229644775, cross_entropy: 2.7978575229644775 +[2025-04-30 14:45:12,784][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 2.514941692352295, cross_entropy: 2.514941692352295 +[2025-04-30 14:45:15,474][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 2.470348358154297, cross_entropy: 2.470348358154297 +[2025-04-30 14:45:15,786][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.4003396034240723, cross_entropy: 1.4003396034240723 +[2025-04-30 14:45:19,155][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 2.064753532409668, cross_entropy: 2.064753532409668 +[2025-04-30 14:45:19,818][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.91596257686615, cross_entropy: 1.91596257686615 +[2025-04-30 14:45:23,142][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 1.2694964408874512, cross_entropy: 1.2694964408874512 +[2025-04-30 14:45:23,486][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 1.1830177307128906, cross_entropy: 1.1830177307128906 +[2025-04-30 14:45:27,896][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.5998581647872925, cross_entropy: 1.5998581647872925 +[2025-04-30 14:45:28,211][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 1.4058318138122559, cross_entropy: 1.4058318138122559 +[2025-04-30 14:45:31,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 2.6803746223449707, cross_entropy: 2.6803746223449707 +[2025-04-30 14:45:32,141][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 1.3090194463729858, cross_entropy: 1.3090194463729858 +[2025-04-30 14:45:35,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.1406619548797607, cross_entropy: 1.1406619548797607 +[2025-04-30 14:45:35,742][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 2.4942126274108887, cross_entropy: 2.4942126274108887 +[2025-04-30 14:45:39,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.259271502494812, cross_entropy: 1.259271502494812 +[2025-04-30 14:45:39,929][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 2.2605106830596924, cross_entropy: 2.2605106830596924 +[2025-04-30 14:45:43,237][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 3.1595206260681152, cross_entropy: 3.1595206260681152 +[2025-04-30 14:45:43,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.610001564025879, cross_entropy: 1.610001564025879 +[2025-04-30 14:45:46,925][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.2611114978790283, cross_entropy: 2.2611114978790283 +[2025-04-30 14:45:47,238][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 2.474177837371826, cross_entropy: 2.474177837371826 +[2025-04-30 14:45:50,279][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.104548692703247, cross_entropy: 1.104548692703247 +[2025-04-30 14:45:50,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 2.913259267807007, cross_entropy: 2.913259267807007 +[2025-04-30 14:45:54,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 3.2433481216430664, cross_entropy: 3.2433481216430664 +[2025-04-30 14:45:54,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 1.5084631443023682, cross_entropy: 1.5084631443023682 +[2025-04-30 14:45:58,228][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 3.0514230728149414, cross_entropy: 3.0514230728149414 +[2025-04-30 14:45:58,568][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 2.957819938659668, cross_entropy: 2.957819938659668 +[2025-04-30 14:46:02,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 2.070244789123535, cross_entropy: 2.070244789123535 +[2025-04-30 14:46:02,372][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.1497652530670166, cross_entropy: 3.1497652530670166 +[2025-04-30 14:46:05,944][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 3.1105456352233887, cross_entropy: 3.1105456352233887 +[2025-04-30 14:46:06,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 2.664839029312134, cross_entropy: 2.664839029312134 +[2025-04-30 14:46:10,837][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 1.0696282386779785, cross_entropy: 1.0696282386779785 +[2025-04-30 14:46:11,186][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 1.639618158340454, cross_entropy: 1.639618158340454 +[2025-04-30 14:46:14,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.6392617225646973, cross_entropy: 2.6392617225646973 +[2025-04-30 14:46:14,741][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 2.759064197540283, cross_entropy: 2.759064197540283 +[2025-04-30 14:46:18,332][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 2.531223773956299, cross_entropy: 2.531223773956299 +[2025-04-30 14:46:18,673][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 1.7585563659667969, cross_entropy: 1.7585563659667969 +[2025-04-30 14:46:21,998][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 2.4169836044311523, cross_entropy: 2.4169836044311523 +[2025-04-30 14:46:22,348][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 1.2214449644088745, cross_entropy: 1.2214449644088745 +[2025-04-30 14:46:26,158][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 1.2808220386505127, cross_entropy: 1.2808220386505127 +[2025-04-30 14:46:26,496][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 2.822711944580078, cross_entropy: 2.822711944580078 +[2025-04-30 14:46:30,267][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 1.0834577083587646, cross_entropy: 1.0834577083587646 +[2025-04-30 14:46:30,621][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.0516295433044434, cross_entropy: 1.0516295433044434 +[2025-04-30 14:46:34,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 1.0486814975738525, cross_entropy: 1.0486814975738525 +[2025-04-30 14:46:34,758][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 2.790130138397217, cross_entropy: 2.790130138397217 +[2025-04-30 14:46:38,202][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.2275781631469727, cross_entropy: 2.2275781631469727 +[2025-04-30 14:46:38,549][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.5201594829559326, cross_entropy: 1.5201594829559326 +[2025-04-30 14:46:42,410][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.5904626846313477, cross_entropy: 2.5904626846313477 +[2025-04-30 14:46:42,726][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.9463138580322266, cross_entropy: 2.9463138580322266 +[2025-04-30 14:46:46,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 2.8150813579559326, cross_entropy: 2.8150813579559326 +[2025-04-30 14:46:46,440][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 1.952633261680603, cross_entropy: 1.952633261680603 +[2025-04-30 14:46:49,834][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 3.058772563934326, cross_entropy: 3.058772563934326 +[2025-04-30 14:46:50,191][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 2.8466930389404297, cross_entropy: 2.8466930389404297 +[2025-04-30 14:46:53,876][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 0.7637670636177063, cross_entropy: 0.7637670636177063 +[2025-04-30 14:46:54,217][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.819851875305176, cross_entropy: 2.819851875305176 +[2025-04-30 14:46:57,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 2.4314332008361816, cross_entropy: 2.4314332008361816 +[2025-04-30 14:46:58,053][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 0.9352511167526245, cross_entropy: 0.9352511167526245 +[2025-04-30 14:47:03,201][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 2.826406240463257, cross_entropy: 2.826406240463257 +[2025-04-30 14:47:03,545][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.248995304107666, cross_entropy: 2.248995304107666 +[2025-04-30 14:47:07,174][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 3.362386465072632, cross_entropy: 3.362386465072632 +[2025-04-30 14:47:07,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.378138303756714, cross_entropy: 2.378138303756714 +[2025-04-30 14:47:11,139][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 1.8828563690185547, cross_entropy: 1.8828563690185547 +[2025-04-30 14:47:11,453][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.6177295446395874, cross_entropy: 1.6177295446395874 +[2025-04-30 14:47:15,409][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 3.054633855819702, cross_entropy: 3.054633855819702 +[2025-04-30 14:47:15,753][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.9369301795959473, cross_entropy: 1.9369301795959473 +[2025-04-30 14:47:19,034][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 1.356062650680542, cross_entropy: 1.356062650680542 +[2025-04-30 14:47:19,349][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 0.8520311713218689, cross_entropy: 0.8520311713218689 +[2025-04-30 14:47:22,898][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 1.112133502960205, cross_entropy: 1.112133502960205 +[2025-04-30 14:47:23,243][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 2.4657764434814453, cross_entropy: 2.4657764434814453 +[2025-04-30 14:47:27,116][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 1.137963891029358, cross_entropy: 1.137963891029358 +[2025-04-30 14:47:27,449][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.3487787246704102, cross_entropy: 1.3487787246704102 +[2025-04-30 14:47:30,244][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.2857956886291504, cross_entropy: 2.2857956886291504 +[2025-04-30 14:47:30,554][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.4461750984191895, cross_entropy: 2.4461750984191895 +[2025-04-30 14:47:34,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 2.3102173805236816, cross_entropy: 2.3102173805236816 +[2025-04-30 14:47:34,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 2.0931994915008545, cross_entropy: 2.0931994915008545 +[2025-04-30 14:47:38,587][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 1.9610657691955566, cross_entropy: 1.9610657691955566 +[2025-04-30 14:47:38,930][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 3.1803157329559326, cross_entropy: 3.1803157329559326 +[2025-04-30 14:47:42,208][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 0.8679484724998474, cross_entropy: 0.8679484724998474 +[2025-04-30 14:47:42,520][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 2.16874361038208, cross_entropy: 2.16874361038208 +[2025-04-30 14:47:45,878][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 0.8756173849105835, cross_entropy: 0.8756173849105835 +[2025-04-30 14:47:46,218][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.419968843460083, cross_entropy: 1.419968843460083 +[2025-04-30 14:47:49,307][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 2.6424951553344727, cross_entropy: 2.6424951553344727 +[2025-04-30 14:47:49,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.3471055030822754, cross_entropy: 1.3471055030822754 +[2025-04-30 14:47:53,262][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.457420825958252, cross_entropy: 2.457420825958252 +[2025-04-30 14:47:53,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 1.9011921882629395, cross_entropy: 1.9011921882629395 +[2025-04-30 14:47:56,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.1192100048065186, cross_entropy: 1.1192100048065186 +[2025-04-30 14:47:57,076][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 1.293395757675171, cross_entropy: 1.293395757675171 +[2025-04-30 14:48:00,526][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 2.071667194366455, cross_entropy: 2.071667194366455 +[2025-04-30 14:48:00,841][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 1.6984481811523438, cross_entropy: 1.6984481811523438 +[2025-04-30 14:48:04,079][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 1.299330711364746, cross_entropy: 1.299330711364746 +[2025-04-30 14:48:04,414][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 1.9463865756988525, cross_entropy: 1.9463865756988525 +[2025-04-30 14:48:08,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 3.0213992595672607, cross_entropy: 3.0213992595672607 +[2025-04-30 14:48:08,669][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 2.0223190784454346, cross_entropy: 2.0223190784454346 +[2025-04-30 14:48:11,578][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 0.8493509292602539, cross_entropy: 0.8493509292602539 +[2025-04-30 14:48:11,914][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 1.680677056312561, cross_entropy: 1.680677056312561 +[2025-04-30 14:48:14,815][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.9592642784118652, cross_entropy: 2.9592642784118652 +[2025-04-30 14:48:15,153][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 1.2270314693450928, cross_entropy: 1.2270314693450928 +[2025-04-30 14:48:18,201][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.530156135559082, cross_entropy: 2.530156135559082 +[2025-04-30 14:48:18,583][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 0.9511270523071289, cross_entropy: 0.9511270523071289 +[2025-04-30 14:48:22,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.1344971656799316, cross_entropy: 1.1344971656799316 +[2025-04-30 14:48:22,663][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.6578423976898193, cross_entropy: 2.6578423976898193 +[2025-04-30 14:48:25,689][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 0.8035110831260681, cross_entropy: 0.8035110831260681 +[2025-04-30 14:48:26,179][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 1.3035367727279663, cross_entropy: 1.3035367727279663 +[2025-04-30 14:48:29,642][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.4038429260253906, cross_entropy: 1.4038429260253906 +[2025-04-30 14:48:30,013][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 2.4166855812072754, cross_entropy: 2.4166855812072754 +[2025-04-30 14:48:33,466][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 1.3569467067718506, cross_entropy: 1.3569467067718506 +[2025-04-30 14:48:34,099][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 1.9010430574417114, cross_entropy: 1.9010430574417114 +[2025-04-30 14:48:38,906][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 1.5918550491333008, cross_entropy: 1.5918550491333008 +[2025-04-30 14:48:39,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.572070598602295, cross_entropy: 2.572070598602295 +[2025-04-30 14:48:42,633][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.5305174589157104, cross_entropy: 1.5305174589157104 +[2025-04-30 14:48:42,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 1.6710116863250732, cross_entropy: 1.6710116863250732 +[2025-04-30 14:48:46,133][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 2.8867344856262207, cross_entropy: 2.8867344856262207 +[2025-04-30 14:48:46,467][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 0.9161598682403564, cross_entropy: 0.9161598682403564 +[2025-04-30 14:48:50,154][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.5022366046905518, cross_entropy: 1.5022366046905518 +[2025-04-30 14:48:50,465][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.2486610412597656, cross_entropy: 1.2486610412597656 +[2025-04-30 14:48:54,049][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 2.3755133152008057, cross_entropy: 2.3755133152008057 +[2025-04-30 14:48:54,363][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 1.8406870365142822, cross_entropy: 1.8406870365142822 +[2025-04-30 14:48:57,470][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.0657541751861572, cross_entropy: 2.0657541751861572 +[2025-04-30 14:48:57,799][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 2.3390040397644043, cross_entropy: 2.3390040397644043 +[2025-04-30 14:49:01,210][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 3.050434112548828, cross_entropy: 3.050434112548828 +[2025-04-30 14:49:01,522][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 2.3193359375, cross_entropy: 2.3193359375 +[2025-04-30 14:49:04,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 1.2924692630767822, cross_entropy: 1.2924692630767822 +[2025-04-30 14:49:05,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.8029913902282715, cross_entropy: 1.8029913902282715 +[2025-04-30 14:49:09,649][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 1.2556157112121582, cross_entropy: 1.2556157112121582 +[2025-04-30 14:49:09,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 1.2091081142425537, cross_entropy: 1.2091081142425537 +[2025-04-30 14:49:13,197][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.7152624130249023, cross_entropy: 2.7152624130249023 +[2025-04-30 14:49:13,535][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 1.5807641744613647, cross_entropy: 1.5807641744613647 +[2025-04-30 14:49:16,758][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 2.2020421028137207, cross_entropy: 2.2020421028137207 +[2025-04-30 14:49:17,095][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 2.36708927154541, cross_entropy: 2.36708927154541 +[2025-04-30 14:49:19,741][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 1.1036722660064697, cross_entropy: 1.1036722660064697 +[2025-04-30 14:49:20,078][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 2.06880521774292, cross_entropy: 2.06880521774292 +[2025-04-30 14:49:23,560][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.1974376440048218, cross_entropy: 1.1974376440048218 +[2025-04-30 14:49:23,895][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 1.974518060684204, cross_entropy: 1.974518060684204 +[2025-04-30 14:49:27,116][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 1.317495584487915, cross_entropy: 1.317495584487915 +[2025-04-30 14:49:27,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 1.1418564319610596, cross_entropy: 1.1418564319610596 +[2025-04-30 14:49:30,616][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 1.3925148248672485, cross_entropy: 1.3925148248672485 +[2025-04-30 14:49:30,958][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 2.0803322792053223, cross_entropy: 2.0803322792053223 +[2025-04-30 14:49:33,970][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 1.1849995851516724, cross_entropy: 1.1849995851516724 +[2025-04-30 14:49:34,319][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 0.7343971133232117, cross_entropy: 0.7343971133232117 +[2025-04-30 14:49:37,120][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.0511324405670166, cross_entropy: 1.0511324405670166 +[2025-04-30 14:49:37,448][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 2.1016197204589844, cross_entropy: 2.1016197204589844 +[2025-04-30 14:49:40,952][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 1.1352394819259644, cross_entropy: 1.1352394819259644 +[2025-04-30 14:49:41,301][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 3.101597309112549, cross_entropy: 3.101597309112549 +[2025-04-30 14:49:44,567][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 2.5914783477783203, cross_entropy: 2.5914783477783203 +[2025-04-30 14:49:44,881][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.9145240783691406, cross_entropy: 1.9145240783691406 +[2025-04-30 14:49:48,343][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 1.43393874168396, cross_entropy: 1.43393874168396 +[2025-04-30 14:49:48,680][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 0.7973518371582031, cross_entropy: 0.7973518371582031 +[2025-04-30 14:49:52,045][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 0.821664035320282, cross_entropy: 0.821664035320282 +[2025-04-30 14:49:52,383][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 1.4757674932479858, cross_entropy: 1.4757674932479858 +[2025-04-30 14:49:56,388][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 1.7650830745697021, cross_entropy: 1.7650830745697021 +[2025-04-30 14:49:56,703][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 0.9918264150619507, cross_entropy: 0.9918264150619507 +[2025-04-30 14:49:59,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 1.0720067024230957, cross_entropy: 1.0720067024230957 +[2025-04-30 14:50:01,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.4562149047851562, cross_entropy: 1.4562149047851562 +[2025-04-30 14:50:03,045][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 1.1760188341140747, cross_entropy: 1.1760188341140747 +[2025-04-30 14:50:04,883][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 2.255444049835205, cross_entropy: 2.255444049835205 +[2025-04-30 14:50:06,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 1.4442834854125977, cross_entropy: 1.4442834854125977 +[2025-04-30 14:50:09,233][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 2.8088440895080566, cross_entropy: 2.8088440895080566 +[2025-04-30 14:50:10,569][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.4593576192855835, cross_entropy: 1.4593576192855835 +[2025-04-30 14:50:13,332][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 2.543886661529541, cross_entropy: 2.543886661529541 +[2025-04-30 14:50:14,734][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 1.3273236751556396, cross_entropy: 1.3273236751556396 +[2025-04-30 14:50:17,575][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 3.188338279724121, cross_entropy: 3.188338279724121 +[2025-04-30 14:50:18,031][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 2.8027219772338867, cross_entropy: 2.8027219772338867 +[2025-04-30 14:50:21,358][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.6394524574279785, cross_entropy: 1.6394524574279785 +[2025-04-30 14:50:22,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.1678671836853027, cross_entropy: 1.1678671836853027 +[2025-04-30 14:50:25,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.481703758239746, cross_entropy: 1.481703758239746 +[2025-04-30 14:50:26,125][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 1.9179691076278687, cross_entropy: 1.9179691076278687 +[2025-04-30 14:50:28,928][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 0.9631402492523193, cross_entropy: 0.9631402492523193 +[2025-04-30 14:50:29,964][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 1.9484418630599976, cross_entropy: 1.9484418630599976 +[2025-04-30 14:50:33,031][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 2.6717662811279297, cross_entropy: 2.6717662811279297 +[2025-04-30 14:50:33,766][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 2.9321162700653076, cross_entropy: 2.9321162700653076 +[2025-04-30 14:50:37,590][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 3.115567207336426, cross_entropy: 3.115567207336426 +[2025-04-30 14:50:37,952][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.4203970432281494, cross_entropy: 3.4203970432281494 +[2025-04-30 14:50:41,317][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.1813206672668457, cross_entropy: 2.1813206672668457 +[2025-04-30 14:50:41,672][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 2.7603039741516113, cross_entropy: 2.7603039741516113 +[2025-04-30 14:50:45,539][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 0.9536539316177368, cross_entropy: 0.9536539316177368 +[2025-04-30 14:50:45,873][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 1.6417617797851562, cross_entropy: 1.6417617797851562 +[2025-04-30 14:50:49,142][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 2.3306660652160645, cross_entropy: 2.3306660652160645 +[2025-04-30 14:50:49,551][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.354769229888916, cross_entropy: 1.354769229888916 +[2025-04-30 14:50:53,107][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.0480555295944214, cross_entropy: 1.0480555295944214 +[2025-04-30 14:50:53,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 1.0383920669555664, cross_entropy: 1.0383920669555664 +[2025-04-30 14:50:57,206][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 1.320124864578247, cross_entropy: 1.320124864578247 +[2025-04-30 14:50:57,536][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 3.365809440612793, cross_entropy: 3.365809440612793 +[2025-04-30 14:51:00,843][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 3.2934792041778564, cross_entropy: 3.2934792041778564 +[2025-04-30 14:51:01,155][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 1.2304270267486572, cross_entropy: 1.2304270267486572 +[2025-04-30 14:51:04,341][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.6222069263458252, cross_entropy: 1.6222069263458252 +[2025-04-30 14:51:04,679][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.2863900661468506, cross_entropy: 1.2863900661468506 +[2025-04-30 14:51:08,325][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 2.9078941345214844, cross_entropy: 2.9078941345214844 +[2025-04-30 14:51:08,636][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.3602185249328613, cross_entropy: 2.3602185249328613 +[2025-04-30 14:51:11,606][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 3.5150842666625977, cross_entropy: 3.5150842666625977 +[2025-04-30 14:54:07,609][BaseTrainer][INFO] - [Epoch 6/10] (train) 1.9167543649673462, cross_entropy: 1.9167543649673462 +[2025-04-30 14:54:07,610][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.3012562990188599, cross_entropy: 1.3012562990188599 +[2025-04-30 14:54:07,610][BaseTrainer][INFO] - [Epoch 6/10] (metrics) roc_auc: 0.9764289259910583 +[2025-04-30 14:54:07,778][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch6.pth. +[2025-04-30 14:54:07,977][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 14:54:12,955][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 2.525339365005493, cross_entropy: 2.525339365005493 +[2025-04-30 14:54:13,293][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 2.5428080558776855, cross_entropy: 2.5428080558776855 +[2025-04-30 14:54:16,529][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 1.2434492111206055, cross_entropy: 1.2434492111206055 +[2025-04-30 14:54:16,864][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 0.7252449989318848, cross_entropy: 0.7252449989318848 +[2025-04-30 14:54:19,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 1.0606238842010498, cross_entropy: 1.0606238842010498 +[2025-04-30 14:54:20,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 1.0235953330993652, cross_entropy: 1.0235953330993652 +[2025-04-30 14:54:23,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 2.685832977294922, cross_entropy: 2.685832977294922 +[2025-04-30 14:54:23,912][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.2149009704589844, cross_entropy: 1.2149009704589844 +[2025-04-30 14:54:27,247][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 1.5167263746261597, cross_entropy: 1.5167263746261597 +[2025-04-30 14:54:27,561][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.2536375522613525, cross_entropy: 1.2536375522613525 +[2025-04-30 14:54:31,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 2.7744975090026855, cross_entropy: 2.7744975090026855 +[2025-04-30 14:54:32,016][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 2.026492118835449, cross_entropy: 2.026492118835449 +[2025-04-30 14:54:34,922][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.7816553115844727, cross_entropy: 2.7816553115844727 +[2025-04-30 14:54:35,397][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 3.10378360748291, cross_entropy: 3.10378360748291 +[2025-04-30 14:54:38,233][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.5567331314086914, cross_entropy: 2.5567331314086914 +[2025-04-30 14:54:38,860][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 2.435919761657715, cross_entropy: 2.435919761657715 +[2025-04-30 14:54:42,092][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 1.907092571258545, cross_entropy: 1.907092571258545 +[2025-04-30 14:54:42,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.2091941833496094, cross_entropy: 3.2091941833496094 +[2025-04-30 14:54:45,604][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.856076240539551, cross_entropy: 2.856076240539551 +[2025-04-30 14:54:45,983][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 0.9803628921508789, cross_entropy: 0.9803628921508789 +[2025-04-30 14:54:48,864][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 1.2122431993484497, cross_entropy: 1.2122431993484497 +[2025-04-30 14:54:49,247][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.3665249347686768, cross_entropy: 2.3665249347686768 +[2025-04-30 14:54:53,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 1.9473812580108643, cross_entropy: 1.9473812580108643 +[2025-04-30 14:54:53,373][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.5173375606536865, cross_entropy: 2.5173375606536865 +[2025-04-30 14:54:56,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 1.8628028631210327, cross_entropy: 1.8628028631210327 +[2025-04-30 14:54:57,205][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 2.446356773376465, cross_entropy: 2.446356773376465 +[2025-04-30 14:55:00,244][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 2.6691317558288574, cross_entropy: 2.6691317558288574 +[2025-04-30 14:55:00,773][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 2.8574066162109375, cross_entropy: 2.8574066162109375 +[2025-04-30 14:55:03,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 1.072796106338501, cross_entropy: 1.072796106338501 +[2025-04-30 14:55:04,616][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.0413875579833984, cross_entropy: 1.0413875579833984 +[2025-04-30 14:55:08,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 1.9023611545562744, cross_entropy: 1.9023611545562744 +[2025-04-30 14:55:08,530][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 2.2430124282836914, cross_entropy: 2.2430124282836914 +[2025-04-30 14:55:11,444][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 2.4079675674438477, cross_entropy: 2.4079675674438477 +[2025-04-30 14:55:12,230][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.1128878593444824, cross_entropy: 1.1128878593444824 +[2025-04-30 14:55:15,309][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.479482412338257, cross_entropy: 2.479482412338257 +[2025-04-30 14:55:15,733][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.6111862659454346, cross_entropy: 1.6111862659454346 +[2025-04-30 14:55:20,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.9135844707489014, cross_entropy: 2.9135844707489014 +[2025-04-30 14:55:20,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 1.1371586322784424, cross_entropy: 1.1371586322784424 +[2025-04-30 14:55:23,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 0.7538673281669617, cross_entropy: 0.7538673281669617 +[2025-04-30 14:55:23,969][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.4383357763290405, cross_entropy: 1.4383357763290405 +[2025-04-30 14:55:27,567][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 1.0550373792648315, cross_entropy: 1.0550373792648315 +[2025-04-30 14:55:27,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 2.189528226852417, cross_entropy: 2.189528226852417 +[2025-04-30 14:55:31,108][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 2.5038046836853027, cross_entropy: 2.5038046836853027 +[2025-04-30 14:55:31,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 2.975829601287842, cross_entropy: 2.975829601287842 +[2025-04-30 14:55:35,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 2.4574575424194336, cross_entropy: 2.4574575424194336 +[2025-04-30 14:55:35,676][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 1.574628472328186, cross_entropy: 1.574628472328186 +[2025-04-30 14:55:38,942][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 0.7546550631523132, cross_entropy: 0.7546550631523132 +[2025-04-30 14:55:39,281][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 1.0213713645935059, cross_entropy: 1.0213713645935059 +[2025-04-30 14:55:43,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.466590404510498, cross_entropy: 2.466590404510498 +[2025-04-30 14:55:43,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.0391045808792114, cross_entropy: 1.0391045808792114 +[2025-04-30 14:55:46,167][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 2.6121370792388916, cross_entropy: 2.6121370792388916 +[2025-04-30 14:55:46,507][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 3.183919906616211, cross_entropy: 3.183919906616211 +[2025-04-30 14:55:50,592][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 2.1931235790252686, cross_entropy: 2.1931235790252686 +[2025-04-30 14:55:50,906][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.7102277278900146, cross_entropy: 2.7102277278900146 +[2025-04-30 14:55:54,428][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 1.973035454750061, cross_entropy: 1.973035454750061 +[2025-04-30 14:55:54,742][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 2.6226298809051514, cross_entropy: 2.6226298809051514 +[2025-04-30 14:55:58,109][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 1.4851453304290771, cross_entropy: 1.4851453304290771 +[2025-04-30 14:55:58,450][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.2025030851364136, cross_entropy: 1.2025030851364136 +[2025-04-30 14:56:03,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 2.885952949523926, cross_entropy: 2.885952949523926 +[2025-04-30 14:56:03,387][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 2.8599863052368164, cross_entropy: 2.8599863052368164 +[2025-04-30 14:56:06,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 1.7997612953186035, cross_entropy: 1.7997612953186035 +[2025-04-30 14:56:07,319][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 1.9823126792907715, cross_entropy: 1.9823126792907715 +[2025-04-30 14:56:10,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.453187108039856, cross_entropy: 1.453187108039856 +[2025-04-30 14:56:10,949][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 0.9101290702819824, cross_entropy: 0.9101290702819824 +[2025-04-30 14:56:14,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.1306824684143066, cross_entropy: 2.1306824684143066 +[2025-04-30 14:56:14,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 1.1654683351516724, cross_entropy: 1.1654683351516724 +[2025-04-30 14:56:17,607][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.1437556743621826, cross_entropy: 1.1437556743621826 +[2025-04-30 14:56:17,947][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 2.750096559524536, cross_entropy: 2.750096559524536 +[2025-04-30 14:56:21,557][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 0.8205247521400452, cross_entropy: 0.8205247521400452 +[2025-04-30 14:56:21,901][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 0.7886852622032166, cross_entropy: 0.7886852622032166 +[2025-04-30 14:56:25,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 2.7494373321533203, cross_entropy: 2.7494373321533203 +[2025-04-30 14:56:26,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 1.2388614416122437, cross_entropy: 1.2388614416122437 +[2025-04-30 14:56:29,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 2.125774621963501, cross_entropy: 2.125774621963501 +[2025-04-30 14:56:30,111][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 2.870391607284546, cross_entropy: 2.870391607284546 +[2025-04-30 14:56:33,028][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 1.0701298713684082, cross_entropy: 1.0701298713684082 +[2025-04-30 14:56:33,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.7501788139343262, cross_entropy: 1.7501788139343262 +[2025-04-30 14:56:36,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 2.2556753158569336, cross_entropy: 2.2556753158569336 +[2025-04-30 14:56:37,246][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 2.6239209175109863, cross_entropy: 2.6239209175109863 +[2025-04-30 14:56:40,774][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.3803341388702393, cross_entropy: 2.3803341388702393 +[2025-04-30 14:56:41,115][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 1.79093599319458, cross_entropy: 1.79093599319458 +[2025-04-30 14:56:44,335][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 0.8462056517601013, cross_entropy: 0.8462056517601013 +[2025-04-30 14:56:44,678][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 1.6322742700576782, cross_entropy: 1.6322742700576782 +[2025-04-30 14:56:48,229][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.5894582271575928, cross_entropy: 2.5894582271575928 +[2025-04-30 14:56:48,573][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 2.8254148960113525, cross_entropy: 2.8254148960113525 +[2025-04-30 14:56:51,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 1.013312816619873, cross_entropy: 1.013312816619873 +[2025-04-30 14:56:52,137][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 2.201895236968994, cross_entropy: 2.201895236968994 +[2025-04-30 14:56:56,087][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 0.8436813354492188, cross_entropy: 0.8436813354492188 +[2025-04-30 14:56:56,431][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 1.370060920715332, cross_entropy: 1.370060920715332 +[2025-04-30 14:56:59,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 2.72979736328125, cross_entropy: 2.72979736328125 +[2025-04-30 14:56:59,778][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.1014046669006348, cross_entropy: 1.1014046669006348 +[2025-04-30 14:57:03,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 2.890291452407837, cross_entropy: 2.890291452407837 +[2025-04-30 14:57:03,957][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 0.9087662100791931, cross_entropy: 0.9087662100791931 +[2025-04-30 14:57:07,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 1.1222965717315674, cross_entropy: 1.1222965717315674 +[2025-04-30 14:57:08,032][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.140678882598877, cross_entropy: 1.140678882598877 +[2025-04-30 14:57:11,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.786813735961914, cross_entropy: 2.786813735961914 +[2025-04-30 14:57:11,600][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.512420892715454, cross_entropy: 1.512420892715454 +[2025-04-30 14:57:14,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 1.092428207397461, cross_entropy: 1.092428207397461 +[2025-04-30 14:57:15,076][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 1.065540075302124, cross_entropy: 1.065540075302124 +[2025-04-30 14:57:19,157][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.6855814456939697, cross_entropy: 1.6855814456939697 +[2025-04-30 14:57:19,499][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 1.6813859939575195, cross_entropy: 1.6813859939575195 +[2025-04-30 14:57:23,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 1.0556647777557373, cross_entropy: 1.0556647777557373 +[2025-04-30 14:57:23,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 0.6172427535057068, cross_entropy: 0.6172427535057068 +[2025-04-30 14:57:27,610][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.083768367767334, cross_entropy: 2.083768367767334 +[2025-04-30 14:57:27,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.318847417831421, cross_entropy: 1.318847417831421 +[2025-04-30 14:57:31,359][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.1520540714263916, cross_entropy: 1.1520540714263916 +[2025-04-30 14:57:31,673][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.0889687538146973, cross_entropy: 1.0889687538146973 +[2025-04-30 14:57:35,003][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.8124020099639893, cross_entropy: 1.8124020099639893 +[2025-04-30 14:57:35,316][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.159733772277832, cross_entropy: 1.159733772277832 +[2025-04-30 14:57:39,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 0.8861758708953857, cross_entropy: 0.8861758708953857 +[2025-04-30 14:57:39,440][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 0.9996277689933777, cross_entropy: 0.9996277689933777 +[2025-04-30 14:57:43,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 0.7286560535430908, cross_entropy: 0.7286560535430908 +[2025-04-30 14:57:43,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 0.844639003276825, cross_entropy: 0.844639003276825 +[2025-04-30 14:57:46,098][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 1.3078193664550781, cross_entropy: 1.3078193664550781 +[2025-04-30 14:57:46,443][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 0.7830963134765625, cross_entropy: 0.7830963134765625 +[2025-04-30 14:57:49,362][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.1583404541015625, cross_entropy: 1.1583404541015625 +[2025-04-30 14:57:49,699][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 0.7170780897140503, cross_entropy: 0.7170780897140503 +[2025-04-30 14:57:53,036][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 0.8668665885925293, cross_entropy: 0.8668665885925293 +[2025-04-30 14:57:53,374][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.6164093017578125, cross_entropy: 2.6164093017578125 +[2025-04-30 14:57:56,961][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 2.3181374073028564, cross_entropy: 2.3181374073028564 +[2025-04-30 14:57:57,296][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 1.1185650825500488, cross_entropy: 1.1185650825500488 +[2025-04-30 14:58:00,493][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 1.1415605545043945, cross_entropy: 1.1415605545043945 +[2025-04-30 14:58:00,816][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 1.1721071004867554, cross_entropy: 1.1721071004867554 +[2025-04-30 14:58:05,217][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 2.0062203407287598, cross_entropy: 2.0062203407287598 +[2025-04-30 14:58:05,556][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 2.341482162475586, cross_entropy: 2.341482162475586 +[2025-04-30 14:58:09,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 0.9915730357170105, cross_entropy: 0.9915730357170105 +[2025-04-30 14:58:09,761][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.0156177282333374, cross_entropy: 1.0156177282333374 +[2025-04-30 14:58:14,592][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.0663671493530273, cross_entropy: 3.0663671493530273 +[2025-04-30 14:58:14,922][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.0002894401550293, cross_entropy: 1.0002894401550293 +[2025-04-30 14:58:17,921][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 0.9723395705223083, cross_entropy: 0.9723395705223083 +[2025-04-30 14:58:18,257][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 1.0084636211395264, cross_entropy: 1.0084636211395264 +[2025-04-30 14:58:21,601][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 1.0714908838272095, cross_entropy: 1.0714908838272095 +[2025-04-30 14:58:21,930][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 2.1489953994750977, cross_entropy: 2.1489953994750977 +[2025-04-30 14:58:24,873][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 2.724334478378296, cross_entropy: 2.724334478378296 +[2025-04-30 14:58:25,213][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.6233068704605103, cross_entropy: 1.6233068704605103 +[2025-04-30 14:58:28,370][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 3.285367727279663, cross_entropy: 3.285367727279663 +[2025-04-30 14:58:28,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 2.6362671852111816, cross_entropy: 2.6362671852111816 +[2025-04-30 14:58:32,448][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 3.072672128677368, cross_entropy: 3.072672128677368 +[2025-04-30 14:58:32,786][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 1.2315922975540161, cross_entropy: 1.2315922975540161 +[2025-04-30 14:58:35,984][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 0.9732739925384521, cross_entropy: 0.9732739925384521 +[2025-04-30 14:58:36,295][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 2.467146873474121, cross_entropy: 2.467146873474121 +[2025-04-30 14:58:39,786][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 0.8728514909744263, cross_entropy: 0.8728514909744263 +[2025-04-30 14:58:40,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 1.4719409942626953, cross_entropy: 1.4719409942626953 +[2025-04-30 14:58:42,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 2.738084554672241, cross_entropy: 2.738084554672241 +[2025-04-30 14:58:42,953][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 1.0640097856521606, cross_entropy: 1.0640097856521606 +[2025-04-30 14:58:46,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.3111087083816528, cross_entropy: 1.3111087083816528 +[2025-04-30 14:58:47,109][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.3092224597930908, cross_entropy: 1.3092224597930908 +[2025-04-30 14:58:50,348][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 2.5512497425079346, cross_entropy: 2.5512497425079346 +[2025-04-30 14:58:50,689][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 0.7453537583351135, cross_entropy: 0.7453537583351135 +[2025-04-30 14:58:54,291][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.6282854080200195, cross_entropy: 2.6282854080200195 +[2025-04-30 14:58:54,603][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 0.8246364593505859, cross_entropy: 0.8246364593505859 +[2025-04-30 14:58:57,600][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 2.1834492683410645, cross_entropy: 2.1834492683410645 +[2025-04-30 14:58:57,936][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 2.8815550804138184, cross_entropy: 2.8815550804138184 +[2025-04-30 14:59:00,996][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.0513358116149902, cross_entropy: 2.0513358116149902 +[2025-04-30 14:59:01,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 2.2947769165039062, cross_entropy: 2.2947769165039062 +[2025-04-30 14:59:04,665][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 2.1036510467529297, cross_entropy: 2.1036510467529297 +[2025-04-30 14:59:05,001][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 0.9362300634384155, cross_entropy: 0.9362300634384155 +[2025-04-30 14:59:08,118][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 1.8174231052398682, cross_entropy: 1.8174231052398682 +[2025-04-30 14:59:08,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 2.8962604999542236, cross_entropy: 2.8962604999542236 +[2025-04-30 14:59:12,001][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 1.2906674146652222, cross_entropy: 1.2906674146652222 +[2025-04-30 14:59:12,336][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 1.2978925704956055, cross_entropy: 1.2978925704956055 +[2025-04-30 14:59:15,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 3.0431385040283203, cross_entropy: 3.0431385040283203 +[2025-04-30 14:59:15,480][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 1.3620147705078125, cross_entropy: 1.3620147705078125 +[2025-04-30 14:59:18,928][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 0.9859921932220459, cross_entropy: 0.9859921932220459 +[2025-04-30 14:59:19,240][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 2.3060121536254883, cross_entropy: 2.3060121536254883 +[2025-04-30 14:59:21,686][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 0.7332766056060791, cross_entropy: 0.7332766056060791 +[2025-04-30 14:59:22,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.1066293716430664, cross_entropy: 1.1066293716430664 +[2025-04-30 14:59:24,698][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 2.6314616203308105, cross_entropy: 2.6314616203308105 +[2025-04-30 14:59:25,043][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 2.6943020820617676, cross_entropy: 2.6943020820617676 +[2025-04-30 14:59:28,870][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 1.2062427997589111, cross_entropy: 1.2062427997589111 +[2025-04-30 14:59:29,182][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 3.104098081588745, cross_entropy: 3.104098081588745 +[2025-04-30 14:59:32,138][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.582072377204895, cross_entropy: 1.582072377204895 +[2025-04-30 14:59:32,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 2.695563554763794, cross_entropy: 2.695563554763794 +[2025-04-30 14:59:35,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 2.7434325218200684, cross_entropy: 2.7434325218200684 +[2025-04-30 14:59:35,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 2.0766406059265137, cross_entropy: 2.0766406059265137 +[2025-04-30 14:59:38,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 3.2014811038970947, cross_entropy: 3.2014811038970947 +[2025-04-30 14:59:39,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.9183986186981201, cross_entropy: 1.9183986186981201 +[2025-04-30 14:59:42,281][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 2.742164134979248, cross_entropy: 2.742164134979248 +[2025-04-30 14:59:42,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.812417984008789, cross_entropy: 1.812417984008789 +[2025-04-30 14:59:46,065][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 2.869171619415283, cross_entropy: 2.869171619415283 +[2025-04-30 14:59:46,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.515039324760437, cross_entropy: 1.515039324760437 +[2025-04-30 14:59:50,366][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 1.4254660606384277, cross_entropy: 1.4254660606384277 +[2025-04-30 14:59:50,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 2.2842233180999756, cross_entropy: 2.2842233180999756 +[2025-04-30 14:59:54,101][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 2.3429605960845947, cross_entropy: 2.3429605960845947 +[2025-04-30 14:59:54,437][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 1.3925888538360596, cross_entropy: 1.3925888538360596 +[2025-04-30 14:59:57,776][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 1.16395103931427, cross_entropy: 1.16395103931427 +[2025-04-30 14:59:58,115][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.551889419555664, cross_entropy: 2.551889419555664 +[2025-04-30 15:00:01,937][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 2.7274272441864014, cross_entropy: 2.7274272441864014 +[2025-04-30 15:00:02,274][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 3.3240394592285156, cross_entropy: 3.3240394592285156 +[2025-04-30 15:00:06,004][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.2655375003814697, cross_entropy: 1.2655375003814697 +[2025-04-30 15:00:06,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 1.9606702327728271, cross_entropy: 1.9606702327728271 +[2025-04-30 15:00:09,279][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 1.8487825393676758, cross_entropy: 1.8487825393676758 +[2025-04-30 15:00:09,613][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 1.8265308141708374, cross_entropy: 1.8265308141708374 +[2025-04-30 15:00:12,953][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 2.9580752849578857, cross_entropy: 2.9580752849578857 +[2025-04-30 15:00:13,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.826603412628174, cross_entropy: 2.826603412628174 +[2025-04-30 15:00:16,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.8163971900939941, cross_entropy: 1.8163971900939941 +[2025-04-30 15:00:16,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.3294159173965454, cross_entropy: 1.3294159173965454 +[2025-04-30 15:00:20,184][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 3.043104887008667, cross_entropy: 3.043104887008667 +[2025-04-30 15:00:20,523][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 0.9626570343971252, cross_entropy: 0.9626570343971252 +[2025-04-30 15:00:23,770][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.080409526824951, cross_entropy: 3.080409526824951 +[2025-04-30 15:00:24,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.5846123695373535, cross_entropy: 1.5846123695373535 +[2025-04-30 15:00:27,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 2.9412450790405273, cross_entropy: 2.9412450790405273 +[2025-04-30 15:00:27,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 2.5729031562805176, cross_entropy: 2.5729031562805176 +[2025-04-30 15:00:30,619][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 0.7135030031204224, cross_entropy: 0.7135030031204224 +[2025-04-30 15:00:30,959][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 2.1192665100097656, cross_entropy: 2.1192665100097656 +[2025-04-30 15:00:35,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 3.1009602546691895, cross_entropy: 3.1009602546691895 +[2025-04-30 15:00:35,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 2.8792166709899902, cross_entropy: 2.8792166709899902 +[2025-04-30 15:00:38,386][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 0.9548419713973999, cross_entropy: 0.9548419713973999 +[2025-04-30 15:00:38,725][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.2645494937896729, cross_entropy: 1.2645494937896729 +[2025-04-30 15:00:41,457][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 0.5880225896835327, cross_entropy: 0.5880225896835327 +[2025-04-30 15:00:41,800][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 3.008901834487915, cross_entropy: 3.008901834487915 +[2025-04-30 15:00:44,789][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 2.9655652046203613, cross_entropy: 2.9655652046203613 +[2025-04-30 15:00:45,128][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.695847511291504, cross_entropy: 1.695847511291504 +[2025-04-30 15:00:48,357][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 2.6612844467163086, cross_entropy: 2.6612844467163086 +[2025-04-30 15:00:48,700][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.2472659349441528, cross_entropy: 1.2472659349441528 +[2025-04-30 15:00:52,106][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.1529889106750488, cross_entropy: 1.1529889106750488 +[2025-04-30 15:00:52,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 3.0197794437408447, cross_entropy: 3.0197794437408447 +[2025-04-30 15:00:56,084][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.9634451866149902, cross_entropy: 2.9634451866149902 +[2025-04-30 15:00:56,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 1.0397509336471558, cross_entropy: 1.0397509336471558 +[2025-04-30 15:00:59,410][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.1193633079528809, cross_entropy: 1.1193633079528809 +[2025-04-30 15:00:59,748][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.579766273498535, cross_entropy: 2.579766273498535 +[2025-04-30 15:01:03,460][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 2.7373030185699463, cross_entropy: 2.7373030185699463 +[2025-04-30 15:01:03,796][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 0.9052159786224365, cross_entropy: 0.9052159786224365 +[2025-04-30 15:01:06,360][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.9322900772094727, cross_entropy: 2.9322900772094727 +[2025-04-30 15:01:06,704][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 3.1241893768310547, cross_entropy: 3.1241893768310547 +[2025-04-30 15:01:09,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.4467753171920776, cross_entropy: 1.4467753171920776 +[2025-04-30 15:01:09,818][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 2.9660356044769287, cross_entropy: 2.9660356044769287 +[2025-04-30 15:01:12,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 1.1480202674865723, cross_entropy: 1.1480202674865723 +[2025-04-30 15:01:12,847][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.9996165037155151, cross_entropy: 1.9996165037155151 +[2025-04-30 15:01:15,738][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 1.483933687210083, cross_entropy: 1.483933687210083 +[2025-04-30 15:01:16,079][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 2.80789852142334, cross_entropy: 2.80789852142334 +[2025-04-30 15:01:19,003][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.862870693206787, cross_entropy: 2.862870693206787 +[2025-04-30 15:01:19,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.0085678100585938, cross_entropy: 1.0085678100585938 +[2025-04-30 15:01:22,733][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 1.7804795503616333, cross_entropy: 1.7804795503616333 +[2025-04-30 15:01:23,045][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.296746253967285, cross_entropy: 2.296746253967285 +[2025-04-30 15:01:26,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 2.016014337539673, cross_entropy: 2.016014337539673 +[2025-04-30 15:01:26,879][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 1.035778522491455, cross_entropy: 1.035778522491455 +[2025-04-30 15:01:30,284][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 1.0359035730361938, cross_entropy: 1.0359035730361938 +[2025-04-30 15:01:30,632][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 3.2028775215148926, cross_entropy: 3.2028775215148926 +[2025-04-30 15:01:34,069][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 1.0391664505004883, cross_entropy: 1.0391664505004883 +[2025-04-30 15:01:34,411][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.4070022106170654, cross_entropy: 2.4070022106170654 +[2025-04-30 15:01:37,889][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 1.6191991567611694, cross_entropy: 1.6191991567611694 +[2025-04-30 15:01:38,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 0.9241111278533936, cross_entropy: 0.9241111278533936 +[2025-04-30 15:01:41,138][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.7398916482925415, cross_entropy: 1.7398916482925415 +[2025-04-30 15:01:41,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 2.533796787261963, cross_entropy: 2.533796787261963 +[2025-04-30 15:01:45,166][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 2.7225427627563477, cross_entropy: 2.7225427627563477 +[2025-04-30 15:01:45,479][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 2.0525684356689453, cross_entropy: 2.0525684356689453 +[2025-04-30 15:01:48,531][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 0.9839590787887573, cross_entropy: 0.9839590787887573 +[2025-04-30 15:01:48,842][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 2.1108644008636475, cross_entropy: 2.1108644008636475 +[2025-04-30 15:01:52,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 0.8254753351211548, cross_entropy: 0.8254753351211548 +[2025-04-30 15:01:52,969][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 0.9424723982810974, cross_entropy: 0.9424723982810974 +[2025-04-30 15:01:56,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.1543996334075928, cross_entropy: 1.1543996334075928 +[2025-04-30 15:01:56,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 1.439996361732483, cross_entropy: 1.439996361732483 +[2025-04-30 15:02:00,343][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 1.148643970489502, cross_entropy: 1.148643970489502 +[2025-04-30 15:02:00,680][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 1.3716577291488647, cross_entropy: 1.3716577291488647 +[2025-04-30 15:02:03,437][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 2.9492998123168945, cross_entropy: 2.9492998123168945 +[2025-04-30 15:02:03,769][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 0.9158217310905457, cross_entropy: 0.9158217310905457 +[2025-04-30 15:02:07,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.749014139175415, cross_entropy: 2.749014139175415 +[2025-04-30 15:02:07,395][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 1.4556759595870972, cross_entropy: 1.4556759595870972 +[2025-04-30 15:02:10,180][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.9082084894180298, cross_entropy: 1.9082084894180298 +[2025-04-30 15:02:10,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.9930496215820312, cross_entropy: 2.9930496215820312 +[2025-04-30 15:02:13,568][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 1.9264719486236572, cross_entropy: 1.9264719486236572 +[2025-04-30 15:02:13,906][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 2.960869312286377, cross_entropy: 2.960869312286377 +[2025-04-30 15:02:17,197][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 1.3118072748184204, cross_entropy: 1.3118072748184204 +[2025-04-30 15:02:17,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 1.7072868347167969, cross_entropy: 1.7072868347167969 +[2025-04-30 15:02:20,490][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 3.02278470993042, cross_entropy: 3.02278470993042 +[2025-04-30 15:02:20,826][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.489224910736084, cross_entropy: 1.489224910736084 +[2025-04-30 15:02:23,804][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.2394819259643555, cross_entropy: 3.2394819259643555 +[2025-04-30 15:02:24,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.0608601570129395, cross_entropy: 2.0608601570129395 +[2025-04-30 15:02:27,245][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 0.6071282625198364, cross_entropy: 0.6071282625198364 +[2025-04-30 15:02:27,585][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 0.8445553779602051, cross_entropy: 0.8445553779602051 +[2025-04-30 15:02:30,645][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 0.9786924123764038, cross_entropy: 0.9786924123764038 +[2025-04-30 15:02:30,984][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 0.9486194849014282, cross_entropy: 0.9486194849014282 +[2025-04-30 15:02:34,965][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 2.24606990814209, cross_entropy: 2.24606990814209 +[2025-04-30 15:02:35,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 0.8321454524993896, cross_entropy: 0.8321454524993896 +[2025-04-30 15:02:38,379][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 2.5862247943878174, cross_entropy: 2.5862247943878174 +[2025-04-30 15:02:38,692][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 1.7053916454315186, cross_entropy: 1.7053916454315186 +[2025-04-30 15:02:41,626][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.5876774787902832, cross_entropy: 1.5876774787902832 +[2025-04-30 15:02:41,972][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 1.076838493347168, cross_entropy: 1.076838493347168 +[2025-04-30 15:02:45,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 0.8437619209289551, cross_entropy: 0.8437619209289551 +[2025-04-30 15:02:45,962][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 1.8827141523361206, cross_entropy: 1.8827141523361206 +[2025-04-30 15:02:49,014][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.3940502405166626, cross_entropy: 1.3940502405166626 +[2025-04-30 15:02:49,334][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 0.9244685173034668, cross_entropy: 0.9244685173034668 +[2025-04-30 15:02:52,442][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 2.7756574153900146, cross_entropy: 2.7756574153900146 +[2025-04-30 15:02:52,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 1.3528389930725098, cross_entropy: 1.3528389930725098 +[2025-04-30 15:02:55,993][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 1.9811158180236816, cross_entropy: 1.9811158180236816 +[2025-04-30 15:02:56,307][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 1.0175104141235352, cross_entropy: 1.0175104141235352 +[2025-04-30 15:02:58,962][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 2.116666316986084, cross_entropy: 2.116666316986084 +[2025-04-30 15:02:59,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 3.129135847091675, cross_entropy: 3.129135847091675 +[2025-04-30 15:03:02,858][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 0.8841758966445923, cross_entropy: 0.8841758966445923 +[2025-04-30 15:03:03,173][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 1.0796711444854736, cross_entropy: 1.0796711444854736 +[2025-04-30 15:03:07,742][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 2.1686456203460693, cross_entropy: 2.1686456203460693 +[2025-04-30 15:03:08,056][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 2.386536121368408, cross_entropy: 2.386536121368408 +[2025-04-30 15:03:11,749][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 3.1343719959259033, cross_entropy: 3.1343719959259033 +[2025-04-30 15:03:12,087][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 2.805574417114258, cross_entropy: 2.805574417114258 +[2025-04-30 15:03:15,039][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 2.8657126426696777, cross_entropy: 2.8657126426696777 +[2025-04-30 15:03:15,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 2.8586549758911133, cross_entropy: 2.8586549758911133 +[2025-04-30 15:03:18,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.2141807079315186, cross_entropy: 2.2141807079315186 +[2025-04-30 15:03:18,747][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 2.093696117401123, cross_entropy: 2.093696117401123 +[2025-04-30 15:03:21,638][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 2.948784828186035, cross_entropy: 2.948784828186035 +[2025-04-30 15:03:21,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 1.0135862827301025, cross_entropy: 1.0135862827301025 +[2025-04-30 15:03:25,045][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.9362401962280273, cross_entropy: 2.9362401962280273 +[2025-04-30 15:03:25,357][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 2.408203601837158, cross_entropy: 2.408203601837158 +[2025-04-30 15:03:28,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 1.1208468675613403, cross_entropy: 1.1208468675613403 +[2025-04-30 15:03:29,226][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 1.3910164833068848, cross_entropy: 1.3910164833068848 +[2025-04-30 15:03:32,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 1.6584422588348389, cross_entropy: 1.6584422588348389 +[2025-04-30 15:03:32,350][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 1.1112861633300781, cross_entropy: 1.1112861633300781 +[2025-04-30 15:03:35,378][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.4656755924224854, cross_entropy: 1.4656755924224854 +[2025-04-30 15:03:35,722][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.1994967460632324, cross_entropy: 2.1994967460632324 +[2025-04-30 15:03:39,934][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 3.11793851852417, cross_entropy: 3.11793851852417 +[2025-04-30 15:03:40,284][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.860628604888916, cross_entropy: 2.860628604888916 +[2025-04-30 15:03:42,759][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.3322014808654785, cross_entropy: 1.3322014808654785 +[2025-04-30 15:03:43,107][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 1.223181962966919, cross_entropy: 1.223181962966919 +[2025-04-30 15:03:45,554][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.1017138957977295, cross_entropy: 1.1017138957977295 +[2025-04-30 15:03:45,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 1.3628721237182617, cross_entropy: 1.3628721237182617 +[2025-04-30 15:03:48,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.395436406135559, cross_entropy: 1.395436406135559 +[2025-04-30 15:03:48,831][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.6830785274505615, cross_entropy: 1.6830785274505615 +[2025-04-30 15:03:51,550][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 1.2621181011199951, cross_entropy: 1.2621181011199951 +[2025-04-30 15:03:51,891][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 2.6375224590301514, cross_entropy: 2.6375224590301514 +[2025-04-30 15:03:56,021][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 3.2981820106506348, cross_entropy: 3.2981820106506348 +[2025-04-30 15:03:56,335][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 2.460270881652832, cross_entropy: 2.460270881652832 +[2025-04-30 15:03:58,989][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 1.450818657875061, cross_entropy: 1.450818657875061 +[2025-04-30 15:03:59,328][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 0.9274280071258545, cross_entropy: 0.9274280071258545 +[2025-04-30 15:04:02,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 1.2957372665405273, cross_entropy: 1.2957372665405273 +[2025-04-30 15:04:02,722][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.5168709754943848, cross_entropy: 2.5168709754943848 +[2025-04-30 15:04:05,583][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 3.131727933883667, cross_entropy: 3.131727933883667 +[2025-04-30 15:04:05,926][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 0.6964036226272583, cross_entropy: 0.6964036226272583 +[2025-04-30 15:04:09,556][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.1241557598114014, cross_entropy: 1.1241557598114014 +[2025-04-30 15:04:09,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 2.9308369159698486, cross_entropy: 2.9308369159698486 +[2025-04-30 15:04:12,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 1.142946720123291, cross_entropy: 1.142946720123291 +[2025-04-30 15:04:12,954][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 2.51455020904541, cross_entropy: 2.51455020904541 +[2025-04-30 15:04:16,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 0.8317000865936279, cross_entropy: 0.8317000865936279 +[2025-04-30 15:04:16,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 1.2503104209899902, cross_entropy: 1.2503104209899902 +[2025-04-30 15:04:19,013][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.7737443447113037, cross_entropy: 2.7737443447113037 +[2025-04-30 15:04:19,350][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.4680421352386475, cross_entropy: 1.4680421352386475 +[2025-04-30 15:04:22,858][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 0.7218531370162964, cross_entropy: 0.7218531370162964 +[2025-04-30 15:04:23,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 2.622121572494507, cross_entropy: 2.622121572494507 +[2025-04-30 15:04:26,451][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 1.286056637763977, cross_entropy: 1.286056637763977 +[2025-04-30 15:04:26,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.5302343368530273, cross_entropy: 1.5302343368530273 +[2025-04-30 15:04:30,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.7495434284210205, cross_entropy: 2.7495434284210205 +[2025-04-30 15:04:30,555][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.2033066749572754, cross_entropy: 2.2033066749572754 +[2025-04-30 15:04:33,772][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 0.5555645227432251, cross_entropy: 0.5555645227432251 +[2025-04-30 15:04:34,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 1.3404312133789062, cross_entropy: 1.3404312133789062 +[2025-04-30 15:04:36,935][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 0.9450821876525879, cross_entropy: 0.9450821876525879 +[2025-04-30 15:04:37,271][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.8913617730140686, cross_entropy: 0.8913617730140686 +[2025-04-30 15:04:41,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.489029884338379, cross_entropy: 1.489029884338379 +[2025-04-30 15:04:41,741][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.794123649597168, cross_entropy: 1.794123649597168 +[2025-04-30 15:04:44,990][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 0.7083258032798767, cross_entropy: 0.7083258032798767 +[2025-04-30 15:04:45,305][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.133321762084961, cross_entropy: 2.133321762084961 +[2025-04-30 15:04:48,769][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.098502278327942, cross_entropy: 1.098502278327942 +[2025-04-30 15:04:49,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.5321729183197021, cross_entropy: 1.5321729183197021 +[2025-04-30 15:04:51,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 2.1128082275390625, cross_entropy: 2.1128082275390625 +[2025-04-30 15:04:52,207][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.8435932397842407, cross_entropy: 1.8435932397842407 +[2025-04-30 15:04:55,617][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.4683746099472046, cross_entropy: 1.4683746099472046 +[2025-04-30 15:04:55,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 3.2115540504455566, cross_entropy: 3.2115540504455566 +[2025-04-30 15:04:58,656][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.2226816415786743, cross_entropy: 1.2226816415786743 +[2025-04-30 15:04:58,934][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.148346424102783, cross_entropy: 2.148346424102783 +[2025-04-30 15:07:40,992][BaseTrainer][INFO] - [Epoch 7/10] (train) 1.8454569578170776, cross_entropy: 1.8454569578170776 +[2025-04-30 15:07:40,992][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.188611388206482, cross_entropy: 1.188611388206482 +[2025-04-30 15:07:40,992][BaseTrainer][INFO] - [Epoch 7/10] (metrics) roc_auc: 0.9813140630722046 +[2025-04-30 15:07:41,209][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 15:07:41,374][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch7.pth. +[2025-04-30 15:07:41,586][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 15:07:46,210][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 1.2565796375274658, cross_entropy: 1.2565796375274658 +[2025-04-30 15:07:46,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.0427355766296387, cross_entropy: 2.0427355766296387 +[2025-04-30 15:07:50,403][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 0.9052352905273438, cross_entropy: 0.9052352905273438 +[2025-04-30 15:07:50,742][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 3.084575653076172, cross_entropy: 3.084575653076172 +[2025-04-30 15:07:54,208][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 2.519615888595581, cross_entropy: 2.519615888595581 +[2025-04-30 15:07:54,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.2023282051086426, cross_entropy: 1.2023282051086426 +[2025-04-30 15:07:57,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 0.7956718802452087, cross_entropy: 0.7956718802452087 +[2025-04-30 15:07:57,994][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.7602195739746094, cross_entropy: 2.7602195739746094 +[2025-04-30 15:08:00,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 0.8207522630691528, cross_entropy: 0.8207522630691528 +[2025-04-30 15:08:01,187][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.607151985168457, cross_entropy: 1.607151985168457 +[2025-04-30 15:08:04,747][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 2.8388843536376953, cross_entropy: 2.8388843536376953 +[2025-04-30 15:08:05,092][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 0.8742675185203552, cross_entropy: 0.8742675185203552 +[2025-04-30 15:08:08,561][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 0.9886503219604492, cross_entropy: 0.9886503219604492 +[2025-04-30 15:08:08,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 2.4222803115844727, cross_entropy: 2.4222803115844727 +[2025-04-30 15:08:11,881][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 0.6870342493057251, cross_entropy: 0.6870342493057251 +[2025-04-30 15:08:12,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 0.5805928111076355, cross_entropy: 0.5805928111076355 +[2025-04-30 15:08:15,552][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 2.0252270698547363, cross_entropy: 2.0252270698547363 +[2025-04-30 15:08:15,962][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 2.275033473968506, cross_entropy: 2.275033473968506 +[2025-04-30 15:08:19,234][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 2.931832790374756, cross_entropy: 2.931832790374756 +[2025-04-30 15:08:19,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 0.6753553748130798, cross_entropy: 0.6753553748130798 +[2025-04-30 15:08:22,699][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.7367017269134521, cross_entropy: 1.7367017269134521 +[2025-04-30 15:08:23,087][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 2.724600315093994, cross_entropy: 2.724600315093994 +[2025-04-30 15:08:26,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.275465965270996, cross_entropy: 1.275465965270996 +[2025-04-30 15:08:27,114][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.491496205329895, cross_entropy: 1.491496205329895 +[2025-04-30 15:08:29,839][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 2.8737709522247314, cross_entropy: 2.8737709522247314 +[2025-04-30 15:08:30,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 2.263110876083374, cross_entropy: 2.263110876083374 +[2025-04-30 15:08:33,533][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 0.7316371202468872, cross_entropy: 0.7316371202468872 +[2025-04-30 15:08:34,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.0485801696777344, cross_entropy: 3.0485801696777344 +[2025-04-30 15:08:36,671][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.2797266244888306, cross_entropy: 1.2797266244888306 +[2025-04-30 15:08:37,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 1.2996433973312378, cross_entropy: 1.2996433973312378 +[2025-04-30 15:08:40,830][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 0.8363494873046875, cross_entropy: 0.8363494873046875 +[2025-04-30 15:08:41,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.236868143081665, cross_entropy: 2.236868143081665 +[2025-04-30 15:08:44,543][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 1.0664812326431274, cross_entropy: 1.0664812326431274 +[2025-04-30 15:08:45,549][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 3.0236129760742188, cross_entropy: 3.0236129760742188 +[2025-04-30 15:08:47,644][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 2.7903366088867188, cross_entropy: 2.7903366088867188 +[2025-04-30 15:08:48,681][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.3457012176513672, cross_entropy: 1.3457012176513672 +[2025-04-30 15:08:51,923][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 1.7698850631713867, cross_entropy: 1.7698850631713867 +[2025-04-30 15:08:52,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 2.79833722114563, cross_entropy: 2.79833722114563 +[2025-04-30 15:08:55,741][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 1.8931313753128052, cross_entropy: 1.8931313753128052 +[2025-04-30 15:08:56,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 1.599607229232788, cross_entropy: 1.599607229232788 +[2025-04-30 15:08:59,377][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 3.1005940437316895, cross_entropy: 3.1005940437316895 +[2025-04-30 15:09:00,314][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 1.2662224769592285, cross_entropy: 1.2662224769592285 +[2025-04-30 15:09:03,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.5317745208740234, cross_entropy: 1.5317745208740234 +[2025-04-30 15:09:04,009][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.0155720710754395, cross_entropy: 1.0155720710754395 +[2025-04-30 15:09:06,740][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 0.9742991328239441, cross_entropy: 0.9742991328239441 +[2025-04-30 15:09:07,683][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.9748785495758057, cross_entropy: 2.9748785495758057 +[2025-04-30 15:09:10,505][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.0498713254928589, cross_entropy: 1.0498713254928589 +[2025-04-30 15:09:11,621][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 2.8016085624694824, cross_entropy: 2.8016085624694824 +[2025-04-30 15:09:14,415][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 2.6395480632781982, cross_entropy: 2.6395480632781982 +[2025-04-30 15:09:15,236][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.381103992462158, cross_entropy: 2.381103992462158 +[2025-04-30 15:09:18,367][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 1.8175618648529053, cross_entropy: 1.8175618648529053 +[2025-04-30 15:09:18,827][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 1.623226284980774, cross_entropy: 1.623226284980774 +[2025-04-30 15:09:21,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 0.8503926992416382, cross_entropy: 0.8503926992416382 +[2025-04-30 15:09:21,969][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 1.7204889059066772, cross_entropy: 1.7204889059066772 +[2025-04-30 15:09:24,728][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 2.6618611812591553, cross_entropy: 2.6618611812591553 +[2025-04-30 15:09:26,048][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 0.9404700398445129, cross_entropy: 0.9404700398445129 +[2025-04-30 15:09:28,342][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.079516887664795, cross_entropy: 2.079516887664795 +[2025-04-30 15:09:29,780][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 1.0522959232330322, cross_entropy: 1.0522959232330322 +[2025-04-30 15:09:31,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 2.0340824127197266, cross_entropy: 2.0340824127197266 +[2025-04-30 15:09:32,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 0.6759480237960815, cross_entropy: 0.6759480237960815 +[2025-04-30 15:09:36,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 2.0144805908203125, cross_entropy: 2.0144805908203125 +[2025-04-30 15:09:36,703][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.4715638160705566, cross_entropy: 1.4715638160705566 +[2025-04-30 15:09:40,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.843553066253662, cross_entropy: 2.843553066253662 +[2025-04-30 15:09:40,851][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 2.81404972076416, cross_entropy: 2.81404972076416 +[2025-04-30 15:09:44,103][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.8223891258239746, cross_entropy: 2.8223891258239746 +[2025-04-30 15:09:44,658][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 0.767103374004364, cross_entropy: 0.767103374004364 +[2025-04-30 15:09:49,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 2.3092451095581055, cross_entropy: 2.3092451095581055 +[2025-04-30 15:09:49,725][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.9291963577270508, cross_entropy: 1.9291963577270508 +[2025-04-30 15:09:53,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 0.9255891442298889, cross_entropy: 0.9255891442298889 +[2025-04-30 15:09:53,432][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.8141183853149414, cross_entropy: 2.8141183853149414 +[2025-04-30 15:09:57,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 0.972133994102478, cross_entropy: 0.972133994102478 +[2025-04-30 15:09:57,757][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 2.587191343307495, cross_entropy: 2.587191343307495 +[2025-04-30 15:10:01,641][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.0783498287200928, cross_entropy: 1.0783498287200928 +[2025-04-30 15:10:01,974][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.4338183403015137, cross_entropy: 1.4338183403015137 +[2025-04-30 15:10:05,748][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.277653694152832, cross_entropy: 1.277653694152832 +[2025-04-30 15:10:06,063][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.7794556617736816, cross_entropy: 2.7794556617736816 +[2025-04-30 15:10:10,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.0929757356643677, cross_entropy: 1.0929757356643677 +[2025-04-30 15:10:10,396][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 0.7998617887496948, cross_entropy: 0.7998617887496948 +[2025-04-30 15:10:13,308][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 2.782341957092285, cross_entropy: 2.782341957092285 +[2025-04-30 15:10:13,648][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.6536293029785156, cross_entropy: 2.6536293029785156 +[2025-04-30 15:10:16,788][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 1.0962371826171875, cross_entropy: 1.0962371826171875 +[2025-04-30 15:10:17,103][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.243006706237793, cross_entropy: 1.243006706237793 +[2025-04-30 15:10:20,561][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 2.007441520690918, cross_entropy: 2.007441520690918 +[2025-04-30 15:10:20,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.2472569942474365, cross_entropy: 1.2472569942474365 +[2025-04-30 15:10:24,864][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.975435495376587, cross_entropy: 1.975435495376587 +[2025-04-30 15:10:25,178][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 1.044695258140564, cross_entropy: 1.044695258140564 +[2025-04-30 15:10:28,930][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 1.7840452194213867, cross_entropy: 1.7840452194213867 +[2025-04-30 15:10:29,271][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 2.975034713745117, cross_entropy: 2.975034713745117 +[2025-04-30 15:10:33,331][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 0.6849868297576904, cross_entropy: 0.6849868297576904 +[2025-04-30 15:10:33,672][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 0.9469341039657593, cross_entropy: 0.9469341039657593 +[2025-04-30 15:10:37,259][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 2.558476448059082, cross_entropy: 2.558476448059082 +[2025-04-30 15:10:37,573][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 1.002150535583496, cross_entropy: 1.002150535583496 +[2025-04-30 15:10:42,169][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 1.139965534210205, cross_entropy: 1.139965534210205 +[2025-04-30 15:10:42,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 0.93896484375, cross_entropy: 0.93896484375 +[2025-04-30 15:10:46,000][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.4469547271728516, cross_entropy: 1.4469547271728516 +[2025-04-30 15:10:46,343][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.415042757987976, cross_entropy: 1.415042757987976 +[2025-04-30 15:10:48,930][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.5864357948303223, cross_entropy: 2.5864357948303223 +[2025-04-30 15:10:49,244][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 0.8691685199737549, cross_entropy: 0.8691685199737549 +[2025-04-30 15:10:52,554][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.5227521657943726, cross_entropy: 1.5227521657943726 +[2025-04-30 15:10:52,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 1.1317297220230103, cross_entropy: 1.1317297220230103 +[2025-04-30 15:10:56,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.4458975791931152, cross_entropy: 2.4458975791931152 +[2025-04-30 15:10:57,137][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.0857529640197754, cross_entropy: 2.0857529640197754 +[2025-04-30 15:11:00,438][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 2.2343647480010986, cross_entropy: 2.2343647480010986 +[2025-04-30 15:11:00,775][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.3929589986801147, cross_entropy: 1.3929589986801147 +[2025-04-30 15:11:04,213][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 3.1598105430603027, cross_entropy: 3.1598105430603027 +[2025-04-30 15:11:04,557][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 2.5311858654022217, cross_entropy: 2.5311858654022217 +[2025-04-30 15:11:07,735][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.641615390777588, cross_entropy: 1.641615390777588 +[2025-04-30 15:11:08,048][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 2.947967290878296, cross_entropy: 2.947967290878296 +[2025-04-30 15:11:10,934][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 0.8053678274154663, cross_entropy: 0.8053678274154663 +[2025-04-30 15:11:11,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 2.4614644050598145, cross_entropy: 2.4614644050598145 +[2025-04-30 15:11:14,124][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 2.148273468017578, cross_entropy: 2.148273468017578 +[2025-04-30 15:11:14,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.9011726379394531, cross_entropy: 1.9011726379394531 +[2025-04-30 15:11:17,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 2.019089698791504, cross_entropy: 2.019089698791504 +[2025-04-30 15:11:17,579][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 0.9300253391265869, cross_entropy: 0.9300253391265869 +[2025-04-30 15:11:20,608][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.0225577354431152, cross_entropy: 2.0225577354431152 +[2025-04-30 15:11:20,925][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 1.4411925077438354, cross_entropy: 1.4411925077438354 +[2025-04-30 15:11:24,180][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.205301284790039, cross_entropy: 2.205301284790039 +[2025-04-30 15:11:24,521][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 1.193244457244873, cross_entropy: 1.193244457244873 +[2025-04-30 15:11:27,144][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 2.6874420642852783, cross_entropy: 2.6874420642852783 +[2025-04-30 15:11:27,547][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 1.6286877393722534, cross_entropy: 1.6286877393722534 +[2025-04-30 15:11:30,871][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 2.4346888065338135, cross_entropy: 2.4346888065338135 +[2025-04-30 15:11:31,215][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 0.6636993885040283, cross_entropy: 0.6636993885040283 +[2025-04-30 15:11:34,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.865748405456543, cross_entropy: 2.865748405456543 +[2025-04-30 15:11:34,565][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 1.4840707778930664, cross_entropy: 1.4840707778930664 +[2025-04-30 15:11:38,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 1.0869777202606201, cross_entropy: 1.0869777202606201 +[2025-04-30 15:11:38,994][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 0.7585257291793823, cross_entropy: 0.7585257291793823 +[2025-04-30 15:11:42,404][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 2.9526000022888184, cross_entropy: 2.9526000022888184 +[2025-04-30 15:11:42,717][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.9636871814727783, cross_entropy: 1.9636871814727783 +[2025-04-30 15:11:46,021][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 1.0320186614990234, cross_entropy: 1.0320186614990234 +[2025-04-30 15:11:46,355][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 0.7814072370529175, cross_entropy: 0.7814072370529175 +[2025-04-30 15:11:49,259][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 2.7783138751983643, cross_entropy: 2.7783138751983643 +[2025-04-30 15:11:49,595][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 2.063730478286743, cross_entropy: 2.063730478286743 +[2025-04-30 15:11:53,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 2.42289400100708, cross_entropy: 2.42289400100708 +[2025-04-30 15:11:53,795][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 1.2439448833465576, cross_entropy: 1.2439448833465576 +[2025-04-30 15:11:57,044][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 2.3348569869995117, cross_entropy: 2.3348569869995117 +[2025-04-30 15:11:57,360][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 2.6493353843688965, cross_entropy: 2.6493353843688965 +[2025-04-30 15:12:00,890][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 2.6940550804138184, cross_entropy: 2.6940550804138184 +[2025-04-30 15:12:01,213][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 2.783905267715454, cross_entropy: 2.783905267715454 +[2025-04-30 15:12:04,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 2.1298768520355225, cross_entropy: 2.1298768520355225 +[2025-04-30 15:12:05,235][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 0.954177975654602, cross_entropy: 0.954177975654602 +[2025-04-30 15:12:08,741][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 0.9615987539291382, cross_entropy: 0.9615987539291382 +[2025-04-30 15:12:09,078][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 2.6861462593078613, cross_entropy: 2.6861462593078613 +[2025-04-30 15:12:12,415][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.102156639099121, cross_entropy: 1.102156639099121 +[2025-04-30 15:12:12,749][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 2.6216583251953125, cross_entropy: 2.6216583251953125 +[2025-04-30 15:12:15,814][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 3.0602874755859375, cross_entropy: 3.0602874755859375 +[2025-04-30 15:12:16,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.597230911254883, cross_entropy: 2.597230911254883 +[2025-04-30 15:12:19,118][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 1.2735027074813843, cross_entropy: 1.2735027074813843 +[2025-04-30 15:12:19,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 0.6787785291671753, cross_entropy: 0.6787785291671753 +[2025-04-30 15:12:23,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 0.693012535572052, cross_entropy: 0.693012535572052 +[2025-04-30 15:12:23,596][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 1.1933563947677612, cross_entropy: 1.1933563947677612 +[2025-04-30 15:12:26,503][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.1379799842834473, cross_entropy: 2.1379799842834473 +[2025-04-30 15:12:26,845][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.3665779829025269, cross_entropy: 1.3665779829025269 +[2025-04-30 15:12:29,966][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.5955917835235596, cross_entropy: 1.5955917835235596 +[2025-04-30 15:12:30,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 1.1355340480804443, cross_entropy: 1.1355340480804443 +[2025-04-30 15:12:33,527][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.9381721019744873, cross_entropy: 1.9381721019744873 +[2025-04-30 15:12:33,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.174461007118225, cross_entropy: 1.174461007118225 +[2025-04-30 15:12:36,888][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 1.2670317888259888, cross_entropy: 1.2670317888259888 +[2025-04-30 15:12:37,235][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 0.726018488407135, cross_entropy: 0.726018488407135 +[2025-04-30 15:12:40,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.411747694015503, cross_entropy: 2.411747694015503 +[2025-04-30 15:12:40,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 2.881971836090088, cross_entropy: 2.881971836090088 +[2025-04-30 15:12:44,373][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.5188169479370117, cross_entropy: 1.5188169479370117 +[2025-04-30 15:12:44,716][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 3.1149001121520996, cross_entropy: 3.1149001121520996 +[2025-04-30 15:12:47,649][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 2.82814359664917, cross_entropy: 2.82814359664917 +[2025-04-30 15:12:47,980][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 1.5363132953643799, cross_entropy: 1.5363132953643799 +[2025-04-30 15:12:50,694][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 2.6192870140075684, cross_entropy: 2.6192870140075684 +[2025-04-30 15:12:51,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.249993085861206, cross_entropy: 1.249993085861206 +[2025-04-30 15:12:53,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.7712364196777344, cross_entropy: 2.7712364196777344 +[2025-04-30 15:12:54,223][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 0.695213258266449, cross_entropy: 0.695213258266449 +[2025-04-30 15:12:57,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 1.9083595275878906, cross_entropy: 1.9083595275878906 +[2025-04-30 15:12:57,489][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 1.0671300888061523, cross_entropy: 1.0671300888061523 +[2025-04-30 15:13:00,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 0.8118616938591003, cross_entropy: 0.8118616938591003 +[2025-04-30 15:13:00,912][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.184838891029358, cross_entropy: 1.184838891029358 +[2025-04-30 15:13:04,646][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 1.379581332206726, cross_entropy: 1.379581332206726 +[2025-04-30 15:13:05,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.8601082563400269, cross_entropy: 1.8601082563400269 +[2025-04-30 15:13:08,272][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 0.7883740663528442, cross_entropy: 0.7883740663528442 +[2025-04-30 15:13:08,647][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.9564493298530579, cross_entropy: 0.9564493298530579 +[2025-04-30 15:13:11,281][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.0664172172546387, cross_entropy: 1.0664172172546387 +[2025-04-30 15:13:11,991][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 1.9883811473846436, cross_entropy: 1.9883811473846436 +[2025-04-30 15:13:15,302][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.2566717863082886, cross_entropy: 1.2566717863082886 +[2025-04-30 15:13:15,836][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 2.456435441970825, cross_entropy: 2.456435441970825 +[2025-04-30 15:13:18,836][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.8569788932800293, cross_entropy: 2.8569788932800293 +[2025-04-30 15:13:19,533][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 2.8847761154174805, cross_entropy: 2.8847761154174805 +[2025-04-30 15:13:22,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 2.813544511795044, cross_entropy: 2.813544511795044 +[2025-04-30 15:13:23,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 3.0088014602661133, cross_entropy: 3.0088014602661133 +[2025-04-30 15:13:26,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.7807254791259766, cross_entropy: 2.7807254791259766 +[2025-04-30 15:13:26,629][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 1.6706669330596924, cross_entropy: 1.6706669330596924 +[2025-04-30 15:13:29,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 1.307129144668579, cross_entropy: 1.307129144668579 +[2025-04-30 15:13:30,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 2.8173274993896484, cross_entropy: 2.8173274993896484 +[2025-04-30 15:13:33,041][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 1.8005443811416626, cross_entropy: 1.8005443811416626 +[2025-04-30 15:13:34,665][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 0.9266940355300903, cross_entropy: 0.9266940355300903 +[2025-04-30 15:13:36,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.0247788429260254, cross_entropy: 2.0247788429260254 +[2025-04-30 15:13:38,088][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.261692762374878, cross_entropy: 1.261692762374878 +[2025-04-30 15:13:40,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 1.9038171768188477, cross_entropy: 1.9038171768188477 +[2025-04-30 15:13:41,312][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.741079568862915, cross_entropy: 1.741079568862915 +[2025-04-30 15:13:43,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 0.6718294620513916, cross_entropy: 0.6718294620513916 +[2025-04-30 15:13:44,321][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 1.9332668781280518, cross_entropy: 1.9332668781280518 +[2025-04-30 15:13:47,014][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 2.6577043533325195, cross_entropy: 2.6577043533325195 +[2025-04-30 15:13:47,993][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 1.8468377590179443, cross_entropy: 1.8468377590179443 +[2025-04-30 15:13:50,780][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 2.8862862586975098, cross_entropy: 2.8862862586975098 +[2025-04-30 15:13:51,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 1.5582871437072754, cross_entropy: 1.5582871437072754 +[2025-04-30 15:13:54,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 2.2030515670776367, cross_entropy: 2.2030515670776367 +[2025-04-30 15:13:54,679][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 3.1235013008117676, cross_entropy: 3.1235013008117676 +[2025-04-30 15:13:57,438][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.4896836280822754, cross_entropy: 2.4896836280822754 +[2025-04-30 15:13:57,784][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.6252589225769043, cross_entropy: 2.6252589225769043 +[2025-04-30 15:14:01,224][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 0.8605279922485352, cross_entropy: 0.8605279922485352 +[2025-04-30 15:14:01,538][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 0.9675999879837036, cross_entropy: 0.9675999879837036 +[2025-04-30 15:14:04,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 0.950365424156189, cross_entropy: 0.950365424156189 +[2025-04-30 15:14:04,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 0.9403486251831055, cross_entropy: 0.9403486251831055 +[2025-04-30 15:14:08,265][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 2.8651559352874756, cross_entropy: 2.8651559352874756 +[2025-04-30 15:14:08,580][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 2.7971842288970947, cross_entropy: 2.7971842288970947 +[2025-04-30 15:14:11,621][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 2.7084388732910156, cross_entropy: 2.7084388732910156 +[2025-04-30 15:14:11,933][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.899886131286621, cross_entropy: 2.899886131286621 +[2025-04-30 15:14:15,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.1404178142547607, cross_entropy: 1.1404178142547607 +[2025-04-30 15:14:15,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 2.8700246810913086, cross_entropy: 2.8700246810913086 +[2025-04-30 15:14:19,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 2.6267831325531006, cross_entropy: 2.6267831325531006 +[2025-04-30 15:14:19,666][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 2.8564767837524414, cross_entropy: 2.8564767837524414 +[2025-04-30 15:14:22,553][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.5134787559509277, cross_entropy: 2.5134787559509277 +[2025-04-30 15:14:22,924][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 2.7996859550476074, cross_entropy: 2.7996859550476074 +[2025-04-30 15:14:27,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 0.8515516519546509, cross_entropy: 0.8515516519546509 +[2025-04-30 15:14:27,639][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.1880173683166504, cross_entropy: 2.1880173683166504 +[2025-04-30 15:14:31,241][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 0.6784487366676331, cross_entropy: 0.6784487366676331 +[2025-04-30 15:14:31,554][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 2.016718864440918, cross_entropy: 2.016718864440918 +[2025-04-30 15:14:34,963][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 2.7032670974731445, cross_entropy: 2.7032670974731445 +[2025-04-30 15:14:35,298][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 2.4979450702667236, cross_entropy: 2.4979450702667236 +[2025-04-30 15:14:38,019][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.537058711051941, cross_entropy: 1.537058711051941 +[2025-04-30 15:14:38,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 2.2189648151397705, cross_entropy: 2.2189648151397705 +[2025-04-30 15:14:41,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.5958259105682373, cross_entropy: 1.5958259105682373 +[2025-04-30 15:14:41,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.1383558511734009, cross_entropy: 1.1383558511734009 +[2025-04-30 15:14:45,300][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 2.309518337249756, cross_entropy: 2.309518337249756 +[2025-04-30 15:14:45,639][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 1.6597529649734497, cross_entropy: 1.6597529649734497 +[2025-04-30 15:14:48,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 1.020033597946167, cross_entropy: 1.020033597946167 +[2025-04-30 15:14:48,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.3742127418518066, cross_entropy: 1.3742127418518066 +[2025-04-30 15:14:52,557][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 0.7657328844070435, cross_entropy: 0.7657328844070435 +[2025-04-30 15:14:52,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 1.038698673248291, cross_entropy: 1.038698673248291 +[2025-04-30 15:14:55,883][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.939344882965088, cross_entropy: 1.939344882965088 +[2025-04-30 15:14:56,785][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 1.7427093982696533, cross_entropy: 1.7427093982696533 +[2025-04-30 15:15:00,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 2.5696845054626465, cross_entropy: 2.5696845054626465 +[2025-04-30 15:15:00,502][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 2.9708638191223145, cross_entropy: 2.9708638191223145 +[2025-04-30 15:15:03,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 0.851546049118042, cross_entropy: 0.851546049118042 +[2025-04-30 15:15:04,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 3.0709164142608643, cross_entropy: 3.0709164142608643 +[2025-04-30 15:15:07,132][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 1.9152060747146606, cross_entropy: 1.9152060747146606 +[2025-04-30 15:15:07,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.111154079437256, cross_entropy: 2.111154079437256 +[2025-04-30 15:15:10,790][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 1.1293253898620605, cross_entropy: 1.1293253898620605 +[2025-04-30 15:15:11,135][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 0.9689472913742065, cross_entropy: 0.9689472913742065 +[2025-04-30 15:15:14,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 2.2430150508880615, cross_entropy: 2.2430150508880615 +[2025-04-30 15:15:14,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.1500282287597656, cross_entropy: 2.1500282287597656 +[2025-04-30 15:15:18,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 1.5139620304107666, cross_entropy: 1.5139620304107666 +[2025-04-30 15:15:18,736][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.2145612239837646, cross_entropy: 1.2145612239837646 +[2025-04-30 15:15:22,171][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 2.832853317260742, cross_entropy: 2.832853317260742 +[2025-04-30 15:15:22,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 2.0268051624298096, cross_entropy: 2.0268051624298096 +[2025-04-30 15:15:25,526][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 2.968507766723633, cross_entropy: 2.968507766723633 +[2025-04-30 15:15:25,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 1.0091701745986938, cross_entropy: 1.0091701745986938 +[2025-04-30 15:15:28,892][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.444199800491333, cross_entropy: 1.444199800491333 +[2025-04-30 15:15:29,240][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 2.5144386291503906, cross_entropy: 2.5144386291503906 +[2025-04-30 15:15:32,893][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 2.8629989624023438, cross_entropy: 2.8629989624023438 +[2025-04-30 15:15:33,209][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 2.0317277908325195, cross_entropy: 2.0317277908325195 +[2025-04-30 15:15:36,554][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 1.2851663827896118, cross_entropy: 1.2851663827896118 +[2025-04-30 15:15:36,885][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.9686741828918457, cross_entropy: 1.9686741828918457 +[2025-04-30 15:15:39,777][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.1150593757629395, cross_entropy: 1.1150593757629395 +[2025-04-30 15:15:40,119][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 1.3767865896224976, cross_entropy: 1.3767865896224976 +[2025-04-30 15:15:44,163][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 2.509343385696411, cross_entropy: 2.509343385696411 +[2025-04-30 15:15:44,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 1.1384971141815186, cross_entropy: 1.1384971141815186 +[2025-04-30 15:15:48,189][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 3.08571720123291, cross_entropy: 3.08571720123291 +[2025-04-30 15:15:48,525][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 0.5666482448577881, cross_entropy: 0.5666482448577881 +[2025-04-30 15:15:51,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 1.4243409633636475, cross_entropy: 1.4243409633636475 +[2025-04-30 15:15:52,176][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 0.9471985101699829, cross_entropy: 0.9471985101699829 +[2025-04-30 15:15:55,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 2.644587993621826, cross_entropy: 2.644587993621826 +[2025-04-30 15:15:56,300][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 1.2351067066192627, cross_entropy: 1.2351067066192627 +[2025-04-30 15:15:59,682][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 2.5914974212646484, cross_entropy: 2.5914974212646484 +[2025-04-30 15:16:00,017][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 2.5617477893829346, cross_entropy: 2.5617477893829346 +[2025-04-30 15:16:03,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 3.239614725112915, cross_entropy: 3.239614725112915 +[2025-04-30 15:16:03,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 2.313917398452759, cross_entropy: 2.313917398452759 +[2025-04-30 15:16:06,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 2.9601426124572754, cross_entropy: 2.9601426124572754 +[2025-04-30 15:16:07,110][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.191372871398926, cross_entropy: 2.191372871398926 +[2025-04-30 15:16:11,015][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 3.1751904487609863, cross_entropy: 3.1751904487609863 +[2025-04-30 15:16:11,333][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.297410011291504, cross_entropy: 1.297410011291504 +[2025-04-30 15:16:14,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 2.6893434524536133, cross_entropy: 2.6893434524536133 +[2025-04-30 15:16:14,841][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 1.1773707866668701, cross_entropy: 1.1773707866668701 +[2025-04-30 15:16:19,176][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 1.1053352355957031, cross_entropy: 1.1053352355957031 +[2025-04-30 15:16:19,510][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 0.8080753684043884, cross_entropy: 0.8080753684043884 +[2025-04-30 15:16:22,882][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.2325077056884766, cross_entropy: 2.2325077056884766 +[2025-04-30 15:16:23,221][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.655040740966797, cross_entropy: 2.655040740966797 +[2025-04-30 15:16:27,912][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 2.5571656227111816, cross_entropy: 2.5571656227111816 +[2025-04-30 15:16:28,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 2.8095273971557617, cross_entropy: 2.8095273971557617 +[2025-04-30 15:16:31,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 0.8935238122940063, cross_entropy: 0.8935238122940063 +[2025-04-30 15:16:31,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 1.7486741542816162, cross_entropy: 1.7486741542816162 +[2025-04-30 15:16:34,435][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 0.9654077887535095, cross_entropy: 0.9654077887535095 +[2025-04-30 15:16:34,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 0.8968276381492615, cross_entropy: 0.8968276381492615 +[2025-04-30 15:16:39,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 1.3538554906845093, cross_entropy: 1.3538554906845093 +[2025-04-30 15:16:40,104][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.1972408294677734, cross_entropy: 1.1972408294677734 +[2025-04-30 15:16:43,547][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.6195242404937744, cross_entropy: 1.6195242404937744 +[2025-04-30 15:16:43,861][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 3.0076792240142822, cross_entropy: 3.0076792240142822 +[2025-04-30 15:16:47,010][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 2.732422351837158, cross_entropy: 2.732422351837158 +[2025-04-30 15:16:47,323][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 3.0663294792175293, cross_entropy: 3.0663294792175293 +[2025-04-30 15:16:51,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.9980227947235107, cross_entropy: 1.9980227947235107 +[2025-04-30 15:16:51,476][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 0.8941977024078369, cross_entropy: 0.8941977024078369 +[2025-04-30 15:16:55,329][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 1.9938515424728394, cross_entropy: 1.9938515424728394 +[2025-04-30 15:16:55,659][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 1.9591522216796875, cross_entropy: 1.9591522216796875 +[2025-04-30 15:16:59,312][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 2.9806394577026367, cross_entropy: 2.9806394577026367 +[2025-04-30 15:16:59,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 1.1061680316925049, cross_entropy: 1.1061680316925049 +[2025-04-30 15:17:03,260][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 2.74375581741333, cross_entropy: 2.74375581741333 +[2025-04-30 15:17:03,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.6978801488876343, cross_entropy: 1.6978801488876343 +[2025-04-30 15:17:06,458][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 1.9970753192901611, cross_entropy: 1.9970753192901611 +[2025-04-30 15:17:06,773][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 0.7859334349632263, cross_entropy: 0.7859334349632263 +[2025-04-30 15:17:10,179][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 1.1986387968063354, cross_entropy: 1.1986387968063354 +[2025-04-30 15:17:10,525][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.1735363006591797, cross_entropy: 1.1735363006591797 +[2025-04-30 15:17:13,580][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.0600581169128418, cross_entropy: 1.0600581169128418 +[2025-04-30 15:17:13,894][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.0892878770828247, cross_entropy: 1.0892878770828247 +[2025-04-30 15:17:16,714][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.1725176572799683, cross_entropy: 1.1725176572799683 +[2025-04-30 15:17:17,048][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 1.7406996488571167, cross_entropy: 1.7406996488571167 +[2025-04-30 15:17:20,184][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 2.6639206409454346, cross_entropy: 2.6639206409454346 +[2025-04-30 15:17:20,497][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 1.5549395084381104, cross_entropy: 1.5549395084381104 +[2025-04-30 15:17:23,809][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 0.6159573793411255, cross_entropy: 0.6159573793411255 +[2025-04-30 15:17:24,154][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 1.6266610622406006, cross_entropy: 1.6266610622406006 +[2025-04-30 15:17:27,377][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 0.8697733879089355, cross_entropy: 0.8697733879089355 +[2025-04-30 15:17:27,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 0.7925747632980347, cross_entropy: 0.7925747632980347 +[2025-04-30 15:17:32,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 0.4964464008808136, cross_entropy: 0.4964464008808136 +[2025-04-30 15:17:32,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 2.7831902503967285, cross_entropy: 2.7831902503967285 +[2025-04-30 15:17:36,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.4487922191619873, cross_entropy: 1.4487922191619873 +[2025-04-30 15:17:36,810][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.4190995693206787, cross_entropy: 1.4190995693206787 +[2025-04-30 15:17:40,615][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 2.696800947189331, cross_entropy: 2.696800947189331 +[2025-04-30 15:17:40,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 0.7903436422348022, cross_entropy: 0.7903436422348022 +[2025-04-30 15:17:44,473][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.6229863166809082, cross_entropy: 1.6229863166809082 +[2025-04-30 15:17:44,827][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 1.9415721893310547, cross_entropy: 1.9415721893310547 +[2025-04-30 15:17:49,323][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 0.9901243448257446, cross_entropy: 0.9901243448257446 +[2025-04-30 15:17:49,660][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 2.73036527633667, cross_entropy: 2.73036527633667 +[2025-04-30 15:17:52,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 2.9388108253479004, cross_entropy: 2.9388108253479004 +[2025-04-30 15:17:53,141][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.83858323097229, cross_entropy: 1.83858323097229 +[2025-04-30 15:17:56,911][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.393944263458252, cross_entropy: 1.393944263458252 +[2025-04-30 15:17:57,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 1.0079329013824463, cross_entropy: 1.0079329013824463 +[2025-04-30 15:18:01,096][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 1.0985386371612549, cross_entropy: 1.0985386371612549 +[2025-04-30 15:18:01,454][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 1.2498631477355957, cross_entropy: 1.2498631477355957 +[2025-04-30 15:18:05,381][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.2198994159698486, cross_entropy: 1.2198994159698486 +[2025-04-30 15:18:05,722][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 1.3353545665740967, cross_entropy: 1.3353545665740967 +[2025-04-30 15:18:09,544][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 3.0759403705596924, cross_entropy: 3.0759403705596924 +[2025-04-30 15:18:09,887][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 0.9257407188415527, cross_entropy: 0.9257407188415527 +[2025-04-30 15:18:13,974][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 1.5659544467926025, cross_entropy: 1.5659544467926025 +[2025-04-30 15:18:14,297][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.1844837665557861, cross_entropy: 1.1844837665557861 +[2025-04-30 15:18:17,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.8985337018966675, cross_entropy: 1.8985337018966675 +[2025-04-30 15:18:17,544][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 3.0394129753112793, cross_entropy: 3.0394129753112793 +[2025-04-30 15:18:20,581][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 0.9726794958114624, cross_entropy: 0.9726794958114624 +[2025-04-30 15:18:20,913][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.7115726470947266, cross_entropy: 2.7115726470947266 +[2025-04-30 15:18:24,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.7683358192443848, cross_entropy: 2.7683358192443848 +[2025-04-30 15:18:24,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 1.9787373542785645, cross_entropy: 1.9787373542785645 +[2025-04-30 15:18:28,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.5374337434768677, cross_entropy: 1.5374337434768677 +[2025-04-30 15:18:28,710][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 2.4414637088775635, cross_entropy: 2.4414637088775635 +[2025-04-30 15:18:31,929][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 2.5626893043518066, cross_entropy: 2.5626893043518066 +[2025-04-30 15:18:32,261][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 1.0855085849761963, cross_entropy: 1.0855085849761963 +[2025-04-30 15:18:35,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.692314624786377, cross_entropy: 2.692314624786377 +[2025-04-30 15:18:35,768][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 1.5567989349365234, cross_entropy: 1.5567989349365234 +[2025-04-30 15:18:39,004][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 1.166528344154358, cross_entropy: 1.166528344154358 +[2025-04-30 15:18:39,352][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 3.0023303031921387, cross_entropy: 3.0023303031921387 +[2025-04-30 15:18:42,465][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 2.6696889400482178, cross_entropy: 2.6696889400482178 +[2025-04-30 15:18:42,800][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 2.830535411834717, cross_entropy: 2.830535411834717 +[2025-04-30 15:18:45,885][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 2.640859842300415, cross_entropy: 2.640859842300415 +[2025-04-30 15:18:46,168][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 0.8834854960441589, cross_entropy: 0.8834854960441589 +[2025-04-30 15:21:46,519][BaseTrainer][INFO] - [Epoch 8/10] (train) 1.829209327697754, cross_entropy: 1.829209327697754 +[2025-04-30 15:21:46,520][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.262538194656372, cross_entropy: 1.262538194656372 +[2025-04-30 15:21:46,520][BaseTrainer][INFO] - [Epoch 8/10] (metrics) roc_auc: 0.9784096479415894 +[2025-04-30 15:21:46,816][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch8.pth. +[2025-04-30 15:21:47,096][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 15:21:51,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 1.4758703708648682, cross_entropy: 1.4758703708648682 +[2025-04-30 15:21:52,576][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.1660916805267334, cross_entropy: 1.1660916805267334 +[2025-04-30 15:21:55,953][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 2.7555203437805176, cross_entropy: 2.7555203437805176 +[2025-04-30 15:21:56,297][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 3.0083656311035156, cross_entropy: 3.0083656311035156 +[2025-04-30 15:21:59,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 2.789581775665283, cross_entropy: 2.789581775665283 +[2025-04-30 15:21:59,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.0449224710464478, cross_entropy: 1.0449224710464478 +[2025-04-30 15:22:03,090][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.2873117923736572, cross_entropy: 2.2873117923736572 +[2025-04-30 15:22:03,431][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 2.207364320755005, cross_entropy: 2.207364320755005 +[2025-04-30 15:22:06,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.0668299198150635, cross_entropy: 2.0668299198150635 +[2025-04-30 15:22:06,871][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 3.0927789211273193, cross_entropy: 3.0927789211273193 +[2025-04-30 15:22:09,929][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.2265275716781616, cross_entropy: 1.2265275716781616 +[2025-04-30 15:22:11,477][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 0.6953235864639282, cross_entropy: 0.6953235864639282 +[2025-04-30 15:22:14,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.9321489334106445, cross_entropy: 2.9321489334106445 +[2025-04-30 15:22:14,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 0.8518950343132019, cross_entropy: 0.8518950343132019 +[2025-04-30 15:22:18,419][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.7497947216033936, cross_entropy: 2.7497947216033936 +[2025-04-30 15:22:18,756][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 0.9978737235069275, cross_entropy: 0.9978737235069275 +[2025-04-30 15:22:22,183][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 0.7921291589736938, cross_entropy: 0.7921291589736938 +[2025-04-30 15:22:22,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 0.9657843112945557, cross_entropy: 0.9657843112945557 +[2025-04-30 15:22:25,051][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 0.8109214305877686, cross_entropy: 0.8109214305877686 +[2025-04-30 15:22:25,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.5517222881317139, cross_entropy: 1.5517222881317139 +[2025-04-30 15:22:28,980][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.7487847805023193, cross_entropy: 1.7487847805023193 +[2025-04-30 15:22:29,294][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 1.3742986917495728, cross_entropy: 1.3742986917495728 +[2025-04-30 15:22:33,405][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 2.4479923248291016, cross_entropy: 2.4479923248291016 +[2025-04-30 15:22:33,723][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 2.4548871517181396, cross_entropy: 2.4548871517181396 +[2025-04-30 15:22:37,787][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 2.8584322929382324, cross_entropy: 2.8584322929382324 +[2025-04-30 15:22:38,137][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 1.7002967596054077, cross_entropy: 1.7002967596054077 +[2025-04-30 15:22:41,135][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.7907850742340088, cross_entropy: 1.7907850742340088 +[2025-04-30 15:22:41,450][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.041257381439209, cross_entropy: 2.041257381439209 +[2025-04-30 15:22:44,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 2.289119005203247, cross_entropy: 2.289119005203247 +[2025-04-30 15:22:45,270][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.3849539756774902, cross_entropy: 1.3849539756774902 +[2025-04-30 15:22:49,041][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 2.7970409393310547, cross_entropy: 2.7970409393310547 +[2025-04-30 15:22:49,356][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.435049295425415, cross_entropy: 1.435049295425415 +[2025-04-30 15:22:53,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.5481212139129639, cross_entropy: 1.5481212139129639 +[2025-04-30 15:22:53,718][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.4041688442230225, cross_entropy: 2.4041688442230225 +[2025-04-30 15:22:57,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 2.8218085765838623, cross_entropy: 2.8218085765838623 +[2025-04-30 15:22:57,638][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 0.8238828182220459, cross_entropy: 0.8238828182220459 +[2025-04-30 15:23:01,266][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 0.8792058229446411, cross_entropy: 0.8792058229446411 +[2025-04-30 15:23:01,583][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 2.74165678024292, cross_entropy: 2.74165678024292 +[2025-04-30 15:23:05,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 0.8031415343284607, cross_entropy: 0.8031415343284607 +[2025-04-30 15:23:05,374][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.879624366760254, cross_entropy: 2.879624366760254 +[2025-04-30 15:23:08,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 2.813106060028076, cross_entropy: 2.813106060028076 +[2025-04-30 15:23:09,038][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.472498893737793, cross_entropy: 2.472498893737793 +[2025-04-30 15:23:12,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.33917236328125, cross_entropy: 2.33917236328125 +[2025-04-30 15:23:12,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 0.6771542429924011, cross_entropy: 0.6771542429924011 +[2025-04-30 15:23:16,209][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.7317734956741333, cross_entropy: 0.7317734956741333 +[2025-04-30 15:23:16,554][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 1.8155666589736938, cross_entropy: 1.8155666589736938 +[2025-04-30 15:23:20,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 3.092830181121826, cross_entropy: 3.092830181121826 +[2025-04-30 15:23:20,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 2.9474356174468994, cross_entropy: 2.9474356174468994 +[2025-04-30 15:23:24,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 3.0701684951782227, cross_entropy: 3.0701684951782227 +[2025-04-30 15:23:24,906][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 0.7814634442329407, cross_entropy: 0.7814634442329407 +[2025-04-30 15:23:28,947][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 1.380408525466919, cross_entropy: 1.380408525466919 +[2025-04-30 15:23:29,289][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 1.0350642204284668, cross_entropy: 1.0350642204284668 +[2025-04-30 15:23:32,583][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 0.6348593235015869, cross_entropy: 0.6348593235015869 +[2025-04-30 15:23:33,021][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.3961732387542725, cross_entropy: 1.3961732387542725 +[2025-04-30 15:23:36,099][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 1.4040334224700928, cross_entropy: 1.4040334224700928 +[2025-04-30 15:23:37,640][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 3.221673011779785, cross_entropy: 3.221673011779785 +[2025-04-30 15:23:39,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 0.6083776950836182, cross_entropy: 0.6083776950836182 +[2025-04-30 15:23:41,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 0.9538379907608032, cross_entropy: 0.9538379907608032 +[2025-04-30 15:23:43,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.5443894863128662, cross_entropy: 1.5443894863128662 +[2025-04-30 15:23:45,373][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 3.052966594696045, cross_entropy: 3.052966594696045 +[2025-04-30 15:23:46,863][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 2.0251615047454834, cross_entropy: 2.0251615047454834 +[2025-04-30 15:23:49,135][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.2071375846862793, cross_entropy: 2.2071375846862793 +[2025-04-30 15:23:50,695][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 0.7800576686859131, cross_entropy: 0.7800576686859131 +[2025-04-30 15:23:52,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.3049585819244385, cross_entropy: 1.3049585819244385 +[2025-04-30 15:23:54,268][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 2.8251423835754395, cross_entropy: 2.8251423835754395 +[2025-04-30 15:23:57,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.891547441482544, cross_entropy: 0.891547441482544 +[2025-04-30 15:23:59,446][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 0.5067335963249207, cross_entropy: 0.5067335963249207 +[2025-04-30 15:24:01,377][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 0.7464828491210938, cross_entropy: 0.7464828491210938 +[2025-04-30 15:24:03,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 0.8202899694442749, cross_entropy: 0.8202899694442749 +[2025-04-30 15:24:04,599][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.1962156295776367, cross_entropy: 1.1962156295776367 +[2025-04-30 15:24:07,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 0.7773300409317017, cross_entropy: 0.7773300409317017 +[2025-04-30 15:24:07,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.1469151973724365, cross_entropy: 1.1469151973724365 +[2025-04-30 15:24:10,828][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 1.0254435539245605, cross_entropy: 1.0254435539245605 +[2025-04-30 15:24:11,367][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 0.69046550989151, cross_entropy: 0.69046550989151 +[2025-04-30 15:24:14,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 2.054243564605713, cross_entropy: 2.054243564605713 +[2025-04-30 15:24:14,786][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 2.7212748527526855, cross_entropy: 2.7212748527526855 +[2025-04-30 15:24:17,890][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 2.580749034881592, cross_entropy: 2.580749034881592 +[2025-04-30 15:24:18,227][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 0.5711842179298401, cross_entropy: 0.5711842179298401 +[2025-04-30 15:24:21,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 2.5580995082855225, cross_entropy: 2.5580995082855225 +[2025-04-30 15:24:21,734][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 0.9780341982841492, cross_entropy: 0.9780341982841492 +[2025-04-30 15:24:24,555][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.8822014331817627, cross_entropy: 1.8822014331817627 +[2025-04-30 15:24:25,762][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 0.8833595514297485, cross_entropy: 0.8833595514297485 +[2025-04-30 15:24:28,509][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.0969315767288208, cross_entropy: 1.0969315767288208 +[2025-04-30 15:24:31,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 2.8464808464050293, cross_entropy: 2.8464808464050293 +[2025-04-30 15:24:31,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 1.180781602859497, cross_entropy: 1.180781602859497 +[2025-04-30 15:24:35,153][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 1.4701340198516846, cross_entropy: 1.4701340198516846 +[2025-04-30 15:24:35,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 2.5237374305725098, cross_entropy: 2.5237374305725098 +[2025-04-30 15:24:38,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 1.8169537782669067, cross_entropy: 1.8169537782669067 +[2025-04-30 15:24:39,146][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 0.7473058700561523, cross_entropy: 0.7473058700561523 +[2025-04-30 15:24:41,992][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 2.3170413970947266, cross_entropy: 2.3170413970947266 +[2025-04-30 15:24:42,357][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 2.910954236984253, cross_entropy: 2.910954236984253 +[2025-04-30 15:24:45,635][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 1.6696138381958008, cross_entropy: 1.6696138381958008 +[2025-04-30 15:24:45,948][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.760653257369995, cross_entropy: 2.760653257369995 +[2025-04-30 15:24:49,176][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 0.9234439134597778, cross_entropy: 0.9234439134597778 +[2025-04-30 15:24:49,490][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 1.8915647268295288, cross_entropy: 1.8915647268295288 +[2025-04-30 15:24:53,138][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 0.9789177775382996, cross_entropy: 0.9789177775382996 +[2025-04-30 15:24:53,481][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 2.6663765907287598, cross_entropy: 2.6663765907287598 +[2025-04-30 15:24:57,205][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 1.31190824508667, cross_entropy: 1.31190824508667 +[2025-04-30 15:24:57,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 1.5121796131134033, cross_entropy: 1.5121796131134033 +[2025-04-30 15:25:01,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.325502634048462, cross_entropy: 1.325502634048462 +[2025-04-30 15:25:01,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 2.9519782066345215, cross_entropy: 2.9519782066345215 +[2025-04-30 15:25:04,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 2.6690256595611572, cross_entropy: 2.6690256595611572 +[2025-04-30 15:25:04,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.3049572706222534, cross_entropy: 1.3049572706222534 +[2025-04-30 15:25:07,357][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.9229745864868164, cross_entropy: 2.9229745864868164 +[2025-04-30 15:25:07,697][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 0.9004834294319153, cross_entropy: 0.9004834294319153 +[2025-04-30 15:25:10,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 2.8206632137298584, cross_entropy: 2.8206632137298584 +[2025-04-30 15:25:10,465][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.7098472118377686, cross_entropy: 2.7098472118377686 +[2025-04-30 15:25:13,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 0.7954196929931641, cross_entropy: 0.7954196929931641 +[2025-04-30 15:25:13,605][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 2.944248676300049, cross_entropy: 2.944248676300049 +[2025-04-30 15:25:17,310][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 0.9813591837882996, cross_entropy: 0.9813591837882996 +[2025-04-30 15:25:17,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 2.910130739212036, cross_entropy: 2.910130739212036 +[2025-04-30 15:25:20,376][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.3010075092315674, cross_entropy: 2.3010075092315674 +[2025-04-30 15:25:20,691][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 2.4088311195373535, cross_entropy: 2.4088311195373535 +[2025-04-30 15:25:23,597][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.5064265727996826, cross_entropy: 1.5064265727996826 +[2025-04-30 15:25:23,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.520637035369873, cross_entropy: 2.520637035369873 +[2025-04-30 15:25:26,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 1.2075012922286987, cross_entropy: 1.2075012922286987 +[2025-04-30 15:25:26,948][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 0.9638864994049072, cross_entropy: 0.9638864994049072 +[2025-04-30 15:25:29,836][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 2.0213863849639893, cross_entropy: 2.0213863849639893 +[2025-04-30 15:25:30,172][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.362852096557617, cross_entropy: 2.362852096557617 +[2025-04-30 15:25:33,070][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 2.136378765106201, cross_entropy: 2.136378765106201 +[2025-04-30 15:25:33,659][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 2.351092576980591, cross_entropy: 2.351092576980591 +[2025-04-30 15:25:36,377][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.0337021350860596, cross_entropy: 1.0337021350860596 +[2025-04-30 15:25:37,726][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 1.4977643489837646, cross_entropy: 1.4977643489837646 +[2025-04-30 15:25:39,658][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.6922054290771484, cross_entropy: 2.6922054290771484 +[2025-04-30 15:25:41,664][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 0.7651817798614502, cross_entropy: 0.7651817798614502 +[2025-04-30 15:25:42,899][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.2255988121032715, cross_entropy: 1.2255988121032715 +[2025-04-30 15:25:44,541][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 1.9939042329788208, cross_entropy: 1.9939042329788208 +[2025-04-30 15:25:46,069][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.3963837623596191, cross_entropy: 1.3963837623596191 +[2025-04-30 15:25:48,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 2.9082252979278564, cross_entropy: 2.9082252979278564 +[2025-04-30 15:25:49,135][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 0.8569620847702026, cross_entropy: 0.8569620847702026 +[2025-04-30 15:25:51,666][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 0.8301181197166443, cross_entropy: 0.8301181197166443 +[2025-04-30 15:25:52,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 2.7436673641204834, cross_entropy: 2.7436673641204834 +[2025-04-30 15:25:54,745][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 0.7060545682907104, cross_entropy: 0.7060545682907104 +[2025-04-30 15:25:55,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 1.2224035263061523, cross_entropy: 1.2224035263061523 +[2025-04-30 15:25:57,713][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.5016205310821533, cross_entropy: 1.5016205310821533 +[2025-04-30 15:25:58,505][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 1.3909120559692383, cross_entropy: 1.3909120559692383 +[2025-04-30 15:26:01,515][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 2.6938228607177734, cross_entropy: 2.6938228607177734 +[2025-04-30 15:26:01,923][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 0.8230090141296387, cross_entropy: 0.8230090141296387 +[2025-04-30 15:26:05,225][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 2.860651969909668, cross_entropy: 2.860651969909668 +[2025-04-30 15:26:05,538][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.6752820014953613, cross_entropy: 2.6752820014953613 +[2025-04-30 15:26:08,302][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 2.489192485809326, cross_entropy: 2.489192485809326 +[2025-04-30 15:26:08,641][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.5869128704071045, cross_entropy: 2.5869128704071045 +[2025-04-30 15:26:11,326][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 2.2369184494018555, cross_entropy: 2.2369184494018555 +[2025-04-30 15:26:11,696][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.248722553253174, cross_entropy: 2.248722553253174 +[2025-04-30 15:26:14,685][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 0.8791802525520325, cross_entropy: 0.8791802525520325 +[2025-04-30 15:26:15,023][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 2.4994263648986816, cross_entropy: 2.4994263648986816 +[2025-04-30 15:26:17,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 0.7912276983261108, cross_entropy: 0.7912276983261108 +[2025-04-30 15:26:18,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.6456681489944458, cross_entropy: 1.6456681489944458 +[2025-04-30 15:26:22,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 0.7517151832580566, cross_entropy: 0.7517151832580566 +[2025-04-30 15:26:22,593][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.1881585121154785, cross_entropy: 2.1881585121154785 +[2025-04-30 15:26:25,171][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 2.769289493560791, cross_entropy: 2.769289493560791 +[2025-04-30 15:26:25,484][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 2.754349946975708, cross_entropy: 2.754349946975708 +[2025-04-30 15:26:28,617][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 1.6877137422561646, cross_entropy: 1.6877137422561646 +[2025-04-30 15:26:28,930][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 2.0532703399658203, cross_entropy: 2.0532703399658203 +[2025-04-30 15:26:31,816][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 2.690962076187134, cross_entropy: 2.690962076187134 +[2025-04-30 15:26:32,129][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 2.740091562271118, cross_entropy: 2.740091562271118 +[2025-04-30 15:26:35,484][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.2471085786819458, cross_entropy: 1.2471085786819458 +[2025-04-30 15:26:35,824][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 0.9750443696975708, cross_entropy: 0.9750443696975708 +[2025-04-30 15:26:38,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 3.093669891357422, cross_entropy: 3.093669891357422 +[2025-04-30 15:26:38,956][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 0.8833150863647461, cross_entropy: 0.8833150863647461 +[2025-04-30 15:26:42,265][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 2.9236388206481934, cross_entropy: 2.9236388206481934 +[2025-04-30 15:26:42,585][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 2.5900986194610596, cross_entropy: 2.5900986194610596 +[2025-04-30 15:26:45,892][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 0.9030735492706299, cross_entropy: 0.9030735492706299 +[2025-04-30 15:26:46,206][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 2.857231616973877, cross_entropy: 2.857231616973877 +[2025-04-30 15:26:49,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 2.538097381591797, cross_entropy: 2.538097381591797 +[2025-04-30 15:26:49,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 0.6886975765228271, cross_entropy: 0.6886975765228271 +[2025-04-30 15:26:52,455][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 0.5644769072532654, cross_entropy: 0.5644769072532654 +[2025-04-30 15:26:52,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.7644131183624268, cross_entropy: 2.7644131183624268 +[2025-04-30 15:26:55,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 0.7752714157104492, cross_entropy: 0.7752714157104492 +[2025-04-30 15:26:56,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 2.182133913040161, cross_entropy: 2.182133913040161 +[2025-04-30 15:26:59,041][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 1.5795282125473022, cross_entropy: 1.5795282125473022 +[2025-04-30 15:26:59,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.598463773727417, cross_entropy: 1.598463773727417 +[2025-04-30 15:27:02,430][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 2.7472410202026367, cross_entropy: 2.7472410202026367 +[2025-04-30 15:27:02,769][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 0.8166453838348389, cross_entropy: 0.8166453838348389 +[2025-04-30 15:27:05,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.6622555255889893, cross_entropy: 1.6622555255889893 +[2025-04-30 15:27:06,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 0.9191741347312927, cross_entropy: 0.9191741347312927 +[2025-04-30 15:27:10,214][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.0324618816375732, cross_entropy: 1.0324618816375732 +[2025-04-30 15:27:10,531][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 1.709710717201233, cross_entropy: 1.709710717201233 +[2025-04-30 15:27:14,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.4144322872161865, cross_entropy: 1.4144322872161865 +[2025-04-30 15:27:14,422][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 2.5556764602661133, cross_entropy: 2.5556764602661133 +[2025-04-30 15:27:17,709][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 2.918826103210449, cross_entropy: 2.918826103210449 +[2025-04-30 15:27:18,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 1.3554627895355225, cross_entropy: 1.3554627895355225 +[2025-04-30 15:27:21,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 1.4042606353759766, cross_entropy: 1.4042606353759766 +[2025-04-30 15:27:21,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 1.3115239143371582, cross_entropy: 1.3115239143371582 +[2025-04-30 15:27:24,361][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 2.6263492107391357, cross_entropy: 2.6263492107391357 +[2025-04-30 15:27:24,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.534067153930664, cross_entropy: 2.534067153930664 +[2025-04-30 15:27:27,938][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 2.5453920364379883, cross_entropy: 2.5453920364379883 +[2025-04-30 15:27:28,276][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 1.0277084112167358, cross_entropy: 1.0277084112167358 +[2025-04-30 15:27:31,211][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 1.8027890920639038, cross_entropy: 1.8027890920639038 +[2025-04-30 15:27:31,523][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.165576696395874, cross_entropy: 1.165576696395874 +[2025-04-30 15:27:34,758][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 1.0341837406158447, cross_entropy: 1.0341837406158447 +[2025-04-30 15:27:35,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.3809807300567627, cross_entropy: 1.3809807300567627 +[2025-04-30 15:27:37,848][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 2.7745561599731445, cross_entropy: 2.7745561599731445 +[2025-04-30 15:27:38,187][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 0.7940014600753784, cross_entropy: 0.7940014600753784 +[2025-04-30 15:27:41,850][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 2.8722000122070312, cross_entropy: 2.8722000122070312 +[2025-04-30 15:27:42,196][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.196547031402588, cross_entropy: 3.196547031402588 +[2025-04-30 15:27:45,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 2.232931613922119, cross_entropy: 2.232931613922119 +[2025-04-30 15:27:45,728][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 1.8021999597549438, cross_entropy: 1.8021999597549438 +[2025-04-30 15:27:48,895][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 2.9121499061584473, cross_entropy: 2.9121499061584473 +[2025-04-30 15:27:49,233][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 1.2700846195220947, cross_entropy: 1.2700846195220947 +[2025-04-30 15:27:51,900][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 0.6968820691108704, cross_entropy: 0.6968820691108704 +[2025-04-30 15:27:52,223][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.0234252214431763, cross_entropy: 1.0234252214431763 +[2025-04-30 15:27:55,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 0.9214691519737244, cross_entropy: 0.9214691519737244 +[2025-04-30 15:27:55,601][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.00528883934021, cross_entropy: 2.00528883934021 +[2025-04-30 15:27:58,701][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.1371722221374512, cross_entropy: 1.1371722221374512 +[2025-04-30 15:27:59,042][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 1.7059352397918701, cross_entropy: 1.7059352397918701 +[2025-04-30 15:28:02,423][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.6755592823028564, cross_entropy: 2.6755592823028564 +[2025-04-30 15:28:02,765][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 1.0259943008422852, cross_entropy: 1.0259943008422852 +[2025-04-30 15:28:05,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 1.3602008819580078, cross_entropy: 1.3602008819580078 +[2025-04-30 15:28:06,029][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 1.783231496810913, cross_entropy: 1.783231496810913 +[2025-04-30 15:28:09,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 0.631615400314331, cross_entropy: 0.631615400314331 +[2025-04-30 15:28:09,424][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 0.6667497754096985, cross_entropy: 0.6667497754096985 +[2025-04-30 15:28:12,867][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 0.8561770915985107, cross_entropy: 0.8561770915985107 +[2025-04-30 15:28:13,212][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 2.2525601387023926, cross_entropy: 2.2525601387023926 +[2025-04-30 15:28:17,308][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.099175214767456, cross_entropy: 1.099175214767456 +[2025-04-30 15:28:17,621][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.889544129371643, cross_entropy: 1.889544129371643 +[2025-04-30 15:28:20,880][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 1.011073350906372, cross_entropy: 1.011073350906372 +[2025-04-30 15:28:21,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 2.6889700889587402, cross_entropy: 2.6889700889587402 +[2025-04-30 15:28:23,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 1.2046366930007935, cross_entropy: 1.2046366930007935 +[2025-04-30 15:28:23,975][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 1.3601031303405762, cross_entropy: 1.3601031303405762 +[2025-04-30 15:28:26,933][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 2.596452474594116, cross_entropy: 2.596452474594116 +[2025-04-30 15:28:27,282][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 1.2373833656311035, cross_entropy: 1.2373833656311035 +[2025-04-30 15:28:29,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 2.9436850547790527, cross_entropy: 2.9436850547790527 +[2025-04-30 15:28:30,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 1.6677262783050537, cross_entropy: 1.6677262783050537 +[2025-04-30 15:28:33,346][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 2.8919596672058105, cross_entropy: 2.8919596672058105 +[2025-04-30 15:28:33,687][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 0.9082921743392944, cross_entropy: 0.9082921743392944 +[2025-04-30 15:28:36,451][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 1.2148505449295044, cross_entropy: 1.2148505449295044 +[2025-04-30 15:28:36,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.0644257068634033, cross_entropy: 2.0644257068634033 +[2025-04-30 15:28:39,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.9389762878417969, cross_entropy: 1.9389762878417969 +[2025-04-30 15:28:39,836][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.1387033462524414, cross_entropy: 2.1387033462524414 +[2025-04-30 15:28:42,733][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 0.780717134475708, cross_entropy: 0.780717134475708 +[2025-04-30 15:28:43,076][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 2.5023984909057617, cross_entropy: 2.5023984909057617 +[2025-04-30 15:28:46,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 0.921375036239624, cross_entropy: 0.921375036239624 +[2025-04-30 15:28:46,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 2.7085118293762207, cross_entropy: 2.7085118293762207 +[2025-04-30 15:28:49,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 0.7025993466377258, cross_entropy: 0.7025993466377258 +[2025-04-30 15:28:49,998][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 2.4203784465789795, cross_entropy: 2.4203784465789795 +[2025-04-30 15:28:53,443][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 1.0117194652557373, cross_entropy: 1.0117194652557373 +[2025-04-30 15:28:53,782][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 2.8818445205688477, cross_entropy: 2.8818445205688477 +[2025-04-30 15:28:57,646][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 2.9844465255737305, cross_entropy: 2.9844465255737305 +[2025-04-30 15:28:57,994][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 0.6507461071014404, cross_entropy: 0.6507461071014404 +[2025-04-30 15:29:01,571][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 0.9621882438659668, cross_entropy: 0.9621882438659668 +[2025-04-30 15:29:01,924][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.1053727865219116, cross_entropy: 1.1053727865219116 +[2025-04-30 15:29:05,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 2.066288471221924, cross_entropy: 2.066288471221924 +[2025-04-30 15:29:05,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 1.1131961345672607, cross_entropy: 1.1131961345672607 +[2025-04-30 15:29:09,130][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 2.3802566528320312, cross_entropy: 2.3802566528320312 +[2025-04-30 15:29:09,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 0.8583278656005859, cross_entropy: 0.8583278656005859 +[2025-04-30 15:29:13,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 0.9468458890914917, cross_entropy: 0.9468458890914917 +[2025-04-30 15:29:13,600][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 0.7522866725921631, cross_entropy: 0.7522866725921631 +[2025-04-30 15:29:16,727][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 1.0164198875427246, cross_entropy: 1.0164198875427246 +[2025-04-30 15:29:17,081][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.1722079515457153, cross_entropy: 1.1722079515457153 +[2025-04-30 15:29:21,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 1.0889827013015747, cross_entropy: 1.0889827013015747 +[2025-04-30 15:29:21,952][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 2.6010239124298096, cross_entropy: 2.6010239124298096 +[2025-04-30 15:29:25,200][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 0.8613896369934082, cross_entropy: 0.8613896369934082 +[2025-04-30 15:29:25,544][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.59907603263855, cross_entropy: 2.59907603263855 +[2025-04-30 15:29:28,333][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 0.8607156276702881, cross_entropy: 0.8607156276702881 +[2025-04-30 15:29:28,672][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 0.7877031564712524, cross_entropy: 0.7877031564712524 +[2025-04-30 15:29:31,399][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.5262668132781982, cross_entropy: 1.5262668132781982 +[2025-04-30 15:29:32,006][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.292041301727295, cross_entropy: 1.292041301727295 +[2025-04-30 15:29:34,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 2.519646167755127, cross_entropy: 2.519646167755127 +[2025-04-30 15:29:35,340][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.836487293243408, cross_entropy: 2.836487293243408 +[2025-04-30 15:29:38,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 2.740551471710205, cross_entropy: 2.740551471710205 +[2025-04-30 15:29:39,128][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 0.8693767189979553, cross_entropy: 0.8693767189979553 +[2025-04-30 15:29:42,024][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 0.9589366912841797, cross_entropy: 0.9589366912841797 +[2025-04-30 15:29:42,414][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 1.1852595806121826, cross_entropy: 1.1852595806121826 +[2025-04-30 15:29:45,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.0464922189712524, cross_entropy: 1.0464922189712524 +[2025-04-30 15:29:45,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 2.262707233428955, cross_entropy: 2.262707233428955 +[2025-04-30 15:29:48,329][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.2189825773239136, cross_entropy: 1.2189825773239136 +[2025-04-30 15:29:49,093][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.1883413791656494, cross_entropy: 2.1883413791656494 +[2025-04-30 15:29:52,120][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 2.251781940460205, cross_entropy: 2.251781940460205 +[2025-04-30 15:29:53,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 1.4791247844696045, cross_entropy: 1.4791247844696045 +[2025-04-30 15:29:55,456][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 2.454909563064575, cross_entropy: 2.454909563064575 +[2025-04-30 15:29:56,478][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 0.9662837982177734, cross_entropy: 0.9662837982177734 +[2025-04-30 15:29:59,221][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 2.519078254699707, cross_entropy: 2.519078254699707 +[2025-04-30 15:29:59,574][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 0.7000324726104736, cross_entropy: 0.7000324726104736 +[2025-04-30 15:30:02,587][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 2.702155113220215, cross_entropy: 2.702155113220215 +[2025-04-30 15:30:02,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 0.768582284450531, cross_entropy: 0.768582284450531 +[2025-04-30 15:30:05,995][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.147080421447754, cross_entropy: 1.147080421447754 +[2025-04-30 15:30:07,068][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 2.083291530609131, cross_entropy: 2.083291530609131 +[2025-04-30 15:30:09,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 2.6903789043426514, cross_entropy: 2.6903789043426514 +[2025-04-30 15:30:10,213][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 1.353044033050537, cross_entropy: 1.353044033050537 +[2025-04-30 15:30:12,579][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 2.5178747177124023, cross_entropy: 2.5178747177124023 +[2025-04-30 15:30:13,779][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 0.8716546297073364, cross_entropy: 0.8716546297073364 +[2025-04-30 15:30:15,483][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 0.8202427625656128, cross_entropy: 0.8202427625656128 +[2025-04-30 15:30:16,965][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 0.9298540353775024, cross_entropy: 0.9298540353775024 +[2025-04-30 15:30:19,015][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 0.8951429128646851, cross_entropy: 0.8951429128646851 +[2025-04-30 15:30:20,247][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 1.4509613513946533, cross_entropy: 1.4509613513946533 +[2025-04-30 15:30:22,251][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 2.0109915733337402, cross_entropy: 2.0109915733337402 +[2025-04-30 15:30:24,268][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 2.7823030948638916, cross_entropy: 2.7823030948638916 +[2025-04-30 15:30:25,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 0.8878269195556641, cross_entropy: 0.8878269195556641 +[2025-04-30 15:30:27,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.7480449676513672, cross_entropy: 1.7480449676513672 +[2025-04-30 15:30:29,553][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 1.0015549659729004, cross_entropy: 1.0015549659729004 +[2025-04-30 15:30:31,083][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.7093311548233032, cross_entropy: 1.7093311548233032 +[2025-04-30 15:30:33,004][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.3814936876296997, cross_entropy: 1.3814936876296997 +[2025-04-30 15:30:34,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 2.541215181350708, cross_entropy: 2.541215181350708 +[2025-04-30 15:30:36,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 2.897136688232422, cross_entropy: 2.897136688232422 +[2025-04-30 15:30:37,960][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.9838364124298096, cross_entropy: 1.9838364124298096 +[2025-04-30 15:30:39,464][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 1.43703293800354, cross_entropy: 1.43703293800354 +[2025-04-30 15:30:41,683][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 1.2918946743011475, cross_entropy: 1.2918946743011475 +[2025-04-30 15:30:42,371][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 2.928015947341919, cross_entropy: 2.928015947341919 +[2025-04-30 15:30:46,345][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 1.348755121231079, cross_entropy: 1.348755121231079 +[2025-04-30 15:30:46,682][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.164619207382202, cross_entropy: 2.164619207382202 +[2025-04-30 15:30:50,169][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 0.7692201733589172, cross_entropy: 0.7692201733589172 +[2025-04-30 15:30:50,506][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 1.9288897514343262, cross_entropy: 1.9288897514343262 +[2025-04-30 15:30:54,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 2.4913783073425293, cross_entropy: 2.4913783073425293 +[2025-04-30 15:30:54,462][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.114928722381592, cross_entropy: 2.114928722381592 +[2025-04-30 15:30:57,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 0.9457350969314575, cross_entropy: 0.9457350969314575 +[2025-04-30 15:30:58,186][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 0.6678757071495056, cross_entropy: 0.6678757071495056 +[2025-04-30 15:31:01,142][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 2.889866352081299, cross_entropy: 2.889866352081299 +[2025-04-30 15:31:01,454][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 2.9379587173461914, cross_entropy: 2.9379587173461914 +[2025-04-30 15:31:04,815][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 0.7023232579231262, cross_entropy: 0.7023232579231262 +[2025-04-30 15:31:05,157][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 0.8427814841270447, cross_entropy: 0.8427814841270447 +[2025-04-30 15:31:07,742][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 2.5460753440856934, cross_entropy: 2.5460753440856934 +[2025-04-30 15:31:08,055][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 1.5131440162658691, cross_entropy: 1.5131440162658691 +[2025-04-30 15:31:10,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 2.9996509552001953, cross_entropy: 2.9996509552001953 +[2025-04-30 15:31:11,058][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 1.0549609661102295, cross_entropy: 1.0549609661102295 +[2025-04-30 15:31:13,880][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.491098165512085, cross_entropy: 2.491098165512085 +[2025-04-30 15:31:14,219][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 0.8577791452407837, cross_entropy: 0.8577791452407837 +[2025-04-30 15:31:17,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 0.8617866039276123, cross_entropy: 0.8617866039276123 +[2025-04-30 15:31:18,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 2.57619047164917, cross_entropy: 2.57619047164917 +[2025-04-30 15:31:21,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 1.8360012769699097, cross_entropy: 1.8360012769699097 +[2025-04-30 15:31:22,198][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 2.751054525375366, cross_entropy: 2.751054525375366 +[2025-04-30 15:31:25,392][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 0.8893520832061768, cross_entropy: 0.8893520832061768 +[2025-04-30 15:31:25,738][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 2.4907948970794678, cross_entropy: 2.4907948970794678 +[2025-04-30 15:31:29,194][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 2.588320255279541, cross_entropy: 2.588320255279541 +[2025-04-30 15:31:29,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 2.8515491485595703, cross_entropy: 2.8515491485595703 +[2025-04-30 15:31:32,304][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.1686623096466064, cross_entropy: 2.1686623096466064 +[2025-04-30 15:31:32,648][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 0.9711847901344299, cross_entropy: 0.9711847901344299 +[2025-04-30 15:31:35,499][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 1.6509978771209717, cross_entropy: 1.6509978771209717 +[2025-04-30 15:31:35,845][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 1.9113085269927979, cross_entropy: 1.9113085269927979 +[2025-04-30 15:31:38,754][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.8234479427337646, cross_entropy: 1.8234479427337646 +[2025-04-30 15:31:39,098][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 2.498748302459717, cross_entropy: 2.498748302459717 +[2025-04-30 15:31:42,363][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 2.4432742595672607, cross_entropy: 2.4432742595672607 +[2025-04-30 15:31:42,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 0.7848402261734009, cross_entropy: 0.7848402261734009 +[2025-04-30 15:31:46,054][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 1.7123430967330933, cross_entropy: 1.7123430967330933 +[2025-04-30 15:31:46,397][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 0.8712071776390076, cross_entropy: 0.8712071776390076 +[2025-04-30 15:31:49,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.6617178916931152, cross_entropy: 2.6617178916931152 +[2025-04-30 15:31:49,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.2477185726165771, cross_entropy: 1.2477185726165771 +[2025-04-30 15:31:52,799][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 2.92758846282959, cross_entropy: 2.92758846282959 +[2025-04-30 15:31:53,112][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 1.048359990119934, cross_entropy: 1.048359990119934 +[2025-04-30 15:31:56,527][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 1.074242353439331, cross_entropy: 1.074242353439331 +[2025-04-30 15:31:56,873][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 0.8646242618560791, cross_entropy: 0.8646242618560791 +[2025-04-30 15:32:01,257][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 2.4367661476135254, cross_entropy: 2.4367661476135254 +[2025-04-30 15:32:01,601][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 3.1480817794799805, cross_entropy: 3.1480817794799805 +[2025-04-30 15:32:04,890][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.562204122543335, cross_entropy: 1.562204122543335 +[2025-04-30 15:32:05,203][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 1.8019294738769531, cross_entropy: 1.8019294738769531 +[2025-04-30 15:32:08,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.043520450592041, cross_entropy: 2.043520450592041 +[2025-04-30 15:32:08,914][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 1.4907848834991455, cross_entropy: 1.4907848834991455 +[2025-04-30 15:32:12,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 1.754706859588623, cross_entropy: 1.754706859588623 +[2025-04-30 15:32:12,367][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 2.8753738403320312, cross_entropy: 2.8753738403320312 +[2025-04-30 15:32:15,339][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.781310558319092, cross_entropy: 2.781310558319092 +[2025-04-30 15:32:15,679][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 2.545877695083618, cross_entropy: 2.545877695083618 +[2025-04-30 15:32:19,130][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 1.8734114170074463, cross_entropy: 1.8734114170074463 +[2025-04-30 15:32:19,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 0.6887837648391724, cross_entropy: 0.6887837648391724 +[2025-04-30 15:32:22,191][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.2766342163085938, cross_entropy: 2.2766342163085938 +[2025-04-30 15:32:22,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 0.9183332920074463, cross_entropy: 0.9183332920074463 +[2025-04-30 15:32:25,121][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.0924463272094727, cross_entropy: 2.0924463272094727 +[2025-04-30 15:35:22,279][BaseTrainer][INFO] - [Epoch 9/10] (train) 1.7627520561218262, cross_entropy: 1.7627520561218262 +[2025-04-30 15:35:22,280][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.2337230443954468, cross_entropy: 1.2337230443954468 +[2025-04-30 15:35:22,280][BaseTrainer][INFO] - [Epoch 9/10] (metrics) roc_auc: 0.9798438549041748 +[2025-04-30 15:35:22,445][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch9.pth. +[2025-04-30 15:35:22,660][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 15:35:27,321][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 0.9949201345443726, cross_entropy: 0.9949201345443726 +[2025-04-30 15:35:27,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.653106927871704, cross_entropy: 1.653106927871704 +[2025-04-30 15:35:30,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 0.663456916809082, cross_entropy: 0.663456916809082 +[2025-04-30 15:35:33,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 2.6905014514923096, cross_entropy: 2.6905014514923096 +[2025-04-30 15:35:33,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.4505486488342285, cross_entropy: 2.4505486488342285 +[2025-04-30 15:35:36,753][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.8843984603881836, cross_entropy: 1.8843984603881836 +[2025-04-30 15:35:38,123][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.663727045059204, cross_entropy: 2.663727045059204 +[2025-04-30 15:35:41,026][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 1.1012074947357178, cross_entropy: 1.1012074947357178 +[2025-04-30 15:35:41,733][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.440459966659546, cross_entropy: 2.440459966659546 +[2025-04-30 15:35:45,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.1848936080932617, cross_entropy: 1.1848936080932617 +[2025-04-30 15:35:45,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 2.1959633827209473, cross_entropy: 2.1959633827209473 +[2025-04-30 15:35:49,945][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 2.2033512592315674, cross_entropy: 2.2033512592315674 +[2025-04-30 15:35:50,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 1.190843105316162, cross_entropy: 1.190843105316162 +[2025-04-30 15:35:53,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.9653451442718506, cross_entropy: 1.9653451442718506 +[2025-04-30 15:35:54,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 2.6518945693969727, cross_entropy: 2.6518945693969727 +[2025-04-30 15:35:57,355][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 0.9283934831619263, cross_entropy: 0.9283934831619263 +[2025-04-30 15:35:58,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 0.8365943431854248, cross_entropy: 0.8365943431854248 +[2025-04-30 15:36:01,048][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 2.0451483726501465, cross_entropy: 2.0451483726501465 +[2025-04-30 15:36:03,058][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 1.3424904346466064, cross_entropy: 1.3424904346466064 +[2025-04-30 15:36:05,522][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 0.6072461605072021, cross_entropy: 0.6072461605072021 +[2025-04-30 15:36:06,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 1.530292272567749, cross_entropy: 1.530292272567749 +[2025-04-30 15:36:08,916][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 3.0623536109924316, cross_entropy: 3.0623536109924316 +[2025-04-30 15:36:11,003][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 0.5752711296081543, cross_entropy: 0.5752711296081543 +[2025-04-30 15:36:12,771][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 0.9551822543144226, cross_entropy: 0.9551822543144226 +[2025-04-30 15:36:15,296][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.145172595977783, cross_entropy: 2.145172595977783 +[2025-04-30 15:36:16,671][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 2.559019088745117, cross_entropy: 2.559019088745117 +[2025-04-30 15:36:19,629][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 0.8697946071624756, cross_entropy: 0.8697946071624756 +[2025-04-30 15:36:20,048][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.0294883251190186, cross_entropy: 2.0294883251190186 +[2025-04-30 15:36:23,447][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 2.780529737472534, cross_entropy: 2.780529737472534 +[2025-04-30 15:36:23,833][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.5161073207855225, cross_entropy: 1.5161073207855225 +[2025-04-30 15:36:27,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 2.3952112197875977, cross_entropy: 2.3952112197875977 +[2025-04-30 15:36:27,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 0.6790481805801392, cross_entropy: 0.6790481805801392 +[2025-04-30 15:36:31,484][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 0.8972742557525635, cross_entropy: 0.8972742557525635 +[2025-04-30 15:36:31,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.1184277534484863, cross_entropy: 2.1184277534484863 +[2025-04-30 15:36:35,709][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 1.369786024093628, cross_entropy: 1.369786024093628 +[2025-04-30 15:36:36,048][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.4520076513290405, cross_entropy: 1.4520076513290405 +[2025-04-30 15:36:39,630][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 2.2868216037750244, cross_entropy: 2.2868216037750244 +[2025-04-30 15:36:39,942][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 0.9661893844604492, cross_entropy: 0.9661893844604492 +[2025-04-30 15:36:43,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 2.398743152618408, cross_entropy: 2.398743152618408 +[2025-04-30 15:36:44,114][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 0.9037214517593384, cross_entropy: 0.9037214517593384 +[2025-04-30 15:36:47,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 1.844774842262268, cross_entropy: 1.844774842262268 +[2025-04-30 15:36:47,509][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.2413978576660156, cross_entropy: 2.2413978576660156 +[2025-04-30 15:36:50,842][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 0.6582493782043457, cross_entropy: 0.6582493782043457 +[2025-04-30 15:36:51,189][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.5841944217681885, cross_entropy: 2.5841944217681885 +[2025-04-30 15:36:55,363][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 1.062701940536499, cross_entropy: 1.062701940536499 +[2025-04-30 15:36:55,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 2.7805559635162354, cross_entropy: 2.7805559635162354 +[2025-04-30 15:36:59,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.9357883930206299, cross_entropy: 1.9357883930206299 +[2025-04-30 15:36:59,558][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 2.438840866088867, cross_entropy: 2.438840866088867 +[2025-04-30 15:37:02,221][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.3448708057403564, cross_entropy: 1.3448708057403564 +[2025-04-30 15:37:02,567][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 2.8149361610412598, cross_entropy: 2.8149361610412598 +[2025-04-30 15:37:05,408][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.1070430278778076, cross_entropy: 2.1070430278778076 +[2025-04-30 15:37:05,750][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 1.7082576751708984, cross_entropy: 1.7082576751708984 +[2025-04-30 15:37:08,406][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.3260204792022705, cross_entropy: 1.3260204792022705 +[2025-04-30 15:37:08,729][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 0.7118938565254211, cross_entropy: 0.7118938565254211 +[2025-04-30 15:37:12,001][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 0.7494024038314819, cross_entropy: 0.7494024038314819 +[2025-04-30 15:37:12,343][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 2.676427125930786, cross_entropy: 2.676427125930786 +[2025-04-30 15:37:15,595][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 1.0692245960235596, cross_entropy: 1.0692245960235596 +[2025-04-30 15:37:15,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 0.9388936758041382, cross_entropy: 0.9388936758041382 +[2025-04-30 15:37:19,169][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.9097048044204712, cross_entropy: 1.9097048044204712 +[2025-04-30 15:37:19,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 0.8294275999069214, cross_entropy: 0.8294275999069214 +[2025-04-30 15:37:23,181][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 2.2384843826293945, cross_entropy: 2.2384843826293945 +[2025-04-30 15:37:23,494][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 1.9278357028961182, cross_entropy: 1.9278357028961182 +[2025-04-30 15:37:27,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 2.4258108139038086, cross_entropy: 2.4258108139038086 +[2025-04-30 15:37:27,788][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 0.7792797684669495, cross_entropy: 0.7792797684669495 +[2025-04-30 15:37:30,963][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 1.8112452030181885, cross_entropy: 1.8112452030181885 +[2025-04-30 15:37:31,305][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 1.6984670162200928, cross_entropy: 1.6984670162200928 +[2025-04-30 15:37:34,233][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 2.7722573280334473, cross_entropy: 2.7722573280334473 +[2025-04-30 15:37:34,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 1.9037408828735352, cross_entropy: 1.9037408828735352 +[2025-04-30 15:37:38,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 0.6924858093261719, cross_entropy: 0.6924858093261719 +[2025-04-30 15:37:38,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 3.005249500274658, cross_entropy: 3.005249500274658 +[2025-04-30 15:37:42,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 0.8601157069206238, cross_entropy: 0.8601157069206238 +[2025-04-30 15:37:42,512][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 0.8540239334106445, cross_entropy: 0.8540239334106445 +[2025-04-30 15:37:45,454][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 0.6799842715263367, cross_entropy: 0.6799842715263367 +[2025-04-30 15:37:45,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 0.6502876877784729, cross_entropy: 0.6502876877784729 +[2025-04-30 15:37:48,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 0.6897894144058228, cross_entropy: 0.6897894144058228 +[2025-04-30 15:37:49,013][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.123957633972168, cross_entropy: 1.123957633972168 +[2025-04-30 15:37:53,169][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 0.7571321725845337, cross_entropy: 0.7571321725845337 +[2025-04-30 15:37:53,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 1.511981725692749, cross_entropy: 1.511981725692749 +[2025-04-30 15:37:56,857][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 0.8990027904510498, cross_entropy: 0.8990027904510498 +[2025-04-30 15:37:57,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.7093376517295837, cross_entropy: 0.7093376517295837 +[2025-04-30 15:38:00,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.5825581550598145, cross_entropy: 1.5825581550598145 +[2025-04-30 15:38:00,390][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 0.5315893888473511, cross_entropy: 0.5315893888473511 +[2025-04-30 15:38:03,698][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 2.861467123031616, cross_entropy: 2.861467123031616 +[2025-04-30 15:38:04,013][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.6383914947509766, cross_entropy: 2.6383914947509766 +[2025-04-30 15:38:06,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 1.0127449035644531, cross_entropy: 1.0127449035644531 +[2025-04-30 15:38:07,189][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 1.085279941558838, cross_entropy: 1.085279941558838 +[2025-04-30 15:38:10,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 2.7654647827148438, cross_entropy: 2.7654647827148438 +[2025-04-30 15:38:10,637][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 0.5493115186691284, cross_entropy: 0.5493115186691284 +[2025-04-30 15:38:13,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 2.809497833251953, cross_entropy: 2.809497833251953 +[2025-04-30 15:38:13,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 1.812375545501709, cross_entropy: 1.812375545501709 +[2025-04-30 15:38:16,798][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 1.133740782737732, cross_entropy: 1.133740782737732 +[2025-04-30 15:38:17,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 2.4175267219543457, cross_entropy: 2.4175267219543457 +[2025-04-30 15:38:20,077][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 1.9538618326187134, cross_entropy: 1.9538618326187134 +[2025-04-30 15:38:20,419][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 2.3357083797454834, cross_entropy: 2.3357083797454834 +[2025-04-30 15:38:23,226][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 0.6725252866744995, cross_entropy: 0.6725252866744995 +[2025-04-30 15:38:23,566][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 1.9002206325531006, cross_entropy: 1.9002206325531006 +[2025-04-30 15:38:26,516][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 2.6934165954589844, cross_entropy: 2.6934165954589844 +[2025-04-30 15:38:26,855][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 0.8304786086082458, cross_entropy: 0.8304786086082458 +[2025-04-30 15:38:29,289][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 1.4319932460784912, cross_entropy: 1.4319932460784912 +[2025-04-30 15:38:29,703][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 2.136225938796997, cross_entropy: 2.136225938796997 +[2025-04-30 15:38:32,518][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 0.7892131805419922, cross_entropy: 0.7892131805419922 +[2025-04-30 15:38:32,897][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 1.5451395511627197, cross_entropy: 1.5451395511627197 +[2025-04-30 15:38:35,799][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 1.4011505842208862, cross_entropy: 1.4011505842208862 +[2025-04-30 15:38:36,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 2.0816755294799805, cross_entropy: 2.0816755294799805 +[2025-04-30 15:38:39,458][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 2.7728700637817383, cross_entropy: 2.7728700637817383 +[2025-04-30 15:38:39,771][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.384711742401123, cross_entropy: 2.384711742401123 +[2025-04-30 15:38:43,092][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 1.2764990329742432, cross_entropy: 1.2764990329742432 +[2025-04-30 15:38:43,433][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 0.809931755065918, cross_entropy: 0.809931755065918 +[2025-04-30 15:38:46,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.682882785797119, cross_entropy: 2.682882785797119 +[2025-04-30 15:38:46,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.6817665100097656, cross_entropy: 2.6817665100097656 +[2025-04-30 15:38:49,349][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 2.7224931716918945, cross_entropy: 2.7224931716918945 +[2025-04-30 15:38:49,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 1.0498617887496948, cross_entropy: 1.0498617887496948 +[2025-04-30 15:38:52,853][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 0.5556007623672485, cross_entropy: 0.5556007623672485 +[2025-04-30 15:38:53,340][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 2.8307056427001953, cross_entropy: 2.8307056427001953 +[2025-04-30 15:38:56,424][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 2.0561437606811523, cross_entropy: 2.0561437606811523 +[2025-04-30 15:38:56,992][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 2.6599912643432617, cross_entropy: 2.6599912643432617 +[2025-04-30 15:39:00,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 1.3097057342529297, cross_entropy: 1.3097057342529297 +[2025-04-30 15:39:00,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 0.5776943564414978, cross_entropy: 0.5776943564414978 +[2025-04-30 15:39:03,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 0.6863341927528381, cross_entropy: 0.6863341927528381 +[2025-04-30 15:39:04,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.2306222915649414, cross_entropy: 2.2306222915649414 +[2025-04-30 15:39:06,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 1.4444688558578491, cross_entropy: 1.4444688558578491 +[2025-04-30 15:39:07,328][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 1.9526907205581665, cross_entropy: 1.9526907205581665 +[2025-04-30 15:39:09,984][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 0.9333742260932922, cross_entropy: 0.9333742260932922 +[2025-04-30 15:39:11,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.472494602203369, cross_entropy: 2.472494602203369 +[2025-04-30 15:39:13,359][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 1.8288800716400146, cross_entropy: 1.8288800716400146 +[2025-04-30 15:39:14,588][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 0.6688233017921448, cross_entropy: 0.6688233017921448 +[2025-04-30 15:39:16,978][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 2.555121421813965, cross_entropy: 2.555121421813965 +[2025-04-30 15:39:17,813][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 2.922477960586548, cross_entropy: 2.922477960586548 +[2025-04-30 15:39:20,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 2.5389156341552734, cross_entropy: 2.5389156341552734 +[2025-04-30 15:39:21,273][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 0.9841292500495911, cross_entropy: 0.9841292500495911 +[2025-04-30 15:39:23,285][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 1.9027692079544067, cross_entropy: 1.9027692079544067 +[2025-04-30 15:39:24,892][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 2.155609607696533, cross_entropy: 2.155609607696533 +[2025-04-30 15:39:27,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.8862344026565552, cross_entropy: 1.8862344026565552 +[2025-04-30 15:39:29,146][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 1.9801114797592163, cross_entropy: 1.9801114797592163 +[2025-04-30 15:39:30,890][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 0.6963452100753784, cross_entropy: 0.6963452100753784 +[2025-04-30 15:39:32,457][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.4611780643463135, cross_entropy: 1.4611780643463135 +[2025-04-30 15:39:34,620][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 2.796372413635254, cross_entropy: 2.796372413635254 +[2025-04-30 15:39:35,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 1.2763216495513916, cross_entropy: 1.2763216495513916 +[2025-04-30 15:39:38,008][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.5811691284179688, cross_entropy: 2.5811691284179688 +[2025-04-30 15:39:39,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.5755531787872314, cross_entropy: 1.5755531787872314 +[2025-04-30 15:39:42,441][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.2768921852111816, cross_entropy: 2.2768921852111816 +[2025-04-30 15:39:43,823][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.1709237098693848, cross_entropy: 2.1709237098693848 +[2025-04-30 15:39:45,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 2.6758737564086914, cross_entropy: 2.6758737564086914 +[2025-04-30 15:39:47,139][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.570397138595581, cross_entropy: 2.570397138595581 +[2025-04-30 15:39:48,578][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.34470272064209, cross_entropy: 2.34470272064209 +[2025-04-30 15:39:51,144][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 0.9597092270851135, cross_entropy: 0.9597092270851135 +[2025-04-30 15:39:51,863][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 0.6917589902877808, cross_entropy: 0.6917589902877808 +[2025-04-30 15:39:54,908][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 2.4439964294433594, cross_entropy: 2.4439964294433594 +[2025-04-30 15:39:55,268][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 1.162252426147461, cross_entropy: 1.162252426147461 +[2025-04-30 15:39:58,076][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 2.366453170776367, cross_entropy: 2.366453170776367 +[2025-04-30 15:39:58,551][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.263237953186035, cross_entropy: 2.263237953186035 +[2025-04-30 15:40:01,126][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.4576759338378906, cross_entropy: 2.4576759338378906 +[2025-04-30 15:40:02,714][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 0.8188124895095825, cross_entropy: 0.8188124895095825 +[2025-04-30 15:40:04,384][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.771383285522461, cross_entropy: 2.771383285522461 +[2025-04-30 15:40:06,605][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 0.9394440650939941, cross_entropy: 0.9394440650939941 +[2025-04-30 15:40:07,504][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 2.7408618927001953, cross_entropy: 2.7408618927001953 +[2025-04-30 15:40:10,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.046656608581543, cross_entropy: 1.046656608581543 +[2025-04-30 15:40:10,823][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.582396984100342, cross_entropy: 2.582396984100342 +[2025-04-30 15:40:13,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 1.04900062084198, cross_entropy: 1.04900062084198 +[2025-04-30 15:40:14,253][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 2.4549131393432617, cross_entropy: 2.4549131393432617 +[2025-04-30 15:40:17,219][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 0.8679376840591431, cross_entropy: 0.8679376840591431 +[2025-04-30 15:40:17,679][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 2.6201817989349365, cross_entropy: 2.6201817989349365 +[2025-04-30 15:40:20,197][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 2.7319324016571045, cross_entropy: 2.7319324016571045 +[2025-04-30 15:40:21,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.377440929412842, cross_entropy: 2.377440929412842 +[2025-04-30 15:40:24,349][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 0.6043819189071655, cross_entropy: 0.6043819189071655 +[2025-04-30 15:40:25,193][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.7732300758361816, cross_entropy: 2.7732300758361816 +[2025-04-30 15:40:27,863][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.756638526916504, cross_entropy: 2.756638526916504 +[2025-04-30 15:40:29,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.8249125480651855, cross_entropy: 0.8249125480651855 +[2025-04-30 15:40:31,446][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 2.4528861045837402, cross_entropy: 2.4528861045837402 +[2025-04-30 15:40:33,895][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 2.597287654876709, cross_entropy: 2.597287654876709 +[2025-04-30 15:40:34,926][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 2.7719736099243164, cross_entropy: 2.7719736099243164 +[2025-04-30 15:40:37,106][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 0.5667718648910522, cross_entropy: 0.5667718648910522 +[2025-04-30 15:40:38,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 1.4522650241851807, cross_entropy: 1.4522650241851807 +[2025-04-30 15:40:40,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.9606099128723145, cross_entropy: 0.9606099128723145 +[2025-04-30 15:40:42,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.1134690046310425, cross_entropy: 1.1134690046310425 +[2025-04-30 15:40:44,126][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 2.3479700088500977, cross_entropy: 2.3479700088500977 +[2025-04-30 15:40:45,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 2.791882038116455, cross_entropy: 2.791882038116455 +[2025-04-30 15:40:47,447][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 2.5198965072631836, cross_entropy: 2.5198965072631836 +[2025-04-30 15:40:49,545][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 0.6836713552474976, cross_entropy: 0.6836713552474976 +[2025-04-30 15:40:51,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 2.399310827255249, cross_entropy: 2.399310827255249 +[2025-04-30 15:40:53,234][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 0.5804750323295593, cross_entropy: 0.5804750323295593 +[2025-04-30 15:40:54,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 0.6082274317741394, cross_entropy: 0.6082274317741394 +[2025-04-30 15:40:56,660][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.1139073371887207, cross_entropy: 1.1139073371887207 +[2025-04-30 15:40:57,855][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.8587381839752197, cross_entropy: 2.8587381839752197 +[2025-04-30 15:40:59,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 0.507786214351654, cross_entropy: 0.507786214351654 +[2025-04-30 15:41:01,208][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.8274837732315063, cross_entropy: 1.8274837732315063 +[2025-04-30 15:41:03,526][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.166104555130005, cross_entropy: 2.166104555130005 +[2025-04-30 15:41:05,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 1.133110761642456, cross_entropy: 1.133110761642456 +[2025-04-30 15:41:07,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 2.246476173400879, cross_entropy: 2.246476173400879 +[2025-04-30 15:41:09,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 0.50272536277771, cross_entropy: 0.50272536277771 +[2025-04-30 15:41:10,956][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 2.6507232189178467, cross_entropy: 2.6507232189178467 +[2025-04-30 15:41:13,324][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 2.312192916870117, cross_entropy: 2.312192916870117 +[2025-04-30 15:41:14,081][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 1.6185102462768555, cross_entropy: 1.6185102462768555 +[2025-04-30 15:41:16,692][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 1.2797887325286865, cross_entropy: 1.2797887325286865 +[2025-04-30 15:41:17,520][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.891252040863037, cross_entropy: 2.891252040863037 +[2025-04-30 15:41:19,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.670773983001709, cross_entropy: 2.670773983001709 +[2025-04-30 15:41:21,410][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 0.506711483001709, cross_entropy: 0.506711483001709 +[2025-04-30 15:41:23,193][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.3533344268798828, cross_entropy: 1.3533344268798828 +[2025-04-30 15:41:24,873][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 2.802891731262207, cross_entropy: 2.802891731262207 +[2025-04-30 15:41:27,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 1.7354141473770142, cross_entropy: 1.7354141473770142 +[2025-04-30 15:41:28,349][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 3.1017074584960938, cross_entropy: 3.1017074584960938 +[2025-04-30 15:41:30,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 0.6665061116218567, cross_entropy: 0.6665061116218567 +[2025-04-30 15:41:31,240][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.7593655586242676, cross_entropy: 1.7593655586242676 +[2025-04-30 15:41:33,769][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.413766384124756, cross_entropy: 2.413766384124756 +[2025-04-30 15:41:34,761][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 0.7406023144721985, cross_entropy: 0.7406023144721985 +[2025-04-30 15:41:37,577][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 0.6677913665771484, cross_entropy: 0.6677913665771484 +[2025-04-30 15:41:38,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 2.6976659297943115, cross_entropy: 2.6976659297943115 +[2025-04-30 15:41:40,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 2.367753028869629, cross_entropy: 2.367753028869629 +[2025-04-30 15:41:41,757][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 1.6616572141647339, cross_entropy: 1.6616572141647339 +[2025-04-30 15:41:44,329][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.7003734111785889, cross_entropy: 1.7003734111785889 +[2025-04-30 15:41:44,895][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 0.6811503171920776, cross_entropy: 0.6811503171920776 +[2025-04-30 15:41:47,402][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.4864144325256348, cross_entropy: 2.4864144325256348 +[2025-04-30 15:41:48,314][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 2.489917039871216, cross_entropy: 2.489917039871216 +[2025-04-30 15:41:50,868][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.554877996444702, cross_entropy: 2.554877996444702 +[2025-04-30 15:41:51,710][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 2.5099802017211914, cross_entropy: 2.5099802017211914 +[2025-04-30 15:41:54,864][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 1.9109405279159546, cross_entropy: 1.9109405279159546 +[2025-04-30 15:41:55,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 2.633375883102417, cross_entropy: 2.633375883102417 +[2025-04-30 15:41:58,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 2.6802077293395996, cross_entropy: 2.6802077293395996 +[2025-04-30 15:41:58,510][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.4816784858703613, cross_entropy: 2.4816784858703613 +[2025-04-30 15:42:01,751][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 2.290239095687866, cross_entropy: 2.290239095687866 +[2025-04-30 15:42:02,190][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 1.077798843383789, cross_entropy: 1.077798843383789 +[2025-04-30 15:42:04,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.2548376321792603, cross_entropy: 1.2548376321792603 +[2025-04-30 15:42:05,591][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.5039939880371094, cross_entropy: 1.5039939880371094 +[2025-04-30 15:42:08,476][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.1969327926635742, cross_entropy: 1.1969327926635742 +[2025-04-30 15:42:09,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 2.573483467102051, cross_entropy: 2.573483467102051 +[2025-04-30 15:42:12,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.759989023208618, cross_entropy: 2.759989023208618 +[2025-04-30 15:42:13,533][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 2.400192975997925, cross_entropy: 2.400192975997925 +[2025-04-30 15:42:16,357][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 3.1590116024017334, cross_entropy: 3.1590116024017334 +[2025-04-30 15:42:16,727][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 0.9566293358802795, cross_entropy: 0.9566293358802795 +[2025-04-30 15:42:20,099][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 1.9744694232940674, cross_entropy: 1.9744694232940674 +[2025-04-30 15:42:20,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.7240800857543945, cross_entropy: 1.7240800857543945 +[2025-04-30 15:42:23,548][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 1.3920173645019531, cross_entropy: 1.3920173645019531 +[2025-04-30 15:42:23,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.2278486490249634, cross_entropy: 1.2278486490249634 +[2025-04-30 15:42:26,800][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 2.486283779144287, cross_entropy: 2.486283779144287 +[2025-04-30 15:42:27,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 2.7284364700317383, cross_entropy: 2.7284364700317383 +[2025-04-30 15:42:30,270][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 1.6614185571670532, cross_entropy: 1.6614185571670532 +[2025-04-30 15:42:30,817][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 2.6156563758850098, cross_entropy: 2.6156563758850098 +[2025-04-30 15:42:33,784][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.8319082260131836, cross_entropy: 1.8319082260131836 +[2025-04-30 15:42:34,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 2.879169225692749, cross_entropy: 2.879169225692749 +[2025-04-30 15:42:37,042][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 1.112033486366272, cross_entropy: 1.112033486366272 +[2025-04-30 15:42:37,360][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 2.0957541465759277, cross_entropy: 2.0957541465759277 +[2025-04-30 15:42:40,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 3.0053040981292725, cross_entropy: 3.0053040981292725 +[2025-04-30 15:42:41,384][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 2.858713388442993, cross_entropy: 2.858713388442993 +[2025-04-30 15:42:44,554][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 0.5582419633865356, cross_entropy: 0.5582419633865356 +[2025-04-30 15:42:44,952][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.6535067558288574, cross_entropy: 2.6535067558288574 +[2025-04-30 15:42:47,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 0.5688943266868591, cross_entropy: 0.5688943266868591 +[2025-04-30 15:42:48,853][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 1.5966417789459229, cross_entropy: 1.5966417789459229 +[2025-04-30 15:42:51,049][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 0.9416741728782654, cross_entropy: 0.9416741728782654 +[2025-04-30 15:42:52,496][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 2.0576915740966797, cross_entropy: 2.0576915740966797 +[2025-04-30 15:42:54,363][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 1.0487582683563232, cross_entropy: 1.0487582683563232 +[2025-04-30 15:42:55,851][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.5391180515289307, cross_entropy: 1.5391180515289307 +[2025-04-30 15:42:57,464][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 2.4358315467834473, cross_entropy: 2.4358315467834473 +[2025-04-30 15:42:59,402][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 2.151275634765625, cross_entropy: 2.151275634765625 +[2025-04-30 15:43:01,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 1.6315407752990723, cross_entropy: 1.6315407752990723 +[2025-04-30 15:43:03,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.176138997077942, cross_entropy: 1.176138997077942 +[2025-04-30 15:43:04,902][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 0.5382127165794373, cross_entropy: 0.5382127165794373 +[2025-04-30 15:43:06,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 0.5827301144599915, cross_entropy: 0.5827301144599915 +[2025-04-30 15:43:08,615][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 0.9846680164337158, cross_entropy: 0.9846680164337158 +[2025-04-30 15:43:10,755][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 1.5737671852111816, cross_entropy: 1.5737671852111816 +[2025-04-30 15:43:12,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.7355669736862183, cross_entropy: 1.7355669736862183 +[2025-04-30 15:43:15,243][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 2.8865249156951904, cross_entropy: 2.8865249156951904 +[2025-04-30 15:43:16,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 1.4575201272964478, cross_entropy: 1.4575201272964478 +[2025-04-30 15:43:18,342][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.438518524169922, cross_entropy: 2.438518524169922 +[2025-04-30 15:43:20,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.4192609786987305, cross_entropy: 2.4192609786987305 +[2025-04-30 15:43:22,795][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.186876058578491, cross_entropy: 2.186876058578491 +[2025-04-30 15:43:24,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 0.7836532592773438, cross_entropy: 0.7836532592773438 +[2025-04-30 15:43:26,414][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 0.9763966798782349, cross_entropy: 0.9763966798782349 +[2025-04-30 15:43:27,508][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.853194236755371, cross_entropy: 1.853194236755371 +[2025-04-30 15:43:29,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 2.806685447692871, cross_entropy: 2.806685447692871 +[2025-04-30 15:43:30,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 0.9151021242141724, cross_entropy: 0.9151021242141724 +[2025-04-30 15:43:33,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.708810329437256, cross_entropy: 2.708810329437256 +[2025-04-30 15:43:34,092][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 2.407209873199463, cross_entropy: 2.407209873199463 +[2025-04-30 15:43:37,154][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 0.8016645312309265, cross_entropy: 0.8016645312309265 +[2025-04-30 15:43:37,478][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 1.821287989616394, cross_entropy: 1.821287989616394 +[2025-04-30 15:43:40,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.8895115852355957, cross_entropy: 2.8895115852355957 +[2025-04-30 15:43:41,256][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 0.9908778667449951, cross_entropy: 0.9908778667449951 +[2025-04-30 15:43:44,967][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 1.8868075609207153, cross_entropy: 1.8868075609207153 +[2025-04-30 15:43:45,308][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 2.7804760932922363, cross_entropy: 2.7804760932922363 +[2025-04-30 15:43:49,014][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 1.1874558925628662, cross_entropy: 1.1874558925628662 +[2025-04-30 15:43:49,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 0.8289450407028198, cross_entropy: 0.8289450407028198 +[2025-04-30 15:43:52,493][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 1.0866146087646484, cross_entropy: 1.0866146087646484 +[2025-04-30 15:43:52,833][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 0.6302446722984314, cross_entropy: 0.6302446722984314 +[2025-04-30 15:43:56,436][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 0.6973490715026855, cross_entropy: 0.6973490715026855 +[2025-04-30 15:43:56,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 2.042605400085449, cross_entropy: 2.042605400085449 +[2025-04-30 15:44:00,171][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 2.869662284851074, cross_entropy: 2.869662284851074 +[2025-04-30 15:44:00,486][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 2.3703348636627197, cross_entropy: 2.3703348636627197 +[2025-04-30 15:44:04,443][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.7328133583068848, cross_entropy: 2.7328133583068848 +[2025-04-30 15:44:04,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 0.9277036190032959, cross_entropy: 0.9277036190032959 +[2025-04-30 15:44:07,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 0.7816264033317566, cross_entropy: 0.7816264033317566 +[2025-04-30 15:44:08,300][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 1.65323805809021, cross_entropy: 1.65323805809021 +[2025-04-30 15:44:12,323][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 1.1173475980758667, cross_entropy: 1.1173475980758667 +[2025-04-30 15:44:12,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 2.7310123443603516, cross_entropy: 2.7310123443603516 +[2025-04-30 15:44:15,927][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 0.7667520046234131, cross_entropy: 0.7667520046234131 +[2025-04-30 15:44:16,274][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 2.7524099349975586, cross_entropy: 2.7524099349975586 +[2025-04-30 15:44:19,964][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 1.0850591659545898, cross_entropy: 1.0850591659545898 +[2025-04-30 15:44:20,307][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 2.989229202270508, cross_entropy: 2.989229202270508 +[2025-04-30 15:44:23,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 0.7270759344100952, cross_entropy: 0.7270759344100952 +[2025-04-30 15:44:24,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 0.9734761118888855, cross_entropy: 0.9734761118888855 +[2025-04-30 15:44:27,078][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.8882813453674316, cross_entropy: 1.8882813453674316 +[2025-04-30 15:44:27,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 2.6541013717651367, cross_entropy: 2.6541013717651367 +[2025-04-30 15:44:29,791][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 0.7383818626403809, cross_entropy: 0.7383818626403809 +[2025-04-30 15:44:30,142][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 1.184584379196167, cross_entropy: 1.184584379196167 +[2025-04-30 15:44:32,902][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 2.0943899154663086, cross_entropy: 2.0943899154663086 +[2025-04-30 15:44:33,246][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.6193416118621826, cross_entropy: 2.6193416118621826 +[2025-04-30 15:44:36,921][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 2.723489761352539, cross_entropy: 2.723489761352539 +[2025-04-30 15:44:37,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 0.743302047252655, cross_entropy: 0.743302047252655 +[2025-04-30 15:44:40,594][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 0.7789040207862854, cross_entropy: 0.7789040207862854 +[2025-04-30 15:44:40,908][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 2.566326141357422, cross_entropy: 2.566326141357422 +[2025-04-30 15:44:44,601][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 0.6038004755973816, cross_entropy: 0.6038004755973816 +[2025-04-30 15:44:44,949][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.765476703643799, cross_entropy: 2.765476703643799 +[2025-04-30 15:44:47,915][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 1.088658332824707, cross_entropy: 1.088658332824707 +[2025-04-30 15:44:48,255][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 1.3943779468536377, cross_entropy: 1.3943779468536377 +[2025-04-30 15:44:52,027][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.6654610633850098, cross_entropy: 1.6654610633850098 +[2025-04-30 15:44:52,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.0920422077178955, cross_entropy: 1.0920422077178955 +[2025-04-30 15:44:55,767][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 2.743528366088867, cross_entropy: 2.743528366088867 +[2025-04-30 15:44:56,108][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.3450021743774414, cross_entropy: 2.3450021743774414 +[2025-04-30 15:44:59,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 0.6397207975387573, cross_entropy: 0.6397207975387573 +[2025-04-30 15:44:59,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 1.1118861436843872, cross_entropy: 1.1118861436843872 +[2025-04-30 15:45:02,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 1.9641010761260986, cross_entropy: 1.9641010761260986 +[2025-04-30 15:45:02,908][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 1.9464757442474365, cross_entropy: 1.9464757442474365 +[2025-04-30 15:45:06,117][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 2.3619747161865234, cross_entropy: 2.3619747161865234 +[2025-04-30 15:45:06,461][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 2.6433422565460205, cross_entropy: 2.6433422565460205 +[2025-04-30 15:45:09,749][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 0.6934647560119629, cross_entropy: 0.6934647560119629 +[2025-04-30 15:45:10,063][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 0.8669019937515259, cross_entropy: 0.8669019937515259 +[2025-04-30 15:45:13,476][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 2.6504781246185303, cross_entropy: 2.6504781246185303 +[2025-04-30 15:45:13,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 2.136641502380371, cross_entropy: 2.136641502380371 +[2025-04-30 15:45:16,950][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.5815224647521973, cross_entropy: 2.5815224647521973 +[2025-04-30 15:45:17,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 2.0428152084350586, cross_entropy: 2.0428152084350586 +[2025-04-30 15:45:20,191][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 1.5944526195526123, cross_entropy: 1.5944526195526123 +[2025-04-30 15:45:20,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 0.9475208520889282, cross_entropy: 0.9475208520889282 +[2025-04-30 15:45:24,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.861569404602051, cross_entropy: 2.861569404602051 +[2025-04-30 15:45:24,372][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 1.4137427806854248, cross_entropy: 1.4137427806854248 +[2025-04-30 15:45:27,047][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 0.9210867881774902, cross_entropy: 0.9210867881774902 +[2025-04-30 15:45:27,361][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 1.5741887092590332, cross_entropy: 1.5741887092590332 +[2025-04-30 15:45:30,024][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 2.9741697311401367, cross_entropy: 2.9741697311401367 +[2025-04-30 15:45:30,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.0683516263961792, cross_entropy: 1.0683516263961792 +[2025-04-30 15:45:33,285][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 0.5657048225402832, cross_entropy: 0.5657048225402832 +[2025-04-30 15:45:33,597][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 2.024336338043213, cross_entropy: 2.024336338043213 +[2025-04-30 15:45:37,215][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.1815197467803955, cross_entropy: 1.1815197467803955 +[2025-04-30 15:45:37,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 2.7444100379943848, cross_entropy: 2.7444100379943848 +[2025-04-30 15:45:40,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.9225075244903564, cross_entropy: 2.9225075244903564 +[2025-04-30 15:45:41,046][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 2.7436180114746094, cross_entropy: 2.7436180114746094 +[2025-04-30 15:45:44,710][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 0.6461025476455688, cross_entropy: 0.6461025476455688 +[2025-04-30 15:45:45,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.766580581665039, cross_entropy: 2.766580581665039 +[2025-04-30 15:45:47,838][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 1.6934363842010498, cross_entropy: 1.6934363842010498 +[2025-04-30 15:45:48,188][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.7426083087921143, cross_entropy: 2.7426083087921143 +[2025-04-30 15:45:51,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 1.0815443992614746, cross_entropy: 1.0815443992614746 +[2025-04-30 15:45:52,054][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.3440730571746826, cross_entropy: 1.3440730571746826 +[2025-04-30 15:45:54,907][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 2.469153881072998, cross_entropy: 2.469153881072998 +[2025-04-30 15:45:55,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 2.766749382019043, cross_entropy: 2.766749382019043 +[2025-04-30 15:45:58,289][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 1.5025964975357056, cross_entropy: 1.5025964975357056 +[2025-04-30 15:45:58,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 0.6409213542938232, cross_entropy: 0.6409213542938232 +[2025-04-30 15:46:02,037][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 2.921468734741211, cross_entropy: 2.921468734741211 +[2025-04-30 15:46:02,352][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 2.2701401710510254, cross_entropy: 2.2701401710510254 +[2025-04-30 15:46:05,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 2.700277090072632, cross_entropy: 2.700277090072632 +[2025-04-30 15:46:05,424][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 1.4412637948989868, cross_entropy: 1.4412637948989868 +[2025-04-30 15:48:49,083][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.7660377025604248, cross_entropy: 1.7660377025604248 +[2025-04-30 15:48:49,083][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.2013005018234253, cross_entropy: 1.2013005018234253 +[2025-04-30 15:48:49,083][BaseTrainer][INFO] - [Epoch 10/10] (metrics) roc_auc: 0.9827538132667542 +[2025-04-30 15:48:49,308][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/best_epoch.pth. +[2025-04-30 15:48:49,467][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/epoch10.pth. +[2025-04-30 15:48:49,676][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. +[2025-04-30 15:48:49,873][BaseTrainer][INFO] - Save model: ./exp/20250430-132920/model/last.pth. diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/best_epoch.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a6203eab3e1fdc7360abdf624093301d6a60363 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e6508d018be159fa17866361ca2c371dcf651478c553c2b4361fd5beeb7f3f +size 51765285 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/last.pth b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..ea280d77f02d6b8edc238eba8ac1e6a7f8f9bbe4 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/exp/20250430-132920/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcd57903fc415a14dddc5e84608ca2701cefd1b9eff2942b3be037d8d15c364 +size 51716643 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-104215/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.2 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-104215/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.2 new file mode 100644 index 0000000000000000000000000000000000000000..d31542c7e5f299a2e87dc4fa2667ca36ecdf19da --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-104215/events.out.tfevents.1746371438.MacBook-Pro-2.local.7605.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632b27c0477a5bd3a5bc862c6a6fa85a19631fd1d6367f85aa8db2d30d4e1f17 +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-115144/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.3 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-115144/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.3 new file mode 100644 index 0000000000000000000000000000000000000000..f8a1a5beeff77aa16f3105fd703d4d81495bbc23 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-115144/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321136e842e2b69300f9370e0ac06c4e3d8e3b2b7a65a47e859f37f5cc45a2fb +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-133045/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.4 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-133045/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.4 new file mode 100644 index 0000000000000000000000000000000000000000..a6f5cff62228575903c727fee9430766af79e85d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250427-133045/events.out.tfevents.1746371439.MacBook-Pro-2.local.7605.4 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c376bc5a0e4dbfabeeca00af5f2a8be28b1cf1e06e26e9efe4dc2a24135b58d +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250428-032422/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.5 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250428-032422/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.5 new file mode 100644 index 0000000000000000000000000000000000000000..240e5df77330bbc9aec0c83e556a6abcb347b82d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250428-032422/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.5 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3009b917f0716678a41d9b117550ff9032e6a7dd9303ca80dff2b044428bf324 +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-075315/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.6 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-075315/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.6 new file mode 100644 index 0000000000000000000000000000000000000000..ae9e16fcb2d826829814005f84a64949719b0ce7 --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-075315/events.out.tfevents.1746371440.MacBook-Pro-2.local.7605.6 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f068a81fbee6ca76b3d0458ca4b549f1b33a87e8e084f7c183419ca06fb882 +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-174748/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.7 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-174748/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.7 new file mode 100644 index 0000000000000000000000000000000000000000..8c38e488256b2894d5fe7118b67e8ab1677aeb1d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250429-174748/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.7 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89272d67599d500c627e3fe84289aea9148e39dcf80d8043e6777511ca542642 +size 472294 diff --git a/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250430-132920/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.8 b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250430-132920/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.8 new file mode 100644 index 0000000000000000000000000000000000000000..8f8fa1db996f78290b10579e5a1f48ff5e88843d --- /dev/null +++ b/recipes/BirdCLEF2025/EfficientNetB0/tensorboard/20250430-132920/events.out.tfevents.1746371441.MacBook-Pro-2.local.7605.8 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0017f45984cd02116c72fa3e3e1749daeb75ba88ca13973ac59109ac50ec5f5 +size 472934 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/config.yaml b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d0f877a93c7b3e47063258a2ab642737eb98642f --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/config.yaml @@ -0,0 +1,212 @@ +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 + csv_path: ??? + submission_path: ??? + audio_root: ??? + subset: ??? + train_ratio: 0.8 +data: + audio: + sample_rate: 32000 + duration: 15 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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/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/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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + validation: + _target_: torch.utils.data.DataLoader + batch_size: 64 + shuffle: false + collate_fn: + _target_: ${...train.collate_fn._target_} + 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} + alpha: ${...train.collate_fn.alpha} + 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/20250329-115632 + tensorboard_dir: ./tensorboard/20250329-115632 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: null + iterations: 1 + lr_scheduler: epoch +test: + dataset: + test: + _target_: torch.utils.data.Dataset + dataset: null + 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.RandomModel + 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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/hydra.yaml b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2f87900275f1df386d94788029bbbfff399ca393 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250329-115632/log/20250329-115635 + sweep: + dir: multirun/${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/20250329-115632/log/20250329-115635 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025 + - train=birdclef2025_random + - model=birdclef2025_random + - optimizer=adam + - lr_scheduler=none + - criterion=dummy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250329-115632 + - train.output.tensorboard_dir=./tensorboard/20250329-115632 + job: + name: train + chdir: false + override_dirname: criterion=dummy,data=birdclef2025,lr_scheduler=none,model=birdclef2025_random,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/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025/list/validation.txt,train.output.exp_dir=./exp/20250329-115632,train.output.tensorboard_dir=./tensorboard/20250329-115632,train.resume.continue_from=,train=birdclef2025_random + 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/Random + 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/Random/conf + schema: file + provider: command-line + - path: '' + schema: structured + provider: schema + output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635 + choices: + criterion: dummy + lr_scheduler: none + optimizer: adam + model: birdclef2025_random + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_random + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025 + 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 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/overrides.yaml b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e1461d4e3466e314050128b3b17999d4dace58be --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025 +- train=birdclef2025_random +- model=birdclef2025_random +- optimizer=adam +- lr_scheduler=none +- criterion=dummy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250329-115632 +- train.output.tensorboard_dir=./tensorboard/20250329-115632 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e4b16082e8c6e78ebb46ca062f682faba66386d5 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/.hydra/resolved_config.yaml @@ -0,0 +1,269 @@ +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 + csv_path: ??? + submission_path: ??? + audio_root: ??? + subset: ??? + train_ratio: 0.8 +data: + audio: + sample_rate: 32000 + duration: 15 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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/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/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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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: true + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + validation: + _target_: torch.utils.data.DataLoader + batch_size: 64 + shuffle: false + collate_fn: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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 + alpha: 0.4 + 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/20250329-115632 + tensorboard_dir: ./tensorboard/20250329-115632 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250329-115632/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250329-115632/model/epoch{epoch}.pth + last: + path: ./exp/20250329-115632/model/last.pth + best_epoch: + path: ./exp/20250329-115632/model/best_epoch.pth + steps: + epochs: null + iterations: 1 + lr_scheduler: epoch +test: + dataset: + test: + _target_: torch.utils.data.Dataset + dataset: null + 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.RandomModel + 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 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/train.log b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/train.log new file mode 100644 index 0000000000000000000000000000000000000000..efa4dffb5bd2a1ea0562f19f05bb7cfe5f8654cd --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/log/20250329-115635/train.log @@ -0,0 +1,223 @@ +[2025-03-29 11:56:52,865][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 + csv_path: ??? + submission_path: ??? + audio_root: ??? + subset: ??? + train_ratio: 0.8 +data: + audio: + sample_rate: 32000 + duration: 15 + melspectrogram: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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/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/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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + validation: + _target_: torch.utils.data.DataLoader + batch_size: 64 + shuffle: false + collate_fn: + _target_: ${...train.collate_fn._target_} + 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} + alpha: ${...train.collate_fn.alpha} + 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/20250329-115632 + tensorboard_dir: ./tensorboard/20250329-115632 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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: null + iterations: 1 + lr_scheduler: epoch +test: + dataset: + test: + _target_: torch.utils.data.Dataset + dataset: null + 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.RandomModel + 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} + +[2025-03-29 11:56:52,865][BaseTrainer][INFO] - RandomModel() +[2025-03-29 11:56:52,865][BaseTrainer][INFO] - # of parameters: 1. +[2025-03-29 11:56:55,258][BaseTrainer][INFO] - [Epoch 1/1, Iter 1/1] 5.327876091003418, cross_entropy: 5.327876091003418 +[2025-03-29 12:00:28,758][BaseTrainer][INFO] - [Epoch 1/1] (train) 5.327876091003418, cross_entropy: 5.327876091003418 +[2025-03-29 12:00:28,758][BaseTrainer][INFO] - [Epoch 1/1] (validation) 5.327876091003418, cross_entropy: 5.327876091003418 +[2025-03-29 12:00:28,785][BaseTrainer][INFO] - Save model: ./exp/20250329-115632/model/best_epoch.pth. +[2025-03-29 12:00:28,829][BaseTrainer][INFO] - Save model: ./exp/20250329-115632/model/epoch1.pth. +[2025-03-29 12:00:28,865][BaseTrainer][INFO] - Save model: ./exp/20250329-115632/model/last.pth. diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/best_epoch.pth b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..83f42db9957dec884abdb6bf1fabd15e5893ce38 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a427dd04f709e72acf811dfa8c8f96eae847cbf3de47a7642f73a033b51a8a +size 8872 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/epoch1.pth b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/epoch1.pth new file mode 100644 index 0000000000000000000000000000000000000000..cbdcfcd0eab3fa7b4cd5418f5542451258fe67a3 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/epoch1.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bf294741af7e2b95bf834354d5e07f297b78a491ce38b3141623bfa7ff1f06 +size 8840 diff --git a/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/last.pth b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..bff44785a99628c1161f52beebed35ebc130c341 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/exp/20250329-115632/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd65160340dc5b2deb48f8c899a4be2746c92062a5069b1ffd2b95f30bdf7881 +size 8824 diff --git a/recipes/BirdCLEF2025/Random/tensorboard/20250329-115632/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.9 b/recipes/BirdCLEF2025/Random/tensorboard/20250329-115632/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.9 new file mode 100644 index 0000000000000000000000000000000000000000..ed213b567e29cca0968288f3b2e3b16efc9ce4b2 --- /dev/null +++ b/recipes/BirdCLEF2025/Random/tensorboard/20250329-115632/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.9 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ffff3cc54bae722c3ee86497b46b7ec9b5925964398d06ca56a172b0df8b5a +size 472 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/README.md b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/README.md new file mode 100644 index 0000000000000000000000000000000000000000..249788481b7983460901e180672f228b9f2a45b1 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/README.md @@ -0,0 +1,6 @@ +data=birdclef2025_15s +train=birdclef2025_swintransformer_tiny +model=birdclef2025_swintransformer_tiny +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.442 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/config.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..097195209d665be65aa0d88f38b06047804f7689 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/config.yaml @@ -0,0 +1,220 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250428-164206 + tensorboard_dir: ./tensorboard/20250428-164206 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.SwinTransformerTiny + weights: ${const:torchvision.models.Swin_T_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/hydra.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..af6392f11eef1128c9aa3507bdc1d4623c4afba2 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250428-164206/log/20250428-164209 + sweep: + dir: multirun/${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/20250428-164206/log/20250428-164209 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_15s + - train=birdclef2025_swintransformer_tiny + - model=birdclef2025_swintransformer_tiny + - optimizer=adam_5e-5 + - lr_scheduler=none + - criterion=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/20250428-164206 + - train.output.tensorboard_dir=./tensorboard/20250428-164206 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_15s,lr_scheduler=none,model=birdclef2025_swintransformer_tiny,optimizer=adam_5e-5,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/20250428-164206,train.output.tensorboard_dir=./tensorboard/20250428-164206,train.resume.continue_from=,train=birdclef2025_swintransformer_tiny + 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/SwinTransformerTiny + 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/SwinTransformerTiny/conf + schema: file + provider: command-line + - path: '' + schema: structured + provider: schema + output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam_5e-5 + model: birdclef2025_swintransformer_tiny + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_swintransformer_tiny + 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 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/overrides.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..2a56b458357caee044bde3a6270b11599a428c8a --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_15s +- train=birdclef2025_swintransformer_tiny +- model=birdclef2025_swintransformer_tiny +- optimizer=adam_5e-5 +- lr_scheduler=none +- criterion=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/20250428-164206 +- train.output.tensorboard_dir=./tensorboard/20250428-164206 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..4b08fd3ca8de32ea9dcf3fdc70fea952eb27d2da --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/.hydra/resolved_config.yaml @@ -0,0 +1,279 @@ +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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025PrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + 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: true + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2024BaselineMelSpectrogram + 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/20250428-164206 + tensorboard_dir: ./tensorboard/20250428-164206 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250428-164206/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250428-164206/model/epoch{epoch}.pth + last: + path: ./exp/20250428-164206/model/last.pth + best_epoch: + path: ./exp/20250428-164206/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.SwinTransformerTiny + weights: IMAGENET1K_V1 + num_classes: 206 +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/train.log b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/train.log new file mode 100644 index 0000000000000000000000000000000000000000..e9ae17021b7d687990a1e3d5fbe0f9f316fd6c78 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/log/20250428-164209/train.log @@ -0,0 +1,4064 @@ +[2025-04-28 16:42:38,194][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.BirdCLEF2024BaselineMelSpectrogram + 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.BirdCLEF2025BaselineCollator + 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: true + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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/20250428-164206 + tensorboard_dir: ./tensorboard/20250428-164206 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.SwinTransformerTiny + weights: ${const:torchvision.models.Swin_T_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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} + +[2025-04-28 16:42:38,194][BaseTrainer][INFO] - SwinTransformerTiny( + (backbone): Sequential( + (0): Sequential( + (0): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4)) + (1): Permute() + (2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + ) + (1): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=96, out_features=288, bias=True) + (proj): Linear(in_features=96, out_features=96, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.0, mode=row) + (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=96, out_features=384, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=384, out_features=96, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=96, out_features=288, bias=True) + (proj): Linear(in_features=96, out_features=96, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.018181818181818184, mode=row) + (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=96, out_features=384, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=384, out_features=96, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (2): PatchMerging( + (reduction): Linear(in_features=384, out_features=192, bias=False) + (norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + ) + (3): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=192, out_features=576, bias=True) + (proj): Linear(in_features=192, out_features=192, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.03636363636363637, mode=row) + (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=192, out_features=768, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=768, out_features=192, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=192, out_features=576, bias=True) + (proj): Linear(in_features=192, out_features=192, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.05454545454545456, mode=row) + (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=192, out_features=768, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=768, out_features=192, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (4): PatchMerging( + (reduction): Linear(in_features=768, out_features=384, bias=False) + (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) + (5): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.07272727272727274, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.09090909090909091, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (2): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.10909090909090911, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (3): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.1272727272727273, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (4): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.14545454545454548, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (5): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.16363636363636364, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (6): PatchMerging( + (reduction): Linear(in_features=1536, out_features=768, bias=False) + (norm): LayerNorm((1536,), eps=1e-05, elementwise_affine=True) + ) + (7): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=768, out_features=2304, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.18181818181818182, mode=row) + (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=768, out_features=3072, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=3072, out_features=768, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=768, out_features=2304, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.2, mode=row) + (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=768, out_features=3072, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=3072, out_features=768, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + ) + (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (permute): Permute() + (avgpool): AdaptiveAvgPool2d(output_size=1) + (flatten): Flatten(start_dim=1, end_dim=-1) + (head): Linear(in_features=768, out_features=206, bias=True) +) +[2025-04-28 16:42:38,197][BaseTrainer][INFO] - # of parameters: 27677768. +[2025-04-28 16:42:44,340][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.40178108215332, cross_entropy: 5.40178108215332 +[2025-04-28 16:42:45,101][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.337717533111572, cross_entropy: 5.337717533111572 +[2025-04-28 16:42:46,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.412962436676025, cross_entropy: 5.412962436676025 +[2025-04-28 16:42:46,731][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.299930572509766, cross_entropy: 5.299930572509766 +[2025-04-28 16:42:49,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.284531593322754, cross_entropy: 5.284531593322754 +[2025-04-28 16:42:50,878][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.2991838455200195, cross_entropy: 5.2991838455200195 +[2025-04-28 16:42:53,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 5.2676897048950195, cross_entropy: 5.2676897048950195 +[2025-04-28 16:42:54,351][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.23328161239624, cross_entropy: 5.23328161239624 +[2025-04-28 16:42:56,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 5.223795413970947, cross_entropy: 5.223795413970947 +[2025-04-28 16:42:57,608][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.1444807052612305, cross_entropy: 5.1444807052612305 +[2025-04-28 16:43:00,192][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.1920928955078125, cross_entropy: 5.1920928955078125 +[2025-04-28 16:43:00,924][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 5.100778102874756, cross_entropy: 5.100778102874756 +[2025-04-28 16:43:04,138][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 5.166948318481445, cross_entropy: 5.166948318481445 +[2025-04-28 16:43:05,318][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 5.013561248779297, cross_entropy: 5.013561248779297 +[2025-04-28 16:43:07,709][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 5.095885753631592, cross_entropy: 5.095885753631592 +[2025-04-28 16:43:08,519][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 4.967357635498047, cross_entropy: 4.967357635498047 +[2025-04-28 16:43:10,957][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 4.984249114990234, cross_entropy: 4.984249114990234 +[2025-04-28 16:43:12,097][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 4.940412521362305, cross_entropy: 4.940412521362305 +[2025-04-28 16:43:14,664][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.954089641571045, cross_entropy: 4.954089641571045 +[2025-04-28 16:43:15,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.894837379455566, cross_entropy: 4.894837379455566 +[2025-04-28 16:43:18,139][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.894682884216309, cross_entropy: 4.894682884216309 +[2025-04-28 16:43:18,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 5.122100830078125, cross_entropy: 5.122100830078125 +[2025-04-28 16:43:22,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 5.049488544464111, cross_entropy: 5.049488544464111 +[2025-04-28 16:43:23,038][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 5.112632751464844, cross_entropy: 5.112632751464844 +[2025-04-28 16:43:25,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.759023189544678, cross_entropy: 4.759023189544678 +[2025-04-28 16:43:26,214][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.8182268142700195, cross_entropy: 4.8182268142700195 +[2025-04-28 16:43:28,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.93607234954834, cross_entropy: 4.93607234954834 +[2025-04-28 16:43:29,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.960544586181641, cross_entropy: 4.960544586181641 +[2025-04-28 16:43:32,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.915124893188477, cross_entropy: 4.915124893188477 +[2025-04-28 16:43:33,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 5.027647972106934, cross_entropy: 5.027647972106934 +[2025-04-28 16:43:36,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.883628845214844, cross_entropy: 4.883628845214844 +[2025-04-28 16:43:36,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 5.058444023132324, cross_entropy: 5.058444023132324 +[2025-04-28 16:43:39,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.982250690460205, cross_entropy: 4.982250690460205 +[2025-04-28 16:43:40,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 5.076845645904541, cross_entropy: 5.076845645904541 +[2025-04-28 16:43:42,851][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 5.036487579345703, cross_entropy: 5.036487579345703 +[2025-04-28 16:43:43,604][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.896752834320068, cross_entropy: 4.896752834320068 +[2025-04-28 16:43:46,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.828824043273926, cross_entropy: 4.828824043273926 +[2025-04-28 16:43:47,280][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.751481056213379, cross_entropy: 4.751481056213379 +[2025-04-28 16:43:50,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.834296703338623, cross_entropy: 4.834296703338623 +[2025-04-28 16:43:51,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.909244537353516, cross_entropy: 4.909244537353516 +[2025-04-28 16:43:54,494][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.867887020111084, cross_entropy: 4.867887020111084 +[2025-04-28 16:43:55,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.6711931228637695, cross_entropy: 4.6711931228637695 +[2025-04-28 16:43:58,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 5.008477210998535, cross_entropy: 5.008477210998535 +[2025-04-28 16:43:59,437][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.7252726554870605, cross_entropy: 4.7252726554870605 +[2025-04-28 16:44:03,372][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.830405235290527, cross_entropy: 4.830405235290527 +[2025-04-28 16:44:04,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.9602437019348145, cross_entropy: 4.9602437019348145 +[2025-04-28 16:44:06,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.804319381713867, cross_entropy: 4.804319381713867 +[2025-04-28 16:44:07,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.580820560455322, cross_entropy: 4.580820560455322 +[2025-04-28 16:44:10,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.790646076202393, cross_entropy: 4.790646076202393 +[2025-04-28 16:44:10,817][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.7921037673950195, cross_entropy: 4.7921037673950195 +[2025-04-28 16:44:13,629][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.7449541091918945, cross_entropy: 4.7449541091918945 +[2025-04-28 16:44:14,326][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.583555698394775, cross_entropy: 4.583555698394775 +[2025-04-28 16:44:16,778][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.793330192565918, cross_entropy: 4.793330192565918 +[2025-04-28 16:44:17,473][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 5.151547431945801, cross_entropy: 5.151547431945801 +[2025-04-28 16:44:20,462][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.832106590270996, cross_entropy: 4.832106590270996 +[2025-04-28 16:44:21,168][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.5385260581970215, cross_entropy: 4.5385260581970215 +[2025-04-28 16:44:24,797][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.808093070983887, cross_entropy: 4.808093070983887 +[2025-04-28 16:44:25,505][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.650064468383789, cross_entropy: 4.650064468383789 +[2025-04-28 16:44:28,630][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.724867343902588, cross_entropy: 4.724867343902588 +[2025-04-28 16:44:29,323][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.573017120361328, cross_entropy: 4.573017120361328 +[2025-04-28 16:44:32,468][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.55192756652832, cross_entropy: 4.55192756652832 +[2025-04-28 16:44:33,159][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.842601776123047, cross_entropy: 4.842601776123047 +[2025-04-28 16:44:36,346][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.758871078491211, cross_entropy: 4.758871078491211 +[2025-04-28 16:44:37,034][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.8894805908203125, cross_entropy: 4.8894805908203125 +[2025-04-28 16:44:39,299][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.533452987670898, cross_entropy: 4.533452987670898 +[2025-04-28 16:44:39,998][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.642319202423096, cross_entropy: 4.642319202423096 +[2025-04-28 16:44:42,463][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.81406307220459, cross_entropy: 4.81406307220459 +[2025-04-28 16:44:43,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 5.08864688873291, cross_entropy: 5.08864688873291 +[2025-04-28 16:44:45,844][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.502502918243408, cross_entropy: 4.502502918243408 +[2025-04-28 16:44:46,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.552464008331299, cross_entropy: 4.552464008331299 +[2025-04-28 16:44:49,275][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.609265327453613, cross_entropy: 4.609265327453613 +[2025-04-28 16:44:49,979][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.609025478363037, cross_entropy: 4.609025478363037 +[2025-04-28 16:44:52,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 4.934771537780762, cross_entropy: 4.934771537780762 +[2025-04-28 16:44:53,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.869722843170166, cross_entropy: 4.869722843170166 +[2025-04-28 16:44:56,121][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.778164386749268, cross_entropy: 4.778164386749268 +[2025-04-28 16:44:56,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.716156959533691, cross_entropy: 4.716156959533691 +[2025-04-28 16:44:59,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.709756851196289, cross_entropy: 4.709756851196289 +[2025-04-28 16:45:00,304][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.796346664428711, cross_entropy: 4.796346664428711 +[2025-04-28 16:45:03,426][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.710153102874756, cross_entropy: 4.710153102874756 +[2025-04-28 16:45:04,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.560970783233643, cross_entropy: 4.560970783233643 +[2025-04-28 16:45:06,441][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.79892635345459, cross_entropy: 4.79892635345459 +[2025-04-28 16:45:07,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.621091842651367, cross_entropy: 4.621091842651367 +[2025-04-28 16:45:10,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.425074577331543, cross_entropy: 4.425074577331543 +[2025-04-28 16:45:10,953][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.713327884674072, cross_entropy: 4.713327884674072 +[2025-04-28 16:45:13,880][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.668362617492676, cross_entropy: 4.668362617492676 +[2025-04-28 16:45:14,556][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 4.513326168060303, cross_entropy: 4.513326168060303 +[2025-04-28 16:45:17,157][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.647843360900879, cross_entropy: 4.647843360900879 +[2025-04-28 16:45:17,895][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.598665237426758, cross_entropy: 4.598665237426758 +[2025-04-28 16:45:20,700][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.522549629211426, cross_entropy: 4.522549629211426 +[2025-04-28 16:45:21,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.6960673332214355, cross_entropy: 4.6960673332214355 +[2025-04-28 16:45:23,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.725637435913086, cross_entropy: 4.725637435913086 +[2025-04-28 16:45:24,584][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 4.778789043426514, cross_entropy: 4.778789043426514 +[2025-04-28 16:45:27,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 4.628641128540039, cross_entropy: 4.628641128540039 +[2025-04-28 16:45:28,343][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.801393508911133, cross_entropy: 4.801393508911133 +[2025-04-28 16:45:30,894][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.806967258453369, cross_entropy: 4.806967258453369 +[2025-04-28 16:45:31,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 4.5905070304870605, cross_entropy: 4.5905070304870605 +[2025-04-28 16:45:33,829][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.532657623291016, cross_entropy: 4.532657623291016 +[2025-04-28 16:45:34,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 4.39429235458374, cross_entropy: 4.39429235458374 +[2025-04-28 16:45:37,101][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.591894149780273, cross_entropy: 4.591894149780273 +[2025-04-28 16:45:38,377][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 4.734030723571777, cross_entropy: 4.734030723571777 +[2025-04-28 16:45:40,157][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.6483354568481445, cross_entropy: 4.6483354568481445 +[2025-04-28 16:45:42,013][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 4.544695854187012, cross_entropy: 4.544695854187012 +[2025-04-28 16:45:43,714][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.605813026428223, cross_entropy: 4.605813026428223 +[2025-04-28 16:45:45,088][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 4.701419353485107, cross_entropy: 4.701419353485107 +[2025-04-28 16:45:46,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 4.6936445236206055, cross_entropy: 4.6936445236206055 +[2025-04-28 16:45:48,659][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.735955715179443, cross_entropy: 4.735955715179443 +[2025-04-28 16:45:53,952][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 4.399019718170166, cross_entropy: 4.399019718170166 +[2025-04-28 16:45:54,760][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.4449238777160645, cross_entropy: 4.4449238777160645 +[2025-04-28 16:45:57,853][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 4.636923789978027, cross_entropy: 4.636923789978027 +[2025-04-28 16:45:58,533][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.636694431304932, cross_entropy: 4.636694431304932 +[2025-04-28 16:46:01,278][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 4.759037971496582, cross_entropy: 4.759037971496582 +[2025-04-28 16:46:02,027][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 4.551105499267578, cross_entropy: 4.551105499267578 +[2025-04-28 16:46:04,666][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.547809600830078, cross_entropy: 4.547809600830078 +[2025-04-28 16:46:05,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.430866241455078, cross_entropy: 4.430866241455078 +[2025-04-28 16:46:07,653][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.619949817657471, cross_entropy: 4.619949817657471 +[2025-04-28 16:46:08,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 4.705740451812744, cross_entropy: 4.705740451812744 +[2025-04-28 16:46:11,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 4.555722713470459, cross_entropy: 4.555722713470459 +[2025-04-28 16:46:11,730][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.307624340057373, cross_entropy: 4.307624340057373 +[2025-04-28 16:46:14,440][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.618320465087891, cross_entropy: 4.618320465087891 +[2025-04-28 16:46:15,156][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.640297889709473, cross_entropy: 4.640297889709473 +[2025-04-28 16:46:18,544][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.5117692947387695, cross_entropy: 4.5117692947387695 +[2025-04-28 16:46:19,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 4.657736301422119, cross_entropy: 4.657736301422119 +[2025-04-28 16:46:22,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 4.891077041625977, cross_entropy: 4.891077041625977 +[2025-04-28 16:46:23,100][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 4.582714557647705, cross_entropy: 4.582714557647705 +[2025-04-28 16:46:25,433][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.504641532897949, cross_entropy: 4.504641532897949 +[2025-04-28 16:46:26,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 4.770197868347168, cross_entropy: 4.770197868347168 +[2025-04-28 16:46:28,473][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 4.541413307189941, cross_entropy: 4.541413307189941 +[2025-04-28 16:46:29,199][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.8039774894714355, cross_entropy: 4.8039774894714355 +[2025-04-28 16:46:31,780][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 4.6948747634887695, cross_entropy: 4.6948747634887695 +[2025-04-28 16:46:32,480][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 4.611076354980469, cross_entropy: 4.611076354980469 +[2025-04-28 16:46:35,189][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.552870750427246, cross_entropy: 4.552870750427246 +[2025-04-28 16:46:35,992][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 4.563856601715088, cross_entropy: 4.563856601715088 +[2025-04-28 16:46:38,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.317537307739258, cross_entropy: 4.317537307739258 +[2025-04-28 16:46:39,785][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.562952041625977, cross_entropy: 4.562952041625977 +[2025-04-28 16:46:42,201][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.732131004333496, cross_entropy: 4.732131004333496 +[2025-04-28 16:46:42,957][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 4.638847351074219, cross_entropy: 4.638847351074219 +[2025-04-28 16:46:46,001][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 4.254970550537109, cross_entropy: 4.254970550537109 +[2025-04-28 16:46:46,761][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.605434417724609, cross_entropy: 4.605434417724609 +[2025-04-28 16:46:49,594][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.680125713348389, cross_entropy: 4.680125713348389 +[2025-04-28 16:46:50,273][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 4.549471378326416, cross_entropy: 4.549471378326416 +[2025-04-28 16:46:53,192][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.659321308135986, cross_entropy: 4.659321308135986 +[2025-04-28 16:46:53,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 4.231394290924072, cross_entropy: 4.231394290924072 +[2025-04-28 16:46:57,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 4.44229793548584, cross_entropy: 4.44229793548584 +[2025-04-28 16:46:57,766][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.751091957092285, cross_entropy: 4.751091957092285 +[2025-04-28 16:47:01,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.475801944732666, cross_entropy: 4.475801944732666 +[2025-04-28 16:47:02,074][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 4.346534729003906, cross_entropy: 4.346534729003906 +[2025-04-28 16:47:05,591][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.485228538513184, cross_entropy: 4.485228538513184 +[2025-04-28 16:47:06,292][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 4.729403972625732, cross_entropy: 4.729403972625732 +[2025-04-28 16:47:08,669][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.4860711097717285, cross_entropy: 4.4860711097717285 +[2025-04-28 16:47:09,346][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.566563129425049, cross_entropy: 4.566563129425049 +[2025-04-28 16:47:12,658][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 4.6146392822265625, cross_entropy: 4.6146392822265625 +[2025-04-28 16:47:13,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 4.073155403137207, cross_entropy: 4.073155403137207 +[2025-04-28 16:47:15,983][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.755198001861572, cross_entropy: 4.755198001861572 +[2025-04-28 16:47:16,681][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 4.41602087020874, cross_entropy: 4.41602087020874 +[2025-04-28 16:47:18,754][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 4.491398811340332, cross_entropy: 4.491398811340332 +[2025-04-28 16:47:19,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 4.186263084411621, cross_entropy: 4.186263084411621 +[2025-04-28 16:47:22,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.294791221618652, cross_entropy: 4.294791221618652 +[2025-04-28 16:47:22,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 4.1558427810668945, cross_entropy: 4.1558427810668945 +[2025-04-28 16:47:25,408][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 4.6102375984191895, cross_entropy: 4.6102375984191895 +[2025-04-28 16:47:26,106][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 4.514311790466309, cross_entropy: 4.514311790466309 +[2025-04-28 16:47:29,324][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 4.447650909423828, cross_entropy: 4.447650909423828 +[2025-04-28 16:47:30,030][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 4.358831882476807, cross_entropy: 4.358831882476807 +[2025-04-28 16:47:32,917][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.306214332580566, cross_entropy: 4.306214332580566 +[2025-04-28 16:47:33,600][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 4.638628005981445, cross_entropy: 4.638628005981445 +[2025-04-28 16:47:36,654][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 4.226198196411133, cross_entropy: 4.226198196411133 +[2025-04-28 16:47:37,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.677862644195557, cross_entropy: 4.677862644195557 +[2025-04-28 16:47:40,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 4.33176851272583, cross_entropy: 4.33176851272583 +[2025-04-28 16:47:40,704][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 4.242952346801758, cross_entropy: 4.242952346801758 +[2025-04-28 16:47:43,283][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.351502418518066, cross_entropy: 4.351502418518066 +[2025-04-28 16:47:43,988][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 4.4868083000183105, cross_entropy: 4.4868083000183105 +[2025-04-28 16:47:46,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 4.294452667236328, cross_entropy: 4.294452667236328 +[2025-04-28 16:47:47,186][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 4.4210638999938965, cross_entropy: 4.4210638999938965 +[2025-04-28 16:47:49,642][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 4.177248954772949, cross_entropy: 4.177248954772949 +[2025-04-28 16:47:50,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.535334587097168, cross_entropy: 4.535334587097168 +[2025-04-28 16:47:53,474][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.2752275466918945, cross_entropy: 4.2752275466918945 +[2025-04-28 16:47:54,172][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 4.253249645233154, cross_entropy: 4.253249645233154 +[2025-04-28 16:47:57,270][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 4.463274002075195, cross_entropy: 4.463274002075195 +[2025-04-28 16:47:57,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 4.365729331970215, cross_entropy: 4.365729331970215 +[2025-04-28 16:48:00,670][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 4.211772918701172, cross_entropy: 4.211772918701172 +[2025-04-28 16:48:01,383][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 4.656911849975586, cross_entropy: 4.656911849975586 +[2025-04-28 16:48:03,550][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 4.42277717590332, cross_entropy: 4.42277717590332 +[2025-04-28 16:48:04,228][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 4.431066989898682, cross_entropy: 4.431066989898682 +[2025-04-28 16:48:06,815][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 4.384746551513672, cross_entropy: 4.384746551513672 +[2025-04-28 16:48:07,511][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.379478454589844, cross_entropy: 4.379478454589844 +[2025-04-28 16:48:10,495][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 4.535761833190918, cross_entropy: 4.535761833190918 +[2025-04-28 16:48:11,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 4.028968811035156, cross_entropy: 4.028968811035156 +[2025-04-28 16:48:15,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 4.151753902435303, cross_entropy: 4.151753902435303 +[2025-04-28 16:48:15,801][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 4.549235820770264, cross_entropy: 4.549235820770264 +[2025-04-28 16:48:18,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 4.320502758026123, cross_entropy: 4.320502758026123 +[2025-04-28 16:48:18,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 3.9460229873657227, cross_entropy: 3.9460229873657227 +[2025-04-28 16:48:21,683][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 3.8549513816833496, cross_entropy: 3.8549513816833496 +[2025-04-28 16:48:22,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 4.108076572418213, cross_entropy: 4.108076572418213 +[2025-04-28 16:48:25,325][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.242867946624756, cross_entropy: 4.242867946624756 +[2025-04-28 16:48:26,002][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 4.240089416503906, cross_entropy: 4.240089416503906 +[2025-04-28 16:48:28,929][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 4.190883636474609, cross_entropy: 4.190883636474609 +[2025-04-28 16:48:29,619][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 4.2535810470581055, cross_entropy: 4.2535810470581055 +[2025-04-28 16:48:31,939][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 4.186203956604004, cross_entropy: 4.186203956604004 +[2025-04-28 16:48:32,634][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 4.148797512054443, cross_entropy: 4.148797512054443 +[2025-04-28 16:48:35,272][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 4.397263526916504, cross_entropy: 4.397263526916504 +[2025-04-28 16:48:35,951][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 4.016921043395996, cross_entropy: 4.016921043395996 +[2025-04-28 16:48:38,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 4.125489234924316, cross_entropy: 4.125489234924316 +[2025-04-28 16:48:39,146][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 4.070559501647949, cross_entropy: 4.070559501647949 +[2025-04-28 16:48:41,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 4.177119255065918, cross_entropy: 4.177119255065918 +[2025-04-28 16:48:42,641][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 3.964974880218506, cross_entropy: 3.964974880218506 +[2025-04-28 16:48:44,793][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.583192825317383, cross_entropy: 4.583192825317383 +[2025-04-28 16:48:45,497][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 4.369405746459961, cross_entropy: 4.369405746459961 +[2025-04-28 16:48:47,972][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 4.345545291900635, cross_entropy: 4.345545291900635 +[2025-04-28 16:48:49,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 4.254613876342773, cross_entropy: 4.254613876342773 +[2025-04-28 16:48:51,567][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 4.0252685546875, cross_entropy: 4.0252685546875 +[2025-04-28 16:48:52,481][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 3.855999231338501, cross_entropy: 3.855999231338501 +[2025-04-28 16:48:55,963][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 4.538383483886719, cross_entropy: 4.538383483886719 +[2025-04-28 16:48:56,643][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 3.9488155841827393, cross_entropy: 3.9488155841827393 +[2025-04-28 16:48:59,456][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 4.115358829498291, cross_entropy: 4.115358829498291 +[2025-04-28 16:49:00,136][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 4.185450553894043, cross_entropy: 4.185450553894043 +[2025-04-28 16:49:02,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 4.165143013000488, cross_entropy: 4.165143013000488 +[2025-04-28 16:49:03,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 4.313198089599609, cross_entropy: 4.313198089599609 +[2025-04-28 16:49:06,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 3.653517246246338, cross_entropy: 3.653517246246338 +[2025-04-28 16:49:06,744][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 4.551640033721924, cross_entropy: 4.551640033721924 +[2025-04-28 16:49:09,907][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 3.8477370738983154, cross_entropy: 3.8477370738983154 +[2025-04-28 16:49:10,604][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 4.312715530395508, cross_entropy: 4.312715530395508 +[2025-04-28 16:49:13,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 3.971756935119629, cross_entropy: 3.971756935119629 +[2025-04-28 16:49:14,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.671932697296143, cross_entropy: 4.671932697296143 +[2025-04-28 16:49:17,064][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 4.260807037353516, cross_entropy: 4.260807037353516 +[2025-04-28 16:49:17,754][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 3.677777051925659, cross_entropy: 3.677777051925659 +[2025-04-28 16:49:21,132][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 3.956486940383911, cross_entropy: 3.956486940383911 +[2025-04-28 16:49:21,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 4.3500895500183105, cross_entropy: 4.3500895500183105 +[2025-04-28 16:49:24,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 3.840709686279297, cross_entropy: 3.840709686279297 +[2025-04-28 16:49:24,819][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 3.7533087730407715, cross_entropy: 3.7533087730407715 +[2025-04-28 16:49:27,093][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 4.0638885498046875, cross_entropy: 4.0638885498046875 +[2025-04-28 16:49:28,435][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 3.5996806621551514, cross_entropy: 3.5996806621551514 +[2025-04-28 16:49:29,884][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 4.071135997772217, cross_entropy: 4.071135997772217 +[2025-04-28 16:49:31,909][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 4.3667988777160645, cross_entropy: 4.3667988777160645 +[2025-04-28 16:49:32,706][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 4.612672328948975, cross_entropy: 4.612672328948975 +[2025-04-28 16:49:35,215][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 4.5453972816467285, cross_entropy: 4.5453972816467285 +[2025-04-28 16:49:36,196][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 4.0409321784973145, cross_entropy: 4.0409321784973145 +[2025-04-28 16:49:38,556][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 4.101779937744141, cross_entropy: 4.101779937744141 +[2025-04-28 16:49:40,539][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 4.01102876663208, cross_entropy: 4.01102876663208 +[2025-04-28 16:49:43,054][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 4.275012016296387, cross_entropy: 4.275012016296387 +[2025-04-28 16:49:44,098][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 4.282450199127197, cross_entropy: 4.282450199127197 +[2025-04-28 16:49:47,151][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 3.83831787109375, cross_entropy: 3.83831787109375 +[2025-04-28 16:49:47,877][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 3.5839481353759766, cross_entropy: 3.5839481353759766 +[2025-04-28 16:49:51,163][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 4.311418533325195, cross_entropy: 4.311418533325195 +[2025-04-28 16:49:51,915][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 4.495015621185303, cross_entropy: 4.495015621185303 +[2025-04-28 16:49:55,747][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 4.601546287536621, cross_entropy: 4.601546287536621 +[2025-04-28 16:49:56,451][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.5940353870391846, cross_entropy: 3.5940353870391846 +[2025-04-28 16:50:01,182][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 3.7040863037109375, cross_entropy: 3.7040863037109375 +[2025-04-28 16:50:01,858][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 3.923123836517334, cross_entropy: 3.923123836517334 +[2025-04-28 16:50:04,146][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 3.928468704223633, cross_entropy: 3.928468704223633 +[2025-04-28 16:50:04,841][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 3.973755121231079, cross_entropy: 3.973755121231079 +[2025-04-28 16:50:07,846][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 4.056705951690674, cross_entropy: 4.056705951690674 +[2025-04-28 16:50:08,521][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 3.9711966514587402, cross_entropy: 3.9711966514587402 +[2025-04-28 16:50:11,552][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 4.021949291229248, cross_entropy: 4.021949291229248 +[2025-04-28 16:50:12,253][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 3.993804931640625, cross_entropy: 3.993804931640625 +[2025-04-28 16:50:15,133][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 4.231468677520752, cross_entropy: 4.231468677520752 +[2025-04-28 16:50:15,840][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 4.1786675453186035, cross_entropy: 4.1786675453186035 +[2025-04-28 16:50:19,091][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 4.056769371032715, cross_entropy: 4.056769371032715 +[2025-04-28 16:50:19,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 4.200534820556641, cross_entropy: 4.200534820556641 +[2025-04-28 16:50:22,521][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 3.9153904914855957, cross_entropy: 3.9153904914855957 +[2025-04-28 16:50:23,211][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 3.7103652954101562, cross_entropy: 3.7103652954101562 +[2025-04-28 16:50:26,946][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 3.988886833190918, cross_entropy: 3.988886833190918 +[2025-04-28 16:50:27,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 3.826223850250244, cross_entropy: 3.826223850250244 +[2025-04-28 16:50:30,666][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 3.765409469604492, cross_entropy: 3.765409469604492 +[2025-04-28 16:50:31,361][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 3.817744493484497, cross_entropy: 3.817744493484497 +[2025-04-28 16:50:34,160][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 4.195840835571289, cross_entropy: 4.195840835571289 +[2025-04-28 16:50:34,857][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 3.6491751670837402, cross_entropy: 3.6491751670837402 +[2025-04-28 16:50:37,296][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 3.8548083305358887, cross_entropy: 3.8548083305358887 +[2025-04-28 16:50:37,976][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 3.8324406147003174, cross_entropy: 3.8324406147003174 +[2025-04-28 16:50:41,104][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 4.459755897521973, cross_entropy: 4.459755897521973 +[2025-04-28 16:50:41,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 4.011679649353027, cross_entropy: 4.011679649353027 +[2025-04-28 16:50:44,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 4.171858787536621, cross_entropy: 4.171858787536621 +[2025-04-28 16:50:44,996][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 4.205986976623535, cross_entropy: 4.205986976623535 +[2025-04-28 16:50:49,781][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 3.7808728218078613, cross_entropy: 3.7808728218078613 +[2025-04-28 16:50:50,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 3.8496198654174805, cross_entropy: 3.8496198654174805 +[2025-04-28 16:50:53,073][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 4.015285015106201, cross_entropy: 4.015285015106201 +[2025-04-28 16:50:53,750][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 3.2241287231445312, cross_entropy: 3.2241287231445312 +[2025-04-28 16:50:56,129][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 4.555050849914551, cross_entropy: 4.555050849914551 +[2025-04-28 16:50:56,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.443547248840332, cross_entropy: 3.443547248840332 +[2025-04-28 16:50:59,712][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 3.9256973266601562, cross_entropy: 3.9256973266601562 +[2025-04-28 16:51:00,410][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.0719499588012695, cross_entropy: 4.0719499588012695 +[2025-04-28 16:51:02,882][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.449820041656494, cross_entropy: 3.449820041656494 +[2025-04-28 16:51:03,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 3.8556110858917236, cross_entropy: 3.8556110858917236 +[2025-04-28 16:51:06,069][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.0578019618988037, cross_entropy: 3.0578019618988037 +[2025-04-28 16:51:06,773][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 4.0222039222717285, cross_entropy: 4.0222039222717285 +[2025-04-28 16:51:09,809][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 3.6171469688415527, cross_entropy: 3.6171469688415527 +[2025-04-28 16:51:10,540][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 3.909559965133667, cross_entropy: 3.909559965133667 +[2025-04-28 16:51:13,551][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.330406904220581, cross_entropy: 3.330406904220581 +[2025-04-28 16:51:14,251][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.67592716217041, cross_entropy: 3.67592716217041 +[2025-04-28 16:51:16,405][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 3.699136257171631, cross_entropy: 3.699136257171631 +[2025-04-28 16:51:17,087][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.7423806190490723, cross_entropy: 3.7423806190490723 +[2025-04-28 16:51:19,776][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 4.1119771003723145, cross_entropy: 4.1119771003723145 +[2025-04-28 16:51:20,656][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 2.8609213829040527, cross_entropy: 2.8609213829040527 +[2025-04-28 16:51:23,309][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 3.5943093299865723, cross_entropy: 3.5943093299865723 +[2025-04-28 16:51:24,031][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 3.3556947708129883, cross_entropy: 3.3556947708129883 +[2025-04-28 16:51:26,407][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 3.4653162956237793, cross_entropy: 3.4653162956237793 +[2025-04-28 16:51:27,158][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 4.412123203277588, cross_entropy: 4.412123203277588 +[2025-04-28 16:51:29,562][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.15045166015625, cross_entropy: 3.15045166015625 +[2025-04-28 16:51:30,251][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 3.9011144638061523, cross_entropy: 3.9011144638061523 +[2025-04-28 16:51:32,801][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.4693093299865723, cross_entropy: 3.4693093299865723 +[2025-04-28 16:51:33,547][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.697018623352051, cross_entropy: 3.697018623352051 +[2025-04-28 16:51:36,180][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.1292922496795654, cross_entropy: 3.1292922496795654 +[2025-04-28 16:51:37,024][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 4.27595329284668, cross_entropy: 4.27595329284668 +[2025-04-28 16:51:40,177][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 4.366191864013672, cross_entropy: 4.366191864013672 +[2025-04-28 16:51:40,952][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 3.5655789375305176, cross_entropy: 3.5655789375305176 +[2025-04-28 16:51:45,531][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 3.804546356201172, cross_entropy: 3.804546356201172 +[2025-04-28 16:51:46,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 3.348832845687866, cross_entropy: 3.348832845687866 +[2025-04-28 16:51:48,795][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 3.8812923431396484, cross_entropy: 3.8812923431396484 +[2025-04-28 16:51:49,493][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 4.331306457519531, cross_entropy: 4.331306457519531 +[2025-04-28 16:51:52,229][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 3.884951114654541, cross_entropy: 3.884951114654541 +[2025-04-28 16:51:52,923][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.4324488639831543, cross_entropy: 3.4324488639831543 +[2025-04-28 16:51:56,813][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 3.306107521057129, cross_entropy: 3.306107521057129 +[2025-04-28 16:51:57,487][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 3.3706445693969727, cross_entropy: 3.3706445693969727 +[2025-04-28 16:52:00,376][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.1148600578308105, cross_entropy: 3.1148600578308105 +[2025-04-28 16:52:01,052][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.845461845397949, cross_entropy: 3.845461845397949 +[2025-04-28 16:52:03,352][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.7491939067840576, cross_entropy: 3.7491939067840576 +[2025-04-28 16:52:04,042][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 3.126615047454834, cross_entropy: 3.126615047454834 +[2025-04-28 16:52:06,554][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 4.314990997314453, cross_entropy: 4.314990997314453 +[2025-04-28 16:52:07,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 3.297764539718628, cross_entropy: 3.297764539718628 +[2025-04-28 16:52:09,917][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.640988826751709, cross_entropy: 3.640988826751709 +[2025-04-28 16:52:10,593][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.138587713241577, cross_entropy: 3.138587713241577 +[2025-04-28 16:52:13,674][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 3.5429954528808594, cross_entropy: 3.5429954528808594 +[2025-04-28 16:52:14,356][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 3.717597723007202, cross_entropy: 3.717597723007202 +[2025-04-28 16:52:17,543][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 3.6786632537841797, cross_entropy: 3.6786632537841797 +[2025-04-28 16:52:18,220][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.3331682682037354, cross_entropy: 3.3331682682037354 +[2025-04-28 16:52:21,544][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 4.202176094055176, cross_entropy: 4.202176094055176 +[2025-04-28 16:52:22,237][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 3.7656161785125732, cross_entropy: 3.7656161785125732 +[2025-04-28 16:52:24,890][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 3.6167283058166504, cross_entropy: 3.6167283058166504 +[2025-04-28 16:52:25,586][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 3.623490810394287, cross_entropy: 3.623490810394287 +[2025-04-28 16:52:27,993][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 4.181125640869141, cross_entropy: 4.181125640869141 +[2025-04-28 16:52:28,688][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.3940610885620117, cross_entropy: 3.3940610885620117 +[2025-04-28 16:52:31,738][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.471404552459717, cross_entropy: 3.471404552459717 +[2025-04-28 16:52:32,430][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.368238925933838, cross_entropy: 3.368238925933838 +[2025-04-28 16:52:35,245][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.538170337677002, cross_entropy: 3.538170337677002 +[2025-04-28 16:52:35,945][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.528717517852783, cross_entropy: 3.528717517852783 +[2025-04-28 16:52:39,082][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.684751510620117, cross_entropy: 3.684751510620117 +[2025-04-28 16:52:39,779][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 3.772441864013672, cross_entropy: 3.772441864013672 +[2025-04-28 16:52:42,339][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 3.9474387168884277, cross_entropy: 3.9474387168884277 +[2025-04-28 16:52:43,032][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 4.009830474853516, cross_entropy: 4.009830474853516 +[2025-04-28 16:52:45,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 4.386306285858154, cross_entropy: 4.386306285858154 +[2025-04-28 16:52:46,196][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 3.288264274597168, cross_entropy: 3.288264274597168 +[2025-04-28 16:52:49,110][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.034449815750122, cross_entropy: 3.034449815750122 +[2025-04-28 16:52:49,794][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.552405595779419, cross_entropy: 3.552405595779419 +[2025-04-28 16:52:52,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 2.9542224407196045, cross_entropy: 2.9542224407196045 +[2025-04-28 16:52:53,107][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 3.9666333198547363, cross_entropy: 3.9666333198547363 +[2025-04-28 16:52:55,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 3.4955320358276367, cross_entropy: 3.4955320358276367 +[2025-04-28 16:52:56,550][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 2.863413095474243, cross_entropy: 2.863413095474243 +[2025-04-28 16:52:59,045][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.552624225616455, cross_entropy: 3.552624225616455 +[2025-04-28 16:52:59,734][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 2.633030414581299, cross_entropy: 2.633030414581299 +[2025-04-28 16:53:02,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 4.182320594787598, cross_entropy: 4.182320594787598 +[2025-04-28 16:53:03,130][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 3.9908194541931152, cross_entropy: 3.9908194541931152 +[2025-04-28 16:53:06,783][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 3.362563133239746, cross_entropy: 3.362563133239746 +[2025-04-28 16:53:07,464][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 3.9988672733306885, cross_entropy: 3.9988672733306885 +[2025-04-28 16:53:10,628][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 4.204957485198975, cross_entropy: 4.204957485198975 +[2025-04-28 16:53:11,327][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.3311033248901367, cross_entropy: 3.3311033248901367 +[2025-04-28 16:53:13,442][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 4.120538711547852, cross_entropy: 4.120538711547852 +[2025-04-28 16:53:14,122][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.3351550102233887, cross_entropy: 3.3351550102233887 +[2025-04-28 16:53:16,821][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.2798430919647217, cross_entropy: 3.2798430919647217 +[2025-04-28 16:56:00,676][BaseTrainer][INFO] - [Epoch 1/10] (train) 4.2988176345825195, cross_entropy: 4.2988176345825195 +[2025-04-28 16:56:00,677][BaseTrainer][INFO] - [Epoch 1/10] (validation) 2.989560842514038, cross_entropy: 2.989560842514038 +[2025-04-28 16:56:01,170][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 16:56:01,644][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch1.pth. +[2025-04-28 16:56:02,117][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 16:56:06,654][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 4.242246627807617, cross_entropy: 4.242246627807617 +[2025-04-28 16:56:07,371][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 4.418604850769043, cross_entropy: 4.418604850769043 +[2025-04-28 16:56:10,159][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.298123836517334, cross_entropy: 3.298123836517334 +[2025-04-28 16:56:10,837][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 4.181632995605469, cross_entropy: 4.181632995605469 +[2025-04-28 16:56:13,601][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 3.0518579483032227, cross_entropy: 3.0518579483032227 +[2025-04-28 16:56:14,279][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 3.2743945121765137, cross_entropy: 3.2743945121765137 +[2025-04-28 16:56:16,843][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 3.7632150650024414, cross_entropy: 3.7632150650024414 +[2025-04-28 16:56:17,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 4.025813102722168, cross_entropy: 4.025813102722168 +[2025-04-28 16:56:20,135][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 3.6071534156799316, cross_entropy: 3.6071534156799316 +[2025-04-28 16:56:20,841][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 3.502251148223877, cross_entropy: 3.502251148223877 +[2025-04-28 16:56:22,983][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 4.003920078277588, cross_entropy: 4.003920078277588 +[2025-04-28 16:56:23,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 2.921018123626709, cross_entropy: 2.921018123626709 +[2025-04-28 16:56:26,088][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.299309253692627, cross_entropy: 3.299309253692627 +[2025-04-28 16:56:26,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 3.8953371047973633, cross_entropy: 3.8953371047973633 +[2025-04-28 16:56:29,152][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.260864734649658, cross_entropy: 3.260864734649658 +[2025-04-28 16:56:29,826][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 4.2144060134887695, cross_entropy: 4.2144060134887695 +[2025-04-28 16:56:32,154][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 3.5620741844177246, cross_entropy: 3.5620741844177246 +[2025-04-28 16:56:32,829][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 3.3545432090759277, cross_entropy: 3.3545432090759277 +[2025-04-28 16:56:35,219][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.1980576515197754, cross_entropy: 3.1980576515197754 +[2025-04-28 16:56:35,920][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.662811756134033, cross_entropy: 2.662811756134033 +[2025-04-28 16:56:38,111][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 3.886855363845825, cross_entropy: 3.886855363845825 +[2025-04-28 16:56:38,839][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 3.496643304824829, cross_entropy: 3.496643304824829 +[2025-04-28 16:56:41,166][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.189941644668579, cross_entropy: 3.189941644668579 +[2025-04-28 16:56:41,984][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 4.265686988830566, cross_entropy: 4.265686988830566 +[2025-04-28 16:56:44,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.5464982986450195, cross_entropy: 3.5464982986450195 +[2025-04-28 16:56:44,915][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 4.034979820251465, cross_entropy: 4.034979820251465 +[2025-04-28 16:56:47,799][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.136120319366455, cross_entropy: 3.136120319366455 +[2025-04-28 16:56:48,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 3.5238797664642334, cross_entropy: 3.5238797664642334 +[2025-04-28 16:56:51,925][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 4.379042148590088, cross_entropy: 4.379042148590088 +[2025-04-28 16:56:52,628][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 3.865997314453125, cross_entropy: 3.865997314453125 +[2025-04-28 16:56:54,439][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 3.787390947341919, cross_entropy: 3.787390947341919 +[2025-04-28 16:56:55,142][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 3.7829806804656982, cross_entropy: 3.7829806804656982 +[2025-04-28 16:56:57,542][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 4.134833335876465, cross_entropy: 4.134833335876465 +[2025-04-28 16:56:58,247][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 3.385730028152466, cross_entropy: 3.385730028152466 +[2025-04-28 16:57:00,677][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 3.8369596004486084, cross_entropy: 3.8369596004486084 +[2025-04-28 16:57:01,380][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.3606717586517334, cross_entropy: 3.3606717586517334 +[2025-04-28 16:57:03,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.254594326019287, cross_entropy: 3.254594326019287 +[2025-04-28 16:57:04,031][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 3.949110507965088, cross_entropy: 3.949110507965088 +[2025-04-28 16:57:06,077][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 3.9533255100250244, cross_entropy: 3.9533255100250244 +[2025-04-28 16:57:06,773][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 3.0133564472198486, cross_entropy: 3.0133564472198486 +[2025-04-28 16:57:09,300][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.2174408435821533, cross_entropy: 3.2174408435821533 +[2025-04-28 16:57:09,980][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 2.774911642074585, cross_entropy: 2.774911642074585 +[2025-04-28 16:57:12,437][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.880009651184082, cross_entropy: 3.880009651184082 +[2025-04-28 16:57:13,174][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 3.2931466102600098, cross_entropy: 3.2931466102600098 +[2025-04-28 16:57:15,749][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.2892837524414062, cross_entropy: 3.2892837524414062 +[2025-04-28 16:57:16,449][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.26582670211792, cross_entropy: 3.26582670211792 +[2025-04-28 16:57:18,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.761862277984619, cross_entropy: 3.761862277984619 +[2025-04-28 16:57:19,463][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 3.453827381134033, cross_entropy: 3.453827381134033 +[2025-04-28 16:57:21,202][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 2.7391867637634277, cross_entropy: 2.7391867637634277 +[2025-04-28 16:57:21,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 3.9973909854888916, cross_entropy: 3.9973909854888916 +[2025-04-28 16:57:24,374][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.0745346546173096, cross_entropy: 3.0745346546173096 +[2025-04-28 16:57:25,079][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 3.91763973236084, cross_entropy: 3.91763973236084 +[2025-04-28 16:57:26,939][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.2796216011047363, cross_entropy: 3.2796216011047363 +[2025-04-28 16:57:27,639][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 2.918327569961548, cross_entropy: 2.918327569961548 +[2025-04-28 16:57:29,683][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.7638492584228516, cross_entropy: 3.7638492584228516 +[2025-04-28 16:57:30,388][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 3.939401626586914, cross_entropy: 3.939401626586914 +[2025-04-28 16:57:32,277][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 3.7853786945343018, cross_entropy: 3.7853786945343018 +[2025-04-28 16:57:32,950][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 3.167387008666992, cross_entropy: 3.167387008666992 +[2025-04-28 16:57:35,263][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.2527875900268555, cross_entropy: 3.2527875900268555 +[2025-04-28 16:57:35,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.871666669845581, cross_entropy: 3.871666669845581 +[2025-04-28 16:57:38,060][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.676574230194092, cross_entropy: 3.676574230194092 +[2025-04-28 16:57:38,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.9081966876983643, cross_entropy: 3.9081966876983643 +[2025-04-28 16:57:40,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 3.6908297538757324, cross_entropy: 3.6908297538757324 +[2025-04-28 16:57:41,604][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 3.96549916267395, cross_entropy: 3.96549916267395 +[2025-04-28 16:57:44,830][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 3.5497870445251465, cross_entropy: 3.5497870445251465 +[2025-04-28 16:57:45,505][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.363522529602051, cross_entropy: 3.363522529602051 +[2025-04-28 16:57:48,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 3.107814311981201, cross_entropy: 3.107814311981201 +[2025-04-28 16:57:49,056][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 3.248478412628174, cross_entropy: 3.248478412628174 +[2025-04-28 16:57:51,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 3.3494229316711426, cross_entropy: 3.3494229316711426 +[2025-04-28 16:57:51,729][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.0089023113250732, cross_entropy: 3.0089023113250732 +[2025-04-28 16:57:54,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.413144111633301, cross_entropy: 3.413144111633301 +[2025-04-28 16:57:54,856][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 4.16323184967041, cross_entropy: 4.16323184967041 +[2025-04-28 16:57:57,000][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.523125410079956, cross_entropy: 3.523125410079956 +[2025-04-28 16:57:57,704][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 3.093252658843994, cross_entropy: 3.093252658843994 +[2025-04-28 16:57:59,599][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 3.432079792022705, cross_entropy: 3.432079792022705 +[2025-04-28 16:58:00,303][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 4.0937933921813965, cross_entropy: 4.0937933921813965 +[2025-04-28 16:58:02,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 3.8614044189453125, cross_entropy: 3.8614044189453125 +[2025-04-28 16:58:02,936][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.4553651809692383, cross_entropy: 3.4553651809692383 +[2025-04-28 16:58:04,615][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.05112624168396, cross_entropy: 3.05112624168396 +[2025-04-28 16:58:05,315][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.385305404663086, cross_entropy: 3.385305404663086 +[2025-04-28 16:58:07,011][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 3.7016687393188477, cross_entropy: 3.7016687393188477 +[2025-04-28 16:58:07,685][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.0622506141662598, cross_entropy: 3.0622506141662598 +[2025-04-28 16:58:09,929][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 2.9708075523376465, cross_entropy: 2.9708075523376465 +[2025-04-28 16:58:10,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.162452220916748, cross_entropy: 3.162452220916748 +[2025-04-28 16:58:13,211][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 2.831974506378174, cross_entropy: 2.831974506378174 +[2025-04-28 16:58:13,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 3.9374756813049316, cross_entropy: 3.9374756813049316 +[2025-04-28 16:58:16,361][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.1150312423706055, cross_entropy: 3.1150312423706055 +[2025-04-28 16:58:17,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.550893783569336, cross_entropy: 3.550893783569336 +[2025-04-28 16:58:19,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 2.8405303955078125, cross_entropy: 2.8405303955078125 +[2025-04-28 16:58:20,014][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 3.456709623336792, cross_entropy: 3.456709623336792 +[2025-04-28 16:58:22,051][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.3038697242736816, cross_entropy: 3.3038697242736816 +[2025-04-28 16:58:22,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 3.987837314605713, cross_entropy: 3.987837314605713 +[2025-04-28 16:58:24,665][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.7166571617126465, cross_entropy: 3.7166571617126465 +[2025-04-28 16:58:25,365][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 3.8028790950775146, cross_entropy: 3.8028790950775146 +[2025-04-28 16:58:27,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 3.4409308433532715, cross_entropy: 3.4409308433532715 +[2025-04-28 16:58:28,549][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 3.142025947570801, cross_entropy: 3.142025947570801 +[2025-04-28 16:58:30,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.448202610015869, cross_entropy: 3.448202610015869 +[2025-04-28 16:58:31,577][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 2.806304454803467, cross_entropy: 2.806304454803467 +[2025-04-28 16:58:33,656][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.272277355194092, cross_entropy: 3.272277355194092 +[2025-04-28 16:58:34,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 2.877896308898926, cross_entropy: 2.877896308898926 +[2025-04-28 16:58:36,377][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 2.5880675315856934, cross_entropy: 2.5880675315856934 +[2025-04-28 16:58:37,084][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.2269959449768066, cross_entropy: 3.2269959449768066 +[2025-04-28 16:58:38,763][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 3.054048776626587, cross_entropy: 3.054048776626587 +[2025-04-28 16:58:39,467][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 2.553710460662842, cross_entropy: 2.553710460662842 +[2025-04-28 16:58:41,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.4544878005981445, cross_entropy: 3.4544878005981445 +[2025-04-28 16:58:42,156][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.905829668045044, cross_entropy: 3.905829668045044 +[2025-04-28 16:58:44,251][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.6500964164733887, cross_entropy: 2.6500964164733887 +[2025-04-28 16:58:44,961][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.668987989425659, cross_entropy: 3.668987989425659 +[2025-04-28 16:58:47,011][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.496640920639038, cross_entropy: 3.496640920639038 +[2025-04-28 16:58:47,735][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.471989393234253, cross_entropy: 3.471989393234253 +[2025-04-28 16:58:50,363][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 2.885037899017334, cross_entropy: 2.885037899017334 +[2025-04-28 16:58:51,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 2.947368621826172, cross_entropy: 2.947368621826172 +[2025-04-28 16:58:53,752][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 4.027257919311523, cross_entropy: 4.027257919311523 +[2025-04-28 16:58:54,429][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 2.88852596282959, cross_entropy: 2.88852596282959 +[2025-04-28 16:58:56,759][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 2.7721102237701416, cross_entropy: 2.7721102237701416 +[2025-04-28 16:58:57,462][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.8766493797302246, cross_entropy: 3.8766493797302246 +[2025-04-28 16:59:00,135][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 3.980137825012207, cross_entropy: 3.980137825012207 +[2025-04-28 16:59:00,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.3294456005096436, cross_entropy: 3.3294456005096436 +[2025-04-28 16:59:03,754][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 3.4843897819519043, cross_entropy: 3.4843897819519043 +[2025-04-28 16:59:04,434][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 3.1926612854003906, cross_entropy: 3.1926612854003906 +[2025-04-28 16:59:07,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.197418212890625, cross_entropy: 3.197418212890625 +[2025-04-28 16:59:07,802][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 4.029559135437012, cross_entropy: 4.029559135437012 +[2025-04-28 16:59:10,000][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 3.735011577606201, cross_entropy: 3.735011577606201 +[2025-04-28 16:59:10,736][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 3.5075559616088867, cross_entropy: 3.5075559616088867 +[2025-04-28 16:59:13,469][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 2.573802947998047, cross_entropy: 2.573802947998047 +[2025-04-28 16:59:14,258][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 3.821460485458374, cross_entropy: 3.821460485458374 +[2025-04-28 16:59:16,450][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.3133456707000732, cross_entropy: 3.3133456707000732 +[2025-04-28 16:59:17,214][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 3.853163719177246, cross_entropy: 3.853163719177246 +[2025-04-28 16:59:18,899][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 2.905996799468994, cross_entropy: 2.905996799468994 +[2025-04-28 16:59:19,693][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 3.9837067127227783, cross_entropy: 3.9837067127227783 +[2025-04-28 16:59:22,242][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 3.913944721221924, cross_entropy: 3.913944721221924 +[2025-04-28 16:59:23,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 2.7333459854125977, cross_entropy: 2.7333459854125977 +[2025-04-28 16:59:24,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 4.122269630432129, cross_entropy: 4.122269630432129 +[2025-04-28 16:59:26,012][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 3.5759284496307373, cross_entropy: 3.5759284496307373 +[2025-04-28 16:59:27,917][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 2.877267837524414, cross_entropy: 2.877267837524414 +[2025-04-28 16:59:28,666][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.078550338745117, cross_entropy: 3.078550338745117 +[2025-04-28 16:59:30,955][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.7289953231811523, cross_entropy: 2.7289953231811523 +[2025-04-28 16:59:31,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 3.9396636486053467, cross_entropy: 3.9396636486053467 +[2025-04-28 16:59:34,726][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.5181665420532227, cross_entropy: 3.5181665420532227 +[2025-04-28 16:59:35,402][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 3.720830202102661, cross_entropy: 3.720830202102661 +[2025-04-28 16:59:37,807][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.0030415058135986, cross_entropy: 3.0030415058135986 +[2025-04-28 16:59:38,544][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.8614425659179688, cross_entropy: 2.8614425659179688 +[2025-04-28 16:59:41,268][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.6572558879852295, cross_entropy: 3.6572558879852295 +[2025-04-28 16:59:41,968][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 2.7003841400146484, cross_entropy: 2.7003841400146484 +[2025-04-28 16:59:44,112][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.5611815452575684, cross_entropy: 2.5611815452575684 +[2025-04-28 16:59:44,868][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 3.0365796089172363, cross_entropy: 3.0365796089172363 +[2025-04-28 16:59:47,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 3.0237855911254883, cross_entropy: 3.0237855911254883 +[2025-04-28 16:59:47,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.34566068649292, cross_entropy: 2.34566068649292 +[2025-04-28 16:59:50,223][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 3.251784086227417, cross_entropy: 3.251784086227417 +[2025-04-28 16:59:50,927][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 2.8367350101470947, cross_entropy: 2.8367350101470947 +[2025-04-28 16:59:53,773][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 4.365346908569336, cross_entropy: 4.365346908569336 +[2025-04-28 16:59:54,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.6882853507995605, cross_entropy: 3.6882853507995605 +[2025-04-28 16:59:56,886][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.9353649616241455, cross_entropy: 3.9353649616241455 +[2025-04-28 16:59:57,585][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 2.621428966522217, cross_entropy: 2.621428966522217 +[2025-04-28 16:59:59,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.14534330368042, cross_entropy: 3.14534330368042 +[2025-04-28 17:00:00,391][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 3.620765209197998, cross_entropy: 3.620765209197998 +[2025-04-28 17:00:03,312][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 2.577465057373047, cross_entropy: 2.577465057373047 +[2025-04-28 17:00:04,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.839728355407715, cross_entropy: 3.839728355407715 +[2025-04-28 17:00:05,557][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.137406826019287, cross_entropy: 3.137406826019287 +[2025-04-28 17:00:06,257][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 3.4214673042297363, cross_entropy: 3.4214673042297363 +[2025-04-28 17:00:08,526][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 3.1857244968414307, cross_entropy: 3.1857244968414307 +[2025-04-28 17:00:09,232][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.459439277648926, cross_entropy: 3.459439277648926 +[2025-04-28 17:00:10,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 3.6305904388427734, cross_entropy: 3.6305904388427734 +[2025-04-28 17:00:11,657][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 3.7453548908233643, cross_entropy: 3.7453548908233643 +[2025-04-28 17:00:14,068][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 3.194277048110962, cross_entropy: 3.194277048110962 +[2025-04-28 17:00:14,742][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.541049003601074, cross_entropy: 2.541049003601074 +[2025-04-28 17:00:17,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 3.4577603340148926, cross_entropy: 3.4577603340148926 +[2025-04-28 17:00:17,695][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 3.009793281555176, cross_entropy: 3.009793281555176 +[2025-04-28 17:00:20,745][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 2.992496967315674, cross_entropy: 2.992496967315674 +[2025-04-28 17:00:21,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 2.840968132019043, cross_entropy: 2.840968132019043 +[2025-04-28 17:00:22,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 4.062169075012207, cross_entropy: 4.062169075012207 +[2025-04-28 17:00:23,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.6492433547973633, cross_entropy: 2.6492433547973633 +[2025-04-28 17:00:25,766][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 3.721726417541504, cross_entropy: 3.721726417541504 +[2025-04-28 17:00:26,466][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.6145362854003906, cross_entropy: 2.6145362854003906 +[2025-04-28 17:00:28,876][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 4.208179950714111, cross_entropy: 4.208179950714111 +[2025-04-28 17:00:29,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 3.4529402256011963, cross_entropy: 3.4529402256011963 +[2025-04-28 17:00:32,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 3.405555486679077, cross_entropy: 3.405555486679077 +[2025-04-28 17:00:32,909][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 3.3668947219848633, cross_entropy: 3.3668947219848633 +[2025-04-28 17:00:35,022][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 2.728463888168335, cross_entropy: 2.728463888168335 +[2025-04-28 17:00:35,732][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 2.7357497215270996, cross_entropy: 2.7357497215270996 +[2025-04-28 17:00:37,960][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.7320351600646973, cross_entropy: 2.7320351600646973 +[2025-04-28 17:00:38,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 4.123425483703613, cross_entropy: 4.123425483703613 +[2025-04-28 17:00:40,471][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 2.8718738555908203, cross_entropy: 2.8718738555908203 +[2025-04-28 17:00:42,387][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 3.396078109741211, cross_entropy: 3.396078109741211 +[2025-04-28 17:00:43,855][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.633723258972168, cross_entropy: 2.633723258972168 +[2025-04-28 17:00:45,458][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 3.8705551624298096, cross_entropy: 3.8705551624298096 +[2025-04-28 17:00:47,084][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.600776195526123, cross_entropy: 2.600776195526123 +[2025-04-28 17:00:48,309][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 2.964155435562134, cross_entropy: 2.964155435562134 +[2025-04-28 17:00:50,287][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.3858530521392822, cross_entropy: 3.3858530521392822 +[2025-04-28 17:00:51,246][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.7663638591766357, cross_entropy: 2.7663638591766357 +[2025-04-28 17:00:53,205][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.001082420349121, cross_entropy: 3.001082420349121 +[2025-04-28 17:00:54,407][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 3.2841286659240723, cross_entropy: 3.2841286659240723 +[2025-04-28 17:00:55,799][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.685375213623047, cross_entropy: 2.685375213623047 +[2025-04-28 17:00:57,397][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 2.871119499206543, cross_entropy: 2.871119499206543 +[2025-04-28 17:00:59,099][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.4635281562805176, cross_entropy: 2.4635281562805176 +[2025-04-28 17:01:00,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 3.7886040210723877, cross_entropy: 3.7886040210723877 +[2025-04-28 17:01:02,072][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.4048519134521484, cross_entropy: 3.4048519134521484 +[2025-04-28 17:01:02,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.0049800872802734, cross_entropy: 3.0049800872802734 +[2025-04-28 17:01:05,273][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.911656379699707, cross_entropy: 3.911656379699707 +[2025-04-28 17:01:06,190][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 2.778350353240967, cross_entropy: 2.778350353240967 +[2025-04-28 17:01:08,033][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 3.076406478881836, cross_entropy: 3.076406478881836 +[2025-04-28 17:01:09,323][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 2.247615337371826, cross_entropy: 2.247615337371826 +[2025-04-28 17:01:11,755][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.85009765625, cross_entropy: 3.85009765625 +[2025-04-28 17:01:13,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 3.6110572814941406, cross_entropy: 3.6110572814941406 +[2025-04-28 17:01:14,946][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 3.788726806640625, cross_entropy: 3.788726806640625 +[2025-04-28 17:01:17,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 3.009470224380493, cross_entropy: 3.009470224380493 +[2025-04-28 17:01:18,588][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 2.9380831718444824, cross_entropy: 2.9380831718444824 +[2025-04-28 17:01:20,292][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 4.386854648590088, cross_entropy: 4.386854648590088 +[2025-04-28 17:01:21,857][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 2.6687052249908447, cross_entropy: 2.6687052249908447 +[2025-04-28 17:01:23,009][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 3.8453407287597656, cross_entropy: 3.8453407287597656 +[2025-04-28 17:01:24,969][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.4670839309692383, cross_entropy: 3.4670839309692383 +[2025-04-28 17:01:26,587][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 2.269672155380249, cross_entropy: 2.269672155380249 +[2025-04-28 17:01:28,110][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 3.8213741779327393, cross_entropy: 3.8213741779327393 +[2025-04-28 17:01:29,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 3.6845178604125977, cross_entropy: 3.6845178604125977 +[2025-04-28 17:01:31,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 4.035249710083008, cross_entropy: 4.035249710083008 +[2025-04-28 17:01:33,362][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 2.595322370529175, cross_entropy: 2.595322370529175 +[2025-04-28 17:01:34,918][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 2.8541808128356934, cross_entropy: 2.8541808128356934 +[2025-04-28 17:01:36,095][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.4856579303741455, cross_entropy: 2.4856579303741455 +[2025-04-28 17:01:37,813][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.784067392349243, cross_entropy: 2.784067392349243 +[2025-04-28 17:01:39,746][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.626924753189087, cross_entropy: 2.626924753189087 +[2025-04-28 17:01:40,911][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 2.4178647994995117, cross_entropy: 2.4178647994995117 +[2025-04-28 17:01:42,697][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 3.8432092666625977, cross_entropy: 3.8432092666625977 +[2025-04-28 17:01:43,730][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.481334686279297, cross_entropy: 2.481334686279297 +[2025-04-28 17:01:45,662][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 3.2510900497436523, cross_entropy: 3.2510900497436523 +[2025-04-28 17:01:47,057][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 4.045265197753906, cross_entropy: 4.045265197753906 +[2025-04-28 17:01:48,373][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 3.646352529525757, cross_entropy: 3.646352529525757 +[2025-04-28 17:01:50,448][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 3.657640218734741, cross_entropy: 3.657640218734741 +[2025-04-28 17:01:51,384][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.636876344680786, cross_entropy: 3.636876344680786 +[2025-04-28 17:01:53,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.5486884117126465, cross_entropy: 3.5486884117126465 +[2025-04-28 17:01:55,078][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.432732582092285, cross_entropy: 2.432732582092285 +[2025-04-28 17:01:55,991][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 2.995727062225342, cross_entropy: 2.995727062225342 +[2025-04-28 17:01:58,648][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.984184503555298, cross_entropy: 2.984184503555298 +[2025-04-28 17:01:59,406][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 2.7477736473083496, cross_entropy: 2.7477736473083496 +[2025-04-28 17:02:02,244][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 3.949115753173828, cross_entropy: 3.949115753173828 +[2025-04-28 17:02:02,954][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.5670881271362305, cross_entropy: 2.5670881271362305 +[2025-04-28 17:02:05,569][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.005985736846924, cross_entropy: 2.005985736846924 +[2025-04-28 17:02:06,278][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 3.323073625564575, cross_entropy: 3.323073625564575 +[2025-04-28 17:02:08,892][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 4.029878616333008, cross_entropy: 4.029878616333008 +[2025-04-28 17:02:09,573][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 3.2196784019470215, cross_entropy: 3.2196784019470215 +[2025-04-28 17:02:12,401][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.8619439601898193, cross_entropy: 2.8619439601898193 +[2025-04-28 17:02:13,111][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 3.77768611907959, cross_entropy: 3.77768611907959 +[2025-04-28 17:02:15,302][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 3.890669822692871, cross_entropy: 3.890669822692871 +[2025-04-28 17:02:16,023][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 2.578974723815918, cross_entropy: 2.578974723815918 +[2025-04-28 17:02:19,092][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.5718579292297363, cross_entropy: 2.5718579292297363 +[2025-04-28 17:02:19,808][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 3.878490924835205, cross_entropy: 3.878490924835205 +[2025-04-28 17:02:22,094][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 3.0178136825561523, cross_entropy: 3.0178136825561523 +[2025-04-28 17:02:22,774][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.78169584274292, cross_entropy: 2.78169584274292 +[2025-04-28 17:02:25,495][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 3.7275032997131348, cross_entropy: 3.7275032997131348 +[2025-04-28 17:02:26,180][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.5968737602233887, cross_entropy: 2.5968737602233887 +[2025-04-28 17:02:29,419][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 3.35020112991333, cross_entropy: 3.35020112991333 +[2025-04-28 17:02:30,097][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 2.443722724914551, cross_entropy: 2.443722724914551 +[2025-04-28 17:02:32,568][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.729640483856201, cross_entropy: 3.729640483856201 +[2025-04-28 17:02:33,306][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.4788150787353516, cross_entropy: 3.4788150787353516 +[2025-04-28 17:02:37,390][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.363420009613037, cross_entropy: 3.363420009613037 +[2025-04-28 17:02:38,102][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.5322155952453613, cross_entropy: 2.5322155952453613 +[2025-04-28 17:02:39,869][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 3.221555233001709, cross_entropy: 3.221555233001709 +[2025-04-28 17:02:40,577][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 4.178959369659424, cross_entropy: 4.178959369659424 +[2025-04-28 17:02:43,020][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.7488183975219727, cross_entropy: 2.7488183975219727 +[2025-04-28 17:02:43,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.366253614425659, cross_entropy: 2.366253614425659 +[2025-04-28 17:02:45,998][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.462860345840454, cross_entropy: 2.462860345840454 +[2025-04-28 17:02:46,705][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 3.3635590076446533, cross_entropy: 3.3635590076446533 +[2025-04-28 17:02:49,248][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 3.6887969970703125, cross_entropy: 3.6887969970703125 +[2025-04-28 17:02:49,927][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.5700159072875977, cross_entropy: 2.5700159072875977 +[2025-04-28 17:02:52,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.561056613922119, cross_entropy: 2.561056613922119 +[2025-04-28 17:02:52,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 2.8256654739379883, cross_entropy: 2.8256654739379883 +[2025-04-28 17:02:55,497][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.402924060821533, cross_entropy: 2.402924060821533 +[2025-04-28 17:02:56,203][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 2.70456600189209, cross_entropy: 2.70456600189209 +[2025-04-28 17:03:00,393][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.706494092941284, cross_entropy: 3.706494092941284 +[2025-04-28 17:03:01,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 2.353665590286255, cross_entropy: 2.353665590286255 +[2025-04-28 17:03:04,626][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 3.6264543533325195, cross_entropy: 3.6264543533325195 +[2025-04-28 17:03:05,329][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 1.9796526432037354, cross_entropy: 1.9796526432037354 +[2025-04-28 17:03:09,871][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 3.9911396503448486, cross_entropy: 3.9911396503448486 +[2025-04-28 17:03:10,577][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.8558602333068848, cross_entropy: 3.8558602333068848 +[2025-04-28 17:03:13,189][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 2.1853911876678467, cross_entropy: 2.1853911876678467 +[2025-04-28 17:03:13,896][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 2.1474533081054688, cross_entropy: 2.1474533081054688 +[2025-04-28 17:03:15,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 2.7896056175231934, cross_entropy: 2.7896056175231934 +[2025-04-28 17:03:16,595][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 2.002326011657715, cross_entropy: 2.002326011657715 +[2025-04-28 17:03:18,471][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 3.353419303894043, cross_entropy: 3.353419303894043 +[2025-04-28 17:03:19,186][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.953303813934326, cross_entropy: 2.953303813934326 +[2025-04-28 17:03:22,240][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.6686391830444336, cross_entropy: 2.6686391830444336 +[2025-04-28 17:03:22,948][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 2.485536575317383, cross_entropy: 2.485536575317383 +[2025-04-28 17:03:25,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.5610952377319336, cross_entropy: 2.5610952377319336 +[2025-04-28 17:03:26,046][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 3.645244598388672, cross_entropy: 3.645244598388672 +[2025-04-28 17:03:28,769][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 3.1669018268585205, cross_entropy: 3.1669018268585205 +[2025-04-28 17:03:29,473][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.8631064891815186, cross_entropy: 2.8631064891815186 +[2025-04-28 17:03:32,674][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.7137062549591064, cross_entropy: 2.7137062549591064 +[2025-04-28 17:03:33,379][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.7266292572021484, cross_entropy: 3.7266292572021484 +[2025-04-28 17:03:35,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 3.605412006378174, cross_entropy: 3.605412006378174 +[2025-04-28 17:03:36,103][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 2.831418514251709, cross_entropy: 2.831418514251709 +[2025-04-28 17:03:38,873][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 2.411531925201416, cross_entropy: 2.411531925201416 +[2025-04-28 17:03:39,581][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 3.8208420276641846, cross_entropy: 3.8208420276641846 +[2025-04-28 17:03:41,681][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.449472665786743, cross_entropy: 2.449472665786743 +[2025-04-28 17:03:42,452][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.4380362033843994, cross_entropy: 3.4380362033843994 +[2025-04-28 17:03:44,620][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 2.5245585441589355, cross_entropy: 2.5245585441589355 +[2025-04-28 17:03:45,344][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 4.012470245361328, cross_entropy: 4.012470245361328 +[2025-04-28 17:03:47,550][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 3.171353340148926, cross_entropy: 3.171353340148926 +[2025-04-28 17:03:48,904][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 2.511396884918213, cross_entropy: 2.511396884918213 +[2025-04-28 17:03:50,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 3.2292113304138184, cross_entropy: 3.2292113304138184 +[2025-04-28 17:03:52,122][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.5132527351379395, cross_entropy: 3.5132527351379395 +[2025-04-28 17:03:53,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.8177270889282227, cross_entropy: 3.8177270889282227 +[2025-04-28 17:03:55,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 3.0304033756256104, cross_entropy: 3.0304033756256104 +[2025-04-28 17:03:56,764][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 2.9697084426879883, cross_entropy: 2.9697084426879883 +[2025-04-28 17:03:58,669][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.350196361541748, cross_entropy: 2.350196361541748 +[2025-04-28 17:03:59,747][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 3.802319049835205, cross_entropy: 3.802319049835205 +[2025-04-28 17:04:01,511][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 2.7177586555480957, cross_entropy: 2.7177586555480957 +[2025-04-28 17:04:02,649][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 2.843658924102783, cross_entropy: 2.843658924102783 +[2025-04-28 17:04:04,071][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.6220345497131348, cross_entropy: 3.6220345497131348 +[2025-04-28 17:04:05,586][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 2.766317367553711, cross_entropy: 2.766317367553711 +[2025-04-28 17:04:07,246][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 1.8673025369644165, cross_entropy: 1.8673025369644165 +[2025-04-28 17:04:09,334][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 2.743497848510742, cross_entropy: 2.743497848510742 +[2025-04-28 17:04:10,179][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 2.0146324634552, cross_entropy: 2.0146324634552 +[2025-04-28 17:04:13,158][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.593796968460083, cross_entropy: 2.593796968460083 +[2025-04-28 17:04:14,014][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 2.523386240005493, cross_entropy: 2.523386240005493 +[2025-04-28 17:04:16,039][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 2.808879852294922, cross_entropy: 2.808879852294922 +[2025-04-28 17:04:16,922][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.2039403915405273, cross_entropy: 2.2039403915405273 +[2025-04-28 17:04:19,073][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 3.975130319595337, cross_entropy: 3.975130319595337 +[2025-04-28 17:04:19,800][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 2.473109722137451, cross_entropy: 2.473109722137451 +[2025-04-28 17:04:21,961][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.329657554626465, cross_entropy: 2.329657554626465 +[2025-04-28 17:04:22,937][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 2.6849563121795654, cross_entropy: 2.6849563121795654 +[2025-04-28 17:04:25,852][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 2.3359413146972656, cross_entropy: 2.3359413146972656 +[2025-04-28 17:04:26,565][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.2901861667633057, cross_entropy: 2.2901861667633057 +[2025-04-28 17:04:29,084][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.374147415161133, cross_entropy: 2.374147415161133 +[2025-04-28 17:04:29,860][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.788764476776123, cross_entropy: 2.788764476776123 +[2025-04-28 17:04:32,522][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.5738868713378906, cross_entropy: 2.5738868713378906 +[2025-04-28 17:04:34,730][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 2.700495719909668, cross_entropy: 2.700495719909668 +[2025-04-28 17:04:36,516][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 3.694209098815918, cross_entropy: 3.694209098815918 +[2025-04-28 17:04:37,689][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.335829734802246, cross_entropy: 2.335829734802246 +[2025-04-28 17:04:39,375][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.673022508621216, cross_entropy: 3.673022508621216 +[2025-04-28 17:04:40,802][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 3.916534423828125, cross_entropy: 3.916534423828125 +[2025-04-28 17:04:43,136][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 3.2688920497894287, cross_entropy: 3.2688920497894287 +[2025-04-28 17:04:44,173][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 2.769412040710449, cross_entropy: 2.769412040710449 +[2025-04-28 17:04:46,715][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.547952651977539, cross_entropy: 3.547952651977539 +[2025-04-28 17:04:47,486][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.4120259284973145, cross_entropy: 3.4120259284973145 +[2025-04-28 17:04:49,671][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 3.78849720954895, cross_entropy: 3.78849720954895 +[2025-04-28 17:04:50,405][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 2.6027653217315674, cross_entropy: 2.6027653217315674 +[2025-04-28 17:04:53,200][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 2.6462888717651367, cross_entropy: 2.6462888717651367 +[2025-04-28 17:04:53,954][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.731265068054199, cross_entropy: 3.731265068054199 +[2025-04-28 17:04:55,835][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 3.687821388244629, cross_entropy: 3.687821388244629 +[2025-04-28 17:04:56,916][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 2.5868239402770996, cross_entropy: 2.5868239402770996 +[2025-04-28 17:04:58,328][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.211026668548584, cross_entropy: 2.211026668548584 +[2025-04-28 17:05:00,677][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.602034091949463, cross_entropy: 3.602034091949463 +[2025-04-28 17:05:01,444][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 3.9120304584503174, cross_entropy: 3.9120304584503174 +[2025-04-28 17:05:04,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 3.6949462890625, cross_entropy: 3.6949462890625 +[2025-04-28 17:05:04,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.6592206954956055, cross_entropy: 3.6592206954956055 +[2025-04-28 17:05:07,377][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 3.6073083877563477, cross_entropy: 3.6073083877563477 +[2025-04-28 17:05:08,072][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 2.6425180435180664, cross_entropy: 2.6425180435180664 +[2025-04-28 17:05:10,903][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.113116502761841, cross_entropy: 3.113116502761841 +[2025-04-28 17:05:11,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 2.890058994293213, cross_entropy: 2.890058994293213 +[2025-04-28 17:05:13,895][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.4530386924743652, cross_entropy: 2.4530386924743652 +[2025-04-28 17:05:14,606][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 4.001585960388184, cross_entropy: 4.001585960388184 +[2025-04-28 17:05:17,793][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.6944828033447266, cross_entropy: 2.6944828033447266 +[2025-04-28 17:05:19,124][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 3.7199180126190186, cross_entropy: 3.7199180126190186 +[2025-04-28 17:05:22,101][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 2.1814794540405273, cross_entropy: 2.1814794540405273 +[2025-04-28 17:05:22,824][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 3.87503981590271, cross_entropy: 3.87503981590271 +[2025-04-28 17:05:25,237][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 3.049842357635498, cross_entropy: 3.049842357635498 +[2025-04-28 17:05:25,850][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 2.97145676612854, cross_entropy: 2.97145676612854 +[2025-04-28 17:07:56,504][BaseTrainer][INFO] - [Epoch 2/10] (train) 3.243356466293335, cross_entropy: 3.243356466293335 +[2025-04-28 17:07:56,505][BaseTrainer][INFO] - [Epoch 2/10] (validation) 2.121924877166748, cross_entropy: 2.121924877166748 +[2025-04-28 17:07:57,436][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 17:07:57,974][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch2.pth. +[2025-04-28 17:07:58,828][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 17:08:04,335][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 2.543409585952759, cross_entropy: 2.543409585952759 +[2025-04-28 17:08:05,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 3.152899742126465, cross_entropy: 3.152899742126465 +[2025-04-28 17:08:08,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 3.40267276763916, cross_entropy: 3.40267276763916 +[2025-04-28 17:08:08,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 3.5984411239624023, cross_entropy: 3.5984411239624023 +[2025-04-28 17:08:11,686][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 3.8544745445251465, cross_entropy: 3.8544745445251465 +[2025-04-28 17:08:12,402][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.352107048034668, cross_entropy: 2.352107048034668 +[2025-04-28 17:08:14,386][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 2.2186574935913086, cross_entropy: 2.2186574935913086 +[2025-04-28 17:08:15,098][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 3.4292094707489014, cross_entropy: 3.4292094707489014 +[2025-04-28 17:08:17,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 3.206850051879883, cross_entropy: 3.206850051879883 +[2025-04-28 17:08:18,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 3.0386509895324707, cross_entropy: 3.0386509895324707 +[2025-04-28 17:08:20,959][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 2.6812820434570312, cross_entropy: 2.6812820434570312 +[2025-04-28 17:08:21,699][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 2.275205135345459, cross_entropy: 2.275205135345459 +[2025-04-28 17:08:24,083][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 2.7226524353027344, cross_entropy: 2.7226524353027344 +[2025-04-28 17:08:24,843][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 3.5009093284606934, cross_entropy: 3.5009093284606934 +[2025-04-28 17:08:27,853][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 2.9707627296447754, cross_entropy: 2.9707627296447754 +[2025-04-28 17:08:28,779][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 3.71598482131958, cross_entropy: 3.71598482131958 +[2025-04-28 17:08:31,332][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.726879119873047, cross_entropy: 3.726879119873047 +[2025-04-28 17:08:32,761][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 3.384910821914673, cross_entropy: 3.384910821914673 +[2025-04-28 17:08:34,511][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 3.2327067852020264, cross_entropy: 3.2327067852020264 +[2025-04-28 17:08:36,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 2.4238529205322266, cross_entropy: 2.4238529205322266 +[2025-04-28 17:08:38,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 2.312880516052246, cross_entropy: 2.312880516052246 +[2025-04-28 17:08:39,796][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 2.912224292755127, cross_entropy: 2.912224292755127 +[2025-04-28 17:08:42,782][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.6978490352630615, cross_entropy: 3.6978490352630615 +[2025-04-28 17:08:43,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 2.216439723968506, cross_entropy: 2.216439723968506 +[2025-04-28 17:08:45,491][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.260094165802002, cross_entropy: 3.260094165802002 +[2025-04-28 17:08:46,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 3.781987190246582, cross_entropy: 3.781987190246582 +[2025-04-28 17:08:49,061][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 3.3821444511413574, cross_entropy: 3.3821444511413574 +[2025-04-28 17:08:49,939][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.492375373840332, cross_entropy: 2.492375373840332 +[2025-04-28 17:08:52,220][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 2.8452985286712646, cross_entropy: 2.8452985286712646 +[2025-04-28 17:08:52,930][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.8985378742218018, cross_entropy: 2.8985378742218018 +[2025-04-28 17:08:55,869][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 2.218449592590332, cross_entropy: 2.218449592590332 +[2025-04-28 17:08:56,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 2.263188600540161, cross_entropy: 2.263188600540161 +[2025-04-28 17:08:59,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 2.620328187942505, cross_entropy: 2.620328187942505 +[2025-04-28 17:09:00,207][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 2.362377166748047, cross_entropy: 2.362377166748047 +[2025-04-28 17:09:02,243][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 2.814523696899414, cross_entropy: 2.814523696899414 +[2025-04-28 17:09:02,985][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 2.0553646087646484, cross_entropy: 2.0553646087646484 +[2025-04-28 17:09:05,403][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 3.9172840118408203, cross_entropy: 3.9172840118408203 +[2025-04-28 17:09:06,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 1.9889150857925415, cross_entropy: 1.9889150857925415 +[2025-04-28 17:09:08,584][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 4.108907699584961, cross_entropy: 4.108907699584961 +[2025-04-28 17:09:09,811][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 3.9895434379577637, cross_entropy: 3.9895434379577637 +[2025-04-28 17:09:12,026][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 3.407442569732666, cross_entropy: 3.407442569732666 +[2025-04-28 17:09:12,937][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 2.284611463546753, cross_entropy: 2.284611463546753 +[2025-04-28 17:09:15,304][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 2.9708895683288574, cross_entropy: 2.9708895683288574 +[2025-04-28 17:09:16,134][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.431919574737549, cross_entropy: 2.431919574737549 +[2025-04-28 17:09:18,823][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.320061206817627, cross_entropy: 2.320061206817627 +[2025-04-28 17:09:19,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 3.3332056999206543, cross_entropy: 3.3332056999206543 +[2025-04-28 17:09:21,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 3.3341100215911865, cross_entropy: 3.3341100215911865 +[2025-04-28 17:09:22,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.5593509674072266, cross_entropy: 2.5593509674072266 +[2025-04-28 17:09:24,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.51796817779541, cross_entropy: 2.51796817779541 +[2025-04-28 17:09:25,423][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 3.612927198410034, cross_entropy: 3.612927198410034 +[2025-04-28 17:09:28,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.5119645595550537, cross_entropy: 2.5119645595550537 +[2025-04-28 17:09:29,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 3.87593412399292, cross_entropy: 3.87593412399292 +[2025-04-28 17:09:31,090][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 2.9713778495788574, cross_entropy: 2.9713778495788574 +[2025-04-28 17:09:32,637][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 2.3218820095062256, cross_entropy: 2.3218820095062256 +[2025-04-28 17:09:34,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 2.6110715866088867, cross_entropy: 2.6110715866088867 +[2025-04-28 17:09:36,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 2.9213361740112305, cross_entropy: 2.9213361740112305 +[2025-04-28 17:09:38,474][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.4047794342041016, cross_entropy: 3.4047794342041016 +[2025-04-28 17:09:39,582][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.563055992126465, cross_entropy: 2.563055992126465 +[2025-04-28 17:09:41,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 1.8891526460647583, cross_entropy: 1.8891526460647583 +[2025-04-28 17:09:43,140][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 2.8924875259399414, cross_entropy: 2.8924875259399414 +[2025-04-28 17:09:44,811][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.4386179447174072, cross_entropy: 2.4386179447174072 +[2025-04-28 17:09:46,318][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.917235851287842, cross_entropy: 2.917235851287842 +[2025-04-28 17:09:47,856][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.7011919021606445, cross_entropy: 3.7011919021606445 +[2025-04-28 17:09:50,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 2.5106825828552246, cross_entropy: 2.5106825828552246 +[2025-04-28 17:09:51,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.038891077041626, cross_entropy: 3.038891077041626 +[2025-04-28 17:09:53,303][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 3.4958982467651367, cross_entropy: 3.4958982467651367 +[2025-04-28 17:09:55,345][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 3.7057483196258545, cross_entropy: 3.7057483196258545 +[2025-04-28 17:09:57,091][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 2.9178428649902344, cross_entropy: 2.9178428649902344 +[2025-04-28 17:09:59,830][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 3.6340713500976562, cross_entropy: 3.6340713500976562 +[2025-04-28 17:10:00,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 2.399099826812744, cross_entropy: 2.399099826812744 +[2025-04-28 17:10:03,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.3048295974731445, cross_entropy: 2.3048295974731445 +[2025-04-28 17:10:04,112][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 2.9984774589538574, cross_entropy: 2.9984774589538574 +[2025-04-28 17:10:06,952][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 3.5477960109710693, cross_entropy: 3.5477960109710693 +[2025-04-28 17:10:07,634][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.1034021377563477, cross_entropy: 2.1034021377563477 +[2025-04-28 17:10:10,295][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.7849650382995605, cross_entropy: 3.7849650382995605 +[2025-04-28 17:10:10,986][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 2.0661635398864746, cross_entropy: 2.0661635398864746 +[2025-04-28 17:10:13,991][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 3.369100570678711, cross_entropy: 3.369100570678711 +[2025-04-28 17:10:14,678][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 3.64288330078125, cross_entropy: 3.64288330078125 +[2025-04-28 17:10:18,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.802276372909546, cross_entropy: 3.802276372909546 +[2025-04-28 17:10:19,303][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 2.407264232635498, cross_entropy: 2.407264232635498 +[2025-04-28 17:10:22,509][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 3.9923171997070312, cross_entropy: 3.9923171997070312 +[2025-04-28 17:10:23,199][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 2.8071277141571045, cross_entropy: 2.8071277141571045 +[2025-04-28 17:10:26,711][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.7615785598754883, cross_entropy: 3.7615785598754883 +[2025-04-28 17:10:27,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 3.2887539863586426, cross_entropy: 3.2887539863586426 +[2025-04-28 17:10:30,293][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 2.4022817611694336, cross_entropy: 2.4022817611694336 +[2025-04-28 17:10:30,981][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.62283992767334, cross_entropy: 2.62283992767334 +[2025-04-28 17:10:33,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 3.9435362815856934, cross_entropy: 3.9435362815856934 +[2025-04-28 17:10:34,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.450589418411255, cross_entropy: 3.450589418411255 +[2025-04-28 17:10:36,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 2.69046950340271, cross_entropy: 2.69046950340271 +[2025-04-28 17:10:37,359][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 2.5174355506896973, cross_entropy: 2.5174355506896973 +[2025-04-28 17:10:41,597][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 2.5396595001220703, cross_entropy: 2.5396595001220703 +[2025-04-28 17:10:42,283][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 3.7880759239196777, cross_entropy: 3.7880759239196777 +[2025-04-28 17:10:46,238][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 2.611046075820923, cross_entropy: 2.611046075820923 +[2025-04-28 17:10:46,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.5296497344970703, cross_entropy: 2.5296497344970703 +[2025-04-28 17:10:50,575][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.45552921295166, cross_entropy: 3.45552921295166 +[2025-04-28 17:10:51,298][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 1.9270390272140503, cross_entropy: 1.9270390272140503 +[2025-04-28 17:10:54,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 2.652134656906128, cross_entropy: 2.652134656906128 +[2025-04-28 17:10:54,967][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 1.8378602266311646, cross_entropy: 1.8378602266311646 +[2025-04-28 17:10:58,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 3.509354591369629, cross_entropy: 3.509354591369629 +[2025-04-28 17:10:58,925][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.256864309310913, cross_entropy: 2.256864309310913 +[2025-04-28 17:11:01,985][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.3000407218933105, cross_entropy: 2.3000407218933105 +[2025-04-28 17:11:02,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 3.238190174102783, cross_entropy: 3.238190174102783 +[2025-04-28 17:11:05,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.7437586784362793, cross_entropy: 2.7437586784362793 +[2025-04-28 17:11:05,915][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 2.3831920623779297, cross_entropy: 2.3831920623779297 +[2025-04-28 17:11:08,804][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 3.377230644226074, cross_entropy: 3.377230644226074 +[2025-04-28 17:11:09,510][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.8988823890686035, cross_entropy: 2.8988823890686035 +[2025-04-28 17:11:11,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 1.7984695434570312, cross_entropy: 1.7984695434570312 +[2025-04-28 17:11:12,603][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 2.795933246612549, cross_entropy: 2.795933246612549 +[2025-04-28 17:11:15,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 3.5716066360473633, cross_entropy: 3.5716066360473633 +[2025-04-28 17:11:15,997][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.4866695404052734, cross_entropy: 2.4866695404052734 +[2025-04-28 17:11:19,055][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 3.555424213409424, cross_entropy: 3.555424213409424 +[2025-04-28 17:11:19,762][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 2.649698495864868, cross_entropy: 2.649698495864868 +[2025-04-28 17:11:22,473][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 3.041992664337158, cross_entropy: 3.041992664337158 +[2025-04-28 17:11:23,186][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 2.194608449935913, cross_entropy: 2.194608449935913 +[2025-04-28 17:11:25,303][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 3.5396728515625, cross_entropy: 3.5396728515625 +[2025-04-28 17:11:26,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 2.5443344116210938, cross_entropy: 2.5443344116210938 +[2025-04-28 17:11:28,343][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.143733024597168, cross_entropy: 2.143733024597168 +[2025-04-28 17:11:29,057][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.1042184829711914, cross_entropy: 2.1042184829711914 +[2025-04-28 17:11:31,235][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.426833391189575, cross_entropy: 3.426833391189575 +[2025-04-28 17:11:31,916][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.579576015472412, cross_entropy: 2.579576015472412 +[2025-04-28 17:11:35,285][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 3.5539045333862305, cross_entropy: 3.5539045333862305 +[2025-04-28 17:11:35,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 2.286391258239746, cross_entropy: 2.286391258239746 +[2025-04-28 17:11:38,515][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 3.66580867767334, cross_entropy: 3.66580867767334 +[2025-04-28 17:11:39,228][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 2.6996946334838867, cross_entropy: 2.6996946334838867 +[2025-04-28 17:11:41,122][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.263495922088623, cross_entropy: 3.263495922088623 +[2025-04-28 17:11:41,829][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.006981372833252, cross_entropy: 2.006981372833252 +[2025-04-28 17:11:44,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 3.3415048122406006, cross_entropy: 3.3415048122406006 +[2025-04-28 17:11:45,247][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 3.4576199054718018, cross_entropy: 3.4576199054718018 +[2025-04-28 17:11:48,096][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 3.9769515991210938, cross_entropy: 3.9769515991210938 +[2025-04-28 17:11:48,812][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.5891637802124023, cross_entropy: 2.5891637802124023 +[2025-04-28 17:11:51,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.0505237579345703, cross_entropy: 2.0505237579345703 +[2025-04-28 17:11:51,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 3.18996000289917, cross_entropy: 3.18996000289917 +[2025-04-28 17:11:53,778][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.3483080863952637, cross_entropy: 2.3483080863952637 +[2025-04-28 17:11:54,529][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.888477325439453, cross_entropy: 2.888477325439453 +[2025-04-28 17:11:57,417][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.4470739364624023, cross_entropy: 2.4470739364624023 +[2025-04-28 17:11:58,129][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 2.5862655639648438, cross_entropy: 2.5862655639648438 +[2025-04-28 17:12:00,333][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.054164409637451, cross_entropy: 2.054164409637451 +[2025-04-28 17:12:01,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 3.7603840827941895, cross_entropy: 3.7603840827941895 +[2025-04-28 17:12:03,341][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.644927501678467, cross_entropy: 2.644927501678467 +[2025-04-28 17:12:04,056][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 1.999260425567627, cross_entropy: 1.999260425567627 +[2025-04-28 17:12:06,755][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 4.0290632247924805, cross_entropy: 4.0290632247924805 +[2025-04-28 17:12:07,471][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 2.0826613903045654, cross_entropy: 2.0826613903045654 +[2025-04-28 17:12:09,901][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.1667492389678955, cross_entropy: 2.1667492389678955 +[2025-04-28 17:12:10,579][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.484307289123535, cross_entropy: 2.484307289123535 +[2025-04-28 17:12:13,265][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.732396125793457, cross_entropy: 2.732396125793457 +[2025-04-28 17:12:13,977][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.0752625465393066, cross_entropy: 2.0752625465393066 +[2025-04-28 17:12:16,968][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 2.421365737915039, cross_entropy: 2.421365737915039 +[2025-04-28 17:12:17,681][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 2.027838945388794, cross_entropy: 2.027838945388794 +[2025-04-28 17:12:20,387][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 2.9876654148101807, cross_entropy: 2.9876654148101807 +[2025-04-28 17:12:21,101][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 3.8983864784240723, cross_entropy: 3.8983864784240723 +[2025-04-28 17:12:23,673][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 2.308152914047241, cross_entropy: 2.308152914047241 +[2025-04-28 17:12:24,356][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.245009422302246, cross_entropy: 2.245009422302246 +[2025-04-28 17:12:26,720][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 3.1072258949279785, cross_entropy: 3.1072258949279785 +[2025-04-28 17:12:27,436][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 3.3531248569488525, cross_entropy: 3.3531248569488525 +[2025-04-28 17:12:30,511][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 2.904006004333496, cross_entropy: 2.904006004333496 +[2025-04-28 17:12:31,195][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.0864217281341553, cross_entropy: 2.0864217281341553 +[2025-04-28 17:12:33,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 2.6704699993133545, cross_entropy: 2.6704699993133545 +[2025-04-28 17:12:34,449][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 3.713700294494629, cross_entropy: 3.713700294494629 +[2025-04-28 17:12:37,159][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 3.262434482574463, cross_entropy: 3.262434482574463 +[2025-04-28 17:12:37,878][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 2.2851879596710205, cross_entropy: 2.2851879596710205 +[2025-04-28 17:12:40,696][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.111574172973633, cross_entropy: 3.111574172973633 +[2025-04-28 17:12:41,453][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.2723002433776855, cross_entropy: 3.2723002433776855 +[2025-04-28 17:12:43,474][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 2.0758118629455566, cross_entropy: 2.0758118629455566 +[2025-04-28 17:12:44,225][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 3.0505034923553467, cross_entropy: 3.0505034923553467 +[2025-04-28 17:12:46,352][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 3.170884609222412, cross_entropy: 3.170884609222412 +[2025-04-28 17:12:47,274][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 2.338029384613037, cross_entropy: 2.338029384613037 +[2025-04-28 17:12:50,249][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 3.579188346862793, cross_entropy: 3.579188346862793 +[2025-04-28 17:12:51,029][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 3.2894718647003174, cross_entropy: 3.2894718647003174 +[2025-04-28 17:12:53,802][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 2.253108501434326, cross_entropy: 2.253108501434326 +[2025-04-28 17:12:54,510][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 2.897714138031006, cross_entropy: 2.897714138031006 +[2025-04-28 17:12:57,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 2.169098377227783, cross_entropy: 2.169098377227783 +[2025-04-28 17:12:57,954][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 3.575882911682129, cross_entropy: 3.575882911682129 +[2025-04-28 17:13:00,593][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.579601764678955, cross_entropy: 3.579601764678955 +[2025-04-28 17:13:01,302][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 3.6415796279907227, cross_entropy: 3.6415796279907227 +[2025-04-28 17:13:03,518][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 3.826910972595215, cross_entropy: 3.826910972595215 +[2025-04-28 17:13:04,296][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 1.6680724620819092, cross_entropy: 1.6680724620819092 +[2025-04-28 17:13:06,586][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.4937076568603516, cross_entropy: 2.4937076568603516 +[2025-04-28 17:13:07,425][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 2.672630786895752, cross_entropy: 2.672630786895752 +[2025-04-28 17:13:09,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 2.104994297027588, cross_entropy: 2.104994297027588 +[2025-04-28 17:13:10,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.8368093967437744, cross_entropy: 2.8368093967437744 +[2025-04-28 17:13:13,682][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 1.8502562046051025, cross_entropy: 1.8502562046051025 +[2025-04-28 17:13:14,394][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.148057699203491, cross_entropy: 2.148057699203491 +[2025-04-28 17:13:16,969][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 1.8736335039138794, cross_entropy: 1.8736335039138794 +[2025-04-28 17:13:17,685][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 3.845736026763916, cross_entropy: 3.845736026763916 +[2025-04-28 17:13:20,968][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 2.747251033782959, cross_entropy: 2.747251033782959 +[2025-04-28 17:13:21,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 2.1095316410064697, cross_entropy: 2.1095316410064697 +[2025-04-28 17:13:24,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 3.4804015159606934, cross_entropy: 3.4804015159606934 +[2025-04-28 17:13:24,841][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 1.735745906829834, cross_entropy: 1.735745906829834 +[2025-04-28 17:13:27,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.420304775238037, cross_entropy: 3.420304775238037 +[2025-04-28 17:13:28,418][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.787081241607666, cross_entropy: 3.787081241607666 +[2025-04-28 17:13:30,494][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.0999577045440674, cross_entropy: 2.0999577045440674 +[2025-04-28 17:13:31,211][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 2.644930601119995, cross_entropy: 2.644930601119995 +[2025-04-28 17:13:33,187][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.663379430770874, cross_entropy: 2.663379430770874 +[2025-04-28 17:13:33,936][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 3.2092936038970947, cross_entropy: 3.2092936038970947 +[2025-04-28 17:13:36,471][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 2.6273233890533447, cross_entropy: 2.6273233890533447 +[2025-04-28 17:13:37,254][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 1.954077124595642, cross_entropy: 1.954077124595642 +[2025-04-28 17:13:39,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 3.8211615085601807, cross_entropy: 3.8211615085601807 +[2025-04-28 17:13:40,070][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 2.4376015663146973, cross_entropy: 2.4376015663146973 +[2025-04-28 17:13:42,636][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 2.3766932487487793, cross_entropy: 2.3766932487487793 +[2025-04-28 17:13:43,347][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 3.7675156593322754, cross_entropy: 3.7675156593322754 +[2025-04-28 17:13:46,539][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.421144485473633, cross_entropy: 2.421144485473633 +[2025-04-28 17:13:47,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.8159589767456055, cross_entropy: 2.8159589767456055 +[2025-04-28 17:13:49,785][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.281259298324585, cross_entropy: 3.281259298324585 +[2025-04-28 17:13:50,501][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.436580181121826, cross_entropy: 2.436580181121826 +[2025-04-28 17:13:52,418][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.429882049560547, cross_entropy: 3.429882049560547 +[2025-04-28 17:13:53,127][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 1.729400396347046, cross_entropy: 1.729400396347046 +[2025-04-28 17:13:55,752][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 3.695931911468506, cross_entropy: 3.695931911468506 +[2025-04-28 17:13:56,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.668196201324463, cross_entropy: 2.668196201324463 +[2025-04-28 17:13:59,544][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.3001301288604736, cross_entropy: 2.3001301288604736 +[2025-04-28 17:14:00,258][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 3.665037155151367, cross_entropy: 3.665037155151367 +[2025-04-28 17:14:02,779][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 3.6403114795684814, cross_entropy: 3.6403114795684814 +[2025-04-28 17:14:03,457][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 2.4580647945404053, cross_entropy: 2.4580647945404053 +[2025-04-28 17:14:05,791][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 3.1154274940490723, cross_entropy: 3.1154274940490723 +[2025-04-28 17:14:06,497][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.4376108646392822, cross_entropy: 2.4376108646392822 +[2025-04-28 17:14:09,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 3.0844383239746094, cross_entropy: 3.0844383239746094 +[2025-04-28 17:14:10,059][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 2.0615925788879395, cross_entropy: 2.0615925788879395 +[2025-04-28 17:14:12,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.2165889739990234, cross_entropy: 2.2165889739990234 +[2025-04-28 17:14:12,909][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.579061508178711, cross_entropy: 3.579061508178711 +[2025-04-28 17:14:16,734][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.5093934535980225, cross_entropy: 2.5093934535980225 +[2025-04-28 17:14:17,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 2.0692057609558105, cross_entropy: 2.0692057609558105 +[2025-04-28 17:14:19,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.8243608474731445, cross_entropy: 1.8243608474731445 +[2025-04-28 17:14:20,670][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 2.7784605026245117, cross_entropy: 2.7784605026245117 +[2025-04-28 17:14:22,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 2.370248794555664, cross_entropy: 2.370248794555664 +[2025-04-28 17:14:23,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.530837059020996, cross_entropy: 3.530837059020996 +[2025-04-28 17:14:26,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.036874532699585, cross_entropy: 3.036874532699585 +[2025-04-28 17:14:27,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 1.911955714225769, cross_entropy: 1.911955714225769 +[2025-04-28 17:14:29,419][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 2.9624269008636475, cross_entropy: 2.9624269008636475 +[2025-04-28 17:14:30,119][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.476325035095215, cross_entropy: 3.476325035095215 +[2025-04-28 17:14:32,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 3.828174114227295, cross_entropy: 3.828174114227295 +[2025-04-28 17:14:33,334][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.4781830310821533, cross_entropy: 3.4781830310821533 +[2025-04-28 17:14:35,706][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.6814827919006348, cross_entropy: 2.6814827919006348 +[2025-04-28 17:14:36,384][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.0293703079223633, cross_entropy: 3.0293703079223633 +[2025-04-28 17:14:38,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 2.02858304977417, cross_entropy: 2.02858304977417 +[2025-04-28 17:14:39,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 3.7165822982788086, cross_entropy: 3.7165822982788086 +[2025-04-28 17:14:42,080][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.6589486598968506, cross_entropy: 3.6589486598968506 +[2025-04-28 17:14:42,798][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.317424774169922, cross_entropy: 2.317424774169922 +[2025-04-28 17:14:44,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 2.696781635284424, cross_entropy: 2.696781635284424 +[2025-04-28 17:14:45,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 3.440666675567627, cross_entropy: 3.440666675567627 +[2025-04-28 17:14:48,017][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 3.168497085571289, cross_entropy: 3.168497085571289 +[2025-04-28 17:14:48,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 2.1353049278259277, cross_entropy: 2.1353049278259277 +[2025-04-28 17:14:50,910][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.402329444885254, cross_entropy: 2.402329444885254 +[2025-04-28 17:14:51,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 1.5651708841323853, cross_entropy: 1.5651708841323853 +[2025-04-28 17:14:53,519][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.4266061782836914, cross_entropy: 2.4266061782836914 +[2025-04-28 17:14:54,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 3.3088715076446533, cross_entropy: 3.3088715076446533 +[2025-04-28 17:14:57,567][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 3.4725341796875, cross_entropy: 3.4725341796875 +[2025-04-28 17:14:58,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.536909341812134, cross_entropy: 2.536909341812134 +[2025-04-28 17:15:01,227][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.8600568771362305, cross_entropy: 3.8600568771362305 +[2025-04-28 17:15:01,907][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.8663270473480225, cross_entropy: 1.8663270473480225 +[2025-04-28 17:15:04,551][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.4820117950439453, cross_entropy: 2.4820117950439453 +[2025-04-28 17:15:05,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.226879835128784, cross_entropy: 2.226879835128784 +[2025-04-28 17:15:07,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 3.074559211730957, cross_entropy: 3.074559211730957 +[2025-04-28 17:15:07,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.7698023319244385, cross_entropy: 1.7698023319244385 +[2025-04-28 17:15:10,195][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 2.8721516132354736, cross_entropy: 2.8721516132354736 +[2025-04-28 17:15:10,907][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 2.4200005531311035, cross_entropy: 2.4200005531311035 +[2025-04-28 17:15:13,245][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.6259772777557373, cross_entropy: 3.6259772777557373 +[2025-04-28 17:15:13,955][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 1.9762632846832275, cross_entropy: 1.9762632846832275 +[2025-04-28 17:15:15,971][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 3.9196650981903076, cross_entropy: 3.9196650981903076 +[2025-04-28 17:15:16,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.546530246734619, cross_entropy: 3.546530246734619 +[2025-04-28 17:15:18,885][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 2.216787338256836, cross_entropy: 2.216787338256836 +[2025-04-28 17:15:19,563][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 1.6198773384094238, cross_entropy: 1.6198773384094238 +[2025-04-28 17:15:21,904][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 3.548391342163086, cross_entropy: 3.548391342163086 +[2025-04-28 17:15:22,609][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 3.831822633743286, cross_entropy: 3.831822633743286 +[2025-04-28 17:15:24,993][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.6877076625823975, cross_entropy: 3.6877076625823975 +[2025-04-28 17:15:25,701][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 3.7652370929718018, cross_entropy: 3.7652370929718018 +[2025-04-28 17:15:28,429][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.433145046234131, cross_entropy: 3.433145046234131 +[2025-04-28 17:15:29,141][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 2.2186827659606934, cross_entropy: 2.2186827659606934 +[2025-04-28 17:15:32,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 1.9907212257385254, cross_entropy: 1.9907212257385254 +[2025-04-28 17:15:32,862][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 2.9518685340881348, cross_entropy: 2.9518685340881348 +[2025-04-28 17:15:35,687][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.5316834449768066, cross_entropy: 3.5316834449768066 +[2025-04-28 17:15:36,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 2.2226996421813965, cross_entropy: 2.2226996421813965 +[2025-04-28 17:15:38,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 2.1312248706817627, cross_entropy: 2.1312248706817627 +[2025-04-28 17:15:39,440][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 3.632100820541382, cross_entropy: 3.632100820541382 +[2025-04-28 17:15:41,651][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.50754976272583, cross_entropy: 3.50754976272583 +[2025-04-28 17:15:42,357][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.1788573265075684, cross_entropy: 2.1788573265075684 +[2025-04-28 17:15:44,854][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 3.8184733390808105, cross_entropy: 3.8184733390808105 +[2025-04-28 17:15:45,564][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 2.273608446121216, cross_entropy: 2.273608446121216 +[2025-04-28 17:15:48,152][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 3.104614019393921, cross_entropy: 3.104614019393921 +[2025-04-28 17:15:48,861][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 3.59610915184021, cross_entropy: 3.59610915184021 +[2025-04-28 17:15:51,058][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.9436057806015015, cross_entropy: 1.9436057806015015 +[2025-04-28 17:15:51,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.624453544616699, cross_entropy: 2.624453544616699 +[2025-04-28 17:15:54,547][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 2.25958514213562, cross_entropy: 2.25958514213562 +[2025-04-28 17:15:55,252][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 2.1600067615509033, cross_entropy: 2.1600067615509033 +[2025-04-28 17:15:57,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 2.2280759811401367, cross_entropy: 2.2280759811401367 +[2025-04-28 17:15:58,095][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 3.017017364501953, cross_entropy: 3.017017364501953 +[2025-04-28 17:16:00,327][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 2.1213605403900146, cross_entropy: 2.1213605403900146 +[2025-04-28 17:16:01,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 2.704040050506592, cross_entropy: 2.704040050506592 +[2025-04-28 17:16:04,135][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.2747740745544434, cross_entropy: 2.2747740745544434 +[2025-04-28 17:16:04,836][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 2.6039628982543945, cross_entropy: 2.6039628982543945 +[2025-04-28 17:16:05,689][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/iteration1000.pth. +[2025-04-28 17:16:08,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 3.3694815635681152, cross_entropy: 3.3694815635681152 +[2025-04-28 17:16:09,451][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 3.1732053756713867, cross_entropy: 3.1732053756713867 +[2025-04-28 17:16:12,170][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 2.391303062438965, cross_entropy: 2.391303062438965 +[2025-04-28 17:16:12,850][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.7519530057907104, cross_entropy: 1.7519530057907104 +[2025-04-28 17:16:15,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 3.630692481994629, cross_entropy: 3.630692481994629 +[2025-04-28 17:16:15,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 3.440430164337158, cross_entropy: 3.440430164337158 +[2025-04-28 17:16:18,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.3674135208129883, cross_entropy: 2.3674135208129883 +[2025-04-28 17:16:19,459][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.314105987548828, cross_entropy: 2.314105987548828 +[2025-04-28 17:16:21,422][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.7152068614959717, cross_entropy: 2.7152068614959717 +[2025-04-28 17:16:22,127][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 3.128081798553467, cross_entropy: 3.128081798553467 +[2025-04-28 17:16:23,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 2.0681958198547363, cross_entropy: 2.0681958198547363 +[2025-04-28 17:16:24,435][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.2922027111053467, cross_entropy: 2.2922027111053467 +[2025-04-28 17:16:26,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 3.542454719543457, cross_entropy: 3.542454719543457 +[2025-04-28 17:16:27,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 3.8932502269744873, cross_entropy: 3.8932502269744873 +[2025-04-28 17:16:29,599][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 3.5386364459991455, cross_entropy: 3.5386364459991455 +[2025-04-28 17:16:30,350][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.0440592765808105, cross_entropy: 3.0440592765808105 +[2025-04-28 17:16:33,190][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.0886170864105225, cross_entropy: 2.0886170864105225 +[2025-04-28 17:16:33,897][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.731264114379883, cross_entropy: 2.731264114379883 +[2025-04-28 17:16:36,202][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.555743932723999, cross_entropy: 2.555743932723999 +[2025-04-28 17:16:36,881][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 3.023789167404175, cross_entropy: 3.023789167404175 +[2025-04-28 17:16:39,744][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.6929824352264404, cross_entropy: 3.6929824352264404 +[2025-04-28 17:16:40,476][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.0501415729522705, cross_entropy: 2.0501415729522705 +[2025-04-28 17:16:43,044][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.789933204650879, cross_entropy: 1.789933204650879 +[2025-04-28 17:16:43,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 2.033061981201172, cross_entropy: 2.033061981201172 +[2025-04-28 17:16:45,902][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 3.628084182739258, cross_entropy: 3.628084182739258 +[2025-04-28 17:16:46,609][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.5534214973449707, cross_entropy: 2.5534214973449707 +[2025-04-28 17:16:48,892][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 2.9118151664733887, cross_entropy: 2.9118151664733887 +[2025-04-28 17:16:49,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 3.5788755416870117, cross_entropy: 3.5788755416870117 +[2025-04-28 17:16:51,442][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 3.4464244842529297, cross_entropy: 3.4464244842529297 +[2025-04-28 17:16:52,694][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 3.37749981880188, cross_entropy: 3.37749981880188 +[2025-04-28 17:16:53,753][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 3.7369742393493652, cross_entropy: 3.7369742393493652 +[2025-04-28 17:16:56,231][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.0882601737976074, cross_entropy: 3.0882601737976074 +[2025-04-28 17:16:57,069][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 2.4181151390075684, cross_entropy: 2.4181151390075684 +[2025-04-28 17:16:59,707][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 2.874356746673584, cross_entropy: 2.874356746673584 +[2025-04-28 17:17:00,453][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 1.9128289222717285, cross_entropy: 1.9128289222717285 +[2025-04-28 17:17:02,488][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 3.6139211654663086, cross_entropy: 3.6139211654663086 +[2025-04-28 17:17:03,173][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 2.806992530822754, cross_entropy: 2.806992530822754 +[2025-04-28 17:17:06,060][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 2.10628604888916, cross_entropy: 2.10628604888916 +[2025-04-28 17:17:06,804][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 2.874474048614502, cross_entropy: 2.874474048614502 +[2025-04-28 17:17:08,875][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.3458075523376465, cross_entropy: 3.3458075523376465 +[2025-04-28 17:17:09,890][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 3.7771897315979004, cross_entropy: 3.7771897315979004 +[2025-04-28 17:17:11,923][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 2.6479053497314453, cross_entropy: 2.6479053497314453 +[2025-04-28 17:17:12,700][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.1061363220214844, cross_entropy: 3.1061363220214844 +[2025-04-28 17:17:14,485][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 3.262360095977783, cross_entropy: 3.262360095977783 +[2025-04-28 17:17:16,247][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 3.5034751892089844, cross_entropy: 3.5034751892089844 +[2025-04-28 17:17:17,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 1.886107325553894, cross_entropy: 1.886107325553894 +[2025-04-28 17:17:19,000][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 3.2395334243774414, cross_entropy: 3.2395334243774414 +[2025-04-28 17:17:20,740][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 3.681236982345581, cross_entropy: 3.681236982345581 +[2025-04-28 17:17:21,939][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 2.824953556060791, cross_entropy: 2.824953556060791 +[2025-04-28 17:17:25,802][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 2.4710469245910645, cross_entropy: 2.4710469245910645 +[2025-04-28 17:17:26,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 1.793500542640686, cross_entropy: 1.793500542640686 +[2025-04-28 17:17:28,925][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 1.8762351274490356, cross_entropy: 1.8762351274490356 +[2025-04-28 17:17:29,637][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 2.689065456390381, cross_entropy: 2.689065456390381 +[2025-04-28 17:17:32,110][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 2.913808584213257, cross_entropy: 2.913808584213257 +[2025-04-28 17:17:32,806][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 2.1620383262634277, cross_entropy: 2.1620383262634277 +[2025-04-28 17:17:35,400][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 2.37503719329834, cross_entropy: 2.37503719329834 +[2025-04-28 17:17:36,111][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 2.314314126968384, cross_entropy: 2.314314126968384 +[2025-04-28 17:17:39,066][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 2.0631346702575684, cross_entropy: 2.0631346702575684 +[2025-04-28 17:17:39,767][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 2.4172208309173584, cross_entropy: 2.4172208309173584 +[2025-04-28 17:17:42,021][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.5122907161712646, cross_entropy: 1.5122907161712646 +[2025-04-28 17:17:42,717][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.7660514116287231, cross_entropy: 1.7660514116287231 +[2025-04-28 17:17:45,108][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 3.705183982849121, cross_entropy: 3.705183982849121 +[2025-04-28 17:17:45,783][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 2.7388155460357666, cross_entropy: 2.7388155460357666 +[2025-04-28 17:17:47,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 1.8651777505874634, cross_entropy: 1.8651777505874634 +[2025-04-28 17:17:48,639][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.053220272064209, cross_entropy: 3.053220272064209 +[2025-04-28 17:17:51,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 1.9808242321014404, cross_entropy: 1.9808242321014404 +[2025-04-28 17:17:51,899][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 1.766865849494934, cross_entropy: 1.766865849494934 +[2025-04-28 17:17:53,604][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 1.9584881067276, cross_entropy: 1.9584881067276 +[2025-04-28 17:20:20,851][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.8297765254974365, cross_entropy: 2.8297765254974365 +[2025-04-28 17:20:20,852][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.7614223957061768, cross_entropy: 1.7614223957061768 +[2025-04-28 17:20:21,731][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 17:20:22,228][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch3.pth. +[2025-04-28 17:20:23,032][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 17:20:27,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 2.1339783668518066, cross_entropy: 2.1339783668518066 +[2025-04-28 17:20:28,008][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 2.8933959007263184, cross_entropy: 2.8933959007263184 +[2025-04-28 17:20:30,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.926826000213623, cross_entropy: 1.926826000213623 +[2025-04-28 17:20:30,930][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.6717379093170166, cross_entropy: 1.6717379093170166 +[2025-04-28 17:20:32,968][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 3.239593505859375, cross_entropy: 3.239593505859375 +[2025-04-28 17:20:34,573][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 2.133841037750244, cross_entropy: 2.133841037750244 +[2025-04-28 17:20:36,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 3.422031879425049, cross_entropy: 3.422031879425049 +[2025-04-28 17:20:37,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 3.544246196746826, cross_entropy: 3.544246196746826 +[2025-04-28 17:20:39,688][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 2.831042528152466, cross_entropy: 2.831042528152466 +[2025-04-28 17:20:42,059][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 3.2839412689208984, cross_entropy: 3.2839412689208984 +[2025-04-28 17:20:42,789][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 2.020548105239868, cross_entropy: 2.020548105239868 +[2025-04-28 17:20:46,426][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.468862533569336, cross_entropy: 2.468862533569336 +[2025-04-28 17:20:47,109][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 3.0450339317321777, cross_entropy: 3.0450339317321777 +[2025-04-28 17:20:51,374][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.4702351093292236, cross_entropy: 2.4702351093292236 +[2025-04-28 17:20:52,080][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 3.37178635597229, cross_entropy: 3.37178635597229 +[2025-04-28 17:20:54,797][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.6942265033721924, cross_entropy: 1.6942265033721924 +[2025-04-28 17:20:55,507][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.067894697189331, cross_entropy: 2.067894697189331 +[2025-04-28 17:20:58,141][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 2.3983118534088135, cross_entropy: 2.3983118534088135 +[2025-04-28 17:20:58,829][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.1217803955078125, cross_entropy: 3.1217803955078125 +[2025-04-28 17:21:01,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.1054470539093018, cross_entropy: 2.1054470539093018 +[2025-04-28 17:21:02,438][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 3.2444043159484863, cross_entropy: 3.2444043159484863 +[2025-04-28 17:21:05,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 2.0186755657196045, cross_entropy: 2.0186755657196045 +[2025-04-28 17:21:06,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.089254856109619, cross_entropy: 2.089254856109619 +[2025-04-28 17:21:09,157][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 3.830533742904663, cross_entropy: 3.830533742904663 +[2025-04-28 17:21:09,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 3.7389047145843506, cross_entropy: 3.7389047145843506 +[2025-04-28 17:21:11,750][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.7122443914413452, cross_entropy: 1.7122443914413452 +[2025-04-28 17:21:12,457][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 1.7378995418548584, cross_entropy: 1.7378995418548584 +[2025-04-28 17:21:14,732][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.2104735374450684, cross_entropy: 3.2104735374450684 +[2025-04-28 17:21:15,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.7819995880126953, cross_entropy: 2.7819995880126953 +[2025-04-28 17:21:18,143][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.042921543121338, cross_entropy: 2.042921543121338 +[2025-04-28 17:21:18,881][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 1.8645395040512085, cross_entropy: 1.8645395040512085 +[2025-04-28 17:21:21,272][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 2.457592487335205, cross_entropy: 2.457592487335205 +[2025-04-28 17:21:22,415][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 3.419771671295166, cross_entropy: 3.419771671295166 +[2025-04-28 17:21:25,188][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.9425156116485596, cross_entropy: 2.9425156116485596 +[2025-04-28 17:21:25,896][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.0647263526916504, cross_entropy: 2.0647263526916504 +[2025-04-28 17:21:28,301][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 2.1849093437194824, cross_entropy: 2.1849093437194824 +[2025-04-28 17:21:29,010][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 2.9112205505371094, cross_entropy: 2.9112205505371094 +[2025-04-28 17:21:31,697][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 3.0175936222076416, cross_entropy: 3.0175936222076416 +[2025-04-28 17:21:32,402][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.3958005905151367, cross_entropy: 3.3958005905151367 +[2025-04-28 17:21:34,879][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 1.7676270008087158, cross_entropy: 1.7676270008087158 +[2025-04-28 17:21:35,557][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.4395008087158203, cross_entropy: 2.4395008087158203 +[2025-04-28 17:21:38,219][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 3.254179000854492, cross_entropy: 3.254179000854492 +[2025-04-28 17:21:38,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.3593201637268066, cross_entropy: 2.3593201637268066 +[2025-04-28 17:21:41,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 3.084822654724121, cross_entropy: 3.084822654724121 +[2025-04-28 17:21:42,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 3.7487361431121826, cross_entropy: 3.7487361431121826 +[2025-04-28 17:21:45,626][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.6467654705047607, cross_entropy: 2.6467654705047607 +[2025-04-28 17:21:46,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 1.8675646781921387, cross_entropy: 1.8675646781921387 +[2025-04-28 17:21:49,045][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 2.6627180576324463, cross_entropy: 2.6627180576324463 +[2025-04-28 17:21:49,764][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 2.722914218902588, cross_entropy: 2.722914218902588 +[2025-04-28 17:21:52,158][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.1093692779541016, cross_entropy: 2.1093692779541016 +[2025-04-28 17:21:52,876][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 2.2250630855560303, cross_entropy: 2.2250630855560303 +[2025-04-28 17:21:55,143][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 3.120887279510498, cross_entropy: 3.120887279510498 +[2025-04-28 17:21:55,823][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.053553342819214, cross_entropy: 2.053553342819214 +[2025-04-28 17:21:58,764][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 3.0876996517181396, cross_entropy: 3.0876996517181396 +[2025-04-28 17:21:59,471][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 2.208205461502075, cross_entropy: 2.208205461502075 +[2025-04-28 17:22:01,760][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 2.0797433853149414, cross_entropy: 2.0797433853149414 +[2025-04-28 17:22:02,486][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.058980941772461, cross_entropy: 2.058980941772461 +[2025-04-28 17:22:04,906][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.4729347229003906, cross_entropy: 2.4729347229003906 +[2025-04-28 17:22:05,627][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 3.6012754440307617, cross_entropy: 3.6012754440307617 +[2025-04-28 17:22:08,583][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.507783889770508, cross_entropy: 2.507783889770508 +[2025-04-28 17:22:09,306][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.7915053367614746, cross_entropy: 1.7915053367614746 +[2025-04-28 17:22:12,213][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 3.4846489429473877, cross_entropy: 3.4846489429473877 +[2025-04-28 17:22:12,897][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 2.160965919494629, cross_entropy: 2.160965919494629 +[2025-04-28 17:22:16,005][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 2.2922756671905518, cross_entropy: 2.2922756671905518 +[2025-04-28 17:22:16,727][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.033135414123535, cross_entropy: 2.033135414123535 +[2025-04-28 17:22:19,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 3.4581968784332275, cross_entropy: 3.4581968784332275 +[2025-04-28 17:22:19,825][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.190675735473633, cross_entropy: 2.190675735473633 +[2025-04-28 17:22:22,432][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.2938754558563232, cross_entropy: 3.2938754558563232 +[2025-04-28 17:22:23,153][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.952584743499756, cross_entropy: 2.952584743499756 +[2025-04-28 17:22:26,709][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.2220559120178223, cross_entropy: 2.2220559120178223 +[2025-04-28 17:22:27,393][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 1.294220209121704, cross_entropy: 1.294220209121704 +[2025-04-28 17:22:30,997][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 2.462679624557495, cross_entropy: 2.462679624557495 +[2025-04-28 17:22:31,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 1.838301658630371, cross_entropy: 1.838301658630371 +[2025-04-28 17:22:34,439][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 2.8619167804718018, cross_entropy: 2.8619167804718018 +[2025-04-28 17:22:35,161][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 3.6756632328033447, cross_entropy: 3.6756632328033447 +[2025-04-28 17:22:38,019][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 2.5190224647521973, cross_entropy: 2.5190224647521973 +[2025-04-28 17:22:38,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 3.353457450866699, cross_entropy: 3.353457450866699 +[2025-04-28 17:22:41,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 2.317227840423584, cross_entropy: 2.317227840423584 +[2025-04-28 17:22:42,070][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 1.7854211330413818, cross_entropy: 1.7854211330413818 +[2025-04-28 17:22:45,308][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 3.4733874797821045, cross_entropy: 3.4733874797821045 +[2025-04-28 17:22:46,003][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.661670684814453, cross_entropy: 3.661670684814453 +[2025-04-28 17:22:50,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.0634915828704834, cross_entropy: 2.0634915828704834 +[2025-04-28 17:22:51,194][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 2.472028970718384, cross_entropy: 2.472028970718384 +[2025-04-28 17:22:53,184][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.827111005783081, cross_entropy: 1.827111005783081 +[2025-04-28 17:22:53,917][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 3.1536359786987305, cross_entropy: 3.1536359786987305 +[2025-04-28 17:22:56,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 2.287503719329834, cross_entropy: 2.287503719329834 +[2025-04-28 17:22:57,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 3.596662998199463, cross_entropy: 3.596662998199463 +[2025-04-28 17:23:01,984][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 2.5346527099609375, cross_entropy: 2.5346527099609375 +[2025-04-28 17:23:02,674][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 3.640906572341919, cross_entropy: 3.640906572341919 +[2025-04-28 17:23:04,948][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 3.0196824073791504, cross_entropy: 3.0196824073791504 +[2025-04-28 17:23:05,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.3437535762786865, cross_entropy: 3.3437535762786865 +[2025-04-28 17:23:08,856][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 1.9991412162780762, cross_entropy: 1.9991412162780762 +[2025-04-28 17:23:09,567][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 2.6187076568603516, cross_entropy: 2.6187076568603516 +[2025-04-28 17:23:12,187][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 1.9468072652816772, cross_entropy: 1.9468072652816772 +[2025-04-28 17:23:12,904][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 1.989457607269287, cross_entropy: 1.989457607269287 +[2025-04-28 17:23:14,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 2.7240242958068848, cross_entropy: 2.7240242958068848 +[2025-04-28 17:23:15,642][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 2.449080467224121, cross_entropy: 2.449080467224121 +[2025-04-28 17:23:18,110][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 2.133472442626953, cross_entropy: 2.133472442626953 +[2025-04-28 17:23:18,794][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 2.43371844291687, cross_entropy: 2.43371844291687 +[2025-04-28 17:23:22,081][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 2.4116344451904297, cross_entropy: 2.4116344451904297 +[2025-04-28 17:23:22,773][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 1.9797887802124023, cross_entropy: 1.9797887802124023 +[2025-04-28 17:23:24,987][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.1978094577789307, cross_entropy: 2.1978094577789307 +[2025-04-28 17:23:25,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 3.218297004699707, cross_entropy: 3.218297004699707 +[2025-04-28 17:23:28,175][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 2.923508882522583, cross_entropy: 2.923508882522583 +[2025-04-28 17:23:28,892][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.74246883392334, cross_entropy: 2.74246883392334 +[2025-04-28 17:23:31,930][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 3.620756149291992, cross_entropy: 3.620756149291992 +[2025-04-28 17:23:32,647][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 2.7649736404418945, cross_entropy: 2.7649736404418945 +[2025-04-28 17:23:34,807][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 2.551971673965454, cross_entropy: 2.551971673965454 +[2025-04-28 17:23:35,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 2.3544750213623047, cross_entropy: 2.3544750213623047 +[2025-04-28 17:23:38,250][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 2.8792247772216797, cross_entropy: 2.8792247772216797 +[2025-04-28 17:23:38,934][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.13777494430542, cross_entropy: 2.13777494430542 +[2025-04-28 17:23:41,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.551839828491211, cross_entropy: 1.551839828491211 +[2025-04-28 17:23:42,087][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 3.346863269805908, cross_entropy: 3.346863269805908 +[2025-04-28 17:23:44,623][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 2.919952392578125, cross_entropy: 2.919952392578125 +[2025-04-28 17:23:45,303][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 3.3945531845092773, cross_entropy: 3.3945531845092773 +[2025-04-28 17:23:48,406][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 3.6032440662384033, cross_entropy: 3.6032440662384033 +[2025-04-28 17:23:49,124][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.573833465576172, cross_entropy: 2.573833465576172 +[2025-04-28 17:23:51,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.9392926692962646, cross_entropy: 1.9392926692962646 +[2025-04-28 17:23:52,248][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 3.3526077270507812, cross_entropy: 3.3526077270507812 +[2025-04-28 17:23:54,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.5082640647888184, cross_entropy: 2.5082640647888184 +[2025-04-28 17:23:54,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.172865867614746, cross_entropy: 3.172865867614746 +[2025-04-28 17:23:56,992][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 1.8168830871582031, cross_entropy: 1.8168830871582031 +[2025-04-28 17:23:57,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 3.3194642066955566, cross_entropy: 3.3194642066955566 +[2025-04-28 17:24:00,388][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 2.33944034576416, cross_entropy: 2.33944034576416 +[2025-04-28 17:24:01,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.7124814987182617, cross_entropy: 1.7124814987182617 +[2025-04-28 17:24:04,067][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.4931449890136719, cross_entropy: 1.4931449890136719 +[2025-04-28 17:24:04,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 1.654280662536621, cross_entropy: 1.654280662536621 +[2025-04-28 17:24:07,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.6368303298950195, cross_entropy: 2.6368303298950195 +[2025-04-28 17:24:07,926][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.792844295501709, cross_entropy: 1.792844295501709 +[2025-04-28 17:24:10,657][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 2.877072334289551, cross_entropy: 2.877072334289551 +[2025-04-28 17:24:11,368][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 2.583601951599121, cross_entropy: 2.583601951599121 +[2025-04-28 17:24:13,313][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.0878429412841797, cross_entropy: 2.0878429412841797 +[2025-04-28 17:24:14,028][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.370039939880371, cross_entropy: 2.370039939880371 +[2025-04-28 17:24:16,471][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 2.58308482170105, cross_entropy: 2.58308482170105 +[2025-04-28 17:24:17,185][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 3.4969286918640137, cross_entropy: 3.4969286918640137 +[2025-04-28 17:24:21,386][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 3.668412685394287, cross_entropy: 3.668412685394287 +[2025-04-28 17:24:22,071][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 2.2460269927978516, cross_entropy: 2.2460269927978516 +[2025-04-28 17:24:24,691][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 2.057121753692627, cross_entropy: 2.057121753692627 +[2025-04-28 17:24:25,409][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 2.478907585144043, cross_entropy: 2.478907585144043 +[2025-04-28 17:24:28,820][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 3.252993106842041, cross_entropy: 3.252993106842041 +[2025-04-28 17:24:29,544][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.5695738792419434, cross_entropy: 3.5695738792419434 +[2025-04-28 17:24:32,071][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 2.3304848670959473, cross_entropy: 2.3304848670959473 +[2025-04-28 17:24:32,790][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 3.168485164642334, cross_entropy: 3.168485164642334 +[2025-04-28 17:24:36,128][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.6014244556427, cross_entropy: 2.6014244556427 +[2025-04-28 17:24:36,807][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 2.0173757076263428, cross_entropy: 2.0173757076263428 +[2025-04-28 17:24:39,150][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 2.0274481773376465, cross_entropy: 2.0274481773376465 +[2025-04-28 17:24:39,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 1.8579444885253906, cross_entropy: 1.8579444885253906 +[2025-04-28 17:24:42,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.594705104827881, cross_entropy: 3.594705104827881 +[2025-04-28 17:24:43,086][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 3.039262294769287, cross_entropy: 3.039262294769287 +[2025-04-28 17:24:45,700][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 3.281039237976074, cross_entropy: 3.281039237976074 +[2025-04-28 17:24:46,416][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 3.230140209197998, cross_entropy: 3.230140209197998 +[2025-04-28 17:24:49,151][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 3.4319934844970703, cross_entropy: 3.4319934844970703 +[2025-04-28 17:24:49,869][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 1.9549508094787598, cross_entropy: 1.9549508094787598 +[2025-04-28 17:24:52,523][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 2.366387367248535, cross_entropy: 2.366387367248535 +[2025-04-28 17:24:53,233][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 2.8401596546173096, cross_entropy: 2.8401596546173096 +[2025-04-28 17:24:55,982][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 1.7732369899749756, cross_entropy: 1.7732369899749756 +[2025-04-28 17:24:56,662][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.3864846229553223, cross_entropy: 2.3864846229553223 +[2025-04-28 17:24:59,673][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 3.6179962158203125, cross_entropy: 3.6179962158203125 +[2025-04-28 17:25:00,354][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 2.463038444519043, cross_entropy: 2.463038444519043 +[2025-04-28 17:25:02,513][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 3.489168643951416, cross_entropy: 3.489168643951416 +[2025-04-28 17:25:03,224][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.9479713439941406, cross_entropy: 2.9479713439941406 +[2025-04-28 17:25:05,971][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 1.7182910442352295, cross_entropy: 1.7182910442352295 +[2025-04-28 17:25:06,681][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 2.7782883644104004, cross_entropy: 2.7782883644104004 +[2025-04-28 17:25:09,579][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.2785348892211914, cross_entropy: 2.2785348892211914 +[2025-04-28 17:25:10,302][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 1.8611993789672852, cross_entropy: 1.8611993789672852 +[2025-04-28 17:25:12,496][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 3.5223608016967773, cross_entropy: 3.5223608016967773 +[2025-04-28 17:25:13,216][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.888380765914917, cross_entropy: 1.888380765914917 +[2025-04-28 17:25:15,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 3.2723801136016846, cross_entropy: 3.2723801136016846 +[2025-04-28 17:25:16,182][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 1.8239156007766724, cross_entropy: 1.8239156007766724 +[2025-04-28 17:25:18,722][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 2.2202606201171875, cross_entropy: 2.2202606201171875 +[2025-04-28 17:25:19,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 1.603550910949707, cross_entropy: 1.603550910949707 +[2025-04-28 17:25:22,185][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 2.186398983001709, cross_entropy: 2.186398983001709 +[2025-04-28 17:25:22,905][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 2.1867825984954834, cross_entropy: 2.1867825984954834 +[2025-04-28 17:25:25,078][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 2.525864601135254, cross_entropy: 2.525864601135254 +[2025-04-28 17:25:25,805][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 1.8593645095825195, cross_entropy: 1.8593645095825195 +[2025-04-28 17:25:28,369][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 1.9729984998703003, cross_entropy: 1.9729984998703003 +[2025-04-28 17:25:29,086][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 1.7759947776794434, cross_entropy: 1.7759947776794434 +[2025-04-28 17:25:32,962][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.9131522178649902, cross_entropy: 1.9131522178649902 +[2025-04-28 17:25:33,675][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 2.227908134460449, cross_entropy: 2.227908134460449 +[2025-04-28 17:25:35,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.59909987449646, cross_entropy: 1.59909987449646 +[2025-04-28 17:25:36,641][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 2.1595377922058105, cross_entropy: 2.1595377922058105 +[2025-04-28 17:25:39,667][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 3.23129940032959, cross_entropy: 3.23129940032959 +[2025-04-28 17:25:40,387][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 3.1979498863220215, cross_entropy: 3.1979498863220215 +[2025-04-28 17:25:43,650][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 3.334684371948242, cross_entropy: 3.334684371948242 +[2025-04-28 17:25:44,366][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 1.8931711912155151, cross_entropy: 1.8931711912155151 +[2025-04-28 17:25:46,757][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 2.6633315086364746, cross_entropy: 2.6633315086364746 +[2025-04-28 17:25:47,468][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 3.676436424255371, cross_entropy: 3.676436424255371 +[2025-04-28 17:25:49,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.9315931797027588, cross_entropy: 1.9315931797027588 +[2025-04-28 17:25:50,184][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.9449015855789185, cross_entropy: 1.9449015855789185 +[2025-04-28 17:25:52,856][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 1.9056665897369385, cross_entropy: 1.9056665897369385 +[2025-04-28 17:25:53,571][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.12349271774292, cross_entropy: 2.12349271774292 +[2025-04-28 17:25:56,940][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 2.6684823036193848, cross_entropy: 2.6684823036193848 +[2025-04-28 17:25:57,661][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 3.1429145336151123, cross_entropy: 3.1429145336151123 +[2025-04-28 17:26:00,693][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 3.3685460090637207, cross_entropy: 3.3685460090637207 +[2025-04-28 17:26:01,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 2.0195815563201904, cross_entropy: 2.0195815563201904 +[2025-04-28 17:26:04,231][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.300940990447998, cross_entropy: 2.300940990447998 +[2025-04-28 17:26:04,912][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 2.2592906951904297, cross_entropy: 2.2592906951904297 +[2025-04-28 17:26:07,370][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.32382869720459, cross_entropy: 2.32382869720459 +[2025-04-28 17:26:08,051][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 2.0664725303649902, cross_entropy: 2.0664725303649902 +[2025-04-28 17:26:10,606][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 3.3595166206359863, cross_entropy: 3.3595166206359863 +[2025-04-28 17:26:11,318][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 2.8172407150268555, cross_entropy: 2.8172407150268555 +[2025-04-28 17:26:13,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 2.871188163757324, cross_entropy: 2.871188163757324 +[2025-04-28 17:26:14,493][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 3.3047971725463867, cross_entropy: 3.3047971725463867 +[2025-04-28 17:26:18,047][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 3.5229880809783936, cross_entropy: 3.5229880809783936 +[2025-04-28 17:26:18,766][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 2.766451358795166, cross_entropy: 2.766451358795166 +[2025-04-28 17:26:21,241][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.5498464107513428, cross_entropy: 2.5498464107513428 +[2025-04-28 17:26:21,922][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 3.6492533683776855, cross_entropy: 3.6492533683776855 +[2025-04-28 17:26:24,461][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 3.1540403366088867, cross_entropy: 3.1540403366088867 +[2025-04-28 17:26:25,172][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 2.6377429962158203, cross_entropy: 2.6377429962158203 +[2025-04-28 17:26:27,529][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 2.899106025695801, cross_entropy: 2.899106025695801 +[2025-04-28 17:26:28,210][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 1.9628612995147705, cross_entropy: 1.9628612995147705 +[2025-04-28 17:26:30,790][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 3.077026128768921, cross_entropy: 3.077026128768921 +[2025-04-28 17:26:31,470][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 2.737982988357544, cross_entropy: 2.737982988357544 +[2025-04-28 17:26:35,176][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 3.354722023010254, cross_entropy: 3.354722023010254 +[2025-04-28 17:26:35,885][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.0095174312591553, cross_entropy: 2.0095174312591553 +[2025-04-28 17:26:38,279][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.2039425373077393, cross_entropy: 2.2039425373077393 +[2025-04-28 17:26:38,959][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 3.159986734390259, cross_entropy: 3.159986734390259 +[2025-04-28 17:26:41,299][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 3.309018611907959, cross_entropy: 3.309018611907959 +[2025-04-28 17:26:41,980][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 3.082131862640381, cross_entropy: 3.082131862640381 +[2025-04-28 17:26:45,555][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 1.8718407154083252, cross_entropy: 1.8718407154083252 +[2025-04-28 17:26:46,285][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 1.8212695121765137, cross_entropy: 1.8212695121765137 +[2025-04-28 17:26:49,075][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 1.7790240049362183, cross_entropy: 1.7790240049362183 +[2025-04-28 17:26:49,781][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 2.142024040222168, cross_entropy: 2.142024040222168 +[2025-04-28 17:26:52,203][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.1823344230651855, cross_entropy: 2.1823344230651855 +[2025-04-28 17:26:52,909][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 1.9523320198059082, cross_entropy: 1.9523320198059082 +[2025-04-28 17:26:55,379][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.2954111099243164, cross_entropy: 3.2954111099243164 +[2025-04-28 17:26:56,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 1.575660228729248, cross_entropy: 1.575660228729248 +[2025-04-28 17:26:58,010][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 3.7324841022491455, cross_entropy: 3.7324841022491455 +[2025-04-28 17:26:58,731][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.615170478820801, cross_entropy: 3.615170478820801 +[2025-04-28 17:27:00,632][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.79443359375, cross_entropy: 1.79443359375 +[2025-04-28 17:27:01,343][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 1.799027681350708, cross_entropy: 1.799027681350708 +[2025-04-28 17:27:03,788][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.2975046634674072, cross_entropy: 2.2975046634674072 +[2025-04-28 17:27:04,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.29923415184021, cross_entropy: 2.29923415184021 +[2025-04-28 17:27:07,108][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 2.176912307739258, cross_entropy: 2.176912307739258 +[2025-04-28 17:27:07,813][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 3.577632427215576, cross_entropy: 3.577632427215576 +[2025-04-28 17:27:10,378][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 1.6733343601226807, cross_entropy: 1.6733343601226807 +[2025-04-28 17:27:11,104][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 2.513798236846924, cross_entropy: 2.513798236846924 +[2025-04-28 17:27:13,157][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.45639705657959, cross_entropy: 2.45639705657959 +[2025-04-28 17:27:13,867][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 2.8041903972625732, cross_entropy: 2.8041903972625732 +[2025-04-28 17:27:17,504][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.7066231966018677, cross_entropy: 1.7066231966018677 +[2025-04-28 17:27:18,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 3.1527886390686035, cross_entropy: 3.1527886390686035 +[2025-04-28 17:27:20,099][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.1844515800476074, cross_entropy: 2.1844515800476074 +[2025-04-28 17:27:20,809][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.3903112411499023, cross_entropy: 2.3903112411499023 +[2025-04-28 17:27:23,244][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 3.1687450408935547, cross_entropy: 3.1687450408935547 +[2025-04-28 17:27:23,954][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 1.6324410438537598, cross_entropy: 1.6324410438537598 +[2025-04-28 17:27:26,516][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 3.933962821960449, cross_entropy: 3.933962821960449 +[2025-04-28 17:27:27,195][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.60831880569458, cross_entropy: 2.60831880569458 +[2025-04-28 17:27:30,623][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.1857337951660156, cross_entropy: 2.1857337951660156 +[2025-04-28 17:27:31,336][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 2.940063953399658, cross_entropy: 2.940063953399658 +[2025-04-28 17:27:34,204][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.7381292581558228, cross_entropy: 1.7381292581558228 +[2025-04-28 17:27:34,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.494223117828369, cross_entropy: 2.494223117828369 +[2025-04-28 17:27:37,021][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 3.268002986907959, cross_entropy: 3.268002986907959 +[2025-04-28 17:27:37,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 2.9928579330444336, cross_entropy: 2.9928579330444336 +[2025-04-28 17:27:40,127][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 1.677282452583313, cross_entropy: 1.677282452583313 +[2025-04-28 17:27:40,810][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 1.5212459564208984, cross_entropy: 1.5212459564208984 +[2025-04-28 17:27:43,062][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 2.5625503063201904, cross_entropy: 2.5625503063201904 +[2025-04-28 17:27:43,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 2.1721832752227783, cross_entropy: 2.1721832752227783 +[2025-04-28 17:27:45,763][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 1.9145785570144653, cross_entropy: 1.9145785570144653 +[2025-04-28 17:27:46,478][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.6107370853424072, cross_entropy: 1.6107370853424072 +[2025-04-28 17:27:49,247][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 2.1050896644592285, cross_entropy: 2.1050896644592285 +[2025-04-28 17:27:49,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 3.636810302734375, cross_entropy: 3.636810302734375 +[2025-04-28 17:27:52,482][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 2.962519407272339, cross_entropy: 2.962519407272339 +[2025-04-28 17:27:53,166][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 3.262463092803955, cross_entropy: 3.262463092803955 +[2025-04-28 17:27:55,687][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 3.3182613849639893, cross_entropy: 3.3182613849639893 +[2025-04-28 17:27:56,399][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 3.189833641052246, cross_entropy: 3.189833641052246 +[2025-04-28 17:27:59,056][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 1.798904299736023, cross_entropy: 1.798904299736023 +[2025-04-28 17:27:59,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 2.8866376876831055, cross_entropy: 2.8866376876831055 +[2025-04-28 17:28:02,493][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 1.9006669521331787, cross_entropy: 1.9006669521331787 +[2025-04-28 17:28:03,174][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 1.7862069606781006, cross_entropy: 1.7862069606781006 +[2025-04-28 17:28:05,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.7934105396270752, cross_entropy: 1.7934105396270752 +[2025-04-28 17:28:06,332][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 1.7455788850784302, cross_entropy: 1.7455788850784302 +[2025-04-28 17:28:09,419][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.4704513549804688, cross_entropy: 1.4704513549804688 +[2025-04-28 17:28:10,134][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 2.8948750495910645, cross_entropy: 2.8948750495910645 +[2025-04-28 17:28:12,795][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.236006259918213, cross_entropy: 2.236006259918213 +[2025-04-28 17:28:13,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 1.9315580129623413, cross_entropy: 1.9315580129623413 +[2025-04-28 17:28:15,682][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 1.9803121089935303, cross_entropy: 1.9803121089935303 +[2025-04-28 17:28:16,363][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 2.6932272911071777, cross_entropy: 2.6932272911071777 +[2025-04-28 17:28:18,717][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 1.730840802192688, cross_entropy: 1.730840802192688 +[2025-04-28 17:28:19,437][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 3.255777359008789, cross_entropy: 3.255777359008789 +[2025-04-28 17:28:22,053][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 3.3102757930755615, cross_entropy: 3.3102757930755615 +[2025-04-28 17:28:22,734][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 3.415520429611206, cross_entropy: 3.415520429611206 +[2025-04-28 17:28:25,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 1.5836520195007324, cross_entropy: 1.5836520195007324 +[2025-04-28 17:28:26,377][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 3.3500752449035645, cross_entropy: 3.3500752449035645 +[2025-04-28 17:28:29,301][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.2488367557525635, cross_entropy: 2.2488367557525635 +[2025-04-28 17:28:29,987][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 3.0310468673706055, cross_entropy: 3.0310468673706055 +[2025-04-28 17:28:32,519][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.0917325019836426, cross_entropy: 2.0917325019836426 +[2025-04-28 17:28:33,201][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.1317901611328125, cross_entropy: 3.1317901611328125 +[2025-04-28 17:28:36,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 3.1846208572387695, cross_entropy: 3.1846208572387695 +[2025-04-28 17:28:36,930][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 3.35360050201416, cross_entropy: 3.35360050201416 +[2025-04-28 17:28:39,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 2.2372941970825195, cross_entropy: 2.2372941970825195 +[2025-04-28 17:28:39,702][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 3.0191822052001953, cross_entropy: 3.0191822052001953 +[2025-04-28 17:28:42,595][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 3.0571961402893066, cross_entropy: 3.0571961402893066 +[2025-04-28 17:28:43,302][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.8879001140594482, cross_entropy: 1.8879001140594482 +[2025-04-28 17:28:47,178][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 2.9983184337615967, cross_entropy: 2.9983184337615967 +[2025-04-28 17:28:47,859][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 2.2886440753936768, cross_entropy: 2.2886440753936768 +[2025-04-28 17:28:50,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 3.7078535556793213, cross_entropy: 3.7078535556793213 +[2025-04-28 17:28:51,303][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.030191421508789, cross_entropy: 2.030191421508789 +[2025-04-28 17:28:53,786][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 1.9993374347686768, cross_entropy: 1.9993374347686768 +[2025-04-28 17:28:54,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.6623778343200684, cross_entropy: 2.6623778343200684 +[2025-04-28 17:28:57,988][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 2.1392440795898438, cross_entropy: 2.1392440795898438 +[2025-04-28 17:28:58,695][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.6220860481262207, cross_entropy: 1.6220860481262207 +[2025-04-28 17:29:01,353][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.1680750846862793, cross_entropy: 2.1680750846862793 +[2025-04-28 17:29:02,072][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.741990327835083, cross_entropy: 1.741990327835083 +[2025-04-28 17:29:05,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.7122994661331177, cross_entropy: 1.7122994661331177 +[2025-04-28 17:29:05,758][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 1.9009708166122437, cross_entropy: 1.9009708166122437 +[2025-04-28 17:29:08,721][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.1699938774108887, cross_entropy: 2.1699938774108887 +[2025-04-28 17:29:09,432][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.8374427556991577, cross_entropy: 1.8374427556991577 +[2025-04-28 17:29:11,918][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 3.565364122390747, cross_entropy: 3.565364122390747 +[2025-04-28 17:29:12,633][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 3.0027761459350586, cross_entropy: 3.0027761459350586 +[2025-04-28 17:29:15,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.463144540786743, cross_entropy: 2.463144540786743 +[2025-04-28 17:29:16,462][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 3.716423749923706, cross_entropy: 3.716423749923706 +[2025-04-28 17:29:18,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 3.296539068222046, cross_entropy: 3.296539068222046 +[2025-04-28 17:29:19,635][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 2.3731014728546143, cross_entropy: 2.3731014728546143 +[2025-04-28 17:29:22,562][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.6177287101745605, cross_entropy: 2.6177287101745605 +[2025-04-28 17:29:23,284][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 2.185051441192627, cross_entropy: 2.185051441192627 +[2025-04-28 17:29:25,685][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 2.094696044921875, cross_entropy: 2.094696044921875 +[2025-04-28 17:29:26,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 2.12467098236084, cross_entropy: 2.12467098236084 +[2025-04-28 17:29:28,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.8976764678955078, cross_entropy: 1.8976764678955078 +[2025-04-28 17:29:29,593][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.57083797454834, cross_entropy: 2.57083797454834 +[2025-04-28 17:29:31,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 2.0774800777435303, cross_entropy: 2.0774800777435303 +[2025-04-28 17:29:32,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.8991641998291016, cross_entropy: 1.8991641998291016 +[2025-04-28 17:29:34,235][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.9293861389160156, cross_entropy: 1.9293861389160156 +[2025-04-28 17:29:34,957][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 1.710614562034607, cross_entropy: 1.710614562034607 +[2025-04-28 17:29:37,496][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 3.3355188369750977, cross_entropy: 3.3355188369750977 +[2025-04-28 17:29:38,259][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 1.8549892902374268, cross_entropy: 1.8549892902374268 +[2025-04-28 17:29:40,774][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 3.061812400817871, cross_entropy: 3.061812400817871 +[2025-04-28 17:29:41,482][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 3.3421974182128906, cross_entropy: 3.3421974182128906 +[2025-04-28 17:29:43,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 3.181654214859009, cross_entropy: 3.181654214859009 +[2025-04-28 17:29:44,334][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 1.7347424030303955, cross_entropy: 1.7347424030303955 +[2025-04-28 17:29:46,528][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.3453774452209473, cross_entropy: 1.3453774452209473 +[2025-04-28 17:29:47,207][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.490082025527954, cross_entropy: 1.490082025527954 +[2025-04-28 17:29:50,224][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.5897510051727295, cross_entropy: 1.5897510051727295 +[2025-04-28 17:29:50,942][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 3.622527599334717, cross_entropy: 3.622527599334717 +[2025-04-28 17:29:53,919][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 1.6159789562225342, cross_entropy: 1.6159789562225342 +[2025-04-28 17:29:54,630][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 2.0867528915405273, cross_entropy: 2.0867528915405273 +[2025-04-28 17:29:57,031][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 1.630908489227295, cross_entropy: 1.630908489227295 +[2025-04-28 17:29:57,753][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.6630511283874512, cross_entropy: 1.6630511283874512 +[2025-04-28 17:30:00,006][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 1.9344977140426636, cross_entropy: 1.9344977140426636 +[2025-04-28 17:30:00,753][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 1.9703624248504639, cross_entropy: 1.9703624248504639 +[2025-04-28 17:30:02,882][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.6443076133728027, cross_entropy: 1.6443076133728027 +[2025-04-28 17:30:03,625][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.947420358657837, cross_entropy: 2.947420358657837 +[2025-04-28 17:30:05,900][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 2.8380813598632812, cross_entropy: 2.8380813598632812 +[2025-04-28 17:30:06,633][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 3.066561698913574, cross_entropy: 3.066561698913574 +[2025-04-28 17:30:09,191][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.7191407680511475, cross_entropy: 1.7191407680511475 +[2025-04-28 17:30:09,951][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 1.5509653091430664, cross_entropy: 1.5509653091430664 +[2025-04-28 17:30:12,497][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 3.500243902206421, cross_entropy: 3.500243902206421 +[2025-04-28 17:30:13,249][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 2.391110897064209, cross_entropy: 2.391110897064209 +[2025-04-28 17:30:15,552][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.6740975379943848, cross_entropy: 2.6740975379943848 +[2025-04-28 17:30:16,373][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 2.754305362701416, cross_entropy: 2.754305362701416 +[2025-04-28 17:30:19,082][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.5506430864334106, cross_entropy: 1.5506430864334106 +[2025-04-28 17:30:19,793][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 2.6122984886169434, cross_entropy: 2.6122984886169434 +[2025-04-28 17:30:22,154][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 2.093757152557373, cross_entropy: 2.093757152557373 +[2025-04-28 17:30:22,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 2.97213077545166, cross_entropy: 2.97213077545166 +[2025-04-28 17:30:25,636][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 1.8503652811050415, cross_entropy: 1.8503652811050415 +[2025-04-28 17:30:26,324][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 3.53056001663208, cross_entropy: 3.53056001663208 +[2025-04-28 17:30:27,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.237700939178467, cross_entropy: 3.237700939178467 +[2025-04-28 17:32:57,280][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.53371000289917, cross_entropy: 2.53371000289917 +[2025-04-28 17:32:57,281][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.557096004486084, cross_entropy: 1.557096004486084 +[2025-04-28 17:32:58,178][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 17:32:58,685][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch4.pth. +[2025-04-28 17:32:59,520][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 17:33:04,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.501828670501709, cross_entropy: 2.501828670501709 +[2025-04-28 17:33:04,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 3.0068931579589844, cross_entropy: 3.0068931579589844 +[2025-04-28 17:33:07,533][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.4831438064575195, cross_entropy: 1.4831438064575195 +[2025-04-28 17:33:08,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 2.3025870323181152, cross_entropy: 2.3025870323181152 +[2025-04-28 17:33:12,215][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.6451616287231445, cross_entropy: 1.6451616287231445 +[2025-04-28 17:33:12,927][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 3.1029815673828125, cross_entropy: 3.1029815673828125 +[2025-04-28 17:33:15,549][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.225757598876953, cross_entropy: 2.225757598876953 +[2025-04-28 17:33:16,266][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 1.8886133432388306, cross_entropy: 1.8886133432388306 +[2025-04-28 17:33:18,434][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 1.5826458930969238, cross_entropy: 1.5826458930969238 +[2025-04-28 17:33:19,159][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.822105050086975, cross_entropy: 1.822105050086975 +[2025-04-28 17:33:21,852][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.499483108520508, cross_entropy: 3.499483108520508 +[2025-04-28 17:33:22,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.7598421573638916, cross_entropy: 1.7598421573638916 +[2025-04-28 17:33:24,469][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 1.3355313539505005, cross_entropy: 1.3355313539505005 +[2025-04-28 17:33:25,163][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.238656997680664, cross_entropy: 2.238656997680664 +[2025-04-28 17:33:28,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 2.99711275100708, cross_entropy: 2.99711275100708 +[2025-04-28 17:33:29,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.800065517425537, cross_entropy: 2.800065517425537 +[2025-04-28 17:33:32,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 3.0417866706848145, cross_entropy: 3.0417866706848145 +[2025-04-28 17:33:32,992][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 1.7033483982086182, cross_entropy: 1.7033483982086182 +[2025-04-28 17:33:36,106][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.758561611175537, cross_entropy: 2.758561611175537 +[2025-04-28 17:33:36,831][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 2.7054193019866943, cross_entropy: 2.7054193019866943 +[2025-04-28 17:33:39,067][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 3.2399086952209473, cross_entropy: 3.2399086952209473 +[2025-04-28 17:33:39,775][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 2.9135818481445312, cross_entropy: 2.9135818481445312 +[2025-04-28 17:33:42,904][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.6008310317993164, cross_entropy: 1.6008310317993164 +[2025-04-28 17:33:43,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.7265708446502686, cross_entropy: 1.7265708446502686 +[2025-04-28 17:33:45,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 2.332101583480835, cross_entropy: 2.332101583480835 +[2025-04-28 17:33:46,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 1.740403175354004, cross_entropy: 1.740403175354004 +[2025-04-28 17:33:50,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 2.5887112617492676, cross_entropy: 2.5887112617492676 +[2025-04-28 17:33:51,399][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.7423861026763916, cross_entropy: 1.7423861026763916 +[2025-04-28 17:33:53,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.348284959793091, cross_entropy: 2.348284959793091 +[2025-04-28 17:33:54,301][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 1.7050151824951172, cross_entropy: 1.7050151824951172 +[2025-04-28 17:33:56,544][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 2.4232864379882812, cross_entropy: 2.4232864379882812 +[2025-04-28 17:33:57,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 2.2600784301757812, cross_entropy: 2.2600784301757812 +[2025-04-28 17:33:59,884][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 2.3811185359954834, cross_entropy: 2.3811185359954834 +[2025-04-28 17:34:00,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 3.590754508972168, cross_entropy: 3.590754508972168 +[2025-04-28 17:34:03,894][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 3.3727188110351562, cross_entropy: 3.3727188110351562 +[2025-04-28 17:34:04,601][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 3.20265531539917, cross_entropy: 3.20265531539917 +[2025-04-28 17:34:06,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 2.588383197784424, cross_entropy: 2.588383197784424 +[2025-04-28 17:34:07,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 2.5418481826782227, cross_entropy: 2.5418481826782227 +[2025-04-28 17:34:09,586][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 1.7597004175186157, cross_entropy: 1.7597004175186157 +[2025-04-28 17:34:10,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.8872981071472168, cross_entropy: 1.8872981071472168 +[2025-04-28 17:34:12,975][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 3.7140748500823975, cross_entropy: 3.7140748500823975 +[2025-04-28 17:34:13,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 2.2847840785980225, cross_entropy: 2.2847840785980225 +[2025-04-28 17:34:16,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 2.0417745113372803, cross_entropy: 2.0417745113372803 +[2025-04-28 17:34:17,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 2.9966390132904053, cross_entropy: 2.9966390132904053 +[2025-04-28 17:34:19,999][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 3.5360374450683594, cross_entropy: 3.5360374450683594 +[2025-04-28 17:34:20,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.6510919332504272, cross_entropy: 1.6510919332504272 +[2025-04-28 17:34:23,497][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 3.6098735332489014, cross_entropy: 3.6098735332489014 +[2025-04-28 17:34:24,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 2.8531129360198975, cross_entropy: 2.8531129360198975 +[2025-04-28 17:34:26,328][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.4229719638824463, cross_entropy: 2.4229719638824463 +[2025-04-28 17:34:27,032][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 2.6686835289001465, cross_entropy: 2.6686835289001465 +[2025-04-28 17:34:29,492][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.145923614501953, cross_entropy: 2.145923614501953 +[2025-04-28 17:34:30,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.5073552131652832, cross_entropy: 1.5073552131652832 +[2025-04-28 17:34:32,573][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.5577565431594849, cross_entropy: 1.5577565431594849 +[2025-04-28 17:34:33,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 1.9641989469528198, cross_entropy: 1.9641989469528198 +[2025-04-28 17:34:36,027][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.0851786136627197, cross_entropy: 2.0851786136627197 +[2025-04-28 17:34:36,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 1.3585295677185059, cross_entropy: 1.3585295677185059 +[2025-04-28 17:34:39,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 2.4875402450561523, cross_entropy: 2.4875402450561523 +[2025-04-28 17:34:40,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 3.0520734786987305, cross_entropy: 3.0520734786987305 +[2025-04-28 17:34:42,650][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 2.143555164337158, cross_entropy: 2.143555164337158 +[2025-04-28 17:34:43,362][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 2.01375150680542, cross_entropy: 2.01375150680542 +[2025-04-28 17:34:45,457][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 3.135270833969116, cross_entropy: 3.135270833969116 +[2025-04-28 17:34:46,202][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.07493257522583, cross_entropy: 2.07493257522583 +[2025-04-28 17:34:48,177][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 3.4980297088623047, cross_entropy: 3.4980297088623047 +[2025-04-28 17:34:48,859][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.7276285886764526, cross_entropy: 1.7276285886764526 +[2025-04-28 17:34:51,842][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.360952615737915, cross_entropy: 2.360952615737915 +[2025-04-28 17:34:52,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 3.299767017364502, cross_entropy: 3.299767017364502 +[2025-04-28 17:34:56,636][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 1.8259965181350708, cross_entropy: 1.8259965181350708 +[2025-04-28 17:34:57,342][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 1.9210704565048218, cross_entropy: 1.9210704565048218 +[2025-04-28 17:34:59,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 2.696113109588623, cross_entropy: 2.696113109588623 +[2025-04-28 17:35:00,665][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 2.754631996154785, cross_entropy: 2.754631996154785 +[2025-04-28 17:35:02,916][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.3852105140686035, cross_entropy: 3.3852105140686035 +[2025-04-28 17:35:03,630][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 1.3521332740783691, cross_entropy: 1.3521332740783691 +[2025-04-28 17:35:05,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 3.1792447566986084, cross_entropy: 3.1792447566986084 +[2025-04-28 17:35:06,365][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 2.059217691421509, cross_entropy: 2.059217691421509 +[2025-04-28 17:35:08,584][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 3.1239590644836426, cross_entropy: 3.1239590644836426 +[2025-04-28 17:35:09,294][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 1.408370852470398, cross_entropy: 1.408370852470398 +[2025-04-28 17:35:11,156][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.5129172801971436, cross_entropy: 1.5129172801971436 +[2025-04-28 17:35:12,053][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.2624454498291016, cross_entropy: 1.2624454498291016 +[2025-04-28 17:35:14,175][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 2.3746185302734375, cross_entropy: 2.3746185302734375 +[2025-04-28 17:35:14,863][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.7187583446502686, cross_entropy: 1.7187583446502686 +[2025-04-28 17:35:17,891][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 2.5230817794799805, cross_entropy: 2.5230817794799805 +[2025-04-28 17:35:18,824][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.041001081466675, cross_entropy: 2.041001081466675 +[2025-04-28 17:35:21,396][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 1.3681963682174683, cross_entropy: 1.3681963682174683 +[2025-04-28 17:35:22,164][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 1.972058653831482, cross_entropy: 1.972058653831482 +[2025-04-28 17:35:24,881][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 3.672880172729492, cross_entropy: 3.672880172729492 +[2025-04-28 17:35:25,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 1.941072702407837, cross_entropy: 1.941072702407837 +[2025-04-28 17:35:28,063][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 3.5963616371154785, cross_entropy: 3.5963616371154785 +[2025-04-28 17:35:28,744][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 3.345656394958496, cross_entropy: 3.345656394958496 +[2025-04-28 17:35:31,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 3.509347677230835, cross_entropy: 3.509347677230835 +[2025-04-28 17:35:32,381][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 2.0713226795196533, cross_entropy: 2.0713226795196533 +[2025-04-28 17:35:35,023][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.829338550567627, cross_entropy: 2.829338550567627 +[2025-04-28 17:35:35,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 2.4925973415374756, cross_entropy: 2.4925973415374756 +[2025-04-28 17:35:38,058][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.0906472206115723, cross_entropy: 2.0906472206115723 +[2025-04-28 17:35:38,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 3.28902530670166, cross_entropy: 3.28902530670166 +[2025-04-28 17:35:41,260][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 1.9715824127197266, cross_entropy: 1.9715824127197266 +[2025-04-28 17:35:41,941][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 2.8269705772399902, cross_entropy: 2.8269705772399902 +[2025-04-28 17:35:44,313][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.2175912857055664, cross_entropy: 2.2175912857055664 +[2025-04-28 17:35:44,993][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 2.765693187713623, cross_entropy: 2.765693187713623 +[2025-04-28 17:35:47,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 2.8349976539611816, cross_entropy: 2.8349976539611816 +[2025-04-28 17:35:47,896][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.3979456424713135, cross_entropy: 1.3979456424713135 +[2025-04-28 17:35:50,484][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.2638752460479736, cross_entropy: 2.2638752460479736 +[2025-04-28 17:35:51,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.99591064453125, cross_entropy: 2.99591064453125 +[2025-04-28 17:35:54,038][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 3.333204746246338, cross_entropy: 3.333204746246338 +[2025-04-28 17:35:54,717][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 1.6421477794647217, cross_entropy: 1.6421477794647217 +[2025-04-28 17:35:56,950][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 1.5505722761154175, cross_entropy: 1.5505722761154175 +[2025-04-28 17:35:57,712][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.8406312465667725, cross_entropy: 1.8406312465667725 +[2025-04-28 17:36:00,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 1.8714613914489746, cross_entropy: 1.8714613914489746 +[2025-04-28 17:36:01,127][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.6315956115722656, cross_entropy: 1.6315956115722656 +[2025-04-28 17:36:03,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 3.168241024017334, cross_entropy: 3.168241024017334 +[2025-04-28 17:36:04,394][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 2.6696457862854004, cross_entropy: 2.6696457862854004 +[2025-04-28 17:36:06,757][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 2.002124786376953, cross_entropy: 2.002124786376953 +[2025-04-28 17:36:07,470][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 2.222137451171875, cross_entropy: 2.222137451171875 +[2025-04-28 17:36:09,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 2.601017951965332, cross_entropy: 2.601017951965332 +[2025-04-28 17:36:10,352][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 3.36171293258667, cross_entropy: 3.36171293258667 +[2025-04-28 17:36:12,402][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 2.5836970806121826, cross_entropy: 2.5836970806121826 +[2025-04-28 17:36:13,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 3.0518345832824707, cross_entropy: 3.0518345832824707 +[2025-04-28 17:36:15,472][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 3.3087244033813477, cross_entropy: 3.3087244033813477 +[2025-04-28 17:36:17,054][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.1814645528793335, cross_entropy: 1.1814645528793335 +[2025-04-28 17:36:19,356][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 3.396979331970215, cross_entropy: 3.396979331970215 +[2025-04-28 17:36:20,531][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.002715587615967, cross_entropy: 2.002715587615967 +[2025-04-28 17:36:22,166][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 3.4512500762939453, cross_entropy: 3.4512500762939453 +[2025-04-28 17:36:24,062][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 3.187587261199951, cross_entropy: 3.187587261199951 +[2025-04-28 17:36:26,178][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.2909436225891113, cross_entropy: 3.2909436225891113 +[2025-04-28 17:36:27,106][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 3.3466155529022217, cross_entropy: 3.3466155529022217 +[2025-04-28 17:36:28,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.5502119064331055, cross_entropy: 2.5502119064331055 +[2025-04-28 17:36:30,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 3.2935945987701416, cross_entropy: 3.2935945987701416 +[2025-04-28 17:36:31,858][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.712475061416626, cross_entropy: 1.712475061416626 +[2025-04-28 17:36:33,013][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 3.206251621246338, cross_entropy: 3.206251621246338 +[2025-04-28 17:36:34,933][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 2.4253664016723633, cross_entropy: 2.4253664016723633 +[2025-04-28 17:36:36,179][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.867231607437134, cross_entropy: 2.867231607437134 +[2025-04-28 17:36:38,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.4748189449310303, cross_entropy: 1.4748189449310303 +[2025-04-28 17:36:39,288][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.297720193862915, cross_entropy: 1.297720193862915 +[2025-04-28 17:36:41,024][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 3.1297733783721924, cross_entropy: 3.1297733783721924 +[2025-04-28 17:36:41,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 3.6435890197753906, cross_entropy: 3.6435890197753906 +[2025-04-28 17:36:44,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.3919131755828857, cross_entropy: 1.3919131755828857 +[2025-04-28 17:36:45,321][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 1.0989444255828857, cross_entropy: 1.0989444255828857 +[2025-04-28 17:36:47,342][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 1.3909196853637695, cross_entropy: 1.3909196853637695 +[2025-04-28 17:36:48,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 2.0965099334716797, cross_entropy: 2.0965099334716797 +[2025-04-28 17:36:50,382][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 3.2249326705932617, cross_entropy: 3.2249326705932617 +[2025-04-28 17:36:51,099][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 3.2286903858184814, cross_entropy: 3.2286903858184814 +[2025-04-28 17:36:53,302][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 2.9734086990356445, cross_entropy: 2.9734086990356445 +[2025-04-28 17:36:54,646][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 3.0546724796295166, cross_entropy: 3.0546724796295166 +[2025-04-28 17:36:56,944][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 2.3773856163024902, cross_entropy: 2.3773856163024902 +[2025-04-28 17:36:57,832][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.815954327583313, cross_entropy: 1.815954327583313 +[2025-04-28 17:37:00,481][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.753051519393921, cross_entropy: 1.753051519393921 +[2025-04-28 17:37:01,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 3.064166784286499, cross_entropy: 3.064166784286499 +[2025-04-28 17:37:03,865][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 1.9914895296096802, cross_entropy: 1.9914895296096802 +[2025-04-28 17:37:04,619][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 1.3792202472686768, cross_entropy: 1.3792202472686768 +[2025-04-28 17:37:07,311][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.1940045356750488, cross_entropy: 1.1940045356750488 +[2025-04-28 17:37:08,026][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 3.1019859313964844, cross_entropy: 3.1019859313964844 +[2025-04-28 17:37:10,785][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.247138738632202, cross_entropy: 3.247138738632202 +[2025-04-28 17:37:11,466][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 3.121370553970337, cross_entropy: 3.121370553970337 +[2025-04-28 17:37:14,100][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 2.8561415672302246, cross_entropy: 2.8561415672302246 +[2025-04-28 17:37:14,785][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 1.9650295972824097, cross_entropy: 1.9650295972824097 +[2025-04-28 17:37:17,438][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 2.8573145866394043, cross_entropy: 2.8573145866394043 +[2025-04-28 17:37:18,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 2.7328126430511475, cross_entropy: 2.7328126430511475 +[2025-04-28 17:37:21,885][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 3.4950685501098633, cross_entropy: 3.4950685501098633 +[2025-04-28 17:37:22,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.8309597969055176, cross_entropy: 1.8309597969055176 +[2025-04-28 17:37:25,076][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.4590954780578613, cross_entropy: 1.4590954780578613 +[2025-04-28 17:37:25,797][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 2.668368339538574, cross_entropy: 2.668368339538574 +[2025-04-28 17:37:28,607][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 3.0259032249450684, cross_entropy: 3.0259032249450684 +[2025-04-28 17:37:29,312][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.854222297668457, cross_entropy: 1.854222297668457 +[2025-04-28 17:37:32,014][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 3.4300928115844727, cross_entropy: 3.4300928115844727 +[2025-04-28 17:37:32,692][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 3.072535991668701, cross_entropy: 3.072535991668701 +[2025-04-28 17:37:35,471][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 1.7635968923568726, cross_entropy: 1.7635968923568726 +[2025-04-28 17:37:36,180][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 2.213214874267578, cross_entropy: 2.213214874267578 +[2025-04-28 17:37:39,071][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 1.823951244354248, cross_entropy: 1.823951244354248 +[2025-04-28 17:37:39,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 2.1887497901916504, cross_entropy: 2.1887497901916504 +[2025-04-28 17:37:42,189][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 3.2431650161743164, cross_entropy: 3.2431650161743164 +[2025-04-28 17:37:42,900][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 2.1597824096679688, cross_entropy: 2.1597824096679688 +[2025-04-28 17:37:45,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 2.0882599353790283, cross_entropy: 2.0882599353790283 +[2025-04-28 17:37:46,289][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 2.641531229019165, cross_entropy: 2.641531229019165 +[2025-04-28 17:37:48,699][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 3.493436813354492, cross_entropy: 3.493436813354492 +[2025-04-28 17:37:49,413][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 2.8057098388671875, cross_entropy: 2.8057098388671875 +[2025-04-28 17:37:51,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 3.2155773639678955, cross_entropy: 3.2155773639678955 +[2025-04-28 17:37:52,194][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.6802215576171875, cross_entropy: 1.6802215576171875 +[2025-04-28 17:37:55,104][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 1.456228494644165, cross_entropy: 1.456228494644165 +[2025-04-28 17:37:55,813][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 3.774223804473877, cross_entropy: 3.774223804473877 +[2025-04-28 17:37:58,040][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.1731888055801392, cross_entropy: 1.1731888055801392 +[2025-04-28 17:37:58,752][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 2.869166135787964, cross_entropy: 2.869166135787964 +[2025-04-28 17:38:01,326][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 1.760292649269104, cross_entropy: 1.760292649269104 +[2025-04-28 17:38:02,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 1.6105587482452393, cross_entropy: 1.6105587482452393 +[2025-04-28 17:38:04,791][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 3.3253443241119385, cross_entropy: 3.3253443241119385 +[2025-04-28 17:38:05,577][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.6076793670654297, cross_entropy: 2.6076793670654297 +[2025-04-28 17:38:08,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 3.5293664932250977, cross_entropy: 3.5293664932250977 +[2025-04-28 17:38:09,255][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 3.2342257499694824, cross_entropy: 3.2342257499694824 +[2025-04-28 17:38:11,204][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.655831813812256, cross_entropy: 2.655831813812256 +[2025-04-28 17:38:11,911][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.0969130992889404, cross_entropy: 2.0969130992889404 +[2025-04-28 17:38:14,888][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 1.894039511680603, cross_entropy: 1.894039511680603 +[2025-04-28 17:38:15,598][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.5550355911254883, cross_entropy: 2.5550355911254883 +[2025-04-28 17:38:18,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 1.9457556009292603, cross_entropy: 1.9457556009292603 +[2025-04-28 17:38:19,400][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 2.7464051246643066, cross_entropy: 2.7464051246643066 +[2025-04-28 17:38:22,906][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 3.008524179458618, cross_entropy: 3.008524179458618 +[2025-04-28 17:38:23,631][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.7212295532226562, cross_entropy: 2.7212295532226562 +[2025-04-28 17:38:26,302][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 3.7512478828430176, cross_entropy: 3.7512478828430176 +[2025-04-28 17:38:27,012][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 1.998692274093628, cross_entropy: 1.998692274093628 +[2025-04-28 17:38:29,205][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.6506295204162598, cross_entropy: 1.6506295204162598 +[2025-04-28 17:38:29,919][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.52390456199646, cross_entropy: 1.52390456199646 +[2025-04-28 17:38:33,127][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 2.510812759399414, cross_entropy: 2.510812759399414 +[2025-04-28 17:38:33,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.2237815856933594, cross_entropy: 2.2237815856933594 +[2025-04-28 17:38:35,624][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.4565058946609497, cross_entropy: 1.4565058946609497 +[2025-04-28 17:38:36,336][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 1.8919236660003662, cross_entropy: 1.8919236660003662 +[2025-04-28 17:38:39,124][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.103173017501831, cross_entropy: 2.103173017501831 +[2025-04-28 17:38:39,809][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 1.8968381881713867, cross_entropy: 1.8968381881713867 +[2025-04-28 17:38:42,250][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.5512423515319824, cross_entropy: 2.5512423515319824 +[2025-04-28 17:38:42,933][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 3.0912139415740967, cross_entropy: 3.0912139415740967 +[2025-04-28 17:38:45,697][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 2.1475324630737305, cross_entropy: 2.1475324630737305 +[2025-04-28 17:38:46,378][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 3.0768046379089355, cross_entropy: 3.0768046379089355 +[2025-04-28 17:38:49,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 2.8180932998657227, cross_entropy: 2.8180932998657227 +[2025-04-28 17:38:50,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 3.0190114974975586, cross_entropy: 3.0190114974975586 +[2025-04-28 17:38:52,818][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.9053928852081299, cross_entropy: 1.9053928852081299 +[2025-04-28 17:38:53,497][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 3.5329136848449707, cross_entropy: 3.5329136848449707 +[2025-04-28 17:38:55,803][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 2.580902338027954, cross_entropy: 2.580902338027954 +[2025-04-28 17:38:56,503][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.6128160953521729, cross_entropy: 1.6128160953521729 +[2025-04-28 17:38:59,472][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 2.6586923599243164, cross_entropy: 2.6586923599243164 +[2025-04-28 17:39:00,149][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 2.23344349861145, cross_entropy: 2.23344349861145 +[2025-04-28 17:39:04,217][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 1.8817201852798462, cross_entropy: 1.8817201852798462 +[2025-04-28 17:39:04,929][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 3.232184410095215, cross_entropy: 3.232184410095215 +[2025-04-28 17:39:07,704][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.2831692695617676, cross_entropy: 2.2831692695617676 +[2025-04-28 17:39:08,390][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 1.501229166984558, cross_entropy: 1.501229166984558 +[2025-04-28 17:39:09,984][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 2.002620220184326, cross_entropy: 2.002620220184326 +[2025-04-28 17:39:10,698][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.4205167293548584, cross_entropy: 3.4205167293548584 +[2025-04-28 17:39:13,802][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 1.9242398738861084, cross_entropy: 1.9242398738861084 +[2025-04-28 17:39:14,483][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 2.504277229309082, cross_entropy: 2.504277229309082 +[2025-04-28 17:39:16,819][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 3.0566306114196777, cross_entropy: 3.0566306114196777 +[2025-04-28 17:39:17,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 2.720407485961914, cross_entropy: 2.720407485961914 +[2025-04-28 17:39:21,126][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 2.56070876121521, cross_entropy: 2.56070876121521 +[2025-04-28 17:39:21,837][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 2.0971198081970215, cross_entropy: 2.0971198081970215 +[2025-04-28 17:39:23,912][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 3.087653875350952, cross_entropy: 3.087653875350952 +[2025-04-28 17:39:24,624][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 1.7384231090545654, cross_entropy: 1.7384231090545654 +[2025-04-28 17:39:26,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.5828611850738525, cross_entropy: 1.5828611850738525 +[2025-04-28 17:39:27,597][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 2.1418495178222656, cross_entropy: 2.1418495178222656 +[2025-04-28 17:39:30,027][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 1.4717607498168945, cross_entropy: 1.4717607498168945 +[2025-04-28 17:39:30,740][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.5270955562591553, cross_entropy: 2.5270955562591553 +[2025-04-28 17:39:33,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.0418968200683594, cross_entropy: 2.0418968200683594 +[2025-04-28 17:39:34,079][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 1.519647479057312, cross_entropy: 1.519647479057312 +[2025-04-28 17:39:36,635][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 1.807567834854126, cross_entropy: 1.807567834854126 +[2025-04-28 17:39:37,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 2.8763556480407715, cross_entropy: 2.8763556480407715 +[2025-04-28 17:39:40,257][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.3182382583618164, cross_entropy: 1.3182382583618164 +[2025-04-28 17:39:40,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 2.9702062606811523, cross_entropy: 2.9702062606811523 +[2025-04-28 17:39:43,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 3.6988513469696045, cross_entropy: 3.6988513469696045 +[2025-04-28 17:39:44,243][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 2.933077335357666, cross_entropy: 2.933077335357666 +[2025-04-28 17:39:46,715][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 3.3238534927368164, cross_entropy: 3.3238534927368164 +[2025-04-28 17:39:47,399][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 1.466291069984436, cross_entropy: 1.466291069984436 +[2025-04-28 17:39:49,882][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 2.8882288932800293, cross_entropy: 2.8882288932800293 +[2025-04-28 17:39:50,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 3.347731113433838, cross_entropy: 3.347731113433838 +[2025-04-28 17:39:53,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 2.0816595554351807, cross_entropy: 2.0816595554351807 +[2025-04-28 17:39:53,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.4218599796295166, cross_entropy: 1.4218599796295166 +[2025-04-28 17:39:56,180][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 2.1461215019226074, cross_entropy: 2.1461215019226074 +[2025-04-28 17:39:56,891][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 3.165438652038574, cross_entropy: 3.165438652038574 +[2025-04-28 17:39:58,885][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.5381035804748535, cross_entropy: 2.5381035804748535 +[2025-04-28 17:39:59,566][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.428898811340332, cross_entropy: 3.428898811340332 +[2025-04-28 17:40:01,968][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.2383615970611572, cross_entropy: 1.2383615970611572 +[2025-04-28 17:40:02,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.067272186279297, cross_entropy: 2.067272186279297 +[2025-04-28 17:40:04,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 1.7084016799926758, cross_entropy: 1.7084016799926758 +[2025-04-28 17:40:04,908][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 2.746288299560547, cross_entropy: 2.746288299560547 +[2025-04-28 17:40:07,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 3.245706796646118, cross_entropy: 3.245706796646118 +[2025-04-28 17:40:08,180][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 2.101179599761963, cross_entropy: 2.101179599761963 +[2025-04-28 17:40:11,017][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 2.6073784828186035, cross_entropy: 2.6073784828186035 +[2025-04-28 17:40:11,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 2.7621140480041504, cross_entropy: 2.7621140480041504 +[2025-04-28 17:40:15,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.599224328994751, cross_entropy: 1.599224328994751 +[2025-04-28 17:40:15,876][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.8593004941940308, cross_entropy: 1.8593004941940308 +[2025-04-28 17:40:18,768][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 2.301128625869751, cross_entropy: 2.301128625869751 +[2025-04-28 17:40:19,444][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 2.74008846282959, cross_entropy: 2.74008846282959 +[2025-04-28 17:40:21,135][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.047609329223633, cross_entropy: 3.047609329223633 +[2025-04-28 17:40:21,848][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 1.6484256982803345, cross_entropy: 1.6484256982803345 +[2025-04-28 17:40:24,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 3.0615220069885254, cross_entropy: 3.0615220069885254 +[2025-04-28 17:40:25,286][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.2817983627319336, cross_entropy: 3.2817983627319336 +[2025-04-28 17:40:27,514][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 3.31268048286438, cross_entropy: 3.31268048286438 +[2025-04-28 17:40:28,222][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.5309323072433472, cross_entropy: 1.5309323072433472 +[2025-04-28 17:40:31,082][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 1.9925830364227295, cross_entropy: 1.9925830364227295 +[2025-04-28 17:40:31,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 3.0364866256713867, cross_entropy: 3.0364866256713867 +[2025-04-28 17:40:33,886][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 2.907538890838623, cross_entropy: 2.907538890838623 +[2025-04-28 17:40:34,596][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 1.9890482425689697, cross_entropy: 1.9890482425689697 +[2025-04-28 17:40:37,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 1.7791017293930054, cross_entropy: 1.7791017293930054 +[2025-04-28 17:40:37,826][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.7221038341522217, cross_entropy: 1.7221038341522217 +[2025-04-28 17:40:40,405][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 3.2303237915039062, cross_entropy: 3.2303237915039062 +[2025-04-28 17:40:41,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.479961395263672, cross_entropy: 2.479961395263672 +[2025-04-28 17:40:43,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 2.6869168281555176, cross_entropy: 2.6869168281555176 +[2025-04-28 17:40:44,369][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 2.167640447616577, cross_entropy: 2.167640447616577 +[2025-04-28 17:40:47,109][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 3.687124013900757, cross_entropy: 3.687124013900757 +[2025-04-28 17:40:47,819][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 1.6324599981307983, cross_entropy: 1.6324599981307983 +[2025-04-28 17:40:50,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 3.263103485107422, cross_entropy: 3.263103485107422 +[2025-04-28 17:40:51,421][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 1.7699322700500488, cross_entropy: 1.7699322700500488 +[2025-04-28 17:40:54,757][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 3.091738224029541, cross_entropy: 3.091738224029541 +[2025-04-28 17:40:55,466][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 2.0492632389068604, cross_entropy: 2.0492632389068604 +[2025-04-28 17:40:57,840][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 1.7406740188598633, cross_entropy: 1.7406740188598633 +[2025-04-28 17:40:58,550][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 2.68870210647583, cross_entropy: 2.68870210647583 +[2025-04-28 17:41:00,531][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 3.3425097465515137, cross_entropy: 3.3425097465515137 +[2025-04-28 17:41:01,241][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 1.8125585317611694, cross_entropy: 1.8125585317611694 +[2025-04-28 17:41:03,591][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 3.312495231628418, cross_entropy: 3.312495231628418 +[2025-04-28 17:41:04,299][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 3.311793088912964, cross_entropy: 3.311793088912964 +[2025-04-28 17:41:06,020][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 2.447726011276245, cross_entropy: 2.447726011276245 +[2025-04-28 17:41:06,736][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 2.867417335510254, cross_entropy: 2.867417335510254 +[2025-04-28 17:41:09,002][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 1.5990402698516846, cross_entropy: 1.5990402698516846 +[2025-04-28 17:41:09,714][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.5032987594604492, cross_entropy: 1.5032987594604492 +[2025-04-28 17:41:12,286][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.8069647550582886, cross_entropy: 1.8069647550582886 +[2025-04-28 17:41:13,004][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.7843356132507324, cross_entropy: 1.7843356132507324 +[2025-04-28 17:41:15,870][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 1.6374359130859375, cross_entropy: 1.6374359130859375 +[2025-04-28 17:41:16,581][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.2643990516662598, cross_entropy: 2.2643990516662598 +[2025-04-28 17:41:19,037][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 1.6222292184829712, cross_entropy: 1.6222292184829712 +[2025-04-28 17:41:19,717][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.087116241455078, cross_entropy: 3.087116241455078 +[2025-04-28 17:41:22,433][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 2.4846200942993164, cross_entropy: 2.4846200942993164 +[2025-04-28 17:41:23,113][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 2.016392946243286, cross_entropy: 2.016392946243286 +[2025-04-28 17:41:25,344][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.6856906414031982, cross_entropy: 2.6856906414031982 +[2025-04-28 17:41:26,061][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 1.867781162261963, cross_entropy: 1.867781162261963 +[2025-04-28 17:41:28,304][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.5596015453338623, cross_entropy: 1.5596015453338623 +[2025-04-28 17:41:29,020][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 1.72943115234375, cross_entropy: 1.72943115234375 +[2025-04-28 17:41:31,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 2.1219642162323, cross_entropy: 2.1219642162323 +[2025-04-28 17:41:32,192][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 2.0080533027648926, cross_entropy: 2.0080533027648926 +[2025-04-28 17:41:34,250][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.6348881721496582, cross_entropy: 1.6348881721496582 +[2025-04-28 17:41:34,931][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 3.4083495140075684, cross_entropy: 3.4083495140075684 +[2025-04-28 17:41:37,089][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 1.8902418613433838, cross_entropy: 1.8902418613433838 +[2025-04-28 17:41:37,913][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 2.722036838531494, cross_entropy: 2.722036838531494 +[2025-04-28 17:41:40,244][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.7371559143066406, cross_entropy: 1.7371559143066406 +[2025-04-28 17:41:41,009][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.3625686168670654, cross_entropy: 2.3625686168670654 +[2025-04-28 17:41:43,339][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 2.6921098232269287, cross_entropy: 2.6921098232269287 +[2025-04-28 17:41:44,127][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 2.0237231254577637, cross_entropy: 2.0237231254577637 +[2025-04-28 17:41:46,512][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 3.481748580932617, cross_entropy: 3.481748580932617 +[2025-04-28 17:41:47,272][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 3.707897424697876, cross_entropy: 3.707897424697876 +[2025-04-28 17:41:49,681][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.463667631149292, cross_entropy: 1.463667631149292 +[2025-04-28 17:41:50,443][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 2.2322778701782227, cross_entropy: 2.2322778701782227 +[2025-04-28 17:41:52,841][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.5909199714660645, cross_entropy: 1.5909199714660645 +[2025-04-28 17:41:53,602][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 2.1619186401367188, cross_entropy: 2.1619186401367188 +[2025-04-28 17:41:55,567][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 3.15242862701416, cross_entropy: 3.15242862701416 +[2025-04-28 17:41:57,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.6956048011779785, cross_entropy: 2.6956048011779785 +[2025-04-28 17:41:58,375][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 1.8603956699371338, cross_entropy: 1.8603956699371338 +[2025-04-28 17:42:00,349][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 1.8241171836853027, cross_entropy: 1.8241171836853027 +[2025-04-28 17:42:01,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.2876505851745605, cross_entropy: 3.2876505851745605 +[2025-04-28 17:42:03,710][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 2.3878135681152344, cross_entropy: 2.3878135681152344 +[2025-04-28 17:42:04,424][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 2.8902087211608887, cross_entropy: 2.8902087211608887 +[2025-04-28 17:42:06,200][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.85547137260437, cross_entropy: 2.85547137260437 +[2025-04-28 17:42:07,039][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.7864727973937988, cross_entropy: 1.7864727973937988 +[2025-04-28 17:42:08,974][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 3.23046875, cross_entropy: 3.23046875 +[2025-04-28 17:42:09,694][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.8269453048706055, cross_entropy: 1.8269453048706055 +[2025-04-28 17:42:11,660][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 1.7020174264907837, cross_entropy: 1.7020174264907837 +[2025-04-28 17:42:13,141][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 1.8008713722229004, cross_entropy: 1.8008713722229004 +[2025-04-28 17:42:14,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 2.9982049465179443, cross_entropy: 2.9982049465179443 +[2025-04-28 17:42:16,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 1.735724925994873, cross_entropy: 1.735724925994873 +[2025-04-28 17:42:18,121][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.327629804611206, cross_entropy: 3.327629804611206 +[2025-04-28 17:42:19,788][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 2.9436635971069336, cross_entropy: 2.9436635971069336 +[2025-04-28 17:42:21,252][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 2.339028835296631, cross_entropy: 2.339028835296631 +[2025-04-28 17:42:23,420][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 2.1432690620422363, cross_entropy: 2.1432690620422363 +[2025-04-28 17:42:24,592][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 3.6415700912475586, cross_entropy: 3.6415700912475586 +[2025-04-28 17:42:26,638][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 1.9030539989471436, cross_entropy: 1.9030539989471436 +[2025-04-28 17:42:27,336][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.2347309589385986, cross_entropy: 1.2347309589385986 +[2025-04-28 17:42:29,707][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 3.260141372680664, cross_entropy: 3.260141372680664 +[2025-04-28 17:42:31,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 3.2020444869995117, cross_entropy: 3.2020444869995117 +[2025-04-28 17:42:34,171][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.5885438919067383, cross_entropy: 1.5885438919067383 +[2025-04-28 17:42:34,878][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 2.2891600131988525, cross_entropy: 2.2891600131988525 +[2025-04-28 17:42:37,044][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 3.4325928688049316, cross_entropy: 3.4325928688049316 +[2025-04-28 17:42:37,808][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 2.9863250255584717, cross_entropy: 2.9863250255584717 +[2025-04-28 17:42:40,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.4532852172851562, cross_entropy: 1.4532852172851562 +[2025-04-28 17:42:40,984][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 2.208030939102173, cross_entropy: 2.208030939102173 +[2025-04-28 17:42:42,557][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 3.0291647911071777, cross_entropy: 3.0291647911071777 +[2025-04-28 17:42:43,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.8240628242492676, cross_entropy: 1.8240628242492676 +[2025-04-28 17:45:07,964][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.4185492992401123, cross_entropy: 2.4185492992401123 +[2025-04-28 17:45:07,964][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.4098501205444336, cross_entropy: 1.4098501205444336 +[2025-04-28 17:45:08,860][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 17:45:09,376][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch5.pth. +[2025-04-28 17:45:10,191][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 17:45:14,159][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 3.0301055908203125, cross_entropy: 3.0301055908203125 +[2025-04-28 17:45:14,946][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.0334827899932861, cross_entropy: 1.0334827899932861 +[2025-04-28 17:45:17,894][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 1.6848549842834473, cross_entropy: 1.6848549842834473 +[2025-04-28 17:45:18,676][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 1.6636821031570435, cross_entropy: 1.6636821031570435 +[2025-04-28 17:45:20,836][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 3.0888707637786865, cross_entropy: 3.0888707637786865 +[2025-04-28 17:45:22,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 1.987410545349121, cross_entropy: 1.987410545349121 +[2025-04-28 17:45:23,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 3.686300277709961, cross_entropy: 3.686300277709961 +[2025-04-28 17:45:26,123][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 2.810053825378418, cross_entropy: 2.810053825378418 +[2025-04-28 17:45:26,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.4334743022918701, cross_entropy: 1.4334743022918701 +[2025-04-28 17:45:29,255][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 1.4009158611297607, cross_entropy: 1.4009158611297607 +[2025-04-28 17:45:30,277][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.074596881866455, cross_entropy: 2.074596881866455 +[2025-04-28 17:45:32,708][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 3.0363097190856934, cross_entropy: 3.0363097190856934 +[2025-04-28 17:45:33,450][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 1.5926017761230469, cross_entropy: 1.5926017761230469 +[2025-04-28 17:45:35,338][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 2.8560190200805664, cross_entropy: 2.8560190200805664 +[2025-04-28 17:45:36,090][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 2.271942138671875, cross_entropy: 2.271942138671875 +[2025-04-28 17:45:38,492][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 1.2536495923995972, cross_entropy: 1.2536495923995972 +[2025-04-28 17:45:39,538][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 2.5465874671936035, cross_entropy: 2.5465874671936035 +[2025-04-28 17:45:41,204][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 1.3933672904968262, cross_entropy: 1.3933672904968262 +[2025-04-28 17:45:42,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.5772137641906738, cross_entropy: 1.5772137641906738 +[2025-04-28 17:45:44,956][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 2.0314512252807617, cross_entropy: 2.0314512252807617 +[2025-04-28 17:45:45,753][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 1.7732629776000977, cross_entropy: 1.7732629776000977 +[2025-04-28 17:45:48,375][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.8564400672912598, cross_entropy: 1.8564400672912598 +[2025-04-28 17:45:49,140][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 3.0883398056030273, cross_entropy: 3.0883398056030273 +[2025-04-28 17:45:51,891][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.54004168510437, cross_entropy: 2.54004168510437 +[2025-04-28 17:45:52,599][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 2.57878041267395, cross_entropy: 2.57878041267395 +[2025-04-28 17:45:54,527][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 1.8188726902008057, cross_entropy: 1.8188726902008057 +[2025-04-28 17:45:55,234][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 3.2173333168029785, cross_entropy: 3.2173333168029785 +[2025-04-28 17:45:57,589][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.966362476348877, cross_entropy: 2.966362476348877 +[2025-04-28 17:45:58,377][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 2.315739154815674, cross_entropy: 2.315739154815674 +[2025-04-28 17:46:01,765][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 2.3393073081970215, cross_entropy: 2.3393073081970215 +[2025-04-28 17:46:02,482][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.6918443441390991, cross_entropy: 1.6918443441390991 +[2025-04-28 17:46:05,319][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.0515899658203125, cross_entropy: 2.0515899658203125 +[2025-04-28 17:46:06,034][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 1.9396965503692627, cross_entropy: 1.9396965503692627 +[2025-04-28 17:46:08,643][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 1.8294427394866943, cross_entropy: 1.8294427394866943 +[2025-04-28 17:46:09,350][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 3.2924883365631104, cross_entropy: 3.2924883365631104 +[2025-04-28 17:46:11,850][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 3.236360549926758, cross_entropy: 3.236360549926758 +[2025-04-28 17:46:12,529][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.5213422775268555, cross_entropy: 1.5213422775268555 +[2025-04-28 17:46:15,075][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 3.1961514949798584, cross_entropy: 3.1961514949798584 +[2025-04-28 17:46:15,783][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 1.8572148084640503, cross_entropy: 1.8572148084640503 +[2025-04-28 17:46:18,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.3658391237258911, cross_entropy: 1.3658391237258911 +[2025-04-28 17:46:19,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 1.6222177743911743, cross_entropy: 1.6222177743911743 +[2025-04-28 17:46:21,612][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.5080628395080566, cross_entropy: 2.5080628395080566 +[2025-04-28 17:46:22,307][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.3502395153045654, cross_entropy: 1.3502395153045654 +[2025-04-28 17:46:24,239][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 1.654871940612793, cross_entropy: 1.654871940612793 +[2025-04-28 17:46:24,950][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 3.334280014038086, cross_entropy: 3.334280014038086 +[2025-04-28 17:46:26,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.493072509765625, cross_entropy: 2.493072509765625 +[2025-04-28 17:46:27,465][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.2193448543548584, cross_entropy: 2.2193448543548584 +[2025-04-28 17:46:29,839][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 1.3475728034973145, cross_entropy: 1.3475728034973145 +[2025-04-28 17:46:30,541][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 3.0690793991088867, cross_entropy: 3.0690793991088867 +[2025-04-28 17:46:32,674][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 2.951913833618164, cross_entropy: 2.951913833618164 +[2025-04-28 17:46:33,377][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 2.393598794937134, cross_entropy: 2.393598794937134 +[2025-04-28 17:46:36,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 1.4397180080413818, cross_entropy: 1.4397180080413818 +[2025-04-28 17:46:37,211][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 3.277141571044922, cross_entropy: 3.277141571044922 +[2025-04-28 17:46:39,771][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.316150188446045, cross_entropy: 1.316150188446045 +[2025-04-28 17:46:40,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.6521353721618652, cross_entropy: 1.6521353721618652 +[2025-04-28 17:46:42,750][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 3.4075188636779785, cross_entropy: 3.4075188636779785 +[2025-04-28 17:46:43,471][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 3.2333574295043945, cross_entropy: 3.2333574295043945 +[2025-04-28 17:46:46,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.054617166519165, cross_entropy: 1.054617166519165 +[2025-04-28 17:46:46,857][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 3.4040744304656982, cross_entropy: 3.4040744304656982 +[2025-04-28 17:46:49,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.3642020225524902, cross_entropy: 2.3642020225524902 +[2025-04-28 17:46:49,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 1.9430232048034668, cross_entropy: 1.9430232048034668 +[2025-04-28 17:46:52,086][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 1.7846953868865967, cross_entropy: 1.7846953868865967 +[2025-04-28 17:46:52,792][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 3.4250917434692383, cross_entropy: 3.4250917434692383 +[2025-04-28 17:46:55,042][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 2.8245325088500977, cross_entropy: 2.8245325088500977 +[2025-04-28 17:46:55,754][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.8254897594451904, cross_entropy: 2.8254897594451904 +[2025-04-28 17:46:57,678][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.562723159790039, cross_entropy: 2.562723159790039 +[2025-04-28 17:46:58,391][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 1.0899726152420044, cross_entropy: 1.0899726152420044 +[2025-04-28 17:47:00,808][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.6882810592651367, cross_entropy: 1.6882810592651367 +[2025-04-28 17:47:01,519][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 2.3193359375, cross_entropy: 2.3193359375 +[2025-04-28 17:47:03,602][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.281336784362793, cross_entropy: 1.281336784362793 +[2025-04-28 17:47:04,321][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 2.9695322513580322, cross_entropy: 2.9695322513580322 +[2025-04-28 17:47:06,385][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.7085907459259033, cross_entropy: 1.7085907459259033 +[2025-04-28 17:47:07,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 1.8551270961761475, cross_entropy: 1.8551270961761475 +[2025-04-28 17:47:09,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.2620511054992676, cross_entropy: 1.2620511054992676 +[2025-04-28 17:47:10,271][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 3.1236085891723633, cross_entropy: 3.1236085891723633 +[2025-04-28 17:47:12,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 1.8442423343658447, cross_entropy: 1.8442423343658447 +[2025-04-28 17:47:13,463][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.844464063644409, cross_entropy: 2.844464063644409 +[2025-04-28 17:47:15,995][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 3.5067942142486572, cross_entropy: 3.5067942142486572 +[2025-04-28 17:47:16,753][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 1.5121684074401855, cross_entropy: 1.5121684074401855 +[2025-04-28 17:47:19,252][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 2.5900511741638184, cross_entropy: 2.5900511741638184 +[2025-04-28 17:47:20,025][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.8108172416687012, cross_entropy: 1.8108172416687012 +[2025-04-28 17:47:21,710][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 1.395192265510559, cross_entropy: 1.395192265510559 +[2025-04-28 17:47:22,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.2784600257873535, cross_entropy: 2.2784600257873535 +[2025-04-28 17:47:24,756][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.8303134441375732, cross_entropy: 1.8303134441375732 +[2025-04-28 17:47:25,468][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 2.881387233734131, cross_entropy: 2.881387233734131 +[2025-04-28 17:47:28,273][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 1.846511960029602, cross_entropy: 1.846511960029602 +[2025-04-28 17:47:28,985][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 3.626826763153076, cross_entropy: 3.626826763153076 +[2025-04-28 17:47:31,213][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.4295597076416016, cross_entropy: 1.4295597076416016 +[2025-04-28 17:47:31,894][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.6004739999771118, cross_entropy: 1.6004739999771118 +[2025-04-28 17:47:34,179][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.2121630907058716, cross_entropy: 1.2121630907058716 +[2025-04-28 17:47:34,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 1.3088066577911377, cross_entropy: 1.3088066577911377 +[2025-04-28 17:47:36,927][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.167729377746582, cross_entropy: 1.167729377746582 +[2025-04-28 17:47:37,656][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.83563232421875, cross_entropy: 1.83563232421875 +[2025-04-28 17:47:40,358][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.54581618309021, cross_entropy: 2.54581618309021 +[2025-04-28 17:47:41,133][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 2.613083839416504, cross_entropy: 2.613083839416504 +[2025-04-28 17:47:43,404][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 3.18790864944458, cross_entropy: 3.18790864944458 +[2025-04-28 17:47:44,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 1.1652053594589233, cross_entropy: 1.1652053594589233 +[2025-04-28 17:47:46,423][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 2.140918731689453, cross_entropy: 2.140918731689453 +[2025-04-28 17:47:47,116][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.4737263917922974, cross_entropy: 1.4737263917922974 +[2025-04-28 17:47:49,331][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.4780808687210083, cross_entropy: 1.4780808687210083 +[2025-04-28 17:47:51,652][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.7480401992797852, cross_entropy: 1.7480401992797852 +[2025-04-28 17:47:52,667][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 3.355576515197754, cross_entropy: 3.355576515197754 +[2025-04-28 17:47:55,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 1.3660626411437988, cross_entropy: 1.3660626411437988 +[2025-04-28 17:47:55,935][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 2.0836057662963867, cross_entropy: 2.0836057662963867 +[2025-04-28 17:47:57,943][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.2185474634170532, cross_entropy: 1.2185474634170532 +[2025-04-28 17:47:59,318][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 1.1087985038757324, cross_entropy: 1.1087985038757324 +[2025-04-28 17:48:00,879][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 2.9230151176452637, cross_entropy: 2.9230151176452637 +[2025-04-28 17:48:01,822][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.5978394746780396, cross_entropy: 1.5978394746780396 +[2025-04-28 17:48:03,916][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.1007537841796875, cross_entropy: 1.1007537841796875 +[2025-04-28 17:48:04,720][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.4214714765548706, cross_entropy: 1.4214714765548706 +[2025-04-28 17:48:08,880][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.3261072635650635, cross_entropy: 1.3261072635650635 +[2025-04-28 17:48:09,592][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.4016691446304321, cross_entropy: 1.4016691446304321 +[2025-04-28 17:48:12,135][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.382017135620117, cross_entropy: 2.382017135620117 +[2025-04-28 17:48:12,846][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 3.090641498565674, cross_entropy: 3.090641498565674 +[2025-04-28 17:48:14,965][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.350144863128662, cross_entropy: 2.350144863128662 +[2025-04-28 17:48:15,676][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 3.4902544021606445, cross_entropy: 3.4902544021606445 +[2025-04-28 17:48:17,791][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.8136284351348877, cross_entropy: 1.8136284351348877 +[2025-04-28 17:48:18,545][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 3.4053263664245605, cross_entropy: 3.4053263664245605 +[2025-04-28 17:48:21,390][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 1.8095483779907227, cross_entropy: 1.8095483779907227 +[2025-04-28 17:48:22,094][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 1.7556748390197754, cross_entropy: 1.7556748390197754 +[2025-04-28 17:48:24,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 1.3981740474700928, cross_entropy: 1.3981740474700928 +[2025-04-28 17:48:25,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.632379412651062, cross_entropy: 1.632379412651062 +[2025-04-28 17:48:28,266][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 1.9114729166030884, cross_entropy: 1.9114729166030884 +[2025-04-28 17:48:28,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 3.240628719329834, cross_entropy: 3.240628719329834 +[2025-04-28 17:48:31,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.546389102935791, cross_entropy: 1.546389102935791 +[2025-04-28 17:48:32,289][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 1.521974802017212, cross_entropy: 1.521974802017212 +[2025-04-28 17:48:34,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 3.510343551635742, cross_entropy: 3.510343551635742 +[2025-04-28 17:48:35,517][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 3.0941216945648193, cross_entropy: 3.0941216945648193 +[2025-04-28 17:48:38,251][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 3.0245025157928467, cross_entropy: 3.0245025157928467 +[2025-04-28 17:48:38,964][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 3.456475257873535, cross_entropy: 3.456475257873535 +[2025-04-28 17:48:41,461][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.3357057571411133, cross_entropy: 2.3357057571411133 +[2025-04-28 17:48:42,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.6255967617034912, cross_entropy: 1.6255967617034912 +[2025-04-28 17:48:45,482][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 1.645781397819519, cross_entropy: 1.645781397819519 +[2025-04-28 17:48:46,203][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.4108028411865234, cross_entropy: 3.4108028411865234 +[2025-04-28 17:48:49,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 1.2972170114517212, cross_entropy: 1.2972170114517212 +[2025-04-28 17:48:49,831][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 2.2512741088867188, cross_entropy: 2.2512741088867188 +[2025-04-28 17:48:52,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 3.0372185707092285, cross_entropy: 3.0372185707092285 +[2025-04-28 17:48:52,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.397106647491455, cross_entropy: 1.397106647491455 +[2025-04-28 17:48:54,706][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 3.3508548736572266, cross_entropy: 3.3508548736572266 +[2025-04-28 17:48:55,386][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 3.1935062408447266, cross_entropy: 3.1935062408447266 +[2025-04-28 17:48:58,412][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 2.058793067932129, cross_entropy: 2.058793067932129 +[2025-04-28 17:48:59,125][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 2.6851296424865723, cross_entropy: 2.6851296424865723 +[2025-04-28 17:49:02,125][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 2.9087181091308594, cross_entropy: 2.9087181091308594 +[2025-04-28 17:49:02,829][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 1.3886282444000244, cross_entropy: 1.3886282444000244 +[2025-04-28 17:49:05,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.0533045530319214, cross_entropy: 1.0533045530319214 +[2025-04-28 17:49:06,092][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.666893482208252, cross_entropy: 1.666893482208252 +[2025-04-28 17:49:07,746][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 2.8052682876586914, cross_entropy: 2.8052682876586914 +[2025-04-28 17:49:08,426][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 3.016350746154785, cross_entropy: 3.016350746154785 +[2025-04-28 17:49:11,158][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 2.3224282264709473, cross_entropy: 2.3224282264709473 +[2025-04-28 17:49:11,860][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 3.245358467102051, cross_entropy: 3.245358467102051 +[2025-04-28 17:49:13,991][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.6819205284118652, cross_entropy: 2.6819205284118652 +[2025-04-28 17:49:14,701][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.0074405670166016, cross_entropy: 2.0074405670166016 +[2025-04-28 17:49:17,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 1.6706231832504272, cross_entropy: 1.6706231832504272 +[2025-04-28 17:49:18,235][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 1.9270707368850708, cross_entropy: 1.9270707368850708 +[2025-04-28 17:49:20,428][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.744796633720398, cross_entropy: 1.744796633720398 +[2025-04-28 17:49:21,141][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.575778603553772, cross_entropy: 1.575778603553772 +[2025-04-28 17:49:24,922][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 3.392772674560547, cross_entropy: 3.392772674560547 +[2025-04-28 17:49:25,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 2.9078850746154785, cross_entropy: 2.9078850746154785 +[2025-04-28 17:49:27,780][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.1674761772155762, cross_entropy: 1.1674761772155762 +[2025-04-28 17:49:28,494][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.8593320846557617, cross_entropy: 1.8593320846557617 +[2025-04-28 17:49:31,639][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 3.1018152236938477, cross_entropy: 3.1018152236938477 +[2025-04-28 17:49:32,341][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 2.855912685394287, cross_entropy: 2.855912685394287 +[2025-04-28 17:49:34,972][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 3.1903276443481445, cross_entropy: 3.1903276443481445 +[2025-04-28 17:49:35,648][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 2.348330020904541, cross_entropy: 2.348330020904541 +[2025-04-28 17:49:38,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 3.160581350326538, cross_entropy: 3.160581350326538 +[2025-04-28 17:49:38,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.616316795349121, cross_entropy: 2.616316795349121 +[2025-04-28 17:49:41,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 3.1785056591033936, cross_entropy: 3.1785056591033936 +[2025-04-28 17:49:42,410][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 1.9118096828460693, cross_entropy: 1.9118096828460693 +[2025-04-28 17:49:45,551][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 3.156224250793457, cross_entropy: 3.156224250793457 +[2025-04-28 17:49:46,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 1.816184163093567, cross_entropy: 1.816184163093567 +[2025-04-28 17:49:49,444][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 3.2874510288238525, cross_entropy: 3.2874510288238525 +[2025-04-28 17:49:50,124][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.6600608825683594, cross_entropy: 1.6600608825683594 +[2025-04-28 17:49:52,131][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 2.2949531078338623, cross_entropy: 2.2949531078338623 +[2025-04-28 17:49:52,840][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 1.8505054712295532, cross_entropy: 1.8505054712295532 +[2025-04-28 17:49:55,471][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 3.1859467029571533, cross_entropy: 3.1859467029571533 +[2025-04-28 17:49:56,150][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 2.2011890411376953, cross_entropy: 2.2011890411376953 +[2025-04-28 17:49:59,349][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 0.9985634684562683, cross_entropy: 0.9985634684562683 +[2025-04-28 17:50:00,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 2.397106647491455, cross_entropy: 2.397106647491455 +[2025-04-28 17:50:02,551][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 1.5259039402008057, cross_entropy: 1.5259039402008057 +[2025-04-28 17:50:03,259][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 2.212113618850708, cross_entropy: 2.212113618850708 +[2025-04-28 17:50:06,049][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 1.7823057174682617, cross_entropy: 1.7823057174682617 +[2025-04-28 17:50:06,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 1.972601294517517, cross_entropy: 1.972601294517517 +[2025-04-28 17:50:09,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.584539771080017, cross_entropy: 1.584539771080017 +[2025-04-28 17:50:09,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 1.2541215419769287, cross_entropy: 1.2541215419769287 +[2025-04-28 17:50:12,664][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.500115156173706, cross_entropy: 1.500115156173706 +[2025-04-28 17:50:13,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.3816460371017456, cross_entropy: 1.3816460371017456 +[2025-04-28 17:50:15,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.7929959297180176, cross_entropy: 2.7929959297180176 +[2025-04-28 17:50:16,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 3.0971834659576416, cross_entropy: 3.0971834659576416 +[2025-04-28 17:50:18,716][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.469290018081665, cross_entropy: 1.469290018081665 +[2025-04-28 17:50:19,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 3.260728597640991, cross_entropy: 3.260728597640991 +[2025-04-28 17:50:22,394][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 1.2512028217315674, cross_entropy: 1.2512028217315674 +[2025-04-28 17:50:23,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.885512351989746, cross_entropy: 2.885512351989746 +[2025-04-28 17:50:25,653][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 1.6805733442306519, cross_entropy: 1.6805733442306519 +[2025-04-28 17:50:26,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 1.7159314155578613, cross_entropy: 1.7159314155578613 +[2025-04-28 17:50:29,206][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.6643370389938354, cross_entropy: 1.6643370389938354 +[2025-04-28 17:50:29,923][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 2.9455409049987793, cross_entropy: 2.9455409049987793 +[2025-04-28 17:50:32,232][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 1.4889990091323853, cross_entropy: 1.4889990091323853 +[2025-04-28 17:50:32,911][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 1.821392297744751, cross_entropy: 1.821392297744751 +[2025-04-28 17:50:35,050][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 3.3962185382843018, cross_entropy: 3.3962185382843018 +[2025-04-28 17:50:35,760][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 3.30855393409729, cross_entropy: 3.30855393409729 +[2025-04-28 17:50:38,106][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.177624225616455, cross_entropy: 2.177624225616455 +[2025-04-28 17:50:38,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 1.428422451019287, cross_entropy: 1.428422451019287 +[2025-04-28 17:50:41,292][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 1.6073027849197388, cross_entropy: 1.6073027849197388 +[2025-04-28 17:50:41,975][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 2.9648804664611816, cross_entropy: 2.9648804664611816 +[2025-04-28 17:50:44,247][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 1.4275094270706177, cross_entropy: 1.4275094270706177 +[2025-04-28 17:50:44,962][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 3.3130133152008057, cross_entropy: 3.3130133152008057 +[2025-04-28 17:50:46,891][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 2.47877836227417, cross_entropy: 2.47877836227417 +[2025-04-28 17:50:47,774][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 1.3085911273956299, cross_entropy: 1.3085911273956299 +[2025-04-28 17:50:50,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 2.3171186447143555, cross_entropy: 2.3171186447143555 +[2025-04-28 17:50:51,320][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.6428303718566895, cross_entropy: 1.6428303718566895 +[2025-04-28 17:50:54,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 3.381674289703369, cross_entropy: 3.381674289703369 +[2025-04-28 17:50:55,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 3.26853609085083, cross_entropy: 3.26853609085083 +[2025-04-28 17:50:57,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 2.752201557159424, cross_entropy: 2.752201557159424 +[2025-04-28 17:50:58,100][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.3952805995941162, cross_entropy: 1.3952805995941162 +[2025-04-28 17:51:00,570][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.31599497795105, cross_entropy: 2.31599497795105 +[2025-04-28 17:51:01,328][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 1.8345788717269897, cross_entropy: 1.8345788717269897 +[2025-04-28 17:51:03,607][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 1.0597797632217407, cross_entropy: 1.0597797632217407 +[2025-04-28 17:51:04,367][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 2.0285110473632812, cross_entropy: 2.0285110473632812 +[2025-04-28 17:51:07,959][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.545919895172119, cross_entropy: 2.545919895172119 +[2025-04-28 17:51:08,667][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 3.0378897190093994, cross_entropy: 3.0378897190093994 +[2025-04-28 17:51:09,501][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/iteration2000.pth. +[2025-04-28 17:51:11,185][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.6510578393936157, cross_entropy: 1.6510578393936157 +[2025-04-28 17:51:11,899][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.7073984146118164, cross_entropy: 2.7073984146118164 +[2025-04-28 17:51:14,578][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 1.0433669090270996, cross_entropy: 1.0433669090270996 +[2025-04-28 17:51:15,257][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 1.7511284351348877, cross_entropy: 1.7511284351348877 +[2025-04-28 17:51:18,466][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 3.200071096420288, cross_entropy: 3.200071096420288 +[2025-04-28 17:51:19,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.383841037750244, cross_entropy: 2.383841037750244 +[2025-04-28 17:51:21,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 1.5739017724990845, cross_entropy: 1.5739017724990845 +[2025-04-28 17:51:22,628][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.867936849594116, cross_entropy: 2.867936849594116 +[2025-04-28 17:51:26,376][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 2.775228977203369, cross_entropy: 2.775228977203369 +[2025-04-28 17:51:27,086][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.267810344696045, cross_entropy: 1.267810344696045 +[2025-04-28 17:51:29,313][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 2.1433181762695312, cross_entropy: 2.1433181762695312 +[2025-04-28 17:51:30,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.751388669013977, cross_entropy: 1.751388669013977 +[2025-04-28 17:51:32,441][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 2.079026699066162, cross_entropy: 2.079026699066162 +[2025-04-28 17:51:33,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 1.5525840520858765, cross_entropy: 1.5525840520858765 +[2025-04-28 17:51:35,381][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 2.636460304260254, cross_entropy: 2.636460304260254 +[2025-04-28 17:51:36,097][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 1.4738426208496094, cross_entropy: 1.4738426208496094 +[2025-04-28 17:51:39,457][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 2.5732927322387695, cross_entropy: 2.5732927322387695 +[2025-04-28 17:51:40,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.694404125213623, cross_entropy: 1.694404125213623 +[2025-04-28 17:51:42,703][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.9987239837646484, cross_entropy: 2.9987239837646484 +[2025-04-28 17:51:43,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.282776355743408, cross_entropy: 2.282776355743408 +[2025-04-28 17:51:45,867][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 1.4537153244018555, cross_entropy: 1.4537153244018555 +[2025-04-28 17:51:46,580][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 1.7050700187683105, cross_entropy: 1.7050700187683105 +[2025-04-28 17:51:48,944][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 3.260237455368042, cross_entropy: 3.260237455368042 +[2025-04-28 17:51:49,622][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 2.3967275619506836, cross_entropy: 2.3967275619506836 +[2025-04-28 17:51:52,451][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 1.2379183769226074, cross_entropy: 1.2379183769226074 +[2025-04-28 17:51:53,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 2.6354849338531494, cross_entropy: 2.6354849338531494 +[2025-04-28 17:51:55,429][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 1.410879135131836, cross_entropy: 1.410879135131836 +[2025-04-28 17:51:56,137][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.505441665649414, cross_entropy: 1.505441665649414 +[2025-04-28 17:51:59,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 1.7228420972824097, cross_entropy: 1.7228420972824097 +[2025-04-28 17:51:59,939][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 1.9997706413269043, cross_entropy: 1.9997706413269043 +[2025-04-28 17:52:02,308][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.4372189044952393, cross_entropy: 2.4372189044952393 +[2025-04-28 17:52:03,030][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 3.173142433166504, cross_entropy: 3.173142433166504 +[2025-04-28 17:52:05,405][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.4181534051895142, cross_entropy: 1.4181534051895142 +[2025-04-28 17:52:06,113][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 2.3901963233947754, cross_entropy: 2.3901963233947754 +[2025-04-28 17:52:08,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 1.8476052284240723, cross_entropy: 1.8476052284240723 +[2025-04-28 17:52:09,186][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 1.3020813465118408, cross_entropy: 1.3020813465118408 +[2025-04-28 17:52:11,104][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 3.15762996673584, cross_entropy: 3.15762996673584 +[2025-04-28 17:52:11,782][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 2.1102075576782227, cross_entropy: 2.1102075576782227 +[2025-04-28 17:52:14,384][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 2.8508055210113525, cross_entropy: 2.8508055210113525 +[2025-04-28 17:52:15,094][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 1.9504265785217285, cross_entropy: 1.9504265785217285 +[2025-04-28 17:52:18,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 1.9182090759277344, cross_entropy: 1.9182090759277344 +[2025-04-28 17:52:18,796][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 2.85366153717041, cross_entropy: 2.85366153717041 +[2025-04-28 17:52:21,129][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 2.915842294692993, cross_entropy: 2.915842294692993 +[2025-04-28 17:52:21,825][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.6634132862091064, cross_entropy: 2.6634132862091064 +[2025-04-28 17:52:24,226][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.552731513977051, cross_entropy: 2.552731513977051 +[2025-04-28 17:52:24,942][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 3.208334445953369, cross_entropy: 3.208334445953369 +[2025-04-28 17:52:27,755][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.543123483657837, cross_entropy: 1.543123483657837 +[2025-04-28 17:52:28,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.302644729614258, cross_entropy: 2.302644729614258 +[2025-04-28 17:52:31,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 2.4798851013183594, cross_entropy: 2.4798851013183594 +[2025-04-28 17:52:31,814][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 2.139425754547119, cross_entropy: 2.139425754547119 +[2025-04-28 17:52:34,199][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.8220140933990479, cross_entropy: 1.8220140933990479 +[2025-04-28 17:52:34,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 1.6182818412780762, cross_entropy: 1.6182818412780762 +[2025-04-28 17:52:37,227][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 2.189531087875366, cross_entropy: 2.189531087875366 +[2025-04-28 17:52:37,938][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 2.923135280609131, cross_entropy: 2.923135280609131 +[2025-04-28 17:52:40,445][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 3.3716678619384766, cross_entropy: 3.3716678619384766 +[2025-04-28 17:52:41,152][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 1.890256404876709, cross_entropy: 1.890256404876709 +[2025-04-28 17:52:43,924][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.778347134590149, cross_entropy: 1.778347134590149 +[2025-04-28 17:52:44,601][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.8725931644439697, cross_entropy: 2.8725931644439697 +[2025-04-28 17:52:47,341][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 1.5536491870880127, cross_entropy: 1.5536491870880127 +[2025-04-28 17:52:48,022][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 1.9340628385543823, cross_entropy: 1.9340628385543823 +[2025-04-28 17:52:50,360][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.605301022529602, cross_entropy: 1.605301022529602 +[2025-04-28 17:52:51,081][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.3094491958618164, cross_entropy: 1.3094491958618164 +[2025-04-28 17:52:54,035][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 1.3203997611999512, cross_entropy: 1.3203997611999512 +[2025-04-28 17:52:54,722][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 2.440554618835449, cross_entropy: 2.440554618835449 +[2025-04-28 17:52:56,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.6252799034118652, cross_entropy: 2.6252799034118652 +[2025-04-28 17:52:57,495][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 1.357625961303711, cross_entropy: 1.357625961303711 +[2025-04-28 17:53:00,653][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 1.7249890565872192, cross_entropy: 1.7249890565872192 +[2025-04-28 17:53:01,335][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 3.185680627822876, cross_entropy: 3.185680627822876 +[2025-04-28 17:53:04,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 2.654954433441162, cross_entropy: 2.654954433441162 +[2025-04-28 17:53:05,129][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.7490358352661133, cross_entropy: 1.7490358352661133 +[2025-04-28 17:53:07,700][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 3.286952018737793, cross_entropy: 3.286952018737793 +[2025-04-28 17:53:08,408][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 2.069746971130371, cross_entropy: 2.069746971130371 +[2025-04-28 17:53:10,418][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.667719841003418, cross_entropy: 2.667719841003418 +[2025-04-28 17:53:11,130][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 2.953853130340576, cross_entropy: 2.953853130340576 +[2025-04-28 17:53:15,046][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 3.113325357437134, cross_entropy: 3.113325357437134 +[2025-04-28 17:53:15,763][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 3.103745222091675, cross_entropy: 3.103745222091675 +[2025-04-28 17:53:18,706][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 2.0165505409240723, cross_entropy: 2.0165505409240723 +[2025-04-28 17:53:19,420][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 3.1431126594543457, cross_entropy: 3.1431126594543457 +[2025-04-28 17:53:22,231][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.5769050121307373, cross_entropy: 1.5769050121307373 +[2025-04-28 17:53:22,944][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 1.8299670219421387, cross_entropy: 1.8299670219421387 +[2025-04-28 17:53:25,985][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.0437843799591064, cross_entropy: 2.0437843799591064 +[2025-04-28 17:53:26,697][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 3.1409912109375, cross_entropy: 3.1409912109375 +[2025-04-28 17:53:29,675][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 2.7293484210968018, cross_entropy: 2.7293484210968018 +[2025-04-28 17:53:30,384][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 1.8644623756408691, cross_entropy: 1.8644623756408691 +[2025-04-28 17:53:32,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 2.8706698417663574, cross_entropy: 2.8706698417663574 +[2025-04-28 17:53:33,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 2.701511859893799, cross_entropy: 2.701511859893799 +[2025-04-28 17:53:35,451][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.3225871324539185, cross_entropy: 1.3225871324539185 +[2025-04-28 17:53:36,162][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 2.477266788482666, cross_entropy: 2.477266788482666 +[2025-04-28 17:53:38,872][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 2.978832721710205, cross_entropy: 2.978832721710205 +[2025-04-28 17:53:39,584][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 1.0970603227615356, cross_entropy: 1.0970603227615356 +[2025-04-28 17:53:41,586][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 3.2153563499450684, cross_entropy: 3.2153563499450684 +[2025-04-28 17:53:42,294][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.0877888202667236, cross_entropy: 1.0877888202667236 +[2025-04-28 17:53:44,512][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 2.991978168487549, cross_entropy: 2.991978168487549 +[2025-04-28 17:53:45,221][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 2.9091036319732666, cross_entropy: 2.9091036319732666 +[2025-04-28 17:53:46,900][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 2.853854179382324, cross_entropy: 2.853854179382324 +[2025-04-28 17:53:47,645][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 2.8104498386383057, cross_entropy: 2.8104498386383057 +[2025-04-28 17:53:50,577][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 2.8832292556762695, cross_entropy: 2.8832292556762695 +[2025-04-28 17:53:51,288][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 2.7053821086883545, cross_entropy: 2.7053821086883545 +[2025-04-28 17:53:53,134][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 2.8318259716033936, cross_entropy: 2.8318259716033936 +[2025-04-28 17:53:53,889][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.125584602355957, cross_entropy: 1.125584602355957 +[2025-04-28 17:53:56,851][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 3.0570228099823, cross_entropy: 3.0570228099823 +[2025-04-28 17:53:57,565][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 1.5789434909820557, cross_entropy: 1.5789434909820557 +[2025-04-28 17:53:59,374][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 2.734935760498047, cross_entropy: 2.734935760498047 +[2025-04-28 17:54:00,109][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 1.6061484813690186, cross_entropy: 1.6061484813690186 +[2025-04-28 17:54:02,773][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.765183687210083, cross_entropy: 1.765183687210083 +[2025-04-28 17:54:03,529][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 3.404679298400879, cross_entropy: 3.404679298400879 +[2025-04-28 17:54:05,904][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 3.096126079559326, cross_entropy: 3.096126079559326 +[2025-04-28 17:54:06,685][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 1.8202731609344482, cross_entropy: 1.8202731609344482 +[2025-04-28 17:54:08,642][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 3.179689407348633, cross_entropy: 3.179689407348633 +[2025-04-28 17:54:10,438][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.5824313163757324, cross_entropy: 1.5824313163757324 +[2025-04-28 17:54:11,979][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.1868782043457031, cross_entropy: 1.1868782043457031 +[2025-04-28 17:54:13,556][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.3217494487762451, cross_entropy: 1.3217494487762451 +[2025-04-28 17:54:14,688][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 2.5002145767211914, cross_entropy: 2.5002145767211914 +[2025-04-28 17:54:17,062][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 2.5806994438171387, cross_entropy: 2.5806994438171387 +[2025-04-28 17:54:17,827][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 3.243701219558716, cross_entropy: 3.243701219558716 +[2025-04-28 17:54:20,102][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 3.26713228225708, cross_entropy: 3.26713228225708 +[2025-04-28 17:54:20,809][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 1.5416653156280518, cross_entropy: 1.5416653156280518 +[2025-04-28 17:54:23,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.5165680646896362, cross_entropy: 1.5165680646896362 +[2025-04-28 17:54:23,781][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 2.960359573364258, cross_entropy: 2.960359573364258 +[2025-04-28 17:54:26,399][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.720423698425293, cross_entropy: 2.720423698425293 +[2025-04-28 17:54:27,163][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 3.101163387298584, cross_entropy: 3.101163387298584 +[2025-04-28 17:54:29,408][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 2.8410253524780273, cross_entropy: 2.8410253524780273 +[2025-04-28 17:54:30,550][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 3.015277624130249, cross_entropy: 3.015277624130249 +[2025-04-28 17:54:32,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 2.296607494354248, cross_entropy: 2.296607494354248 +[2025-04-28 17:54:34,509][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.5903213024139404, cross_entropy: 1.5903213024139404 +[2025-04-28 17:54:35,365][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.5545378923416138, cross_entropy: 1.5545378923416138 +[2025-04-28 17:54:37,831][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 3.2537899017333984, cross_entropy: 3.2537899017333984 +[2025-04-28 17:54:39,615][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 2.978513717651367, cross_entropy: 2.978513717651367 +[2025-04-28 17:54:41,026][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 2.1490654945373535, cross_entropy: 2.1490654945373535 +[2025-04-28 17:54:42,586][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.5399422645568848, cross_entropy: 1.5399422645568848 +[2025-04-28 17:54:44,023][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 2.4209179878234863, cross_entropy: 2.4209179878234863 +[2025-04-28 17:54:45,549][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.5066484212875366, cross_entropy: 1.5066484212875366 +[2025-04-28 17:54:47,815][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.3540058135986328, cross_entropy: 1.3540058135986328 +[2025-04-28 17:54:48,818][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.4685746431350708, cross_entropy: 1.4685746431350708 +[2025-04-28 17:54:51,636][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.460608959197998, cross_entropy: 2.460608959197998 +[2025-04-28 17:54:52,250][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 3.164846420288086, cross_entropy: 3.164846420288086 +[2025-04-28 17:57:21,197][BaseTrainer][INFO] - [Epoch 6/10] (train) 2.2349979877471924, cross_entropy: 2.2349979877471924 +[2025-04-28 17:57:21,198][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.348495602607727, cross_entropy: 1.348495602607727 +[2025-04-28 17:57:22,094][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 17:57:22,600][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch6.pth. +[2025-04-28 17:57:23,413][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 17:57:27,674][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 3.1666769981384277, cross_entropy: 3.1666769981384277 +[2025-04-28 17:57:28,386][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 1.5450087785720825, cross_entropy: 1.5450087785720825 +[2025-04-28 17:57:30,758][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 3.159989833831787, cross_entropy: 3.159989833831787 +[2025-04-28 17:57:31,473][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 1.1521596908569336, cross_entropy: 1.1521596908569336 +[2025-04-28 17:57:34,823][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 2.1196513175964355, cross_entropy: 2.1196513175964355 +[2025-04-28 17:57:35,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 2.1822686195373535, cross_entropy: 2.1822686195373535 +[2025-04-28 17:57:38,079][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 1.2767903804779053, cross_entropy: 1.2767903804779053 +[2025-04-28 17:57:38,785][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.6319615840911865, cross_entropy: 1.6319615840911865 +[2025-04-28 17:57:41,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 2.629908800125122, cross_entropy: 2.629908800125122 +[2025-04-28 17:57:41,834][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.0476692914962769, cross_entropy: 1.0476692914962769 +[2025-04-28 17:57:45,212][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 1.5304710865020752, cross_entropy: 1.5304710865020752 +[2025-04-28 17:57:45,922][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.5592321157455444, cross_entropy: 1.5592321157455444 +[2025-04-28 17:57:48,470][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.697756767272949, cross_entropy: 2.697756767272949 +[2025-04-28 17:57:49,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 1.0709348917007446, cross_entropy: 1.0709348917007446 +[2025-04-28 17:57:52,087][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.444697856903076, cross_entropy: 2.444697856903076 +[2025-04-28 17:57:52,795][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 1.788171410560608, cross_entropy: 1.788171410560608 +[2025-04-28 17:57:57,911][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 1.960153579711914, cross_entropy: 1.960153579711914 +[2025-04-28 17:57:58,614][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 3.050053834915161, cross_entropy: 3.050053834915161 +[2025-04-28 17:58:00,536][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.883319854736328, cross_entropy: 2.883319854736328 +[2025-04-28 17:58:01,245][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.6102863550186157, cross_entropy: 1.6102863550186157 +[2025-04-28 17:58:03,935][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 3.064361095428467, cross_entropy: 3.064361095428467 +[2025-04-28 17:58:04,638][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.8106284141540527, cross_entropy: 2.8106284141540527 +[2025-04-28 17:58:07,275][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 2.3498404026031494, cross_entropy: 2.3498404026031494 +[2025-04-28 17:58:07,988][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.341909408569336, cross_entropy: 2.341909408569336 +[2025-04-28 17:58:10,922][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 2.289133310317993, cross_entropy: 2.289133310317993 +[2025-04-28 17:58:11,634][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 3.2286581993103027, cross_entropy: 3.2286581993103027 +[2025-04-28 17:58:14,253][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 1.975109577178955, cross_entropy: 1.975109577178955 +[2025-04-28 17:58:14,959][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 3.1011228561401367, cross_entropy: 3.1011228561401367 +[2025-04-28 17:58:17,011][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 2.573256015777588, cross_entropy: 2.573256015777588 +[2025-04-28 17:58:17,814][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.2742211818695068, cross_entropy: 1.2742211818695068 +[2025-04-28 17:58:20,258][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 1.033296823501587, cross_entropy: 1.033296823501587 +[2025-04-28 17:58:21,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 1.205531358718872, cross_entropy: 1.205531358718872 +[2025-04-28 17:58:23,171][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 1.560881495475769, cross_entropy: 1.560881495475769 +[2025-04-28 17:58:23,908][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 1.9917198419570923, cross_entropy: 1.9917198419570923 +[2025-04-28 17:58:26,521][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.6585311889648438, cross_entropy: 2.6585311889648438 +[2025-04-28 17:58:27,431][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.241253137588501, cross_entropy: 1.241253137588501 +[2025-04-28 17:58:30,584][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.3429348468780518, cross_entropy: 2.3429348468780518 +[2025-04-28 17:58:31,261][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 2.9908499717712402, cross_entropy: 2.9908499717712402 +[2025-04-28 17:58:33,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 2.5821373462677, cross_entropy: 2.5821373462677 +[2025-04-28 17:58:34,711][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.310565710067749, cross_entropy: 1.310565710067749 +[2025-04-28 17:58:36,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 2.2605795860290527, cross_entropy: 2.2605795860290527 +[2025-04-28 17:58:37,564][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 1.600360631942749, cross_entropy: 1.600360631942749 +[2025-04-28 17:58:39,667][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 1.7050540447235107, cross_entropy: 1.7050540447235107 +[2025-04-28 17:58:40,464][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 2.0574991703033447, cross_entropy: 2.0574991703033447 +[2025-04-28 17:58:43,027][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 3.0584158897399902, cross_entropy: 3.0584158897399902 +[2025-04-28 17:58:43,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 3.111302614212036, cross_entropy: 3.111302614212036 +[2025-04-28 17:58:45,994][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 3.173110246658325, cross_entropy: 3.173110246658325 +[2025-04-28 17:58:46,788][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 1.9573508501052856, cross_entropy: 1.9573508501052856 +[2025-04-28 17:58:48,979][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.3436074256896973, cross_entropy: 2.3436074256896973 +[2025-04-28 17:58:49,868][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 1.979356050491333, cross_entropy: 1.979356050491333 +[2025-04-28 17:58:51,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 1.273754596710205, cross_entropy: 1.273754596710205 +[2025-04-28 17:58:53,227][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.2801854610443115, cross_entropy: 1.2801854610443115 +[2025-04-28 17:58:54,937][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 1.8263564109802246, cross_entropy: 1.8263564109802246 +[2025-04-28 17:58:56,815][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 2.8668200969696045, cross_entropy: 2.8668200969696045 +[2025-04-28 17:58:57,944][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 1.9162161350250244, cross_entropy: 1.9162161350250244 +[2025-04-28 17:58:59,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 1.6923415660858154, cross_entropy: 1.6923415660858154 +[2025-04-28 17:59:01,030][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 3.0118842124938965, cross_entropy: 3.0118842124938965 +[2025-04-28 17:59:02,779][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.397231101989746, cross_entropy: 1.397231101989746 +[2025-04-28 17:59:04,549][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 1.4463554620742798, cross_entropy: 1.4463554620742798 +[2025-04-28 17:59:05,753][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 2.0099997520446777, cross_entropy: 2.0099997520446777 +[2025-04-28 17:59:07,711][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.297248125076294, cross_entropy: 2.297248125076294 +[2025-04-28 17:59:09,397][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 2.182903289794922, cross_entropy: 2.182903289794922 +[2025-04-28 17:59:11,177][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.651179552078247, cross_entropy: 1.651179552078247 +[2025-04-28 17:59:12,269][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 2.240586757659912, cross_entropy: 2.240586757659912 +[2025-04-28 17:59:14,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.120556592941284, cross_entropy: 2.120556592941284 +[2025-04-28 17:59:15,265][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 2.980489492416382, cross_entropy: 2.980489492416382 +[2025-04-28 17:59:17,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.576472282409668, cross_entropy: 1.576472282409668 +[2025-04-28 17:59:18,163][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 1.8101181983947754, cross_entropy: 1.8101181983947754 +[2025-04-28 17:59:20,505][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 1.584101676940918, cross_entropy: 1.584101676940918 +[2025-04-28 17:59:21,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 2.570920467376709, cross_entropy: 2.570920467376709 +[2025-04-28 17:59:23,149][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 1.5425055027008057, cross_entropy: 1.5425055027008057 +[2025-04-28 17:59:24,073][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 1.452094316482544, cross_entropy: 1.452094316482544 +[2025-04-28 17:59:27,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 1.3690533638000488, cross_entropy: 1.3690533638000488 +[2025-04-28 17:59:28,136][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 2.7619495391845703, cross_entropy: 2.7619495391845703 +[2025-04-28 17:59:30,894][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 3.3758697509765625, cross_entropy: 3.3758697509765625 +[2025-04-28 17:59:31,605][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.345685601234436, cross_entropy: 1.345685601234436 +[2025-04-28 17:59:34,562][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 1.167604923248291, cross_entropy: 1.167604923248291 +[2025-04-28 17:59:35,277][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 3.3820903301239014, cross_entropy: 3.3820903301239014 +[2025-04-28 17:59:38,254][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.195234775543213, cross_entropy: 2.195234775543213 +[2025-04-28 17:59:38,971][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 3.1933295726776123, cross_entropy: 3.1933295726776123 +[2025-04-28 17:59:41,647][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 3.207033634185791, cross_entropy: 3.207033634185791 +[2025-04-28 17:59:42,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 3.2698988914489746, cross_entropy: 3.2698988914489746 +[2025-04-28 17:59:44,913][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.7751364707946777, cross_entropy: 2.7751364707946777 +[2025-04-28 17:59:45,595][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 1.6332168579101562, cross_entropy: 1.6332168579101562 +[2025-04-28 17:59:48,047][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 2.6599764823913574, cross_entropy: 2.6599764823913574 +[2025-04-28 17:59:48,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 2.708927631378174, cross_entropy: 2.708927631378174 +[2025-04-28 17:59:51,467][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 1.5066595077514648, cross_entropy: 1.5066595077514648 +[2025-04-28 17:59:52,178][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 1.3842968940734863, cross_entropy: 1.3842968940734863 +[2025-04-28 17:59:54,350][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 3.1012558937072754, cross_entropy: 3.1012558937072754 +[2025-04-28 17:59:55,034][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.4510092735290527, cross_entropy: 1.4510092735290527 +[2025-04-28 17:59:58,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 1.596243143081665, cross_entropy: 1.596243143081665 +[2025-04-28 17:59:59,373][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 3.1832528114318848, cross_entropy: 3.1832528114318848 +[2025-04-28 18:00:02,938][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 3.260080099105835, cross_entropy: 3.260080099105835 +[2025-04-28 18:00:03,628][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.4415538311004639, cross_entropy: 1.4415538311004639 +[2025-04-28 18:00:06,480][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.1948089599609375, cross_entropy: 2.1948089599609375 +[2025-04-28 18:00:07,160][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.518255591392517, cross_entropy: 1.518255591392517 +[2025-04-28 18:00:09,574][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 2.313661575317383, cross_entropy: 2.313661575317383 +[2025-04-28 18:00:10,256][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 2.926384687423706, cross_entropy: 2.926384687423706 +[2025-04-28 18:00:12,922][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.585601568222046, cross_entropy: 1.585601568222046 +[2025-04-28 18:00:13,604][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 2.6966583728790283, cross_entropy: 2.6966583728790283 +[2025-04-28 18:00:16,141][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 3.137213945388794, cross_entropy: 3.137213945388794 +[2025-04-28 18:00:16,820][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 1.2793117761611938, cross_entropy: 1.2793117761611938 +[2025-04-28 18:00:19,088][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.3801867961883545, cross_entropy: 2.3801867961883545 +[2025-04-28 18:00:19,806][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.1142091751098633, cross_entropy: 1.1142091751098633 +[2025-04-28 18:00:22,337][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.148888349533081, cross_entropy: 1.148888349533081 +[2025-04-28 18:00:23,047][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.472700595855713, cross_entropy: 1.472700595855713 +[2025-04-28 18:00:25,369][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 1.9113215208053589, cross_entropy: 1.9113215208053589 +[2025-04-28 18:00:26,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.132576584815979, cross_entropy: 1.132576584815979 +[2025-04-28 18:00:28,756][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 2.412587881088257, cross_entropy: 2.412587881088257 +[2025-04-28 18:00:29,468][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 2.4639291763305664, cross_entropy: 2.4639291763305664 +[2025-04-28 18:00:32,327][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 3.046809196472168, cross_entropy: 3.046809196472168 +[2025-04-28 18:00:33,036][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 1.3562875986099243, cross_entropy: 1.3562875986099243 +[2025-04-28 18:00:35,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 2.4449515342712402, cross_entropy: 2.4449515342712402 +[2025-04-28 18:00:36,352][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 1.3080850839614868, cross_entropy: 1.3080850839614868 +[2025-04-28 18:00:39,113][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.5214884281158447, cross_entropy: 1.5214884281158447 +[2025-04-28 18:00:39,825][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 2.5131423473358154, cross_entropy: 2.5131423473358154 +[2025-04-28 18:00:42,183][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.538970947265625, cross_entropy: 1.538970947265625 +[2025-04-28 18:00:42,897][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.081160306930542, cross_entropy: 2.081160306930542 +[2025-04-28 18:00:45,870][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 1.6831908226013184, cross_entropy: 1.6831908226013184 +[2025-04-28 18:00:46,586][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 2.1263909339904785, cross_entropy: 2.1263909339904785 +[2025-04-28 18:00:49,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 3.3756680488586426, cross_entropy: 3.3756680488586426 +[2025-04-28 18:00:50,193][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 3.138920783996582, cross_entropy: 3.138920783996582 +[2025-04-28 18:00:52,718][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 1.4900217056274414, cross_entropy: 1.4900217056274414 +[2025-04-28 18:00:53,421][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.08944571018219, cross_entropy: 1.08944571018219 +[2025-04-28 18:00:55,202][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 1.5279186964035034, cross_entropy: 1.5279186964035034 +[2025-04-28 18:00:55,911][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.0090619325637817, cross_entropy: 1.0090619325637817 +[2025-04-28 18:00:58,462][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.184495449066162, cross_entropy: 3.184495449066162 +[2025-04-28 18:00:59,144][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.171431541442871, cross_entropy: 1.171431541442871 +[2025-04-28 18:01:02,120][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 2.0514426231384277, cross_entropy: 2.0514426231384277 +[2025-04-28 18:01:02,834][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 1.3931337594985962, cross_entropy: 1.3931337594985962 +[2025-04-28 18:01:05,751][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 1.3398466110229492, cross_entropy: 1.3398466110229492 +[2025-04-28 18:01:06,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 3.5918965339660645, cross_entropy: 3.5918965339660645 +[2025-04-28 18:01:08,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 0.8906286954879761, cross_entropy: 0.8906286954879761 +[2025-04-28 18:01:09,208][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.032122015953064, cross_entropy: 1.032122015953064 +[2025-04-28 18:01:11,436][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 1.9154304265975952, cross_entropy: 1.9154304265975952 +[2025-04-28 18:01:12,146][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 3.1120643615722656, cross_entropy: 3.1120643615722656 +[2025-04-28 18:01:14,801][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 1.7541923522949219, cross_entropy: 1.7541923522949219 +[2025-04-28 18:01:15,524][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 3.428105354309082, cross_entropy: 3.428105354309082 +[2025-04-28 18:01:17,564][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 0.9029536843299866, cross_entropy: 0.9029536843299866 +[2025-04-28 18:01:18,276][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 3.603278636932373, cross_entropy: 3.603278636932373 +[2025-04-28 18:01:20,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 1.418835997581482, cross_entropy: 1.418835997581482 +[2025-04-28 18:01:21,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 3.109549045562744, cross_entropy: 3.109549045562744 +[2025-04-28 18:01:23,582][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 1.7909538745880127, cross_entropy: 1.7909538745880127 +[2025-04-28 18:01:24,260][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.563518524169922, cross_entropy: 2.563518524169922 +[2025-04-28 18:01:27,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.7541813850402832, cross_entropy: 1.7541813850402832 +[2025-04-28 18:01:27,876][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.826224446296692, cross_entropy: 1.826224446296692 +[2025-04-28 18:01:30,316][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 3.1195406913757324, cross_entropy: 3.1195406913757324 +[2025-04-28 18:01:30,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 1.741589069366455, cross_entropy: 1.741589069366455 +[2025-04-28 18:01:34,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.9547717571258545, cross_entropy: 2.9547717571258545 +[2025-04-28 18:01:35,001][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 2.5618486404418945, cross_entropy: 2.5618486404418945 +[2025-04-28 18:01:37,585][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 3.3505425453186035, cross_entropy: 3.3505425453186035 +[2025-04-28 18:01:38,294][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 1.340873122215271, cross_entropy: 1.340873122215271 +[2025-04-28 18:01:40,821][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.714416265487671, cross_entropy: 2.714416265487671 +[2025-04-28 18:01:41,527][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 1.3013750314712524, cross_entropy: 1.3013750314712524 +[2025-04-28 18:01:43,465][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 1.2947732210159302, cross_entropy: 1.2947732210159302 +[2025-04-28 18:01:44,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 2.212911605834961, cross_entropy: 2.212911605834961 +[2025-04-28 18:01:46,401][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 3.1363391876220703, cross_entropy: 3.1363391876220703 +[2025-04-28 18:01:47,116][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 1.9882715940475464, cross_entropy: 1.9882715940475464 +[2025-04-28 18:01:49,698][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 3.3625760078430176, cross_entropy: 3.3625760078430176 +[2025-04-28 18:01:50,378][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 2.836958408355713, cross_entropy: 2.836958408355713 +[2025-04-28 18:01:53,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 1.3661019802093506, cross_entropy: 1.3661019802093506 +[2025-04-28 18:01:53,950][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 2.056384563446045, cross_entropy: 2.056384563446045 +[2025-04-28 18:01:55,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.7361916303634644, cross_entropy: 1.7361916303634644 +[2025-04-28 18:01:56,522][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 1.7881085872650146, cross_entropy: 1.7881085872650146 +[2025-04-28 18:01:58,699][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.1744245290756226, cross_entropy: 1.1744245290756226 +[2025-04-28 18:01:59,381][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.6800141334533691, cross_entropy: 1.6800141334533691 +[2025-04-28 18:02:01,563][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 3.142988443374634, cross_entropy: 3.142988443374634 +[2025-04-28 18:02:02,272][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 1.8423322439193726, cross_entropy: 1.8423322439193726 +[2025-04-28 18:02:03,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 2.2549257278442383, cross_entropy: 2.2549257278442383 +[2025-04-28 18:02:04,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 1.3020802736282349, cross_entropy: 1.3020802736282349 +[2025-04-28 18:02:07,024][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.6163313388824463, cross_entropy: 1.6163313388824463 +[2025-04-28 18:02:07,904][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 1.138669490814209, cross_entropy: 1.138669490814209 +[2025-04-28 18:02:11,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.885870099067688, cross_entropy: 1.885870099067688 +[2025-04-28 18:02:11,940][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 3.166646718978882, cross_entropy: 3.166646718978882 +[2025-04-28 18:02:14,017][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 2.3206937313079834, cross_entropy: 2.3206937313079834 +[2025-04-28 18:02:14,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.544802188873291, cross_entropy: 1.544802188873291 +[2025-04-28 18:02:17,492][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 3.3519792556762695, cross_entropy: 3.3519792556762695 +[2025-04-28 18:02:18,259][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.0922220945358276, cross_entropy: 1.0922220945358276 +[2025-04-28 18:02:21,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 1.3684191703796387, cross_entropy: 1.3684191703796387 +[2025-04-28 18:02:22,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.9495387077331543, cross_entropy: 1.9495387077331543 +[2025-04-28 18:02:24,092][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.7641048431396484, cross_entropy: 2.7641048431396484 +[2025-04-28 18:02:25,796][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 1.227352261543274, cross_entropy: 1.227352261543274 +[2025-04-28 18:02:27,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.0785496234893799, cross_entropy: 1.0785496234893799 +[2025-04-28 18:02:28,305][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 2.9592936038970947, cross_entropy: 2.9592936038970947 +[2025-04-28 18:02:31,466][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 3.468356132507324, cross_entropy: 3.468356132507324 +[2025-04-28 18:02:32,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.701491594314575, cross_entropy: 2.701491594314575 +[2025-04-28 18:02:34,936][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 3.009891986846924, cross_entropy: 3.009891986846924 +[2025-04-28 18:02:35,657][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 1.4141809940338135, cross_entropy: 1.4141809940338135 +[2025-04-28 18:02:37,815][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.3688206672668457, cross_entropy: 1.3688206672668457 +[2025-04-28 18:02:38,533][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 2.19273042678833, cross_entropy: 2.19273042678833 +[2025-04-28 18:02:40,720][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 2.934159994125366, cross_entropy: 2.934159994125366 +[2025-04-28 18:02:41,433][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 2.6897811889648438, cross_entropy: 2.6897811889648438 +[2025-04-28 18:02:43,559][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 1.8592172861099243, cross_entropy: 1.8592172861099243 +[2025-04-28 18:02:44,282][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 1.99001145362854, cross_entropy: 1.99001145362854 +[2025-04-28 18:02:46,401][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.509627103805542, cross_entropy: 1.509627103805542 +[2025-04-28 18:02:47,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.0177781581878662, cross_entropy: 1.0177781581878662 +[2025-04-28 18:02:49,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 0.9655124545097351, cross_entropy: 0.9655124545097351 +[2025-04-28 18:02:50,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 2.7745683193206787, cross_entropy: 2.7745683193206787 +[2025-04-28 18:02:52,867][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.1334633827209473, cross_entropy: 3.1334633827209473 +[2025-04-28 18:02:53,579][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.2873070240020752, cross_entropy: 1.2873070240020752 +[2025-04-28 18:02:55,799][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 3.2222795486450195, cross_entropy: 3.2222795486450195 +[2025-04-28 18:02:56,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 1.1759989261627197, cross_entropy: 1.1759989261627197 +[2025-04-28 18:02:59,231][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.419130563735962, cross_entropy: 1.419130563735962 +[2025-04-28 18:02:59,954][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 3.1754910945892334, cross_entropy: 3.1754910945892334 +[2025-04-28 18:03:01,802][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 2.8406548500061035, cross_entropy: 2.8406548500061035 +[2025-04-28 18:03:02,520][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 1.5286457538604736, cross_entropy: 1.5286457538604736 +[2025-04-28 18:03:04,448][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 1.5022990703582764, cross_entropy: 1.5022990703582764 +[2025-04-28 18:03:05,130][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.3013842105865479, cross_entropy: 1.3013842105865479 +[2025-04-28 18:03:08,375][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 3.271667242050171, cross_entropy: 3.271667242050171 +[2025-04-28 18:03:09,090][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 1.2342056035995483, cross_entropy: 1.2342056035995483 +[2025-04-28 18:03:11,832][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 2.0345633029937744, cross_entropy: 2.0345633029937744 +[2025-04-28 18:03:12,544][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.1539103984832764, cross_entropy: 1.1539103984832764 +[2025-04-28 18:03:14,930][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 3.4118266105651855, cross_entropy: 3.4118266105651855 +[2025-04-28 18:03:15,642][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.3696627616882324, cross_entropy: 1.3696627616882324 +[2025-04-28 18:03:18,467][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.3084208965301514, cross_entropy: 1.3084208965301514 +[2025-04-28 18:03:19,182][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 1.1384100914001465, cross_entropy: 1.1384100914001465 +[2025-04-28 18:03:20,969][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 2.954371452331543, cross_entropy: 2.954371452331543 +[2025-04-28 18:03:21,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 2.847395420074463, cross_entropy: 2.847395420074463 +[2025-04-28 18:03:24,129][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.365752935409546, cross_entropy: 1.365752935409546 +[2025-04-28 18:03:24,850][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.7464749813079834, cross_entropy: 2.7464749813079834 +[2025-04-28 18:03:27,060][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 3.4858779907226562, cross_entropy: 3.4858779907226562 +[2025-04-28 18:03:27,797][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 1.9608134031295776, cross_entropy: 1.9608134031295776 +[2025-04-28 18:03:30,581][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.7358038425445557, cross_entropy: 2.7358038425445557 +[2025-04-28 18:03:31,290][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 2.672598361968994, cross_entropy: 2.672598361968994 +[2025-04-28 18:03:33,838][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.5455620288848877, cross_entropy: 1.5455620288848877 +[2025-04-28 18:03:34,546][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 3.3594040870666504, cross_entropy: 3.3594040870666504 +[2025-04-28 18:03:38,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 3.501098155975342, cross_entropy: 3.501098155975342 +[2025-04-28 18:03:38,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.4840723276138306, cross_entropy: 1.4840723276138306 +[2025-04-28 18:03:41,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 2.034226417541504, cross_entropy: 2.034226417541504 +[2025-04-28 18:03:42,624][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 1.2916901111602783, cross_entropy: 1.2916901111602783 +[2025-04-28 18:03:45,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.614966869354248, cross_entropy: 2.614966869354248 +[2025-04-28 18:03:46,181][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.599370002746582, cross_entropy: 1.599370002746582 +[2025-04-28 18:03:48,408][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 2.537937641143799, cross_entropy: 2.537937641143799 +[2025-04-28 18:03:49,131][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.6089134216308594, cross_entropy: 2.6089134216308594 +[2025-04-28 18:03:51,694][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 2.5133614540100098, cross_entropy: 2.5133614540100098 +[2025-04-28 18:03:52,409][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 3.1274704933166504, cross_entropy: 3.1274704933166504 +[2025-04-28 18:03:54,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 1.7218334674835205, cross_entropy: 1.7218334674835205 +[2025-04-28 18:03:55,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 2.1732239723205566, cross_entropy: 2.1732239723205566 +[2025-04-28 18:03:57,915][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.1079351902008057, cross_entropy: 2.1079351902008057 +[2025-04-28 18:03:58,625][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 2.0041110515594482, cross_entropy: 2.0041110515594482 +[2025-04-28 18:04:01,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.174922466278076, cross_entropy: 2.174922466278076 +[2025-04-28 18:04:01,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 1.662426471710205, cross_entropy: 1.662426471710205 +[2025-04-28 18:04:04,110][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 1.9368946552276611, cross_entropy: 1.9368946552276611 +[2025-04-28 18:04:04,797][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 1.86858332157135, cross_entropy: 1.86858332157135 +[2025-04-28 18:04:07,599][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.17841374874115, cross_entropy: 1.17841374874115 +[2025-04-28 18:04:08,283][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 1.2826988697052002, cross_entropy: 1.2826988697052002 +[2025-04-28 18:04:11,048][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 2.4798123836517334, cross_entropy: 2.4798123836517334 +[2025-04-28 18:04:11,766][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 2.2659049034118652, cross_entropy: 2.2659049034118652 +[2025-04-28 18:04:14,364][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 1.4065032005310059, cross_entropy: 1.4065032005310059 +[2025-04-28 18:04:15,089][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.376136541366577, cross_entropy: 2.376136541366577 +[2025-04-28 18:04:17,891][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.8392565250396729, cross_entropy: 1.8392565250396729 +[2025-04-28 18:04:18,607][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 3.069812297821045, cross_entropy: 3.069812297821045 +[2025-04-28 18:04:21,044][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 1.4955124855041504, cross_entropy: 1.4955124855041504 +[2025-04-28 18:04:21,764][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 2.106165647506714, cross_entropy: 2.106165647506714 +[2025-04-28 18:04:24,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 3.3997201919555664, cross_entropy: 3.3997201919555664 +[2025-04-28 18:04:25,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.4249980449676514, cross_entropy: 2.4249980449676514 +[2025-04-28 18:04:27,685][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.237989902496338, cross_entropy: 2.237989902496338 +[2025-04-28 18:04:28,400][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 2.501800537109375, cross_entropy: 2.501800537109375 +[2025-04-28 18:04:31,367][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.1880165338516235, cross_entropy: 1.1880165338516235 +[2025-04-28 18:04:32,088][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.13332200050354, cross_entropy: 2.13332200050354 +[2025-04-28 18:04:33,946][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 2.565680980682373, cross_entropy: 2.565680980682373 +[2025-04-28 18:04:34,661][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.7600154876708984, cross_entropy: 1.7600154876708984 +[2025-04-28 18:04:36,903][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 3.2051351070404053, cross_entropy: 3.2051351070404053 +[2025-04-28 18:04:37,663][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 3.063086986541748, cross_entropy: 3.063086986541748 +[2025-04-28 18:04:40,072][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 3.381147861480713, cross_entropy: 3.381147861480713 +[2025-04-28 18:04:40,862][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.3779159784317017, cross_entropy: 1.3779159784317017 +[2025-04-28 18:04:43,086][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.2512154579162598, cross_entropy: 3.2512154579162598 +[2025-04-28 18:04:43,851][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.4318952560424805, cross_entropy: 2.4318952560424805 +[2025-04-28 18:04:46,223][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 2.3463473320007324, cross_entropy: 2.3463473320007324 +[2025-04-28 18:04:47,098][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.445317268371582, cross_entropy: 1.445317268371582 +[2025-04-28 18:04:49,747][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 3.3330297470092773, cross_entropy: 3.3330297470092773 +[2025-04-28 18:04:50,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 2.1975975036621094, cross_entropy: 2.1975975036621094 +[2025-04-28 18:04:53,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 1.2496782541275024, cross_entropy: 1.2496782541275024 +[2025-04-28 18:04:54,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.3864721059799194, cross_entropy: 1.3864721059799194 +[2025-04-28 18:04:56,612][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 1.7668488025665283, cross_entropy: 1.7668488025665283 +[2025-04-28 18:04:57,328][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 2.8133959770202637, cross_entropy: 2.8133959770202637 +[2025-04-28 18:04:59,482][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.5057326555252075, cross_entropy: 1.5057326555252075 +[2025-04-28 18:05:00,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 2.973463535308838, cross_entropy: 2.973463535308838 +[2025-04-28 18:05:02,980][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.8143256902694702, cross_entropy: 1.8143256902694702 +[2025-04-28 18:05:03,694][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 2.144775152206421, cross_entropy: 2.144775152206421 +[2025-04-28 18:05:06,083][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.7395589351654053, cross_entropy: 1.7395589351654053 +[2025-04-28 18:05:06,797][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 2.8804492950439453, cross_entropy: 2.8804492950439453 +[2025-04-28 18:05:08,775][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 3.2722668647766113, cross_entropy: 3.2722668647766113 +[2025-04-28 18:05:09,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 2.659288167953491, cross_entropy: 2.659288167953491 +[2025-04-28 18:05:11,422][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 3.335808515548706, cross_entropy: 3.335808515548706 +[2025-04-28 18:05:12,170][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.919022798538208, cross_entropy: 2.919022798538208 +[2025-04-28 18:05:14,916][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.3786871433258057, cross_entropy: 1.3786871433258057 +[2025-04-28 18:05:15,631][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 1.6838555335998535, cross_entropy: 1.6838555335998535 +[2025-04-28 18:05:19,101][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 2.2841622829437256, cross_entropy: 2.2841622829437256 +[2025-04-28 18:05:19,809][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.730008125305176, cross_entropy: 2.730008125305176 +[2025-04-28 18:05:22,543][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.39919912815094, cross_entropy: 1.39919912815094 +[2025-04-28 18:05:23,263][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 1.605260968208313, cross_entropy: 1.605260968208313 +[2025-04-28 18:05:26,061][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 2.4533517360687256, cross_entropy: 2.4533517360687256 +[2025-04-28 18:05:26,741][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 2.15521502494812, cross_entropy: 2.15521502494812 +[2025-04-28 18:05:29,491][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 1.4939844608306885, cross_entropy: 1.4939844608306885 +[2025-04-28 18:05:30,175][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.8248682022094727, cross_entropy: 1.8248682022094727 +[2025-04-28 18:05:33,292][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.2313854694366455, cross_entropy: 2.2313854694366455 +[2025-04-28 18:05:33,974][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 3.1146037578582764, cross_entropy: 3.1146037578582764 +[2025-04-28 18:05:36,515][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 1.6244680881500244, cross_entropy: 1.6244680881500244 +[2025-04-28 18:05:37,196][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 2.9389595985412598, cross_entropy: 2.9389595985412598 +[2025-04-28 18:05:39,615][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 2.9172070026397705, cross_entropy: 2.9172070026397705 +[2025-04-28 18:05:40,329][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 2.247554302215576, cross_entropy: 2.247554302215576 +[2025-04-28 18:05:42,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 2.945190906524658, cross_entropy: 2.945190906524658 +[2025-04-28 18:05:43,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 2.7007880210876465, cross_entropy: 2.7007880210876465 +[2025-04-28 18:05:45,869][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 2.9957175254821777, cross_entropy: 2.9957175254821777 +[2025-04-28 18:05:46,580][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.352004289627075, cross_entropy: 2.352004289627075 +[2025-04-28 18:05:48,917][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.6942483186721802, cross_entropy: 1.6942483186721802 +[2025-04-28 18:05:49,597][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.7345376014709473, cross_entropy: 2.7345376014709473 +[2025-04-28 18:05:52,896][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 2.1674821376800537, cross_entropy: 2.1674821376800537 +[2025-04-28 18:05:53,595][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.485645294189453, cross_entropy: 2.485645294189453 +[2025-04-28 18:05:56,188][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.249563455581665, cross_entropy: 1.249563455581665 +[2025-04-28 18:05:56,899][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 2.3117666244506836, cross_entropy: 2.3117666244506836 +[2025-04-28 18:05:59,242][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.6203093528747559, cross_entropy: 1.6203093528747559 +[2025-04-28 18:05:59,964][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 2.91021728515625, cross_entropy: 2.91021728515625 +[2025-04-28 18:06:01,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.3469676971435547, cross_entropy: 1.3469676971435547 +[2025-04-28 18:06:02,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.4634737968444824, cross_entropy: 1.4634737968444824 +[2025-04-28 18:06:05,159][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 3.248121738433838, cross_entropy: 3.248121738433838 +[2025-04-28 18:06:05,883][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.1141849756240845, cross_entropy: 1.1141849756240845 +[2025-04-28 18:06:08,889][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 1.824426293373108, cross_entropy: 1.824426293373108 +[2025-04-28 18:06:09,607][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 3.779489040374756, cross_entropy: 3.779489040374756 +[2025-04-28 18:06:12,727][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.0092248916625977, cross_entropy: 2.0092248916625977 +[2025-04-28 18:06:13,412][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 1.9002833366394043, cross_entropy: 1.9002833366394043 +[2025-04-28 18:06:16,336][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 2.576780319213867, cross_entropy: 2.576780319213867 +[2025-04-28 18:06:17,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.8641200065612793, cross_entropy: 2.8641200065612793 +[2025-04-28 18:06:19,362][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 1.582552433013916, cross_entropy: 1.582552433013916 +[2025-04-28 18:06:20,071][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 2.4340455532073975, cross_entropy: 2.4340455532073975 +[2025-04-28 18:06:22,661][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.6945221424102783, cross_entropy: 1.6945221424102783 +[2025-04-28 18:06:23,384][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.4399968385696411, cross_entropy: 1.4399968385696411 +[2025-04-28 18:06:26,092][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 2.4181196689605713, cross_entropy: 2.4181196689605713 +[2025-04-28 18:06:26,810][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 1.569288969039917, cross_entropy: 1.569288969039917 +[2025-04-28 18:06:29,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 2.0513498783111572, cross_entropy: 2.0513498783111572 +[2025-04-28 18:06:30,363][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 2.9265575408935547, cross_entropy: 2.9265575408935547 +[2025-04-28 18:06:33,186][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.8824875354766846, cross_entropy: 2.8824875354766846 +[2025-04-28 18:06:33,914][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.5496420860290527, cross_entropy: 1.5496420860290527 +[2025-04-28 18:06:36,815][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 1.560890555381775, cross_entropy: 1.560890555381775 +[2025-04-28 18:06:37,535][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.075212001800537, cross_entropy: 1.075212001800537 +[2025-04-28 18:06:39,731][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 2.843930721282959, cross_entropy: 2.843930721282959 +[2025-04-28 18:06:40,446][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.429794192314148, cross_entropy: 1.429794192314148 +[2025-04-28 18:06:42,789][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.2143807411193848, cross_entropy: 2.2143807411193848 +[2025-04-28 18:06:43,487][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.78664493560791, cross_entropy: 2.78664493560791 +[2025-04-28 18:06:46,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 2.748411178588867, cross_entropy: 2.748411178588867 +[2025-04-28 18:06:46,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 3.1319613456726074, cross_entropy: 3.1319613456726074 +[2025-04-28 18:06:49,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.0621910095214844, cross_entropy: 2.0621910095214844 +[2025-04-28 18:06:50,255][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 0.9988587498664856, cross_entropy: 0.9988587498664856 +[2025-04-28 18:06:53,068][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.1248760223388672, cross_entropy: 1.1248760223388672 +[2025-04-28 18:06:53,784][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.3765448331832886, cross_entropy: 1.3765448331832886 +[2025-04-28 18:06:56,262][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 1.3926252126693726, cross_entropy: 1.3926252126693726 +[2025-04-28 18:06:56,944][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.061415433883667, cross_entropy: 2.061415433883667 +[2025-04-28 18:06:59,973][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.4465186595916748, cross_entropy: 1.4465186595916748 +[2025-04-28 18:07:00,659][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.3024437427520752, cross_entropy: 1.3024437427520752 +[2025-04-28 18:07:03,371][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 2.76086688041687, cross_entropy: 2.76086688041687 +[2025-04-28 18:07:04,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.3556084632873535, cross_entropy: 1.3556084632873535 +[2025-04-28 18:07:06,538][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.327823281288147, cross_entropy: 1.327823281288147 +[2025-04-28 18:07:07,217][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 1.9464547634124756, cross_entropy: 1.9464547634124756 +[2025-04-28 18:07:09,289][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.8970565795898438, cross_entropy: 1.8970565795898438 +[2025-04-28 18:07:09,900][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.9885833263397217, cross_entropy: 2.9885833263397217 +[2025-04-28 18:09:36,526][BaseTrainer][INFO] - [Epoch 7/10] (train) 2.134509563446045, cross_entropy: 2.134509563446045 +[2025-04-28 18:09:36,527][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.310387372970581, cross_entropy: 1.310387372970581 +[2025-04-28 18:09:37,422][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 18:09:37,934][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch7.pth. +[2025-04-28 18:09:38,753][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 18:09:42,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 3.2469024658203125, cross_entropy: 3.2469024658203125 +[2025-04-28 18:09:43,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.878844976425171, cross_entropy: 2.878844976425171 +[2025-04-28 18:09:45,808][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.246275782585144, cross_entropy: 1.246275782585144 +[2025-04-28 18:09:46,506][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.593310832977295, cross_entropy: 2.593310832977295 +[2025-04-28 18:09:49,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.4654040336608887, cross_entropy: 1.4654040336608887 +[2025-04-28 18:09:49,749][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 1.83295738697052, cross_entropy: 1.83295738697052 +[2025-04-28 18:09:51,776][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 2.0994160175323486, cross_entropy: 2.0994160175323486 +[2025-04-28 18:09:52,583][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 2.064023971557617, cross_entropy: 2.064023971557617 +[2025-04-28 18:09:54,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 1.9197890758514404, cross_entropy: 1.9197890758514404 +[2025-04-28 18:09:55,617][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.175229787826538, cross_entropy: 1.175229787826538 +[2025-04-28 18:09:57,885][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 3.423224925994873, cross_entropy: 3.423224925994873 +[2025-04-28 18:09:59,128][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 3.1166017055511475, cross_entropy: 3.1166017055511475 +[2025-04-28 18:10:00,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 2.515854835510254, cross_entropy: 2.515854835510254 +[2025-04-28 18:10:02,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 1.296709656715393, cross_entropy: 1.296709656715393 +[2025-04-28 18:10:04,176][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 3.1128339767456055, cross_entropy: 3.1128339767456055 +[2025-04-28 18:10:06,226][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 3.1311545372009277, cross_entropy: 3.1311545372009277 +[2025-04-28 18:10:07,039][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 3.0915865898132324, cross_entropy: 3.0915865898132324 +[2025-04-28 18:10:10,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 1.0642043352127075, cross_entropy: 1.0642043352127075 +[2025-04-28 18:10:11,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 1.186941385269165, cross_entropy: 1.186941385269165 +[2025-04-28 18:10:14,551][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.4580934047698975, cross_entropy: 1.4580934047698975 +[2025-04-28 18:10:15,233][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.4264607429504395, cross_entropy: 1.4264607429504395 +[2025-04-28 18:10:17,674][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 3.1667819023132324, cross_entropy: 3.1667819023132324 +[2025-04-28 18:10:18,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.3922659158706665, cross_entropy: 1.3922659158706665 +[2025-04-28 18:10:20,195][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.5785435438156128, cross_entropy: 1.5785435438156128 +[2025-04-28 18:10:20,961][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 1.599501132965088, cross_entropy: 1.599501132965088 +[2025-04-28 18:10:23,548][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 3.013749122619629, cross_entropy: 3.013749122619629 +[2025-04-28 18:10:24,279][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 3.417178153991699, cross_entropy: 3.417178153991699 +[2025-04-28 18:10:26,835][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.029008626937866, cross_entropy: 3.029008626937866 +[2025-04-28 18:10:28,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.0329207181930542, cross_entropy: 1.0329207181930542 +[2025-04-28 18:10:29,700][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 2.637875556945801, cross_entropy: 2.637875556945801 +[2025-04-28 18:10:31,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 1.6342204809188843, cross_entropy: 1.6342204809188843 +[2025-04-28 18:10:33,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 1.994774580001831, cross_entropy: 1.994774580001831 +[2025-04-28 18:10:34,672][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 2.6107239723205566, cross_entropy: 2.6107239723205566 +[2025-04-28 18:10:36,078][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 1.0403237342834473, cross_entropy: 1.0403237342834473 +[2025-04-28 18:10:37,816][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 1.6855554580688477, cross_entropy: 1.6855554580688477 +[2025-04-28 18:10:39,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.2803847789764404, cross_entropy: 1.2803847789764404 +[2025-04-28 18:10:41,653][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 1.2643357515335083, cross_entropy: 1.2643357515335083 +[2025-04-28 18:10:42,337][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 1.0890867710113525, cross_entropy: 1.0890867710113525 +[2025-04-28 18:10:45,257][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 2.672339916229248, cross_entropy: 2.672339916229248 +[2025-04-28 18:10:46,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 2.302462100982666, cross_entropy: 2.302462100982666 +[2025-04-28 18:10:48,522][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 1.462656021118164, cross_entropy: 1.462656021118164 +[2025-04-28 18:10:49,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 2.721815586090088, cross_entropy: 2.721815586090088 +[2025-04-28 18:10:52,109][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.7000229358673096, cross_entropy: 1.7000229358673096 +[2025-04-28 18:10:52,822][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.4411180019378662, cross_entropy: 1.4411180019378662 +[2025-04-28 18:10:55,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 3.245260715484619, cross_entropy: 3.245260715484619 +[2025-04-28 18:10:56,201][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.6681904792785645, cross_entropy: 2.6681904792785645 +[2025-04-28 18:10:59,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.9174152612686157, cross_entropy: 1.9174152612686157 +[2025-04-28 18:10:59,846][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 1.170409917831421, cross_entropy: 1.170409917831421 +[2025-04-28 18:11:03,537][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 1.0619381666183472, cross_entropy: 1.0619381666183472 +[2025-04-28 18:11:04,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.9013733863830566, cross_entropy: 2.9013733863830566 +[2025-04-28 18:11:07,142][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 1.976098656654358, cross_entropy: 1.976098656654358 +[2025-04-28 18:11:07,823][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 3.2682156562805176, cross_entropy: 3.2682156562805176 +[2025-04-28 18:11:10,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 1.7405047416687012, cross_entropy: 1.7405047416687012 +[2025-04-28 18:11:10,688][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 2.559197425842285, cross_entropy: 2.559197425842285 +[2025-04-28 18:11:13,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 3.058131217956543, cross_entropy: 3.058131217956543 +[2025-04-28 18:11:14,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 1.2383042573928833, cross_entropy: 1.2383042573928833 +[2025-04-28 18:11:17,320][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 1.8355132341384888, cross_entropy: 1.8355132341384888 +[2025-04-28 18:11:18,030][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 2.9207746982574463, cross_entropy: 2.9207746982574463 +[2025-04-28 18:11:20,164][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 3.226372241973877, cross_entropy: 3.226372241973877 +[2025-04-28 18:11:20,871][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 2.9489026069641113, cross_entropy: 2.9489026069641113 +[2025-04-28 18:11:22,867][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 2.363615036010742, cross_entropy: 2.363615036010742 +[2025-04-28 18:11:23,582][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.403470754623413, cross_entropy: 1.403470754623413 +[2025-04-28 18:11:25,850][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.098123073577881, cross_entropy: 2.098123073577881 +[2025-04-28 18:11:26,531][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 3.100302219390869, cross_entropy: 3.100302219390869 +[2025-04-28 18:11:29,289][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.626957893371582, cross_entropy: 2.626957893371582 +[2025-04-28 18:11:29,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 3.158846855163574, cross_entropy: 3.158846855163574 +[2025-04-28 18:11:32,504][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 1.0943125486373901, cross_entropy: 1.0943125486373901 +[2025-04-28 18:11:33,208][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.227785348892212, cross_entropy: 1.227785348892212 +[2025-04-28 18:11:35,233][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 2.515359878540039, cross_entropy: 2.515359878540039 +[2025-04-28 18:11:35,944][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.2104573249816895, cross_entropy: 2.2104573249816895 +[2025-04-28 18:11:38,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.2394495010375977, cross_entropy: 1.2394495010375977 +[2025-04-28 18:11:39,020][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 1.406715989112854, cross_entropy: 1.406715989112854 +[2025-04-28 18:11:41,590][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.0268089771270752, cross_entropy: 1.0268089771270752 +[2025-04-28 18:11:42,312][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.1810650825500488, cross_entropy: 1.1810650825500488 +[2025-04-28 18:11:44,047][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.6116251945495605, cross_entropy: 1.6116251945495605 +[2025-04-28 18:11:44,761][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.748049736022949, cross_entropy: 2.748049736022949 +[2025-04-28 18:11:47,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.7031285762786865, cross_entropy: 1.7031285762786865 +[2025-04-28 18:11:48,114][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.271341323852539, cross_entropy: 1.271341323852539 +[2025-04-28 18:11:49,925][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 1.3206281661987305, cross_entropy: 1.3206281661987305 +[2025-04-28 18:11:50,640][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.296297788619995, cross_entropy: 2.296297788619995 +[2025-04-28 18:11:53,020][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 2.028003692626953, cross_entropy: 2.028003692626953 +[2025-04-28 18:11:53,733][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.743532657623291, cross_entropy: 1.743532657623291 +[2025-04-28 18:11:56,152][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 0.9743105173110962, cross_entropy: 0.9743105173110962 +[2025-04-28 18:11:56,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.367708444595337, cross_entropy: 1.367708444595337 +[2025-04-28 18:11:59,810][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.700299620628357, cross_entropy: 1.700299620628357 +[2025-04-28 18:12:00,517][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 2.5471675395965576, cross_entropy: 2.5471675395965576 +[2025-04-28 18:12:03,493][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.240635871887207, cross_entropy: 2.240635871887207 +[2025-04-28 18:12:04,200][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 3.1085205078125, cross_entropy: 3.1085205078125 +[2025-04-28 18:12:06,088][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 2.855557680130005, cross_entropy: 2.855557680130005 +[2025-04-28 18:12:06,806][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 2.834299087524414, cross_entropy: 2.834299087524414 +[2025-04-28 18:12:08,992][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 1.0213769674301147, cross_entropy: 1.0213769674301147 +[2025-04-28 18:12:09,687][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 3.2287468910217285, cross_entropy: 3.2287468910217285 +[2025-04-28 18:12:11,810][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 3.0315980911254883, cross_entropy: 3.0315980911254883 +[2025-04-28 18:12:12,516][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.316133975982666, cross_entropy: 2.316133975982666 +[2025-04-28 18:12:15,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.614231824874878, cross_entropy: 1.614231824874878 +[2025-04-28 18:12:16,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.8666410446166992, cross_entropy: 1.8666410446166992 +[2025-04-28 18:12:20,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.224660873413086, cross_entropy: 2.224660873413086 +[2025-04-28 18:12:21,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 2.42207407951355, cross_entropy: 2.42207407951355 +[2025-04-28 18:12:23,592][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.37165105342865, cross_entropy: 1.37165105342865 +[2025-04-28 18:12:24,299][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 3.154167652130127, cross_entropy: 3.154167652130127 +[2025-04-28 18:12:27,127][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.2120323181152344, cross_entropy: 2.2120323181152344 +[2025-04-28 18:12:27,836][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 2.943903684616089, cross_entropy: 2.943903684616089 +[2025-04-28 18:12:29,543][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 1.6424397230148315, cross_entropy: 1.6424397230148315 +[2025-04-28 18:12:30,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 0.8542276620864868, cross_entropy: 0.8542276620864868 +[2025-04-28 18:12:32,706][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 1.725175142288208, cross_entropy: 1.725175142288208 +[2025-04-28 18:12:33,423][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 1.295281171798706, cross_entropy: 1.295281171798706 +[2025-04-28 18:12:35,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 0.8942095637321472, cross_entropy: 0.8942095637321472 +[2025-04-28 18:12:36,272][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 2.8223390579223633, cross_entropy: 2.8223390579223633 +[2025-04-28 18:12:38,472][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.6678310632705688, cross_entropy: 1.6678310632705688 +[2025-04-28 18:12:39,187][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 1.3743855953216553, cross_entropy: 1.3743855953216553 +[2025-04-28 18:12:40,993][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 1.8544750213623047, cross_entropy: 1.8544750213623047 +[2025-04-28 18:12:41,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.2554404735565186, cross_entropy: 1.2554404735565186 +[2025-04-28 18:12:44,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 1.600262999534607, cross_entropy: 1.600262999534607 +[2025-04-28 18:12:45,083][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 2.911743640899658, cross_entropy: 2.911743640899658 +[2025-04-28 18:12:47,503][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.908945322036743, cross_entropy: 2.908945322036743 +[2025-04-28 18:12:48,413][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 3.022434949874878, cross_entropy: 3.022434949874878 +[2025-04-28 18:12:50,839][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 1.8812440633773804, cross_entropy: 1.8812440633773804 +[2025-04-28 18:12:51,728][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 3.0048294067382812, cross_entropy: 3.0048294067382812 +[2025-04-28 18:12:53,586][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 1.4586595296859741, cross_entropy: 1.4586595296859741 +[2025-04-28 18:12:54,781][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 1.405387043952942, cross_entropy: 1.405387043952942 +[2025-04-28 18:12:56,478][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 1.3569414615631104, cross_entropy: 1.3569414615631104 +[2025-04-28 18:12:57,636][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 1.8027745485305786, cross_entropy: 1.8027745485305786 +[2025-04-28 18:12:59,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.7186567783355713, cross_entropy: 2.7186567783355713 +[2025-04-28 18:13:00,286][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 3.1123156547546387, cross_entropy: 3.1123156547546387 +[2025-04-28 18:13:03,284][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 3.2444329261779785, cross_entropy: 3.2444329261779785 +[2025-04-28 18:13:04,001][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 2.9835851192474365, cross_entropy: 2.9835851192474365 +[2025-04-28 18:13:07,578][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 2.2927870750427246, cross_entropy: 2.2927870750427246 +[2025-04-28 18:13:08,287][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.8764326572418213, cross_entropy: 1.8764326572418213 +[2025-04-28 18:13:10,882][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 3.083695411682129, cross_entropy: 3.083695411682129 +[2025-04-28 18:13:11,563][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 2.7669172286987305, cross_entropy: 2.7669172286987305 +[2025-04-28 18:13:13,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 1.7061097621917725, cross_entropy: 1.7061097621917725 +[2025-04-28 18:13:14,224][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 1.906087875366211, cross_entropy: 1.906087875366211 +[2025-04-28 18:13:16,935][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 1.6578259468078613, cross_entropy: 1.6578259468078613 +[2025-04-28 18:13:17,618][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 3.079821825027466, cross_entropy: 3.079821825027466 +[2025-04-28 18:13:20,403][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 1.6748191118240356, cross_entropy: 1.6748191118240356 +[2025-04-28 18:13:21,117][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 1.766338586807251, cross_entropy: 1.766338586807251 +[2025-04-28 18:13:23,928][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 2.3172454833984375, cross_entropy: 2.3172454833984375 +[2025-04-28 18:13:24,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 3.2968382835388184, cross_entropy: 3.2968382835388184 +[2025-04-28 18:13:26,838][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 1.5653218030929565, cross_entropy: 1.5653218030929565 +[2025-04-28 18:13:27,520][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 1.3949991464614868, cross_entropy: 1.3949991464614868 +[2025-04-28 18:13:29,921][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 1.4714022874832153, cross_entropy: 1.4714022874832153 +[2025-04-28 18:13:30,634][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 1.2275986671447754, cross_entropy: 1.2275986671447754 +[2025-04-28 18:13:32,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.4424753189086914, cross_entropy: 1.4424753189086914 +[2025-04-28 18:13:33,591][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 1.5296030044555664, cross_entropy: 1.5296030044555664 +[2025-04-28 18:13:35,580][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 1.6148903369903564, cross_entropy: 1.6148903369903564 +[2025-04-28 18:13:36,293][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.298828601837158, cross_entropy: 2.298828601837158 +[2025-04-28 18:13:38,959][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 2.2637948989868164, cross_entropy: 2.2637948989868164 +[2025-04-28 18:13:39,641][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 3.0454111099243164, cross_entropy: 3.0454111099243164 +[2025-04-28 18:13:41,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 2.8171310424804688, cross_entropy: 2.8171310424804688 +[2025-04-28 18:13:42,376][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 2.5102736949920654, cross_entropy: 2.5102736949920654 +[2025-04-28 18:13:44,597][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.2653510570526123, cross_entropy: 2.2653510570526123 +[2025-04-28 18:13:45,311][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 0.9483013153076172, cross_entropy: 0.9483013153076172 +[2025-04-28 18:13:47,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.115953803062439, cross_entropy: 1.115953803062439 +[2025-04-28 18:13:48,178][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 2.914651393890381, cross_entropy: 2.914651393890381 +[2025-04-28 18:13:50,246][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.173607587814331, cross_entropy: 1.173607587814331 +[2025-04-28 18:13:50,961][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.9299850463867188, cross_entropy: 1.9299850463867188 +[2025-04-28 18:13:53,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 2.393859386444092, cross_entropy: 2.393859386444092 +[2025-04-28 18:13:53,911][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 2.065189838409424, cross_entropy: 2.065189838409424 +[2025-04-28 18:13:56,305][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.901076316833496, cross_entropy: 2.901076316833496 +[2025-04-28 18:13:57,018][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 1.0716192722320557, cross_entropy: 1.0716192722320557 +[2025-04-28 18:13:59,688][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.6531404256820679, cross_entropy: 1.6531404256820679 +[2025-04-28 18:14:00,400][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 1.2631049156188965, cross_entropy: 1.2631049156188965 +[2025-04-28 18:14:02,330][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 1.1448099613189697, cross_entropy: 1.1448099613189697 +[2025-04-28 18:14:03,050][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 3.0358588695526123, cross_entropy: 3.0358588695526123 +[2025-04-28 18:14:05,701][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 1.0878064632415771, cross_entropy: 1.0878064632415771 +[2025-04-28 18:14:06,418][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.222873568534851, cross_entropy: 1.222873568534851 +[2025-04-28 18:14:08,751][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.2954366207122803, cross_entropy: 2.2954366207122803 +[2025-04-28 18:14:09,464][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 1.0287138223648071, cross_entropy: 1.0287138223648071 +[2025-04-28 18:14:11,813][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.187295436859131, cross_entropy: 2.187295436859131 +[2025-04-28 18:14:12,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 2.041365146636963, cross_entropy: 2.041365146636963 +[2025-04-28 18:14:14,475][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.5483288764953613, cross_entropy: 1.5483288764953613 +[2025-04-28 18:14:15,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.4895033836364746, cross_entropy: 1.4895033836364746 +[2025-04-28 18:14:17,430][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.5348544120788574, cross_entropy: 2.5348544120788574 +[2025-04-28 18:14:18,124][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.219433069229126, cross_entropy: 1.219433069229126 +[2025-04-28 18:14:20,464][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 1.110368251800537, cross_entropy: 1.110368251800537 +[2025-04-28 18:14:21,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 0.9765453934669495, cross_entropy: 0.9765453934669495 +[2025-04-28 18:14:23,907][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.2181111574172974, cross_entropy: 1.2181111574172974 +[2025-04-28 18:14:24,626][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 1.3024213314056396, cross_entropy: 1.3024213314056396 +[2025-04-28 18:14:27,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.1322152614593506, cross_entropy: 1.1322152614593506 +[2025-04-28 18:14:28,039][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 1.4303689002990723, cross_entropy: 1.4303689002990723 +[2025-04-28 18:14:30,224][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.265005588531494, cross_entropy: 2.265005588531494 +[2025-04-28 18:14:30,992][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 2.9352450370788574, cross_entropy: 2.9352450370788574 +[2025-04-28 18:14:33,335][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 2.7911317348480225, cross_entropy: 2.7911317348480225 +[2025-04-28 18:14:34,055][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 2.9551429748535156, cross_entropy: 2.9551429748535156 +[2025-04-28 18:14:36,668][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.251034736633301, cross_entropy: 2.251034736633301 +[2025-04-28 18:14:37,379][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 1.584455132484436, cross_entropy: 1.584455132484436 +[2025-04-28 18:14:39,551][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 3.0259196758270264, cross_entropy: 3.0259196758270264 +[2025-04-28 18:14:40,258][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 1.554081678390503, cross_entropy: 1.554081678390503 +[2025-04-28 18:14:42,726][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 1.4648317098617554, cross_entropy: 1.4648317098617554 +[2025-04-28 18:14:43,436][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 3.311768054962158, cross_entropy: 3.311768054962158 +[2025-04-28 18:14:45,393][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.577216148376465, cross_entropy: 2.577216148376465 +[2025-04-28 18:14:46,108][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.7271605730056763, cross_entropy: 1.7271605730056763 +[2025-04-28 18:14:48,205][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 3.229262351989746, cross_entropy: 3.229262351989746 +[2025-04-28 18:14:48,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.5165915489196777, cross_entropy: 1.5165915489196777 +[2025-04-28 18:14:51,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 2.7139892578125, cross_entropy: 2.7139892578125 +[2025-04-28 18:14:52,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 0.8726558685302734, cross_entropy: 0.8726558685302734 +[2025-04-28 18:14:54,408][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 1.2166252136230469, cross_entropy: 1.2166252136230469 +[2025-04-28 18:14:55,117][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 3.004385471343994, cross_entropy: 3.004385471343994 +[2025-04-28 18:14:57,466][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 3.098299026489258, cross_entropy: 3.098299026489258 +[2025-04-28 18:14:58,177][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 3.1806087493896484, cross_entropy: 3.1806087493896484 +[2025-04-28 18:15:02,223][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.1837817430496216, cross_entropy: 1.1837817430496216 +[2025-04-28 18:15:02,937][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 2.722405433654785, cross_entropy: 2.722405433654785 +[2025-04-28 18:15:04,848][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.19333815574646, cross_entropy: 2.19333815574646 +[2025-04-28 18:15:05,562][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.760890483856201, cross_entropy: 2.760890483856201 +[2025-04-28 18:15:07,867][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 3.2589011192321777, cross_entropy: 3.2589011192321777 +[2025-04-28 18:15:08,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 3.1018857955932617, cross_entropy: 3.1018857955932617 +[2025-04-28 18:15:10,710][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 2.438724994659424, cross_entropy: 2.438724994659424 +[2025-04-28 18:15:11,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 2.942544460296631, cross_entropy: 2.942544460296631 +[2025-04-28 18:15:13,384][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 1.4865596294403076, cross_entropy: 1.4865596294403076 +[2025-04-28 18:15:14,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 2.825356960296631, cross_entropy: 2.825356960296631 +[2025-04-28 18:15:16,671][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 1.2590763568878174, cross_entropy: 1.2590763568878174 +[2025-04-28 18:15:17,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.6794705390930176, cross_entropy: 2.6794705390930176 +[2025-04-28 18:15:19,950][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.6263519525527954, cross_entropy: 1.6263519525527954 +[2025-04-28 18:15:20,667][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 1.279664158821106, cross_entropy: 1.279664158821106 +[2025-04-28 18:15:22,769][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 3.036623954772949, cross_entropy: 3.036623954772949 +[2025-04-28 18:15:23,481][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 1.50945246219635, cross_entropy: 1.50945246219635 +[2025-04-28 18:15:26,334][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 2.898746967315674, cross_entropy: 2.898746967315674 +[2025-04-28 18:15:27,051][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 2.719355583190918, cross_entropy: 2.719355583190918 +[2025-04-28 18:15:29,876][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 3.082720994949341, cross_entropy: 3.082720994949341 +[2025-04-28 18:15:30,589][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.8786492347717285, cross_entropy: 2.8786492347717285 +[2025-04-28 18:15:33,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 1.4401482343673706, cross_entropy: 1.4401482343673706 +[2025-04-28 18:15:33,744][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 3.2433559894561768, cross_entropy: 3.2433559894561768 +[2025-04-28 18:15:35,854][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 1.2409809827804565, cross_entropy: 1.2409809827804565 +[2025-04-28 18:15:36,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 1.0919246673583984, cross_entropy: 1.0919246673583984 +[2025-04-28 18:15:39,192][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.200153112411499, cross_entropy: 1.200153112411499 +[2025-04-28 18:15:39,909][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 1.1099380254745483, cross_entropy: 1.1099380254745483 +[2025-04-28 18:15:42,253][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 2.0858964920043945, cross_entropy: 2.0858964920043945 +[2025-04-28 18:15:42,971][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.3119761943817139, cross_entropy: 1.3119761943817139 +[2025-04-28 18:15:45,986][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 3.0322656631469727, cross_entropy: 3.0322656631469727 +[2025-04-28 18:15:46,691][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 3.121356248855591, cross_entropy: 3.121356248855591 +[2025-04-28 18:15:49,818][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 2.6525278091430664, cross_entropy: 2.6525278091430664 +[2025-04-28 18:15:50,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.6007696390151978, cross_entropy: 1.6007696390151978 +[2025-04-28 18:15:52,932][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 2.915348768234253, cross_entropy: 2.915348768234253 +[2025-04-28 18:15:53,644][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 3.1120455265045166, cross_entropy: 3.1120455265045166 +[2025-04-28 18:15:56,497][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.6280512809753418, cross_entropy: 1.6280512809753418 +[2025-04-28 18:15:57,209][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 2.8663320541381836, cross_entropy: 2.8663320541381836 +[2025-04-28 18:15:59,281][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.5928845405578613, cross_entropy: 1.5928845405578613 +[2025-04-28 18:15:59,962][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 3.0759716033935547, cross_entropy: 3.0759716033935547 +[2025-04-28 18:16:02,641][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 2.3662843704223633, cross_entropy: 2.3662843704223633 +[2025-04-28 18:16:03,357][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 2.564427137374878, cross_entropy: 2.564427137374878 +[2025-04-28 18:16:05,668][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 3.0810961723327637, cross_entropy: 3.0810961723327637 +[2025-04-28 18:16:06,381][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 3.0035853385925293, cross_entropy: 3.0035853385925293 +[2025-04-28 18:16:08,317][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 2.4649815559387207, cross_entropy: 2.4649815559387207 +[2025-04-28 18:16:09,029][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 1.2020971775054932, cross_entropy: 1.2020971775054932 +[2025-04-28 18:16:11,431][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 1.210503101348877, cross_entropy: 1.210503101348877 +[2025-04-28 18:16:12,173][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 3.073659896850586, cross_entropy: 3.073659896850586 +[2025-04-28 18:16:14,532][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 2.426039695739746, cross_entropy: 2.426039695739746 +[2025-04-28 18:16:15,213][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.3083633184432983, cross_entropy: 1.3083633184432983 +[2025-04-28 18:16:17,869][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 1.959057331085205, cross_entropy: 1.959057331085205 +[2025-04-28 18:16:18,584][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 1.346744418144226, cross_entropy: 1.346744418144226 +[2025-04-28 18:16:20,771][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 3.1927924156188965, cross_entropy: 3.1927924156188965 +[2025-04-28 18:16:21,482][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 3.0330605506896973, cross_entropy: 3.0330605506896973 +[2025-04-28 18:16:23,504][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.3143625259399414, cross_entropy: 1.3143625259399414 +[2025-04-28 18:16:24,222][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 1.6884015798568726, cross_entropy: 1.6884015798568726 +[2025-04-28 18:16:26,614][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 1.5659635066986084, cross_entropy: 1.5659635066986084 +[2025-04-28 18:16:27,385][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 3.216981887817383, cross_entropy: 3.216981887817383 +[2025-04-28 18:16:29,026][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 1.6384942531585693, cross_entropy: 1.6384942531585693 +[2025-04-28 18:16:30,880][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.084470272064209, cross_entropy: 1.084470272064209 +[2025-04-28 18:16:32,065][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.5007109642028809, cross_entropy: 1.5007109642028809 +[2025-04-28 18:16:33,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 3.0316951274871826, cross_entropy: 3.0316951274871826 +[2025-04-28 18:16:35,239][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 1.652486801147461, cross_entropy: 1.652486801147461 +[2025-04-28 18:16:37,228][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 3.227891206741333, cross_entropy: 3.227891206741333 +[2025-04-28 18:16:39,150][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 1.9408133029937744, cross_entropy: 1.9408133029937744 +[2025-04-28 18:16:40,544][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 1.3206006288528442, cross_entropy: 1.3206006288528442 +[2025-04-28 18:16:41,915][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.5183730125427246, cross_entropy: 2.5183730125427246 +[2025-04-28 18:16:43,188][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 1.5811011791229248, cross_entropy: 1.5811011791229248 +[2025-04-28 18:16:46,388][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.854334831237793, cross_entropy: 1.854334831237793 +[2025-04-28 18:16:47,092][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 3.0736565589904785, cross_entropy: 3.0736565589904785 +[2025-04-28 18:16:49,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 1.461565375328064, cross_entropy: 1.461565375328064 +[2025-04-28 18:16:50,495][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 3.336589813232422, cross_entropy: 3.336589813232422 +[2025-04-28 18:16:53,098][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 3.110731840133667, cross_entropy: 3.110731840133667 +[2025-04-28 18:16:53,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 1.1389355659484863, cross_entropy: 1.1389355659484863 +[2025-04-28 18:16:55,658][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 1.7026419639587402, cross_entropy: 1.7026419639587402 +[2025-04-28 18:16:56,370][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.091801166534424, cross_entropy: 2.091801166534424 +[2025-04-28 18:16:58,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.90299129486084, cross_entropy: 2.90299129486084 +[2025-04-28 18:16:59,141][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.4689888954162598, cross_entropy: 1.4689888954162598 +[2025-04-28 18:17:00,967][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.1258379220962524, cross_entropy: 1.1258379220962524 +[2025-04-28 18:17:01,727][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 2.075392961502075, cross_entropy: 2.075392961502075 +[2025-04-28 18:17:03,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 2.971217155456543, cross_entropy: 2.971217155456543 +[2025-04-28 18:17:04,671][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 2.4745378494262695, cross_entropy: 2.4745378494262695 +[2025-04-28 18:17:07,251][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 2.8134512901306152, cross_entropy: 2.8134512901306152 +[2025-04-28 18:17:07,977][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.408163547515869, cross_entropy: 2.408163547515869 +[2025-04-28 18:17:10,331][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 1.076596975326538, cross_entropy: 1.076596975326538 +[2025-04-28 18:17:11,109][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 3.0503945350646973, cross_entropy: 3.0503945350646973 +[2025-04-28 18:17:13,774][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 2.698493480682373, cross_entropy: 2.698493480682373 +[2025-04-28 18:17:14,452][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.033062219619751, cross_entropy: 2.033062219619751 +[2025-04-28 18:17:17,166][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 2.885404586791992, cross_entropy: 2.885404586791992 +[2025-04-28 18:17:17,870][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.7935817241668701, cross_entropy: 1.7935817241668701 +[2025-04-28 18:17:20,421][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 2.8881607055664062, cross_entropy: 2.8881607055664062 +[2025-04-28 18:17:21,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.6354554891586304, cross_entropy: 1.6354554891586304 +[2025-04-28 18:17:23,733][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.49552583694458, cross_entropy: 1.49552583694458 +[2025-04-28 18:17:24,422][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 2.1235342025756836, cross_entropy: 2.1235342025756836 +[2025-04-28 18:17:26,731][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.5483441352844238, cross_entropy: 1.5483441352844238 +[2025-04-28 18:17:27,447][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 2.0093069076538086, cross_entropy: 2.0093069076538086 +[2025-04-28 18:17:29,538][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.153379201889038, cross_entropy: 1.153379201889038 +[2025-04-28 18:17:30,248][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 2.1909360885620117, cross_entropy: 2.1909360885620117 +[2025-04-28 18:17:32,027][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.2341201305389404, cross_entropy: 2.2341201305389404 +[2025-04-28 18:17:32,735][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.3354523181915283, cross_entropy: 2.3354523181915283 +[2025-04-28 18:17:34,531][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.6073780059814453, cross_entropy: 1.6073780059814453 +[2025-04-28 18:17:35,243][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.337998867034912, cross_entropy: 2.337998867034912 +[2025-04-28 18:17:37,558][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 1.8006818294525146, cross_entropy: 1.8006818294525146 +[2025-04-28 18:17:38,240][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.306992769241333, cross_entropy: 1.306992769241333 +[2025-04-28 18:17:40,589][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 2.2907567024230957, cross_entropy: 2.2907567024230957 +[2025-04-28 18:17:41,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 1.5865113735198975, cross_entropy: 1.5865113735198975 +[2025-04-28 18:17:43,783][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 3.2692339420318604, cross_entropy: 3.2692339420318604 +[2025-04-28 18:17:44,499][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 1.8692889213562012, cross_entropy: 1.8692889213562012 +[2025-04-28 18:17:46,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 0.9261270761489868, cross_entropy: 0.9261270761489868 +[2025-04-28 18:17:47,680][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.0947566032409668, cross_entropy: 1.0947566032409668 +[2025-04-28 18:17:50,007][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 0.9517570734024048, cross_entropy: 0.9517570734024048 +[2025-04-28 18:17:50,720][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 2.864556312561035, cross_entropy: 2.864556312561035 +[2025-04-28 18:17:52,477][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 1.4534826278686523, cross_entropy: 1.4534826278686523 +[2025-04-28 18:17:53,742][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 2.5607247352600098, cross_entropy: 2.5607247352600098 +[2025-04-28 18:17:55,984][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 3.0479259490966797, cross_entropy: 3.0479259490966797 +[2025-04-28 18:17:57,053][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 2.0694937705993652, cross_entropy: 2.0694937705993652 +[2025-04-28 18:17:59,246][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 1.015078067779541, cross_entropy: 1.015078067779541 +[2025-04-28 18:18:00,302][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.1908884048461914, cross_entropy: 1.1908884048461914 +[2025-04-28 18:18:02,438][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 2.408428430557251, cross_entropy: 2.408428430557251 +[2025-04-28 18:18:03,417][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 1.6045314073562622, cross_entropy: 1.6045314073562622 +[2025-04-28 18:18:05,441][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.8588993549346924, cross_entropy: 1.8588993549346924 +[2025-04-28 18:18:06,191][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.701840877532959, cross_entropy: 1.701840877532959 +[2025-04-28 18:18:09,138][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 1.8920388221740723, cross_entropy: 1.8920388221740723 +[2025-04-28 18:18:09,820][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 3.351567506790161, cross_entropy: 3.351567506790161 +[2025-04-28 18:18:13,461][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.4998421669006348, cross_entropy: 1.4998421669006348 +[2025-04-28 18:18:14,179][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 2.136404514312744, cross_entropy: 2.136404514312744 +[2025-04-28 18:18:16,840][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.4191714525222778, cross_entropy: 1.4191714525222778 +[2025-04-28 18:18:17,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 1.3947467803955078, cross_entropy: 1.3947467803955078 +[2025-04-28 18:18:20,875][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 1.6658109426498413, cross_entropy: 1.6658109426498413 +[2025-04-28 18:18:21,585][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.5338940620422363, cross_entropy: 1.5338940620422363 +[2025-04-28 18:18:23,575][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.1149983406066895, cross_entropy: 1.1149983406066895 +[2025-04-28 18:18:24,282][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 3.0702037811279297, cross_entropy: 3.0702037811279297 +[2025-04-28 18:18:26,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 2.9516851902008057, cross_entropy: 2.9516851902008057 +[2025-04-28 18:18:26,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 2.5804178714752197, cross_entropy: 2.5804178714752197 +[2025-04-28 18:18:29,521][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.3800565004348755, cross_entropy: 1.3800565004348755 +[2025-04-28 18:18:30,229][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 2.202054738998413, cross_entropy: 2.202054738998413 +[2025-04-28 18:18:32,494][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 1.365074634552002, cross_entropy: 1.365074634552002 +[2025-04-28 18:18:33,205][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 2.4993200302124023, cross_entropy: 2.4993200302124023 +[2025-04-28 18:18:35,898][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 3.236921787261963, cross_entropy: 3.236921787261963 +[2025-04-28 18:18:36,606][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.125058650970459, cross_entropy: 1.125058650970459 +[2025-04-28 18:18:39,189][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.3216376304626465, cross_entropy: 1.3216376304626465 +[2025-04-28 18:18:39,877][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 1.0925445556640625, cross_entropy: 1.0925445556640625 +[2025-04-28 18:18:42,389][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 0.9643954038619995, cross_entropy: 0.9643954038619995 +[2025-04-28 18:18:43,103][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.967461109161377, cross_entropy: 2.967461109161377 +[2025-04-28 18:18:45,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.715797185897827, cross_entropy: 2.715797185897827 +[2025-04-28 18:18:46,657][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 2.5135011672973633, cross_entropy: 2.5135011672973633 +[2025-04-28 18:18:48,982][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.534440279006958, cross_entropy: 1.534440279006958 +[2025-04-28 18:18:49,689][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 3.0584254264831543, cross_entropy: 3.0584254264831543 +[2025-04-28 18:18:51,838][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 1.5501821041107178, cross_entropy: 1.5501821041107178 +[2025-04-28 18:18:53,006][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 3.059666633605957, cross_entropy: 3.059666633605957 +[2025-04-28 18:18:55,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.8331708908081055, cross_entropy: 2.8331708908081055 +[2025-04-28 18:18:55,987][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 0.8682544231414795, cross_entropy: 0.8682544231414795 +[2025-04-28 18:18:57,507][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 2.7919750213623047, cross_entropy: 2.7919750213623047 +[2025-04-28 18:18:59,183][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 2.0967607498168945, cross_entropy: 2.0967607498168945 +[2025-04-28 18:19:01,252][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 3.0176937580108643, cross_entropy: 3.0176937580108643 +[2025-04-28 18:19:02,038][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 1.783427119255066, cross_entropy: 1.783427119255066 +[2025-04-28 18:19:04,032][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 1.3130571842193604, cross_entropy: 1.3130571842193604 +[2025-04-28 18:19:05,300][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 2.4192371368408203, cross_entropy: 2.4192371368408203 +[2025-04-28 18:21:24,324][BaseTrainer][INFO] - [Epoch 8/10] (train) 2.083332061767578, cross_entropy: 2.083332061767578 +[2025-04-28 18:21:24,324][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.2257322072982788, cross_entropy: 1.2257322072982788 +[2025-04-28 18:21:25,195][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 18:21:25,732][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch8.pth. +[2025-04-28 18:21:26,524][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 18:21:30,858][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 2.0637853145599365, cross_entropy: 2.0637853145599365 +[2025-04-28 18:21:31,561][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.259416937828064, cross_entropy: 1.259416937828064 +[2025-04-28 18:21:34,434][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 1.8422091007232666, cross_entropy: 1.8422091007232666 +[2025-04-28 18:21:35,112][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 2.8611552715301514, cross_entropy: 2.8611552715301514 +[2025-04-28 18:21:37,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 0.9835528135299683, cross_entropy: 0.9835528135299683 +[2025-04-28 18:21:38,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.2282673120498657, cross_entropy: 1.2282673120498657 +[2025-04-28 18:21:41,066][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.765279769897461, cross_entropy: 2.765279769897461 +[2025-04-28 18:21:41,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 1.2176117897033691, cross_entropy: 1.2176117897033691 +[2025-04-28 18:21:43,965][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.3714609146118164, cross_entropy: 2.3714609146118164 +[2025-04-28 18:21:44,665][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 0.915932297706604, cross_entropy: 0.915932297706604 +[2025-04-28 18:21:46,907][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.2263541221618652, cross_entropy: 1.2263541221618652 +[2025-04-28 18:21:47,585][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 2.064664363861084, cross_entropy: 2.064664363861084 +[2025-04-28 18:21:49,921][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.245537757873535, cross_entropy: 2.245537757873535 +[2025-04-28 18:21:50,616][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 1.537510633468628, cross_entropy: 1.537510633468628 +[2025-04-28 18:21:52,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.182969570159912, cross_entropy: 2.182969570159912 +[2025-04-28 18:21:53,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 3.0111730098724365, cross_entropy: 3.0111730098724365 +[2025-04-28 18:21:56,687][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 1.2730343341827393, cross_entropy: 1.2730343341827393 +[2025-04-28 18:21:57,366][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.30025315284729, cross_entropy: 1.30025315284729 +[2025-04-28 18:22:00,234][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.6858006715774536, cross_entropy: 1.6858006715774536 +[2025-04-28 18:22:00,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.1356682777404785, cross_entropy: 1.1356682777404785 +[2025-04-28 18:22:03,227][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.0178368091583252, cross_entropy: 1.0178368091583252 +[2025-04-28 18:22:03,929][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 2.968475341796875, cross_entropy: 2.968475341796875 +[2025-04-28 18:22:06,795][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 1.47734797000885, cross_entropy: 1.47734797000885 +[2025-04-28 18:22:07,474][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 1.1588689088821411, cross_entropy: 1.1588689088821411 +[2025-04-28 18:22:09,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 1.8303766250610352, cross_entropy: 1.8303766250610352 +[2025-04-28 18:22:10,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 3.1760330200195312, cross_entropy: 3.1760330200195312 +[2025-04-28 18:22:13,146][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.214681625366211, cross_entropy: 1.214681625366211 +[2025-04-28 18:22:13,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.191927909851074, cross_entropy: 2.191927909851074 +[2025-04-28 18:22:16,672][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 3.021779775619507, cross_entropy: 3.021779775619507 +[2025-04-28 18:22:17,368][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.736829161643982, cross_entropy: 1.736829161643982 +[2025-04-28 18:22:19,557][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 1.1499335765838623, cross_entropy: 1.1499335765838623 +[2025-04-28 18:22:20,234][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.7333059310913086, cross_entropy: 1.7333059310913086 +[2025-04-28 18:22:22,519][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.462164282798767, cross_entropy: 1.462164282798767 +[2025-04-28 18:22:23,222][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.560429334640503, cross_entropy: 2.560429334640503 +[2025-04-28 18:22:25,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 3.2616357803344727, cross_entropy: 3.2616357803344727 +[2025-04-28 18:22:26,158][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 3.0028254985809326, cross_entropy: 3.0028254985809326 +[2025-04-28 18:22:28,802][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 1.3313862085342407, cross_entropy: 1.3313862085342407 +[2025-04-28 18:22:29,481][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 1.6093794107437134, cross_entropy: 1.6093794107437134 +[2025-04-28 18:22:31,889][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 1.814201831817627, cross_entropy: 1.814201831817627 +[2025-04-28 18:22:32,596][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.252473831176758, cross_entropy: 2.252473831176758 +[2025-04-28 18:22:34,792][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 1.3399382829666138, cross_entropy: 1.3399382829666138 +[2025-04-28 18:22:35,502][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.635684013366699, cross_entropy: 2.635684013366699 +[2025-04-28 18:22:37,658][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 2.9206223487854004, cross_entropy: 2.9206223487854004 +[2025-04-28 18:22:38,367][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 3.080193519592285, cross_entropy: 3.080193519592285 +[2025-04-28 18:22:40,707][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.9006426334381104, cross_entropy: 0.9006426334381104 +[2025-04-28 18:22:41,411][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 2.9376206398010254, cross_entropy: 2.9376206398010254 +[2025-04-28 18:22:43,588][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 1.5435264110565186, cross_entropy: 1.5435264110565186 +[2025-04-28 18:22:44,292][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 1.6297370195388794, cross_entropy: 1.6297370195388794 +[2025-04-28 18:22:46,758][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 1.048129916191101, cross_entropy: 1.048129916191101 +[2025-04-28 18:22:47,465][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 2.740187883377075, cross_entropy: 2.740187883377075 +[2025-04-28 18:22:49,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 2.00641131401062, cross_entropy: 2.00641131401062 +[2025-04-28 18:22:50,166][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 2.9935154914855957, cross_entropy: 2.9935154914855957 +[2025-04-28 18:22:52,633][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 2.827162265777588, cross_entropy: 2.827162265777588 +[2025-04-28 18:22:53,340][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.1929577589035034, cross_entropy: 1.1929577589035034 +[2025-04-28 18:22:55,134][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 3.2050209045410156, cross_entropy: 3.2050209045410156 +[2025-04-28 18:22:55,835][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 1.6244068145751953, cross_entropy: 1.6244068145751953 +[2025-04-28 18:22:58,937][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.631871223449707, cross_entropy: 1.631871223449707 +[2025-04-28 18:22:59,647][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 2.7265114784240723, cross_entropy: 2.7265114784240723 +[2025-04-28 18:23:02,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 0.8115447759628296, cross_entropy: 0.8115447759628296 +[2025-04-28 18:23:03,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 1.2394897937774658, cross_entropy: 1.2394897937774658 +[2025-04-28 18:23:05,670][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 0.8188822269439697, cross_entropy: 0.8188822269439697 +[2025-04-28 18:23:06,349][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.099106788635254, cross_entropy: 2.099106788635254 +[2025-04-28 18:23:08,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 1.207538366317749, cross_entropy: 1.207538366317749 +[2025-04-28 18:23:09,618][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.41874098777771, cross_entropy: 1.41874098777771 +[2025-04-28 18:23:11,254][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 3.0780205726623535, cross_entropy: 3.0780205726623535 +[2025-04-28 18:23:11,969][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 0.8957438468933105, cross_entropy: 0.8957438468933105 +[2025-04-28 18:23:14,576][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 2.9296088218688965, cross_entropy: 2.9296088218688965 +[2025-04-28 18:23:15,256][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 2.3201332092285156, cross_entropy: 2.3201332092285156 +[2025-04-28 18:23:17,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 3.025947093963623, cross_entropy: 3.025947093963623 +[2025-04-28 18:23:18,452][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.0073496103286743, cross_entropy: 1.0073496103286743 +[2025-04-28 18:23:20,748][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 0.9403925538063049, cross_entropy: 0.9403925538063049 +[2025-04-28 18:23:21,460][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.3060352802276611, cross_entropy: 1.3060352802276611 +[2025-04-28 18:23:24,005][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 2.037870407104492, cross_entropy: 2.037870407104492 +[2025-04-28 18:23:24,711][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 1.380163311958313, cross_entropy: 1.380163311958313 +[2025-04-28 18:23:27,538][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 1.3979206085205078, cross_entropy: 1.3979206085205078 +[2025-04-28 18:23:28,214][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 1.3207955360412598, cross_entropy: 1.3207955360412598 +[2025-04-28 18:23:30,536][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 1.0990656614303589, cross_entropy: 1.0990656614303589 +[2025-04-28 18:23:31,243][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 2.5504069328308105, cross_entropy: 2.5504069328308105 +[2025-04-28 18:23:34,132][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 1.153017520904541, cross_entropy: 1.153017520904541 +[2025-04-28 18:23:34,848][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 2.67685604095459, cross_entropy: 2.67685604095459 +[2025-04-28 18:23:38,458][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.1909524202346802, cross_entropy: 1.1909524202346802 +[2025-04-28 18:23:39,161][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 2.177680015563965, cross_entropy: 2.177680015563965 +[2025-04-28 18:23:40,778][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 1.7598176002502441, cross_entropy: 1.7598176002502441 +[2025-04-28 18:23:41,456][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 1.9629439115524292, cross_entropy: 1.9629439115524292 +[2025-04-28 18:23:43,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 2.5903749465942383, cross_entropy: 2.5903749465942383 +[2025-04-28 18:23:44,521][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 2.2423887252807617, cross_entropy: 2.2423887252807617 +[2025-04-28 18:23:47,141][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 3.3765945434570312, cross_entropy: 3.3765945434570312 +[2025-04-28 18:23:47,847][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 2.314932346343994, cross_entropy: 2.314932346343994 +[2025-04-28 18:23:50,245][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 2.3496694564819336, cross_entropy: 2.3496694564819336 +[2025-04-28 18:23:50,931][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 1.1751124858856201, cross_entropy: 1.1751124858856201 +[2025-04-28 18:23:53,708][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 1.728151559829712, cross_entropy: 1.728151559829712 +[2025-04-28 18:23:54,410][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 2.8627123832702637, cross_entropy: 2.8627123832702637 +[2025-04-28 18:23:56,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.9060769081115723, cross_entropy: 2.9060769081115723 +[2025-04-28 18:23:57,571][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 3.107722759246826, cross_entropy: 3.107722759246826 +[2025-04-28 18:24:00,032][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 1.8650083541870117, cross_entropy: 1.8650083541870117 +[2025-04-28 18:24:00,713][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.824394941329956, cross_entropy: 1.824394941329956 +[2025-04-28 18:24:03,114][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 1.9903130531311035, cross_entropy: 1.9903130531311035 +[2025-04-28 18:24:03,822][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 2.866365909576416, cross_entropy: 2.866365909576416 +[2025-04-28 18:24:06,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 2.6370956897735596, cross_entropy: 2.6370956897735596 +[2025-04-28 18:24:07,356][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.8016319274902344, cross_entropy: 1.8016319274902344 +[2025-04-28 18:24:09,385][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 1.2520475387573242, cross_entropy: 1.2520475387573242 +[2025-04-28 18:24:10,088][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 2.0619664192199707, cross_entropy: 2.0619664192199707 +[2025-04-28 18:24:12,695][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.2632958889007568, cross_entropy: 1.2632958889007568 +[2025-04-28 18:24:13,415][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.1489202976226807, cross_entropy: 2.1489202976226807 +[2025-04-28 18:24:15,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 2.7117953300476074, cross_entropy: 2.7117953300476074 +[2025-04-28 18:24:15,923][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 2.3987903594970703, cross_entropy: 2.3987903594970703 +[2025-04-28 18:24:17,824][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.553889751434326, cross_entropy: 2.553889751434326 +[2025-04-28 18:24:18,504][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 2.9622480869293213, cross_entropy: 2.9622480869293213 +[2025-04-28 18:24:21,631][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 1.8884296417236328, cross_entropy: 1.8884296417236328 +[2025-04-28 18:24:22,338][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 1.2878079414367676, cross_entropy: 1.2878079414367676 +[2025-04-28 18:24:24,935][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 1.129072904586792, cross_entropy: 1.129072904586792 +[2025-04-28 18:24:25,639][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 1.8953646421432495, cross_entropy: 1.8953646421432495 +[2025-04-28 18:24:28,206][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 3.2412631511688232, cross_entropy: 3.2412631511688232 +[2025-04-28 18:24:28,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.2404030561447144, cross_entropy: 1.2404030561447144 +[2025-04-28 18:24:31,128][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.5882415771484375, cross_entropy: 2.5882415771484375 +[2025-04-28 18:24:31,806][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 2.1724140644073486, cross_entropy: 2.1724140644073486 +[2025-04-28 18:24:34,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 2.367577075958252, cross_entropy: 2.367577075958252 +[2025-04-28 18:24:35,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 3.381385326385498, cross_entropy: 3.381385326385498 +[2025-04-28 18:24:37,949][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 1.8539724349975586, cross_entropy: 1.8539724349975586 +[2025-04-28 18:24:38,652][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 1.072463035583496, cross_entropy: 1.072463035583496 +[2025-04-28 18:24:40,886][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 1.4712038040161133, cross_entropy: 1.4712038040161133 +[2025-04-28 18:24:41,594][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.3112775087356567, cross_entropy: 1.3112775087356567 +[2025-04-28 18:24:43,880][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.8033359050750732, cross_entropy: 2.8033359050750732 +[2025-04-28 18:24:44,591][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.5536129474639893, cross_entropy: 2.5536129474639893 +[2025-04-28 18:24:47,621][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.1353576183319092, cross_entropy: 1.1353576183319092 +[2025-04-28 18:24:48,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.4357740879058838, cross_entropy: 1.4357740879058838 +[2025-04-28 18:24:50,848][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 2.764411449432373, cross_entropy: 2.764411449432373 +[2025-04-28 18:24:51,558][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.3235924243927002, cross_entropy: 1.3235924243927002 +[2025-04-28 18:24:53,789][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 1.1249864101409912, cross_entropy: 1.1249864101409912 +[2025-04-28 18:24:54,495][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 3.2758102416992188, cross_entropy: 3.2758102416992188 +[2025-04-28 18:24:57,050][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 2.326233148574829, cross_entropy: 2.326233148574829 +[2025-04-28 18:24:57,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 1.2511091232299805, cross_entropy: 1.2511091232299805 +[2025-04-28 18:25:00,608][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.3688193559646606, cross_entropy: 1.3688193559646606 +[2025-04-28 18:25:01,282][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 2.654919385910034, cross_entropy: 2.654919385910034 +[2025-04-28 18:25:03,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.1540089845657349, cross_entropy: 1.1540089845657349 +[2025-04-28 18:25:04,501][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 2.4183244705200195, cross_entropy: 2.4183244705200195 +[2025-04-28 18:25:06,839][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 1.45908522605896, cross_entropy: 1.45908522605896 +[2025-04-28 18:25:07,549][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 2.598891258239746, cross_entropy: 2.598891258239746 +[2025-04-28 18:25:10,150][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 1.2975409030914307, cross_entropy: 1.2975409030914307 +[2025-04-28 18:25:10,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.5255022048950195, cross_entropy: 2.5255022048950195 +[2025-04-28 18:25:12,800][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 1.4201961755752563, cross_entropy: 1.4201961755752563 +[2025-04-28 18:25:13,477][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.126605987548828, cross_entropy: 2.126605987548828 +[2025-04-28 18:25:16,390][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 1.4049007892608643, cross_entropy: 1.4049007892608643 +[2025-04-28 18:25:17,073][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.673490524291992, cross_entropy: 2.673490524291992 +[2025-04-28 18:25:19,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 1.9764598608016968, cross_entropy: 1.9764598608016968 +[2025-04-28 18:25:19,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 3.3716511726379395, cross_entropy: 3.3716511726379395 +[2025-04-28 18:25:22,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 1.2217673063278198, cross_entropy: 1.2217673063278198 +[2025-04-28 18:25:22,819][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.456434965133667, cross_entropy: 1.456434965133667 +[2025-04-28 18:25:24,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 1.305585265159607, cross_entropy: 1.305585265159607 +[2025-04-28 18:25:25,569][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.4411301612854004, cross_entropy: 2.4411301612854004 +[2025-04-28 18:25:28,065][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 2.546315908432007, cross_entropy: 2.546315908432007 +[2025-04-28 18:25:28,773][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 2.824988842010498, cross_entropy: 2.824988842010498 +[2025-04-28 18:25:29,541][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/iteration3000.pth. +[2025-04-28 18:25:31,347][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 1.5273444652557373, cross_entropy: 1.5273444652557373 +[2025-04-28 18:25:32,062][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 1.4727668762207031, cross_entropy: 1.4727668762207031 +[2025-04-28 18:25:34,447][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 1.2750251293182373, cross_entropy: 1.2750251293182373 +[2025-04-28 18:25:35,152][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 3.1936326026916504, cross_entropy: 3.1936326026916504 +[2025-04-28 18:25:37,542][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.9092326164245605, cross_entropy: 1.9092326164245605 +[2025-04-28 18:25:38,612][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 1.823432445526123, cross_entropy: 1.823432445526123 +[2025-04-28 18:25:40,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 2.611588954925537, cross_entropy: 2.611588954925537 +[2025-04-28 18:25:41,448][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 1.8423633575439453, cross_entropy: 1.8423633575439453 +[2025-04-28 18:25:44,010][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 1.3542331457138062, cross_entropy: 1.3542331457138062 +[2025-04-28 18:25:44,719][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 2.8713035583496094, cross_entropy: 2.8713035583496094 +[2025-04-28 18:25:47,069][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 2.165351390838623, cross_entropy: 2.165351390838623 +[2025-04-28 18:25:47,745][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 2.9818549156188965, cross_entropy: 2.9818549156188965 +[2025-04-28 18:25:50,971][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 1.220818281173706, cross_entropy: 1.220818281173706 +[2025-04-28 18:25:51,648][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 2.6479010581970215, cross_entropy: 2.6479010581970215 +[2025-04-28 18:25:54,288][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 1.9179611206054688, cross_entropy: 1.9179611206054688 +[2025-04-28 18:25:54,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.5128612518310547, cross_entropy: 2.5128612518310547 +[2025-04-28 18:25:56,828][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 2.7157132625579834, cross_entropy: 2.7157132625579834 +[2025-04-28 18:25:57,542][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 1.1548471450805664, cross_entropy: 1.1548471450805664 +[2025-04-28 18:26:00,240][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 3.0539889335632324, cross_entropy: 3.0539889335632324 +[2025-04-28 18:26:00,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.0017138719558716, cross_entropy: 1.0017138719558716 +[2025-04-28 18:26:02,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 1.2493534088134766, cross_entropy: 1.2493534088134766 +[2025-04-28 18:26:03,636][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 2.553415298461914, cross_entropy: 2.553415298461914 +[2025-04-28 18:26:06,449][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.1433870792388916, cross_entropy: 1.1433870792388916 +[2025-04-28 18:26:07,159][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 3.0371382236480713, cross_entropy: 3.0371382236480713 +[2025-04-28 18:26:09,045][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.6029173135757446, cross_entropy: 1.6029173135757446 +[2025-04-28 18:26:09,756][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 2.856288433074951, cross_entropy: 2.856288433074951 +[2025-04-28 18:26:12,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.7036428451538086, cross_entropy: 1.7036428451538086 +[2025-04-28 18:26:12,993][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 0.8524584770202637, cross_entropy: 0.8524584770202637 +[2025-04-28 18:26:15,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 1.9361234903335571, cross_entropy: 1.9361234903335571 +[2025-04-28 18:26:16,252][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 2.101524829864502, cross_entropy: 2.101524829864502 +[2025-04-28 18:26:18,991][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 3.0901894569396973, cross_entropy: 3.0901894569396973 +[2025-04-28 18:26:19,694][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 3.168630599975586, cross_entropy: 3.168630599975586 +[2025-04-28 18:26:21,283][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 1.2588133811950684, cross_entropy: 1.2588133811950684 +[2025-04-28 18:26:21,986][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.26338529586792, cross_entropy: 2.26338529586792 +[2025-04-28 18:26:24,298][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 1.4696857929229736, cross_entropy: 1.4696857929229736 +[2025-04-28 18:26:24,975][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 2.8411290645599365, cross_entropy: 2.8411290645599365 +[2025-04-28 18:26:27,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 2.7490391731262207, cross_entropy: 2.7490391731262207 +[2025-04-28 18:26:28,311][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.432602882385254, cross_entropy: 1.432602882385254 +[2025-04-28 18:26:30,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 2.893368721008301, cross_entropy: 2.893368721008301 +[2025-04-28 18:26:31,365][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.3307253122329712, cross_entropy: 1.3307253122329712 +[2025-04-28 18:26:33,774][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 1.2613530158996582, cross_entropy: 1.2613530158996582 +[2025-04-28 18:26:34,448][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 1.139783263206482, cross_entropy: 1.139783263206482 +[2025-04-28 18:26:37,394][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 3.1633641719818115, cross_entropy: 3.1633641719818115 +[2025-04-28 18:26:38,116][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 2.9753646850585938, cross_entropy: 2.9753646850585938 +[2025-04-28 18:26:40,146][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 1.5920379161834717, cross_entropy: 1.5920379161834717 +[2025-04-28 18:26:40,845][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 3.0191922187805176, cross_entropy: 3.0191922187805176 +[2025-04-28 18:26:43,505][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 1.408104419708252, cross_entropy: 1.408104419708252 +[2025-04-28 18:26:44,213][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 2.1324257850646973, cross_entropy: 2.1324257850646973 +[2025-04-28 18:26:47,278][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 1.8544014692306519, cross_entropy: 1.8544014692306519 +[2025-04-28 18:26:47,988][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.566603422164917, cross_entropy: 1.566603422164917 +[2025-04-28 18:26:50,046][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 1.4193415641784668, cross_entropy: 1.4193415641784668 +[2025-04-28 18:26:50,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.9230973720550537, cross_entropy: 2.9230973720550537 +[2025-04-28 18:26:52,786][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.5986723899841309, cross_entropy: 1.5986723899841309 +[2025-04-28 18:26:53,462][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 2.089505672454834, cross_entropy: 2.089505672454834 +[2025-04-28 18:26:55,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.2714667320251465, cross_entropy: 2.2714667320251465 +[2025-04-28 18:26:56,572][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 2.025897741317749, cross_entropy: 2.025897741317749 +[2025-04-28 18:26:59,127][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 2.0026156902313232, cross_entropy: 2.0026156902313232 +[2025-04-28 18:26:59,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 2.983487129211426, cross_entropy: 2.983487129211426 +[2025-04-28 18:27:03,443][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.4046292304992676, cross_entropy: 2.4046292304992676 +[2025-04-28 18:27:04,148][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 2.670558452606201, cross_entropy: 2.670558452606201 +[2025-04-28 18:27:06,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 2.4905669689178467, cross_entropy: 2.4905669689178467 +[2025-04-28 18:27:07,333][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 2.8198044300079346, cross_entropy: 2.8198044300079346 +[2025-04-28 18:27:09,849][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.8517146110534668, cross_entropy: 1.8517146110534668 +[2025-04-28 18:27:10,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.783779263496399, cross_entropy: 1.783779263496399 +[2025-04-28 18:27:13,490][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.779176712036133, cross_entropy: 2.779176712036133 +[2025-04-28 18:27:14,167][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 2.0289251804351807, cross_entropy: 2.0289251804351807 +[2025-04-28 18:27:16,871][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 2.9873459339141846, cross_entropy: 2.9873459339141846 +[2025-04-28 18:27:17,579][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 3.0462493896484375, cross_entropy: 3.0462493896484375 +[2025-04-28 18:27:20,230][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 1.2419863939285278, cross_entropy: 1.2419863939285278 +[2025-04-28 18:27:20,908][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 3.097303628921509, cross_entropy: 3.097303628921509 +[2025-04-28 18:27:23,366][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 3.3209493160247803, cross_entropy: 3.3209493160247803 +[2025-04-28 18:27:24,067][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 2.230036735534668, cross_entropy: 2.230036735534668 +[2025-04-28 18:27:26,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 3.164794683456421, cross_entropy: 3.164794683456421 +[2025-04-28 18:27:26,846][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 1.239976167678833, cross_entropy: 1.239976167678833 +[2025-04-28 18:27:29,266][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 1.2666690349578857, cross_entropy: 1.2666690349578857 +[2025-04-28 18:27:29,979][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.2415037155151367, cross_entropy: 2.2415037155151367 +[2025-04-28 18:27:32,688][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 1.114363670349121, cross_entropy: 1.114363670349121 +[2025-04-28 18:27:33,403][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.2148423194885254, cross_entropy: 2.2148423194885254 +[2025-04-28 18:27:35,597][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 1.4192826747894287, cross_entropy: 1.4192826747894287 +[2025-04-28 18:27:36,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 1.0616657733917236, cross_entropy: 1.0616657733917236 +[2025-04-28 18:27:38,537][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 2.9624671936035156, cross_entropy: 2.9624671936035156 +[2025-04-28 18:27:39,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 2.29075026512146, cross_entropy: 2.29075026512146 +[2025-04-28 18:27:40,892][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 1.9256967306137085, cross_entropy: 1.9256967306137085 +[2025-04-28 18:27:41,573][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 1.1655722856521606, cross_entropy: 1.1655722856521606 +[2025-04-28 18:27:43,757][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 2.9436516761779785, cross_entropy: 2.9436516761779785 +[2025-04-28 18:27:44,463][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 1.2143677473068237, cross_entropy: 1.2143677473068237 +[2025-04-28 18:27:47,517][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 3.1309049129486084, cross_entropy: 3.1309049129486084 +[2025-04-28 18:27:48,216][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 1.4336014986038208, cross_entropy: 1.4336014986038208 +[2025-04-28 18:27:51,674][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.4327796697616577, cross_entropy: 1.4327796697616577 +[2025-04-28 18:27:52,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.3881217241287231, cross_entropy: 1.3881217241287231 +[2025-04-28 18:27:55,047][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 1.2962195873260498, cross_entropy: 1.2962195873260498 +[2025-04-28 18:27:55,760][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 1.7078077793121338, cross_entropy: 1.7078077793121338 +[2025-04-28 18:27:57,705][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 1.0426703691482544, cross_entropy: 1.0426703691482544 +[2025-04-28 18:27:58,381][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 1.2059991359710693, cross_entropy: 1.2059991359710693 +[2025-04-28 18:28:00,685][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 2.978468894958496, cross_entropy: 2.978468894958496 +[2025-04-28 18:28:01,362][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 2.6472415924072266, cross_entropy: 2.6472415924072266 +[2025-04-28 18:28:03,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 3.155057191848755, cross_entropy: 3.155057191848755 +[2025-04-28 18:28:03,989][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.4012501239776611, cross_entropy: 1.4012501239776611 +[2025-04-28 18:28:05,959][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 1.0706040859222412, cross_entropy: 1.0706040859222412 +[2025-04-28 18:28:06,766][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 3.2084662914276123, cross_entropy: 3.2084662914276123 +[2025-04-28 18:28:09,000][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.3226733207702637, cross_entropy: 1.3226733207702637 +[2025-04-28 18:28:09,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.4873743057250977, cross_entropy: 2.4873743057250977 +[2025-04-28 18:28:12,195][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 1.4904077053070068, cross_entropy: 1.4904077053070068 +[2025-04-28 18:28:13,011][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 2.5792012214660645, cross_entropy: 2.5792012214660645 +[2025-04-28 18:28:15,109][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.7461985349655151, cross_entropy: 1.7461985349655151 +[2025-04-28 18:28:15,945][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.5688878297805786, cross_entropy: 1.5688878297805786 +[2025-04-28 18:28:18,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 1.3260011672973633, cross_entropy: 1.3260011672973633 +[2025-04-28 18:28:19,322][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.8340649604797363, cross_entropy: 2.8340649604797363 +[2025-04-28 18:28:22,395][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 3.2232186794281006, cross_entropy: 3.2232186794281006 +[2025-04-28 18:28:23,100][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 2.9358022212982178, cross_entropy: 2.9358022212982178 +[2025-04-28 18:28:25,085][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 1.5588572025299072, cross_entropy: 1.5588572025299072 +[2025-04-28 18:28:25,791][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 2.0426578521728516, cross_entropy: 2.0426578521728516 +[2025-04-28 18:28:27,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.402418613433838, cross_entropy: 1.402418613433838 +[2025-04-28 18:28:28,459][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 1.7140226364135742, cross_entropy: 1.7140226364135742 +[2025-04-28 18:28:30,408][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.55690598487854, cross_entropy: 1.55690598487854 +[2025-04-28 18:28:31,107][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.4646620750427246, cross_entropy: 2.4646620750427246 +[2025-04-28 18:28:33,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 1.466249704360962, cross_entropy: 1.466249704360962 +[2025-04-28 18:28:34,823][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 1.3197073936462402, cross_entropy: 1.3197073936462402 +[2025-04-28 18:28:36,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 1.7679523229599, cross_entropy: 1.7679523229599 +[2025-04-28 18:28:38,027][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 2.2095420360565186, cross_entropy: 2.2095420360565186 +[2025-04-28 18:28:39,499][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 1.0093882083892822, cross_entropy: 1.0093882083892822 +[2025-04-28 18:28:42,223][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 1.0971477031707764, cross_entropy: 1.0971477031707764 +[2025-04-28 18:28:42,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 1.3553318977355957, cross_entropy: 1.3553318977355957 +[2025-04-28 18:28:45,101][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 1.1677613258361816, cross_entropy: 1.1677613258361816 +[2025-04-28 18:28:45,849][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.1494019031524658, cross_entropy: 1.1494019031524658 +[2025-04-28 18:28:47,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.3118032217025757, cross_entropy: 1.3118032217025757 +[2025-04-28 18:28:48,680][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 1.6704679727554321, cross_entropy: 1.6704679727554321 +[2025-04-28 18:28:50,598][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 3.1267218589782715, cross_entropy: 3.1267218589782715 +[2025-04-28 18:28:51,341][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.4089502096176147, cross_entropy: 1.4089502096176147 +[2025-04-28 18:28:53,919][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.3637924194335938, cross_entropy: 2.3637924194335938 +[2025-04-28 18:28:54,730][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 2.793661117553711, cross_entropy: 2.793661117553711 +[2025-04-28 18:28:57,174][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 1.4967701435089111, cross_entropy: 1.4967701435089111 +[2025-04-28 18:28:58,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 1.351980209350586, cross_entropy: 1.351980209350586 +[2025-04-28 18:29:00,186][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 2.8702945709228516, cross_entropy: 2.8702945709228516 +[2025-04-28 18:29:01,140][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 1.691906452178955, cross_entropy: 1.691906452178955 +[2025-04-28 18:29:03,545][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 2.8871190547943115, cross_entropy: 2.8871190547943115 +[2025-04-28 18:29:04,251][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 1.4201130867004395, cross_entropy: 1.4201130867004395 +[2025-04-28 18:29:06,048][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.6409547328948975, cross_entropy: 1.6409547328948975 +[2025-04-28 18:29:06,822][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 0.8585940599441528, cross_entropy: 0.8585940599441528 +[2025-04-28 18:29:09,542][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.1159008741378784, cross_entropy: 1.1159008741378784 +[2025-04-28 18:29:10,247][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.0832905769348145, cross_entropy: 1.0832905769348145 +[2025-04-28 18:29:12,430][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 2.978466272354126, cross_entropy: 2.978466272354126 +[2025-04-28 18:29:13,108][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 0.9251534342765808, cross_entropy: 0.9251534342765808 +[2025-04-28 18:29:15,213][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 0.8383873701095581, cross_entropy: 0.8383873701095581 +[2025-04-28 18:29:15,895][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 2.4187021255493164, cross_entropy: 2.4187021255493164 +[2025-04-28 18:29:18,078][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 1.9459080696105957, cross_entropy: 1.9459080696105957 +[2025-04-28 18:29:18,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 0.8975573778152466, cross_entropy: 0.8975573778152466 +[2025-04-28 18:29:20,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 2.8958754539489746, cross_entropy: 2.8958754539489746 +[2025-04-28 18:29:21,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 3.0374302864074707, cross_entropy: 3.0374302864074707 +[2025-04-28 18:29:24,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 1.725426435470581, cross_entropy: 1.725426435470581 +[2025-04-28 18:29:24,932][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 3.2072489261627197, cross_entropy: 3.2072489261627197 +[2025-04-28 18:29:27,437][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 1.244424819946289, cross_entropy: 1.244424819946289 +[2025-04-28 18:29:28,114][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.7249937057495117, cross_entropy: 2.7249937057495117 +[2025-04-28 18:29:30,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 1.6741584539413452, cross_entropy: 1.6741584539413452 +[2025-04-28 18:29:31,291][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 2.133643388748169, cross_entropy: 2.133643388748169 +[2025-04-28 18:29:33,707][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 3.3012540340423584, cross_entropy: 3.3012540340423584 +[2025-04-28 18:29:34,385][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 3.0045037269592285, cross_entropy: 3.0045037269592285 +[2025-04-28 18:29:37,312][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 2.992004632949829, cross_entropy: 2.992004632949829 +[2025-04-28 18:29:37,988][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 0.8844455480575562, cross_entropy: 0.8844455480575562 +[2025-04-28 18:29:40,409][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 1.9098961353302002, cross_entropy: 1.9098961353302002 +[2025-04-28 18:29:41,115][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 2.6153640747070312, cross_entropy: 2.6153640747070312 +[2025-04-28 18:29:43,702][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.7903289794921875, cross_entropy: 1.7903289794921875 +[2025-04-28 18:29:44,407][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 2.9610939025878906, cross_entropy: 2.9610939025878906 +[2025-04-28 18:29:46,319][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.2255280017852783, cross_entropy: 2.2255280017852783 +[2025-04-28 18:29:47,190][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 2.5720295906066895, cross_entropy: 2.5720295906066895 +[2025-04-28 18:29:49,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 1.2289615869522095, cross_entropy: 1.2289615869522095 +[2025-04-28 18:29:50,068][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 1.4621249437332153, cross_entropy: 1.4621249437332153 +[2025-04-28 18:29:52,319][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 2.083014965057373, cross_entropy: 2.083014965057373 +[2025-04-28 18:29:53,038][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.1164840459823608, cross_entropy: 1.1164840459823608 +[2025-04-28 18:29:55,391][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 1.683822512626648, cross_entropy: 1.683822512626648 +[2025-04-28 18:29:57,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 1.6692564487457275, cross_entropy: 1.6692564487457275 +[2025-04-28 18:29:59,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 3.195924997329712, cross_entropy: 3.195924997329712 +[2025-04-28 18:30:00,370][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 2.962430000305176, cross_entropy: 2.962430000305176 +[2025-04-28 18:30:02,237][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.426635503768921, cross_entropy: 2.426635503768921 +[2025-04-28 18:30:03,330][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 1.6888163089752197, cross_entropy: 1.6888163089752197 +[2025-04-28 18:30:05,162][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 2.693680763244629, cross_entropy: 2.693680763244629 +[2025-04-28 18:30:06,551][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 2.343076705932617, cross_entropy: 2.343076705932617 +[2025-04-28 18:30:08,340][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.1131712198257446, cross_entropy: 1.1131712198257446 +[2025-04-28 18:30:09,892][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 2.9311580657958984, cross_entropy: 2.9311580657958984 +[2025-04-28 18:30:10,987][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 1.0329914093017578, cross_entropy: 1.0329914093017578 +[2025-04-28 18:30:12,973][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 2.531442165374756, cross_entropy: 2.531442165374756 +[2025-04-28 18:30:14,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 2.472262382507324, cross_entropy: 2.472262382507324 +[2025-04-28 18:30:15,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 3.4001364707946777, cross_entropy: 3.4001364707946777 +[2025-04-28 18:30:17,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.416064500808716, cross_entropy: 2.416064500808716 +[2025-04-28 18:30:18,872][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.8410229682922363, cross_entropy: 1.8410229682922363 +[2025-04-28 18:30:20,262][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 3.150451898574829, cross_entropy: 3.150451898574829 +[2025-04-28 18:30:21,967][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 2.246467113494873, cross_entropy: 2.246467113494873 +[2025-04-28 18:30:23,458][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 0.9895471334457397, cross_entropy: 0.9895471334457397 +[2025-04-28 18:30:24,870][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 1.9137225151062012, cross_entropy: 1.9137225151062012 +[2025-04-28 18:30:25,900][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 3.32747483253479, cross_entropy: 3.32747483253479 +[2025-04-28 18:30:28,202][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 1.2668535709381104, cross_entropy: 1.2668535709381104 +[2025-04-28 18:30:28,922][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.6097989082336426, cross_entropy: 1.6097989082336426 +[2025-04-28 18:30:31,323][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 2.38004732131958, cross_entropy: 2.38004732131958 +[2025-04-28 18:30:32,095][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.4152541160583496, cross_entropy: 2.4152541160583496 +[2025-04-28 18:30:33,982][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 2.8907346725463867, cross_entropy: 2.8907346725463867 +[2025-04-28 18:30:34,875][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.8884599208831787, cross_entropy: 2.8884599208831787 +[2025-04-28 18:30:37,417][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 3.0997912883758545, cross_entropy: 3.0997912883758545 +[2025-04-28 18:30:38,188][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.1996357440948486, cross_entropy: 2.1996357440948486 +[2025-04-28 18:30:40,829][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 1.68002450466156, cross_entropy: 1.68002450466156 +[2025-04-28 18:30:41,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 2.6740593910217285, cross_entropy: 2.6740593910217285 +[2025-04-28 18:30:43,538][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 2.702086925506592, cross_entropy: 2.702086925506592 +[2025-04-28 18:30:44,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 1.879685878753662, cross_entropy: 1.879685878753662 +[2025-04-28 18:30:47,528][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 2.6922669410705566, cross_entropy: 2.6922669410705566 +[2025-04-28 18:30:48,133][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.5640740394592285, cross_entropy: 2.5640740394592285 +[2025-04-28 18:33:10,923][BaseTrainer][INFO] - [Epoch 9/10] (train) 2.0281295776367188, cross_entropy: 2.0281295776367188 +[2025-04-28 18:33:10,924][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.183003306388855, cross_entropy: 1.183003306388855 +[2025-04-28 18:33:11,827][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 18:33:12,345][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch9.pth. +[2025-04-28 18:33:13,191][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 18:33:17,263][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.2531002759933472, cross_entropy: 1.2531002759933472 +[2025-04-28 18:33:18,207][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.7275400161743164, cross_entropy: 1.7275400161743164 +[2025-04-28 18:33:20,990][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 2.552670478820801, cross_entropy: 2.552670478820801 +[2025-04-28 18:33:21,754][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 3.0941965579986572, cross_entropy: 3.0941965579986572 +[2025-04-28 18:33:24,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.51945161819458, cross_entropy: 2.51945161819458 +[2025-04-28 18:33:24,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 0.8814119100570679, cross_entropy: 0.8814119100570679 +[2025-04-28 18:33:26,373][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.749659538269043, cross_entropy: 2.749659538269043 +[2025-04-28 18:33:27,134][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.7538517713546753, cross_entropy: 0.7538517713546753 +[2025-04-28 18:33:29,061][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.2477166652679443, cross_entropy: 2.2477166652679443 +[2025-04-28 18:33:29,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 0.9522050619125366, cross_entropy: 0.9522050619125366 +[2025-04-28 18:33:32,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 1.1481633186340332, cross_entropy: 1.1481633186340332 +[2025-04-28 18:33:32,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 0.8128469586372375, cross_entropy: 0.8128469586372375 +[2025-04-28 18:33:35,389][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 2.8154141902923584, cross_entropy: 2.8154141902923584 +[2025-04-28 18:33:36,126][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.7344415187835693, cross_entropy: 1.7344415187835693 +[2025-04-28 18:33:38,507][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 1.4032924175262451, cross_entropy: 1.4032924175262451 +[2025-04-28 18:33:39,281][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 3.1547820568084717, cross_entropy: 3.1547820568084717 +[2025-04-28 18:33:42,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 2.7337894439697266, cross_entropy: 2.7337894439697266 +[2025-04-28 18:33:43,187][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 1.0074307918548584, cross_entropy: 1.0074307918548584 +[2025-04-28 18:33:45,026][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.767472982406616, cross_entropy: 2.767472982406616 +[2025-04-28 18:33:46,108][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.41506826877594, cross_entropy: 1.41506826877594 +[2025-04-28 18:33:48,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 2.3603785037994385, cross_entropy: 2.3603785037994385 +[2025-04-28 18:33:49,242][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 1.3472586870193481, cross_entropy: 1.3472586870193481 +[2025-04-28 18:33:51,212][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 3.1224875450134277, cross_entropy: 3.1224875450134277 +[2025-04-28 18:33:52,528][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 1.1264100074768066, cross_entropy: 1.1264100074768066 +[2025-04-28 18:33:54,264][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.333665609359741, cross_entropy: 2.333665609359741 +[2025-04-28 18:33:56,267][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 1.2037522792816162, cross_entropy: 1.2037522792816162 +[2025-04-28 18:33:57,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 3.202834367752075, cross_entropy: 3.202834367752075 +[2025-04-28 18:33:59,637][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.6786084175109863, cross_entropy: 2.6786084175109863 +[2025-04-28 18:34:00,341][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 1.073512077331543, cross_entropy: 1.073512077331543 +[2025-04-28 18:34:02,442][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.9016730785369873, cross_entropy: 1.9016730785369873 +[2025-04-28 18:34:03,627][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 1.3413795232772827, cross_entropy: 1.3413795232772827 +[2025-04-28 18:34:05,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 2.8931283950805664, cross_entropy: 2.8931283950805664 +[2025-04-28 18:34:06,419][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 1.4144872426986694, cross_entropy: 1.4144872426986694 +[2025-04-28 18:34:08,404][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 1.8427398204803467, cross_entropy: 1.8427398204803467 +[2025-04-28 18:34:09,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 2.3600897789001465, cross_entropy: 2.3600897789001465 +[2025-04-28 18:34:10,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 0.9783211350440979, cross_entropy: 0.9783211350440979 +[2025-04-28 18:34:12,746][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 3.1072611808776855, cross_entropy: 3.1072611808776855 +[2025-04-28 18:34:14,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 1.7635996341705322, cross_entropy: 1.7635996341705322 +[2025-04-28 18:34:16,878][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 3.004751205444336, cross_entropy: 3.004751205444336 +[2025-04-28 18:34:17,811][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 2.057028293609619, cross_entropy: 2.057028293609619 +[2025-04-28 18:34:19,833][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 2.7891058921813965, cross_entropy: 2.7891058921813965 +[2025-04-28 18:34:20,857][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 2.0910451412200928, cross_entropy: 2.0910451412200928 +[2025-04-28 18:34:23,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 2.7883548736572266, cross_entropy: 2.7883548736572266 +[2025-04-28 18:34:23,757][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.8937127590179443, cross_entropy: 2.8937127590179443 +[2025-04-28 18:34:25,583][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 2.486546754837036, cross_entropy: 2.486546754837036 +[2025-04-28 18:34:27,763][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 1.2331831455230713, cross_entropy: 1.2331831455230713 +[2025-04-28 18:34:28,500][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.5883023738861084, cross_entropy: 1.5883023738861084 +[2025-04-28 18:34:30,570][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 0.9228922128677368, cross_entropy: 0.9228922128677368 +[2025-04-28 18:34:31,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.0483226776123047, cross_entropy: 1.0483226776123047 +[2025-04-28 18:34:33,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 1.788854956626892, cross_entropy: 1.788854956626892 +[2025-04-28 18:34:34,187][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.1726231575012207, cross_entropy: 2.1726231575012207 +[2025-04-28 18:34:35,958][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 2.6910834312438965, cross_entropy: 2.6910834312438965 +[2025-04-28 18:34:37,519][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.064381718635559, cross_entropy: 1.064381718635559 +[2025-04-28 18:34:39,771][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 2.9604198932647705, cross_entropy: 2.9604198932647705 +[2025-04-28 18:34:40,561][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.280309796333313, cross_entropy: 1.280309796333313 +[2025-04-28 18:34:42,302][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 1.9902253150939941, cross_entropy: 1.9902253150939941 +[2025-04-28 18:34:43,677][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 2.172386646270752, cross_entropy: 2.172386646270752 +[2025-04-28 18:34:47,186][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 1.4248348474502563, cross_entropy: 1.4248348474502563 +[2025-04-28 18:34:47,900][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.450531005859375, cross_entropy: 1.450531005859375 +[2025-04-28 18:34:50,837][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 2.218940258026123, cross_entropy: 2.218940258026123 +[2025-04-28 18:34:51,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 1.3062965869903564, cross_entropy: 1.3062965869903564 +[2025-04-28 18:34:54,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 2.764592409133911, cross_entropy: 2.764592409133911 +[2025-04-28 18:34:54,809][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 1.7692866325378418, cross_entropy: 1.7692866325378418 +[2025-04-28 18:34:56,967][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 1.2854106426239014, cross_entropy: 1.2854106426239014 +[2025-04-28 18:34:57,674][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 2.84224271774292, cross_entropy: 2.84224271774292 +[2025-04-28 18:35:00,037][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 3.0017848014831543, cross_entropy: 3.0017848014831543 +[2025-04-28 18:35:00,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 3.2659695148468018, cross_entropy: 3.2659695148468018 +[2025-04-28 18:35:03,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 0.7939475774765015, cross_entropy: 0.7939475774765015 +[2025-04-28 18:35:03,829][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 2.102968215942383, cross_entropy: 2.102968215942383 +[2025-04-28 18:35:06,184][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 3.118478298187256, cross_entropy: 3.118478298187256 +[2025-04-28 18:35:06,867][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 3.036189079284668, cross_entropy: 3.036189079284668 +[2025-04-28 18:35:09,597][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 1.2564120292663574, cross_entropy: 1.2564120292663574 +[2025-04-28 18:35:10,315][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.8586552143096924, cross_entropy: 1.8586552143096924 +[2025-04-28 18:35:11,894][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.092367172241211, cross_entropy: 2.092367172241211 +[2025-04-28 18:35:12,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 3.3441169261932373, cross_entropy: 3.3441169261932373 +[2025-04-28 18:35:15,127][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.2062163352966309, cross_entropy: 1.2062163352966309 +[2025-04-28 18:35:15,808][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.1517512798309326, cross_entropy: 1.1517512798309326 +[2025-04-28 18:35:18,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 3.014639377593994, cross_entropy: 3.014639377593994 +[2025-04-28 18:35:19,542][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.6049304008483887, cross_entropy: 1.6049304008483887 +[2025-04-28 18:35:22,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 0.8676391839981079, cross_entropy: 0.8676391839981079 +[2025-04-28 18:35:23,000][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.1520304679870605, cross_entropy: 1.1520304679870605 +[2025-04-28 18:35:25,498][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 3.1605048179626465, cross_entropy: 3.1605048179626465 +[2025-04-28 18:35:26,196][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 3.0213239192962646, cross_entropy: 3.0213239192962646 +[2025-04-28 18:35:28,759][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 2.8941397666931152, cross_entropy: 2.8941397666931152 +[2025-04-28 18:35:29,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 3.0588040351867676, cross_entropy: 3.0588040351867676 +[2025-04-28 18:35:31,610][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 1.1208832263946533, cross_entropy: 1.1208832263946533 +[2025-04-28 18:35:32,290][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 1.3489956855773926, cross_entropy: 1.3489956855773926 +[2025-04-28 18:35:34,868][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 3.2841382026672363, cross_entropy: 3.2841382026672363 +[2025-04-28 18:35:35,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 1.329509973526001, cross_entropy: 1.329509973526001 +[2025-04-28 18:35:37,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 2.4293274879455566, cross_entropy: 2.4293274879455566 +[2025-04-28 18:35:38,390][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 2.106522560119629, cross_entropy: 2.106522560119629 +[2025-04-28 18:35:40,329][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 2.2416834831237793, cross_entropy: 2.2416834831237793 +[2025-04-28 18:35:41,046][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.6124682426452637, cross_entropy: 2.6124682426452637 +[2025-04-28 18:35:42,869][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 3.277254581451416, cross_entropy: 3.277254581451416 +[2025-04-28 18:35:43,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.1272404193878174, cross_entropy: 1.1272404193878174 +[2025-04-28 18:35:45,169][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 3.0960330963134766, cross_entropy: 3.0960330963134766 +[2025-04-28 18:35:45,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 1.5283722877502441, cross_entropy: 1.5283722877502441 +[2025-04-28 18:35:48,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 2.776182174682617, cross_entropy: 2.776182174682617 +[2025-04-28 18:35:49,067][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 0.8926814198493958, cross_entropy: 0.8926814198493958 +[2025-04-28 18:35:51,656][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 1.4191040992736816, cross_entropy: 1.4191040992736816 +[2025-04-28 18:35:52,359][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 1.0650522708892822, cross_entropy: 1.0650522708892822 +[2025-04-28 18:35:54,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 2.522674083709717, cross_entropy: 2.522674083709717 +[2025-04-28 18:35:54,748][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 0.4683452844619751, cross_entropy: 0.4683452844619751 +[2025-04-28 18:35:57,249][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 1.5687955617904663, cross_entropy: 1.5687955617904663 +[2025-04-28 18:35:57,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 3.133592128753662, cross_entropy: 3.133592128753662 +[2025-04-28 18:36:00,992][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.868290662765503, cross_entropy: 2.868290662765503 +[2025-04-28 18:36:01,699][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 2.3952677249908447, cross_entropy: 2.3952677249908447 +[2025-04-28 18:36:04,201][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 2.9323816299438477, cross_entropy: 2.9323816299438477 +[2025-04-28 18:36:04,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.9125523567199707, cross_entropy: 2.9125523567199707 +[2025-04-28 18:36:07,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.3643720149993896, cross_entropy: 2.3643720149993896 +[2025-04-28 18:36:07,968][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 1.841112732887268, cross_entropy: 1.841112732887268 +[2025-04-28 18:36:09,617][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 2.8314499855041504, cross_entropy: 2.8314499855041504 +[2025-04-28 18:36:10,297][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 1.0635043382644653, cross_entropy: 1.0635043382644653 +[2025-04-28 18:36:12,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 1.3998997211456299, cross_entropy: 1.3998997211456299 +[2025-04-28 18:36:13,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 1.7186617851257324, cross_entropy: 1.7186617851257324 +[2025-04-28 18:36:14,989][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 1.3775016069412231, cross_entropy: 1.3775016069412231 +[2025-04-28 18:36:15,786][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 2.6638975143432617, cross_entropy: 2.6638975143432617 +[2025-04-28 18:36:18,008][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 2.838728189468384, cross_entropy: 2.838728189468384 +[2025-04-28 18:36:19,598][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.1223260164260864, cross_entropy: 1.1223260164260864 +[2025-04-28 18:36:20,802][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.200263738632202, cross_entropy: 2.200263738632202 +[2025-04-28 18:36:22,189][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 2.675518274307251, cross_entropy: 2.675518274307251 +[2025-04-28 18:36:23,940][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 2.1419992446899414, cross_entropy: 2.1419992446899414 +[2025-04-28 18:36:25,620][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.262526035308838, cross_entropy: 1.262526035308838 +[2025-04-28 18:36:27,009][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.519561290740967, cross_entropy: 2.519561290740967 +[2025-04-28 18:36:28,622][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 1.291841983795166, cross_entropy: 1.291841983795166 +[2025-04-28 18:36:29,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 1.2929599285125732, cross_entropy: 1.2929599285125732 +[2025-04-28 18:36:31,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 1.2322585582733154, cross_entropy: 1.2322585582733154 +[2025-04-28 18:36:33,008][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 1.6495888233184814, cross_entropy: 1.6495888233184814 +[2025-04-28 18:36:35,054][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 3.2633070945739746, cross_entropy: 3.2633070945739746 +[2025-04-28 18:36:36,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 1.3332171440124512, cross_entropy: 1.3332171440124512 +[2025-04-28 18:36:38,252][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.8108301162719727, cross_entropy: 2.8108301162719727 +[2025-04-28 18:36:38,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 1.1340141296386719, cross_entropy: 1.1340141296386719 +[2025-04-28 18:36:42,070][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.919568657875061, cross_entropy: 1.919568657875061 +[2025-04-28 18:36:42,778][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 0.9182669520378113, cross_entropy: 0.9182669520378113 +[2025-04-28 18:36:44,461][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 2.619143009185791, cross_entropy: 2.619143009185791 +[2025-04-28 18:36:45,142][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.2378588914871216, cross_entropy: 1.2378588914871216 +[2025-04-28 18:36:47,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 1.8718445301055908, cross_entropy: 1.8718445301055908 +[2025-04-28 18:36:48,260][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 1.4918537139892578, cross_entropy: 1.4918537139892578 +[2025-04-28 18:36:50,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.5450756549835205, cross_entropy: 2.5450756549835205 +[2025-04-28 18:36:51,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.7179572582244873, cross_entropy: 1.7179572582244873 +[2025-04-28 18:36:52,816][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.447383403778076, cross_entropy: 2.447383403778076 +[2025-04-28 18:36:54,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.5423851013183594, cross_entropy: 2.5423851013183594 +[2025-04-28 18:36:55,906][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 1.110915184020996, cross_entropy: 1.110915184020996 +[2025-04-28 18:36:58,119][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.9205713272094727, cross_entropy: 2.9205713272094727 +[2025-04-28 18:36:59,777][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.7770791053771973, cross_entropy: 2.7770791053771973 +[2025-04-28 18:37:01,197][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 3.1069812774658203, cross_entropy: 3.1069812774658203 +[2025-04-28 18:37:02,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 1.0977129936218262, cross_entropy: 1.0977129936218262 +[2025-04-28 18:37:04,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.6036226749420166, cross_entropy: 1.6036226749420166 +[2025-04-28 18:37:05,359][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 2.469818353652954, cross_entropy: 2.469818353652954 +[2025-04-28 18:37:07,136][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 1.3663274049758911, cross_entropy: 1.3663274049758911 +[2025-04-28 18:37:08,090][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.06245493888855, cross_entropy: 2.06245493888855 +[2025-04-28 18:37:09,772][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 1.9430955648422241, cross_entropy: 1.9430955648422241 +[2025-04-28 18:37:11,084][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 2.693143129348755, cross_entropy: 2.693143129348755 +[2025-04-28 18:37:12,806][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 1.9914429187774658, cross_entropy: 1.9914429187774658 +[2025-04-28 18:37:14,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 1.5485508441925049, cross_entropy: 1.5485508441925049 +[2025-04-28 18:37:16,186][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 2.922109365463257, cross_entropy: 2.922109365463257 +[2025-04-28 18:37:17,167][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 0.7349319458007812, cross_entropy: 0.7349319458007812 +[2025-04-28 18:37:19,321][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.2290961742401123, cross_entropy: 2.2290961742401123 +[2025-04-28 18:37:20,074][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 2.2384543418884277, cross_entropy: 2.2384543418884277 +[2025-04-28 18:37:21,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 1.223353385925293, cross_entropy: 1.223353385925293 +[2025-04-28 18:37:22,668][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 2.424712657928467, cross_entropy: 2.424712657928467 +[2025-04-28 18:37:25,404][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 2.7174973487854004, cross_entropy: 2.7174973487854004 +[2025-04-28 18:37:26,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 1.2361695766448975, cross_entropy: 1.2361695766448975 +[2025-04-28 18:37:30,742][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.197007179260254, cross_entropy: 2.197007179260254 +[2025-04-28 18:37:31,456][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 1.188884973526001, cross_entropy: 1.188884973526001 +[2025-04-28 18:37:33,641][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.594620704650879, cross_entropy: 2.594620704650879 +[2025-04-28 18:37:34,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.4378230571746826, cross_entropy: 2.4378230571746826 +[2025-04-28 18:37:36,237][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.825410008430481, cross_entropy: 0.825410008430481 +[2025-04-28 18:37:36,953][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 0.9830867052078247, cross_entropy: 0.9830867052078247 +[2025-04-28 18:37:39,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 0.9509226679801941, cross_entropy: 0.9509226679801941 +[2025-04-28 18:37:40,118][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 1.7096749544143677, cross_entropy: 1.7096749544143677 +[2025-04-28 18:37:41,897][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 3.0338311195373535, cross_entropy: 3.0338311195373535 +[2025-04-28 18:37:42,613][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 2.7554359436035156, cross_entropy: 2.7554359436035156 +[2025-04-28 18:37:45,156][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 0.9509928226470947, cross_entropy: 0.9509928226470947 +[2025-04-28 18:37:45,845][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.4127883911132812, cross_entropy: 1.4127883911132812 +[2025-04-28 18:37:48,319][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.532078742980957, cross_entropy: 1.532078742980957 +[2025-04-28 18:37:49,032][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 3.0908665657043457, cross_entropy: 3.0908665657043457 +[2025-04-28 18:37:51,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 0.9431682825088501, cross_entropy: 0.9431682825088501 +[2025-04-28 18:37:52,080][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.0308637619018555, cross_entropy: 1.0308637619018555 +[2025-04-28 18:37:53,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 2.953078269958496, cross_entropy: 2.953078269958496 +[2025-04-28 18:37:54,534][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 2.957826852798462, cross_entropy: 2.957826852798462 +[2025-04-28 18:37:56,829][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 3.183192253112793, cross_entropy: 3.183192253112793 +[2025-04-28 18:37:57,614][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.3050950765609741, cross_entropy: 1.3050950765609741 +[2025-04-28 18:38:00,098][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.8174350261688232, cross_entropy: 2.8174350261688232 +[2025-04-28 18:38:00,909][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.3662145137786865, cross_entropy: 1.3662145137786865 +[2025-04-28 18:38:03,351][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.7282655239105225, cross_entropy: 1.7282655239105225 +[2025-04-28 18:38:04,039][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 1.8304858207702637, cross_entropy: 1.8304858207702637 +[2025-04-28 18:38:06,952][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 3.122021198272705, cross_entropy: 3.122021198272705 +[2025-04-28 18:38:07,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 1.3558082580566406, cross_entropy: 1.3558082580566406 +[2025-04-28 18:38:09,693][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 1.3608506917953491, cross_entropy: 1.3608506917953491 +[2025-04-28 18:38:10,432][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 1.2002804279327393, cross_entropy: 1.2002804279327393 +[2025-04-28 18:38:13,016][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 1.0200536251068115, cross_entropy: 1.0200536251068115 +[2025-04-28 18:38:13,731][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 2.7820630073547363, cross_entropy: 2.7820630073547363 +[2025-04-28 18:38:16,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.4662113189697266, cross_entropy: 2.4662113189697266 +[2025-04-28 18:38:16,748][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.9210762977600098, cross_entropy: 2.9210762977600098 +[2025-04-28 18:38:18,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.736725330352783, cross_entropy: 2.736725330352783 +[2025-04-28 18:38:19,214][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 1.7546125650405884, cross_entropy: 1.7546125650405884 +[2025-04-28 18:38:22,118][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.5553820133209229, cross_entropy: 1.5553820133209229 +[2025-04-28 18:38:22,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 2.572939395904541, cross_entropy: 2.572939395904541 +[2025-04-28 18:38:24,658][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.496328353881836, cross_entropy: 2.496328353881836 +[2025-04-28 18:38:25,369][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 1.2525010108947754, cross_entropy: 1.2525010108947754 +[2025-04-28 18:38:27,789][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.2294931411743164, cross_entropy: 2.2294931411743164 +[2025-04-28 18:38:28,494][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.056767463684082, cross_entropy: 1.056767463684082 +[2025-04-28 18:38:31,007][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 1.969762921333313, cross_entropy: 1.969762921333313 +[2025-04-28 18:38:31,690][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 2.8965768814086914, cross_entropy: 2.8965768814086914 +[2025-04-28 18:38:33,766][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 1.2888548374176025, cross_entropy: 1.2888548374176025 +[2025-04-28 18:38:34,442][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 1.0693093538284302, cross_entropy: 1.0693093538284302 +[2025-04-28 18:38:36,903][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 1.0392379760742188, cross_entropy: 1.0392379760742188 +[2025-04-28 18:38:37,609][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 2.1770174503326416, cross_entropy: 2.1770174503326416 +[2025-04-28 18:38:39,515][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.3572916984558105, cross_entropy: 1.3572916984558105 +[2025-04-28 18:38:40,220][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 2.9903616905212402, cross_entropy: 2.9903616905212402 +[2025-04-28 18:38:42,387][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.7484922409057617, cross_entropy: 2.7484922409057617 +[2025-04-28 18:38:43,066][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 1.1252410411834717, cross_entropy: 1.1252410411834717 +[2025-04-28 18:38:45,878][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.293126344680786, cross_entropy: 2.293126344680786 +[2025-04-28 18:38:46,559][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 0.7158698439598083, cross_entropy: 0.7158698439598083 +[2025-04-28 18:38:49,150][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 2.4588847160339355, cross_entropy: 2.4588847160339355 +[2025-04-28 18:38:49,859][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 1.7641406059265137, cross_entropy: 1.7641406059265137 +[2025-04-28 18:38:52,972][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 0.7378180027008057, cross_entropy: 0.7378180027008057 +[2025-04-28 18:38:53,656][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.7792611122131348, cross_entropy: 2.7792611122131348 +[2025-04-28 18:38:55,247][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 1.7262308597564697, cross_entropy: 1.7262308597564697 +[2025-04-28 18:38:55,952][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 1.939466953277588, cross_entropy: 1.939466953277588 +[2025-04-28 18:38:58,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.7536921501159668, cross_entropy: 1.7536921501159668 +[2025-04-28 18:38:59,562][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 0.9863879680633545, cross_entropy: 0.9863879680633545 +[2025-04-28 18:39:01,578][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.6661028861999512, cross_entropy: 1.6661028861999512 +[2025-04-28 18:39:02,294][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 1.2824201583862305, cross_entropy: 1.2824201583862305 +[2025-04-28 18:39:04,830][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.79338002204895, cross_entropy: 2.79338002204895 +[2025-04-28 18:39:05,537][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 2.9128410816192627, cross_entropy: 2.9128410816192627 +[2025-04-28 18:39:08,095][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 1.6493141651153564, cross_entropy: 1.6493141651153564 +[2025-04-28 18:39:08,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 2.753049850463867, cross_entropy: 2.753049850463867 +[2025-04-28 18:39:10,713][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 2.4029300212860107, cross_entropy: 2.4029300212860107 +[2025-04-28 18:39:11,487][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.0986390113830566, cross_entropy: 1.0986390113830566 +[2025-04-28 18:39:13,816][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 2.7745189666748047, cross_entropy: 2.7745189666748047 +[2025-04-28 18:39:14,555][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.8612724542617798, cross_entropy: 1.8612724542617798 +[2025-04-28 18:39:17,107][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 3.404675006866455, cross_entropy: 3.404675006866455 +[2025-04-28 18:39:18,022][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 1.6057099103927612, cross_entropy: 1.6057099103927612 +[2025-04-28 18:39:19,561][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 1.8217114210128784, cross_entropy: 1.8217114210128784 +[2025-04-28 18:39:21,429][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 0.8906857371330261, cross_entropy: 0.8906857371330261 +[2025-04-28 18:39:22,195][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.2293986082077026, cross_entropy: 1.2293986082077026 +[2025-04-28 18:39:23,768][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.9632961750030518, cross_entropy: 1.9632961750030518 +[2025-04-28 18:39:25,364][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 0.8732693195343018, cross_entropy: 0.8732693195343018 +[2025-04-28 18:39:26,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 2.4785704612731934, cross_entropy: 2.4785704612731934 +[2025-04-28 18:39:29,388][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.8861515522003174, cross_entropy: 2.8861515522003174 +[2025-04-28 18:39:30,341][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 1.682471513748169, cross_entropy: 1.682471513748169 +[2025-04-28 18:39:32,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 1.0278632640838623, cross_entropy: 1.0278632640838623 +[2025-04-28 18:39:33,242][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.575514078140259, cross_entropy: 2.575514078140259 +[2025-04-28 18:39:35,396][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 1.3918838500976562, cross_entropy: 1.3918838500976562 +[2025-04-28 18:39:36,672][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 3.0189049243927, cross_entropy: 3.0189049243927 +[2025-04-28 18:39:38,830][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.156881332397461, cross_entropy: 2.156881332397461 +[2025-04-28 18:39:39,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 1.3451874256134033, cross_entropy: 1.3451874256134033 +[2025-04-28 18:39:41,897][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 1.0342611074447632, cross_entropy: 1.0342611074447632 +[2025-04-28 18:39:42,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.9192440509796143, cross_entropy: 1.9192440509796143 +[2025-04-28 18:39:44,688][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 1.5902159214019775, cross_entropy: 1.5902159214019775 +[2025-04-28 18:39:45,398][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 1.8710243701934814, cross_entropy: 1.8710243701934814 +[2025-04-28 18:39:47,143][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 2.6448612213134766, cross_entropy: 2.6448612213134766 +[2025-04-28 18:39:47,873][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.1519489288330078, cross_entropy: 1.1519489288330078 +[2025-04-28 18:39:50,359][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 2.1238675117492676, cross_entropy: 2.1238675117492676 +[2025-04-28 18:39:51,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 0.9445560574531555, cross_entropy: 0.9445560574531555 +[2025-04-28 18:39:53,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 1.969542145729065, cross_entropy: 1.969542145729065 +[2025-04-28 18:39:54,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 0.913055419921875, cross_entropy: 0.913055419921875 +[2025-04-28 18:39:56,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.2055578231811523, cross_entropy: 1.2055578231811523 +[2025-04-28 18:39:57,537][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 0.9057235717773438, cross_entropy: 0.9057235717773438 +[2025-04-28 18:40:00,824][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 2.2669925689697266, cross_entropy: 2.2669925689697266 +[2025-04-28 18:40:01,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.837031364440918, cross_entropy: 2.837031364440918 +[2025-04-28 18:40:04,021][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 1.9079899787902832, cross_entropy: 1.9079899787902832 +[2025-04-28 18:40:04,716][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.1178135871887207, cross_entropy: 2.1178135871887207 +[2025-04-28 18:40:07,878][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 2.2321038246154785, cross_entropy: 2.2321038246154785 +[2025-04-28 18:40:08,588][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 1.4616763591766357, cross_entropy: 1.4616763591766357 +[2025-04-28 18:40:10,953][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.8938466310501099, cross_entropy: 1.8938466310501099 +[2025-04-28 18:40:11,659][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 1.521567940711975, cross_entropy: 1.521567940711975 +[2025-04-28 18:40:14,330][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 2.607123374938965, cross_entropy: 2.607123374938965 +[2025-04-28 18:40:15,010][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.8178839683532715, cross_entropy: 2.8178839683532715 +[2025-04-28 18:40:17,473][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 2.3051958084106445, cross_entropy: 2.3051958084106445 +[2025-04-28 18:40:18,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 2.0462160110473633, cross_entropy: 2.0462160110473633 +[2025-04-28 18:40:20,346][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 3.037564992904663, cross_entropy: 3.037564992904663 +[2025-04-28 18:40:21,026][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.860992431640625, cross_entropy: 2.860992431640625 +[2025-04-28 18:40:23,497][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.690260410308838, cross_entropy: 2.690260410308838 +[2025-04-28 18:40:24,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.4828991889953613, cross_entropy: 2.4828991889953613 +[2025-04-28 18:40:26,068][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 1.2423597574234009, cross_entropy: 1.2423597574234009 +[2025-04-28 18:40:26,780][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 2.2772727012634277, cross_entropy: 2.2772727012634277 +[2025-04-28 18:40:28,649][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 2.449634313583374, cross_entropy: 2.449634313583374 +[2025-04-28 18:40:29,365][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 2.825185775756836, cross_entropy: 2.825185775756836 +[2025-04-28 18:40:31,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 2.7646937370300293, cross_entropy: 2.7646937370300293 +[2025-04-28 18:40:32,125][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 2.022845983505249, cross_entropy: 2.022845983505249 +[2025-04-28 18:40:34,687][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 2.6604371070861816, cross_entropy: 2.6604371070861816 +[2025-04-28 18:40:35,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 0.7338085174560547, cross_entropy: 0.7338085174560547 +[2025-04-28 18:40:37,304][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 1.8353712558746338, cross_entropy: 1.8353712558746338 +[2025-04-28 18:40:38,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.86746883392334, cross_entropy: 2.86746883392334 +[2025-04-28 18:40:40,176][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 2.909142017364502, cross_entropy: 2.909142017364502 +[2025-04-28 18:40:40,884][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.7329821586608887, cross_entropy: 2.7329821586608887 +[2025-04-28 18:40:42,790][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 1.1305376291275024, cross_entropy: 1.1305376291275024 +[2025-04-28 18:40:43,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 2.8613743782043457, cross_entropy: 2.8613743782043457 +[2025-04-28 18:40:45,312][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 1.0222954750061035, cross_entropy: 1.0222954750061035 +[2025-04-28 18:40:46,028][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 1.981431007385254, cross_entropy: 1.981431007385254 +[2025-04-28 18:40:48,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 1.170312762260437, cross_entropy: 1.170312762260437 +[2025-04-28 18:40:49,111][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 2.279895305633545, cross_entropy: 2.279895305633545 +[2025-04-28 18:40:51,717][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 1.0368905067443848, cross_entropy: 1.0368905067443848 +[2025-04-28 18:40:52,621][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 2.063082456588745, cross_entropy: 2.063082456588745 +[2025-04-28 18:40:54,531][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.1818006038665771, cross_entropy: 1.1818006038665771 +[2025-04-28 18:40:55,470][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.4803614616394043, cross_entropy: 1.4803614616394043 +[2025-04-28 18:40:58,176][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 1.9108737707138062, cross_entropy: 1.9108737707138062 +[2025-04-28 18:40:58,924][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 3.05704402923584, cross_entropy: 3.05704402923584 +[2025-04-28 18:41:01,070][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 2.949375629425049, cross_entropy: 2.949375629425049 +[2025-04-28 18:41:02,054][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 1.2562973499298096, cross_entropy: 1.2562973499298096 +[2025-04-28 18:41:03,859][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.189422130584717, cross_entropy: 2.189422130584717 +[2025-04-28 18:41:05,488][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 0.9021123647689819, cross_entropy: 0.9021123647689819 +[2025-04-28 18:41:06,577][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 1.4636512994766235, cross_entropy: 1.4636512994766235 +[2025-04-28 18:41:08,437][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 2.9114575386047363, cross_entropy: 2.9114575386047363 +[2025-04-28 18:41:09,429][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 1.3861123323440552, cross_entropy: 1.3861123323440552 +[2025-04-28 18:41:11,105][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 2.241652011871338, cross_entropy: 2.241652011871338 +[2025-04-28 18:41:12,966][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.4239401817321777, cross_entropy: 2.4239401817321777 +[2025-04-28 18:41:14,345][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 3.075981378555298, cross_entropy: 3.075981378555298 +[2025-04-28 18:41:15,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 3.0869011878967285, cross_entropy: 3.0869011878967285 +[2025-04-28 18:41:17,377][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.7774780988693237, cross_entropy: 1.7774780988693237 +[2025-04-28 18:41:19,107][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.2657849788665771, cross_entropy: 1.2657849788665771 +[2025-04-28 18:41:20,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 1.4798529148101807, cross_entropy: 1.4798529148101807 +[2025-04-28 18:41:21,655][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.940260171890259, cross_entropy: 2.940260171890259 +[2025-04-28 18:41:23,813][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 2.332932949066162, cross_entropy: 2.332932949066162 +[2025-04-28 18:41:24,602][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 1.219927191734314, cross_entropy: 1.219927191734314 +[2025-04-28 18:41:27,422][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 0.7665930390357971, cross_entropy: 0.7665930390357971 +[2025-04-28 18:41:28,128][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 2.188645839691162, cross_entropy: 2.188645839691162 +[2025-04-28 18:41:30,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 1.3607559204101562, cross_entropy: 1.3607559204101562 +[2025-04-28 18:41:31,277][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.1519526243209839, cross_entropy: 1.1519526243209839 +[2025-04-28 18:41:34,172][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 1.1960549354553223, cross_entropy: 1.1960549354553223 +[2025-04-28 18:41:34,877][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 1.3903106451034546, cross_entropy: 1.3903106451034546 +[2025-04-28 18:41:37,050][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 0.943307638168335, cross_entropy: 0.943307638168335 +[2025-04-28 18:41:37,776][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 1.1627333164215088, cross_entropy: 1.1627333164215088 +[2025-04-28 18:41:39,380][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.343367576599121, cross_entropy: 2.343367576599121 +[2025-04-28 18:41:40,090][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 1.315361499786377, cross_entropy: 1.315361499786377 +[2025-04-28 18:41:42,402][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 0.9723876714706421, cross_entropy: 0.9723876714706421 +[2025-04-28 18:41:43,106][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 1.2244583368301392, cross_entropy: 1.2244583368301392 +[2025-04-28 18:41:45,787][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.4787073135375977, cross_entropy: 2.4787073135375977 +[2025-04-28 18:41:46,576][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 1.8897706270217896, cross_entropy: 1.8897706270217896 +[2025-04-28 18:41:48,590][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 1.171103835105896, cross_entropy: 1.171103835105896 +[2025-04-28 18:41:49,528][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 2.4155797958374023, cross_entropy: 2.4155797958374023 +[2025-04-28 18:41:52,078][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 1.7886157035827637, cross_entropy: 1.7886157035827637 +[2025-04-28 18:41:52,917][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.2665882110595703, cross_entropy: 1.2665882110595703 +[2025-04-28 18:41:55,678][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 1.2697339057922363, cross_entropy: 1.2697339057922363 +[2025-04-28 18:41:56,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 0.9660094976425171, cross_entropy: 0.9660094976425171 +[2025-04-28 18:41:58,703][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.4595096111297607, cross_entropy: 1.4595096111297607 +[2025-04-28 18:41:59,426][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.8967468738555908, cross_entropy: 1.8967468738555908 +[2025-04-28 18:42:02,554][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.3554868698120117, cross_entropy: 2.3554868698120117 +[2025-04-28 18:42:03,266][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 1.6540807485580444, cross_entropy: 1.6540807485580444 +[2025-04-28 18:42:05,643][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 1.4296915531158447, cross_entropy: 1.4296915531158447 +[2025-04-28 18:42:06,333][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 3.0535850524902344, cross_entropy: 3.0535850524902344 +[2025-04-28 18:42:09,435][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 0.8792586326599121, cross_entropy: 0.8792586326599121 +[2025-04-28 18:42:10,141][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.339412212371826, cross_entropy: 2.339412212371826 +[2025-04-28 18:42:12,158][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 0.9298915863037109, cross_entropy: 0.9298915863037109 +[2025-04-28 18:42:12,861][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.196706771850586, cross_entropy: 1.196706771850586 +[2025-04-28 18:42:15,226][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 1.0761064291000366, cross_entropy: 1.0761064291000366 +[2025-04-28 18:42:15,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 2.978410005569458, cross_entropy: 2.978410005569458 +[2025-04-28 18:42:18,231][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 1.0410765409469604, cross_entropy: 1.0410765409469604 +[2025-04-28 18:42:18,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 1.3239357471466064, cross_entropy: 1.3239357471466064 +[2025-04-28 18:42:21,152][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 2.7407143115997314, cross_entropy: 2.7407143115997314 +[2025-04-28 18:42:21,832][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.2281975746154785, cross_entropy: 1.2281975746154785 +[2025-04-28 18:42:24,606][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 2.0108041763305664, cross_entropy: 2.0108041763305664 +[2025-04-28 18:42:25,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 3.0490872859954834, cross_entropy: 3.0490872859954834 +[2025-04-28 18:44:46,730][BaseTrainer][INFO] - [Epoch 10/10] (train) 1.9516081809997559, cross_entropy: 1.9516081809997559 +[2025-04-28 18:44:46,730][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.1475001573562622, cross_entropy: 1.1475001573562622 +[2025-04-28 18:44:47,628][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/best_epoch.pth. +[2025-04-28 18:44:48,118][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/epoch10.pth. +[2025-04-28 18:44:48,942][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. +[2025-04-28 18:44:49,775][BaseTrainer][INFO] - Save model: ./exp/20250428-164206/model/last.pth. diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/best_epoch.pth b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4a89dcb4c5077d4448ee15fe61562b2d8ff3921 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b93107e8cc9707e99c38826614d3fde1a95e1625a1fe6d07d2c45a47381a5501 +size 332603710 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/last.pth b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..d8527a8e8ac3b3bd648d836c877b6e432433d66b --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250428-164206/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7678995bda0bfefa653c77f5b13f6f043561f195e5d781bff3a9d89a9395ba +size 332568742 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/README.md b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/README.md new file mode 100644 index 0000000000000000000000000000000000000000..419c8dcb4677e7cb6c6d9e655f2435fcfffbf3e2 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/README.md @@ -0,0 +1,6 @@ +data=birdclef2025_reshape_15s +train=birdclef2025_swintransformer_tiny +model=birdclef2025_swintransformer_tiny +criterion=birdclef2025_categorical_cross_entropy + +public_score: 0.455 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/config.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..65b53611865d215f4950b5a9b9a8eeab7f8b2abe --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/config.yaml @@ -0,0 +1,222 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: ${..audio.sample_rate} + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-035024 + tensorboard_dir: ./tensorboard/20250429-035024 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.SwinTransformerTiny + weights: ${const:torchvision.models.Swin_T_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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: ${train.dataloader.train.collate_fn.composer.label_index_key} diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/hydra.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/hydra.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dee10c0f9185157f36ba757505cd18caad7772e7 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/hydra.yaml @@ -0,0 +1,189 @@ +hydra: + run: + dir: ./exp/20250429-035024/log/20250429-035027 + sweep: + dir: multirun/${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/20250429-035024/log/20250429-035027 + - hydra.mode=RUN + task: + - system=cuda + - preprocess=birdclef2025 + - data=birdclef2025_reshape_15s + - train=birdclef2025_reshape_swintransformer_tiny + - model=birdclef2025_swintransformer_tiny + - optimizer=adam_5e-5 + - lr_scheduler=none + - criterion=birdclef2025_categorical_cross_entropy + - preprocess.dump_format=birdclef2025 + - train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt + - train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 + - train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt + - train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 + - train.resume.continue_from= + - train.output.exp_dir=./exp/20250429-035024 + - train.output.tensorboard_dir=./tensorboard/20250429-035024 + job: + name: train + chdir: false + override_dirname: criterion=birdclef2025_categorical_cross_entropy,data=birdclef2025_reshape_15s,lr_scheduler=none,model=birdclef2025_swintransformer_tiny,optimizer=adam_5e-5,preprocess.dump_format=birdclef2025,preprocess=birdclef2025,system=cuda,train.dataset.train.feature_dir=/kaggle/input/birdclef-2025,train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt,train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025,train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt,train.output.exp_dir=./exp/20250429-035024,train.output.tensorboard_dir=./tensorboard/20250429-035024,train.resume.continue_from=,train=birdclef2025_reshape_swintransformer_tiny + 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/SwinTransformerTiny + 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/SwinTransformerTiny/conf + schema: file + provider: command-line + - path: '' + schema: structured + provider: schema + output_dir: /kaggle/working/BirdCLEF2025/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027 + choices: + criterion: birdclef2025_categorical_cross_entropy + lr_scheduler: none + optimizer: adam_5e-5 + model: birdclef2025_swintransformer_tiny + test: default + test/dataloader: default + test/dataset: default + train: birdclef2025_reshape_swintransformer_tiny + train/record: default + train/clip_gradient: default + train/dataloader: default + train/dataset: birdclef2025_primary-label + data: birdclef2025_reshape_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 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/overrides.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/overrides.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1748e1c59ea8c2a5b1613285c55df9b8ebeae97a --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/overrides.yaml @@ -0,0 +1,16 @@ +- system=cuda +- preprocess=birdclef2025 +- data=birdclef2025_reshape_15s +- train=birdclef2025_reshape_swintransformer_tiny +- model=birdclef2025_swintransformer_tiny +- optimizer=adam_5e-5 +- lr_scheduler=none +- criterion=birdclef2025_categorical_cross_entropy +- preprocess.dump_format=birdclef2025 +- train.dataset.train.list_path=dump/birdclef2025_reshape_15s/list/train.txt +- train.dataset.train.feature_dir=/kaggle/input/birdclef-2025 +- train.dataset.validation.list_path=dump/birdclef2025_reshape_15s/list/validation.txt +- train.dataset.validation.feature_dir=/kaggle/input/birdclef-2025 +- train.resume.continue_from= +- train.output.exp_dir=./exp/20250429-035024 +- train.output.tensorboard_dir=./tensorboard/20250429-035024 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/resolved_config.yaml b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/resolved_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7516082c1e0b838dee8f79122ffc72efe0b45626 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/.hydra/resolved_config.yaml @@ -0,0 +1,281 @@ +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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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: true + target_shape: 256 + melspectrogram_key: log_melspectrogram + label_index_key: label_index + alpha: 0.4 + 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.BirdCLEF2025ReshapePrimaryLabelComposer + melspectrogram_transform: + _target_: birdclef2025.transforms.birdclef.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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 + target_shape: 256 + 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/20250429-035024 + tensorboard_dir: ./tensorboard/20250429-035024 + save_checkpoint: + iteration: + every: 1000 + path: ./exp/20250429-035024/model/iteration{iteration}.pth + epoch: + every: 1 + path: ./exp/20250429-035024/model/epoch{epoch}.pth + last: + path: ./exp/20250429-035024/model/last.pth + best_epoch: + path: ./exp/20250429-035024/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.SwinTransformerTiny + weights: IMAGENET1K_V1 + num_classes: 206 +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/train.log b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/train.log new file mode 100644 index 0000000000000000000000000000000000000000..03ea213c2dba044ae64ccb9fa27b61cc0da426ba --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/log/20250429-035027/train.log @@ -0,0 +1,4066 @@ +[2025-04-29 03:50:56,317][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.BirdCLEF2024BaselineMelSpectrogram + sample_rate: 32000 + hop_length: 512 + 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_reshape_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_reshape_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.BirdCLEF2025BaselineCollator + composer: + _target_: birdclef2025.utils.data.birdclef.BirdCLEF2025ReshapePrimaryLabelComposer + 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: true + target_shape: 256 + melspectrogram_key: ${.composer.melspectrogram_key} + label_index_key: ${.composer.label_index_key} + alpha: 0.4 + 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 + target_shape: ${....train.collate_fn.composer.target_shape} + 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/20250429-035024 + tensorboard_dir: ./tensorboard/20250429-035024 + save_checkpoint: + iteration: + every: 1000 + path: ${...exp_dir}/model/iteration{iteration}.pth + epoch: + every: 1 + 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.SwinTransformerTiny + weights: ${const:torchvision.models.Swin_T_Weights.IMAGENET1K_V1} + num_classes: ${const:birdclef2025.utils.data.birdclef.num_birdclef2025_primary_labels} +optimizer: + _target_: torch.optim.Adam + lr: 5.0e-05 +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} + +[2025-04-29 03:50:56,317][BaseTrainer][INFO] - SwinTransformerTiny( + (backbone): Sequential( + (0): Sequential( + (0): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4)) + (1): Permute() + (2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + ) + (1): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=96, out_features=288, bias=True) + (proj): Linear(in_features=96, out_features=96, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.0, mode=row) + (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=96, out_features=384, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=384, out_features=96, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=96, out_features=288, bias=True) + (proj): Linear(in_features=96, out_features=96, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.018181818181818184, mode=row) + (norm2): LayerNorm((96,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=96, out_features=384, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=384, out_features=96, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (2): PatchMerging( + (reduction): Linear(in_features=384, out_features=192, bias=False) + (norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + ) + (3): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=192, out_features=576, bias=True) + (proj): Linear(in_features=192, out_features=192, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.03636363636363637, mode=row) + (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=192, out_features=768, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=768, out_features=192, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=192, out_features=576, bias=True) + (proj): Linear(in_features=192, out_features=192, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.05454545454545456, mode=row) + (norm2): LayerNorm((192,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=192, out_features=768, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=768, out_features=192, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (4): PatchMerging( + (reduction): Linear(in_features=768, out_features=384, bias=False) + (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + ) + (5): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.07272727272727274, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.09090909090909091, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (2): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.10909090909090911, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (3): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.1272727272727273, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (4): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.14545454545454548, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (5): SwinTransformerBlock( + (norm1): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=384, out_features=1152, bias=True) + (proj): Linear(in_features=384, out_features=384, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.16363636363636364, mode=row) + (norm2): LayerNorm((384,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=384, out_features=1536, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=1536, out_features=384, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + (6): PatchMerging( + (reduction): Linear(in_features=1536, out_features=768, bias=False) + (norm): LayerNorm((1536,), eps=1e-05, elementwise_affine=True) + ) + (7): Sequential( + (0): SwinTransformerBlock( + (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=768, out_features=2304, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.18181818181818182, mode=row) + (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=768, out_features=3072, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=3072, out_features=768, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + (1): SwinTransformerBlock( + (norm1): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (attn): ShiftedWindowAttention( + (qkv): Linear(in_features=768, out_features=2304, bias=True) + (proj): Linear(in_features=768, out_features=768, bias=True) + ) + (stochastic_depth): StochasticDepth(p=0.2, mode=row) + (norm2): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (mlp): MLP( + (0): Linear(in_features=768, out_features=3072, bias=True) + (1): GELU(approximate='none') + (2): Dropout(p=0.0, inplace=False) + (3): Linear(in_features=3072, out_features=768, bias=True) + (4): Dropout(p=0.0, inplace=False) + ) + ) + ) + ) + (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True) + (permute): Permute() + (avgpool): AdaptiveAvgPool2d(output_size=1) + (flatten): Flatten(start_dim=1, end_dim=-1) + (head): Linear(in_features=768, out_features=206, bias=True) +) +[2025-04-29 03:50:56,320][BaseTrainer][INFO] - # of parameters: 27677768. +[2025-04-29 03:51:03,373][BaseTrainer][INFO] - [Epoch 1/10, Iter 1/3560] 5.411228179931641, cross_entropy: 5.411228179931641 +[2025-04-29 03:51:04,322][BaseTrainer][INFO] - [Epoch 1/10, Iter 2/3560] 5.326308250427246, cross_entropy: 5.326308250427246 +[2025-04-29 03:51:05,740][BaseTrainer][INFO] - [Epoch 1/10, Iter 3/3560] 5.350808620452881, cross_entropy: 5.350808620452881 +[2025-04-29 03:51:06,746][BaseTrainer][INFO] - [Epoch 1/10, Iter 4/3560] 5.293325424194336, cross_entropy: 5.293325424194336 +[2025-04-29 03:51:10,103][BaseTrainer][INFO] - [Epoch 1/10, Iter 5/3560] 5.280702590942383, cross_entropy: 5.280702590942383 +[2025-04-29 03:51:11,163][BaseTrainer][INFO] - [Epoch 1/10, Iter 6/3560] 5.303257465362549, cross_entropy: 5.303257465362549 +[2025-04-29 03:51:14,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 7/3560] 5.257952690124512, cross_entropy: 5.257952690124512 +[2025-04-29 03:51:15,425][BaseTrainer][INFO] - [Epoch 1/10, Iter 8/3560] 5.222829818725586, cross_entropy: 5.222829818725586 +[2025-04-29 03:51:18,618][BaseTrainer][INFO] - [Epoch 1/10, Iter 9/3560] 5.211668014526367, cross_entropy: 5.211668014526367 +[2025-04-29 03:51:19,479][BaseTrainer][INFO] - [Epoch 1/10, Iter 10/3560] 5.119588851928711, cross_entropy: 5.119588851928711 +[2025-04-29 03:51:22,603][BaseTrainer][INFO] - [Epoch 1/10, Iter 11/3560] 5.196344375610352, cross_entropy: 5.196344375610352 +[2025-04-29 03:51:23,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 12/3560] 5.079385757446289, cross_entropy: 5.079385757446289 +[2025-04-29 03:51:27,623][BaseTrainer][INFO] - [Epoch 1/10, Iter 13/3560] 5.1692681312561035, cross_entropy: 5.1692681312561035 +[2025-04-29 03:51:28,548][BaseTrainer][INFO] - [Epoch 1/10, Iter 14/3560] 5.083315849304199, cross_entropy: 5.083315849304199 +[2025-04-29 03:51:32,053][BaseTrainer][INFO] - [Epoch 1/10, Iter 15/3560] 5.061381816864014, cross_entropy: 5.061381816864014 +[2025-04-29 03:51:33,000][BaseTrainer][INFO] - [Epoch 1/10, Iter 16/3560] 5.016298294067383, cross_entropy: 5.016298294067383 +[2025-04-29 03:51:36,266][BaseTrainer][INFO] - [Epoch 1/10, Iter 17/3560] 5.076254367828369, cross_entropy: 5.076254367828369 +[2025-04-29 03:51:37,214][BaseTrainer][INFO] - [Epoch 1/10, Iter 18/3560] 4.978205680847168, cross_entropy: 4.978205680847168 +[2025-04-29 03:51:40,971][BaseTrainer][INFO] - [Epoch 1/10, Iter 19/3560] 4.98561954498291, cross_entropy: 4.98561954498291 +[2025-04-29 03:51:41,916][BaseTrainer][INFO] - [Epoch 1/10, Iter 20/3560] 4.976997375488281, cross_entropy: 4.976997375488281 +[2025-04-29 03:51:45,137][BaseTrainer][INFO] - [Epoch 1/10, Iter 21/3560] 4.903976917266846, cross_entropy: 4.903976917266846 +[2025-04-29 03:51:46,014][BaseTrainer][INFO] - [Epoch 1/10, Iter 22/3560] 5.026098251342773, cross_entropy: 5.026098251342773 +[2025-04-29 03:51:49,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 23/3560] 5.024344444274902, cross_entropy: 5.024344444274902 +[2025-04-29 03:51:50,806][BaseTrainer][INFO] - [Epoch 1/10, Iter 24/3560] 5.108546257019043, cross_entropy: 5.108546257019043 +[2025-04-29 03:51:54,057][BaseTrainer][INFO] - [Epoch 1/10, Iter 25/3560] 4.844984531402588, cross_entropy: 4.844984531402588 +[2025-04-29 03:51:54,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 26/3560] 4.813947677612305, cross_entropy: 4.813947677612305 +[2025-04-29 03:51:58,549][BaseTrainer][INFO] - [Epoch 1/10, Iter 27/3560] 4.903429985046387, cross_entropy: 4.903429985046387 +[2025-04-29 03:51:59,416][BaseTrainer][INFO] - [Epoch 1/10, Iter 28/3560] 4.950313568115234, cross_entropy: 4.950313568115234 +[2025-04-29 03:52:02,770][BaseTrainer][INFO] - [Epoch 1/10, Iter 29/3560] 4.912384986877441, cross_entropy: 4.912384986877441 +[2025-04-29 03:52:03,642][BaseTrainer][INFO] - [Epoch 1/10, Iter 30/3560] 4.997768402099609, cross_entropy: 4.997768402099609 +[2025-04-29 03:52:07,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 31/3560] 4.913612365722656, cross_entropy: 4.913612365722656 +[2025-04-29 03:52:08,129][BaseTrainer][INFO] - [Epoch 1/10, Iter 32/3560] 5.040102958679199, cross_entropy: 5.040102958679199 +[2025-04-29 03:52:11,471][BaseTrainer][INFO] - [Epoch 1/10, Iter 33/3560] 4.983542442321777, cross_entropy: 4.983542442321777 +[2025-04-29 03:52:12,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 34/3560] 5.077971458435059, cross_entropy: 5.077971458435059 +[2025-04-29 03:52:15,578][BaseTrainer][INFO] - [Epoch 1/10, Iter 35/3560] 5.035216808319092, cross_entropy: 5.035216808319092 +[2025-04-29 03:52:16,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 36/3560] 4.88897705078125, cross_entropy: 4.88897705078125 +[2025-04-29 03:52:19,771][BaseTrainer][INFO] - [Epoch 1/10, Iter 37/3560] 4.830021858215332, cross_entropy: 4.830021858215332 +[2025-04-29 03:52:20,650][BaseTrainer][INFO] - [Epoch 1/10, Iter 38/3560] 4.786526203155518, cross_entropy: 4.786526203155518 +[2025-04-29 03:52:24,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 39/3560] 4.8158674240112305, cross_entropy: 4.8158674240112305 +[2025-04-29 03:52:25,188][BaseTrainer][INFO] - [Epoch 1/10, Iter 40/3560] 4.91750955581665, cross_entropy: 4.91750955581665 +[2025-04-29 03:52:28,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 41/3560] 4.846195220947266, cross_entropy: 4.846195220947266 +[2025-04-29 03:52:29,795][BaseTrainer][INFO] - [Epoch 1/10, Iter 42/3560] 4.722458839416504, cross_entropy: 4.722458839416504 +[2025-04-29 03:52:33,670][BaseTrainer][INFO] - [Epoch 1/10, Iter 43/3560] 5.0293474197387695, cross_entropy: 5.0293474197387695 +[2025-04-29 03:52:34,556][BaseTrainer][INFO] - [Epoch 1/10, Iter 44/3560] 4.793488502502441, cross_entropy: 4.793488502502441 +[2025-04-29 03:52:38,934][BaseTrainer][INFO] - [Epoch 1/10, Iter 45/3560] 4.88974666595459, cross_entropy: 4.88974666595459 +[2025-04-29 03:52:39,820][BaseTrainer][INFO] - [Epoch 1/10, Iter 46/3560] 4.956118583679199, cross_entropy: 4.956118583679199 +[2025-04-29 03:52:42,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 47/3560] 4.813953876495361, cross_entropy: 4.813953876495361 +[2025-04-29 03:52:43,845][BaseTrainer][INFO] - [Epoch 1/10, Iter 48/3560] 4.624031066894531, cross_entropy: 4.624031066894531 +[2025-04-29 03:52:47,212][BaseTrainer][INFO] - [Epoch 1/10, Iter 49/3560] 4.785970211029053, cross_entropy: 4.785970211029053 +[2025-04-29 03:52:48,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 50/3560] 4.831158638000488, cross_entropy: 4.831158638000488 +[2025-04-29 03:52:51,150][BaseTrainer][INFO] - [Epoch 1/10, Iter 51/3560] 4.750035285949707, cross_entropy: 4.750035285949707 +[2025-04-29 03:52:52,034][BaseTrainer][INFO] - [Epoch 1/10, Iter 52/3560] 4.648120880126953, cross_entropy: 4.648120880126953 +[2025-04-29 03:52:55,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 53/3560] 4.80324649810791, cross_entropy: 4.80324649810791 +[2025-04-29 03:52:55,998][BaseTrainer][INFO] - [Epoch 1/10, Iter 54/3560] 5.109537124633789, cross_entropy: 5.109537124633789 +[2025-04-29 03:52:59,719][BaseTrainer][INFO] - [Epoch 1/10, Iter 55/3560] 4.840610504150391, cross_entropy: 4.840610504150391 +[2025-04-29 03:53:00,613][BaseTrainer][INFO] - [Epoch 1/10, Iter 56/3560] 4.556056499481201, cross_entropy: 4.556056499481201 +[2025-04-29 03:53:04,627][BaseTrainer][INFO] - [Epoch 1/10, Iter 57/3560] 4.846474647521973, cross_entropy: 4.846474647521973 +[2025-04-29 03:53:05,492][BaseTrainer][INFO] - [Epoch 1/10, Iter 58/3560] 4.601120471954346, cross_entropy: 4.601120471954346 +[2025-04-29 03:53:08,939][BaseTrainer][INFO] - [Epoch 1/10, Iter 59/3560] 4.78448486328125, cross_entropy: 4.78448486328125 +[2025-04-29 03:53:09,802][BaseTrainer][INFO] - [Epoch 1/10, Iter 60/3560] 4.613044738769531, cross_entropy: 4.613044738769531 +[2025-04-29 03:53:13,412][BaseTrainer][INFO] - [Epoch 1/10, Iter 61/3560] 4.615819931030273, cross_entropy: 4.615819931030273 +[2025-04-29 03:53:14,294][BaseTrainer][INFO] - [Epoch 1/10, Iter 62/3560] 4.949972152709961, cross_entropy: 4.949972152709961 +[2025-04-29 03:53:17,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 63/3560] 4.812685012817383, cross_entropy: 4.812685012817383 +[2025-04-29 03:53:18,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 64/3560] 4.855861663818359, cross_entropy: 4.855861663818359 +[2025-04-29 03:53:21,496][BaseTrainer][INFO] - [Epoch 1/10, Iter 65/3560] 4.602956295013428, cross_entropy: 4.602956295013428 +[2025-04-29 03:53:22,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 66/3560] 4.683041572570801, cross_entropy: 4.683041572570801 +[2025-04-29 03:53:25,314][BaseTrainer][INFO] - [Epoch 1/10, Iter 67/3560] 4.872323036193848, cross_entropy: 4.872323036193848 +[2025-04-29 03:53:26,191][BaseTrainer][INFO] - [Epoch 1/10, Iter 68/3560] 5.089642524719238, cross_entropy: 5.089642524719238 +[2025-04-29 03:53:29,285][BaseTrainer][INFO] - [Epoch 1/10, Iter 69/3560] 4.5846099853515625, cross_entropy: 4.5846099853515625 +[2025-04-29 03:53:30,148][BaseTrainer][INFO] - [Epoch 1/10, Iter 70/3560] 4.599716663360596, cross_entropy: 4.599716663360596 +[2025-04-29 03:53:33,580][BaseTrainer][INFO] - [Epoch 1/10, Iter 71/3560] 4.646193504333496, cross_entropy: 4.646193504333496 +[2025-04-29 03:53:34,459][BaseTrainer][INFO] - [Epoch 1/10, Iter 72/3560] 4.676871299743652, cross_entropy: 4.676871299743652 +[2025-04-29 03:53:37,987][BaseTrainer][INFO] - [Epoch 1/10, Iter 73/3560] 4.970476150512695, cross_entropy: 4.970476150512695 +[2025-04-29 03:53:38,854][BaseTrainer][INFO] - [Epoch 1/10, Iter 74/3560] 4.961256980895996, cross_entropy: 4.961256980895996 +[2025-04-29 03:53:41,716][BaseTrainer][INFO] - [Epoch 1/10, Iter 75/3560] 4.895186424255371, cross_entropy: 4.895186424255371 +[2025-04-29 03:53:42,602][BaseTrainer][INFO] - [Epoch 1/10, Iter 76/3560] 4.773867130279541, cross_entropy: 4.773867130279541 +[2025-04-29 03:53:45,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 77/3560] 4.6993560791015625, cross_entropy: 4.6993560791015625 +[2025-04-29 03:53:46,693][BaseTrainer][INFO] - [Epoch 1/10, Iter 78/3560] 4.913639068603516, cross_entropy: 4.913639068603516 +[2025-04-29 03:53:50,184][BaseTrainer][INFO] - [Epoch 1/10, Iter 79/3560] 4.778014183044434, cross_entropy: 4.778014183044434 +[2025-04-29 03:53:51,050][BaseTrainer][INFO] - [Epoch 1/10, Iter 80/3560] 4.625033855438232, cross_entropy: 4.625033855438232 +[2025-04-29 03:53:54,101][BaseTrainer][INFO] - [Epoch 1/10, Iter 81/3560] 4.8742194175720215, cross_entropy: 4.8742194175720215 +[2025-04-29 03:53:54,966][BaseTrainer][INFO] - [Epoch 1/10, Iter 82/3560] 4.734098434448242, cross_entropy: 4.734098434448242 +[2025-04-29 03:53:58,514][BaseTrainer][INFO] - [Epoch 1/10, Iter 83/3560] 4.555626392364502, cross_entropy: 4.555626392364502 +[2025-04-29 03:53:59,382][BaseTrainer][INFO] - [Epoch 1/10, Iter 84/3560] 4.817509174346924, cross_entropy: 4.817509174346924 +[2025-04-29 03:54:02,705][BaseTrainer][INFO] - [Epoch 1/10, Iter 85/3560] 4.715076446533203, cross_entropy: 4.715076446533203 +[2025-04-29 03:54:03,584][BaseTrainer][INFO] - [Epoch 1/10, Iter 86/3560] 4.593515872955322, cross_entropy: 4.593515872955322 +[2025-04-29 03:54:07,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 87/3560] 4.72119140625, cross_entropy: 4.72119140625 +[2025-04-29 03:54:07,941][BaseTrainer][INFO] - [Epoch 1/10, Iter 88/3560] 4.659254550933838, cross_entropy: 4.659254550933838 +[2025-04-29 03:54:11,377][BaseTrainer][INFO] - [Epoch 1/10, Iter 89/3560] 4.661882400512695, cross_entropy: 4.661882400512695 +[2025-04-29 03:54:12,240][BaseTrainer][INFO] - [Epoch 1/10, Iter 90/3560] 4.7867889404296875, cross_entropy: 4.7867889404296875 +[2025-04-29 03:54:15,176][BaseTrainer][INFO] - [Epoch 1/10, Iter 91/3560] 4.788687705993652, cross_entropy: 4.788687705993652 +[2025-04-29 03:54:16,035][BaseTrainer][INFO] - [Epoch 1/10, Iter 92/3560] 4.752260208129883, cross_entropy: 4.752260208129883 +[2025-04-29 03:54:18,937][BaseTrainer][INFO] - [Epoch 1/10, Iter 93/3560] 4.8471479415893555, cross_entropy: 4.8471479415893555 +[2025-04-29 03:54:19,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 94/3560] 4.860617160797119, cross_entropy: 4.860617160797119 +[2025-04-29 03:54:22,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 95/3560] 4.898463249206543, cross_entropy: 4.898463249206543 +[2025-04-29 03:54:23,847][BaseTrainer][INFO] - [Epoch 1/10, Iter 96/3560] 4.639015197753906, cross_entropy: 4.639015197753906 +[2025-04-29 03:54:26,536][BaseTrainer][INFO] - [Epoch 1/10, Iter 97/3560] 4.690740585327148, cross_entropy: 4.690740585327148 +[2025-04-29 03:54:27,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 98/3560] 4.606671333312988, cross_entropy: 4.606671333312988 +[2025-04-29 03:54:30,466][BaseTrainer][INFO] - [Epoch 1/10, Iter 99/3560] 4.6867570877075195, cross_entropy: 4.6867570877075195 +[2025-04-29 03:54:31,408][BaseTrainer][INFO] - [Epoch 1/10, Iter 100/3560] 4.769169807434082, cross_entropy: 4.769169807434082 +[2025-04-29 03:54:34,348][BaseTrainer][INFO] - [Epoch 1/10, Iter 101/3560] 4.759827136993408, cross_entropy: 4.759827136993408 +[2025-04-29 03:54:35,266][BaseTrainer][INFO] - [Epoch 1/10, Iter 102/3560] 4.668373107910156, cross_entropy: 4.668373107910156 +[2025-04-29 03:54:38,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 103/3560] 4.704163551330566, cross_entropy: 4.704163551330566 +[2025-04-29 03:54:39,559][BaseTrainer][INFO] - [Epoch 1/10, Iter 104/3560] 4.766327381134033, cross_entropy: 4.766327381134033 +[2025-04-29 03:54:42,348][BaseTrainer][INFO] - [Epoch 1/10, Iter 105/3560] 4.8119730949401855, cross_entropy: 4.8119730949401855 +[2025-04-29 03:54:43,564][BaseTrainer][INFO] - [Epoch 1/10, Iter 106/3560] 4.879399299621582, cross_entropy: 4.879399299621582 +[2025-04-29 03:54:47,170][BaseTrainer][INFO] - [Epoch 1/10, Iter 107/3560] 4.6024017333984375, cross_entropy: 4.6024017333984375 +[2025-04-29 03:54:48,094][BaseTrainer][INFO] - [Epoch 1/10, Iter 108/3560] 4.716461658477783, cross_entropy: 4.716461658477783 +[2025-04-29 03:54:51,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 109/3560] 4.649908065795898, cross_entropy: 4.649908065795898 +[2025-04-29 03:54:52,374][BaseTrainer][INFO] - [Epoch 1/10, Iter 110/3560] 4.772797584533691, cross_entropy: 4.772797584533691 +[2025-04-29 03:54:55,501][BaseTrainer][INFO] - [Epoch 1/10, Iter 111/3560] 4.7543439865112305, cross_entropy: 4.7543439865112305 +[2025-04-29 03:54:56,423][BaseTrainer][INFO] - [Epoch 1/10, Iter 112/3560] 4.681631088256836, cross_entropy: 4.681631088256836 +[2025-04-29 03:54:59,541][BaseTrainer][INFO] - [Epoch 1/10, Iter 113/3560] 4.649949550628662, cross_entropy: 4.649949550628662 +[2025-04-29 03:55:00,400][BaseTrainer][INFO] - [Epoch 1/10, Iter 114/3560] 4.55333948135376, cross_entropy: 4.55333948135376 +[2025-04-29 03:55:03,244][BaseTrainer][INFO] - [Epoch 1/10, Iter 115/3560] 4.815901279449463, cross_entropy: 4.815901279449463 +[2025-04-29 03:55:04,131][BaseTrainer][INFO] - [Epoch 1/10, Iter 116/3560] 4.89208984375, cross_entropy: 4.89208984375 +[2025-04-29 03:55:07,398][BaseTrainer][INFO] - [Epoch 1/10, Iter 117/3560] 4.73472785949707, cross_entropy: 4.73472785949707 +[2025-04-29 03:55:08,378][BaseTrainer][INFO] - [Epoch 1/10, Iter 118/3560] 4.537909507751465, cross_entropy: 4.537909507751465 +[2025-04-29 03:55:12,072][BaseTrainer][INFO] - [Epoch 1/10, Iter 119/3560] 4.751783847808838, cross_entropy: 4.751783847808838 +[2025-04-29 03:55:12,990][BaseTrainer][INFO] - [Epoch 1/10, Iter 120/3560] 4.710554122924805, cross_entropy: 4.710554122924805 +[2025-04-29 03:55:16,680][BaseTrainer][INFO] - [Epoch 1/10, Iter 121/3560] 4.679354667663574, cross_entropy: 4.679354667663574 +[2025-04-29 03:55:17,553][BaseTrainer][INFO] - [Epoch 1/10, Iter 122/3560] 4.827630996704102, cross_entropy: 4.827630996704102 +[2025-04-29 03:55:21,060][BaseTrainer][INFO] - [Epoch 1/10, Iter 123/3560] 4.945981979370117, cross_entropy: 4.945981979370117 +[2025-04-29 03:55:21,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 124/3560] 4.674063682556152, cross_entropy: 4.674063682556152 +[2025-04-29 03:55:24,737][BaseTrainer][INFO] - [Epoch 1/10, Iter 125/3560] 4.637377738952637, cross_entropy: 4.637377738952637 +[2025-04-29 03:55:25,726][BaseTrainer][INFO] - [Epoch 1/10, Iter 126/3560] 4.891280174255371, cross_entropy: 4.891280174255371 +[2025-04-29 03:55:28,363][BaseTrainer][INFO] - [Epoch 1/10, Iter 127/3560] 4.629692077636719, cross_entropy: 4.629692077636719 +[2025-04-29 03:55:29,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 128/3560] 4.916015625, cross_entropy: 4.916015625 +[2025-04-29 03:55:32,431][BaseTrainer][INFO] - [Epoch 1/10, Iter 129/3560] 4.754817962646484, cross_entropy: 4.754817962646484 +[2025-04-29 03:55:33,355][BaseTrainer][INFO] - [Epoch 1/10, Iter 130/3560] 4.6887922286987305, cross_entropy: 4.6887922286987305 +[2025-04-29 03:55:36,377][BaseTrainer][INFO] - [Epoch 1/10, Iter 131/3560] 4.6829633712768555, cross_entropy: 4.6829633712768555 +[2025-04-29 03:55:37,266][BaseTrainer][INFO] - [Epoch 1/10, Iter 132/3560] 4.757431507110596, cross_entropy: 4.757431507110596 +[2025-04-29 03:55:40,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 133/3560] 4.563571453094482, cross_entropy: 4.563571453094482 +[2025-04-29 03:55:41,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 134/3560] 4.729748725891113, cross_entropy: 4.729748725891113 +[2025-04-29 03:55:44,434][BaseTrainer][INFO] - [Epoch 1/10, Iter 135/3560] 4.7958879470825195, cross_entropy: 4.7958879470825195 +[2025-04-29 03:55:45,461][BaseTrainer][INFO] - [Epoch 1/10, Iter 136/3560] 4.756902694702148, cross_entropy: 4.756902694702148 +[2025-04-29 03:55:48,520][BaseTrainer][INFO] - [Epoch 1/10, Iter 137/3560] 4.5798845291137695, cross_entropy: 4.5798845291137695 +[2025-04-29 03:55:49,598][BaseTrainer][INFO] - [Epoch 1/10, Iter 138/3560] 4.805875778198242, cross_entropy: 4.805875778198242 +[2025-04-29 03:55:52,887][BaseTrainer][INFO] - [Epoch 1/10, Iter 139/3560] 4.832217216491699, cross_entropy: 4.832217216491699 +[2025-04-29 03:55:54,113][BaseTrainer][INFO] - [Epoch 1/10, Iter 140/3560] 4.657682418823242, cross_entropy: 4.657682418823242 +[2025-04-29 03:55:57,159][BaseTrainer][INFO] - [Epoch 1/10, Iter 141/3560] 4.825308799743652, cross_entropy: 4.825308799743652 +[2025-04-29 03:55:58,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 142/3560] 4.547209739685059, cross_entropy: 4.547209739685059 +[2025-04-29 03:56:01,630][BaseTrainer][INFO] - [Epoch 1/10, Iter 143/3560] 4.5786333084106445, cross_entropy: 4.5786333084106445 +[2025-04-29 03:56:02,504][BaseTrainer][INFO] - [Epoch 1/10, Iter 144/3560] 4.883941650390625, cross_entropy: 4.883941650390625 +[2025-04-29 03:56:06,311][BaseTrainer][INFO] - [Epoch 1/10, Iter 145/3560] 4.700857162475586, cross_entropy: 4.700857162475586 +[2025-04-29 03:56:07,173][BaseTrainer][INFO] - [Epoch 1/10, Iter 146/3560] 4.569692134857178, cross_entropy: 4.569692134857178 +[2025-04-29 03:56:10,702][BaseTrainer][INFO] - [Epoch 1/10, Iter 147/3560] 4.740861415863037, cross_entropy: 4.740861415863037 +[2025-04-29 03:56:11,566][BaseTrainer][INFO] - [Epoch 1/10, Iter 148/3560] 4.83964729309082, cross_entropy: 4.83964729309082 +[2025-04-29 03:56:14,928][BaseTrainer][INFO] - [Epoch 1/10, Iter 149/3560] 4.726656913757324, cross_entropy: 4.726656913757324 +[2025-04-29 03:56:15,812][BaseTrainer][INFO] - [Epoch 1/10, Iter 150/3560] 4.802675247192383, cross_entropy: 4.802675247192383 +[2025-04-29 03:56:19,202][BaseTrainer][INFO] - [Epoch 1/10, Iter 151/3560] 4.765745639801025, cross_entropy: 4.765745639801025 +[2025-04-29 03:56:20,061][BaseTrainer][INFO] - [Epoch 1/10, Iter 152/3560] 4.4511542320251465, cross_entropy: 4.4511542320251465 +[2025-04-29 03:56:23,611][BaseTrainer][INFO] - [Epoch 1/10, Iter 153/3560] 4.763216972351074, cross_entropy: 4.763216972351074 +[2025-04-29 03:56:24,478][BaseTrainer][INFO] - [Epoch 1/10, Iter 154/3560] 4.70405912399292, cross_entropy: 4.70405912399292 +[2025-04-29 03:56:27,488][BaseTrainer][INFO] - [Epoch 1/10, Iter 155/3560] 4.779129505157471, cross_entropy: 4.779129505157471 +[2025-04-29 03:56:28,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 156/3560] 4.539516448974609, cross_entropy: 4.539516448974609 +[2025-04-29 03:56:31,368][BaseTrainer][INFO] - [Epoch 1/10, Iter 157/3560] 4.680275917053223, cross_entropy: 4.680275917053223 +[2025-04-29 03:56:32,246][BaseTrainer][INFO] - [Epoch 1/10, Iter 158/3560] 4.631655693054199, cross_entropy: 4.631655693054199 +[2025-04-29 03:56:35,286][BaseTrainer][INFO] - [Epoch 1/10, Iter 159/3560] 4.758448123931885, cross_entropy: 4.758448123931885 +[2025-04-29 03:56:36,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 160/3560] 4.652571678161621, cross_entropy: 4.652571678161621 +[2025-04-29 03:56:39,863][BaseTrainer][INFO] - [Epoch 1/10, Iter 161/3560] 4.841875076293945, cross_entropy: 4.841875076293945 +[2025-04-29 03:56:40,725][BaseTrainer][INFO] - [Epoch 1/10, Iter 162/3560] 4.621004104614258, cross_entropy: 4.621004104614258 +[2025-04-29 03:56:44,141][BaseTrainer][INFO] - [Epoch 1/10, Iter 163/3560] 4.70074462890625, cross_entropy: 4.70074462890625 +[2025-04-29 03:56:45,022][BaseTrainer][INFO] - [Epoch 1/10, Iter 164/3560] 4.771272659301758, cross_entropy: 4.771272659301758 +[2025-04-29 03:56:48,556][BaseTrainer][INFO] - [Epoch 1/10, Iter 165/3560] 4.537560939788818, cross_entropy: 4.537560939788818 +[2025-04-29 03:56:49,424][BaseTrainer][INFO] - [Epoch 1/10, Iter 166/3560] 4.81849479675293, cross_entropy: 4.81849479675293 +[2025-04-29 03:56:52,420][BaseTrainer][INFO] - [Epoch 1/10, Iter 167/3560] 4.763338088989258, cross_entropy: 4.763338088989258 +[2025-04-29 03:56:53,305][BaseTrainer][INFO] - [Epoch 1/10, Iter 168/3560] 4.539179801940918, cross_entropy: 4.539179801940918 +[2025-04-29 03:56:56,301][BaseTrainer][INFO] - [Epoch 1/10, Iter 169/3560] 4.557906150817871, cross_entropy: 4.557906150817871 +[2025-04-29 03:56:57,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 170/3560] 4.60353422164917, cross_entropy: 4.60353422164917 +[2025-04-29 03:57:00,376][BaseTrainer][INFO] - [Epoch 1/10, Iter 171/3560] 4.624458312988281, cross_entropy: 4.624458312988281 +[2025-04-29 03:57:01,281][BaseTrainer][INFO] - [Epoch 1/10, Iter 172/3560] 4.524557113647461, cross_entropy: 4.524557113647461 +[2025-04-29 03:57:04,235][BaseTrainer][INFO] - [Epoch 1/10, Iter 173/3560] 4.563745498657227, cross_entropy: 4.563745498657227 +[2025-04-29 03:57:05,168][BaseTrainer][INFO] - [Epoch 1/10, Iter 174/3560] 4.641665935516357, cross_entropy: 4.641665935516357 +[2025-04-29 03:57:08,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 175/3560] 4.552617073059082, cross_entropy: 4.552617073059082 +[2025-04-29 03:57:09,649][BaseTrainer][INFO] - [Epoch 1/10, Iter 176/3560] 4.60416841506958, cross_entropy: 4.60416841506958 +[2025-04-29 03:57:13,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 177/3560] 4.639400959014893, cross_entropy: 4.639400959014893 +[2025-04-29 03:57:13,987][BaseTrainer][INFO] - [Epoch 1/10, Iter 178/3560] 4.660977363586426, cross_entropy: 4.660977363586426 +[2025-04-29 03:57:17,337][BaseTrainer][INFO] - [Epoch 1/10, Iter 179/3560] 4.436344146728516, cross_entropy: 4.436344146728516 +[2025-04-29 03:57:18,222][BaseTrainer][INFO] - [Epoch 1/10, Iter 180/3560] 4.716192722320557, cross_entropy: 4.716192722320557 +[2025-04-29 03:57:21,098][BaseTrainer][INFO] - [Epoch 1/10, Iter 181/3560] 4.554729461669922, cross_entropy: 4.554729461669922 +[2025-04-29 03:57:21,960][BaseTrainer][INFO] - [Epoch 1/10, Iter 182/3560] 4.695268630981445, cross_entropy: 4.695268630981445 +[2025-04-29 03:57:25,132][BaseTrainer][INFO] - [Epoch 1/10, Iter 183/3560] 4.773662567138672, cross_entropy: 4.773662567138672 +[2025-04-29 03:57:25,991][BaseTrainer][INFO] - [Epoch 1/10, Iter 184/3560] 4.5318193435668945, cross_entropy: 4.5318193435668945 +[2025-04-29 03:57:29,561][BaseTrainer][INFO] - [Epoch 1/10, Iter 185/3560] 4.620760440826416, cross_entropy: 4.620760440826416 +[2025-04-29 03:57:30,444][BaseTrainer][INFO] - [Epoch 1/10, Iter 186/3560] 4.338088035583496, cross_entropy: 4.338088035583496 +[2025-04-29 03:57:34,724][BaseTrainer][INFO] - [Epoch 1/10, Iter 187/3560] 4.465566635131836, cross_entropy: 4.465566635131836 +[2025-04-29 03:57:35,580][BaseTrainer][INFO] - [Epoch 1/10, Iter 188/3560] 4.707744598388672, cross_entropy: 4.707744598388672 +[2025-04-29 03:57:38,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 189/3560] 4.623146057128906, cross_entropy: 4.623146057128906 +[2025-04-29 03:57:39,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 190/3560] 4.335187911987305, cross_entropy: 4.335187911987305 +[2025-04-29 03:57:42,911][BaseTrainer][INFO] - [Epoch 1/10, Iter 191/3560] 4.318432331085205, cross_entropy: 4.318432331085205 +[2025-04-29 03:57:43,768][BaseTrainer][INFO] - [Epoch 1/10, Iter 192/3560] 4.457706928253174, cross_entropy: 4.457706928253174 +[2025-04-29 03:57:47,225][BaseTrainer][INFO] - [Epoch 1/10, Iter 193/3560] 4.468080043792725, cross_entropy: 4.468080043792725 +[2025-04-29 03:57:48,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 194/3560] 4.568390369415283, cross_entropy: 4.568390369415283 +[2025-04-29 03:57:52,144][BaseTrainer][INFO] - [Epoch 1/10, Iter 195/3560] 4.584739685058594, cross_entropy: 4.584739685058594 +[2025-04-29 03:57:53,017][BaseTrainer][INFO] - [Epoch 1/10, Iter 196/3560] 4.578558921813965, cross_entropy: 4.578558921813965 +[2025-04-29 03:57:56,066][BaseTrainer][INFO] - [Epoch 1/10, Iter 197/3560] 4.428112030029297, cross_entropy: 4.428112030029297 +[2025-04-29 03:57:56,942][BaseTrainer][INFO] - [Epoch 1/10, Iter 198/3560] 4.449770927429199, cross_entropy: 4.449770927429199 +[2025-04-29 03:58:00,379][BaseTrainer][INFO] - [Epoch 1/10, Iter 199/3560] 4.496957778930664, cross_entropy: 4.496957778930664 +[2025-04-29 03:58:01,260][BaseTrainer][INFO] - [Epoch 1/10, Iter 200/3560] 4.525393486022949, cross_entropy: 4.525393486022949 +[2025-04-29 03:58:04,423][BaseTrainer][INFO] - [Epoch 1/10, Iter 201/3560] 4.583217620849609, cross_entropy: 4.583217620849609 +[2025-04-29 03:58:05,299][BaseTrainer][INFO] - [Epoch 1/10, Iter 202/3560] 4.260021209716797, cross_entropy: 4.260021209716797 +[2025-04-29 03:58:08,457][BaseTrainer][INFO] - [Epoch 1/10, Iter 203/3560] 4.436371326446533, cross_entropy: 4.436371326446533 +[2025-04-29 03:58:09,315][BaseTrainer][INFO] - [Epoch 1/10, Iter 204/3560] 4.319688320159912, cross_entropy: 4.319688320159912 +[2025-04-29 03:58:11,970][BaseTrainer][INFO] - [Epoch 1/10, Iter 205/3560] 4.820395469665527, cross_entropy: 4.820395469665527 +[2025-04-29 03:58:12,833][BaseTrainer][INFO] - [Epoch 1/10, Iter 206/3560] 4.65728759765625, cross_entropy: 4.65728759765625 +[2025-04-29 03:58:15,839][BaseTrainer][INFO] - [Epoch 1/10, Iter 207/3560] 4.517533779144287, cross_entropy: 4.517533779144287 +[2025-04-29 03:58:16,701][BaseTrainer][INFO] - [Epoch 1/10, Iter 208/3560] 4.539955139160156, cross_entropy: 4.539955139160156 +[2025-04-29 03:58:19,752][BaseTrainer][INFO] - [Epoch 1/10, Iter 209/3560] 4.4601287841796875, cross_entropy: 4.4601287841796875 +[2025-04-29 03:58:20,611][BaseTrainer][INFO] - [Epoch 1/10, Iter 210/3560] 4.457553863525391, cross_entropy: 4.457553863525391 +[2025-04-29 03:58:24,933][BaseTrainer][INFO] - [Epoch 1/10, Iter 211/3560] 4.708923816680908, cross_entropy: 4.708923816680908 +[2025-04-29 03:58:25,797][BaseTrainer][INFO] - [Epoch 1/10, Iter 212/3560] 4.420874118804932, cross_entropy: 4.420874118804932 +[2025-04-29 03:58:28,998][BaseTrainer][INFO] - [Epoch 1/10, Iter 213/3560] 4.476608753204346, cross_entropy: 4.476608753204346 +[2025-04-29 03:58:29,879][BaseTrainer][INFO] - [Epoch 1/10, Iter 214/3560] 4.5680036544799805, cross_entropy: 4.5680036544799805 +[2025-04-29 03:58:32,587][BaseTrainer][INFO] - [Epoch 1/10, Iter 215/3560] 4.408716201782227, cross_entropy: 4.408716201782227 +[2025-04-29 03:58:33,465][BaseTrainer][INFO] - [Epoch 1/10, Iter 216/3560] 4.571257591247559, cross_entropy: 4.571257591247559 +[2025-04-29 03:58:36,515][BaseTrainer][INFO] - [Epoch 1/10, Iter 217/3560] 4.148280620574951, cross_entropy: 4.148280620574951 +[2025-04-29 03:58:37,399][BaseTrainer][INFO] - [Epoch 1/10, Iter 218/3560] 4.7082109451293945, cross_entropy: 4.7082109451293945 +[2025-04-29 03:58:41,075][BaseTrainer][INFO] - [Epoch 1/10, Iter 219/3560] 4.197643756866455, cross_entropy: 4.197643756866455 +[2025-04-29 03:58:41,956][BaseTrainer][INFO] - [Epoch 1/10, Iter 220/3560] 4.497784614562988, cross_entropy: 4.497784614562988 +[2025-04-29 03:58:45,102][BaseTrainer][INFO] - [Epoch 1/10, Iter 221/3560] 4.251280784606934, cross_entropy: 4.251280784606934 +[2025-04-29 03:58:45,962][BaseTrainer][INFO] - [Epoch 1/10, Iter 222/3560] 4.9125494956970215, cross_entropy: 4.9125494956970215 +[2025-04-29 03:58:49,429][BaseTrainer][INFO] - [Epoch 1/10, Iter 223/3560] 4.520625114440918, cross_entropy: 4.520625114440918 +[2025-04-29 03:58:50,308][BaseTrainer][INFO] - [Epoch 1/10, Iter 224/3560] 4.115731716156006, cross_entropy: 4.115731716156006 +[2025-04-29 03:58:54,448][BaseTrainer][INFO] - [Epoch 1/10, Iter 225/3560] 4.238337516784668, cross_entropy: 4.238337516784668 +[2025-04-29 03:58:55,334][BaseTrainer][INFO] - [Epoch 1/10, Iter 226/3560] 4.546703338623047, cross_entropy: 4.546703338623047 +[2025-04-29 03:58:58,330][BaseTrainer][INFO] - [Epoch 1/10, Iter 227/3560] 4.207208633422852, cross_entropy: 4.207208633422852 +[2025-04-29 03:58:59,216][BaseTrainer][INFO] - [Epoch 1/10, Iter 228/3560] 4.152148246765137, cross_entropy: 4.152148246765137 +[2025-04-29 03:59:02,207][BaseTrainer][INFO] - [Epoch 1/10, Iter 229/3560] 4.342123508453369, cross_entropy: 4.342123508453369 +[2025-04-29 03:59:03,067][BaseTrainer][INFO] - [Epoch 1/10, Iter 230/3560] 3.9569246768951416, cross_entropy: 3.9569246768951416 +[2025-04-29 03:59:05,825][BaseTrainer][INFO] - [Epoch 1/10, Iter 231/3560] 4.566572189331055, cross_entropy: 4.566572189331055 +[2025-04-29 03:59:06,697][BaseTrainer][INFO] - [Epoch 1/10, Iter 232/3560] 4.501919269561768, cross_entropy: 4.501919269561768 +[2025-04-29 03:59:09,395][BaseTrainer][INFO] - [Epoch 1/10, Iter 233/3560] 4.7696638107299805, cross_entropy: 4.7696638107299805 +[2025-04-29 03:59:10,263][BaseTrainer][INFO] - [Epoch 1/10, Iter 234/3560] 4.66086483001709, cross_entropy: 4.66086483001709 +[2025-04-29 03:59:13,432][BaseTrainer][INFO] - [Epoch 1/10, Iter 235/3560] 4.385364055633545, cross_entropy: 4.385364055633545 +[2025-04-29 03:59:14,303][BaseTrainer][INFO] - [Epoch 1/10, Iter 236/3560] 4.288883209228516, cross_entropy: 4.288883209228516 +[2025-04-29 03:59:18,617][BaseTrainer][INFO] - [Epoch 1/10, Iter 237/3560] 4.354473114013672, cross_entropy: 4.354473114013672 +[2025-04-29 03:59:19,494][BaseTrainer][INFO] - [Epoch 1/10, Iter 238/3560] 4.568304538726807, cross_entropy: 4.568304538726807 +[2025-04-29 03:59:22,763][BaseTrainer][INFO] - [Epoch 1/10, Iter 239/3560] 4.563237190246582, cross_entropy: 4.563237190246582 +[2025-04-29 03:59:23,679][BaseTrainer][INFO] - [Epoch 1/10, Iter 240/3560] 4.38338565826416, cross_entropy: 4.38338565826416 +[2025-04-29 03:59:26,944][BaseTrainer][INFO] - [Epoch 1/10, Iter 241/3560] 4.000222206115723, cross_entropy: 4.000222206115723 +[2025-04-29 03:59:27,888][BaseTrainer][INFO] - [Epoch 1/10, Iter 242/3560] 4.6486968994140625, cross_entropy: 4.6486968994140625 +[2025-04-29 03:59:31,667][BaseTrainer][INFO] - [Epoch 1/10, Iter 243/3560] 4.633556842803955, cross_entropy: 4.633556842803955 +[2025-04-29 03:59:33,130][BaseTrainer][INFO] - [Epoch 1/10, Iter 244/3560] 4.660493850708008, cross_entropy: 4.660493850708008 +[2025-04-29 03:59:35,421][BaseTrainer][INFO] - [Epoch 1/10, Iter 245/3560] 3.979581117630005, cross_entropy: 3.979581117630005 +[2025-04-29 03:59:39,344][BaseTrainer][INFO] - [Epoch 1/10, Iter 246/3560] 4.221005439758301, cross_entropy: 4.221005439758301 +[2025-04-29 03:59:40,321][BaseTrainer][INFO] - [Epoch 1/10, Iter 247/3560] 4.34035587310791, cross_entropy: 4.34035587310791 +[2025-04-29 03:59:43,065][BaseTrainer][INFO] - [Epoch 1/10, Iter 248/3560] 4.27496862411499, cross_entropy: 4.27496862411499 +[2025-04-29 03:59:43,965][BaseTrainer][INFO] - [Epoch 1/10, Iter 249/3560] 4.194278717041016, cross_entropy: 4.194278717041016 +[2025-04-29 03:59:47,341][BaseTrainer][INFO] - [Epoch 1/10, Iter 250/3560] 4.183381080627441, cross_entropy: 4.183381080627441 +[2025-04-29 03:59:48,284][BaseTrainer][INFO] - [Epoch 1/10, Iter 251/3560] 4.399839878082275, cross_entropy: 4.399839878082275 +[2025-04-29 03:59:51,778][BaseTrainer][INFO] - [Epoch 1/10, Iter 252/3560] 4.283953666687012, cross_entropy: 4.283953666687012 +[2025-04-29 03:59:52,695][BaseTrainer][INFO] - [Epoch 1/10, Iter 253/3560] 4.280735015869141, cross_entropy: 4.280735015869141 +[2025-04-29 03:59:56,233][BaseTrainer][INFO] - [Epoch 1/10, Iter 254/3560] 4.40898323059082, cross_entropy: 4.40898323059082 +[2025-04-29 03:59:57,154][BaseTrainer][INFO] - [Epoch 1/10, Iter 255/3560] 4.37021541595459, cross_entropy: 4.37021541595459 +[2025-04-29 04:00:00,910][BaseTrainer][INFO] - [Epoch 1/10, Iter 256/3560] 4.32253360748291, cross_entropy: 4.32253360748291 +[2025-04-29 04:00:01,814][BaseTrainer][INFO] - [Epoch 1/10, Iter 257/3560] 4.3809099197387695, cross_entropy: 4.3809099197387695 +[2025-04-29 04:00:05,133][BaseTrainer][INFO] - [Epoch 1/10, Iter 258/3560] 4.241121292114258, cross_entropy: 4.241121292114258 +[2025-04-29 04:00:05,993][BaseTrainer][INFO] - [Epoch 1/10, Iter 259/3560] 4.146637439727783, cross_entropy: 4.146637439727783 +[2025-04-29 04:00:10,328][BaseTrainer][INFO] - [Epoch 1/10, Iter 260/3560] 4.227459907531738, cross_entropy: 4.227459907531738 +[2025-04-29 04:00:11,208][BaseTrainer][INFO] - [Epoch 1/10, Iter 261/3560] 4.057389259338379, cross_entropy: 4.057389259338379 +[2025-04-29 04:00:14,968][BaseTrainer][INFO] - [Epoch 1/10, Iter 262/3560] 3.951655387878418, cross_entropy: 3.951655387878418 +[2025-04-29 04:00:15,826][BaseTrainer][INFO] - [Epoch 1/10, Iter 263/3560] 4.291309356689453, cross_entropy: 4.291309356689453 +[2025-04-29 04:00:18,804][BaseTrainer][INFO] - [Epoch 1/10, Iter 264/3560] 4.298403739929199, cross_entropy: 4.298403739929199 +[2025-04-29 04:00:19,668][BaseTrainer][INFO] - [Epoch 1/10, Iter 265/3560] 4.179551124572754, cross_entropy: 4.179551124572754 +[2025-04-29 04:00:22,487][BaseTrainer][INFO] - [Epoch 1/10, Iter 266/3560] 4.119930744171143, cross_entropy: 4.119930744171143 +[2025-04-29 04:00:23,364][BaseTrainer][INFO] - [Epoch 1/10, Iter 267/3560] 4.073514461517334, cross_entropy: 4.073514461517334 +[2025-04-29 04:00:26,899][BaseTrainer][INFO] - [Epoch 1/10, Iter 268/3560] 4.435415267944336, cross_entropy: 4.435415267944336 +[2025-04-29 04:00:27,767][BaseTrainer][INFO] - [Epoch 1/10, Iter 269/3560] 4.220373630523682, cross_entropy: 4.220373630523682 +[2025-04-29 04:00:30,937][BaseTrainer][INFO] - [Epoch 1/10, Iter 270/3560] 4.3852996826171875, cross_entropy: 4.3852996826171875 +[2025-04-29 04:00:31,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 271/3560] 4.394962310791016, cross_entropy: 4.394962310791016 +[2025-04-29 04:00:36,764][BaseTrainer][INFO] - [Epoch 1/10, Iter 272/3560] 4.092965126037598, cross_entropy: 4.092965126037598 +[2025-04-29 04:00:37,625][BaseTrainer][INFO] - [Epoch 1/10, Iter 273/3560] 4.064014434814453, cross_entropy: 4.064014434814453 +[2025-04-29 04:00:40,568][BaseTrainer][INFO] - [Epoch 1/10, Iter 274/3560] 4.157781600952148, cross_entropy: 4.157781600952148 +[2025-04-29 04:00:41,441][BaseTrainer][INFO] - [Epoch 1/10, Iter 275/3560] 3.764064073562622, cross_entropy: 3.764064073562622 +[2025-04-29 04:00:44,385][BaseTrainer][INFO] - [Epoch 1/10, Iter 276/3560] 4.5732574462890625, cross_entropy: 4.5732574462890625 +[2025-04-29 04:00:45,254][BaseTrainer][INFO] - [Epoch 1/10, Iter 277/3560] 3.866283655166626, cross_entropy: 3.866283655166626 +[2025-04-29 04:00:48,994][BaseTrainer][INFO] - [Epoch 1/10, Iter 278/3560] 4.130692481994629, cross_entropy: 4.130692481994629 +[2025-04-29 04:00:50,085][BaseTrainer][INFO] - [Epoch 1/10, Iter 279/3560] 4.324062347412109, cross_entropy: 4.324062347412109 +[2025-04-29 04:00:53,155][BaseTrainer][INFO] - [Epoch 1/10, Iter 280/3560] 3.78397536277771, cross_entropy: 3.78397536277771 +[2025-04-29 04:00:54,096][BaseTrainer][INFO] - [Epoch 1/10, Iter 281/3560] 4.211706161499023, cross_entropy: 4.211706161499023 +[2025-04-29 04:00:57,219][BaseTrainer][INFO] - [Epoch 1/10, Iter 282/3560] 3.549536943435669, cross_entropy: 3.549536943435669 +[2025-04-29 04:00:58,165][BaseTrainer][INFO] - [Epoch 1/10, Iter 283/3560] 4.288302421569824, cross_entropy: 4.288302421569824 +[2025-04-29 04:01:01,860][BaseTrainer][INFO] - [Epoch 1/10, Iter 284/3560] 3.8461110591888428, cross_entropy: 3.8461110591888428 +[2025-04-29 04:01:02,808][BaseTrainer][INFO] - [Epoch 1/10, Iter 285/3560] 4.054022312164307, cross_entropy: 4.054022312164307 +[2025-04-29 04:01:06,540][BaseTrainer][INFO] - [Epoch 1/10, Iter 286/3560] 3.7692103385925293, cross_entropy: 3.7692103385925293 +[2025-04-29 04:01:07,480][BaseTrainer][INFO] - [Epoch 1/10, Iter 287/3560] 3.894895076751709, cross_entropy: 3.894895076751709 +[2025-04-29 04:01:10,127][BaseTrainer][INFO] - [Epoch 1/10, Iter 288/3560] 4.123183250427246, cross_entropy: 4.123183250427246 +[2025-04-29 04:01:11,076][BaseTrainer][INFO] - [Epoch 1/10, Iter 289/3560] 3.822779655456543, cross_entropy: 3.822779655456543 +[2025-04-29 04:01:14,231][BaseTrainer][INFO] - [Epoch 1/10, Iter 290/3560] 4.294681549072266, cross_entropy: 4.294681549072266 +[2025-04-29 04:01:15,195][BaseTrainer][INFO] - [Epoch 1/10, Iter 291/3560] 3.2703166007995605, cross_entropy: 3.2703166007995605 +[2025-04-29 04:01:18,621][BaseTrainer][INFO] - [Epoch 1/10, Iter 292/3560] 4.013341903686523, cross_entropy: 4.013341903686523 +[2025-04-29 04:01:19,529][BaseTrainer][INFO] - [Epoch 1/10, Iter 293/3560] 3.7534892559051514, cross_entropy: 3.7534892559051514 +[2025-04-29 04:01:22,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 294/3560] 3.7768187522888184, cross_entropy: 3.7768187522888184 +[2025-04-29 04:01:23,268][BaseTrainer][INFO] - [Epoch 1/10, Iter 295/3560] 4.524715423583984, cross_entropy: 4.524715423583984 +[2025-04-29 04:01:26,351][BaseTrainer][INFO] - [Epoch 1/10, Iter 296/3560] 3.412299633026123, cross_entropy: 3.412299633026123 +[2025-04-29 04:01:27,333][BaseTrainer][INFO] - [Epoch 1/10, Iter 297/3560] 4.092043876647949, cross_entropy: 4.092043876647949 +[2025-04-29 04:01:30,399][BaseTrainer][INFO] - [Epoch 1/10, Iter 298/3560] 3.995973825454712, cross_entropy: 3.995973825454712 +[2025-04-29 04:01:31,285][BaseTrainer][INFO] - [Epoch 1/10, Iter 299/3560] 3.9488205909729004, cross_entropy: 3.9488205909729004 +[2025-04-29 04:01:34,452][BaseTrainer][INFO] - [Epoch 1/10, Iter 300/3560] 3.5030877590179443, cross_entropy: 3.5030877590179443 +[2025-04-29 04:01:35,335][BaseTrainer][INFO] - [Epoch 1/10, Iter 301/3560] 4.390974044799805, cross_entropy: 4.390974044799805 +[2025-04-29 04:01:39,394][BaseTrainer][INFO] - [Epoch 1/10, Iter 302/3560] 4.316288471221924, cross_entropy: 4.316288471221924 +[2025-04-29 04:01:40,371][BaseTrainer][INFO] - [Epoch 1/10, Iter 303/3560] 3.958214521408081, cross_entropy: 3.958214521408081 +[2025-04-29 04:01:45,566][BaseTrainer][INFO] - [Epoch 1/10, Iter 304/3560] 4.042844772338867, cross_entropy: 4.042844772338867 +[2025-04-29 04:01:46,438][BaseTrainer][INFO] - [Epoch 1/10, Iter 305/3560] 3.6777238845825195, cross_entropy: 3.6777238845825195 +[2025-04-29 04:01:49,401][BaseTrainer][INFO] - [Epoch 1/10, Iter 306/3560] 4.215240001678467, cross_entropy: 4.215240001678467 +[2025-04-29 04:01:50,313][BaseTrainer][INFO] - [Epoch 1/10, Iter 307/3560] 4.476088523864746, cross_entropy: 4.476088523864746 +[2025-04-29 04:01:53,239][BaseTrainer][INFO] - [Epoch 1/10, Iter 308/3560] 4.27946662902832, cross_entropy: 4.27946662902832 +[2025-04-29 04:01:54,140][BaseTrainer][INFO] - [Epoch 1/10, Iter 309/3560] 3.6541216373443604, cross_entropy: 3.6541216373443604 +[2025-04-29 04:01:58,509][BaseTrainer][INFO] - [Epoch 1/10, Iter 310/3560] 3.8336126804351807, cross_entropy: 3.8336126804351807 +[2025-04-29 04:01:59,392][BaseTrainer][INFO] - [Epoch 1/10, Iter 311/3560] 3.710049867630005, cross_entropy: 3.710049867630005 +[2025-04-29 04:02:02,604][BaseTrainer][INFO] - [Epoch 1/10, Iter 312/3560] 3.4412906169891357, cross_entropy: 3.4412906169891357 +[2025-04-29 04:02:03,470][BaseTrainer][INFO] - [Epoch 1/10, Iter 313/3560] 3.906787872314453, cross_entropy: 3.906787872314453 +[2025-04-29 04:02:06,510][BaseTrainer][INFO] - [Epoch 1/10, Iter 314/3560] 3.9302117824554443, cross_entropy: 3.9302117824554443 +[2025-04-29 04:02:07,391][BaseTrainer][INFO] - [Epoch 1/10, Iter 315/3560] 3.5995850563049316, cross_entropy: 3.5995850563049316 +[2025-04-29 04:02:10,650][BaseTrainer][INFO] - [Epoch 1/10, Iter 316/3560] 4.377900123596191, cross_entropy: 4.377900123596191 +[2025-04-29 04:02:11,513][BaseTrainer][INFO] - [Epoch 1/10, Iter 317/3560] 3.7945497035980225, cross_entropy: 3.7945497035980225 +[2025-04-29 04:02:14,842][BaseTrainer][INFO] - [Epoch 1/10, Iter 318/3560] 3.875148057937622, cross_entropy: 3.875148057937622 +[2025-04-29 04:02:15,700][BaseTrainer][INFO] - [Epoch 1/10, Iter 319/3560] 3.5999393463134766, cross_entropy: 3.5999393463134766 +[2025-04-29 04:02:19,261][BaseTrainer][INFO] - [Epoch 1/10, Iter 320/3560] 3.790041208267212, cross_entropy: 3.790041208267212 +[2025-04-29 04:02:20,132][BaseTrainer][INFO] - [Epoch 1/10, Iter 321/3560] 4.082025527954102, cross_entropy: 4.082025527954102 +[2025-04-29 04:02:23,855][BaseTrainer][INFO] - [Epoch 1/10, Iter 322/3560] 4.081284999847412, cross_entropy: 4.081284999847412 +[2025-04-29 04:02:24,728][BaseTrainer][INFO] - [Epoch 1/10, Iter 323/3560] 3.6984453201293945, cross_entropy: 3.6984453201293945 +[2025-04-29 04:02:28,803][BaseTrainer][INFO] - [Epoch 1/10, Iter 324/3560] 4.3651018142700195, cross_entropy: 4.3651018142700195 +[2025-04-29 04:02:29,661][BaseTrainer][INFO] - [Epoch 1/10, Iter 325/3560] 4.012119293212891, cross_entropy: 4.012119293212891 +[2025-04-29 04:02:32,827][BaseTrainer][INFO] - [Epoch 1/10, Iter 326/3560] 4.037024021148682, cross_entropy: 4.037024021148682 +[2025-04-29 04:02:33,691][BaseTrainer][INFO] - [Epoch 1/10, Iter 327/3560] 4.0961480140686035, cross_entropy: 4.0961480140686035 +[2025-04-29 04:02:36,582][BaseTrainer][INFO] - [Epoch 1/10, Iter 328/3560] 4.258394241333008, cross_entropy: 4.258394241333008 +[2025-04-29 04:02:37,508][BaseTrainer][INFO] - [Epoch 1/10, Iter 329/3560] 3.723886489868164, cross_entropy: 3.723886489868164 +[2025-04-29 04:02:41,517][BaseTrainer][INFO] - [Epoch 1/10, Iter 330/3560] 3.8061296939849854, cross_entropy: 3.8061296939849854 +[2025-04-29 04:02:42,396][BaseTrainer][INFO] - [Epoch 1/10, Iter 331/3560] 3.6794278621673584, cross_entropy: 3.6794278621673584 +[2025-04-29 04:02:45,881][BaseTrainer][INFO] - [Epoch 1/10, Iter 332/3560] 3.815311908721924, cross_entropy: 3.815311908721924 +[2025-04-29 04:02:46,816][BaseTrainer][INFO] - [Epoch 1/10, Iter 333/3560] 3.7661361694335938, cross_entropy: 3.7661361694335938 +[2025-04-29 04:02:50,502][BaseTrainer][INFO] - [Epoch 1/10, Iter 334/3560] 3.7582733631134033, cross_entropy: 3.7582733631134033 +[2025-04-29 04:02:51,381][BaseTrainer][INFO] - [Epoch 1/10, Iter 335/3560] 3.940930128097534, cross_entropy: 3.940930128097534 +[2025-04-29 04:02:54,359][BaseTrainer][INFO] - [Epoch 1/10, Iter 336/3560] 3.982063055038452, cross_entropy: 3.982063055038452 +[2025-04-29 04:02:55,291][BaseTrainer][INFO] - [Epoch 1/10, Iter 337/3560] 4.292200565338135, cross_entropy: 4.292200565338135 +[2025-04-29 04:02:58,347][BaseTrainer][INFO] - [Epoch 1/10, Iter 338/3560] 4.428729057312012, cross_entropy: 4.428729057312012 +[2025-04-29 04:02:59,348][BaseTrainer][INFO] - [Epoch 1/10, Iter 339/3560] 3.5893847942352295, cross_entropy: 3.5893847942352295 +[2025-04-29 04:03:02,936][BaseTrainer][INFO] - [Epoch 1/10, Iter 340/3560] 3.222172975540161, cross_entropy: 3.222172975540161 +[2025-04-29 04:03:03,947][BaseTrainer][INFO] - [Epoch 1/10, Iter 341/3560] 3.8427724838256836, cross_entropy: 3.8427724838256836 +[2025-04-29 04:03:07,230][BaseTrainer][INFO] - [Epoch 1/10, Iter 342/3560] 3.3253493309020996, cross_entropy: 3.3253493309020996 +[2025-04-29 04:03:08,427][BaseTrainer][INFO] - [Epoch 1/10, Iter 343/3560] 4.099583148956299, cross_entropy: 4.099583148956299 +[2025-04-29 04:03:11,644][BaseTrainer][INFO] - [Epoch 1/10, Iter 344/3560] 3.8094663619995117, cross_entropy: 3.8094663619995117 +[2025-04-29 04:03:12,610][BaseTrainer][INFO] - [Epoch 1/10, Iter 345/3560] 3.0844647884368896, cross_entropy: 3.0844647884368896 +[2025-04-29 04:03:15,721][BaseTrainer][INFO] - [Epoch 1/10, Iter 346/3560] 3.9478559494018555, cross_entropy: 3.9478559494018555 +[2025-04-29 04:03:16,635][BaseTrainer][INFO] - [Epoch 1/10, Iter 347/3560] 3.077096462249756, cross_entropy: 3.077096462249756 +[2025-04-29 04:03:19,849][BaseTrainer][INFO] - [Epoch 1/10, Iter 348/3560] 4.294935703277588, cross_entropy: 4.294935703277588 +[2025-04-29 04:03:20,742][BaseTrainer][INFO] - [Epoch 1/10, Iter 349/3560] 4.3177947998046875, cross_entropy: 4.3177947998046875 +[2025-04-29 04:03:24,843][BaseTrainer][INFO] - [Epoch 1/10, Iter 350/3560] 3.702781915664673, cross_entropy: 3.702781915664673 +[2025-04-29 04:03:25,708][BaseTrainer][INFO] - [Epoch 1/10, Iter 351/3560] 4.233819961547852, cross_entropy: 4.233819961547852 +[2025-04-29 04:03:29,043][BaseTrainer][INFO] - [Epoch 1/10, Iter 352/3560] 4.336699485778809, cross_entropy: 4.336699485778809 +[2025-04-29 04:03:30,105][BaseTrainer][INFO] - [Epoch 1/10, Iter 353/3560] 3.6021742820739746, cross_entropy: 3.6021742820739746 +[2025-04-29 04:03:32,873][BaseTrainer][INFO] - [Epoch 1/10, Iter 354/3560] 4.2480363845825195, cross_entropy: 4.2480363845825195 +[2025-04-29 04:03:33,736][BaseTrainer][INFO] - [Epoch 1/10, Iter 355/3560] 3.831845283508301, cross_entropy: 3.831845283508301 +[2025-04-29 04:03:36,889][BaseTrainer][INFO] - [Epoch 1/10, Iter 356/3560] 3.483886241912842, cross_entropy: 3.483886241912842 +[2025-04-29 04:06:49,978][BaseTrainer][INFO] - [Epoch 1/10] (train) 4.491538047790527, cross_entropy: 4.491538047790527 +[2025-04-29 04:06:49,979][BaseTrainer][INFO] - [Epoch 1/10] (validation) 3.30770206451416, cross_entropy: 3.30770206451416 +[2025-04-29 04:06:50,463][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 04:06:50,939][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch1.pth. +[2025-04-29 04:06:51,409][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 04:06:56,437][BaseTrainer][INFO] - [Epoch 2/10, Iter 357/3560] 4.265798568725586, cross_entropy: 4.265798568725586 +[2025-04-29 04:06:57,318][BaseTrainer][INFO] - [Epoch 2/10, Iter 358/3560] 4.42331600189209, cross_entropy: 4.42331600189209 +[2025-04-29 04:06:59,933][BaseTrainer][INFO] - [Epoch 2/10, Iter 359/3560] 3.6322078704833984, cross_entropy: 3.6322078704833984 +[2025-04-29 04:07:00,820][BaseTrainer][INFO] - [Epoch 2/10, Iter 360/3560] 4.206532955169678, cross_entropy: 4.206532955169678 +[2025-04-29 04:07:03,786][BaseTrainer][INFO] - [Epoch 2/10, Iter 361/3560] 3.486245632171631, cross_entropy: 3.486245632171631 +[2025-04-29 04:07:04,639][BaseTrainer][INFO] - [Epoch 2/10, Iter 362/3560] 3.714881181716919, cross_entropy: 3.714881181716919 +[2025-04-29 04:07:07,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 363/3560] 3.8980143070220947, cross_entropy: 3.8980143070220947 +[2025-04-29 04:07:08,822][BaseTrainer][INFO] - [Epoch 2/10, Iter 364/3560] 3.9916999340057373, cross_entropy: 3.9916999340057373 +[2025-04-29 04:07:11,798][BaseTrainer][INFO] - [Epoch 2/10, Iter 365/3560] 3.901961326599121, cross_entropy: 3.901961326599121 +[2025-04-29 04:07:12,686][BaseTrainer][INFO] - [Epoch 2/10, Iter 366/3560] 3.7752954959869385, cross_entropy: 3.7752954959869385 +[2025-04-29 04:07:15,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 367/3560] 4.148785591125488, cross_entropy: 4.148785591125488 +[2025-04-29 04:07:16,189][BaseTrainer][INFO] - [Epoch 2/10, Iter 368/3560] 3.2265799045562744, cross_entropy: 3.2265799045562744 +[2025-04-29 04:07:19,000][BaseTrainer][INFO] - [Epoch 2/10, Iter 369/3560] 3.7123184204101562, cross_entropy: 3.7123184204101562 +[2025-04-29 04:07:19,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 370/3560] 4.0374531745910645, cross_entropy: 4.0374531745910645 +[2025-04-29 04:07:22,723][BaseTrainer][INFO] - [Epoch 2/10, Iter 371/3560] 3.551177740097046, cross_entropy: 3.551177740097046 +[2025-04-29 04:07:23,582][BaseTrainer][INFO] - [Epoch 2/10, Iter 372/3560] 4.2924675941467285, cross_entropy: 4.2924675941467285 +[2025-04-29 04:07:26,818][BaseTrainer][INFO] - [Epoch 2/10, Iter 373/3560] 3.496880531311035, cross_entropy: 3.496880531311035 +[2025-04-29 04:07:27,685][BaseTrainer][INFO] - [Epoch 2/10, Iter 374/3560] 3.565247058868408, cross_entropy: 3.565247058868408 +[2025-04-29 04:07:29,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 375/3560] 3.3897247314453125, cross_entropy: 3.3897247314453125 +[2025-04-29 04:07:30,654][BaseTrainer][INFO] - [Epoch 2/10, Iter 376/3560] 2.947176933288574, cross_entropy: 2.947176933288574 +[2025-04-29 04:07:33,576][BaseTrainer][INFO] - [Epoch 2/10, Iter 377/3560] 4.067695140838623, cross_entropy: 4.067695140838623 +[2025-04-29 04:07:34,435][BaseTrainer][INFO] - [Epoch 2/10, Iter 378/3560] 3.5632121562957764, cross_entropy: 3.5632121562957764 +[2025-04-29 04:07:37,171][BaseTrainer][INFO] - [Epoch 2/10, Iter 379/3560] 3.5535521507263184, cross_entropy: 3.5535521507263184 +[2025-04-29 04:07:38,052][BaseTrainer][INFO] - [Epoch 2/10, Iter 380/3560] 4.436768054962158, cross_entropy: 4.436768054962158 +[2025-04-29 04:07:40,610][BaseTrainer][INFO] - [Epoch 2/10, Iter 381/3560] 3.7029497623443604, cross_entropy: 3.7029497623443604 +[2025-04-29 04:07:41,477][BaseTrainer][INFO] - [Epoch 2/10, Iter 382/3560] 4.29213809967041, cross_entropy: 4.29213809967041 +[2025-04-29 04:07:44,831][BaseTrainer][INFO] - [Epoch 2/10, Iter 383/3560] 3.5911765098571777, cross_entropy: 3.5911765098571777 +[2025-04-29 04:07:45,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 384/3560] 3.911015510559082, cross_entropy: 3.911015510559082 +[2025-04-29 04:07:49,554][BaseTrainer][INFO] - [Epoch 2/10, Iter 385/3560] 4.418492317199707, cross_entropy: 4.418492317199707 +[2025-04-29 04:07:50,412][BaseTrainer][INFO] - [Epoch 2/10, Iter 386/3560] 3.9467990398406982, cross_entropy: 3.9467990398406982 +[2025-04-29 04:07:53,304][BaseTrainer][INFO] - [Epoch 2/10, Iter 387/3560] 3.937669277191162, cross_entropy: 3.937669277191162 +[2025-04-29 04:07:54,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 388/3560] 3.9123916625976562, cross_entropy: 3.9123916625976562 +[2025-04-29 04:07:57,075][BaseTrainer][INFO] - [Epoch 2/10, Iter 389/3560] 4.18856143951416, cross_entropy: 4.18856143951416 +[2025-04-29 04:07:57,958][BaseTrainer][INFO] - [Epoch 2/10, Iter 390/3560] 3.750946283340454, cross_entropy: 3.750946283340454 +[2025-04-29 04:08:00,749][BaseTrainer][INFO] - [Epoch 2/10, Iter 391/3560] 4.055242538452148, cross_entropy: 4.055242538452148 +[2025-04-29 04:08:01,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 392/3560] 3.5161261558532715, cross_entropy: 3.5161261558532715 +[2025-04-29 04:08:04,686][BaseTrainer][INFO] - [Epoch 2/10, Iter 393/3560] 3.289442539215088, cross_entropy: 3.289442539215088 +[2025-04-29 04:08:05,570][BaseTrainer][INFO] - [Epoch 2/10, Iter 394/3560] 4.022046089172363, cross_entropy: 4.022046089172363 +[2025-04-29 04:08:08,149][BaseTrainer][INFO] - [Epoch 2/10, Iter 395/3560] 4.18299674987793, cross_entropy: 4.18299674987793 +[2025-04-29 04:08:09,035][BaseTrainer][INFO] - [Epoch 2/10, Iter 396/3560] 3.293382167816162, cross_entropy: 3.293382167816162 +[2025-04-29 04:08:12,008][BaseTrainer][INFO] - [Epoch 2/10, Iter 397/3560] 3.4589996337890625, cross_entropy: 3.4589996337890625 +[2025-04-29 04:08:12,890][BaseTrainer][INFO] - [Epoch 2/10, Iter 398/3560] 3.0998764038085938, cross_entropy: 3.0998764038085938 +[2025-04-29 04:08:15,468][BaseTrainer][INFO] - [Epoch 2/10, Iter 399/3560] 3.8616440296173096, cross_entropy: 3.8616440296173096 +[2025-04-29 04:08:16,327][BaseTrainer][INFO] - [Epoch 2/10, Iter 400/3560] 3.4395484924316406, cross_entropy: 3.4395484924316406 +[2025-04-29 04:08:19,653][BaseTrainer][INFO] - [Epoch 2/10, Iter 401/3560] 3.395909309387207, cross_entropy: 3.395909309387207 +[2025-04-29 04:08:20,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 402/3560] 3.673957347869873, cross_entropy: 3.673957347869873 +[2025-04-29 04:08:23,043][BaseTrainer][INFO] - [Epoch 2/10, Iter 403/3560] 3.782221555709839, cross_entropy: 3.782221555709839 +[2025-04-29 04:08:23,923][BaseTrainer][INFO] - [Epoch 2/10, Iter 404/3560] 3.6576998233795166, cross_entropy: 3.6576998233795166 +[2025-04-29 04:08:26,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 405/3560] 2.9228322505950928, cross_entropy: 2.9228322505950928 +[2025-04-29 04:08:27,168][BaseTrainer][INFO] - [Epoch 2/10, Iter 406/3560] 4.112514019012451, cross_entropy: 4.112514019012451 +[2025-04-29 04:08:29,915][BaseTrainer][INFO] - [Epoch 2/10, Iter 407/3560] 3.5831518173217773, cross_entropy: 3.5831518173217773 +[2025-04-29 04:08:30,791][BaseTrainer][INFO] - [Epoch 2/10, Iter 408/3560] 4.2095232009887695, cross_entropy: 4.2095232009887695 +[2025-04-29 04:08:33,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 409/3560] 3.5338778495788574, cross_entropy: 3.5338778495788574 +[2025-04-29 04:08:34,197][BaseTrainer][INFO] - [Epoch 2/10, Iter 410/3560] 3.2648608684539795, cross_entropy: 3.2648608684539795 +[2025-04-29 04:08:36,966][BaseTrainer][INFO] - [Epoch 2/10, Iter 411/3560] 3.955033302307129, cross_entropy: 3.955033302307129 +[2025-04-29 04:08:37,863][BaseTrainer][INFO] - [Epoch 2/10, Iter 412/3560] 4.150869369506836, cross_entropy: 4.150869369506836 +[2025-04-29 04:08:40,119][BaseTrainer][INFO] - [Epoch 2/10, Iter 413/3560] 3.9001755714416504, cross_entropy: 3.9001755714416504 +[2025-04-29 04:08:40,992][BaseTrainer][INFO] - [Epoch 2/10, Iter 414/3560] 3.232672691345215, cross_entropy: 3.232672691345215 +[2025-04-29 04:08:43,630][BaseTrainer][INFO] - [Epoch 2/10, Iter 415/3560] 3.5087199211120605, cross_entropy: 3.5087199211120605 +[2025-04-29 04:08:44,512][BaseTrainer][INFO] - [Epoch 2/10, Iter 416/3560] 3.9055802822113037, cross_entropy: 3.9055802822113037 +[2025-04-29 04:08:47,355][BaseTrainer][INFO] - [Epoch 2/10, Iter 417/3560] 3.8518896102905273, cross_entropy: 3.8518896102905273 +[2025-04-29 04:08:48,236][BaseTrainer][INFO] - [Epoch 2/10, Iter 418/3560] 3.9051427841186523, cross_entropy: 3.9051427841186523 +[2025-04-29 04:08:51,130][BaseTrainer][INFO] - [Epoch 2/10, Iter 419/3560] 3.9728243350982666, cross_entropy: 3.9728243350982666 +[2025-04-29 04:08:51,987][BaseTrainer][INFO] - [Epoch 2/10, Iter 420/3560] 3.9931130409240723, cross_entropy: 3.9931130409240723 +[2025-04-29 04:08:55,480][BaseTrainer][INFO] - [Epoch 2/10, Iter 421/3560] 3.779557704925537, cross_entropy: 3.779557704925537 +[2025-04-29 04:08:56,339][BaseTrainer][INFO] - [Epoch 2/10, Iter 422/3560] 3.5634279251098633, cross_entropy: 3.5634279251098633 +[2025-04-29 04:08:59,099][BaseTrainer][INFO] - [Epoch 2/10, Iter 423/3560] 3.3274316787719727, cross_entropy: 3.3274316787719727 +[2025-04-29 04:08:59,986][BaseTrainer][INFO] - [Epoch 2/10, Iter 424/3560] 3.465634346008301, cross_entropy: 3.465634346008301 +[2025-04-29 04:09:02,502][BaseTrainer][INFO] - [Epoch 2/10, Iter 425/3560] 3.7899837493896484, cross_entropy: 3.7899837493896484 +[2025-04-29 04:09:03,387][BaseTrainer][INFO] - [Epoch 2/10, Iter 426/3560] 3.0367531776428223, cross_entropy: 3.0367531776428223 +[2025-04-29 04:09:06,605][BaseTrainer][INFO] - [Epoch 2/10, Iter 427/3560] 3.528761386871338, cross_entropy: 3.528761386871338 +[2025-04-29 04:09:07,486][BaseTrainer][INFO] - [Epoch 2/10, Iter 428/3560] 4.223817825317383, cross_entropy: 4.223817825317383 +[2025-04-29 04:09:10,147][BaseTrainer][INFO] - [Epoch 2/10, Iter 429/3560] 3.790984630584717, cross_entropy: 3.790984630584717 +[2025-04-29 04:09:11,029][BaseTrainer][INFO] - [Epoch 2/10, Iter 430/3560] 3.312687397003174, cross_entropy: 3.312687397003174 +[2025-04-29 04:09:13,300][BaseTrainer][INFO] - [Epoch 2/10, Iter 431/3560] 3.573166608810425, cross_entropy: 3.573166608810425 +[2025-04-29 04:09:14,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 432/3560] 4.262478828430176, cross_entropy: 4.262478828430176 +[2025-04-29 04:09:17,181][BaseTrainer][INFO] - [Epoch 2/10, Iter 433/3560] 4.033688545227051, cross_entropy: 4.033688545227051 +[2025-04-29 04:09:18,064][BaseTrainer][INFO] - [Epoch 2/10, Iter 434/3560] 3.674790382385254, cross_entropy: 3.674790382385254 +[2025-04-29 04:09:20,503][BaseTrainer][INFO] - [Epoch 2/10, Iter 435/3560] 3.4913077354431152, cross_entropy: 3.4913077354431152 +[2025-04-29 04:09:21,385][BaseTrainer][INFO] - [Epoch 2/10, Iter 436/3560] 3.5415849685668945, cross_entropy: 3.5415849685668945 +[2025-04-29 04:09:23,999][BaseTrainer][INFO] - [Epoch 2/10, Iter 437/3560] 3.8005294799804688, cross_entropy: 3.8005294799804688 +[2025-04-29 04:09:24,859][BaseTrainer][INFO] - [Epoch 2/10, Iter 438/3560] 3.351451873779297, cross_entropy: 3.351451873779297 +[2025-04-29 04:09:27,667][BaseTrainer][INFO] - [Epoch 2/10, Iter 439/3560] 3.2185685634613037, cross_entropy: 3.2185685634613037 +[2025-04-29 04:09:28,523][BaseTrainer][INFO] - [Epoch 2/10, Iter 440/3560] 3.450582981109619, cross_entropy: 3.450582981109619 +[2025-04-29 04:09:31,806][BaseTrainer][INFO] - [Epoch 2/10, Iter 441/3560] 2.805607795715332, cross_entropy: 2.805607795715332 +[2025-04-29 04:09:32,677][BaseTrainer][INFO] - [Epoch 2/10, Iter 442/3560] 4.038756370544434, cross_entropy: 4.038756370544434 +[2025-04-29 04:09:34,706][BaseTrainer][INFO] - [Epoch 2/10, Iter 443/3560] 3.339752674102783, cross_entropy: 3.339752674102783 +[2025-04-29 04:09:35,591][BaseTrainer][INFO] - [Epoch 2/10, Iter 444/3560] 3.7510032653808594, cross_entropy: 3.7510032653808594 +[2025-04-29 04:09:38,384][BaseTrainer][INFO] - [Epoch 2/10, Iter 445/3560] 3.246997117996216, cross_entropy: 3.246997117996216 +[2025-04-29 04:09:39,274][BaseTrainer][INFO] - [Epoch 2/10, Iter 446/3560] 3.472682476043701, cross_entropy: 3.472682476043701 +[2025-04-29 04:09:41,876][BaseTrainer][INFO] - [Epoch 2/10, Iter 447/3560] 3.558073043823242, cross_entropy: 3.558073043823242 +[2025-04-29 04:09:42,765][BaseTrainer][INFO] - [Epoch 2/10, Iter 448/3560] 4.1125593185424805, cross_entropy: 4.1125593185424805 +[2025-04-29 04:09:44,891][BaseTrainer][INFO] - [Epoch 2/10, Iter 449/3560] 3.879453659057617, cross_entropy: 3.879453659057617 +[2025-04-29 04:09:45,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 450/3560] 4.0033650398254395, cross_entropy: 4.0033650398254395 +[2025-04-29 04:09:48,617][BaseTrainer][INFO] - [Epoch 2/10, Iter 451/3560] 3.5629360675811768, cross_entropy: 3.5629360675811768 +[2025-04-29 04:09:49,505][BaseTrainer][INFO] - [Epoch 2/10, Iter 452/3560] 3.4709765911102295, cross_entropy: 3.4709765911102295 +[2025-04-29 04:09:52,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 453/3560] 3.6906731128692627, cross_entropy: 3.6906731128692627 +[2025-04-29 04:09:53,250][BaseTrainer][INFO] - [Epoch 2/10, Iter 454/3560] 3.0105624198913574, cross_entropy: 3.0105624198913574 +[2025-04-29 04:09:55,641][BaseTrainer][INFO] - [Epoch 2/10, Iter 455/3560] 3.321672201156616, cross_entropy: 3.321672201156616 +[2025-04-29 04:09:56,503][BaseTrainer][INFO] - [Epoch 2/10, Iter 456/3560] 3.0201072692871094, cross_entropy: 3.0201072692871094 +[2025-04-29 04:09:59,239][BaseTrainer][INFO] - [Epoch 2/10, Iter 457/3560] 2.8636057376861572, cross_entropy: 2.8636057376861572 +[2025-04-29 04:10:00,097][BaseTrainer][INFO] - [Epoch 2/10, Iter 458/3560] 3.579012632369995, cross_entropy: 3.579012632369995 +[2025-04-29 04:10:02,836][BaseTrainer][INFO] - [Epoch 2/10, Iter 459/3560] 3.3627400398254395, cross_entropy: 3.3627400398254395 +[2025-04-29 04:10:03,720][BaseTrainer][INFO] - [Epoch 2/10, Iter 460/3560] 3.0632734298706055, cross_entropy: 3.0632734298706055 +[2025-04-29 04:10:06,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 461/3560] 3.582454204559326, cross_entropy: 3.582454204559326 +[2025-04-29 04:10:07,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 462/3560] 3.9428181648254395, cross_entropy: 3.9428181648254395 +[2025-04-29 04:10:10,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 463/3560] 2.9703404903411865, cross_entropy: 2.9703404903411865 +[2025-04-29 04:10:11,334][BaseTrainer][INFO] - [Epoch 2/10, Iter 464/3560] 3.864732503890991, cross_entropy: 3.864732503890991 +[2025-04-29 04:10:14,406][BaseTrainer][INFO] - [Epoch 2/10, Iter 465/3560] 3.6385769844055176, cross_entropy: 3.6385769844055176 +[2025-04-29 04:10:15,296][BaseTrainer][INFO] - [Epoch 2/10, Iter 466/3560] 3.590243339538574, cross_entropy: 3.590243339538574 +[2025-04-29 04:10:18,320][BaseTrainer][INFO] - [Epoch 2/10, Iter 467/3560] 3.21525502204895, cross_entropy: 3.21525502204895 +[2025-04-29 04:10:19,212][BaseTrainer][INFO] - [Epoch 2/10, Iter 468/3560] 3.2253708839416504, cross_entropy: 3.2253708839416504 +[2025-04-29 04:10:21,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 469/3560] 4.17938756942749, cross_entropy: 4.17938756942749 +[2025-04-29 04:10:22,734][BaseTrainer][INFO] - [Epoch 2/10, Iter 470/3560] 3.1160755157470703, cross_entropy: 3.1160755157470703 +[2025-04-29 04:10:25,266][BaseTrainer][INFO] - [Epoch 2/10, Iter 471/3560] 3.306333065032959, cross_entropy: 3.306333065032959 +[2025-04-29 04:10:26,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 472/3560] 3.9956367015838623, cross_entropy: 3.9956367015838623 +[2025-04-29 04:10:29,758][BaseTrainer][INFO] - [Epoch 2/10, Iter 473/3560] 4.037564754486084, cross_entropy: 4.037564754486084 +[2025-04-29 04:10:30,646][BaseTrainer][INFO] - [Epoch 2/10, Iter 474/3560] 3.2524664402008057, cross_entropy: 3.2524664402008057 +[2025-04-29 04:10:34,622][BaseTrainer][INFO] - [Epoch 2/10, Iter 475/3560] 3.5908961296081543, cross_entropy: 3.5908961296081543 +[2025-04-29 04:10:35,507][BaseTrainer][INFO] - [Epoch 2/10, Iter 476/3560] 3.323613166809082, cross_entropy: 3.323613166809082 +[2025-04-29 04:10:38,373][BaseTrainer][INFO] - [Epoch 2/10, Iter 477/3560] 3.2735509872436523, cross_entropy: 3.2735509872436523 +[2025-04-29 04:10:39,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 478/3560] 4.2024946212768555, cross_entropy: 4.2024946212768555 +[2025-04-29 04:10:42,502][BaseTrainer][INFO] - [Epoch 2/10, Iter 479/3560] 3.802414655685425, cross_entropy: 3.802414655685425 +[2025-04-29 04:10:43,366][BaseTrainer][INFO] - [Epoch 2/10, Iter 480/3560] 3.7283382415771484, cross_entropy: 3.7283382415771484 +[2025-04-29 04:10:47,074][BaseTrainer][INFO] - [Epoch 2/10, Iter 481/3560] 2.6942496299743652, cross_entropy: 2.6942496299743652 +[2025-04-29 04:10:47,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 482/3560] 4.098520278930664, cross_entropy: 4.098520278930664 +[2025-04-29 04:10:50,523][BaseTrainer][INFO] - [Epoch 2/10, Iter 483/3560] 3.420071840286255, cross_entropy: 3.420071840286255 +[2025-04-29 04:10:51,415][BaseTrainer][INFO] - [Epoch 2/10, Iter 484/3560] 4.073922157287598, cross_entropy: 4.073922157287598 +[2025-04-29 04:10:53,997][BaseTrainer][INFO] - [Epoch 2/10, Iter 485/3560] 3.108610153198242, cross_entropy: 3.108610153198242 +[2025-04-29 04:10:54,858][BaseTrainer][INFO] - [Epoch 2/10, Iter 486/3560] 3.8815910816192627, cross_entropy: 3.8815910816192627 +[2025-04-29 04:10:57,661][BaseTrainer][INFO] - [Epoch 2/10, Iter 487/3560] 3.8160831928253174, cross_entropy: 3.8160831928253174 +[2025-04-29 04:10:58,551][BaseTrainer][INFO] - [Epoch 2/10, Iter 488/3560] 3.0432209968566895, cross_entropy: 3.0432209968566895 +[2025-04-29 04:11:01,430][BaseTrainer][INFO] - [Epoch 2/10, Iter 489/3560] 4.142930507659912, cross_entropy: 4.142930507659912 +[2025-04-29 04:11:02,325][BaseTrainer][INFO] - [Epoch 2/10, Iter 490/3560] 3.6127307415008545, cross_entropy: 3.6127307415008545 +[2025-04-29 04:11:05,007][BaseTrainer][INFO] - [Epoch 2/10, Iter 491/3560] 3.035158634185791, cross_entropy: 3.035158634185791 +[2025-04-29 04:11:05,882][BaseTrainer][INFO] - [Epoch 2/10, Iter 492/3560] 3.206202507019043, cross_entropy: 3.206202507019043 +[2025-04-29 04:11:08,539][BaseTrainer][INFO] - [Epoch 2/10, Iter 493/3560] 2.8616104125976562, cross_entropy: 2.8616104125976562 +[2025-04-29 04:11:09,436][BaseTrainer][INFO] - [Epoch 2/10, Iter 494/3560] 4.039885520935059, cross_entropy: 4.039885520935059 +[2025-04-29 04:11:12,746][BaseTrainer][INFO] - [Epoch 2/10, Iter 495/3560] 3.5606491565704346, cross_entropy: 3.5606491565704346 +[2025-04-29 04:11:13,648][BaseTrainer][INFO] - [Epoch 2/10, Iter 496/3560] 3.6757874488830566, cross_entropy: 3.6757874488830566 +[2025-04-29 04:11:16,356][BaseTrainer][INFO] - [Epoch 2/10, Iter 497/3560] 3.0000178813934326, cross_entropy: 3.0000178813934326 +[2025-04-29 04:11:17,242][BaseTrainer][INFO] - [Epoch 2/10, Iter 498/3560] 2.9972195625305176, cross_entropy: 2.9972195625305176 +[2025-04-29 04:11:20,613][BaseTrainer][INFO] - [Epoch 2/10, Iter 499/3560] 3.7726244926452637, cross_entropy: 3.7726244926452637 +[2025-04-29 04:11:21,499][BaseTrainer][INFO] - [Epoch 2/10, Iter 500/3560] 3.0518434047698975, cross_entropy: 3.0518434047698975 +[2025-04-29 04:11:24,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 501/3560] 2.947054862976074, cross_entropy: 2.947054862976074 +[2025-04-29 04:11:25,472][BaseTrainer][INFO] - [Epoch 2/10, Iter 502/3560] 3.1657657623291016, cross_entropy: 3.1657657623291016 +[2025-04-29 04:11:28,291][BaseTrainer][INFO] - [Epoch 2/10, Iter 503/3560] 3.1800966262817383, cross_entropy: 3.1800966262817383 +[2025-04-29 04:11:29,173][BaseTrainer][INFO] - [Epoch 2/10, Iter 504/3560] 2.6029038429260254, cross_entropy: 2.6029038429260254 +[2025-04-29 04:11:31,788][BaseTrainer][INFO] - [Epoch 2/10, Iter 505/3560] 3.3459322452545166, cross_entropy: 3.3459322452545166 +[2025-04-29 04:11:32,670][BaseTrainer][INFO] - [Epoch 2/10, Iter 506/3560] 2.8357319831848145, cross_entropy: 2.8357319831848145 +[2025-04-29 04:11:35,690][BaseTrainer][INFO] - [Epoch 2/10, Iter 507/3560] 4.305234432220459, cross_entropy: 4.305234432220459 +[2025-04-29 04:11:36,548][BaseTrainer][INFO] - [Epoch 2/10, Iter 508/3560] 3.8261637687683105, cross_entropy: 3.8261637687683105 +[2025-04-29 04:11:39,569][BaseTrainer][INFO] - [Epoch 2/10, Iter 509/3560] 3.9691293239593506, cross_entropy: 3.9691293239593506 +[2025-04-29 04:11:40,458][BaseTrainer][INFO] - [Epoch 2/10, Iter 510/3560] 2.937032699584961, cross_entropy: 2.937032699584961 +[2025-04-29 04:11:42,629][BaseTrainer][INFO] - [Epoch 2/10, Iter 511/3560] 3.212282657623291, cross_entropy: 3.212282657623291 +[2025-04-29 04:11:43,488][BaseTrainer][INFO] - [Epoch 2/10, Iter 512/3560] 3.8078861236572266, cross_entropy: 3.8078861236572266 +[2025-04-29 04:11:47,218][BaseTrainer][INFO] - [Epoch 2/10, Iter 513/3560] 2.7930397987365723, cross_entropy: 2.7930397987365723 +[2025-04-29 04:11:48,099][BaseTrainer][INFO] - [Epoch 2/10, Iter 514/3560] 3.9577531814575195, cross_entropy: 3.9577531814575195 +[2025-04-29 04:11:50,422][BaseTrainer][INFO] - [Epoch 2/10, Iter 515/3560] 3.1703970432281494, cross_entropy: 3.1703970432281494 +[2025-04-29 04:11:51,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 516/3560] 3.5777785778045654, cross_entropy: 3.5777785778045654 +[2025-04-29 04:11:53,923][BaseTrainer][INFO] - [Epoch 2/10, Iter 517/3560] 3.3135454654693604, cross_entropy: 3.3135454654693604 +[2025-04-29 04:11:54,781][BaseTrainer][INFO] - [Epoch 2/10, Iter 518/3560] 3.6540956497192383, cross_entropy: 3.6540956497192383 +[2025-04-29 04:11:57,519][BaseTrainer][INFO] - [Epoch 2/10, Iter 519/3560] 3.6520278453826904, cross_entropy: 3.6520278453826904 +[2025-04-29 04:11:58,379][BaseTrainer][INFO] - [Epoch 2/10, Iter 520/3560] 3.7951574325561523, cross_entropy: 3.7951574325561523 +[2025-04-29 04:12:01,305][BaseTrainer][INFO] - [Epoch 2/10, Iter 521/3560] 3.2996973991394043, cross_entropy: 3.2996973991394043 +[2025-04-29 04:12:02,192][BaseTrainer][INFO] - [Epoch 2/10, Iter 522/3560] 2.6534273624420166, cross_entropy: 2.6534273624420166 +[2025-04-29 04:12:04,379][BaseTrainer][INFO] - [Epoch 2/10, Iter 523/3560] 3.6122188568115234, cross_entropy: 3.6122188568115234 +[2025-04-29 04:12:05,265][BaseTrainer][INFO] - [Epoch 2/10, Iter 524/3560] 3.098959445953369, cross_entropy: 3.098959445953369 +[2025-04-29 04:12:08,532][BaseTrainer][INFO] - [Epoch 2/10, Iter 525/3560] 3.2111635208129883, cross_entropy: 3.2111635208129883 +[2025-04-29 04:12:09,413][BaseTrainer][INFO] - [Epoch 2/10, Iter 526/3560] 3.0871787071228027, cross_entropy: 3.0871787071228027 +[2025-04-29 04:12:11,994][BaseTrainer][INFO] - [Epoch 2/10, Iter 527/3560] 4.199715614318848, cross_entropy: 4.199715614318848 +[2025-04-29 04:12:12,884][BaseTrainer][INFO] - [Epoch 2/10, Iter 528/3560] 2.884760856628418, cross_entropy: 2.884760856628418 +[2025-04-29 04:12:15,206][BaseTrainer][INFO] - [Epoch 2/10, Iter 529/3560] 3.842566967010498, cross_entropy: 3.842566967010498 +[2025-04-29 04:12:16,094][BaseTrainer][INFO] - [Epoch 2/10, Iter 530/3560] 2.751349925994873, cross_entropy: 2.751349925994873 +[2025-04-29 04:12:19,530][BaseTrainer][INFO] - [Epoch 2/10, Iter 531/3560] 4.092459678649902, cross_entropy: 4.092459678649902 +[2025-04-29 04:12:20,414][BaseTrainer][INFO] - [Epoch 2/10, Iter 532/3560] 3.654115676879883, cross_entropy: 3.654115676879883 +[2025-04-29 04:12:23,847][BaseTrainer][INFO] - [Epoch 2/10, Iter 533/3560] 3.609990119934082, cross_entropy: 3.609990119934082 +[2025-04-29 04:12:24,739][BaseTrainer][INFO] - [Epoch 2/10, Iter 534/3560] 3.5311546325683594, cross_entropy: 3.5311546325683594 +[2025-04-29 04:12:27,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 535/3560] 3.005702018737793, cross_entropy: 3.005702018737793 +[2025-04-29 04:12:28,393][BaseTrainer][INFO] - [Epoch 2/10, Iter 536/3560] 3.0562868118286133, cross_entropy: 3.0562868118286133 +[2025-04-29 04:12:31,508][BaseTrainer][INFO] - [Epoch 2/10, Iter 537/3560] 2.948896884918213, cross_entropy: 2.948896884918213 +[2025-04-29 04:12:32,393][BaseTrainer][INFO] - [Epoch 2/10, Iter 538/3560] 4.201766014099121, cross_entropy: 4.201766014099121 +[2025-04-29 04:12:34,701][BaseTrainer][INFO] - [Epoch 2/10, Iter 539/3560] 3.097747325897217, cross_entropy: 3.097747325897217 +[2025-04-29 04:12:35,562][BaseTrainer][INFO] - [Epoch 2/10, Iter 540/3560] 3.424138069152832, cross_entropy: 3.424138069152832 +[2025-04-29 04:12:39,013][BaseTrainer][INFO] - [Epoch 2/10, Iter 541/3560] 2.8763504028320312, cross_entropy: 2.8763504028320312 +[2025-04-29 04:12:39,897][BaseTrainer][INFO] - [Epoch 2/10, Iter 542/3560] 3.9479942321777344, cross_entropy: 3.9479942321777344 +[2025-04-29 04:12:42,518][BaseTrainer][INFO] - [Epoch 2/10, Iter 543/3560] 2.937354564666748, cross_entropy: 2.937354564666748 +[2025-04-29 04:12:43,379][BaseTrainer][INFO] - [Epoch 2/10, Iter 544/3560] 3.2494544982910156, cross_entropy: 3.2494544982910156 +[2025-04-29 04:12:46,892][BaseTrainer][INFO] - [Epoch 2/10, Iter 545/3560] 3.6185290813446045, cross_entropy: 3.6185290813446045 +[2025-04-29 04:12:47,779][BaseTrainer][INFO] - [Epoch 2/10, Iter 546/3560] 2.8969483375549316, cross_entropy: 2.8969483375549316 +[2025-04-29 04:12:50,140][BaseTrainer][INFO] - [Epoch 2/10, Iter 547/3560] 3.2293283939361572, cross_entropy: 3.2293283939361572 +[2025-04-29 04:12:51,025][BaseTrainer][INFO] - [Epoch 2/10, Iter 548/3560] 3.2564940452575684, cross_entropy: 3.2564940452575684 +[2025-04-29 04:12:53,764][BaseTrainer][INFO] - [Epoch 2/10, Iter 549/3560] 2.683619499206543, cross_entropy: 2.683619499206543 +[2025-04-29 04:12:54,649][BaseTrainer][INFO] - [Epoch 2/10, Iter 550/3560] 3.2713005542755127, cross_entropy: 3.2713005542755127 +[2025-04-29 04:12:58,105][BaseTrainer][INFO] - [Epoch 2/10, Iter 551/3560] 2.8401308059692383, cross_entropy: 2.8401308059692383 +[2025-04-29 04:12:58,988][BaseTrainer][INFO] - [Epoch 2/10, Iter 552/3560] 3.92283034324646, cross_entropy: 3.92283034324646 +[2025-04-29 04:13:01,602][BaseTrainer][INFO] - [Epoch 2/10, Iter 553/3560] 3.369049310684204, cross_entropy: 3.369049310684204 +[2025-04-29 04:13:02,492][BaseTrainer][INFO] - [Epoch 2/10, Iter 554/3560] 3.0746212005615234, cross_entropy: 3.0746212005615234 +[2025-04-29 04:13:05,298][BaseTrainer][INFO] - [Epoch 2/10, Iter 555/3560] 3.929316759109497, cross_entropy: 3.929316759109497 +[2025-04-29 04:13:06,182][BaseTrainer][INFO] - [Epoch 2/10, Iter 556/3560] 3.291365146636963, cross_entropy: 3.291365146636963 +[2025-04-29 04:13:08,827][BaseTrainer][INFO] - [Epoch 2/10, Iter 557/3560] 3.114919900894165, cross_entropy: 3.114919900894165 +[2025-04-29 04:13:09,713][BaseTrainer][INFO] - [Epoch 2/10, Iter 558/3560] 2.412397861480713, cross_entropy: 2.412397861480713 +[2025-04-29 04:13:12,896][BaseTrainer][INFO] - [Epoch 2/10, Iter 559/3560] 3.842180013656616, cross_entropy: 3.842180013656616 +[2025-04-29 04:13:13,781][BaseTrainer][INFO] - [Epoch 2/10, Iter 560/3560] 3.770458221435547, cross_entropy: 3.770458221435547 +[2025-04-29 04:13:16,822][BaseTrainer][INFO] - [Epoch 2/10, Iter 561/3560] 3.8024964332580566, cross_entropy: 3.8024964332580566 +[2025-04-29 04:13:17,709][BaseTrainer][INFO] - [Epoch 2/10, Iter 562/3560] 3.058119058609009, cross_entropy: 3.058119058609009 +[2025-04-29 04:13:20,725][BaseTrainer][INFO] - [Epoch 2/10, Iter 563/3560] 3.1990647315979004, cross_entropy: 3.1990647315979004 +[2025-04-29 04:13:21,614][BaseTrainer][INFO] - [Epoch 2/10, Iter 564/3560] 4.195237159729004, cross_entropy: 4.195237159729004 +[2025-04-29 04:13:24,267][BaseTrainer][INFO] - [Epoch 2/10, Iter 565/3560] 2.8254480361938477, cross_entropy: 2.8254480361938477 +[2025-04-29 04:13:25,157][BaseTrainer][INFO] - [Epoch 2/10, Iter 566/3560] 3.816058874130249, cross_entropy: 3.816058874130249 +[2025-04-29 04:13:28,174][BaseTrainer][INFO] - [Epoch 2/10, Iter 567/3560] 3.585552215576172, cross_entropy: 3.585552215576172 +[2025-04-29 04:13:29,060][BaseTrainer][INFO] - [Epoch 2/10, Iter 568/3560] 2.495706796646118, cross_entropy: 2.495706796646118 +[2025-04-29 04:13:31,616][BaseTrainer][INFO] - [Epoch 2/10, Iter 569/3560] 3.8632607460021973, cross_entropy: 3.8632607460021973 +[2025-04-29 04:13:32,474][BaseTrainer][INFO] - [Epoch 2/10, Iter 570/3560] 3.8000216484069824, cross_entropy: 3.8000216484069824 +[2025-04-29 04:13:35,215][BaseTrainer][INFO] - [Epoch 2/10, Iter 571/3560] 4.131048202514648, cross_entropy: 4.131048202514648 +[2025-04-29 04:13:36,100][BaseTrainer][INFO] - [Epoch 2/10, Iter 572/3560] 2.883059024810791, cross_entropy: 2.883059024810791 +[2025-04-29 04:13:39,243][BaseTrainer][INFO] - [Epoch 2/10, Iter 573/3560] 3.127577066421509, cross_entropy: 3.127577066421509 +[2025-04-29 04:13:40,129][BaseTrainer][INFO] - [Epoch 2/10, Iter 574/3560] 2.4811553955078125, cross_entropy: 2.4811553955078125 +[2025-04-29 04:13:42,426][BaseTrainer][INFO] - [Epoch 2/10, Iter 575/3560] 2.929722785949707, cross_entropy: 2.929722785949707 +[2025-04-29 04:13:43,307][BaseTrainer][INFO] - [Epoch 2/10, Iter 576/3560] 2.722534656524658, cross_entropy: 2.722534656524658 +[2025-04-29 04:13:46,091][BaseTrainer][INFO] - [Epoch 2/10, Iter 577/3560] 2.5189781188964844, cross_entropy: 2.5189781188964844 +[2025-04-29 04:13:46,976][BaseTrainer][INFO] - [Epoch 2/10, Iter 578/3560] 3.983217716217041, cross_entropy: 3.983217716217041 +[2025-04-29 04:13:49,403][BaseTrainer][INFO] - [Epoch 2/10, Iter 579/3560] 2.6316089630126953, cross_entropy: 2.6316089630126953 +[2025-04-29 04:13:50,286][BaseTrainer][INFO] - [Epoch 2/10, Iter 580/3560] 3.3773746490478516, cross_entropy: 3.3773746490478516 +[2025-04-29 04:13:52,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 581/3560] 4.0543413162231445, cross_entropy: 4.0543413162231445 +[2025-04-29 04:13:53,619][BaseTrainer][INFO] - [Epoch 2/10, Iter 582/3560] 3.853816509246826, cross_entropy: 3.853816509246826 +[2025-04-29 04:13:56,386][BaseTrainer][INFO] - [Epoch 2/10, Iter 583/3560] 3.6605234146118164, cross_entropy: 3.6605234146118164 +[2025-04-29 04:13:57,269][BaseTrainer][INFO] - [Epoch 2/10, Iter 584/3560] 3.8224799633026123, cross_entropy: 3.8224799633026123 +[2025-04-29 04:13:59,609][BaseTrainer][INFO] - [Epoch 2/10, Iter 585/3560] 3.8117918968200684, cross_entropy: 3.8117918968200684 +[2025-04-29 04:14:00,496][BaseTrainer][INFO] - [Epoch 2/10, Iter 586/3560] 2.752183437347412, cross_entropy: 2.752183437347412 +[2025-04-29 04:14:02,901][BaseTrainer][INFO] - [Epoch 2/10, Iter 587/3560] 3.267536163330078, cross_entropy: 3.267536163330078 +[2025-04-29 04:14:03,784][BaseTrainer][INFO] - [Epoch 2/10, Iter 588/3560] 2.9991261959075928, cross_entropy: 2.9991261959075928 +[2025-04-29 04:14:06,162][BaseTrainer][INFO] - [Epoch 2/10, Iter 589/3560] 2.965982437133789, cross_entropy: 2.965982437133789 +[2025-04-29 04:14:07,044][BaseTrainer][INFO] - [Epoch 2/10, Iter 590/3560] 4.171225547790527, cross_entropy: 4.171225547790527 +[2025-04-29 04:14:09,441][BaseTrainer][INFO] - [Epoch 2/10, Iter 591/3560] 2.6209349632263184, cross_entropy: 2.6209349632263184 +[2025-04-29 04:14:10,394][BaseTrainer][INFO] - [Epoch 2/10, Iter 592/3560] 2.1059539318084717, cross_entropy: 2.1059539318084717 +[2025-04-29 04:14:13,066][BaseTrainer][INFO] - [Epoch 2/10, Iter 593/3560] 3.4195210933685303, cross_entropy: 3.4195210933685303 +[2025-04-29 04:14:13,927][BaseTrainer][INFO] - [Epoch 2/10, Iter 594/3560] 3.958282947540283, cross_entropy: 3.958282947540283 +[2025-04-29 04:14:16,733][BaseTrainer][INFO] - [Epoch 2/10, Iter 595/3560] 3.3948516845703125, cross_entropy: 3.3948516845703125 +[2025-04-29 04:14:17,640][BaseTrainer][INFO] - [Epoch 2/10, Iter 596/3560] 2.940514087677002, cross_entropy: 2.940514087677002 +[2025-04-29 04:14:20,027][BaseTrainer][INFO] - [Epoch 2/10, Iter 597/3560] 3.9935848712921143, cross_entropy: 3.9935848712921143 +[2025-04-29 04:14:21,135][BaseTrainer][INFO] - [Epoch 2/10, Iter 598/3560] 3.9150962829589844, cross_entropy: 3.9150962829589844 +[2025-04-29 04:14:23,797][BaseTrainer][INFO] - [Epoch 2/10, Iter 599/3560] 2.73343563079834, cross_entropy: 2.73343563079834 +[2025-04-29 04:14:24,684][BaseTrainer][INFO] - [Epoch 2/10, Iter 600/3560] 2.8807895183563232, cross_entropy: 2.8807895183563232 +[2025-04-29 04:14:28,183][BaseTrainer][INFO] - [Epoch 2/10, Iter 601/3560] 4.06822395324707, cross_entropy: 4.06822395324707 +[2025-04-29 04:14:29,076][BaseTrainer][INFO] - [Epoch 2/10, Iter 602/3560] 3.205763578414917, cross_entropy: 3.205763578414917 +[2025-04-29 04:14:31,400][BaseTrainer][INFO] - [Epoch 2/10, Iter 603/3560] 2.877713680267334, cross_entropy: 2.877713680267334 +[2025-04-29 04:14:32,330][BaseTrainer][INFO] - [Epoch 2/10, Iter 604/3560] 3.8019285202026367, cross_entropy: 3.8019285202026367 +[2025-04-29 04:14:35,465][BaseTrainer][INFO] - [Epoch 2/10, Iter 605/3560] 2.983471393585205, cross_entropy: 2.983471393585205 +[2025-04-29 04:14:36,349][BaseTrainer][INFO] - [Epoch 2/10, Iter 606/3560] 3.4702224731445312, cross_entropy: 3.4702224731445312 +[2025-04-29 04:14:39,234][BaseTrainer][INFO] - [Epoch 2/10, Iter 607/3560] 2.6006886959075928, cross_entropy: 2.6006886959075928 +[2025-04-29 04:14:40,162][BaseTrainer][INFO] - [Epoch 2/10, Iter 608/3560] 3.8263754844665527, cross_entropy: 3.8263754844665527 +[2025-04-29 04:14:42,500][BaseTrainer][INFO] - [Epoch 2/10, Iter 609/3560] 3.6928153038024902, cross_entropy: 3.6928153038024902 +[2025-04-29 04:14:44,523][BaseTrainer][INFO] - [Epoch 2/10, Iter 610/3560] 3.4878292083740234, cross_entropy: 3.4878292083740234 +[2025-04-29 04:14:46,270][BaseTrainer][INFO] - [Epoch 2/10, Iter 611/3560] 2.544895648956299, cross_entropy: 2.544895648956299 +[2025-04-29 04:14:47,629][BaseTrainer][INFO] - [Epoch 2/10, Iter 612/3560] 3.228545904159546, cross_entropy: 3.228545904159546 +[2025-04-29 04:14:49,882][BaseTrainer][INFO] - [Epoch 2/10, Iter 613/3560] 4.177563190460205, cross_entropy: 4.177563190460205 +[2025-04-29 04:14:51,065][BaseTrainer][INFO] - [Epoch 2/10, Iter 614/3560] 2.9751148223876953, cross_entropy: 2.9751148223876953 +[2025-04-29 04:14:54,247][BaseTrainer][INFO] - [Epoch 2/10, Iter 615/3560] 2.5551764965057373, cross_entropy: 2.5551764965057373 +[2025-04-29 04:14:55,111][BaseTrainer][INFO] - [Epoch 2/10, Iter 616/3560] 2.867098331451416, cross_entropy: 2.867098331451416 +[2025-04-29 04:14:57,866][BaseTrainer][INFO] - [Epoch 2/10, Iter 617/3560] 3.5062403678894043, cross_entropy: 3.5062403678894043 +[2025-04-29 04:14:58,772][BaseTrainer][INFO] - [Epoch 2/10, Iter 618/3560] 3.6704540252685547, cross_entropy: 3.6704540252685547 +[2025-04-29 04:15:01,117][BaseTrainer][INFO] - [Epoch 2/10, Iter 619/3560] 2.759194850921631, cross_entropy: 2.759194850921631 +[2025-04-29 04:15:02,016][BaseTrainer][INFO] - [Epoch 2/10, Iter 620/3560] 2.679030179977417, cross_entropy: 2.679030179977417 +[2025-04-29 04:15:04,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 621/3560] 3.011880397796631, cross_entropy: 3.011880397796631 +[2025-04-29 04:15:05,636][BaseTrainer][INFO] - [Epoch 2/10, Iter 622/3560] 2.7106759548187256, cross_entropy: 2.7106759548187256 +[2025-04-29 04:15:07,726][BaseTrainer][INFO] - [Epoch 2/10, Iter 623/3560] 2.991211414337158, cross_entropy: 2.991211414337158 +[2025-04-29 04:15:10,908][BaseTrainer][INFO] - [Epoch 2/10, Iter 624/3560] 3.8427793979644775, cross_entropy: 3.8427793979644775 +[2025-04-29 04:15:11,827][BaseTrainer][INFO] - [Epoch 2/10, Iter 625/3560] 2.7323665618896484, cross_entropy: 2.7323665618896484 +[2025-04-29 04:15:15,773][BaseTrainer][INFO] - [Epoch 2/10, Iter 626/3560] 3.6935412883758545, cross_entropy: 3.6935412883758545 +[2025-04-29 04:15:16,628][BaseTrainer][INFO] - [Epoch 2/10, Iter 627/3560] 2.398045063018799, cross_entropy: 2.398045063018799 +[2025-04-29 04:15:21,244][BaseTrainer][INFO] - [Epoch 2/10, Iter 628/3560] 3.983574151992798, cross_entropy: 3.983574151992798 +[2025-04-29 04:15:22,128][BaseTrainer][INFO] - [Epoch 2/10, Iter 629/3560] 3.882784605026245, cross_entropy: 3.882784605026245 +[2025-04-29 04:15:25,370][BaseTrainer][INFO] - [Epoch 2/10, Iter 630/3560] 2.3920841217041016, cross_entropy: 2.3920841217041016 +[2025-04-29 04:15:26,252][BaseTrainer][INFO] - [Epoch 2/10, Iter 631/3560] 2.2906572818756104, cross_entropy: 2.2906572818756104 +[2025-04-29 04:15:28,600][BaseTrainer][INFO] - [Epoch 2/10, Iter 632/3560] 3.07289457321167, cross_entropy: 3.07289457321167 +[2025-04-29 04:15:29,460][BaseTrainer][INFO] - [Epoch 2/10, Iter 633/3560] 2.211735725402832, cross_entropy: 2.211735725402832 +[2025-04-29 04:15:32,311][BaseTrainer][INFO] - [Epoch 2/10, Iter 634/3560] 3.756338357925415, cross_entropy: 3.756338357925415 +[2025-04-29 04:15:33,196][BaseTrainer][INFO] - [Epoch 2/10, Iter 635/3560] 2.924043655395508, cross_entropy: 2.924043655395508 +[2025-04-29 04:15:36,317][BaseTrainer][INFO] - [Epoch 2/10, Iter 636/3560] 2.7256016731262207, cross_entropy: 2.7256016731262207 +[2025-04-29 04:15:37,202][BaseTrainer][INFO] - [Epoch 2/10, Iter 637/3560] 2.5837392807006836, cross_entropy: 2.5837392807006836 +[2025-04-29 04:15:39,964][BaseTrainer][INFO] - [Epoch 2/10, Iter 638/3560] 2.65332293510437, cross_entropy: 2.65332293510437 +[2025-04-29 04:15:40,847][BaseTrainer][INFO] - [Epoch 2/10, Iter 639/3560] 3.670928716659546, cross_entropy: 3.670928716659546 +[2025-04-29 04:15:43,941][BaseTrainer][INFO] - [Epoch 2/10, Iter 640/3560] 3.257519483566284, cross_entropy: 3.257519483566284 +[2025-04-29 04:15:44,828][BaseTrainer][INFO] - [Epoch 2/10, Iter 641/3560] 2.9565556049346924, cross_entropy: 2.9565556049346924 +[2025-04-29 04:15:48,105][BaseTrainer][INFO] - [Epoch 2/10, Iter 642/3560] 2.8600847721099854, cross_entropy: 2.8600847721099854 +[2025-04-29 04:15:48,988][BaseTrainer][INFO] - [Epoch 2/10, Iter 643/3560] 3.7579641342163086, cross_entropy: 3.7579641342163086 +[2025-04-29 04:15:51,696][BaseTrainer][INFO] - [Epoch 2/10, Iter 644/3560] 3.611826181411743, cross_entropy: 3.611826181411743 +[2025-04-29 04:15:52,578][BaseTrainer][INFO] - [Epoch 2/10, Iter 645/3560] 3.0539040565490723, cross_entropy: 3.0539040565490723 +[2025-04-29 04:15:55,271][BaseTrainer][INFO] - [Epoch 2/10, Iter 646/3560] 2.5228192806243896, cross_entropy: 2.5228192806243896 +[2025-04-29 04:15:56,158][BaseTrainer][INFO] - [Epoch 2/10, Iter 647/3560] 3.793173313140869, cross_entropy: 3.793173313140869 +[2025-04-29 04:15:58,208][BaseTrainer][INFO] - [Epoch 2/10, Iter 648/3560] 2.541703462600708, cross_entropy: 2.541703462600708 +[2025-04-29 04:15:59,068][BaseTrainer][INFO] - [Epoch 2/10, Iter 649/3560] 3.5628437995910645, cross_entropy: 3.5628437995910645 +[2025-04-29 04:16:02,118][BaseTrainer][INFO] - [Epoch 2/10, Iter 650/3560] 2.658639430999756, cross_entropy: 2.658639430999756 +[2025-04-29 04:16:02,977][BaseTrainer][INFO] - [Epoch 2/10, Iter 651/3560] 4.06088399887085, cross_entropy: 4.06088399887085 +[2025-04-29 04:16:05,698][BaseTrainer][INFO] - [Epoch 2/10, Iter 652/3560] 3.2828750610351562, cross_entropy: 3.2828750610351562 +[2025-04-29 04:16:06,591][BaseTrainer][INFO] - [Epoch 2/10, Iter 653/3560] 2.682640552520752, cross_entropy: 2.682640552520752 +[2025-04-29 04:16:09,086][BaseTrainer][INFO] - [Epoch 2/10, Iter 654/3560] 3.5818862915039062, cross_entropy: 3.5818862915039062 +[2025-04-29 04:16:10,040][BaseTrainer][INFO] - [Epoch 2/10, Iter 655/3560] 3.6017091274261475, cross_entropy: 3.6017091274261475 +[2025-04-29 04:16:12,885][BaseTrainer][INFO] - [Epoch 2/10, Iter 656/3560] 3.894225835800171, cross_entropy: 3.894225835800171 +[2025-04-29 04:16:13,792][BaseTrainer][INFO] - [Epoch 2/10, Iter 657/3560] 3.0963544845581055, cross_entropy: 3.0963544845581055 +[2025-04-29 04:16:16,459][BaseTrainer][INFO] - [Epoch 2/10, Iter 658/3560] 3.1099913120269775, cross_entropy: 3.1099913120269775 +[2025-04-29 04:16:17,384][BaseTrainer][INFO] - [Epoch 2/10, Iter 659/3560] 2.4347574710845947, cross_entropy: 2.4347574710845947 +[2025-04-29 04:16:19,959][BaseTrainer][INFO] - [Epoch 2/10, Iter 660/3560] 3.8390612602233887, cross_entropy: 3.8390612602233887 +[2025-04-29 04:16:20,966][BaseTrainer][INFO] - [Epoch 2/10, Iter 661/3560] 2.9794821739196777, cross_entropy: 2.9794821739196777 +[2025-04-29 04:16:23,215][BaseTrainer][INFO] - [Epoch 2/10, Iter 662/3560] 3.252216100692749, cross_entropy: 3.252216100692749 +[2025-04-29 04:16:24,123][BaseTrainer][INFO] - [Epoch 2/10, Iter 663/3560] 3.8037302494049072, cross_entropy: 3.8037302494049072 +[2025-04-29 04:16:26,736][BaseTrainer][INFO] - [Epoch 2/10, Iter 664/3560] 2.934640884399414, cross_entropy: 2.934640884399414 +[2025-04-29 04:16:27,840][BaseTrainer][INFO] - [Epoch 2/10, Iter 665/3560] 2.254225015640259, cross_entropy: 2.254225015640259 +[2025-04-29 04:16:31,207][BaseTrainer][INFO] - [Epoch 2/10, Iter 666/3560] 2.9416489601135254, cross_entropy: 2.9416489601135254 +[2025-04-29 04:16:32,070][BaseTrainer][INFO] - [Epoch 2/10, Iter 667/3560] 2.099785804748535, cross_entropy: 2.099785804748535 +[2025-04-29 04:16:34,881][BaseTrainer][INFO] - [Epoch 2/10, Iter 668/3560] 2.8224358558654785, cross_entropy: 2.8224358558654785 +[2025-04-29 04:16:35,945][BaseTrainer][INFO] - [Epoch 2/10, Iter 669/3560] 2.7550125122070312, cross_entropy: 2.7550125122070312 +[2025-04-29 04:16:38,224][BaseTrainer][INFO] - [Epoch 2/10, Iter 670/3560] 2.9409544467926025, cross_entropy: 2.9409544467926025 +[2025-04-29 04:16:39,116][BaseTrainer][INFO] - [Epoch 2/10, Iter 671/3560] 2.3514509201049805, cross_entropy: 2.3514509201049805 +[2025-04-29 04:16:41,571][BaseTrainer][INFO] - [Epoch 2/10, Iter 672/3560] 4.044675350189209, cross_entropy: 4.044675350189209 +[2025-04-29 04:16:42,485][BaseTrainer][INFO] - [Epoch 2/10, Iter 673/3560] 2.4890244007110596, cross_entropy: 2.4890244007110596 +[2025-04-29 04:16:45,119][BaseTrainer][INFO] - [Epoch 2/10, Iter 674/3560] 2.4085769653320312, cross_entropy: 2.4085769653320312 +[2025-04-29 04:16:46,427][BaseTrainer][INFO] - [Epoch 2/10, Iter 675/3560] 2.779338836669922, cross_entropy: 2.779338836669922 +[2025-04-29 04:16:49,857][BaseTrainer][INFO] - [Epoch 2/10, Iter 676/3560] 2.4169609546661377, cross_entropy: 2.4169609546661377 +[2025-04-29 04:16:50,741][BaseTrainer][INFO] - [Epoch 2/10, Iter 677/3560] 2.4890408515930176, cross_entropy: 2.4890408515930176 +[2025-04-29 04:16:53,089][BaseTrainer][INFO] - [Epoch 2/10, Iter 678/3560] 2.4931483268737793, cross_entropy: 2.4931483268737793 +[2025-04-29 04:16:54,395][BaseTrainer][INFO] - [Epoch 2/10, Iter 679/3560] 2.9672932624816895, cross_entropy: 2.9672932624816895 +[2025-04-29 04:16:56,504][BaseTrainer][INFO] - [Epoch 2/10, Iter 680/3560] 2.513741970062256, cross_entropy: 2.513741970062256 +[2025-04-29 04:16:58,737][BaseTrainer][INFO] - [Epoch 2/10, Iter 681/3560] 2.8762407302856445, cross_entropy: 2.8762407302856445 +[2025-04-29 04:17:00,708][BaseTrainer][INFO] - [Epoch 2/10, Iter 682/3560] 3.7298784255981445, cross_entropy: 3.7298784255981445 +[2025-04-29 04:17:01,976][BaseTrainer][INFO] - [Epoch 2/10, Iter 683/3560] 2.6012911796569824, cross_entropy: 2.6012911796569824 +[2025-04-29 04:17:03,762][BaseTrainer][INFO] - [Epoch 2/10, Iter 684/3560] 3.5750927925109863, cross_entropy: 3.5750927925109863 +[2025-04-29 04:17:05,462][BaseTrainer][INFO] - [Epoch 2/10, Iter 685/3560] 4.081140518188477, cross_entropy: 4.081140518188477 +[2025-04-29 04:17:07,875][BaseTrainer][INFO] - [Epoch 2/10, Iter 686/3560] 3.4566268920898438, cross_entropy: 3.4566268920898438 +[2025-04-29 04:17:08,972][BaseTrainer][INFO] - [Epoch 2/10, Iter 687/3560] 3.0062355995178223, cross_entropy: 3.0062355995178223 +[2025-04-29 04:17:11,538][BaseTrainer][INFO] - [Epoch 2/10, Iter 688/3560] 3.739098072052002, cross_entropy: 3.739098072052002 +[2025-04-29 04:17:13,034][BaseTrainer][INFO] - [Epoch 2/10, Iter 689/3560] 3.427795648574829, cross_entropy: 3.427795648574829 +[2025-04-29 04:17:15,455][BaseTrainer][INFO] - [Epoch 2/10, Iter 690/3560] 3.956364631652832, cross_entropy: 3.956364631652832 +[2025-04-29 04:17:16,741][BaseTrainer][INFO] - [Epoch 2/10, Iter 691/3560] 2.742530345916748, cross_entropy: 2.742530345916748 +[2025-04-29 04:17:19,457][BaseTrainer][INFO] - [Epoch 2/10, Iter 692/3560] 3.018831253051758, cross_entropy: 3.018831253051758 +[2025-04-29 04:17:20,411][BaseTrainer][INFO] - [Epoch 2/10, Iter 693/3560] 3.6314029693603516, cross_entropy: 3.6314029693603516 +[2025-04-29 04:17:22,557][BaseTrainer][INFO] - [Epoch 2/10, Iter 694/3560] 3.780226230621338, cross_entropy: 3.780226230621338 +[2025-04-29 04:17:24,235][BaseTrainer][INFO] - [Epoch 2/10, Iter 695/3560] 2.9213008880615234, cross_entropy: 2.9213008880615234 +[2025-04-29 04:17:25,924][BaseTrainer][INFO] - [Epoch 2/10, Iter 696/3560] 2.423936128616333, cross_entropy: 2.423936128616333 +[2025-04-29 04:17:27,888][BaseTrainer][INFO] - [Epoch 2/10, Iter 697/3560] 3.796609401702881, cross_entropy: 3.796609401702881 +[2025-04-29 04:17:29,196][BaseTrainer][INFO] - [Epoch 2/10, Iter 698/3560] 3.9506137371063232, cross_entropy: 3.9506137371063232 +[2025-04-29 04:17:32,126][BaseTrainer][INFO] - [Epoch 2/10, Iter 699/3560] 3.5707762241363525, cross_entropy: 3.5707762241363525 +[2025-04-29 04:17:33,055][BaseTrainer][INFO] - [Epoch 2/10, Iter 700/3560] 3.6793689727783203, cross_entropy: 3.6793689727783203 +[2025-04-29 04:17:35,676][BaseTrainer][INFO] - [Epoch 2/10, Iter 701/3560] 3.624598741531372, cross_entropy: 3.624598741531372 +[2025-04-29 04:17:36,604][BaseTrainer][INFO] - [Epoch 2/10, Iter 702/3560] 2.950045108795166, cross_entropy: 2.950045108795166 +[2025-04-29 04:17:39,476][BaseTrainer][INFO] - [Epoch 2/10, Iter 703/3560] 3.195228099822998, cross_entropy: 3.195228099822998 +[2025-04-29 04:17:40,419][BaseTrainer][INFO] - [Epoch 2/10, Iter 704/3560] 3.0067403316497803, cross_entropy: 3.0067403316497803 +[2025-04-29 04:17:42,967][BaseTrainer][INFO] - [Epoch 2/10, Iter 705/3560] 2.5690884590148926, cross_entropy: 2.5690884590148926 +[2025-04-29 04:17:43,985][BaseTrainer][INFO] - [Epoch 2/10, Iter 706/3560] 4.0439276695251465, cross_entropy: 4.0439276695251465 +[2025-04-29 04:17:47,212][BaseTrainer][INFO] - [Epoch 2/10, Iter 707/3560] 2.5646278858184814, cross_entropy: 2.5646278858184814 +[2025-04-29 04:17:48,106][BaseTrainer][INFO] - [Epoch 2/10, Iter 708/3560] 3.771775960922241, cross_entropy: 3.771775960922241 +[2025-04-29 04:17:51,439][BaseTrainer][INFO] - [Epoch 2/10, Iter 709/3560] 2.4460136890411377, cross_entropy: 2.4460136890411377 +[2025-04-29 04:17:52,400][BaseTrainer][INFO] - [Epoch 2/10, Iter 710/3560] 4.0791215896606445, cross_entropy: 4.0791215896606445 +[2025-04-29 04:17:54,759][BaseTrainer][INFO] - [Epoch 2/10, Iter 711/3560] 3.1841726303100586, cross_entropy: 3.1841726303100586 +[2025-04-29 04:17:55,533][BaseTrainer][INFO] - [Epoch 2/10, Iter 712/3560] 3.1948554515838623, cross_entropy: 3.1948554515838623 +[2025-04-29 04:20:40,362][BaseTrainer][INFO] - [Epoch 2/10] (train) 3.4004735946655273, cross_entropy: 3.4004735946655273 +[2025-04-29 04:20:40,362][BaseTrainer][INFO] - [Epoch 2/10] (validation) 2.271209478378296, cross_entropy: 2.271209478378296 +[2025-04-29 04:20:41,208][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 04:20:41,677][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch2.pth. +[2025-04-29 04:20:42,454][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 04:20:48,327][BaseTrainer][INFO] - [Epoch 3/10, Iter 713/3560] 2.708207845687866, cross_entropy: 2.708207845687866 +[2025-04-29 04:20:49,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 714/3560] 3.312605142593384, cross_entropy: 3.312605142593384 +[2025-04-29 04:20:52,151][BaseTrainer][INFO] - [Epoch 3/10, Iter 715/3560] 3.5091986656188965, cross_entropy: 3.5091986656188965 +[2025-04-29 04:20:53,019][BaseTrainer][INFO] - [Epoch 3/10, Iter 716/3560] 3.7295989990234375, cross_entropy: 3.7295989990234375 +[2025-04-29 04:20:56,400][BaseTrainer][INFO] - [Epoch 3/10, Iter 717/3560] 3.905937671661377, cross_entropy: 3.905937671661377 +[2025-04-29 04:20:57,280][BaseTrainer][INFO] - [Epoch 3/10, Iter 718/3560] 2.6727256774902344, cross_entropy: 2.6727256774902344 +[2025-04-29 04:20:59,856][BaseTrainer][INFO] - [Epoch 3/10, Iter 719/3560] 2.486868381500244, cross_entropy: 2.486868381500244 +[2025-04-29 04:21:00,736][BaseTrainer][INFO] - [Epoch 3/10, Iter 720/3560] 3.5070748329162598, cross_entropy: 3.5070748329162598 +[2025-04-29 04:21:03,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 721/3560] 3.404482841491699, cross_entropy: 3.404482841491699 +[2025-04-29 04:21:04,321][BaseTrainer][INFO] - [Epoch 3/10, Iter 722/3560] 3.284322738647461, cross_entropy: 3.284322738647461 +[2025-04-29 04:21:07,380][BaseTrainer][INFO] - [Epoch 3/10, Iter 723/3560] 3.033214569091797, cross_entropy: 3.033214569091797 +[2025-04-29 04:21:08,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 724/3560] 2.5899221897125244, cross_entropy: 2.5899221897125244 +[2025-04-29 04:21:10,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 725/3560] 2.908623218536377, cross_entropy: 2.908623218536377 +[2025-04-29 04:21:11,747][BaseTrainer][INFO] - [Epoch 3/10, Iter 726/3560] 3.500993490219116, cross_entropy: 3.500993490219116 +[2025-04-29 04:21:15,169][BaseTrainer][INFO] - [Epoch 3/10, Iter 727/3560] 3.0422258377075195, cross_entropy: 3.0422258377075195 +[2025-04-29 04:21:16,030][BaseTrainer][INFO] - [Epoch 3/10, Iter 728/3560] 3.703188896179199, cross_entropy: 3.703188896179199 +[2025-04-29 04:21:19,141][BaseTrainer][INFO] - [Epoch 3/10, Iter 729/3560] 3.719633102416992, cross_entropy: 3.719633102416992 +[2025-04-29 04:21:20,025][BaseTrainer][INFO] - [Epoch 3/10, Iter 730/3560] 3.443164825439453, cross_entropy: 3.443164825439453 +[2025-04-29 04:21:22,215][BaseTrainer][INFO] - [Epoch 3/10, Iter 731/3560] 3.2315549850463867, cross_entropy: 3.2315549850463867 +[2025-04-29 04:21:23,098][BaseTrainer][INFO] - [Epoch 3/10, Iter 732/3560] 2.4886269569396973, cross_entropy: 2.4886269569396973 +[2025-04-29 04:21:26,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 733/3560] 2.585702896118164, cross_entropy: 2.585702896118164 +[2025-04-29 04:21:27,670][BaseTrainer][INFO] - [Epoch 3/10, Iter 734/3560] 2.9583001136779785, cross_entropy: 2.9583001136779785 +[2025-04-29 04:21:30,669][BaseTrainer][INFO] - [Epoch 3/10, Iter 735/3560] 3.7257556915283203, cross_entropy: 3.7257556915283203 +[2025-04-29 04:21:31,548][BaseTrainer][INFO] - [Epoch 3/10, Iter 736/3560] 2.419391393661499, cross_entropy: 2.419391393661499 +[2025-04-29 04:21:34,737][BaseTrainer][INFO] - [Epoch 3/10, Iter 737/3560] 3.483025074005127, cross_entropy: 3.483025074005127 +[2025-04-29 04:21:35,607][BaseTrainer][INFO] - [Epoch 3/10, Iter 738/3560] 3.9889955520629883, cross_entropy: 3.9889955520629883 +[2025-04-29 04:21:38,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 739/3560] 3.5546464920043945, cross_entropy: 3.5546464920043945 +[2025-04-29 04:21:39,256][BaseTrainer][INFO] - [Epoch 3/10, Iter 740/3560] 2.598026752471924, cross_entropy: 2.598026752471924 +[2025-04-29 04:21:41,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 741/3560] 3.0721495151519775, cross_entropy: 3.0721495151519775 +[2025-04-29 04:21:42,826][BaseTrainer][INFO] - [Epoch 3/10, Iter 742/3560] 2.9986889362335205, cross_entropy: 2.9986889362335205 +[2025-04-29 04:21:45,844][BaseTrainer][INFO] - [Epoch 3/10, Iter 743/3560] 2.523190498352051, cross_entropy: 2.523190498352051 +[2025-04-29 04:21:46,731][BaseTrainer][INFO] - [Epoch 3/10, Iter 744/3560] 2.4478869438171387, cross_entropy: 2.4478869438171387 +[2025-04-29 04:21:49,368][BaseTrainer][INFO] - [Epoch 3/10, Iter 745/3560] 2.8262503147125244, cross_entropy: 2.8262503147125244 +[2025-04-29 04:21:50,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 746/3560] 2.5251259803771973, cross_entropy: 2.5251259803771973 +[2025-04-29 04:21:52,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 747/3560] 2.969785690307617, cross_entropy: 2.969785690307617 +[2025-04-29 04:21:53,408][BaseTrainer][INFO] - [Epoch 3/10, Iter 748/3560] 2.35536527633667, cross_entropy: 2.35536527633667 +[2025-04-29 04:21:56,201][BaseTrainer][INFO] - [Epoch 3/10, Iter 749/3560] 3.9419779777526855, cross_entropy: 3.9419779777526855 +[2025-04-29 04:21:57,074][BaseTrainer][INFO] - [Epoch 3/10, Iter 750/3560] 2.2226884365081787, cross_entropy: 2.2226884365081787 +[2025-04-29 04:21:59,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 751/3560] 4.053617000579834, cross_entropy: 4.053617000579834 +[2025-04-29 04:22:00,547][BaseTrainer][INFO] - [Epoch 3/10, Iter 752/3560] 4.049869537353516, cross_entropy: 4.049869537353516 +[2025-04-29 04:22:03,455][BaseTrainer][INFO] - [Epoch 3/10, Iter 753/3560] 3.4670557975769043, cross_entropy: 3.4670557975769043 +[2025-04-29 04:22:04,336][BaseTrainer][INFO] - [Epoch 3/10, Iter 754/3560] 2.6184868812561035, cross_entropy: 2.6184868812561035 +[2025-04-29 04:22:07,379][BaseTrainer][INFO] - [Epoch 3/10, Iter 755/3560] 3.1911377906799316, cross_entropy: 3.1911377906799316 +[2025-04-29 04:22:08,248][BaseTrainer][INFO] - [Epoch 3/10, Iter 756/3560] 2.689676284790039, cross_entropy: 2.689676284790039 +[2025-04-29 04:22:11,226][BaseTrainer][INFO] - [Epoch 3/10, Iter 757/3560] 2.453226327896118, cross_entropy: 2.453226327896118 +[2025-04-29 04:22:12,110][BaseTrainer][INFO] - [Epoch 3/10, Iter 758/3560] 3.5367865562438965, cross_entropy: 3.5367865562438965 +[2025-04-29 04:22:14,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 759/3560] 3.5398764610290527, cross_entropy: 3.5398764610290527 +[2025-04-29 04:22:15,415][BaseTrainer][INFO] - [Epoch 3/10, Iter 760/3560] 2.6868820190429688, cross_entropy: 2.6868820190429688 +[2025-04-29 04:22:17,772][BaseTrainer][INFO] - [Epoch 3/10, Iter 761/3560] 2.7475316524505615, cross_entropy: 2.7475316524505615 +[2025-04-29 04:22:18,659][BaseTrainer][INFO] - [Epoch 3/10, Iter 762/3560] 3.5613346099853516, cross_entropy: 3.5613346099853516 +[2025-04-29 04:22:21,730][BaseTrainer][INFO] - [Epoch 3/10, Iter 763/3560] 2.466188907623291, cross_entropy: 2.466188907623291 +[2025-04-29 04:22:22,620][BaseTrainer][INFO] - [Epoch 3/10, Iter 764/3560] 3.881049633026123, cross_entropy: 3.881049633026123 +[2025-04-29 04:22:24,538][BaseTrainer][INFO] - [Epoch 3/10, Iter 765/3560] 3.033048152923584, cross_entropy: 3.033048152923584 +[2025-04-29 04:22:25,396][BaseTrainer][INFO] - [Epoch 3/10, Iter 766/3560] 2.288863182067871, cross_entropy: 2.288863182067871 +[2025-04-29 04:22:28,643][BaseTrainer][INFO] - [Epoch 3/10, Iter 767/3560] 2.7385106086730957, cross_entropy: 2.7385106086730957 +[2025-04-29 04:22:29,505][BaseTrainer][INFO] - [Epoch 3/10, Iter 768/3560] 3.1273438930511475, cross_entropy: 3.1273438930511475 +[2025-04-29 04:22:32,721][BaseTrainer][INFO] - [Epoch 3/10, Iter 769/3560] 3.406198501586914, cross_entropy: 3.406198501586914 +[2025-04-29 04:22:33,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 770/3560] 2.7904319763183594, cross_entropy: 2.7904319763183594 +[2025-04-29 04:22:36,478][BaseTrainer][INFO] - [Epoch 3/10, Iter 771/3560] 1.9626200199127197, cross_entropy: 1.9626200199127197 +[2025-04-29 04:22:37,363][BaseTrainer][INFO] - [Epoch 3/10, Iter 772/3560] 3.1452887058258057, cross_entropy: 3.1452887058258057 +[2025-04-29 04:22:40,200][BaseTrainer][INFO] - [Epoch 3/10, Iter 773/3560] 2.7419700622558594, cross_entropy: 2.7419700622558594 +[2025-04-29 04:22:41,082][BaseTrainer][INFO] - [Epoch 3/10, Iter 774/3560] 2.9905200004577637, cross_entropy: 2.9905200004577637 +[2025-04-29 04:22:43,762][BaseTrainer][INFO] - [Epoch 3/10, Iter 775/3560] 3.6700520515441895, cross_entropy: 3.6700520515441895 +[2025-04-29 04:22:44,623][BaseTrainer][INFO] - [Epoch 3/10, Iter 776/3560] 2.518801689147949, cross_entropy: 2.518801689147949 +[2025-04-29 04:22:47,399][BaseTrainer][INFO] - [Epoch 3/10, Iter 777/3560] 3.0647454261779785, cross_entropy: 3.0647454261779785 +[2025-04-29 04:22:48,254][BaseTrainer][INFO] - [Epoch 3/10, Iter 778/3560] 3.5124588012695312, cross_entropy: 3.5124588012695312 +[2025-04-29 04:22:51,891][BaseTrainer][INFO] - [Epoch 3/10, Iter 779/3560] 3.768178701400757, cross_entropy: 3.768178701400757 +[2025-04-29 04:22:52,777][BaseTrainer][INFO] - [Epoch 3/10, Iter 780/3560] 3.2038819789886475, cross_entropy: 3.2038819789886475 +[2025-04-29 04:22:56,816][BaseTrainer][INFO] - [Epoch 3/10, Iter 781/3560] 3.552248954772949, cross_entropy: 3.552248954772949 +[2025-04-29 04:22:57,675][BaseTrainer][INFO] - [Epoch 3/10, Iter 782/3560] 2.281552314758301, cross_entropy: 2.281552314758301 +[2025-04-29 04:23:00,371][BaseTrainer][INFO] - [Epoch 3/10, Iter 783/3560] 2.4383373260498047, cross_entropy: 2.4383373260498047 +[2025-04-29 04:23:01,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 784/3560] 3.0873024463653564, cross_entropy: 3.0873024463653564 +[2025-04-29 04:23:03,889][BaseTrainer][INFO] - [Epoch 3/10, Iter 785/3560] 3.647827625274658, cross_entropy: 3.647827625274658 +[2025-04-29 04:23:04,781][BaseTrainer][INFO] - [Epoch 3/10, Iter 786/3560] 2.1254212856292725, cross_entropy: 2.1254212856292725 +[2025-04-29 04:23:07,513][BaseTrainer][INFO] - [Epoch 3/10, Iter 787/3560] 3.7577335834503174, cross_entropy: 3.7577335834503174 +[2025-04-29 04:23:08,398][BaseTrainer][INFO] - [Epoch 3/10, Iter 788/3560] 2.234534740447998, cross_entropy: 2.234534740447998 +[2025-04-29 04:23:11,570][BaseTrainer][INFO] - [Epoch 3/10, Iter 789/3560] 3.4736852645874023, cross_entropy: 3.4736852645874023 +[2025-04-29 04:23:12,458][BaseTrainer][INFO] - [Epoch 3/10, Iter 790/3560] 3.805805206298828, cross_entropy: 3.805805206298828 +[2025-04-29 04:23:15,828][BaseTrainer][INFO] - [Epoch 3/10, Iter 791/3560] 3.7337186336517334, cross_entropy: 3.7337186336517334 +[2025-04-29 04:23:16,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 792/3560] 2.5132880210876465, cross_entropy: 2.5132880210876465 +[2025-04-29 04:23:19,757][BaseTrainer][INFO] - [Epoch 3/10, Iter 793/3560] 4.079842567443848, cross_entropy: 4.079842567443848 +[2025-04-29 04:23:20,641][BaseTrainer][INFO] - [Epoch 3/10, Iter 794/3560] 2.821659564971924, cross_entropy: 2.821659564971924 +[2025-04-29 04:23:23,689][BaseTrainer][INFO] - [Epoch 3/10, Iter 795/3560] 3.7607364654541016, cross_entropy: 3.7607364654541016 +[2025-04-29 04:23:24,576][BaseTrainer][INFO] - [Epoch 3/10, Iter 796/3560] 3.456860065460205, cross_entropy: 3.456860065460205 +[2025-04-29 04:23:27,288][BaseTrainer][INFO] - [Epoch 3/10, Iter 797/3560] 2.4545059204101562, cross_entropy: 2.4545059204101562 +[2025-04-29 04:23:28,175][BaseTrainer][INFO] - [Epoch 3/10, Iter 798/3560] 2.8074371814727783, cross_entropy: 2.8074371814727783 +[2025-04-29 04:23:30,818][BaseTrainer][INFO] - [Epoch 3/10, Iter 799/3560] 3.8356707096099854, cross_entropy: 3.8356707096099854 +[2025-04-29 04:23:31,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 800/3560] 3.60054874420166, cross_entropy: 3.60054874420166 +[2025-04-29 04:23:34,414][BaseTrainer][INFO] - [Epoch 3/10, Iter 801/3560] 3.0424106121063232, cross_entropy: 3.0424106121063232 +[2025-04-29 04:23:35,276][BaseTrainer][INFO] - [Epoch 3/10, Iter 802/3560] 2.7111501693725586, cross_entropy: 2.7111501693725586 +[2025-04-29 04:23:38,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 803/3560] 2.670267105102539, cross_entropy: 2.670267105102539 +[2025-04-29 04:23:39,589][BaseTrainer][INFO] - [Epoch 3/10, Iter 804/3560] 3.6271555423736572, cross_entropy: 3.6271555423736572 +[2025-04-29 04:23:43,742][BaseTrainer][INFO] - [Epoch 3/10, Iter 805/3560] 2.7887277603149414, cross_entropy: 2.7887277603149414 +[2025-04-29 04:23:44,600][BaseTrainer][INFO] - [Epoch 3/10, Iter 806/3560] 2.6300125122070312, cross_entropy: 2.6300125122070312 +[2025-04-29 04:23:48,097][BaseTrainer][INFO] - [Epoch 3/10, Iter 807/3560] 3.4944629669189453, cross_entropy: 3.4944629669189453 +[2025-04-29 04:23:48,984][BaseTrainer][INFO] - [Epoch 3/10, Iter 808/3560] 2.0916008949279785, cross_entropy: 2.0916008949279785 +[2025-04-29 04:23:52,000][BaseTrainer][INFO] - [Epoch 3/10, Iter 809/3560] 2.772368907928467, cross_entropy: 2.772368907928467 +[2025-04-29 04:23:52,890][BaseTrainer][INFO] - [Epoch 3/10, Iter 810/3560] 1.8890308141708374, cross_entropy: 1.8890308141708374 +[2025-04-29 04:23:55,463][BaseTrainer][INFO] - [Epoch 3/10, Iter 811/3560] 3.5396370887756348, cross_entropy: 3.5396370887756348 +[2025-04-29 04:23:56,349][BaseTrainer][INFO] - [Epoch 3/10, Iter 812/3560] 2.5332119464874268, cross_entropy: 2.5332119464874268 +[2025-04-29 04:23:59,362][BaseTrainer][INFO] - [Epoch 3/10, Iter 813/3560] 2.394883394241333, cross_entropy: 2.394883394241333 +[2025-04-29 04:24:00,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 814/3560] 3.2652783393859863, cross_entropy: 3.2652783393859863 +[2025-04-29 04:24:03,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 815/3560] 2.8058159351348877, cross_entropy: 2.8058159351348877 +[2025-04-29 04:24:03,874][BaseTrainer][INFO] - [Epoch 3/10, Iter 816/3560] 2.5020313262939453, cross_entropy: 2.5020313262939453 +[2025-04-29 04:24:06,907][BaseTrainer][INFO] - [Epoch 3/10, Iter 817/3560] 3.608647346496582, cross_entropy: 3.608647346496582 +[2025-04-29 04:24:07,792][BaseTrainer][INFO] - [Epoch 3/10, Iter 818/3560] 2.955514907836914, cross_entropy: 2.955514907836914 +[2025-04-29 04:24:10,285][BaseTrainer][INFO] - [Epoch 3/10, Iter 819/3560] 2.056351661682129, cross_entropy: 2.056351661682129 +[2025-04-29 04:24:11,164][BaseTrainer][INFO] - [Epoch 3/10, Iter 820/3560] 3.0510284900665283, cross_entropy: 3.0510284900665283 +[2025-04-29 04:24:13,998][BaseTrainer][INFO] - [Epoch 3/10, Iter 821/3560] 3.6185860633850098, cross_entropy: 3.6185860633850098 +[2025-04-29 04:24:14,885][BaseTrainer][INFO] - [Epoch 3/10, Iter 822/3560] 2.433256149291992, cross_entropy: 2.433256149291992 +[2025-04-29 04:24:18,203][BaseTrainer][INFO] - [Epoch 3/10, Iter 823/3560] 3.705577850341797, cross_entropy: 3.705577850341797 +[2025-04-29 04:24:19,093][BaseTrainer][INFO] - [Epoch 3/10, Iter 824/3560] 2.8098015785217285, cross_entropy: 2.8098015785217285 +[2025-04-29 04:24:21,951][BaseTrainer][INFO] - [Epoch 3/10, Iter 825/3560] 3.040907621383667, cross_entropy: 3.040907621383667 +[2025-04-29 04:24:22,836][BaseTrainer][INFO] - [Epoch 3/10, Iter 826/3560] 2.2643280029296875, cross_entropy: 2.2643280029296875 +[2025-04-29 04:24:25,447][BaseTrainer][INFO] - [Epoch 3/10, Iter 827/3560] 3.5187346935272217, cross_entropy: 3.5187346935272217 +[2025-04-29 04:24:26,337][BaseTrainer][INFO] - [Epoch 3/10, Iter 828/3560] 2.601851463317871, cross_entropy: 2.601851463317871 +[2025-04-29 04:24:29,064][BaseTrainer][INFO] - [Epoch 3/10, Iter 829/3560] 2.174313545227051, cross_entropy: 2.174313545227051 +[2025-04-29 04:24:29,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 830/3560] 2.2347476482391357, cross_entropy: 2.2347476482391357 +[2025-04-29 04:24:32,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 831/3560] 3.586719512939453, cross_entropy: 3.586719512939453 +[2025-04-29 04:24:33,397][BaseTrainer][INFO] - [Epoch 3/10, Iter 832/3560] 2.6602187156677246, cross_entropy: 2.6602187156677246 +[2025-04-29 04:24:36,790][BaseTrainer][INFO] - [Epoch 3/10, Iter 833/3560] 3.635829210281372, cross_entropy: 3.635829210281372 +[2025-04-29 04:24:37,684][BaseTrainer][INFO] - [Epoch 3/10, Iter 834/3560] 2.412841796875, cross_entropy: 2.412841796875 +[2025-04-29 04:24:39,924][BaseTrainer][INFO] - [Epoch 3/10, Iter 835/3560] 3.705899715423584, cross_entropy: 3.705899715423584 +[2025-04-29 04:24:40,781][BaseTrainer][INFO] - [Epoch 3/10, Iter 836/3560] 2.7311153411865234, cross_entropy: 2.7311153411865234 +[2025-04-29 04:24:43,412][BaseTrainer][INFO] - [Epoch 3/10, Iter 837/3560] 3.3646883964538574, cross_entropy: 3.3646883964538574 +[2025-04-29 04:24:44,305][BaseTrainer][INFO] - [Epoch 3/10, Iter 838/3560] 2.127112865447998, cross_entropy: 2.127112865447998 +[2025-04-29 04:24:47,422][BaseTrainer][INFO] - [Epoch 3/10, Iter 839/3560] 3.4975502490997314, cross_entropy: 3.4975502490997314 +[2025-04-29 04:24:48,309][BaseTrainer][INFO] - [Epoch 3/10, Iter 840/3560] 3.546046257019043, cross_entropy: 3.546046257019043 +[2025-04-29 04:24:51,407][BaseTrainer][INFO] - [Epoch 3/10, Iter 841/3560] 4.029386043548584, cross_entropy: 4.029386043548584 +[2025-04-29 04:24:52,265][BaseTrainer][INFO] - [Epoch 3/10, Iter 842/3560] 2.733844757080078, cross_entropy: 2.733844757080078 +[2025-04-29 04:24:55,391][BaseTrainer][INFO] - [Epoch 3/10, Iter 843/3560] 2.216435432434082, cross_entropy: 2.216435432434082 +[2025-04-29 04:24:56,271][BaseTrainer][INFO] - [Epoch 3/10, Iter 844/3560] 3.360785961151123, cross_entropy: 3.360785961151123 +[2025-04-29 04:24:58,214][BaseTrainer][INFO] - [Epoch 3/10, Iter 845/3560] 2.8047780990600586, cross_entropy: 2.8047780990600586 +[2025-04-29 04:24:59,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 846/3560] 2.9983043670654297, cross_entropy: 2.9983043670654297 +[2025-04-29 04:25:02,082][BaseTrainer][INFO] - [Epoch 3/10, Iter 847/3560] 2.739987850189209, cross_entropy: 2.739987850189209 +[2025-04-29 04:25:02,939][BaseTrainer][INFO] - [Epoch 3/10, Iter 848/3560] 2.578784942626953, cross_entropy: 2.578784942626953 +[2025-04-29 04:25:05,676][BaseTrainer][INFO] - [Epoch 3/10, Iter 849/3560] 2.071812391281128, cross_entropy: 2.071812391281128 +[2025-04-29 04:25:06,560][BaseTrainer][INFO] - [Epoch 3/10, Iter 850/3560] 3.7208919525146484, cross_entropy: 3.7208919525146484 +[2025-04-29 04:25:09,084][BaseTrainer][INFO] - [Epoch 3/10, Iter 851/3560] 2.9501397609710693, cross_entropy: 2.9501397609710693 +[2025-04-29 04:25:09,963][BaseTrainer][INFO] - [Epoch 3/10, Iter 852/3560] 2.3229994773864746, cross_entropy: 2.3229994773864746 +[2025-04-29 04:25:12,751][BaseTrainer][INFO] - [Epoch 3/10, Iter 853/3560] 4.0741777420043945, cross_entropy: 4.0741777420043945 +[2025-04-29 04:25:13,611][BaseTrainer][INFO] - [Epoch 3/10, Iter 854/3560] 2.316783905029297, cross_entropy: 2.316783905029297 +[2025-04-29 04:25:16,635][BaseTrainer][INFO] - [Epoch 3/10, Iter 855/3560] 2.448467969894409, cross_entropy: 2.448467969894409 +[2025-04-29 04:25:17,495][BaseTrainer][INFO] - [Epoch 3/10, Iter 856/3560] 2.6473801136016846, cross_entropy: 2.6473801136016846 +[2025-04-29 04:25:20,332][BaseTrainer][INFO] - [Epoch 3/10, Iter 857/3560] 2.7614784240722656, cross_entropy: 2.7614784240722656 +[2025-04-29 04:25:21,192][BaseTrainer][INFO] - [Epoch 3/10, Iter 858/3560] 2.3622398376464844, cross_entropy: 2.3622398376464844 +[2025-04-29 04:25:24,469][BaseTrainer][INFO] - [Epoch 3/10, Iter 859/3560] 2.4609599113464355, cross_entropy: 2.4609599113464355 +[2025-04-29 04:25:25,336][BaseTrainer][INFO] - [Epoch 3/10, Iter 860/3560] 2.1400794982910156, cross_entropy: 2.1400794982910156 +[2025-04-29 04:25:28,854][BaseTrainer][INFO] - [Epoch 3/10, Iter 861/3560] 3.231009006500244, cross_entropy: 3.231009006500244 +[2025-04-29 04:25:29,738][BaseTrainer][INFO] - [Epoch 3/10, Iter 862/3560] 3.952293634414673, cross_entropy: 3.952293634414673 +[2025-04-29 04:25:32,759][BaseTrainer][INFO] - [Epoch 3/10, Iter 863/3560] 2.5157690048217773, cross_entropy: 2.5157690048217773 +[2025-04-29 04:25:33,617][BaseTrainer][INFO] - [Epoch 3/10, Iter 864/3560] 2.314030170440674, cross_entropy: 2.314030170440674 +[2025-04-29 04:25:36,085][BaseTrainer][INFO] - [Epoch 3/10, Iter 865/3560] 3.2802186012268066, cross_entropy: 3.2802186012268066 +[2025-04-29 04:25:36,945][BaseTrainer][INFO] - [Epoch 3/10, Iter 866/3560] 3.336073875427246, cross_entropy: 3.336073875427246 +[2025-04-29 04:25:40,406][BaseTrainer][INFO] - [Epoch 3/10, Iter 867/3560] 3.031796455383301, cross_entropy: 3.031796455383301 +[2025-04-29 04:25:41,291][BaseTrainer][INFO] - [Epoch 3/10, Iter 868/3560] 2.4293951988220215, cross_entropy: 2.4293951988220215 +[2025-04-29 04:25:44,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 869/3560] 2.9150891304016113, cross_entropy: 2.9150891304016113 +[2025-04-29 04:25:44,914][BaseTrainer][INFO] - [Epoch 3/10, Iter 870/3560] 3.811305046081543, cross_entropy: 3.811305046081543 +[2025-04-29 04:25:47,897][BaseTrainer][INFO] - [Epoch 3/10, Iter 871/3560] 3.4444565773010254, cross_entropy: 3.4444565773010254 +[2025-04-29 04:25:48,789][BaseTrainer][INFO] - [Epoch 3/10, Iter 872/3560] 2.3969457149505615, cross_entropy: 2.3969457149505615 +[2025-04-29 04:25:51,803][BaseTrainer][INFO] - [Epoch 3/10, Iter 873/3560] 3.3091320991516113, cross_entropy: 3.3091320991516113 +[2025-04-29 04:25:52,690][BaseTrainer][INFO] - [Epoch 3/10, Iter 874/3560] 3.4365124702453613, cross_entropy: 3.4365124702453613 +[2025-04-29 04:25:55,499][BaseTrainer][INFO] - [Epoch 3/10, Iter 875/3560] 2.1640405654907227, cross_entropy: 2.1640405654907227 +[2025-04-29 04:25:56,393][BaseTrainer][INFO] - [Epoch 3/10, Iter 876/3560] 3.075930595397949, cross_entropy: 3.075930595397949 +[2025-04-29 04:25:58,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 877/3560] 3.308074474334717, cross_entropy: 3.308074474334717 +[2025-04-29 04:25:59,489][BaseTrainer][INFO] - [Epoch 3/10, Iter 878/3560] 2.482515811920166, cross_entropy: 2.482515811920166 +[2025-04-29 04:26:02,330][BaseTrainer][INFO] - [Epoch 3/10, Iter 879/3560] 3.662051200866699, cross_entropy: 3.662051200866699 +[2025-04-29 04:26:03,218][BaseTrainer][INFO] - [Epoch 3/10, Iter 880/3560] 3.3744187355041504, cross_entropy: 3.3744187355041504 +[2025-04-29 04:26:06,208][BaseTrainer][INFO] - [Epoch 3/10, Iter 881/3560] 2.5953798294067383, cross_entropy: 2.5953798294067383 +[2025-04-29 04:26:07,099][BaseTrainer][INFO] - [Epoch 3/10, Iter 882/3560] 2.920823097229004, cross_entropy: 2.920823097229004 +[2025-04-29 04:26:09,957][BaseTrainer][INFO] - [Epoch 3/10, Iter 883/3560] 2.1409506797790527, cross_entropy: 2.1409506797790527 +[2025-04-29 04:26:10,842][BaseTrainer][INFO] - [Epoch 3/10, Iter 884/3560] 3.672988176345825, cross_entropy: 3.672988176345825 +[2025-04-29 04:26:13,290][BaseTrainer][INFO] - [Epoch 3/10, Iter 885/3560] 3.6175827980041504, cross_entropy: 3.6175827980041504 +[2025-04-29 04:26:14,174][BaseTrainer][INFO] - [Epoch 3/10, Iter 886/3560] 3.618605136871338, cross_entropy: 3.618605136871338 +[2025-04-29 04:26:16,605][BaseTrainer][INFO] - [Epoch 3/10, Iter 887/3560] 3.8729727268218994, cross_entropy: 3.8729727268218994 +[2025-04-29 04:26:17,536][BaseTrainer][INFO] - [Epoch 3/10, Iter 888/3560] 1.8856137990951538, cross_entropy: 1.8856137990951538 +[2025-04-29 04:26:20,537][BaseTrainer][INFO] - [Epoch 3/10, Iter 889/3560] 2.622781276702881, cross_entropy: 2.622781276702881 +[2025-04-29 04:26:21,463][BaseTrainer][INFO] - [Epoch 3/10, Iter 890/3560] 2.8415474891662598, cross_entropy: 2.8415474891662598 +[2025-04-29 04:26:25,003][BaseTrainer][INFO] - [Epoch 3/10, Iter 891/3560] 2.2430782318115234, cross_entropy: 2.2430782318115234 +[2025-04-29 04:26:25,886][BaseTrainer][INFO] - [Epoch 3/10, Iter 892/3560] 2.8054685592651367, cross_entropy: 2.8054685592651367 +[2025-04-29 04:26:29,235][BaseTrainer][INFO] - [Epoch 3/10, Iter 893/3560] 2.1234652996063232, cross_entropy: 2.1234652996063232 +[2025-04-29 04:26:30,124][BaseTrainer][INFO] - [Epoch 3/10, Iter 894/3560] 2.4156904220581055, cross_entropy: 2.4156904220581055 +[2025-04-29 04:26:33,462][BaseTrainer][INFO] - [Epoch 3/10, Iter 895/3560] 1.9878381490707397, cross_entropy: 1.9878381490707397 +[2025-04-29 04:26:34,355][BaseTrainer][INFO] - [Epoch 3/10, Iter 896/3560] 4.002109527587891, cross_entropy: 4.002109527587891 +[2025-04-29 04:26:37,764][BaseTrainer][INFO] - [Epoch 3/10, Iter 897/3560] 2.8658108711242676, cross_entropy: 2.8658108711242676 +[2025-04-29 04:26:38,662][BaseTrainer][INFO] - [Epoch 3/10, Iter 898/3560] 2.1693480014801025, cross_entropy: 2.1693480014801025 +[2025-04-29 04:26:41,692][BaseTrainer][INFO] - [Epoch 3/10, Iter 899/3560] 3.3813629150390625, cross_entropy: 3.3813629150390625 +[2025-04-29 04:26:42,580][BaseTrainer][INFO] - [Epoch 3/10, Iter 900/3560] 2.0756964683532715, cross_entropy: 2.0756964683532715 +[2025-04-29 04:26:46,012][BaseTrainer][INFO] - [Epoch 3/10, Iter 901/3560] 3.591379404067993, cross_entropy: 3.591379404067993 +[2025-04-29 04:26:46,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 902/3560] 3.857229232788086, cross_entropy: 3.857229232788086 +[2025-04-29 04:26:49,291][BaseTrainer][INFO] - [Epoch 3/10, Iter 903/3560] 2.424734115600586, cross_entropy: 2.424734115600586 +[2025-04-29 04:26:50,154][BaseTrainer][INFO] - [Epoch 3/10, Iter 904/3560] 2.814857244491577, cross_entropy: 2.814857244491577 +[2025-04-29 04:26:53,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 905/3560] 2.9405577182769775, cross_entropy: 2.9405577182769775 +[2025-04-29 04:26:53,894][BaseTrainer][INFO] - [Epoch 3/10, Iter 906/3560] 3.2588138580322266, cross_entropy: 3.2588138580322266 +[2025-04-29 04:26:57,046][BaseTrainer][INFO] - [Epoch 3/10, Iter 907/3560] 2.619781494140625, cross_entropy: 2.619781494140625 +[2025-04-29 04:26:57,934][BaseTrainer][INFO] - [Epoch 3/10, Iter 908/3560] 2.102539539337158, cross_entropy: 2.102539539337158 +[2025-04-29 04:27:00,503][BaseTrainer][INFO] - [Epoch 3/10, Iter 909/3560] 3.7974777221679688, cross_entropy: 3.7974777221679688 +[2025-04-29 04:27:01,390][BaseTrainer][INFO] - [Epoch 3/10, Iter 910/3560] 2.5570173263549805, cross_entropy: 2.5570173263549805 +[2025-04-29 04:27:03,906][BaseTrainer][INFO] - [Epoch 3/10, Iter 911/3560] 2.7069497108459473, cross_entropy: 2.7069497108459473 +[2025-04-29 04:27:04,786][BaseTrainer][INFO] - [Epoch 3/10, Iter 912/3560] 3.8230817317962646, cross_entropy: 3.8230817317962646 +[2025-04-29 04:27:08,281][BaseTrainer][INFO] - [Epoch 3/10, Iter 913/3560] 2.4996485710144043, cross_entropy: 2.4996485710144043 +[2025-04-29 04:27:09,161][BaseTrainer][INFO] - [Epoch 3/10, Iter 914/3560] 2.9945566654205322, cross_entropy: 2.9945566654205322 +[2025-04-29 04:27:11,909][BaseTrainer][INFO] - [Epoch 3/10, Iter 915/3560] 3.248462677001953, cross_entropy: 3.248462677001953 +[2025-04-29 04:27:12,768][BaseTrainer][INFO] - [Epoch 3/10, Iter 916/3560] 2.795938491821289, cross_entropy: 2.795938491821289 +[2025-04-29 04:27:15,388][BaseTrainer][INFO] - [Epoch 3/10, Iter 917/3560] 3.5447793006896973, cross_entropy: 3.5447793006896973 +[2025-04-29 04:27:16,245][BaseTrainer][INFO] - [Epoch 3/10, Iter 918/3560] 2.0161614418029785, cross_entropy: 2.0161614418029785 +[2025-04-29 04:27:19,520][BaseTrainer][INFO] - [Epoch 3/10, Iter 919/3560] 3.769543409347534, cross_entropy: 3.769543409347534 +[2025-04-29 04:27:20,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 920/3560] 2.7559595108032227, cross_entropy: 2.7559595108032227 +[2025-04-29 04:27:23,754][BaseTrainer][INFO] - [Epoch 3/10, Iter 921/3560] 2.2543485164642334, cross_entropy: 2.2543485164642334 +[2025-04-29 04:27:24,639][BaseTrainer][INFO] - [Epoch 3/10, Iter 922/3560] 3.8532605171203613, cross_entropy: 3.8532605171203613 +[2025-04-29 04:27:27,452][BaseTrainer][INFO] - [Epoch 3/10, Iter 923/3560] 3.913475751876831, cross_entropy: 3.913475751876831 +[2025-04-29 04:27:28,335][BaseTrainer][INFO] - [Epoch 3/10, Iter 924/3560] 2.742551803588867, cross_entropy: 2.742551803588867 +[2025-04-29 04:27:31,065][BaseTrainer][INFO] - [Epoch 3/10, Iter 925/3560] 3.1495494842529297, cross_entropy: 3.1495494842529297 +[2025-04-29 04:27:31,960][BaseTrainer][INFO] - [Epoch 3/10, Iter 926/3560] 2.6125168800354004, cross_entropy: 2.6125168800354004 +[2025-04-29 04:27:35,263][BaseTrainer][INFO] - [Epoch 3/10, Iter 927/3560] 3.335204601287842, cross_entropy: 3.335204601287842 +[2025-04-29 04:27:36,123][BaseTrainer][INFO] - [Epoch 3/10, Iter 928/3560] 2.27344012260437, cross_entropy: 2.27344012260437 +[2025-04-29 04:27:38,611][BaseTrainer][INFO] - [Epoch 3/10, Iter 929/3560] 2.3790125846862793, cross_entropy: 2.3790125846862793 +[2025-04-29 04:27:39,467][BaseTrainer][INFO] - [Epoch 3/10, Iter 930/3560] 3.7113003730773926, cross_entropy: 3.7113003730773926 +[2025-04-29 04:27:43,799][BaseTrainer][INFO] - [Epoch 3/10, Iter 931/3560] 2.6535587310791016, cross_entropy: 2.6535587310791016 +[2025-04-29 04:27:44,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 932/3560] 2.138091564178467, cross_entropy: 2.138091564178467 +[2025-04-29 04:27:47,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 933/3560] 1.868680477142334, cross_entropy: 1.868680477142334 +[2025-04-29 04:27:48,541][BaseTrainer][INFO] - [Epoch 3/10, Iter 934/3560] 2.90554141998291, cross_entropy: 2.90554141998291 +[2025-04-29 04:27:51,366][BaseTrainer][INFO] - [Epoch 3/10, Iter 935/3560] 2.587042808532715, cross_entropy: 2.587042808532715 +[2025-04-29 04:27:52,256][BaseTrainer][INFO] - [Epoch 3/10, Iter 936/3560] 3.466552734375, cross_entropy: 3.466552734375 +[2025-04-29 04:27:55,475][BaseTrainer][INFO] - [Epoch 3/10, Iter 937/3560] 3.2317957878112793, cross_entropy: 3.2317957878112793 +[2025-04-29 04:27:56,336][BaseTrainer][INFO] - [Epoch 3/10, Iter 938/3560] 2.2058372497558594, cross_entropy: 2.2058372497558594 +[2025-04-29 04:27:58,990][BaseTrainer][INFO] - [Epoch 3/10, Iter 939/3560] 3.0852432250976562, cross_entropy: 3.0852432250976562 +[2025-04-29 04:27:59,847][BaseTrainer][INFO] - [Epoch 3/10, Iter 940/3560] 3.678905963897705, cross_entropy: 3.678905963897705 +[2025-04-29 04:28:03,387][BaseTrainer][INFO] - [Epoch 3/10, Iter 941/3560] 3.9332332611083984, cross_entropy: 3.9332332611083984 +[2025-04-29 04:28:04,272][BaseTrainer][INFO] - [Epoch 3/10, Iter 942/3560] 3.513636827468872, cross_entropy: 3.513636827468872 +[2025-04-29 04:28:07,081][BaseTrainer][INFO] - [Epoch 3/10, Iter 943/3560] 2.8802762031555176, cross_entropy: 2.8802762031555176 +[2025-04-29 04:28:07,941][BaseTrainer][INFO] - [Epoch 3/10, Iter 944/3560] 3.2701799869537354, cross_entropy: 3.2701799869537354 +[2025-04-29 04:28:10,758][BaseTrainer][INFO] - [Epoch 3/10, Iter 945/3560] 2.139474391937256, cross_entropy: 2.139474391937256 +[2025-04-29 04:28:11,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 946/3560] 3.655324697494507, cross_entropy: 3.655324697494507 +[2025-04-29 04:28:14,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 947/3560] 3.6731653213500977, cross_entropy: 3.6731653213500977 +[2025-04-29 04:28:15,760][BaseTrainer][INFO] - [Epoch 3/10, Iter 948/3560] 2.2940635681152344, cross_entropy: 2.2940635681152344 +[2025-04-29 04:28:18,431][BaseTrainer][INFO] - [Epoch 3/10, Iter 949/3560] 2.8004415035247803, cross_entropy: 2.8004415035247803 +[2025-04-29 04:28:19,323][BaseTrainer][INFO] - [Epoch 3/10, Iter 950/3560] 3.4865188598632812, cross_entropy: 3.4865188598632812 +[2025-04-29 04:28:22,239][BaseTrainer][INFO] - [Epoch 3/10, Iter 951/3560] 3.15480899810791, cross_entropy: 3.15480899810791 +[2025-04-29 04:28:23,114][BaseTrainer][INFO] - [Epoch 3/10, Iter 952/3560] 2.3973612785339355, cross_entropy: 2.3973612785339355 +[2025-04-29 04:28:26,047][BaseTrainer][INFO] - [Epoch 3/10, Iter 953/3560] 2.527299642562866, cross_entropy: 2.527299642562866 +[2025-04-29 04:28:26,907][BaseTrainer][INFO] - [Epoch 3/10, Iter 954/3560] 1.676531195640564, cross_entropy: 1.676531195640564 +[2025-04-29 04:28:29,628][BaseTrainer][INFO] - [Epoch 3/10, Iter 955/3560] 2.697638511657715, cross_entropy: 2.697638511657715 +[2025-04-29 04:28:30,498][BaseTrainer][INFO] - [Epoch 3/10, Iter 956/3560] 3.535944938659668, cross_entropy: 3.535944938659668 +[2025-04-29 04:28:34,018][BaseTrainer][INFO] - [Epoch 3/10, Iter 957/3560] 3.5182948112487793, cross_entropy: 3.5182948112487793 +[2025-04-29 04:28:34,877][BaseTrainer][INFO] - [Epoch 3/10, Iter 958/3560] 2.729538917541504, cross_entropy: 2.729538917541504 +[2025-04-29 04:28:38,315][BaseTrainer][INFO] - [Epoch 3/10, Iter 959/3560] 3.8289525508880615, cross_entropy: 3.8289525508880615 +[2025-04-29 04:28:39,196][BaseTrainer][INFO] - [Epoch 3/10, Iter 960/3560] 1.9638936519622803, cross_entropy: 1.9638936519622803 +[2025-04-29 04:28:41,913][BaseTrainer][INFO] - [Epoch 3/10, Iter 961/3560] 2.529787063598633, cross_entropy: 2.529787063598633 +[2025-04-29 04:28:42,798][BaseTrainer][INFO] - [Epoch 3/10, Iter 962/3560] 2.5082478523254395, cross_entropy: 2.5082478523254395 +[2025-04-29 04:28:45,395][BaseTrainer][INFO] - [Epoch 3/10, Iter 963/3560] 3.1577401161193848, cross_entropy: 3.1577401161193848 +[2025-04-29 04:28:46,253][BaseTrainer][INFO] - [Epoch 3/10, Iter 964/3560] 1.8967007398605347, cross_entropy: 1.8967007398605347 +[2025-04-29 04:28:49,051][BaseTrainer][INFO] - [Epoch 3/10, Iter 965/3560] 2.934849262237549, cross_entropy: 2.934849262237549 +[2025-04-29 04:28:49,913][BaseTrainer][INFO] - [Epoch 3/10, Iter 966/3560] 2.4348230361938477, cross_entropy: 2.4348230361938477 +[2025-04-29 04:28:52,595][BaseTrainer][INFO] - [Epoch 3/10, Iter 967/3560] 3.683103322982788, cross_entropy: 3.683103322982788 +[2025-04-29 04:28:53,482][BaseTrainer][INFO] - [Epoch 3/10, Iter 968/3560] 2.1906657218933105, cross_entropy: 2.1906657218933105 +[2025-04-29 04:28:55,860][BaseTrainer][INFO] - [Epoch 3/10, Iter 969/3560] 3.872849225997925, cross_entropy: 3.872849225997925 +[2025-04-29 04:28:56,745][BaseTrainer][INFO] - [Epoch 3/10, Iter 970/3560] 3.7550952434539795, cross_entropy: 3.7550952434539795 +[2025-04-29 04:28:59,653][BaseTrainer][INFO] - [Epoch 3/10, Iter 971/3560] 2.26102352142334, cross_entropy: 2.26102352142334 +[2025-04-29 04:29:00,512][BaseTrainer][INFO] - [Epoch 3/10, Iter 972/3560] 1.668857216835022, cross_entropy: 1.668857216835022 +[2025-04-29 04:29:02,931][BaseTrainer][INFO] - [Epoch 3/10, Iter 973/3560] 3.6269948482513428, cross_entropy: 3.6269948482513428 +[2025-04-29 04:29:03,826][BaseTrainer][INFO] - [Epoch 3/10, Iter 974/3560] 3.832580089569092, cross_entropy: 3.832580089569092 +[2025-04-29 04:29:07,126][BaseTrainer][INFO] - [Epoch 3/10, Iter 975/3560] 3.6299822330474854, cross_entropy: 3.6299822330474854 +[2025-04-29 04:29:07,986][BaseTrainer][INFO] - [Epoch 3/10, Iter 976/3560] 3.725294828414917, cross_entropy: 3.725294828414917 +[2025-04-29 04:29:11,157][BaseTrainer][INFO] - [Epoch 3/10, Iter 977/3560] 3.500176429748535, cross_entropy: 3.500176429748535 +[2025-04-29 04:29:12,039][BaseTrainer][INFO] - [Epoch 3/10, Iter 978/3560] 2.4433388710021973, cross_entropy: 2.4433388710021973 +[2025-04-29 04:29:14,640][BaseTrainer][INFO] - [Epoch 3/10, Iter 979/3560] 2.1101880073547363, cross_entropy: 2.1101880073547363 +[2025-04-29 04:29:15,533][BaseTrainer][INFO] - [Epoch 3/10, Iter 980/3560] 2.9945268630981445, cross_entropy: 2.9945268630981445 +[2025-04-29 04:29:18,922][BaseTrainer][INFO] - [Epoch 3/10, Iter 981/3560] 3.4455153942108154, cross_entropy: 3.4455153942108154 +[2025-04-29 04:29:19,784][BaseTrainer][INFO] - [Epoch 3/10, Iter 982/3560] 2.3817660808563232, cross_entropy: 2.3817660808563232 +[2025-04-29 04:29:22,420][BaseTrainer][INFO] - [Epoch 3/10, Iter 983/3560] 2.4271585941314697, cross_entropy: 2.4271585941314697 +[2025-04-29 04:29:23,284][BaseTrainer][INFO] - [Epoch 3/10, Iter 984/3560] 3.695484161376953, cross_entropy: 3.695484161376953 +[2025-04-29 04:29:26,058][BaseTrainer][INFO] - [Epoch 3/10, Iter 985/3560] 3.6609349250793457, cross_entropy: 3.6609349250793457 +[2025-04-29 04:29:26,916][BaseTrainer][INFO] - [Epoch 3/10, Iter 986/3560] 2.472867965698242, cross_entropy: 2.472867965698242 +[2025-04-29 04:29:29,838][BaseTrainer][INFO] - [Epoch 3/10, Iter 987/3560] 3.816289186477661, cross_entropy: 3.816289186477661 +[2025-04-29 04:29:30,699][BaseTrainer][INFO] - [Epoch 3/10, Iter 988/3560] 2.4080734252929688, cross_entropy: 2.4080734252929688 +[2025-04-29 04:29:34,145][BaseTrainer][INFO] - [Epoch 3/10, Iter 989/3560] 3.2085916996002197, cross_entropy: 3.2085916996002197 +[2025-04-29 04:29:35,002][BaseTrainer][INFO] - [Epoch 3/10, Iter 990/3560] 3.658825159072876, cross_entropy: 3.658825159072876 +[2025-04-29 04:29:37,472][BaseTrainer][INFO] - [Epoch 3/10, Iter 991/3560] 1.8677761554718018, cross_entropy: 1.8677761554718018 +[2025-04-29 04:29:38,360][BaseTrainer][INFO] - [Epoch 3/10, Iter 992/3560] 2.724677562713623, cross_entropy: 2.724677562713623 +[2025-04-29 04:29:41,851][BaseTrainer][INFO] - [Epoch 3/10, Iter 993/3560] 2.408707857131958, cross_entropy: 2.408707857131958 +[2025-04-29 04:29:42,732][BaseTrainer][INFO] - [Epoch 3/10, Iter 994/3560] 2.3914713859558105, cross_entropy: 2.3914713859558105 +[2025-04-29 04:29:44,939][BaseTrainer][INFO] - [Epoch 3/10, Iter 995/3560] 2.251173973083496, cross_entropy: 2.251173973083496 +[2025-04-29 04:29:45,796][BaseTrainer][INFO] - [Epoch 3/10, Iter 996/3560] 3.0327463150024414, cross_entropy: 3.0327463150024414 +[2025-04-29 04:29:48,915][BaseTrainer][INFO] - [Epoch 3/10, Iter 997/3560] 2.122077465057373, cross_entropy: 2.122077465057373 +[2025-04-29 04:29:49,803][BaseTrainer][INFO] - [Epoch 3/10, Iter 998/3560] 2.936466693878174, cross_entropy: 2.936466693878174 +[2025-04-29 04:29:53,038][BaseTrainer][INFO] - [Epoch 3/10, Iter 999/3560] 2.3003058433532715, cross_entropy: 2.3003058433532715 +[2025-04-29 04:29:53,933][BaseTrainer][INFO] - [Epoch 3/10, Iter 1000/3560] 2.613132953643799, cross_entropy: 2.613132953643799 +[2025-04-29 04:29:54,624][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/iteration1000.pth. +[2025-04-29 04:29:58,428][BaseTrainer][INFO] - [Epoch 3/10, Iter 1001/3560] 3.387881278991699, cross_entropy: 3.387881278991699 +[2025-04-29 04:29:59,284][BaseTrainer][INFO] - [Epoch 3/10, Iter 1002/3560] 3.3596577644348145, cross_entropy: 3.3596577644348145 +[2025-04-29 04:30:02,377][BaseTrainer][INFO] - [Epoch 3/10, Iter 1003/3560] 2.508021116256714, cross_entropy: 2.508021116256714 +[2025-04-29 04:30:03,257][BaseTrainer][INFO] - [Epoch 3/10, Iter 1004/3560] 1.9367632865905762, cross_entropy: 1.9367632865905762 +[2025-04-29 04:30:05,662][BaseTrainer][INFO] - [Epoch 3/10, Iter 1005/3560] 3.8353192806243896, cross_entropy: 3.8353192806243896 +[2025-04-29 04:30:06,555][BaseTrainer][INFO] - [Epoch 3/10, Iter 1006/3560] 3.5092647075653076, cross_entropy: 3.5092647075653076 +[2025-04-29 04:30:09,375][BaseTrainer][INFO] - [Epoch 3/10, Iter 1007/3560] 2.6536147594451904, cross_entropy: 2.6536147594451904 +[2025-04-29 04:30:10,259][BaseTrainer][INFO] - [Epoch 3/10, Iter 1008/3560] 2.516663074493408, cross_entropy: 2.516663074493408 +[2025-04-29 04:30:13,364][BaseTrainer][INFO] - [Epoch 3/10, Iter 1009/3560] 2.960275173187256, cross_entropy: 2.960275173187256 +[2025-04-29 04:30:14,254][BaseTrainer][INFO] - [Epoch 3/10, Iter 1010/3560] 3.2669014930725098, cross_entropy: 3.2669014930725098 +[2025-04-29 04:30:16,512][BaseTrainer][INFO] - [Epoch 3/10, Iter 1011/3560] 2.0083651542663574, cross_entropy: 2.0083651542663574 +[2025-04-29 04:30:17,370][BaseTrainer][INFO] - [Epoch 3/10, Iter 1012/3560] 2.203392505645752, cross_entropy: 2.203392505645752 +[2025-04-29 04:30:19,950][BaseTrainer][INFO] - [Epoch 3/10, Iter 1013/3560] 3.5941386222839355, cross_entropy: 3.5941386222839355 +[2025-04-29 04:30:20,840][BaseTrainer][INFO] - [Epoch 3/10, Iter 1014/3560] 3.8201863765716553, cross_entropy: 3.8201863765716553 +[2025-04-29 04:30:23,703][BaseTrainer][INFO] - [Epoch 3/10, Iter 1015/3560] 3.5809805393218994, cross_entropy: 3.5809805393218994 +[2025-04-29 04:30:24,586][BaseTrainer][INFO] - [Epoch 3/10, Iter 1016/3560] 3.0433096885681152, cross_entropy: 3.0433096885681152 +[2025-04-29 04:30:27,523][BaseTrainer][INFO] - [Epoch 3/10, Iter 1017/3560] 2.069125175476074, cross_entropy: 2.069125175476074 +[2025-04-29 04:30:28,407][BaseTrainer][INFO] - [Epoch 3/10, Iter 1018/3560] 2.611720085144043, cross_entropy: 2.611720085144043 +[2025-04-29 04:30:30,967][BaseTrainer][INFO] - [Epoch 3/10, Iter 1019/3560] 2.6782045364379883, cross_entropy: 2.6782045364379883 +[2025-04-29 04:30:31,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 1020/3560] 3.286508560180664, cross_entropy: 3.286508560180664 +[2025-04-29 04:30:34,627][BaseTrainer][INFO] - [Epoch 3/10, Iter 1021/3560] 3.6428706645965576, cross_entropy: 3.6428706645965576 +[2025-04-29 04:30:35,491][BaseTrainer][INFO] - [Epoch 3/10, Iter 1022/3560] 2.104485034942627, cross_entropy: 2.104485034942627 +[2025-04-29 04:30:38,612][BaseTrainer][INFO] - [Epoch 3/10, Iter 1023/3560] 1.8506274223327637, cross_entropy: 1.8506274223327637 +[2025-04-29 04:30:39,472][BaseTrainer][INFO] - [Epoch 3/10, Iter 1024/3560] 2.1115026473999023, cross_entropy: 2.1115026473999023 +[2025-04-29 04:30:41,690][BaseTrainer][INFO] - [Epoch 3/10, Iter 1025/3560] 3.724208354949951, cross_entropy: 3.724208354949951 +[2025-04-29 04:30:42,578][BaseTrainer][INFO] - [Epoch 3/10, Iter 1026/3560] 2.7441048622131348, cross_entropy: 2.7441048622131348 +[2025-04-29 04:30:45,648][BaseTrainer][INFO] - [Epoch 3/10, Iter 1027/3560] 2.999448299407959, cross_entropy: 2.999448299407959 +[2025-04-29 04:30:46,506][BaseTrainer][INFO] - [Epoch 3/10, Iter 1028/3560] 3.8136115074157715, cross_entropy: 3.8136115074157715 +[2025-04-29 04:30:48,794][BaseTrainer][INFO] - [Epoch 3/10, Iter 1029/3560] 3.5096499919891357, cross_entropy: 3.5096499919891357 +[2025-04-29 04:30:49,655][BaseTrainer][INFO] - [Epoch 3/10, Iter 1030/3560] 3.3946352005004883, cross_entropy: 3.3946352005004883 +[2025-04-29 04:30:52,241][BaseTrainer][INFO] - [Epoch 3/10, Iter 1031/3560] 3.7530577182769775, cross_entropy: 3.7530577182769775 +[2025-04-29 04:30:53,135][BaseTrainer][INFO] - [Epoch 3/10, Iter 1032/3560] 3.144503593444824, cross_entropy: 3.144503593444824 +[2025-04-29 04:30:56,004][BaseTrainer][INFO] - [Epoch 3/10, Iter 1033/3560] 2.5412187576293945, cross_entropy: 2.5412187576293945 +[2025-04-29 04:30:56,947][BaseTrainer][INFO] - [Epoch 3/10, Iter 1034/3560] 3.0463123321533203, cross_entropy: 3.0463123321533203 +[2025-04-29 04:30:59,195][BaseTrainer][INFO] - [Epoch 3/10, Iter 1035/3560] 2.0477025508880615, cross_entropy: 2.0477025508880615 +[2025-04-29 04:31:00,090][BaseTrainer][INFO] - [Epoch 3/10, Iter 1036/3560] 3.7852461338043213, cross_entropy: 3.7852461338043213 +[2025-04-29 04:31:02,508][BaseTrainer][INFO] - [Epoch 3/10, Iter 1037/3560] 3.074718952178955, cross_entropy: 3.074718952178955 +[2025-04-29 04:31:03,499][BaseTrainer][INFO] - [Epoch 3/10, Iter 1038/3560] 2.1342275142669678, cross_entropy: 2.1342275142669678 +[2025-04-29 04:31:06,229][BaseTrainer][INFO] - [Epoch 3/10, Iter 1039/3560] 2.9914729595184326, cross_entropy: 2.9914729595184326 +[2025-04-29 04:31:07,086][BaseTrainer][INFO] - [Epoch 3/10, Iter 1040/3560] 3.5184125900268555, cross_entropy: 3.5184125900268555 +[2025-04-29 04:31:10,163][BaseTrainer][INFO] - [Epoch 3/10, Iter 1041/3560] 4.002313613891602, cross_entropy: 4.002313613891602 +[2025-04-29 04:31:11,031][BaseTrainer][INFO] - [Epoch 3/10, Iter 1042/3560] 2.602440118789673, cross_entropy: 2.602440118789673 +[2025-04-29 04:31:13,743][BaseTrainer][INFO] - [Epoch 3/10, Iter 1043/3560] 3.224076747894287, cross_entropy: 3.224076747894287 +[2025-04-29 04:31:14,623][BaseTrainer][INFO] - [Epoch 3/10, Iter 1044/3560] 3.5102040767669678, cross_entropy: 3.5102040767669678 +[2025-04-29 04:31:18,344][BaseTrainer][INFO] - [Epoch 3/10, Iter 1045/3560] 3.564067840576172, cross_entropy: 3.564067840576172 +[2025-04-29 04:31:19,229][BaseTrainer][INFO] - [Epoch 3/10, Iter 1046/3560] 2.028345823287964, cross_entropy: 2.028345823287964 +[2025-04-29 04:31:21,870][BaseTrainer][INFO] - [Epoch 3/10, Iter 1047/3560] 3.3883752822875977, cross_entropy: 3.3883752822875977 +[2025-04-29 04:31:22,729][BaseTrainer][INFO] - [Epoch 3/10, Iter 1048/3560] 3.7721939086914062, cross_entropy: 3.7721939086914062 +[2025-04-29 04:31:25,255][BaseTrainer][INFO] - [Epoch 3/10, Iter 1049/3560] 2.8896946907043457, cross_entropy: 2.8896946907043457 +[2025-04-29 04:31:26,172][BaseTrainer][INFO] - [Epoch 3/10, Iter 1050/3560] 2.3659989833831787, cross_entropy: 2.3659989833831787 +[2025-04-29 04:31:28,423][BaseTrainer][INFO] - [Epoch 3/10, Iter 1051/3560] 2.1313858032226562, cross_entropy: 2.1313858032226562 +[2025-04-29 04:31:29,342][BaseTrainer][INFO] - [Epoch 3/10, Iter 1052/3560] 2.010928153991699, cross_entropy: 2.010928153991699 +[2025-04-29 04:31:32,103][BaseTrainer][INFO] - [Epoch 3/10, Iter 1053/3560] 2.903629779815674, cross_entropy: 2.903629779815674 +[2025-04-29 04:31:33,005][BaseTrainer][INFO] - [Epoch 3/10, Iter 1054/3560] 3.0198378562927246, cross_entropy: 3.0198378562927246 +[2025-04-29 04:31:35,449][BaseTrainer][INFO] - [Epoch 3/10, Iter 1055/3560] 2.2799885272979736, cross_entropy: 2.2799885272979736 +[2025-04-29 04:31:36,985][BaseTrainer][INFO] - [Epoch 3/10, Iter 1056/3560] 2.3615965843200684, cross_entropy: 2.3615965843200684 +[2025-04-29 04:31:38,448][BaseTrainer][INFO] - [Epoch 3/10, Iter 1057/3560] 2.3022966384887695, cross_entropy: 2.3022966384887695 +[2025-04-29 04:31:40,712][BaseTrainer][INFO] - [Epoch 3/10, Iter 1058/3560] 2.120150327682495, cross_entropy: 2.120150327682495 +[2025-04-29 04:31:42,024][BaseTrainer][INFO] - [Epoch 3/10, Iter 1059/3560] 2.3426098823547363, cross_entropy: 2.3426098823547363 +[2025-04-29 04:31:44,386][BaseTrainer][INFO] - [Epoch 3/10, Iter 1060/3560] 1.6553990840911865, cross_entropy: 1.6553990840911865 +[2025-04-29 04:31:45,487][BaseTrainer][INFO] - [Epoch 3/10, Iter 1061/3560] 1.8546082973480225, cross_entropy: 1.8546082973480225 +[2025-04-29 04:31:48,569][BaseTrainer][INFO] - [Epoch 3/10, Iter 1062/3560] 3.965524196624756, cross_entropy: 3.965524196624756 +[2025-04-29 04:31:50,325][BaseTrainer][INFO] - [Epoch 3/10, Iter 1063/3560] 2.78900146484375, cross_entropy: 2.78900146484375 +[2025-04-29 04:31:51,739][BaseTrainer][INFO] - [Epoch 3/10, Iter 1064/3560] 1.957629680633545, cross_entropy: 1.957629680633545 +[2025-04-29 04:31:54,036][BaseTrainer][INFO] - [Epoch 3/10, Iter 1065/3560] 3.0600152015686035, cross_entropy: 3.0600152015686035 +[2025-04-29 04:31:55,964][BaseTrainer][INFO] - [Epoch 3/10, Iter 1066/3560] 2.0557732582092285, cross_entropy: 2.0557732582092285 +[2025-04-29 04:31:57,935][BaseTrainer][INFO] - [Epoch 3/10, Iter 1067/3560] 2.0636515617370605, cross_entropy: 2.0636515617370605 +[2025-04-29 04:31:58,708][BaseTrainer][INFO] - [Epoch 3/10, Iter 1068/3560] 2.0736942291259766, cross_entropy: 2.0736942291259766 +[2025-04-29 04:34:42,461][BaseTrainer][INFO] - [Epoch 3/10] (train) 2.9449541568756104, cross_entropy: 2.9449541568756104 +[2025-04-29 04:34:42,462][BaseTrainer][INFO] - [Epoch 3/10] (validation) 1.883060336112976, cross_entropy: 1.883060336112976 +[2025-04-29 04:34:43,304][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 04:34:43,810][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch3.pth. +[2025-04-29 04:34:44,607][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 04:34:49,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1069/3560] 2.4173178672790527, cross_entropy: 2.4173178672790527 +[2025-04-29 04:34:50,246][BaseTrainer][INFO] - [Epoch 4/10, Iter 1070/3560] 2.8243331909179688, cross_entropy: 2.8243331909179688 +[2025-04-29 04:34:52,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1071/3560] 1.9169038534164429, cross_entropy: 1.9169038534164429 +[2025-04-29 04:34:53,591][BaseTrainer][INFO] - [Epoch 4/10, Iter 1072/3560] 1.8741776943206787, cross_entropy: 1.8741776943206787 +[2025-04-29 04:34:56,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1073/3560] 3.2291388511657715, cross_entropy: 3.2291388511657715 +[2025-04-29 04:34:57,138][BaseTrainer][INFO] - [Epoch 4/10, Iter 1074/3560] 1.9960683584213257, cross_entropy: 1.9960683584213257 +[2025-04-29 04:34:59,868][BaseTrainer][INFO] - [Epoch 4/10, Iter 1075/3560] 3.4677329063415527, cross_entropy: 3.4677329063415527 +[2025-04-29 04:35:01,017][BaseTrainer][INFO] - [Epoch 4/10, Iter 1076/3560] 3.5267796516418457, cross_entropy: 3.5267796516418457 +[2025-04-29 04:35:03,971][BaseTrainer][INFO] - [Epoch 4/10, Iter 1077/3560] 3.0081591606140137, cross_entropy: 3.0081591606140137 +[2025-04-29 04:35:05,705][BaseTrainer][INFO] - [Epoch 4/10, Iter 1078/3560] 3.273181915283203, cross_entropy: 3.273181915283203 +[2025-04-29 04:35:07,793][BaseTrainer][INFO] - [Epoch 4/10, Iter 1079/3560] 2.213202476501465, cross_entropy: 2.213202476501465 +[2025-04-29 04:35:09,804][BaseTrainer][INFO] - [Epoch 4/10, Iter 1080/3560] 2.5455591678619385, cross_entropy: 2.5455591678619385 +[2025-04-29 04:35:11,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1081/3560] 3.0939712524414062, cross_entropy: 3.0939712524414062 +[2025-04-29 04:35:14,995][BaseTrainer][INFO] - [Epoch 4/10, Iter 1082/3560] 2.6275296211242676, cross_entropy: 2.6275296211242676 +[2025-04-29 04:35:15,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1083/3560] 3.4280378818511963, cross_entropy: 3.4280378818511963 +[2025-04-29 04:35:18,957][BaseTrainer][INFO] - [Epoch 4/10, Iter 1084/3560] 1.9217665195465088, cross_entropy: 1.9217665195465088 +[2025-04-29 04:35:19,839][BaseTrainer][INFO] - [Epoch 4/10, Iter 1085/3560] 2.013871908187866, cross_entropy: 2.013871908187866 +[2025-04-29 04:35:22,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1086/3560] 2.4278948307037354, cross_entropy: 2.4278948307037354 +[2025-04-29 04:35:23,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1087/3560] 3.257657051086426, cross_entropy: 3.257657051086426 +[2025-04-29 04:35:26,865][BaseTrainer][INFO] - [Epoch 4/10, Iter 1088/3560] 2.2923617362976074, cross_entropy: 2.2923617362976074 +[2025-04-29 04:35:27,723][BaseTrainer][INFO] - [Epoch 4/10, Iter 1089/3560] 3.4054903984069824, cross_entropy: 3.4054903984069824 +[2025-04-29 04:35:31,224][BaseTrainer][INFO] - [Epoch 4/10, Iter 1090/3560] 2.1131911277770996, cross_entropy: 2.1131911277770996 +[2025-04-29 04:35:32,107][BaseTrainer][INFO] - [Epoch 4/10, Iter 1091/3560] 2.2128705978393555, cross_entropy: 2.2128705978393555 +[2025-04-29 04:35:35,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1092/3560] 3.8223061561584473, cross_entropy: 3.8223061561584473 +[2025-04-29 04:35:36,521][BaseTrainer][INFO] - [Epoch 4/10, Iter 1093/3560] 3.876303195953369, cross_entropy: 3.876303195953369 +[2025-04-29 04:35:39,119][BaseTrainer][INFO] - [Epoch 4/10, Iter 1094/3560] 1.7255980968475342, cross_entropy: 1.7255980968475342 +[2025-04-29 04:35:40,002][BaseTrainer][INFO] - [Epoch 4/10, Iter 1095/3560] 2.0215840339660645, cross_entropy: 2.0215840339660645 +[2025-04-29 04:35:42,831][BaseTrainer][INFO] - [Epoch 4/10, Iter 1096/3560] 3.3042783737182617, cross_entropy: 3.3042783737182617 +[2025-04-29 04:35:43,732][BaseTrainer][INFO] - [Epoch 4/10, Iter 1097/3560] 2.8484106063842773, cross_entropy: 2.8484106063842773 +[2025-04-29 04:35:46,879][BaseTrainer][INFO] - [Epoch 4/10, Iter 1098/3560] 2.373635768890381, cross_entropy: 2.373635768890381 +[2025-04-29 04:35:48,098][BaseTrainer][INFO] - [Epoch 4/10, Iter 1099/3560] 2.216141700744629, cross_entropy: 2.216141700744629 +[2025-04-29 04:35:50,726][BaseTrainer][INFO] - [Epoch 4/10, Iter 1100/3560] 2.7257907390594482, cross_entropy: 2.7257907390594482 +[2025-04-29 04:35:51,640][BaseTrainer][INFO] - [Epoch 4/10, Iter 1101/3560] 3.558407783508301, cross_entropy: 3.558407783508301 +[2025-04-29 04:35:55,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1102/3560] 2.9595184326171875, cross_entropy: 2.9595184326171875 +[2025-04-29 04:35:56,065][BaseTrainer][INFO] - [Epoch 4/10, Iter 1103/3560] 2.288154363632202, cross_entropy: 2.288154363632202 +[2025-04-29 04:35:59,295][BaseTrainer][INFO] - [Epoch 4/10, Iter 1104/3560] 2.495225429534912, cross_entropy: 2.495225429534912 +[2025-04-29 04:36:00,182][BaseTrainer][INFO] - [Epoch 4/10, Iter 1105/3560] 3.0493955612182617, cross_entropy: 3.0493955612182617 +[2025-04-29 04:36:03,278][BaseTrainer][INFO] - [Epoch 4/10, Iter 1106/3560] 3.2155628204345703, cross_entropy: 3.2155628204345703 +[2025-04-29 04:36:04,143][BaseTrainer][INFO] - [Epoch 4/10, Iter 1107/3560] 3.407776117324829, cross_entropy: 3.407776117324829 +[2025-04-29 04:36:07,383][BaseTrainer][INFO] - [Epoch 4/10, Iter 1108/3560] 1.8667421340942383, cross_entropy: 1.8667421340942383 +[2025-04-29 04:36:08,245][BaseTrainer][INFO] - [Epoch 4/10, Iter 1109/3560] 2.5738906860351562, cross_entropy: 2.5738906860351562 +[2025-04-29 04:36:11,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1110/3560] 3.1881532669067383, cross_entropy: 3.1881532669067383 +[2025-04-29 04:36:12,007][BaseTrainer][INFO] - [Epoch 4/10, Iter 1111/3560] 2.6099977493286133, cross_entropy: 2.6099977493286133 +[2025-04-29 04:36:15,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1112/3560] 2.995850086212158, cross_entropy: 2.995850086212158 +[2025-04-29 04:36:16,255][BaseTrainer][INFO] - [Epoch 4/10, Iter 1113/3560] 3.7331111431121826, cross_entropy: 3.7331111431121826 +[2025-04-29 04:36:20,361][BaseTrainer][INFO] - [Epoch 4/10, Iter 1114/3560] 2.7432782649993896, cross_entropy: 2.7432782649993896 +[2025-04-29 04:36:21,244][BaseTrainer][INFO] - [Epoch 4/10, Iter 1115/3560] 2.1526529788970947, cross_entropy: 2.1526529788970947 +[2025-04-29 04:36:24,119][BaseTrainer][INFO] - [Epoch 4/10, Iter 1116/3560] 2.6251139640808105, cross_entropy: 2.6251139640808105 +[2025-04-29 04:36:25,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1117/3560] 2.906625270843506, cross_entropy: 2.906625270843506 +[2025-04-29 04:36:27,884][BaseTrainer][INFO] - [Epoch 4/10, Iter 1118/3560] 2.245265245437622, cross_entropy: 2.245265245437622 +[2025-04-29 04:36:28,746][BaseTrainer][INFO] - [Epoch 4/10, Iter 1119/3560] 2.1931045055389404, cross_entropy: 2.1931045055389404 +[2025-04-29 04:36:31,323][BaseTrainer][INFO] - [Epoch 4/10, Iter 1120/3560] 3.1536850929260254, cross_entropy: 3.1536850929260254 +[2025-04-29 04:36:32,208][BaseTrainer][INFO] - [Epoch 4/10, Iter 1121/3560] 2.062167167663574, cross_entropy: 2.062167167663574 +[2025-04-29 04:36:35,220][BaseTrainer][INFO] - [Epoch 4/10, Iter 1122/3560] 3.017230987548828, cross_entropy: 3.017230987548828 +[2025-04-29 04:36:36,078][BaseTrainer][INFO] - [Epoch 4/10, Iter 1123/3560] 2.1580798625946045, cross_entropy: 2.1580798625946045 +[2025-04-29 04:36:38,880][BaseTrainer][INFO] - [Epoch 4/10, Iter 1124/3560] 2.300201654434204, cross_entropy: 2.300201654434204 +[2025-04-29 04:36:39,771][BaseTrainer][INFO] - [Epoch 4/10, Iter 1125/3560] 2.228154182434082, cross_entropy: 2.228154182434082 +[2025-04-29 04:36:42,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1126/3560] 2.5682239532470703, cross_entropy: 2.5682239532470703 +[2025-04-29 04:36:43,371][BaseTrainer][INFO] - [Epoch 4/10, Iter 1127/3560] 3.6816153526306152, cross_entropy: 3.6816153526306152 +[2025-04-29 04:36:46,639][BaseTrainer][INFO] - [Epoch 4/10, Iter 1128/3560] 2.6262617111206055, cross_entropy: 2.6262617111206055 +[2025-04-29 04:36:47,496][BaseTrainer][INFO] - [Epoch 4/10, Iter 1129/3560] 1.8794348239898682, cross_entropy: 1.8794348239898682 +[2025-04-29 04:36:50,300][BaseTrainer][INFO] - [Epoch 4/10, Iter 1130/3560] 3.587965965270996, cross_entropy: 3.587965965270996 +[2025-04-29 04:36:51,156][BaseTrainer][INFO] - [Epoch 4/10, Iter 1131/3560] 2.373244285583496, cross_entropy: 2.373244285583496 +[2025-04-29 04:36:54,421][BaseTrainer][INFO] - [Epoch 4/10, Iter 1132/3560] 2.6413378715515137, cross_entropy: 2.6413378715515137 +[2025-04-29 04:36:55,282][BaseTrainer][INFO] - [Epoch 4/10, Iter 1133/3560] 2.4108450412750244, cross_entropy: 2.4108450412750244 +[2025-04-29 04:36:58,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1134/3560] 3.517805337905884, cross_entropy: 3.517805337905884 +[2025-04-29 04:36:59,165][BaseTrainer][INFO] - [Epoch 4/10, Iter 1135/3560] 2.388118028640747, cross_entropy: 2.388118028640747 +[2025-04-29 04:37:01,666][BaseTrainer][INFO] - [Epoch 4/10, Iter 1136/3560] 3.2875332832336426, cross_entropy: 3.2875332832336426 +[2025-04-29 04:37:02,551][BaseTrainer][INFO] - [Epoch 4/10, Iter 1137/3560] 2.797119617462158, cross_entropy: 2.797119617462158 +[2025-04-29 04:37:05,681][BaseTrainer][INFO] - [Epoch 4/10, Iter 1138/3560] 2.1800601482391357, cross_entropy: 2.1800601482391357 +[2025-04-29 04:37:06,561][BaseTrainer][INFO] - [Epoch 4/10, Iter 1139/3560] 1.7291651964187622, cross_entropy: 1.7291651964187622 +[2025-04-29 04:37:09,540][BaseTrainer][INFO] - [Epoch 4/10, Iter 1140/3560] 2.6699600219726562, cross_entropy: 2.6699600219726562 +[2025-04-29 04:37:10,429][BaseTrainer][INFO] - [Epoch 4/10, Iter 1141/3560] 2.0617551803588867, cross_entropy: 2.0617551803588867 +[2025-04-29 04:37:13,473][BaseTrainer][INFO] - [Epoch 4/10, Iter 1142/3560] 2.782061815261841, cross_entropy: 2.782061815261841 +[2025-04-29 04:37:14,330][BaseTrainer][INFO] - [Epoch 4/10, Iter 1143/3560] 3.6676416397094727, cross_entropy: 3.6676416397094727 +[2025-04-29 04:37:17,206][BaseTrainer][INFO] - [Epoch 4/10, Iter 1144/3560] 2.535116672515869, cross_entropy: 2.535116672515869 +[2025-04-29 04:37:18,072][BaseTrainer][INFO] - [Epoch 4/10, Iter 1145/3560] 3.322225570678711, cross_entropy: 3.322225570678711 +[2025-04-29 04:37:20,454][BaseTrainer][INFO] - [Epoch 4/10, Iter 1146/3560] 2.4193105697631836, cross_entropy: 2.4193105697631836 +[2025-04-29 04:37:21,338][BaseTrainer][INFO] - [Epoch 4/10, Iter 1147/3560] 2.0172247886657715, cross_entropy: 2.0172247886657715 +[2025-04-29 04:37:24,481][BaseTrainer][INFO] - [Epoch 4/10, Iter 1148/3560] 3.5255401134490967, cross_entropy: 3.5255401134490967 +[2025-04-29 04:37:25,341][BaseTrainer][INFO] - [Epoch 4/10, Iter 1149/3560] 3.729172706604004, cross_entropy: 3.729172706604004 +[2025-04-29 04:37:29,848][BaseTrainer][INFO] - [Epoch 4/10, Iter 1150/3560] 2.107787609100342, cross_entropy: 2.107787609100342 +[2025-04-29 04:37:30,705][BaseTrainer][INFO] - [Epoch 4/10, Iter 1151/3560] 2.4871280193328857, cross_entropy: 2.4871280193328857 +[2025-04-29 04:37:32,808][BaseTrainer][INFO] - [Epoch 4/10, Iter 1152/3560] 1.9241759777069092, cross_entropy: 1.9241759777069092 +[2025-04-29 04:37:33,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1153/3560] 3.010823965072632, cross_entropy: 3.010823965072632 +[2025-04-29 04:37:36,663][BaseTrainer][INFO] - [Epoch 4/10, Iter 1154/3560] 2.416259527206421, cross_entropy: 2.416259527206421 +[2025-04-29 04:37:37,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1155/3560] 3.653785228729248, cross_entropy: 3.653785228729248 +[2025-04-29 04:37:41,122][BaseTrainer][INFO] - [Epoch 4/10, Iter 1156/3560] 2.698024034500122, cross_entropy: 2.698024034500122 +[2025-04-29 04:37:42,009][BaseTrainer][INFO] - [Epoch 4/10, Iter 1157/3560] 3.487567663192749, cross_entropy: 3.487567663192749 +[2025-04-29 04:37:44,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1158/3560] 3.1406373977661133, cross_entropy: 3.1406373977661133 +[2025-04-29 04:37:45,636][BaseTrainer][INFO] - [Epoch 4/10, Iter 1159/3560] 3.2847063541412354, cross_entropy: 3.2847063541412354 +[2025-04-29 04:37:48,844][BaseTrainer][INFO] - [Epoch 4/10, Iter 1160/3560] 2.0785813331604004, cross_entropy: 2.0785813331604004 +[2025-04-29 04:37:49,704][BaseTrainer][INFO] - [Epoch 4/10, Iter 1161/3560] 2.7995033264160156, cross_entropy: 2.7995033264160156 +[2025-04-29 04:37:52,928][BaseTrainer][INFO] - [Epoch 4/10, Iter 1162/3560] 2.1145334243774414, cross_entropy: 2.1145334243774414 +[2025-04-29 04:37:53,796][BaseTrainer][INFO] - [Epoch 4/10, Iter 1163/3560] 2.122347831726074, cross_entropy: 2.122347831726074 +[2025-04-29 04:37:56,101][BaseTrainer][INFO] - [Epoch 4/10, Iter 1164/3560] 2.9193360805511475, cross_entropy: 2.9193360805511475 +[2025-04-29 04:37:56,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1165/3560] 2.5666375160217285, cross_entropy: 2.5666375160217285 +[2025-04-29 04:37:59,710][BaseTrainer][INFO] - [Epoch 4/10, Iter 1166/3560] 2.185490846633911, cross_entropy: 2.185490846633911 +[2025-04-29 04:38:00,598][BaseTrainer][INFO] - [Epoch 4/10, Iter 1167/3560] 2.4874331951141357, cross_entropy: 2.4874331951141357 +[2025-04-29 04:38:03,853][BaseTrainer][INFO] - [Epoch 4/10, Iter 1168/3560] 2.43618106842041, cross_entropy: 2.43618106842041 +[2025-04-29 04:38:04,720][BaseTrainer][INFO] - [Epoch 4/10, Iter 1169/3560] 2.247192859649658, cross_entropy: 2.247192859649658 +[2025-04-29 04:38:06,971][BaseTrainer][INFO] - [Epoch 4/10, Iter 1170/3560] 2.2504210472106934, cross_entropy: 2.2504210472106934 +[2025-04-29 04:38:07,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1171/3560] 3.4611546993255615, cross_entropy: 3.4611546993255615 +[2025-04-29 04:38:10,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1172/3560] 3.0757389068603516, cross_entropy: 3.0757389068603516 +[2025-04-29 04:38:11,716][BaseTrainer][INFO] - [Epoch 4/10, Iter 1173/3560] 2.9884471893310547, cross_entropy: 2.9884471893310547 +[2025-04-29 04:38:14,502][BaseTrainer][INFO] - [Epoch 4/10, Iter 1174/3560] 3.6327409744262695, cross_entropy: 3.6327409744262695 +[2025-04-29 04:38:15,388][BaseTrainer][INFO] - [Epoch 4/10, Iter 1175/3560] 2.716278553009033, cross_entropy: 2.716278553009033 +[2025-04-29 04:38:18,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1176/3560] 2.614987850189209, cross_entropy: 2.614987850189209 +[2025-04-29 04:38:18,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1177/3560] 2.2447168827056885, cross_entropy: 2.2447168827056885 +[2025-04-29 04:38:21,821][BaseTrainer][INFO] - [Epoch 4/10, Iter 1178/3560] 3.059065103530884, cross_entropy: 3.059065103530884 +[2025-04-29 04:38:22,679][BaseTrainer][INFO] - [Epoch 4/10, Iter 1179/3560] 2.3681392669677734, cross_entropy: 2.3681392669677734 +[2025-04-29 04:38:25,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1180/3560] 1.7029414176940918, cross_entropy: 1.7029414176940918 +[2025-04-29 04:38:26,269][BaseTrainer][INFO] - [Epoch 4/10, Iter 1181/3560] 3.261431932449341, cross_entropy: 3.261431932449341 +[2025-04-29 04:38:29,141][BaseTrainer][INFO] - [Epoch 4/10, Iter 1182/3560] 3.1578195095062256, cross_entropy: 3.1578195095062256 +[2025-04-29 04:38:30,025][BaseTrainer][INFO] - [Epoch 4/10, Iter 1183/3560] 3.44159197807312, cross_entropy: 3.44159197807312 +[2025-04-29 04:38:32,993][BaseTrainer][INFO] - [Epoch 4/10, Iter 1184/3560] 3.5352554321289062, cross_entropy: 3.5352554321289062 +[2025-04-29 04:38:33,889][BaseTrainer][INFO] - [Epoch 4/10, Iter 1185/3560] 2.7958574295043945, cross_entropy: 2.7958574295043945 +[2025-04-29 04:38:36,662][BaseTrainer][INFO] - [Epoch 4/10, Iter 1186/3560] 1.9895578622817993, cross_entropy: 1.9895578622817993 +[2025-04-29 04:38:37,546][BaseTrainer][INFO] - [Epoch 4/10, Iter 1187/3560] 3.4534695148468018, cross_entropy: 3.4534695148468018 +[2025-04-29 04:38:40,118][BaseTrainer][INFO] - [Epoch 4/10, Iter 1188/3560] 2.5195040702819824, cross_entropy: 2.5195040702819824 +[2025-04-29 04:38:40,982][BaseTrainer][INFO] - [Epoch 4/10, Iter 1189/3560] 3.212784767150879, cross_entropy: 3.212784767150879 +[2025-04-29 04:38:43,856][BaseTrainer][INFO] - [Epoch 4/10, Iter 1190/3560] 1.9406452178955078, cross_entropy: 1.9406452178955078 +[2025-04-29 04:38:44,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1191/3560] 3.4546329975128174, cross_entropy: 3.4546329975128174 +[2025-04-29 04:38:47,936][BaseTrainer][INFO] - [Epoch 4/10, Iter 1192/3560] 2.460463523864746, cross_entropy: 2.460463523864746 +[2025-04-29 04:38:48,826][BaseTrainer][INFO] - [Epoch 4/10, Iter 1193/3560] 1.856210708618164, cross_entropy: 1.856210708618164 +[2025-04-29 04:38:51,557][BaseTrainer][INFO] - [Epoch 4/10, Iter 1194/3560] 1.4886435270309448, cross_entropy: 1.4886435270309448 +[2025-04-29 04:38:52,442][BaseTrainer][INFO] - [Epoch 4/10, Iter 1195/3560] 1.932783603668213, cross_entropy: 1.932783603668213 +[2025-04-29 04:38:55,214][BaseTrainer][INFO] - [Epoch 4/10, Iter 1196/3560] 2.611339569091797, cross_entropy: 2.611339569091797 +[2025-04-29 04:38:56,096][BaseTrainer][INFO] - [Epoch 4/10, Iter 1197/3560] 1.7940101623535156, cross_entropy: 1.7940101623535156 +[2025-04-29 04:38:59,234][BaseTrainer][INFO] - [Epoch 4/10, Iter 1198/3560] 3.0555474758148193, cross_entropy: 3.0555474758148193 +[2025-04-29 04:39:00,091][BaseTrainer][INFO] - [Epoch 4/10, Iter 1199/3560] 2.557316780090332, cross_entropy: 2.557316780090332 +[2025-04-29 04:39:02,533][BaseTrainer][INFO] - [Epoch 4/10, Iter 1200/3560] 2.2099976539611816, cross_entropy: 2.2099976539611816 +[2025-04-29 04:39:03,392][BaseTrainer][INFO] - [Epoch 4/10, Iter 1201/3560] 2.505903720855713, cross_entropy: 2.505903720855713 +[2025-04-29 04:39:06,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1202/3560] 2.495814323425293, cross_entropy: 2.495814323425293 +[2025-04-29 04:39:07,870][BaseTrainer][INFO] - [Epoch 4/10, Iter 1203/3560] 3.3443808555603027, cross_entropy: 3.3443808555603027 +[2025-04-29 04:39:11,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1204/3560] 3.6038622856140137, cross_entropy: 3.6038622856140137 +[2025-04-29 04:39:12,820][BaseTrainer][INFO] - [Epoch 4/10, Iter 1205/3560] 2.2307186126708984, cross_entropy: 2.2307186126708984 +[2025-04-29 04:39:15,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1206/3560] 1.930862545967102, cross_entropy: 1.930862545967102 +[2025-04-29 04:39:16,331][BaseTrainer][INFO] - [Epoch 4/10, Iter 1207/3560] 2.670708417892456, cross_entropy: 2.670708417892456 +[2025-04-29 04:39:19,652][BaseTrainer][INFO] - [Epoch 4/10, Iter 1208/3560] 3.2279582023620605, cross_entropy: 3.2279582023620605 +[2025-04-29 04:39:20,514][BaseTrainer][INFO] - [Epoch 4/10, Iter 1209/3560] 3.6334850788116455, cross_entropy: 3.6334850788116455 +[2025-04-29 04:39:23,725][BaseTrainer][INFO] - [Epoch 4/10, Iter 1210/3560] 2.3055026531219482, cross_entropy: 2.3055026531219482 +[2025-04-29 04:39:24,612][BaseTrainer][INFO] - [Epoch 4/10, Iter 1211/3560] 3.256803512573242, cross_entropy: 3.256803512573242 +[2025-04-29 04:39:27,490][BaseTrainer][INFO] - [Epoch 4/10, Iter 1212/3560] 2.77559232711792, cross_entropy: 2.77559232711792 +[2025-04-29 04:39:28,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1213/3560] 2.0429892539978027, cross_entropy: 2.0429892539978027 +[2025-04-29 04:39:31,148][BaseTrainer][INFO] - [Epoch 4/10, Iter 1214/3560] 2.118666648864746, cross_entropy: 2.118666648864746 +[2025-04-29 04:39:32,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1215/3560] 2.065531015396118, cross_entropy: 2.065531015396118 +[2025-04-29 04:39:35,215][BaseTrainer][INFO] - [Epoch 4/10, Iter 1216/3560] 3.5842556953430176, cross_entropy: 3.5842556953430176 +[2025-04-29 04:39:36,106][BaseTrainer][INFO] - [Epoch 4/10, Iter 1217/3560] 3.035223960876465, cross_entropy: 3.035223960876465 +[2025-04-29 04:39:38,691][BaseTrainer][INFO] - [Epoch 4/10, Iter 1218/3560] 3.4271745681762695, cross_entropy: 3.4271745681762695 +[2025-04-29 04:39:39,588][BaseTrainer][INFO] - [Epoch 4/10, Iter 1219/3560] 3.276630163192749, cross_entropy: 3.276630163192749 +[2025-04-29 04:39:42,279][BaseTrainer][INFO] - [Epoch 4/10, Iter 1220/3560] 3.6231942176818848, cross_entropy: 3.6231942176818848 +[2025-04-29 04:39:43,136][BaseTrainer][INFO] - [Epoch 4/10, Iter 1221/3560] 2.2534596920013428, cross_entropy: 2.2534596920013428 +[2025-04-29 04:39:46,375][BaseTrainer][INFO] - [Epoch 4/10, Iter 1222/3560] 2.6559338569641113, cross_entropy: 2.6559338569641113 +[2025-04-29 04:39:47,268][BaseTrainer][INFO] - [Epoch 4/10, Iter 1223/3560] 2.9501261711120605, cross_entropy: 2.9501261711120605 +[2025-04-29 04:39:50,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1224/3560] 1.6958509683609009, cross_entropy: 1.6958509683609009 +[2025-04-29 04:39:51,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1225/3560] 2.4309685230255127, cross_entropy: 2.4309685230255127 +[2025-04-29 04:39:54,665][BaseTrainer][INFO] - [Epoch 4/10, Iter 1226/3560] 3.5440165996551514, cross_entropy: 3.5440165996551514 +[2025-04-29 04:39:55,526][BaseTrainer][INFO] - [Epoch 4/10, Iter 1227/3560] 2.591325283050537, cross_entropy: 2.591325283050537 +[2025-04-29 04:39:58,222][BaseTrainer][INFO] - [Epoch 4/10, Iter 1228/3560] 3.4744153022766113, cross_entropy: 3.4744153022766113 +[2025-04-29 04:39:59,111][BaseTrainer][INFO] - [Epoch 4/10, Iter 1229/3560] 2.9412548542022705, cross_entropy: 2.9412548542022705 +[2025-04-29 04:40:02,052][BaseTrainer][INFO] - [Epoch 4/10, Iter 1230/3560] 1.6672642230987549, cross_entropy: 1.6672642230987549 +[2025-04-29 04:40:02,939][BaseTrainer][INFO] - [Epoch 4/10, Iter 1231/3560] 2.9130728244781494, cross_entropy: 2.9130728244781494 +[2025-04-29 04:40:05,585][BaseTrainer][INFO] - [Epoch 4/10, Iter 1232/3560] 2.2163000106811523, cross_entropy: 2.2163000106811523 +[2025-04-29 04:40:06,480][BaseTrainer][INFO] - [Epoch 4/10, Iter 1233/3560] 2.1163296699523926, cross_entropy: 2.1163296699523926 +[2025-04-29 04:40:09,289][BaseTrainer][INFO] - [Epoch 4/10, Iter 1234/3560] 3.5850346088409424, cross_entropy: 3.5850346088409424 +[2025-04-29 04:40:10,150][BaseTrainer][INFO] - [Epoch 4/10, Iter 1235/3560] 1.9133261442184448, cross_entropy: 1.9133261442184448 +[2025-04-29 04:40:12,778][BaseTrainer][INFO] - [Epoch 4/10, Iter 1236/3560] 3.3208389282226562, cross_entropy: 3.3208389282226562 +[2025-04-29 04:40:13,639][BaseTrainer][INFO] - [Epoch 4/10, Iter 1237/3560] 2.1911792755126953, cross_entropy: 2.1911792755126953 +[2025-04-29 04:40:16,407][BaseTrainer][INFO] - [Epoch 4/10, Iter 1238/3560] 2.213716745376587, cross_entropy: 2.213716745376587 +[2025-04-29 04:40:17,300][BaseTrainer][INFO] - [Epoch 4/10, Iter 1239/3560] 1.8440403938293457, cross_entropy: 1.8440403938293457 +[2025-04-29 04:40:20,259][BaseTrainer][INFO] - [Epoch 4/10, Iter 1240/3560] 2.1511130332946777, cross_entropy: 2.1511130332946777 +[2025-04-29 04:40:21,123][BaseTrainer][INFO] - [Epoch 4/10, Iter 1241/3560] 2.317483901977539, cross_entropy: 2.317483901977539 +[2025-04-29 04:40:23,860][BaseTrainer][INFO] - [Epoch 4/10, Iter 1242/3560] 2.778491973876953, cross_entropy: 2.778491973876953 +[2025-04-29 04:40:24,755][BaseTrainer][INFO] - [Epoch 4/10, Iter 1243/3560] 2.082493305206299, cross_entropy: 2.082493305206299 +[2025-04-29 04:40:27,806][BaseTrainer][INFO] - [Epoch 4/10, Iter 1244/3560] 2.0142784118652344, cross_entropy: 2.0142784118652344 +[2025-04-29 04:40:28,668][BaseTrainer][INFO] - [Epoch 4/10, Iter 1245/3560] 1.6729896068572998, cross_entropy: 1.6729896068572998 +[2025-04-29 04:40:32,704][BaseTrainer][INFO] - [Epoch 4/10, Iter 1246/3560] 1.794316291809082, cross_entropy: 1.794316291809082 +[2025-04-29 04:40:33,594][BaseTrainer][INFO] - [Epoch 4/10, Iter 1247/3560] 2.2323319911956787, cross_entropy: 2.2323319911956787 +[2025-04-29 04:40:36,060][BaseTrainer][INFO] - [Epoch 4/10, Iter 1248/3560] 1.541779637336731, cross_entropy: 1.541779637336731 +[2025-04-29 04:40:36,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1249/3560] 2.2395644187927246, cross_entropy: 2.2395644187927246 +[2025-04-29 04:40:40,089][BaseTrainer][INFO] - [Epoch 4/10, Iter 1250/3560] 3.3725998401641846, cross_entropy: 3.3725998401641846 +[2025-04-29 04:40:40,950][BaseTrainer][INFO] - [Epoch 4/10, Iter 1251/3560] 3.2669973373413086, cross_entropy: 3.2669973373413086 +[2025-04-29 04:40:44,430][BaseTrainer][INFO] - [Epoch 4/10, Iter 1252/3560] 3.477376699447632, cross_entropy: 3.477376699447632 +[2025-04-29 04:40:45,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1253/3560] 2.0420992374420166, cross_entropy: 2.0420992374420166 +[2025-04-29 04:40:48,270][BaseTrainer][INFO] - [Epoch 4/10, Iter 1254/3560] 2.8844375610351562, cross_entropy: 2.8844375610351562 +[2025-04-29 04:40:49,131][BaseTrainer][INFO] - [Epoch 4/10, Iter 1255/3560] 3.6332314014434814, cross_entropy: 3.6332314014434814 +[2025-04-29 04:40:51,624][BaseTrainer][INFO] - [Epoch 4/10, Iter 1256/3560] 1.9290571212768555, cross_entropy: 1.9290571212768555 +[2025-04-29 04:40:52,524][BaseTrainer][INFO] - [Epoch 4/10, Iter 1257/3560] 1.9526628255844116, cross_entropy: 1.9526628255844116 +[2025-04-29 04:40:55,419][BaseTrainer][INFO] - [Epoch 4/10, Iter 1258/3560] 1.9711861610412598, cross_entropy: 1.9711861610412598 +[2025-04-29 04:40:56,314][BaseTrainer][INFO] - [Epoch 4/10, Iter 1259/3560] 2.2645888328552246, cross_entropy: 2.2645888328552246 +[2025-04-29 04:41:00,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1260/3560] 2.824047088623047, cross_entropy: 2.824047088623047 +[2025-04-29 04:41:00,929][BaseTrainer][INFO] - [Epoch 4/10, Iter 1261/3560] 3.1322808265686035, cross_entropy: 3.1322808265686035 +[2025-04-29 04:41:04,121][BaseTrainer][INFO] - [Epoch 4/10, Iter 1262/3560] 3.4662997722625732, cross_entropy: 3.4662997722625732 +[2025-04-29 04:41:04,980][BaseTrainer][INFO] - [Epoch 4/10, Iter 1263/3560] 2.197188138961792, cross_entropy: 2.197188138961792 +[2025-04-29 04:41:08,559][BaseTrainer][INFO] - [Epoch 4/10, Iter 1264/3560] 2.306138038635254, cross_entropy: 2.306138038635254 +[2025-04-29 04:41:09,444][BaseTrainer][INFO] - [Epoch 4/10, Iter 1265/3560] 2.470834732055664, cross_entropy: 2.470834732055664 +[2025-04-29 04:41:11,724][BaseTrainer][INFO] - [Epoch 4/10, Iter 1266/3560] 2.4276010990142822, cross_entropy: 2.4276010990142822 +[2025-04-29 04:41:12,615][BaseTrainer][INFO] - [Epoch 4/10, Iter 1267/3560] 1.979381799697876, cross_entropy: 1.979381799697876 +[2025-04-29 04:41:15,418][BaseTrainer][INFO] - [Epoch 4/10, Iter 1268/3560] 3.224199056625366, cross_entropy: 3.224199056625366 +[2025-04-29 04:41:16,315][BaseTrainer][INFO] - [Epoch 4/10, Iter 1269/3560] 2.9566879272460938, cross_entropy: 2.9566879272460938 +[2025-04-29 04:41:18,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1270/3560] 2.9358112812042236, cross_entropy: 2.9358112812042236 +[2025-04-29 04:41:19,641][BaseTrainer][INFO] - [Epoch 4/10, Iter 1271/3560] 3.364628314971924, cross_entropy: 3.364628314971924 +[2025-04-29 04:41:23,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1272/3560] 3.5601048469543457, cross_entropy: 3.5601048469543457 +[2025-04-29 04:41:24,381][BaseTrainer][INFO] - [Epoch 4/10, Iter 1273/3560] 3.0272319316864014, cross_entropy: 3.0272319316864014 +[2025-04-29 04:41:27,162][BaseTrainer][INFO] - [Epoch 4/10, Iter 1274/3560] 2.609987497329712, cross_entropy: 2.609987497329712 +[2025-04-29 04:41:28,045][BaseTrainer][INFO] - [Epoch 4/10, Iter 1275/3560] 3.702695608139038, cross_entropy: 3.702695608139038 +[2025-04-29 04:41:30,916][BaseTrainer][INFO] - [Epoch 4/10, Iter 1276/3560] 3.148092269897461, cross_entropy: 3.148092269897461 +[2025-04-29 04:41:31,812][BaseTrainer][INFO] - [Epoch 4/10, Iter 1277/3560] 2.6439132690429688, cross_entropy: 2.6439132690429688 +[2025-04-29 04:41:34,445][BaseTrainer][INFO] - [Epoch 4/10, Iter 1278/3560] 3.028254985809326, cross_entropy: 3.028254985809326 +[2025-04-29 04:41:35,337][BaseTrainer][INFO] - [Epoch 4/10, Iter 1279/3560] 2.170652389526367, cross_entropy: 2.170652389526367 +[2025-04-29 04:41:37,725][BaseTrainer][INFO] - [Epoch 4/10, Iter 1280/3560] 3.2289743423461914, cross_entropy: 3.2289743423461914 +[2025-04-29 04:41:38,584][BaseTrainer][INFO] - [Epoch 4/10, Iter 1281/3560] 2.740617036819458, cross_entropy: 2.740617036819458 +[2025-04-29 04:41:42,694][BaseTrainer][INFO] - [Epoch 4/10, Iter 1282/3560] 3.4940848350524902, cross_entropy: 3.4940848350524902 +[2025-04-29 04:41:43,554][BaseTrainer][INFO] - [Epoch 4/10, Iter 1283/3560] 2.13372802734375, cross_entropy: 2.13372802734375 +[2025-04-29 04:41:46,582][BaseTrainer][INFO] - [Epoch 4/10, Iter 1284/3560] 2.3839523792266846, cross_entropy: 2.3839523792266846 +[2025-04-29 04:41:47,465][BaseTrainer][INFO] - [Epoch 4/10, Iter 1285/3560] 3.2309417724609375, cross_entropy: 3.2309417724609375 +[2025-04-29 04:41:50,026][BaseTrainer][INFO] - [Epoch 4/10, Iter 1286/3560] 3.288942813873291, cross_entropy: 3.288942813873291 +[2025-04-29 04:41:50,887][BaseTrainer][INFO] - [Epoch 4/10, Iter 1287/3560] 3.1207480430603027, cross_entropy: 3.1207480430603027 +[2025-04-29 04:41:54,507][BaseTrainer][INFO] - [Epoch 4/10, Iter 1288/3560] 1.9570485353469849, cross_entropy: 1.9570485353469849 +[2025-04-29 04:41:55,391][BaseTrainer][INFO] - [Epoch 4/10, Iter 1289/3560] 2.021608829498291, cross_entropy: 2.021608829498291 +[2025-04-29 04:41:58,129][BaseTrainer][INFO] - [Epoch 4/10, Iter 1290/3560] 2.1273043155670166, cross_entropy: 2.1273043155670166 +[2025-04-29 04:41:59,011][BaseTrainer][INFO] - [Epoch 4/10, Iter 1291/3560] 2.119581937789917, cross_entropy: 2.119581937789917 +[2025-04-29 04:42:01,831][BaseTrainer][INFO] - [Epoch 4/10, Iter 1292/3560] 2.208921194076538, cross_entropy: 2.208921194076538 +[2025-04-29 04:42:02,714][BaseTrainer][INFO] - [Epoch 4/10, Iter 1293/3560] 2.0878374576568604, cross_entropy: 2.0878374576568604 +[2025-04-29 04:42:05,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1294/3560] 3.413266181945801, cross_entropy: 3.413266181945801 +[2025-04-29 04:42:06,800][BaseTrainer][INFO] - [Epoch 4/10, Iter 1295/3560] 1.7859828472137451, cross_entropy: 1.7859828472137451 +[2025-04-29 04:42:09,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1296/3560] 3.984506845474243, cross_entropy: 3.984506845474243 +[2025-04-29 04:42:10,233][BaseTrainer][INFO] - [Epoch 4/10, Iter 1297/3560] 3.687446355819702, cross_entropy: 3.687446355819702 +[2025-04-29 04:42:12,921][BaseTrainer][INFO] - [Epoch 4/10, Iter 1298/3560] 1.9416444301605225, cross_entropy: 1.9416444301605225 +[2025-04-29 04:42:13,789][BaseTrainer][INFO] - [Epoch 4/10, Iter 1299/3560] 1.9347972869873047, cross_entropy: 1.9347972869873047 +[2025-04-29 04:42:17,040][BaseTrainer][INFO] - [Epoch 4/10, Iter 1300/3560] 2.35583758354187, cross_entropy: 2.35583758354187 +[2025-04-29 04:42:17,899][BaseTrainer][INFO] - [Epoch 4/10, Iter 1301/3560] 2.3850455284118652, cross_entropy: 2.3850455284118652 +[2025-04-29 04:42:20,568][BaseTrainer][INFO] - [Epoch 4/10, Iter 1302/3560] 2.3204305171966553, cross_entropy: 2.3204305171966553 +[2025-04-29 04:42:21,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1303/3560] 3.6660029888153076, cross_entropy: 3.6660029888153076 +[2025-04-29 04:42:24,098][BaseTrainer][INFO] - [Epoch 4/10, Iter 1304/3560] 1.8137671947479248, cross_entropy: 1.8137671947479248 +[2025-04-29 04:42:24,960][BaseTrainer][INFO] - [Epoch 4/10, Iter 1305/3560] 2.6563491821289062, cross_entropy: 2.6563491821289062 +[2025-04-29 04:42:27,684][BaseTrainer][INFO] - [Epoch 4/10, Iter 1306/3560] 2.6457326412200928, cross_entropy: 2.6457326412200928 +[2025-04-29 04:42:28,566][BaseTrainer][INFO] - [Epoch 4/10, Iter 1307/3560] 3.0083670616149902, cross_entropy: 3.0083670616149902 +[2025-04-29 04:42:31,653][BaseTrainer][INFO] - [Epoch 4/10, Iter 1308/3560] 1.9555267095565796, cross_entropy: 1.9555267095565796 +[2025-04-29 04:42:32,538][BaseTrainer][INFO] - [Epoch 4/10, Iter 1309/3560] 3.278683662414551, cross_entropy: 3.278683662414551 +[2025-04-29 04:42:35,218][BaseTrainer][INFO] - [Epoch 4/10, Iter 1310/3560] 2.0874781608581543, cross_entropy: 2.0874781608581543 +[2025-04-29 04:42:36,078][BaseTrainer][INFO] - [Epoch 4/10, Iter 1311/3560] 2.4536054134368896, cross_entropy: 2.4536054134368896 +[2025-04-29 04:42:39,459][BaseTrainer][INFO] - [Epoch 4/10, Iter 1312/3560] 3.129185199737549, cross_entropy: 3.129185199737549 +[2025-04-29 04:42:40,343][BaseTrainer][INFO] - [Epoch 4/10, Iter 1313/3560] 2.101405143737793, cross_entropy: 2.101405143737793 +[2025-04-29 04:42:43,027][BaseTrainer][INFO] - [Epoch 4/10, Iter 1314/3560] 3.9241750240325928, cross_entropy: 3.9241750240325928 +[2025-04-29 04:42:43,886][BaseTrainer][INFO] - [Epoch 4/10, Iter 1315/3560] 2.700345993041992, cross_entropy: 2.700345993041992 +[2025-04-29 04:42:47,529][BaseTrainer][INFO] - [Epoch 4/10, Iter 1316/3560] 2.3475341796875, cross_entropy: 2.3475341796875 +[2025-04-29 04:42:48,412][BaseTrainer][INFO] - [Epoch 4/10, Iter 1317/3560] 3.153465747833252, cross_entropy: 3.153465747833252 +[2025-04-29 04:42:51,276][BaseTrainer][INFO] - [Epoch 4/10, Iter 1318/3560] 1.7641735076904297, cross_entropy: 1.7641735076904297 +[2025-04-29 04:42:52,163][BaseTrainer][INFO] - [Epoch 4/10, Iter 1319/3560] 2.678267002105713, cross_entropy: 2.678267002105713 +[2025-04-29 04:42:54,672][BaseTrainer][INFO] - [Epoch 4/10, Iter 1320/3560] 3.2920875549316406, cross_entropy: 3.2920875549316406 +[2025-04-29 04:42:55,537][BaseTrainer][INFO] - [Epoch 4/10, Iter 1321/3560] 2.9755377769470215, cross_entropy: 2.9755377769470215 +[2025-04-29 04:42:58,410][BaseTrainer][INFO] - [Epoch 4/10, Iter 1322/3560] 1.9472019672393799, cross_entropy: 1.9472019672393799 +[2025-04-29 04:42:59,290][BaseTrainer][INFO] - [Epoch 4/10, Iter 1323/3560] 1.6639564037322998, cross_entropy: 1.6639564037322998 +[2025-04-29 04:43:01,604][BaseTrainer][INFO] - [Epoch 4/10, Iter 1324/3560] 2.671895980834961, cross_entropy: 2.671895980834961 +[2025-04-29 04:43:02,485][BaseTrainer][INFO] - [Epoch 4/10, Iter 1325/3560] 2.2457642555236816, cross_entropy: 2.2457642555236816 +[2025-04-29 04:43:04,962][BaseTrainer][INFO] - [Epoch 4/10, Iter 1326/3560] 2.1278791427612305, cross_entropy: 2.1278791427612305 +[2025-04-29 04:43:05,852][BaseTrainer][INFO] - [Epoch 4/10, Iter 1327/3560] 1.6481497287750244, cross_entropy: 1.6481497287750244 +[2025-04-29 04:43:08,895][BaseTrainer][INFO] - [Epoch 4/10, Iter 1328/3560] 2.004716396331787, cross_entropy: 2.004716396331787 +[2025-04-29 04:43:09,780][BaseTrainer][INFO] - [Epoch 4/10, Iter 1329/3560] 3.672840118408203, cross_entropy: 3.672840118408203 +[2025-04-29 04:43:12,578][BaseTrainer][INFO] - [Epoch 4/10, Iter 1330/3560] 3.043053150177002, cross_entropy: 3.043053150177002 +[2025-04-29 04:43:13,469][BaseTrainer][INFO] - [Epoch 4/10, Iter 1331/3560] 3.4355602264404297, cross_entropy: 3.4355602264404297 +[2025-04-29 04:43:15,964][BaseTrainer][INFO] - [Epoch 4/10, Iter 1332/3560] 3.271110773086548, cross_entropy: 3.271110773086548 +[2025-04-29 04:43:16,854][BaseTrainer][INFO] - [Epoch 4/10, Iter 1333/3560] 3.0807056427001953, cross_entropy: 3.0807056427001953 +[2025-04-29 04:43:19,943][BaseTrainer][INFO] - [Epoch 4/10, Iter 1334/3560] 1.898531198501587, cross_entropy: 1.898531198501587 +[2025-04-29 04:43:20,806][BaseTrainer][INFO] - [Epoch 4/10, Iter 1335/3560] 3.131885051727295, cross_entropy: 3.131885051727295 +[2025-04-29 04:43:23,961][BaseTrainer][INFO] - [Epoch 4/10, Iter 1336/3560] 2.0277345180511475, cross_entropy: 2.0277345180511475 +[2025-04-29 04:43:24,823][BaseTrainer][INFO] - [Epoch 4/10, Iter 1337/3560] 1.7695438861846924, cross_entropy: 1.7695438861846924 +[2025-04-29 04:43:27,548][BaseTrainer][INFO] - [Epoch 4/10, Iter 1338/3560] 1.6191933155059814, cross_entropy: 1.6191933155059814 +[2025-04-29 04:43:28,437][BaseTrainer][INFO] - [Epoch 4/10, Iter 1339/3560] 1.933028221130371, cross_entropy: 1.933028221130371 +[2025-04-29 04:43:31,714][BaseTrainer][INFO] - [Epoch 4/10, Iter 1340/3560] 1.475762128829956, cross_entropy: 1.475762128829956 +[2025-04-29 04:43:32,603][BaseTrainer][INFO] - [Epoch 4/10, Iter 1341/3560] 3.1668648719787598, cross_entropy: 3.1668648719787598 +[2025-04-29 04:43:35,743][BaseTrainer][INFO] - [Epoch 4/10, Iter 1342/3560] 2.437157154083252, cross_entropy: 2.437157154083252 +[2025-04-29 04:43:36,614][BaseTrainer][INFO] - [Epoch 4/10, Iter 1343/3560] 1.9748284816741943, cross_entropy: 1.9748284816741943 +[2025-04-29 04:43:39,822][BaseTrainer][INFO] - [Epoch 4/10, Iter 1344/3560] 2.1540367603302, cross_entropy: 2.1540367603302 +[2025-04-29 04:43:40,701][BaseTrainer][INFO] - [Epoch 4/10, Iter 1345/3560] 2.90914249420166, cross_entropy: 2.90914249420166 +[2025-04-29 04:43:43,063][BaseTrainer][INFO] - [Epoch 4/10, Iter 1346/3560] 2.0471692085266113, cross_entropy: 2.0471692085266113 +[2025-04-29 04:43:43,952][BaseTrainer][INFO] - [Epoch 4/10, Iter 1347/3560] 3.3449132442474365, cross_entropy: 3.3449132442474365 +[2025-04-29 04:43:46,592][BaseTrainer][INFO] - [Epoch 4/10, Iter 1348/3560] 3.381743907928467, cross_entropy: 3.381743907928467 +[2025-04-29 04:43:47,479][BaseTrainer][INFO] - [Epoch 4/10, Iter 1349/3560] 3.367133855819702, cross_entropy: 3.367133855819702 +[2025-04-29 04:43:50,518][BaseTrainer][INFO] - [Epoch 4/10, Iter 1350/3560] 1.7804286479949951, cross_entropy: 1.7804286479949951 +[2025-04-29 04:43:51,408][BaseTrainer][INFO] - [Epoch 4/10, Iter 1351/3560] 3.4865338802337646, cross_entropy: 3.4865338802337646 +[2025-04-29 04:43:54,747][BaseTrainer][INFO] - [Epoch 4/10, Iter 1352/3560] 2.2782154083251953, cross_entropy: 2.2782154083251953 +[2025-04-29 04:43:55,627][BaseTrainer][INFO] - [Epoch 4/10, Iter 1353/3560] 3.0345675945281982, cross_entropy: 3.0345675945281982 +[2025-04-29 04:43:57,954][BaseTrainer][INFO] - [Epoch 4/10, Iter 1354/3560] 2.0737698078155518, cross_entropy: 2.0737698078155518 +[2025-04-29 04:43:58,812][BaseTrainer][INFO] - [Epoch 4/10, Iter 1355/3560] 3.1191372871398926, cross_entropy: 3.1191372871398926 +[2025-04-29 04:44:02,044][BaseTrainer][INFO] - [Epoch 4/10, Iter 1356/3560] 3.1785247325897217, cross_entropy: 3.1785247325897217 +[2025-04-29 04:44:02,927][BaseTrainer][INFO] - [Epoch 4/10, Iter 1357/3560] 3.3434271812438965, cross_entropy: 3.3434271812438965 +[2025-04-29 04:44:05,115][BaseTrainer][INFO] - [Epoch 4/10, Iter 1358/3560] 2.324296474456787, cross_entropy: 2.324296474456787 +[2025-04-29 04:44:06,000][BaseTrainer][INFO] - [Epoch 4/10, Iter 1359/3560] 3.0426599979400635, cross_entropy: 3.0426599979400635 +[2025-04-29 04:44:09,047][BaseTrainer][INFO] - [Epoch 4/10, Iter 1360/3560] 3.2140917778015137, cross_entropy: 3.2140917778015137 +[2025-04-29 04:44:09,937][BaseTrainer][INFO] - [Epoch 4/10, Iter 1361/3560] 1.883052945137024, cross_entropy: 1.883052945137024 +[2025-04-29 04:44:14,416][BaseTrainer][INFO] - [Epoch 4/10, Iter 1362/3560] 3.0765812397003174, cross_entropy: 3.0765812397003174 +[2025-04-29 04:44:15,272][BaseTrainer][INFO] - [Epoch 4/10, Iter 1363/3560] 2.3185367584228516, cross_entropy: 2.3185367584228516 +[2025-04-29 04:44:17,981][BaseTrainer][INFO] - [Epoch 4/10, Iter 1364/3560] 3.822012424468994, cross_entropy: 3.822012424468994 +[2025-04-29 04:44:18,861][BaseTrainer][INFO] - [Epoch 4/10, Iter 1365/3560] 2.334407329559326, cross_entropy: 2.334407329559326 +[2025-04-29 04:44:21,504][BaseTrainer][INFO] - [Epoch 4/10, Iter 1366/3560] 2.2849326133728027, cross_entropy: 2.2849326133728027 +[2025-04-29 04:44:22,390][BaseTrainer][INFO] - [Epoch 4/10, Iter 1367/3560] 2.699195384979248, cross_entropy: 2.699195384979248 +[2025-04-29 04:44:25,800][BaseTrainer][INFO] - [Epoch 4/10, Iter 1368/3560] 2.267669677734375, cross_entropy: 2.267669677734375 +[2025-04-29 04:44:26,683][BaseTrainer][INFO] - [Epoch 4/10, Iter 1369/3560] 1.7782683372497559, cross_entropy: 1.7782683372497559 +[2025-04-29 04:44:29,719][BaseTrainer][INFO] - [Epoch 4/10, Iter 1370/3560] 2.2897374629974365, cross_entropy: 2.2897374629974365 +[2025-04-29 04:44:30,601][BaseTrainer][INFO] - [Epoch 4/10, Iter 1371/3560] 1.897555947303772, cross_entropy: 1.897555947303772 +[2025-04-29 04:44:33,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1372/3560] 1.9637939929962158, cross_entropy: 1.9637939929962158 +[2025-04-29 04:44:34,492][BaseTrainer][INFO] - [Epoch 4/10, Iter 1373/3560] 2.0493640899658203, cross_entropy: 2.0493640899658203 +[2025-04-29 04:44:37,575][BaseTrainer][INFO] - [Epoch 4/10, Iter 1374/3560] 2.451388359069824, cross_entropy: 2.451388359069824 +[2025-04-29 04:44:38,435][BaseTrainer][INFO] - [Epoch 4/10, Iter 1375/3560] 1.926735758781433, cross_entropy: 1.926735758781433 +[2025-04-29 04:44:41,033][BaseTrainer][INFO] - [Epoch 4/10, Iter 1376/3560] 3.5434603691101074, cross_entropy: 3.5434603691101074 +[2025-04-29 04:44:41,924][BaseTrainer][INFO] - [Epoch 4/10, Iter 1377/3560] 3.173372507095337, cross_entropy: 3.173372507095337 +[2025-04-29 04:44:45,737][BaseTrainer][INFO] - [Epoch 4/10, Iter 1378/3560] 2.543900489807129, cross_entropy: 2.543900489807129 +[2025-04-29 04:44:46,597][BaseTrainer][INFO] - [Epoch 4/10, Iter 1379/3560] 3.5685389041900635, cross_entropy: 3.5685389041900635 +[2025-04-29 04:44:49,725][BaseTrainer][INFO] - [Epoch 4/10, Iter 1380/3560] 3.4458541870117188, cross_entropy: 3.4458541870117188 +[2025-04-29 04:44:50,608][BaseTrainer][INFO] - [Epoch 4/10, Iter 1381/3560] 2.485295057296753, cross_entropy: 2.485295057296753 +[2025-04-29 04:44:53,205][BaseTrainer][INFO] - [Epoch 4/10, Iter 1382/3560] 2.553398370742798, cross_entropy: 2.553398370742798 +[2025-04-29 04:44:54,068][BaseTrainer][INFO] - [Epoch 4/10, Iter 1383/3560] 2.040034294128418, cross_entropy: 2.040034294128418 +[2025-04-29 04:44:57,090][BaseTrainer][INFO] - [Epoch 4/10, Iter 1384/3560] 2.291114568710327, cross_entropy: 2.291114568710327 +[2025-04-29 04:44:57,975][BaseTrainer][INFO] - [Epoch 4/10, Iter 1385/3560] 2.1678881645202637, cross_entropy: 2.1678881645202637 +[2025-04-29 04:45:00,481][BaseTrainer][INFO] - [Epoch 4/10, Iter 1386/3560] 1.752272129058838, cross_entropy: 1.752272129058838 +[2025-04-29 04:45:01,367][BaseTrainer][INFO] - [Epoch 4/10, Iter 1387/3560] 2.4789133071899414, cross_entropy: 2.4789133071899414 +[2025-04-29 04:45:03,785][BaseTrainer][INFO] - [Epoch 4/10, Iter 1388/3560] 1.9817562103271484, cross_entropy: 1.9817562103271484 +[2025-04-29 04:45:04,642][BaseTrainer][INFO] - [Epoch 4/10, Iter 1389/3560] 1.7294237613677979, cross_entropy: 1.7294237613677979 +[2025-04-29 04:45:07,106][BaseTrainer][INFO] - [Epoch 4/10, Iter 1390/3560] 1.861772894859314, cross_entropy: 1.861772894859314 +[2025-04-29 04:45:07,991][BaseTrainer][INFO] - [Epoch 4/10, Iter 1391/3560] 1.9155640602111816, cross_entropy: 1.9155640602111816 +[2025-04-29 04:45:10,680][BaseTrainer][INFO] - [Epoch 4/10, Iter 1392/3560] 3.257050037384033, cross_entropy: 3.257050037384033 +[2025-04-29 04:45:11,539][BaseTrainer][INFO] - [Epoch 4/10, Iter 1393/3560] 1.9319308996200562, cross_entropy: 1.9319308996200562 +[2025-04-29 04:45:14,628][BaseTrainer][INFO] - [Epoch 4/10, Iter 1394/3560] 3.179637908935547, cross_entropy: 3.179637908935547 +[2025-04-29 04:45:15,505][BaseTrainer][INFO] - [Epoch 4/10, Iter 1395/3560] 3.217625856399536, cross_entropy: 3.217625856399536 +[2025-04-29 04:45:18,530][BaseTrainer][INFO] - [Epoch 4/10, Iter 1396/3560] 3.1464552879333496, cross_entropy: 3.1464552879333496 +[2025-04-29 04:45:19,386][BaseTrainer][INFO] - [Epoch 4/10, Iter 1397/3560] 1.9413503408432007, cross_entropy: 1.9413503408432007 +[2025-04-29 04:45:21,823][BaseTrainer][INFO] - [Epoch 4/10, Iter 1398/3560] 1.5165858268737793, cross_entropy: 1.5165858268737793 +[2025-04-29 04:45:22,712][BaseTrainer][INFO] - [Epoch 4/10, Iter 1399/3560] 1.6282947063446045, cross_entropy: 1.6282947063446045 +[2025-04-29 04:45:25,610][BaseTrainer][INFO] - [Epoch 4/10, Iter 1400/3560] 1.601266622543335, cross_entropy: 1.601266622543335 +[2025-04-29 04:45:26,494][BaseTrainer][INFO] - [Epoch 4/10, Iter 1401/3560] 3.594651222229004, cross_entropy: 3.594651222229004 +[2025-04-29 04:45:29,541][BaseTrainer][INFO] - [Epoch 4/10, Iter 1402/3560] 1.8340587615966797, cross_entropy: 1.8340587615966797 +[2025-04-29 04:45:30,430][BaseTrainer][INFO] - [Epoch 4/10, Iter 1403/3560] 2.001309871673584, cross_entropy: 2.001309871673584 +[2025-04-29 04:45:32,490][BaseTrainer][INFO] - [Epoch 4/10, Iter 1404/3560] 1.7066130638122559, cross_entropy: 1.7066130638122559 +[2025-04-29 04:45:33,381][BaseTrainer][INFO] - [Epoch 4/10, Iter 1405/3560] 1.8251069784164429, cross_entropy: 1.8251069784164429 +[2025-04-29 04:45:35,383][BaseTrainer][INFO] - [Epoch 4/10, Iter 1406/3560] 2.172691822052002, cross_entropy: 2.172691822052002 +[2025-04-29 04:45:36,269][BaseTrainer][INFO] - [Epoch 4/10, Iter 1407/3560] 2.0040154457092285, cross_entropy: 2.0040154457092285 +[2025-04-29 04:45:38,877][BaseTrainer][INFO] - [Epoch 4/10, Iter 1408/3560] 1.745381236076355, cross_entropy: 1.745381236076355 +[2025-04-29 04:45:39,736][BaseTrainer][INFO] - [Epoch 4/10, Iter 1409/3560] 2.929030656814575, cross_entropy: 2.929030656814575 +[2025-04-29 04:45:42,647][BaseTrainer][INFO] - [Epoch 4/10, Iter 1410/3560] 3.0225419998168945, cross_entropy: 3.0225419998168945 +[2025-04-29 04:45:43,508][BaseTrainer][INFO] - [Epoch 4/10, Iter 1411/3560] 3.229581356048584, cross_entropy: 3.229581356048584 +[2025-04-29 04:45:46,554][BaseTrainer][INFO] - [Epoch 4/10, Iter 1412/3560] 1.6535282135009766, cross_entropy: 1.6535282135009766 +[2025-04-29 04:45:47,441][BaseTrainer][INFO] - [Epoch 4/10, Iter 1413/3560] 1.7315990924835205, cross_entropy: 1.7315990924835205 +[2025-04-29 04:45:50,380][BaseTrainer][INFO] - [Epoch 4/10, Iter 1414/3560] 3.470489501953125, cross_entropy: 3.470489501953125 +[2025-04-29 04:45:51,265][BaseTrainer][INFO] - [Epoch 4/10, Iter 1415/3560] 2.3444509506225586, cross_entropy: 2.3444509506225586 +[2025-04-29 04:45:53,594][BaseTrainer][INFO] - [Epoch 4/10, Iter 1416/3560] 2.777351140975952, cross_entropy: 2.777351140975952 +[2025-04-29 04:45:54,455][BaseTrainer][INFO] - [Epoch 4/10, Iter 1417/3560] 2.9020485877990723, cross_entropy: 2.9020485877990723 +[2025-04-29 04:45:57,356][BaseTrainer][INFO] - [Epoch 4/10, Iter 1418/3560] 1.9681994915008545, cross_entropy: 1.9681994915008545 +[2025-04-29 04:45:58,212][BaseTrainer][INFO] - [Epoch 4/10, Iter 1419/3560] 2.550210475921631, cross_entropy: 2.550210475921631 +[2025-04-29 04:46:01,287][BaseTrainer][INFO] - [Epoch 4/10, Iter 1420/3560] 2.396002769470215, cross_entropy: 2.396002769470215 +[2025-04-29 04:46:02,149][BaseTrainer][INFO] - [Epoch 4/10, Iter 1421/3560] 2.919732093811035, cross_entropy: 2.919732093811035 +[2025-04-29 04:46:05,079][BaseTrainer][INFO] - [Epoch 4/10, Iter 1422/3560] 1.8939523696899414, cross_entropy: 1.8939523696899414 +[2025-04-29 04:46:05,938][BaseTrainer][INFO] - [Epoch 4/10, Iter 1423/3560] 3.542245864868164, cross_entropy: 3.542245864868164 +[2025-04-29 04:46:07,350][BaseTrainer][INFO] - [Epoch 4/10, Iter 1424/3560] 3.159205913543701, cross_entropy: 3.159205913543701 +[2025-04-29 04:48:57,218][BaseTrainer][INFO] - [Epoch 4/10] (train) 2.6204771995544434, cross_entropy: 2.6204771995544434 +[2025-04-29 04:48:57,218][BaseTrainer][INFO] - [Epoch 4/10] (validation) 1.673889398574829, cross_entropy: 1.673889398574829 +[2025-04-29 04:48:58,064][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 04:48:58,773][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch4.pth. +[2025-04-29 04:48:59,581][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 04:49:04,603][BaseTrainer][INFO] - [Epoch 5/10, Iter 1425/3560] 2.467355489730835, cross_entropy: 2.467355489730835 +[2025-04-29 04:49:05,522][BaseTrainer][INFO] - [Epoch 5/10, Iter 1426/3560] 3.1311731338500977, cross_entropy: 3.1311731338500977 +[2025-04-29 04:49:08,480][BaseTrainer][INFO] - [Epoch 5/10, Iter 1427/3560] 1.559366226196289, cross_entropy: 1.559366226196289 +[2025-04-29 04:49:09,485][BaseTrainer][INFO] - [Epoch 5/10, Iter 1428/3560] 2.3398208618164062, cross_entropy: 2.3398208618164062 +[2025-04-29 04:49:12,466][BaseTrainer][INFO] - [Epoch 5/10, Iter 1429/3560] 1.792649745941162, cross_entropy: 1.792649745941162 +[2025-04-29 04:49:13,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1430/3560] 3.2360610961914062, cross_entropy: 3.2360610961914062 +[2025-04-29 04:49:16,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1431/3560] 2.306800603866577, cross_entropy: 2.306800603866577 +[2025-04-29 04:49:17,162][BaseTrainer][INFO] - [Epoch 5/10, Iter 1432/3560] 2.005507469177246, cross_entropy: 2.005507469177246 +[2025-04-29 04:49:19,600][BaseTrainer][INFO] - [Epoch 5/10, Iter 1433/3560] 1.6901882886886597, cross_entropy: 1.6901882886886597 +[2025-04-29 04:49:20,457][BaseTrainer][INFO] - [Epoch 5/10, Iter 1434/3560] 1.930985689163208, cross_entropy: 1.930985689163208 +[2025-04-29 04:49:23,442][BaseTrainer][INFO] - [Epoch 5/10, Iter 1435/3560] 3.3810863494873047, cross_entropy: 3.3810863494873047 +[2025-04-29 04:49:24,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1436/3560] 1.7721456289291382, cross_entropy: 1.7721456289291382 +[2025-04-29 04:49:26,699][BaseTrainer][INFO] - [Epoch 5/10, Iter 1437/3560] 1.5042204856872559, cross_entropy: 1.5042204856872559 +[2025-04-29 04:49:27,614][BaseTrainer][INFO] - [Epoch 5/10, Iter 1438/3560] 2.3103322982788086, cross_entropy: 2.3103322982788086 +[2025-04-29 04:49:30,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1439/3560] 3.213993549346924, cross_entropy: 3.213993549346924 +[2025-04-29 04:49:31,849][BaseTrainer][INFO] - [Epoch 5/10, Iter 1440/3560] 2.766007423400879, cross_entropy: 2.766007423400879 +[2025-04-29 04:49:35,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1441/3560] 3.0571255683898926, cross_entropy: 3.0571255683898926 +[2025-04-29 04:49:36,333][BaseTrainer][INFO] - [Epoch 5/10, Iter 1442/3560] 1.6711359024047852, cross_entropy: 1.6711359024047852 +[2025-04-29 04:49:39,520][BaseTrainer][INFO] - [Epoch 5/10, Iter 1443/3560] 2.8323426246643066, cross_entropy: 2.8323426246643066 +[2025-04-29 04:49:40,403][BaseTrainer][INFO] - [Epoch 5/10, Iter 1444/3560] 2.729098320007324, cross_entropy: 2.729098320007324 +[2025-04-29 04:49:43,379][BaseTrainer][INFO] - [Epoch 5/10, Iter 1445/3560] 3.2544357776641846, cross_entropy: 3.2544357776641846 +[2025-04-29 04:49:44,267][BaseTrainer][INFO] - [Epoch 5/10, Iter 1446/3560] 3.1252260208129883, cross_entropy: 3.1252260208129883 +[2025-04-29 04:49:47,330][BaseTrainer][INFO] - [Epoch 5/10, Iter 1447/3560] 1.7967835664749146, cross_entropy: 1.7967835664749146 +[2025-04-29 04:49:48,212][BaseTrainer][INFO] - [Epoch 5/10, Iter 1448/3560] 1.8222695589065552, cross_entropy: 1.8222695589065552 +[2025-04-29 04:49:50,589][BaseTrainer][INFO] - [Epoch 5/10, Iter 1449/3560] 2.423926830291748, cross_entropy: 2.423926830291748 +[2025-04-29 04:49:51,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1450/3560] 2.026346206665039, cross_entropy: 2.026346206665039 +[2025-04-29 04:49:56,016][BaseTrainer][INFO] - [Epoch 5/10, Iter 1451/3560] 2.674535036087036, cross_entropy: 2.674535036087036 +[2025-04-29 04:49:56,900][BaseTrainer][INFO] - [Epoch 5/10, Iter 1452/3560] 1.905745267868042, cross_entropy: 1.905745267868042 +[2025-04-29 04:49:59,229][BaseTrainer][INFO] - [Epoch 5/10, Iter 1453/3560] 2.4942965507507324, cross_entropy: 2.4942965507507324 +[2025-04-29 04:50:00,108][BaseTrainer][INFO] - [Epoch 5/10, Iter 1454/3560] 1.9225982427597046, cross_entropy: 1.9225982427597046 +[2025-04-29 04:50:03,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1455/3560] 2.4968395233154297, cross_entropy: 2.4968395233154297 +[2025-04-29 04:50:03,990][BaseTrainer][INFO] - [Epoch 5/10, Iter 1456/3560] 2.2579855918884277, cross_entropy: 2.2579855918884277 +[2025-04-29 04:50:06,644][BaseTrainer][INFO] - [Epoch 5/10, Iter 1457/3560] 2.442441701889038, cross_entropy: 2.442441701889038 +[2025-04-29 04:50:07,501][BaseTrainer][INFO] - [Epoch 5/10, Iter 1458/3560] 3.566666603088379, cross_entropy: 3.566666603088379 +[2025-04-29 04:50:12,042][BaseTrainer][INFO] - [Epoch 5/10, Iter 1459/3560] 3.3879776000976562, cross_entropy: 3.3879776000976562 +[2025-04-29 04:50:12,924][BaseTrainer][INFO] - [Epoch 5/10, Iter 1460/3560] 3.2082347869873047, cross_entropy: 3.2082347869873047 +[2025-04-29 04:50:15,176][BaseTrainer][INFO] - [Epoch 5/10, Iter 1461/3560] 2.693484306335449, cross_entropy: 2.693484306335449 +[2025-04-29 04:50:16,033][BaseTrainer][INFO] - [Epoch 5/10, Iter 1462/3560] 2.5358855724334717, cross_entropy: 2.5358855724334717 +[2025-04-29 04:50:19,358][BaseTrainer][INFO] - [Epoch 5/10, Iter 1463/3560] 1.816170334815979, cross_entropy: 1.816170334815979 +[2025-04-29 04:50:20,240][BaseTrainer][INFO] - [Epoch 5/10, Iter 1464/3560] 1.8896044492721558, cross_entropy: 1.8896044492721558 +[2025-04-29 04:50:23,120][BaseTrainer][INFO] - [Epoch 5/10, Iter 1465/3560] 3.8226494789123535, cross_entropy: 3.8226494789123535 +[2025-04-29 04:50:23,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1466/3560] 2.3712730407714844, cross_entropy: 2.3712730407714844 +[2025-04-29 04:50:27,112][BaseTrainer][INFO] - [Epoch 5/10, Iter 1467/3560] 2.271820545196533, cross_entropy: 2.271820545196533 +[2025-04-29 04:50:27,994][BaseTrainer][INFO] - [Epoch 5/10, Iter 1468/3560] 2.985261917114258, cross_entropy: 2.985261917114258 +[2025-04-29 04:50:30,783][BaseTrainer][INFO] - [Epoch 5/10, Iter 1469/3560] 3.5766351222991943, cross_entropy: 3.5766351222991943 +[2025-04-29 04:50:31,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1470/3560] 1.7644014358520508, cross_entropy: 1.7644014358520508 +[2025-04-29 04:50:34,684][BaseTrainer][INFO] - [Epoch 5/10, Iter 1471/3560] 3.6632442474365234, cross_entropy: 3.6632442474365234 +[2025-04-29 04:50:35,544][BaseTrainer][INFO] - [Epoch 5/10, Iter 1472/3560] 2.885335922241211, cross_entropy: 2.885335922241211 +[2025-04-29 04:50:38,755][BaseTrainer][INFO] - [Epoch 5/10, Iter 1473/3560] 2.610029697418213, cross_entropy: 2.610029697418213 +[2025-04-29 04:50:39,640][BaseTrainer][INFO] - [Epoch 5/10, Iter 1474/3560] 2.9292759895324707, cross_entropy: 2.9292759895324707 +[2025-04-29 04:50:42,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1475/3560] 2.3162856101989746, cross_entropy: 2.3162856101989746 +[2025-04-29 04:50:43,077][BaseTrainer][INFO] - [Epoch 5/10, Iter 1476/3560] 1.7084977626800537, cross_entropy: 1.7084977626800537 +[2025-04-29 04:50:46,146][BaseTrainer][INFO] - [Epoch 5/10, Iter 1477/3560] 1.685160756111145, cross_entropy: 1.685160756111145 +[2025-04-29 04:50:47,029][BaseTrainer][INFO] - [Epoch 5/10, Iter 1478/3560] 1.9665666818618774, cross_entropy: 1.9665666818618774 +[2025-04-29 04:50:49,852][BaseTrainer][INFO] - [Epoch 5/10, Iter 1479/3560] 2.3036556243896484, cross_entropy: 2.3036556243896484 +[2025-04-29 04:50:50,739][BaseTrainer][INFO] - [Epoch 5/10, Iter 1480/3560] 1.5335705280303955, cross_entropy: 1.5335705280303955 +[2025-04-29 04:50:53,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1481/3560] 2.656898021697998, cross_entropy: 2.656898021697998 +[2025-04-29 04:50:54,621][BaseTrainer][INFO] - [Epoch 5/10, Iter 1482/3560] 3.0026230812072754, cross_entropy: 3.0026230812072754 +[2025-04-29 04:50:57,451][BaseTrainer][INFO] - [Epoch 5/10, Iter 1483/3560] 2.3134329319000244, cross_entropy: 2.3134329319000244 +[2025-04-29 04:50:58,308][BaseTrainer][INFO] - [Epoch 5/10, Iter 1484/3560] 2.08785080909729, cross_entropy: 2.08785080909729 +[2025-04-29 04:51:00,945][BaseTrainer][INFO] - [Epoch 5/10, Iter 1485/3560] 3.1686646938323975, cross_entropy: 3.1686646938323975 +[2025-04-29 04:51:01,830][BaseTrainer][INFO] - [Epoch 5/10, Iter 1486/3560] 2.2169549465179443, cross_entropy: 2.2169549465179443 +[2025-04-29 04:51:03,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1487/3560] 3.730168104171753, cross_entropy: 3.730168104171753 +[2025-04-29 04:51:04,540][BaseTrainer][INFO] - [Epoch 5/10, Iter 1488/3560] 1.797980546951294, cross_entropy: 1.797980546951294 +[2025-04-29 04:51:07,661][BaseTrainer][INFO] - [Epoch 5/10, Iter 1489/3560] 2.4411723613739014, cross_entropy: 2.4411723613739014 +[2025-04-29 04:51:08,558][BaseTrainer][INFO] - [Epoch 5/10, Iter 1490/3560] 3.352602005004883, cross_entropy: 3.352602005004883 +[2025-04-29 04:51:13,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1491/3560] 2.02018666267395, cross_entropy: 2.02018666267395 +[2025-04-29 04:51:14,118][BaseTrainer][INFO] - [Epoch 5/10, Iter 1492/3560] 1.9249310493469238, cross_entropy: 1.9249310493469238 +[2025-04-29 04:51:16,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1493/3560] 2.886136293411255, cross_entropy: 2.886136293411255 +[2025-04-29 04:51:17,821][BaseTrainer][INFO] - [Epoch 5/10, Iter 1494/3560] 2.78680419921875, cross_entropy: 2.78680419921875 +[2025-04-29 04:51:20,348][BaseTrainer][INFO] - [Epoch 5/10, Iter 1495/3560] 3.5297484397888184, cross_entropy: 3.5297484397888184 +[2025-04-29 04:51:21,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1496/3560] 1.5297952890396118, cross_entropy: 1.5297952890396118 +[2025-04-29 04:51:23,805][BaseTrainer][INFO] - [Epoch 5/10, Iter 1497/3560] 3.392183780670166, cross_entropy: 3.392183780670166 +[2025-04-29 04:51:24,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1498/3560] 2.2595324516296387, cross_entropy: 2.2595324516296387 +[2025-04-29 04:51:27,247][BaseTrainer][INFO] - [Epoch 5/10, Iter 1499/3560] 3.171191692352295, cross_entropy: 3.171191692352295 +[2025-04-29 04:51:28,107][BaseTrainer][INFO] - [Epoch 5/10, Iter 1500/3560] 1.5196894407272339, cross_entropy: 1.5196894407272339 +[2025-04-29 04:51:30,720][BaseTrainer][INFO] - [Epoch 5/10, Iter 1501/3560] 1.560689926147461, cross_entropy: 1.560689926147461 +[2025-04-29 04:51:31,609][BaseTrainer][INFO] - [Epoch 5/10, Iter 1502/3560] 1.3792247772216797, cross_entropy: 1.3792247772216797 +[2025-04-29 04:51:34,059][BaseTrainer][INFO] - [Epoch 5/10, Iter 1503/3560] 2.516448497772217, cross_entropy: 2.516448497772217 +[2025-04-29 04:51:34,947][BaseTrainer][INFO] - [Epoch 5/10, Iter 1504/3560] 1.9423590898513794, cross_entropy: 1.9423590898513794 +[2025-04-29 04:51:37,666][BaseTrainer][INFO] - [Epoch 5/10, Iter 1505/3560] 2.6667380332946777, cross_entropy: 2.6667380332946777 +[2025-04-29 04:51:38,524][BaseTrainer][INFO] - [Epoch 5/10, Iter 1506/3560] 2.2514569759368896, cross_entropy: 2.2514569759368896 +[2025-04-29 04:51:41,367][BaseTrainer][INFO] - [Epoch 5/10, Iter 1507/3560] 1.2046451568603516, cross_entropy: 1.2046451568603516 +[2025-04-29 04:51:42,252][BaseTrainer][INFO] - [Epoch 5/10, Iter 1508/3560] 2.171881675720215, cross_entropy: 2.171881675720215 +[2025-04-29 04:51:45,414][BaseTrainer][INFO] - [Epoch 5/10, Iter 1509/3560] 3.5932536125183105, cross_entropy: 3.5932536125183105 +[2025-04-29 04:51:46,273][BaseTrainer][INFO] - [Epoch 5/10, Iter 1510/3560] 2.0448966026306152, cross_entropy: 2.0448966026306152 +[2025-04-29 04:51:49,443][BaseTrainer][INFO] - [Epoch 5/10, Iter 1511/3560] 3.593264102935791, cross_entropy: 3.593264102935791 +[2025-04-29 04:51:50,329][BaseTrainer][INFO] - [Epoch 5/10, Iter 1512/3560] 3.3162553310394287, cross_entropy: 3.3162553310394287 +[2025-04-29 04:51:53,240][BaseTrainer][INFO] - [Epoch 5/10, Iter 1513/3560] 3.7131972312927246, cross_entropy: 3.7131972312927246 +[2025-04-29 04:51:54,119][BaseTrainer][INFO] - [Epoch 5/10, Iter 1514/3560] 2.3574721813201904, cross_entropy: 2.3574721813201904 +[2025-04-29 04:51:57,047][BaseTrainer][INFO] - [Epoch 5/10, Iter 1515/3560] 2.9732894897460938, cross_entropy: 2.9732894897460938 +[2025-04-29 04:51:57,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1516/3560] 2.5822558403015137, cross_entropy: 2.5822558403015137 +[2025-04-29 04:52:00,678][BaseTrainer][INFO] - [Epoch 5/10, Iter 1517/3560] 2.3537964820861816, cross_entropy: 2.3537964820861816 +[2025-04-29 04:52:01,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1518/3560] 3.5099411010742188, cross_entropy: 3.5099411010742188 +[2025-04-29 04:52:04,521][BaseTrainer][INFO] - [Epoch 5/10, Iter 1519/3560] 2.178022861480713, cross_entropy: 2.178022861480713 +[2025-04-29 04:52:05,387][BaseTrainer][INFO] - [Epoch 5/10, Iter 1520/3560] 2.9601552486419678, cross_entropy: 2.9601552486419678 +[2025-04-29 04:52:07,991][BaseTrainer][INFO] - [Epoch 5/10, Iter 1521/3560] 2.240220069885254, cross_entropy: 2.240220069885254 +[2025-04-29 04:52:08,885][BaseTrainer][INFO] - [Epoch 5/10, Iter 1522/3560] 2.7411866188049316, cross_entropy: 2.7411866188049316 +[2025-04-29 04:52:11,262][BaseTrainer][INFO] - [Epoch 5/10, Iter 1523/3560] 2.991358995437622, cross_entropy: 2.991358995437622 +[2025-04-29 04:52:12,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1524/3560] 1.676279902458191, cross_entropy: 1.676279902458191 +[2025-04-29 04:52:14,990][BaseTrainer][INFO] - [Epoch 5/10, Iter 1525/3560] 2.2503747940063477, cross_entropy: 2.2503747940063477 +[2025-04-29 04:52:15,875][BaseTrainer][INFO] - [Epoch 5/10, Iter 1526/3560] 2.8456733226776123, cross_entropy: 2.8456733226776123 +[2025-04-29 04:52:18,683][BaseTrainer][INFO] - [Epoch 5/10, Iter 1527/3560] 3.4011077880859375, cross_entropy: 3.4011077880859375 +[2025-04-29 04:52:19,566][BaseTrainer][INFO] - [Epoch 5/10, Iter 1528/3560] 1.7664780616760254, cross_entropy: 1.7664780616760254 +[2025-04-29 04:52:22,183][BaseTrainer][INFO] - [Epoch 5/10, Iter 1529/3560] 1.696013331413269, cross_entropy: 1.696013331413269 +[2025-04-29 04:52:23,072][BaseTrainer][INFO] - [Epoch 5/10, Iter 1530/3560] 1.9606815576553345, cross_entropy: 1.9606815576553345 +[2025-04-29 04:52:26,122][BaseTrainer][INFO] - [Epoch 5/10, Iter 1531/3560] 2.018115520477295, cross_entropy: 2.018115520477295 +[2025-04-29 04:52:27,013][BaseTrainer][INFO] - [Epoch 5/10, Iter 1532/3560] 1.6691780090332031, cross_entropy: 1.6691780090332031 +[2025-04-29 04:52:29,448][BaseTrainer][INFO] - [Epoch 5/10, Iter 1533/3560] 3.2298152446746826, cross_entropy: 3.2298152446746826 +[2025-04-29 04:52:30,305][BaseTrainer][INFO] - [Epoch 5/10, Iter 1534/3560] 2.696668863296509, cross_entropy: 2.696668863296509 +[2025-04-29 04:52:33,583][BaseTrainer][INFO] - [Epoch 5/10, Iter 1535/3560] 2.2482314109802246, cross_entropy: 2.2482314109802246 +[2025-04-29 04:52:34,456][BaseTrainer][INFO] - [Epoch 5/10, Iter 1536/3560] 2.4472620487213135, cross_entropy: 2.4472620487213135 +[2025-04-29 04:52:36,947][BaseTrainer][INFO] - [Epoch 5/10, Iter 1537/3560] 2.5955045223236084, cross_entropy: 2.5955045223236084 +[2025-04-29 04:52:37,827][BaseTrainer][INFO] - [Epoch 5/10, Iter 1538/3560] 3.336408853530884, cross_entropy: 3.336408853530884 +[2025-04-29 04:52:40,599][BaseTrainer][INFO] - [Epoch 5/10, Iter 1539/3560] 2.793081283569336, cross_entropy: 2.793081283569336 +[2025-04-29 04:52:41,485][BaseTrainer][INFO] - [Epoch 5/10, Iter 1540/3560] 3.0889225006103516, cross_entropy: 3.0889225006103516 +[2025-04-29 04:52:44,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1541/3560] 3.4956655502319336, cross_entropy: 3.4956655502319336 +[2025-04-29 04:52:45,194][BaseTrainer][INFO] - [Epoch 5/10, Iter 1542/3560] 1.4205145835876465, cross_entropy: 1.4205145835876465 +[2025-04-29 04:52:48,469][BaseTrainer][INFO] - [Epoch 5/10, Iter 1543/3560] 3.3685996532440186, cross_entropy: 3.3685996532440186 +[2025-04-29 04:52:49,354][BaseTrainer][INFO] - [Epoch 5/10, Iter 1544/3560] 2.1757991313934326, cross_entropy: 2.1757991313934326 +[2025-04-29 04:52:51,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1545/3560] 3.570524215698242, cross_entropy: 3.570524215698242 +[2025-04-29 04:52:52,634][BaseTrainer][INFO] - [Epoch 5/10, Iter 1546/3560] 3.1369142532348633, cross_entropy: 3.1369142532348633 +[2025-04-29 04:52:56,153][BaseTrainer][INFO] - [Epoch 5/10, Iter 1547/3560] 3.310516595840454, cross_entropy: 3.310516595840454 +[2025-04-29 04:52:57,034][BaseTrainer][INFO] - [Epoch 5/10, Iter 1548/3560] 3.376899242401123, cross_entropy: 3.376899242401123 +[2025-04-29 04:52:59,311][BaseTrainer][INFO] - [Epoch 5/10, Iter 1549/3560] 2.8421645164489746, cross_entropy: 2.8421645164489746 +[2025-04-29 04:53:00,203][BaseTrainer][INFO] - [Epoch 5/10, Iter 1550/3560] 3.252718210220337, cross_entropy: 3.252718210220337 +[2025-04-29 04:53:02,623][BaseTrainer][INFO] - [Epoch 5/10, Iter 1551/3560] 1.7301523685455322, cross_entropy: 1.7301523685455322 +[2025-04-29 04:53:03,507][BaseTrainer][INFO] - [Epoch 5/10, Iter 1552/3560] 3.1410858631134033, cross_entropy: 3.1410858631134033 +[2025-04-29 04:53:06,248][BaseTrainer][INFO] - [Epoch 5/10, Iter 1553/3560] 2.4919581413269043, cross_entropy: 2.4919581413269043 +[2025-04-29 04:53:07,134][BaseTrainer][INFO] - [Epoch 5/10, Iter 1554/3560] 2.8705291748046875, cross_entropy: 2.8705291748046875 +[2025-04-29 04:53:09,669][BaseTrainer][INFO] - [Epoch 5/10, Iter 1555/3560] 1.638157606124878, cross_entropy: 1.638157606124878 +[2025-04-29 04:53:10,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1556/3560] 1.3875281810760498, cross_entropy: 1.3875281810760498 +[2025-04-29 04:53:12,819][BaseTrainer][INFO] - [Epoch 5/10, Iter 1557/3560] 3.176520824432373, cross_entropy: 3.176520824432373 +[2025-04-29 04:53:13,682][BaseTrainer][INFO] - [Epoch 5/10, Iter 1558/3560] 3.699486494064331, cross_entropy: 3.699486494064331 +[2025-04-29 04:53:16,880][BaseTrainer][INFO] - [Epoch 5/10, Iter 1559/3560] 1.7117483615875244, cross_entropy: 1.7117483615875244 +[2025-04-29 04:53:17,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1560/3560] 1.2911978960037231, cross_entropy: 1.2911978960037231 +[2025-04-29 04:53:20,116][BaseTrainer][INFO] - [Epoch 5/10, Iter 1561/3560] 1.629755973815918, cross_entropy: 1.629755973815918 +[2025-04-29 04:53:21,008][BaseTrainer][INFO] - [Epoch 5/10, Iter 1562/3560] 2.22542667388916, cross_entropy: 2.22542667388916 +[2025-04-29 04:53:23,372][BaseTrainer][INFO] - [Epoch 5/10, Iter 1563/3560] 3.279209613800049, cross_entropy: 3.279209613800049 +[2025-04-29 04:53:24,260][BaseTrainer][INFO] - [Epoch 5/10, Iter 1564/3560] 2.98828125, cross_entropy: 2.98828125 +[2025-04-29 04:53:26,703][BaseTrainer][INFO] - [Epoch 5/10, Iter 1565/3560] 3.1458396911621094, cross_entropy: 3.1458396911621094 +[2025-04-29 04:53:27,589][BaseTrainer][INFO] - [Epoch 5/10, Iter 1566/3560] 3.0934066772460938, cross_entropy: 3.0934066772460938 +[2025-04-29 04:53:30,285][BaseTrainer][INFO] - [Epoch 5/10, Iter 1567/3560] 2.508517265319824, cross_entropy: 2.508517265319824 +[2025-04-29 04:53:31,172][BaseTrainer][INFO] - [Epoch 5/10, Iter 1568/3560] 1.9571951627731323, cross_entropy: 1.9571951627731323 +[2025-04-29 04:53:34,263][BaseTrainer][INFO] - [Epoch 5/10, Iter 1569/3560] 1.8041951656341553, cross_entropy: 1.8041951656341553 +[2025-04-29 04:53:35,201][BaseTrainer][INFO] - [Epoch 5/10, Iter 1570/3560] 3.1286540031433105, cross_entropy: 3.1286540031433105 +[2025-04-29 04:53:37,991][BaseTrainer][INFO] - [Epoch 5/10, Iter 1571/3560] 2.1472315788269043, cross_entropy: 2.1472315788269043 +[2025-04-29 04:53:38,877][BaseTrainer][INFO] - [Epoch 5/10, Iter 1572/3560] 1.3767433166503906, cross_entropy: 1.3767433166503906 +[2025-04-29 04:53:41,581][BaseTrainer][INFO] - [Epoch 5/10, Iter 1573/3560] 1.2752845287322998, cross_entropy: 1.2752845287322998 +[2025-04-29 04:53:42,468][BaseTrainer][INFO] - [Epoch 5/10, Iter 1574/3560] 3.140054702758789, cross_entropy: 3.140054702758789 +[2025-04-29 04:53:45,692][BaseTrainer][INFO] - [Epoch 5/10, Iter 1575/3560] 3.23384165763855, cross_entropy: 3.23384165763855 +[2025-04-29 04:53:46,551][BaseTrainer][INFO] - [Epoch 5/10, Iter 1576/3560] 3.2035789489746094, cross_entropy: 3.2035789489746094 +[2025-04-29 04:53:49,525][BaseTrainer][INFO] - [Epoch 5/10, Iter 1577/3560] 2.987697124481201, cross_entropy: 2.987697124481201 +[2025-04-29 04:53:50,413][BaseTrainer][INFO] - [Epoch 5/10, Iter 1578/3560] 2.0276551246643066, cross_entropy: 2.0276551246643066 +[2025-04-29 04:53:53,543][BaseTrainer][INFO] - [Epoch 5/10, Iter 1579/3560] 2.8974080085754395, cross_entropy: 2.8974080085754395 +[2025-04-29 04:53:54,426][BaseTrainer][INFO] - [Epoch 5/10, Iter 1580/3560] 3.0178275108337402, cross_entropy: 3.0178275108337402 +[2025-04-29 04:53:58,336][BaseTrainer][INFO] - [Epoch 5/10, Iter 1581/3560] 3.712827205657959, cross_entropy: 3.712827205657959 +[2025-04-29 04:53:59,221][BaseTrainer][INFO] - [Epoch 5/10, Iter 1582/3560] 1.8135672807693481, cross_entropy: 1.8135672807693481 +[2025-04-29 04:54:02,034][BaseTrainer][INFO] - [Epoch 5/10, Iter 1583/3560] 1.7253689765930176, cross_entropy: 1.7253689765930176 +[2025-04-29 04:54:02,926][BaseTrainer][INFO] - [Epoch 5/10, Iter 1584/3560] 2.8289132118225098, cross_entropy: 2.8289132118225098 +[2025-04-29 04:54:05,286][BaseTrainer][INFO] - [Epoch 5/10, Iter 1585/3560] 3.143036365509033, cross_entropy: 3.143036365509033 +[2025-04-29 04:54:06,187][BaseTrainer][INFO] - [Epoch 5/10, Iter 1586/3560] 1.7315665483474731, cross_entropy: 1.7315665483474731 +[2025-04-29 04:54:09,271][BaseTrainer][INFO] - [Epoch 5/10, Iter 1587/3560] 3.5165317058563232, cross_entropy: 3.5165317058563232 +[2025-04-29 04:54:10,157][BaseTrainer][INFO] - [Epoch 5/10, Iter 1588/3560] 3.068361759185791, cross_entropy: 3.068361759185791 +[2025-04-29 04:54:12,948][BaseTrainer][INFO] - [Epoch 5/10, Iter 1589/3560] 1.6785387992858887, cross_entropy: 1.6785387992858887 +[2025-04-29 04:54:13,834][BaseTrainer][INFO] - [Epoch 5/10, Iter 1590/3560] 2.2364821434020996, cross_entropy: 2.2364821434020996 +[2025-04-29 04:54:17,123][BaseTrainer][INFO] - [Epoch 5/10, Iter 1591/3560] 1.9368342161178589, cross_entropy: 1.9368342161178589 +[2025-04-29 04:54:17,983][BaseTrainer][INFO] - [Epoch 5/10, Iter 1592/3560] 2.220869541168213, cross_entropy: 2.220869541168213 +[2025-04-29 04:54:20,690][BaseTrainer][INFO] - [Epoch 5/10, Iter 1593/3560] 3.1678709983825684, cross_entropy: 3.1678709983825684 +[2025-04-29 04:54:21,551][BaseTrainer][INFO] - [Epoch 5/10, Iter 1594/3560] 2.202086925506592, cross_entropy: 2.202086925506592 +[2025-04-29 04:54:25,290][BaseTrainer][INFO] - [Epoch 5/10, Iter 1595/3560] 2.1794724464416504, cross_entropy: 2.1794724464416504 +[2025-04-29 04:54:26,182][BaseTrainer][INFO] - [Epoch 5/10, Iter 1596/3560] 2.6481027603149414, cross_entropy: 2.6481027603149414 +[2025-04-29 04:54:29,115][BaseTrainer][INFO] - [Epoch 5/10, Iter 1597/3560] 3.5459108352661133, cross_entropy: 3.5459108352661133 +[2025-04-29 04:54:30,001][BaseTrainer][INFO] - [Epoch 5/10, Iter 1598/3560] 2.88234281539917, cross_entropy: 2.88234281539917 +[2025-04-29 04:54:32,363][BaseTrainer][INFO] - [Epoch 5/10, Iter 1599/3560] 3.3496150970458984, cross_entropy: 3.3496150970458984 +[2025-04-29 04:54:33,253][BaseTrainer][INFO] - [Epoch 5/10, Iter 1600/3560] 1.8817119598388672, cross_entropy: 1.8817119598388672 +[2025-04-29 04:54:36,607][BaseTrainer][INFO] - [Epoch 5/10, Iter 1601/3560] 1.6124147176742554, cross_entropy: 1.6124147176742554 +[2025-04-29 04:54:37,499][BaseTrainer][INFO] - [Epoch 5/10, Iter 1602/3560] 3.632333993911743, cross_entropy: 3.632333993911743 +[2025-04-29 04:54:39,803][BaseTrainer][INFO] - [Epoch 5/10, Iter 1603/3560] 1.1599127054214478, cross_entropy: 1.1599127054214478 +[2025-04-29 04:54:40,696][BaseTrainer][INFO] - [Epoch 5/10, Iter 1604/3560] 3.049440622329712, cross_entropy: 3.049440622329712 +[2025-04-29 04:54:42,768][BaseTrainer][INFO] - [Epoch 5/10, Iter 1605/3560] 2.043356418609619, cross_entropy: 2.043356418609619 +[2025-04-29 04:54:43,630][BaseTrainer][INFO] - [Epoch 5/10, Iter 1606/3560] 1.7724330425262451, cross_entropy: 1.7724330425262451 +[2025-04-29 04:54:46,467][BaseTrainer][INFO] - [Epoch 5/10, Iter 1607/3560] 3.2321133613586426, cross_entropy: 3.2321133613586426 +[2025-04-29 04:54:47,353][BaseTrainer][INFO] - [Epoch 5/10, Iter 1608/3560] 2.6257824897766113, cross_entropy: 2.6257824897766113 +[2025-04-29 04:54:50,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1609/3560] 3.2610340118408203, cross_entropy: 3.2610340118408203 +[2025-04-29 04:54:51,103][BaseTrainer][INFO] - [Epoch 5/10, Iter 1610/3560] 3.2022078037261963, cross_entropy: 3.2022078037261963 +[2025-04-29 04:54:53,777][BaseTrainer][INFO] - [Epoch 5/10, Iter 1611/3560] 2.654231071472168, cross_entropy: 2.654231071472168 +[2025-04-29 04:54:54,662][BaseTrainer][INFO] - [Epoch 5/10, Iter 1612/3560] 2.2373342514038086, cross_entropy: 2.2373342514038086 +[2025-04-29 04:54:58,005][BaseTrainer][INFO] - [Epoch 5/10, Iter 1613/3560] 1.999983310699463, cross_entropy: 1.999983310699463 +[2025-04-29 04:54:58,862][BaseTrainer][INFO] - [Epoch 5/10, Iter 1614/3560] 2.7205851078033447, cross_entropy: 2.7205851078033447 +[2025-04-29 04:55:02,090][BaseTrainer][INFO] - [Epoch 5/10, Iter 1615/3560] 2.1988587379455566, cross_entropy: 2.1988587379455566 +[2025-04-29 04:55:02,972][BaseTrainer][INFO] - [Epoch 5/10, Iter 1616/3560] 2.8620681762695312, cross_entropy: 2.8620681762695312 +[2025-04-29 04:55:06,161][BaseTrainer][INFO] - [Epoch 5/10, Iter 1617/3560] 3.1092095375061035, cross_entropy: 3.1092095375061035 +[2025-04-29 04:55:07,049][BaseTrainer][INFO] - [Epoch 5/10, Iter 1618/3560] 2.866267442703247, cross_entropy: 2.866267442703247 +[2025-04-29 04:55:10,141][BaseTrainer][INFO] - [Epoch 5/10, Iter 1619/3560] 3.611001968383789, cross_entropy: 3.611001968383789 +[2025-04-29 04:55:10,998][BaseTrainer][INFO] - [Epoch 5/10, Iter 1620/3560] 2.058732748031616, cross_entropy: 2.058732748031616 +[2025-04-29 04:55:13,786][BaseTrainer][INFO] - [Epoch 5/10, Iter 1621/3560] 1.740715503692627, cross_entropy: 1.740715503692627 +[2025-04-29 04:55:14,646][BaseTrainer][INFO] - [Epoch 5/10, Iter 1622/3560] 1.7079713344573975, cross_entropy: 1.7079713344573975 +[2025-04-29 04:55:17,411][BaseTrainer][INFO] - [Epoch 5/10, Iter 1623/3560] 2.6384119987487793, cross_entropy: 2.6384119987487793 +[2025-04-29 04:55:18,292][BaseTrainer][INFO] - [Epoch 5/10, Iter 1624/3560] 2.183176040649414, cross_entropy: 2.183176040649414 +[2025-04-29 04:55:20,211][BaseTrainer][INFO] - [Epoch 5/10, Iter 1625/3560] 1.7750238180160522, cross_entropy: 1.7750238180160522 +[2025-04-29 04:55:21,096][BaseTrainer][INFO] - [Epoch 5/10, Iter 1626/3560] 1.8592946529388428, cross_entropy: 1.8592946529388428 +[2025-04-29 04:55:24,113][BaseTrainer][INFO] - [Epoch 5/10, Iter 1627/3560] 2.158407688140869, cross_entropy: 2.158407688140869 +[2025-04-29 04:55:24,970][BaseTrainer][INFO] - [Epoch 5/10, Iter 1628/3560] 2.0164430141448975, cross_entropy: 2.0164430141448975 +[2025-04-29 04:55:28,364][BaseTrainer][INFO] - [Epoch 5/10, Iter 1629/3560] 2.6347713470458984, cross_entropy: 2.6347713470458984 +[2025-04-29 04:55:29,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1630/3560] 2.970715284347534, cross_entropy: 2.970715284347534 +[2025-04-29 04:55:31,541][BaseTrainer][INFO] - [Epoch 5/10, Iter 1631/3560] 2.25566029548645, cross_entropy: 2.25566029548645 +[2025-04-29 04:55:32,402][BaseTrainer][INFO] - [Epoch 5/10, Iter 1632/3560] 3.018153667449951, cross_entropy: 3.018153667449951 +[2025-04-29 04:55:35,296][BaseTrainer][INFO] - [Epoch 5/10, Iter 1633/3560] 2.8411178588867188, cross_entropy: 2.8411178588867188 +[2025-04-29 04:55:36,154][BaseTrainer][INFO] - [Epoch 5/10, Iter 1634/3560] 3.1447701454162598, cross_entropy: 3.1447701454162598 +[2025-04-29 04:55:39,938][BaseTrainer][INFO] - [Epoch 5/10, Iter 1635/3560] 1.90358567237854, cross_entropy: 1.90358567237854 +[2025-04-29 04:55:40,823][BaseTrainer][INFO] - [Epoch 5/10, Iter 1636/3560] 3.530351161956787, cross_entropy: 3.530351161956787 +[2025-04-29 04:55:43,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1637/3560] 2.821861743927002, cross_entropy: 2.821861743927002 +[2025-04-29 04:55:44,246][BaseTrainer][INFO] - [Epoch 5/10, Iter 1638/3560] 1.714930534362793, cross_entropy: 1.714930534362793 +[2025-04-29 04:55:47,424][BaseTrainer][INFO] - [Epoch 5/10, Iter 1639/3560] 2.8059935569763184, cross_entropy: 2.8059935569763184 +[2025-04-29 04:55:48,303][BaseTrainer][INFO] - [Epoch 5/10, Iter 1640/3560] 2.2226920127868652, cross_entropy: 2.2226920127868652 +[2025-04-29 04:55:52,263][BaseTrainer][INFO] - [Epoch 5/10, Iter 1641/3560] 1.945732831954956, cross_entropy: 1.945732831954956 +[2025-04-29 04:55:53,143][BaseTrainer][INFO] - [Epoch 5/10, Iter 1642/3560] 3.312979221343994, cross_entropy: 3.312979221343994 +[2025-04-29 04:55:56,102][BaseTrainer][INFO] - [Epoch 5/10, Iter 1643/3560] 2.505272626876831, cross_entropy: 2.505272626876831 +[2025-04-29 04:55:56,961][BaseTrainer][INFO] - [Epoch 5/10, Iter 1644/3560] 1.6876180171966553, cross_entropy: 1.6876180171966553 +[2025-04-29 04:55:59,564][BaseTrainer][INFO] - [Epoch 5/10, Iter 1645/3560] 2.218182325363159, cross_entropy: 2.218182325363159 +[2025-04-29 04:56:00,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1646/3560] 3.444843292236328, cross_entropy: 3.444843292236328 +[2025-04-29 04:56:04,193][BaseTrainer][INFO] - [Epoch 5/10, Iter 1647/3560] 2.193331241607666, cross_entropy: 2.193331241607666 +[2025-04-29 04:56:05,078][BaseTrainer][INFO] - [Epoch 5/10, Iter 1648/3560] 2.8035120964050293, cross_entropy: 2.8035120964050293 +[2025-04-29 04:56:07,476][BaseTrainer][INFO] - [Epoch 5/10, Iter 1649/3560] 2.910344123840332, cross_entropy: 2.910344123840332 +[2025-04-29 04:56:08,337][BaseTrainer][INFO] - [Epoch 5/10, Iter 1650/3560] 2.9269354343414307, cross_entropy: 2.9269354343414307 +[2025-04-29 04:56:12,491][BaseTrainer][INFO] - [Epoch 5/10, Iter 1651/3560] 2.5288071632385254, cross_entropy: 2.5288071632385254 +[2025-04-29 04:56:13,369][BaseTrainer][INFO] - [Epoch 5/10, Iter 1652/3560] 2.397545337677002, cross_entropy: 2.397545337677002 +[2025-04-29 04:56:16,031][BaseTrainer][INFO] - [Epoch 5/10, Iter 1653/3560] 3.104419469833374, cross_entropy: 3.104419469833374 +[2025-04-29 04:56:16,920][BaseTrainer][INFO] - [Epoch 5/10, Iter 1654/3560] 2.0103769302368164, cross_entropy: 2.0103769302368164 +[2025-04-29 04:56:19,972][BaseTrainer][INFO] - [Epoch 5/10, Iter 1655/3560] 1.7783379554748535, cross_entropy: 1.7783379554748535 +[2025-04-29 04:56:20,854][BaseTrainer][INFO] - [Epoch 5/10, Iter 1656/3560] 2.168044090270996, cross_entropy: 2.168044090270996 +[2025-04-29 04:56:23,258][BaseTrainer][INFO] - [Epoch 5/10, Iter 1657/3560] 1.5836822986602783, cross_entropy: 1.5836822986602783 +[2025-04-29 04:56:24,147][BaseTrainer][INFO] - [Epoch 5/10, Iter 1658/3560] 2.551705837249756, cross_entropy: 2.551705837249756 +[2025-04-29 04:56:27,496][BaseTrainer][INFO] - [Epoch 5/10, Iter 1659/3560] 2.079874038696289, cross_entropy: 2.079874038696289 +[2025-04-29 04:56:28,380][BaseTrainer][INFO] - [Epoch 5/10, Iter 1660/3560] 1.711422324180603, cross_entropy: 1.711422324180603 +[2025-04-29 04:56:30,873][BaseTrainer][INFO] - [Epoch 5/10, Iter 1661/3560] 1.9026751518249512, cross_entropy: 1.9026751518249512 +[2025-04-29 04:56:31,767][BaseTrainer][INFO] - [Epoch 5/10, Iter 1662/3560] 2.87101411819458, cross_entropy: 2.87101411819458 +[2025-04-29 04:56:35,067][BaseTrainer][INFO] - [Epoch 5/10, Iter 1663/3560] 1.550255298614502, cross_entropy: 1.550255298614502 +[2025-04-29 04:56:35,962][BaseTrainer][INFO] - [Epoch 5/10, Iter 1664/3560] 3.0355746746063232, cross_entropy: 3.0355746746063232 +[2025-04-29 04:56:39,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1665/3560] 3.692615270614624, cross_entropy: 3.692615270614624 +[2025-04-29 04:56:39,905][BaseTrainer][INFO] - [Epoch 5/10, Iter 1666/3560] 2.9578750133514404, cross_entropy: 2.9578750133514404 +[2025-04-29 04:56:42,818][BaseTrainer][INFO] - [Epoch 5/10, Iter 1667/3560] 3.4915854930877686, cross_entropy: 3.4915854930877686 +[2025-04-29 04:56:43,701][BaseTrainer][INFO] - [Epoch 5/10, Iter 1668/3560] 1.5642248392105103, cross_entropy: 1.5642248392105103 +[2025-04-29 04:56:46,371][BaseTrainer][INFO] - [Epoch 5/10, Iter 1669/3560] 2.958536148071289, cross_entropy: 2.958536148071289 +[2025-04-29 04:56:47,257][BaseTrainer][INFO] - [Epoch 5/10, Iter 1670/3560] 3.6112990379333496, cross_entropy: 3.6112990379333496 +[2025-04-29 04:56:50,079][BaseTrainer][INFO] - [Epoch 5/10, Iter 1671/3560] 2.1874115467071533, cross_entropy: 2.1874115467071533 +[2025-04-29 04:56:50,963][BaseTrainer][INFO] - [Epoch 5/10, Iter 1672/3560] 1.7194404602050781, cross_entropy: 1.7194404602050781 +[2025-04-29 04:56:53,920][BaseTrainer][INFO] - [Epoch 5/10, Iter 1673/3560] 2.358093500137329, cross_entropy: 2.358093500137329 +[2025-04-29 04:56:54,781][BaseTrainer][INFO] - [Epoch 5/10, Iter 1674/3560] 3.272686004638672, cross_entropy: 3.272686004638672 +[2025-04-29 04:56:57,578][BaseTrainer][INFO] - [Epoch 5/10, Iter 1675/3560] 2.6401610374450684, cross_entropy: 2.6401610374450684 +[2025-04-29 04:56:58,463][BaseTrainer][INFO] - [Epoch 5/10, Iter 1676/3560] 3.443366050720215, cross_entropy: 3.443366050720215 +[2025-04-29 04:57:00,844][BaseTrainer][INFO] - [Epoch 5/10, Iter 1677/3560] 1.4059357643127441, cross_entropy: 1.4059357643127441 +[2025-04-29 04:57:01,732][BaseTrainer][INFO] - [Epoch 5/10, Iter 1678/3560] 2.0318336486816406, cross_entropy: 2.0318336486816406 +[2025-04-29 04:57:04,080][BaseTrainer][INFO] - [Epoch 5/10, Iter 1679/3560] 1.6209901571273804, cross_entropy: 1.6209901571273804 +[2025-04-29 04:57:04,942][BaseTrainer][INFO] - [Epoch 5/10, Iter 1680/3560] 2.816210985183716, cross_entropy: 2.816210985183716 +[2025-04-29 04:57:07,844][BaseTrainer][INFO] - [Epoch 5/10, Iter 1681/3560] 3.2978222370147705, cross_entropy: 3.2978222370147705 +[2025-04-29 04:57:08,730][BaseTrainer][INFO] - [Epoch 5/10, Iter 1682/3560] 2.207524299621582, cross_entropy: 2.207524299621582 +[2025-04-29 04:57:11,790][BaseTrainer][INFO] - [Epoch 5/10, Iter 1683/3560] 2.6769556999206543, cross_entropy: 2.6769556999206543 +[2025-04-29 04:57:12,649][BaseTrainer][INFO] - [Epoch 5/10, Iter 1684/3560] 2.721862316131592, cross_entropy: 2.721862316131592 +[2025-04-29 04:57:17,055][BaseTrainer][INFO] - [Epoch 5/10, Iter 1685/3560] 1.730320930480957, cross_entropy: 1.730320930480957 +[2025-04-29 04:57:17,942][BaseTrainer][INFO] - [Epoch 5/10, Iter 1686/3560] 1.8230829238891602, cross_entropy: 1.8230829238891602 +[2025-04-29 04:57:20,654][BaseTrainer][INFO] - [Epoch 5/10, Iter 1687/3560] 2.4147565364837646, cross_entropy: 2.4147565364837646 +[2025-04-29 04:57:21,544][BaseTrainer][INFO] - [Epoch 5/10, Iter 1688/3560] 2.791670799255371, cross_entropy: 2.791670799255371 +[2025-04-29 04:57:23,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1689/3560] 3.061431884765625, cross_entropy: 3.061431884765625 +[2025-04-29 04:57:24,424][BaseTrainer][INFO] - [Epoch 5/10, Iter 1690/3560] 1.6985642910003662, cross_entropy: 1.6985642910003662 +[2025-04-29 04:57:27,695][BaseTrainer][INFO] - [Epoch 5/10, Iter 1691/3560] 3.096442222595215, cross_entropy: 3.096442222595215 +[2025-04-29 04:57:28,552][BaseTrainer][INFO] - [Epoch 5/10, Iter 1692/3560] 3.3319690227508545, cross_entropy: 3.3319690227508545 +[2025-04-29 04:57:31,227][BaseTrainer][INFO] - [Epoch 5/10, Iter 1693/3560] 3.3376193046569824, cross_entropy: 3.3376193046569824 +[2025-04-29 04:57:32,092][BaseTrainer][INFO] - [Epoch 5/10, Iter 1694/3560] 1.5284260511398315, cross_entropy: 1.5284260511398315 +[2025-04-29 04:57:35,360][BaseTrainer][INFO] - [Epoch 5/10, Iter 1695/3560] 2.10219669342041, cross_entropy: 2.10219669342041 +[2025-04-29 04:57:36,249][BaseTrainer][INFO] - [Epoch 5/10, Iter 1696/3560] 3.249260902404785, cross_entropy: 3.249260902404785 +[2025-04-29 04:57:39,166][BaseTrainer][INFO] - [Epoch 5/10, Iter 1697/3560] 2.9166455268859863, cross_entropy: 2.9166455268859863 +[2025-04-29 04:57:40,023][BaseTrainer][INFO] - [Epoch 5/10, Iter 1698/3560] 2.117732524871826, cross_entropy: 2.117732524871826 +[2025-04-29 04:57:42,826][BaseTrainer][INFO] - [Epoch 5/10, Iter 1699/3560] 1.9446282386779785, cross_entropy: 1.9446282386779785 +[2025-04-29 04:57:43,685][BaseTrainer][INFO] - [Epoch 5/10, Iter 1700/3560] 1.91835355758667, cross_entropy: 1.91835355758667 +[2025-04-29 04:57:46,572][BaseTrainer][INFO] - [Epoch 5/10, Iter 1701/3560] 3.2227187156677246, cross_entropy: 3.2227187156677246 +[2025-04-29 04:57:47,461][BaseTrainer][INFO] - [Epoch 5/10, Iter 1702/3560] 2.6030611991882324, cross_entropy: 2.6030611991882324 +[2025-04-29 04:57:49,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1703/3560] 2.8327088356018066, cross_entropy: 2.8327088356018066 +[2025-04-29 04:57:50,724][BaseTrainer][INFO] - [Epoch 5/10, Iter 1704/3560] 2.265382766723633, cross_entropy: 2.265382766723633 +[2025-04-29 04:57:53,691][BaseTrainer][INFO] - [Epoch 5/10, Iter 1705/3560] 3.776785373687744, cross_entropy: 3.776785373687744 +[2025-04-29 04:57:54,550][BaseTrainer][INFO] - [Epoch 5/10, Iter 1706/3560] 1.7353304624557495, cross_entropy: 1.7353304624557495 +[2025-04-29 04:57:57,903][BaseTrainer][INFO] - [Epoch 5/10, Iter 1707/3560] 3.264395236968994, cross_entropy: 3.264395236968994 +[2025-04-29 04:57:58,761][BaseTrainer][INFO] - [Epoch 5/10, Iter 1708/3560] 1.98476243019104, cross_entropy: 1.98476243019104 +[2025-04-29 04:58:02,655][BaseTrainer][INFO] - [Epoch 5/10, Iter 1709/3560] 3.186192750930786, cross_entropy: 3.186192750930786 +[2025-04-29 04:58:03,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1710/3560] 2.3006412982940674, cross_entropy: 2.3006412982940674 +[2025-04-29 04:58:06,656][BaseTrainer][INFO] - [Epoch 5/10, Iter 1711/3560] 1.8915393352508545, cross_entropy: 1.8915393352508545 +[2025-04-29 04:58:07,542][BaseTrainer][INFO] - [Epoch 5/10, Iter 1712/3560] 2.6378884315490723, cross_entropy: 2.6378884315490723 +[2025-04-29 04:58:10,217][BaseTrainer][INFO] - [Epoch 5/10, Iter 1713/3560] 3.427870512008667, cross_entropy: 3.427870512008667 +[2025-04-29 04:58:11,100][BaseTrainer][INFO] - [Epoch 5/10, Iter 1714/3560] 1.8896974325180054, cross_entropy: 1.8896974325180054 +[2025-04-29 04:58:13,967][BaseTrainer][INFO] - [Epoch 5/10, Iter 1715/3560] 3.337697982788086, cross_entropy: 3.337697982788086 +[2025-04-29 04:58:14,826][BaseTrainer][INFO] - [Epoch 5/10, Iter 1716/3560] 3.3922743797302246, cross_entropy: 3.3922743797302246 +[2025-04-29 04:58:17,453][BaseTrainer][INFO] - [Epoch 5/10, Iter 1717/3560] 2.565885066986084, cross_entropy: 2.565885066986084 +[2025-04-29 04:58:18,334][BaseTrainer][INFO] - [Epoch 5/10, Iter 1718/3560] 2.9317944049835205, cross_entropy: 2.9317944049835205 +[2025-04-29 04:58:20,855][BaseTrainer][INFO] - [Epoch 5/10, Iter 1719/3560] 1.8861998319625854, cross_entropy: 1.8861998319625854 +[2025-04-29 04:58:21,744][BaseTrainer][INFO] - [Epoch 5/10, Iter 1720/3560] 1.5021836757659912, cross_entropy: 1.5021836757659912 +[2025-04-29 04:58:25,254][BaseTrainer][INFO] - [Epoch 5/10, Iter 1721/3560] 1.9716778993606567, cross_entropy: 1.9716778993606567 +[2025-04-29 04:58:26,110][BaseTrainer][INFO] - [Epoch 5/10, Iter 1722/3560] 1.8245887756347656, cross_entropy: 1.8245887756347656 +[2025-04-29 04:58:29,293][BaseTrainer][INFO] - [Epoch 5/10, Iter 1723/3560] 1.5009808540344238, cross_entropy: 1.5009808540344238 +[2025-04-29 04:58:30,175][BaseTrainer][INFO] - [Epoch 5/10, Iter 1724/3560] 2.3837649822235107, cross_entropy: 2.3837649822235107 +[2025-04-29 04:58:33,032][BaseTrainer][INFO] - [Epoch 5/10, Iter 1725/3560] 1.6417007446289062, cross_entropy: 1.6417007446289062 +[2025-04-29 04:58:33,890][BaseTrainer][INFO] - [Epoch 5/10, Iter 1726/3560] 3.177605152130127, cross_entropy: 3.177605152130127 +[2025-04-29 04:58:37,256][BaseTrainer][INFO] - [Epoch 5/10, Iter 1727/3560] 2.4276223182678223, cross_entropy: 2.4276223182678223 +[2025-04-29 04:58:38,135][BaseTrainer][INFO] - [Epoch 5/10, Iter 1728/3560] 2.034900665283203, cross_entropy: 2.034900665283203 +[2025-04-29 04:58:40,765][BaseTrainer][INFO] - [Epoch 5/10, Iter 1729/3560] 2.7671802043914795, cross_entropy: 2.7671802043914795 +[2025-04-29 04:58:41,658][BaseTrainer][INFO] - [Epoch 5/10, Iter 1730/3560] 2.043046236038208, cross_entropy: 2.043046236038208 +[2025-04-29 04:58:44,343][BaseTrainer][INFO] - [Epoch 5/10, Iter 1731/3560] 1.6480944156646729, cross_entropy: 1.6480944156646729 +[2025-04-29 04:58:45,209][BaseTrainer][INFO] - [Epoch 5/10, Iter 1732/3560] 2.0624616146087646, cross_entropy: 2.0624616146087646 +[2025-04-29 04:58:48,826][BaseTrainer][INFO] - [Epoch 5/10, Iter 1733/3560] 2.202924966812134, cross_entropy: 2.202924966812134 +[2025-04-29 04:58:49,688][BaseTrainer][INFO] - [Epoch 5/10, Iter 1734/3560] 1.9597288370132446, cross_entropy: 1.9597288370132446 +[2025-04-29 04:58:52,310][BaseTrainer][INFO] - [Epoch 5/10, Iter 1735/3560] 1.8201638460159302, cross_entropy: 1.8201638460159302 +[2025-04-29 04:58:53,198][BaseTrainer][INFO] - [Epoch 5/10, Iter 1736/3560] 3.4218058586120605, cross_entropy: 3.4218058586120605 +[2025-04-29 04:58:55,341][BaseTrainer][INFO] - [Epoch 5/10, Iter 1737/3560] 2.0160460472106934, cross_entropy: 2.0160460472106934 +[2025-04-29 04:58:56,251][BaseTrainer][INFO] - [Epoch 5/10, Iter 1738/3560] 2.7100868225097656, cross_entropy: 2.7100868225097656 +[2025-04-29 04:58:59,563][BaseTrainer][INFO] - [Epoch 5/10, Iter 1739/3560] 1.6335644721984863, cross_entropy: 1.6335644721984863 +[2025-04-29 04:59:00,427][BaseTrainer][INFO] - [Epoch 5/10, Iter 1740/3560] 2.5880672931671143, cross_entropy: 2.5880672931671143 +[2025-04-29 04:59:03,181][BaseTrainer][INFO] - [Epoch 5/10, Iter 1741/3560] 2.802346706390381, cross_entropy: 2.802346706390381 +[2025-04-29 04:59:04,064][BaseTrainer][INFO] - [Epoch 5/10, Iter 1742/3560] 1.998480200767517, cross_entropy: 1.998480200767517 +[2025-04-29 04:59:06,711][BaseTrainer][INFO] - [Epoch 5/10, Iter 1743/3560] 3.43985652923584, cross_entropy: 3.43985652923584 +[2025-04-29 04:59:07,573][BaseTrainer][INFO] - [Epoch 5/10, Iter 1744/3560] 3.6144392490386963, cross_entropy: 3.6144392490386963 +[2025-04-29 04:59:10,534][BaseTrainer][INFO] - [Epoch 5/10, Iter 1745/3560] 1.646218180656433, cross_entropy: 1.646218180656433 +[2025-04-29 04:59:11,393][BaseTrainer][INFO] - [Epoch 5/10, Iter 1746/3560] 2.261683940887451, cross_entropy: 2.261683940887451 +[2025-04-29 04:59:15,307][BaseTrainer][INFO] - [Epoch 5/10, Iter 1747/3560] 1.5044231414794922, cross_entropy: 1.5044231414794922 +[2025-04-29 04:59:16,167][BaseTrainer][INFO] - [Epoch 5/10, Iter 1748/3560] 2.296074867248535, cross_entropy: 2.296074867248535 +[2025-04-29 04:59:19,145][BaseTrainer][INFO] - [Epoch 5/10, Iter 1749/3560] 3.3339755535125732, cross_entropy: 3.3339755535125732 +[2025-04-29 04:59:20,029][BaseTrainer][INFO] - [Epoch 5/10, Iter 1750/3560] 2.6344356536865234, cross_entropy: 2.6344356536865234 +[2025-04-29 04:59:22,731][BaseTrainer][INFO] - [Epoch 5/10, Iter 1751/3560] 2.1408543586730957, cross_entropy: 2.1408543586730957 +[2025-04-29 04:59:23,623][BaseTrainer][INFO] - [Epoch 5/10, Iter 1752/3560] 1.8899171352386475, cross_entropy: 1.8899171352386475 +[2025-04-29 04:59:26,300][BaseTrainer][INFO] - [Epoch 5/10, Iter 1753/3560] 3.2101075649261475, cross_entropy: 3.2101075649261475 +[2025-04-29 04:59:27,235][BaseTrainer][INFO] - [Epoch 5/10, Iter 1754/3560] 2.552084445953369, cross_entropy: 2.552084445953369 +[2025-04-29 04:59:29,936][BaseTrainer][INFO] - [Epoch 5/10, Iter 1755/3560] 3.020839214324951, cross_entropy: 3.020839214324951 +[2025-04-29 04:59:30,838][BaseTrainer][INFO] - [Epoch 5/10, Iter 1756/3560] 2.910926580429077, cross_entropy: 2.910926580429077 +[2025-04-29 04:59:33,410][BaseTrainer][INFO] - [Epoch 5/10, Iter 1757/3560] 1.805560827255249, cross_entropy: 1.805560827255249 +[2025-04-29 04:59:34,287][BaseTrainer][INFO] - [Epoch 5/10, Iter 1758/3560] 3.225260019302368, cross_entropy: 3.225260019302368 +[2025-04-29 04:59:36,626][BaseTrainer][INFO] - [Epoch 5/10, Iter 1759/3560] 1.9967765808105469, cross_entropy: 1.9967765808105469 +[2025-04-29 04:59:37,537][BaseTrainer][INFO] - [Epoch 5/10, Iter 1760/3560] 1.8264449834823608, cross_entropy: 1.8264449834823608 +[2025-04-29 04:59:41,195][BaseTrainer][INFO] - [Epoch 5/10, Iter 1761/3560] 1.9201470613479614, cross_entropy: 1.9201470613479614 +[2025-04-29 04:59:42,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1762/3560] 3.0896530151367188, cross_entropy: 3.0896530151367188 +[2025-04-29 04:59:44,843][BaseTrainer][INFO] - [Epoch 5/10, Iter 1763/3560] 1.8830459117889404, cross_entropy: 1.8830459117889404 +[2025-04-29 04:59:45,729][BaseTrainer][INFO] - [Epoch 5/10, Iter 1764/3560] 3.368034839630127, cross_entropy: 3.368034839630127 +[2025-04-29 04:59:49,019][BaseTrainer][INFO] - [Epoch 5/10, Iter 1765/3560] 3.0169177055358887, cross_entropy: 3.0169177055358887 +[2025-04-29 04:59:49,882][BaseTrainer][INFO] - [Epoch 5/10, Iter 1766/3560] 2.375809669494629, cross_entropy: 2.375809669494629 +[2025-04-29 04:59:53,294][BaseTrainer][INFO] - [Epoch 5/10, Iter 1767/3560] 2.2438626289367676, cross_entropy: 2.2438626289367676 +[2025-04-29 04:59:54,154][BaseTrainer][INFO] - [Epoch 5/10, Iter 1768/3560] 3.717836380004883, cross_entropy: 3.717836380004883 +[2025-04-29 04:59:57,357][BaseTrainer][INFO] - [Epoch 5/10, Iter 1769/3560] 1.9685012102127075, cross_entropy: 1.9685012102127075 +[2025-04-29 04:59:58,216][BaseTrainer][INFO] - [Epoch 5/10, Iter 1770/3560] 1.3059487342834473, cross_entropy: 1.3059487342834473 +[2025-04-29 05:00:01,086][BaseTrainer][INFO] - [Epoch 5/10, Iter 1771/3560] 3.2613511085510254, cross_entropy: 3.2613511085510254 +[2025-04-29 05:00:01,975][BaseTrainer][INFO] - [Epoch 5/10, Iter 1772/3560] 3.271210193634033, cross_entropy: 3.271210193634033 +[2025-04-29 05:00:05,869][BaseTrainer][INFO] - [Epoch 5/10, Iter 1773/3560] 1.8657429218292236, cross_entropy: 1.8657429218292236 +[2025-04-29 05:00:06,750][BaseTrainer][INFO] - [Epoch 5/10, Iter 1774/3560] 2.437572956085205, cross_entropy: 2.437572956085205 +[2025-04-29 05:00:09,562][BaseTrainer][INFO] - [Epoch 5/10, Iter 1775/3560] 3.2322990894317627, cross_entropy: 3.2322990894317627 +[2025-04-29 05:00:10,423][BaseTrainer][INFO] - [Epoch 5/10, Iter 1776/3560] 2.7813053131103516, cross_entropy: 2.7813053131103516 +[2025-04-29 05:00:13,618][BaseTrainer][INFO] - [Epoch 5/10, Iter 1777/3560] 1.5323832035064697, cross_entropy: 1.5323832035064697 +[2025-04-29 05:00:14,473][BaseTrainer][INFO] - [Epoch 5/10, Iter 1778/3560] 2.338866710662842, cross_entropy: 2.338866710662842 +[2025-04-29 05:00:16,354][BaseTrainer][INFO] - [Epoch 5/10, Iter 1779/3560] 3.0293266773223877, cross_entropy: 3.0293266773223877 +[2025-04-29 05:00:17,127][BaseTrainer][INFO] - [Epoch 5/10, Iter 1780/3560] 1.8512307405471802, cross_entropy: 1.8512307405471802 +[2025-04-29 05:03:07,209][BaseTrainer][INFO] - [Epoch 5/10] (train) 2.5047683715820312, cross_entropy: 2.5047683715820312 +[2025-04-29 05:03:07,210][BaseTrainer][INFO] - [Epoch 5/10] (validation) 1.5352567434310913, cross_entropy: 1.5352567434310913 +[2025-04-29 05:03:08,073][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 05:03:08,560][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch5.pth. +[2025-04-29 05:03:09,370][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 05:03:14,334][BaseTrainer][INFO] - [Epoch 6/10, Iter 1781/3560] 3.1244606971740723, cross_entropy: 3.1244606971740723 +[2025-04-29 05:03:15,309][BaseTrainer][INFO] - [Epoch 6/10, Iter 1782/3560] 1.3236489295959473, cross_entropy: 1.3236489295959473 +[2025-04-29 05:03:18,278][BaseTrainer][INFO] - [Epoch 6/10, Iter 1783/3560] 1.6725552082061768, cross_entropy: 1.6725552082061768 +[2025-04-29 05:03:19,160][BaseTrainer][INFO] - [Epoch 6/10, Iter 1784/3560] 1.8264795541763306, cross_entropy: 1.8264795541763306 +[2025-04-29 05:03:21,780][BaseTrainer][INFO] - [Epoch 6/10, Iter 1785/3560] 3.161475419998169, cross_entropy: 3.161475419998169 +[2025-04-29 05:03:23,880][BaseTrainer][INFO] - [Epoch 6/10, Iter 1786/3560] 2.312805414199829, cross_entropy: 2.312805414199829 +[2025-04-29 05:03:25,284][BaseTrainer][INFO] - [Epoch 6/10, Iter 1787/3560] 3.5879969596862793, cross_entropy: 3.5879969596862793 +[2025-04-29 05:03:27,902][BaseTrainer][INFO] - [Epoch 6/10, Iter 1788/3560] 2.8429038524627686, cross_entropy: 2.8429038524627686 +[2025-04-29 05:03:28,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 1789/3560] 1.638660192489624, cross_entropy: 1.638660192489624 +[2025-04-29 05:03:31,667][BaseTrainer][INFO] - [Epoch 6/10, Iter 1790/3560] 1.446305513381958, cross_entropy: 1.446305513381958 +[2025-04-29 05:03:33,023][BaseTrainer][INFO] - [Epoch 6/10, Iter 1791/3560] 2.231767416000366, cross_entropy: 2.231767416000366 +[2025-04-29 05:03:35,658][BaseTrainer][INFO] - [Epoch 6/10, Iter 1792/3560] 3.051126480102539, cross_entropy: 3.051126480102539 +[2025-04-29 05:03:36,545][BaseTrainer][INFO] - [Epoch 6/10, Iter 1793/3560] 1.6346086263656616, cross_entropy: 1.6346086263656616 +[2025-04-29 05:03:39,256][BaseTrainer][INFO] - [Epoch 6/10, Iter 1794/3560] 3.0109047889709473, cross_entropy: 3.0109047889709473 +[2025-04-29 05:03:40,323][BaseTrainer][INFO] - [Epoch 6/10, Iter 1795/3560] 2.3641743659973145, cross_entropy: 2.3641743659973145 +[2025-04-29 05:03:43,058][BaseTrainer][INFO] - [Epoch 6/10, Iter 1796/3560] 1.4811362028121948, cross_entropy: 1.4811362028121948 +[2025-04-29 05:03:44,022][BaseTrainer][INFO] - [Epoch 6/10, Iter 1797/3560] 2.68212628364563, cross_entropy: 2.68212628364563 +[2025-04-29 05:03:46,570][BaseTrainer][INFO] - [Epoch 6/10, Iter 1798/3560] 1.5384483337402344, cross_entropy: 1.5384483337402344 +[2025-04-29 05:03:47,574][BaseTrainer][INFO] - [Epoch 6/10, Iter 1799/3560] 1.6267035007476807, cross_entropy: 1.6267035007476807 +[2025-04-29 05:03:50,545][BaseTrainer][INFO] - [Epoch 6/10, Iter 1800/3560] 1.9854624271392822, cross_entropy: 1.9854624271392822 +[2025-04-29 05:03:51,504][BaseTrainer][INFO] - [Epoch 6/10, Iter 1801/3560] 1.7592153549194336, cross_entropy: 1.7592153549194336 +[2025-04-29 05:03:53,992][BaseTrainer][INFO] - [Epoch 6/10, Iter 1802/3560] 1.9226422309875488, cross_entropy: 1.9226422309875488 +[2025-04-29 05:03:54,923][BaseTrainer][INFO] - [Epoch 6/10, Iter 1803/3560] 3.2197914123535156, cross_entropy: 3.2197914123535156 +[2025-04-29 05:03:57,880][BaseTrainer][INFO] - [Epoch 6/10, Iter 1804/3560] 2.715463161468506, cross_entropy: 2.715463161468506 +[2025-04-29 05:03:58,779][BaseTrainer][INFO] - [Epoch 6/10, Iter 1805/3560] 2.7271060943603516, cross_entropy: 2.7271060943603516 +[2025-04-29 05:04:01,530][BaseTrainer][INFO] - [Epoch 6/10, Iter 1806/3560] 1.8733099699020386, cross_entropy: 1.8733099699020386 +[2025-04-29 05:04:02,489][BaseTrainer][INFO] - [Epoch 6/10, Iter 1807/3560] 3.331810474395752, cross_entropy: 3.331810474395752 +[2025-04-29 05:04:05,543][BaseTrainer][INFO] - [Epoch 6/10, Iter 1808/3560] 2.997641086578369, cross_entropy: 2.997641086578369 +[2025-04-29 05:04:06,483][BaseTrainer][INFO] - [Epoch 6/10, Iter 1809/3560] 2.4743552207946777, cross_entropy: 2.4743552207946777 +[2025-04-29 05:04:09,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 1810/3560] 2.502988815307617, cross_entropy: 2.502988815307617 +[2025-04-29 05:04:10,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 1811/3560] 1.8839690685272217, cross_entropy: 1.8839690685272217 +[2025-04-29 05:04:13,605][BaseTrainer][INFO] - [Epoch 6/10, Iter 1812/3560] 2.248572826385498, cross_entropy: 2.248572826385498 +[2025-04-29 05:04:14,524][BaseTrainer][INFO] - [Epoch 6/10, Iter 1813/3560] 2.000682830810547, cross_entropy: 2.000682830810547 +[2025-04-29 05:04:17,386][BaseTrainer][INFO] - [Epoch 6/10, Iter 1814/3560] 1.826507329940796, cross_entropy: 1.826507329940796 +[2025-04-29 05:04:18,290][BaseTrainer][INFO] - [Epoch 6/10, Iter 1815/3560] 3.2911460399627686, cross_entropy: 3.2911460399627686 +[2025-04-29 05:04:21,581][BaseTrainer][INFO] - [Epoch 6/10, Iter 1816/3560] 3.3663814067840576, cross_entropy: 3.3663814067840576 +[2025-04-29 05:04:22,473][BaseTrainer][INFO] - [Epoch 6/10, Iter 1817/3560] 1.5539464950561523, cross_entropy: 1.5539464950561523 +[2025-04-29 05:04:24,771][BaseTrainer][INFO] - [Epoch 6/10, Iter 1818/3560] 3.309741497039795, cross_entropy: 3.309741497039795 +[2025-04-29 05:04:25,659][BaseTrainer][INFO] - [Epoch 6/10, Iter 1819/3560] 1.7269155979156494, cross_entropy: 1.7269155979156494 +[2025-04-29 05:04:28,496][BaseTrainer][INFO] - [Epoch 6/10, Iter 1820/3560] 1.6471331119537354, cross_entropy: 1.6471331119537354 +[2025-04-29 05:04:29,357][BaseTrainer][INFO] - [Epoch 6/10, Iter 1821/3560] 1.4902427196502686, cross_entropy: 1.4902427196502686 +[2025-04-29 05:04:32,345][BaseTrainer][INFO] - [Epoch 6/10, Iter 1822/3560] 2.6735758781433105, cross_entropy: 2.6735758781433105 +[2025-04-29 05:04:33,205][BaseTrainer][INFO] - [Epoch 6/10, Iter 1823/3560] 1.433251142501831, cross_entropy: 1.433251142501831 +[2025-04-29 05:04:36,340][BaseTrainer][INFO] - [Epoch 6/10, Iter 1824/3560] 1.7472363710403442, cross_entropy: 1.7472363710403442 +[2025-04-29 05:04:37,224][BaseTrainer][INFO] - [Epoch 6/10, Iter 1825/3560] 3.4108877182006836, cross_entropy: 3.4108877182006836 +[2025-04-29 05:04:39,790][BaseTrainer][INFO] - [Epoch 6/10, Iter 1826/3560] 2.7976951599121094, cross_entropy: 2.7976951599121094 +[2025-04-29 05:04:40,662][BaseTrainer][INFO] - [Epoch 6/10, Iter 1827/3560] 2.3863446712493896, cross_entropy: 2.3863446712493896 +[2025-04-29 05:04:43,879][BaseTrainer][INFO] - [Epoch 6/10, Iter 1828/3560] 1.4353997707366943, cross_entropy: 1.4353997707366943 +[2025-04-29 05:04:44,764][BaseTrainer][INFO] - [Epoch 6/10, Iter 1829/3560] 3.080857753753662, cross_entropy: 3.080857753753662 +[2025-04-29 05:04:47,013][BaseTrainer][INFO] - [Epoch 6/10, Iter 1830/3560] 2.840397834777832, cross_entropy: 2.840397834777832 +[2025-04-29 05:04:47,873][BaseTrainer][INFO] - [Epoch 6/10, Iter 1831/3560] 2.384141445159912, cross_entropy: 2.384141445159912 +[2025-04-29 05:04:51,190][BaseTrainer][INFO] - [Epoch 6/10, Iter 1832/3560] 1.3466140031814575, cross_entropy: 1.3466140031814575 +[2025-04-29 05:04:52,049][BaseTrainer][INFO] - [Epoch 6/10, Iter 1833/3560] 3.362531900405884, cross_entropy: 3.362531900405884 +[2025-04-29 05:04:55,249][BaseTrainer][INFO] - [Epoch 6/10, Iter 1834/3560] 1.458680510520935, cross_entropy: 1.458680510520935 +[2025-04-29 05:04:56,137][BaseTrainer][INFO] - [Epoch 6/10, Iter 1835/3560] 1.6117417812347412, cross_entropy: 1.6117417812347412 +[2025-04-29 05:04:59,205][BaseTrainer][INFO] - [Epoch 6/10, Iter 1836/3560] 3.461536407470703, cross_entropy: 3.461536407470703 +[2025-04-29 05:05:00,064][BaseTrainer][INFO] - [Epoch 6/10, Iter 1837/3560] 3.299490451812744, cross_entropy: 3.299490451812744 +[2025-04-29 05:05:03,308][BaseTrainer][INFO] - [Epoch 6/10, Iter 1838/3560] 1.2293825149536133, cross_entropy: 1.2293825149536133 +[2025-04-29 05:05:04,196][BaseTrainer][INFO] - [Epoch 6/10, Iter 1839/3560] 3.4119820594787598, cross_entropy: 3.4119820594787598 +[2025-04-29 05:05:06,544][BaseTrainer][INFO] - [Epoch 6/10, Iter 1840/3560] 2.3543195724487305, cross_entropy: 2.3543195724487305 +[2025-04-29 05:05:07,443][BaseTrainer][INFO] - [Epoch 6/10, Iter 1841/3560] 1.9960271120071411, cross_entropy: 1.9960271120071411 +[2025-04-29 05:05:10,359][BaseTrainer][INFO] - [Epoch 6/10, Iter 1842/3560] 1.901190996170044, cross_entropy: 1.901190996170044 +[2025-04-29 05:05:11,243][BaseTrainer][INFO] - [Epoch 6/10, Iter 1843/3560] 3.405949592590332, cross_entropy: 3.405949592590332 +[2025-04-29 05:05:13,915][BaseTrainer][INFO] - [Epoch 6/10, Iter 1844/3560] 2.8350019454956055, cross_entropy: 2.8350019454956055 +[2025-04-29 05:05:14,776][BaseTrainer][INFO] - [Epoch 6/10, Iter 1845/3560] 2.9904544353485107, cross_entropy: 2.9904544353485107 +[2025-04-29 05:05:17,551][BaseTrainer][INFO] - [Epoch 6/10, Iter 1846/3560] 2.6253671646118164, cross_entropy: 2.6253671646118164 +[2025-04-29 05:05:18,439][BaseTrainer][INFO] - [Epoch 6/10, Iter 1847/3560] 1.2261121273040771, cross_entropy: 1.2261121273040771 +[2025-04-29 05:05:21,192][BaseTrainer][INFO] - [Epoch 6/10, Iter 1848/3560] 1.8501700162887573, cross_entropy: 1.8501700162887573 +[2025-04-29 05:05:22,081][BaseTrainer][INFO] - [Epoch 6/10, Iter 1849/3560] 2.406346321105957, cross_entropy: 2.406346321105957 +[2025-04-29 05:05:24,772][BaseTrainer][INFO] - [Epoch 6/10, Iter 1850/3560] 1.3728141784667969, cross_entropy: 1.3728141784667969 +[2025-04-29 05:05:25,632][BaseTrainer][INFO] - [Epoch 6/10, Iter 1851/3560] 3.079146385192871, cross_entropy: 3.079146385192871 +[2025-04-29 05:05:28,173][BaseTrainer][INFO] - [Epoch 6/10, Iter 1852/3560] 1.9265238046646118, cross_entropy: 1.9265238046646118 +[2025-04-29 05:05:29,057][BaseTrainer][INFO] - [Epoch 6/10, Iter 1853/3560] 1.904861569404602, cross_entropy: 1.904861569404602 +[2025-04-29 05:05:31,788][BaseTrainer][INFO] - [Epoch 6/10, Iter 1854/3560] 1.3429408073425293, cross_entropy: 1.3429408073425293 +[2025-04-29 05:05:32,674][BaseTrainer][INFO] - [Epoch 6/10, Iter 1855/3560] 3.386636257171631, cross_entropy: 3.386636257171631 +[2025-04-29 05:05:35,821][BaseTrainer][INFO] - [Epoch 6/10, Iter 1856/3560] 2.088840961456299, cross_entropy: 2.088840961456299 +[2025-04-29 05:05:36,708][BaseTrainer][INFO] - [Epoch 6/10, Iter 1857/3560] 2.9932475090026855, cross_entropy: 2.9932475090026855 +[2025-04-29 05:05:39,995][BaseTrainer][INFO] - [Epoch 6/10, Iter 1858/3560] 3.477942943572998, cross_entropy: 3.477942943572998 +[2025-04-29 05:05:40,877][BaseTrainer][INFO] - [Epoch 6/10, Iter 1859/3560] 1.7484815120697021, cross_entropy: 1.7484815120697021 +[2025-04-29 05:05:44,254][BaseTrainer][INFO] - [Epoch 6/10, Iter 1860/3560] 2.6355791091918945, cross_entropy: 2.6355791091918945 +[2025-04-29 05:05:45,138][BaseTrainer][INFO] - [Epoch 6/10, Iter 1861/3560] 1.911025047302246, cross_entropy: 1.911025047302246 +[2025-04-29 05:05:47,392][BaseTrainer][INFO] - [Epoch 6/10, Iter 1862/3560] 1.6995965242385864, cross_entropy: 1.6995965242385864 +[2025-04-29 05:05:48,275][BaseTrainer][INFO] - [Epoch 6/10, Iter 1863/3560] 2.3149425983428955, cross_entropy: 2.3149425983428955 +[2025-04-29 05:05:51,094][BaseTrainer][INFO] - [Epoch 6/10, Iter 1864/3560] 1.9934030771255493, cross_entropy: 1.9934030771255493 +[2025-04-29 05:05:51,988][BaseTrainer][INFO] - [Epoch 6/10, Iter 1865/3560] 2.929260492324829, cross_entropy: 2.929260492324829 +[2025-04-29 05:05:54,817][BaseTrainer][INFO] - [Epoch 6/10, Iter 1866/3560] 1.8460572957992554, cross_entropy: 1.8460572957992554 +[2025-04-29 05:05:55,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1867/3560] 3.583064556121826, cross_entropy: 3.583064556121826 +[2025-04-29 05:05:58,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 1868/3560] 1.6467037200927734, cross_entropy: 1.6467037200927734 +[2025-04-29 05:05:59,471][BaseTrainer][INFO] - [Epoch 6/10, Iter 1869/3560] 1.6490466594696045, cross_entropy: 1.6490466594696045 +[2025-04-29 05:06:02,594][BaseTrainer][INFO] - [Epoch 6/10, Iter 1870/3560] 1.438263177871704, cross_entropy: 1.438263177871704 +[2025-04-29 05:06:03,476][BaseTrainer][INFO] - [Epoch 6/10, Iter 1871/3560] 1.3307112455368042, cross_entropy: 1.3307112455368042 +[2025-04-29 05:06:06,145][BaseTrainer][INFO] - [Epoch 6/10, Iter 1872/3560] 1.2372779846191406, cross_entropy: 1.2372779846191406 +[2025-04-29 05:06:07,027][BaseTrainer][INFO] - [Epoch 6/10, Iter 1873/3560] 1.976090431213379, cross_entropy: 1.976090431213379 +[2025-04-29 05:06:09,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 1874/3560] 2.716510772705078, cross_entropy: 2.716510772705078 +[2025-04-29 05:06:10,649][BaseTrainer][INFO] - [Epoch 6/10, Iter 1875/3560] 2.4989235401153564, cross_entropy: 2.4989235401153564 +[2025-04-29 05:06:14,348][BaseTrainer][INFO] - [Epoch 6/10, Iter 1876/3560] 3.179107904434204, cross_entropy: 3.179107904434204 +[2025-04-29 05:06:15,231][BaseTrainer][INFO] - [Epoch 6/10, Iter 1877/3560] 1.3396540880203247, cross_entropy: 1.3396540880203247 +[2025-04-29 05:06:17,730][BaseTrainer][INFO] - [Epoch 6/10, Iter 1878/3560] 2.1352813243865967, cross_entropy: 2.1352813243865967 +[2025-04-29 05:06:18,610][BaseTrainer][INFO] - [Epoch 6/10, Iter 1879/3560] 1.5210208892822266, cross_entropy: 1.5210208892822266 +[2025-04-29 05:06:21,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1880/3560] 1.5728687047958374, cross_entropy: 1.5728687047958374 +[2025-04-29 05:06:22,113][BaseTrainer][INFO] - [Epoch 6/10, Iter 1881/3560] 1.799271821975708, cross_entropy: 1.799271821975708 +[2025-04-29 05:06:25,313][BaseTrainer][INFO] - [Epoch 6/10, Iter 1882/3560] 3.394562005996704, cross_entropy: 3.394562005996704 +[2025-04-29 05:06:26,169][BaseTrainer][INFO] - [Epoch 6/10, Iter 1883/3560] 1.5226662158966064, cross_entropy: 1.5226662158966064 +[2025-04-29 05:06:28,909][BaseTrainer][INFO] - [Epoch 6/10, Iter 1884/3560] 2.2357115745544434, cross_entropy: 2.2357115745544434 +[2025-04-29 05:06:29,779][BaseTrainer][INFO] - [Epoch 6/10, Iter 1885/3560] 1.3699541091918945, cross_entropy: 1.3699541091918945 +[2025-04-29 05:06:33,323][BaseTrainer][INFO] - [Epoch 6/10, Iter 1886/3560] 1.42897629737854, cross_entropy: 1.42897629737854 +[2025-04-29 05:06:34,223][BaseTrainer][INFO] - [Epoch 6/10, Iter 1887/3560] 3.020545721054077, cross_entropy: 3.020545721054077 +[2025-04-29 05:06:36,789][BaseTrainer][INFO] - [Epoch 6/10, Iter 1888/3560] 1.7873409986495972, cross_entropy: 1.7873409986495972 +[2025-04-29 05:06:37,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 1889/3560] 1.2520533800125122, cross_entropy: 1.2520533800125122 +[2025-04-29 05:06:40,528][BaseTrainer][INFO] - [Epoch 6/10, Iter 1890/3560] 1.5498319864273071, cross_entropy: 1.5498319864273071 +[2025-04-29 05:06:41,447][BaseTrainer][INFO] - [Epoch 6/10, Iter 1891/3560] 1.362663984298706, cross_entropy: 1.362663984298706 +[2025-04-29 05:06:44,297][BaseTrainer][INFO] - [Epoch 6/10, Iter 1892/3560] 1.3966343402862549, cross_entropy: 1.3966343402862549 +[2025-04-29 05:06:45,244][BaseTrainer][INFO] - [Epoch 6/10, Iter 1893/3560] 2.4907355308532715, cross_entropy: 2.4907355308532715 +[2025-04-29 05:06:48,589][BaseTrainer][INFO] - [Epoch 6/10, Iter 1894/3560] 3.1574244499206543, cross_entropy: 3.1574244499206543 +[2025-04-29 05:06:49,473][BaseTrainer][INFO] - [Epoch 6/10, Iter 1895/3560] 2.3922781944274902, cross_entropy: 2.3922781944274902 +[2025-04-29 05:06:52,128][BaseTrainer][INFO] - [Epoch 6/10, Iter 1896/3560] 3.4251065254211426, cross_entropy: 3.4251065254211426 +[2025-04-29 05:06:52,987][BaseTrainer][INFO] - [Epoch 6/10, Iter 1897/3560] 1.8023676872253418, cross_entropy: 1.8023676872253418 +[2025-04-29 05:06:56,327][BaseTrainer][INFO] - [Epoch 6/10, Iter 1898/3560] 3.449728488922119, cross_entropy: 3.449728488922119 +[2025-04-29 05:06:57,224][BaseTrainer][INFO] - [Epoch 6/10, Iter 1899/3560] 1.80672287940979, cross_entropy: 1.80672287940979 +[2025-04-29 05:06:59,767][BaseTrainer][INFO] - [Epoch 6/10, Iter 1900/3560] 2.0488505363464355, cross_entropy: 2.0488505363464355 +[2025-04-29 05:07:00,684][BaseTrainer][INFO] - [Epoch 6/10, Iter 1901/3560] 1.669118881225586, cross_entropy: 1.669118881225586 +[2025-04-29 05:07:03,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 1902/3560] 1.7558326721191406, cross_entropy: 1.7558326721191406 +[2025-04-29 05:07:04,500][BaseTrainer][INFO] - [Epoch 6/10, Iter 1903/3560] 2.0361251831054688, cross_entropy: 2.0361251831054688 +[2025-04-29 05:07:07,072][BaseTrainer][INFO] - [Epoch 6/10, Iter 1904/3560] 3.3885302543640137, cross_entropy: 3.3885302543640137 +[2025-04-29 05:07:08,022][BaseTrainer][INFO] - [Epoch 6/10, Iter 1905/3560] 1.6095595359802246, cross_entropy: 1.6095595359802246 +[2025-04-29 05:07:10,943][BaseTrainer][INFO] - [Epoch 6/10, Iter 1906/3560] 1.5837100744247437, cross_entropy: 1.5837100744247437 +[2025-04-29 05:07:11,844][BaseTrainer][INFO] - [Epoch 6/10, Iter 1907/3560] 3.698331594467163, cross_entropy: 3.698331594467163 +[2025-04-29 05:07:14,862][BaseTrainer][INFO] - [Epoch 6/10, Iter 1908/3560] 3.0964255332946777, cross_entropy: 3.0964255332946777 +[2025-04-29 05:07:15,828][BaseTrainer][INFO] - [Epoch 6/10, Iter 1909/3560] 3.1022725105285645, cross_entropy: 3.1022725105285645 +[2025-04-29 05:07:18,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1910/3560] 3.577653408050537, cross_entropy: 3.577653408050537 +[2025-04-29 05:07:19,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 1911/3560] 2.50380277633667, cross_entropy: 2.50380277633667 +[2025-04-29 05:07:22,786][BaseTrainer][INFO] - [Epoch 6/10, Iter 1912/3560] 1.8377525806427002, cross_entropy: 1.8377525806427002 +[2025-04-29 05:07:24,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 1913/3560] 1.7866120338439941, cross_entropy: 1.7866120338439941 +[2025-04-29 05:07:26,185][BaseTrainer][INFO] - [Epoch 6/10, Iter 1914/3560] 3.464480400085449, cross_entropy: 3.464480400085449 +[2025-04-29 05:07:28,741][BaseTrainer][INFO] - [Epoch 6/10, Iter 1915/3560] 1.6076788902282715, cross_entropy: 1.6076788902282715 +[2025-04-29 05:07:30,284][BaseTrainer][INFO] - [Epoch 6/10, Iter 1916/3560] 2.282313585281372, cross_entropy: 2.282313585281372 +[2025-04-29 05:07:32,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 1917/3560] 3.094320774078369, cross_entropy: 3.094320774078369 +[2025-04-29 05:07:34,028][BaseTrainer][INFO] - [Epoch 6/10, Iter 1918/3560] 1.4496057033538818, cross_entropy: 1.4496057033538818 +[2025-04-29 05:07:35,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1919/3560] 3.47658371925354, cross_entropy: 3.47658371925354 +[2025-04-29 05:07:37,994][BaseTrainer][INFO] - [Epoch 6/10, Iter 1920/3560] 3.271228551864624, cross_entropy: 3.271228551864624 +[2025-04-29 05:07:39,403][BaseTrainer][INFO] - [Epoch 6/10, Iter 1921/3560] 2.0051252841949463, cross_entropy: 2.0051252841949463 +[2025-04-29 05:07:41,322][BaseTrainer][INFO] - [Epoch 6/10, Iter 1922/3560] 2.710801601409912, cross_entropy: 2.710801601409912 +[2025-04-29 05:07:43,602][BaseTrainer][INFO] - [Epoch 6/10, Iter 1923/3560] 2.961487054824829, cross_entropy: 2.961487054824829 +[2025-04-29 05:07:45,182][BaseTrainer][INFO] - [Epoch 6/10, Iter 1924/3560] 1.6379203796386719, cross_entropy: 1.6379203796386719 +[2025-04-29 05:07:47,446][BaseTrainer][INFO] - [Epoch 6/10, Iter 1925/3560] 1.238270878791809, cross_entropy: 1.238270878791809 +[2025-04-29 05:07:50,699][BaseTrainer][INFO] - [Epoch 6/10, Iter 1926/3560] 1.8664988279342651, cross_entropy: 1.8664988279342651 +[2025-04-29 05:07:51,558][BaseTrainer][INFO] - [Epoch 6/10, Iter 1927/3560] 2.8566477298736572, cross_entropy: 2.8566477298736572 +[2025-04-29 05:07:54,369][BaseTrainer][INFO] - [Epoch 6/10, Iter 1928/3560] 3.228990077972412, cross_entropy: 3.228990077972412 +[2025-04-29 05:07:55,257][BaseTrainer][INFO] - [Epoch 6/10, Iter 1929/3560] 2.361330032348633, cross_entropy: 2.361330032348633 +[2025-04-29 05:07:58,213][BaseTrainer][INFO] - [Epoch 6/10, Iter 1930/3560] 3.2510459423065186, cross_entropy: 3.2510459423065186 +[2025-04-29 05:07:59,073][BaseTrainer][INFO] - [Epoch 6/10, Iter 1931/3560] 2.8566274642944336, cross_entropy: 2.8566274642944336 +[2025-04-29 05:08:02,010][BaseTrainer][INFO] - [Epoch 6/10, Iter 1932/3560] 2.234567642211914, cross_entropy: 2.234567642211914 +[2025-04-29 05:08:02,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 1933/3560] 1.7971934080123901, cross_entropy: 1.7971934080123901 +[2025-04-29 05:08:05,714][BaseTrainer][INFO] - [Epoch 6/10, Iter 1934/3560] 2.1452627182006836, cross_entropy: 2.1452627182006836 +[2025-04-29 05:08:06,571][BaseTrainer][INFO] - [Epoch 6/10, Iter 1935/3560] 1.8699015378952026, cross_entropy: 1.8699015378952026 +[2025-04-29 05:08:09,561][BaseTrainer][INFO] - [Epoch 6/10, Iter 1936/3560] 1.7362167835235596, cross_entropy: 1.7362167835235596 +[2025-04-29 05:08:10,519][BaseTrainer][INFO] - [Epoch 6/10, Iter 1937/3560] 3.4993550777435303, cross_entropy: 3.4993550777435303 +[2025-04-29 05:08:13,229][BaseTrainer][INFO] - [Epoch 6/10, Iter 1938/3560] 3.101207733154297, cross_entropy: 3.101207733154297 +[2025-04-29 05:08:14,290][BaseTrainer][INFO] - [Epoch 6/10, Iter 1939/3560] 1.4025192260742188, cross_entropy: 1.4025192260742188 +[2025-04-29 05:08:16,639][BaseTrainer][INFO] - [Epoch 6/10, Iter 1940/3560] 1.957845687866211, cross_entropy: 1.957845687866211 +[2025-04-29 05:08:18,524][BaseTrainer][INFO] - [Epoch 6/10, Iter 1941/3560] 3.212111473083496, cross_entropy: 3.212111473083496 +[2025-04-29 05:08:19,833][BaseTrainer][INFO] - [Epoch 6/10, Iter 1942/3560] 2.9062976837158203, cross_entropy: 2.9062976837158203 +[2025-04-29 05:08:23,220][BaseTrainer][INFO] - [Epoch 6/10, Iter 1943/3560] 3.2343392372131348, cross_entropy: 3.2343392372131348 +[2025-04-29 05:08:24,118][BaseTrainer][INFO] - [Epoch 6/10, Iter 1944/3560] 2.419984817504883, cross_entropy: 2.419984817504883 +[2025-04-29 05:08:27,219][BaseTrainer][INFO] - [Epoch 6/10, Iter 1945/3560] 3.16719651222229, cross_entropy: 3.16719651222229 +[2025-04-29 05:08:28,105][BaseTrainer][INFO] - [Epoch 6/10, Iter 1946/3560] 2.6565465927124023, cross_entropy: 2.6565465927124023 +[2025-04-29 05:08:31,523][BaseTrainer][INFO] - [Epoch 6/10, Iter 1947/3560] 3.145232677459717, cross_entropy: 3.145232677459717 +[2025-04-29 05:08:32,412][BaseTrainer][INFO] - [Epoch 6/10, Iter 1948/3560] 2.0057098865509033, cross_entropy: 2.0057098865509033 +[2025-04-29 05:08:36,312][BaseTrainer][INFO] - [Epoch 6/10, Iter 1949/3560] 3.179150104522705, cross_entropy: 3.179150104522705 +[2025-04-29 05:08:37,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 1950/3560] 1.9967234134674072, cross_entropy: 1.9967234134674072 +[2025-04-29 05:08:40,011][BaseTrainer][INFO] - [Epoch 6/10, Iter 1951/3560] 3.4158830642700195, cross_entropy: 3.4158830642700195 +[2025-04-29 05:08:40,870][BaseTrainer][INFO] - [Epoch 6/10, Iter 1952/3560] 1.7258408069610596, cross_entropy: 1.7258408069610596 +[2025-04-29 05:08:43,547][BaseTrainer][INFO] - [Epoch 6/10, Iter 1953/3560] 2.3857197761535645, cross_entropy: 2.3857197761535645 +[2025-04-29 05:08:44,406][BaseTrainer][INFO] - [Epoch 6/10, Iter 1954/3560] 2.25130295753479, cross_entropy: 2.25130295753479 +[2025-04-29 05:08:47,400][BaseTrainer][INFO] - [Epoch 6/10, Iter 1955/3560] 3.4357473850250244, cross_entropy: 3.4357473850250244 +[2025-04-29 05:08:48,260][BaseTrainer][INFO] - [Epoch 6/10, Iter 1956/3560] 2.234858512878418, cross_entropy: 2.234858512878418 +[2025-04-29 05:08:51,472][BaseTrainer][INFO] - [Epoch 6/10, Iter 1957/3560] 1.177680492401123, cross_entropy: 1.177680492401123 +[2025-04-29 05:08:52,356][BaseTrainer][INFO] - [Epoch 6/10, Iter 1958/3560] 2.4078192710876465, cross_entropy: 2.4078192710876465 +[2025-04-29 05:08:55,726][BaseTrainer][INFO] - [Epoch 6/10, Iter 1959/3560] 1.6314740180969238, cross_entropy: 1.6314740180969238 +[2025-04-29 05:08:56,586][BaseTrainer][INFO] - [Epoch 6/10, Iter 1960/3560] 2.3064169883728027, cross_entropy: 2.3064169883728027 +[2025-04-29 05:08:59,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 1961/3560] 2.034363269805908, cross_entropy: 2.034363269805908 +[2025-04-29 05:09:00,619][BaseTrainer][INFO] - [Epoch 6/10, Iter 1962/3560] 1.9961796998977661, cross_entropy: 1.9961796998977661 +[2025-04-29 05:09:03,120][BaseTrainer][INFO] - [Epoch 6/10, Iter 1963/3560] 1.9035755395889282, cross_entropy: 1.9035755395889282 +[2025-04-29 05:09:04,009][BaseTrainer][INFO] - [Epoch 6/10, Iter 1964/3560] 1.347947597503662, cross_entropy: 1.347947597503662 +[2025-04-29 05:09:07,096][BaseTrainer][INFO] - [Epoch 6/10, Iter 1965/3560] 1.4904097318649292, cross_entropy: 1.4904097318649292 +[2025-04-29 05:09:07,983][BaseTrainer][INFO] - [Epoch 6/10, Iter 1966/3560] 1.545517921447754, cross_entropy: 1.545517921447754 +[2025-04-29 05:09:10,478][BaseTrainer][INFO] - [Epoch 6/10, Iter 1967/3560] 2.813286304473877, cross_entropy: 2.813286304473877 +[2025-04-29 05:09:11,336][BaseTrainer][INFO] - [Epoch 6/10, Iter 1968/3560] 3.040174722671509, cross_entropy: 3.040174722671509 +[2025-04-29 05:09:14,136][BaseTrainer][INFO] - [Epoch 6/10, Iter 1969/3560] 1.442901611328125, cross_entropy: 1.442901611328125 +[2025-04-29 05:09:14,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 1970/3560] 3.293062448501587, cross_entropy: 3.293062448501587 +[2025-04-29 05:09:18,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 1971/3560] 1.2343714237213135, cross_entropy: 1.2343714237213135 +[2025-04-29 05:09:19,078][BaseTrainer][INFO] - [Epoch 6/10, Iter 1972/3560] 2.9599411487579346, cross_entropy: 2.9599411487579346 +[2025-04-29 05:09:22,070][BaseTrainer][INFO] - [Epoch 6/10, Iter 1973/3560] 1.5478211641311646, cross_entropy: 1.5478211641311646 +[2025-04-29 05:09:22,953][BaseTrainer][INFO] - [Epoch 6/10, Iter 1974/3560] 1.9893510341644287, cross_entropy: 1.9893510341644287 +[2025-04-29 05:09:25,800][BaseTrainer][INFO] - [Epoch 6/10, Iter 1975/3560] 1.8434252738952637, cross_entropy: 1.8434252738952637 +[2025-04-29 05:09:26,681][BaseTrainer][INFO] - [Epoch 6/10, Iter 1976/3560] 3.085150957107544, cross_entropy: 3.085150957107544 +[2025-04-29 05:09:29,642][BaseTrainer][INFO] - [Epoch 6/10, Iter 1977/3560] 1.6729693412780762, cross_entropy: 1.6729693412780762 +[2025-04-29 05:09:30,526][BaseTrainer][INFO] - [Epoch 6/10, Iter 1978/3560] 1.881345272064209, cross_entropy: 1.881345272064209 +[2025-04-29 05:09:33,221][BaseTrainer][INFO] - [Epoch 6/10, Iter 1979/3560] 3.499560832977295, cross_entropy: 3.499560832977295 +[2025-04-29 05:09:34,117][BaseTrainer][INFO] - [Epoch 6/10, Iter 1980/3560] 3.189833879470825, cross_entropy: 3.189833879470825 +[2025-04-29 05:09:36,857][BaseTrainer][INFO] - [Epoch 6/10, Iter 1981/3560] 2.262049913406372, cross_entropy: 2.262049913406372 +[2025-04-29 05:09:37,739][BaseTrainer][INFO] - [Epoch 6/10, Iter 1982/3560] 1.4167202711105347, cross_entropy: 1.4167202711105347 +[2025-04-29 05:09:40,993][BaseTrainer][INFO] - [Epoch 6/10, Iter 1983/3560] 1.6600592136383057, cross_entropy: 1.6600592136383057 +[2025-04-29 05:09:41,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 1984/3560] 3.0192370414733887, cross_entropy: 3.0192370414733887 +[2025-04-29 05:09:44,569][BaseTrainer][INFO] - [Epoch 6/10, Iter 1985/3560] 1.6010991334915161, cross_entropy: 1.6010991334915161 +[2025-04-29 05:09:45,459][BaseTrainer][INFO] - [Epoch 6/10, Iter 1986/3560] 3.3753561973571777, cross_entropy: 3.3753561973571777 +[2025-04-29 05:09:47,674][BaseTrainer][INFO] - [Epoch 6/10, Iter 1987/3560] 2.5136823654174805, cross_entropy: 2.5136823654174805 +[2025-04-29 05:09:48,561][BaseTrainer][INFO] - [Epoch 6/10, Iter 1988/3560] 1.3925507068634033, cross_entropy: 1.3925507068634033 +[2025-04-29 05:09:51,353][BaseTrainer][INFO] - [Epoch 6/10, Iter 1989/3560] 2.386585235595703, cross_entropy: 2.386585235595703 +[2025-04-29 05:09:52,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 1990/3560] 1.7502188682556152, cross_entropy: 1.7502188682556152 +[2025-04-29 05:09:55,721][BaseTrainer][INFO] - [Epoch 6/10, Iter 1991/3560] 3.418513059616089, cross_entropy: 3.418513059616089 +[2025-04-29 05:09:56,600][BaseTrainer][INFO] - [Epoch 6/10, Iter 1992/3560] 3.439605712890625, cross_entropy: 3.439605712890625 +[2025-04-29 05:09:59,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 1993/3560] 3.0083963871002197, cross_entropy: 3.0083963871002197 +[2025-04-29 05:10:00,302][BaseTrainer][INFO] - [Epoch 6/10, Iter 1994/3560] 1.525831937789917, cross_entropy: 1.525831937789917 +[2025-04-29 05:10:03,061][BaseTrainer][INFO] - [Epoch 6/10, Iter 1995/3560] 2.451608419418335, cross_entropy: 2.451608419418335 +[2025-04-29 05:10:03,950][BaseTrainer][INFO] - [Epoch 6/10, Iter 1996/3560] 2.198117971420288, cross_entropy: 2.198117971420288 +[2025-04-29 05:10:06,664][BaseTrainer][INFO] - [Epoch 6/10, Iter 1997/3560] 1.1695770025253296, cross_entropy: 1.1695770025253296 +[2025-04-29 05:10:07,546][BaseTrainer][INFO] - [Epoch 6/10, Iter 1998/3560] 2.1355059146881104, cross_entropy: 2.1355059146881104 +[2025-04-29 05:10:11,501][BaseTrainer][INFO] - [Epoch 6/10, Iter 1999/3560] 2.532221794128418, cross_entropy: 2.532221794128418 +[2025-04-29 05:10:12,357][BaseTrainer][INFO] - [Epoch 6/10, Iter 2000/3560] 3.0695314407348633, cross_entropy: 3.0695314407348633 +[2025-04-29 05:10:13,099][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/iteration2000.pth. +[2025-04-29 05:10:14,723][BaseTrainer][INFO] - [Epoch 6/10, Iter 2001/3560] 1.6692233085632324, cross_entropy: 1.6692233085632324 +[2025-04-29 05:10:15,609][BaseTrainer][INFO] - [Epoch 6/10, Iter 2002/3560] 2.929852247238159, cross_entropy: 2.929852247238159 +[2025-04-29 05:10:18,693][BaseTrainer][INFO] - [Epoch 6/10, Iter 2003/3560] 1.2573683261871338, cross_entropy: 1.2573683261871338 +[2025-04-29 05:10:19,579][BaseTrainer][INFO] - [Epoch 6/10, Iter 2004/3560] 1.814809799194336, cross_entropy: 1.814809799194336 +[2025-04-29 05:10:22,519][BaseTrainer][INFO] - [Epoch 6/10, Iter 2005/3560] 3.254497528076172, cross_entropy: 3.254497528076172 +[2025-04-29 05:10:23,376][BaseTrainer][INFO] - [Epoch 6/10, Iter 2006/3560] 2.351016044616699, cross_entropy: 2.351016044616699 +[2025-04-29 05:10:26,667][BaseTrainer][INFO] - [Epoch 6/10, Iter 2007/3560] 1.8114675283432007, cross_entropy: 1.8114675283432007 +[2025-04-29 05:10:27,554][BaseTrainer][INFO] - [Epoch 6/10, Iter 2008/3560] 2.813314437866211, cross_entropy: 2.813314437866211 +[2025-04-29 05:10:31,352][BaseTrainer][INFO] - [Epoch 6/10, Iter 2009/3560] 2.9254424571990967, cross_entropy: 2.9254424571990967 +[2025-04-29 05:10:32,240][BaseTrainer][INFO] - [Epoch 6/10, Iter 2010/3560] 1.2361208200454712, cross_entropy: 1.2361208200454712 +[2025-04-29 05:10:35,264][BaseTrainer][INFO] - [Epoch 6/10, Iter 2011/3560] 2.1520118713378906, cross_entropy: 2.1520118713378906 +[2025-04-29 05:10:36,150][BaseTrainer][INFO] - [Epoch 6/10, Iter 2012/3560] 1.8566012382507324, cross_entropy: 1.8566012382507324 +[2025-04-29 05:10:38,735][BaseTrainer][INFO] - [Epoch 6/10, Iter 2013/3560] 2.116427421569824, cross_entropy: 2.116427421569824 +[2025-04-29 05:10:39,592][BaseTrainer][INFO] - [Epoch 6/10, Iter 2014/3560] 1.5702214241027832, cross_entropy: 1.5702214241027832 +[2025-04-29 05:10:42,516][BaseTrainer][INFO] - [Epoch 6/10, Iter 2015/3560] 2.7223267555236816, cross_entropy: 2.7223267555236816 +[2025-04-29 05:10:43,402][BaseTrainer][INFO] - [Epoch 6/10, Iter 2016/3560] 1.7274736166000366, cross_entropy: 1.7274736166000366 +[2025-04-29 05:10:46,929][BaseTrainer][INFO] - [Epoch 6/10, Iter 2017/3560] 2.53403902053833, cross_entropy: 2.53403902053833 +[2025-04-29 05:10:47,813][BaseTrainer][INFO] - [Epoch 6/10, Iter 2018/3560] 1.8879520893096924, cross_entropy: 1.8879520893096924 +[2025-04-29 05:10:50,917][BaseTrainer][INFO] - [Epoch 6/10, Iter 2019/3560] 2.991522789001465, cross_entropy: 2.991522789001465 +[2025-04-29 05:10:51,775][BaseTrainer][INFO] - [Epoch 6/10, Iter 2020/3560] 2.4013729095458984, cross_entropy: 2.4013729095458984 +[2025-04-29 05:10:54,973][BaseTrainer][INFO] - [Epoch 6/10, Iter 2021/3560] 1.634486436843872, cross_entropy: 1.634486436843872 +[2025-04-29 05:10:55,856][BaseTrainer][INFO] - [Epoch 6/10, Iter 2022/3560] 1.7156763076782227, cross_entropy: 1.7156763076782227 +[2025-04-29 05:10:58,745][BaseTrainer][INFO] - [Epoch 6/10, Iter 2023/3560] 3.5520715713500977, cross_entropy: 3.5520715713500977 +[2025-04-29 05:10:59,602][BaseTrainer][INFO] - [Epoch 6/10, Iter 2024/3560] 2.4328298568725586, cross_entropy: 2.4328298568725586 +[2025-04-29 05:11:02,726][BaseTrainer][INFO] - [Epoch 6/10, Iter 2025/3560] 1.4774091243743896, cross_entropy: 1.4774091243743896 +[2025-04-29 05:11:03,605][BaseTrainer][INFO] - [Epoch 6/10, Iter 2026/3560] 2.6145691871643066, cross_entropy: 2.6145691871643066 +[2025-04-29 05:11:06,421][BaseTrainer][INFO] - [Epoch 6/10, Iter 2027/3560] 1.5678638219833374, cross_entropy: 1.5678638219833374 +[2025-04-29 05:11:07,279][BaseTrainer][INFO] - [Epoch 6/10, Iter 2028/3560] 1.615056037902832, cross_entropy: 1.615056037902832 +[2025-04-29 05:11:10,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 2029/3560] 1.9055495262145996, cross_entropy: 1.9055495262145996 +[2025-04-29 05:11:11,432][BaseTrainer][INFO] - [Epoch 6/10, Iter 2030/3560] 2.126361846923828, cross_entropy: 2.126361846923828 +[2025-04-29 05:11:14,428][BaseTrainer][INFO] - [Epoch 6/10, Iter 2031/3560] 2.649627685546875, cross_entropy: 2.649627685546875 +[2025-04-29 05:11:15,315][BaseTrainer][INFO] - [Epoch 6/10, Iter 2032/3560] 3.318181037902832, cross_entropy: 3.318181037902832 +[2025-04-29 05:11:18,332][BaseTrainer][INFO] - [Epoch 6/10, Iter 2033/3560] 1.4523577690124512, cross_entropy: 1.4523577690124512 +[2025-04-29 05:11:19,215][BaseTrainer][INFO] - [Epoch 6/10, Iter 2034/3560] 2.5331852436065674, cross_entropy: 2.5331852436065674 +[2025-04-29 05:11:22,068][BaseTrainer][INFO] - [Epoch 6/10, Iter 2035/3560] 1.8108621835708618, cross_entropy: 1.8108621835708618 +[2025-04-29 05:11:22,953][BaseTrainer][INFO] - [Epoch 6/10, Iter 2036/3560] 1.3980276584625244, cross_entropy: 1.3980276584625244 +[2025-04-29 05:11:25,181][BaseTrainer][INFO] - [Epoch 6/10, Iter 2037/3560] 3.0740747451782227, cross_entropy: 3.0740747451782227 +[2025-04-29 05:11:26,055][BaseTrainer][INFO] - [Epoch 6/10, Iter 2038/3560] 2.2130236625671387, cross_entropy: 2.2130236625671387 +[2025-04-29 05:11:28,749][BaseTrainer][INFO] - [Epoch 6/10, Iter 2039/3560] 2.804028034210205, cross_entropy: 2.804028034210205 +[2025-04-29 05:11:29,629][BaseTrainer][INFO] - [Epoch 6/10, Iter 2040/3560] 2.110321521759033, cross_entropy: 2.110321521759033 +[2025-04-29 05:11:32,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 2041/3560] 2.2490434646606445, cross_entropy: 2.2490434646606445 +[2025-04-29 05:11:33,728][BaseTrainer][INFO] - [Epoch 6/10, Iter 2042/3560] 2.9317259788513184, cross_entropy: 2.9317259788513184 +[2025-04-29 05:11:36,168][BaseTrainer][INFO] - [Epoch 6/10, Iter 2043/3560] 3.102339029312134, cross_entropy: 3.102339029312134 +[2025-04-29 05:11:37,052][BaseTrainer][INFO] - [Epoch 6/10, Iter 2044/3560] 2.8421623706817627, cross_entropy: 2.8421623706817627 +[2025-04-29 05:11:39,833][BaseTrainer][INFO] - [Epoch 6/10, Iter 2045/3560] 2.8460240364074707, cross_entropy: 2.8460240364074707 +[2025-04-29 05:11:40,691][BaseTrainer][INFO] - [Epoch 6/10, Iter 2046/3560] 3.3870882987976074, cross_entropy: 3.3870882987976074 +[2025-04-29 05:11:44,101][BaseTrainer][INFO] - [Epoch 6/10, Iter 2047/3560] 1.7389354705810547, cross_entropy: 1.7389354705810547 +[2025-04-29 05:11:44,957][BaseTrainer][INFO] - [Epoch 6/10, Iter 2048/3560] 2.41316556930542, cross_entropy: 2.41316556930542 +[2025-04-29 05:11:47,649][BaseTrainer][INFO] - [Epoch 6/10, Iter 2049/3560] 2.858144760131836, cross_entropy: 2.858144760131836 +[2025-04-29 05:11:48,533][BaseTrainer][INFO] - [Epoch 6/10, Iter 2050/3560] 2.1459460258483887, cross_entropy: 2.1459460258483887 +[2025-04-29 05:11:51,080][BaseTrainer][INFO] - [Epoch 6/10, Iter 2051/3560] 1.9225302934646606, cross_entropy: 1.9225302934646606 +[2025-04-29 05:11:51,966][BaseTrainer][INFO] - [Epoch 6/10, Iter 2052/3560] 1.7084336280822754, cross_entropy: 1.7084336280822754 +[2025-04-29 05:11:54,542][BaseTrainer][INFO] - [Epoch 6/10, Iter 2053/3560] 2.3616702556610107, cross_entropy: 2.3616702556610107 +[2025-04-29 05:11:55,429][BaseTrainer][INFO] - [Epoch 6/10, Iter 2054/3560] 2.928988218307495, cross_entropy: 2.928988218307495 +[2025-04-29 05:11:58,129][BaseTrainer][INFO] - [Epoch 6/10, Iter 2055/3560] 3.4640955924987793, cross_entropy: 3.4640955924987793 +[2025-04-29 05:11:58,986][BaseTrainer][INFO] - [Epoch 6/10, Iter 2056/3560] 2.078005790710449, cross_entropy: 2.078005790710449 +[2025-04-29 05:12:02,144][BaseTrainer][INFO] - [Epoch 6/10, Iter 2057/3560] 1.8139044046401978, cross_entropy: 1.8139044046401978 +[2025-04-29 05:12:03,027][BaseTrainer][INFO] - [Epoch 6/10, Iter 2058/3560] 2.97560715675354, cross_entropy: 2.97560715675354 +[2025-04-29 05:12:05,951][BaseTrainer][INFO] - [Epoch 6/10, Iter 2059/3560] 1.7852028608322144, cross_entropy: 1.7852028608322144 +[2025-04-29 05:12:06,838][BaseTrainer][INFO] - [Epoch 6/10, Iter 2060/3560] 2.103803873062134, cross_entropy: 2.103803873062134 +[2025-04-29 05:12:10,147][BaseTrainer][INFO] - [Epoch 6/10, Iter 2061/3560] 1.6072057485580444, cross_entropy: 1.6072057485580444 +[2025-04-29 05:12:11,007][BaseTrainer][INFO] - [Epoch 6/10, Iter 2062/3560] 1.2931838035583496, cross_entropy: 1.2931838035583496 +[2025-04-29 05:12:14,122][BaseTrainer][INFO] - [Epoch 6/10, Iter 2063/3560] 1.3573951721191406, cross_entropy: 1.3573951721191406 +[2025-04-29 05:12:14,984][BaseTrainer][INFO] - [Epoch 6/10, Iter 2064/3560] 2.447171688079834, cross_entropy: 2.447171688079834 +[2025-04-29 05:12:17,633][BaseTrainer][INFO] - [Epoch 6/10, Iter 2065/3560] 2.7386341094970703, cross_entropy: 2.7386341094970703 +[2025-04-29 05:12:18,491][BaseTrainer][INFO] - [Epoch 6/10, Iter 2066/3560] 1.523897647857666, cross_entropy: 1.523897647857666 +[2025-04-29 05:12:21,858][BaseTrainer][INFO] - [Epoch 6/10, Iter 2067/3560] 1.7572448253631592, cross_entropy: 1.7572448253631592 +[2025-04-29 05:12:22,720][BaseTrainer][INFO] - [Epoch 6/10, Iter 2068/3560] 3.1326515674591064, cross_entropy: 3.1326515674591064 +[2025-04-29 05:12:25,740][BaseTrainer][INFO] - [Epoch 6/10, Iter 2069/3560] 2.595569610595703, cross_entropy: 2.595569610595703 +[2025-04-29 05:12:26,620][BaseTrainer][INFO] - [Epoch 6/10, Iter 2070/3560] 1.8802993297576904, cross_entropy: 1.8802993297576904 +[2025-04-29 05:12:29,566][BaseTrainer][INFO] - [Epoch 6/10, Iter 2071/3560] 3.528639316558838, cross_entropy: 3.528639316558838 +[2025-04-29 05:12:30,424][BaseTrainer][INFO] - [Epoch 6/10, Iter 2072/3560] 2.1162657737731934, cross_entropy: 2.1162657737731934 +[2025-04-29 05:12:33,085][BaseTrainer][INFO] - [Epoch 6/10, Iter 2073/3560] 2.7662363052368164, cross_entropy: 2.7662363052368164 +[2025-04-29 05:12:33,968][BaseTrainer][INFO] - [Epoch 6/10, Iter 2074/3560] 2.984388828277588, cross_entropy: 2.984388828277588 +[2025-04-29 05:12:38,128][BaseTrainer][INFO] - [Epoch 6/10, Iter 2075/3560] 3.2129404544830322, cross_entropy: 3.2129404544830322 +[2025-04-29 05:12:38,986][BaseTrainer][INFO] - [Epoch 6/10, Iter 2076/3560] 3.1713356971740723, cross_entropy: 3.1713356971740723 +[2025-04-29 05:12:42,314][BaseTrainer][INFO] - [Epoch 6/10, Iter 2077/3560] 1.9961798191070557, cross_entropy: 1.9961798191070557 +[2025-04-29 05:12:43,188][BaseTrainer][INFO] - [Epoch 6/10, Iter 2078/3560] 3.3284597396850586, cross_entropy: 3.3284597396850586 +[2025-04-29 05:12:46,296][BaseTrainer][INFO] - [Epoch 6/10, Iter 2079/3560] 1.834330439567566, cross_entropy: 1.834330439567566 +[2025-04-29 05:12:47,172][BaseTrainer][INFO] - [Epoch 6/10, Iter 2080/3560] 1.9941177368164062, cross_entropy: 1.9941177368164062 +[2025-04-29 05:12:50,370][BaseTrainer][INFO] - [Epoch 6/10, Iter 2081/3560] 2.2137012481689453, cross_entropy: 2.2137012481689453 +[2025-04-29 05:12:51,250][BaseTrainer][INFO] - [Epoch 6/10, Iter 2082/3560] 3.2069473266601562, cross_entropy: 3.2069473266601562 +[2025-04-29 05:12:54,631][BaseTrainer][INFO] - [Epoch 6/10, Iter 2083/3560] 2.8906378746032715, cross_entropy: 2.8906378746032715 +[2025-04-29 05:12:55,513][BaseTrainer][INFO] - [Epoch 6/10, Iter 2084/3560] 1.9733223915100098, cross_entropy: 1.9733223915100098 +[2025-04-29 05:12:57,886][BaseTrainer][INFO] - [Epoch 6/10, Iter 2085/3560] 3.0595173835754395, cross_entropy: 3.0595173835754395 +[2025-04-29 05:12:58,780][BaseTrainer][INFO] - [Epoch 6/10, Iter 2086/3560] 2.786682605743408, cross_entropy: 2.786682605743408 +[2025-04-29 05:13:00,711][BaseTrainer][INFO] - [Epoch 6/10, Iter 2087/3560] 1.415076732635498, cross_entropy: 1.415076732635498 +[2025-04-29 05:13:01,598][BaseTrainer][INFO] - [Epoch 6/10, Iter 2088/3560] 2.440845251083374, cross_entropy: 2.440845251083374 +[2025-04-29 05:13:04,614][BaseTrainer][INFO] - [Epoch 6/10, Iter 2089/3560] 3.0392727851867676, cross_entropy: 3.0392727851867676 +[2025-04-29 05:13:05,505][BaseTrainer][INFO] - [Epoch 6/10, Iter 2090/3560] 1.4138212203979492, cross_entropy: 1.4138212203979492 +[2025-04-29 05:13:08,091][BaseTrainer][INFO] - [Epoch 6/10, Iter 2091/3560] 3.2298381328582764, cross_entropy: 3.2298381328582764 +[2025-04-29 05:13:08,980][BaseTrainer][INFO] - [Epoch 6/10, Iter 2092/3560] 1.1678352355957031, cross_entropy: 1.1678352355957031 +[2025-04-29 05:13:11,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 2093/3560] 2.7476065158843994, cross_entropy: 2.7476065158843994 +[2025-04-29 05:13:12,419][BaseTrainer][INFO] - [Epoch 6/10, Iter 2094/3560] 2.855062484741211, cross_entropy: 2.855062484741211 +[2025-04-29 05:13:15,017][BaseTrainer][INFO] - [Epoch 6/10, Iter 2095/3560] 2.976654529571533, cross_entropy: 2.976654529571533 +[2025-04-29 05:13:15,908][BaseTrainer][INFO] - [Epoch 6/10, Iter 2096/3560] 2.8770453929901123, cross_entropy: 2.8770453929901123 +[2025-04-29 05:13:18,968][BaseTrainer][INFO] - [Epoch 6/10, Iter 2097/3560] 2.9324276447296143, cross_entropy: 2.9324276447296143 +[2025-04-29 05:13:19,852][BaseTrainer][INFO] - [Epoch 6/10, Iter 2098/3560] 2.9046621322631836, cross_entropy: 2.9046621322631836 +[2025-04-29 05:13:22,407][BaseTrainer][INFO] - [Epoch 6/10, Iter 2099/3560] 2.936385154724121, cross_entropy: 2.936385154724121 +[2025-04-29 05:13:23,286][BaseTrainer][INFO] - [Epoch 6/10, Iter 2100/3560] 1.2558687925338745, cross_entropy: 1.2558687925338745 +[2025-04-29 05:13:26,569][BaseTrainer][INFO] - [Epoch 6/10, Iter 2101/3560] 3.234541416168213, cross_entropy: 3.234541416168213 +[2025-04-29 05:13:27,451][BaseTrainer][INFO] - [Epoch 6/10, Iter 2102/3560] 1.4848748445510864, cross_entropy: 1.4848748445510864 +[2025-04-29 05:13:29,821][BaseTrainer][INFO] - [Epoch 6/10, Iter 2103/3560] 2.9218130111694336, cross_entropy: 2.9218130111694336 +[2025-04-29 05:13:30,707][BaseTrainer][INFO] - [Epoch 6/10, Iter 2104/3560] 1.648856282234192, cross_entropy: 1.648856282234192 +[2025-04-29 05:13:33,360][BaseTrainer][INFO] - [Epoch 6/10, Iter 2105/3560] 1.9861245155334473, cross_entropy: 1.9861245155334473 +[2025-04-29 05:13:34,241][BaseTrainer][INFO] - [Epoch 6/10, Iter 2106/3560] 3.32379150390625, cross_entropy: 3.32379150390625 +[2025-04-29 05:13:36,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 2107/3560] 3.1424176692962646, cross_entropy: 3.1424176692962646 +[2025-04-29 05:13:37,853][BaseTrainer][INFO] - [Epoch 6/10, Iter 2108/3560] 1.9881402254104614, cross_entropy: 1.9881402254104614 +[2025-04-29 05:13:40,712][BaseTrainer][INFO] - [Epoch 6/10, Iter 2109/3560] 3.1482441425323486, cross_entropy: 3.1482441425323486 +[2025-04-29 05:13:41,569][BaseTrainer][INFO] - [Epoch 6/10, Iter 2110/3560] 1.7861460447311401, cross_entropy: 1.7861460447311401 +[2025-04-29 05:13:44,677][BaseTrainer][INFO] - [Epoch 6/10, Iter 2111/3560] 1.2674508094787598, cross_entropy: 1.2674508094787598 +[2025-04-29 05:13:45,576][BaseTrainer][INFO] - [Epoch 6/10, Iter 2112/3560] 1.4226295948028564, cross_entropy: 1.4226295948028564 +[2025-04-29 05:13:48,329][BaseTrainer][INFO] - [Epoch 6/10, Iter 2113/3560] 2.7350027561187744, cross_entropy: 2.7350027561187744 +[2025-04-29 05:13:49,215][BaseTrainer][INFO] - [Epoch 6/10, Iter 2114/3560] 2.6435015201568604, cross_entropy: 2.6435015201568604 +[2025-04-29 05:13:51,628][BaseTrainer][INFO] - [Epoch 6/10, Iter 2115/3560] 3.316580295562744, cross_entropy: 3.316580295562744 +[2025-04-29 05:13:52,514][BaseTrainer][INFO] - [Epoch 6/10, Iter 2116/3560] 3.3602468967437744, cross_entropy: 3.3602468967437744 +[2025-04-29 05:13:55,089][BaseTrainer][INFO] - [Epoch 6/10, Iter 2117/3560] 1.7219023704528809, cross_entropy: 1.7219023704528809 +[2025-04-29 05:13:55,945][BaseTrainer][INFO] - [Epoch 6/10, Iter 2118/3560] 1.6696686744689941, cross_entropy: 1.6696686744689941 +[2025-04-29 05:13:58,996][BaseTrainer][INFO] - [Epoch 6/10, Iter 2119/3560] 3.0229239463806152, cross_entropy: 3.0229239463806152 +[2025-04-29 05:13:59,881][BaseTrainer][INFO] - [Epoch 6/10, Iter 2120/3560] 2.585440158843994, cross_entropy: 2.585440158843994 +[2025-04-29 05:14:02,387][BaseTrainer][INFO] - [Epoch 6/10, Iter 2121/3560] 3.056966781616211, cross_entropy: 3.056966781616211 +[2025-04-29 05:14:03,279][BaseTrainer][INFO] - [Epoch 6/10, Iter 2122/3560] 3.0162734985351562, cross_entropy: 3.0162734985351562 +[2025-04-29 05:14:06,642][BaseTrainer][INFO] - [Epoch 6/10, Iter 2123/3560] 3.2324886322021484, cross_entropy: 3.2324886322021484 +[2025-04-29 05:14:07,531][BaseTrainer][INFO] - [Epoch 6/10, Iter 2124/3560] 2.2850966453552246, cross_entropy: 2.2850966453552246 +[2025-04-29 05:14:10,773][BaseTrainer][INFO] - [Epoch 6/10, Iter 2125/3560] 1.7445459365844727, cross_entropy: 1.7445459365844727 +[2025-04-29 05:14:11,653][BaseTrainer][INFO] - [Epoch 6/10, Iter 2126/3560] 1.812293291091919, cross_entropy: 1.812293291091919 +[2025-04-29 05:14:14,803][BaseTrainer][INFO] - [Epoch 6/10, Iter 2127/3560] 3.2609615325927734, cross_entropy: 3.2609615325927734 +[2025-04-29 05:14:15,659][BaseTrainer][INFO] - [Epoch 6/10, Iter 2128/3560] 3.07090425491333, cross_entropy: 3.07090425491333 +[2025-04-29 05:14:19,156][BaseTrainer][INFO] - [Epoch 6/10, Iter 2129/3560] 2.112138271331787, cross_entropy: 2.112138271331787 +[2025-04-29 05:14:20,037][BaseTrainer][INFO] - [Epoch 6/10, Iter 2130/3560] 1.4309840202331543, cross_entropy: 1.4309840202331543 +[2025-04-29 05:14:22,425][BaseTrainer][INFO] - [Epoch 6/10, Iter 2131/3560] 2.4150586128234863, cross_entropy: 2.4150586128234863 +[2025-04-29 05:14:23,308][BaseTrainer][INFO] - [Epoch 6/10, Iter 2132/3560] 1.7220029830932617, cross_entropy: 1.7220029830932617 +[2025-04-29 05:14:26,806][BaseTrainer][INFO] - [Epoch 6/10, Iter 2133/3560] 1.3557939529418945, cross_entropy: 1.3557939529418945 +[2025-04-29 05:14:27,662][BaseTrainer][INFO] - [Epoch 6/10, Iter 2134/3560] 1.8782554864883423, cross_entropy: 1.8782554864883423 +[2025-04-29 05:14:30,647][BaseTrainer][INFO] - [Epoch 6/10, Iter 2135/3560] 2.5520079135894775, cross_entropy: 2.5520079135894775 +[2025-04-29 05:14:31,417][BaseTrainer][INFO] - [Epoch 6/10, Iter 2136/3560] 3.261878252029419, cross_entropy: 3.261878252029419 +[2025-04-29 05:17:20,652][BaseTrainer][INFO] - [Epoch 6/10] (train) 2.3328158855438232, cross_entropy: 2.3328158855438232 +[2025-04-29 05:17:20,652][BaseTrainer][INFO] - [Epoch 6/10] (validation) 1.4448975324630737, cross_entropy: 1.4448975324630737 +[2025-04-29 05:17:21,517][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 05:17:21,994][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch6.pth. +[2025-04-29 05:17:22,790][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 05:17:27,456][BaseTrainer][INFO] - [Epoch 7/10, Iter 2137/3560] 3.2561452388763428, cross_entropy: 3.2561452388763428 +[2025-04-29 05:17:28,360][BaseTrainer][INFO] - [Epoch 7/10, Iter 2138/3560] 1.5910022258758545, cross_entropy: 1.5910022258758545 +[2025-04-29 05:17:31,287][BaseTrainer][INFO] - [Epoch 7/10, Iter 2139/3560] 3.258314609527588, cross_entropy: 3.258314609527588 +[2025-04-29 05:17:32,171][BaseTrainer][INFO] - [Epoch 7/10, Iter 2140/3560] 1.2593204975128174, cross_entropy: 1.2593204975128174 +[2025-04-29 05:17:35,912][BaseTrainer][INFO] - [Epoch 7/10, Iter 2141/3560] 2.144454002380371, cross_entropy: 2.144454002380371 +[2025-04-29 05:17:36,768][BaseTrainer][INFO] - [Epoch 7/10, Iter 2142/3560] 2.323749542236328, cross_entropy: 2.323749542236328 +[2025-04-29 05:17:39,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2143/3560] 1.3656425476074219, cross_entropy: 1.3656425476074219 +[2025-04-29 05:17:40,383][BaseTrainer][INFO] - [Epoch 7/10, Iter 2144/3560] 1.747096061706543, cross_entropy: 1.747096061706543 +[2025-04-29 05:17:43,794][BaseTrainer][INFO] - [Epoch 7/10, Iter 2145/3560] 2.6534924507141113, cross_entropy: 2.6534924507141113 +[2025-04-29 05:17:44,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2146/3560] 1.025648832321167, cross_entropy: 1.025648832321167 +[2025-04-29 05:17:48,121][BaseTrainer][INFO] - [Epoch 7/10, Iter 2147/3560] 1.6399245262145996, cross_entropy: 1.6399245262145996 +[2025-04-29 05:17:48,977][BaseTrainer][INFO] - [Epoch 7/10, Iter 2148/3560] 1.7657420635223389, cross_entropy: 1.7657420635223389 +[2025-04-29 05:17:51,905][BaseTrainer][INFO] - [Epoch 7/10, Iter 2149/3560] 2.941311836242676, cross_entropy: 2.941311836242676 +[2025-04-29 05:17:52,766][BaseTrainer][INFO] - [Epoch 7/10, Iter 2150/3560] 1.097022533416748, cross_entropy: 1.097022533416748 +[2025-04-29 05:17:55,688][BaseTrainer][INFO] - [Epoch 7/10, Iter 2151/3560] 2.3699097633361816, cross_entropy: 2.3699097633361816 +[2025-04-29 05:17:56,547][BaseTrainer][INFO] - [Epoch 7/10, Iter 2152/3560] 1.9145424365997314, cross_entropy: 1.9145424365997314 +[2025-04-29 05:18:01,729][BaseTrainer][INFO] - [Epoch 7/10, Iter 2153/3560] 2.0002098083496094, cross_entropy: 2.0002098083496094 +[2025-04-29 05:18:02,589][BaseTrainer][INFO] - [Epoch 7/10, Iter 2154/3560] 2.992030620574951, cross_entropy: 2.992030620574951 +[2025-04-29 05:18:05,735][BaseTrainer][INFO] - [Epoch 7/10, Iter 2155/3560] 2.836899518966675, cross_entropy: 2.836899518966675 +[2025-04-29 05:18:06,593][BaseTrainer][INFO] - [Epoch 7/10, Iter 2156/3560] 1.9954482316970825, cross_entropy: 1.9954482316970825 +[2025-04-29 05:18:09,905][BaseTrainer][INFO] - [Epoch 7/10, Iter 2157/3560] 3.125157594680786, cross_entropy: 3.125157594680786 +[2025-04-29 05:18:10,761][BaseTrainer][INFO] - [Epoch 7/10, Iter 2158/3560] 2.991081714630127, cross_entropy: 2.991081714630127 +[2025-04-29 05:18:13,843][BaseTrainer][INFO] - [Epoch 7/10, Iter 2159/3560] 2.500983476638794, cross_entropy: 2.500983476638794 +[2025-04-29 05:18:14,734][BaseTrainer][INFO] - [Epoch 7/10, Iter 2160/3560] 2.5068225860595703, cross_entropy: 2.5068225860595703 +[2025-04-29 05:18:17,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2161/3560] 2.2726686000823975, cross_entropy: 2.2726686000823975 +[2025-04-29 05:18:18,224][BaseTrainer][INFO] - [Epoch 7/10, Iter 2162/3560] 3.274411201477051, cross_entropy: 3.274411201477051 +[2025-04-29 05:18:21,334][BaseTrainer][INFO] - [Epoch 7/10, Iter 2163/3560] 1.9921684265136719, cross_entropy: 1.9921684265136719 +[2025-04-29 05:18:22,192][BaseTrainer][INFO] - [Epoch 7/10, Iter 2164/3560] 3.134631633758545, cross_entropy: 3.134631633758545 +[2025-04-29 05:18:25,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2165/3560] 2.628168821334839, cross_entropy: 2.628168821334839 +[2025-04-29 05:18:25,976][BaseTrainer][INFO] - [Epoch 7/10, Iter 2166/3560] 1.471113920211792, cross_entropy: 1.471113920211792 +[2025-04-29 05:18:28,930][BaseTrainer][INFO] - [Epoch 7/10, Iter 2167/3560] 1.295551061630249, cross_entropy: 1.295551061630249 +[2025-04-29 05:18:29,809][BaseTrainer][INFO] - [Epoch 7/10, Iter 2168/3560] 1.3729417324066162, cross_entropy: 1.3729417324066162 +[2025-04-29 05:18:32,338][BaseTrainer][INFO] - [Epoch 7/10, Iter 2169/3560] 1.5872057676315308, cross_entropy: 1.5872057676315308 +[2025-04-29 05:18:33,195][BaseTrainer][INFO] - [Epoch 7/10, Iter 2170/3560] 2.1762871742248535, cross_entropy: 2.1762871742248535 +[2025-04-29 05:18:37,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2171/3560] 2.7640304565429688, cross_entropy: 2.7640304565429688 +[2025-04-29 05:18:37,980][BaseTrainer][INFO] - [Epoch 7/10, Iter 2172/3560] 1.60781991481781, cross_entropy: 1.60781991481781 +[2025-04-29 05:18:41,512][BaseTrainer][INFO] - [Epoch 7/10, Iter 2173/3560] 2.5818164348602295, cross_entropy: 2.5818164348602295 +[2025-04-29 05:18:42,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2174/3560] 3.0521621704101562, cross_entropy: 3.0521621704101562 +[2025-04-29 05:18:45,304][BaseTrainer][INFO] - [Epoch 7/10, Iter 2175/3560] 2.7334132194519043, cross_entropy: 2.7334132194519043 +[2025-04-29 05:18:46,187][BaseTrainer][INFO] - [Epoch 7/10, Iter 2176/3560] 1.3235604763031006, cross_entropy: 1.3235604763031006 +[2025-04-29 05:18:49,112][BaseTrainer][INFO] - [Epoch 7/10, Iter 2177/3560] 2.3656654357910156, cross_entropy: 2.3656654357910156 +[2025-04-29 05:18:49,997][BaseTrainer][INFO] - [Epoch 7/10, Iter 2178/3560] 1.7009177207946777, cross_entropy: 1.7009177207946777 +[2025-04-29 05:18:52,653][BaseTrainer][INFO] - [Epoch 7/10, Iter 2179/3560] 1.8432178497314453, cross_entropy: 1.8432178497314453 +[2025-04-29 05:18:53,535][BaseTrainer][INFO] - [Epoch 7/10, Iter 2180/3560] 2.073500156402588, cross_entropy: 2.073500156402588 +[2025-04-29 05:18:56,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2181/3560] 3.1698544025421143, cross_entropy: 3.1698544025421143 +[2025-04-29 05:18:57,057][BaseTrainer][INFO] - [Epoch 7/10, Iter 2182/3560] 3.084641218185425, cross_entropy: 3.084641218185425 +[2025-04-29 05:18:59,834][BaseTrainer][INFO] - [Epoch 7/10, Iter 2183/3560] 3.218780755996704, cross_entropy: 3.218780755996704 +[2025-04-29 05:19:00,719][BaseTrainer][INFO] - [Epoch 7/10, Iter 2184/3560] 2.211900472640991, cross_entropy: 2.211900472640991 +[2025-04-29 05:19:03,298][BaseTrainer][INFO] - [Epoch 7/10, Iter 2185/3560] 2.2371158599853516, cross_entropy: 2.2371158599853516 +[2025-04-29 05:19:04,180][BaseTrainer][INFO] - [Epoch 7/10, Iter 2186/3560] 2.0085830688476562, cross_entropy: 2.0085830688476562 +[2025-04-29 05:19:06,624][BaseTrainer][INFO] - [Epoch 7/10, Iter 2187/3560] 1.6387639045715332, cross_entropy: 1.6387639045715332 +[2025-04-29 05:19:07,510][BaseTrainer][INFO] - [Epoch 7/10, Iter 2188/3560] 1.6341254711151123, cross_entropy: 1.6341254711151123 +[2025-04-29 05:19:10,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2189/3560] 1.9968476295471191, cross_entropy: 1.9968476295471191 +[2025-04-29 05:19:11,490][BaseTrainer][INFO] - [Epoch 7/10, Iter 2190/3560] 3.040325880050659, cross_entropy: 3.040325880050659 +[2025-04-29 05:19:13,987][BaseTrainer][INFO] - [Epoch 7/10, Iter 2191/3560] 2.0403528213500977, cross_entropy: 2.0403528213500977 +[2025-04-29 05:19:14,843][BaseTrainer][INFO] - [Epoch 7/10, Iter 2192/3560] 1.6648269891738892, cross_entropy: 1.6648269891738892 +[2025-04-29 05:19:17,602][BaseTrainer][INFO] - [Epoch 7/10, Iter 2193/3560] 3.2489700317382812, cross_entropy: 3.2489700317382812 +[2025-04-29 05:19:18,489][BaseTrainer][INFO] - [Epoch 7/10, Iter 2194/3560] 1.4277870655059814, cross_entropy: 1.4277870655059814 +[2025-04-29 05:19:21,287][BaseTrainer][INFO] - [Epoch 7/10, Iter 2195/3560] 1.5174367427825928, cross_entropy: 1.5174367427825928 +[2025-04-29 05:19:22,147][BaseTrainer][INFO] - [Epoch 7/10, Iter 2196/3560] 2.246183395385742, cross_entropy: 2.246183395385742 +[2025-04-29 05:19:25,536][BaseTrainer][INFO] - [Epoch 7/10, Iter 2197/3560] 2.3001317977905273, cross_entropy: 2.3001317977905273 +[2025-04-29 05:19:26,393][BaseTrainer][INFO] - [Epoch 7/10, Iter 2198/3560] 2.342555284500122, cross_entropy: 2.342555284500122 +[2025-04-29 05:19:29,350][BaseTrainer][INFO] - [Epoch 7/10, Iter 2199/3560] 1.603693962097168, cross_entropy: 1.603693962097168 +[2025-04-29 05:19:30,210][BaseTrainer][INFO] - [Epoch 7/10, Iter 2200/3560] 2.274409055709839, cross_entropy: 2.274409055709839 +[2025-04-29 05:19:33,160][BaseTrainer][INFO] - [Epoch 7/10, Iter 2201/3560] 2.176703929901123, cross_entropy: 2.176703929901123 +[2025-04-29 05:19:34,049][BaseTrainer][INFO] - [Epoch 7/10, Iter 2202/3560] 2.9272658824920654, cross_entropy: 2.9272658824920654 +[2025-04-29 05:19:37,067][BaseTrainer][INFO] - [Epoch 7/10, Iter 2203/3560] 1.627169132232666, cross_entropy: 1.627169132232666 +[2025-04-29 05:19:37,943][BaseTrainer][INFO] - [Epoch 7/10, Iter 2204/3560] 1.7244534492492676, cross_entropy: 1.7244534492492676 +[2025-04-29 05:19:40,914][BaseTrainer][INFO] - [Epoch 7/10, Iter 2205/3560] 1.6409351825714111, cross_entropy: 1.6409351825714111 +[2025-04-29 05:19:41,792][BaseTrainer][INFO] - [Epoch 7/10, Iter 2206/3560] 2.675285816192627, cross_entropy: 2.675285816192627 +[2025-04-29 05:19:44,476][BaseTrainer][INFO] - [Epoch 7/10, Iter 2207/3560] 1.582411527633667, cross_entropy: 1.582411527633667 +[2025-04-29 05:19:45,358][BaseTrainer][INFO] - [Epoch 7/10, Iter 2208/3560] 1.5799813270568848, cross_entropy: 1.5799813270568848 +[2025-04-29 05:19:48,938][BaseTrainer][INFO] - [Epoch 7/10, Iter 2209/3560] 1.4462705850601196, cross_entropy: 1.4462705850601196 +[2025-04-29 05:19:49,820][BaseTrainer][INFO] - [Epoch 7/10, Iter 2210/3560] 2.855469226837158, cross_entropy: 2.855469226837158 +[2025-04-29 05:19:51,999][BaseTrainer][INFO] - [Epoch 7/10, Iter 2211/3560] 3.2944304943084717, cross_entropy: 3.2944304943084717 +[2025-04-29 05:19:52,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2212/3560] 1.5840160846710205, cross_entropy: 1.5840160846710205 +[2025-04-29 05:19:55,978][BaseTrainer][INFO] - [Epoch 7/10, Iter 2213/3560] 1.3253140449523926, cross_entropy: 1.3253140449523926 +[2025-04-29 05:19:56,858][BaseTrainer][INFO] - [Epoch 7/10, Iter 2214/3560] 3.2653098106384277, cross_entropy: 3.2653098106384277 +[2025-04-29 05:19:59,981][BaseTrainer][INFO] - [Epoch 7/10, Iter 2215/3560] 2.2531681060791016, cross_entropy: 2.2531681060791016 +[2025-04-29 05:20:00,865][BaseTrainer][INFO] - [Epoch 7/10, Iter 2216/3560] 3.2992048263549805, cross_entropy: 3.2992048263549805 +[2025-04-29 05:20:03,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2217/3560] 3.11318039894104, cross_entropy: 3.11318039894104 +[2025-04-29 05:20:04,250][BaseTrainer][INFO] - [Epoch 7/10, Iter 2218/3560] 3.2037315368652344, cross_entropy: 3.2037315368652344 +[2025-04-29 05:20:07,311][BaseTrainer][INFO] - [Epoch 7/10, Iter 2219/3560] 2.8592689037323, cross_entropy: 2.8592689037323 +[2025-04-29 05:20:08,199][BaseTrainer][INFO] - [Epoch 7/10, Iter 2220/3560] 1.568941593170166, cross_entropy: 1.568941593170166 +[2025-04-29 05:20:10,960][BaseTrainer][INFO] - [Epoch 7/10, Iter 2221/3560] 2.7183585166931152, cross_entropy: 2.7183585166931152 +[2025-04-29 05:20:11,840][BaseTrainer][INFO] - [Epoch 7/10, Iter 2222/3560] 2.859886884689331, cross_entropy: 2.859886884689331 +[2025-04-29 05:20:15,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2223/3560] 1.5809640884399414, cross_entropy: 1.5809640884399414 +[2025-04-29 05:20:16,213][BaseTrainer][INFO] - [Epoch 7/10, Iter 2224/3560] 1.450439453125, cross_entropy: 1.450439453125 +[2025-04-29 05:20:18,404][BaseTrainer][INFO] - [Epoch 7/10, Iter 2225/3560] 3.08737850189209, cross_entropy: 3.08737850189209 +[2025-04-29 05:20:19,263][BaseTrainer][INFO] - [Epoch 7/10, Iter 2226/3560] 1.5375021696090698, cross_entropy: 1.5375021696090698 +[2025-04-29 05:20:22,924][BaseTrainer][INFO] - [Epoch 7/10, Iter 2227/3560] 1.865844964981079, cross_entropy: 1.865844964981079 +[2025-04-29 05:20:23,781][BaseTrainer][INFO] - [Epoch 7/10, Iter 2228/3560] 3.1506636142730713, cross_entropy: 3.1506636142730713 +[2025-04-29 05:20:27,418][BaseTrainer][INFO] - [Epoch 7/10, Iter 2229/3560] 3.2639386653900146, cross_entropy: 3.2639386653900146 +[2025-04-29 05:20:28,301][BaseTrainer][INFO] - [Epoch 7/10, Iter 2230/3560] 1.5738900899887085, cross_entropy: 1.5738900899887085 +[2025-04-29 05:20:31,387][BaseTrainer][INFO] - [Epoch 7/10, Iter 2231/3560] 2.4144091606140137, cross_entropy: 2.4144091606140137 +[2025-04-29 05:20:32,245][BaseTrainer][INFO] - [Epoch 7/10, Iter 2232/3560] 1.6475154161453247, cross_entropy: 1.6475154161453247 +[2025-04-29 05:20:34,942][BaseTrainer][INFO] - [Epoch 7/10, Iter 2233/3560] 2.4646759033203125, cross_entropy: 2.4646759033203125 +[2025-04-29 05:20:35,822][BaseTrainer][INFO] - [Epoch 7/10, Iter 2234/3560] 3.0715532302856445, cross_entropy: 3.0715532302856445 +[2025-04-29 05:20:38,538][BaseTrainer][INFO] - [Epoch 7/10, Iter 2235/3560] 1.8186975717544556, cross_entropy: 1.8186975717544556 +[2025-04-29 05:20:39,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2236/3560] 2.6084563732147217, cross_entropy: 2.6084563732147217 +[2025-04-29 05:20:42,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2237/3560] 3.072065830230713, cross_entropy: 3.072065830230713 +[2025-04-29 05:20:43,385][BaseTrainer][INFO] - [Epoch 7/10, Iter 2238/3560] 1.3419862985610962, cross_entropy: 1.3419862985610962 +[2025-04-29 05:20:45,553][BaseTrainer][INFO] - [Epoch 7/10, Iter 2239/3560] 2.5073671340942383, cross_entropy: 2.5073671340942383 +[2025-04-29 05:20:46,441][BaseTrainer][INFO] - [Epoch 7/10, Iter 2240/3560] 1.357832670211792, cross_entropy: 1.357832670211792 +[2025-04-29 05:20:49,655][BaseTrainer][INFO] - [Epoch 7/10, Iter 2241/3560] 1.2127889394760132, cross_entropy: 1.2127889394760132 +[2025-04-29 05:20:50,519][BaseTrainer][INFO] - [Epoch 7/10, Iter 2242/3560] 1.6718096733093262, cross_entropy: 1.6718096733093262 +[2025-04-29 05:20:53,549][BaseTrainer][INFO] - [Epoch 7/10, Iter 2243/3560] 2.04971981048584, cross_entropy: 2.04971981048584 +[2025-04-29 05:20:54,406][BaseTrainer][INFO] - [Epoch 7/10, Iter 2244/3560] 1.5021734237670898, cross_entropy: 1.5021734237670898 +[2025-04-29 05:20:57,752][BaseTrainer][INFO] - [Epoch 7/10, Iter 2245/3560] 2.576822280883789, cross_entropy: 2.576822280883789 +[2025-04-29 05:20:58,635][BaseTrainer][INFO] - [Epoch 7/10, Iter 2246/3560] 2.465707302093506, cross_entropy: 2.465707302093506 +[2025-04-29 05:21:01,215][BaseTrainer][INFO] - [Epoch 7/10, Iter 2247/3560] 3.004304885864258, cross_entropy: 3.004304885864258 +[2025-04-29 05:21:02,096][BaseTrainer][INFO] - [Epoch 7/10, Iter 2248/3560] 1.5960183143615723, cross_entropy: 1.5960183143615723 +[2025-04-29 05:21:05,035][BaseTrainer][INFO] - [Epoch 7/10, Iter 2249/3560] 2.566464424133301, cross_entropy: 2.566464424133301 +[2025-04-29 05:21:05,893][BaseTrainer][INFO] - [Epoch 7/10, Iter 2250/3560] 1.5074689388275146, cross_entropy: 1.5074689388275146 +[2025-04-29 05:21:08,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2251/3560] 1.8217313289642334, cross_entropy: 1.8217313289642334 +[2025-04-29 05:21:09,646][BaseTrainer][INFO] - [Epoch 7/10, Iter 2252/3560] 2.766298294067383, cross_entropy: 2.766298294067383 +[2025-04-29 05:21:12,333][BaseTrainer][INFO] - [Epoch 7/10, Iter 2253/3560] 1.7688590288162231, cross_entropy: 1.7688590288162231 +[2025-04-29 05:21:13,217][BaseTrainer][INFO] - [Epoch 7/10, Iter 2254/3560] 2.06555438041687, cross_entropy: 2.06555438041687 +[2025-04-29 05:21:16,888][BaseTrainer][INFO] - [Epoch 7/10, Iter 2255/3560] 1.876007318496704, cross_entropy: 1.876007318496704 +[2025-04-29 05:21:17,771][BaseTrainer][INFO] - [Epoch 7/10, Iter 2256/3560] 2.1842260360717773, cross_entropy: 2.1842260360717773 +[2025-04-29 05:21:20,893][BaseTrainer][INFO] - [Epoch 7/10, Iter 2257/3560] 3.3742787837982178, cross_entropy: 3.3742787837982178 +[2025-04-29 05:21:21,763][BaseTrainer][INFO] - [Epoch 7/10, Iter 2258/3560] 3.023071765899658, cross_entropy: 3.023071765899658 +[2025-04-29 05:21:24,345][BaseTrainer][INFO] - [Epoch 7/10, Iter 2259/3560] 1.8041305541992188, cross_entropy: 1.8041305541992188 +[2025-04-29 05:21:25,225][BaseTrainer][INFO] - [Epoch 7/10, Iter 2260/3560] 1.266303300857544, cross_entropy: 1.266303300857544 +[2025-04-29 05:21:27,172][BaseTrainer][INFO] - [Epoch 7/10, Iter 2261/3560] 1.9476571083068848, cross_entropy: 1.9476571083068848 +[2025-04-29 05:21:28,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2262/3560] 1.196555256843567, cross_entropy: 1.196555256843567 +[2025-04-29 05:21:30,559][BaseTrainer][INFO] - [Epoch 7/10, Iter 2263/3560] 3.3370859622955322, cross_entropy: 3.3370859622955322 +[2025-04-29 05:21:31,439][BaseTrainer][INFO] - [Epoch 7/10, Iter 2264/3560] 1.3562190532684326, cross_entropy: 1.3562190532684326 +[2025-04-29 05:21:34,269][BaseTrainer][INFO] - [Epoch 7/10, Iter 2265/3560] 2.186574935913086, cross_entropy: 2.186574935913086 +[2025-04-29 05:21:35,153][BaseTrainer][INFO] - [Epoch 7/10, Iter 2266/3560] 1.5773206949234009, cross_entropy: 1.5773206949234009 +[2025-04-29 05:21:37,784][BaseTrainer][INFO] - [Epoch 7/10, Iter 2267/3560] 1.4709267616271973, cross_entropy: 1.4709267616271973 +[2025-04-29 05:21:38,640][BaseTrainer][INFO] - [Epoch 7/10, Iter 2268/3560] 3.39802885055542, cross_entropy: 3.39802885055542 +[2025-04-29 05:21:41,047][BaseTrainer][INFO] - [Epoch 7/10, Iter 2269/3560] 1.136390209197998, cross_entropy: 1.136390209197998 +[2025-04-29 05:21:41,904][BaseTrainer][INFO] - [Epoch 7/10, Iter 2270/3560] 1.1401622295379639, cross_entropy: 1.1401622295379639 +[2025-04-29 05:21:44,831][BaseTrainer][INFO] - [Epoch 7/10, Iter 2271/3560] 2.0346572399139404, cross_entropy: 2.0346572399139404 +[2025-04-29 05:21:45,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2272/3560] 3.2295076847076416, cross_entropy: 3.2295076847076416 +[2025-04-29 05:21:48,981][BaseTrainer][INFO] - [Epoch 7/10, Iter 2273/3560] 1.5984110832214355, cross_entropy: 1.5984110832214355 +[2025-04-29 05:21:49,861][BaseTrainer][INFO] - [Epoch 7/10, Iter 2274/3560] 3.4374380111694336, cross_entropy: 3.4374380111694336 +[2025-04-29 05:21:52,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2275/3560] 0.927139401435852, cross_entropy: 0.927139401435852 +[2025-04-29 05:21:53,534][BaseTrainer][INFO] - [Epoch 7/10, Iter 2276/3560] 3.6167373657226562, cross_entropy: 3.6167373657226562 +[2025-04-29 05:21:56,714][BaseTrainer][INFO] - [Epoch 7/10, Iter 2277/3560] 1.6602818965911865, cross_entropy: 1.6602818965911865 +[2025-04-29 05:21:57,591][BaseTrainer][INFO] - [Epoch 7/10, Iter 2278/3560] 3.1489462852478027, cross_entropy: 3.1489462852478027 +[2025-04-29 05:22:00,032][BaseTrainer][INFO] - [Epoch 7/10, Iter 2279/3560] 1.8402504920959473, cross_entropy: 1.8402504920959473 +[2025-04-29 05:22:00,891][BaseTrainer][INFO] - [Epoch 7/10, Iter 2280/3560] 2.731117010116577, cross_entropy: 2.731117010116577 +[2025-04-29 05:22:03,713][BaseTrainer][INFO] - [Epoch 7/10, Iter 2281/3560] 1.8901169300079346, cross_entropy: 1.8901169300079346 +[2025-04-29 05:22:04,571][BaseTrainer][INFO] - [Epoch 7/10, Iter 2282/3560] 1.99262535572052, cross_entropy: 1.99262535572052 +[2025-04-29 05:22:07,503][BaseTrainer][INFO] - [Epoch 7/10, Iter 2283/3560] 3.1876306533813477, cross_entropy: 3.1876306533813477 +[2025-04-29 05:22:08,359][BaseTrainer][INFO] - [Epoch 7/10, Iter 2284/3560] 1.943187952041626, cross_entropy: 1.943187952041626 +[2025-04-29 05:22:12,039][BaseTrainer][INFO] - [Epoch 7/10, Iter 2285/3560] 2.9979891777038574, cross_entropy: 2.9979891777038574 +[2025-04-29 05:22:12,895][BaseTrainer][INFO] - [Epoch 7/10, Iter 2286/3560] 2.641909122467041, cross_entropy: 2.641909122467041 +[2025-04-29 05:22:15,190][BaseTrainer][INFO] - [Epoch 7/10, Iter 2287/3560] 3.2907392978668213, cross_entropy: 3.2907392978668213 +[2025-04-29 05:22:16,079][BaseTrainer][INFO] - [Epoch 7/10, Iter 2288/3560] 1.728859543800354, cross_entropy: 1.728859543800354 +[2025-04-29 05:22:18,672][BaseTrainer][INFO] - [Epoch 7/10, Iter 2289/3560] 2.8024420738220215, cross_entropy: 2.8024420738220215 +[2025-04-29 05:22:19,551][BaseTrainer][INFO] - [Epoch 7/10, Iter 2290/3560] 1.3722455501556396, cross_entropy: 1.3722455501556396 +[2025-04-29 05:22:22,100][BaseTrainer][INFO] - [Epoch 7/10, Iter 2291/3560] 1.3866543769836426, cross_entropy: 1.3866543769836426 +[2025-04-29 05:22:22,990][BaseTrainer][INFO] - [Epoch 7/10, Iter 2292/3560] 2.2799229621887207, cross_entropy: 2.2799229621887207 +[2025-04-29 05:22:25,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2293/3560] 3.1262636184692383, cross_entropy: 3.1262636184692383 +[2025-04-29 05:22:26,389][BaseTrainer][INFO] - [Epoch 7/10, Iter 2294/3560] 1.9074164628982544, cross_entropy: 1.9074164628982544 +[2025-04-29 05:22:29,091][BaseTrainer][INFO] - [Epoch 7/10, Iter 2295/3560] 3.555879592895508, cross_entropy: 3.555879592895508 +[2025-04-29 05:22:29,969][BaseTrainer][INFO] - [Epoch 7/10, Iter 2296/3560] 2.9172749519348145, cross_entropy: 2.9172749519348145 +[2025-04-29 05:22:32,855][BaseTrainer][INFO] - [Epoch 7/10, Iter 2297/3560] 1.648789882659912, cross_entropy: 1.648789882659912 +[2025-04-29 05:22:33,724][BaseTrainer][INFO] - [Epoch 7/10, Iter 2298/3560] 2.142162561416626, cross_entropy: 2.142162561416626 +[2025-04-29 05:22:35,926][BaseTrainer][INFO] - [Epoch 7/10, Iter 2299/3560] 1.7684996128082275, cross_entropy: 1.7684996128082275 +[2025-04-29 05:22:36,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2300/3560] 1.901320457458496, cross_entropy: 1.901320457458496 +[2025-04-29 05:22:39,502][BaseTrainer][INFO] - [Epoch 7/10, Iter 2301/3560] 1.32345712184906, cross_entropy: 1.32345712184906 +[2025-04-29 05:22:40,390][BaseTrainer][INFO] - [Epoch 7/10, Iter 2302/3560] 1.9907817840576172, cross_entropy: 1.9907817840576172 +[2025-04-29 05:22:42,682][BaseTrainer][INFO] - [Epoch 7/10, Iter 2303/3560] 3.249246120452881, cross_entropy: 3.249246120452881 +[2025-04-29 05:22:43,567][BaseTrainer][INFO] - [Epoch 7/10, Iter 2304/3560] 1.9775795936584473, cross_entropy: 1.9775795936584473 +[2025-04-29 05:22:45,881][BaseTrainer][INFO] - [Epoch 7/10, Iter 2305/3560] 2.272976875305176, cross_entropy: 2.272976875305176 +[2025-04-29 05:22:46,742][BaseTrainer][INFO] - [Epoch 7/10, Iter 2306/3560] 1.4959238767623901, cross_entropy: 1.4959238767623901 +[2025-04-29 05:22:49,382][BaseTrainer][INFO] - [Epoch 7/10, Iter 2307/3560] 1.5957424640655518, cross_entropy: 1.5957424640655518 +[2025-04-29 05:22:50,270][BaseTrainer][INFO] - [Epoch 7/10, Iter 2308/3560] 1.2525756359100342, cross_entropy: 1.2525756359100342 +[2025-04-29 05:22:53,451][BaseTrainer][INFO] - [Epoch 7/10, Iter 2309/3560] 1.9887702465057373, cross_entropy: 1.9887702465057373 +[2025-04-29 05:22:54,339][BaseTrainer][INFO] - [Epoch 7/10, Iter 2310/3560] 3.2209324836730957, cross_entropy: 3.2209324836730957 +[2025-04-29 05:22:57,145][BaseTrainer][INFO] - [Epoch 7/10, Iter 2311/3560] 2.328561782836914, cross_entropy: 2.328561782836914 +[2025-04-29 05:22:58,002][BaseTrainer][INFO] - [Epoch 7/10, Iter 2312/3560] 1.7471802234649658, cross_entropy: 1.7471802234649658 +[2025-04-29 05:23:01,221][BaseTrainer][INFO] - [Epoch 7/10, Iter 2313/3560] 3.5072426795959473, cross_entropy: 3.5072426795959473 +[2025-04-29 05:23:02,081][BaseTrainer][INFO] - [Epoch 7/10, Iter 2314/3560] 1.1632241010665894, cross_entropy: 1.1632241010665894 +[2025-04-29 05:23:05,282][BaseTrainer][INFO] - [Epoch 7/10, Iter 2315/3560] 1.5289270877838135, cross_entropy: 1.5289270877838135 +[2025-04-29 05:23:06,139][BaseTrainer][INFO] - [Epoch 7/10, Iter 2316/3560] 1.935136318206787, cross_entropy: 1.935136318206787 +[2025-04-29 05:23:09,226][BaseTrainer][INFO] - [Epoch 7/10, Iter 2317/3560] 2.8389971256256104, cross_entropy: 2.8389971256256104 +[2025-04-29 05:23:10,084][BaseTrainer][INFO] - [Epoch 7/10, Iter 2318/3560] 1.3927514553070068, cross_entropy: 1.3927514553070068 +[2025-04-29 05:23:12,808][BaseTrainer][INFO] - [Epoch 7/10, Iter 2319/3560] 1.2487046718597412, cross_entropy: 1.2487046718597412 +[2025-04-29 05:23:13,701][BaseTrainer][INFO] - [Epoch 7/10, Iter 2320/3560] 3.0771892070770264, cross_entropy: 3.0771892070770264 +[2025-04-29 05:23:17,287][BaseTrainer][INFO] - [Epoch 7/10, Iter 2321/3560] 3.479133129119873, cross_entropy: 3.479133129119873 +[2025-04-29 05:23:18,168][BaseTrainer][INFO] - [Epoch 7/10, Iter 2322/3560] 2.775334596633911, cross_entropy: 2.775334596633911 +[2025-04-29 05:23:20,847][BaseTrainer][INFO] - [Epoch 7/10, Iter 2323/3560] 2.9823317527770996, cross_entropy: 2.9823317527770996 +[2025-04-29 05:23:21,706][BaseTrainer][INFO] - [Epoch 7/10, Iter 2324/3560] 1.6175932884216309, cross_entropy: 1.6175932884216309 +[2025-04-29 05:23:24,354][BaseTrainer][INFO] - [Epoch 7/10, Iter 2325/3560] 1.5206630229949951, cross_entropy: 1.5206630229949951 +[2025-04-29 05:23:25,236][BaseTrainer][INFO] - [Epoch 7/10, Iter 2326/3560] 2.032949924468994, cross_entropy: 2.032949924468994 +[2025-04-29 05:23:27,712][BaseTrainer][INFO] - [Epoch 7/10, Iter 2327/3560] 3.002932548522949, cross_entropy: 3.002932548522949 +[2025-04-29 05:23:28,597][BaseTrainer][INFO] - [Epoch 7/10, Iter 2328/3560] 2.8692612648010254, cross_entropy: 2.8692612648010254 +[2025-04-29 05:23:31,126][BaseTrainer][INFO] - [Epoch 7/10, Iter 2329/3560] 1.8350293636322021, cross_entropy: 1.8350293636322021 +[2025-04-29 05:23:32,012][BaseTrainer][INFO] - [Epoch 7/10, Iter 2330/3560] 2.1142659187316895, cross_entropy: 2.1142659187316895 +[2025-04-29 05:23:34,277][BaseTrainer][INFO] - [Epoch 7/10, Iter 2331/3560] 1.7447936534881592, cross_entropy: 1.7447936534881592 +[2025-04-29 05:23:35,158][BaseTrainer][INFO] - [Epoch 7/10, Iter 2332/3560] 1.0819941759109497, cross_entropy: 1.0819941759109497 +[2025-04-29 05:23:37,825][BaseTrainer][INFO] - [Epoch 7/10, Iter 2333/3560] 1.2403571605682373, cross_entropy: 1.2403571605682373 +[2025-04-29 05:23:38,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2334/3560] 2.9105677604675293, cross_entropy: 2.9105677604675293 +[2025-04-29 05:23:41,434][BaseTrainer][INFO] - [Epoch 7/10, Iter 2335/3560] 3.2832705974578857, cross_entropy: 3.2832705974578857 +[2025-04-29 05:23:42,315][BaseTrainer][INFO] - [Epoch 7/10, Iter 2336/3560] 1.253028392791748, cross_entropy: 1.253028392791748 +[2025-04-29 05:23:44,868][BaseTrainer][INFO] - [Epoch 7/10, Iter 2337/3560] 3.257411241531372, cross_entropy: 3.257411241531372 +[2025-04-29 05:23:45,752][BaseTrainer][INFO] - [Epoch 7/10, Iter 2338/3560] 1.2654081583023071, cross_entropy: 1.2654081583023071 +[2025-04-29 05:23:48,826][BaseTrainer][INFO] - [Epoch 7/10, Iter 2339/3560] 1.68220853805542, cross_entropy: 1.68220853805542 +[2025-04-29 05:23:49,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2340/3560] 3.197439193725586, cross_entropy: 3.197439193725586 +[2025-04-29 05:23:51,647][BaseTrainer][INFO] - [Epoch 7/10, Iter 2341/3560] 2.8806166648864746, cross_entropy: 2.8806166648864746 +[2025-04-29 05:23:52,528][BaseTrainer][INFO] - [Epoch 7/10, Iter 2342/3560] 1.76564359664917, cross_entropy: 1.76564359664917 +[2025-04-29 05:23:54,912][BaseTrainer][INFO] - [Epoch 7/10, Iter 2343/3560] 1.6379375457763672, cross_entropy: 1.6379375457763672 +[2025-04-29 05:23:55,769][BaseTrainer][INFO] - [Epoch 7/10, Iter 2344/3560] 1.4307634830474854, cross_entropy: 1.4307634830474854 +[2025-04-29 05:23:59,251][BaseTrainer][INFO] - [Epoch 7/10, Iter 2345/3560] 3.400681495666504, cross_entropy: 3.400681495666504 +[2025-04-29 05:24:00,141][BaseTrainer][INFO] - [Epoch 7/10, Iter 2346/3560] 1.395427942276001, cross_entropy: 1.395427942276001 +[2025-04-29 05:24:02,932][BaseTrainer][INFO] - [Epoch 7/10, Iter 2347/3560] 1.9342886209487915, cross_entropy: 1.9342886209487915 +[2025-04-29 05:24:03,793][BaseTrainer][INFO] - [Epoch 7/10, Iter 2348/3560] 1.4145973920822144, cross_entropy: 1.4145973920822144 +[2025-04-29 05:24:06,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2349/3560] 3.4163308143615723, cross_entropy: 3.4163308143615723 +[2025-04-29 05:24:07,294][BaseTrainer][INFO] - [Epoch 7/10, Iter 2350/3560] 1.50955069065094, cross_entropy: 1.50955069065094 +[2025-04-29 05:24:10,368][BaseTrainer][INFO] - [Epoch 7/10, Iter 2351/3560] 1.4521315097808838, cross_entropy: 1.4521315097808838 +[2025-04-29 05:24:11,248][BaseTrainer][INFO] - [Epoch 7/10, Iter 2352/3560] 1.4025721549987793, cross_entropy: 1.4025721549987793 +[2025-04-29 05:24:13,884][BaseTrainer][INFO] - [Epoch 7/10, Iter 2353/3560] 3.047400951385498, cross_entropy: 3.047400951385498 +[2025-04-29 05:24:14,758][BaseTrainer][INFO] - [Epoch 7/10, Iter 2354/3560] 2.9824137687683105, cross_entropy: 2.9824137687683105 +[2025-04-29 05:24:17,239][BaseTrainer][INFO] - [Epoch 7/10, Iter 2355/3560] 1.4280073642730713, cross_entropy: 1.4280073642730713 +[2025-04-29 05:24:18,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2356/3560] 2.830064058303833, cross_entropy: 2.830064058303833 +[2025-04-29 05:24:20,483][BaseTrainer][INFO] - [Epoch 7/10, Iter 2357/3560] 3.5506558418273926, cross_entropy: 3.5506558418273926 +[2025-04-29 05:24:21,342][BaseTrainer][INFO] - [Epoch 7/10, Iter 2358/3560] 1.9617469310760498, cross_entropy: 1.9617469310760498 +[2025-04-29 05:24:24,679][BaseTrainer][INFO] - [Epoch 7/10, Iter 2359/3560] 2.691645383834839, cross_entropy: 2.691645383834839 +[2025-04-29 05:24:25,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2360/3560] 2.8374853134155273, cross_entropy: 2.8374853134155273 +[2025-04-29 05:24:28,762][BaseTrainer][INFO] - [Epoch 7/10, Iter 2361/3560] 1.684333086013794, cross_entropy: 1.684333086013794 +[2025-04-29 05:24:29,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2362/3560] 3.4113972187042236, cross_entropy: 3.4113972187042236 +[2025-04-29 05:24:33,775][BaseTrainer][INFO] - [Epoch 7/10, Iter 2363/3560] 3.504397392272949, cross_entropy: 3.504397392272949 +[2025-04-29 05:24:34,637][BaseTrainer][INFO] - [Epoch 7/10, Iter 2364/3560] 1.650282859802246, cross_entropy: 1.650282859802246 +[2025-04-29 05:24:37,482][BaseTrainer][INFO] - [Epoch 7/10, Iter 2365/3560] 2.0861141681671143, cross_entropy: 2.0861141681671143 +[2025-04-29 05:24:38,341][BaseTrainer][INFO] - [Epoch 7/10, Iter 2366/3560] 1.469589114189148, cross_entropy: 1.469589114189148 +[2025-04-29 05:24:41,170][BaseTrainer][INFO] - [Epoch 7/10, Iter 2367/3560] 2.536932945251465, cross_entropy: 2.536932945251465 +[2025-04-29 05:24:42,052][BaseTrainer][INFO] - [Epoch 7/10, Iter 2368/3560] 1.7268457412719727, cross_entropy: 1.7268457412719727 +[2025-04-29 05:24:44,462][BaseTrainer][INFO] - [Epoch 7/10, Iter 2369/3560] 2.5178327560424805, cross_entropy: 2.5178327560424805 +[2025-04-29 05:24:45,346][BaseTrainer][INFO] - [Epoch 7/10, Iter 2370/3560] 2.72782564163208, cross_entropy: 2.72782564163208 +[2025-04-29 05:24:48,438][BaseTrainer][INFO] - [Epoch 7/10, Iter 2371/3560] 2.5988008975982666, cross_entropy: 2.5988008975982666 +[2025-04-29 05:24:49,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2372/3560] 3.1796441078186035, cross_entropy: 3.1796441078186035 +[2025-04-29 05:24:52,222][BaseTrainer][INFO] - [Epoch 7/10, Iter 2373/3560] 1.820521593093872, cross_entropy: 1.820521593093872 +[2025-04-29 05:24:53,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2374/3560] 2.1901893615722656, cross_entropy: 2.1901893615722656 +[2025-04-29 05:24:55,572][BaseTrainer][INFO] - [Epoch 7/10, Iter 2375/3560] 2.208408832550049, cross_entropy: 2.208408832550049 +[2025-04-29 05:24:56,427][BaseTrainer][INFO] - [Epoch 7/10, Iter 2376/3560] 1.963277816772461, cross_entropy: 1.963277816772461 +[2025-04-29 05:24:59,818][BaseTrainer][INFO] - [Epoch 7/10, Iter 2377/3560] 2.391411781311035, cross_entropy: 2.391411781311035 +[2025-04-29 05:25:00,681][BaseTrainer][INFO] - [Epoch 7/10, Iter 2378/3560] 1.4207324981689453, cross_entropy: 1.4207324981689453 +[2025-04-29 05:25:03,343][BaseTrainer][INFO] - [Epoch 7/10, Iter 2379/3560] 2.0434651374816895, cross_entropy: 2.0434651374816895 +[2025-04-29 05:25:04,243][BaseTrainer][INFO] - [Epoch 7/10, Iter 2380/3560] 1.975996494293213, cross_entropy: 1.975996494293213 +[2025-04-29 05:25:07,604][BaseTrainer][INFO] - [Epoch 7/10, Iter 2381/3560] 1.2871372699737549, cross_entropy: 1.2871372699737549 +[2025-04-29 05:25:08,484][BaseTrainer][INFO] - [Epoch 7/10, Iter 2382/3560] 1.423713207244873, cross_entropy: 1.423713207244873 +[2025-04-29 05:25:11,102][BaseTrainer][INFO] - [Epoch 7/10, Iter 2383/3560] 2.7011752128601074, cross_entropy: 2.7011752128601074 +[2025-04-29 05:25:11,990][BaseTrainer][INFO] - [Epoch 7/10, Iter 2384/3560] 2.3487346172332764, cross_entropy: 2.3487346172332764 +[2025-04-29 05:25:14,846][BaseTrainer][INFO] - [Epoch 7/10, Iter 2385/3560] 1.3118376731872559, cross_entropy: 1.3118376731872559 +[2025-04-29 05:25:15,736][BaseTrainer][INFO] - [Epoch 7/10, Iter 2386/3560] 2.5710158348083496, cross_entropy: 2.5710158348083496 +[2025-04-29 05:25:17,998][BaseTrainer][INFO] - [Epoch 7/10, Iter 2387/3560] 1.8743441104888916, cross_entropy: 1.8743441104888916 +[2025-04-29 05:25:18,887][BaseTrainer][INFO] - [Epoch 7/10, Iter 2388/3560] 3.11061429977417, cross_entropy: 3.11061429977417 +[2025-04-29 05:25:21,343][BaseTrainer][INFO] - [Epoch 7/10, Iter 2389/3560] 1.7793769836425781, cross_entropy: 1.7793769836425781 +[2025-04-29 05:25:22,226][BaseTrainer][INFO] - [Epoch 7/10, Iter 2390/3560] 2.1358377933502197, cross_entropy: 2.1358377933502197 +[2025-04-29 05:25:25,128][BaseTrainer][INFO] - [Epoch 7/10, Iter 2391/3560] 3.4394283294677734, cross_entropy: 3.4394283294677734 +[2025-04-29 05:25:26,010][BaseTrainer][INFO] - [Epoch 7/10, Iter 2392/3560] 2.451291561126709, cross_entropy: 2.451291561126709 +[2025-04-29 05:25:28,715][BaseTrainer][INFO] - [Epoch 7/10, Iter 2393/3560] 2.311631679534912, cross_entropy: 2.311631679534912 +[2025-04-29 05:25:29,606][BaseTrainer][INFO] - [Epoch 7/10, Iter 2394/3560] 2.5996885299682617, cross_entropy: 2.5996885299682617 +[2025-04-29 05:25:32,846][BaseTrainer][INFO] - [Epoch 7/10, Iter 2395/3560] 1.43533194065094, cross_entropy: 1.43533194065094 +[2025-04-29 05:25:33,705][BaseTrainer][INFO] - [Epoch 7/10, Iter 2396/3560] 2.1080384254455566, cross_entropy: 2.1080384254455566 +[2025-04-29 05:25:36,286][BaseTrainer][INFO] - [Epoch 7/10, Iter 2397/3560] 2.5725669860839844, cross_entropy: 2.5725669860839844 +[2025-04-29 05:25:37,176][BaseTrainer][INFO] - [Epoch 7/10, Iter 2398/3560] 1.8636471033096313, cross_entropy: 1.8636471033096313 +[2025-04-29 05:25:40,165][BaseTrainer][INFO] - [Epoch 7/10, Iter 2399/3560] 3.237971305847168, cross_entropy: 3.237971305847168 +[2025-04-29 05:25:41,026][BaseTrainer][INFO] - [Epoch 7/10, Iter 2400/3560] 3.20320463180542, cross_entropy: 3.20320463180542 +[2025-04-29 05:25:43,790][BaseTrainer][INFO] - [Epoch 7/10, Iter 2401/3560] 3.3872671127319336, cross_entropy: 3.3872671127319336 +[2025-04-29 05:25:44,648][BaseTrainer][INFO] - [Epoch 7/10, Iter 2402/3560] 1.5301477909088135, cross_entropy: 1.5301477909088135 +[2025-04-29 05:25:47,328][BaseTrainer][INFO] - [Epoch 7/10, Iter 2403/3560] 3.3318300247192383, cross_entropy: 3.3318300247192383 +[2025-04-29 05:25:48,214][BaseTrainer][INFO] - [Epoch 7/10, Iter 2404/3560] 2.548788547515869, cross_entropy: 2.548788547515869 +[2025-04-29 05:25:50,540][BaseTrainer][INFO] - [Epoch 7/10, Iter 2405/3560] 2.475537061691284, cross_entropy: 2.475537061691284 +[2025-04-29 05:25:51,425][BaseTrainer][INFO] - [Epoch 7/10, Iter 2406/3560] 1.6286593675613403, cross_entropy: 1.6286593675613403 +[2025-04-29 05:25:54,092][BaseTrainer][INFO] - [Epoch 7/10, Iter 2407/3560] 3.340536594390869, cross_entropy: 3.340536594390869 +[2025-04-29 05:25:54,949][BaseTrainer][INFO] - [Epoch 7/10, Iter 2408/3560] 2.1462960243225098, cross_entropy: 2.1462960243225098 +[2025-04-29 05:25:58,059][BaseTrainer][INFO] - [Epoch 7/10, Iter 2409/3560] 1.480992078781128, cross_entropy: 1.480992078781128 +[2025-04-29 05:25:58,919][BaseTrainer][INFO] - [Epoch 7/10, Iter 2410/3560] 1.6043980121612549, cross_entropy: 1.6043980121612549 +[2025-04-29 05:26:01,811][BaseTrainer][INFO] - [Epoch 7/10, Iter 2411/3560] 1.9078991413116455, cross_entropy: 1.9078991413116455 +[2025-04-29 05:26:02,675][BaseTrainer][INFO] - [Epoch 7/10, Iter 2412/3560] 2.8970704078674316, cross_entropy: 2.8970704078674316 +[2025-04-29 05:26:05,302][BaseTrainer][INFO] - [Epoch 7/10, Iter 2413/3560] 1.534063696861267, cross_entropy: 1.534063696861267 +[2025-04-29 05:26:06,162][BaseTrainer][INFO] - [Epoch 7/10, Iter 2414/3560] 3.1377522945404053, cross_entropy: 3.1377522945404053 +[2025-04-29 05:26:09,633][BaseTrainer][INFO] - [Epoch 7/10, Iter 2415/3560] 1.9868597984313965, cross_entropy: 1.9868597984313965 +[2025-04-29 05:26:10,520][BaseTrainer][INFO] - [Epoch 7/10, Iter 2416/3560] 2.2727160453796387, cross_entropy: 2.2727160453796387 +[2025-04-29 05:26:13,245][BaseTrainer][INFO] - [Epoch 7/10, Iter 2417/3560] 1.8038012981414795, cross_entropy: 1.8038012981414795 +[2025-04-29 05:26:14,111][BaseTrainer][INFO] - [Epoch 7/10, Iter 2418/3560] 2.9897351264953613, cross_entropy: 2.9897351264953613 +[2025-04-29 05:26:16,774][BaseTrainer][INFO] - [Epoch 7/10, Iter 2419/3560] 3.455556869506836, cross_entropy: 3.455556869506836 +[2025-04-29 05:26:17,635][BaseTrainer][INFO] - [Epoch 7/10, Iter 2420/3560] 2.787170171737671, cross_entropy: 2.787170171737671 +[2025-04-29 05:26:20,051][BaseTrainer][INFO] - [Epoch 7/10, Iter 2421/3560] 3.251035451889038, cross_entropy: 3.251035451889038 +[2025-04-29 05:26:20,919][BaseTrainer][INFO] - [Epoch 7/10, Iter 2422/3560] 2.987290382385254, cross_entropy: 2.987290382385254 +[2025-04-29 05:26:23,824][BaseTrainer][INFO] - [Epoch 7/10, Iter 2423/3560] 1.5632953643798828, cross_entropy: 1.5632953643798828 +[2025-04-29 05:26:24,713][BaseTrainer][INFO] - [Epoch 7/10, Iter 2424/3560] 1.8581068515777588, cross_entropy: 1.8581068515777588 +[2025-04-29 05:26:28,218][BaseTrainer][INFO] - [Epoch 7/10, Iter 2425/3560] 2.4365973472595215, cross_entropy: 2.4365973472595215 +[2025-04-29 05:26:29,095][BaseTrainer][INFO] - [Epoch 7/10, Iter 2426/3560] 2.6693015098571777, cross_entropy: 2.6693015098571777 +[2025-04-29 05:26:31,442][BaseTrainer][INFO] - [Epoch 7/10, Iter 2427/3560] 1.5476899147033691, cross_entropy: 1.5476899147033691 +[2025-04-29 05:26:32,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2428/3560] 1.6714930534362793, cross_entropy: 1.6714930534362793 +[2025-04-29 05:26:35,347][BaseTrainer][INFO] - [Epoch 7/10, Iter 2429/3560] 2.4984872341156006, cross_entropy: 2.4984872341156006 +[2025-04-29 05:26:36,204][BaseTrainer][INFO] - [Epoch 7/10, Iter 2430/3560] 2.138701915740967, cross_entropy: 2.138701915740967 +[2025-04-29 05:26:39,040][BaseTrainer][INFO] - [Epoch 7/10, Iter 2431/3560] 1.7352386713027954, cross_entropy: 1.7352386713027954 +[2025-04-29 05:26:39,929][BaseTrainer][INFO] - [Epoch 7/10, Iter 2432/3560] 1.9062122106552124, cross_entropy: 1.9062122106552124 +[2025-04-29 05:26:43,264][BaseTrainer][INFO] - [Epoch 7/10, Iter 2433/3560] 2.411653518676758, cross_entropy: 2.411653518676758 +[2025-04-29 05:26:44,130][BaseTrainer][INFO] - [Epoch 7/10, Iter 2434/3560] 3.16064715385437, cross_entropy: 3.16064715385437 +[2025-04-29 05:26:46,652][BaseTrainer][INFO] - [Epoch 7/10, Iter 2435/3560] 1.823893427848816, cross_entropy: 1.823893427848816 +[2025-04-29 05:26:47,511][BaseTrainer][INFO] - [Epoch 7/10, Iter 2436/3560] 2.9963505268096924, cross_entropy: 2.9963505268096924 +[2025-04-29 05:26:50,310][BaseTrainer][INFO] - [Epoch 7/10, Iter 2437/3560] 3.164020538330078, cross_entropy: 3.164020538330078 +[2025-04-29 05:26:51,191][BaseTrainer][INFO] - [Epoch 7/10, Iter 2438/3560] 2.3918933868408203, cross_entropy: 2.3918933868408203 +[2025-04-29 05:26:53,424][BaseTrainer][INFO] - [Epoch 7/10, Iter 2439/3560] 3.017096519470215, cross_entropy: 3.017096519470215 +[2025-04-29 05:26:54,317][BaseTrainer][INFO] - [Epoch 7/10, Iter 2440/3560] 2.7949018478393555, cross_entropy: 2.7949018478393555 +[2025-04-29 05:26:57,455][BaseTrainer][INFO] - [Epoch 7/10, Iter 2441/3560] 3.0933918952941895, cross_entropy: 3.0933918952941895 +[2025-04-29 05:26:58,312][BaseTrainer][INFO] - [Epoch 7/10, Iter 2442/3560] 2.367776393890381, cross_entropy: 2.367776393890381 +[2025-04-29 05:27:01,171][BaseTrainer][INFO] - [Epoch 7/10, Iter 2443/3560] 1.8057622909545898, cross_entropy: 1.8057622909545898 +[2025-04-29 05:27:02,028][BaseTrainer][INFO] - [Epoch 7/10, Iter 2444/3560] 2.7701334953308105, cross_entropy: 2.7701334953308105 +[2025-04-29 05:27:05,235][BaseTrainer][INFO] - [Epoch 7/10, Iter 2445/3560] 2.3641250133514404, cross_entropy: 2.3641250133514404 +[2025-04-29 05:27:06,117][BaseTrainer][INFO] - [Epoch 7/10, Iter 2446/3560] 2.50823974609375, cross_entropy: 2.50823974609375 +[2025-04-29 05:27:08,852][BaseTrainer][INFO] - [Epoch 7/10, Iter 2447/3560] 1.5578951835632324, cross_entropy: 1.5578951835632324 +[2025-04-29 05:27:09,734][BaseTrainer][INFO] - [Epoch 7/10, Iter 2448/3560] 2.2790441513061523, cross_entropy: 2.2790441513061523 +[2025-04-29 05:27:12,085][BaseTrainer][INFO] - [Epoch 7/10, Iter 2449/3560] 1.8024778366088867, cross_entropy: 1.8024778366088867 +[2025-04-29 05:27:12,968][BaseTrainer][INFO] - [Epoch 7/10, Iter 2450/3560] 2.781583786010742, cross_entropy: 2.781583786010742 +[2025-04-29 05:27:15,798][BaseTrainer][INFO] - [Epoch 7/10, Iter 2451/3560] 1.4561526775360107, cross_entropy: 1.4561526775360107 +[2025-04-29 05:27:16,680][BaseTrainer][INFO] - [Epoch 7/10, Iter 2452/3560] 1.5888886451721191, cross_entropy: 1.5888886451721191 +[2025-04-29 05:27:19,475][BaseTrainer][INFO] - [Epoch 7/10, Iter 2453/3560] 3.2957119941711426, cross_entropy: 3.2957119941711426 +[2025-04-29 05:27:20,343][BaseTrainer][INFO] - [Epoch 7/10, Iter 2454/3560] 1.2356679439544678, cross_entropy: 1.2356679439544678 +[2025-04-29 05:27:23,822][BaseTrainer][INFO] - [Epoch 7/10, Iter 2455/3560] 1.8661969900131226, cross_entropy: 1.8661969900131226 +[2025-04-29 05:27:24,702][BaseTrainer][INFO] - [Epoch 7/10, Iter 2456/3560] 3.8110337257385254, cross_entropy: 3.8110337257385254 +[2025-04-29 05:27:27,639][BaseTrainer][INFO] - [Epoch 7/10, Iter 2457/3560] 2.1825191974639893, cross_entropy: 2.1825191974639893 +[2025-04-29 05:27:28,496][BaseTrainer][INFO] - [Epoch 7/10, Iter 2458/3560] 1.8591594696044922, cross_entropy: 1.8591594696044922 +[2025-04-29 05:27:31,377][BaseTrainer][INFO] - [Epoch 7/10, Iter 2459/3560] 2.7272417545318604, cross_entropy: 2.7272417545318604 +[2025-04-29 05:27:32,252][BaseTrainer][INFO] - [Epoch 7/10, Iter 2460/3560] 2.9172239303588867, cross_entropy: 2.9172239303588867 +[2025-04-29 05:27:34,789][BaseTrainer][INFO] - [Epoch 7/10, Iter 2461/3560] 1.8700377941131592, cross_entropy: 1.8700377941131592 +[2025-04-29 05:27:35,662][BaseTrainer][INFO] - [Epoch 7/10, Iter 2462/3560] 2.4746694564819336, cross_entropy: 2.4746694564819336 +[2025-04-29 05:27:38,363][BaseTrainer][INFO] - [Epoch 7/10, Iter 2463/3560] 1.8876495361328125, cross_entropy: 1.8876495361328125 +[2025-04-29 05:27:39,218][BaseTrainer][INFO] - [Epoch 7/10, Iter 2464/3560] 1.5206880569458008, cross_entropy: 1.5206880569458008 +[2025-04-29 05:27:42,291][BaseTrainer][INFO] - [Epoch 7/10, Iter 2465/3560] 2.4448468685150146, cross_entropy: 2.4448468685150146 +[2025-04-29 05:27:43,169][BaseTrainer][INFO] - [Epoch 7/10, Iter 2466/3560] 1.606771469116211, cross_entropy: 1.606771469116211 +[2025-04-29 05:27:45,709][BaseTrainer][INFO] - [Epoch 7/10, Iter 2467/3560] 2.034194231033325, cross_entropy: 2.034194231033325 +[2025-04-29 05:27:46,600][BaseTrainer][INFO] - [Epoch 7/10, Iter 2468/3560] 3.053875684738159, cross_entropy: 3.053875684738159 +[2025-04-29 05:27:49,616][BaseTrainer][INFO] - [Epoch 7/10, Iter 2469/3560] 2.952486515045166, cross_entropy: 2.952486515045166 +[2025-04-29 05:27:50,479][BaseTrainer][INFO] - [Epoch 7/10, Iter 2470/3560] 1.6360597610473633, cross_entropy: 1.6360597610473633 +[2025-04-29 05:27:53,548][BaseTrainer][INFO] - [Epoch 7/10, Iter 2471/3560] 1.6172820329666138, cross_entropy: 1.6172820329666138 +[2025-04-29 05:27:54,429][BaseTrainer][INFO] - [Epoch 7/10, Iter 2472/3560] 1.3017727136611938, cross_entropy: 1.3017727136611938 +[2025-04-29 05:27:56,941][BaseTrainer][INFO] - [Epoch 7/10, Iter 2473/3560] 3.0215237140655518, cross_entropy: 3.0215237140655518 +[2025-04-29 05:27:57,828][BaseTrainer][INFO] - [Epoch 7/10, Iter 2474/3560] 1.3911941051483154, cross_entropy: 1.3911941051483154 +[2025-04-29 05:28:00,526][BaseTrainer][INFO] - [Epoch 7/10, Iter 2475/3560] 2.4139604568481445, cross_entropy: 2.4139604568481445 +[2025-04-29 05:28:01,407][BaseTrainer][INFO] - [Epoch 7/10, Iter 2476/3560] 2.8559412956237793, cross_entropy: 2.8559412956237793 +[2025-04-29 05:28:04,104][BaseTrainer][INFO] - [Epoch 7/10, Iter 2477/3560] 2.8538107872009277, cross_entropy: 2.8538107872009277 +[2025-04-29 05:28:04,986][BaseTrainer][INFO] - [Epoch 7/10, Iter 2478/3560] 3.2337160110473633, cross_entropy: 3.2337160110473633 +[2025-04-29 05:28:07,692][BaseTrainer][INFO] - [Epoch 7/10, Iter 2479/3560] 2.155390739440918, cross_entropy: 2.155390739440918 +[2025-04-29 05:28:08,551][BaseTrainer][INFO] - [Epoch 7/10, Iter 2480/3560] 1.3244946002960205, cross_entropy: 1.3244946002960205 +[2025-04-29 05:28:11,684][BaseTrainer][INFO] - [Epoch 7/10, Iter 2481/3560] 1.3753046989440918, cross_entropy: 1.3753046989440918 +[2025-04-29 05:28:12,542][BaseTrainer][INFO] - [Epoch 7/10, Iter 2482/3560] 1.6041040420532227, cross_entropy: 1.6041040420532227 +[2025-04-29 05:28:15,143][BaseTrainer][INFO] - [Epoch 7/10, Iter 2483/3560] 1.645448923110962, cross_entropy: 1.645448923110962 +[2025-04-29 05:28:16,032][BaseTrainer][INFO] - [Epoch 7/10, Iter 2484/3560] 2.3594107627868652, cross_entropy: 2.3594107627868652 +[2025-04-29 05:28:18,972][BaseTrainer][INFO] - [Epoch 7/10, Iter 2485/3560] 1.526861310005188, cross_entropy: 1.526861310005188 +[2025-04-29 05:28:19,830][BaseTrainer][INFO] - [Epoch 7/10, Iter 2486/3560] 1.3181374073028564, cross_entropy: 1.3181374073028564 +[2025-04-29 05:28:22,837][BaseTrainer][INFO] - [Epoch 7/10, Iter 2487/3560] 2.7873239517211914, cross_entropy: 2.7873239517211914 +[2025-04-29 05:28:23,717][BaseTrainer][INFO] - [Epoch 7/10, Iter 2488/3560] 1.456180214881897, cross_entropy: 1.456180214881897 +[2025-04-29 05:28:26,198][BaseTrainer][INFO] - [Epoch 7/10, Iter 2489/3560] 1.4025797843933105, cross_entropy: 1.4025797843933105 +[2025-04-29 05:28:27,055][BaseTrainer][INFO] - [Epoch 7/10, Iter 2490/3560] 2.2578821182250977, cross_entropy: 2.2578821182250977 +[2025-04-29 05:28:29,564][BaseTrainer][INFO] - [Epoch 7/10, Iter 2491/3560] 1.8567984104156494, cross_entropy: 1.8567984104156494 +[2025-04-29 05:28:30,335][BaseTrainer][INFO] - [Epoch 7/10, Iter 2492/3560] 2.963453531265259, cross_entropy: 2.963453531265259 +[2025-04-29 05:31:16,617][BaseTrainer][INFO] - [Epoch 7/10] (train) 2.2339465618133545, cross_entropy: 2.2339465618133545 +[2025-04-29 05:31:16,617][BaseTrainer][INFO] - [Epoch 7/10] (validation) 1.3541619777679443, cross_entropy: 1.3541619777679443 +[2025-04-29 05:31:17,483][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 05:31:17,962][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch7.pth. +[2025-04-29 05:31:18,758][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 05:31:23,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2493/3560] 3.2478978633880615, cross_entropy: 3.2478978633880615 +[2025-04-29 05:31:24,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2494/3560] 2.911992073059082, cross_entropy: 2.911992073059082 +[2025-04-29 05:31:26,704][BaseTrainer][INFO] - [Epoch 8/10, Iter 2495/3560] 1.3015373945236206, cross_entropy: 1.3015373945236206 +[2025-04-29 05:31:27,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2496/3560] 2.628788709640503, cross_entropy: 2.628788709640503 +[2025-04-29 05:31:30,454][BaseTrainer][INFO] - [Epoch 8/10, Iter 2497/3560] 1.4706934690475464, cross_entropy: 1.4706934690475464 +[2025-04-29 05:31:31,338][BaseTrainer][INFO] - [Epoch 8/10, Iter 2498/3560] 2.1533384323120117, cross_entropy: 2.1533384323120117 +[2025-04-29 05:31:34,451][BaseTrainer][INFO] - [Epoch 8/10, Iter 2499/3560] 1.965166687965393, cross_entropy: 1.965166687965393 +[2025-04-29 05:31:35,351][BaseTrainer][INFO] - [Epoch 8/10, Iter 2500/3560] 1.9692009687423706, cross_entropy: 1.9692009687423706 +[2025-04-29 05:31:37,812][BaseTrainer][INFO] - [Epoch 8/10, Iter 2501/3560] 2.0378713607788086, cross_entropy: 2.0378713607788086 +[2025-04-29 05:31:38,697][BaseTrainer][INFO] - [Epoch 8/10, Iter 2502/3560] 1.1277105808258057, cross_entropy: 1.1277105808258057 +[2025-04-29 05:31:41,902][BaseTrainer][INFO] - [Epoch 8/10, Iter 2503/3560] 3.4156594276428223, cross_entropy: 3.4156594276428223 +[2025-04-29 05:31:42,847][BaseTrainer][INFO] - [Epoch 8/10, Iter 2504/3560] 3.1266181468963623, cross_entropy: 3.1266181468963623 +[2025-04-29 05:31:45,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2505/3560] 2.622309446334839, cross_entropy: 2.622309446334839 +[2025-04-29 05:31:46,684][BaseTrainer][INFO] - [Epoch 8/10, Iter 2506/3560] 1.5012142658233643, cross_entropy: 1.5012142658233643 +[2025-04-29 05:31:49,334][BaseTrainer][INFO] - [Epoch 8/10, Iter 2507/3560] 3.1646525859832764, cross_entropy: 3.1646525859832764 +[2025-04-29 05:31:50,471][BaseTrainer][INFO] - [Epoch 8/10, Iter 2508/3560] 3.2224769592285156, cross_entropy: 3.2224769592285156 +[2025-04-29 05:31:52,828][BaseTrainer][INFO] - [Epoch 8/10, Iter 2509/3560] 3.129855155944824, cross_entropy: 3.129855155944824 +[2025-04-29 05:31:55,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2510/3560] 1.15877366065979, cross_entropy: 1.15877366065979 +[2025-04-29 05:31:56,155][BaseTrainer][INFO] - [Epoch 8/10, Iter 2511/3560] 1.3308943510055542, cross_entropy: 1.3308943510055542 +[2025-04-29 05:31:59,300][BaseTrainer][INFO] - [Epoch 8/10, Iter 2512/3560] 1.5731797218322754, cross_entropy: 1.5731797218322754 +[2025-04-29 05:32:00,340][BaseTrainer][INFO] - [Epoch 8/10, Iter 2513/3560] 1.6426618099212646, cross_entropy: 1.6426618099212646 +[2025-04-29 05:32:02,965][BaseTrainer][INFO] - [Epoch 8/10, Iter 2514/3560] 3.2782483100891113, cross_entropy: 3.2782483100891113 +[2025-04-29 05:32:04,156][BaseTrainer][INFO] - [Epoch 8/10, Iter 2515/3560] 1.5994873046875, cross_entropy: 1.5994873046875 +[2025-04-29 05:32:06,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2516/3560] 1.5921087265014648, cross_entropy: 1.5921087265014648 +[2025-04-29 05:32:08,148][BaseTrainer][INFO] - [Epoch 8/10, Iter 2517/3560] 1.5895949602127075, cross_entropy: 1.5895949602127075 +[2025-04-29 05:32:10,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2518/3560] 3.0500521659851074, cross_entropy: 3.0500521659851074 +[2025-04-29 05:32:12,130][BaseTrainer][INFO] - [Epoch 8/10, Iter 2519/3560] 3.3627450466156006, cross_entropy: 3.3627450466156006 +[2025-04-29 05:32:14,449][BaseTrainer][INFO] - [Epoch 8/10, Iter 2520/3560] 3.246915578842163, cross_entropy: 3.246915578842163 +[2025-04-29 05:32:16,999][BaseTrainer][INFO] - [Epoch 8/10, Iter 2521/3560] 1.036285638809204, cross_entropy: 1.036285638809204 +[2025-04-29 05:32:17,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2522/3560] 2.7268433570861816, cross_entropy: 2.7268433570861816 +[2025-04-29 05:32:20,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2523/3560] 1.6162395477294922, cross_entropy: 1.6162395477294922 +[2025-04-29 05:32:21,752][BaseTrainer][INFO] - [Epoch 8/10, Iter 2524/3560] 2.112501621246338, cross_entropy: 2.112501621246338 +[2025-04-29 05:32:23,766][BaseTrainer][INFO] - [Epoch 8/10, Iter 2525/3560] 2.8045685291290283, cross_entropy: 2.8045685291290283 +[2025-04-29 05:32:25,230][BaseTrainer][INFO] - [Epoch 8/10, Iter 2526/3560] 1.0349903106689453, cross_entropy: 1.0349903106689453 +[2025-04-29 05:32:27,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2527/3560] 1.5971721410751343, cross_entropy: 1.5971721410751343 +[2025-04-29 05:32:28,485][BaseTrainer][INFO] - [Epoch 8/10, Iter 2528/3560] 1.4946800470352173, cross_entropy: 1.4946800470352173 +[2025-04-29 05:32:31,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2529/3560] 1.255876064300537, cross_entropy: 1.255876064300537 +[2025-04-29 05:32:32,249][BaseTrainer][INFO] - [Epoch 8/10, Iter 2530/3560] 1.2016206979751587, cross_entropy: 1.2016206979751587 +[2025-04-29 05:32:35,853][BaseTrainer][INFO] - [Epoch 8/10, Iter 2531/3560] 2.7526371479034424, cross_entropy: 2.7526371479034424 +[2025-04-29 05:32:36,792][BaseTrainer][INFO] - [Epoch 8/10, Iter 2532/3560] 2.4480457305908203, cross_entropy: 2.4480457305908203 +[2025-04-29 05:32:39,868][BaseTrainer][INFO] - [Epoch 8/10, Iter 2533/3560] 1.6866283416748047, cross_entropy: 1.6866283416748047 +[2025-04-29 05:32:40,748][BaseTrainer][INFO] - [Epoch 8/10, Iter 2534/3560] 2.8080577850341797, cross_entropy: 2.8080577850341797 +[2025-04-29 05:32:43,638][BaseTrainer][INFO] - [Epoch 8/10, Iter 2535/3560] 1.8791829347610474, cross_entropy: 1.8791829347610474 +[2025-04-29 05:32:44,509][BaseTrainer][INFO] - [Epoch 8/10, Iter 2536/3560] 1.5963504314422607, cross_entropy: 1.5963504314422607 +[2025-04-29 05:32:47,394][BaseTrainer][INFO] - [Epoch 8/10, Iter 2537/3560] 3.054048538208008, cross_entropy: 3.054048538208008 +[2025-04-29 05:32:48,280][BaseTrainer][INFO] - [Epoch 8/10, Iter 2538/3560] 2.8627471923828125, cross_entropy: 2.8627471923828125 +[2025-04-29 05:32:51,245][BaseTrainer][INFO] - [Epoch 8/10, Iter 2539/3560] 1.919801950454712, cross_entropy: 1.919801950454712 +[2025-04-29 05:32:52,107][BaseTrainer][INFO] - [Epoch 8/10, Iter 2540/3560] 1.2360050678253174, cross_entropy: 1.2360050678253174 +[2025-04-29 05:32:55,698][BaseTrainer][INFO] - [Epoch 8/10, Iter 2541/3560] 1.356027603149414, cross_entropy: 1.356027603149414 +[2025-04-29 05:32:56,582][BaseTrainer][INFO] - [Epoch 8/10, Iter 2542/3560] 2.9903390407562256, cross_entropy: 2.9903390407562256 +[2025-04-29 05:32:59,928][BaseTrainer][INFO] - [Epoch 8/10, Iter 2543/3560] 2.101346731185913, cross_entropy: 2.101346731185913 +[2025-04-29 05:33:00,787][BaseTrainer][INFO] - [Epoch 8/10, Iter 2544/3560] 3.374236583709717, cross_entropy: 3.374236583709717 +[2025-04-29 05:33:03,256][BaseTrainer][INFO] - [Epoch 8/10, Iter 2545/3560] 1.744638442993164, cross_entropy: 1.744638442993164 +[2025-04-29 05:33:04,137][BaseTrainer][INFO] - [Epoch 8/10, Iter 2546/3560] 2.52070689201355, cross_entropy: 2.52070689201355 +[2025-04-29 05:33:07,036][BaseTrainer][INFO] - [Epoch 8/10, Iter 2547/3560] 3.107006072998047, cross_entropy: 3.107006072998047 +[2025-04-29 05:33:07,896][BaseTrainer][INFO] - [Epoch 8/10, Iter 2548/3560] 1.3179203271865845, cross_entropy: 1.3179203271865845 +[2025-04-29 05:33:11,700][BaseTrainer][INFO] - [Epoch 8/10, Iter 2549/3560] 2.041835069656372, cross_entropy: 2.041835069656372 +[2025-04-29 05:33:12,556][BaseTrainer][INFO] - [Epoch 8/10, Iter 2550/3560] 2.882737159729004, cross_entropy: 2.882737159729004 +[2025-04-29 05:33:15,327][BaseTrainer][INFO] - [Epoch 8/10, Iter 2551/3560] 3.501206874847412, cross_entropy: 3.501206874847412 +[2025-04-29 05:33:16,209][BaseTrainer][INFO] - [Epoch 8/10, Iter 2552/3560] 2.8964192867279053, cross_entropy: 2.8964192867279053 +[2025-04-29 05:33:18,439][BaseTrainer][INFO] - [Epoch 8/10, Iter 2553/3560] 2.2949411869049072, cross_entropy: 2.2949411869049072 +[2025-04-29 05:33:19,297][BaseTrainer][INFO] - [Epoch 8/10, Iter 2554/3560] 1.484344482421875, cross_entropy: 1.484344482421875 +[2025-04-29 05:33:22,247][BaseTrainer][INFO] - [Epoch 8/10, Iter 2555/3560] 2.3545117378234863, cross_entropy: 2.3545117378234863 +[2025-04-29 05:33:23,129][BaseTrainer][INFO] - [Epoch 8/10, Iter 2556/3560] 3.0187084674835205, cross_entropy: 3.0187084674835205 +[2025-04-29 05:33:25,775][BaseTrainer][INFO] - [Epoch 8/10, Iter 2557/3560] 2.731205701828003, cross_entropy: 2.731205701828003 +[2025-04-29 05:33:26,632][BaseTrainer][INFO] - [Epoch 8/10, Iter 2558/3560] 3.2066493034362793, cross_entropy: 3.2066493034362793 +[2025-04-29 05:33:29,850][BaseTrainer][INFO] - [Epoch 8/10, Iter 2559/3560] 1.2861915826797485, cross_entropy: 1.2861915826797485 +[2025-04-29 05:33:30,729][BaseTrainer][INFO] - [Epoch 8/10, Iter 2560/3560] 1.374506950378418, cross_entropy: 1.374506950378418 +[2025-04-29 05:33:32,960][BaseTrainer][INFO] - [Epoch 8/10, Iter 2561/3560] 2.6005992889404297, cross_entropy: 2.6005992889404297 +[2025-04-29 05:33:33,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2562/3560] 2.3391618728637695, cross_entropy: 2.3391618728637695 +[2025-04-29 05:33:36,887][BaseTrainer][INFO] - [Epoch 8/10, Iter 2563/3560] 1.4462299346923828, cross_entropy: 1.4462299346923828 +[2025-04-29 05:33:37,743][BaseTrainer][INFO] - [Epoch 8/10, Iter 2564/3560] 1.6445305347442627, cross_entropy: 1.6445305347442627 +[2025-04-29 05:33:40,627][BaseTrainer][INFO] - [Epoch 8/10, Iter 2565/3560] 1.0493278503417969, cross_entropy: 1.0493278503417969 +[2025-04-29 05:33:41,528][BaseTrainer][INFO] - [Epoch 8/10, Iter 2566/3560] 1.2645713090896606, cross_entropy: 1.2645713090896606 +[2025-04-29 05:33:44,108][BaseTrainer][INFO] - [Epoch 8/10, Iter 2567/3560] 1.4554499387741089, cross_entropy: 1.4554499387741089 +[2025-04-29 05:33:44,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2568/3560] 2.730619430541992, cross_entropy: 2.730619430541992 +[2025-04-29 05:33:47,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2569/3560] 1.824434757232666, cross_entropy: 1.824434757232666 +[2025-04-29 05:33:48,341][BaseTrainer][INFO] - [Epoch 8/10, Iter 2570/3560] 1.3921188116073608, cross_entropy: 1.3921188116073608 +[2025-04-29 05:33:50,450][BaseTrainer][INFO] - [Epoch 8/10, Iter 2571/3560] 1.5290858745574951, cross_entropy: 1.5290858745574951 +[2025-04-29 05:33:51,307][BaseTrainer][INFO] - [Epoch 8/10, Iter 2572/3560] 2.407813549041748, cross_entropy: 2.407813549041748 +[2025-04-29 05:33:54,143][BaseTrainer][INFO] - [Epoch 8/10, Iter 2573/3560] 2.309324026107788, cross_entropy: 2.309324026107788 +[2025-04-29 05:33:55,002][BaseTrainer][INFO] - [Epoch 8/10, Iter 2574/3560] 1.7429018020629883, cross_entropy: 1.7429018020629883 +[2025-04-29 05:33:58,219][BaseTrainer][INFO] - [Epoch 8/10, Iter 2575/3560] 0.8866293430328369, cross_entropy: 0.8866293430328369 +[2025-04-29 05:33:59,076][BaseTrainer][INFO] - [Epoch 8/10, Iter 2576/3560] 1.3936247825622559, cross_entropy: 1.3936247825622559 +[2025-04-29 05:34:02,140][BaseTrainer][INFO] - [Epoch 8/10, Iter 2577/3560] 1.9280401468276978, cross_entropy: 1.9280401468276978 +[2025-04-29 05:34:02,997][BaseTrainer][INFO] - [Epoch 8/10, Iter 2578/3560] 2.6818408966064453, cross_entropy: 2.6818408966064453 +[2025-04-29 05:34:06,501][BaseTrainer][INFO] - [Epoch 8/10, Iter 2579/3560] 2.5502309799194336, cross_entropy: 2.5502309799194336 +[2025-04-29 05:34:07,379][BaseTrainer][INFO] - [Epoch 8/10, Iter 2580/3560] 3.1373488903045654, cross_entropy: 3.1373488903045654 +[2025-04-29 05:34:09,662][BaseTrainer][INFO] - [Epoch 8/10, Iter 2581/3560] 2.866006374359131, cross_entropy: 2.866006374359131 +[2025-04-29 05:34:10,546][BaseTrainer][INFO] - [Epoch 8/10, Iter 2582/3560] 2.977555274963379, cross_entropy: 2.977555274963379 +[2025-04-29 05:34:13,342][BaseTrainer][INFO] - [Epoch 8/10, Iter 2583/3560] 1.259116768836975, cross_entropy: 1.259116768836975 +[2025-04-29 05:34:14,235][BaseTrainer][INFO] - [Epoch 8/10, Iter 2584/3560] 3.4003238677978516, cross_entropy: 3.4003238677978516 +[2025-04-29 05:34:16,939][BaseTrainer][INFO] - [Epoch 8/10, Iter 2585/3560] 3.2364463806152344, cross_entropy: 3.2364463806152344 +[2025-04-29 05:34:17,799][BaseTrainer][INFO] - [Epoch 8/10, Iter 2586/3560] 2.309662342071533, cross_entropy: 2.309662342071533 +[2025-04-29 05:34:21,343][BaseTrainer][INFO] - [Epoch 8/10, Iter 2587/3560] 1.6008121967315674, cross_entropy: 1.6008121967315674 +[2025-04-29 05:34:22,225][BaseTrainer][INFO] - [Epoch 8/10, Iter 2588/3560] 1.9288402795791626, cross_entropy: 1.9288402795791626 +[2025-04-29 05:34:26,456][BaseTrainer][INFO] - [Epoch 8/10, Iter 2589/3560] 2.186455726623535, cross_entropy: 2.186455726623535 +[2025-04-29 05:34:27,338][BaseTrainer][INFO] - [Epoch 8/10, Iter 2590/3560] 2.5317511558532715, cross_entropy: 2.5317511558532715 +[2025-04-29 05:34:30,183][BaseTrainer][INFO] - [Epoch 8/10, Iter 2591/3560] 1.6412545442581177, cross_entropy: 1.6412545442581177 +[2025-04-29 05:34:31,043][BaseTrainer][INFO] - [Epoch 8/10, Iter 2592/3560] 3.2060484886169434, cross_entropy: 3.2060484886169434 +[2025-04-29 05:34:34,263][BaseTrainer][INFO] - [Epoch 8/10, Iter 2593/3560] 2.316988468170166, cross_entropy: 2.316988468170166 +[2025-04-29 05:34:35,146][BaseTrainer][INFO] - [Epoch 8/10, Iter 2594/3560] 3.0808849334716797, cross_entropy: 3.0808849334716797 +[2025-04-29 05:34:36,917][BaseTrainer][INFO] - [Epoch 8/10, Iter 2595/3560] 1.7087349891662598, cross_entropy: 1.7087349891662598 +[2025-04-29 05:34:37,804][BaseTrainer][INFO] - [Epoch 8/10, Iter 2596/3560] 1.2891417741775513, cross_entropy: 1.2891417741775513 +[2025-04-29 05:34:40,040][BaseTrainer][INFO] - [Epoch 8/10, Iter 2597/3560] 1.8099242448806763, cross_entropy: 1.8099242448806763 +[2025-04-29 05:34:40,953][BaseTrainer][INFO] - [Epoch 8/10, Iter 2598/3560] 1.1851930618286133, cross_entropy: 1.1851930618286133 +[2025-04-29 05:34:43,797][BaseTrainer][INFO] - [Epoch 8/10, Iter 2599/3560] 1.2703611850738525, cross_entropy: 1.2703611850738525 +[2025-04-29 05:34:44,655][BaseTrainer][INFO] - [Epoch 8/10, Iter 2600/3560] 3.159180164337158, cross_entropy: 3.159180164337158 +[2025-04-29 05:34:47,845][BaseTrainer][INFO] - [Epoch 8/10, Iter 2601/3560] 1.8343666791915894, cross_entropy: 1.8343666791915894 +[2025-04-29 05:34:48,717][BaseTrainer][INFO] - [Epoch 8/10, Iter 2602/3560] 1.415541172027588, cross_entropy: 1.415541172027588 +[2025-04-29 05:34:51,334][BaseTrainer][INFO] - [Epoch 8/10, Iter 2603/3560] 1.7907752990722656, cross_entropy: 1.7907752990722656 +[2025-04-29 05:34:52,193][BaseTrainer][INFO] - [Epoch 8/10, Iter 2604/3560] 1.5560134649276733, cross_entropy: 1.5560134649276733 +[2025-04-29 05:34:54,963][BaseTrainer][INFO] - [Epoch 8/10, Iter 2605/3560] 1.624157190322876, cross_entropy: 1.624157190322876 +[2025-04-29 05:34:55,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2606/3560] 2.7049684524536133, cross_entropy: 2.7049684524536133 +[2025-04-29 05:34:58,531][BaseTrainer][INFO] - [Epoch 8/10, Iter 2607/3560] 2.8142476081848145, cross_entropy: 2.8142476081848145 +[2025-04-29 05:34:59,397][BaseTrainer][INFO] - [Epoch 8/10, Iter 2608/3560] 2.894458293914795, cross_entropy: 2.894458293914795 +[2025-04-29 05:35:02,230][BaseTrainer][INFO] - [Epoch 8/10, Iter 2609/3560] 2.0303492546081543, cross_entropy: 2.0303492546081543 +[2025-04-29 05:35:03,112][BaseTrainer][INFO] - [Epoch 8/10, Iter 2610/3560] 3.0571932792663574, cross_entropy: 3.0571932792663574 +[2025-04-29 05:35:05,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2611/3560] 1.4476269483566284, cross_entropy: 1.4476269483566284 +[2025-04-29 05:35:06,238][BaseTrainer][INFO] - [Epoch 8/10, Iter 2612/3560] 1.2582173347473145, cross_entropy: 1.2582173347473145 +[2025-04-29 05:35:09,001][BaseTrainer][INFO] - [Epoch 8/10, Iter 2613/3560] 1.584537148475647, cross_entropy: 1.584537148475647 +[2025-04-29 05:35:09,860][BaseTrainer][INFO] - [Epoch 8/10, Iter 2614/3560] 1.8268357515335083, cross_entropy: 1.8268357515335083 +[2025-04-29 05:35:12,732][BaseTrainer][INFO] - [Epoch 8/10, Iter 2615/3560] 2.848362922668457, cross_entropy: 2.848362922668457 +[2025-04-29 05:35:13,612][BaseTrainer][INFO] - [Epoch 8/10, Iter 2616/3560] 3.0517568588256836, cross_entropy: 3.0517568588256836 +[2025-04-29 05:35:16,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2617/3560] 3.154860258102417, cross_entropy: 3.154860258102417 +[2025-04-29 05:35:17,344][BaseTrainer][INFO] - [Epoch 8/10, Iter 2618/3560] 3.0626306533813477, cross_entropy: 3.0626306533813477 +[2025-04-29 05:35:21,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2619/3560] 2.411935329437256, cross_entropy: 2.411935329437256 +[2025-04-29 05:35:22,329][BaseTrainer][INFO] - [Epoch 8/10, Iter 2620/3560] 1.9361953735351562, cross_entropy: 1.9361953735351562 +[2025-04-29 05:35:25,460][BaseTrainer][INFO] - [Epoch 8/10, Iter 2621/3560] 3.1912314891815186, cross_entropy: 3.1912314891815186 +[2025-04-29 05:35:26,322][BaseTrainer][INFO] - [Epoch 8/10, Iter 2622/3560] 2.8669965267181396, cross_entropy: 2.8669965267181396 +[2025-04-29 05:35:28,449][BaseTrainer][INFO] - [Epoch 8/10, Iter 2623/3560] 1.8879923820495605, cross_entropy: 1.8879923820495605 +[2025-04-29 05:35:29,332][BaseTrainer][INFO] - [Epoch 8/10, Iter 2624/3560] 1.957761526107788, cross_entropy: 1.957761526107788 +[2025-04-29 05:35:32,214][BaseTrainer][INFO] - [Epoch 8/10, Iter 2625/3560] 1.7084546089172363, cross_entropy: 1.7084546089172363 +[2025-04-29 05:35:33,100][BaseTrainer][INFO] - [Epoch 8/10, Iter 2626/3560] 3.100158214569092, cross_entropy: 3.100158214569092 +[2025-04-29 05:35:35,696][BaseTrainer][INFO] - [Epoch 8/10, Iter 2627/3560] 1.7475547790527344, cross_entropy: 1.7475547790527344 +[2025-04-29 05:35:36,584][BaseTrainer][INFO] - [Epoch 8/10, Iter 2628/3560] 1.8303673267364502, cross_entropy: 1.8303673267364502 +[2025-04-29 05:35:39,275][BaseTrainer][INFO] - [Epoch 8/10, Iter 2629/3560] 2.1975841522216797, cross_entropy: 2.1975841522216797 +[2025-04-29 05:35:40,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2630/3560] 3.2712066173553467, cross_entropy: 3.2712066173553467 +[2025-04-29 05:35:42,880][BaseTrainer][INFO] - [Epoch 8/10, Iter 2631/3560] 1.8483026027679443, cross_entropy: 1.8483026027679443 +[2025-04-29 05:35:43,738][BaseTrainer][INFO] - [Epoch 8/10, Iter 2632/3560] 1.662353277206421, cross_entropy: 1.662353277206421 +[2025-04-29 05:35:46,857][BaseTrainer][INFO] - [Epoch 8/10, Iter 2633/3560] 1.4998345375061035, cross_entropy: 1.4998345375061035 +[2025-04-29 05:35:47,714][BaseTrainer][INFO] - [Epoch 8/10, Iter 2634/3560] 1.4020684957504272, cross_entropy: 1.4020684957504272 +[2025-04-29 05:35:50,519][BaseTrainer][INFO] - [Epoch 8/10, Iter 2635/3560] 1.612412929534912, cross_entropy: 1.612412929534912 +[2025-04-29 05:35:51,380][BaseTrainer][INFO] - [Epoch 8/10, Iter 2636/3560] 1.5676548480987549, cross_entropy: 1.5676548480987549 +[2025-04-29 05:35:54,060][BaseTrainer][INFO] - [Epoch 8/10, Iter 2637/3560] 1.6679195165634155, cross_entropy: 1.6679195165634155 +[2025-04-29 05:35:54,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2638/3560] 2.3626365661621094, cross_entropy: 2.3626365661621094 +[2025-04-29 05:35:57,803][BaseTrainer][INFO] - [Epoch 8/10, Iter 2639/3560] 2.4058573246002197, cross_entropy: 2.4058573246002197 +[2025-04-29 05:35:58,686][BaseTrainer][INFO] - [Epoch 8/10, Iter 2640/3560] 3.078618049621582, cross_entropy: 3.078618049621582 +[2025-04-29 05:36:00,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2641/3560] 2.9174418449401855, cross_entropy: 2.9174418449401855 +[2025-04-29 05:36:01,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2642/3560] 2.6571455001831055, cross_entropy: 2.6571455001831055 +[2025-04-29 05:36:04,536][BaseTrainer][INFO] - [Epoch 8/10, Iter 2643/3560] 2.3219518661499023, cross_entropy: 2.3219518661499023 +[2025-04-29 05:36:05,416][BaseTrainer][INFO] - [Epoch 8/10, Iter 2644/3560] 1.0628803968429565, cross_entropy: 1.0628803968429565 +[2025-04-29 05:36:07,721][BaseTrainer][INFO] - [Epoch 8/10, Iter 2645/3560] 1.3542561531066895, cross_entropy: 1.3542561531066895 +[2025-04-29 05:36:08,601][BaseTrainer][INFO] - [Epoch 8/10, Iter 2646/3560] 3.1416406631469727, cross_entropy: 3.1416406631469727 +[2025-04-29 05:36:10,989][BaseTrainer][INFO] - [Epoch 8/10, Iter 2647/3560] 1.3049037456512451, cross_entropy: 1.3049037456512451 +[2025-04-29 05:36:11,878][BaseTrainer][INFO] - [Epoch 8/10, Iter 2648/3560] 1.9696605205535889, cross_entropy: 1.9696605205535889 +[2025-04-29 05:36:14,338][BaseTrainer][INFO] - [Epoch 8/10, Iter 2649/3560] 2.5968079566955566, cross_entropy: 2.5968079566955566 +[2025-04-29 05:36:15,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2650/3560] 2.326639413833618, cross_entropy: 2.326639413833618 +[2025-04-29 05:36:17,890][BaseTrainer][INFO] - [Epoch 8/10, Iter 2651/3560] 2.9188990592956543, cross_entropy: 2.9188990592956543 +[2025-04-29 05:36:18,750][BaseTrainer][INFO] - [Epoch 8/10, Iter 2652/3560] 1.0525739192962646, cross_entropy: 1.0525739192962646 +[2025-04-29 05:36:21,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2653/3560] 1.6873016357421875, cross_entropy: 1.6873016357421875 +[2025-04-29 05:36:22,797][BaseTrainer][INFO] - [Epoch 8/10, Iter 2654/3560] 1.3594250679016113, cross_entropy: 1.3594250679016113 +[2025-04-29 05:36:25,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2655/3560] 1.31936776638031, cross_entropy: 1.31936776638031 +[2025-04-29 05:36:26,459][BaseTrainer][INFO] - [Epoch 8/10, Iter 2656/3560] 3.133841037750244, cross_entropy: 3.133841037750244 +[2025-04-29 05:36:29,622][BaseTrainer][INFO] - [Epoch 8/10, Iter 2657/3560] 1.4641716480255127, cross_entropy: 1.4641716480255127 +[2025-04-29 05:36:30,501][BaseTrainer][INFO] - [Epoch 8/10, Iter 2658/3560] 1.3192657232284546, cross_entropy: 1.3192657232284546 +[2025-04-29 05:36:33,502][BaseTrainer][INFO] - [Epoch 8/10, Iter 2659/3560] 2.1880931854248047, cross_entropy: 2.1880931854248047 +[2025-04-29 05:36:34,383][BaseTrainer][INFO] - [Epoch 8/10, Iter 2660/3560] 1.0772254467010498, cross_entropy: 1.0772254467010498 +[2025-04-29 05:36:37,062][BaseTrainer][INFO] - [Epoch 8/10, Iter 2661/3560] 2.09299373626709, cross_entropy: 2.09299373626709 +[2025-04-29 05:36:37,922][BaseTrainer][INFO] - [Epoch 8/10, Iter 2662/3560] 2.1028518676757812, cross_entropy: 2.1028518676757812 +[2025-04-29 05:36:40,475][BaseTrainer][INFO] - [Epoch 8/10, Iter 2663/3560] 1.632117509841919, cross_entropy: 1.632117509841919 +[2025-04-29 05:36:41,339][BaseTrainer][INFO] - [Epoch 8/10, Iter 2664/3560] 1.6877052783966064, cross_entropy: 1.6877052783966064 +[2025-04-29 05:36:44,141][BaseTrainer][INFO] - [Epoch 8/10, Iter 2665/3560] 2.5110225677490234, cross_entropy: 2.5110225677490234 +[2025-04-29 05:36:45,025][BaseTrainer][INFO] - [Epoch 8/10, Iter 2666/3560] 1.1444674730300903, cross_entropy: 1.1444674730300903 +[2025-04-29 05:36:47,874][BaseTrainer][INFO] - [Epoch 8/10, Iter 2667/3560] 1.1823570728302002, cross_entropy: 1.1823570728302002 +[2025-04-29 05:36:48,755][BaseTrainer][INFO] - [Epoch 8/10, Iter 2668/3560] 1.1114004850387573, cross_entropy: 1.1114004850387573 +[2025-04-29 05:36:51,382][BaseTrainer][INFO] - [Epoch 8/10, Iter 2669/3560] 1.1546529531478882, cross_entropy: 1.1546529531478882 +[2025-04-29 05:36:52,273][BaseTrainer][INFO] - [Epoch 8/10, Iter 2670/3560] 1.3614099025726318, cross_entropy: 1.3614099025726318 +[2025-04-29 05:36:55,543][BaseTrainer][INFO] - [Epoch 8/10, Iter 2671/3560] 1.4353421926498413, cross_entropy: 1.4353421926498413 +[2025-04-29 05:36:56,421][BaseTrainer][INFO] - [Epoch 8/10, Iter 2672/3560] 1.3778884410858154, cross_entropy: 1.3778884410858154 +[2025-04-29 05:36:58,889][BaseTrainer][INFO] - [Epoch 8/10, Iter 2673/3560] 2.4605350494384766, cross_entropy: 2.4605350494384766 +[2025-04-29 05:36:59,777][BaseTrainer][INFO] - [Epoch 8/10, Iter 2674/3560] 2.9770140647888184, cross_entropy: 2.9770140647888184 +[2025-04-29 05:37:02,600][BaseTrainer][INFO] - [Epoch 8/10, Iter 2675/3560] 3.0084409713745117, cross_entropy: 3.0084409713745117 +[2025-04-29 05:37:03,481][BaseTrainer][INFO] - [Epoch 8/10, Iter 2676/3560] 3.2644572257995605, cross_entropy: 3.2644572257995605 +[2025-04-29 05:37:06,115][BaseTrainer][INFO] - [Epoch 8/10, Iter 2677/3560] 2.621652603149414, cross_entropy: 2.621652603149414 +[2025-04-29 05:37:07,000][BaseTrainer][INFO] - [Epoch 8/10, Iter 2678/3560] 1.640872836112976, cross_entropy: 1.640872836112976 +[2025-04-29 05:37:09,331][BaseTrainer][INFO] - [Epoch 8/10, Iter 2679/3560] 3.013955593109131, cross_entropy: 3.013955593109131 +[2025-04-29 05:37:10,220][BaseTrainer][INFO] - [Epoch 8/10, Iter 2680/3560] 1.5492222309112549, cross_entropy: 1.5492222309112549 +[2025-04-29 05:37:13,091][BaseTrainer][INFO] - [Epoch 8/10, Iter 2681/3560] 1.6143882274627686, cross_entropy: 1.6143882274627686 +[2025-04-29 05:37:13,975][BaseTrainer][INFO] - [Epoch 8/10, Iter 2682/3560] 3.295809745788574, cross_entropy: 3.295809745788574 +[2025-04-29 05:37:16,317][BaseTrainer][INFO] - [Epoch 8/10, Iter 2683/3560] 2.6984407901763916, cross_entropy: 2.6984407901763916 +[2025-04-29 05:37:17,201][BaseTrainer][INFO] - [Epoch 8/10, Iter 2684/3560] 1.744314432144165, cross_entropy: 1.744314432144165 +[2025-04-29 05:37:19,859][BaseTrainer][INFO] - [Epoch 8/10, Iter 2685/3560] 3.2582449913024902, cross_entropy: 3.2582449913024902 +[2025-04-29 05:37:20,741][BaseTrainer][INFO] - [Epoch 8/10, Iter 2686/3560] 1.7014927864074707, cross_entropy: 1.7014927864074707 +[2025-04-29 05:37:23,860][BaseTrainer][INFO] - [Epoch 8/10, Iter 2687/3560] 2.814988136291504, cross_entropy: 2.814988136291504 +[2025-04-29 05:37:24,719][BaseTrainer][INFO] - [Epoch 8/10, Iter 2688/3560] 0.912065863609314, cross_entropy: 0.912065863609314 +[2025-04-29 05:37:27,481][BaseTrainer][INFO] - [Epoch 8/10, Iter 2689/3560] 1.3762534856796265, cross_entropy: 1.3762534856796265 +[2025-04-29 05:37:28,363][BaseTrainer][INFO] - [Epoch 8/10, Iter 2690/3560] 3.1289801597595215, cross_entropy: 3.1289801597595215 +[2025-04-29 05:37:30,909][BaseTrainer][INFO] - [Epoch 8/10, Iter 2691/3560] 3.2269420623779297, cross_entropy: 3.2269420623779297 +[2025-04-29 05:37:31,768][BaseTrainer][INFO] - [Epoch 8/10, Iter 2692/3560] 3.2184085845947266, cross_entropy: 3.2184085845947266 +[2025-04-29 05:37:35,842][BaseTrainer][INFO] - [Epoch 8/10, Iter 2693/3560] 1.2968804836273193, cross_entropy: 1.2968804836273193 +[2025-04-29 05:37:36,704][BaseTrainer][INFO] - [Epoch 8/10, Iter 2694/3560] 2.7235989570617676, cross_entropy: 2.7235989570617676 +[2025-04-29 05:37:39,294][BaseTrainer][INFO] - [Epoch 8/10, Iter 2695/3560] 2.2541375160217285, cross_entropy: 2.2541375160217285 +[2025-04-29 05:37:40,168][BaseTrainer][INFO] - [Epoch 8/10, Iter 2696/3560] 2.985226631164551, cross_entropy: 2.985226631164551 +[2025-04-29 05:37:42,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2697/3560] 3.2912275791168213, cross_entropy: 3.2912275791168213 +[2025-04-29 05:37:43,440][BaseTrainer][INFO] - [Epoch 8/10, Iter 2698/3560] 3.066819667816162, cross_entropy: 3.066819667816162 +[2025-04-29 05:37:45,619][BaseTrainer][INFO] - [Epoch 8/10, Iter 2699/3560] 2.423776388168335, cross_entropy: 2.423776388168335 +[2025-04-29 05:37:46,479][BaseTrainer][INFO] - [Epoch 8/10, Iter 2700/3560] 2.9214487075805664, cross_entropy: 2.9214487075805664 +[2025-04-29 05:37:49,355][BaseTrainer][INFO] - [Epoch 8/10, Iter 2701/3560] 1.5060253143310547, cross_entropy: 1.5060253143310547 +[2025-04-29 05:37:50,216][BaseTrainer][INFO] - [Epoch 8/10, Iter 2702/3560] 3.0382516384124756, cross_entropy: 3.0382516384124756 +[2025-04-29 05:37:53,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2703/3560] 1.2660090923309326, cross_entropy: 1.2660090923309326 +[2025-04-29 05:37:54,057][BaseTrainer][INFO] - [Epoch 8/10, Iter 2704/3560] 2.933253288269043, cross_entropy: 2.933253288269043 +[2025-04-29 05:37:57,100][BaseTrainer][INFO] - [Epoch 8/10, Iter 2705/3560] 1.725624680519104, cross_entropy: 1.725624680519104 +[2025-04-29 05:37:57,976][BaseTrainer][INFO] - [Epoch 8/10, Iter 2706/3560] 1.439833641052246, cross_entropy: 1.439833641052246 +[2025-04-29 05:38:00,996][BaseTrainer][INFO] - [Epoch 8/10, Iter 2707/3560] 3.0174975395202637, cross_entropy: 3.0174975395202637 +[2025-04-29 05:38:01,873][BaseTrainer][INFO] - [Epoch 8/10, Iter 2708/3560] 1.521543264389038, cross_entropy: 1.521543264389038 +[2025-04-29 05:38:05,091][BaseTrainer][INFO] - [Epoch 8/10, Iter 2709/3560] 3.1224842071533203, cross_entropy: 3.1224842071533203 +[2025-04-29 05:38:05,953][BaseTrainer][INFO] - [Epoch 8/10, Iter 2710/3560] 2.8541040420532227, cross_entropy: 2.8541040420532227 +[2025-04-29 05:38:09,354][BaseTrainer][INFO] - [Epoch 8/10, Iter 2711/3560] 3.103898763656616, cross_entropy: 3.103898763656616 +[2025-04-29 05:38:10,218][BaseTrainer][INFO] - [Epoch 8/10, Iter 2712/3560] 2.943411111831665, cross_entropy: 2.943411111831665 +[2025-04-29 05:38:12,741][BaseTrainer][INFO] - [Epoch 8/10, Iter 2713/3560] 1.5251586437225342, cross_entropy: 1.5251586437225342 +[2025-04-29 05:38:13,601][BaseTrainer][INFO] - [Epoch 8/10, Iter 2714/3560] 3.362579822540283, cross_entropy: 3.362579822540283 +[2025-04-29 05:38:16,167][BaseTrainer][INFO] - [Epoch 8/10, Iter 2715/3560] 1.485111951828003, cross_entropy: 1.485111951828003 +[2025-04-29 05:38:17,055][BaseTrainer][INFO] - [Epoch 8/10, Iter 2716/3560] 1.2334668636322021, cross_entropy: 1.2334668636322021 +[2025-04-29 05:38:19,944][BaseTrainer][INFO] - [Epoch 8/10, Iter 2717/3560] 1.2768559455871582, cross_entropy: 1.2768559455871582 +[2025-04-29 05:38:20,824][BaseTrainer][INFO] - [Epoch 8/10, Iter 2718/3560] 1.1402883529663086, cross_entropy: 1.1402883529663086 +[2025-04-29 05:38:23,560][BaseTrainer][INFO] - [Epoch 8/10, Iter 2719/3560] 1.974616527557373, cross_entropy: 1.974616527557373 +[2025-04-29 05:38:24,442][BaseTrainer][INFO] - [Epoch 8/10, Iter 2720/3560] 1.4593093395233154, cross_entropy: 1.4593093395233154 +[2025-04-29 05:38:27,443][BaseTrainer][INFO] - [Epoch 8/10, Iter 2721/3560] 3.063824415206909, cross_entropy: 3.063824415206909 +[2025-04-29 05:38:28,302][BaseTrainer][INFO] - [Epoch 8/10, Iter 2722/3560] 3.079592227935791, cross_entropy: 3.079592227935791 +[2025-04-29 05:38:32,414][BaseTrainer][INFO] - [Epoch 8/10, Iter 2723/3560] 2.8333582878112793, cross_entropy: 2.8333582878112793 +[2025-04-29 05:38:33,283][BaseTrainer][INFO] - [Epoch 8/10, Iter 2724/3560] 1.5947680473327637, cross_entropy: 1.5947680473327637 +[2025-04-29 05:38:36,214][BaseTrainer][INFO] - [Epoch 8/10, Iter 2725/3560] 3.0999178886413574, cross_entropy: 3.0999178886413574 +[2025-04-29 05:38:37,099][BaseTrainer][INFO] - [Epoch 8/10, Iter 2726/3560] 3.2595386505126953, cross_entropy: 3.2595386505126953 +[2025-04-29 05:38:40,142][BaseTrainer][INFO] - [Epoch 8/10, Iter 2727/3560] 1.9638023376464844, cross_entropy: 1.9638023376464844 +[2025-04-29 05:38:40,998][BaseTrainer][INFO] - [Epoch 8/10, Iter 2728/3560] 3.0221519470214844, cross_entropy: 3.0221519470214844 +[2025-04-29 05:38:43,656][BaseTrainer][INFO] - [Epoch 8/10, Iter 2729/3560] 1.5202752351760864, cross_entropy: 1.5202752351760864 +[2025-04-29 05:38:44,541][BaseTrainer][INFO] - [Epoch 8/10, Iter 2730/3560] 3.0357511043548584, cross_entropy: 3.0357511043548584 +[2025-04-29 05:38:47,310][BaseTrainer][INFO] - [Epoch 8/10, Iter 2731/3560] 2.5017318725585938, cross_entropy: 2.5017318725585938 +[2025-04-29 05:38:48,196][BaseTrainer][INFO] - [Epoch 8/10, Iter 2732/3560] 2.705687999725342, cross_entropy: 2.705687999725342 +[2025-04-29 05:38:50,468][BaseTrainer][INFO] - [Epoch 8/10, Iter 2733/3560] 3.0481832027435303, cross_entropy: 3.0481832027435303 +[2025-04-29 05:38:51,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2734/3560] 2.9901089668273926, cross_entropy: 2.9901089668273926 +[2025-04-29 05:38:53,847][BaseTrainer][INFO] - [Epoch 8/10, Iter 2735/3560] 2.5278613567352295, cross_entropy: 2.5278613567352295 +[2025-04-29 05:38:54,702][BaseTrainer][INFO] - [Epoch 8/10, Iter 2736/3560] 1.381608486175537, cross_entropy: 1.381608486175537 +[2025-04-29 05:38:57,571][BaseTrainer][INFO] - [Epoch 8/10, Iter 2737/3560] 1.3130989074707031, cross_entropy: 1.3130989074707031 +[2025-04-29 05:38:58,561][BaseTrainer][INFO] - [Epoch 8/10, Iter 2738/3560] 2.958552122116089, cross_entropy: 2.958552122116089 +[2025-04-29 05:39:01,698][BaseTrainer][INFO] - [Epoch 8/10, Iter 2739/3560] 2.511958122253418, cross_entropy: 2.511958122253418 +[2025-04-29 05:39:02,583][BaseTrainer][INFO] - [Epoch 8/10, Iter 2740/3560] 1.505951166152954, cross_entropy: 1.505951166152954 +[2025-04-29 05:39:05,520][BaseTrainer][INFO] - [Epoch 8/10, Iter 2741/3560] 2.126875162124634, cross_entropy: 2.126875162124634 +[2025-04-29 05:39:06,378][BaseTrainer][INFO] - [Epoch 8/10, Iter 2742/3560] 1.4005030393600464, cross_entropy: 1.4005030393600464 +[2025-04-29 05:39:09,418][BaseTrainer][INFO] - [Epoch 8/10, Iter 2743/3560] 3.2587785720825195, cross_entropy: 3.2587785720825195 +[2025-04-29 05:39:10,306][BaseTrainer][INFO] - [Epoch 8/10, Iter 2744/3560] 3.161512851715088, cross_entropy: 3.161512851715088 +[2025-04-29 05:39:12,856][BaseTrainer][INFO] - [Epoch 8/10, Iter 2745/3560] 1.6937816143035889, cross_entropy: 1.6937816143035889 +[2025-04-29 05:39:13,737][BaseTrainer][INFO] - [Epoch 8/10, Iter 2746/3560] 1.8437933921813965, cross_entropy: 1.8437933921813965 +[2025-04-29 05:39:16,366][BaseTrainer][INFO] - [Epoch 8/10, Iter 2747/3560] 1.6559576988220215, cross_entropy: 1.6559576988220215 +[2025-04-29 05:39:17,227][BaseTrainer][INFO] - [Epoch 8/10, Iter 2748/3560] 3.2146081924438477, cross_entropy: 3.2146081924438477 +[2025-04-29 05:39:19,463][BaseTrainer][INFO] - [Epoch 8/10, Iter 2749/3560] 1.6880415678024292, cross_entropy: 1.6880415678024292 +[2025-04-29 05:39:20,347][BaseTrainer][INFO] - [Epoch 8/10, Iter 2750/3560] 1.1724891662597656, cross_entropy: 1.1724891662597656 +[2025-04-29 05:39:23,146][BaseTrainer][INFO] - [Epoch 8/10, Iter 2751/3560] 1.6460100412368774, cross_entropy: 1.6460100412368774 +[2025-04-29 05:39:24,029][BaseTrainer][INFO] - [Epoch 8/10, Iter 2752/3560] 3.2689032554626465, cross_entropy: 3.2689032554626465 +[2025-04-29 05:39:26,623][BaseTrainer][INFO] - [Epoch 8/10, Iter 2753/3560] 1.863946795463562, cross_entropy: 1.863946795463562 +[2025-04-29 05:39:27,485][BaseTrainer][INFO] - [Epoch 8/10, Iter 2754/3560] 3.2336184978485107, cross_entropy: 3.2336184978485107 +[2025-04-29 05:39:30,904][BaseTrainer][INFO] - [Epoch 8/10, Iter 2755/3560] 1.988718032836914, cross_entropy: 1.988718032836914 +[2025-04-29 05:39:31,766][BaseTrainer][INFO] - [Epoch 8/10, Iter 2756/3560] 1.5338506698608398, cross_entropy: 1.5338506698608398 +[2025-04-29 05:39:34,359][BaseTrainer][INFO] - [Epoch 8/10, Iter 2757/3560] 2.6827754974365234, cross_entropy: 2.6827754974365234 +[2025-04-29 05:39:35,252][BaseTrainer][INFO] - [Epoch 8/10, Iter 2758/3560] 1.6168994903564453, cross_entropy: 1.6168994903564453 +[2025-04-29 05:39:39,152][BaseTrainer][INFO] - [Epoch 8/10, Iter 2759/3560] 1.813420295715332, cross_entropy: 1.813420295715332 +[2025-04-29 05:39:40,039][BaseTrainer][INFO] - [Epoch 8/10, Iter 2760/3560] 3.021703004837036, cross_entropy: 3.021703004837036 +[2025-04-29 05:39:43,038][BaseTrainer][INFO] - [Epoch 8/10, Iter 2761/3560] 1.5234341621398926, cross_entropy: 1.5234341621398926 +[2025-04-29 05:39:43,927][BaseTrainer][INFO] - [Epoch 8/10, Iter 2762/3560] 3.426827907562256, cross_entropy: 3.426827907562256 +[2025-04-29 05:39:46,770][BaseTrainer][INFO] - [Epoch 8/10, Iter 2763/3560] 3.167398452758789, cross_entropy: 3.167398452758789 +[2025-04-29 05:39:47,654][BaseTrainer][INFO] - [Epoch 8/10, Iter 2764/3560] 1.3435494899749756, cross_entropy: 1.3435494899749756 +[2025-04-29 05:39:50,133][BaseTrainer][INFO] - [Epoch 8/10, Iter 2765/3560] 1.6760895252227783, cross_entropy: 1.6760895252227783 +[2025-04-29 05:39:51,016][BaseTrainer][INFO] - [Epoch 8/10, Iter 2766/3560] 2.1404335498809814, cross_entropy: 2.1404335498809814 +[2025-04-29 05:39:53,146][BaseTrainer][INFO] - [Epoch 8/10, Iter 2767/3560] 2.98544979095459, cross_entropy: 2.98544979095459 +[2025-04-29 05:39:54,034][BaseTrainer][INFO] - [Epoch 8/10, Iter 2768/3560] 1.503272294998169, cross_entropy: 1.503272294998169 +[2025-04-29 05:39:56,255][BaseTrainer][INFO] - [Epoch 8/10, Iter 2769/3560] 1.2055139541625977, cross_entropy: 1.2055139541625977 +[2025-04-29 05:39:57,115][BaseTrainer][INFO] - [Epoch 8/10, Iter 2770/3560] 2.2165961265563965, cross_entropy: 2.2165961265563965 +[2025-04-29 05:39:59,946][BaseTrainer][INFO] - [Epoch 8/10, Iter 2771/3560] 3.0779647827148438, cross_entropy: 3.0779647827148438 +[2025-04-29 05:40:00,821][BaseTrainer][INFO] - [Epoch 8/10, Iter 2772/3560] 2.417057752609253, cross_entropy: 2.417057752609253 +[2025-04-29 05:40:03,858][BaseTrainer][INFO] - [Epoch 8/10, Iter 2773/3560] 3.0281317234039307, cross_entropy: 3.0281317234039307 +[2025-04-29 05:40:04,747][BaseTrainer][INFO] - [Epoch 8/10, Iter 2774/3560] 2.357699155807495, cross_entropy: 2.357699155807495 +[2025-04-29 05:40:07,666][BaseTrainer][INFO] - [Epoch 8/10, Iter 2775/3560] 1.3709113597869873, cross_entropy: 1.3709113597869873 +[2025-04-29 05:40:08,564][BaseTrainer][INFO] - [Epoch 8/10, Iter 2776/3560] 3.0900802612304688, cross_entropy: 3.0900802612304688 +[2025-04-29 05:40:11,763][BaseTrainer][INFO] - [Epoch 8/10, Iter 2777/3560] 2.9020466804504395, cross_entropy: 2.9020466804504395 +[2025-04-29 05:40:12,623][BaseTrainer][INFO] - [Epoch 8/10, Iter 2778/3560] 2.160428047180176, cross_entropy: 2.160428047180176 +[2025-04-29 05:40:16,165][BaseTrainer][INFO] - [Epoch 8/10, Iter 2779/3560] 2.8462321758270264, cross_entropy: 2.8462321758270264 +[2025-04-29 05:40:17,024][BaseTrainer][INFO] - [Epoch 8/10, Iter 2780/3560] 1.7848783731460571, cross_entropy: 1.7848783731460571 +[2025-04-29 05:40:19,943][BaseTrainer][INFO] - [Epoch 8/10, Iter 2781/3560] 2.930415391921997, cross_entropy: 2.930415391921997 +[2025-04-29 05:40:20,837][BaseTrainer][INFO] - [Epoch 8/10, Iter 2782/3560] 1.7853052616119385, cross_entropy: 1.7853052616119385 +[2025-04-29 05:40:23,738][BaseTrainer][INFO] - [Epoch 8/10, Iter 2783/3560] 1.7199487686157227, cross_entropy: 1.7199487686157227 +[2025-04-29 05:40:24,620][BaseTrainer][INFO] - [Epoch 8/10, Iter 2784/3560] 2.357804775238037, cross_entropy: 2.357804775238037 +[2025-04-29 05:40:27,555][BaseTrainer][INFO] - [Epoch 8/10, Iter 2785/3560] 1.6712586879730225, cross_entropy: 1.6712586879730225 +[2025-04-29 05:40:28,437][BaseTrainer][INFO] - [Epoch 8/10, Iter 2786/3560] 2.097761869430542, cross_entropy: 2.097761869430542 +[2025-04-29 05:40:31,588][BaseTrainer][INFO] - [Epoch 8/10, Iter 2787/3560] 1.3152021169662476, cross_entropy: 1.3152021169662476 +[2025-04-29 05:40:32,475][BaseTrainer][INFO] - [Epoch 8/10, Iter 2788/3560] 2.167391300201416, cross_entropy: 2.167391300201416 +[2025-04-29 05:40:34,496][BaseTrainer][INFO] - [Epoch 8/10, Iter 2789/3560] 2.4257917404174805, cross_entropy: 2.4257917404174805 +[2025-04-29 05:40:35,385][BaseTrainer][INFO] - [Epoch 8/10, Iter 2790/3560] 2.2237401008605957, cross_entropy: 2.2237401008605957 +[2025-04-29 05:40:37,705][BaseTrainer][INFO] - [Epoch 8/10, Iter 2791/3560] 1.6039462089538574, cross_entropy: 1.6039462089538574 +[2025-04-29 05:40:38,566][BaseTrainer][INFO] - [Epoch 8/10, Iter 2792/3560] 2.424520254135132, cross_entropy: 2.424520254135132 +[2025-04-29 05:40:42,098][BaseTrainer][INFO] - [Epoch 8/10, Iter 2793/3560] 1.8711378574371338, cross_entropy: 1.8711378574371338 +[2025-04-29 05:40:42,982][BaseTrainer][INFO] - [Epoch 8/10, Iter 2794/3560] 1.4082648754119873, cross_entropy: 1.4082648754119873 +[2025-04-29 05:40:45,550][BaseTrainer][INFO] - [Epoch 8/10, Iter 2795/3560] 2.400489568710327, cross_entropy: 2.400489568710327 +[2025-04-29 05:40:46,434][BaseTrainer][INFO] - [Epoch 8/10, Iter 2796/3560] 1.7330524921417236, cross_entropy: 1.7330524921417236 +[2025-04-29 05:40:49,171][BaseTrainer][INFO] - [Epoch 8/10, Iter 2797/3560] 3.1936581134796143, cross_entropy: 3.1936581134796143 +[2025-04-29 05:40:50,051][BaseTrainer][INFO] - [Epoch 8/10, Iter 2798/3560] 2.020385503768921, cross_entropy: 2.020385503768921 +[2025-04-29 05:40:52,784][BaseTrainer][INFO] - [Epoch 8/10, Iter 2799/3560] 1.0725544691085815, cross_entropy: 1.0725544691085815 +[2025-04-29 05:40:53,642][BaseTrainer][INFO] - [Epoch 8/10, Iter 2800/3560] 1.1479917764663696, cross_entropy: 1.1479917764663696 +[2025-04-29 05:40:56,843][BaseTrainer][INFO] - [Epoch 8/10, Iter 2801/3560] 1.0327900648117065, cross_entropy: 1.0327900648117065 +[2025-04-29 05:40:57,724][BaseTrainer][INFO] - [Epoch 8/10, Iter 2802/3560] 3.012666940689087, cross_entropy: 3.012666940689087 +[2025-04-29 05:41:00,055][BaseTrainer][INFO] - [Epoch 8/10, Iter 2803/3560] 1.6157442331314087, cross_entropy: 1.6157442331314087 +[2025-04-29 05:41:00,914][BaseTrainer][INFO] - [Epoch 8/10, Iter 2804/3560] 2.485182762145996, cross_entropy: 2.485182762145996 +[2025-04-29 05:41:04,342][BaseTrainer][INFO] - [Epoch 8/10, Iter 2805/3560] 3.025688648223877, cross_entropy: 3.025688648223877 +[2025-04-29 05:41:05,227][BaseTrainer][INFO] - [Epoch 8/10, Iter 2806/3560] 2.1304616928100586, cross_entropy: 2.1304616928100586 +[2025-04-29 05:41:08,296][BaseTrainer][INFO] - [Epoch 8/10, Iter 2807/3560] 1.172257661819458, cross_entropy: 1.172257661819458 +[2025-04-29 05:41:09,183][BaseTrainer][INFO] - [Epoch 8/10, Iter 2808/3560] 1.220031976699829, cross_entropy: 1.220031976699829 +[2025-04-29 05:41:11,713][BaseTrainer][INFO] - [Epoch 8/10, Iter 2809/3560] 2.684523582458496, cross_entropy: 2.684523582458496 +[2025-04-29 05:41:12,602][BaseTrainer][INFO] - [Epoch 8/10, Iter 2810/3560] 1.6443495750427246, cross_entropy: 1.6443495750427246 +[2025-04-29 05:41:15,725][BaseTrainer][INFO] - [Epoch 8/10, Iter 2811/3560] 1.997135043144226, cross_entropy: 1.997135043144226 +[2025-04-29 05:41:16,604][BaseTrainer][INFO] - [Epoch 8/10, Iter 2812/3560] 1.775451898574829, cross_entropy: 1.775451898574829 +[2025-04-29 05:41:19,764][BaseTrainer][INFO] - [Epoch 8/10, Iter 2813/3560] 1.9158612489700317, cross_entropy: 1.9158612489700317 +[2025-04-29 05:41:20,645][BaseTrainer][INFO] - [Epoch 8/10, Iter 2814/3560] 3.413235664367676, cross_entropy: 3.413235664367676 +[2025-04-29 05:41:23,999][BaseTrainer][INFO] - [Epoch 8/10, Iter 2815/3560] 1.5565505027770996, cross_entropy: 1.5565505027770996 +[2025-04-29 05:41:24,866][BaseTrainer][INFO] - [Epoch 8/10, Iter 2816/3560] 2.1482198238372803, cross_entropy: 2.1482198238372803 +[2025-04-29 05:41:27,915][BaseTrainer][INFO] - [Epoch 8/10, Iter 2817/3560] 1.434856653213501, cross_entropy: 1.434856653213501 +[2025-04-29 05:41:28,799][BaseTrainer][INFO] - [Epoch 8/10, Iter 2818/3560] 1.6142104864120483, cross_entropy: 1.6142104864120483 +[2025-04-29 05:41:32,262][BaseTrainer][INFO] - [Epoch 8/10, Iter 2819/3560] 1.70949125289917, cross_entropy: 1.70949125289917 +[2025-04-29 05:41:33,121][BaseTrainer][INFO] - [Epoch 8/10, Iter 2820/3560] 1.5211350917816162, cross_entropy: 1.5211350917816162 +[2025-04-29 05:41:35,577][BaseTrainer][INFO] - [Epoch 8/10, Iter 2821/3560] 1.1181485652923584, cross_entropy: 1.1181485652923584 +[2025-04-29 05:41:36,457][BaseTrainer][INFO] - [Epoch 8/10, Iter 2822/3560] 2.951242208480835, cross_entropy: 2.951242208480835 +[2025-04-29 05:41:39,125][BaseTrainer][INFO] - [Epoch 8/10, Iter 2823/3560] 2.9618730545043945, cross_entropy: 2.9618730545043945 +[2025-04-29 05:41:40,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2824/3560] 2.604698896408081, cross_entropy: 2.604698896408081 +[2025-04-29 05:41:42,673][BaseTrainer][INFO] - [Epoch 8/10, Iter 2825/3560] 1.3985607624053955, cross_entropy: 1.3985607624053955 +[2025-04-29 05:41:43,551][BaseTrainer][INFO] - [Epoch 8/10, Iter 2826/3560] 2.19352388381958, cross_entropy: 2.19352388381958 +[2025-04-29 05:41:46,046][BaseTrainer][INFO] - [Epoch 8/10, Iter 2827/3560] 1.2575159072875977, cross_entropy: 1.2575159072875977 +[2025-04-29 05:41:46,902][BaseTrainer][INFO] - [Epoch 8/10, Iter 2828/3560] 2.665739059448242, cross_entropy: 2.665739059448242 +[2025-04-29 05:41:50,130][BaseTrainer][INFO] - [Epoch 8/10, Iter 2829/3560] 3.343003988265991, cross_entropy: 3.343003988265991 +[2025-04-29 05:41:51,012][BaseTrainer][INFO] - [Epoch 8/10, Iter 2830/3560] 1.1836612224578857, cross_entropy: 1.1836612224578857 +[2025-04-29 05:41:54,446][BaseTrainer][INFO] - [Epoch 8/10, Iter 2831/3560] 1.489456057548523, cross_entropy: 1.489456057548523 +[2025-04-29 05:41:55,325][BaseTrainer][INFO] - [Epoch 8/10, Iter 2832/3560] 1.2646374702453613, cross_entropy: 1.2646374702453613 +[2025-04-29 05:41:57,908][BaseTrainer][INFO] - [Epoch 8/10, Iter 2833/3560] 1.1953487396240234, cross_entropy: 1.1953487396240234 +[2025-04-29 05:41:58,789][BaseTrainer][INFO] - [Epoch 8/10, Iter 2834/3560] 2.990947961807251, cross_entropy: 2.990947961807251 +[2025-04-29 05:42:01,571][BaseTrainer][INFO] - [Epoch 8/10, Iter 2835/3560] 2.711573600769043, cross_entropy: 2.711573600769043 +[2025-04-29 05:42:02,456][BaseTrainer][INFO] - [Epoch 8/10, Iter 2836/3560] 2.587066173553467, cross_entropy: 2.587066173553467 +[2025-04-29 05:42:05,232][BaseTrainer][INFO] - [Epoch 8/10, Iter 2837/3560] 1.5306289196014404, cross_entropy: 1.5306289196014404 +[2025-04-29 05:42:06,092][BaseTrainer][INFO] - [Epoch 8/10, Iter 2838/3560] 3.1107006072998047, cross_entropy: 3.1107006072998047 +[2025-04-29 05:42:09,201][BaseTrainer][INFO] - [Epoch 8/10, Iter 2839/3560] 1.607633352279663, cross_entropy: 1.607633352279663 +[2025-04-29 05:42:10,086][BaseTrainer][INFO] - [Epoch 8/10, Iter 2840/3560] 3.155076503753662, cross_entropy: 3.155076503753662 +[2025-04-29 05:42:13,003][BaseTrainer][INFO] - [Epoch 8/10, Iter 2841/3560] 2.929816484451294, cross_entropy: 2.929816484451294 +[2025-04-29 05:42:13,895][BaseTrainer][INFO] - [Epoch 8/10, Iter 2842/3560] 1.0760140419006348, cross_entropy: 1.0760140419006348 +[2025-04-29 05:42:16,056][BaseTrainer][INFO] - [Epoch 8/10, Iter 2843/3560] 2.821193218231201, cross_entropy: 2.821193218231201 +[2025-04-29 05:42:16,952][BaseTrainer][INFO] - [Epoch 8/10, Iter 2844/3560] 2.1957736015319824, cross_entropy: 2.1957736015319824 +[2025-04-29 05:42:20,441][BaseTrainer][INFO] - [Epoch 8/10, Iter 2845/3560] 3.127431631088257, cross_entropy: 3.127431631088257 +[2025-04-29 05:42:21,323][BaseTrainer][INFO] - [Epoch 8/10, Iter 2846/3560] 1.8049626350402832, cross_entropy: 1.8049626350402832 +[2025-04-29 05:42:23,425][BaseTrainer][INFO] - [Epoch 8/10, Iter 2847/3560] 1.4261478185653687, cross_entropy: 1.4261478185653687 +[2025-04-29 05:42:24,205][BaseTrainer][INFO] - [Epoch 8/10, Iter 2848/3560] 2.592790365219116, cross_entropy: 2.592790365219116 +[2025-04-29 05:45:12,313][BaseTrainer][INFO] - [Epoch 8/10] (train) 2.1684610843658447, cross_entropy: 2.1684610843658447 +[2025-04-29 05:45:12,314][BaseTrainer][INFO] - [Epoch 8/10] (validation) 1.3179892301559448, cross_entropy: 1.3179892301559448 +[2025-04-29 05:45:13,192][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 05:45:13,693][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch8.pth. +[2025-04-29 05:45:14,470][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 05:45:19,419][BaseTrainer][INFO] - [Epoch 9/10, Iter 2849/3560] 2.1126389503479004, cross_entropy: 2.1126389503479004 +[2025-04-29 05:45:20,280][BaseTrainer][INFO] - [Epoch 9/10, Iter 2850/3560] 1.3529062271118164, cross_entropy: 1.3529062271118164 +[2025-04-29 05:45:23,926][BaseTrainer][INFO] - [Epoch 9/10, Iter 2851/3560] 1.8364694118499756, cross_entropy: 1.8364694118499756 +[2025-04-29 05:45:24,805][BaseTrainer][INFO] - [Epoch 9/10, Iter 2852/3560] 2.9035463333129883, cross_entropy: 2.9035463333129883 +[2025-04-29 05:45:27,721][BaseTrainer][INFO] - [Epoch 9/10, Iter 2853/3560] 1.122495412826538, cross_entropy: 1.122495412826538 +[2025-04-29 05:45:28,582][BaseTrainer][INFO] - [Epoch 9/10, Iter 2854/3560] 1.395634412765503, cross_entropy: 1.395634412765503 +[2025-04-29 05:45:31,687][BaseTrainer][INFO] - [Epoch 9/10, Iter 2855/3560] 2.9955596923828125, cross_entropy: 2.9955596923828125 +[2025-04-29 05:45:32,545][BaseTrainer][INFO] - [Epoch 9/10, Iter 2856/3560] 1.3049653768539429, cross_entropy: 1.3049653768539429 +[2025-04-29 05:45:35,708][BaseTrainer][INFO] - [Epoch 9/10, Iter 2857/3560] 2.3080861568450928, cross_entropy: 2.3080861568450928 +[2025-04-29 05:45:36,574][BaseTrainer][INFO] - [Epoch 9/10, Iter 2858/3560] 1.113032579421997, cross_entropy: 1.113032579421997 +[2025-04-29 05:45:39,401][BaseTrainer][INFO] - [Epoch 9/10, Iter 2859/3560] 1.3549115657806396, cross_entropy: 1.3549115657806396 +[2025-04-29 05:45:40,286][BaseTrainer][INFO] - [Epoch 9/10, Iter 2860/3560] 2.199295997619629, cross_entropy: 2.199295997619629 +[2025-04-29 05:45:42,296][BaseTrainer][INFO] - [Epoch 9/10, Iter 2861/3560] 2.45127534866333, cross_entropy: 2.45127534866333 +[2025-04-29 05:45:43,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2862/3560] 1.7027266025543213, cross_entropy: 1.7027266025543213 +[2025-04-29 05:45:45,953][BaseTrainer][INFO] - [Epoch 9/10, Iter 2863/3560] 2.222609519958496, cross_entropy: 2.222609519958496 +[2025-04-29 05:45:46,813][BaseTrainer][INFO] - [Epoch 9/10, Iter 2864/3560] 3.087221622467041, cross_entropy: 3.087221622467041 +[2025-04-29 05:45:50,041][BaseTrainer][INFO] - [Epoch 9/10, Iter 2865/3560] 1.3871684074401855, cross_entropy: 1.3871684074401855 +[2025-04-29 05:45:50,896][BaseTrainer][INFO] - [Epoch 9/10, Iter 2866/3560] 1.3865288496017456, cross_entropy: 1.3865288496017456 +[2025-04-29 05:45:54,109][BaseTrainer][INFO] - [Epoch 9/10, Iter 2867/3560] 1.863245964050293, cross_entropy: 1.863245964050293 +[2025-04-29 05:45:54,991][BaseTrainer][INFO] - [Epoch 9/10, Iter 2868/3560] 1.436311960220337, cross_entropy: 1.436311960220337 +[2025-04-29 05:45:57,681][BaseTrainer][INFO] - [Epoch 9/10, Iter 2869/3560] 1.2379162311553955, cross_entropy: 1.2379162311553955 +[2025-04-29 05:45:58,565][BaseTrainer][INFO] - [Epoch 9/10, Iter 2870/3560] 3.0448665618896484, cross_entropy: 3.0448665618896484 +[2025-04-29 05:46:01,727][BaseTrainer][INFO] - [Epoch 9/10, Iter 2871/3560] 1.6017632484436035, cross_entropy: 1.6017632484436035 +[2025-04-29 05:46:02,622][BaseTrainer][INFO] - [Epoch 9/10, Iter 2872/3560] 0.9460286498069763, cross_entropy: 0.9460286498069763 +[2025-04-29 05:46:05,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 2873/3560] 1.860344409942627, cross_entropy: 1.860344409942627 +[2025-04-29 05:46:06,501][BaseTrainer][INFO] - [Epoch 9/10, Iter 2874/3560] 3.145031690597534, cross_entropy: 3.145031690597534 +[2025-04-29 05:46:09,898][BaseTrainer][INFO] - [Epoch 9/10, Iter 2875/3560] 1.3633008003234863, cross_entropy: 1.3633008003234863 +[2025-04-29 05:46:10,778][BaseTrainer][INFO] - [Epoch 9/10, Iter 2876/3560] 2.3179898262023926, cross_entropy: 2.3179898262023926 +[2025-04-29 05:46:14,272][BaseTrainer][INFO] - [Epoch 9/10, Iter 2877/3560] 3.0940446853637695, cross_entropy: 3.0940446853637695 +[2025-04-29 05:46:15,143][BaseTrainer][INFO] - [Epoch 9/10, Iter 2878/3560] 1.8540432453155518, cross_entropy: 1.8540432453155518 +[2025-04-29 05:46:17,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 2879/3560] 1.2387077808380127, cross_entropy: 1.2387077808380127 +[2025-04-29 05:46:18,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 2880/3560] 1.9496946334838867, cross_entropy: 1.9496946334838867 +[2025-04-29 05:46:21,345][BaseTrainer][INFO] - [Epoch 9/10, Iter 2881/3560] 1.5062663555145264, cross_entropy: 1.5062663555145264 +[2025-04-29 05:46:22,227][BaseTrainer][INFO] - [Epoch 9/10, Iter 2882/3560] 2.6375415325164795, cross_entropy: 2.6375415325164795 +[2025-04-29 05:46:24,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 2883/3560] 3.1791152954101562, cross_entropy: 3.1791152954101562 +[2025-04-29 05:46:25,677][BaseTrainer][INFO] - [Epoch 9/10, Iter 2884/3560] 2.995767593383789, cross_entropy: 2.995767593383789 +[2025-04-29 05:46:28,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 2885/3560] 1.4333105087280273, cross_entropy: 1.4333105087280273 +[2025-04-29 05:46:29,266][BaseTrainer][INFO] - [Epoch 9/10, Iter 2886/3560] 1.5896855592727661, cross_entropy: 1.5896855592727661 +[2025-04-29 05:46:31,466][BaseTrainer][INFO] - [Epoch 9/10, Iter 2887/3560] 2.071908473968506, cross_entropy: 2.071908473968506 +[2025-04-29 05:46:32,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 2888/3560] 2.4629271030426025, cross_entropy: 2.4629271030426025 +[2025-04-29 05:46:35,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 2889/3560] 1.4402997493743896, cross_entropy: 1.4402997493743896 +[2025-04-29 05:46:36,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 2890/3560] 2.6348726749420166, cross_entropy: 2.6348726749420166 +[2025-04-29 05:46:39,416][BaseTrainer][INFO] - [Epoch 9/10, Iter 2891/3560] 3.0028936862945557, cross_entropy: 3.0028936862945557 +[2025-04-29 05:46:40,274][BaseTrainer][INFO] - [Epoch 9/10, Iter 2892/3560] 3.120487928390503, cross_entropy: 3.120487928390503 +[2025-04-29 05:46:43,211][BaseTrainer][INFO] - [Epoch 9/10, Iter 2893/3560] 0.9589077234268188, cross_entropy: 0.9589077234268188 +[2025-04-29 05:46:44,091][BaseTrainer][INFO] - [Epoch 9/10, Iter 2894/3560] 2.9167182445526123, cross_entropy: 2.9167182445526123 +[2025-04-29 05:46:47,119][BaseTrainer][INFO] - [Epoch 9/10, Iter 2895/3560] 1.651313304901123, cross_entropy: 1.651313304901123 +[2025-04-29 05:46:47,983][BaseTrainer][INFO] - [Epoch 9/10, Iter 2896/3560] 1.7380506992340088, cross_entropy: 1.7380506992340088 +[2025-04-29 05:46:50,894][BaseTrainer][INFO] - [Epoch 9/10, Iter 2897/3560] 1.2449228763580322, cross_entropy: 1.2449228763580322 +[2025-04-29 05:46:51,762][BaseTrainer][INFO] - [Epoch 9/10, Iter 2898/3560] 2.74216365814209, cross_entropy: 2.74216365814209 +[2025-04-29 05:46:54,194][BaseTrainer][INFO] - [Epoch 9/10, Iter 2899/3560] 2.221287727355957, cross_entropy: 2.221287727355957 +[2025-04-29 05:46:55,056][BaseTrainer][INFO] - [Epoch 9/10, Iter 2900/3560] 3.0118556022644043, cross_entropy: 3.0118556022644043 +[2025-04-29 05:46:58,018][BaseTrainer][INFO] - [Epoch 9/10, Iter 2901/3560] 3.0665013790130615, cross_entropy: 3.0665013790130615 +[2025-04-29 05:46:58,901][BaseTrainer][INFO] - [Epoch 9/10, Iter 2902/3560] 1.4734370708465576, cross_entropy: 1.4734370708465576 +[2025-04-29 05:47:00,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 2903/3560] 3.0821316242218018, cross_entropy: 3.0821316242218018 +[2025-04-29 05:47:01,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 2904/3560] 1.5540213584899902, cross_entropy: 1.5540213584899902 +[2025-04-29 05:47:05,442][BaseTrainer][INFO] - [Epoch 9/10, Iter 2905/3560] 1.7610042095184326, cross_entropy: 1.7610042095184326 +[2025-04-29 05:47:06,302][BaseTrainer][INFO] - [Epoch 9/10, Iter 2906/3560] 3.0850565433502197, cross_entropy: 3.0850565433502197 +[2025-04-29 05:47:09,649][BaseTrainer][INFO] - [Epoch 9/10, Iter 2907/3560] 1.005354642868042, cross_entropy: 1.005354642868042 +[2025-04-29 05:47:10,530][BaseTrainer][INFO] - [Epoch 9/10, Iter 2908/3560] 1.2254329919815063, cross_entropy: 1.2254329919815063 +[2025-04-29 05:47:13,509][BaseTrainer][INFO] - [Epoch 9/10, Iter 2909/3560] 1.1522574424743652, cross_entropy: 1.1522574424743652 +[2025-04-29 05:47:14,378][BaseTrainer][INFO] - [Epoch 9/10, Iter 2910/3560] 2.194709300994873, cross_entropy: 2.194709300994873 +[2025-04-29 05:47:17,080][BaseTrainer][INFO] - [Epoch 9/10, Iter 2911/3560] 1.2270444631576538, cross_entropy: 1.2270444631576538 +[2025-04-29 05:47:17,964][BaseTrainer][INFO] - [Epoch 9/10, Iter 2912/3560] 1.5177738666534424, cross_entropy: 1.5177738666534424 +[2025-04-29 05:47:20,534][BaseTrainer][INFO] - [Epoch 9/10, Iter 2913/3560] 3.125499725341797, cross_entropy: 3.125499725341797 +[2025-04-29 05:47:21,418][BaseTrainer][INFO] - [Epoch 9/10, Iter 2914/3560] 1.1944198608398438, cross_entropy: 1.1944198608398438 +[2025-04-29 05:47:24,422][BaseTrainer][INFO] - [Epoch 9/10, Iter 2915/3560] 3.0168426036834717, cross_entropy: 3.0168426036834717 +[2025-04-29 05:47:25,279][BaseTrainer][INFO] - [Epoch 9/10, Iter 2916/3560] 2.315948486328125, cross_entropy: 2.315948486328125 +[2025-04-29 05:47:28,407][BaseTrainer][INFO] - [Epoch 9/10, Iter 2917/3560] 3.0976407527923584, cross_entropy: 3.0976407527923584 +[2025-04-29 05:47:29,290][BaseTrainer][INFO] - [Epoch 9/10, Iter 2918/3560] 1.1176108121871948, cross_entropy: 1.1176108121871948 +[2025-04-29 05:47:31,868][BaseTrainer][INFO] - [Epoch 9/10, Iter 2919/3560] 1.0486650466918945, cross_entropy: 1.0486650466918945 +[2025-04-29 05:47:32,753][BaseTrainer][INFO] - [Epoch 9/10, Iter 2920/3560] 1.3600046634674072, cross_entropy: 1.3600046634674072 +[2025-04-29 05:47:36,063][BaseTrainer][INFO] - [Epoch 9/10, Iter 2921/3560] 2.181497812271118, cross_entropy: 2.181497812271118 +[2025-04-29 05:47:36,942][BaseTrainer][INFO] - [Epoch 9/10, Iter 2922/3560] 1.3722732067108154, cross_entropy: 1.3722732067108154 +[2025-04-29 05:47:40,326][BaseTrainer][INFO] - [Epoch 9/10, Iter 2923/3560] 1.6045637130737305, cross_entropy: 1.6045637130737305 +[2025-04-29 05:47:41,185][BaseTrainer][INFO] - [Epoch 9/10, Iter 2924/3560] 1.3851622343063354, cross_entropy: 1.3851622343063354 +[2025-04-29 05:47:43,899][BaseTrainer][INFO] - [Epoch 9/10, Iter 2925/3560] 1.2265205383300781, cross_entropy: 1.2265205383300781 +[2025-04-29 05:47:44,777][BaseTrainer][INFO] - [Epoch 9/10, Iter 2926/3560] 2.4788784980773926, cross_entropy: 2.4788784980773926 +[2025-04-29 05:47:47,676][BaseTrainer][INFO] - [Epoch 9/10, Iter 2927/3560] 1.364302396774292, cross_entropy: 1.364302396774292 +[2025-04-29 05:47:48,559][BaseTrainer][INFO] - [Epoch 9/10, Iter 2928/3560] 2.7267937660217285, cross_entropy: 2.7267937660217285 +[2025-04-29 05:47:52,699][BaseTrainer][INFO] - [Epoch 9/10, Iter 2929/3560] 1.424360990524292, cross_entropy: 1.424360990524292 +[2025-04-29 05:47:53,557][BaseTrainer][INFO] - [Epoch 9/10, Iter 2930/3560] 2.114461898803711, cross_entropy: 2.114461898803711 +[2025-04-29 05:47:55,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 2931/3560] 2.077998638153076, cross_entropy: 2.077998638153076 +[2025-04-29 05:47:56,686][BaseTrainer][INFO] - [Epoch 9/10, Iter 2932/3560] 1.9972654581069946, cross_entropy: 1.9972654581069946 +[2025-04-29 05:47:59,663][BaseTrainer][INFO] - [Epoch 9/10, Iter 2933/3560] 2.6533756256103516, cross_entropy: 2.6533756256103516 +[2025-04-29 05:48:00,522][BaseTrainer][INFO] - [Epoch 9/10, Iter 2934/3560] 2.4054453372955322, cross_entropy: 2.4054453372955322 +[2025-04-29 05:48:03,727][BaseTrainer][INFO] - [Epoch 9/10, Iter 2935/3560] 3.454956531524658, cross_entropy: 3.454956531524658 +[2025-04-29 05:48:04,610][BaseTrainer][INFO] - [Epoch 9/10, Iter 2936/3560] 2.4326305389404297, cross_entropy: 2.4326305389404297 +[2025-04-29 05:48:07,807][BaseTrainer][INFO] - [Epoch 9/10, Iter 2937/3560] 2.347353935241699, cross_entropy: 2.347353935241699 +[2025-04-29 05:48:08,691][BaseTrainer][INFO] - [Epoch 9/10, Iter 2938/3560] 1.2541364431381226, cross_entropy: 1.2541364431381226 +[2025-04-29 05:48:11,641][BaseTrainer][INFO] - [Epoch 9/10, Iter 2939/3560] 1.7277395725250244, cross_entropy: 1.7277395725250244 +[2025-04-29 05:48:12,516][BaseTrainer][INFO] - [Epoch 9/10, Iter 2940/3560] 3.057563304901123, cross_entropy: 3.057563304901123 +[2025-04-29 05:48:15,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 2941/3560] 2.9706616401672363, cross_entropy: 2.9706616401672363 +[2025-04-29 05:48:16,489][BaseTrainer][INFO] - [Epoch 9/10, Iter 2942/3560] 3.201751232147217, cross_entropy: 3.201751232147217 +[2025-04-29 05:48:19,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 2943/3560] 2.044379234313965, cross_entropy: 2.044379234313965 +[2025-04-29 05:48:20,318][BaseTrainer][INFO] - [Epoch 9/10, Iter 2944/3560] 1.987177848815918, cross_entropy: 1.987177848815918 +[2025-04-29 05:48:22,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 2945/3560] 2.134981632232666, cross_entropy: 2.134981632232666 +[2025-04-29 05:48:23,409][BaseTrainer][INFO] - [Epoch 9/10, Iter 2946/3560] 2.9591572284698486, cross_entropy: 2.9591572284698486 +[2025-04-29 05:48:26,456][BaseTrainer][INFO] - [Epoch 9/10, Iter 2947/3560] 2.795750856399536, cross_entropy: 2.795750856399536 +[2025-04-29 05:48:27,337][BaseTrainer][INFO] - [Epoch 9/10, Iter 2948/3560] 1.800938606262207, cross_entropy: 1.800938606262207 +[2025-04-29 05:48:29,859][BaseTrainer][INFO] - [Epoch 9/10, Iter 2949/3560] 1.3946478366851807, cross_entropy: 1.3946478366851807 +[2025-04-29 05:48:30,715][BaseTrainer][INFO] - [Epoch 9/10, Iter 2950/3560] 1.927281141281128, cross_entropy: 1.927281141281128 +[2025-04-29 05:48:33,954][BaseTrainer][INFO] - [Epoch 9/10, Iter 2951/3560] 1.4460716247558594, cross_entropy: 1.4460716247558594 +[2025-04-29 05:48:34,816][BaseTrainer][INFO] - [Epoch 9/10, Iter 2952/3560] 2.2630233764648438, cross_entropy: 2.2630233764648438 +[2025-04-29 05:48:37,241][BaseTrainer][INFO] - [Epoch 9/10, Iter 2953/3560] 2.842942237854004, cross_entropy: 2.842942237854004 +[2025-04-29 05:48:38,122][BaseTrainer][INFO] - [Epoch 9/10, Iter 2954/3560] 2.485311508178711, cross_entropy: 2.485311508178711 +[2025-04-29 05:48:40,814][BaseTrainer][INFO] - [Epoch 9/10, Iter 2955/3560] 2.6216084957122803, cross_entropy: 2.6216084957122803 +[2025-04-29 05:48:41,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 2956/3560] 2.9622092247009277, cross_entropy: 2.9622092247009277 +[2025-04-29 05:48:45,511][BaseTrainer][INFO] - [Epoch 9/10, Iter 2957/3560] 2.123824119567871, cross_entropy: 2.123824119567871 +[2025-04-29 05:48:46,376][BaseTrainer][INFO] - [Epoch 9/10, Iter 2958/3560] 1.4120020866394043, cross_entropy: 1.4120020866394043 +[2025-04-29 05:48:49,518][BaseTrainer][INFO] - [Epoch 9/10, Iter 2959/3560] 1.0246607065200806, cross_entropy: 1.0246607065200806 +[2025-04-29 05:48:50,379][BaseTrainer][INFO] - [Epoch 9/10, Iter 2960/3560] 2.0169126987457275, cross_entropy: 2.0169126987457275 +[2025-04-29 05:48:53,613][BaseTrainer][INFO] - [Epoch 9/10, Iter 2961/3560] 3.1303629875183105, cross_entropy: 3.1303629875183105 +[2025-04-29 05:48:55,070][BaseTrainer][INFO] - [Epoch 9/10, Iter 2962/3560] 1.3571290969848633, cross_entropy: 1.3571290969848633 +[2025-04-29 05:48:57,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 2963/3560] 2.6183154582977295, cross_entropy: 2.6183154582977295 +[2025-04-29 05:48:58,515][BaseTrainer][INFO] - [Epoch 9/10, Iter 2964/3560] 2.3882973194122314, cross_entropy: 2.3882973194122314 +[2025-04-29 05:49:01,276][BaseTrainer][INFO] - [Epoch 9/10, Iter 2965/3560] 2.3957035541534424, cross_entropy: 2.3957035541534424 +[2025-04-29 05:49:02,156][BaseTrainer][INFO] - [Epoch 9/10, Iter 2966/3560] 3.265015125274658, cross_entropy: 3.265015125274658 +[2025-04-29 05:49:05,256][BaseTrainer][INFO] - [Epoch 9/10, Iter 2967/3560] 2.064432144165039, cross_entropy: 2.064432144165039 +[2025-04-29 05:49:06,133][BaseTrainer][INFO] - [Epoch 9/10, Iter 2968/3560] 1.2187917232513428, cross_entropy: 1.2187917232513428 +[2025-04-29 05:49:08,336][BaseTrainer][INFO] - [Epoch 9/10, Iter 2969/3560] 1.5382471084594727, cross_entropy: 1.5382471084594727 +[2025-04-29 05:49:09,220][BaseTrainer][INFO] - [Epoch 9/10, Iter 2970/3560] 1.2473955154418945, cross_entropy: 1.2473955154418945 +[2025-04-29 05:49:11,840][BaseTrainer][INFO] - [Epoch 9/10, Iter 2971/3560] 2.8558177947998047, cross_entropy: 2.8558177947998047 +[2025-04-29 05:49:12,722][BaseTrainer][INFO] - [Epoch 9/10, Iter 2972/3560] 2.727536678314209, cross_entropy: 2.727536678314209 +[2025-04-29 05:49:16,249][BaseTrainer][INFO] - [Epoch 9/10, Iter 2973/3560] 1.3195838928222656, cross_entropy: 1.3195838928222656 +[2025-04-29 05:49:17,111][BaseTrainer][INFO] - [Epoch 9/10, Iter 2974/3560] 1.502884030342102, cross_entropy: 1.502884030342102 +[2025-04-29 05:49:20,211][BaseTrainer][INFO] - [Epoch 9/10, Iter 2975/3560] 2.8623743057250977, cross_entropy: 2.8623743057250977 +[2025-04-29 05:49:21,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 2976/3560] 1.4098420143127441, cross_entropy: 1.4098420143127441 +[2025-04-29 05:49:23,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 2977/3560] 1.2766530513763428, cross_entropy: 1.2766530513763428 +[2025-04-29 05:49:24,515][BaseTrainer][INFO] - [Epoch 9/10, Iter 2978/3560] 3.2456376552581787, cross_entropy: 3.2456376552581787 +[2025-04-29 05:49:27,470][BaseTrainer][INFO] - [Epoch 9/10, Iter 2979/3560] 2.5230607986450195, cross_entropy: 2.5230607986450195 +[2025-04-29 05:49:28,354][BaseTrainer][INFO] - [Epoch 9/10, Iter 2980/3560] 1.32045316696167, cross_entropy: 1.32045316696167 +[2025-04-29 05:49:31,277][BaseTrainer][INFO] - [Epoch 9/10, Iter 2981/3560] 1.4429347515106201, cross_entropy: 1.4429347515106201 +[2025-04-29 05:49:32,136][BaseTrainer][INFO] - [Epoch 9/10, Iter 2982/3560] 2.6747541427612305, cross_entropy: 2.6747541427612305 +[2025-04-29 05:49:35,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 2983/3560] 1.447858214378357, cross_entropy: 1.447858214378357 +[2025-04-29 05:49:35,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 2984/3560] 2.4787814617156982, cross_entropy: 2.4787814617156982 +[2025-04-29 05:49:38,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 2985/3560] 1.3418071269989014, cross_entropy: 1.3418071269989014 +[2025-04-29 05:49:39,435][BaseTrainer][INFO] - [Epoch 9/10, Iter 2986/3560] 2.6710000038146973, cross_entropy: 2.6710000038146973 +[2025-04-29 05:49:42,464][BaseTrainer][INFO] - [Epoch 9/10, Iter 2987/3560] 1.3602781295776367, cross_entropy: 1.3602781295776367 +[2025-04-29 05:49:43,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 2988/3560] 2.7519240379333496, cross_entropy: 2.7519240379333496 +[2025-04-29 05:49:45,519][BaseTrainer][INFO] - [Epoch 9/10, Iter 2989/3560] 1.5484983921051025, cross_entropy: 1.5484983921051025 +[2025-04-29 05:49:46,405][BaseTrainer][INFO] - [Epoch 9/10, Iter 2990/3560] 2.1369757652282715, cross_entropy: 2.1369757652282715 +[2025-04-29 05:49:49,855][BaseTrainer][INFO] - [Epoch 9/10, Iter 2991/3560] 1.5890816450119019, cross_entropy: 1.5890816450119019 +[2025-04-29 05:49:50,716][BaseTrainer][INFO] - [Epoch 9/10, Iter 2992/3560] 2.7519896030426025, cross_entropy: 2.7519896030426025 +[2025-04-29 05:49:53,359][BaseTrainer][INFO] - [Epoch 9/10, Iter 2993/3560] 1.990067958831787, cross_entropy: 1.990067958831787 +[2025-04-29 05:49:54,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 2994/3560] 3.5345821380615234, cross_entropy: 3.5345821380615234 +[2025-04-29 05:49:56,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 2995/3560] 1.370198369026184, cross_entropy: 1.370198369026184 +[2025-04-29 05:49:57,690][BaseTrainer][INFO] - [Epoch 9/10, Iter 2996/3560] 1.5504425764083862, cross_entropy: 1.5504425764083862 +[2025-04-29 05:50:00,207][BaseTrainer][INFO] - [Epoch 9/10, Iter 2997/3560] 1.4050105810165405, cross_entropy: 1.4050105810165405 +[2025-04-29 05:50:01,089][BaseTrainer][INFO] - [Epoch 9/10, Iter 2998/3560] 2.479193925857544, cross_entropy: 2.479193925857544 +[2025-04-29 05:50:03,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 2999/3560] 2.4457905292510986, cross_entropy: 2.4457905292510986 +[2025-04-29 05:50:04,785][BaseTrainer][INFO] - [Epoch 9/10, Iter 3000/3560] 2.878983974456787, cross_entropy: 2.878983974456787 +[2025-04-29 05:50:05,273][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/iteration3000.pth. +[2025-04-29 05:50:08,244][BaseTrainer][INFO] - [Epoch 9/10, Iter 3001/3560] 1.7239251136779785, cross_entropy: 1.7239251136779785 +[2025-04-29 05:50:09,103][BaseTrainer][INFO] - [Epoch 9/10, Iter 3002/3560] 1.5756926536560059, cross_entropy: 1.5756926536560059 +[2025-04-29 05:50:11,862][BaseTrainer][INFO] - [Epoch 9/10, Iter 3003/3560] 1.3605060577392578, cross_entropy: 1.3605060577392578 +[2025-04-29 05:50:12,729][BaseTrainer][INFO] - [Epoch 9/10, Iter 3004/3560] 3.188809871673584, cross_entropy: 3.188809871673584 +[2025-04-29 05:50:15,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 3005/3560] 1.9385716915130615, cross_entropy: 1.9385716915130615 +[2025-04-29 05:50:16,575][BaseTrainer][INFO] - [Epoch 9/10, Iter 3006/3560] 1.9058517217636108, cross_entropy: 1.9058517217636108 +[2025-04-29 05:50:18,986][BaseTrainer][INFO] - [Epoch 9/10, Iter 3007/3560] 2.5784363746643066, cross_entropy: 2.5784363746643066 +[2025-04-29 05:50:19,876][BaseTrainer][INFO] - [Epoch 9/10, Iter 3008/3560] 2.0139474868774414, cross_entropy: 2.0139474868774414 +[2025-04-29 05:50:22,850][BaseTrainer][INFO] - [Epoch 9/10, Iter 3009/3560] 1.4342797994613647, cross_entropy: 1.4342797994613647 +[2025-04-29 05:50:23,736][BaseTrainer][INFO] - [Epoch 9/10, Iter 3010/3560] 3.0365829467773438, cross_entropy: 3.0365829467773438 +[2025-04-29 05:50:26,581][BaseTrainer][INFO] - [Epoch 9/10, Iter 3011/3560] 2.045281410217285, cross_entropy: 2.045281410217285 +[2025-04-29 05:50:27,437][BaseTrainer][INFO] - [Epoch 9/10, Iter 3012/3560] 3.0318212509155273, cross_entropy: 3.0318212509155273 +[2025-04-29 05:50:30,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 3013/3560] 1.3124738931655884, cross_entropy: 1.3124738931655884 +[2025-04-29 05:50:31,835][BaseTrainer][INFO] - [Epoch 9/10, Iter 3014/3560] 2.7364261150360107, cross_entropy: 2.7364261150360107 +[2025-04-29 05:50:34,996][BaseTrainer][INFO] - [Epoch 9/10, Iter 3015/3560] 2.000412940979004, cross_entropy: 2.000412940979004 +[2025-04-29 05:50:35,853][BaseTrainer][INFO] - [Epoch 9/10, Iter 3016/3560] 2.6736748218536377, cross_entropy: 2.6736748218536377 +[2025-04-29 05:50:38,745][BaseTrainer][INFO] - [Epoch 9/10, Iter 3017/3560] 2.8833718299865723, cross_entropy: 2.8833718299865723 +[2025-04-29 05:50:39,643][BaseTrainer][INFO] - [Epoch 9/10, Iter 3018/3560] 1.135414481163025, cross_entropy: 1.135414481163025 +[2025-04-29 05:50:42,737][BaseTrainer][INFO] - [Epoch 9/10, Iter 3019/3560] 3.097137689590454, cross_entropy: 3.097137689590454 +[2025-04-29 05:50:43,605][BaseTrainer][INFO] - [Epoch 9/10, Iter 3020/3560] 1.139284610748291, cross_entropy: 1.139284610748291 +[2025-04-29 05:50:45,918][BaseTrainer][INFO] - [Epoch 9/10, Iter 3021/3560] 1.398841381072998, cross_entropy: 1.398841381072998 +[2025-04-29 05:50:46,807][BaseTrainer][INFO] - [Epoch 9/10, Iter 3022/3560] 2.599668264389038, cross_entropy: 2.599668264389038 +[2025-04-29 05:50:49,432][BaseTrainer][INFO] - [Epoch 9/10, Iter 3023/3560] 1.2808555364608765, cross_entropy: 1.2808555364608765 +[2025-04-29 05:50:50,311][BaseTrainer][INFO] - [Epoch 9/10, Iter 3024/3560] 3.2011518478393555, cross_entropy: 3.2011518478393555 +[2025-04-29 05:50:53,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3025/3560] 1.8118629455566406, cross_entropy: 1.8118629455566406 +[2025-04-29 05:50:53,972][BaseTrainer][INFO] - [Epoch 9/10, Iter 3026/3560] 2.928551197052002, cross_entropy: 2.928551197052002 +[2025-04-29 05:50:56,961][BaseTrainer][INFO] - [Epoch 9/10, Iter 3027/3560] 1.8914499282836914, cross_entropy: 1.8914499282836914 +[2025-04-29 05:50:57,818][BaseTrainer][INFO] - [Epoch 9/10, Iter 3028/3560] 0.986009955406189, cross_entropy: 0.986009955406189 +[2025-04-29 05:51:00,526][BaseTrainer][INFO] - [Epoch 9/10, Iter 3029/3560] 1.7634713649749756, cross_entropy: 1.7634713649749756 +[2025-04-29 05:51:01,382][BaseTrainer][INFO] - [Epoch 9/10, Iter 3030/3560] 2.2952282428741455, cross_entropy: 2.2952282428741455 +[2025-04-29 05:51:04,725][BaseTrainer][INFO] - [Epoch 9/10, Iter 3031/3560] 3.088611602783203, cross_entropy: 3.088611602783203 +[2025-04-29 05:51:05,582][BaseTrainer][INFO] - [Epoch 9/10, Iter 3032/3560] 3.005359649658203, cross_entropy: 3.005359649658203 +[2025-04-29 05:51:07,904][BaseTrainer][INFO] - [Epoch 9/10, Iter 3033/3560] 1.444643259048462, cross_entropy: 1.444643259048462 +[2025-04-29 05:51:08,781][BaseTrainer][INFO] - [Epoch 9/10, Iter 3034/3560] 2.470064640045166, cross_entropy: 2.470064640045166 +[2025-04-29 05:51:11,580][BaseTrainer][INFO] - [Epoch 9/10, Iter 3035/3560] 1.5525455474853516, cross_entropy: 1.5525455474853516 +[2025-04-29 05:51:12,436][BaseTrainer][INFO] - [Epoch 9/10, Iter 3036/3560] 3.0071723461151123, cross_entropy: 3.0071723461151123 +[2025-04-29 05:51:15,410][BaseTrainer][INFO] - [Epoch 9/10, Iter 3037/3560] 2.8957607746124268, cross_entropy: 2.8957607746124268 +[2025-04-29 05:51:16,290][BaseTrainer][INFO] - [Epoch 9/10, Iter 3038/3560] 1.412981629371643, cross_entropy: 1.412981629371643 +[2025-04-29 05:51:19,364][BaseTrainer][INFO] - [Epoch 9/10, Iter 3039/3560] 2.998281955718994, cross_entropy: 2.998281955718994 +[2025-04-29 05:51:20,223][BaseTrainer][INFO] - [Epoch 9/10, Iter 3040/3560] 1.4184948205947876, cross_entropy: 1.4184948205947876 +[2025-04-29 05:51:23,160][BaseTrainer][INFO] - [Epoch 9/10, Iter 3041/3560] 1.5555561780929565, cross_entropy: 1.5555561780929565 +[2025-04-29 05:51:24,022][BaseTrainer][INFO] - [Epoch 9/10, Iter 3042/3560] 1.2036972045898438, cross_entropy: 1.2036972045898438 +[2025-04-29 05:51:27,880][BaseTrainer][INFO] - [Epoch 9/10, Iter 3043/3560] 3.284816265106201, cross_entropy: 3.284816265106201 +[2025-04-29 05:51:28,752][BaseTrainer][INFO] - [Epoch 9/10, Iter 3044/3560] 3.1208741664886475, cross_entropy: 3.1208741664886475 +[2025-04-29 05:51:31,412][BaseTrainer][INFO] - [Epoch 9/10, Iter 3045/3560] 1.7709909677505493, cross_entropy: 1.7709909677505493 +[2025-04-29 05:51:32,295][BaseTrainer][INFO] - [Epoch 9/10, Iter 3046/3560] 3.0238425731658936, cross_entropy: 3.0238425731658936 +[2025-04-29 05:51:35,172][BaseTrainer][INFO] - [Epoch 9/10, Iter 3047/3560] 1.4063518047332764, cross_entropy: 1.4063518047332764 +[2025-04-29 05:51:36,058][BaseTrainer][INFO] - [Epoch 9/10, Iter 3048/3560] 2.1889946460723877, cross_entropy: 2.1889946460723877 +[2025-04-29 05:51:38,876][BaseTrainer][INFO] - [Epoch 9/10, Iter 3049/3560] 1.785757064819336, cross_entropy: 1.785757064819336 +[2025-04-29 05:51:39,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 3050/3560] 1.7583341598510742, cross_entropy: 1.7583341598510742 +[2025-04-29 05:51:42,356][BaseTrainer][INFO] - [Epoch 9/10, Iter 3051/3560] 1.6295465230941772, cross_entropy: 1.6295465230941772 +[2025-04-29 05:51:43,238][BaseTrainer][INFO] - [Epoch 9/10, Iter 3052/3560] 2.9686942100524902, cross_entropy: 2.9686942100524902 +[2025-04-29 05:51:45,655][BaseTrainer][INFO] - [Epoch 9/10, Iter 3053/3560] 1.5827817916870117, cross_entropy: 1.5827817916870117 +[2025-04-29 05:51:46,537][BaseTrainer][INFO] - [Epoch 9/10, Iter 3054/3560] 2.2068867683410645, cross_entropy: 2.2068867683410645 +[2025-04-29 05:51:49,343][BaseTrainer][INFO] - [Epoch 9/10, Iter 3055/3560] 2.408947229385376, cross_entropy: 2.408947229385376 +[2025-04-29 05:51:50,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 3056/3560] 2.134657621383667, cross_entropy: 2.134657621383667 +[2025-04-29 05:51:53,231][BaseTrainer][INFO] - [Epoch 9/10, Iter 3057/3560] 2.1405086517333984, cross_entropy: 2.1405086517333984 +[2025-04-29 05:51:54,097][BaseTrainer][INFO] - [Epoch 9/10, Iter 3058/3560] 3.10662579536438, cross_entropy: 3.10662579536438 +[2025-04-29 05:51:58,675][BaseTrainer][INFO] - [Epoch 9/10, Iter 3059/3560] 2.5608458518981934, cross_entropy: 2.5608458518981934 +[2025-04-29 05:51:59,535][BaseTrainer][INFO] - [Epoch 9/10, Iter 3060/3560] 2.710268497467041, cross_entropy: 2.710268497467041 +[2025-04-29 05:52:02,380][BaseTrainer][INFO] - [Epoch 9/10, Iter 3061/3560] 2.7615156173706055, cross_entropy: 2.7615156173706055 +[2025-04-29 05:52:03,263][BaseTrainer][INFO] - [Epoch 9/10, Iter 3062/3560] 2.9403669834136963, cross_entropy: 2.9403669834136963 +[2025-04-29 05:52:05,793][BaseTrainer][INFO] - [Epoch 9/10, Iter 3063/3560] 1.94053316116333, cross_entropy: 1.94053316116333 +[2025-04-29 05:52:06,676][BaseTrainer][INFO] - [Epoch 9/10, Iter 3064/3560] 1.6531085968017578, cross_entropy: 1.6531085968017578 +[2025-04-29 05:52:10,346][BaseTrainer][INFO] - [Epoch 9/10, Iter 3065/3560] 2.881636142730713, cross_entropy: 2.881636142730713 +[2025-04-29 05:52:11,232][BaseTrainer][INFO] - [Epoch 9/10, Iter 3066/3560] 1.985653281211853, cross_entropy: 1.985653281211853 +[2025-04-29 05:52:13,966][BaseTrainer][INFO] - [Epoch 9/10, Iter 3067/3560] 2.933060646057129, cross_entropy: 2.933060646057129 +[2025-04-29 05:52:14,851][BaseTrainer][INFO] - [Epoch 9/10, Iter 3068/3560] 2.9379353523254395, cross_entropy: 2.9379353523254395 +[2025-04-29 05:52:17,879][BaseTrainer][INFO] - [Epoch 9/10, Iter 3069/3560] 1.197719693183899, cross_entropy: 1.197719693183899 +[2025-04-29 05:52:18,763][BaseTrainer][INFO] - [Epoch 9/10, Iter 3070/3560] 3.0897669792175293, cross_entropy: 3.0897669792175293 +[2025-04-29 05:52:21,698][BaseTrainer][INFO] - [Epoch 9/10, Iter 3071/3560] 3.395995616912842, cross_entropy: 3.395995616912842 +[2025-04-29 05:52:22,556][BaseTrainer][INFO] - [Epoch 9/10, Iter 3072/3560] 2.354884386062622, cross_entropy: 2.354884386062622 +[2025-04-29 05:52:25,306][BaseTrainer][INFO] - [Epoch 9/10, Iter 3073/3560] 3.1760387420654297, cross_entropy: 3.1760387420654297 +[2025-04-29 05:52:26,184][BaseTrainer][INFO] - [Epoch 9/10, Iter 3074/3560] 1.2410759925842285, cross_entropy: 1.2410759925842285 +[2025-04-29 05:52:28,808][BaseTrainer][INFO] - [Epoch 9/10, Iter 3075/3560] 1.30293869972229, cross_entropy: 1.30293869972229 +[2025-04-29 05:52:29,691][BaseTrainer][INFO] - [Epoch 9/10, Iter 3076/3560] 2.4900624752044678, cross_entropy: 2.4900624752044678 +[2025-04-29 05:52:33,033][BaseTrainer][INFO] - [Epoch 9/10, Iter 3077/3560] 0.9489491581916809, cross_entropy: 0.9489491581916809 +[2025-04-29 05:52:33,913][BaseTrainer][INFO] - [Epoch 9/10, Iter 3078/3560] 2.3364334106445312, cross_entropy: 2.3364334106445312 +[2025-04-29 05:52:36,429][BaseTrainer][INFO] - [Epoch 9/10, Iter 3079/3560] 1.5668113231658936, cross_entropy: 1.5668113231658936 +[2025-04-29 05:52:37,316][BaseTrainer][INFO] - [Epoch 9/10, Iter 3080/3560] 1.2381489276885986, cross_entropy: 1.2381489276885986 +[2025-04-29 05:52:39,979][BaseTrainer][INFO] - [Epoch 9/10, Iter 3081/3560] 2.994065284729004, cross_entropy: 2.994065284729004 +[2025-04-29 05:52:40,852][BaseTrainer][INFO] - [Epoch 9/10, Iter 3082/3560] 2.4177865982055664, cross_entropy: 2.4177865982055664 +[2025-04-29 05:52:43,167][BaseTrainer][INFO] - [Epoch 9/10, Iter 3083/3560] 1.9589128494262695, cross_entropy: 1.9589128494262695 +[2025-04-29 05:52:44,028][BaseTrainer][INFO] - [Epoch 9/10, Iter 3084/3560] 1.2063335180282593, cross_entropy: 1.2063335180282593 +[2025-04-29 05:52:46,650][BaseTrainer][INFO] - [Epoch 9/10, Iter 3085/3560] 2.914113759994507, cross_entropy: 2.914113759994507 +[2025-04-29 05:52:47,532][BaseTrainer][INFO] - [Epoch 9/10, Iter 3086/3560] 1.2620720863342285, cross_entropy: 1.2620720863342285 +[2025-04-29 05:52:51,072][BaseTrainer][INFO] - [Epoch 9/10, Iter 3087/3560] 3.087998867034912, cross_entropy: 3.087998867034912 +[2025-04-29 05:52:51,947][BaseTrainer][INFO] - [Epoch 9/10, Iter 3088/3560] 1.509332299232483, cross_entropy: 1.509332299232483 +[2025-04-29 05:52:55,359][BaseTrainer][INFO] - [Epoch 9/10, Iter 3089/3560] 1.3417441844940186, cross_entropy: 1.3417441844940186 +[2025-04-29 05:52:56,218][BaseTrainer][INFO] - [Epoch 9/10, Iter 3090/3560] 1.3677455186843872, cross_entropy: 1.3677455186843872 +[2025-04-29 05:52:59,164][BaseTrainer][INFO] - [Epoch 9/10, Iter 3091/3560] 1.261892557144165, cross_entropy: 1.261892557144165 +[2025-04-29 05:53:00,021][BaseTrainer][INFO] - [Epoch 9/10, Iter 3092/3560] 1.7262815237045288, cross_entropy: 1.7262815237045288 +[2025-04-29 05:53:03,273][BaseTrainer][INFO] - [Epoch 9/10, Iter 3093/3560] 1.092797040939331, cross_entropy: 1.092797040939331 +[2025-04-29 05:53:04,141][BaseTrainer][INFO] - [Epoch 9/10, Iter 3094/3560] 1.1595417261123657, cross_entropy: 1.1595417261123657 +[2025-04-29 05:53:06,552][BaseTrainer][INFO] - [Epoch 9/10, Iter 3095/3560] 3.1779441833496094, cross_entropy: 3.1779441833496094 +[2025-04-29 05:53:07,412][BaseTrainer][INFO] - [Epoch 9/10, Iter 3096/3560] 2.691586494445801, cross_entropy: 2.691586494445801 +[2025-04-29 05:53:10,037][BaseTrainer][INFO] - [Epoch 9/10, Iter 3097/3560] 3.17738938331604, cross_entropy: 3.17738938331604 +[2025-04-29 05:53:10,917][BaseTrainer][INFO] - [Epoch 9/10, Iter 3098/3560] 1.464388132095337, cross_entropy: 1.464388132095337 +[2025-04-29 05:53:13,589][BaseTrainer][INFO] - [Epoch 9/10, Iter 3099/3560] 1.039100170135498, cross_entropy: 1.039100170135498 +[2025-04-29 05:53:14,473][BaseTrainer][INFO] - [Epoch 9/10, Iter 3100/3560] 3.2465736865997314, cross_entropy: 3.2465736865997314 +[2025-04-29 05:53:17,070][BaseTrainer][INFO] - [Epoch 9/10, Iter 3101/3560] 1.3460479974746704, cross_entropy: 1.3460479974746704 +[2025-04-29 05:53:17,955][BaseTrainer][INFO] - [Epoch 9/10, Iter 3102/3560] 2.5617899894714355, cross_entropy: 2.5617899894714355 +[2025-04-29 05:53:20,441][BaseTrainer][INFO] - [Epoch 9/10, Iter 3103/3560] 1.7334076166152954, cross_entropy: 1.7334076166152954 +[2025-04-29 05:53:21,300][BaseTrainer][INFO] - [Epoch 9/10, Iter 3104/3560] 2.686901807785034, cross_entropy: 2.686901807785034 +[2025-04-29 05:53:24,299][BaseTrainer][INFO] - [Epoch 9/10, Iter 3105/3560] 1.8884433507919312, cross_entropy: 1.8884433507919312 +[2025-04-29 05:53:25,180][BaseTrainer][INFO] - [Epoch 9/10, Iter 3106/3560] 1.8132983446121216, cross_entropy: 1.8132983446121216 +[2025-04-29 05:53:28,749][BaseTrainer][INFO] - [Epoch 9/10, Iter 3107/3560] 1.587618112564087, cross_entropy: 1.587618112564087 +[2025-04-29 05:53:29,632][BaseTrainer][INFO] - [Epoch 9/10, Iter 3108/3560] 2.9051969051361084, cross_entropy: 2.9051969051361084 +[2025-04-29 05:53:32,928][BaseTrainer][INFO] - [Epoch 9/10, Iter 3109/3560] 3.2260959148406982, cross_entropy: 3.2260959148406982 +[2025-04-29 05:53:33,822][BaseTrainer][INFO] - [Epoch 9/10, Iter 3110/3560] 3.0470919609069824, cross_entropy: 3.0470919609069824 +[2025-04-29 05:53:36,891][BaseTrainer][INFO] - [Epoch 9/10, Iter 3111/3560] 1.4912309646606445, cross_entropy: 1.4912309646606445 +[2025-04-29 05:53:37,775][BaseTrainer][INFO] - [Epoch 9/10, Iter 3112/3560] 2.1005477905273438, cross_entropy: 2.1005477905273438 +[2025-04-29 05:53:40,128][BaseTrainer][INFO] - [Epoch 9/10, Iter 3113/3560] 1.6471920013427734, cross_entropy: 1.6471920013427734 +[2025-04-29 05:53:41,009][BaseTrainer][INFO] - [Epoch 9/10, Iter 3114/3560] 1.7687376737594604, cross_entropy: 1.7687376737594604 +[2025-04-29 05:53:43,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 3115/3560] 1.5454603433609009, cross_entropy: 1.5454603433609009 +[2025-04-29 05:53:44,017][BaseTrainer][INFO] - [Epoch 9/10, Iter 3116/3560] 2.5235559940338135, cross_entropy: 2.5235559940338135 +[2025-04-29 05:53:47,166][BaseTrainer][INFO] - [Epoch 9/10, Iter 3117/3560] 1.5123956203460693, cross_entropy: 1.5123956203460693 +[2025-04-29 05:53:48,025][BaseTrainer][INFO] - [Epoch 9/10, Iter 3118/3560] 1.5526227951049805, cross_entropy: 1.5526227951049805 +[2025-04-29 05:53:50,848][BaseTrainer][INFO] - [Epoch 9/10, Iter 3119/3560] 1.7421127557754517, cross_entropy: 1.7421127557754517 +[2025-04-29 05:53:51,706][BaseTrainer][INFO] - [Epoch 9/10, Iter 3120/3560] 2.348116874694824, cross_entropy: 2.348116874694824 +[2025-04-29 05:53:54,723][BaseTrainer][INFO] - [Epoch 9/10, Iter 3121/3560] 1.176872730255127, cross_entropy: 1.176872730255127 +[2025-04-29 05:53:55,650][BaseTrainer][INFO] - [Epoch 9/10, Iter 3122/3560] 1.0840874910354614, cross_entropy: 1.0840874910354614 +[2025-04-29 05:53:58,059][BaseTrainer][INFO] - [Epoch 9/10, Iter 3123/3560] 1.4432686567306519, cross_entropy: 1.4432686567306519 +[2025-04-29 05:53:59,018][BaseTrainer][INFO] - [Epoch 9/10, Iter 3124/3560] 1.2356584072113037, cross_entropy: 1.2356584072113037 +[2025-04-29 05:54:01,656][BaseTrainer][INFO] - [Epoch 9/10, Iter 3125/3560] 1.353323221206665, cross_entropy: 1.353323221206665 +[2025-04-29 05:54:02,625][BaseTrainer][INFO] - [Epoch 9/10, Iter 3126/3560] 1.3869212865829468, cross_entropy: 1.3869212865829468 +[2025-04-29 05:54:05,735][BaseTrainer][INFO] - [Epoch 9/10, Iter 3127/3560] 1.767524003982544, cross_entropy: 1.767524003982544 +[2025-04-29 05:54:06,624][BaseTrainer][INFO] - [Epoch 9/10, Iter 3128/3560] 3.1277878284454346, cross_entropy: 3.1277878284454346 +[2025-04-29 05:54:09,344][BaseTrainer][INFO] - [Epoch 9/10, Iter 3129/3560] 1.561808466911316, cross_entropy: 1.561808466911316 +[2025-04-29 05:54:10,227][BaseTrainer][INFO] - [Epoch 9/10, Iter 3130/3560] 2.524721145629883, cross_entropy: 2.524721145629883 +[2025-04-29 05:54:13,144][BaseTrainer][INFO] - [Epoch 9/10, Iter 3131/3560] 2.8679347038269043, cross_entropy: 2.8679347038269043 +[2025-04-29 05:54:14,030][BaseTrainer][INFO] - [Epoch 9/10, Iter 3132/3560] 1.440424919128418, cross_entropy: 1.440424919128418 +[2025-04-29 05:54:16,637][BaseTrainer][INFO] - [Epoch 9/10, Iter 3133/3560] 1.4752705097198486, cross_entropy: 1.4752705097198486 +[2025-04-29 05:54:17,520][BaseTrainer][INFO] - [Epoch 9/10, Iter 3134/3560] 3.017697334289551, cross_entropy: 3.017697334289551 +[2025-04-29 05:54:20,492][BaseTrainer][INFO] - [Epoch 9/10, Iter 3135/3560] 1.7247989177703857, cross_entropy: 1.7247989177703857 +[2025-04-29 05:54:21,353][BaseTrainer][INFO] - [Epoch 9/10, Iter 3136/3560] 3.0944647789001465, cross_entropy: 3.0944647789001465 +[2025-04-29 05:54:23,910][BaseTrainer][INFO] - [Epoch 9/10, Iter 3137/3560] 1.2811294794082642, cross_entropy: 1.2811294794082642 +[2025-04-29 05:54:24,770][BaseTrainer][INFO] - [Epoch 9/10, Iter 3138/3560] 1.6747572422027588, cross_entropy: 1.6747572422027588 +[2025-04-29 05:54:27,347][BaseTrainer][INFO] - [Epoch 9/10, Iter 3139/3560] 0.9140145778656006, cross_entropy: 0.9140145778656006 +[2025-04-29 05:54:28,253][BaseTrainer][INFO] - [Epoch 9/10, Iter 3140/3560] 1.2409617900848389, cross_entropy: 1.2409617900848389 +[2025-04-29 05:54:31,236][BaseTrainer][INFO] - [Epoch 9/10, Iter 3141/3560] 1.2653305530548096, cross_entropy: 1.2653305530548096 +[2025-04-29 05:54:32,098][BaseTrainer][INFO] - [Epoch 9/10, Iter 3142/3560] 3.1353421211242676, cross_entropy: 3.1353421211242676 +[2025-04-29 05:54:34,971][BaseTrainer][INFO] - [Epoch 9/10, Iter 3143/3560] 1.1075966358184814, cross_entropy: 1.1075966358184814 +[2025-04-29 05:54:35,830][BaseTrainer][INFO] - [Epoch 9/10, Iter 3144/3560] 1.0647238492965698, cross_entropy: 1.0647238492965698 +[2025-04-29 05:54:38,856][BaseTrainer][INFO] - [Epoch 9/10, Iter 3145/3560] 2.5297975540161133, cross_entropy: 2.5297975540161133 +[2025-04-29 05:54:39,746][BaseTrainer][INFO] - [Epoch 9/10, Iter 3146/3560] 1.9120407104492188, cross_entropy: 1.9120407104492188 +[2025-04-29 05:54:42,708][BaseTrainer][INFO] - [Epoch 9/10, Iter 3147/3560] 1.067528247833252, cross_entropy: 1.067528247833252 +[2025-04-29 05:54:43,591][BaseTrainer][INFO] - [Epoch 9/10, Iter 3148/3560] 2.9182612895965576, cross_entropy: 2.9182612895965576 +[2025-04-29 05:54:46,280][BaseTrainer][INFO] - [Epoch 9/10, Iter 3149/3560] 2.9641823768615723, cross_entropy: 2.9641823768615723 +[2025-04-29 05:54:47,167][BaseTrainer][INFO] - [Epoch 9/10, Iter 3150/3560] 1.9090895652770996, cross_entropy: 1.9090895652770996 +[2025-04-29 05:54:49,179][BaseTrainer][INFO] - [Epoch 9/10, Iter 3151/3560] 3.252281665802002, cross_entropy: 3.252281665802002 +[2025-04-29 05:54:50,110][BaseTrainer][INFO] - [Epoch 9/10, Iter 3152/3560] 1.3388463258743286, cross_entropy: 1.3388463258743286 +[2025-04-29 05:54:52,866][BaseTrainer][INFO] - [Epoch 9/10, Iter 3153/3560] 2.6879043579101562, cross_entropy: 2.6879043579101562 +[2025-04-29 05:54:53,797][BaseTrainer][INFO] - [Epoch 9/10, Iter 3154/3560] 1.6499505043029785, cross_entropy: 1.6499505043029785 +[2025-04-29 05:54:56,192][BaseTrainer][INFO] - [Epoch 9/10, Iter 3155/3560] 2.4205527305603027, cross_entropy: 2.4205527305603027 +[2025-04-29 05:54:57,200][BaseTrainer][INFO] - [Epoch 9/10, Iter 3156/3560] 3.3830928802490234, cross_entropy: 3.3830928802490234 +[2025-04-29 05:54:59,663][BaseTrainer][INFO] - [Epoch 9/10, Iter 3157/3560] 3.1782784461975098, cross_entropy: 3.1782784461975098 +[2025-04-29 05:55:00,723][BaseTrainer][INFO] - [Epoch 9/10, Iter 3158/3560] 2.969787359237671, cross_entropy: 2.969787359237671 +[2025-04-29 05:55:03,427][BaseTrainer][INFO] - [Epoch 9/10, Iter 3159/3560] 0.9925233125686646, cross_entropy: 0.9925233125686646 +[2025-04-29 05:55:04,566][BaseTrainer][INFO] - [Epoch 9/10, Iter 3160/3560] 1.9330601692199707, cross_entropy: 1.9330601692199707 +[2025-04-29 05:55:07,550][BaseTrainer][INFO] - [Epoch 9/10, Iter 3161/3560] 2.739532947540283, cross_entropy: 2.739532947540283 +[2025-04-29 05:55:08,638][BaseTrainer][INFO] - [Epoch 9/10, Iter 3162/3560] 1.9003353118896484, cross_entropy: 1.9003353118896484 +[2025-04-29 05:55:12,225][BaseTrainer][INFO] - [Epoch 9/10, Iter 3163/3560] 3.015242338180542, cross_entropy: 3.015242338180542 +[2025-04-29 05:55:13,084][BaseTrainer][INFO] - [Epoch 9/10, Iter 3164/3560] 2.3178799152374268, cross_entropy: 2.3178799152374268 +[2025-04-29 05:55:15,703][BaseTrainer][INFO] - [Epoch 9/10, Iter 3165/3560] 2.586358070373535, cross_entropy: 2.586358070373535 +[2025-04-29 05:55:16,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 3166/3560] 1.381004810333252, cross_entropy: 1.381004810333252 +[2025-04-29 05:55:19,630][BaseTrainer][INFO] - [Epoch 9/10, Iter 3167/3560] 1.7531218528747559, cross_entropy: 1.7531218528747559 +[2025-04-29 05:55:20,615][BaseTrainer][INFO] - [Epoch 9/10, Iter 3168/3560] 2.17034912109375, cross_entropy: 2.17034912109375 +[2025-04-29 05:55:23,201][BaseTrainer][INFO] - [Epoch 9/10, Iter 3169/3560] 1.221144437789917, cross_entropy: 1.221144437789917 +[2025-04-29 05:55:24,173][BaseTrainer][INFO] - [Epoch 9/10, Iter 3170/3560] 1.5253405570983887, cross_entropy: 1.5253405570983887 +[2025-04-29 05:55:27,978][BaseTrainer][INFO] - [Epoch 9/10, Iter 3171/3560] 1.6189711093902588, cross_entropy: 1.6189711093902588 +[2025-04-29 05:55:28,860][BaseTrainer][INFO] - [Epoch 9/10, Iter 3172/3560] 3.3045029640197754, cross_entropy: 3.3045029640197754 +[2025-04-29 05:55:31,428][BaseTrainer][INFO] - [Epoch 9/10, Iter 3173/3560] 3.055208444595337, cross_entropy: 3.055208444595337 +[2025-04-29 05:55:32,285][BaseTrainer][INFO] - [Epoch 9/10, Iter 3174/3560] 2.671070098876953, cross_entropy: 2.671070098876953 +[2025-04-29 05:55:34,692][BaseTrainer][INFO] - [Epoch 9/10, Iter 3175/3560] 1.735158920288086, cross_entropy: 1.735158920288086 +[2025-04-29 05:55:35,576][BaseTrainer][INFO] - [Epoch 9/10, Iter 3176/3560] 2.810227394104004, cross_entropy: 2.810227394104004 +[2025-04-29 05:55:38,642][BaseTrainer][INFO] - [Epoch 9/10, Iter 3177/3560] 2.5346012115478516, cross_entropy: 2.5346012115478516 +[2025-04-29 05:55:39,528][BaseTrainer][INFO] - [Epoch 9/10, Iter 3178/3560] 1.2078680992126465, cross_entropy: 1.2078680992126465 +[2025-04-29 05:55:42,119][BaseTrainer][INFO] - [Epoch 9/10, Iter 3179/3560] 3.0202667713165283, cross_entropy: 3.0202667713165283 +[2025-04-29 05:55:43,000][BaseTrainer][INFO] - [Epoch 9/10, Iter 3180/3560] 1.1639659404754639, cross_entropy: 1.1639659404754639 +[2025-04-29 05:55:45,824][BaseTrainer][INFO] - [Epoch 9/10, Iter 3181/3560] 2.763667583465576, cross_entropy: 2.763667583465576 +[2025-04-29 05:55:46,712][BaseTrainer][INFO] - [Epoch 9/10, Iter 3182/3560] 2.54093599319458, cross_entropy: 2.54093599319458 +[2025-04-29 05:55:49,207][BaseTrainer][INFO] - [Epoch 9/10, Iter 3183/3560] 3.343989849090576, cross_entropy: 3.343989849090576 +[2025-04-29 05:55:50,155][BaseTrainer][INFO] - [Epoch 9/10, Iter 3184/3560] 2.4972078800201416, cross_entropy: 2.4972078800201416 +[2025-04-29 05:55:52,977][BaseTrainer][INFO] - [Epoch 9/10, Iter 3185/3560] 1.8835651874542236, cross_entropy: 1.8835651874542236 +[2025-04-29 05:55:53,898][BaseTrainer][INFO] - [Epoch 9/10, Iter 3186/3560] 3.243439197540283, cross_entropy: 3.243439197540283 +[2025-04-29 05:55:56,858][BaseTrainer][INFO] - [Epoch 9/10, Iter 3187/3560] 2.178149700164795, cross_entropy: 2.178149700164795 +[2025-04-29 05:55:57,792][BaseTrainer][INFO] - [Epoch 9/10, Iter 3188/3560] 1.030733346939087, cross_entropy: 1.030733346939087 +[2025-04-29 05:56:00,606][BaseTrainer][INFO] - [Epoch 9/10, Iter 3189/3560] 2.0250024795532227, cross_entropy: 2.0250024795532227 +[2025-04-29 05:56:01,486][BaseTrainer][INFO] - [Epoch 9/10, Iter 3190/3560] 3.316704273223877, cross_entropy: 3.316704273223877 +[2025-04-29 05:56:04,077][BaseTrainer][INFO] - [Epoch 9/10, Iter 3191/3560] 1.389000415802002, cross_entropy: 1.389000415802002 +[2025-04-29 05:56:04,936][BaseTrainer][INFO] - [Epoch 9/10, Iter 3192/3560] 1.7852418422698975, cross_entropy: 1.7852418422698975 +[2025-04-29 05:56:07,812][BaseTrainer][INFO] - [Epoch 9/10, Iter 3193/3560] 2.4722375869750977, cross_entropy: 2.4722375869750977 +[2025-04-29 05:56:08,704][BaseTrainer][INFO] - [Epoch 9/10, Iter 3194/3560] 2.4277830123901367, cross_entropy: 2.4277830123901367 +[2025-04-29 05:56:11,433][BaseTrainer][INFO] - [Epoch 9/10, Iter 3195/3560] 2.8146121501922607, cross_entropy: 2.8146121501922607 +[2025-04-29 05:56:12,295][BaseTrainer][INFO] - [Epoch 9/10, Iter 3196/3560] 2.8254494667053223, cross_entropy: 2.8254494667053223 +[2025-04-29 05:56:15,776][BaseTrainer][INFO] - [Epoch 9/10, Iter 3197/3560] 3.0968592166900635, cross_entropy: 3.0968592166900635 +[2025-04-29 05:56:16,657][BaseTrainer][INFO] - [Epoch 9/10, Iter 3198/3560] 2.3861947059631348, cross_entropy: 2.3861947059631348 +[2025-04-29 05:56:19,672][BaseTrainer][INFO] - [Epoch 9/10, Iter 3199/3560] 1.8190644979476929, cross_entropy: 1.8190644979476929 +[2025-04-29 05:56:20,555][BaseTrainer][INFO] - [Epoch 9/10, Iter 3200/3560] 2.8276515007019043, cross_entropy: 2.8276515007019043 +[2025-04-29 05:56:23,372][BaseTrainer][INFO] - [Epoch 9/10, Iter 3201/3560] 2.8581082820892334, cross_entropy: 2.8581082820892334 +[2025-04-29 05:56:24,261][BaseTrainer][INFO] - [Epoch 9/10, Iter 3202/3560] 2.0719707012176514, cross_entropy: 2.0719707012176514 +[2025-04-29 05:56:27,628][BaseTrainer][INFO] - [Epoch 9/10, Iter 3203/3560] 2.798443078994751, cross_entropy: 2.798443078994751 +[2025-04-29 05:56:28,397][BaseTrainer][INFO] - [Epoch 9/10, Iter 3204/3560] 2.7393906116485596, cross_entropy: 2.7393906116485596 +[2025-04-29 05:59:13,800][BaseTrainer][INFO] - [Epoch 9/10] (train) 2.11360502243042, cross_entropy: 2.11360502243042 +[2025-04-29 05:59:13,801][BaseTrainer][INFO] - [Epoch 9/10] (validation) 1.2575591802597046, cross_entropy: 1.2575591802597046 +[2025-04-29 05:59:14,670][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 05:59:15,145][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch9.pth. +[2025-04-29 05:59:15,951][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 05:59:20,569][BaseTrainer][INFO] - [Epoch 10/10, Iter 3205/3560] 1.6122984886169434, cross_entropy: 1.6122984886169434 +[2025-04-29 05:59:21,655][BaseTrainer][INFO] - [Epoch 10/10, Iter 3206/3560] 1.8466064929962158, cross_entropy: 1.8466064929962158 +[2025-04-29 05:59:24,692][BaseTrainer][INFO] - [Epoch 10/10, Iter 3207/3560] 2.5064752101898193, cross_entropy: 2.5064752101898193 +[2025-04-29 05:59:25,580][BaseTrainer][INFO] - [Epoch 10/10, Iter 3208/3560] 3.095668315887451, cross_entropy: 3.095668315887451 +[2025-04-29 05:59:28,415][BaseTrainer][INFO] - [Epoch 10/10, Iter 3209/3560] 2.6586952209472656, cross_entropy: 2.6586952209472656 +[2025-04-29 05:59:29,295][BaseTrainer][INFO] - [Epoch 10/10, Iter 3210/3560] 1.0103154182434082, cross_entropy: 1.0103154182434082 +[2025-04-29 05:59:31,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3211/3560] 2.9404191970825195, cross_entropy: 2.9404191970825195 +[2025-04-29 05:59:32,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3212/3560] 0.9994689226150513, cross_entropy: 0.9994689226150513 +[2025-04-29 05:59:34,371][BaseTrainer][INFO] - [Epoch 10/10, Iter 3213/3560] 2.4547064304351807, cross_entropy: 2.4547064304351807 +[2025-04-29 05:59:35,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3214/3560] 1.0461033582687378, cross_entropy: 1.0461033582687378 +[2025-04-29 05:59:38,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3215/3560] 1.3211345672607422, cross_entropy: 1.3211345672607422 +[2025-04-29 05:59:39,206][BaseTrainer][INFO] - [Epoch 10/10, Iter 3216/3560] 1.178694725036621, cross_entropy: 1.178694725036621 +[2025-04-29 05:59:42,245][BaseTrainer][INFO] - [Epoch 10/10, Iter 3217/3560] 2.9008071422576904, cross_entropy: 2.9008071422576904 +[2025-04-29 05:59:43,162][BaseTrainer][INFO] - [Epoch 10/10, Iter 3218/3560] 1.804067850112915, cross_entropy: 1.804067850112915 +[2025-04-29 05:59:46,215][BaseTrainer][INFO] - [Epoch 10/10, Iter 3219/3560] 1.402071475982666, cross_entropy: 1.402071475982666 +[2025-04-29 05:59:47,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3220/3560] 3.3096301555633545, cross_entropy: 3.3096301555633545 +[2025-04-29 05:59:50,052][BaseTrainer][INFO] - [Epoch 10/10, Iter 3221/3560] 2.8243908882141113, cross_entropy: 2.8243908882141113 +[2025-04-29 05:59:50,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3222/3560] 1.0715081691741943, cross_entropy: 1.0715081691741943 +[2025-04-29 05:59:53,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3223/3560] 2.766963005065918, cross_entropy: 2.766963005065918 +[2025-04-29 05:59:54,549][BaseTrainer][INFO] - [Epoch 10/10, Iter 3224/3560] 1.479715347290039, cross_entropy: 1.479715347290039 +[2025-04-29 05:59:56,966][BaseTrainer][INFO] - [Epoch 10/10, Iter 3225/3560] 2.343287706375122, cross_entropy: 2.343287706375122 +[2025-04-29 05:59:57,904][BaseTrainer][INFO] - [Epoch 10/10, Iter 3226/3560] 1.3094782829284668, cross_entropy: 1.3094782829284668 +[2025-04-29 06:00:00,736][BaseTrainer][INFO] - [Epoch 10/10, Iter 3227/3560] 3.1032471656799316, cross_entropy: 3.1032471656799316 +[2025-04-29 06:00:01,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3228/3560] 1.2067430019378662, cross_entropy: 1.2067430019378662 +[2025-04-29 06:00:04,150][BaseTrainer][INFO] - [Epoch 10/10, Iter 3229/3560] 2.4363551139831543, cross_entropy: 2.4363551139831543 +[2025-04-29 06:00:05,582][BaseTrainer][INFO] - [Epoch 10/10, Iter 3230/3560] 1.3244761228561401, cross_entropy: 1.3244761228561401 +[2025-04-29 06:00:07,629][BaseTrainer][INFO] - [Epoch 10/10, Iter 3231/3560] 3.195483922958374, cross_entropy: 3.195483922958374 +[2025-04-29 06:00:09,796][BaseTrainer][INFO] - [Epoch 10/10, Iter 3232/3560] 2.736344575881958, cross_entropy: 2.736344575881958 +[2025-04-29 06:00:10,725][BaseTrainer][INFO] - [Epoch 10/10, Iter 3233/3560] 1.2886455059051514, cross_entropy: 1.2886455059051514 +[2025-04-29 06:00:13,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3234/3560] 1.8947689533233643, cross_entropy: 1.8947689533233643 +[2025-04-29 06:00:14,900][BaseTrainer][INFO] - [Epoch 10/10, Iter 3235/3560] 1.4521327018737793, cross_entropy: 1.4521327018737793 +[2025-04-29 06:00:16,905][BaseTrainer][INFO] - [Epoch 10/10, Iter 3236/3560] 2.957641124725342, cross_entropy: 2.957641124725342 +[2025-04-29 06:00:18,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3237/3560] 1.535132646560669, cross_entropy: 1.535132646560669 +[2025-04-29 06:00:20,973][BaseTrainer][INFO] - [Epoch 10/10, Iter 3238/3560] 2.007206439971924, cross_entropy: 2.007206439971924 +[2025-04-29 06:00:22,196][BaseTrainer][INFO] - [Epoch 10/10, Iter 3239/3560] 2.3727452754974365, cross_entropy: 2.3727452754974365 +[2025-04-29 06:00:24,702][BaseTrainer][INFO] - [Epoch 10/10, Iter 3240/3560] 1.1064404249191284, cross_entropy: 1.1064404249191284 +[2025-04-29 06:00:26,400][BaseTrainer][INFO] - [Epoch 10/10, Iter 3241/3560] 3.080273151397705, cross_entropy: 3.080273151397705 +[2025-04-29 06:00:28,422][BaseTrainer][INFO] - [Epoch 10/10, Iter 3242/3560] 1.8056873083114624, cross_entropy: 1.8056873083114624 +[2025-04-29 06:00:31,131][BaseTrainer][INFO] - [Epoch 10/10, Iter 3243/3560] 3.0373880863189697, cross_entropy: 3.0373880863189697 +[2025-04-29 06:00:32,278][BaseTrainer][INFO] - [Epoch 10/10, Iter 3244/3560] 2.0951807498931885, cross_entropy: 2.0951807498931885 +[2025-04-29 06:00:35,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3245/3560] 2.8551647663116455, cross_entropy: 2.8551647663116455 +[2025-04-29 06:00:36,438][BaseTrainer][INFO] - [Epoch 10/10, Iter 3246/3560] 1.9729400873184204, cross_entropy: 1.9729400873184204 +[2025-04-29 06:00:38,892][BaseTrainer][INFO] - [Epoch 10/10, Iter 3247/3560] 2.8520867824554443, cross_entropy: 2.8520867824554443 +[2025-04-29 06:00:40,246][BaseTrainer][INFO] - [Epoch 10/10, Iter 3248/3560] 2.9287476539611816, cross_entropy: 2.9287476539611816 +[2025-04-29 06:00:42,179][BaseTrainer][INFO] - [Epoch 10/10, Iter 3249/3560] 2.5337157249450684, cross_entropy: 2.5337157249450684 +[2025-04-29 06:00:44,574][BaseTrainer][INFO] - [Epoch 10/10, Iter 3250/3560] 1.4174931049346924, cross_entropy: 1.4174931049346924 +[2025-04-29 06:00:45,554][BaseTrainer][INFO] - [Epoch 10/10, Iter 3251/3560] 1.6724364757537842, cross_entropy: 1.6724364757537842 +[2025-04-29 06:00:48,563][BaseTrainer][INFO] - [Epoch 10/10, Iter 3252/3560] 1.14804208278656, cross_entropy: 1.14804208278656 +[2025-04-29 06:00:49,468][BaseTrainer][INFO] - [Epoch 10/10, Iter 3253/3560] 1.0396809577941895, cross_entropy: 1.0396809577941895 +[2025-04-29 06:00:51,819][BaseTrainer][INFO] - [Epoch 10/10, Iter 3254/3560] 1.8795896768569946, cross_entropy: 1.8795896768569946 +[2025-04-29 06:00:52,732][BaseTrainer][INFO] - [Epoch 10/10, Iter 3255/3560] 2.369978189468384, cross_entropy: 2.369978189468384 +[2025-04-29 06:00:55,149][BaseTrainer][INFO] - [Epoch 10/10, Iter 3256/3560] 2.7892861366271973, cross_entropy: 2.7892861366271973 +[2025-04-29 06:00:56,683][BaseTrainer][INFO] - [Epoch 10/10, Iter 3257/3560] 1.2570276260375977, cross_entropy: 1.2570276260375977 +[2025-04-29 06:00:59,306][BaseTrainer][INFO] - [Epoch 10/10, Iter 3258/3560] 3.0425374507904053, cross_entropy: 3.0425374507904053 +[2025-04-29 06:01:00,255][BaseTrainer][INFO] - [Epoch 10/10, Iter 3259/3560] 1.444045066833496, cross_entropy: 1.444045066833496 +[2025-04-29 06:01:02,783][BaseTrainer][INFO] - [Epoch 10/10, Iter 3260/3560] 2.2239928245544434, cross_entropy: 2.2239928245544434 +[2025-04-29 06:01:03,957][BaseTrainer][INFO] - [Epoch 10/10, Iter 3261/3560] 2.1936111450195312, cross_entropy: 2.1936111450195312 +[2025-04-29 06:01:08,080][BaseTrainer][INFO] - [Epoch 10/10, Iter 3262/3560] 1.586134433746338, cross_entropy: 1.586134433746338 +[2025-04-29 06:01:08,965][BaseTrainer][INFO] - [Epoch 10/10, Iter 3263/3560] 1.6246867179870605, cross_entropy: 1.6246867179870605 +[2025-04-29 06:01:12,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3264/3560] 2.311784029006958, cross_entropy: 2.311784029006958 +[2025-04-29 06:01:13,026][BaseTrainer][INFO] - [Epoch 10/10, Iter 3265/3560] 1.3089537620544434, cross_entropy: 1.3089537620544434 +[2025-04-29 06:01:15,949][BaseTrainer][INFO] - [Epoch 10/10, Iter 3266/3560] 2.8374874591827393, cross_entropy: 2.8374874591827393 +[2025-04-29 06:01:16,835][BaseTrainer][INFO] - [Epoch 10/10, Iter 3267/3560] 1.711223840713501, cross_entropy: 1.711223840713501 +[2025-04-29 06:01:19,589][BaseTrainer][INFO] - [Epoch 10/10, Iter 3268/3560] 1.420506238937378, cross_entropy: 1.420506238937378 +[2025-04-29 06:01:20,448][BaseTrainer][INFO] - [Epoch 10/10, Iter 3269/3560] 2.920351266860962, cross_entropy: 2.920351266860962 +[2025-04-29 06:01:23,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3270/3560] 3.148378849029541, cross_entropy: 3.148378849029541 +[2025-04-29 06:01:24,348][BaseTrainer][INFO] - [Epoch 10/10, Iter 3271/3560] 3.1549072265625, cross_entropy: 3.1549072265625 +[2025-04-29 06:01:27,317][BaseTrainer][INFO] - [Epoch 10/10, Iter 3272/3560] 0.8662244081497192, cross_entropy: 0.8662244081497192 +[2025-04-29 06:01:28,198][BaseTrainer][INFO] - [Epoch 10/10, Iter 3273/3560] 2.1284990310668945, cross_entropy: 2.1284990310668945 +[2025-04-29 06:01:31,148][BaseTrainer][INFO] - [Epoch 10/10, Iter 3274/3560] 3.0889627933502197, cross_entropy: 3.0889627933502197 +[2025-04-29 06:01:32,033][BaseTrainer][INFO] - [Epoch 10/10, Iter 3275/3560] 3.1684916019439697, cross_entropy: 3.1684916019439697 +[2025-04-29 06:01:35,082][BaseTrainer][INFO] - [Epoch 10/10, Iter 3276/3560] 1.3614253997802734, cross_entropy: 1.3614253997802734 +[2025-04-29 06:01:35,968][BaseTrainer][INFO] - [Epoch 10/10, Iter 3277/3560] 1.8218224048614502, cross_entropy: 1.8218224048614502 +[2025-04-29 06:01:37,986][BaseTrainer][INFO] - [Epoch 10/10, Iter 3278/3560] 2.3175268173217773, cross_entropy: 2.3175268173217773 +[2025-04-29 06:01:38,871][BaseTrainer][INFO] - [Epoch 10/10, Iter 3279/3560] 3.3478264808654785, cross_entropy: 3.3478264808654785 +[2025-04-29 06:01:41,670][BaseTrainer][INFO] - [Epoch 10/10, Iter 3280/3560] 1.2362213134765625, cross_entropy: 1.2362213134765625 +[2025-04-29 06:01:42,529][BaseTrainer][INFO] - [Epoch 10/10, Iter 3281/3560] 1.1875736713409424, cross_entropy: 1.1875736713409424 +[2025-04-29 06:01:45,565][BaseTrainer][INFO] - [Epoch 10/10, Iter 3282/3560] 2.971140146255493, cross_entropy: 2.971140146255493 +[2025-04-29 06:01:46,425][BaseTrainer][INFO] - [Epoch 10/10, Iter 3283/3560] 1.5706236362457275, cross_entropy: 1.5706236362457275 +[2025-04-29 06:01:49,756][BaseTrainer][INFO] - [Epoch 10/10, Iter 3284/3560] 1.0684950351715088, cross_entropy: 1.0684950351715088 +[2025-04-29 06:01:50,642][BaseTrainer][INFO] - [Epoch 10/10, Iter 3285/3560] 1.0887856483459473, cross_entropy: 1.0887856483459473 +[2025-04-29 06:01:53,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3286/3560] 3.0150132179260254, cross_entropy: 3.0150132179260254 +[2025-04-29 06:01:54,535][BaseTrainer][INFO] - [Epoch 10/10, Iter 3287/3560] 3.1932051181793213, cross_entropy: 3.1932051181793213 +[2025-04-29 06:01:57,423][BaseTrainer][INFO] - [Epoch 10/10, Iter 3288/3560] 3.044180154800415, cross_entropy: 3.044180154800415 +[2025-04-29 06:01:58,309][BaseTrainer][INFO] - [Epoch 10/10, Iter 3289/3560] 3.309762954711914, cross_entropy: 3.309762954711914 +[2025-04-29 06:02:01,032][BaseTrainer][INFO] - [Epoch 10/10, Iter 3290/3560] 1.166505217552185, cross_entropy: 1.166505217552185 +[2025-04-29 06:02:01,913][BaseTrainer][INFO] - [Epoch 10/10, Iter 3291/3560] 1.569672703742981, cross_entropy: 1.569672703742981 +[2025-04-29 06:02:04,791][BaseTrainer][INFO] - [Epoch 10/10, Iter 3292/3560] 3.3513567447662354, cross_entropy: 3.3513567447662354 +[2025-04-29 06:02:05,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3293/3560] 1.554779052734375, cross_entropy: 1.554779052734375 +[2025-04-29 06:02:08,745][BaseTrainer][INFO] - [Epoch 10/10, Iter 3294/3560] 2.3129003047943115, cross_entropy: 2.3129003047943115 +[2025-04-29 06:02:09,629][BaseTrainer][INFO] - [Epoch 10/10, Iter 3295/3560] 2.2144851684570312, cross_entropy: 2.2144851684570312 +[2025-04-29 06:02:11,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3296/3560] 2.295708656311035, cross_entropy: 2.295708656311035 +[2025-04-29 06:02:12,863][BaseTrainer][INFO] - [Epoch 10/10, Iter 3297/3560] 2.828061580657959, cross_entropy: 2.828061580657959 +[2025-04-29 06:02:15,498][BaseTrainer][INFO] - [Epoch 10/10, Iter 3298/3560] 3.286921977996826, cross_entropy: 3.286921977996826 +[2025-04-29 06:02:16,386][BaseTrainer][INFO] - [Epoch 10/10, Iter 3299/3560] 1.1898597478866577, cross_entropy: 1.1898597478866577 +[2025-04-29 06:02:18,785][BaseTrainer][INFO] - [Epoch 10/10, Iter 3300/3560] 3.171715259552002, cross_entropy: 3.171715259552002 +[2025-04-29 06:02:19,646][BaseTrainer][INFO] - [Epoch 10/10, Iter 3301/3560] 1.5806134939193726, cross_entropy: 1.5806134939193726 +[2025-04-29 06:02:23,058][BaseTrainer][INFO] - [Epoch 10/10, Iter 3302/3560] 2.942660331726074, cross_entropy: 2.942660331726074 +[2025-04-29 06:02:23,936][BaseTrainer][INFO] - [Epoch 10/10, Iter 3303/3560] 0.982223629951477, cross_entropy: 0.982223629951477 +[2025-04-29 06:02:26,540][BaseTrainer][INFO] - [Epoch 10/10, Iter 3304/3560] 1.5985043048858643, cross_entropy: 1.5985043048858643 +[2025-04-29 06:02:27,399][BaseTrainer][INFO] - [Epoch 10/10, Iter 3305/3560] 1.0593549013137817, cross_entropy: 1.0593549013137817 +[2025-04-29 06:02:30,180][BaseTrainer][INFO] - [Epoch 10/10, Iter 3306/3560] 2.6360392570495605, cross_entropy: 2.6360392570495605 +[2025-04-29 06:02:31,081][BaseTrainer][INFO] - [Epoch 10/10, Iter 3307/3560] 0.7582761645317078, cross_entropy: 0.7582761645317078 +[2025-04-29 06:02:33,792][BaseTrainer][INFO] - [Epoch 10/10, Iter 3308/3560] 1.726109266281128, cross_entropy: 1.726109266281128 +[2025-04-29 06:02:34,685][BaseTrainer][INFO] - [Epoch 10/10, Iter 3309/3560] 3.292198896408081, cross_entropy: 3.292198896408081 +[2025-04-29 06:02:38,497][BaseTrainer][INFO] - [Epoch 10/10, Iter 3310/3560] 2.880140781402588, cross_entropy: 2.880140781402588 +[2025-04-29 06:02:39,358][BaseTrainer][INFO] - [Epoch 10/10, Iter 3311/3560] 2.409808874130249, cross_entropy: 2.409808874130249 +[2025-04-29 06:02:42,189][BaseTrainer][INFO] - [Epoch 10/10, Iter 3312/3560] 2.972179889678955, cross_entropy: 2.972179889678955 +[2025-04-29 06:02:43,071][BaseTrainer][INFO] - [Epoch 10/10, Iter 3313/3560] 2.8632867336273193, cross_entropy: 2.8632867336273193 +[2025-04-29 06:02:46,165][BaseTrainer][INFO] - [Epoch 10/10, Iter 3314/3560] 2.401447296142578, cross_entropy: 2.401447296142578 +[2025-04-29 06:02:47,051][BaseTrainer][INFO] - [Epoch 10/10, Iter 3315/3560] 1.9465317726135254, cross_entropy: 1.9465317726135254 +[2025-04-29 06:02:49,072][BaseTrainer][INFO] - [Epoch 10/10, Iter 3316/3560] 2.862060070037842, cross_entropy: 2.862060070037842 +[2025-04-29 06:02:49,961][BaseTrainer][INFO] - [Epoch 10/10, Iter 3317/3560] 1.1854320764541626, cross_entropy: 1.1854320764541626 +[2025-04-29 06:02:52,289][BaseTrainer][INFO] - [Epoch 10/10, Iter 3318/3560] 1.4755244255065918, cross_entropy: 1.4755244255065918 +[2025-04-29 06:02:53,151][BaseTrainer][INFO] - [Epoch 10/10, Iter 3319/3560] 1.9361282587051392, cross_entropy: 1.9361282587051392 +[2025-04-29 06:02:55,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3320/3560] 1.6194071769714355, cross_entropy: 1.6194071769714355 +[2025-04-29 06:02:56,480][BaseTrainer][INFO] - [Epoch 10/10, Iter 3321/3560] 2.839733600616455, cross_entropy: 2.839733600616455 +[2025-04-29 06:02:59,525][BaseTrainer][INFO] - [Epoch 10/10, Iter 3322/3560] 2.829684019088745, cross_entropy: 2.829684019088745 +[2025-04-29 06:03:00,509][BaseTrainer][INFO] - [Epoch 10/10, Iter 3323/3560] 1.1700377464294434, cross_entropy: 1.1700377464294434 +[2025-04-29 06:03:02,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3324/3560] 2.465641975402832, cross_entropy: 2.465641975402832 +[2025-04-29 06:03:03,721][BaseTrainer][INFO] - [Epoch 10/10, Iter 3325/3560] 2.756345272064209, cross_entropy: 2.756345272064209 +[2025-04-29 06:03:06,087][BaseTrainer][INFO] - [Epoch 10/10, Iter 3326/3560] 2.161536693572998, cross_entropy: 2.161536693572998 +[2025-04-29 06:03:07,064][BaseTrainer][INFO] - [Epoch 10/10, Iter 3327/3560] 1.5532341003417969, cross_entropy: 1.5532341003417969 +[2025-04-29 06:03:09,937][BaseTrainer][INFO] - [Epoch 10/10, Iter 3328/3560] 2.5721611976623535, cross_entropy: 2.5721611976623535 +[2025-04-29 06:03:10,843][BaseTrainer][INFO] - [Epoch 10/10, Iter 3329/3560] 1.3518463373184204, cross_entropy: 1.3518463373184204 +[2025-04-29 06:03:13,707][BaseTrainer][INFO] - [Epoch 10/10, Iter 3330/3560] 1.2897043228149414, cross_entropy: 1.2897043228149414 +[2025-04-29 06:03:14,628][BaseTrainer][INFO] - [Epoch 10/10, Iter 3331/3560] 1.3381521701812744, cross_entropy: 1.3381521701812744 +[2025-04-29 06:03:18,003][BaseTrainer][INFO] - [Epoch 10/10, Iter 3332/3560] 1.6871403455734253, cross_entropy: 1.6871403455734253 +[2025-04-29 06:03:18,925][BaseTrainer][INFO] - [Epoch 10/10, Iter 3333/3560] 3.247450828552246, cross_entropy: 3.247450828552246 +[2025-04-29 06:03:21,637][BaseTrainer][INFO] - [Epoch 10/10, Iter 3334/3560] 1.3580430746078491, cross_entropy: 1.3580430746078491 +[2025-04-29 06:03:22,575][BaseTrainer][INFO] - [Epoch 10/10, Iter 3335/3560] 2.788698196411133, cross_entropy: 2.788698196411133 +[2025-04-29 06:03:24,972][BaseTrainer][INFO] - [Epoch 10/10, Iter 3336/3560] 1.3145755529403687, cross_entropy: 1.3145755529403687 +[2025-04-29 06:03:26,017][BaseTrainer][INFO] - [Epoch 10/10, Iter 3337/3560] 1.9090583324432373, cross_entropy: 1.9090583324432373 +[2025-04-29 06:03:28,929][BaseTrainer][INFO] - [Epoch 10/10, Iter 3338/3560] 0.9496111273765564, cross_entropy: 0.9496111273765564 +[2025-04-29 06:03:29,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3339/3560] 2.6447904109954834, cross_entropy: 2.6447904109954834 +[2025-04-29 06:03:32,301][BaseTrainer][INFO] - [Epoch 10/10, Iter 3340/3560] 1.2438405752182007, cross_entropy: 1.2438405752182007 +[2025-04-29 06:03:33,250][BaseTrainer][INFO] - [Epoch 10/10, Iter 3341/3560] 2.073556423187256, cross_entropy: 2.073556423187256 +[2025-04-29 06:03:35,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3342/3560] 1.6199004650115967, cross_entropy: 1.6199004650115967 +[2025-04-29 06:03:36,730][BaseTrainer][INFO] - [Epoch 10/10, Iter 3343/3560] 2.5631752014160156, cross_entropy: 2.5631752014160156 +[2025-04-29 06:03:39,316][BaseTrainer][INFO] - [Epoch 10/10, Iter 3344/3560] 1.6705116033554077, cross_entropy: 1.6705116033554077 +[2025-04-29 06:03:40,184][BaseTrainer][INFO] - [Epoch 10/10, Iter 3345/3560] 2.444632053375244, cross_entropy: 2.444632053375244 +[2025-04-29 06:03:43,934][BaseTrainer][INFO] - [Epoch 10/10, Iter 3346/3560] 2.5750088691711426, cross_entropy: 2.5750088691711426 +[2025-04-29 06:03:44,815][BaseTrainer][INFO] - [Epoch 10/10, Iter 3347/3560] 1.2766127586364746, cross_entropy: 1.2766127586364746 +[2025-04-29 06:03:48,153][BaseTrainer][INFO] - [Epoch 10/10, Iter 3348/3560] 2.9798364639282227, cross_entropy: 2.9798364639282227 +[2025-04-29 06:03:49,012][BaseTrainer][INFO] - [Epoch 10/10, Iter 3349/3560] 2.780001640319824, cross_entropy: 2.780001640319824 +[2025-04-29 06:03:51,936][BaseTrainer][INFO] - [Epoch 10/10, Iter 3350/3560] 3.139617443084717, cross_entropy: 3.139617443084717 +[2025-04-29 06:03:52,820][BaseTrainer][INFO] - [Epoch 10/10, Iter 3351/3560] 1.1900806427001953, cross_entropy: 1.1900806427001953 +[2025-04-29 06:03:55,331][BaseTrainer][INFO] - [Epoch 10/10, Iter 3352/3560] 1.5431241989135742, cross_entropy: 1.5431241989135742 +[2025-04-29 06:03:56,214][BaseTrainer][INFO] - [Epoch 10/10, Iter 3353/3560] 2.4138758182525635, cross_entropy: 2.4138758182525635 +[2025-04-29 06:03:58,557][BaseTrainer][INFO] - [Epoch 10/10, Iter 3354/3560] 1.256422996520996, cross_entropy: 1.256422996520996 +[2025-04-29 06:03:59,414][BaseTrainer][INFO] - [Epoch 10/10, Iter 3355/3560] 2.1209449768066406, cross_entropy: 2.1209449768066406 +[2025-04-29 06:04:01,828][BaseTrainer][INFO] - [Epoch 10/10, Iter 3356/3560] 2.021899700164795, cross_entropy: 2.021899700164795 +[2025-04-29 06:04:02,738][BaseTrainer][INFO] - [Epoch 10/10, Iter 3357/3560] 2.7513060569763184, cross_entropy: 2.7513060569763184 +[2025-04-29 06:04:05,535][BaseTrainer][INFO] - [Epoch 10/10, Iter 3358/3560] 2.206815719604492, cross_entropy: 2.206815719604492 +[2025-04-29 06:04:06,395][BaseTrainer][INFO] - [Epoch 10/10, Iter 3359/3560] 1.6897165775299072, cross_entropy: 1.6897165775299072 +[2025-04-29 06:04:10,132][BaseTrainer][INFO] - [Epoch 10/10, Iter 3360/3560] 2.9675188064575195, cross_entropy: 2.9675188064575195 +[2025-04-29 06:04:11,023][BaseTrainer][INFO] - [Epoch 10/10, Iter 3361/3560] 1.097658395767212, cross_entropy: 1.097658395767212 +[2025-04-29 06:04:13,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3362/3560] 2.232057809829712, cross_entropy: 2.232057809829712 +[2025-04-29 06:04:14,162][BaseTrainer][INFO] - [Epoch 10/10, Iter 3363/3560] 2.343593120574951, cross_entropy: 2.343593120574951 +[2025-04-29 06:04:16,544][BaseTrainer][INFO] - [Epoch 10/10, Iter 3364/3560] 1.5024266242980957, cross_entropy: 1.5024266242980957 +[2025-04-29 06:04:17,402][BaseTrainer][INFO] - [Epoch 10/10, Iter 3365/3560] 2.38405179977417, cross_entropy: 2.38405179977417 +[2025-04-29 06:04:21,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3366/3560] 2.8205223083496094, cross_entropy: 2.8205223083496094 +[2025-04-29 06:04:21,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3367/3560] 1.3267822265625, cross_entropy: 1.3267822265625 +[2025-04-29 06:04:26,944][BaseTrainer][INFO] - [Epoch 10/10, Iter 3368/3560] 2.2695934772491455, cross_entropy: 2.2695934772491455 +[2025-04-29 06:04:27,831][BaseTrainer][INFO] - [Epoch 10/10, Iter 3369/3560] 1.4479320049285889, cross_entropy: 1.4479320049285889 +[2025-04-29 06:04:30,539][BaseTrainer][INFO] - [Epoch 10/10, Iter 3370/3560] 2.7827200889587402, cross_entropy: 2.7827200889587402 +[2025-04-29 06:04:31,416][BaseTrainer][INFO] - [Epoch 10/10, Iter 3371/3560] 2.4304590225219727, cross_entropy: 2.4304590225219727 +[2025-04-29 06:04:33,441][BaseTrainer][INFO] - [Epoch 10/10, Iter 3372/3560] 0.9080036282539368, cross_entropy: 0.9080036282539368 +[2025-04-29 06:04:34,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3373/3560] 1.2355215549468994, cross_entropy: 1.2355215549468994 +[2025-04-29 06:04:37,014][BaseTrainer][INFO] - [Epoch 10/10, Iter 3374/3560] 1.0875519514083862, cross_entropy: 1.0875519514083862 +[2025-04-29 06:04:37,891][BaseTrainer][INFO] - [Epoch 10/10, Iter 3375/3560] 1.8539776802062988, cross_entropy: 1.8539776802062988 +[2025-04-29 06:04:40,661][BaseTrainer][INFO] - [Epoch 10/10, Iter 3376/3560] 2.982483386993408, cross_entropy: 2.982483386993408 +[2025-04-29 06:04:41,554][BaseTrainer][INFO] - [Epoch 10/10, Iter 3377/3560] 2.6397600173950195, cross_entropy: 2.6397600173950195 +[2025-04-29 06:04:44,232][BaseTrainer][INFO] - [Epoch 10/10, Iter 3378/3560] 1.1081702709197998, cross_entropy: 1.1081702709197998 +[2025-04-29 06:04:45,094][BaseTrainer][INFO] - [Epoch 10/10, Iter 3379/3560] 1.5435625314712524, cross_entropy: 1.5435625314712524 +[2025-04-29 06:04:48,280][BaseTrainer][INFO] - [Epoch 10/10, Iter 3380/3560] 1.6931177377700806, cross_entropy: 1.6931177377700806 +[2025-04-29 06:04:49,171][BaseTrainer][INFO] - [Epoch 10/10, Iter 3381/3560] 3.051614999771118, cross_entropy: 3.051614999771118 +[2025-04-29 06:04:52,514][BaseTrainer][INFO] - [Epoch 10/10, Iter 3382/3560] 0.9627302289009094, cross_entropy: 0.9627302289009094 +[2025-04-29 06:04:53,402][BaseTrainer][INFO] - [Epoch 10/10, Iter 3383/3560] 1.2588322162628174, cross_entropy: 1.2588322162628174 +[2025-04-29 06:04:56,091][BaseTrainer][INFO] - [Epoch 10/10, Iter 3384/3560] 3.0087361335754395, cross_entropy: 3.0087361335754395 +[2025-04-29 06:04:56,974][BaseTrainer][INFO] - [Epoch 10/10, Iter 3385/3560] 2.9685311317443848, cross_entropy: 2.9685311317443848 +[2025-04-29 06:04:59,803][BaseTrainer][INFO] - [Epoch 10/10, Iter 3386/3560] 3.377948760986328, cross_entropy: 3.377948760986328 +[2025-04-29 06:05:00,689][BaseTrainer][INFO] - [Epoch 10/10, Iter 3387/3560] 1.191341757774353, cross_entropy: 1.191341757774353 +[2025-04-29 06:05:03,462][BaseTrainer][INFO] - [Epoch 10/10, Iter 3388/3560] 2.844529151916504, cross_entropy: 2.844529151916504 +[2025-04-29 06:05:04,334][BaseTrainer][INFO] - [Epoch 10/10, Iter 3389/3560] 1.3003880977630615, cross_entropy: 1.3003880977630615 +[2025-04-29 06:05:07,502][BaseTrainer][INFO] - [Epoch 10/10, Iter 3390/3560] 1.8032469749450684, cross_entropy: 1.8032469749450684 +[2025-04-29 06:05:08,383][BaseTrainer][INFO] - [Epoch 10/10, Iter 3391/3560] 2.049795627593994, cross_entropy: 2.049795627593994 +[2025-04-29 06:05:11,211][BaseTrainer][INFO] - [Epoch 10/10, Iter 3392/3560] 3.204684019088745, cross_entropy: 3.204684019088745 +[2025-04-29 06:05:12,079][BaseTrainer][INFO] - [Epoch 10/10, Iter 3393/3560] 1.2365691661834717, cross_entropy: 1.2365691661834717 +[2025-04-29 06:05:14,740][BaseTrainer][INFO] - [Epoch 10/10, Iter 3394/3560] 1.466300368309021, cross_entropy: 1.466300368309021 +[2025-04-29 06:05:15,604][BaseTrainer][INFO] - [Epoch 10/10, Iter 3395/3560] 1.0855047702789307, cross_entropy: 1.0855047702789307 +[2025-04-29 06:05:18,655][BaseTrainer][INFO] - [Epoch 10/10, Iter 3396/3560] 1.2117700576782227, cross_entropy: 1.2117700576782227 +[2025-04-29 06:05:19,517][BaseTrainer][INFO] - [Epoch 10/10, Iter 3397/3560] 2.8564400672912598, cross_entropy: 2.8564400672912598 +[2025-04-29 06:05:21,980][BaseTrainer][INFO] - [Epoch 10/10, Iter 3398/3560] 2.3589389324188232, cross_entropy: 2.3589389324188232 +[2025-04-29 06:05:22,846][BaseTrainer][INFO] - [Epoch 10/10, Iter 3399/3560] 2.8652987480163574, cross_entropy: 2.8652987480163574 +[2025-04-29 06:05:25,651][BaseTrainer][INFO] - [Epoch 10/10, Iter 3400/3560] 2.7954001426696777, cross_entropy: 2.7954001426696777 +[2025-04-29 06:05:26,511][BaseTrainer][INFO] - [Epoch 10/10, Iter 3401/3560] 1.8873717784881592, cross_entropy: 1.8873717784881592 +[2025-04-29 06:05:30,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3402/3560] 1.4846415519714355, cross_entropy: 1.4846415519714355 +[2025-04-29 06:05:30,902][BaseTrainer][INFO] - [Epoch 10/10, Iter 3403/3560] 2.585676670074463, cross_entropy: 2.585676670074463 +[2025-04-29 06:05:33,303][BaseTrainer][INFO] - [Epoch 10/10, Iter 3404/3560] 2.59829044342041, cross_entropy: 2.59829044342041 +[2025-04-29 06:05:34,174][BaseTrainer][INFO] - [Epoch 10/10, Iter 3405/3560] 1.280861258506775, cross_entropy: 1.280861258506775 +[2025-04-29 06:05:37,171][BaseTrainer][INFO] - [Epoch 10/10, Iter 3406/3560] 2.1961851119995117, cross_entropy: 2.1961851119995117 +[2025-04-29 06:05:38,057][BaseTrainer][INFO] - [Epoch 10/10, Iter 3407/3560] 1.1833757162094116, cross_entropy: 1.1833757162094116 +[2025-04-29 06:05:40,539][BaseTrainer][INFO] - [Epoch 10/10, Iter 3408/3560] 2.0072133541107178, cross_entropy: 2.0072133541107178 +[2025-04-29 06:05:41,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3409/3560] 2.908599853515625, cross_entropy: 2.908599853515625 +[2025-04-29 06:05:43,631][BaseTrainer][INFO] - [Epoch 10/10, Iter 3410/3560] 1.3097748756408691, cross_entropy: 1.3097748756408691 +[2025-04-29 06:05:44,522][BaseTrainer][INFO] - [Epoch 10/10, Iter 3411/3560] 1.3129656314849854, cross_entropy: 1.3129656314849854 +[2025-04-29 06:05:47,093][BaseTrainer][INFO] - [Epoch 10/10, Iter 3412/3560] 1.223707914352417, cross_entropy: 1.223707914352417 +[2025-04-29 06:05:47,953][BaseTrainer][INFO] - [Epoch 10/10, Iter 3413/3560] 2.256556749343872, cross_entropy: 2.256556749343872 +[2025-04-29 06:05:50,451][BaseTrainer][INFO] - [Epoch 10/10, Iter 3414/3560] 1.5827463865280151, cross_entropy: 1.5827463865280151 +[2025-04-29 06:05:51,311][BaseTrainer][INFO] - [Epoch 10/10, Iter 3415/3560] 3.0587666034698486, cross_entropy: 3.0587666034698486 +[2025-04-29 06:05:54,164][BaseTrainer][INFO] - [Epoch 10/10, Iter 3416/3560] 2.916097402572632, cross_entropy: 2.916097402572632 +[2025-04-29 06:05:55,042][BaseTrainer][INFO] - [Epoch 10/10, Iter 3417/3560] 1.2931475639343262, cross_entropy: 1.2931475639343262 +[2025-04-29 06:05:58,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3418/3560] 2.455874443054199, cross_entropy: 2.455874443054199 +[2025-04-29 06:05:59,241][BaseTrainer][INFO] - [Epoch 10/10, Iter 3419/3560] 0.7681252956390381, cross_entropy: 0.7681252956390381 +[2025-04-29 06:06:02,178][BaseTrainer][INFO] - [Epoch 10/10, Iter 3420/3560] 2.429868698120117, cross_entropy: 2.429868698120117 +[2025-04-29 06:06:03,039][BaseTrainer][INFO] - [Epoch 10/10, Iter 3421/3560] 1.797047734260559, cross_entropy: 1.797047734260559 +[2025-04-29 06:06:06,530][BaseTrainer][INFO] - [Epoch 10/10, Iter 3422/3560] 0.9730772972106934, cross_entropy: 0.9730772972106934 +[2025-04-29 06:06:07,390][BaseTrainer][INFO] - [Epoch 10/10, Iter 3423/3560] 2.8140530586242676, cross_entropy: 2.8140530586242676 +[2025-04-29 06:06:09,452][BaseTrainer][INFO] - [Epoch 10/10, Iter 3424/3560] 1.8907010555267334, cross_entropy: 1.8907010555267334 +[2025-04-29 06:06:10,338][BaseTrainer][INFO] - [Epoch 10/10, Iter 3425/3560] 2.0507893562316895, cross_entropy: 2.0507893562316895 +[2025-04-29 06:06:13,417][BaseTrainer][INFO] - [Epoch 10/10, Iter 3426/3560] 1.9104957580566406, cross_entropy: 1.9104957580566406 +[2025-04-29 06:06:14,313][BaseTrainer][INFO] - [Epoch 10/10, Iter 3427/3560] 1.1183420419692993, cross_entropy: 1.1183420419692993 +[2025-04-29 06:06:17,116][BaseTrainer][INFO] - [Epoch 10/10, Iter 3428/3560] 1.6306774616241455, cross_entropy: 1.6306774616241455 +[2025-04-29 06:06:18,003][BaseTrainer][INFO] - [Epoch 10/10, Iter 3429/3560] 1.3050670623779297, cross_entropy: 1.3050670623779297 +[2025-04-29 06:06:20,551][BaseTrainer][INFO] - [Epoch 10/10, Iter 3430/3560] 2.923365592956543, cross_entropy: 2.923365592956543 +[2025-04-29 06:06:21,437][BaseTrainer][INFO] - [Epoch 10/10, Iter 3431/3560] 3.044339656829834, cross_entropy: 3.044339656829834 +[2025-04-29 06:06:24,464][BaseTrainer][INFO] - [Epoch 10/10, Iter 3432/3560] 1.8067508935928345, cross_entropy: 1.8067508935928345 +[2025-04-29 06:06:25,351][BaseTrainer][INFO] - [Epoch 10/10, Iter 3433/3560] 2.6507487297058105, cross_entropy: 2.6507487297058105 +[2025-04-29 06:06:27,943][BaseTrainer][INFO] - [Epoch 10/10, Iter 3434/3560] 2.519754409790039, cross_entropy: 2.519754409790039 +[2025-04-29 06:06:28,804][BaseTrainer][INFO] - [Epoch 10/10, Iter 3435/3560] 1.1123461723327637, cross_entropy: 1.1123461723327637 +[2025-04-29 06:06:32,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3436/3560] 2.870840072631836, cross_entropy: 2.870840072631836 +[2025-04-29 06:06:33,393][BaseTrainer][INFO] - [Epoch 10/10, Iter 3437/3560] 1.9358270168304443, cross_entropy: 1.9358270168304443 +[2025-04-29 06:06:36,459][BaseTrainer][INFO] - [Epoch 10/10, Iter 3438/3560] 3.457939624786377, cross_entropy: 3.457939624786377 +[2025-04-29 06:06:37,353][BaseTrainer][INFO] - [Epoch 10/10, Iter 3439/3560] 1.9134553670883179, cross_entropy: 1.9134553670883179 +[2025-04-29 06:06:39,438][BaseTrainer][INFO] - [Epoch 10/10, Iter 3440/3560] 1.8275740146636963, cross_entropy: 1.8275740146636963 +[2025-04-29 06:06:40,298][BaseTrainer][INFO] - [Epoch 10/10, Iter 3441/3560] 1.11883544921875, cross_entropy: 1.11883544921875 +[2025-04-29 06:06:43,029][BaseTrainer][INFO] - [Epoch 10/10, Iter 3442/3560] 1.6337124109268188, cross_entropy: 1.6337124109268188 +[2025-04-29 06:06:43,888][BaseTrainer][INFO] - [Epoch 10/10, Iter 3443/3560] 1.9712859392166138, cross_entropy: 1.9712859392166138 +[2025-04-29 06:06:46,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3444/3560] 0.9001617431640625, cross_entropy: 0.9001617431640625 +[2025-04-29 06:06:47,726][BaseTrainer][INFO] - [Epoch 10/10, Iter 3445/3560] 2.5650644302368164, cross_entropy: 2.5650644302368164 +[2025-04-29 06:06:51,078][BaseTrainer][INFO] - [Epoch 10/10, Iter 3446/3560] 2.9856173992156982, cross_entropy: 2.9856173992156982 +[2025-04-29 06:06:51,938][BaseTrainer][INFO] - [Epoch 10/10, Iter 3447/3560] 1.7835509777069092, cross_entropy: 1.7835509777069092 +[2025-04-29 06:06:55,036][BaseTrainer][INFO] - [Epoch 10/10, Iter 3448/3560] 1.0096826553344727, cross_entropy: 1.0096826553344727 +[2025-04-29 06:06:55,896][BaseTrainer][INFO] - [Epoch 10/10, Iter 3449/3560] 2.769944667816162, cross_entropy: 2.769944667816162 +[2025-04-29 06:06:58,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3450/3560] 1.523071527481079, cross_entropy: 1.523071527481079 +[2025-04-29 06:06:59,523][BaseTrainer][INFO] - [Epoch 10/10, Iter 3451/3560] 3.13838529586792, cross_entropy: 3.13838529586792 +[2025-04-29 06:07:02,587][BaseTrainer][INFO] - [Epoch 10/10, Iter 3452/3560] 2.4170494079589844, cross_entropy: 2.4170494079589844 +[2025-04-29 06:07:03,474][BaseTrainer][INFO] - [Epoch 10/10, Iter 3453/3560] 1.5774288177490234, cross_entropy: 1.5774288177490234 +[2025-04-29 06:07:06,259][BaseTrainer][INFO] - [Epoch 10/10, Iter 3454/3560] 1.1810356378555298, cross_entropy: 1.1810356378555298 +[2025-04-29 06:07:07,121][BaseTrainer][INFO] - [Epoch 10/10, Iter 3455/3560] 1.9605884552001953, cross_entropy: 1.9605884552001953 +[2025-04-29 06:07:09,821][BaseTrainer][INFO] - [Epoch 10/10, Iter 3456/3560] 1.686856746673584, cross_entropy: 1.686856746673584 +[2025-04-29 06:07:10,712][BaseTrainer][INFO] - [Epoch 10/10, Iter 3457/3560] 1.8653258085250854, cross_entropy: 1.8653258085250854 +[2025-04-29 06:07:13,269][BaseTrainer][INFO] - [Epoch 10/10, Iter 3458/3560] 2.7042746543884277, cross_entropy: 2.7042746543884277 +[2025-04-29 06:07:14,137][BaseTrainer][INFO] - [Epoch 10/10, Iter 3459/3560] 1.034604787826538, cross_entropy: 1.034604787826538 +[2025-04-29 06:07:17,034][BaseTrainer][INFO] - [Epoch 10/10, Iter 3460/3560] 2.239826202392578, cross_entropy: 2.239826202392578 +[2025-04-29 06:07:17,923][BaseTrainer][INFO] - [Epoch 10/10, Iter 3461/3560] 1.0423060655593872, cross_entropy: 1.0423060655593872 +[2025-04-29 06:07:20,839][BaseTrainer][INFO] - [Epoch 10/10, Iter 3462/3560] 2.0296502113342285, cross_entropy: 2.0296502113342285 +[2025-04-29 06:07:21,705][BaseTrainer][INFO] - [Epoch 10/10, Iter 3463/3560] 1.3589537143707275, cross_entropy: 1.3589537143707275 +[2025-04-29 06:07:24,556][BaseTrainer][INFO] - [Epoch 10/10, Iter 3464/3560] 1.1878371238708496, cross_entropy: 1.1878371238708496 +[2025-04-29 06:07:25,439][BaseTrainer][INFO] - [Epoch 10/10, Iter 3465/3560] 1.0944304466247559, cross_entropy: 1.0944304466247559 +[2025-04-29 06:07:28,792][BaseTrainer][INFO] - [Epoch 10/10, Iter 3466/3560] 2.2595221996307373, cross_entropy: 2.2595221996307373 +[2025-04-29 06:07:29,654][BaseTrainer][INFO] - [Epoch 10/10, Iter 3467/3560] 2.9953112602233887, cross_entropy: 2.9953112602233887 +[2025-04-29 06:07:32,691][BaseTrainer][INFO] - [Epoch 10/10, Iter 3468/3560] 2.0361719131469727, cross_entropy: 2.0361719131469727 +[2025-04-29 06:07:33,555][BaseTrainer][INFO] - [Epoch 10/10, Iter 3469/3560] 2.2195072174072266, cross_entropy: 2.2195072174072266 +[2025-04-29 06:07:37,275][BaseTrainer][INFO] - [Epoch 10/10, Iter 3470/3560] 2.4858927726745605, cross_entropy: 2.4858927726745605 +[2025-04-29 06:07:38,138][BaseTrainer][INFO] - [Epoch 10/10, Iter 3471/3560] 1.5705630779266357, cross_entropy: 1.5705630779266357 +[2025-04-29 06:07:40,856][BaseTrainer][INFO] - [Epoch 10/10, Iter 3472/3560] 1.8154405355453491, cross_entropy: 1.8154405355453491 +[2025-04-29 06:07:41,747][BaseTrainer][INFO] - [Epoch 10/10, Iter 3473/3560] 1.9149909019470215, cross_entropy: 1.9149909019470215 +[2025-04-29 06:07:45,242][BaseTrainer][INFO] - [Epoch 10/10, Iter 3474/3560] 2.65456485748291, cross_entropy: 2.65456485748291 +[2025-04-29 06:07:46,131][BaseTrainer][INFO] - [Epoch 10/10, Iter 3475/3560] 2.8184051513671875, cross_entropy: 2.8184051513671875 +[2025-04-29 06:07:48,620][BaseTrainer][INFO] - [Epoch 10/10, Iter 3476/3560] 2.334832191467285, cross_entropy: 2.334832191467285 +[2025-04-29 06:07:49,506][BaseTrainer][INFO] - [Epoch 10/10, Iter 3477/3560] 2.1689252853393555, cross_entropy: 2.1689252853393555 +[2025-04-29 06:07:52,105][BaseTrainer][INFO] - [Epoch 10/10, Iter 3478/3560] 3.1056571006774902, cross_entropy: 3.1056571006774902 +[2025-04-29 06:07:52,994][BaseTrainer][INFO] - [Epoch 10/10, Iter 3479/3560] 2.96056866645813, cross_entropy: 2.96056866645813 +[2025-04-29 06:07:55,368][BaseTrainer][INFO] - [Epoch 10/10, Iter 3480/3560] 2.7596893310546875, cross_entropy: 2.7596893310546875 +[2025-04-29 06:07:56,262][BaseTrainer][INFO] - [Epoch 10/10, Iter 3481/3560] 2.4761691093444824, cross_entropy: 2.4761691093444824 +[2025-04-29 06:07:58,653][BaseTrainer][INFO] - [Epoch 10/10, Iter 3482/3560] 1.3016784191131592, cross_entropy: 1.3016784191131592 +[2025-04-29 06:07:59,544][BaseTrainer][INFO] - [Epoch 10/10, Iter 3483/3560] 2.2266416549682617, cross_entropy: 2.2266416549682617 +[2025-04-29 06:08:01,802][BaseTrainer][INFO] - [Epoch 10/10, Iter 3484/3560] 2.5311567783355713, cross_entropy: 2.5311567783355713 +[2025-04-29 06:08:02,664][BaseTrainer][INFO] - [Epoch 10/10, Iter 3485/3560] 2.934605121612549, cross_entropy: 2.934605121612549 +[2025-04-29 06:08:05,708][BaseTrainer][INFO] - [Epoch 10/10, Iter 3486/3560] 2.891770839691162, cross_entropy: 2.891770839691162 +[2025-04-29 06:08:06,596][BaseTrainer][INFO] - [Epoch 10/10, Iter 3487/3560] 2.1934151649475098, cross_entropy: 2.1934151649475098 +[2025-04-29 06:08:10,001][BaseTrainer][INFO] - [Epoch 10/10, Iter 3488/3560] 2.6273813247680664, cross_entropy: 2.6273813247680664 +[2025-04-29 06:08:10,884][BaseTrainer][INFO] - [Epoch 10/10, Iter 3489/3560] 0.9465482234954834, cross_entropy: 0.9465482234954834 +[2025-04-29 06:08:13,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3490/3560] 1.9189234972000122, cross_entropy: 1.9189234972000122 +[2025-04-29 06:08:14,243][BaseTrainer][INFO] - [Epoch 10/10, Iter 3491/3560] 2.9269356727600098, cross_entropy: 2.9269356727600098 +[2025-04-29 06:08:16,875][BaseTrainer][INFO] - [Epoch 10/10, Iter 3492/3560] 2.878607749938965, cross_entropy: 2.878607749938965 +[2025-04-29 06:08:17,768][BaseTrainer][INFO] - [Epoch 10/10, Iter 3493/3560] 2.711789608001709, cross_entropy: 2.711789608001709 +[2025-04-29 06:08:20,310][BaseTrainer][INFO] - [Epoch 10/10, Iter 3494/3560] 1.3860023021697998, cross_entropy: 1.3860023021697998 +[2025-04-29 06:08:21,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3495/3560] 3.178771734237671, cross_entropy: 3.178771734237671 +[2025-04-29 06:08:23,673][BaseTrainer][INFO] - [Epoch 10/10, Iter 3496/3560] 1.0576860904693604, cross_entropy: 1.0576860904693604 +[2025-04-29 06:08:24,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3497/3560] 2.146782875061035, cross_entropy: 2.146782875061035 +[2025-04-29 06:08:27,489][BaseTrainer][INFO] - [Epoch 10/10, Iter 3498/3560] 1.241683840751648, cross_entropy: 1.241683840751648 +[2025-04-29 06:08:28,350][BaseTrainer][INFO] - [Epoch 10/10, Iter 3499/3560] 2.3413100242614746, cross_entropy: 2.3413100242614746 +[2025-04-29 06:08:31,342][BaseTrainer][INFO] - [Epoch 10/10, Iter 3500/3560] 1.247687816619873, cross_entropy: 1.247687816619873 +[2025-04-29 06:08:32,235][BaseTrainer][INFO] - [Epoch 10/10, Iter 3501/3560] 2.257674217224121, cross_entropy: 2.257674217224121 +[2025-04-29 06:08:34,578][BaseTrainer][INFO] - [Epoch 10/10, Iter 3502/3560] 1.2873672246932983, cross_entropy: 1.2873672246932983 +[2025-04-29 06:08:35,444][BaseTrainer][INFO] - [Epoch 10/10, Iter 3503/3560] 1.6403520107269287, cross_entropy: 1.6403520107269287 +[2025-04-29 06:08:38,881][BaseTrainer][INFO] - [Epoch 10/10, Iter 3504/3560] 2.0292611122131348, cross_entropy: 2.0292611122131348 +[2025-04-29 06:08:39,774][BaseTrainer][INFO] - [Epoch 10/10, Iter 3505/3560] 3.0599143505096436, cross_entropy: 3.0599143505096436 +[2025-04-29 06:08:42,495][BaseTrainer][INFO] - [Epoch 10/10, Iter 3506/3560] 2.9429054260253906, cross_entropy: 2.9429054260253906 +[2025-04-29 06:08:43,354][BaseTrainer][INFO] - [Epoch 10/10, Iter 3507/3560] 1.5113892555236816, cross_entropy: 1.5113892555236816 +[2025-04-29 06:08:46,281][BaseTrainer][INFO] - [Epoch 10/10, Iter 3508/3560] 2.0600810050964355, cross_entropy: 2.0600810050964355 +[2025-04-29 06:08:47,145][BaseTrainer][INFO] - [Epoch 10/10, Iter 3509/3560] 1.1374274492263794, cross_entropy: 1.1374274492263794 +[2025-04-29 06:08:49,783][BaseTrainer][INFO] - [Epoch 10/10, Iter 3510/3560] 1.626983642578125, cross_entropy: 1.626983642578125 +[2025-04-29 06:08:50,645][BaseTrainer][INFO] - [Epoch 10/10, Iter 3511/3560] 3.0145111083984375, cross_entropy: 3.0145111083984375 +[2025-04-29 06:08:53,547][BaseTrainer][INFO] - [Epoch 10/10, Iter 3512/3560] 1.4537897109985352, cross_entropy: 1.4537897109985352 +[2025-04-29 06:08:54,440][BaseTrainer][INFO] - [Epoch 10/10, Iter 3513/3560] 2.326782703399658, cross_entropy: 2.326782703399658 +[2025-04-29 06:08:57,203][BaseTrainer][INFO] - [Epoch 10/10, Iter 3514/3560] 2.409397602081299, cross_entropy: 2.409397602081299 +[2025-04-29 06:08:58,091][BaseTrainer][INFO] - [Epoch 10/10, Iter 3515/3560] 3.2040276527404785, cross_entropy: 3.2040276527404785 +[2025-04-29 06:09:01,081][BaseTrainer][INFO] - [Epoch 10/10, Iter 3516/3560] 3.2426435947418213, cross_entropy: 3.2426435947418213 +[2025-04-29 06:09:01,970][BaseTrainer][INFO] - [Epoch 10/10, Iter 3517/3560] 1.8965860605239868, cross_entropy: 1.8965860605239868 +[2025-04-29 06:09:04,993][BaseTrainer][INFO] - [Epoch 10/10, Iter 3518/3560] 1.3487896919250488, cross_entropy: 1.3487896919250488 +[2025-04-29 06:09:05,889][BaseTrainer][INFO] - [Epoch 10/10, Iter 3519/3560] 1.4201891422271729, cross_entropy: 1.4201891422271729 +[2025-04-29 06:09:08,587][BaseTrainer][INFO] - [Epoch 10/10, Iter 3520/3560] 2.947963237762451, cross_entropy: 2.947963237762451 +[2025-04-29 06:09:09,446][BaseTrainer][INFO] - [Epoch 10/10, Iter 3521/3560] 2.399472713470459, cross_entropy: 2.399472713470459 +[2025-04-29 06:09:12,120][BaseTrainer][INFO] - [Epoch 10/10, Iter 3522/3560] 1.3148047924041748, cross_entropy: 1.3148047924041748 +[2025-04-29 06:09:13,010][BaseTrainer][INFO] - [Epoch 10/10, Iter 3523/3560] 0.863667905330658, cross_entropy: 0.863667905330658 +[2025-04-29 06:09:15,500][BaseTrainer][INFO] - [Epoch 10/10, Iter 3524/3560] 2.319753885269165, cross_entropy: 2.319753885269165 +[2025-04-29 06:09:16,362][BaseTrainer][INFO] - [Epoch 10/10, Iter 3525/3560] 1.5708739757537842, cross_entropy: 1.5708739757537842 +[2025-04-29 06:09:18,811][BaseTrainer][INFO] - [Epoch 10/10, Iter 3526/3560] 1.332846760749817, cross_entropy: 1.332846760749817 +[2025-04-29 06:09:19,996][BaseTrainer][INFO] - [Epoch 10/10, Iter 3527/3560] 1.4047884941101074, cross_entropy: 1.4047884941101074 +[2025-04-29 06:09:22,080][BaseTrainer][INFO] - [Epoch 10/10, Iter 3528/3560] 1.369750738143921, cross_entropy: 1.369750738143921 +[2025-04-29 06:09:23,503][BaseTrainer][INFO] - [Epoch 10/10, Iter 3529/3560] 1.1143192052841187, cross_entropy: 1.1143192052841187 +[2025-04-29 06:09:25,910][BaseTrainer][INFO] - [Epoch 10/10, Iter 3530/3560] 1.2692800760269165, cross_entropy: 1.2692800760269165 +[2025-04-29 06:09:26,810][BaseTrainer][INFO] - [Epoch 10/10, Iter 3531/3560] 2.4856619834899902, cross_entropy: 2.4856619834899902 +[2025-04-29 06:09:29,994][BaseTrainer][INFO] - [Epoch 10/10, Iter 3532/3560] 1.3584928512573242, cross_entropy: 1.3584928512573242 +[2025-04-29 06:09:30,879][BaseTrainer][INFO] - [Epoch 10/10, Iter 3533/3560] 0.9577933549880981, cross_entropy: 0.9577933549880981 +[2025-04-29 06:09:33,834][BaseTrainer][INFO] - [Epoch 10/10, Iter 3534/3560] 1.3748444318771362, cross_entropy: 1.3748444318771362 +[2025-04-29 06:09:34,697][BaseTrainer][INFO] - [Epoch 10/10, Iter 3535/3560] 2.518332004547119, cross_entropy: 2.518332004547119 +[2025-04-29 06:09:38,543][BaseTrainer][INFO] - [Epoch 10/10, Iter 3536/3560] 1.903557300567627, cross_entropy: 1.903557300567627 +[2025-04-29 06:09:39,405][BaseTrainer][INFO] - [Epoch 10/10, Iter 3537/3560] 1.430262804031372, cross_entropy: 1.430262804031372 +[2025-04-29 06:09:42,411][BaseTrainer][INFO] - [Epoch 10/10, Iter 3538/3560] 2.3999545574188232, cross_entropy: 2.3999545574188232 +[2025-04-29 06:09:43,287][BaseTrainer][INFO] - [Epoch 10/10, Iter 3539/3560] 1.7470777034759521, cross_entropy: 1.7470777034759521 +[2025-04-29 06:09:46,499][BaseTrainer][INFO] - [Epoch 10/10, Iter 3540/3560] 1.3506921529769897, cross_entropy: 1.3506921529769897 +[2025-04-29 06:09:47,392][BaseTrainer][INFO] - [Epoch 10/10, Iter 3541/3560] 1.3761284351348877, cross_entropy: 1.3761284351348877 +[2025-04-29 06:09:50,566][BaseTrainer][INFO] - [Epoch 10/10, Iter 3542/3560] 0.9975250959396362, cross_entropy: 0.9975250959396362 +[2025-04-29 06:09:51,455][BaseTrainer][INFO] - [Epoch 10/10, Iter 3543/3560] 1.5073972940444946, cross_entropy: 1.5073972940444946 +[2025-04-29 06:09:54,122][BaseTrainer][INFO] - [Epoch 10/10, Iter 3544/3560] 1.8913496732711792, cross_entropy: 1.8913496732711792 +[2025-04-29 06:09:54,985][BaseTrainer][INFO] - [Epoch 10/10, Iter 3545/3560] 2.3556437492370605, cross_entropy: 2.3556437492370605 +[2025-04-29 06:09:57,494][BaseTrainer][INFO] - [Epoch 10/10, Iter 3546/3560] 1.754473328590393, cross_entropy: 1.754473328590393 +[2025-04-29 06:09:58,382][BaseTrainer][INFO] - [Epoch 10/10, Iter 3547/3560] 1.500248670578003, cross_entropy: 1.500248670578003 +[2025-04-29 06:10:01,035][BaseTrainer][INFO] - [Epoch 10/10, Iter 3548/3560] 2.935145139694214, cross_entropy: 2.935145139694214 +[2025-04-29 06:10:01,929][BaseTrainer][INFO] - [Epoch 10/10, Iter 3549/3560] 0.9542328715324402, cross_entropy: 0.9542328715324402 +[2025-04-29 06:10:04,619][BaseTrainer][INFO] - [Epoch 10/10, Iter 3550/3560] 2.203373432159424, cross_entropy: 2.203373432159424 +[2025-04-29 06:10:05,545][BaseTrainer][INFO] - [Epoch 10/10, Iter 3551/3560] 1.0321382284164429, cross_entropy: 1.0321382284164429 +[2025-04-29 06:10:08,538][BaseTrainer][INFO] - [Epoch 10/10, Iter 3552/3560] 1.409450650215149, cross_entropy: 1.409450650215149 +[2025-04-29 06:10:09,485][BaseTrainer][INFO] - [Epoch 10/10, Iter 3553/3560] 1.2449636459350586, cross_entropy: 1.2449636459350586 +[2025-04-29 06:10:11,848][BaseTrainer][INFO] - [Epoch 10/10, Iter 3554/3560] 3.1907424926757812, cross_entropy: 3.1907424926757812 +[2025-04-29 06:10:12,767][BaseTrainer][INFO] - [Epoch 10/10, Iter 3555/3560] 1.0968669652938843, cross_entropy: 1.0968669652938843 +[2025-04-29 06:10:15,330][BaseTrainer][INFO] - [Epoch 10/10, Iter 3556/3560] 1.3817977905273438, cross_entropy: 1.3817977905273438 +[2025-04-29 06:10:16,299][BaseTrainer][INFO] - [Epoch 10/10, Iter 3557/3560] 2.899799346923828, cross_entropy: 2.899799346923828 +[2025-04-29 06:10:19,532][BaseTrainer][INFO] - [Epoch 10/10, Iter 3558/3560] 1.2647719383239746, cross_entropy: 1.2647719383239746 +[2025-04-29 06:10:20,400][BaseTrainer][INFO] - [Epoch 10/10, Iter 3559/3560] 1.8884209394454956, cross_entropy: 1.8884209394454956 +[2025-04-29 06:10:22,340][BaseTrainer][INFO] - [Epoch 10/10, Iter 3560/3560] 3.2871932983398438, cross_entropy: 3.2871932983398438 +[2025-04-29 06:13:13,560][BaseTrainer][INFO] - [Epoch 10/10] (train) 2.037014961242676, cross_entropy: 2.037014961242676 +[2025-04-29 06:13:13,561][BaseTrainer][INFO] - [Epoch 10/10] (validation) 1.2304948568344116, cross_entropy: 1.2304948568344116 +[2025-04-29 06:13:14,430][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/best_epoch.pth. +[2025-04-29 06:13:14,920][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/epoch10.pth. +[2025-04-29 06:13:15,721][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. +[2025-04-29 06:13:16,507][BaseTrainer][INFO] - Save model: ./exp/20250429-035024/model/last.pth. diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/best_epoch.pth b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/best_epoch.pth new file mode 100644 index 0000000000000000000000000000000000000000..e05d46c736df15581a005959dcd65d7e09a7ab49 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/best_epoch.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4af12d8af13ccaefaf7d2f20c124d2eeb1fb2669e689b748d076ba1dafb92266 +size 332603774 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/last.pth b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/last.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd10687dd3a75c747b386981e80aa58293d6d965 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/exp/20250429-035024/model/last.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80952d059840f7e7cf2cbdc3026be5362329f76eb5fbce7e1ae40d17d27c950 +size 332568806 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250428-164206/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.10 b/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250428-164206/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.10 new file mode 100644 index 0000000000000000000000000000000000000000..27c476e4a3c23654162c10cfc26f046c052a7366 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250428-164206/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92af6d07cb6dc6a61f1a68cdc0487ff4c00bfc72dac20a439a9130ff8062f589 +size 472294 diff --git a/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250429-035024/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.11 b/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250429-035024/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.11 new file mode 100644 index 0000000000000000000000000000000000000000..376817254a1238305619de762294e1d16b1b10c6 --- /dev/null +++ b/recipes/BirdCLEF2025/SwinTransformerTiny/tensorboard/20250429-035024/events.out.tfevents.1746371442.MacBook-Pro-2.local.7605.11 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81972eb62acb958f94f2c6a4da3f4aafd7c05dd9e05ac0bb2646566db25c0bbe +size 471582