Ignore wandb logs

wandb/debug-internal.log

@@ -1,7 +0,0 @@
-{"time":"2025-02-17T21:46:18.764731866Z","level":"INFO","msg":"stream: starting","core version":"0.19.6","symlink path":"/home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug-core.log"}
-{"time":"2025-02-17T21:46:18.87215251Z","level":"INFO","msg":"created new stream","id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.8722139Z","level":"INFO","msg":"stream: started","id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.872282469Z","level":"INFO","msg":"writer: Do: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.872363578Z","level":"INFO","msg":"handler: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.87291405Z","level":"INFO","msg":"sender: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:19.182639444Z","level":"INFO","msg":"Starting system monitor"}

wandb/debug.log

@@ -1,25 +0,0 @@
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Current SDK version is 0.19.6
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Configure stats pid to 168016
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from /home/tknika/.config/wandb/settings
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/settings
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from environment variables
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:setup_run_log_directory():637] Logging user logs to /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug.log
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:setup_run_log_directory():638] Logging internal logs to /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug-internal.log
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():756] calling init triggers
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():761] wandb.init called with sweep_config: {}
-config: {'_wandb': {}}
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():789] starting backend
-2025-02-17 21:46:18,752 INFO    MainThread:168016 [wandb_init.py:init():793] sending inform_init request
-2025-02-17 21:46:18,758 INFO    MainThread:168016 [backend.py:_multiprocessing_setup():97] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2025-02-17 21:46:18,759 INFO    MainThread:168016 [wandb_init.py:init():808] backend started and connected
-2025-02-17 21:46:18,761 INFO    MainThread:168016 [wandb_init.py:init():901] updated telemetry
-2025-02-17 21:46:18,768 INFO    MainThread:168016 [wandb_init.py:init():936] communicating run to backend with 90.0 second timeout
-2025-02-17 21:46:19,179 INFO    MainThread:168016 [wandb_init.py:init():994] starting run threads in backend
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_console_start():2385] atexit reg
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2235] redirect: wrap_raw
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2300] Wrapping output streams.
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2325] Redirects installed.
-2025-02-17 21:46:19,300 INFO    MainThread:168016 [wandb_init.py:init():1036] run started, returning control to user process
-2025-02-17 21:46:19,301 INFO    MainThread:168016 [wandb_run.py:_config_callback():1253] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 384, 'encoder_layers': 4, 'encoder_attention_heads': 6, 'decoder_layers': 4, 'decoder_attention_heads': 6, 'decoder_ffn_dim': 1536, 'encoder_ffn_dim': 1536, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 4, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-tiny', '_attn_implementation_autoset': True, 'transformers_version': '4.49.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3.75e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 10000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Feb17_21-45-10_tknika', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'whisper-tiny-eu-2025.02', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}
-2025-02-17 21:46:19,303 INFO    MainThread:168016 [wandb_config.py:__setitem__():154] config set model/num_parameters = 37760640 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x735fac35e9c0>>
-2025-02-17 21:46:19,303 INFO    MainThread:168016 [wandb_run.py:_config_callback():1253] config_cb model/num_parameters 37760640 None

wandb/run-20250217_214618-7bygcjmf/files/requirements.txt

@@ -1,122 +0,0 @@
-aiosignal==1.3.2
-Markdown==3.7
-more-itertools==10.6.0
-requests==2.32.3
-sentry-sdk==2.21.0
-torchaudio==2.6.0
-charset-normalizer==3.4.1
-docker-pycreds==0.4.0
-nvidia-cusolver-cu12==11.6.1.9
-PyYAML==6.0.2
-flatbuffers==25.2.10
-librosa==0.10.2.post1
-soxr==0.5.0.post1
-multiprocess==0.70.16
-setuptools==75.8.0
-nvidia-cufft-cu12==11.2.1.3
-joblib==1.4.2
-pytz==2025.1
-pip==24.0
-humanfriendly==10.0
-scikit-learn==1.6.1
-ctranslate2==4.5.0
-certifi==2025.1.31
-jiwer==3.1.0
-regex==2024.11.6
-annotated-types==0.7.0
-grpcio==1.70.0
-msgpack==1.1.0
-mpmath==1.3.0
-nvidia-cudnn-cu12==9.1.0.70
-soundfile==0.13.1
-dill==0.3.8
-nvidia-nvtx-cu12==12.4.127
-six==1.17.0
-nvidia-cuda-cupti-cu12==12.4.127
-pyarrow==19.0.0
-nvidia-nccl-cu12==2.21.5
-decorator==5.1.1
-llvmlite==0.44.0
-frozenlist==1.5.0
-pydantic==2.10.6
-networkx==3.4.2
-idna==3.10
-wandb==0.19.6
-aiohttp==3.11.12
-RapidFuzz==3.12.1
-pandas==2.2.3
-python-dateutil==2.9.0.post0
-numpy==2.1.3
-coloredlogs==15.0.1
-tokenizers==0.21.0
-nvidia-cusparselt-cu12==0.6.2
-typing_extensions==4.12.2
-urllib3==2.3.0
-setproctitle==1.3.4
-onnxruntime==1.20.1
-tzdata==2025.1
-datasets==3.3.1.dev0
-sympy==1.13.1
-faster-whisper==1.1.1
-pooch==1.8.2
-click==8.1.8
-pydantic_core==2.27.2
-MarkupSafe==3.0.2
-scipy==1.15.1
-accelerate==1.3.0
-tensorboard==2.19.0
-protobuf==5.29.3
-gitdb==4.0.12
-smmap==5.0.2
-absl-py==2.1.0
-tqdm==4.67.1
-yarl==1.18.3
-pycparser==2.22
-nvidia-cusparse-cu12==12.3.1.170
-attrs==25.1.0
-lazy_loader==0.4
-tensorboard-data-server==0.7.2
-threadpoolctl==3.5.0
-GitPython==3.1.44
-safetensors==0.5.2
-fsspec==2024.12.0
-nvidia-cuda-nvrtc-cu12==12.4.127
-filelock==3.17.0
-aiohappyeyeballs==2.4.6
-packaging==24.2
-audioread==3.0.1
-propcache==0.2.1
-transformers==4.49.0.dev0
-nvidia-cuda-runtime-cu12==12.4.127
-cffi==1.17.1
-evaluate==0.4.3
-Werkzeug==3.1.3
-huggingface-hub==0.28.1
-Jinja2==3.1.5
-torch==2.6.0
-psutil==7.0.0
-nvidia-curand-cu12==10.3.5.147
-xxhash==3.5.0
-platformdirs==4.3.6
-multidict==6.1.0
-nvidia-cublas-cu12==12.4.5.8
-av==14.1.0
-nvidia-nvjitlink-cu12==12.4.127
-triton==3.2.0
-numba==0.61.0
-importlib_metadata==8.0.0
-platformdirs==4.2.2
-typeguard==4.3.0
-more-itertools==10.3.0
-tomli==2.0.1
-autocommand==2.2.2
-zipp==3.19.2
-typing_extensions==4.12.2
-backports.tarfile==1.2.0
-inflect==7.3.1
-jaraco.text==3.12.1
-wheel==0.43.0
-packaging==24.2
-jaraco.collections==5.1.0
-jaraco.functools==4.0.1
-jaraco.context==5.3.0

wandb/run-20250217_214618-7bygcjmf/files/wandb-metadata.json

@@ -1,86 +0,0 @@
-{
-  "os":  "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
-  "python":  "CPython 3.12.3",
-  "startedAt":  "2025-02-17T21:46:18.759581Z",
-  "args":  [
-    "--model_name_or_path=openai/whisper-tiny",
-    "--dataset_name=asierhv/composite_corpus_eu_v2.1",
-    "--language=basque",
-    "--train_split_name=train",
-    "--eval_split_name=dev_parl+test_parl+test_cv+test_oslr",
-    "--model_index_name=Whisper Tiny Basque",
-    "--max_steps=10000",
-    "--output_dir=./",
-    "--per_device_train_batch_size=32",
-    "--per_device_eval_batch_size=16",
-    "--gradient_accumulation_steps=1",
-    "--logging_steps=25",
-    "--learning_rate=3.75e-5",
-    "--warmup_steps=1000",
-    "--evaluation_strategy=steps",
-    "--eval_steps=1000",
-    "--save_strategy=steps",
-    "--save_steps=1000",
-    "--generation_max_length=225",
-    "--length_column_name=input_length",
-    "--max_duration_in_seconds=30",
-    "--audio_column_name=audio",
-    "--text_column_name=sentence",
-    "--freeze_feature_encoder=False",
-    "--report_to=tensorboard",
-    "--metric_for_best_model=wer",
-    "--greater_is_better=False",
-    "--load_best_model_at_end",
-    "--gradient_checkpointing",
-    "--fp16",
-    "--overwrite_output_dir",
-    "--do_train",
-    "--do_eval",
-    "--predict_with_generate",
-    "--do_normalize_eval",
-    "--streaming",
-    "--use_auth_token",
-    "--push_to_hub",
-    "--report_to",
-    "wandb",
-    "--run_name",
-    "whisper-tiny-eu-2025.02"
-  ],
-  "program":  "/home/tknika/xezpeleta/whisper/whisper-tiny-eu/run_speech_recognition_seq2seq_streaming.py",
-  "codePath":  "run_speech_recognition_seq2seq_streaming.py",
-  "git":  {
-    "remote":  "https://huggingface.co/xezpeleta/whisper-tiny-eu",
-    "commit":  "424998f63b9d278b4ce5a8fa14342bd43c6971ad"
-  },
-  "email":  "xezpeleta@gmail.com",
-  "root":  "/home/tknika/xezpeleta/whisper/whisper-tiny-eu",
-  "host":  "tknika",
-  "executable":  "/home/tknika/xezpeleta/whisper/.venv/bin/python",
-  "codePathLocal":  "run_speech_recognition_seq2seq_streaming.py",
-  "cpu_count":  8,
-  "cpu_count_logical":  8,
-  "gpu":  "NVIDIA L40-48Q",
-  "gpu_count":  1,
-  "disk":  {
-    "/":  {
-      "total":  "525987168256",
-      "used":  "447815217152"
-    }
-  },
-  "memory":  {
-    "total":  "33654022144"
-  },
-  "cpu":  {
-    "count":  8,
-    "countLogical":  8
-  },
-  "gpu_nvidia":  [
-    {
-      "name":  "NVIDIA L40-48Q",
-      "memoryTotal":  "51539607552",
-      "cudaCores":  18176,
-      "architecture":  "Ada"
-    }
-  ],
-  "cudaVersion":  "12.4"
-}

wandb/run-20250217_214618-7bygcjmf/logs/debug-core.log

@@ -1,6 +0,0 @@
-{"time":"2025-02-17T21:46:18.667916236Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpzsw7ot30/port-168016.txt","pid":168016,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false}
-{"time":"2025-02-17T21:46:18.685302193Z","level":"INFO","msg":"Will exit if parent process dies.","ppid":168016}
-{"time":"2025-02-17T21:46:18.685729677Z","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":40697,"Zone":""}}
-{"time":"2025-02-17T21:46:18.752659702Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:58468"}
-{"time":"2025-02-17T21:46:18.764274372Z","level":"INFO","msg":"handleInformInit: received","streamId":"7bygcjmf","id":"127.0.0.1:58468"}
-{"time":"2025-02-17T21:46:18.87222342Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"7bygcjmf","id":"127.0.0.1:58468"}

wandb/run-20250217_214618-7bygcjmf/logs/debug-internal.log

@@ -1,7 +0,0 @@
-{"time":"2025-02-17T21:46:18.764731866Z","level":"INFO","msg":"stream: starting","core version":"0.19.6","symlink path":"/home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug-core.log"}
-{"time":"2025-02-17T21:46:18.87215251Z","level":"INFO","msg":"created new stream","id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.8722139Z","level":"INFO","msg":"stream: started","id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.872282469Z","level":"INFO","msg":"writer: Do: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.872363578Z","level":"INFO","msg":"handler: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:18.87291405Z","level":"INFO","msg":"sender: started","stream_id":"7bygcjmf"}
-{"time":"2025-02-17T21:46:19.182639444Z","level":"INFO","msg":"Starting system monitor"}

wandb/run-20250217_214618-7bygcjmf/logs/debug.log

@@ -1,25 +0,0 @@
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Current SDK version is 0.19.6
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Configure stats pid to 168016
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from /home/tknika/.config/wandb/settings
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/settings
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_setup.py:_flush():68] Loading settings from environment variables
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:setup_run_log_directory():637] Logging user logs to /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug.log
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:setup_run_log_directory():638] Logging internal logs to /home/tknika/xezpeleta/whisper/whisper-tiny-eu/wandb/run-20250217_214618-7bygcjmf/logs/debug-internal.log
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():756] calling init triggers
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():761] wandb.init called with sweep_config: {}
-config: {'_wandb': {}}
-2025-02-17 21:46:18,542 INFO    MainThread:168016 [wandb_init.py:init():789] starting backend
-2025-02-17 21:46:18,752 INFO    MainThread:168016 [wandb_init.py:init():793] sending inform_init request
-2025-02-17 21:46:18,758 INFO    MainThread:168016 [backend.py:_multiprocessing_setup():97] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2025-02-17 21:46:18,759 INFO    MainThread:168016 [wandb_init.py:init():808] backend started and connected
-2025-02-17 21:46:18,761 INFO    MainThread:168016 [wandb_init.py:init():901] updated telemetry
-2025-02-17 21:46:18,768 INFO    MainThread:168016 [wandb_init.py:init():936] communicating run to backend with 90.0 second timeout
-2025-02-17 21:46:19,179 INFO    MainThread:168016 [wandb_init.py:init():994] starting run threads in backend
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_console_start():2385] atexit reg
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2235] redirect: wrap_raw
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2300] Wrapping output streams.
-2025-02-17 21:46:19,298 INFO    MainThread:168016 [wandb_run.py:_redirect():2325] Redirects installed.
-2025-02-17 21:46:19,300 INFO    MainThread:168016 [wandb_init.py:init():1036] run started, returning control to user process
-2025-02-17 21:46:19,301 INFO    MainThread:168016 [wandb_run.py:_config_callback():1253] config_cb None None {'vocab_size': 51865, 'num_mel_bins': 80, 'd_model': 384, 'encoder_layers': 4, 'encoder_attention_heads': 6, 'decoder_layers': 4, 'decoder_attention_heads': 6, 'decoder_ffn_dim': 1536, 'encoder_ffn_dim': 1536, 'dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.0, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'use_cache': False, 'num_hidden_layers': 4, 'scale_embedding': False, 'max_source_positions': 1500, 'max_target_positions': 448, 'classifier_proj_size': 256, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.05, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'median_filter_width': 7, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 448, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': [220, 50257], 'architectures': ['WhisperForConditionalGeneration'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 50257, 'pad_token_id': 50257, 'eos_token_id': 50257, 'sep_token_id': None, 'decoder_start_token_id': 50258, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'openai/whisper-tiny', '_attn_implementation_autoset': True, 'transformers_version': '4.49.0.dev0', 'forced_decoder_ids': None, 'model_type': 'whisper', 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 3.75e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 3.0, 'max_steps': 10000, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': './runs/Feb17_21-45-10_tknika', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 25, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 1000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 1000, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'whisper-tiny-eu-2025.02', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': True, 'metric_for_best_model': 'wer', 'greater_is_better': False, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'input_length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': 'steps', 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 225, 'generation_num_beams': None, 'generation_config': None}
-2025-02-17 21:46:19,303 INFO    MainThread:168016 [wandb_config.py:__setitem__():154] config set model/num_parameters = 37760640 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x735fac35e9c0>>
-2025-02-17 21:46:19,303 INFO    MainThread:168016 [wandb_run.py:_config_callback():1253] config_cb model/num_parameters 37760640 None

wandb/run-20250217_214618-7bygcjmf/run-7bygcjmf.wandb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7b24350895068d2eeaab4073bdf0d0a76ef0d5ec72269f30f06e8afe5fbb6315
-size 4980736