Training in progress, step 5000

.hydra/config.yaml

@@ -0,0 +1,49 @@
+paths:
+  root_dir: .
+  data_dir: ${paths.root_dir}/data/
+  log_dir: ${paths.root_dir}/logs/
+  output_dir: ${hydra:runtime.output_dir}
+  work_dir: ${hydra:runtime.cwd}
+data_config:
+  name: mitermix/audiosnippets
+  streaming: true
+  audio_key: mp3
+  caption_key: caption
+model_config:
+  tokenizer_name: openai/whisper-tiny
+  model_name: openai/whisper-base
+  attn_implementation: flash_attention_2
+  name: openai/whisper-tiny
+trainer_config:
+  tf32: true
+  bf16: true
+  fp16: false
+  dataloader_num_workers: 16
+  eval_strategy: 'no'
+  eval_steps: null
+  save_strategy: steps
+  save_steps: 5000
+  save_total_limit: 5
+  gradient_checkpointing: false
+  gradient_checkpointing_kwargs:
+    use_reentrant: false
+  ddp_find_unused_parameters: false
+  logging_steps: 50
+  seed: 998244353
+  optim: adamw_torch
+  adam_beta1: 0.9
+  adam_beta2: 0.98
+  max_grad_norm: 1.0
+  per_device_train_batch_size: 128
+  output_dir: ${paths.output_dir}
+  report_to: tensorboard
+  logging_dir: ${trainer_config.output_dir}/tb
+  lr_scheduler_type: cosine
+  learning_rate: 0.0001
+  warmup_steps: 5000
+  max_steps: 50000
+  label_smoothing_factor: 0.0
+  push_to_hub: true
+  hub_model_id: seastar105/whisper-base-emo-speech-caption
+  dataloader_prefetch_factor: 4
+task_name: tiny-test

.hydra/hydra.yaml

@@ -0,0 +1,169 @@
+hydra:
+  run:
+    dir: ${paths.log_dir}/${task_name}/runs/${now:%Y-%m-%d}_${now:%H-%M-%S}
+  sweep:
+    dir: ${paths.log_dir}/${task_name}/multiruns/${now:%Y-%m-%d}_${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: ${hydra.runtime.output_dir}/${task_name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - model_config.model_name=openai/whisper-base
+    - model_config.attn_implementation=flash_attention_2
+    - data_config.name=mitermix/audiosnippets
+    - data_config.audio_key=mp3
+    - data_config.caption_key=caption
+    - trainer_config.bf16=true
+    - trainer_config.dataloader_num_workers=16
+    - trainer_config.per_device_train_batch_size=128
+    - trainer_config.max_steps=50000
+    - ++trainer_config.push_to_hub=true
+    - ++trainer_config.hub_model_id=seastar105/whisper-base-emo-speech-caption
+    - ++trainer_config.save_total_limit=5
+    - ++trainer_config.save_steps=5000
+    - ++trainer_config.dataloader_prefetch_factor=4
+    - ++trainer_config.warmup_steps=5000
+  job:
+    name: train
+    chdir: null
+    override_dirname: ++trainer_config.dataloader_prefetch_factor=4,++trainer_config.hub_model_id=seastar105/whisper-base-emo-speech-caption,++trainer_config.push_to_hub=true,++trainer_config.save_steps=5000,++trainer_config.save_total_limit=5,++trainer_config.warmup_steps=5000,data_config.audio_key=mp3,data_config.caption_key=caption,data_config.name=mitermix/audiosnippets,model_config.attn_implementation=flash_attention_2,model_config.model_name=openai/whisper-base,trainer_config.bf16=true,trainer_config.dataloader_num_workers=16,trainer_config.max_steps=50000,trainer_config.per_device_train_batch_size=128
+    id: ???
+    num: ???
+    config_name: main
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /root/audio-caption
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /root/audio-caption/configs
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /root/audio-caption/logs/tiny-test/runs/2025-01-05_02-24-57
+    choices:
+      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

.hydra/overrides.yaml

@@ -0,0 +1,15 @@
+- model_config.model_name=openai/whisper-base
+- model_config.attn_implementation=flash_attention_2
+- data_config.name=mitermix/audiosnippets
+- data_config.audio_key=mp3
+- data_config.caption_key=caption
+- trainer_config.bf16=true
+- trainer_config.dataloader_num_workers=16
+- trainer_config.per_device_train_batch_size=128
+- trainer_config.max_steps=50000
+- ++trainer_config.push_to_hub=true
+- ++trainer_config.hub_model_id=seastar105/whisper-base-emo-speech-caption
+- ++trainer_config.save_total_limit=5
+- ++trainer_config.save_steps=5000
+- ++trainer_config.dataloader_prefetch_factor=4
+- ++trainer_config.warmup_steps=5000

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "openai/whisper-base",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": null,
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": null,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 6,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be343d994b8f72a0348fa21a10f77df07ab9ceca576dd60a89b564bf7d27b342
+size 290403936

tb/events.out.tfevents.1736043901.5f4e103e0ee7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c819a6f5bf99b7e21632f0ade49c41334c2002842660403ba6bf1129db993e4f
+size 27675

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c408606756c80c14750aef57d23effec7e94468930a74be618d0505e2b908948
+size 5432