Training in progress, step 5000

.hydra/config.yaml

@@ -0,0 +1,45 @@
+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: krishnakalyan3/emo_webds_2
+model_config:
+  name: openai/whisper-tiny
+  attn_implementation: sdpa
+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: 2000
+  max_steps: 25000
+  label_smoothing_factor: 0.0
+  push_to_hub: true
+  hub_model_id: seastar105/whisper-base-emo-speech-caption
+  split_batches: true
+  dataloader_prefetch_factor: 4
+task_name: tiny-test

.hydra/hydra.yaml

@@ -0,0 +1,164 @@
+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:
+    - trainer_config.per_device_train_batch_size=128
+    - ++trainer_config.bf16=true
+    - trainer_config.max_steps=25000
+    - ++trainer_config.push_to_hub=true
+    - ++trainer_config.hub_model_id=seastar105/whisper-base-emo-speech-caption
+    - ++trainer_config.split_batches=true
+    - ++trainer_config.save_total_limit=5
+    - ++trainer_config.save_steps=5000
+    - ++trainer_config.dataloader_prefetch_factor=4
+    - ++trainer_config.dataloader_num_workers=16
+  job:
+    name: train
+    chdir: null
+    override_dirname: ++trainer_config.bf16=true,++trainer_config.dataloader_num_workers=16,++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.split_batches=true,trainer_config.max_steps=25000,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/2024-12-26_15-36-11
+    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 +1,10 @@
+- trainer_config.per_device_train_batch_size=128
+- ++trainer_config.bf16=true
+- trainer_config.max_steps=25000
+- ++trainer_config.push_to_hub=true
+- ++trainer_config.hub_model_id=seastar105/whisper-base-emo-speech-caption
+- ++trainer_config.split_batches=true
+- ++trainer_config.save_total_limit=5
+- ++trainer_config.save_steps=5000
+- ++trainer_config.dataloader_prefetch_factor=4
+- ++trainer_config.dataloader_num_workers=16

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "openai/whisper-tiny",
+  "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": 384,
+  "decoder_attention_heads": 6,
+  "decoder_ffn_dim": 1536,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 6,
+  "encoder_ffn_dim": 1536,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "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": 4,
+  "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 sha256:8b86d035092ca3b34763dc3cffd8c20b0534b87e11b83d23f12ad615cd428f28
+size 151061672

tb/events.out.tfevents.1735227385.c76029f3d320

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e73cd0bcc8d77f479ec5c4ffd15a72e9bd2bdac10c244be7c0d4c899d6199f7
+size 27674

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784cdd034747ae293a66620e63a46c3dcd9545583f708cd6aaf2c774962d1099
+size 5432