adapter_meta.json

{
  "base_model": "CohereLabs/cohere-transcribe-arabic-07-2026",
  "recipe": "method",
  "lora_scope": "decoder",
  "conv_adapter": true,
  "language": "ar",
  "lora": {
    "r": 32,
    "lora_alpha": 64,
    "lora_dropout": 0.05,
    "bias": "none",
    "target_kinds": [
      "q_proj",
      "k_proj",
      "v_proj",
      "o_proj"
    ]
  },
  "lora_targets": [
    "model.decoder.layers.0.self_attn.q_proj",
    "model.decoder.layers.0.self_attn.k_proj",
    "model.decoder.layers.0.self_attn.v_proj",
    "model.decoder.layers.0.self_attn.o_proj",
    "model.decoder.layers.0.encoder_attn.q_proj",
    "model.decoder.layers.0.encoder_attn.k_proj",
    "model.decoder.layers.0.encoder_attn.v_proj",
    "model.decoder.layers.0.encoder_attn.o_proj",
    "model.decoder.layers.1.self_attn.q_proj",
    "model.decoder.layers.1.self_attn.k_proj",
    "model.decoder.layers.1.self_attn.v_proj",
    "model.decoder.layers.1.self_attn.o_proj",
    "model.decoder.layers.1.encoder_attn.q_proj",
    "model.decoder.layers.1.encoder_attn.k_proj",
    "model.decoder.layers.1.encoder_attn.v_proj",
    "model.decoder.layers.1.encoder_attn.o_proj",
    "model.decoder.layers.2.self_attn.q_proj",
    "model.decoder.layers.2.self_attn.k_proj",
    "model.decoder.layers.2.self_attn.v_proj",
    "model.decoder.layers.2.self_attn.o_proj",
    "model.decoder.layers.2.encoder_attn.q_proj",
    "model.decoder.layers.2.encoder_attn.k_proj",
    "model.decoder.layers.2.encoder_attn.v_proj",
    "model.decoder.layers.2.encoder_attn.o_proj",
    "model.decoder.layers.3.self_attn.q_proj",
    "model.decoder.layers.3.self_attn.k_proj",
    "model.decoder.layers.3.self_attn.v_proj",
    "model.decoder.layers.3.self_attn.o_proj",
    "model.decoder.layers.3.encoder_attn.q_proj",
    "model.decoder.layers.3.encoder_attn.k_proj",
    "model.decoder.layers.3.encoder_attn.v_proj",
    "model.decoder.layers.3.encoder_attn.o_proj",
    "model.decoder.layers.4.self_attn.q_proj",
    "model.decoder.layers.4.self_attn.k_proj",
    "model.decoder.layers.4.self_attn.v_proj",
    "model.decoder.layers.4.self_attn.o_proj",
    "model.decoder.layers.4.encoder_attn.q_proj",
    "model.decoder.layers.4.encoder_attn.k_proj",
    "model.decoder.layers.4.encoder_attn.v_proj",
    "model.decoder.layers.4.encoder_attn.o_proj",
    "model.decoder.layers.5.self_attn.q_proj",
    "model.decoder.layers.5.self_attn.k_proj",
    "model.decoder.layers.5.self_attn.v_proj",
    "model.decoder.layers.5.self_attn.o_proj",
    "model.decoder.layers.5.encoder_attn.q_proj",
    "model.decoder.layers.5.encoder_attn.k_proj",
    "model.decoder.layers.5.encoder_attn.v_proj",
    "model.decoder.layers.5.encoder_attn.o_proj",
    "model.decoder.layers.6.self_attn.q_proj",
    "model.decoder.layers.6.self_attn.k_proj",
    "model.decoder.layers.6.self_attn.v_proj",
    "model.decoder.layers.6.self_attn.o_proj",
    "model.decoder.layers.6.encoder_attn.q_proj",
    "model.decoder.layers.6.encoder_attn.k_proj",
    "model.decoder.layers.6.encoder_attn.v_proj",
    "model.decoder.layers.6.encoder_attn.o_proj",
    "model.decoder.layers.7.self_attn.q_proj",
    "model.decoder.layers.7.self_attn.k_proj",
    "model.decoder.layers.7.self_attn.v_proj",
    "model.decoder.layers.7.self_attn.o_proj",
    "model.decoder.layers.7.encoder_attn.q_proj",
    "model.decoder.layers.7.encoder_attn.k_proj",
    "model.decoder.layers.7.encoder_attn.v_proj",
    "model.decoder.layers.7.encoder_attn.o_proj"
  ],
  "skip_bottom_frac": 0.33,
  "n_layers": 48,
  "start_layer": 15,
  "attached_layers": [
    15,
    16,
    17,
    18,
    19,
    20,
    21,
    22,
    23,
    24,
    25,
    26,
    27,
    28,
    29,
    30,
    31,
    32,
    33,
    34,
    35,
    36,
    37,
    38,
    39,
    40,
    41,
    42,
    43,
    44,
    45,
    46,
    47
  ],
  "d_model": 1280,
  "bottleneck": 64,
  "kernels": [
    7,
    15,
    23,
    31
  ],
  "fusion": "concat_fusion",
  "merge_kernel": 31,
  "dropout": 0.1,
  "trainable": {
    "trainable": 21145216,
    "total": 2086793088,
    "pct": 1.013287619246705
  },
  "decoder_lr": 0.0005,
  "encoder_adapter_lr": 0.0001,
  "optimizer": "adamw",
  "betas": [
    0.9,
    0.98
  ],
  "scheduler": "cosine+warmup_ratio_0.1",
  "precision": "bf16",
  "seed": 42,
  "epochs": 5,
  "steps_per_epoch": 23,
  "vram_budget_gb": 16.0,
  "vram_peak_gb": 18.0323486328125,
  "sampler": "length_bucket",
  "sampler_mix": 4,
  "pad_waste_duration_random": 0.4951037898430557,
  "pad_waste_duration_bucket": 0.11339504348548876,
  "pad_waste_mel_running": null
}