training_args.json

{
  "batch_size": 32,
  "data_path": "train/en-zh_cn_vad_mix.csv",
  "dtype": "fp16",
  "encoding": "utf-8",
  "epochs": 4,
  "errors": "ignore",
  "eval_batch_size": 0,
  "eval_batches": 200,
  "eval_every": 100,
  "eval_ratio": 0.01,
  "grad_accum_steps": 4,
  "huber_delta": 1.0,
  "learning_rate": 1e-05,
  "log_every": 1,
  "loss": "huber",
  "max_length": 512,
  "max_rows": null,
  "max_steps": 5000,
  "min_chars": 2,
  "model_name": "hfl/chinese-macbert-base",
  "num_labels": 3,
  "num_rows": 400000,
  "output_dir": "train/vad-macbert-mix",
  "resume_from": "train/vad-macbert-long/best",
  "save_every": 100,
  "seed": 42,
  "shuffle_buffer": 4096,
  "warmup_ratio": 0.1,
  "warmup_steps": 0,
  "weight_decay": 0.01
}