training_parameters.json

{
  "lora_name": "Waxwing",
  "always_override": false,
  "save_steps": 0.0,
  "micro_batch_size": 3,
  "batch_size": 0,
  "epochs": 1.0,
  "learning_rate": "3e-4",
  "lr_scheduler_type": "linear",
  "lora_rank": 16,
  "lora_alpha": 8,
  "lora_dropout": 0.05,
  "cutoff_len": 1280,
  "dataset": "dataset_11.27.23",
  "eval_dataset": "None",
  "format": "t2d_oobabooga_training_format",
  "eval_steps": 100.0,
  "raw_text_file": "None",
  "higher_rank_limit": false,
  "warmup_steps": 100.0,
  "optimizer": "adamw_torch_fused",
  "hard_cut_string": "\\n\\n\\n",
  "train_only_after": "",
  "stop_at_loss": 0,
  "add_eos_token": false,
  "min_chars": 0.0,
  "report_to": "None",
  "precize_slicing_overlap": true,
  "add_eos_token_type": "Every Block",
  "save_steps_under_loss": 1.8,
  "add_bos_token": false,
  "training_projection": "all",
  "sliding_window": false,
  "warmup_ratio": 0,
  "grad_accumulation": 4,
  "neft_noise_alpha": 3
}