training_parameters.json

{
  "lora_name": "surge_final",
  "always_override": false,
  "q_proj_en": true,
  "v_proj_en": true,
  "k_proj_en": false,
  "o_proj_en": false,
  "gate_proj_en": false,
  "down_proj_en": false,
  "up_proj_en": false,
  "save_steps": 10000,
  "micro_batch_size": 6,
  "batch_size": 500,
  "epochs": 3,
  "learning_rate": "3e-4",
  "lr_scheduler_type": "linear",
  "lora_rank": 512,
  "lora_alpha": 1024,
  "lora_dropout": 0.05,
  "cutoff_len": 256,
  "dataset": "dataset",
  "eval_dataset": "None",
  "format": "alpaca-format",
  "eval_steps": 100,
  "raw_text_file": "None",
  "overlap_len": 128,
  "newline_favor_len": 128,
  "higher_rank_limit": false,
  "warmup_steps": 100,
  "optimizer": "adamw_torch",
  "hard_cut_string": "\\n\\n\\n",
  "train_only_after": "",
  "stop_at_loss": 0,
  "add_eos_token": false,
  "min_chars": 0,
  "report_to": "None"
}