dcbv
/

PEFT
charluv-lora / training_parameters.json
rondlite's picture
update qlora
9d46fa2
raw
history blame contribute delete
920 Bytes
{
"lora_name": "charluv-lora",
"always_override": true,
"save_steps": 1000.0,
"micro_batch_size": 4,
"batch_size": 0,
"epochs": 1.0,
"learning_rate": "3e-4",
"lr_scheduler_type": "linear",
"lora_rank": 128,
"lora_alpha": 256,
"lora_dropout": 0.05,
"cutoff_len": 256,
"dataset": "training",
"eval_dataset": "None",
"format": "alpaca-format",
"eval_steps": 100.0,
"raw_text_file": "None",
"higher_rank_limit": false,
"warmup_steps": 100.0,
"optimizer": "adamw_torch",
"hard_cut_string": "\\n\\n\\n",
"train_only_after": "",
"stop_at_loss": 0.1,
"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": true,
"training_projection": "all",
"sliding_window": false,
"warmup_ratio": 0,
"grad_accumulation": 1,
"neft_noise_alpha": 0
}