Zira-v7-advanced / training_params.json
HyperX-Sentience's picture
Upload folder using huggingface_hub
846447f verified
{
"model": "bigscience/bloom-560m",
"project_name": "Zira-v7-advanced",
"data_path": "HyperX-Sentience/Zira-advanced-Instruct",
"train_split": "train",
"valid_split": null,
"add_eos_token": true,
"block_size": 1024,
"model_max_length": 2048,
"padding": "right",
"trainer": "sft",
"use_flash_attention_2": false,
"log": "none",
"disable_gradient_checkpointing": false,
"logging_steps": 10,
"eval_strategy": "epoch",
"save_total_limit": 1,
"auto_find_batch_size": false,
"mixed_precision": "fp16",
"lr": 2e-05,
"epochs": 1,
"batch_size": 2,
"warmup_ratio": 0.03,
"gradient_accumulation": 2,
"optimizer": "adamw_torch",
"scheduler": "cosine",
"weight_decay": 0.01,
"max_grad_norm": 1.0,
"seed": 43,
"chat_template": null,
"quantization": "int4",
"target_modules": "all-linear",
"merge_adapter": false,
"peft": true,
"lora_r": 16,
"lora_alpha": 32,
"lora_dropout": 0.05,
"model_ref": null,
"dpo_beta": 0.1,
"max_prompt_length": 2048,
"max_completion_length": null,
"prompt_text_column": null,
"text_column": "text",
"rejected_text_column": null,
"push_to_hub": true,
"username": "HyperX-Sentience",
"unsloth": false,
"distributed_backend": null
}