llama3-2-1b-Solutions
/
models--psd401--llama3-2-1b-Solutions
/snapshots
/0b2a76d7ecedea05b1009b450a47dc843b4b1b53
/training_params.json
{ | |
"model": "meta-llama/Llama-3.2-1B-Instruct", | |
"project_name": "llama3-2-1b-Solutions", | |
"data_path": "psd401/PSD401SolutionsData/data/dataset.jsonl", | |
"train_split": "train", | |
"valid_split": null, | |
"add_eos_token": true, | |
"block_size": -1, | |
"model_max_length": 2048, | |
"padding": "right", | |
"trainer": "sft", | |
"use_flash_attention_2": false, | |
"log": "tensorboard", | |
"disable_gradient_checkpointing": false, | |
"logging_steps": -1, | |
"eval_strategy": "epoch", | |
"save_total_limit": 1, | |
"auto_find_batch_size": false, | |
"mixed_precision": "bf16", | |
"lr": 0.00001, | |
"epochs": 3, | |
"batch_size": 1, | |
"warmup_ratio": 0.1, | |
"gradient_accumulation": 8, | |
"optimizer": "paged_adamw_8bit", | |
"scheduler": "cosine", | |
"weight_decay": 0.0, | |
"max_grad_norm": 1.0, | |
"seed": 42, | |
"chat_template": "tokenizer", | |
"quantization": "int8", | |
"target_modules": "all-linear", | |
"merge_adapter": true, | |
"peft": true, | |
"lora_r": 16, | |
"lora_alpha": 32, | |
"lora_dropout": 0.05, | |
"model_ref": null, | |
"dpo_beta": 0.1, | |
"max_prompt_length": 128, | |
"max_completion_length": null, | |
"prompt_text_column": null, | |
"text_column": "messages", | |
"rejected_text_column": null, | |
"push_to_hub": false, | |
"username": null, | |
"token": null, | |
"unsloth": false, | |
"distributed_backend": null | |
} |