Files
llama2_7b-chat_gsm8k_full_f…/finetune_config.json
ModelHub XC 1a17680a46 初始化项目,由ModelHub XC社区提供模型
Model: kmseong/llama2_7b-chat_gsm8k_full_ft_lr5e-5
Source: Original Platform
2026-07-31 18:58:16 +08:00

19 lines
484 B
JSON

{
"base_model": "kmseong/llama2_7b-chat-Safety-FT-lr5e-5",
"fine_tuning_type": "Full Parameter Fine-tuning",
"dataset": "GSM8K",
"num_train_samples": 7473,
"batch_size": 4,
"grad_accum": 4,
"learning_rate": 5e-05,
"weight_decay": 0.01,
"warmup_ratio": 0.1,
"epochs": 3,
"max_length": 1024,
"max_grad_norm": 1.0,
"lr_scheduler_type": "cosine",
"optimizer": "AdamW (torch)",
"gradient_checkpointing": false,
"dtype": "bf16",
"trainer_type": "Trainer"
}