kmseong/Llama-3.1-8B-base-gsm8k-SSFT_lr1e-5
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: kmseong/Llama-3.1-8B-base-gsm8k-SSFT_lr1e-5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-23 04:39:15 +08:00
commit ef45fa3571
15 changed files with 2606 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
finetune_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"base_model": "kmseong/Llama-3.1-8B-base-SSFT_lr5e-5",
"fine_tuning_type": "Full Parameter Fine-tuning",
"dataset": "GSM8K",
"num_train_samples": 7473,
"batch_size": 4,
"grad_accum": 4,
"learning_rate": 1e-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",
"safety_mix_ratio": 0.0,
"safety_data_path": null
}