-
Notifications
You must be signed in to change notification settings - Fork 289
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
16 additions
and
16 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,18 +1,18 @@ | ||
{ | ||
"max_position_embeddings": 4096, # 训练最大上下文长度 | ||
"batch_size": 1, # 训练批次 | ||
"accumulation_steps": 256, # 累积步数 | ||
"num_train_epochs": 1, # 训练轮次 | ||
"learning_rate": 1e-05, # 学习率 | ||
"save_steps": 1000, # 保存步数 | ||
"logging_steps": 100, # 日志步数 | ||
"pre_train_path": "", # 预训练模型路径 | ||
"pre_tokenizer_path": "", # 预训练模型tokenizer路径 | ||
"dataset_path": "", # 数据集路径,一般为json或jsonl格式 | ||
"train_option": "pretrain", # 训练方式 pretrain sft chatml mistral | ||
"output_dir": "", # 输出路径 | ||
"use_lora": false, # 是否使用lora,false即全量微调 | ||
"pre_lora_train_path": "", # 继续训练时上一步lora保存的路径 | ||
"lora_rank": 8, # lora rank 越大训练参数越多 | ||
"lora_alpha": 32 # lora aplpha | ||
"max_position_embeddings": 4096, | ||
"batch_size": 1, | ||
"accumulation_steps": 256, | ||
"num_train_epochs": 1, | ||
"learning_rate": 1e-05, | ||
"save_steps": 1000, | ||
"logging_steps": 100, | ||
"pre_train_path": "", | ||
"pre_tokenizer_path": "", | ||
"dataset_path": "", | ||
"train_option": "pretrain", | ||
"output_dir": "", | ||
"use_lora": false, | ||
"pre_lora_train_path": "", | ||
"lora_rank": 8, | ||
"lora_alpha": 32 | ||
} |