From 01ef5baffbda781c322ea4cf2c545d294facac42 Mon Sep 17 00:00:00 2001 From: Zhihao Lin <36994684+LZHgrla@users.noreply.github.com> Date: Wed, 15 Nov 2023 18:29:20 +0800 Subject: [PATCH] [Fix] Set default `eta_min` to 0. (#223) eta_min to 0.0 --- docs/zh_cn/user_guides/config.md | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_e3.py | 2 +- .../baichuan2_13b_base_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan2_13b_base_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_zh_e3.py | 2 +- .../baichuan2_13b_base_qlora_arxiv_gentitle_e3.py | 2 +- .../baichuan2_13b_base_qlora_code_alpaca_e3.py | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_colorist_e5.py | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_lawyer_e3.py | 2 +- .../baichuan2_13b_base_qlora_oasst1_512_e3.py | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_e3.py | 2 +- .../baichuan2_13b_base_qlora_open_platypus_e3.py | 2 +- .../baichuan2_13b_base/baichuan2_13b_base_qlora_sql_e3.py | 2 +- .../baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_e3.py | 2 +- .../baichuan2_13b_chat_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan2_13b_chat_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_zh_e3.py | 2 +- .../baichuan2_13b_chat_qlora_code_alpaca_e3.py | 2 +- .../baichuan2_13b_chat/baichuan2_13b_chat_qlora_lawyer_e3.py | 2 +- .../baichuan2_13b_chat_qlora_oasst1_512_e3.py | 2 +- .../baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_e3.py | 2 +- .../baichuan2_13b_chat_qlora_open_platypus_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan2_7b_base_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_zh_e3.py | 2 +- .../baichuan2_7b_base_qlora_arxiv_gentitle_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_code_alpaca_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_colorist_e5.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_lawyer_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_512_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_e3.py | 2 +- .../baichuan2_7b_base_qlora_open_platypus_e3.py | 2 +- .../baichuan2_7b_base/baichuan2_7b_base_qlora_sql_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_zh_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_code_alpaca_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_lawyer_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_512_e3.py | 2 +- .../baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_e3.py | 2 +- .../baichuan2_7b_chat_qlora_open_platypus_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_alpaca_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan_13b_base_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_alpaca_zh_e3.py | 2 +- .../baichuan_13b_base_qlora_arxiv_gentitle_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_code_alpaca_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_colorist_e5.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_lawyer_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_medical_e1.py | 2 +- .../baichuan_13b_base_qlora_moss_sft_all_e1.py | 2 +- .../baichuan_13b_base_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../baichuan_13b_base_qlora_moss_sft_plugins_e1.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_oasst1_512_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_oasst1_e3.py | 2 +- .../baichuan_13b_base_qlora_open_platypus_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_openorca_e1.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_sql_e3.py | 2 +- .../baichuan_13b_base/baichuan_13b_base_qlora_tiny_codes_e1.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan_13b_chat_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_zh_e3.py | 2 +- .../baichuan_13b_chat_qlora_arxiv_gentitle_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_code_alpaca_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_colorist_e5.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_lawyer_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_medical_e1.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_512_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_e3.py | 2 +- .../baichuan_13b_chat_qlora_open_platypus_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_openorca_e1.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_sql_e3.py | 2 +- .../baichuan_13b_chat/baichuan_13b_chat_qlora_tiny_codes_e1.py | 2 +- .../configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_e3.py | 2 +- .../baichuan_7b/baichuan_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_zh_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_arxiv_gentitle_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_code_alpaca_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_colorist_e5.py | 2 +- .../configs/baichuan/baichuan_7b/baichuan_7b_qlora_lawyer_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_medical_e1.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e1.py | 2 +- .../baichuan_7b/baichuan_7b_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../baichuan_7b/baichuan_7b_qlora_moss_sft_plugins_e1.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_512_e3.py | 2 +- .../configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_open_platypus_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_openorca_e1.py | 2 +- xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_sql_e3.py | 2 +- .../baichuan/baichuan_7b/baichuan_7b_qlora_tiny_codes_e1.py | 2 +- .../configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_e3.py | 2 +- .../chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_zh_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_arxiv_gentitle_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_code_alpaca_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_colorist_e5.py | 2 +- .../configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_lawyer_e3.py | 2 +- .../configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_medical_e1.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_512_e3.py | 2 +- .../configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_open_platypus_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_openorca_e1.py | 2 +- xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_sql_e3.py | 2 +- .../chatglm/chatglm2_6b/chatglm2_6b_qlora_tiny_codes_e1.py | 2 +- .../configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_e3.py | 2 +- .../chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_zh_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_arxiv_gentitle_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_code_alpaca_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_colorist_e5.py | 2 +- .../configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_lawyer_e3.py | 2 +- .../configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_medical_e1.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_512_e3.py | 2 +- .../configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_open_platypus_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_openorca_e1.py | 2 +- xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_sql_e3.py | 2 +- .../chatglm/chatglm3_6b/chatglm3_6b_qlora_tiny_codes_e1.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_e3.py | 2 +- .../chatglm3_6b_base_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_zh_e3.py | 2 +- .../chatglm3_6b_base_qlora_arxiv_gentitle_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_code_alpaca_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_colorist_e5.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_lawyer_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_medical_e1.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_512_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_open_platypus_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_openorca_e1.py | 2 +- .../chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_sql_e3.py | 2 +- .../chatglm3_6b_base/chatglm3_6b_base_qlora_tiny_codes_e1.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_alpaca_e3.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_e3.py | 2 +- .../internlm_20b/internlm_20b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_alpaca_zh_e3.py | 2 +- .../internlm_20b/internlm_20b_qlora_arxiv_gentitle_e3.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_code_alpaca_e3.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_colorist_e5.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_lawyer_e3.py | 2 +- .../internlm_20b/internlm_20b_qlora_msagent_react_e3_gpu8.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_oasst1_512_e3.py | 2 +- .../internlm/internlm_20b/internlm_20b_qlora_oasst1_e3.py | 2 +- .../internlm_20b/internlm_20b_qlora_open_platypus_e3.py | 2 +- .../configs/internlm/internlm_20b/internlm_20b_qlora_sql_e3.py | 2 +- .../configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py | 2 +- .../internlm_7b/internlm_7b_full_alpaca_enzh_oasst1_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_full_alpaca_zh_e3.py | 2 +- .../configs/internlm/internlm_7b/internlm_7b_full_oasst1_e3.py | 2 +- .../configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_e3.py | 2 +- .../internlm_7b/internlm_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_alpaca_zh_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_arxiv_gentitle_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_code_alpaca_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_colorist_e5.py | 2 +- .../configs/internlm/internlm_7b/internlm_7b_qlora_lawyer_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_medical_e1.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e1.py | 2 +- .../internlm_7b/internlm_7b_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../internlm_7b/internlm_7b_qlora_moss_sft_plugins_e1.py | 2 +- .../internlm_7b/internlm_7b_qlora_msagent_react_e3_gpu8.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_oasst1_512_e3.py | 2 +- .../configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_oasst1_mmlu_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_open_platypus_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_openorca_e1.py | 2 +- xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_sql_e3.py | 2 +- .../internlm/internlm_7b/internlm_7b_qlora_tiny_codes_e1.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_alpaca_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_e3.py | 2 +- .../internlm_chat_20b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_alpaca_zh_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_code_alpaca_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_lawyer_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_oasst1_512_e3.py | 2 +- .../internlm_chat_20b/internlm_chat_20b_qlora_oasst1_e3.py | 2 +- .../internlm_chat_20b_qlora_open_platypus_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_alpaca_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_e3.py | 2 +- .../internlm_chat_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_alpaca_zh_e3.py | 2 +- .../internlm_chat_7b_qlora_arxiv_gentitle_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_code_alpaca_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_colorist_e5.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_lawyer_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_medical_e1.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_oasst1_512_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_oasst1_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_open_platypus_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_openorca_e1.py | 2 +- .../internlm/internlm_chat_7b/internlm_chat_7b_qlora_sql_e3.py | 2 +- .../internlm_chat_7b/internlm_chat_7b_qlora_tiny_codes_e1.py | 2 +- .../llama/llama2_70b/llama2_70b_int8_lora_open_platypus_e1.py | 2 +- .../llama/llama2_70b/llama2_70b_qlora_open_platypus_e1.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_full_wizardlm_e1.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_e3.py | 2 +- .../configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_e3.py | 2 +- .../llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_zh_e3.py | 2 +- .../llama/llama2_7b/llama2_7b_qlora_arxiv_gentitle_e3.py | 2 +- .../configs/llama/llama2_7b/llama2_7b_qlora_code_alpaca_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_colorist_e5.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_lawyer_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_medical_e1.py | 2 +- .../configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e1.py | 2 +- .../llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../llama/llama2_7b/llama2_7b_qlora_moss_sft_plugins_e1.py | 2 +- .../llama/llama2_7b/llama2_7b_qlora_msagent_react_e3_gpu8.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_512_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_e3.py | 2 +- .../configs/llama/llama2_7b/llama2_7b_qlora_open_platypus_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_openorca_e1.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_sql_e3.py | 2 +- xtuner/configs/llama/llama2_7b/llama2_7b_qlora_tiny_codes_e1.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_e3.py | 2 +- .../llama2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_zh_e3.py | 2 +- .../llama2_7b_chat/llama2_7b_chat_qlora_arxiv_gentitle_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_code_alpaca_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_colorist_e5.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_lawyer_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_medical_e1.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_512_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_e3.py | 2 +- .../llama2_7b_chat/llama2_7b_chat_qlora_open_platypus_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_openorca_e1.py | 2 +- .../configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_sql_e3.py | 2 +- .../llama/llama2_7b_chat/llama2_7b_chat_qlora_tiny_codes_e1.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_e3.py | 2 +- .../llama/llama_7b/llama_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_zh_e3.py | 2 +- .../configs/llama/llama_7b/llama_7b_qlora_arxiv_gentitle_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_code_alpaca_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_colorist_e5.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_lawyer_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_medical_e1.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e1.py | 2 +- .../llama/llama_7b/llama_7b_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../llama/llama_7b/llama_7b_qlora_moss_sft_plugins_e1.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_512_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_e3.py | 2 +- .../configs/llama/llama_7b/llama_7b_qlora_open_platypus_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_openorca_e1.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_sql_e3.py | 2 +- xtuner/configs/llama/llama_7b/llama_7b_qlora_tiny_codes_e1.py | 2 +- xtuner/configs/mistral/mistral_7b_qlora_skypile_pretrain_e1.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_e3.py | 2 +- .../configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_oasst1_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_zh_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_arxiv_gentitle_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_code_alpaca_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_colorist_e5.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_lawyer_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_medical_e1.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e1.py | 2 +- .../configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e2_gpu8.py | 2 +- .../configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_plugins_e1.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_512_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_open_platypus_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_openorca_e1.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_sql_e3.py | 2 +- xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_tiny_codes_e1.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_e3.py | 2 +- .../qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_oasst1_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_zh_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_arxiv_gentitle_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_code_alpaca_e3.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_colorist_e5.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_lawyer_e3.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_medical_e1.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_512_e3.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_open_platypus_e3.py | 2 +- .../configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_openorca_e1.py | 2 +- xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_sql_e3.py | 2 +- .../qwen/qwen_7b_chat/qwen_7b_chat_qlora_tiny_codes_e1.py | 2 +- .../configs/starcoder/starcoder_qlora_stack_exchange_example.py | 2 +- xtuner/configs/yi/yi_34b/yi_34b_qlora_alpaca_enzh_e3.py | 2 +- xtuner/configs/yi/yi_6b/yi_6b_qlora_alpaca_enzh_e3.py | 2 +- xtuner/configs/zephyr/zephyr_7b_beta_qlora_alpaca_e3.py | 2 +- 294 files changed, 294 insertions(+), 294 deletions(-) diff --git a/docs/zh_cn/user_guides/config.md b/docs/zh_cn/user_guides/config.md index fa1e5d2ef..2632cb9f3 100644 --- a/docs/zh_cn/user_guides/config.md +++ b/docs/zh_cn/user_guides/config.md @@ -124,7 +124,7 @@ optim_wrapper = dict( # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( # 学习率 scheduler 配置 type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_e3.py index dafe3b712..4c63bdda6 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_e3.py index 91288d451..b76b76818 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_oasst1_e3.py index b135ba146..e0e4d5078 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_zh_e3.py index 5bb43fbed..437764294 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_arxiv_gentitle_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_arxiv_gentitle_e3.py index 5555f886b..302ff1ba1 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_code_alpaca_e3.py index b15b8adea..729712040 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_colorist_e5.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_colorist_e5.py index e4a5f2756..0e5796c50 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_colorist_e5.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_lawyer_e3.py index 3653b7d52..3f56e4e83 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_512_e3.py index 04bb84093..7d1ccc833 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_e3.py index 46ffdce06..4534e0d95 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_open_platypus_e3.py index 146265982..02ba72c6e 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_sql_e3.py b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_sql_e3.py index 098538a2e..df712c21f 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_sql_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_base/baichuan2_13b_base_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_e3.py index d929474de..d286e23ec 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_e3.py index f8b3e8382..0fe7d28d4 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_oasst1_e3.py index 978622883..66681f428 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_zh_e3.py index d1524b3ea..b65874f91 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_code_alpaca_e3.py index 0c03e961a..9b9057259 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_lawyer_e3.py index 370ffcbb0..509a61819 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_512_e3.py index 8f1d4fa6b..b095e6c0b 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_e3.py index cec58460d..28af60bf1 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_open_platypus_e3.py index a19e01060..f91be8c7c 100644 --- a/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan2_13b_chat/baichuan2_13b_chat_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_e3.py index 448d4672e..a6c8aa088 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_e3.py index 5dd4c5cee..814e464f0 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_oasst1_e3.py index fb58077e6..718ac47d6 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_zh_e3.py index d79190ec0..aadd6f565 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_arxiv_gentitle_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_arxiv_gentitle_e3.py index 0aca5928c..611920eb7 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_code_alpaca_e3.py index 336e9a078..5fc3f94b0 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_colorist_e5.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_colorist_e5.py index fae416f7e..4a486ec29 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_colorist_e5.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_lawyer_e3.py index f317e5b61..2109cb984 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_512_e3.py index ccbf3b1c3..ce85eeb24 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_e3.py index ccc5e6add..f10ee3967 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_open_platypus_e3.py index fc9ab40e9..0828d8f5c 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_sql_e3.py b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_sql_e3.py index 8f9ac534f..9f7ee0022 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_sql_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_base/baichuan2_7b_base_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_e3.py index 6f5c90e00..12356c7fb 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_e3.py index 8e5304687..0eeb6b519 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py index d5f03a788..b00614c56 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_zh_e3.py index 8e59d94a7..5fa95ffa8 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_code_alpaca_e3.py index 676c2bfa0..931772a4b 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_lawyer_e3.py index c43ce574b..b256acf6d 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_512_e3.py index 4306d7a57..f40c415ad 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_e3.py index 03b37a54d..f207cbfcc 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_open_platypus_e3.py index 589a31e17..4cd2dbd41 100644 --- a/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan2_7b_chat/baichuan2_7b_chat_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_e3.py index 3ec1e4d97..9dfb527bf 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_e3.py index 04dd26a65..77dbc9d0f 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_oasst1_e3.py index 195b0d4a0..752738b82 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_zh_e3.py index afc3ccdb9..6422a3939 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_arxiv_gentitle_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_arxiv_gentitle_e3.py index cdb340186..ab36004f4 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_code_alpaca_e3.py index 83a5db2e7..3686d40c1 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_colorist_e5.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_colorist_e5.py index fb133b242..aeb5c627d 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_colorist_e5.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_lawyer_e3.py index ee4d32ba1..d216c66a1 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_medical_e1.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_medical_e1.py index 612896678..5ed18febd 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_medical_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e1.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e1.py index c06106024..1bbcdf73b 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e1.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e2_gpu8.py index 158b342c8..2e033fcde 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_all_e2_gpu8.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_plugins_e1.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_plugins_e1.py index a54741115..7bc3bccdd 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_moss_sft_plugins_e1.py @@ -113,7 +113,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_512_e3.py index ba3514fbf..207b56820 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_e3.py index ed8fdbb51..66a32dcca 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_open_platypus_e3.py index 24aa5b338..f122cf014 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_openorca_e1.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_openorca_e1.py index a7ddae0ad..5ba4c2623 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_openorca_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_sql_e3.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_sql_e3.py index 9c0b70e81..3ebf924bc 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_sql_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_tiny_codes_e1.py b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_tiny_codes_e1.py index 5366890af..dc71ebe41 100644 --- a/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_tiny_codes_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_base/baichuan_13b_base_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_e3.py index f94a54725..098d3046a 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_e3.py index 05ef453be..ce695cfea 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_oasst1_e3.py index 747fcf3e0..8fadb07d7 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_zh_e3.py index 5f8baf7ad..e5291a04c 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_arxiv_gentitle_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_arxiv_gentitle_e3.py index 62fc9e7e9..f0b3f6897 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_code_alpaca_e3.py index 86245a5df..a3efcaf24 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_colorist_e5.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_colorist_e5.py index 14a0bdcf9..ec0fdaa81 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_colorist_e5.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_lawyer_e3.py index c723e897f..4252c86c0 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_medical_e1.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_medical_e1.py index 6a7a6299d..8f170a5ee 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_medical_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_512_e3.py index 1ae252c38..05f5f9f8a 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_e3.py index 100a9a110..45994d811 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_open_platypus_e3.py index 5adda4265..0d50aaa7c 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_openorca_e1.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_openorca_e1.py index 9c0d82e98..6d62ea4bd 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_openorca_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_sql_e3.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_sql_e3.py index 64b967bdb..e0d790510 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_sql_e3.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_tiny_codes_e1.py b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_tiny_codes_e1.py index d6fb78b82..afff6d070 100644 --- a/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_tiny_codes_e1.py +++ b/xtuner/configs/baichuan/baichuan_13b_chat/baichuan_13b_chat_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_e3.py index 3f6f0d25a..909112b0f 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_e3.py index 91f538d8e..c4b3625f3 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_oasst1_e3.py index 21f22df58..8f9f4300c 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_zh_e3.py index d0d3f836a..e256b9b93 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_arxiv_gentitle_e3.py index b30bf1278..dbe7981d9 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_code_alpaca_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_code_alpaca_e3.py index c7232f30f..f9cc972d7 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_colorist_e5.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_colorist_e5.py index 4ab59797c..fde51e061 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_colorist_e5.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_lawyer_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_lawyer_e3.py index 2d568ebbe..cdfbf1f5e 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_medical_e1.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_medical_e1.py index b5f6accba..abb7abcbb 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_medical_e1.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e1.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e1.py index 2b919a46f..0465c0d8d 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e1.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e2_gpu8.py index 415a7f276..982ef68f4 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_all_e2_gpu8.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_plugins_e1.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_plugins_e1.py index 16195e5e1..5b68d4640 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_moss_sft_plugins_e1.py @@ -113,7 +113,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_512_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_512_e3.py index 0bc07e255..3e9542b30 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_e3.py index 9ec2b8eed..0c55baf61 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_open_platypus_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_open_platypus_e3.py index c96fd79e8..edcb8df03 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_openorca_e1.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_openorca_e1.py index f1a6aa1a6..bac54acc8 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_openorca_e1.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_sql_e3.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_sql_e3.py index 640f2be06..05bae7973 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_sql_e3.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_tiny_codes_e1.py b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_tiny_codes_e1.py index d4e4afc01..8ccc095e1 100644 --- a/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/baichuan/baichuan_7b/baichuan_7b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_e3.py index 8a9d36c40..cede13b3b 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_e3.py index b40e6df7e..d454d21ba 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_oasst1_e3.py index 58a043451..cdf7bcf6f 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_zh_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_zh_e3.py index 6718181f3..cf6f80c23 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_arxiv_gentitle_e3.py index cd5c9fc5c..d7e457a2d 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_code_alpaca_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_code_alpaca_e3.py index 10052e080..0172e83da 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_colorist_e5.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_colorist_e5.py index 9c7933cb1..1812a60ff 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_colorist_e5.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_lawyer_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_lawyer_e3.py index 1f1c5babe..af3769538 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_lawyer_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_medical_e1.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_medical_e1.py index 771d8885d..1686b2eee 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_medical_e1.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_512_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_512_e3.py index 5e89a823e..ac3fc08f7 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_e3.py index f57b86ee4..2aca5c4c1 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_open_platypus_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_open_platypus_e3.py index 4b82e1f2f..65222070f 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_open_platypus_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_openorca_e1.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_openorca_e1.py index 6edc5f1f4..e37657f1a 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_openorca_e1.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_sql_e3.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_sql_e3.py index 5a92db073..9546e7635 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_sql_e3.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_tiny_codes_e1.py b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_tiny_codes_e1.py index fb1582530..f96883fd7 100644 --- a/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/chatglm/chatglm2_6b/chatglm2_6b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_e3.py index 59debe384..a208943ae 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_e3.py index e53bae2f9..bb314659b 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_e3.py @@ -138,7 +138,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_oasst1_e3.py index 7164873f8..46fe7bf2f 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_enzh_oasst1_e3.py @@ -151,7 +151,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_zh_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_zh_e3.py index 128c6c2a6..060a9bff2 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_alpaca_zh_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_arxiv_gentitle_e3.py index 57000b6fa..926412e58 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_arxiv_gentitle_e3.py @@ -155,7 +155,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_code_alpaca_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_code_alpaca_e3.py index 7f9e97bae..778b77676 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_code_alpaca_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_colorist_e5.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_colorist_e5.py index 572697f1e..3b4f7a6a5 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_colorist_e5.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_colorist_e5.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_lawyer_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_lawyer_e3.py index 59fc11e33..e507657f3 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_lawyer_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_lawyer_e3.py @@ -146,7 +146,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_medical_e1.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_medical_e1.py index 3f3918063..9dee8ab3f 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_medical_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_medical_e1.py @@ -122,7 +122,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_512_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_512_e3.py index 61a6ff1d4..2da31e466 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_512_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_e3.py index bb04b5eca..e275be967 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_oasst1_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_open_platypus_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_open_platypus_e3.py index a60726746..9fff4c8a9 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_open_platypus_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_open_platypus_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_openorca_e1.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_openorca_e1.py index 7356d30bd..623a69b53 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_openorca_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_openorca_e1.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_sql_e3.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_sql_e3.py index 154a3b07c..4391f1cac 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_sql_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_sql_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_tiny_codes_e1.py b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_tiny_codes_e1.py index 4978c4053..91fc6d092 100644 --- a/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b/chatglm3_6b_qlora_tiny_codes_e1.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_e3.py index 5c3f91b3a..080185e15 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_e3.py index da55d9ff8..d64412f61 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_e3.py @@ -138,7 +138,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_oasst1_e3.py index 5b39b3727..b2735f867 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_enzh_oasst1_e3.py @@ -151,7 +151,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_zh_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_zh_e3.py index a85212686..eee7655df 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_alpaca_zh_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_arxiv_gentitle_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_arxiv_gentitle_e3.py index c826e33eb..3a0b504da 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_arxiv_gentitle_e3.py @@ -155,7 +155,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_code_alpaca_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_code_alpaca_e3.py index 43c83b7bb..f43795cb4 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_code_alpaca_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_code_alpaca_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_colorist_e5.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_colorist_e5.py index 598ad368f..3bc0707c2 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_colorist_e5.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_colorist_e5.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_lawyer_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_lawyer_e3.py index 068bff02b..c0affeec7 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_lawyer_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_lawyer_e3.py @@ -146,7 +146,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_medical_e1.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_medical_e1.py index 6a6917cea..2d8c5b2f4 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_medical_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_medical_e1.py @@ -122,7 +122,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_512_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_512_e3.py index 3ae7381e9..a05918899 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_512_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_512_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_e3.py index 3d778d348..10f7b87d3 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_oasst1_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_open_platypus_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_open_platypus_e3.py index 039ea8ef5..8dbf9c266 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_open_platypus_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_open_platypus_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_openorca_e1.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_openorca_e1.py index 42dc2e7b4..e6972dcb8 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_openorca_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_openorca_e1.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_sql_e3.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_sql_e3.py index 7c826cc76..24036dfc8 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_sql_e3.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_sql_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_tiny_codes_e1.py b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_tiny_codes_e1.py index 6ede6df61..7bbc9cfc6 100644 --- a/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_tiny_codes_e1.py +++ b/xtuner/configs/chatglm/chatglm3_6b_base/chatglm3_6b_base_qlora_tiny_codes_e1.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_e3.py index 3177a79f1..afad91f7a 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_e3.py index bff56c658..f0cf06f47 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_oasst1_e3.py index b90f78416..6e7978b9e 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_zh_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_zh_e3.py index 6e9549959..7c1d190c8 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_arxiv_gentitle_e3.py index d19c07faa..77a9ad408 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_code_alpaca_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_code_alpaca_e3.py index 6dd725fce..af2978231 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_colorist_e5.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_colorist_e5.py index e1d973138..33add41de 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_colorist_e5.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_lawyer_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_lawyer_e3.py index a804f95f3..5f5646baa 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_lawyer_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_msagent_react_e3_gpu8.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_msagent_react_e3_gpu8.py index 9f7ad3733..24d512bed 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_msagent_react_e3_gpu8.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_msagent_react_e3_gpu8.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_512_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_512_e3.py index 335fb000c..1c3dadf4b 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_e3.py index 723a51c0e..04c867648 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_open_platypus_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_open_platypus_e3.py index 10ff36983..0c22c139d 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_open_platypus_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_sql_e3.py b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_sql_e3.py index 64f142d08..b9fea2faa 100644 --- a/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_sql_e3.py +++ b/xtuner/configs/internlm/internlm_20b/internlm_20b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py index 30e20a449..966284430 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_e3.py @@ -98,7 +98,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py index 574875bce..dc1f2e69c 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_e3.py @@ -116,7 +116,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_oasst1_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_oasst1_e3.py index 78e1b0a5b..1b1274d17 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_enzh_oasst1_e3.py @@ -129,7 +129,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_zh_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_zh_e3.py index cc3777c2f..82ec21a33 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_zh_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_alpaca_zh_e3.py @@ -98,7 +98,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_oasst1_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_oasst1_e3.py index 9772f3fe7..572eb88d9 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_full_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_full_oasst1_e3.py @@ -99,7 +99,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_e3.py index c2e5aef85..858e018f7 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_e3.py index 3b6c33520..953f5138c 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_oasst1_e3.py index c9b4ff35e..a1bcdf593 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_zh_e3.py index d48c574c5..209eaf65b 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_arxiv_gentitle_e3.py index aa96320fc..0867dbe77 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_code_alpaca_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_code_alpaca_e3.py index 903c7f70c..bc0f61565 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_colorist_e5.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_colorist_e5.py index bd1a479db..bdee3f809 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_colorist_e5.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_lawyer_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_lawyer_e3.py index b41ccafbd..ef477b551 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_medical_e1.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_medical_e1.py index e8ebe9257..dd115a102 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_medical_e1.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e1.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e1.py index f96ce5f26..3d0ff0375 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e1.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e2_gpu8.py index b504535de..81c323c5e 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_all_e2_gpu8.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_plugins_e1.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_plugins_e1.py index 80f5aac57..d6890aeb2 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_moss_sft_plugins_e1.py @@ -113,7 +113,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_msagent_react_e3_gpu8.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_msagent_react_e3_gpu8.py index b0ff3d416..7966e7262 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_msagent_react_e3_gpu8.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_msagent_react_e3_gpu8.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_512_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_512_e3.py index fcefddc78..12a95e902 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_e3.py index 942a7a104..f32585ace 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_mmlu_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_mmlu_e3.py index 30d9a61a2..b09d59c86 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_mmlu_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_oasst1_mmlu_e3.py @@ -172,7 +172,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_open_platypus_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_open_platypus_e3.py index f7c4ba77e..52ac355d3 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_openorca_e1.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_openorca_e1.py index e152900f5..35574651b 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_openorca_e1.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_sql_e3.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_sql_e3.py index 9cd2273c6..f0260c907 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_sql_e3.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_tiny_codes_e1.py b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_tiny_codes_e1.py index 8c1d80151..396a35cd1 100644 --- a/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/internlm/internlm_7b/internlm_7b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_e3.py index 57ee1d888..f63278175 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_e3.py index 3144710a7..0c058efe3 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_oasst1_e3.py index 9bd50ea3f..07d474e5c 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_zh_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_zh_e3.py index aa7f853ea..ea57f0e1f 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_code_alpaca_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_code_alpaca_e3.py index 7e9b51fd8..b43604c1f 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_lawyer_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_lawyer_e3.py index c4d835ff6..fa45c3f46 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_lawyer_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_512_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_512_e3.py index f7fff8868..d1bba03c1 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_e3.py index 0f9a4c923..9ea109c74 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_open_platypus_e3.py b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_open_platypus_e3.py index f1a878a0a..6a221cafd 100644 --- a/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_open_platypus_e3.py +++ b/xtuner/configs/internlm/internlm_chat_20b/internlm_chat_20b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_e3.py index 3a0b4c397..d339e14e2 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_e3.py index 0026d5812..d27203572 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_oasst1_e3.py index b1d81c302..ec5af75ec 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_zh_e3.py index 6ac69c832..82fd330d5 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_arxiv_gentitle_e3.py index 0ba0ba2d4..576b91281 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_code_alpaca_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_code_alpaca_e3.py index 9fd8d6437..5eb79c4f7 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_colorist_e5.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_colorist_e5.py index 059bd3164..101be4357 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_colorist_e5.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_lawyer_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_lawyer_e3.py index 779bc00c6..687082987 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_medical_e1.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_medical_e1.py index 2e073201c..80551ee70 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_medical_e1.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_512_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_512_e3.py index da04f58a6..2d4d35c44 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_e3.py index cafd0724f..a285b6071 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_open_platypus_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_open_platypus_e3.py index 0f80f9a94..4bfbd9487 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_openorca_e1.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_openorca_e1.py index bc914fe42..94e7db4cd 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_openorca_e1.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_sql_e3.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_sql_e3.py index ac69c2c48..21ff6b045 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_sql_e3.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_tiny_codes_e1.py b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_tiny_codes_e1.py index b33ce7fdc..da5802bcb 100644 --- a/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/internlm/internlm_chat_7b/internlm_chat_7b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_70b/llama2_70b_int8_lora_open_platypus_e1.py b/xtuner/configs/llama/llama2_70b/llama2_70b_int8_lora_open_platypus_e1.py index 7f7a0b485..cbbe23341 100644 --- a/xtuner/configs/llama/llama2_70b/llama2_70b_int8_lora_open_platypus_e1.py +++ b/xtuner/configs/llama/llama2_70b/llama2_70b_int8_lora_open_platypus_e1.py @@ -111,7 +111,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_70b/llama2_70b_qlora_open_platypus_e1.py b/xtuner/configs/llama/llama2_70b/llama2_70b_qlora_open_platypus_e1.py index 6c8ccd1b9..3ce9275d8 100644 --- a/xtuner/configs/llama/llama2_70b/llama2_70b_qlora_open_platypus_e1.py +++ b/xtuner/configs/llama/llama2_70b/llama2_70b_qlora_open_platypus_e1.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_full_wizardlm_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_full_wizardlm_e1.py index 7a6203606..c4e557541 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_full_wizardlm_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_full_wizardlm_e1.py @@ -99,7 +99,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_e3.py index 843bfd390..4e65d8fc7 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_e3.py index b869d2bc8..79ac17d10 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_oasst1_e3.py index 3389df798..eb0276d0e 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_zh_e3.py index ee6dba9d9..025d6dbe0 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_arxiv_gentitle_e3.py index 835ee4722..96b39f7c8 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_code_alpaca_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_code_alpaca_e3.py index 0a4496372..da6ce2bbb 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_colorist_e5.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_colorist_e5.py index 231df869e..d962fcab1 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_colorist_e5.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_lawyer_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_lawyer_e3.py index cf3147d9f..08839450a 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_medical_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_medical_e1.py index aa98020c5..8baee3220 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_medical_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e1.py index 95223f9a6..c557dac6b 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e1.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e2_gpu8.py index 867f9d727..79dce953d 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_all_e2_gpu8.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_plugins_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_plugins_e1.py index 72a9639b9..ab1fe478e 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_moss_sft_plugins_e1.py @@ -113,7 +113,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_msagent_react_e3_gpu8.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_msagent_react_e3_gpu8.py index 320e705b5..ce7834d1d 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_msagent_react_e3_gpu8.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_msagent_react_e3_gpu8.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_512_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_512_e3.py index 84ee8d69a..e4642af77 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_e3.py index cdf88e60e..6e8be8ca9 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_open_platypus_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_open_platypus_e3.py index 93e3e67f9..70a391668 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_openorca_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_openorca_e1.py index e84ed750e..23ee7e592 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_openorca_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_sql_e3.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_sql_e3.py index 220515565..fc42457f4 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_sql_e3.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_tiny_codes_e1.py b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_tiny_codes_e1.py index ec95d73cf..ab3f8d17b 100644 --- a/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/llama/llama2_7b/llama2_7b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_e3.py index efbed02bc..fff24ea05 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_e3.py index aa6d16d54..df2d0b899 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py index c89e517c4..a4a181af4 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_zh_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_zh_e3.py index 4c47d9e66..5e2131498 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_arxiv_gentitle_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_arxiv_gentitle_e3.py index 88b6578e5..a78f70c0a 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_code_alpaca_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_code_alpaca_e3.py index 985348f6e..82f4b897f 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_code_alpaca_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_colorist_e5.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_colorist_e5.py index 09bc751b6..9dd3aed82 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_colorist_e5.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_lawyer_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_lawyer_e3.py index 6a0f37160..c7443ed35 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_lawyer_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_medical_e1.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_medical_e1.py index 59b01a023..534169fd7 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_medical_e1.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_512_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_512_e3.py index 3419717c6..eb9060a02 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_512_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_e3.py index d253cf892..4d32af6f1 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_open_platypus_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_open_platypus_e3.py index d4df0326a..2d8ab55f6 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_open_platypus_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_openorca_e1.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_openorca_e1.py index 942674ed3..2da66d7e8 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_openorca_e1.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_sql_e3.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_sql_e3.py index e8b544c00..3d96389b6 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_sql_e3.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_tiny_codes_e1.py b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_tiny_codes_e1.py index ed6c4d933..6d6c3386d 100644 --- a/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_tiny_codes_e1.py +++ b/xtuner/configs/llama/llama2_7b_chat/llama2_7b_chat_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_e3.py index 2366670e9..f3ed96b51 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_e3.py index d51478d37..fadabdd1c 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_oasst1_e3.py index ff02e242c..12173c911 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -150,7 +150,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_zh_e3.py index 2cdfe8ccb..c036de63f 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_alpaca_zh_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_arxiv_gentitle_e3.py index 7ada31276..12bcf9c9c 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_arxiv_gentitle_e3.py @@ -154,7 +154,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_code_alpaca_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_code_alpaca_e3.py index 3077eea3c..b70205f1a 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_code_alpaca_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_colorist_e5.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_colorist_e5.py index 8005013b7..a9a7139b9 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_colorist_e5.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_colorist_e5.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_lawyer_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_lawyer_e3.py index b54b11e56..14a746d1c 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_lawyer_e3.py @@ -145,7 +145,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_medical_e1.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_medical_e1.py index b53d972f0..c25a92c4f 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_medical_e1.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_medical_e1.py @@ -121,7 +121,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e1.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e1.py index e215dd775..c39414bfd 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e1.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e2_gpu8.py index 8e14d5439..547b3529a 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_all_e2_gpu8.py @@ -127,7 +127,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_plugins_e1.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_plugins_e1.py index 86177f9a9..69f3edae5 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_moss_sft_plugins_e1.py @@ -113,7 +113,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_512_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_512_e3.py index 2527cdda1..8bbc46986 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_512_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_e3.py index 5cbed4b10..42ef29596 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_oasst1_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_open_platypus_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_open_platypus_e3.py index 5c3f49fe4..b8e5c1b61 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_open_platypus_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_openorca_e1.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_openorca_e1.py index d814e4e4f..1eca257e6 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_openorca_e1.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_openorca_e1.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_sql_e3.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_sql_e3.py index de63c0714..d03ab0337 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_sql_e3.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_sql_e3.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/llama/llama_7b/llama_7b_qlora_tiny_codes_e1.py b/xtuner/configs/llama/llama_7b/llama_7b_qlora_tiny_codes_e1.py index c788158e4..545075069 100644 --- a/xtuner/configs/llama/llama_7b/llama_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/llama/llama_7b/llama_7b_qlora_tiny_codes_e1.py @@ -123,7 +123,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/mistral/mistral_7b_qlora_skypile_pretrain_e1.py b/xtuner/configs/mistral/mistral_7b_qlora_skypile_pretrain_e1.py index 8717b3296..2728b328e 100644 --- a/xtuner/configs/mistral/mistral_7b_qlora_skypile_pretrain_e1.py +++ b/xtuner/configs/mistral/mistral_7b_qlora_skypile_pretrain_e1.py @@ -112,7 +112,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_e3.py index 110e9201c..21d3775dc 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_e3.py index 9a0d4489f..a00056e82 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_e3.py @@ -138,7 +138,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_oasst1_e3.py index a5650a11f..63bdae5a5 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_enzh_oasst1_e3.py @@ -151,7 +151,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_zh_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_zh_e3.py index 1fd9f8099..3d2055ac8 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_alpaca_zh_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_arxiv_gentitle_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_arxiv_gentitle_e3.py index e5de6fe35..97ef25b15 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_arxiv_gentitle_e3.py @@ -155,7 +155,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_code_alpaca_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_code_alpaca_e3.py index f578621c4..0a5fa748b 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_code_alpaca_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_code_alpaca_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_colorist_e5.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_colorist_e5.py index 301dc6ea8..5e1b53847 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_colorist_e5.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_colorist_e5.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_lawyer_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_lawyer_e3.py index ff1a9c6e0..28f3e99c6 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_lawyer_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_lawyer_e3.py @@ -146,7 +146,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_medical_e1.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_medical_e1.py index 806a17bbf..35eeaa053 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_medical_e1.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_medical_e1.py @@ -122,7 +122,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e1.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e1.py index 4bd57b0aa..3d5aff48d 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e1.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e1.py @@ -128,7 +128,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e2_gpu8.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e2_gpu8.py index 14b4e1349..6c17b5253 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e2_gpu8.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_all_e2_gpu8.py @@ -128,7 +128,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_plugins_e1.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_plugins_e1.py index f2f5edd52..54b15fcce 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_plugins_e1.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_moss_sft_plugins_e1.py @@ -114,7 +114,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_512_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_512_e3.py index 85282a4cf..51bb10f92 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_512_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_512_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_e3.py index 88a052ef5..d19b60878 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_oasst1_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_open_platypus_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_open_platypus_e3.py index 8e2bac41e..a2e223a5f 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_open_platypus_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_open_platypus_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_openorca_e1.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_openorca_e1.py index f6e764a56..bc6b8731e 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_openorca_e1.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_openorca_e1.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_sql_e3.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_sql_e3.py index 04371ad95..21c90bf06 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_sql_e3.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_sql_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_tiny_codes_e1.py b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_tiny_codes_e1.py index e7416ae10..47dc564c3 100644 --- a/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_tiny_codes_e1.py +++ b/xtuner/configs/qwen/qwen_7b/qwen_7b_qlora_tiny_codes_e1.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_e3.py index d796fb8f8..5ea740bd8 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_e3.py index 1b7fe82a2..ff4aaeead 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_e3.py @@ -138,7 +138,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_oasst1_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_oasst1_e3.py index f201ff7c8..7d0023c45 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_oasst1_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_enzh_oasst1_e3.py @@ -151,7 +151,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_zh_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_zh_e3.py index 64e63fd7b..7701d165e 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_zh_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_alpaca_zh_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_arxiv_gentitle_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_arxiv_gentitle_e3.py index 6bee80e81..315378227 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_arxiv_gentitle_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_arxiv_gentitle_e3.py @@ -155,7 +155,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_code_alpaca_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_code_alpaca_e3.py index 4d540bc85..0f261aedc 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_code_alpaca_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_code_alpaca_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_colorist_e5.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_colorist_e5.py index 1d5ee97b9..50dfc050a 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_colorist_e5.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_colorist_e5.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_lawyer_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_lawyer_e3.py index 456fe4c00..8e7a12722 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_lawyer_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_lawyer_e3.py @@ -146,7 +146,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_medical_e1.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_medical_e1.py index 7a137a19c..27e62918c 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_medical_e1.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_medical_e1.py @@ -122,7 +122,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_512_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_512_e3.py index 3dad3666e..1baae8d2c 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_512_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_512_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_e3.py index 0cf0932a3..2269f062c 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_oasst1_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_open_platypus_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_open_platypus_e3.py index ae1602fd4..ccc8cc413 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_open_platypus_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_open_platypus_e3.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_openorca_e1.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_openorca_e1.py index 991b1ec5d..2ef8915ff 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_openorca_e1.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_openorca_e1.py @@ -120,7 +120,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_sql_e3.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_sql_e3.py index 79b14171b..fccb7775b 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_sql_e3.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_sql_e3.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_tiny_codes_e1.py b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_tiny_codes_e1.py index 08b2764b4..ed7a001c4 100644 --- a/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_tiny_codes_e1.py +++ b/xtuner/configs/qwen/qwen_7b_chat/qwen_7b_chat_qlora_tiny_codes_e1.py @@ -124,7 +124,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/starcoder/starcoder_qlora_stack_exchange_example.py b/xtuner/configs/starcoder/starcoder_qlora_stack_exchange_example.py index 218c1a7f3..ec6ab3ff3 100644 --- a/xtuner/configs/starcoder/starcoder_qlora_stack_exchange_example.py +++ b/xtuner/configs/starcoder/starcoder_qlora_stack_exchange_example.py @@ -128,7 +128,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/yi/yi_34b/yi_34b_qlora_alpaca_enzh_e3.py b/xtuner/configs/yi/yi_34b/yi_34b_qlora_alpaca_enzh_e3.py index 6de89fd66..e55378d3e 100644 --- a/xtuner/configs/yi/yi_34b/yi_34b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/yi/yi_34b/yi_34b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/yi/yi_6b/yi_6b_qlora_alpaca_enzh_e3.py b/xtuner/configs/yi/yi_6b/yi_6b_qlora_alpaca_enzh_e3.py index 5148a71e2..3b1b466f0 100644 --- a/xtuner/configs/yi/yi_6b/yi_6b_qlora_alpaca_enzh_e3.py +++ b/xtuner/configs/yi/yi_6b/yi_6b_qlora_alpaca_enzh_e3.py @@ -137,7 +137,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True) diff --git a/xtuner/configs/zephyr/zephyr_7b_beta_qlora_alpaca_e3.py b/xtuner/configs/zephyr/zephyr_7b_beta_qlora_alpaca_e3.py index e51c32777..04b555bc6 100644 --- a/xtuner/configs/zephyr/zephyr_7b_beta_qlora_alpaca_e3.py +++ b/xtuner/configs/zephyr/zephyr_7b_beta_qlora_alpaca_e3.py @@ -119,7 +119,7 @@ # More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 param_scheduler = dict( type=CosineAnnealingLR, - eta_min=lr * 0.1, + eta_min=0.0, by_epoch=True, T_max=max_epochs, convert_to_iter_based=True)