feat✨: 添加OLORA支持,新增训练脚本并更新现有代码以适应新配置
This commit is contained in:
@@ -18,7 +18,7 @@ accelerate launch --config_file configs/accelerate_configs/deepspeed_zero1.yaml
|
||||
--lr_scheduler_type cosine \
|
||||
--bf16 \
|
||||
--torch_dtype bfloat16 \
|
||||
--logging_steps 100 \
|
||||
--logging_steps 300 \
|
||||
--gradient_checkpointing \
|
||||
--weight_decay 0.1 \
|
||||
--eval_strategy steps \
|
||||
Executable
+25
@@ -0,0 +1,25 @@
|
||||
#!/bin/bash
|
||||
|
||||
accelerate launch --config_file configs/accelerate_configs/deepspeed_zero1.yaml train.py \
|
||||
--dataset_name textvqa \
|
||||
--use_peft \
|
||||
--peft_type OLORA \
|
||||
--model_name_or_path Qwen/Qwen2.5-Omni-3B \
|
||||
--lora_target_modules .*model\.layers.*proj\|.*merger.*0\|.*merger.*1 \
|
||||
--lora_r 8 \
|
||||
--lora_alpha 32 \
|
||||
--per_device_train_batch_size 3 \
|
||||
--per_device_eval_batch_size 1 \
|
||||
--gradient_accumulation_steps 2 \
|
||||
--num_train_epochs 1 \
|
||||
--output_dir checkpoint/qwen2_5omni_olora/ \
|
||||
--learning_rate 2e-4 \
|
||||
--warmup_ratio 0.03 \
|
||||
--lr_scheduler_type cosine \
|
||||
--bf16 \
|
||||
--torch_dtype bfloat16 \
|
||||
--logging_steps 300 \
|
||||
--gradient_checkpointing \
|
||||
--weight_decay 0.1 \
|
||||
--eval_strategy steps \
|
||||
# --resume_from_checkpoint /root/autodl-tmp/zhouyunyao/projects/CL-LMM/src/checkpoint/qwen2_5omni_moelora/checkpoint-1500
|
||||
Reference in New Issue
Block a user