lucas
/
LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

remove extras

This commit is contained in:
hiyouga 2024-04-22 00:35:41 +08:00
parent 1197513a16
commit ddbd29d777
7 changed files with 0 additions and 217 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
examples/extras/MoD/sft.sh
View File

@ -1,33 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../../data \
--template default \
--finetuning_type full \
--mixture_of_depths convert \
--output_dir ../../../saves/LLaMA2-7B/mod/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 8 \
--optim paged_adamw_8bit \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--plot_loss \
--pure_bf16

35
examples/extras/badam/sft.sh
View File

@ -1,35 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../../data \
--template default \
--finetuning_type full \
--use_badam \
--badam_switch_mode descending \
--badam_switch_block_every 50 \
--badam_verbose 2 \
--output_dir ../../../saves/LLaMA2-7B/badam/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 8 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--plot_loss \
--pure_bf16

40
examples/extras/fsdp_qlora/sft.sh
View File

@ -1,40 +0,0 @@
#!/bin/bash
pip install "transformers>=4.39.1"
pip install "accelerate>=0.28.0"
pip install "bitsandbytes>=0.43.0"
CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
--config_file ../../accelerate/fsdp_config.yaml \
../../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-70b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../../data \
--template default \
--finetuning_type lora \
--lora_target q_proj,v_proj \
--output_dir ../../../saves/LLaMA2-70B/lora/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 4 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--ddp_timeout 180000000 \
--quantization_bit 4 \
--plot_loss \
--fp16

36
examples/extras/galore/sft.sh
View File

@ -1,36 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../../data \
--template default \
--finetuning_type full \
--use_galore \
--galore_layerwise \
--galore_target mlp,self_attn \
--galore_rank 128 \
--galore_scale 2.0 \
--output_dir ../../../saves/LLaMA2-7B/galore/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 1 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--plot_loss \
--pure_bf16

6
examples/extras/llama_pro/expand.sh
View File

@ -1,6 +0,0 @@
#!/bin/bash
python ../../../scripts/llama_pro.py \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--output_dir ../../../models/llama2-7b-pro \
--num_expand 8

34
examples/extras/llama_pro/sft.sh
View File

@ -1,34 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path ../../../models/llama2-7b-pro \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../../data \
--template default \
--finetuning_type freeze \
--name_module_trainable all \
--num_layer_trainable 8 \
--use_llama_pro \
--output_dir ../../../saves/LLaMA2-7B-Pro/lora/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 8 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--plot_loss \
--fp16

33
examples/extras/loraplus/sft.sh
View File

@ -1,33 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--stage sft \
--do_train \
--model_name_or_path meta-llama/Llama-2-7b-hf \
--dataset alpaca_gpt4_en,glaive_toolcall \
--dataset_dir ../../data \
--template default \
--finetuning_type lora \
--lora_target q_proj,v_proj \
--loraplus_lr_ratio 16.0 \
--output_dir ../../saves/LLaMA2-7B/loraplus/sft \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--per_device_eval_batch_size 1 \
--gradient_accumulation_steps 8 \
--lr_scheduler_type cosine \
--logging_steps 10 \
--warmup_steps 20 \
--save_steps 100 \
--eval_steps 100 \
--evaluation_strategy steps \
--load_best_model_at_end \
--learning_rate 5e-5 \
--num_train_epochs 3.0 \
--max_samples 3000 \
--val_size 0.1 \
--plot_loss \
--fp16