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

update examples

Browse Source 
Former-commit-id: 194e25606515bfa42c3be27d68f68d604191514b
This commit is contained in:
hiyouga
2024-03-06 13:14:57 +08:00
parent 3168abc0a1
commit 6b407092d9
13 changed files with 124 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/lora_single_gpu/dpo.sh
View File

@@ -15,11 +15,13 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--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 \

1
examples/lora_single_gpu/ppo.sh
View File

@@ -16,6 +16,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 512 \
--preprocessing_num_workers 16 \
--per_device_train_batch_size 1 \
--gradient_accumulation_steps 8 \
--lr_scheduler_type cosine \

1
examples/lora_single_gpu/predict.sh
View File

@@ -13,6 +13,7 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--overwrite_cache \
--overwrite_output_dir \
--cutoff_len 1024 \
--preprocessing_num_workers 16 \
--per_device_eval_batch_size 1 \
--max_samples 20 \
--predict_with_generate

2
examples/lora_single_gpu/pretrain.sh
View File

@@ -12,11 +12,13 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--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 \

2
examples/lora_single_gpu/reward.sh
View File

@@ -15,11 +15,13 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--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 \

2
examples/lora_single_gpu/sft.sh
View File

@@ -13,11 +13,13 @@ CUDA_VISIBLE_DEVICES=0 python ../../src/train_bash.py \
--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 \