add: add include_num_input_tokens_seen

This commit is contained in:
wql 2024-08-20 09:42:58 +08:00
parent d3f91c8e2f
commit c93a5b8b8f
1 changed files with 41 additions and 0 deletions

View File

@ -0,0 +1,41 @@
### model
model_name_or_path: modelscope/Llama-2-7b-ms
### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all
### dataset
dataset: identity,alpaca_en_demo
template: llama2
cutoff_len: 1024
max_samples: 10000
overwrite_cache: true
preprocessing_num_workers: 16
### output
output_dir: ./results/lora_sft/Llama2-7B_2/llama2_lora_sft_1_test_token
logging_steps: 3
save_steps: 100
plot_loss: true
overwrite_output_dir: true
### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
learning_rate: 1.0e-4
num_train_epochs: 10.0
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: true
ddp_timeout: 180000000
max_steps: 100
include_num_input_tokens_seen: true
### eval
val_size: 0.1
per_device_eval_batch_size: 2
eval_strategy: steps
eval_steps: 500