[ColossalChat] Hotfix for ColossalChat (#5910)

* add ignore and tiny llama

* fix path issue

* run style

* fix issue

* update bash

* add ignore and tiny llama

* fix path issue

* run style

* fix issue

* update bash

* fix ddp issue

* add Qwen 1.5 32B
This commit is contained in:
Tong Li
2024-07-19 13:40:07 +08:00
committed by GitHub
parent 8cc8f645cd
commit f585d4e38e
11 changed files with 42 additions and 30 deletions

View File

@@ -15,10 +15,9 @@ set_n_least_used_CUDA_VISIBLE_DEVICES() {
}
set_n_least_used_CUDA_VISIBLE_DEVICES 8
PROJECT_NAME="ppo"
PROJECT_NAME="PPO"
PARENT_SAVE_DIR="" # Path to a folder to save checkpoints
PARENT_TENSORBOARD_DIR="" # Path to a folder to save logs
PARENT_CONFIG_FILE="" # Path to a folder to save training config logs
PRETRAINED_MODEL_PATH="" # local pretrained model path (from RLHF step 1: SFT)
PRETRAINED_TOKENIZER_PATH="" # huggingface or local tokenizer path
@@ -54,7 +53,7 @@ declare -a ptx_dataset=(
TIMESTAMP=$(date +%Y-%m-%d-%H-%M-%S)
FULL_PROJECT_NAME="${PROJECT_NAME}-${TIMESTAMP}"
SAVE_DIR="${PARENT_SAVE_DIR}${FULL_PROJECT_NAME}"
CONFIG_FILE="${PARENT_CONFIG_FILE}-${FULL_PROJECT_NAME}.json"
CONFIG_FILE="${PARENT_CONFIG_FILE}${FULL_PROJECT_NAME}.json"
colossalai run --nproc_per_node 8 --hostfile hostfile --master_port 31312 train_ppo.py \
--pretrain $PRETRAINED_MODEL_PATH \