ColossalAI/applications/Chat/examples

Examples

Install requirements

pip install -r requirements.txt

Train the reward model (Stage 2)

Use these code to train your reward model.

# Take naive reward model training with opt-350m as example
python train_reward_model.py --pretrain "facebook/opt-350m" --model 'opt' --strategy naive
# use colossalai_zero2
torchrun --standalone --nproc_per_node=2 train_reward_model.py --pretrain "facebook/opt-350m" --model 'opt' --strategy colossalai_zero2

Features and tricks in RM training

• We support Anthropic/hh-rlhfandrm-static datasets.
• We support 2 kinds of loss_function named 'log_sig'(used by OpenAI) and 'log_exp'(used by Anthropic).
• We change the loss to valid_acc and pair_dist to monitor progress during training.
• We add special token to the end of the sequence to get better result.
• We use cosine-reducing lr-scheduler for RM training.
• We set value_head as 1 liner layer and initialize the weight of value_head using N(0，1/(d_model + 1)) distribution.
• We train a Bloom-560m reward model for 1 epoch and find the test acc of the model achieve the performance mentions in Anthropics paper.

Experiment result

Model performance in Anthropics paper:

Our training & test result of bloom-560m for 1 epoch:

Train with dummy prompt data (Stage 3)

This script supports 4 kinds of strategies:

• naive
• ddp
• colossalai_zero2
• colossalai_gemini

It uses random generated prompt data.

Naive strategy only support single GPU training:

python train_dummy.py --strategy naive
# display cli help
python train_dummy.py -h

DDP strategy and ColossalAI strategy support multi GPUs training:

# run DDP on 2 GPUs
torchrun --standalone --nproc_per_node=2 train_dummy.py --strategy ddp
# run ColossalAI on 2 GPUs
torchrun --standalone --nproc_per_node=2 train_dummy.py --strategy colossalai_zero2

Train with real prompt data (Stage 3)

We use awesome-chatgpt-prompts as example dataset. It is a small dataset with hundreds of prompts.

You should download prompts.csv first.

This script also supports 4 strategies.

# display cli help
python train_dummy.py -h
# run naive on 1 GPU
python train_prompts.py prompts.csv --strategy naive
# run DDP on 2 GPUs
torchrun --standalone --nproc_per_node=2 train_prompts.py prompts.csv --strategy ddp
# run ColossalAI on 2 GPUs
torchrun --standalone --nproc_per_node=2 train_prompts.py prompts.csv --strategy colossalai_zero2

Inference example(After Stage3)

We support naive inference demo after training.

# inference, using pretrain path to configure model
python inference.py --model_path <your actor model path> --model <your model type> --pretrain <your pretrain model name/path>
# example
python inference.py --model_path ./actor_checkpoint_prompts.pt --pretrain bigscience/bloom-560m --model bloom

Attention

The examples is just a demo for testing our progress of RM and PPO training.

data

• rm-static
• hh-rlhf
• openai/summarize_from_feedback
• openai/webgpt_comparisons
• Dahoas/instruct-synthetic-prompt-responses

Support Model

GPT

• GPT2-S (s)
• GPT2-M (m)
• GPT2-L (l)
• GPT2-XL (xl)
• GPT2-4B (4b)
• GPT2-6B (6b)
• GPT2-8B (8b)
• GPT2-10B (10b)
• GPT2-12B (12b)
• GPT2-15B (15b)
• GPT2-18B (18b)
• GPT2-20B (20b)
• GPT2-24B (24b)
• GPT2-28B (28b)
• GPT2-32B (32b)
• GPT2-36B (36b)
• GPT2-40B (40b)
• GPT3 (175b)

BLOOM

• BLOOM-560m
• BLOOM-1b1
• BLOOM-3b
• BLOOM-7b
• BLOOM-175b

OPT

• OPT-125M
• OPT-350M
• OPT-1.3B
• OPT-2.7B
• OPT-6.7B
• OPT-13B
• OPT-30B