History

Wenhao Chen 7b9b86441f [chat]: update rm, add wandb and fix bugs (#4471 ) * feat: modify forward fn of critic and reward model * feat: modify calc_action_log_probs * to: add wandb in sft and rm trainer * feat: update train_sft * feat: update train_rm * style: modify type annotation and add warning * feat: pass tokenizer to ppo trainer * to: modify trainer base and maker base * feat: add wandb in ppo trainer * feat: pass tokenizer to generate * test: update generate fn tests * test: update train tests * fix: remove action_mask * feat: remove unused code * fix: fix wrong ignore_index * fix: fix mock tokenizer * chore: update requirements * revert: modify make_experience * fix: fix inference * fix: add padding side * style: modify _on_learn_batch_end * test: use mock tokenizer * fix: use bf16 to avoid overflow * fix: fix workflow * [chat] fix gemini strategy * [chat] fix * sync: update colossalai strategy * fix: fix args and model dtype * fix: fix checkpoint test * fix: fix requirements * fix: fix missing import and wrong arg * fix: temporarily skip gemini test in stage 3 * style: apply pre-commit * fix: temporarily skip gemini test in stage 1&2 --------- Co-authored-by: Mingyan Jiang <1829166702@qq.com>		2023-09-20 15:53:58 +08:00
..
ray	[misc] update pre-commit and run all files (#4752 )	2023-09-19 14:20:26 +08:00
README.md	[doc] update Coati README (#4405 )	2023-08-14 15:26:27 +08:00
benchmark_opt_lora_dummy.py	[chat]: update rm, add wandb and fix bugs (#4471 )	2023-09-20 15:53:58 +08:00

README.md

Benchmarks

Benchmark OPT with LoRA on dummy prompt data

We provide various OPT models (string in parentheses is the corresponding model name used in this script):

OPT-125M (125m)
OPT-350M (350m)
OPT-700M (700m)
OPT-1.3B (1.3b)
OPT-2.7B (2.7b)
OPT-3.5B (3.5b)
OPT-5.5B (5.5b)
OPT-6.7B (6.7b)
OPT-10B (10b)
OPT-13B (13b)

We also provide various training strategies:

ddp: torch DDP
colossalai_gemini: ColossalAI GeminiDDP with placement_policy="cuda", like zero3
colossalai_gemini_cpu: ColossalAI GeminiDDP with placement_policy="cpu", like zero3-offload
colossalai_zero2: ColossalAI zero2
colossalai_zero2_cpu: ColossalAI zero2-offload
colossalai_zero1: ColossalAI zero1
colossalai_zero1_cpu: ColossalAI zero1-offload

We only support torchrun to launch now. E.g.

# run OPT-125M with no lora (lora_rank=0) on single-node single-GPU with min batch size
torchrun --standalone --nproc_per_node 1 benchmark_opt_lora_dummy.py \
    --model 125m --critic_model 125m --strategy ddp \
    --experience_batch_size 1 --train_batch_size 1 --lora_rank 0
# run Actor (OPT-1.3B) and Critic (OPT-350M) with lora_rank=4 on single-node 4-GPU
torchrun --standalone --nproc_per_node 4 benchmark_opt_lora_dummy.py \
    --model 1.3b --critic_model 350m --strategy colossalai_zero2 --lora_rank 4