From 3652f9783c63b4a3ced5acf9217a113bb0f93310 Mon Sep 17 00:00:00 2001 From: ChenQiaoling00 Date: Wed, 12 Jul 2023 18:57:32 +0800 Subject: [PATCH] fix/fix_submodule_err --- doc/en/usage.md | 4 ++-- doc/usage.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/doc/en/usage.md b/doc/en/usage.md index d6adf9f..b0fec39 100644 --- a/doc/en/usage.md +++ b/doc/en/usage.md @@ -192,7 +192,7 @@ $ srun -p internllm -N 2 -n 16 --ntasks-per-node=8 --gpus-per-task=1 python trai If you want to start distributed training on torch with 8 GPUs on a single node, use the following command: ```bash -$ torchrun --nnodes=1 --nproc_per_node=8 train.py --config ./configs/7B_sft.py +$ torchrun --nnodes=1 --nproc_per_node=8 train.py --config ./configs/7B_sft.py --launcher "torch" ``` ### Training Results @@ -217,4 +217,4 @@ Taking the configuration of the demo training on a single machine with 8 GPUs on 2023-07-07 12:29:09,307 INFO train.py:323 in record_current_batch_training_metrics -- tflops=188.8613541410694,step=3,loss=11.099515914916992,tgs (tokens/gpu/second)=4252.55,lr=1.0000000000000002e-06,loss_scale=65536.0,grad_norm=63.5478796484391,micro_num=4,num_consumed_tokens=524288,inf_nan_skip_batches=0,num_samples_in_batch=16,largest_length=2048,largest_batch=5,smallest_batch=3,adam_beta2=0.95,fwd_bwd_time=3.7 2023-07-07 12:29:13,147 INFO train.py:323 in record_current_batch_training_metrics -- tflops=189.65918563194305,step=4,loss=10.149517059326172,tgs (tokens/gpu/second)=4270.52,lr=1.2000000000000002e-06,loss_scale=65536.0,grad_norm=51.582841631508145,micro_num=4,num_consumed_tokens=655360,inf_nan_skip_batches=0,num_samples_in_batch=19,largest_length=2048,largest_batch=6,smallest_batch=3,adam_beta2=0.95,fwd_bwd_time=3.68 2023-07-07 12:29:16,994 INFO train.py:323 in record_current_batch_training_metrics -- tflops=189.3109313713174,step=5,loss=9.822169303894043,tgs (tokens/gpu/second)=4262.67,lr=1.4000000000000001e-06,loss_scale=65536.0,grad_norm=47.10386835560855,micro_num=4,num_consumed_tokens=786432,inf_nan_skip_batches=0,num_samples_in_batch=17,largest_length=2048,largest_batch=6,smallest_batch=3,adam_beta2=0.95,fwd_bwd_time=3.69 -``` \ No newline at end of file +``` diff --git a/doc/usage.md b/doc/usage.md index d6e85ae..ef173ac 100644 --- a/doc/usage.md +++ b/doc/usage.md @@ -175,7 +175,7 @@ $ srun -p internllm -N 2 -n 16 --ntasks-per-node=8 --gpus-per-task=1 python trai 若在 torch 上启动分布式运行环境，单节点 8 卡的运行命令如下所示： ```bash -$ torchrun --nnodes=1 --nproc_per_node=8 train.py --config ./configs/7B_sft.py +$ torchrun --nnodes=1 --nproc_per_node=8 train.py --config ./configs/7B_sft.py --launcher "torch" ``` ### 运行结果