Example of using dice updated

dice-group · Oct 16, 2023 · f7baf63 · f7baf63
1 parent f81a27d
commit f7baf63
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -100,6 +100,12 @@ Models can be easily trained in a single node multi-gpu setting
 ```bash
 dice --accelerator "gpu" --strategy "ddp" --dataset_dir "KGs/UMLS" --model Keci --eval_model "train_val_test" 
 ```
+Similarly, models can be easily trained in a multi-node multi-gpu setting
+```bash
+torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 0 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.run --trainer torchDDP --dataset_dir KGs/UMLS
+torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 1 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.run --trainer torchDDP --dataset_dir KGs/UMLS
+```
+
 Train a KGE model by providing the path of a single file and store all parameters under newly created directory
 called `KeciFamilyRun`.
 ```bash

diff --git a/docs/index.rst b/docs/index.rst
@@ -19,16 +19,16 @@ Welcome to DICE Embeddings!
    .. code-block:: bash
 
       // 1 CPU
-      (dicee) $ python -m dicee.run --path_dataset_folder KGs/UMLS
+      (dicee) $ dice --dataset_dir KGs/UMLS
       // 10 CPU
-      (dicee) $ python -m dicee.run --path_dataset_folder KGs/UMLS --num_core 10
+      (dicee) $ dice --dataset_dir KGs/UMLS --num_core 10
       // Distributed Data Parallel (DDP) with all GPUs
-      (dicee) $ python -m dicee.run --trainer PL --accelerator gpu --strategy ddp --path_dataset_folder KGs/UMLS
+      (dicee) $ dice --trainer PL --accelerator gpu --strategy ddp --dataset_dir KGs/UMLS
       // Model Parallel with all GPUs and low precision
-      (dicee) $ python -m dicee.run --trainer PL --accelerator gpu --strategy deepspeed_stage_3 --path_dataset_folder KGs/UMLS --precision 16
+      (dicee) $ dice --trainer PL --accelerator gpu --strategy deepspeed_stage_3 --dataset_dir KGs/UMLS --precision 16
       // DDP with all GPUs on two nodes (felis and nebula):
-      (dicee) cdemir@felis  $ torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 0 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.main --trainer torchDDP --path_dataset_folder KGs/UMLS
-      (dicee) cdemir@nebula $ torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 1 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.main --trainer torchDDP --path_dataset_folder KGs/UMLS
+      (dicee) cdemir@felis  $ torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 0 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.run --trainer torchDDP --dataset_dir KGs/UMLS
+      (dicee) cdemir@nebula $ torchrun --nnodes 2 --nproc_per_node=gpu  --node_rank 1 --rdzv_id 455 --rdzv_backend c10d --rdzv_endpoint=nebula -m dicee.run --trainer torchDDP --dataset_dir KGs/UMLS
 
 .. toctree::
    :maxdepth: 2