From 64b0c2eb71c68fba0bca7306eca6e7839657193b Mon Sep 17 00:00:00 2001 From: Apoorv Khandelwal Date: Mon, 17 Mar 2025 19:37:31 -0400 Subject: [PATCH 1/2] Update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 969d2a5..b1d342a 100644 --- a/README.md +++ b/README.md @@ -70,10 +70,10 @@ We can distribute and run this function (e.g. on 2 machines x 2 GPUs) using **`t ```python import logging -logging.basicConfig(level=logging.INFO) - import torchrunx +logging.basicConfig(level=logging.INFO) + launcher = torchrunx.Launcher( hostnames = ["localhost", "second_machine"], # or IP addresses workers_per_host = 2 # e.g. number of GPUs per host @@ -93,7 +93,7 @@ trained_model: nn.Module = results.rank(0) # or: results.index(hostname="localhost", local_rank=0) # and continue your script -torch.save(trained_model.state_dict(), "output/model.pth") +torch.save(trained_model.state_dict(), "outputs/model.pth") ``` **See more examples where we fine-tune LLMs using:** From 44446340838d62e1996c716919b0b836554ba143 Mon Sep 17 00:00:00 2001 From: Apoorv Khandelwal Date: Mon, 17 Mar 2025 19:38:41 -0400 Subject: [PATCH 2/2] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index b1d342a..88b720d 100644 --- a/README.md +++ b/README.md @@ -76,7 +76,7 @@ logging.basicConfig(level=logging.INFO) launcher = torchrunx.Launcher( hostnames = ["localhost", "second_machine"], # or IP addresses - workers_per_host = 2 # e.g. number of GPUs per host + workers_per_host = "gpu" # default, or just: 2 ) results = launcher.run(