Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add compute validations #2371

Merged
merged 2 commits into from
Jun 14, 2023
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,10 @@
" gpu_count_found = True\n",
"# if gpu_count_found not found, then print an error\n",
"if gpu_count_found:\n",
" print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
" print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
"else:\n",
" raise ValueError(\n",
" f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
" )\n",
"# CPU based finetune works only for single-node single-process\n",
Expand All @@ -135,6 +135,11 @@
" )\n",
" gpus_per_node = 1\n",
"\n",
"# Computes with K80 GPUs are not supported\n",
"unsupported_gpu_vm_list = [\"standard_nc6\", \"standard_nc12\", \"standard_nc24\", \"standard_nc24r\"]\n",
"if compute.size.lower() in unsupported_gpu_vm_list:\n",
" raise ValueError(f\"VM size {compute.size} is currently not supported for finetuning\")\n",
"\n",
"# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
"timestamp = str(int(time.time()))"
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -121,10 +121,10 @@
" gpu_count_found = True\n",
"# if gpu_count_found not found, then print an error\n",
"if gpu_count_found:\n",
" print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
" print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
"else:\n",
" raise ValueError(\n",
" f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
" )\n",
"# CPU based finetune works only for single-node single-process\n",
Expand All @@ -134,6 +134,11 @@
" )\n",
" gpus_per_node = 1\n",
"\n",
"# Computes with K80 GPUs are not supported\n",
"unsupported_gpu_vm_list = [\"standard_nc6\", \"standard_nc12\", \"standard_nc24\", \"standard_nc24r\"]\n",
"if compute.size.lower() in unsupported_gpu_vm_list:\n",
" raise ValueError(f\"VM size {compute.size} is currently not supported for finetuning\")\n",
"\n",
"# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
"timestamp = str(int(time.time()))"
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -122,10 +122,10 @@
" gpu_count_found = True\n",
"# if gpu_count_found not found, then print an error\n",
"if gpu_count_found:\n",
" print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
" print(f\"Number of GPU's in compute {compute.size}: {gpus_per_node}\")\n",
"else:\n",
" raise ValueError(\n",
" f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
" )\n",
"# CPU based finetune works only for single-node single-process\n",
Expand All @@ -135,6 +135,11 @@
" )\n",
" gpus_per_node = 1\n",
"\n",
"# Computes with K80 GPUs are not supported\n",
"unsupported_gpu_vm_list = [\"standard_nc6\", \"standard_nc12\", \"standard_nc24\", \"standard_nc24r\"]\n",
"if compute.size.lower() in unsupported_gpu_vm_list:\n",
" raise ValueError(f\"VM size {compute.size} is currently not supported for finetuning\")\n",
"\n",
"# generating a unique timestamp that can be used for names and versions that need to be unique\n",
"timestamp = str(int(time.time()))"
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,7 @@
" print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
"else:\n",
" raise ValueError(\n",
" f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
" )\n",
"# CPU based finetune works only for single-node single-process\n",
Expand All @@ -135,6 +135,11 @@
" )\n",
" gpus_per_node = 1\n",
"\n",
"# Computes with K80 GPUs are not supported\n",
"unsupported_gpu_vm_list = [\"standard_nc6\", \"standard_nc12\", \"standard_nc24\", \"standard_nc24r\"]\n",
"if compute.size.lower() in unsupported_gpu_vm_list:\n",
" raise ValueError(f\"VM size {compute.size} is currently not supported for finetuning\")\n",
"\n",
"# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
"timestamp = str(int(time.time()))"
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -124,7 +124,7 @@
" print(f\"Number of GPU's in copute {compute.size}: {gpus_per_node}\")\n",
"else:\n",
" raise ValueError(\n",
" f\"Number of GPU's in copute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"Number of GPU's in compute {compute.size} not found. Available skus are: {available_sku_sizes}.\"\n",
" f\"This should not happen. Please check the selected compute cluster: {compute_cluster} and try again.\"\n",
" )\n",
"# CPU based finetune works only for single-node single-process\n",
Expand All @@ -134,6 +134,11 @@
" )\n",
" gpus_per_node = 1\n",
"\n",
"# Computes with K80 GPUs are not supported\n",
"unsupported_gpu_vm_list = [\"standard_nc6\", \"standard_nc12\", \"standard_nc24\", \"standard_nc24r\"]\n",
"if compute.size.lower() in unsupported_gpu_vm_list:\n",
" raise ValueError(f\"VM size {compute.size} is currently not supported for finetuning\")\n",
"\n",
"# genrating a unique timestamp that can be used for names and versions that need to be unique\n",
"timestamp = str(int(time.time()))"
]
Expand Down
Loading