Skip to content

Commit

Permalink
wip: hub_token error
Browse files Browse the repository at this point in the history
  • Loading branch information
@mahdikhashan
mahdikhashan committed Jan 16, 2025
1 parent f23f5ea commit d33dd00
Showing 1 changed file with 14 additions and 14 deletions.
28 changes: 14 additions & 14 deletions examples/v1beta1/sdk/llm-hp-optimization.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -226,8 +226,8 @@
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-16T14:19:59.810915Z",
"start_time": "2025-01-16T14:19:59.739935Z"
"end_time": "2025-01-16T14:21:47.465728Z",
"start_time": "2025-01-16T14:21:47.429577Z"
}
},
"cell_type": "code",
Expand All @@ -247,13 +247,13 @@
"hf_tuning_parameters = HuggingFaceTrainerParams(\n",
" training_parameters = TrainingArguments(\n",
" output_dir = \"results\",\n",
" save_strategy = \"no\",\n",
" save_strategy = \"epoch\",\n",
" learning_rate = 1e-05, #katib.search.double(min=1e-05, max=5e-05),\n",
" num_train_epochs=3,\n",
" ),\n",
" # Set LoRA config to reduce number of trainable model parameters.\n",
" lora_config = LoraConfig(\n",
" r = 1 ,# katib.search.int(min=8, max=32),\n",
" r = 1,# katib.search.int(min=8, max=32),\n",
" lora_alpha = 8,\n",
" lora_dropout = 0.1,\n",
" bias = \"none\",\n",
Expand All @@ -262,26 +262,26 @@
],
"id": "45c5a2476e1bffb7",
"outputs": [],
"execution_count": 35
"execution_count": 44
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-16T14:20:00.485519Z",
"start_time": "2025-01-16T14:20:00.414142Z"
"end_time": "2025-01-16T14:21:48.609074Z",
"start_time": "2025-01-16T14:21:48.408780Z"
}
},
"cell_type": "code",
"source": "cl = KatibClient(namespace=\"kubeflow\")",
"id": "c7995d6934399e6c",
"outputs": [],
"execution_count": 36
"execution_count": 45
},
{
"metadata": {
"ExecuteTime": {
"end_time": "2025-01-16T14:20:09.331479Z",
"start_time": "2025-01-16T14:20:09.033401Z"
"end_time": "2025-01-16T14:22:02.371604Z",
"start_time": "2025-01-16T14:22:02.030931Z"
}
},
"cell_type": "code",
Expand All @@ -296,8 +296,8 @@
" objective_metric_name = \"train_loss\",\n",
" objective_type = \"minimize\",\n",
" algorithm_name = \"random\",\n",
" max_trial_count = 10,\n",
" parallel_trial_count = 2,\n",
" # max_trial_count = 10,\n",
" # parallel_trial_count = 2,\n",
" # resources_per_trial={\n",
" # \"gpu\": \"2\",\n",
" # \"cpu\": \"4\",\n",
Expand Down Expand Up @@ -330,7 +330,7 @@
"\u001B[0;31mValueError\u001B[0m: '<HUB_TOKEN>' is not a valid HubStrategy",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001B[0;31mValueError\u001B[0m Traceback (most recent call last)",
"Cell \u001B[0;32mIn[38], line 3\u001B[0m\n\u001B[1;32m 1\u001B[0m \u001B[38;5;66;03m# Fine-tuning for Binary Classification\u001B[39;00m\n\u001B[1;32m 2\u001B[0m exp_name \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mtestllm\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m----> 3\u001B[0m \u001B[43mcl\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtune\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 4\u001B[0m \u001B[43m \u001B[49m\u001B[43mname\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mexp_name\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 5\u001B[0m \u001B[43m \u001B[49m\u001B[43mmodel_provider_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_model\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 6\u001B[0m \u001B[43m \u001B[49m\u001B[43mdataset_provider_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_dataset\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 7\u001B[0m \u001B[43m \u001B[49m\u001B[43mtrainer_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_tuning_parameters\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 8\u001B[0m \u001B[43m \u001B[49m\u001B[43mobjective_metric_name\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtrain_loss\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 9\u001B[0m \u001B[43m \u001B[49m\u001B[43mobjective_type\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mminimize\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 10\u001B[0m \u001B[43m \u001B[49m\u001B[43malgorithm_name\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrandom\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 11\u001B[0m \u001B[43m \u001B[49m\u001B[43mmax_trial_count\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;241;43m10\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 12\u001B[0m \u001B[43m \u001B[49m\u001B[43mparallel_trial_count\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;241;43m2\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 13\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# resources_per_trial={\u001B[39;49;00m\n\u001B[1;32m 14\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"gpu\": \"2\",\u001B[39;49;00m\n\u001B[1;32m 15\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"cpu\": \"4\",\u001B[39;49;00m\n\u001B[1;32m 16\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"memory\": \"10G\",\u001B[39;49;00m\n\u001B[1;32m 17\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# },\u001B[39;49;00m\n\u001B[1;32m 18\u001B[0m \u001B[43m)\u001B[49m\n\u001B[1;32m 20\u001B[0m cl\u001B[38;5;241m.\u001B[39mwait_for_experiment_condition(name\u001B[38;5;241m=\u001B[39mexp_name)\n\u001B[1;32m 22\u001B[0m \u001B[38;5;66;03m# Get the best hyperparameters.\u001B[39;00m\n",
"Cell \u001B[0;32mIn[47], line 3\u001B[0m\n\u001B[1;32m 1\u001B[0m \u001B[38;5;66;03m# Fine-tuning for Binary Classification\u001B[39;00m\n\u001B[1;32m 2\u001B[0m exp_name \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mtestllm\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[0;32m----> 3\u001B[0m \u001B[43mcl\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtune\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 4\u001B[0m \u001B[43m \u001B[49m\u001B[43mname\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mexp_name\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 5\u001B[0m \u001B[43m \u001B[49m\u001B[43mmodel_provider_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_model\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 6\u001B[0m \u001B[43m \u001B[49m\u001B[43mdataset_provider_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_dataset\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 7\u001B[0m \u001B[43m \u001B[49m\u001B[43mtrainer_parameters\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[43mhf_tuning_parameters\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 8\u001B[0m \u001B[43m \u001B[49m\u001B[43mobjective_metric_name\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mtrain_loss\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 9\u001B[0m \u001B[43m \u001B[49m\u001B[43mobjective_type\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mminimize\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 10\u001B[0m \u001B[43m \u001B[49m\u001B[43malgorithm_name\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43m \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrandom\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m 11\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# max_trial_count = 10,\u001B[39;49;00m\n\u001B[1;32m 12\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# parallel_trial_count = 2,\u001B[39;49;00m\n\u001B[1;32m 13\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# resources_per_trial={\u001B[39;49;00m\n\u001B[1;32m 14\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"gpu\": \"2\",\u001B[39;49;00m\n\u001B[1;32m 15\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"cpu\": \"4\",\u001B[39;49;00m\n\u001B[1;32m 16\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# \"memory\": \"10G\",\u001B[39;49;00m\n\u001B[1;32m 17\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;66;43;03m# },\u001B[39;49;00m\n\u001B[1;32m 18\u001B[0m \u001B[43m)\u001B[49m\n\u001B[1;32m 20\u001B[0m cl\u001B[38;5;241m.\u001B[39mwait_for_experiment_condition(name\u001B[38;5;241m=\u001B[39mexp_name)\n\u001B[1;32m 22\u001B[0m \u001B[38;5;66;03m# Get the best hyperparameters.\u001B[39;00m\n",
"File \u001B[0;32m~/miniconda3/envs/llm-hp-optimization-katib-nb/lib/python3.9/site-packages/kubeflow/katib/api/katib_client.py:602\u001B[0m, in \u001B[0;36mKatibClient.tune\u001B[0;34m(self, name, model_provider_parameters, dataset_provider_parameters, trainer_parameters, storage_config, objective, base_image, parameters, namespace, env_per_trial, algorithm_name, algorithm_settings, objective_metric_name, additional_metric_names, objective_type, objective_goal, max_trial_count, parallel_trial_count, max_failed_trial_count, resources_per_trial, retain_trials, packages_to_install, pip_index_url, metrics_collector_config)\u001B[0m\n\u001B[1;32m 600\u001B[0m experiment_params \u001B[38;5;241m=\u001B[39m []\n\u001B[1;32m 601\u001B[0m trial_params \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m--> 602\u001B[0m training_args \u001B[38;5;241m=\u001B[39m \u001B[43mutils\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_trial_substitutions_from_trainer\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m 603\u001B[0m \u001B[43m \u001B[49m\u001B[43mtrainer_parameters\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtraining_parameters\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mexperiment_params\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mtrial_params\u001B[49m\n\u001B[1;32m 604\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 605\u001B[0m lora_config \u001B[38;5;241m=\u001B[39m utils\u001B[38;5;241m.\u001B[39mget_trial_substitutions_from_trainer(\n\u001B[1;32m 606\u001B[0m trainer_parameters\u001B[38;5;241m.\u001B[39mlora_config, experiment_params, trial_params\n\u001B[1;32m 607\u001B[0m )\n\u001B[1;32m 609\u001B[0m \u001B[38;5;66;03m# Create the init and the primary container.\u001B[39;00m\n",
"File \u001B[0;32m~/miniconda3/envs/llm-hp-optimization-katib-nb/lib/python3.9/site-packages/kubeflow/katib/utils/utils.py:207\u001B[0m, in \u001B[0;36mget_trial_substitutions_from_trainer\u001B[0;34m(parameters, experiment_params, trial_params)\u001B[0m\n\u001B[1;32m 205\u001B[0m value \u001B[38;5;241m=\u001B[39m copy\u001B[38;5;241m.\u001B[39mdeepcopy(p_value)\n\u001B[1;32m 206\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m--> 207\u001B[0m value \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mtype\u001B[39;49m\u001B[43m(\u001B[49m\u001B[43mold_attr\u001B[49m\u001B[43m)\u001B[49m\u001B[43m(\u001B[49m\u001B[43mp_value\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 208\u001B[0m \u001B[38;5;28msetattr\u001B[39m(parameters, p_name, value)\n\u001B[1;32m 210\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(parameters, TrainingArguments):\n",
"File \u001B[0;32m~/miniconda3/envs/llm-hp-optimization-katib-nb/lib/python3.9/enum.py:384\u001B[0m, in \u001B[0;36mEnumMeta.__call__\u001B[0;34m(cls, value, names, module, qualname, type, start)\u001B[0m\n\u001B[1;32m 359\u001B[0m \u001B[38;5;250m\u001B[39m\u001B[38;5;124;03m\"\"\"\u001B[39;00m\n\u001B[1;32m 360\u001B[0m \u001B[38;5;124;03mEither returns an existing member, or creates a new enum class.\u001B[39;00m\n\u001B[1;32m 361\u001B[0m \n\u001B[0;32m (...)\u001B[0m\n\u001B[1;32m 381\u001B[0m \u001B[38;5;124;03m`type`, if set, will be mixed in as the first base class.\u001B[39;00m\n\u001B[1;32m 382\u001B[0m \u001B[38;5;124;03m\"\"\"\u001B[39;00m\n\u001B[1;32m 383\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m names \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m: \u001B[38;5;66;03m# simple value lookup\u001B[39;00m\n\u001B[0;32m--> 384\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mcls\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[38;5;21;43m__new__\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mcls\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mvalue\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 385\u001B[0m \u001B[38;5;66;03m# otherwise, functional API: we're creating a new Enum type\u001B[39;00m\n\u001B[1;32m 386\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mcls\u001B[39m\u001B[38;5;241m.\u001B[39m_create_(\n\u001B[1;32m 387\u001B[0m value,\n\u001B[1;32m 388\u001B[0m names,\n\u001B[0;32m (...)\u001B[0m\n\u001B[1;32m 392\u001B[0m start\u001B[38;5;241m=\u001B[39mstart,\n\u001B[1;32m 393\u001B[0m )\n",
Expand All @@ -341,7 +341,7 @@
]
}
],
"execution_count": 38
"execution_count": 47
},
{
"metadata": {},
Expand Down

0 comments on commit d33dd00

Please sign in to comment.