Skip to content

Commit

Permalink
removed logs from rag and reverted the community_lm notebook to match…
Browse files Browse the repository at this point in the history 
… the main branch
  • Loading branch information
@mihir86
mihir86 committed Dec 9, 2024
1 parent c49f776 commit ef90ba7
Show file tree
Hide file tree
Showing 2 changed files with 34 additions and 4,497 deletions.
201 changes: 20 additions & 181 deletions examples/community_lm/community_lm.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,20 +20,20 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "29563e5d-41b0-4f89-8d8b-a54b40f8dfb7",
"metadata": {},
"outputs": [],
"source": [
"from llments.lm.base.hugging_face import HuggingFaceLM, HuggingFaceLMFitter\n",
"# from llments.lm.base.empirical import load_from_text_file\n",
"from llments.lm.base.empirical import load_from_text_file\n",
"from llments.eval.sentiment import HuggingFaceSentimentEvaluator\n",
"import pandas as pd\n",
"import numpy as np\n",
"from examples.community_lm.community_lm_constants import politician_feelings, groups_feelings, anes_df\n",
"from examples.community_lm.community_lm_utils import generate_community_opinion, compute_group_stance\n",
"from community_lm_constants import politician_feelings, groups_feelings, anes_df\n",
"from community_lm_utils import generate_community_opinion, compute_group_stance\n",
"\n",
"device = 'cuda' # change to 'mps' if you have a mac, or 'cuda:0' if you have an NVIDIA GPU "
"device = 'mps' # change to 'mps' if you have a mac, or 'cuda:0' if you have an NVIDIA GPU "
]
},
{
Expand Down Expand Up @@ -101,172 +101,7 @@
"execution_count": null,
"id": "d2049390",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Some weights of the model checkpoint at cardiffnlp/twitter-roberta-base-sentiment-latest were not used when initializing RobertaForSequenceClassification: ['roberta.pooler.dense.bias', 'roberta.pooler.dense.weight']\n",
"- This IS expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
"- This IS NOT expected if you are initializing RobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing run_1 ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processing questions: 33%|███▎ | 10/30 [00:37<01:22, 4.14s/it]--- Logging error ---\n",
"Traceback (most recent call last):\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/logging/__init__.py\", line 1110, in emit\n",
" msg = self.format(record)\n",
" ^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/logging/__init__.py\", line 953, in format\n",
" return fmt.format(record)\n",
" ^^^^^^^^^^^^^^^^^^\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/logging/__init__.py\", line 687, in format\n",
" record.message = record.getMessage()\n",
" ^^^^^^^^^^^^^^^^^^^\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/logging/__init__.py\", line 377, in getMessage\n",
" msg = msg % self.args\n",
" ~~~~^~~~~~~~~~~\n",
"TypeError: not all arguments converted during string formatting\n",
"Call stack:\n",
" File \"<frozen runpy>\", line 198, in _run_module_as_main\n",
" File \"<frozen runpy>\", line 88, in _run_code\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel_launcher.py\", line 18, in <module>\n",
" app.launch_new_instance()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/traitlets/config/application.py\", line 1075, in launch_instance\n",
" app.start()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/kernelapp.py\", line 739, in start\n",
" self.io_loop.start()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/tornado/platform/asyncio.py\", line 205, in start\n",
" self.asyncio_loop.run_forever()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/asyncio/base_events.py\", line 608, in run_forever\n",
" self._run_once()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/asyncio/base_events.py\", line 1936, in _run_once\n",
" handle._run()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/asyncio/events.py\", line 84, in _run\n",
" self._context.run(self._callback, *self._args)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/kernelbase.py\", line 545, in dispatch_queue\n",
" await self.process_one()\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/kernelbase.py\", line 534, in process_one\n",
" await dispatch(*args)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/kernelbase.py\", line 437, in dispatch_shell\n",
" await result\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/ipkernel.py\", line 359, in execute_request\n",
" await super().execute_request(stream, ident, parent)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/kernelbase.py\", line 778, in execute_request\n",
" reply_content = await reply_content\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/ipkernel.py\", line 446, in do_execute\n",
" res = shell.run_cell(\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/ipykernel/zmqshell.py\", line 549, in run_cell\n",
" return super().run_cell(*args, **kwargs)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/interactiveshell.py\", line 3075, in run_cell\n",
" result = self._run_cell(\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/interactiveshell.py\", line 3130, in _run_cell\n",
" result = runner(coro)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/async_helpers.py\", line 129, in _pseudo_sync_runner\n",
" coro.send(None)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/interactiveshell.py\", line 3334, in run_cell_async\n",
" has_raised = await self.run_ast_nodes(code_ast.body, cell_name,\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/interactiveshell.py\", line 3517, in run_ast_nodes\n",
" if await self.run_code(code, result, async_=asy):\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/IPython/core/interactiveshell.py\", line 3577, in run_code\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n",
" File \"/tmp/ipykernel_1778592/4055455867.py\", line 6, in <module>\n",
" compute_group_stance(\n",
" File \"/home/mihirban/llments/examples/community_lm/community_lm_utils.py\", line 155, in compute_group_stance\n",
" sentiment_vals = evaluator.evaluate_batch(\n",
" File \"/home/mihirban/llments/llments/eval/sentiment.py\", line 105, in evaluate_batch\n",
" for x in self.sentiment_pipeline(minibatch)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/transformers/pipelines/text_classification.py\", line 156, in __call__\n",
" result = super().__call__(*inputs, **kwargs)\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/transformers/pipelines/base.py\", line 1167, in __call__\n",
" logger.warning_once(\n",
" File \"/home/mihirban/miniconda3/lib/python3.11/site-packages/transformers/utils/logging.py\", line 329, in warning_once\n",
" self.warning(*args, **kwargs)\n",
"Message: 'You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset'\n",
"Arguments: (<class 'UserWarning'>,)\n",
"Processing questions: 100%|██████████| 30/30 [02:01<00:00, 4.05s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.18s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.18s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing run_2 ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processing questions: 100%|██████████| 30/30 [02:04<00:00, 4.16s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.18s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.18s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing run_3 ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:04<00:00, 4.17s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing run_4 ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.18s/it]\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Processing run_5 ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Processing questions: 100%|██████████| 30/30 [02:05<00:00, 4.17s/it]\n",
"Processing questions: 13%|█▎ | 4/30 [00:16<01:48, 4.18s/it]"
]
}
],
"outputs": [],
"source": [
"evaluator = HuggingFaceSentimentEvaluator(\n",
" \"cardiffnlp/twitter-roberta-base-sentiment-latest\",\n",
Expand Down Expand Up @@ -349,7 +184,7 @@
"df_politician_results['Prompt4'] = anes_df['Prompt4'].to_list()\n",
"\n",
"df_politician_results['pid'] = df_politician_results.index\n",
"df_politician_results.to_csv(\"output/anes2020_pilot_prompt_probing_ft.csv\", index=False)\n",
"df_politician_results.to_csv(\"output/anes2020_pilot_prompt_probing.csv\", index=False)\n",
"# df_politician_results"
]
},
Expand Down Expand Up @@ -420,7 +255,7 @@
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"output/anes2020_pilot_prompt_probing_ft.csv\")\n",
"df = pd.read_csv(\"output/anes2020_pilot_prompt_probing.csv\")\n",
"df_scores = compute_scores(df, df_dem, df_repub)\n",
"df_scores"
]
Expand Down Expand Up @@ -570,21 +405,25 @@
"plt.tight_layout()\n",
"plt.savefig('rankings/gold_repub_rank.png', bbox_inches = \"tight\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e5082d3c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.7"
}
},
"nbformat": 4,
Expand Down
Loading

0 comments on commit ef90ba7

Please sign in to comment.