Spaces:

inflaton-ai
/

logical-reasoning

Build error

App Files Files Community

dh-mc commited on Jul 24, 2024

Commit

c41fec1

1 Parent(s): e524368

gemma2 results

Browse files

Files changed (3) hide show

competition/15a_Gemma_NV4090_test.ipynb +1 -0
llm_toolkit/tune_logical_reasoning.py +0 -6
results/mgtv-results_colab_p2_gemma2.csv +0 -0

competition/15a_Gemma_NV4090_test.ipynb ADDED Viewed

	@@ -0,0 +1 @@

+ {"cells":[{"cell_type":"code","execution_count":1,"metadata":{"executionInfo":{"elapsed":476,"status":"ok","timestamp":1720679526275,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"uWKRSV6eZsCn"},"outputs":[],"source":["%load_ext autoreload\n","%autoreload 2"]},{"cell_type":"code","execution_count":2,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"eb33b19f-1206-41ee-84e2-e6258a12eef7","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":2534,"status":"ok","timestamp":1720679529344,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"xwFh14uiZBrI","outputId":"d767799c-34c2-46a5-f052-378146a55321"},"outputs":[],"source":["from pathlib import Path\n","\n","try:\n"," from google.colab import drive\n","\n"," drive.mount(\"/content/drive\")\n"," workding_dir = \"/content/drive/MyDrive/logical-reasoning/\"\n","except ModuleNotFoundError:\n"," workding_dir = str(Path.cwd().parent)"]},{"cell_type":"code","execution_count":3,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"6d394937-6c99-4a7c-9d32-7600a280032f","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"G5pNu3zgZBrL","outputId":"160a554f-fb08-4aa0-bc00-0422fb7c1fac"},"outputs":[{"name":"stdout","output_type":"stream","text":["workding dir: /home/inflaton/code/logical-reasoning\n"]}],"source":["import os\n","import sys\n","from pathlib import Path\n","\n","os.chdir(workding_dir)\n","sys.path.append(workding_dir)\n","print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":4,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"9f67ec60-2f24-411c-84eb-0dd664b44775","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hPCC-6m7ZBrM","outputId":"c7aa2c96-5e99-440a-c148-201d79465ff9"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading env vars from: /home/inflaton/code/logical-reasoning/.env\n"]},{"data":{"text/plain":["True"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["from dotenv import find_dotenv, load_dotenv\n","\n","found_dotenv = find_dotenv(\".env\")\n","\n","if len(found_dotenv) == 0:\n"," found_dotenv = find_dotenv(\".env.example\")\n","print(f\"loading env vars from: {found_dotenv}\")\n","load_dotenv(found_dotenv, override=True)"]},{"cell_type":"code","execution_count":5,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"f1597656-8042-4878-9d3b-9ebfb8dd86dc","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"1M3IraVtZBrM","outputId":"29ab35f6-2970-4ade-d85d-3174acf8cda0"},"outputs":[{"name":"stdout","output_type":"stream","text":["unsloth/gemma-2-9b None False datasets/mgtv results/mgtv-results_colab_p2_gemma2.csv\n"]}],"source":["import os\n","\n","model_name = os.getenv(\"MODEL_NAME\")\n","adapter_name_or_path = os.getenv(\"ADAPTER_NAME_OR_PATH\")\n","load_in_4bit = os.getenv(\"LOAD_IN_4BIT\") == \"true\"\n","data_path = os.getenv(\"LOGICAL_REASONING_DATA_PATH\")\n","results_path = os.getenv(\"LOGICAL_REASONING_RESULTS_PATH\")\n","use_english_datasets = os.getenv(\"USE_ENGLISH_DATASETS\") == \"true\"\n","\n","print(model_name, adapter_name_or_path, load_in_4bit, data_path, results_path)"]},{"cell_type":"code","execution_count":6,"metadata":{},"outputs":[{"data":{"text/plain":["False"]},"execution_count":6,"metadata":{},"output_type":"execute_result"}],"source":["need_to_setup_env = os.getenv(\"NEED_TO_SETUP_ENV\") == \"true\"\n","need_to_setup_env"]},{"cell_type":"code","execution_count":7,"metadata":{},"outputs":[],"source":["%%capture\n","if need_to_setup_env:\n"," !pip install -r requirements.txt\n","\n"," # Installs Unsloth, Xformers (Flash Attention) and all other packages!\n"," !pip install \"unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git\"\n"," !pip install --no-deps \"xformers<0.0.27\" \"trl<0.9.0\" peft accelerate bitsandbytes\n"]},{"cell_type":"code","execution_count":8,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"b2a43943-9324-4839-9a47-cfa72de2244b","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":564,"status":"ok","timestamp":1720679529907,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"UgMvt6dIZBrM","outputId":"ce37581c-fd26-46c2-ad87-d933d99f68f7"},"outputs":[{"name":"stdout","output_type":"stream","text":["Python 3.11.9\n","Name: transformers\n","Version: 4.43.2\n","Summary: State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow\n","Home-page: https://github.com/huggingface/transformers\n","Author: The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)\n","Author-email: transformers@huggingface.co\n","License: Apache 2.0 License\n","Location: /home/inflaton/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages\n","Requires: filelock, huggingface-hub, numpy, packaging, pyyaml, regex, requests, safetensors, tokenizers, tqdm\n","Required-by: llamafactory, peft, trl\n","---\n","Name: torch\n","Version: 2.3.1\n","Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration\n","Home-page: https://pytorch.org/\n","Author: PyTorch Team\n","Author-email: packages@pytorch.org\n","License: BSD-3\n","Location: /home/inflaton/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages\n","Requires: filelock, fsspec, jinja2, networkx, nvidia-cublas-cu12, nvidia-cuda-cupti-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-runtime-cu12, nvidia-cudnn-cu12, nvidia-cufft-cu12, nvidia-curand-cu12, nvidia-cusolver-cu12, nvidia-cusparse-cu12, nvidia-nccl-cu12, nvidia-nvtx-cu12, sympy, triton, typing-extensions\n","Required-by: accelerate, bitsandbytes, peft, trl, xformers\n","---\n","Name: unsloth\n","Version: 2024.7\n","Summary: 2-5X faster LLM finetuning\n","Home-page: \n","Author: Unsloth AI team\n","Author-email: info@unsloth.ai\n","License: Apache License\n"," Version 2.0, January 2004\n"," http://www.apache.org/licenses/\n","\n"," TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION\n","\n"," 1. Definitions.\n","\n"," \"License\" shall mean the terms and conditions for use, reproduction,\n"," and distribution as defined by Sections 1 through 9 of this document.\n","\n"," \"Licensor\" shall mean the copyright owner or entity authorized by\n"," the copyright owner that is granting the License.\n","\n"," \"Legal Entity\" shall mean the union of the acting entity and all\n"," other entities that control, are controlled by, or are under common\n"," control with that entity. For the purposes of this definition,\n"," \"control\" means (i) the power, direct or indirect, to cause the\n"," direction or management of such entity, whether by contract or\n"," otherwise, or (ii) ownership of fifty percent (50%) or more of the\n"," outstanding shares, or (iii) beneficial ownership of such entity.\n","\n"," \"You\" (or \"Your\") shall mean an individual or Legal Entity\n"," exercising permissions granted by this License.\n","\n"," \"Source\" form shall mean the preferred form for making modifications,\n"," including but not limited to software source code, documentation\n"," source, and configuration files.\n","\n"," \"Object\" form shall mean any form resulting from mechanical\n"," transformation or translation of a Source form, including but\n"," not limited to compiled object code, generated documentation,\n"," and conversions to other media types.\n","\n"," \"Work\" shall mean the work of authorship, whether in Source or\n"," Object form, made available under the License, as indicated by a\n"," copyright notice that is included in or attached to the work\n"," (an example is provided in the Appendix below).\n","\n"," \"Derivative Works\" shall mean any work, whether in Source or Object\n"," form, that is based on (or derived from) the Work and for which the\n"," editorial revisions, annotations, elaborations, or other modifications\n"," represent, as a whole, an original work of authorship. For the purposes\n"," of this License, Derivative Works shall not include works that remain\n"," separable from, or merely link (or bind by name) to the interfaces of,\n"," the Work and Derivative Works thereof.\n","\n"," \"Contribution\" shall mean any work of authorship, including\n"," the original version of the Work and any modifications or additions\n"," to that Work or Derivative Works thereof, that is intentionally\n"," submitted to Licensor for inclusion in the Work by the copyright owner\n"," or by an individual or Legal Entity authorized to submit on behalf of\n"," the copyright owner. For the purposes of this definition, \"submitted\"\n"," means any form of electronic, verbal, or written communication sent\n"," to the Licensor or its representatives, including but not limited to\n"," communication on electronic mailing lists, source code control systems,\n"," and issue tracking systems that are managed by, or on behalf of, the\n"," Licensor for the purpose of discussing and improving the Work, but\n"," excluding communication that is conspicuously marked or otherwise\n"," designated in writing by the copyright owner as \"Not a Contribution.\"\n","\n"," \"Contributor\" shall mean Licensor and any individual or Legal Entity\n"," on behalf of whom a Contribution has been received by Licensor and\n"," subsequently incorporated within the Work.\n","\n"," 2. Grant of Copyright License. Subject to the terms and conditions of\n"," this License, each Contributor hereby grants to You a perpetual,\n"," worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n"," copyright license to reproduce, prepare Derivative Works of,\n"," publicly display, publicly perform, sublicense, and distribute the\n"," Work and such Derivative Works in Source or Object form.\n","\n"," 3. Grant of Patent License. Subject to the terms and conditions of\n"," this License, each Contributor hereby grants to You a perpetual,\n"," worldwide, non-exclusive, no-charge, royalty-free, irrevocable\n"," (except as stated in this section) patent license to make, have made,\n"," use, offer to sell, sell, import, and otherwise transfer the Work,\n"," where such license applies only to those patent claims licensable\n"," by such Contributor that are necessarily infringed by their\n"," Contribution(s) alone or by combination of their Contribution(s)\n"," with the Work to which such Contribution(s) was submitted. If You\n"," institute patent litigation against any entity (including a\n"," cross-claim or counterclaim in a lawsuit) alleging that the Work\n"," or a Contribution incorporated within the Work constitutes direct\n"," or contributory patent infringement, then any patent licenses\n"," granted to You under this License for that Work shall terminate\n"," as of the date such litigation is filed.\n","\n"," 4. Redistribution. You may reproduce and distribute copies of the\n"," Work or Derivative Works thereof in any medium, with or without\n"," modifications, and in Source or Object form, provided that You\n"," meet the following conditions:\n","\n"," (a) You must give any other recipients of the Work or\n"," Derivative Works a copy of this License; and\n","\n"," (b) You must cause any modified files to carry prominent notices\n"," stating that You changed the files; and\n","\n"," (c) You must retain, in the Source form of any Derivative Works\n"," that You distribute, all copyright, patent, trademark, and\n"," attribution notices from the Source form of the Work,\n"," excluding those notices that do not pertain to any part of\n"," the Derivative Works; and\n","\n"," (d) If the Work includes a \"NOTICE\" text file as part of its\n"," distribution, then any Derivative Works that You distribute must\n"," include a readable copy of the attribution notices contained\n"," within such NOTICE file, excluding those notices that do not\n"," pertain to any part of the Derivative Works, in at least one\n"," of the following places: within a NOTICE text file distributed\n"," as part of the Derivative Works; within the Source form or\n"," documentation, if provided along with the Derivative Works; or,\n"," within a display generated by the Derivative Works, if and\n"," wherever such third-party notices normally appear. The contents\n"," of the NOTICE file are for informational purposes only and\n"," do not modify the License. You may add Your own attribution\n"," notices within Derivative Works that You distribute, alongside\n"," or as an addendum to the NOTICE text from the Work, provided\n"," that such additional attribution notices cannot be construed\n"," as modifying the License.\n","\n"," You may add Your own copyright statement to Your modifications and\n"," may provide additional or different license terms and conditions\n"," for use, reproduction, or distribution of Your modifications, or\n"," for any such Derivative Works as a whole, provided Your use,\n"," reproduction, and distribution of the Work otherwise complies with\n"," the conditions stated in this License.\n","\n"," 5. Submission of Contributions. Unless You explicitly state otherwise,\n"," any Contribution intentionally submitted for inclusion in the Work\n"," by You to the Licensor shall be under the terms and conditions of\n"," this License, without any additional terms or conditions.\n"," Notwithstanding the above, nothing herein shall supersede or modify\n"," the terms of any separate license agreement you may have executed\n"," with Licensor regarding such Contributions.\n","\n"," 6. Trademarks. This License does not grant permission to use the trade\n"," names, trademarks, service marks, or product names of the Licensor,\n"," except as required for reasonable and customary use in describing the\n"," origin of the Work and reproducing the content of the NOTICE file.\n","\n"," 7. Disclaimer of Warranty. Unless required by applicable law or\n"," agreed to in writing, Licensor provides the Work (and each\n"," Contributor provides its Contributions) on an \"AS IS\" BASIS,\n"," WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or\n"," implied, including, without limitation, any warranties or conditions\n"," of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A\n"," PARTICULAR PURPOSE. You are solely responsible for determining the\n"," appropriateness of using or redistributing the Work and assume any\n"," risks associated with Your exercise of permissions under this License.\n","\n"," 8. Limitation of Liability. In no event and under no legal theory,\n"," whether in tort (including negligence), contract, or otherwise,\n"," unless required by applicable law (such as deliberate and grossly\n"," negligent acts) or agreed to in writing, shall any Contributor be\n"," liable to You for damages, including any direct, indirect, special,\n"," incidental, or consequential damages of any character arising as a\n"," result of this License or out of the use or inability to use the\n"," Work (including but not limited to damages for loss of goodwill,\n"," work stoppage, computer failure or malfunction, or any and all\n"," other commercial damages or losses), even if such Contributor\n"," has been advised of the possibility of such damages.\n","\n"," 9. Accepting Warranty or Additional Liability. While redistributing\n"," the Work or Derivative Works thereof, You may choose to offer,\n"," and charge a fee for, acceptance of support, warranty, indemnity,\n"," or other liability obligations and/or rights consistent with this\n"," License. However, in accepting such obligations, You may act only\n"," on Your own behalf and on Your sole responsibility, not on behalf\n"," of any other Contributor, and only if You agree to indemnify,\n"," defend, and hold each Contributor harmless for any liability\n"," incurred by, or claims asserted against, such Contributor by reason\n"," of your accepting any such warranty or additional liability.\n","\n"," END OF TERMS AND CONDITIONS\n","\n"," APPENDIX: How to apply the Apache License to your work.\n","\n"," To apply the Apache License to your work, attach the following\n"," boilerplate notice, with the fields enclosed by brackets \"[]\"\n"," replaced with your own identifying information. (Don't include\n"," the brackets!) The text should be enclosed in the appropriate\n"," comment syntax for the file format. We also recommend that a\n"," file or class name and description of purpose be included on the\n"," same \"printed page\" as the copyright notice for easier\n"," identification within third-party archives.\n","\n"," Copyright [2024-] [Unsloth AI, Daniel Han-Chen & Michael Han-Chen]\n","\n"," Licensed under the Apache License, Version 2.0 (the \"License\");\n"," you may not use this file except in compliance with the License.\n"," You may obtain a copy of the License at\n","\n"," http://www.apache.org/licenses/LICENSE-2.0\n","\n"," Unless required by applicable law or agreed to in writing, software\n"," distributed under the License is distributed on an \"AS IS\" BASIS,\n"," WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n"," See the License for the specific language governing permissions and\n"," limitations under the License.\n","\n","Location: /home/inflaton/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages\n","Requires: \n","Required-by: \n","CPU times: user 25.8 ms, sys: 1.07 ms, total: 26.9 ms\n","Wall time: 2.75 s\n"]}],"source":["%%time\n","!python --version\n","!pip show transformers torch unsloth"]},{"cell_type":"code","execution_count":9,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":1685,"status":"ok","timestamp":1720679531591,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"ZuS_FsLyZBrN","outputId":"2cba0105-c505-4395-afbd-2f2fee6581d0"},"outputs":[{"name":"stdout","output_type":"stream","text":["loading /home/inflaton/code/logical-reasoning/llm_toolkit/logical_reasoning_utils.py\n","CUDA is available, we have found 1 GPU(s)\n","NVIDIA GeForce RTX 4090\n","CUDA version: 12.1\n"]}],"source":["from llm_toolkit.llm_utils import *\n","from llm_toolkit.logical_reasoning_utils import *\n","\n","device = check_gpu()"]},{"cell_type":"code","execution_count":10,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["CPU times: user 1 μs, sys: 0 ns, total: 1 μs\n","Wall time: 3.34 μs\n"]}],"source":["%%time\n","\n","# !python llm_toolkit/tune_logical_reasoning.py"]},{"cell_type":"code","execution_count":11,"metadata":{},"outputs":[],"source":["# %%time\n","\n","# from unsloth import FastLanguageModel\n","\n","# model, tokenizer = FastLanguageModel.from_pretrained(\n","# model_name = \"unsloth_rtx4090/checkpoint-6000\", # YOUR MODEL YOU USED FOR TRAINING\n","# max_seq_length = 4096,\n","# dtype = None,\n","# load_in_4bit = load_in_4bit,\n","# )\n","# FastLanguageModel.for_inference(model) # Enable native 2x faster inference"]},{"cell_type":"code","execution_count":12,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: unsloth/gemma-2-9b with adapter: unsloth_rtx4090/checkpoint-6000\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"7bf22f8c1baf4c5297552a01e2259555","version_major":2,"version_minor":0},"text/plain":["Loading checkpoint shards: 0%| | 0/4 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["CPU times: user 9.1 s, sys: 707 ms, total: 9.8 s\n","Wall time: 6.31 s\n"]}],"source":["%%time\n","adapter_name_or_path = \"unsloth_rtx4090/checkpoint-6000\"\n","model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":13,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading train/test data files\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"a777805798b94d788b4df0c66a0c6abf","version_major":2,"version_minor":0},"text/plain":["Map: 0%| | 0/25000 [00:00<?, ? examples/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stderr","output_type":"stream","text":["No chat template is set for this tokenizer, falling back to a default class-level template. This is very error-prone, because models are often trained with templates different from the class default! Default chat templates are a legacy feature and will be removed in Transformers v4.43, at which point any code depending on them will stop working. We recommend setting a valid chat template before then to ensure that this model continues working without issues.\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"c733633be8b0489b8c277baa9868070f","version_major":2,"version_minor":0},"text/plain":["Map: 0%| | 0/3000 [00:00<?, ? examples/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["DatasetDict({\n"," train: Dataset({\n"," features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n"," num_rows: 25000\n"," })\n"," test: Dataset({\n"," features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n"," num_rows: 3000\n"," })\n","})\n"]}],"source":["datasets = load_logical_reasoning_dataset(\n"," data_path,\n"," tokenizer=tokenizer,\n"," chinese_prompt=not use_english_datasets,\n"," using_p1=False,\n",")"]},{"cell_type":"code","execution_count":14,"metadata":{},"outputs":[],"source":["def evaluate_model(model, tokenizer, model_name, dataset):\n"," print(f\"Evaluating model: {model_name} on {device}\")\n"," predictions = eval_model(model, tokenizer, dataset, device=device)\n","\n"," save_results(\n"," model_name,\n"," results_path,\n"," dataset,\n"," predictions,\n"," debug=False,\n"," )\n","\n"," metrics = calc_metrics(dataset[\"label\"], predictions, debug=False)\n"," print(metrics)"]},{"cell_type":"code","execution_count":15,"metadata":{},"outputs":[{"data":{"text/plain":["Embedding(256000, 3584, padding_idx=0)"]},"execution_count":15,"metadata":{},"output_type":"execute_result"}],"source":["model.resize_token_embeddings(len(tokenizer), pad_to_multiple_of=32)"]},{"cell_type":"code","execution_count":16,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Evaluating model: unsloth/gemma-2-9b_checkpoint-6000 on cuda\n"]},{"name":"stderr","output_type":"stream","text":[" 0%| | 1/3000 [00:02<1:44:41, 2.09s/it]"]},{"name":"stdout","output_type":"stream","text":["Batch output: ['不是']\n"]},{"name":"stderr","output_type":"stream","text":["100%|██████████| 3000/3000 [34:22<00:00, 1.45it/s] "]},{"name":"stdout","output_type":"stream","text":["{'accuracy': 0.6776666666666666}\n","CPU times: user 24min 7s, sys: 10min 15s, total: 34min 23s\n","Wall time: 34min 22s\n"]},{"name":"stderr","output_type":"stream","text":["\n"]}],"source":["%%time\n","\n","evaluate_model(model, tokenizer, f\"{model_name}_checkpoint-6000\", datasets[\"test\"])"]},{"cell_type":"code","execution_count":19,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading train/test data files\n","DatasetDict({\n"," train: Dataset({\n"," features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n"," num_rows: 25000\n"," })\n"," test: Dataset({\n"," features: ['text', 'label', 'answer', 'title', 'puzzle', 'truth', 'train_text', 'prompt'],\n"," num_rows: 30000\n"," })\n","})\n","Evaluating model: unsloth/gemma-2-9b\n"]},{"name":"stderr","output_type":"stream","text":[" 0%| | 1/30000 [00:02<23:25:29, 2.81s/it]"]},{"name":"stdout","output_type":"stream","text":["Batch output: ['不是']\n"]},{"name":"stderr","output_type":"stream","text":[" 6%|▌ | 1767/30000 [1:32:05<24:31:19, 3.13s/it]\n"]},{"ename":"KeyboardInterrupt","evalue":"","output_type":"error","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","File \u001b[0;32m<timed exec>:15\u001b[0m\n","File \u001b[0;32m~/code/logical-reasoning/llm_toolkit/llm_utils.py:183\u001b[0m, in \u001b[0;36meval_model\u001b[0;34m(model, tokenizer, eval_dataset, device, max_new_tokens, repetition_penalty, batch_size)\u001b[0m\n\u001b[1;32m 176\u001b[0m batch_prompts \u001b[38;5;241m=\u001b[39m eval_dataset[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprompt\u001b[39m\u001b[38;5;124m\"\u001b[39m][i:batch_end]\n\u001b[1;32m 177\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tokenizer(\n\u001b[1;32m 178\u001b[0m batch_prompts,\n\u001b[1;32m 179\u001b[0m return_tensors\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[1;32m 180\u001b[0m padding\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, \u001b[38;5;66;03m# Ensure all inputs in the batch have the same length\u001b[39;00m\n\u001b[1;32m 181\u001b[0m )\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m--> 183\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 184\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 185\u001b[0m \u001b[43m \u001b[49m\u001b[43mmax_new_tokens\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_new_tokens\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 186\u001b[0m \u001b[43m \u001b[49m\u001b[43mrepetition_penalty\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepetition_penalty\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 187\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 188\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 189\u001b[0m outputs \u001b[38;5;241m=\u001b[39m outputs[:, inputs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minput_ids\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m1\u001b[39m] :]\n\u001b[1;32m 190\u001b[0m decoded_output \u001b[38;5;241m=\u001b[39m tokenizer\u001b[38;5;241m.\u001b[39mbatch_decode(\n\u001b[1;32m 191\u001b[0m outputs, skip_special_tokens\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 192\u001b[0m ) \u001b[38;5;66;03m# Skip special tokens for clean output\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/utils/_contextlib.py:115\u001b[0m, in \u001b[0;36mcontext_decorator.<locals>.decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 112\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 113\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 115\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/generation/utils.py:1989\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 1981\u001b[0m input_ids, model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_expand_inputs_for_generation(\n\u001b[1;32m 1982\u001b[0m input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m 1983\u001b[0m expand_size\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mnum_return_sequences,\n\u001b[1;32m 1984\u001b[0m is_encoder_decoder\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mis_encoder_decoder,\n\u001b[1;32m 1985\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m 1986\u001b[0m )\n\u001b[1;32m 1988\u001b[0m \u001b[38;5;66;03m# 13. run sample (it degenerates to greedy search when `generation_config.do_sample=False`)\u001b[39;00m\n\u001b[0;32m-> 1989\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_sample\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1990\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1991\u001b[0m \u001b[43m \u001b[49m\u001b[43mlogits_processor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_logits_processor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1992\u001b[0m \u001b[43m \u001b[49m\u001b[43mlogits_warper\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_logits_warper\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1993\u001b[0m \u001b[43m \u001b[49m\u001b[43mstopping_criteria\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprepared_stopping_criteria\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1994\u001b[0m \u001b[43m \u001b[49m\u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgeneration_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1995\u001b[0m \u001b[43m \u001b[49m\u001b[43msynced_gpus\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msynced_gpus\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1996\u001b[0m \u001b[43m \u001b[49m\u001b[43mstreamer\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstreamer\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1997\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1998\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 2000\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m generation_mode \u001b[38;5;129;01min\u001b[39;00m (GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SAMPLE, GenerationMode\u001b[38;5;241m.\u001b[39mBEAM_SEARCH):\n\u001b[1;32m 2001\u001b[0m \u001b[38;5;66;03m# 11. prepare logits warper\u001b[39;00m\n\u001b[1;32m 2002\u001b[0m prepared_logits_warper \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 2003\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_get_logits_warper(generation_config, device\u001b[38;5;241m=\u001b[39minput_ids\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m 2004\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m generation_config\u001b[38;5;241m.\u001b[39mdo_sample\n\u001b[1;32m 2005\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 2006\u001b[0m )\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/generation/utils.py:2932\u001b[0m, in \u001b[0;36mGenerationMixin._sample\u001b[0;34m(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, logits_warper, **model_kwargs)\u001b[0m\n\u001b[1;32m 2929\u001b[0m model_inputs\u001b[38;5;241m.\u001b[39mupdate({\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_hidden_states\u001b[39m\u001b[38;5;124m\"\u001b[39m: output_hidden_states} \u001b[38;5;28;01mif\u001b[39;00m output_hidden_states \u001b[38;5;28;01melse\u001b[39;00m {})\n\u001b[1;32m 2931\u001b[0m \u001b[38;5;66;03m# forward pass to get next token\u001b[39;00m\n\u001b[0;32m-> 2932\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\n\u001b[1;32m 2934\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m synced_gpus \u001b[38;5;129;01mand\u001b[39;00m this_peer_finished:\n\u001b[1;32m 2935\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m \u001b[38;5;66;03m# don't waste resources running the code we don't need\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1539\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1540\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1541\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1544\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.py:944\u001b[0m, in \u001b[0;36mGemma2ForCausalLM.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict, cache_position)\u001b[0m\n\u001b[1;32m 941\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[1;32m 943\u001b[0m \u001b[38;5;66;03m# decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)\u001b[39;00m\n\u001b[0;32m--> 944\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 945\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 946\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 947\u001b[0m \u001b[43m \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 948\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 949\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 950\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 951\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 952\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 953\u001b[0m \u001b[43m \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 954\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_position\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 955\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 957\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 958\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlm_head(hidden_states)\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1539\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1540\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1541\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1544\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.py:784\u001b[0m, in \u001b[0;36mGemma2Model.forward\u001b[0;34m(self, input_ids, attention_mask, position_ids, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict, cache_position)\u001b[0m\n\u001b[1;32m 773\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(\n\u001b[1;32m 774\u001b[0m decoder_layer\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m,\n\u001b[1;32m 775\u001b[0m hidden_states,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 781\u001b[0m cache_position,\n\u001b[1;32m 782\u001b[0m )\n\u001b[1;32m 783\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 784\u001b[0m layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mdecoder_layer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 785\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 786\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcausal_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 787\u001b[0m \u001b[43m \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 788\u001b[0m \u001b[43m \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 789\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 790\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 791\u001b[0m \u001b[43m \u001b[49m\u001b[43mcache_position\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_position\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 792\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 794\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 796\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m output_attentions:\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1539\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1540\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1541\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1544\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.py:539\u001b[0m, in \u001b[0;36mGemma2DecoderLayer.forward\u001b[0;34m(self, hidden_states, attention_mask, position_ids, past_key_value, output_attentions, use_cache, cache_position)\u001b[0m\n\u001b[1;32m 536\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m residual \u001b[38;5;241m+\u001b[39m hidden_states\n\u001b[1;32m 538\u001b[0m residual \u001b[38;5;241m=\u001b[39m hidden_states\n\u001b[0;32m--> 539\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpre_feedforward_layernorm\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 540\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmlp(hidden_states)\n\u001b[1;32m 541\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpost_feedforward_layernorm(hidden_states)\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1530\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1532\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/torch/nn/modules/module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1539\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1540\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1541\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 1544\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.py:67\u001b[0m, in \u001b[0;36mGemma2RMSNorm.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x):\n\u001b[0;32m---> 67\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_norm\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfloat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 68\u001b[0m \u001b[38;5;66;03m# Llama does x.to(float16) * w whilst Gemma2 is (x * w).to(float16)\u001b[39;00m\n\u001b[1;32m 69\u001b[0m \u001b[38;5;66;03m# See https://github.com/huggingface/transformers/pull/29402\u001b[39;00m\n\u001b[1;32m 70\u001b[0m output \u001b[38;5;241m=\u001b[39m output \u001b[38;5;241m*\u001b[39m (\u001b[38;5;241m1.0\u001b[39m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mweight\u001b[38;5;241m.\u001b[39mfloat())\n","File \u001b[0;32m~/miniconda3/envs/llm-finetuning/lib/python3.11/site-packages/transformers/models/gemma2/modeling_gemma2.py:64\u001b[0m, in \u001b[0;36mGemma2RMSNorm._norm\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 63\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_norm\u001b[39m(\u001b[38;5;28mself\u001b[39m, x):\n\u001b[0;32m---> 64\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m x \u001b[38;5;241m*\u001b[39m torch\u001b[38;5;241m.\u001b[39mrsqrt(\u001b[43mx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpow\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmean\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m-\u001b[39;49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkeepdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39meps)\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "]}],"source":["%%time\n","\n","test_data = \"test_b\"\n","results_path = f\"{test_data}-results_r6.csv\"\n","max_new_tokens = 16\n","repetition_penalty = 1.0\n","\n","datasets = load_logical_reasoning_dataset(\n"," data_path,\n"," tokenizer=tokenizer,\n"," chinese_prompt=True,\n"," using_p1=False,\n"," test_data=test_data,\n",")\n","\n","print(\"Evaluating model: \" + model_name)\n","predictions = eval_model(\n"," model,\n"," tokenizer,\n"," datasets[\"test\"],\n"," max_new_tokens=max_new_tokens,\n"," repetition_penalty=repetition_penalty,\n",")\n","\n","save_results(\n"," \"answer\",\n"," results_path,\n"," datasets[\"test\"],\n"," predictions,\n"," debug=True,\n",")"]}],"metadata":{"accelerator":"GPU","application/vnd.databricks.v1+notebook":{"dashboards":[],"environmentMetadata":null,"language":"python","notebookMetadata":{"mostRecentlyExecutedCommandWithImplicitDF":{"commandId":-1,"dataframes":["_sqldf"]},"pythonIndentUnit":4},"notebookName":"10_eval-lf-medium-py3.11","widgets":{}},"colab":{"gpuType":"L4","provenance":[]},"kernelspec":{"display_name":"Python 3","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":"3.11.9"}},"nbformat":4,"nbformat_minor":0}

llm_toolkit/tune_logical_reasoning.py CHANGED Viewed

@@ -32,12 +32,6 @@ results_path = os.getenv("LOGICAL_REASONING_RESULTS_PATH")
 print(model_name, load_in_4bit, data_path, results_path)
-max_seq_length = 2048  # Choose any! We auto support RoPE Scaling internally!
-dtype = (
-    None  # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
-)
 max_seq_length = 4096  # Choose any! We auto support RoPE Scaling internally!
 dtype = (
     None  # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+

 print(model_name, load_in_4bit, data_path, results_path)
 max_seq_length = 4096  # Choose any! We auto support RoPE Scaling internally!
 dtype = (
     None  # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+

results/mgtv-results_colab_p2_gemma2.csv ADDED Viewed

The diff for this file is too large to render. See raw diff