Spaces:

inflaton-ai
/

logical-reasoning

Build error

App Files Files Community

dh-mc commited on Jul 20, 2024

Commit

f74c0d2

1 Parent(s): d2b86f6

completed Llama3-8b analysis

Browse files

Files changed (11) hide show

competition/00a_InternLM2.5_Llama3_GLM4_Results.ipynb +0 -0
competition/00a_InternLM_2.5_and_Llama_3_Results.ipynb +0 -0
competition/11_Llama-3_8b_analysis.ipynb +0 -0
competition/11a_Llama-3_8b_p2_analysis.ipynb +0 -0
competition/12b_InternLM_Push_LoRA_to_hub.ipynb +1 -1
competition/14_GLM-4_M3_eval.ipynb +1 -1
competition/14b_GLM-4-9b_p1_analysis.ipynb +0 -0
competition/14c_GLM-4-9b_p2_analysis.ipynb +0 -0
results/mgtv-glm-4-9b_p1_full_metrics.csv +6 -0
results/mgtv-glm-4-9b_p2_full_metrics.csv +5 -0
results/mgtv-llama3_p2_full_metrics.csv +2 -2

competition/00a_InternLM2.5_Llama3_GLM4_Results.ipynb ADDED Viewed

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

competition/00a_InternLM_2.5_and_Llama_3_Results.ipynb DELETED Viewed

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

competition/11_Llama-3_8b_analysis.ipynb CHANGED Viewed

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

competition/11a_Llama-3_8b_p2_analysis.ipynb CHANGED Viewed

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

competition/12b_InternLM_Push_LoRA_to_hub.ipynb CHANGED Viewed

@@ -1 +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/projects/courses/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/projects/courses/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":["internlm/internlm2_5-7b-chat-1m llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 True datasets/mgtv results/mgtv-results_internlm_best.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":{"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","\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n","\u001b[0mCPU times: user 284 ms, sys: 88 ms, total: 372 ms\n","Wall time: 4.21 s\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"cell_type":"code","execution_count":7,"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/projects/courses/logical-reasoning/llm_toolkit/logical_reasoning_utils.py\n","GPU is available\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":8,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading model: llama-factory/saves/internlm2_5_7b/lora/sft_bf16_p2_full/checkpoint-88 with adapter: None\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"f59b2bb4da404f3f8aba87b5a732222b","version_major":2,"version_minor":0},"text/plain":["Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"}],"source":["%%time\n","\n","# model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)\n","model, tokenizer = load_model(adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":11,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["loading train/test data files\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"fc9a5f2556b24b42b3fb425da63fb8fc","version_major":2,"version_minor":0},"text/plain":["Map: 0%| | 0/25000 [00:00<?, ? examples/s]"]},"metadata":{},"output_type":"display_data"},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"268ca08da54c4f30be9e04477a42e40d","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":12,"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":13,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Evaluating model: THUDM/glm-4-9b-chat-1m_NV4080 on cuda\n"]},{"name":"stderr","output_type":"stream","text":[" 0%| | 1/3000 [1:24:27<4221:21:42, 5067.32s/it]"]},{"name":"stdout","output_type":"stream","text":["--------\n","step 1: \n","不是\n","--------\n","step 2: \n","不是\n","--------\n","step 3: \n","不是\n","--------\n","step 4: 不是\n","--------\n","step 5: 不是\n"]},{"name":"stderr","output_type":"stream","text":[" 13%|█▎ | 392/3000 [5:21:45<35:40:38, 49.25s/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 eval>:1\u001b[0m\n","Cell \u001b[0;32mIn[12], line 3\u001b[0m, in \u001b[0;36mevaluate_model\u001b[0;34m(model, tokenizer, model_name, dataset)\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mevaluate_model\u001b[39m(model, tokenizer, model_name, dataset):\n\u001b[1;32m 2\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEvaluating model: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mmodel_name\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m on \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdevice\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m----> 3\u001b[0m predictions \u001b[38;5;241m=\u001b[39m \u001b[43meval_model\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtokenizer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdataset\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdevice\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 5\u001b[0m save_results(\n\u001b[1;32m 6\u001b[0m model_name,\n\u001b[1;32m 7\u001b[0m results_path,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 10\u001b[0m debug\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m 11\u001b[0m )\n\u001b[1;32m 13\u001b[0m metrics \u001b[38;5;241m=\u001b[39m calc_metrics(dataset[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlabel\u001b[39m\u001b[38;5;124m\"\u001b[39m], predictions, debug\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m)\n","File \u001b[0;32m~/code/projects/courses/logical-reasoning/llm_toolkit/llm_utils.py:164\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 157\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 158\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tokenizer(\n\u001b[1;32m 159\u001b[0m batch_prompts,\n\u001b[1;32m 160\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 161\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 162\u001b[0m )\u001b[38;5;241m.\u001b[39mto(device)\n\u001b[0;32m--> 164\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 165\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 166\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 167\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 168\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 169\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 170\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 171\u001b[0m decoded_output \u001b[38;5;241m=\u001b[39m tokenizer\u001b[38;5;241m.\u001b[39mbatch_decode(\n\u001b[1;32m 172\u001b[0m outputs, skip_special_tokens\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 173\u001b[0m ) \u001b[38;5;66;03m# Skip special tokens for clean output\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/lib/python3.11/site-packages/transformers/generation/utils.py:1969\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 1961\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 1962\u001b[0m input_ids\u001b[38;5;241m=\u001b[39minput_ids,\n\u001b[1;32m 1963\u001b[0m expand_size\u001b[38;5;241m=\u001b[39mgeneration_config\u001b[38;5;241m.\u001b[39mnum_return_sequences,\n\u001b[1;32m 1964\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 1965\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mmodel_kwargs,\n\u001b[1;32m 1966\u001b[0m )\n\u001b[1;32m 1968\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-> 1969\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 1970\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1971\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 1972\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 1973\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 1974\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 1975\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 1976\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 1977\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 1978\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1980\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 1981\u001b[0m \u001b[38;5;66;03m# 11. prepare logits warper\u001b[39;00m\n\u001b[1;32m 1982\u001b[0m prepared_logits_warper \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m 1983\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 1984\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m generation_config\u001b[38;5;241m.\u001b[39mdo_sample\n\u001b[1;32m 1985\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1986\u001b[0m )\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/lib/python3.11/site-packages/transformers/generation/utils.py:2912\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 2909\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 2911\u001b[0m \u001b[38;5;66;03m# forward pass to get next token\u001b[39;00m\n\u001b[0;32m-> 2912\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 2914\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 2915\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/llama-factory/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/llama-factory/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/llama-factory/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_old_forward\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 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n","File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/THUDM/glm-4-9b-chat-1m/7d23e9e0bb8e63d85c4489b37b099489c1515370/modeling_chatglm.py:1003\u001b[0m, in \u001b[0;36mChatGLMForConditionalGeneration.forward\u001b[0;34m(self, input_ids, position_ids, attention_mask, past_key_values, inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict, return_last_logit)\u001b[0m\n\u001b[1;32m 1000\u001b[0m use_cache \u001b[38;5;241m=\u001b[39m use_cache \u001b[38;5;28;01mif\u001b[39;00m use_cache \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_cache\n\u001b[1;32m 1001\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[0;32m-> 1003\u001b[0m transformer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtransformer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1004\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 1005\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 1006\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 1007\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 1008\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 1009\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 1010\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 1011\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 1012\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1014\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m transformer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[1;32m 1015\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m return_last_logit:\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/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~/.cache/huggingface/modules/transformers_modules/THUDM/glm-4-9b-chat-1m/7d23e9e0bb8e63d85c4489b37b099489c1515370/modeling_chatglm.py:898\u001b[0m, in \u001b[0;36mChatGLMModel.forward\u001b[0;34m(self, input_ids, position_ids, attention_mask, full_attention_mask, past_key_values, inputs_embeds, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[1;32m 895\u001b[0m rotary_pos_emb \u001b[38;5;241m=\u001b[39m rotary_pos_emb[\u001b[38;5;28;01mNone\u001b[39;00m, :seq_length]\n\u001b[1;32m 897\u001b[0m \u001b[38;5;66;03m# Run encoder.\u001b[39;00m\n\u001b[0;32m--> 898\u001b[0m hidden_states, presents, all_hidden_states, all_self_attentions \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 899\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfull_attention_mask\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrotary_pos_emb\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrotary_pos_emb\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 900\u001b[0m \u001b[43m \u001b[49m\u001b[43mkv_caches\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\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\u001b[43m \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\n\u001b[1;32m 901\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 902\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m presents \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;129;01mand\u001b[39;00m \u001b[38;5;28mtype\u001b[39m(presents) \u001b[38;5;129;01mis\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mTensor:\n\u001b[1;32m 903\u001b[0m presents \u001b[38;5;241m=\u001b[39m presents\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;241m1\u001b[39m, dim\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m)\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/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~/.cache/huggingface/modules/transformers_modules/THUDM/glm-4-9b-chat-1m/7d23e9e0bb8e63d85c4489b37b099489c1515370/modeling_chatglm.py:727\u001b[0m, in \u001b[0;36mGLMTransformer.forward\u001b[0;34m(self, hidden_states, attention_mask, rotary_pos_emb, kv_caches, use_cache, output_hidden_states)\u001b[0m\n\u001b[1;32m 717\u001b[0m layer_ret \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mutils\u001b[38;5;241m.\u001b[39mcheckpoint\u001b[38;5;241m.\u001b[39mcheckpoint(\n\u001b[1;32m 718\u001b[0m layer,\n\u001b[1;32m 719\u001b[0m hidden_states,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 724\u001b[0m use_reentrant\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m 725\u001b[0m )\n\u001b[1;32m 726\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 727\u001b[0m layer_ret \u001b[38;5;241m=\u001b[39m \u001b[43mlayer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 728\u001b[0m \u001b[43m \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 729\u001b[0m \u001b[43m \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 730\u001b[0m \u001b[43m \u001b[49m\u001b[43mrotary_pos_emb\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 731\u001b[0m \u001b[43m \u001b[49m\u001b[43mkv_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkv_caches\u001b[49m\u001b[43m[\u001b[49m\u001b[43mindex\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 732\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\n\u001b[1;32m 733\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 734\u001b[0m hidden_states, kv_cache \u001b[38;5;241m=\u001b[39m layer_ret\n\u001b[1;32m 735\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache:\n\u001b[1;32m 736\u001b[0m \u001b[38;5;66;03m# token by token decoding, use tuple format\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/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/llama-factory/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_old_forward\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 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n","File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/THUDM/glm-4-9b-chat-1m/7d23e9e0bb8e63d85c4489b37b099489c1515370/modeling_chatglm.py:651\u001b[0m, in \u001b[0;36mGLMBlock.forward\u001b[0;34m(self, hidden_states, attention_mask, rotary_pos_emb, kv_cache, use_cache)\u001b[0m\n\u001b[1;32m 648\u001b[0m layernorm_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpost_attention_layernorm(layernorm_input)\n\u001b[1;32m 650\u001b[0m \u001b[38;5;66;03m# MLP.\u001b[39;00m\n\u001b[0;32m--> 651\u001b[0m mlp_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmlp\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlayernorm_output\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 653\u001b[0m \u001b[38;5;66;03m# Second residual connection.\u001b[39;00m\n\u001b[1;32m 654\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mapply_residual_connection_post_layernorm:\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/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/llama-factory/lib/python3.11/site-packages/accelerate/hooks.py:166\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 164\u001b[0m output \u001b[38;5;241m=\u001b[39m module\u001b[38;5;241m.\u001b[39m_old_forward(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 165\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 166\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_old_forward\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 167\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mpost_forward(module, output)\n","File \u001b[0;32m~/.cache/huggingface/modules/transformers_modules/THUDM/glm-4-9b-chat-1m/7d23e9e0bb8e63d85c4489b37b099489c1515370/modeling_chatglm.py:584\u001b[0m, in \u001b[0;36mMLP.forward\u001b[0;34m(self, hidden_states)\u001b[0m\n\u001b[1;32m 582\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, hidden_states):\n\u001b[1;32m 583\u001b[0m \u001b[38;5;66;03m# [s, b, 4hp]\u001b[39;00m\n\u001b[0;32m--> 584\u001b[0m intermediate_parallel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdense_h_to_4h\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 585\u001b[0m intermediate_parallel \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mactivation_func(intermediate_parallel)\n\u001b[1;32m 586\u001b[0m \u001b[38;5;66;03m# [s, b, h]\u001b[39;00m\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/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/llama-factory/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/llama-factory/lib/python3.11/site-packages/accelerate/hooks.py:161\u001b[0m, in \u001b[0;36madd_hook_to_module.<locals>.new_forward\u001b[0;34m(module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 160\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mnew_forward\u001b[39m(module, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[0;32m--> 161\u001b[0m args, kwargs \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_hf_hook\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mpre_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\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 162\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m module\u001b[38;5;241m.\u001b[39m_hf_hook\u001b[38;5;241m.\u001b[39mno_grad:\n\u001b[1;32m 163\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mno_grad():\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/lib/python3.11/site-packages/accelerate/hooks.py:347\u001b[0m, in \u001b[0;36mAlignDevicesHook.pre_forward\u001b[0;34m(self, module, *args, **kwargs)\u001b[0m\n\u001b[1;32m 339\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m 340\u001b[0m value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 341\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtied_params_map \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 342\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m value\u001b[38;5;241m.\u001b[39mdata_ptr() \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtied_params_map\n\u001b[1;32m 343\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexecution_device \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtied_params_map[value\u001b[38;5;241m.\u001b[39mdata_ptr()]\n\u001b[1;32m 344\u001b[0m ):\n\u001b[1;32m 345\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtied_pointers_to_remove\u001b[38;5;241m.\u001b[39madd((value\u001b[38;5;241m.\u001b[39mdata_ptr(), \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexecution_device))\n\u001b[0;32m--> 347\u001b[0m \u001b[43mset_module_tensor_to_device\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 348\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodule\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 349\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 350\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecution_device\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 351\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 352\u001b[0m \u001b[43m \u001b[49m\u001b[43mfp16_statistics\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfp16_statistics\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 353\u001b[0m \u001b[43m \u001b[49m\u001b[43mtied_params_map\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtied_params_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 354\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 356\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m send_to_device(args, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexecution_device), send_to_device(\n\u001b[1;32m 357\u001b[0m kwargs, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexecution_device, skip_keys\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mskip_keys\n\u001b[1;32m 358\u001b[0m )\n","File \u001b[0;32m~/miniconda3/envs/llama-factory/lib/python3.11/site-packages/accelerate/utils/modeling.py:400\u001b[0m, in \u001b[0;36mset_module_tensor_to_device\u001b[0;34m(module, tensor_name, device, value, dtype, fp16_statistics, tied_params_map)\u001b[0m\n\u001b[1;32m 398\u001b[0m module\u001b[38;5;241m.\u001b[39m_parameters[tensor_name] \u001b[38;5;241m=\u001b[39m param_cls(new_value, requires_grad\u001b[38;5;241m=\u001b[39mold_value\u001b[38;5;241m.\u001b[39mrequires_grad)\n\u001b[1;32m 399\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(value, torch\u001b[38;5;241m.\u001b[39mTensor):\n\u001b[0;32m--> 400\u001b[0m new_value \u001b[38;5;241m=\u001b[39m \u001b[43mvalue\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mto\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdevice\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 401\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 402\u001b[0m new_value \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mtensor(value, device\u001b[38;5;241m=\u001b[39mdevice)\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "]}],"source":["%%time\n","\n","evaluate_model(model, tokenizer, f\"{model_name}{'_' + adapter_name_or_path if adapter_name_or_path else ''}_NV4080\", datasets[\"test\"])"]}],"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}

competition/14_GLM-4_M3_eval.ipynb CHANGED Viewed

@@ -1 +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: /Users/inflaton/code/engd/projects/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":"ac667aba-076e-4de6-9984-8f6a67cb09cd","showTitle":false,"title":""},"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"0dVRAabNZBrL","outputId":"b977e116-df16-47cd-9160-a24f611da687"},"outputs":[{"data":{"text/plain":["False"]},"execution_count":4,"metadata":{},"output_type":"execute_result"}],"source":["need_to_setup_env = False\n","need_to_setup_env"]},{"cell_type":"code","execution_count":5,"metadata":{"application/vnd.databricks.v1+cell":{"cellMetadata":{"byteLimit":2048000,"rowLimit":10000},"inputWidgets":{},"nuid":"72f9cf79-7b0d-4d9e-90a0-1fa5251b947f","showTitle":false,"title":""},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1720679529345,"user":{"displayName":"HUANG DONGHAO _","userId":"00977795705617022768"},"user_tz":-480},"id":"hKUOfP2HZBrL"},"outputs":[],"source":["if need_to_setup_env:\n"," %pip install -r requirements.txt\n"," %cd /content/\n"," %rm -rf LLaMA-Factory\n"," !git clone https://github.com/hiyouga/LLaMA-Factory.git\n"," %cd LLaMA-Factory\n"," %ls\n"," %pip install -e .[torch,bitsandbytes]\n"," \n"," os.chdir(workding_dir)\n"," sys.path.append(workding_dir)\n"," print(\"workding dir:\", workding_dir)"]},{"cell_type":"code","execution_count":6,"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: /Users/inflaton/code/engd/projects/logical-reasoning/.env\n"]},{"data":{"text/plain":["True"]},"execution_count":6,"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":7,"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":["THUDM/glm-4-9b-chat-1m None False datasets/mgtv results/mgtv-results_m3.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":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","\u001b[33mWARNING: Package(s) not found: flash-attn\u001b[0m\u001b[33m\n","\u001b[0mCPU times: user 3.48 ms, sys: 6.05 ms, total: 9.54 ms\n","Wall time: 634 ms\n"]}],"source":["%%time\n","!python --version\n","!pip show flash-attn"]},{"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 /Users/inflaton/code/engd/projects/logical-reasoning/llm_toolkit/logical_reasoning_utils.py\n","MPS is available\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":["loading model: THUDM/glm-4-9b-chat-1m with adapter: None\n"]},{"name":"stderr","output_type":"stream","text":["Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"]},{"data":{"application/vnd.jupyter.widget-view+json":{"model_id":"5c2efdd89c3848a99a92b1dd3597cbd1","version_major":2,"version_minor":0},"text/plain":["Loading checkpoint shards: 0%| | 0/10 [00:00<?, ?it/s]"]},"metadata":{},"output_type":"display_data"},{"name":"stdout","output_type":"stream","text":["CPU times: user 1.07 s, sys: 1.28 s, total: 2.35 s\n","Wall time: 7.08 s\n"]}],"source":["%%time\n","\n","model, tokenizer = load_model(model_name, adapter_name_or_path=adapter_name_or_path, using_llama_factory=False)"]},{"cell_type":"code","execution_count":11,"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: 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":12,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["--------------------------------------------------\n","text: 甄加索是自杀吗\n","--------------------------------------------------\n","label: 不是\n","--------------------------------------------------\n","answer: nan\n","--------------------------------------------------\n","title: 海岸之谜\n","--------------------------------------------------\n","puzzle: 在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任何打斗的迹象。请问甄加索的死因是什么？\n","--------------------------------------------------\n","truth: 甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在创作一幅描绘海洋生物的画作。在画即将完成的前一天晚上，他骑着自行车外出，打算在海边观赏夜景。然而，他在沙滩上意外发现了一只搁浅的海豚，为了救助这只海豚，他耗费了极大的体力，最终成功将其送回海中。筋疲力尽的甄加索在沙滩上睡着了，由于他患有严重的心脏病，却未告知旁人，在寒冷的海风中，他的心脏停止了跳动。因此，警方在现场只发现了车轮痕迹和未完成的画作，而没有发现任何他杀的迹象。\n","--------------------------------------------------\n","train_text: [gMASK]<sop><|system|>\n","You are an expert in logical reasoning.<|user|>\n","你是一个情景猜谜游戏的主持人。游戏规则如下：\n","\n","1. 参与者会得到一个谜面，谜面会描述一个简单又难以理解的事件。\n","2. 主持人知道谜底，谜底是谜面的答案。\n","3. 参与者可以询问任何封闭式问题来找寻事件的真相。\n","4. 对于每个问题，主持人将根据实际情况回答以下五个选项之一：是、不是、不重要、回答正确、问法错误。各回答的判断标准如下：\n"," - 若谜面和谜底能找到问题的答案，回答：是或者不是\n"," - 若谜面和谜底不能直接或者间接推断出问题的答案，回答：不重要\n"," - 若参与者提问不是一个封闭式问题或者问题难以理解，回答：问法错误\n"," - 若参与者提问基本还原了谜底真相，回答：回答正确\n","5. 回答中不能添加任何其它信息，也不能省略选项中的任何一个字。例如，不可以把“不是”省略成“不”。\n","\n","请严格按照这些规则回答参与者提出的问题。\n","\n","**谜面:** 在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任何打斗的迹象。请问甄加索的死因是什么？\n","\n","**谜底:** 甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在创作一幅描绘海洋生物的画作。在画即将完成的前一天晚上，他骑着自行车外出，打算在海边观赏夜景。然而，他在沙滩上意外发现了一只搁浅的海豚，为了救助这只海豚，他耗费了极大的体力，最终成功将其送回海中。筋疲力尽的甄加索在沙滩上睡着了，由于他患有严重的心脏病，却未告知旁人，在寒冷的海风中，他的心脏停止了跳动。因此，警方在现场只发现了车轮痕迹和未完成的画作，而没有发现任何他杀的迹象。\n","\n","**参与者提出的问题:** 甄加索是自杀吗\n","<|assistant|>不是<|endoftext|>\n","--------------------------------------------------\n","prompt: [gMASK]<sop><|system|>\n","You are an expert in logical reasoning.<|user|>\n","你是一个情景猜谜游戏的主持人。游戏规则如下：\n","\n","1. 参与者会得到一个谜面，谜面会描述一个简单又难以理解��事件。\n","2. 主持人知道谜底，谜底是谜面的答案。\n","3. 参与者可以询问任何封闭式问题来找寻事件的真相。\n","4. 对于每个问题，主持人将根据实际情况回答以下五个选项之一：是、不是、不重要、回答正确、问法错误。各回答的判断标准如下：\n"," - 若谜面和谜底能找到问题的答案，回答：是或者不是\n"," - 若谜面和谜底不能直接或者间接推断出问题的答案，回答：不重要\n"," - 若参与者提问不是一个封闭式问题或者问题难以理解，回答：问法错误\n"," - 若参与者提问基本还原了谜底真相，回答：回答正确\n","5. 回答中不能添加任何其它信息，也不能省略选项中的任何一个字。例如，不可以把“不是”省略成“不”。\n","\n","请严格按照这些规则回答参与者提出的问题。\n","\n","**谜面:** 在远离城市喧嚣的海边小屋，一天清晨，邻居发现甄加索僵卧在沙滩上，已无生命迹象。现场没有发现任何打斗的迹象。请问甄加索的死因是什么？\n","\n","**谜底:** 甄加索是一位热爱自然的画家，他每年都会来到这个海边小屋寻找灵感。在他生命的最后几天，他一直在创作一幅描绘海洋生物的画作。在画即将完成的前一天晚上，他骑着自行车外出，打算在海边观赏夜景。然而，他在沙滩上意外发现了一只搁浅的海豚，为了救助这只海豚，他耗费了极大的体力，最终成功将其送回海中。筋疲力尽的甄加索在沙滩上睡着了，由于他患有严重的心脏病，却未告知旁人，在寒冷的海风中，他的心脏停止了跳动。因此，警方在现场只发现了车轮痕迹和未完成的画作，而没有发现任何他杀的迹象。\n","\n","**参与者提出的问题:** 甄加索是自杀吗\n","<|assistant|>\n"]}],"source":["print_row_details(datasets[\"test\"].to_pandas())"]},{"cell_type":"code","execution_count":13,"metadata":{},"outputs":[],"source":["def evaluate_model(model, tokenizer, model_name, dataset, batch_size=1):\n"," print(f\"Evaluating model: {model_name} on {device}\")\n"," predictions = eval_model(\n"," model, tokenizer, dataset, device=device, batch_size=batch_size\n"," )\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":14,"metadata":{},"outputs":[{"name":"stderr","output_type":"stream","text":["/Users/inflaton/anaconda3/envs/logical-reasoning/lib/python3.11/site-packages/transformers/generation/utils.py:1513: UserWarning: The operator 'aten::isin.Tensor_Tensor_out' is not currently supported on the MPS backend and will fall back to run on the CPU. This may have performance implications. (Triggered internally at /Users/runner/work/pytorch/pytorch/pytorch/aten/src/ATen/mps/MPSFallback.mm:13.)\n"," if eos_token_id is not None and torch.isin(elements=eos_token_id, test_elements=pad_token_id).any():\n"]},{"name":"stdout","output_type":"stream","text":["\n","是\n","CPU times: user 888 ms, sys: 312 ms, total: 1.2 s\n","Wall time: 2.29 s\n"]},{"ename":"","evalue":"","output_type":"error","traceback":["\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n","\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n","\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n","\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."]}],"source":["%%time\n","\n","prompt1 = datasets[\"test\"][\"prompt\"][1000]\n","\n","gen_kwargs = {\"max_length\": 4096, \"do_sample\": True, \"top_k\": 1}\n","with torch.no_grad():\n"," inputs = tokenizer(\n"," [prompt1],\n"," return_tensors=\"pt\",\n"," ).to(device)\n"," outputs = model.generate(**inputs, **gen_kwargs)\n"," outputs = outputs[:, inputs['input_ids'].shape[1]:]\n"," print(tokenizer.decode(outputs[0], skip_special_tokens=True))"]},{"cell_type":"code","execution_count":15,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["Evaluating model: THUDM/glm-4-9b-chat-1m on mps\n"]},{"name":"stderr","output_type":"stream","text":[" 1%| | 1/188 [01:42<5:20:47, 102.93s/it]"]},{"name":"stdout","output_type":"stream","text":["--------\n","step 1: \n","不是\n","--------\n","step 2: \n","不是\n","--------\n","step 3: \n","不是\n","--------\n","step 4: 不是\n","--------\n","step 5: 不是\n"]},{"name":"stderr","output_type":"stream","text":[" 23%|██▎ | 43/188 [3:53:29<17:57:22, 445.81s/it]"]}],"source":["%%time\n","\n","evaluate_model(model, tokenizer, f\"{model_name}{'_' + adapter_name_or_path if adapter_name_or_path else ''}\", datasets[\"test\"], batch_size=16)"]}],"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}

competition/14b_GLM-4-9b_p1_analysis.ipynb ADDED Viewed

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

competition/14c_GLM-4-9b_p2_analysis.ipynb ADDED Viewed

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

results/mgtv-glm-4-9b_p1_full_metrics.csv ADDED Viewed

	@@ -0,0 +1,6 @@

+epoch,model,accuracy,precision,recall,f1
+0,THUDM/glm-4-9b-chat-1m,0.581,0.7030063507392827,0.581,0.6169152550060966
+1,THUDM/glm-4-9b-chat-1m_checkpoint-175,0.465,0.4626983424145981,0.47806716929403703,0.45282323637311034
+2,THUDM/glm-4-9b-chat-1m_checkpoint-350,0.579,0.677205249618572,0.579,0.607768567422897
+3,THUDM/glm-4-9b-chat-1m_checkpoint-525,0.6053333333333333,0.7220227211816735,0.6053333333333333,0.6379065537566594
+4,THUDM/glm-4-9b-chat-1m_checkpoint-700,0.593,0.7202870096146446,0.593,0.631178867641037

results/mgtv-glm-4-9b_p2_full_metrics.csv ADDED Viewed

	@@ -0,0 +1,5 @@

+epoch,model,accuracy,precision,recall,f1
+0,THUDM/glm-4-9b-chat-1m,0.395,0.667648445898918,0.395,0.4583896948511759
+1,THUDM/glm-4-9b-chat-1m_checkpoint-175,0.5946666666666667,0.7056249544340455,0.5946666666666667,0.631524021431916
+2,THUDM/glm-4-9b-chat-1m_checkpoint-350,0.549,0.7006542472262678,0.549,0.595639891731556
+3,THUDM/glm-4-9b-chat-1m_checkpoint-525,0.5986666666666667,0.7150511133873729,0.5986666666666667,0.6253567774596996

results/mgtv-llama3_p2_full_metrics.csv CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f411f819fe8137dc75d5addb5b1d6e5a2244ceb0bfe87554e3b82d42dcfb4a17
-size 977

 version https://git-lfs.github.com/spec/v1
+oid sha256:fbc58da2045e8e4c69e0c9d61d4f16cddb9eca8bfa84861823e008e2dc80cb52
+size 905