{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:43:21.422682Z", "iopub.status.busy": "2025-06-03T18:43:21.422323Z", "iopub.status.idle": "2025-06-03T18:43:21.433788Z", "shell.execute_reply": "2025-06-03T18:43:21.433436Z", "shell.execute_reply.started": "2025-06-03T18:43:21.422664Z" } }, "outputs": [], "source": [ "# setup autoload\n", "%load_ext autoreload\n", "%autoreload 2" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:21.040680Z", "start_time": "2024-05-16T13:58:19.777010Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:43:21.434457Z", "iopub.status.busy": "2025-06-03T18:43:21.434202Z", "iopub.status.idle": "2025-06-03T18:43:23.188013Z", "shell.execute_reply": "2025-06-03T18:43:23.187655Z", "shell.execute_reply.started": "2025-06-03T18:43:21.434445Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "The autoreload extension is already loaded. To reload it, use:\n", " %reload_ext autoreload\n" ] } ], "source": [ "import ast\n", "import os\n", "import shutil\n", "import sys\n", "from collections import defaultdict\n", "\n", "import json\n", "import numpy as np\n", "import pandas as pd\n", "\n", "sys.path.append(\"/home/tony/Work/tony/Preference\")\n", "from preference_data_preparation_4min_30b_task import *\n", "from preference_helper import *\n", "from sklearn.model_selection import train_test_split\n", "from suno_utils.utils.s3 import download_s3_files\n", "from suno_utils.utils.text import read_json, read_jsonl, write_json, write_jsonl\n", "from tqdm import tqdm\n", "\n", "pd.set_option(\"display.max_rows\", 500)\n", "pd.set_option(\"display.max_columns\", 500)\n", "pd.set_option(\"display.width\", 1000)\n", "\n", "# setup autoload\n", "%load_ext autoreload\n", "%autoreload 2\n", "\n", "\n", "def custom_parse(x):\n", " try:\n", " return json.loads(x)\n", " except:\n", " return {}" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:21.082172Z", "start_time": "2024-05-16T13:58:21.041926Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:43:23.188700Z", "iopub.status.busy": "2025-06-03T18:43:23.188396Z", "iopub.status.idle": "2025-06-03T18:43:23.245326Z", "shell.execute_reply": "2025-06-03T18:43:23.244958Z", "shell.execute_reply.started": "2025-06-03T18:43:23.188686Z" } }, "outputs": [], "source": [ "OUT_DATA_DIR = \"/app/suno/data/dpo/auk_mix_t1_v14\"\n", "os.makedirs(OUT_DATA_DIR, exist_ok=True)\n", "shutil.copyfile(\n", " \"/app/suno/data/dpo/7v_v20_full/tokenizer_60k.json\",\n", " os.path.join(OUT_DATA_DIR, \"tokenizer_60k.json\"),\n", ")\n", "NPZ_DIR = \"/app/suno/data/dpo/30b_npz\"\n", "# NOTE FOR 30b we increase this from 6016 up\n", "N_TOKENS_AUDIO = 6016" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:53.962528Z", "start_time": "2024-05-16T13:58:21.105919Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:43:23.246328Z", "iopub.status.busy": "2025-06-03T18:43:23.246152Z", "iopub.status.idle": "2025-06-03T18:43:37.586617Z", "shell.execute_reply": "2025-06-03T18:43:37.586255Z", "shell.execute_reply.started": "2025-06-03T18:43:23.246316Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Preference data shape (931852, 90)\n" ] } ], "source": [ "df = pd.read_pickle(\n", " \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250501_full_long.pkl\"\n", ")\n", "print(\"Preference data shape\", df.shape)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:43:37.587228Z", "iopub.status.busy": "2025-06-03T18:43:37.587012Z", "iopub.status.idle": "2025-06-03T18:43:39.597769Z", "shell.execute_reply": "2025-06-03T18:43:39.597399Z", "shell.execute_reply.started": "2025-06-03T18:43:37.587215Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(931852, 90) (465684, 90)\n", "after date cut (465684, 90)\n" ] } ], "source": [ "df[\"created_at\"] = pd.to_datetime(df[\"created_at\"], utc=True)\n", "cutoff_date = pd.to_datetime(\"2025-04-12\", utc=True)\n", "# cutoff_date = pd.to_datetime(\"2025-04-17\", utc=True)\n", "print(df.shape, df[df[\"created_at\"] >= cutoff_date].shape)\n", "df = df[(df[\"created_at\"] >= cutoff_date)].copy()\n", "print(\"after date cut\", df.shape)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:43:39.602984Z", "iopub.status.busy": "2025-06-03T18:43:39.602745Z", "iopub.status.idle": "2025-06-03T18:43:40.429557Z", "shell.execute_reply": "2025-06-03T18:43:40.429193Z", "shell.execute_reply.started": "2025-06-03T18:43:39.602970Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after dropna (465684, 85)\n" ] } ], "source": [ "df = df.dropna(axis=1, how=\"all\")\n", "print(\"after dropna\", df.shape)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.199480Z", "start_time": "2024-05-16T13:58:53.963687Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:43:40.430543Z", "iopub.status.busy": "2025-06-03T18:43:40.430301Z", "iopub.status.idle": "2025-06-03T18:49:02.664583Z", "shell.execute_reply": "2025-06-03T18:49:02.664215Z", "shell.execute_reply.started": "2025-06-03T18:43:40.430530Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "6442462\n", "6442462\n", "pre-downloaded df (465684, 85)\n", "downloaded df (465683, 85)\n" ] } ], "source": [ "converted_paths = os.listdir(NPZ_DIR)\n", "print(len(converted_paths))\n", "\n", "converted_paths = set([f.replace(\".npz\", \"\") for f in converted_paths])\n", "print(len(converted_paths))\n", "\n", "print(\"pre-downloaded df\", df.shape)\n", "df[df[\"s3_id\"].isin(converted_paths)].shape\n", "df = df[df[\"s3_id\"].isin(converted_paths)].copy()\n", "print(\"downloaded df\", df.shape)" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.467253Z", "start_time": "2024-05-16T13:58:56.207647Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:49:02.665136Z", "iopub.status.busy": "2025-06-03T18:49:02.664973Z", "iopub.status.idle": "2025-06-03T18:49:03.822609Z", "shell.execute_reply": "2025-06-03T18:49:03.822260Z", "shell.execute_reply.started": "2025-06-03T18:49:02.665123Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_30b\n", "True 465683\n", "Name: count, dtype: int64\n" ] }, { "data": { "text/plain": [ "task\n", "cover 256083\n", "artist_consistency 182810\n", "infill 26786\n", "artist_extend 4\n", "Name: count, dtype: int64" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"is_30b\"] = df[\"model_name\"].str.contains(\"-t\")\n", "print(df[\"is_30b\"].value_counts())\n", "df[\"task\"].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# LET's do the data prep" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:49:03.823240Z", "iopub.status.busy": "2025-06-03T18:49:03.823001Z", "iopub.status.idle": "2025-06-03T18:49:03.836953Z", "shell.execute_reply": "2025-06-03T18:49:03.836653Z", "shell.execute_reply.started": "2025-06-03T18:49:03.823228Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(465683, 86)\n" ] } ], "source": [ "# drop extend for now\n", "# reason is -- cause they are likely caused by extend from 13b\n", "# we don't want contamination\n", "# df = df[df[\"task\"] != \"extend\"].copy()\n", "print(df.shape)" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.592883Z", "start_time": "2024-05-16T13:58:56.470781Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:49:03.837446Z", "iopub.status.busy": "2025-06-03T18:49:03.837271Z", "iopub.status.idle": "2025-06-03T18:49:03.996198Z", "shell.execute_reply": "2025-06-03T18:49:03.995838Z", "shell.execute_reply.started": "2025-06-03T18:49:03.837434Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "preference model_name \n", "False chirp-v4-h-t-6 232842\n", "True chirp-v4-h-t-6 232841\n", "Name: count, dtype: int64\n", "before filter on model name (465683, 86)\n", "after filter on model name (465683, 86)\n" ] } ], "source": [ "## for 13b this is easy for now\n", "print(df.groupby([\"preference\"])[\"model_name\"].value_counts())\n", "print(\"before filter on model name\", df.shape)\n", "df = df[df[\"model_name\"].isin([\"chirp-v4-h-t-6\", \"chirp-v3p5-engine-t-6\"])]\n", "# df = df[df[\"model_name\"].isin([\"chirp-v3p5-engine-t-6\"])]\n", "print(\"after filter on model name\", df.shape)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:49:03.996770Z", "iopub.status.busy": "2025-06-03T18:49:03.996573Z", "iopub.status.idle": "2025-06-03T18:49:04.012270Z", "shell.execute_reply": "2025-06-03T18:49:04.011995Z", "shell.execute_reply.started": "2025-06-03T18:49:03.996758Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 454090\n", "True 11593\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(df[\"is_public\"].value_counts())\n", "# remove public for now cause fucking users\n", "# df = df[~df[\"is_public\"]]" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.909539Z", "start_time": "2024-05-16T13:58:56.595736Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:49:04.012734Z", "iopub.status.busy": "2025-06-03T18:49:04.012579Z", "iopub.status.idle": "2025-06-03T18:49:04.624021Z", "shell.execute_reply": "2025-06-03T18:49:04.623628Z", "shell.execute_reply.started": "2025-06-03T18:49:04.012723Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "before filter on request id pairs (465683, 86)\n", "after filter on request id pairs (465682, 86)\n", "preference model_name \n", "False chirp-v4-h-t-6 232841\n", "True chirp-v4-h-t-6 232841\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(\"before filter on request id pairs\", df.shape)\n", "df = df[\n", " df[\"request_id\"].isin(\n", " df[\"request_id\"].value_counts().index[df[\"request_id\"].value_counts() == 2]\n", " )\n", "]\n", "print(\"after filter on request id pairs\", df.shape)\n", "print(df.groupby([\"preference\"])[\"model_name\"].value_counts())\n", "assert df.shape[0] == df[\"request_id\"].nunique() * 2" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:49:04.625796Z", "iopub.status.busy": "2025-06-03T18:49:04.625607Z", "iopub.status.idle": "2025-06-03T18:50:15.511358Z", "shell.execute_reply": "2025-06-03T18:50:15.510996Z", "shell.execute_reply.started": "2025-06-03T18:49:04.625783Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "unique_requests 232841\n", "before removing duplicates (465682, 160)\n", "after removing duplicates (465682, 153)\n" ] } ], "source": [ "# Let's use the old selection for now -- for quality assurance\n", "# expand the metadata columns -- this takes forever...~ 6 mins\n", "# test_slice = df[\"metadata\"].apply(lambda x: ast.literal_eval(str(x)))\n", "# test_slice = df[\"metadata\"].apply(lambda x: custom_parse(x))\n", "test_slice = df[\"metadata\"] # .apply(lambda x: custom_parse(x))\n", "test_slice_series = test_slice.apply(pd.Series)\n", "df = pd.concat([df, test_slice_series], axis=1, join=\"inner\")\n", "print(\"unique_requests\", df[\"request_id\"].nunique())\n", "# remove the duplicates\n", "print(\"before removing duplicates\", df.shape)\n", "df = df.loc[:, ~df.columns.duplicated()].copy()\n", "print(\"after removing duplicates\", df.shape)" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:15.512060Z", "iopub.status.busy": "2025-06-03T18:50:15.511749Z", "iopub.status.idle": "2025-06-03T18:50:16.319307Z", "shell.execute_reply": "2025-06-03T18:50:16.318970Z", "shell.execute_reply.started": "2025-06-03T18:50:15.512047Z" } }, "outputs": [ { "data": { "text/plain": [ "task\n", "cover 256082\n", "artist_consistency 182810\n", "infill 26786\n", "artist_extend 4\n", "Name: count, dtype: int64" ] }, "execution_count": 14, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"task\"].value_counts()" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:16.319885Z", "iopub.status.busy": "2025-06-03T18:50:16.319685Z", "iopub.status.idle": "2025-06-03T18:50:17.187823Z", "shell.execute_reply": "2025-06-03T18:50:17.187497Z", "shell.execute_reply.started": "2025-06-03T18:50:16.319873Z" } }, "outputs": [ { "data": { "text/plain": [ "pos_diff_preference\n", "1.0 161927\n", "2.0 70914\n", "Name: count, dtype: int64" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df = df.sort_values(by=[\"request_id\", \"preference\", \"diff_preference\"])\n", "df[\"pos_diff_preference\"] = df[\"diff_preference\"].diff()\n", "# df[\"cer_diff_preference\"] = df[\"cer\"].diff()\n", "df[df[\"preference\"]][\"pos_diff_preference\"].value_counts()" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:17.188415Z", "iopub.status.busy": "2025-06-03T18:50:17.188181Z", "iopub.status.idle": "2025-06-03T18:50:17.489079Z", "shell.execute_reply": "2025-06-03T18:50:17.488721Z", "shell.execute_reply.started": "2025-06-03T18:50:17.188402Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive param_experiment\n", "text_1 5758\n", "temp_s_80 5605\n", "temp_s_70 5489\n", "Name: count, dtype: int64\n" ] } ], "source": [ "try:\n", " print(\"positive\", df[df[\"preference\"]][\"param_experiment\"].value_counts())\n", "except:\n", " pass" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:17.489680Z", "iopub.status.busy": "2025-06-03T18:50:17.489479Z", "iopub.status.idle": "2025-06-03T18:50:30.989567Z", "shell.execute_reply": "2025-06-03T18:50:30.989209Z", "shell.execute_reply.started": "2025-06-03T18:50:17.489667Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found 39551 duplicated prompts 19776 unique requests\n", "Found 9451 request_ids with duplicate prompts but not highest play counts in their group\n", "['fa5aba0d-4424-438b-9f87-ba5d0ef503cb', '115a0270-2735-43a2-80d4-05b371926471', '14e7fadb-f34c-4f26-9bda-c378283f529a', '90a5dfe0-d1ba-4a62-9813-936e80ccabb8', '5c18e378-278c-4a9c-a60c-7c9508bbfaf3', 'f3edfa94-39fe-4c6b-b00d-7aea44f16447', '6897cd2a-59ee-4a54-831f-4e0f56ea74e1', '19726b9e-0f6e-4638-91f2-18d0a9d02050', '266d9dbb-ace9-42fe-b92e-e04d0d9bd3a8', 'a982e31f-1ff4-4503-83de-14cbe0a11f55']\n", "Before dedup user gen requests 465682\n", "After dedup user gen requests 465682\n" ] } ], "source": [ "# Find duplicated prompts with count > 2\n", "duplicate_entries = df.groupby(\n", " [\"user_id\", \"prompt_text\", \"tags\", \"task\", \"edited_clip_id\"]\n", ").filter(lambda x: len(x) > 2)\n", "print(\n", " \"Found\",\n", " len(duplicate_entries),\n", " \"duplicated prompts\",\n", " len(duplicate_entries[\"request_id\"].unique()),\n", " \"unique requests\",\n", ")\n", "\n", "# Group by user_id, prompt_text, and tags to find duplicate prompt groups\n", "prompt_groups = duplicate_entries.groupby(\n", " [\"user_id\", \"prompt_text\", \"tags\", \"task\", \"edited_clip_id\"]\n", ")\n", "\n", "# For each prompt group, find the request_id with the highest total reaction_play_count\n", "low_play_count_request_ids = []\n", "for prompt_key, prompt_group in prompt_groups:\n", " # Get the sum of reaction_play_count for each request_id in this group\n", " request_play_counts = prompt_group.groupby(\"request_id\")[\n", " \"reaction_play_count\"\n", " ].sum()\n", "\n", " # Find the max play count in this group\n", " max_play_count = request_play_counts.max()\n", "\n", " # Add request_ids that don't have the max play count to our filter list\n", " lower_play_count_request_ids = request_play_counts[\n", " request_play_counts < max_play_count\n", " ].index.tolist()\n", " low_play_count_request_ids.extend(lower_play_count_request_ids)\n", "\n", "# Display the filtered request IDs\n", "print(\n", " f\"Found {len(low_play_count_request_ids)} request_ids with duplicate prompts but not highest play counts in their group\"\n", ")\n", "print(\n", " low_play_count_request_ids[:10]\n", " if len(low_play_count_request_ids) > 10\n", " else low_play_count_request_ids\n", ")\n", "print(\"Before dedup user gen requests\", df.shape[0])\n", "# df = df[~df[\"request_id\"].isin(low_play_count_request_ids)]\n", "print(\"After dedup user gen requests\", df.shape[0])" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:40.799375Z", "start_time": "2024-05-16T13:59:36.394236Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:30.990093Z", "iopub.status.busy": "2025-06-03T18:50:30.989949Z", "iopub.status.idle": "2025-06-03T18:50:33.107667Z", "shell.execute_reply": "2025-06-03T18:50:33.107316Z", "shell.execute_reply.started": "2025-06-03T18:50:30.990080Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "11875\n", "good_continue_at\n", "True 465682\n", "Name: count, dtype: int64\n", "\n", " Check some basics... \n", " preference\n", "False 232841\n", "True 232841\n", "Name: count, dtype: int64 is_30b\n", "True 465682\n", "Name: count, dtype: int64 model_name\n", "chirp-v4-h-t-6 465682\n", "Name: count, dtype: int64 preference model_name \n", "False chirp-v4-h-t-6 232841\n", "True chirp-v4-h-t-6 232841\n", "Name: count, dtype: int64\n", "task\n", "cover 256082\n", "artist_consistency 182810\n", "infill 26786\n", "artist_extend 4\n", "Name: count, dtype: int64\n" ] } ], "source": [ "df[\"id\"] = df[\"str_id\"]\n", "# get the original duration of the clips, if they are concacted\n", "df[\"original_duration_s\"] = df[\"total_start_s\"] + df[\"duration\"]\n", "# classify the continue at behavoirs by the duration choice\n", "audio_prompt_id_to_continue_at = {}\n", "\n", "for _, row in df[~df[\"continued_parent\"].isna()].iterrows():\n", " audio_prompt_id = row[\"continued_parent\"]\n", " if audio_prompt_id not in audio_prompt_id_to_continue_at:\n", " audio_prompt_id_to_continue_at[audio_prompt_id] = row[\"continue_at\"]\n", " else:\n", " # pick the max\n", " audio_prompt_id = max(\n", " audio_prompt_id_to_continue_at[audio_prompt_id], row[\"continue_at\"]\n", " )\n", "print(len(audio_prompt_id_to_continue_at))\n", "df[\"has_continue_and_start_continue_at\"] = df[\"id\"].apply(\n", " lambda x: audio_prompt_id_to_continue_at.get(x)\n", ")\n", "# we want continue at to be at most of the clip...\n", "df[\"good_continue_at\"] = (\n", " (df[\"has_continue_and_start_continue_at\"] / df[\"duration\"]) > 0.9\n", ") | df[\"has_continue_and_start_continue_at\"].isna()\n", "print(df[\"good_continue_at\"].value_counts())\n", "\n", "\n", "print(\n", " \"\\n Check some basics... \\n\",\n", " df[\"preference\"].value_counts(),\n", " df[\"is_30b\"].value_counts(),\n", " df[\"model_name\"].value_counts(),\n", " df.groupby([\"preference\"])[\"model_name\"].value_counts(),\n", ")\n", "\n", "df = df.sort_values(by=[\"request_id\", \"preference\"])\n", "df[\"duration_rel_diff\"] = df[\"duration\"].diff()\n", "df[\"play_rel_diff\"] = df[\"reaction_play_count\"].diff()\n", "print(df[\"task\"].value_counts())\n", "\n", "df[\"post_infill_duration\"] = (\n", " df[\"duration\"]\n", " + df[\"infill_context_end_s\"]\n", " - df[\"infill_context_start_s\"]\n", " - df[\"include_future_s\"]\n", " - df[\"include_history_s\"]\n", " - df[\"infill_dur_s\"]\n", ")" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:33.108248Z", "iopub.status.busy": "2025-06-03T18:50:33.108048Z", "iopub.status.idle": "2025-06-03T18:50:33.276257Z", "shell.execute_reply": "2025-06-03T18:50:33.275933Z", "shell.execute_reply.started": "2025-06-03T18:50:33.108235Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df[\"post_infill_duration\"].hist(bins=np.linspace(-5, 360, 100))\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.035167Z", "start_time": "2024-05-16T13:59:40.801098Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:33.276843Z", "iopub.status.busy": "2025-06-03T18:50:33.276689Z", "iopub.status.idle": "2025-06-03T18:50:34.560313Z", "shell.execute_reply": "2025-06-03T18:50:34.559953Z", "shell.execute_reply.started": "2025-06-03T18:50:33.276830Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after duration 0.9955162535807697\n", "after infill duration 0.9978977070189529\n", "neg_filter_reaction_play_count 1.0\n", "neg_filter_upvote_count 0.9901\n", "neg_filter_norm_play_frac 1.0\n", "neg_filter_continues 1.0\n", "----------------\n", "pos_filter_continues 1.0\n", "pos_filter_reaction_play_count 1.0\n", "pos_filter_relative_play_count 0.9744\n", "pos_filter_cer_diff_preference 1.0\n", "pos_filter_bad_flags 0.9999\n", "after filter on play counts 0.9731\n", "after filter on higher quality 0.3144\n", "----------------\n", "negative 229029 positive 63875\n", "----------------\n", "total pair requests 232841 --> selected pair requests 63272 frac 0.272\n" ] } ], "source": [ "normal_pos_play_count = 3\n", "# this is lower, cause a concat is probably already ensuring that it is good\n", "concat_pos_play_count = 1\n", "# this is a filter on the concated clip\n", "concat_total_play_count = 3\n", "\n", "all_fitlers = (df[\"duration\"] >= 10) & (df[\"duration\"] <= 240)\n", "print(\"after duration\", all_fitlers.sum() / df.shape[0])\n", "infill_duration_filter = (\n", " ~df[\"task\"].isin(\n", " [\n", " \"infill\",\n", " \"infill_intro\",\n", " \"infill_outro\",\n", " ]\n", " )\n", ") | (df[\"post_infill_duration\"] <= 239)\n", "print(\"after infill duration\", infill_duration_filter.sum() / df.shape[0])\n", "# negative fitlers\n", "total_negative = df[~df[\"preference\"]].shape[0]\n", "neg_filter_reaction_play_count = (~df[\"preference\"]) & (df[\"reaction_play_count\"] >= 1)\n", "print(\n", " \"neg_filter_reaction_play_count\",\n", " round(neg_filter_reaction_play_count.sum() / total_negative, 4),\n", ")\n", "neg_filter_upvote_count = (~df[\"preference\"]) & (df[\"upvote_count\"] == 0)\n", "print(\n", " \"neg_filter_upvote_count\",\n", " round(neg_filter_upvote_count.sum() / total_negative, 4),\n", ")\n", "neg_filter_norm_play_frac = (~df[\"preference\"]) & (df[\"norm_play_frac\"] <= 3.1)\n", "print(\n", " \"neg_filter_norm_play_frac\",\n", " round(neg_filter_norm_play_frac.sum() / total_negative, 4),\n", ")\n", "neg_filter_continues = (~df[\"preference\"]) & (\n", " df[\"has_continue_and_start_continue_at\"].isna()\n", ")\n", "print(\n", " \"neg_filter_continues\",\n", " round(neg_filter_continues.sum() / total_negative, 4),\n", ")\n", "\n", "neg_filter_selection_mask = (\n", " all_fitlers\n", " & infill_duration_filter\n", " & neg_filter_reaction_play_count\n", " & neg_filter_upvote_count\n", " & neg_filter_norm_play_frac\n", " & neg_filter_continues\n", ")\n", "\n", "print(\"----------------\")\n", "total_positive = df[df[\"preference\"]].shape[0]\n", "assert total_positive == total_negative\n", "pos_filter_continues = (df[\"preference\"]) & (df[\"good_continue_at\"])\n", "print(\"pos_filter_continues\", round(pos_filter_continues.sum() / total_positive, 4))\n", "pos_filter_reaction_play_count = (df[\"preference\"]) & (df[\"reaction_play_count\"] >= 1)\n", "print(\n", " \"pos_filter_reaction_play_count\",\n", " round(pos_filter_reaction_play_count.sum() / total_positive, 4),\n", ")\n", "pos_filter_relative_play_count = (df[\"preference\"]) & (df[\"play_rel_diff\"] >= 0)\n", "print(\n", " \"pos_filter_relative_play_count\",\n", " round(pos_filter_relative_play_count.sum() / total_positive, 4),\n", ")\n", "pos_filter_cer_diff_preference = (\n", " df[\n", " \"preference\"\n", " ] # & (df[\"pos_diff_preference\"] == 2) # & (df[\"cer_diff_preference\"] < 0.5) & (df[\"cer\"] < 0.99)\n", ")\n", "print(\n", " \"pos_filter_cer_diff_preference\",\n", " round(pos_filter_cer_diff_preference.sum() / total_positive, 4),\n", ")\n", "pos_filter_bad_flags = (\n", " (df[\"preference\"]) & (df[\"flag_count\"] == 0) & (df[\"dislike_count\"] == 0)\n", ")\n", "print(\n", " \"pos_filter_bad_flags\",\n", " round(pos_filter_bad_flags.sum() / total_positive, 4),\n", ")\n", "pos_filter_play_counts = (df[\"preference\"]) & (\n", " (\n", " (df[\"part_of_concat\"])\n", " & (df[\"reaction_play_count\"] >= concat_pos_play_count)\n", " & (df[\"concat_play_counts\"] >= concat_total_play_count)\n", " )\n", " | (\n", " (~df[\"part_of_concat\"]) & (df[\"reaction_play_count\"] >= normal_pos_play_count)\n", " # & (df[\"norm_play_frac\"] >= 2.1) # this is a bit of a luxury cut...\n", " )\n", " | (df[\"task\"].isin([\"infill\", \"infill_intro\", \"infill_outro\"]))\n", ")\n", "print(\n", " \"after filter on play counts\",\n", " round(pos_filter_play_counts.sum() / total_positive, 4),\n", ")\n", "high_quality_tasks_filter = (\n", " (df[\"task\"].isin([\"cover\", \"extend\", \"artist_consistency\", \"\"]))\n", " & (\n", " (df[\"upvote_count\"] >= 1) # (df[\"upvote_count\"] >= 1)\n", " | (df[\"reaction_play_count\"] >= 5)\n", " | (df[\"concat_play_counts\"] >= 5)\n", " )\n", " & (\n", " (df[\"part_of_concat\"])\n", " | (\n", " (~df[\"part_of_concat\"])\n", " & (df[\"norm_play_frac\"] >= 5.1) # this is a bit of a luxury cut...\n", " & (\n", " df[\"norm_play_frac\"] >= df[\"reaction_play_count\"] / 3\n", " ) # play duration is not low on average\n", " )\n", " )\n", ")\n", "medium_quality_tasks_filter = (\n", " df[\"task\"].isin(\n", " [\n", " \"infill\",\n", " \"infill_intro\",\n", " \"infill_outro\",\n", " ]\n", " )\n", ") & ( # let more infill through only in this case...\n", " (\n", " df[\"upvote_count\"] >= 0\n", " ) # (df[\"upvote_count\"] >= 1) (df[\"pos_diff_preference\"] == 2)\n", " | (df[\"reaction_play_count\"] >= 1)\n", " | (df[\"concat_play_counts\"] >= 1)\n", ")\n", "pos_filter_higher_quality = (df[\"preference\"]) & (\n", " high_quality_tasks_filter | medium_quality_tasks_filter\n", ")\n", "print(\n", " \"after filter on higher quality\",\n", " round(pos_filter_higher_quality.sum() / total_positive, 4),\n", ")\n", "\n", "user_gen_filter = (\n", " df[\"user_n_clips\"] >= 100\n", ") # user needs to have genereated at least 100 over the time period\n", "\n", "print(\"----------------\")\n", "pos_filter_selectin_mask = (\n", " (df[\"preference\"]) # get basics aligned\n", " & all_fitlers\n", " & infill_duration_filter\n", " & pos_filter_continues\n", " & pos_filter_reaction_play_count\n", " & pos_filter_relative_play_count\n", " & pos_filter_cer_diff_preference\n", " & pos_filter_bad_flags\n", " & pos_filter_play_counts\n", " & pos_filter_higher_quality\n", " & user_gen_filter\n", ")\n", "print(\n", " \"negative\",\n", " sum(neg_filter_selection_mask),\n", " \"positive\",\n", " sum(pos_filter_selectin_mask),\n", ")\n", "\n", "neg_filter_requests = df[neg_filter_selection_mask][\"request_id\"].unique()\n", "pos_filter_requests = df[pos_filter_selectin_mask][\"request_id\"].unique()\n", "# looking for very strong signal here:\n", "# listen to the positive/negative more than once\n", "# disliked one of the clips\n", "unique_requests = set(pos_filter_requests).intersection(neg_filter_requests)\n", "print(\"----------------\")\n", "print(\n", " \"total pair requests\",\n", " df[\"request_id\"].nunique(),\n", " \" --> selected pair requests\",\n", " len(unique_requests),\n", " f\"frac {len(unique_requests) / df['request_id'].nunique():.3f}\",\n", ")" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.250737Z", "start_time": "2024-05-16T13:59:41.036434Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:34.560925Z", "iopub.status.busy": "2025-06-03T18:50:34.560763Z", "iopub.status.idle": "2025-06-03T18:50:35.016290Z", "shell.execute_reply": "2025-06-03T18:50:35.015931Z", "shell.execute_reply.started": "2025-06-03T18:50:34.560912Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "auk_mix_t1_v14 requests 63272 clips 126544 total khrs 5.382; N gpus for 1000 iters 7.909; 4 gpus for x iters 1977.250; n unique users 26926 n pro users 26111\n" ] } ], "source": [ "df_slice = df[df[\"request_id\"].isin(set(unique_requests))].copy()\n", "print(\n", " f\"{os.path.basename(OUT_DATA_DIR)} requests\",\n", " df_slice[\"request_id\"].nunique(),\n", " \"clips\",\n", " df_slice.shape[0],\n", " f\"total khrs {sum(df_slice['duration'] / 3600 / 1000):.3f};\",\n", " f\"N gpus for 1000 iters {df_slice.shape[0] / 8 / 2 / 1000:.3f};\",\n", " f\"4 gpus for x iters {df_slice.shape[0] / 8 / 2 / 4:.3f};\",\n", " f\"n unique users {df_slice['user_id'].nunique()}\",\n", " f\"n pro users {df_slice[df_slice['is_pro_user']]['user_id'].nunique()}\",\n", ")\n", "# 76171 152342 total khrs 2.880 n gpus for 1250 iters 3.809\n", "# v10 has 78866\n", "# v14 has 110402\n", "# 30b_t4_v12 requests 47755 clips 95510 total khrs 4.555; N gpus for 1000 iters 5.969; 4 gpus for x iters 1492.344; n unique users 13790 n pro users 13526\n", "# 30b_t4_v20 requests 18306 clips 36612 total khrs 1.754; N gpus for 1000 iters 2.288; 4 gpus for x iters 572.062; n unique users 6943 n pro users 6714\n", "# 30b_t5_v5 requests 21318 clips 42636 total khrs 1.938; N gpus for 1000 iters 2.665; 4 gpus for x iters 666.188; n unique users 11661 n pro users 9347\n", "# 30b_t5_v6 requests 22833 clips 45666 total khrs 2.072; N gpus for 1000 iters 2.854; 4 gpus for x iters 713.531; n unique users 12576 n pro users 9910\n", "# 30b_t5_v7 requests 33197 clips 66394 total khrs 2.846; N gpus for 1000 iters 4.150; 4 gpus for x iters 1037.406; n unique users 16665 n pro users 13050\n", "# 30b_t5_v8 requests 20907 clips 41814 total khrs 1.629; N gpus for 1000 iters 2.613; 4 gpus for x iters 653.344; n unique users 11102 n pro users 9052\n", "# 30b_t5_v9 requests 24645 clips 49290 total khrs 1.918; N gpus for 1000 iters 3.081; 4 gpus for x iters 770.156; n unique users 12661 n pro users 10229\n", "# 30b_t5_v11 requests 21975 clips 43950 total khrs 1.508; N gpus for 1000 iters 2.747; 4 gpus for x iters 686.719; n unique users 11173 n pro users 9270\n", "# 30b_t5_v12 requests 21436 clips 42872 total khrs 1.582; N gpus for 1000 iters 2.679; 4 gpus for x iters 669.875; n unique users 11553 n pro users 9374\n", "# 30b_t5_v13 requests 25912 clips 51824 total khrs 1.922; N gpus for 1000 iters 3.239; 4 gpus for x iters 809.750; n unique users 13429 n pro users 10737\n", "# 30b_t5_v14 requests 27687 clips 55374 total khrs 2.036; N gpus for 1000 iters 3.461; 4 gpus for x iters 865.219; n unique users 14196 n pro users 11227\n", "# 30b_t5_v15 requests 29563 clips 59126 total khrs 2.225; N gpus for 1000 iters 3.695; 4 gpus for x iters 923.844; n unique users 14684 n pro users 11642\n", "# 30b_t6_v1 requests 24678 clips 49356 total khrs 1.934; N gpus for 1000 iters 3.085; 4 gpus for x iters 771.188; n unique users 11350 n pro users 10065\n", "# 30b_t6_v2 requests 49341 clips 98682 total khrs 4.332; N gpus for 1000 iters 6.168; 4 gpus for x iters 1541.906; n unique users 19992 n pro users 16972\n", "# 30b_t6_v3 requests 54967 clips 109934 total khrs 4.826; N gpus for 1000 iters 6.871; 4 gpus for x iters 1717.719; n unique users 21653 n pro users 18266\n", "# 30b_t6_v5 requests 29459 clips 58918 total khrs 2.657; N gpus for 1000 iters 3.682; 4 gpus for x iters 920.594; n unique users 14091 n pro users 11884\n", "# 30b_t6_v7 requests 40056 clips 80112 total khrs 3.354; N gpus for 1000 iters 5.007; 4 gpus for x iters 1251.750; n unique users 17440 n pro users 14476\n", "# 30b_t6_v8 requests 31681 clips 63362 total khrs 2.681; N gpus for 1000 iters 3.960; 4 gpus for x iters 990.031; n unique users 15180 n pro users 15078\n", "# 30b_t6_v9 requests 55785 clips 111570 total khrs 4.727; N gpus for 1000 iters 6.973; 4 gpus for x iters 1743.281; n unique users 23114 n pro users 22871\n", "# 30b_t6_v10 requests 52209 clips 104418 total khrs 4.515; N gpus for 1000 iters 6.526; 4 gpus for x iters 1631.531; n unique users 22216 n pro users 21893\n", "# 30b_t6_v11 requests 31338 clips 62676 total khrs 2.493; N gpus for 1000 iters 3.917; 4 gpus for x iters 979.312; n unique users 15190 n pro users 14973\n", "# 30b_t6_v13 requests 50856 clips 101712 total khrs 3.987; N gpus for 1000 iters 6.357; 4 gpus for x iters 1589.250; n unique users 23547 n pro users 23097\n", "# 30b_t6_v15 requests 65213 clips 130426 total khrs 5.217; N gpus for 1000 iters 8.152; 4 gpus for x iters 2037.906; n unique users 28763 n pro users 27964\n", "# 30b_t6_v16 requests 37907 clips 75814 total khrs 2.956; N gpus for 1000 iters 4.738; 4 gpus for x iters 1184.594; n unique users 18448 n pro users 17212\n", "# 30b_t6_v17 requests 51543 clips 103086 total khrs 4.154; N gpus for 1000 iters 6.443; 4 gpus for x iters 1610.719; n unique users 24223 n pro users 21829\n", "# 30b_t6_v18 requests 94965 clips 189930 total khrs 7.483; N gpus for 1000 iters 11.871; 4 gpus for x iters 2967.656; n unique users 23852 n pro users 21767\n", "# 30b_t6_v19 requests 34289 clips 68578 total khrs 2.846; N gpus for 1000 iters 4.286; 4 gpus for x iters 1071.531; n unique users 11802 n pro users 10830\n", "# 30b_t6_v20 requests 53258 clips 106516 total khrs 4.270; N gpus for 1000 iters 6.657; 4 gpus for x iters 1664.312; n unique users 22096 n pro users 21171\n", "# 30b_t6_v22 requests 29971 clips 59942 total khrs 1.992; N gpus for 1000 iters 3.746; 4 gpus for x iters 936.594; n unique users 13611 n pro users 13036\n", "# 30b_t6_v24 requests 45333 clips 90666 total khrs 3.343; N gpus for 1000 iters 5.667; 4 gpus for x iters 1416.656; n unique users 18853 n pro users 18049\n", "# 30b_t6_v25 requests 28154 clips 56308 total khrs 2.401; N gpus for 1000 iters 3.519; 4 gpus for x iters 879.812; n unique users 12946 n pro users 12361\n", "# 30b_t6_v26 requests 30428 clips 60856 total khrs 2.599; N gpus for 1000 iters 3.804; 4 gpus for x iters 950.875; n unique users 13822 n pro users 13163\n", "# 30b_t6_v27 requests 43731 clips 87462 total khrs 3.862; N gpus for 1000 iters 5.466; 4 gpus for x iters 1366.594; n unique users 17898 n pro users 16865\n", "# 30b_t6_v28 requests 56869 clips 113738 total khrs 5.064; N gpus for 1000 iters 7.109; 4 gpus for x iters 1777.156; n unique users 22004 n pro users 20244\n", "# 30b_t6_v29 requests 32729 clips 65458 total khrs 2.604; N gpus for 1000 iters 4.091; 4 gpus for x iters 1022.781; n unique users 13739 n pro users 13503\n", "# 30b_t6_v30 requests 32553 clips 65106 total khrs 2.592; N gpus for 1000 iters 4.069; 4 gpus for x iters 1017.281; n unique users 13712 n pro users 13478\n", "# 30b_t6_v31 requests 41523 clips 83046 total khrs 3.164; N gpus for 1000 iters 5.190; 4 gpus for x iters 1297.594; n unique users 16266 n pro users 15967\n", "# 30b_t6_v32 requests 55942 clips 111884 total khrs 4.361; N gpus for 1000 iters 6.993; 4 gpus for x iters 1748.188; n unique users 20808 n pro users 20271\n", "# 30b_t6_v33 requests 182096 clips 364192 total khrs 13.745; N gpus for 1000 iters 22.762; 4 gpus for x iters 5690.500; n unique users 40437 n pro users 34524\n", "# auk_mix_t1_v2 requests 102002 clips 204004 total khrs 9.191; N gpus for 1000 iters 12.750; 4 gpus for x iters 3187.562; n unique users 36408 n pro users 34038\n", "# auk_mix_t1_v13 requests 53011 clips 106022 total khrs 4.496; N gpus for 1000 iters 6.626; 4 gpus for x iters 1656.594; n unique users 23713 n pro users 23117\n", "# auk_mix_t1_v14 requests 63272 clips 126544 total khrs 5.382; N gpus for 1000 iters 7.909; 4 gpus for x iters 1977.250; n unique users 26926 n pro users 26111" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.277006Z", "start_time": "2024-05-16T13:59:41.252105Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:35.016936Z", "iopub.status.busy": "2025-06-03T18:50:35.016692Z", "iopub.status.idle": "2025-06-03T18:50:35.067301Z", "shell.execute_reply": "2025-06-03T18:50:35.066966Z", "shell.execute_reply.started": "2025-06-03T18:50:35.016922Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive in playlist (13493, 159)\n", "task\n", "cover 53704\n", "artist_consistency 51122\n", "infill 21718\n", "Name: count, dtype: int64\n" ] } ], "source": [ "test_mask = (df_slice[\"preference\"]) & (\n", " (df_slice[\"is_in_playlist\"]) | (df_slice[\"concat_in_playlist\"])\n", ")\n", "print(\"positive in playlist\", df_slice[test_mask].shape)\n", "print(df_slice[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.067867Z", "iopub.status.busy": "2025-06-03T18:50:35.067676Z", "iopub.status.idle": "2025-06-03T18:50:35.201249Z", "shell.execute_reply": "2025-06-03T18:50:35.200924Z", "shell.execute_reply.started": "2025-06-03T18:50:35.067854Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "df_slice[\"post_infill_duration\"].hist(bins=np.linspace(-5, 300, 100))\n", "plt.show()" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.323409Z", "start_time": "2024-05-16T13:59:41.278278Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:35.201815Z", "iopub.status.busy": "2025-06-03T18:50:35.201622Z", "iopub.status.idle": "2025-06-03T18:50:35.215331Z", "shell.execute_reply": "2025-06-03T18:50:35.215061Z", "shell.execute_reply.started": "2025-06-03T18:50:35.201801Z" } }, "outputs": [], "source": [ "# interesting_clips_must_be_positive_mask = (\n", "# (df_slice[\"upvoted\"] == True)\n", "# | (df_slice[\"has_action\"] == True)\n", "# | (df_slice[\"part_of_concat\"] == True)\n", "# )\n", "# interesting_clips_must_be_not_negative_mask = (df_slice[\"downvoted\"] == False) # & (df_slice[\"dislike_count\"] < 1)\n", "# interesting_clips_mask = interesting_clips_must_be_positive_mask & interesting_clips_must_be_not_negative_mask\n", "# assert interesting_clips_mask.eq(df_slice[\"preference\"]).all()" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.392244Z", "start_time": "2024-05-16T13:59:41.324472Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:35.215816Z", "iopub.status.busy": "2025-06-03T18:50:35.215644Z", "iopub.status.idle": "2025-06-03T18:50:35.225703Z", "shell.execute_reply": "2025-06-03T18:50:35.225448Z", "shell.execute_reply.started": "2025-06-03T18:50:35.215805Z" } }, "outputs": [], "source": [ "# save positive ids\n", "# positive_preference_ids = df_slice[df_slice[\"preference\"] == False][\"s3_id\"].to_json(orient='values')\n", "# with open('/home/tony/Data/Preference/7b_v2/7v_v20_full_recut_id_negative.json', 'w') as file:\n", "# file.write(positive_preference_ids)" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.226170Z", "iopub.status.busy": "2025-06-03T18:50:35.226004Z", "iopub.status.idle": "2025-06-03T18:50:35.235969Z", "shell.execute_reply": "2025-06-03T18:50:35.235713Z", "shell.execute_reply.started": "2025-06-03T18:50:35.226159Z" } }, "outputs": [], "source": [ "# df_slice_2 = pd.read_pickle(\"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_t_6_20241118_full_slice.pkl\")\n", "# df_total = pd.concat([df_slice, df_slice_2])\n", "# print(df_total.shape)\n", "# df_slice = df_total" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.236465Z", "iopub.status.busy": "2025-06-03T18:50:35.236269Z", "iopub.status.idle": "2025-06-03T18:50:35.246348Z", "shell.execute_reply": "2025-06-03T18:50:35.246094Z", "shell.execute_reply.started": "2025-06-03T18:50:35.236454Z" } }, "outputs": [], "source": [ "# df_slice_prev = pd.read_pickle(\n", "# \"/home/tony/Data/Preference/30b_v2/interesting_clips_v4_t_3_v13_20240902_slice.pkl\"\n", "# )\n", "# df_slice_prev = df_slice_prev[\n", "# (\n", "# (df_slice_prev[\"task\"] != \"infill\")\n", "# & (df_slice_prev[\"task\"] != \"cover\")\n", "# & (df_slice_prev[\"task\"] != \"artist_consistency\")\n", "# )\n", "# ].copy()\n", "# df_slice = pd.concat([df_slice, df_slice_prev])\n", "# print(df_slice.shape)\n", "# print(df_slice[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.246835Z", "iopub.status.busy": "2025-06-03T18:50:35.246651Z", "iopub.status.idle": "2025-06-03T18:50:35.256718Z", "shell.execute_reply": "2025-06-03T18:50:35.256463Z", "shell.execute_reply.started": "2025-06-03T18:50:35.246823Z" } }, "outputs": [], "source": [ "# df_slice[(df_slice[\"preference\"]) & ((df_slice[\"task\"].str.strip() == \"\") | (df_slice[\"task\"].str.strip() == \"cover\"))].to_pickle(\n", "# \"/home/tony/Data/Preference/30b_v5/interesting_clips_v4_t_5_20241018_full_with_cer_pos_gen.pkl\"\n", "# )\n", "# df_slice[(df_slice[\"preference\"]) & ((df_slice[\"task\"].str.strip() == \"\") | (df_slice[\"task\"].str.strip() == \"cover\"))].shape" ] }, { "cell_type": "code", "execution_count": 29, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.257162Z", "iopub.status.busy": "2025-06-03T18:50:35.257016Z", "iopub.status.idle": "2025-06-03T18:50:35.267032Z", "shell.execute_reply": "2025-06-03T18:50:35.266774Z", "shell.execute_reply.started": "2025-06-03T18:50:35.257151Z" } }, "outputs": [], "source": [ "# df_slice.to_pickle(\"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250108_full_slice.pkl\")" ] }, { "cell_type": "code", "execution_count": 30, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.267490Z", "iopub.status.busy": "2025-06-03T18:50:35.267325Z", "iopub.status.idle": "2025-06-03T18:50:35.277243Z", "shell.execute_reply": "2025-06-03T18:50:35.276985Z", "shell.execute_reply.started": "2025-06-03T18:50:35.267479Z" } }, "outputs": [], "source": [ "# with open(\"/home/tony/Data/Preference/30b_v6/similarities_30b_t6.json\", \"r\") as fp:\n", "# all_similarities = json.load(fp)\n", "\n", "# df_slice[\"similarity\"] = df_slice[\"id\"].map(all_similarities)\n", "# df_cover = df_slice[df_slice[\"task\"] == \"cover\"].copy()\n", "# df_artist = df_slice[df_slice[\"task\"] == \"artist_consistency\"].copy()" ] }, { "cell_type": "code", "execution_count": 31, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.277739Z", "iopub.status.busy": "2025-06-03T18:50:35.277546Z", "iopub.status.idle": "2025-06-03T18:50:35.287627Z", "shell.execute_reply": "2025-06-03T18:50:35.287374Z", "shell.execute_reply.started": "2025-06-03T18:50:35.277728Z" } }, "outputs": [], "source": [ "# df_cover[df_cover[\"preference\"]][\"similarity\"].hist(bins=200, label=\"positive\", alpha=0.5)\n", "# df_cover[~df_cover[\"preference\"]][\"similarity\"].hist(bins=200, label=\"negative\", alpha=0.5)\n", "# plt.legend()\n", "# plt.show()\n", "# df_cover[\"similarity_diff\"] = df_cover[\"similarity\"].diff()\n", "# df_cover[df_cover[\"preference\"]][\"similarity_diff\"].hist(bins=200)\n", "# plt.show()\n", "# df_cover[\"continued_parent\"] = None\n", "# df_cover[\"continue_at\"] = -1\n", "# too_similar = (df_cover[\"similarity\"] >= 0.99)\n", "# too_different = ( df_cover[\"similarity\"] < 0.25)\n", "# too_big_difference = (df_cover[\"similarity_diff\"] < -0.2)\n", "# df_cover_drops_id = df_cover[\n", "# (df_cover[\"preference\"])\n", "# & (too_similar | too_different | too_big_difference)\n", "# ][\"s3_id\"].unique()\n", "# print(\"total rows\", df_cover.shape[0], \"total drops\", len(df_cover_drops_id))" ] }, { "cell_type": "code", "execution_count": 32, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.288082Z", "iopub.status.busy": "2025-06-03T18:50:35.287920Z", "iopub.status.idle": "2025-06-03T18:50:35.298005Z", "shell.execute_reply": "2025-06-03T18:50:35.297748Z", "shell.execute_reply.started": "2025-06-03T18:50:35.288071Z" } }, "outputs": [], "source": [ "# df_artist[df_artist[\"preference\"]][\"similarity\"].hist(bins=200, label=\"positive\", alpha=0.5)\n", "# df_artist[~df_artist[\"preference\"]][\"similarity\"].hist(bins=200, label=\"negative\", alpha=0.5)\n", "# plt.legend()\n", "# plt.show()\n", "# df_artist[\"similarity_diff\"] = df_artist[\"similarity\"].diff()\n", "# df_artist[df_artist[\"preference\"]][\"similarity_diff\"].hist(bins=200)\n", "# plt.show()\n", "# too_similar = (df_artist[\"similarity\"] >= 0.95)\n", "# too_different = ( df_artist[\"similarity\"] < 0.4)\n", "# too_big_difference = (df_artist[\"similarity_diff\"] < -0.2)\n", "# df_artist_drops_id = df_artist[\n", "# (df_artist[\"preference\"])\n", "# & (too_similar | too_different | too_big_difference)\n", "# ][\"s3_id\"].unique()\n", "# print(\"total rows\", df_artist.shape[0], \"total drops\", len(df_artist_drops_id))" ] }, { "cell_type": "code", "execution_count": 33, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.298447Z", "iopub.status.busy": "2025-06-03T18:50:35.298301Z", "iopub.status.idle": "2025-06-03T18:50:35.308335Z", "shell.execute_reply": "2025-06-03T18:50:35.308084Z", "shell.execute_reply.started": "2025-06-03T18:50:35.298436Z" } }, "outputs": [], "source": [ "# print(\"before filter on cover similarity\", df_slice.shape)\n", "# df_slice = df_slice[~df_slice[\"s3_id\"].isin(df_cover_drops_id)].copy()\n", "# print(\"after filter on cover similarity\", df_slice.shape)\n", "# df_slice = df_slice[~df_slice[\"s3_id\"].isin(df_artist_drops_id)].copy()\n", "# print(\"after filter on artist similarity\", df_slice.shape)\n", "# df_slice = df_slice[\n", "# df_slice[\"request_id\"].isin(\n", "# df_slice[\"request_id\"].value_counts().index[df_slice[\"request_id\"].value_counts() == 2]\n", "# )\n", "# ]\n", "# print(\"after filter on request id pairs\", df_slice.shape)\n", "# print(df_slice.groupby([\"preference\"])[\"model_name\"].value_counts())\n", "# assert df_slice.shape[0] == df_slice[\"request_id\"].nunique() * 2" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.308788Z", "iopub.status.busy": "2025-06-03T18:50:35.308627Z", "iopub.status.idle": "2025-06-03T18:50:35.319960Z", "shell.execute_reply": "2025-06-03T18:50:35.319700Z", "shell.execute_reply.started": "2025-06-03T18:50:35.308777Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 121494\n", "True 5050\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(df_slice[\"is_public\"].value_counts())" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:50:35.320436Z", "iopub.status.busy": "2025-06-03T18:50:35.320253Z", "iopub.status.idle": "2025-06-03T18:50:35.352175Z", "shell.execute_reply": "2025-06-03T18:50:35.351860Z", "shell.execute_reply.started": "2025-06-03T18:50:35.320425Z" } }, "outputs": [], "source": [ "df_slice[\"npz_path\"] = df_slice[\"s3_id\"].map(lambda x: f\"{NPZ_DIR}/{x}.npz\")" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T14:00:20.866354Z", "start_time": "2024-05-16T14:00:12.443344Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:50:35.352703Z", "iopub.status.busy": "2025-06-03T18:50:35.352523Z", "iopub.status.idle": "2025-06-03T18:50:35.997156Z", "shell.execute_reply": "2025-06-03T18:50:35.995850Z", "shell.execute_reply.started": "2025-06-03T18:50:35.352691Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(104826, 160)\n", "task\n", "cover 53704\n", "artist_consistency 51122\n", "Name: count, dtype: int64\n", "(104826, 160)\n", "task\n", "cover 53704\n", "artist_consistency 51122\n", "Name: count, dtype: int64\n" ] }, { "ename": "NameError", "evalue": "name 'BREAK' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[37], line 9\u001b[0m\n\u001b[1;32m 7\u001b[0m \u001b[38;5;28mprint\u001b[39m(df_slice\u001b[38;5;241m.\u001b[39mshape)\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28mprint\u001b[39m(df_slice[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtask\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mvalue_counts())\n\u001b[0;32m----> 9\u001b[0m \u001b[43mBREAK\u001b[49m\n", "\u001b[0;31mNameError\u001b[0m: name 'BREAK' is not defined" ] } ], "source": [ "# df_slice.to_pickle(\n", "# \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250426_20250501_full_long_slice.pkl\"\n", "# )\n", "print(df_slice.shape)\n", "print(df_slice[\"task\"].value_counts())\n", "df_slice = df_slice[df_slice[\"task\"].isin([\"cover\", \"artist_consistency\"])].copy()\n", "print(df_slice.shape)\n", "print(df_slice[\"task\"].value_counts())\n", "BREAK" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:22.836920Z", "iopub.status.busy": "2025-06-03T18:51:22.836662Z", "iopub.status.idle": "2025-06-03T18:51:29.217557Z", "shell.execute_reply": "2025-06-03T18:51:29.217200Z", "shell.execute_reply.started": "2025-06-03T18:51:22.836904Z" } }, "outputs": [], "source": [ "df_13b_slice = pd.read_pickle(\n", " \"/home/tony/Data/Preference/13b_v32/interesting_clips_v4_h_s_32_20250412_20250501_full_long_slice.pkl\"\n", ")\n", "print(df_13b_slice.shape)\n", "print(df_13b_slice[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:29.218356Z", "iopub.status.busy": "2025-06-03T18:51:29.218166Z", "iopub.status.idle": "2025-06-03T18:51:29.297846Z", "shell.execute_reply": "2025-06-03T18:51:29.297497Z", "shell.execute_reply.started": "2025-06-03T18:51:29.218343Z" } }, "outputs": [], "source": [ "df_30b_slice = df_slice.copy()\n", "print(df_30b_slice.shape)\n", "print(df_30b_slice[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:29.298429Z", "iopub.status.busy": "2025-06-03T18:51:29.298226Z", "iopub.status.idle": "2025-06-03T18:51:31.598782Z", "shell.execute_reply": "2025-06-03T18:51:31.598434Z", "shell.execute_reply.started": "2025-06-03T18:51:29.298416Z" } }, "outputs": [], "source": [ "df_total = pd.concat([df_13b_slice, df_30b_slice])\n", "print(df_total.shape)\n", "print(df_total[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:31.599367Z", "iopub.status.busy": "2025-06-03T18:51:31.599166Z", "iopub.status.idle": "2025-06-03T18:51:32.358937Z", "shell.execute_reply": "2025-06-03T18:51:32.358525Z", "shell.execute_reply.started": "2025-06-03T18:51:31.599353Z" } }, "outputs": [], "source": [ "df_slice = df_total.copy()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Need to kick out the ones has gpt prompt -- these are pairs with different text inputs" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932296Z", "start_time": "2024-05-16T13:59:41.932287Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:32.360028Z", "iopub.status.busy": "2025-06-03T18:51:32.359826Z", "iopub.status.idle": "2025-06-03T18:51:32.384119Z", "shell.execute_reply": "2025-06-03T18:51:32.383751Z", "shell.execute_reply.started": "2025-06-03T18:51:32.360015Z" } }, "outputs": [], "source": [ "# don't have continue at\n", "df_slice[\"request_id\"] = df_slice[\"request_id\"].astype(str)\n", "# df_slice[\"npz_path\"] = df_slice[\"npz_path\"].apply(lambda x: str(x).replace(\"_npz\", \"_npz/\"))\n", "# df_slice[df_slice[\"continue_at\"].isna()][\"request_id\"].nunique(), df_slice[\"request_id\"].nunique()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:32.384670Z", "iopub.status.busy": "2025-06-03T18:51:32.384492Z", "iopub.status.idle": "2025-06-03T18:51:33.187908Z", "shell.execute_reply": "2025-06-03T18:51:33.187547Z", "shell.execute_reply.started": "2025-06-03T18:51:32.384658Z" } }, "outputs": [], "source": [ "print(df_slice.shape)\n", "df_slice = df_slice[df_slice[\"request_id\"].apply(lambda x: len(x) > 3)]\n", "print(df_slice.shape)\n", "# df_slice = df_slice[df_slice[\"is_pro_user\"]].copy()\n", "print(df_slice.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932966Z", "start_time": "2024-05-16T13:59:41.932957Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:33.188429Z", "iopub.status.busy": "2025-06-03T18:51:33.188303Z", "iopub.status.idle": "2025-06-03T18:51:33.273381Z", "shell.execute_reply": "2025-06-03T18:51:33.273015Z", "shell.execute_reply.started": "2025-06-03T18:51:33.188416Z" } }, "outputs": [], "source": [ "final_filtered_requests = df_slice[\"request_id\"].astype(str).unique()\n", "# final_filtered_requests = df_slice[df_slice[\"is_pro_user\"]][\"request_id\"].astype(str).unique()\n", "print(len(final_filtered_requests))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.933558Z", "start_time": "2024-05-16T13:59:41.933550Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:33.273958Z", "iopub.status.busy": "2025-06-03T18:51:33.273768Z", "iopub.status.idle": "2025-06-03T18:51:33.289902Z", "shell.execute_reply": "2025-06-03T18:51:33.289634Z", "shell.execute_reply.started": "2025-06-03T18:51:33.273945Z" } }, "outputs": [], "source": [ "# df_slice.to_csv(\"/home/tony/Data/Preference/30b_v2/interesting_clips_v4_t_3_20240902_slice.csv\", index=False)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:51:33.290361Z", "iopub.status.busy": "2025-06-03T18:51:33.290209Z", "iopub.status.idle": "2025-06-03T18:51:33.300501Z", "shell.execute_reply": "2025-06-03T18:51:33.300246Z", "shell.execute_reply.started": "2025-06-03T18:51:33.290349Z" } }, "outputs": [], "source": [ "# df_slice[\"continue_at\"] = -1" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934277Z", "start_time": "2024-05-16T13:59:41.934268Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:33.300975Z", "iopub.status.busy": "2025-06-03T18:51:33.300802Z", "iopub.status.idle": "2025-06-03T18:51:34.807160Z", "shell.execute_reply": "2025-06-03T18:51:34.806809Z", "shell.execute_reply.started": "2025-06-03T18:51:33.300964Z" } }, "outputs": [], "source": [ "train_requests, val_requests = train_test_split(\n", " sorted(list(final_filtered_requests)), test_size=0.01, random_state=42\n", ")\n", "print(len(train_requests), len(val_requests))\n", "\n", "train_df = df_slice[df_slice[\"request_id\"].astype(str).isin(set(train_requests))].copy()\n", "val_df = df_slice[df_slice[\"request_id\"].astype(str).isin(set(val_requests))].copy()\n", "train_df = train_df.sort_values(by=[\"request_id\", \"preference\"])\n", "train_df = train_df # .reset_index()\n", "val_df = val_df.sort_values(by=[\"request_id\", \"preference\"])\n", "val_df = val_df # .reset_index()\n", "train_df = train_df.reset_index(drop=True)\n", "val_df = val_df.reset_index(drop=True)\n", "print(train_df.shape, val_df.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Actually make" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.935620Z", "start_time": "2024-05-16T13:59:41.935613Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:34.807744Z", "iopub.status.busy": "2025-06-03T18:51:34.807545Z", "iopub.status.idle": "2025-06-03T18:51:41.670198Z", "shell.execute_reply": "2025-06-03T18:51:41.669838Z", "shell.execute_reply.started": "2025-06-03T18:51:34.807731Z" } }, "outputs": [], "source": [ "total_duration = 0\n", "for i, row in tqdm(train_df.iterrows(), total=len(train_df)):\n", " # we need to alternate between preference: neg, pos\n", " # print(i, row)\n", " try:\n", " assert row[\"preference\"] == (i % 2 == 1)\n", " total_duration += row[\"duration\"]\n", " except Exception as E:\n", " print(i, row)\n", " print(E)\n", " raise ValueError()\n", "\n", "print(\n", " f\"{round(total_duration / 60 / 60):,} hours of {train_df.shape[0]} clips, {train_df.shape[0] / 8 / 2 / 1000} nodes, {train_df.shape[0] / 8 / 2 / 6} iters\"\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936268Z", "start_time": "2024-05-16T13:59:41.936260Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:51:41.670782Z", "iopub.status.busy": "2025-06-03T18:51:41.670586Z", "iopub.status.idle": "2025-06-03T18:52:25.994438Z", "shell.execute_reply": "2025-06-03T18:52:25.994082Z", "shell.execute_reply.started": "2025-06-03T18:51:41.670768Z" } }, "outputs": [], "source": [ "make_dataset(\n", " val_df, OUT_DATA_DIR, is_val=True, npz_dir=NPZ_DIR, t_data_memmap=N_TOKENS_AUDIO\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:52:25.994970Z", "iopub.status.busy": "2025-06-03T18:52:25.994821Z", "iopub.status.idle": "2025-06-03T18:52:26.781829Z", "shell.execute_reply": "2025-06-03T18:52:26.781430Z", "shell.execute_reply.started": "2025-06-03T18:52:25.994958Z" } }, "outputs": [], "source": [ "# test_npz = np.load(\"/app/suno/data/dpo/30b_npz/26d19085-18da-4701-af43-122684543891.npz\")\n", "# for k in test_npz.keys():\n", "# print(k)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936964Z", "start_time": "2024-05-16T13:59:41.936957Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:52:26.783432Z", "iopub.status.busy": "2025-06-03T18:52:26.783241Z", "iopub.status.idle": "2025-06-03T20:07:51.453039Z", "shell.execute_reply": "2025-06-03T20:07:51.452579Z", "shell.execute_reply.started": "2025-06-03T18:52:26.783420Z" } }, "outputs": [], "source": [ "make_dataset(\n", " train_df, OUT_DATA_DIR, is_val=False, npz_dir=NPZ_DIR, t_data_memmap=N_TOKENS_AUDIO\n", ")" ] }, { "cell_type": "markdown", "metadata": { "ExecuteTime": { "end_time": "2024-01-29T19:46:47.549860Z", "start_time": "2024-01-29T19:46:47.548015Z" } }, "source": [ "# Validation" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.937879Z", "start_time": "2024-05-16T13:59:41.937870Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:51.453690Z", "iopub.status.busy": "2025-06-03T20:07:51.453543Z", "iopub.status.idle": "2025-06-03T20:07:52.489344Z", "shell.execute_reply": "2025-06-03T20:07:52.488848Z", "shell.execute_reply.started": "2025-06-03T20:07:51.453675Z" } }, "outputs": [], "source": [ "# verify\n", "mm = np.memmap(os.path.join(OUT_DATA_DIR, f\"data_val.bin\"), dtype=np.uint16, mode=\"r\")\n", "test_metas = read_jsonl(os.path.join(OUT_DATA_DIR, f\"meta_val.jsonl\"))\n", "test_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_val.json\"))\n", "mm = mm.reshape(-1, N_TOKENS_AUDIO, 13)\n", "assert len(mm) == len(test_metas)\n", "assert mm[:100, :, 0].min() >= 0\n", "assert mm[:100, :, 0].max() <= 4000\n", "assert mm[:100, :, 1:].min() >= 0\n", "assert mm[:100, :, 1:].max() <= 2048" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T20:07:52.489976Z", "iopub.status.busy": "2025-06-03T20:07:52.489841Z", "iopub.status.idle": "2025-06-03T20:07:52.508923Z", "shell.execute_reply": "2025-06-03T20:07:52.508626Z", "shell.execute_reply.started": "2025-06-03T20:07:52.489962Z" } }, "outputs": [], "source": [ "task_counts = Counter()\n", "for test_meta in test_metas:\n", " task_counts[test_meta.get(\"task\")] += 1\n", "print(task_counts)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.938629Z", "start_time": "2024-05-16T13:59:41.938621Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.509393Z", "iopub.status.busy": "2025-06-03T20:07:52.509280Z", "iopub.status.idle": "2025-06-03T20:07:52.520565Z", "shell.execute_reply": "2025-06-03T20:07:52.520277Z", "shell.execute_reply.started": "2025-06-03T20:07:52.509381Z" } }, "outputs": [], "source": [ "# # randomly listen to some stuff\n", "# from suno_utils.tasks.dac_2c_12cb import preload_models as preload_codec_models\n", "# from suno_utils.tasks.dac_2c_12cb import (\n", "# encode as codec_encode,\n", "# decode_stream_to_full_audio as codec_decode,\n", "# EMBEDDING_RATE as CODEC_EMBEDDING_RATE,\n", "# decode as decode\n", "# )\n", "# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"0\"\n", "# _ = preload_codec_models(\"/app/suno/data/dpo/models/dac_2c_25x12.pt\", device=\"cuda\")\n", "# assert len(test_metas) == len(mm)\n", "# idx_list = list(range(len(test_metas)))\n", "# # random.shuffle(idx_list)\n", "# # idx_list = [idx for idx in idx_list if \"text\" in test_metas[idx]]\n", "# print(len(mm))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939205Z", "start_time": "2024-05-16T13:59:41.939198Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.521024Z", "iopub.status.busy": "2025-06-03T20:07:52.520913Z", "iopub.status.idle": "2025-06-03T20:07:52.531794Z", "shell.execute_reply": "2025-06-03T20:07:52.531502Z", "shell.execute_reply.started": "2025-06-03T20:07:52.521013Z" } }, "outputs": [], "source": [ "# import random\n", "# idx = random.choice(test_info[\"perference_0\"][\"idx_list\"])\n", "# assert \"original_duration_s\" in test_metas[idx]\n", "# # positive index should be shifted by 1\n", "# pos_idx = idx + 1\n", "# print(\n", "# \"tags:\",\n", "# test_metas[idx].get(\"tags\") == test_metas[pos_idx].get(\"tags\"),\n", "# test_metas[idx].get(\"tags\"),\n", "# )\n", "# arr = mm[idx, 1:].copy().astype(np.int16)[:, 1:]\n", "# pos_arr = mm[pos_idx, 1:].copy().astype(np.int16)[:, 1:]\n", "# pad_idx_arr = np.where(arr == COARSE_PAD_TOKEN)[0]\n", "# if len(pad_idx_arr) > 0:\n", "# arr = arr[: pad_idx_arr[0], :]\n", "# pos_pad_idx_arr = np.where(pos_arr == COARSE_PAD_TOKEN)[0]\n", "# if len(pos_pad_idx_arr) > 0:\n", "# pos_arr = pos_arr[: pos_pad_idx_arr[0], :]\n", "# a = decode(arr)\n", "# print(\"\\n negative example \\n\", test_metas[idx])\n", "# a.play(compress=False)\n", "# pos_a = decode(pos_arr)\n", "# print(\"\\n positive example \\n\", test_metas[pos_idx])\n", "# pos_a.play(compress=False)\n", "# print(\n", "# \"text:\",\n", "# test_metas[idx].get(\"text\") == test_metas[pos_idx].get(\"text\"),\n", "# test_metas[idx].get(\"text\"),\n", "# )" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939977Z", "start_time": "2024-05-16T13:59:41.939969Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.532238Z", "iopub.status.busy": "2025-06-03T20:07:52.532130Z", "iopub.status.idle": "2025-06-03T20:07:52.542621Z", "shell.execute_reply": "2025-06-03T20:07:52.542340Z", "shell.execute_reply.started": "2025-06-03T20:07:52.532227Z" } }, "outputs": [], "source": [ "# val_df[val_df[\"tags\"] == 'a vibrant blend of experimental jazz fusion, drum-and-bass and swagger fuzzed-out guitars']" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.940610Z", "start_time": "2024-05-16T13:59:41.940603Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.543056Z", "iopub.status.busy": "2025-06-03T20:07:52.542950Z", "iopub.status.idle": "2025-06-03T20:07:52.553203Z", "shell.execute_reply": "2025-06-03T20:07:52.552918Z", "shell.execute_reply.started": "2025-06-03T20:07:52.543045Z" } }, "outputs": [], "source": [ "# from collections import Counter\n", "# c = Counter()\n", "# for _, row in df_slice.iterrows():\n", "# # print(row[\"metadata\"])\n", "# for k in ast.literal_eval(row[\"metadata\"]).keys():\n", "# c[k] += 1" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941167Z", "start_time": "2024-05-16T13:59:41.941159Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.553652Z", "iopub.status.busy": "2025-06-03T20:07:52.553542Z", "iopub.status.idle": "2025-06-03T20:07:52.564230Z", "shell.execute_reply": "2025-06-03T20:07:52.563947Z", "shell.execute_reply.started": "2025-06-03T20:07:52.553641Z" } }, "outputs": [], "source": [ "# original_npz_path = f\"/app/suno/data/dpo/7b_npz/{test_metas[idx]['id']}.npz\"\n", "# original_npz_path = \"/app/suno/data/dpo/7b_npz/729c3011-f672-4ccd-8d82-1cbf2b52ff69.npz\"\n", "# original_arr = np.load(original_npz_path)[\"v2_raw\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941801Z", "start_time": "2024-05-16T13:59:41.941793Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.564680Z", "iopub.status.busy": "2025-06-03T20:07:52.564572Z", "iopub.status.idle": "2025-06-03T20:07:52.579004Z", "shell.execute_reply": "2025-06-03T20:07:52.578725Z", "shell.execute_reply.started": "2025-06-03T20:07:52.564669Z" } }, "outputs": [], "source": [ "def validation_on_metas(input_metas):\n", " total_bad = 0\n", " total_good = 0\n", " for idx in range(len(input_metas)):\n", " if idx % 2 == 0:\n", " pos_idx = idx + 1\n", " if input_metas[idx].get(\"tags\") != input_metas[pos_idx].get(\"tags\"):\n", " # print(test_metas[idx].get(\"text\") == test_metas[pos_idx].get(\"text\"), test_metas[idx].get(\"tags\"), test_metas[pos_idx].get(\"tags\"))\n", " total_bad += 1\n", " else:\n", " total_good += 1\n", " print(total_good, total_bad)\n", " return\n", "\n", "\n", "validation_on_metas(test_metas)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.942520Z", "start_time": "2024-05-16T13:59:41.942511Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.579456Z", "iopub.status.busy": "2025-06-03T20:07:52.579345Z", "iopub.status.idle": "2025-06-03T20:07:52.616801Z", "shell.execute_reply": "2025-06-03T20:07:52.616424Z", "shell.execute_reply.started": "2025-06-03T20:07:52.579444Z" } }, "outputs": [], "source": [ "train_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_tr.json\"))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.943072Z", "start_time": "2024-05-16T13:59:41.943065Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.617329Z", "iopub.status.busy": "2025-06-03T20:07:52.617210Z", "iopub.status.idle": "2025-06-03T20:07:52.644453Z", "shell.execute_reply": "2025-06-03T20:07:52.644091Z", "shell.execute_reply.started": "2025-06-03T20:07:52.617317Z" } }, "outputs": [], "source": [ "n_neg_tr = train_info[\"perference_0\"][\"idx_list\"]\n", "n_pos_tr = train_info[\"perference_1\"][\"idx_list\"]\n", "assert len(n_pos_tr) == len(n_neg_tr)\n", "# make sure they are offset by 1 and exactly 1\n", "for i, j in zip(n_neg_tr, n_pos_tr):\n", " assert i == j - 1" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.944246Z", "start_time": "2024-05-16T13:59:41.944237Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.644970Z", "iopub.status.busy": "2025-06-03T20:07:52.644851Z", "iopub.status.idle": "2025-06-03T20:07:52.658030Z", "shell.execute_reply": "2025-06-03T20:07:52.657745Z", "shell.execute_reply.started": "2025-06-03T20:07:52.644957Z" } }, "outputs": [], "source": [ "total_iters = len(n_neg_tr) + len(n_pos_tr)\n", "print(\"total samples\", total_iters, train_df.shape)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945249Z", "start_time": "2024-05-16T13:59:41.945241Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.658485Z", "iopub.status.busy": "2025-06-03T20:07:52.658373Z", "iopub.status.idle": "2025-06-03T20:07:52.669600Z", "shell.execute_reply": "2025-06-03T20:07:52.669327Z", "shell.execute_reply.started": "2025-06-03T20:07:52.658474Z" } }, "outputs": [], "source": [ "print(\"1 epoch per batch 4, total\", total_iters / 8 / 2 / 4)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945972Z", "start_time": "2024-05-16T13:59:41.945964Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.670039Z", "iopub.status.busy": "2025-06-03T20:07:52.669932Z", "iopub.status.idle": "2025-06-03T20:07:52.680339Z", "shell.execute_reply": "2025-06-03T20:07:52.680059Z", "shell.execute_reply.started": "2025-06-03T20:07:52.670027Z" } }, "outputs": [], "source": [ "# !cd /home/tony/Work/tony/slurm/sem_4p5_dpo && sbatch sbatch_ipo_4p5" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T20:07:52.680780Z", "iopub.status.busy": "2025-06-03T20:07:52.680672Z", "iopub.status.idle": "2025-06-03T20:07:52.702362Z", "shell.execute_reply": "2025-06-03T20:07:52.702062Z", "shell.execute_reply.started": "2025-06-03T20:07:52.680769Z" } }, "outputs": [], "source": [ "import shutil\n", "\n", "# Basic file copy\n", "shutil.copy(\n", " \"/home/tony/Work/tony/Preference/make_dataset_auk_mixed_2.ipynb\",\n", " os.path.join(OUT_DATA_DIR, \"make_dataset.ipynb\"),\n", ")\n", "print(\"Cache kept!\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# some gymathtics loading prev data" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.946562Z", "start_time": "2024-05-16T13:59:41.946555Z" }, "execution": { "iopub.execute_input": "2025-06-03T20:07:52.702825Z", "iopub.status.busy": "2025-06-03T20:07:52.702715Z", "iopub.status.idle": "2025-06-03T20:07:52.714040Z", "shell.execute_reply": "2025-06-03T20:07:52.713754Z", "shell.execute_reply.started": "2025-06-03T20:07:52.702814Z" } }, "outputs": [], "source": [ "# prev_v3_data = \"/app/suno/data/dpo/7v_v20_full/\"\n", "\n", "# test_val_metas = read_jsonl(os.path.join(prev_v3_data, f\"meta_val.jsonl\"))\n", "# test_tr_metas = read_jsonl(os.path.join(prev_v3_data, f\"meta_tr.jsonl\"))\n", "\n", "# all_ids = set()\n", "# for meta in test_val_metas:\n", "# all_ids.add(meta[\"id\"])\n", "# for meta in test_tr_metas:\n", "# all_ids.add(meta[\"id\"])\n", "# print(len(all_ids), len(test_val_metas) + len(test_tr_metas))\n", "\n", "# all_ids = list(all_ids)\n", "# with open(\"/home/tony/Data/Preference/7b_v2/7v_v20_full_recut_id.json\", \"w\") as fp:\n", "# json.dump(all_ids, fp)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T20:07:52.714481Z", "iopub.status.busy": "2025-06-03T20:07:52.714374Z", "iopub.status.idle": "2025-06-03T20:07:52.725047Z", "shell.execute_reply": "2025-06-03T20:07:52.724758Z", "shell.execute_reply.started": "2025-06-03T20:07:52.714470Z" } }, "outputs": [], "source": [ "# x_data = train_df[train_df[\"preference\"]][\"similarity\"]\n", "# y_data = train_df[~train_df[\"preference\"]][\"similarity\"]\n", "# from matplotlib.colors import LogNorm\n", "\n", "# fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 10))\n", "\n", "# # 2D Histogram\n", "# h = ax1.hist2d(\n", "# x_data,\n", "# y_data,\n", "# bins=(50, 50),\n", "# cmap=\"coolwarm\",\n", "# range=[[0, 1], [0, 1]],\n", "# norm=LogNorm(),\n", "# )\n", "\n", "# ax1.set_xlabel(\"Semantic Distance (Preferred)\")\n", "# ax1.set_ylabel(\"Semantic Distance (Non-Preferred)\")\n", "# ax1.set_title(\n", "# \"2D Histogram of Semantic Distances: Preferred vs Non-Preferred (Log Scale)\"\n", "# )\n", "\n", "# cbar1 = plt.colorbar(h[3], ax=ax1)\n", "# cbar1.set_label(\"Number of Request IDs (Log Scale)\")\n", "\n", "# # Scatter plot\n", "# ax2.scatter(x_data, y_data, alpha=0.1, s=1)\n", "# ax2.set_xlabel(\"Semantic Distance (Preferred)\")\n", "# ax2.set_ylabel(\"Semantic Distance (Non-Preferred)\")\n", "# ax2.set_title(\"Scatter Plot of Semantic Distances: Preferred vs Non-Preferred\")\n", "# ax2.set_xlim(0, 1)\n", "# ax2.set_ylim(0, 1)\n", "\n", "# plt.tight_layout()\n", "# plt.show()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T20:07:52.725490Z", "iopub.status.busy": "2025-06-03T20:07:52.725382Z", "iopub.status.idle": "2025-06-03T20:07:52.735771Z", "shell.execute_reply": "2025-06-03T20:07:52.735493Z", "shell.execute_reply.started": "2025-06-03T20:07:52.725478Z" } }, "outputs": [], "source": [ "# train_metas = read_jsonl(os.path.join(OUT_DATA_DIR, f\"meta_tr.jsonl\"))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T20:07:52.736200Z", "iopub.status.busy": "2025-06-03T20:07:52.736093Z", "iopub.status.idle": "2025-06-03T20:07:52.747156Z", "shell.execute_reply": "2025-06-03T20:07:52.746905Z", "shell.execute_reply.started": "2025-06-03T20:07:52.736189Z" } }, "outputs": [], "source": [ "train_info.keys()" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "suno_env_dev", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.10.15" }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": true, "sideBar": true, "skip_h1_title": false, "title_cell": "Table of Contents", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": true, "toc_window_display": false } }, "nbformat": 4, "nbformat_minor": 4 }