{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:01:39.943375Z", "iopub.status.busy": "2025-06-03T18:01:39.943112Z", "iopub.status.idle": "2025-06-03T18:01:39.954936Z", "shell.execute_reply": "2025-06-03T18:01:39.954600Z", "shell.execute_reply.started": "2025-06-03T18:01:39.943359Z" } }, "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": "2025-06-03T18:01:39.956523Z", "iopub.status.busy": "2025-06-03T18:01:39.956328Z", "iopub.status.idle": "2025-06-03T18:01:42.175119Z", "shell.execute_reply": "2025-06-03T18:01:42.174671Z", "shell.execute_reply.started": "2025-06-03T18:01:39.956511Z" } }, "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": "2025-06-03T18:01:42.176906Z", "iopub.status.busy": "2025-06-03T18:01:42.176702Z", "iopub.status.idle": "2025-06-03T18:01:42.244863Z", "shell.execute_reply": "2025-06-03T18:01:42.244421Z", "shell.execute_reply.started": "2025-06-03T18:01:42.176893Z" } }, "outputs": [], "source": [ "OUT_DATA_DIR = \"/app/suno/data/dpo/auk_mix_t1_v6\"\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": "2025-06-03T18:01:42.246330Z", "iopub.status.busy": "2025-06-03T18:01:42.246228Z", "iopub.status.idle": "2025-06-03T18:02:09.757603Z", "shell.execute_reply": "2025-06-03T18:02:09.757104Z", "shell.execute_reply.started": "2025-06-03T18:01:42.246319Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Preference data shape (1063314, 90)\n" ] } ], "source": [ "df = pd.read_pickle(\n", " \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250411_full_long.pkl\"\n", ")\n", "print(\"Preference data shape\", df.shape)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:02:09.759354Z", "iopub.status.busy": "2025-06-03T18:02:09.759143Z", "iopub.status.idle": "2025-06-03T18:02:11.084415Z", "shell.execute_reply": "2025-06-03T18:02:11.083934Z", "shell.execute_reply.started": "2025-06-03T18:02:09.759340Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after dropna (1063314, 85)\n" ] } ], "source": [ "df = df.dropna(axis=1, how=\"all\")\n", "print(\"after dropna\", df.shape)" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.199480Z", "start_time": "2024-05-16T13:58:53.963687Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:02:11.085102Z", "iopub.status.busy": "2025-06-03T18:02:11.084923Z", "iopub.status.idle": "2025-06-03T18:08:02.705226Z", "shell.execute_reply": "2025-06-03T18:08:02.704729Z", "shell.execute_reply.started": "2025-06-03T18:02:11.085088Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "6442462\n", "6442462\n", "pre-downloaded df (1063314, 85)\n", "downloaded df (1063314, 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": 7, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.467253Z", "start_time": "2024-05-16T13:58:56.207647Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:08:02.705963Z", "iopub.status.busy": "2025-06-03T18:08:02.705731Z", "iopub.status.idle": "2025-06-03T18:08:02.994671Z", "shell.execute_reply": "2025-06-03T18:08:02.994257Z", "shell.execute_reply.started": "2025-06-03T18:08:02.705949Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_30b\n", "True 1063314\n", "Name: count, dtype: int64\n" ] }, { "data": { "text/plain": [ "task\n", "cover 555186\n", "artist_consistency 465022\n", "infill 43090\n", " 10\n", "artist_cover 6\n", "Name: count, dtype: int64" ] }, "execution_count": 7, "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": 8, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:08:02.995334Z", "iopub.status.busy": "2025-06-03T18:08:02.995162Z", "iopub.status.idle": "2025-06-03T18:08:03.009014Z", "shell.execute_reply": "2025-06-03T18:08:03.008655Z", "shell.execute_reply.started": "2025-06-03T18:08:02.995322Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(1063314, 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": 9, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.592883Z", "start_time": "2024-05-16T13:58:56.470781Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:08:03.009646Z", "iopub.status.busy": "2025-06-03T18:08:03.009435Z", "iopub.status.idle": "2025-06-03T18:08:03.309926Z", "shell.execute_reply": "2025-06-03T18:08:03.309449Z", "shell.execute_reply.started": "2025-06-03T18:08:03.009633Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "preference model_name \n", "False chirp-v4-h-t-6 531657\n", "True chirp-v4-h-t-6 531657\n", "Name: count, dtype: int64\n", "before filter on model name (1063314, 86)\n", "after filter on model name (1063314, 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": 10, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:08:03.310604Z", "iopub.status.busy": "2025-06-03T18:08:03.310433Z", "iopub.status.idle": "2025-06-03T18:08:03.327935Z", "shell.execute_reply": "2025-06-03T18:08:03.327572Z", "shell.execute_reply.started": "2025-06-03T18:08:03.310591Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 1034392\n", "True 28922\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": 11, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.909539Z", "start_time": "2024-05-16T13:58:56.595736Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:08:03.328466Z", "iopub.status.busy": "2025-06-03T18:08:03.328356Z", "iopub.status.idle": "2025-06-03T18:08:04.462762Z", "shell.execute_reply": "2025-06-03T18:08:04.462250Z", "shell.execute_reply.started": "2025-06-03T18:08:03.328456Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "before filter on request id pairs (1063314, 86)\n", "after filter on request id pairs (1063314, 86)\n", "preference model_name \n", "False chirp-v4-h-t-6 531657\n", "True chirp-v4-h-t-6 531657\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": 12, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:08:04.463476Z", "iopub.status.busy": "2025-06-03T18:08:04.463283Z", "iopub.status.idle": "2025-06-03T18:10:22.985317Z", "shell.execute_reply": "2025-06-03T18:10:22.984814Z", "shell.execute_reply.started": "2025-06-03T18:08:04.463462Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "unique_requests 531657\n", "before removing duplicates (1063314, 159)\n", "after removing duplicates (1063314, 152)\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": 13, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:10:22.985998Z", "iopub.status.busy": "2025-06-03T18:10:22.985819Z", "iopub.status.idle": "2025-06-03T18:10:23.824437Z", "shell.execute_reply": "2025-06-03T18:10:23.824018Z", "shell.execute_reply.started": "2025-06-03T18:10:22.985984Z" } }, "outputs": [ { "data": { "text/plain": [ "task\n", "cover 555186\n", "artist_consistency 465022\n", "infill 43090\n", " 10\n", "artist_cover 6\n", "Name: count, dtype: int64" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"task\"].value_counts()" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:10:23.825119Z", "iopub.status.busy": "2025-06-03T18:10:23.824926Z", "iopub.status.idle": "2025-06-03T18:10:25.450414Z", "shell.execute_reply": "2025-06-03T18:10:25.449990Z", "shell.execute_reply.started": "2025-06-03T18:10:23.825105Z" } }, "outputs": [ { "data": { "text/plain": [ "pos_diff_preference\n", "1.0 365487\n", "2.0 166170\n", "Name: count, dtype: int64" ] }, "execution_count": 14, "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": 15, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:10:25.451078Z", "iopub.status.busy": "2025-06-03T18:10:25.450905Z", "iopub.status.idle": "2025-06-03T18:10:25.984488Z", "shell.execute_reply": "2025-06-03T18:10:25.984002Z", "shell.execute_reply.started": "2025-06-03T18:10:25.451065Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive param_experiment\n", "min_p_0001 16919\n", "min_p_002 15970\n", "text_1 13273\n", "temp_s_80 13141\n", "temp_s_70 12382\n", "step_12 8452\n", "text_3 8135\n", "step_8 8025\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": 16, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:10:25.985194Z", "iopub.status.busy": "2025-06-03T18:10:25.985015Z", "iopub.status.idle": "2025-06-03T18:11:03.817706Z", "shell.execute_reply": "2025-06-03T18:11:03.817197Z", "shell.execute_reply.started": "2025-06-03T18:10:25.985180Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found 89692 duplicated prompts 44847 unique requests\n", "Found 21934 request_ids with duplicate prompts but not highest play counts in their group\n", "['31f6cf77-5db4-466d-a6f5-c455dcdab4d7', '5ad6125e-1eac-48a5-ae59-716454c0225d', 'c8390ab2-e5be-4d69-b5bf-4e9404088949', 'e12dafc1-45e3-4abd-9a58-d5e4293ae33b', '6f5b4451-853e-4196-818c-345d9fa0f684', '69e8eef7-4326-4796-b9f7-833143e3afde', 'b75e653f-eb32-409e-a5ce-1ef39f1fa1c1', '0b3c3723-51a7-43ea-9f36-a7cd229c52b3', 'a5ff1bec-31e3-4454-9489-819b63900441', '4dd11a3d-190a-41e6-afe1-6456bd5a81d9']\n", "Before dedup user gen requests 1063314\n", "After dedup user gen requests 1019446\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": 17, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:40.799375Z", "start_time": "2024-05-16T13:59:36.394236Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:03.818406Z", "iopub.status.busy": "2025-06-03T18:11:03.818221Z", "iopub.status.idle": "2025-06-03T18:11:07.581161Z", "shell.execute_reply": "2025-06-03T18:11:07.580686Z", "shell.execute_reply.started": "2025-06-03T18:11:03.818392Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "19362\n", "good_continue_at\n", "True 1019446\n", "Name: count, dtype: int64\n", "\n", " Check some basics... \n", " preference\n", "False 509723\n", "True 509723\n", "Name: count, dtype: int64 is_30b\n", "True 1019446\n", "Name: count, dtype: int64 model_name\n", "chirp-v4-h-t-6 1019446\n", "Name: count, dtype: int64 preference model_name \n", "False chirp-v4-h-t-6 509723\n", "True chirp-v4-h-t-6 509723\n", "Name: count, dtype: int64\n", "task\n", "cover 532368\n", "artist_consistency 445310\n", "infill 41752\n", " 10\n", "artist_cover 6\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": 18, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:07.581842Z", "iopub.status.busy": "2025-06-03T18:11:07.581667Z", "iopub.status.idle": "2025-06-03T18:11:07.741484Z", "shell.execute_reply": "2025-06-03T18:11:07.741078Z", "shell.execute_reply.started": "2025-06-03T18:11:07.581828Z" } }, "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": 19, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.035167Z", "start_time": "2024-05-16T13:59:40.801098Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:07.742194Z", "iopub.status.busy": "2025-06-03T18:11:07.742015Z", "iopub.status.idle": "2025-06-03T18:11:09.917857Z", "shell.execute_reply": "2025-06-03T18:11:09.917350Z", "shell.execute_reply.started": "2025-06-03T18:11:07.742180Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after duration 0.9961214228119979\n", "after infill duration 0.9984216917816148\n", "neg_filter_reaction_play_count 1.0\n", "neg_filter_upvote_count 0.9889\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 0.9736\n", "pos_filter_cer_diff_preference 1.0\n", "pos_filter_bad_flags 0.9999\n", "after filter on play counts 0.9663\n", "after filter on higher quality 0.2964\n", "----------------\n", "negative 501342 positive 128465\n", "----------------\n", "total pair requests 509723 --> selected pair requests 126863 frac 0.249\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", ")\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", ") & (\n", " (\n", " df[\"upvote_count\"] >= 1\n", " ) # (df[\"upvote_count\"] >= 1) (df[\"pos_diff_preference\"] == 2)\n", " | (df[\"reaction_play_count\"] >= 5)\n", " | (df[\"concat_play_counts\"] >= 5)\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": 20, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.250737Z", "start_time": "2024-05-16T13:59:41.036434Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:09.921088Z", "iopub.status.busy": "2025-06-03T18:11:09.920883Z", "iopub.status.idle": "2025-06-03T18:11:10.720508Z", "shell.execute_reply": "2025-06-03T18:11:10.720006Z", "shell.execute_reply.started": "2025-06-03T18:11:09.921074Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "auk_mix_t1_v6 requests 126863 clips 253726 total khrs 11.363; N gpus for 1000 iters 15.858; 4 gpus for x iters 3964.469; n unique users 42720 n pro users 39331\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" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.277006Z", "start_time": "2024-05-16T13:59:41.252105Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:10.721191Z", "iopub.status.busy": "2025-06-03T18:11:10.721009Z", "iopub.status.idle": "2025-06-03T18:11:10.807895Z", "shell.execute_reply": "2025-06-03T18:11:10.807423Z", "shell.execute_reply.started": "2025-06-03T18:11:10.721177Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive in playlist (33953, 158)\n", "task\n", "artist_consistency 117588\n", "cover 107618\n", "infill 28516\n", " 4\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": 22, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:10.808569Z", "iopub.status.busy": "2025-06-03T18:11:10.808398Z", "iopub.status.idle": "2025-06-03T18:11:10.945498Z", "shell.execute_reply": "2025-06-03T18:11:10.945083Z", "shell.execute_reply.started": "2025-06-03T18:11:10.808555Z" } }, "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": 23, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.323409Z", "start_time": "2024-05-16T13:59:41.278278Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:10.946153Z", "iopub.status.busy": "2025-06-03T18:11:10.945991Z", "iopub.status.idle": "2025-06-03T18:11:10.959666Z", "shell.execute_reply": "2025-06-03T18:11:10.959321Z", "shell.execute_reply.started": "2025-06-03T18:11:10.946140Z" } }, "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": 24, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.392244Z", "start_time": "2024-05-16T13:59:41.324472Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:10.960209Z", "iopub.status.busy": "2025-06-03T18:11:10.960101Z", "iopub.status.idle": "2025-06-03T18:11:10.971006Z", "shell.execute_reply": "2025-06-03T18:11:10.970662Z", "shell.execute_reply.started": "2025-06-03T18:11:10.960197Z" } }, "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": 25, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:10.971471Z", "iopub.status.busy": "2025-06-03T18:11:10.971366Z", "iopub.status.idle": "2025-06-03T18:11:10.982416Z", "shell.execute_reply": "2025-06-03T18:11:10.982075Z", "shell.execute_reply.started": "2025-06-03T18:11:10.971460Z" } }, "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": 26, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:10.983059Z", "iopub.status.busy": "2025-06-03T18:11:10.982871Z", "iopub.status.idle": "2025-06-03T18:11:10.993834Z", "shell.execute_reply": "2025-06-03T18:11:10.993491Z", "shell.execute_reply.started": "2025-06-03T18:11:10.983048Z" } }, "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": 27, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:10.994295Z", "iopub.status.busy": "2025-06-03T18:11:10.994189Z", "iopub.status.idle": "2025-06-03T18:11:11.005608Z", "shell.execute_reply": "2025-06-03T18:11:11.005258Z", "shell.execute_reply.started": "2025-06-03T18:11:10.994284Z" } }, "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": 28, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.006195Z", "iopub.status.busy": "2025-06-03T18:11:11.005993Z", "iopub.status.idle": "2025-06-03T18:11:11.016540Z", "shell.execute_reply": "2025-06-03T18:11:11.016204Z", "shell.execute_reply.started": "2025-06-03T18:11:11.006183Z" } }, "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": 29, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.017043Z", "iopub.status.busy": "2025-06-03T18:11:11.016935Z", "iopub.status.idle": "2025-06-03T18:11:11.027649Z", "shell.execute_reply": "2025-06-03T18:11:11.027316Z", "shell.execute_reply.started": "2025-06-03T18:11:11.017032Z" } }, "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": 30, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.028117Z", "iopub.status.busy": "2025-06-03T18:11:11.028008Z", "iopub.status.idle": "2025-06-03T18:11:11.038825Z", "shell.execute_reply": "2025-06-03T18:11:11.038493Z", "shell.execute_reply.started": "2025-06-03T18:11:11.028106Z" } }, "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": 31, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.039430Z", "iopub.status.busy": "2025-06-03T18:11:11.039235Z", "iopub.status.idle": "2025-06-03T18:11:11.049676Z", "shell.execute_reply": "2025-06-03T18:11:11.049337Z", "shell.execute_reply.started": "2025-06-03T18:11:11.039418Z" } }, "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": 32, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.050137Z", "iopub.status.busy": "2025-06-03T18:11:11.050032Z", "iopub.status.idle": "2025-06-03T18:11:11.060876Z", "shell.execute_reply": "2025-06-03T18:11:11.060547Z", "shell.execute_reply.started": "2025-06-03T18:11:11.050127Z" } }, "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": 33, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.061490Z", "iopub.status.busy": "2025-06-03T18:11:11.061294Z", "iopub.status.idle": "2025-06-03T18:11:11.073893Z", "shell.execute_reply": "2025-06-03T18:11:11.073532Z", "shell.execute_reply.started": "2025-06-03T18:11:11.061478Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 241971\n", "True 11755\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(df_slice[\"is_public\"].value_counts())" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:11:11.074496Z", "iopub.status.busy": "2025-06-03T18:11:11.074295Z", "iopub.status.idle": "2025-06-03T18:11:11.126264Z", "shell.execute_reply": "2025-06-03T18:11:11.125835Z", "shell.execute_reply.started": "2025-06-03T18:11:11.074484Z" } }, "outputs": [], "source": [ "df_slice[\"npz_path\"] = df_slice[\"s3_id\"].map(lambda x: f\"{NPZ_DIR}/{x}.npz\")" ] }, { "cell_type": "code", "execution_count": 35, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T14:00:20.866354Z", "start_time": "2024-05-16T14:00:12.443344Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:11:11.126977Z", "iopub.status.busy": "2025-06-03T18:11:11.126746Z", "iopub.status.idle": "2025-06-03T18:11:11.412481Z", "shell.execute_reply": "2025-06-03T18:11:11.411953Z", "shell.execute_reply.started": "2025-06-03T18:11:11.126963Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(253726, 159)\n", "task\n", "artist_consistency 117588\n", "cover 107618\n", "infill 28516\n", " 4\n", "Name: count, dtype: int64\n", "(253726, 159)\n", "task\n", "artist_consistency 117588\n", "cover 107618\n", "infill 28516\n", " 4\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[35], 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_20250411_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([\"extend\", \"\"])].copy()\n", "print(df_slice.shape)\n", "print(df_slice[\"task\"].value_counts())\n", "BREAK" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:07.061169Z", "iopub.status.busy": "2025-06-03T18:13:07.060857Z", "iopub.status.idle": "2025-06-03T18:13:10.925347Z", "shell.execute_reply": "2025-06-03T18:13:10.924981Z", "shell.execute_reply.started": "2025-06-03T18:13:07.061153Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(153414, 159)\n", "task\n", " 121424\n", "extend 19502\n", "upload_extend 12488\n", "Name: count, dtype: int64\n" ] } ], "source": [ "df_13b_slice = pd.read_pickle(\n", " \"/home/tony/Data/Preference/13b_v32/interesting_clips_v4_h_s_32_20250411_full_long_slice.pkl\"\n", ")\n", "print(df_13b_slice.shape)\n", "print(df_13b_slice[\"task\"].value_counts())" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:10.926055Z", "iopub.status.busy": "2025-06-03T18:13:10.925927Z", "iopub.status.idle": "2025-06-03T18:13:11.400805Z", "shell.execute_reply": "2025-06-03T18:13:11.400458Z", "shell.execute_reply.started": "2025-06-03T18:13:10.926042Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(253726, 159)\n", "task\n", "artist_consistency 117588\n", "cover 107618\n", "infill 28516\n", " 4\n", "Name: count, dtype: int64\n" ] } ], "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": 38, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:11.401416Z", "iopub.status.busy": "2025-06-03T18:13:11.401210Z", "iopub.status.idle": "2025-06-03T18:13:15.452290Z", "shell.execute_reply": "2025-06-03T18:13:15.451948Z", "shell.execute_reply.started": "2025-06-03T18:13:11.401403Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(407140, 168)\n", "task\n", " 121428\n", "artist_consistency 117588\n", "cover 107618\n", "infill 28516\n", "extend 19502\n", "upload_extend 12488\n", "Name: count, dtype: int64\n" ] } ], "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": 39, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:15.453350Z", "iopub.status.busy": "2025-06-03T18:13:15.452919Z", "iopub.status.idle": "2025-06-03T18:13:16.429832Z", "shell.execute_reply": "2025-06-03T18:13:16.429427Z", "shell.execute_reply.started": "2025-06-03T18:13:15.453335Z" } }, "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": 40, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932296Z", "start_time": "2024-05-16T13:59:41.932287Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:36.734381Z", "iopub.status.busy": "2025-06-03T18:13:36.734073Z", "iopub.status.idle": "2025-06-03T18:13:36.758380Z", "shell.execute_reply": "2025-06-03T18:13:36.758004Z", "shell.execute_reply.started": "2025-06-03T18:13:36.734366Z" } }, "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": 41, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:36.759195Z", "iopub.status.busy": "2025-06-03T18:13:36.759005Z", "iopub.status.idle": "2025-06-03T18:13:37.782012Z", "shell.execute_reply": "2025-06-03T18:13:37.781660Z", "shell.execute_reply.started": "2025-06-03T18:13:36.759181Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(407140, 168)\n", "(407140, 168)\n", "(407140, 168)\n" ] } ], "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": 42, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932966Z", "start_time": "2024-05-16T13:59:41.932957Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:37.782525Z", "iopub.status.busy": "2025-06-03T18:13:37.782399Z", "iopub.status.idle": "2025-06-03T18:13:37.867572Z", "shell.execute_reply": "2025-06-03T18:13:37.867221Z", "shell.execute_reply.started": "2025-06-03T18:13:37.782512Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "203570\n" ] } ], "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": 43, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.933558Z", "start_time": "2024-05-16T13:59:41.933550Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:37.868099Z", "iopub.status.busy": "2025-06-03T18:13:37.867974Z", "iopub.status.idle": "2025-06-03T18:13:37.881709Z", "shell.execute_reply": "2025-06-03T18:13:37.881422Z", "shell.execute_reply.started": "2025-06-03T18:13:37.868086Z" } }, "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": 44, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:13:37.882686Z", "iopub.status.busy": "2025-06-03T18:13:37.882513Z", "iopub.status.idle": "2025-06-03T18:13:37.893225Z", "shell.execute_reply": "2025-06-03T18:13:37.892961Z", "shell.execute_reply.started": "2025-06-03T18:13:37.882674Z" } }, "outputs": [], "source": [ "# df_slice[\"continue_at\"] = -1" ] }, { "cell_type": "code", "execution_count": 45, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934277Z", "start_time": "2024-05-16T13:59:41.934268Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:37.893700Z", "iopub.status.busy": "2025-06-03T18:13:37.893540Z", "iopub.status.idle": "2025-06-03T18:13:39.823484Z", "shell.execute_reply": "2025-06-03T18:13:39.823142Z", "shell.execute_reply.started": "2025-06-03T18:13:37.893688Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "201534 2036\n", "(403068, 168) (4072, 168)\n" ] } ], "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": 46, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.935620Z", "start_time": "2024-05-16T13:59:41.935613Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:39.823993Z", "iopub.status.busy": "2025-06-03T18:13:39.823877Z", "iopub.status.idle": "2025-06-03T18:13:48.686054Z", "shell.execute_reply": "2025-06-03T18:13:48.685702Z", "shell.execute_reply.started": "2025-06-03T18:13:39.823981Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████████████████████████████████████████████████████████████| 403068/403068 [00:08<00:00, 45565.76it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "18,741 hours of 403068 clips, 25.19175 nodes, 4198.625 iters\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "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": 47, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936268Z", "start_time": "2024-05-16T13:59:41.936260Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:13:48.686562Z", "iopub.status.busy": "2025-06-03T18:13:48.686444Z", "iopub.status.idle": "2025-06-03T18:14:54.782609Z", "shell.execute_reply": "2025-06-03T18:14:54.782278Z", "shell.execute_reply.started": "2025-06-03T18:13:48.686549Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t_data_memmap is set to: 6016\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4072/4072 [01:05<00:00, 61.83it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 4072 clips, 0 different prompts\n", "118 hours of False\n", "117 hours of True\n", "artist_consistency: 79.8 hours\n", "cover: 66.0 hours\n", "infill: 6.0 hours\n", "extend: 19.6 hours\n", "gen: 64.6 hours\n", "Done\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "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": 48, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T18:14:54.783182Z", "iopub.status.busy": "2025-06-03T18:14:54.782981Z", "iopub.status.idle": "2025-06-03T18:14:54.831842Z", "shell.execute_reply": "2025-06-03T18:14:54.831514Z", "shell.execute_reply.started": "2025-06-03T18:14:54.783169Z" } }, "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": 49, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936964Z", "start_time": "2024-05-16T13:59:41.936957Z" }, "execution": { "iopub.execute_input": "2025-06-03T18:14:54.832518Z", "iopub.status.busy": "2025-06-03T18:14:54.832198Z", "iopub.status.idle": "2025-06-03T19:57:29.950093Z", "shell.execute_reply": "2025-06-03T19:57:29.949583Z", "shell.execute_reply.started": "2025-06-03T18:14:54.832506Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t_data_memmap is set to: 6016\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%|▎ | 1149/403068 [00:20<1:41:19, 66.12it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1138, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/ccb707e8-1c1a-4317-8370-a8fc312a4b87.npz.\n", "WTF --> 1139, skip, preference: True, 692d2bb5-2634-413b-aa9b-f9a1bc291967, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|██████ | 23722/403068 [06:12<1:29:11, 70.89it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "23714, 'history_arr is not a file in the archive', upload_extend, /app/suno/data/dpo/13b_s32_npz/c8ad50dc-58c3-470f-a094-676e03f25de9.npz.\n", "WTF --> 23715, skip, preference: True, 10754475-08f0-4951-b71a-c2fe0991c409, task: upload_extend.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|███████▋ | 29774/403068 [07:44<1:30:29, 68.76it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "29760, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/dbd5f931-c157-41fb-b204-90ec3baa5db3.npz.\n", "WTF --> 29761, skip, preference: True, dd1cd0d7-e6ba-4306-b200-9a490d9aa5a0, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|███████████▊ | 45675/403068 [11:44<1:24:27, 70.53it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "45660, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/2f176b3f-ef12-4179-aee5-556756deae58.npz.\n", "WTF --> 45661, skip, preference: True, 9a5c7e2c-2698-423a-9688-836fe9f78058, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|█████████████████▎ | 66882/403068 [16:58<1:17:05, 72.68it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "66874, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/8dddfd98-f72b-47c5-a5b5-637e3e3f6e5a.npz.\n", "WTF --> 66875, skip, preference: True, 539f7741-6451-4eab-a55c-e32946a685ec, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|███████████████████▋ | 76135/403068 [19:16<1:17:28, 70.33it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "76120, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/c5cf93c9-178b-4c62-ad9e-582cf563b2e0.npz.\n", "WTF --> 76121, skip, preference: True, b1a272e3-8180-4128-a876-7c3babea63fe, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|████████████████████▋ | 80339/403068 [20:20<1:16:44, 70.09it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "80326, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/22af1130-3df2-4798-87bf-d002d0e5bdb2.npz.\n", "WTF --> 80327, skip, preference: True, c25c2fac-5f9a-4a67-9f49-93dbc19c36d0, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|███████████████████████▍ | 90957/403068 [22:58<1:12:22, 71.88it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "90948, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/419cca10-dc66-48db-b3a6-db8d7b661539.npz.\n", "WTF --> 90949, skip, preference: True, 85e59615-85da-4d60-80d5-67a617f4ceb7, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|████████████████████████ | 93481/403068 [23:36<1:12:47, 70.88it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "93466, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/f23bf59e-143e-44ab-bb2c-749914a0015d.npz.\n", "WTF --> 93467, skip, preference: True, bf776438-653a-4a89-a9f4-1c230b31cc4d, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|███████████████████████████████████ | 137204/403068 [34:28<1:03:44, 69.51it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "weird, /app/suno/data/dpo/30b_npz/025128d0-1ef2-497b-a7aa-b77645e04131.npz, with only v3.0\n", "137189, 'cover_arr is not a file in the archive', cover, /app/suno/data/dpo/30b_npz/025128d0-1ef2-497b-a7aa-b77645e04131.npz.\n", "WTF --> 137189, 'cover_arr is not a file in the archive', cover, /app/suno/data/dpo/30b_npz/025128d0-1ef2-497b-a7aa-b77645e04131.npz.\n", "WTF --> 137190, skip, preference: False, 73b9f258-0fb2-40ed-82c4-c047c0668f69, task: artist_consistency.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|██████████████████████████████████████▌ | 150886/403068 [37:52<1:00:25, 69.55it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "150874, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/94e21fbb-3c89-43fa-b2d7-57447ca9bac6.npz.\n", "WTF --> 150875, skip, preference: True, f01db30d-818b-49c4-95ac-f4621c02d833, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|████████████████████████████████████████████████▌ | 186387/403068 [46:44<52:02, 69.38it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "186376, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/db9b3c17-eb96-406f-8886-5cf8fe5583cf.npz.\n", "WTF --> 186377, skip, preference: True, 169cfd5d-8150-4099-ac45-eb694b40b3fe, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|████████████████████████████████████████████████████████▍ | 216515/403068 [54:49<44:18, 70.17it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "216506, 'history_arr is not a file in the archive', upload_extend, /app/suno/data/dpo/13b_s32_npz/cc918963-4a41-4bf1-b846-c9a140d1951b.npz.\n", "WTF --> 216507, skip, preference: True, 409fc6b6-73a1-4884-b80f-6d34ee88ccd1, task: upload_extend.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|█████████████████████████████████████████████████████████████████▌ | 256575/403068 [1:04:50<35:30, 68.77it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "256564, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4d5be30b-404c-4f1d-8ebd-5c4661ca819f.npz.\n", "WTF --> 256565, skip, preference: True, f5253d4c-ef09-4215-9e03-60df4b4256c9, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|████████████████████████████████████████████████████████████████████████▊ | 284932/403068 [1:11:57<28:18, 69.55it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "284924, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/233c39fd-7a7c-4484-9f12-e8132061a41d.npz.\n", "WTF --> 284925, skip, preference: True, d984ee29-f547-44f8-837b-999308310e6b, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|█████████████████████████████████████████████████████████████████████████▉ | 289118/403068 [1:13:00<26:33, 71.50it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "289104, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/885100f5-63d2-48e6-b95e-629617184741.npz.\n", "WTF --> 289105, skip, preference: True, 2a11cb67-e7aa-4f7c-a862-9cb60b06b31c, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|█████████████████████████████████████████████████████████████████████████▉ | 289278/403068 [1:13:03<27:04, 70.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "289264, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/655f5238-cff6-4e56-aaae-571565be42ce.npz.\n", "WTF --> 289265, skip, preference: True, b32277a3-0c3c-4ff3-b114-81bebe908873, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|█████████████████████████████████████████████████████████████████████████████▍ | 302910/403068 [1:16:30<24:09, 69.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "302902, 'history_arr is not a file in the archive', upload_extend, /app/suno/data/dpo/13b_s32_npz/bb5e7c57-8c2b-40d9-8069-2e87877246b1.npz.\n", "WTF --> 302903, skip, preference: True, b86b7cb4-72de-424b-99ed-f94f13e1475f, task: upload_extend.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|████████████████████████████████████████████████████████████████████████████████████████▎ | 345430/403068 [1:27:10<13:45, 69.83it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "345418, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/ceff47b5-c7f9-469e-8be4-fee5899ca309.npz.\n", "WTF --> 345419, skip, preference: True, 85c0d3fe-e67d-4657-ba92-dd57ed5784d2, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|█████████████████████████████████████████████████████████████████████████████████████████████████████ | 395608/403068 [1:40:25<01:46, 69.89it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "395596, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/9ab4b856-e426-4ffe-96c4-b9d19b8504bc.npz.\n", "WTF --> 395597, skip, preference: True, 67f1bef1-b8b7-4eca-bd9f-500761f5cbeb, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 403068/403068 [1:42:15<00:00, 65.69it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 403028 clips, 40 different prompts\n", "11,735 hours of False\n", "11,596 hours of True\n", "artist_consistency: 7719.4 hours\n", "infill: 595.0 hours\n", "gen: 6432.6 hours\n", "cover: 6840.9 hours\n", "extend: 1743.3 hours\n", "🚨 Error infill: 16\n", "🚨 Error upload_extend: 3\n", "🚨 Error cover: 1\n", "Done\n" ] } ], "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": 50, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.937879Z", "start_time": "2024-05-16T13:59:41.937870Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:29.950933Z", "iopub.status.busy": "2025-06-03T19:57:29.950633Z", "iopub.status.idle": "2025-06-03T19:57:31.604606Z", "shell.execute_reply": "2025-06-03T19:57:31.604118Z", "shell.execute_reply.started": "2025-06-03T19:57:29.950919Z" } }, "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": 51, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T19:57:31.605427Z", "iopub.status.busy": "2025-06-03T19:57:31.605102Z", "iopub.status.idle": "2025-06-03T19:57:31.621615Z", "shell.execute_reply": "2025-06-03T19:57:31.621241Z", "shell.execute_reply.started": "2025-06-03T19:57:31.605412Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Counter({'artist_consistency': 1202, None: 1198, 'cover': 1036, 'extend': 356, 'infill': 280})\n" ] } ], "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": 52, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.938629Z", "start_time": "2024-05-16T13:59:41.938621Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.622294Z", "iopub.status.busy": "2025-06-03T19:57:31.622039Z", "iopub.status.idle": "2025-06-03T19:57:31.632721Z", "shell.execute_reply": "2025-06-03T19:57:31.632384Z", "shell.execute_reply.started": "2025-06-03T19:57:31.622281Z" } }, "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": 53, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939205Z", "start_time": "2024-05-16T13:59:41.939198Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.634323Z", "iopub.status.busy": "2025-06-03T19:57:31.634075Z", "iopub.status.idle": "2025-06-03T19:57:31.644924Z", "shell.execute_reply": "2025-06-03T19:57:31.644583Z", "shell.execute_reply.started": "2025-06-03T19:57:31.634311Z" } }, "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": 54, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939977Z", "start_time": "2024-05-16T13:59:41.939969Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.645523Z", "iopub.status.busy": "2025-06-03T19:57:31.645311Z", "iopub.status.idle": "2025-06-03T19:57:31.656253Z", "shell.execute_reply": "2025-06-03T19:57:31.655910Z", "shell.execute_reply.started": "2025-06-03T19:57:31.645512Z" } }, "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": 55, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.940610Z", "start_time": "2024-05-16T13:59:41.940603Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.656910Z", "iopub.status.busy": "2025-06-03T19:57:31.656660Z", "iopub.status.idle": "2025-06-03T19:57:31.666801Z", "shell.execute_reply": "2025-06-03T19:57:31.666462Z", "shell.execute_reply.started": "2025-06-03T19:57:31.656898Z" } }, "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": 56, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941167Z", "start_time": "2024-05-16T13:59:41.941159Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.667288Z", "iopub.status.busy": "2025-06-03T19:57:31.667182Z", "iopub.status.idle": "2025-06-03T19:57:31.677945Z", "shell.execute_reply": "2025-06-03T19:57:31.677607Z", "shell.execute_reply.started": "2025-06-03T19:57:31.667277Z" } }, "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": 57, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941801Z", "start_time": "2024-05-16T13:59:41.941793Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.678575Z", "iopub.status.busy": "2025-06-03T19:57:31.678329Z", "iopub.status.idle": "2025-06-03T19:57:31.691751Z", "shell.execute_reply": "2025-06-03T19:57:31.691391Z", "shell.execute_reply.started": "2025-06-03T19:57:31.678563Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "2036 0\n" ] } ], "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": 58, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.942520Z", "start_time": "2024-05-16T13:59:41.942511Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.692431Z", "iopub.status.busy": "2025-06-03T19:57:31.692171Z", "iopub.status.idle": "2025-06-03T19:57:31.725064Z", "shell.execute_reply": "2025-06-03T19:57:31.724673Z", "shell.execute_reply.started": "2025-06-03T19:57:31.692419Z" } }, "outputs": [], "source": [ "train_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_tr.json\"))" ] }, { "cell_type": "code", "execution_count": 59, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.943072Z", "start_time": "2024-05-16T13:59:41.943065Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.725756Z", "iopub.status.busy": "2025-06-03T19:57:31.725511Z", "iopub.status.idle": "2025-06-03T19:57:31.751157Z", "shell.execute_reply": "2025-06-03T19:57:31.750775Z", "shell.execute_reply.started": "2025-06-03T19:57:31.725744Z" } }, "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": 60, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.944246Z", "start_time": "2024-05-16T13:59:41.944237Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.751699Z", "iopub.status.busy": "2025-06-03T19:57:31.751587Z", "iopub.status.idle": "2025-06-03T19:57:31.763391Z", "shell.execute_reply": "2025-06-03T19:57:31.763037Z", "shell.execute_reply.started": "2025-06-03T19:57:31.751687Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "total samples 403028 (403068, 168)\n" ] } ], "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": 61, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945249Z", "start_time": "2024-05-16T13:59:41.945241Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.764011Z", "iopub.status.busy": "2025-06-03T19:57:31.763784Z", "iopub.status.idle": "2025-06-03T19:57:31.774617Z", "shell.execute_reply": "2025-06-03T19:57:31.774269Z", "shell.execute_reply.started": "2025-06-03T19:57:31.763998Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1 epoch per batch 4, total 6297.3125\n" ] } ], "source": [ "print(\"1 epoch per batch 4, total\", total_iters / 8 / 2 / 4)" ] }, { "cell_type": "code", "execution_count": 62, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945972Z", "start_time": "2024-05-16T13:59:41.945964Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.775255Z", "iopub.status.busy": "2025-06-03T19:57:31.775003Z", "iopub.status.idle": "2025-06-03T19:57:31.785224Z", "shell.execute_reply": "2025-06-03T19:57:31.784893Z", "shell.execute_reply.started": "2025-06-03T19:57:31.775243Z" } }, "outputs": [], "source": [ "# !cd /home/tony/Work/tony/slurm/sem_4p5_dpo && sbatch sbatch_ipo_4p5" ] }, { "cell_type": "code", "execution_count": 63, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T19:57:31.785754Z", "iopub.status.busy": "2025-06-03T19:57:31.785650Z", "iopub.status.idle": "2025-06-03T19:57:31.810029Z", "shell.execute_reply": "2025-06-03T19:57:31.809652Z", "shell.execute_reply.started": "2025-06-03T19:57:31.785744Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Cache kept!\n" ] } ], "source": [ "import shutil\n", "\n", "# Basic file copy\n", "shutil.copy(\n", " \"/home/tony/Work/tony/Preference/make_dataset_auk_mixed.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": 64, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.946562Z", "start_time": "2024-05-16T13:59:41.946555Z" }, "execution": { "iopub.execute_input": "2025-06-03T19:57:31.810608Z", "iopub.status.busy": "2025-06-03T19:57:31.810452Z", "iopub.status.idle": "2025-06-03T19:57:31.821322Z", "shell.execute_reply": "2025-06-03T19:57:31.820971Z", "shell.execute_reply.started": "2025-06-03T19:57:31.810596Z" } }, "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": 65, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T19:57:31.821928Z", "iopub.status.busy": "2025-06-03T19:57:31.821819Z", "iopub.status.idle": "2025-06-03T19:57:31.832315Z", "shell.execute_reply": "2025-06-03T19:57:31.831985Z", "shell.execute_reply.started": "2025-06-03T19:57:31.821917Z" } }, "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": 66, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T19:57:31.832882Z", "iopub.status.busy": "2025-06-03T19:57:31.832777Z", "iopub.status.idle": "2025-06-03T19:57:31.843176Z", "shell.execute_reply": "2025-06-03T19:57:31.842847Z", "shell.execute_reply.started": "2025-06-03T19:57:31.832871Z" } }, "outputs": [], "source": [ "# train_metas = read_jsonl(os.path.join(OUT_DATA_DIR, f\"meta_tr.jsonl\"))" ] }, { "cell_type": "code", "execution_count": 67, "metadata": { "execution": { "iopub.execute_input": "2025-06-03T19:57:31.843787Z", "iopub.status.busy": "2025-06-03T19:57:31.843564Z", "iopub.status.idle": "2025-06-03T19:57:31.854910Z", "shell.execute_reply": "2025-06-03T19:57:31.854591Z", "shell.execute_reply.started": "2025-06-03T19:57:31.843775Z" } }, "outputs": [ { "data": { "text/plain": [ "dict_keys(['perference_0', 'perference_1'])" ] }, "execution_count": 67, "metadata": {}, "output_type": "execute_result" } ], "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 }