{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:21.040680Z", "start_time": "2024-05-16T13:58:19.777010Z" }, "execution": { "iopub.execute_input": "2025-03-20T20:14:22.619680Z", "iopub.status.busy": "2025-03-20T20:14:22.619548Z", "iopub.status.idle": "2025-03-20T20:14:26.463647Z", "shell.execute_reply": "2025-03-20T20:14:26.463110Z", "shell.execute_reply.started": "2025-03-20T20:14:22.619666Z" } }, "outputs": [], "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", "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": 2, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:21.082172Z", "start_time": "2024-05-16T13:58:21.041926Z" }, "execution": { "iopub.execute_input": "2025-03-20T20:14:26.465664Z", "iopub.status.busy": "2025-03-20T20:14:26.465537Z", "iopub.status.idle": "2025-03-20T20:14:26.524781Z", "shell.execute_reply": "2025-03-20T20:14:26.524341Z", "shell.execute_reply.started": "2025-03-20T20:14:26.465651Z" } }, "outputs": [], "source": [ "OUT_DATA_DIR = \"/app/suno/data/dpo/30b_t6_v35\"\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": 3, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:53.962528Z", "start_time": "2024-05-16T13:58:21.105919Z" }, "execution": { "iopub.execute_input": "2025-03-20T20:14:26.526478Z", "iopub.status.busy": "2025-03-20T20:14:26.526352Z", "iopub.status.idle": "2025-03-20T20:15:20.749130Z", "shell.execute_reply": "2025-03-20T20:15:20.748547Z", "shell.execute_reply.started": "2025-03-20T20:14:26.526465Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Preference data shape (1705756, 90)\n" ] } ], "source": [ "df = pd.read_pickle(\n", " # \"/home/tony/Data/Preference/30b_v3/interesting_clips_v4_t_4_20240923_full_with_sem_distance_and_similarity.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v2/interesting_clips_v4_t_3_20240919_full_l10_with_cer.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v3/interesting_clips_v4_t_4_20240925_full_l10_with_cer.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v5/interesting_clips_v4_t_5_20241029_full_with_cer.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_t_6_20241117_full_with_cer.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_t_6_20241118_full.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250222_full.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250301_full.pkl\"\n", " \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250227_full_long.pkl\"\n", " # \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250107_full.pkl\"\n", ") # , engine='python')\n", "# df = pd.read_csv(\n", "# \"/home/tony/Data/Preference/30b_v0/interesting_clips_v4_t_1_20240808.csv\"\n", "# ) # , engine='python')\n", "print(\"Preference data shape\", df.shape)\n", "\n", "# df_cover = pd.read_pickle(\n", "# \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_t_6_20241109_full_with_sem_distance_and_similarity.pkl\"\n", "# )\n", "# print(df_cover.shape)\n", "\n", "# df_artist = pd.read_pickle(\n", "# \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_t_6_20241109_full_with_sem_distance_and_similarity_artist.pkl\"\n", "# )\n", "# print(df_cover.shape)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "pre-infill filter (1705756, 90) unique user ids 71248\n", "post-infill filter (131428, 90) unique user ids 16221\n" ] } ], "source": [ "# infill only filter\n", "print(\"pre-infill filter\", df.shape, \"unique user ids\", df[\"user_id\"].nunique())\n", "df = df[df[\"task\"].isin([\"infill\", \"infill_intro\", \"infill_outro\"])].copy()\n", "print(\"post-infill filter\", df.shape, \"unique user ids\", df[\"user_id\"].nunique())" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2025-03-20T20:15:20.751109Z", "iopub.status.busy": "2025-03-20T20:15:20.750979Z", "iopub.status.idle": "2025-03-20T20:15:21.096600Z", "shell.execute_reply": "2025-03-20T20:15:21.096129Z", "shell.execute_reply.started": "2025-03-20T20:15:20.751095Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Preference data shape (1074004, 90)\n", "pre-infill filter (1074004, 90) unique user ids 84323\n", "post-infill filter (49746, 90) unique user ids 12934\n", "post-infill merge (181174, 90) unique user ids 26633\n" ] } ], "source": [ "df_2 = pd.read_pickle(\n", " \"/home/tony/Data/Preference/30b_v6/interesting_clips_v4_h_t_6_20250421_full_long.pkl\"\n", ")\n", "print(\"Preference data shape\", df_2.shape)\n", "# infill only filter\n", "print(\"pre-infill filter\", df_2.shape, \"unique user ids\", df_2[\"user_id\"].nunique())\n", "df_2 = df_2[df_2[\"task\"].isin([\"infill\", \"infill_intro\", \"infill_outro\"])].copy()\n", "print(\"post-infill filter\", df_2.shape, \"unique user ids\", df_2[\"user_id\"].nunique())\n", "df = pd.concat([df, df_2])\n", "print(\"post-infill merge\", df.shape, \"unique user ids\", df[\"user_id\"].nunique())" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2025-03-20T20:15:21.126691Z", "iopub.status.busy": "2025-03-20T20:15:21.126566Z", "iopub.status.idle": "2025-03-20T20:15:31.943706Z", "shell.execute_reply": "2025-03-20T20:15:31.943122Z", "shell.execute_reply.started": "2025-03-20T20:15:21.126678Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after dropna (181174, 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": "2025-03-20T20:15:31.944427Z", "iopub.status.busy": "2025-03-20T20:15:31.944276Z", "iopub.status.idle": "2025-03-20T20:17:51.270886Z", "shell.execute_reply": "2025-03-20T20:17:51.270121Z", "shell.execute_reply.started": "2025-03-20T20:15:31.944412Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "6138759\n", "6138759\n", "pre-downloaded df (181174, 85)\n", "downloaded df (181174, 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": "2025-03-20T20:17:51.271813Z", "iopub.status.busy": "2025-03-20T20:17:51.271632Z", "iopub.status.idle": "2025-03-20T20:17:52.714796Z", "shell.execute_reply": "2025-03-20T20:17:52.714179Z", "shell.execute_reply.started": "2025-03-20T20:17:51.271796Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_30b\n", "True 181174\n", "Name: count, dtype: int64\n" ] }, { "data": { "text/plain": [ "task\n", "infill 181076\n", "infill_intro 98\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": "2025-03-20T20:17:52.715693Z", "iopub.status.busy": "2025-03-20T20:17:52.715519Z", "iopub.status.idle": "2025-03-20T20:17:52.732265Z", "shell.execute_reply": "2025-03-20T20:17:52.731701Z", "shell.execute_reply.started": "2025-03-20T20:17:52.715676Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(181174, 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": "2025-03-20T20:17:52.733063Z", "iopub.status.busy": "2025-03-20T20:17:52.732911Z", "iopub.status.idle": "2025-03-20T20:17:53.572077Z", "shell.execute_reply": "2025-03-20T20:17:53.571330Z", "shell.execute_reply.started": "2025-03-20T20:17:52.733047Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "preference model_name \n", "False chirp-v4-h-t-6 90587\n", "True chirp-v4-h-t-6 90587\n", "Name: count, dtype: int64\n", "before filter on model name (181174, 86)\n", "after filter on model name (181174, 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": "2025-03-20T20:17:53.572996Z", "iopub.status.busy": "2025-03-20T20:17:53.572827Z", "iopub.status.idle": "2025-03-20T20:17:53.596310Z", "shell.execute_reply": "2025-03-20T20:17:53.595725Z", "shell.execute_reply.started": "2025-03-20T20:17:53.572977Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 181100\n", "True 74\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": "2025-03-20T20:17:53.597088Z", "iopub.status.busy": "2025-03-20T20:17:53.596936Z", "iopub.status.idle": "2025-03-20T20:17:56.247824Z", "shell.execute_reply": "2025-03-20T20:17:56.247019Z", "shell.execute_reply.started": "2025-03-20T20:17:53.597073Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "before filter on request id pairs (181174, 86)\n", "after filter on request id pairs (181174, 86)\n", "preference model_name \n", "False chirp-v4-h-t-6 90587\n", "True chirp-v4-h-t-6 90587\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": "2025-03-20T20:17:56.248782Z", "iopub.status.busy": "2025-03-20T20:17:56.248602Z", "iopub.status.idle": "2025-03-20T20:23:43.102711Z", "shell.execute_reply": "2025-03-20T20:23:43.101954Z", "shell.execute_reply.started": "2025-03-20T20:17:56.248765Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "unique_requests 90587\n", "before removing duplicates (181174, 155)\n", "after removing duplicates (181174, 148)\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": "2025-03-20T20:23:43.103635Z", "iopub.status.busy": "2025-03-20T20:23:43.103461Z", "iopub.status.idle": "2025-03-20T20:23:43.880658Z", "shell.execute_reply": "2025-03-20T20:23:43.880120Z", "shell.execute_reply.started": "2025-03-20T20:23:43.103618Z" } }, "outputs": [ { "data": { "text/plain": [ "task\n", "infill 181076\n", "infill_intro 98\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": "2025-03-20T20:23:43.881441Z", "iopub.status.busy": "2025-03-20T20:23:43.881283Z", "iopub.status.idle": "2025-03-20T20:23:48.072815Z", "shell.execute_reply": "2025-03-20T20:23:48.072197Z", "shell.execute_reply.started": "2025-03-20T20:23:43.881426Z" } }, "outputs": [ { "data": { "text/plain": [ "pos_diff_preference\n", "1.0 67330\n", "2.0 23257\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": "2025-03-20T20:23:48.073685Z", "iopub.status.busy": "2025-03-20T20:23:48.073520Z", "iopub.status.idle": "2025-03-20T20:23:49.564713Z", "shell.execute_reply": "2025-03-20T20:23:49.564009Z", "shell.execute_reply.started": "2025-03-20T20:23:48.073670Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive param_experiment\n", "temp_s_70 2357\n", "temp_s_80 2330\n", "step_8 2316\n", "text_1 2166\n", "text_3 1525\n", "step_16 1146\n", "step_12 1127\n", "step_10 826\n", "temp_s_90 696\n", "step_16_text_1 648\n", "adjust_cfg_steps 440\n", "text_15 417\n", "temp_s_95 409\n", "min_p_002 392\n", "min_p_0001 378\n", "text_25 356\n", "s_10_t_12 108\n", "text_2 98\n", "s_20_t_12 94\n", "min_p_02 64\n", "min_p_01 59\n", "min_p_005 48\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": "2025-03-20T20:23:49.568824Z", "iopub.status.busy": "2025-03-20T20:23:49.568511Z", "iopub.status.idle": "2025-03-20T20:23:49.585611Z", "shell.execute_reply": "2025-03-20T20:23:49.585061Z", "shell.execute_reply.started": "2025-03-20T20:23:49.568804Z" } }, "outputs": [], "source": [ "# df[df[\"preference\"]][\"cer_diff_preference\"].hist(bins=50)\n", "# print(df[df[\"preference\"]][\"cer_diff_preference\"].quantile(0.95))\n", "# plt.show()\n", "# print(df[df[\"preference\"]][\"cer\"].hist(bins=50))\n", "# plt.show()" ] }, { "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": "2025-03-20T20:23:49.586385Z", "iopub.status.busy": "2025-03-20T20:23:49.586234Z", "iopub.status.idle": "2025-03-20T20:24:08.098903Z", "shell.execute_reply": "2025-03-20T20:24:08.098166Z", "shell.execute_reply.started": "2025-03-20T20:23:49.586370Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "0\n", "good_continue_at\n", "True 181174\n", "Name: count, dtype: int64\n", "\n", " Check some basics... \n", " preference\n", "False 90587\n", "True 90587\n", "Name: count, dtype: int64 is_30b\n", "True 181174\n", "Name: count, dtype: int64 model_name\n", "chirp-v4-h-t-6 181174\n", "Name: count, dtype: int64 preference model_name \n", "False chirp-v4-h-t-6 90587\n", "True chirp-v4-h-t-6 90587\n", "Name: count, dtype: int64\n", "task\n", "infill 181076\n", "infill_intro 98\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", " if row[\"continue_at\"] is not None:\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": "2025-03-20T20:24:08.099823Z", "iopub.status.busy": "2025-03-20T20:24:08.099657Z", "iopub.status.idle": "2025-03-20T20:24:08.377857Z", "shell.execute_reply": "2025-03-20T20:24:08.377272Z", "shell.execute_reply.started": "2025-03-20T20:24:08.099807Z" } }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" }, { "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))" ] }, { "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": "2025-03-20T20:24:08.394678Z", "iopub.status.busy": "2025-03-20T20:24:08.394527Z", "iopub.status.idle": "2025-03-20T20:24:14.019169Z", "shell.execute_reply": "2025-03-20T20:24:14.018389Z", "shell.execute_reply.started": "2025-03-20T20:24:08.394664Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "after duration 0.9737600317926414\n", "after infill duration 0.8913420247938446\n", "neg_filter_reaction_play_count 1.0\n", "neg_filter_upvote_count 0.9968\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 0.9308\n", "pos_filter_cer_diff_preference 1.0\n", "pos_filter_bad_flags 1.0\n", "after filter on play counts 0.8702\n", "after filter on higher quality 1.0\n", "----------------\n", "negative 78013 positive 63379\n", "----------------\n", "total pair requests 90587 --> selected pair requests 62247 frac 0.687\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": 21, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.250737Z", "start_time": "2024-05-16T13:59:41.036434Z" }, "execution": { "iopub.execute_input": "2025-03-20T20:24:14.020133Z", "iopub.status.busy": "2025-03-20T20:24:14.019953Z", "iopub.status.idle": "2025-03-20T20:24:15.729012Z", "shell.execute_reply": "2025-03-20T20:24:15.728301Z", "shell.execute_reply.started": "2025-03-20T20:24:14.020116Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "30b_t6_v35 requests 62247 clips 124494 total khrs 1.090; N gpus for 1000 iters 7.781; 4 gpus for x iters 1945.219; n unique users 21873 n pro users 19541\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", "# 30b_t6_v34 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", "# 30b_t6_v35 requests 62247 clips 124494 total khrs 1.090; N gpus for 1000 iters 7.781; 4 gpus for x iters 1945.219; n unique users 21873 n pro users 19541" ] }, { "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": "2025-03-20T20:24:15.729911Z", "iopub.status.busy": "2025-03-20T20:24:15.729740Z", "iopub.status.idle": "2025-03-20T20:24:15.903147Z", "shell.execute_reply": "2025-03-20T20:24:15.902501Z", "shell.execute_reply.started": "2025-03-20T20:24:15.729894Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive in playlist (10144, 154)\n", "task\n", "infill 124422\n", "infill_intro 72\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": "2025-03-20T20:24:15.904002Z", "iopub.status.busy": "2025-03-20T20:24:15.903831Z", "iopub.status.idle": "2025-03-20T20:24:16.096590Z", "shell.execute_reply": "2025-03-20T20:24:16.096007Z", "shell.execute_reply.started": "2025-03-20T20:24:15.903985Z" } }, "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": "2025-03-20T20:24:16.097392Z", "iopub.status.busy": "2025-03-20T20:24:16.097234Z", "iopub.status.idle": "2025-03-20T20:24:16.112785Z", "shell.execute_reply": "2025-03-20T20:24:16.112275Z", "shell.execute_reply.started": "2025-03-20T20:24:16.097376Z" } }, "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": "2025-03-20T20:24:16.113509Z", "iopub.status.busy": "2025-03-20T20:24:16.113362Z", "iopub.status.idle": "2025-03-20T20:24:16.125183Z", "shell.execute_reply": "2025-03-20T20:24:16.124673Z", "shell.execute_reply.started": "2025-03-20T20:24:16.113494Z" } }, "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": "2025-03-20T20:24:16.125907Z", "iopub.status.busy": "2025-03-20T20:24:16.125754Z", "iopub.status.idle": "2025-03-20T20:24:16.137273Z", "shell.execute_reply": "2025-03-20T20:24:16.136777Z", "shell.execute_reply.started": "2025-03-20T20:24:16.125893Z" } }, "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": "2025-03-20T20:24:16.137974Z", "iopub.status.busy": "2025-03-20T20:24:16.137830Z", "iopub.status.idle": "2025-03-20T20:24:16.149347Z", "shell.execute_reply": "2025-03-20T20:24:16.148849Z", "shell.execute_reply.started": "2025-03-20T20:24:16.137961Z" } }, "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": "2025-03-20T20:24:16.150179Z", "iopub.status.busy": "2025-03-20T20:24:16.149875Z", "iopub.status.idle": "2025-03-20T20:24:16.161328Z", "shell.execute_reply": "2025-03-20T20:24:16.160821Z", "shell.execute_reply.started": "2025-03-20T20:24:16.150163Z" } }, "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": "2025-03-20T20:24:16.162018Z", "iopub.status.busy": "2025-03-20T20:24:16.161874Z", "iopub.status.idle": "2025-03-20T20:24:16.173437Z", "shell.execute_reply": "2025-03-20T20:24:16.172935Z", "shell.execute_reply.started": "2025-03-20T20:24:16.162004Z" } }, "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": "2025-03-20T20:24:16.174378Z", "iopub.status.busy": "2025-03-20T20:24:16.174003Z", "iopub.status.idle": "2025-03-20T20:24:16.185551Z", "shell.execute_reply": "2025-03-20T20:24:16.185036Z", "shell.execute_reply.started": "2025-03-20T20:24:16.174363Z" } }, "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": "2025-03-20T20:24:16.186283Z", "iopub.status.busy": "2025-03-20T20:24:16.186139Z", "iopub.status.idle": "2025-03-20T20:24:16.197880Z", "shell.execute_reply": "2025-03-20T20:24:16.197373Z", "shell.execute_reply.started": "2025-03-20T20:24:16.186269Z" } }, "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": "2025-03-20T20:24:16.198583Z", "iopub.status.busy": "2025-03-20T20:24:16.198437Z", "iopub.status.idle": "2025-03-20T20:24:16.210321Z", "shell.execute_reply": "2025-03-20T20:24:16.209808Z", "shell.execute_reply.started": "2025-03-20T20:24:16.198570Z" } }, "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": "2025-03-20T20:24:16.211020Z", "iopub.status.busy": "2025-03-20T20:24:16.210880Z", "iopub.status.idle": "2025-03-20T20:24:16.222443Z", "shell.execute_reply": "2025-03-20T20:24:16.221937Z", "shell.execute_reply.started": "2025-03-20T20:24:16.211007Z" } }, "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": "2025-03-20T20:24:16.223115Z", "iopub.status.busy": "2025-03-20T20:24:16.222977Z", "iopub.status.idle": "2025-03-20T20:24:16.237166Z", "shell.execute_reply": "2025-03-20T20:24:16.236608Z", "shell.execute_reply.started": "2025-03-20T20:24:16.223101Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "is_public\n", "False 124441\n", "True 53\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(df_slice[\"is_public\"].value_counts())" ] }, { "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": "2025-03-20T20:27:49.687447Z", "iopub.status.busy": "2025-03-20T20:27:49.686995Z", "iopub.status.idle": "2025-03-20T20:28:04.487710Z", "shell.execute_reply": "2025-03-20T20:28:04.486910Z", "shell.execute_reply.started": "2025-03-20T20:27:49.687425Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(124494, 154)\n", "task\n", "infill 124422\n", "infill_intro 72\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_20250227_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": "markdown", "metadata": {}, "source": [ "## Need to kick out the ones has gpt prompt -- these are pairs with different text inputs" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932296Z", "start_time": "2024-05-16T13:59:41.932287Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.576185Z", "iopub.status.idle": "2025-03-20T20:24:16.576382Z", "shell.execute_reply": "2025-03-20T20:24:16.576291Z", "shell.execute_reply.started": "2025-03-20T20:24:16.576282Z" } }, "outputs": [], "source": [ "# don't have continue at\n", "df_slice[\"request_id\"] = df_slice[\"request_id\"].astype(str)\n", "# df_slice[df_slice[\"continue_at\"].isna()][\"request_id\"].nunique(), df_slice[\"request_id\"].nunique()" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.577057Z", "iopub.status.idle": "2025-03-20T20:24:16.577227Z", "shell.execute_reply": "2025-03-20T20:24:16.577148Z", "shell.execute_reply.started": "2025-03-20T20:24:16.577140Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(124494, 154)\n", "(124494, 154)\n", "(124494, 154)\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": 38, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932966Z", "start_time": "2024-05-16T13:59:41.932957Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.577743Z", "iopub.status.idle": "2025-03-20T20:24:16.577916Z", "shell.execute_reply": "2025-03-20T20:24:16.577837Z", "shell.execute_reply.started": "2025-03-20T20:24:16.577828Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "62247\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": 39, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.933558Z", "start_time": "2024-05-16T13:59:41.933550Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.578560Z", "iopub.status.idle": "2025-03-20T20:24:16.578959Z", "shell.execute_reply": "2025-03-20T20:24:16.578858Z", "shell.execute_reply.started": "2025-03-20T20:24:16.578847Z" } }, "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": 40, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.579328Z", "iopub.status.idle": "2025-03-20T20:24:16.579477Z", "shell.execute_reply": "2025-03-20T20:24:16.579409Z", "shell.execute_reply.started": "2025-03-20T20:24:16.579402Z" } }, "outputs": [], "source": [ "# df_slice[\"continue_at\"] = -1" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934277Z", "start_time": "2024-05-16T13:59:41.934268Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.579938Z", "iopub.status.idle": "2025-03-20T20:24:16.580095Z", "shell.execute_reply": "2025-03-20T20:24:16.580021Z", "shell.execute_reply.started": "2025-03-20T20:24:16.580014Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "61624 623\n", "(123248, 154) (1246, 154)\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", "\n", "print(train_df.shape, val_df.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Actually make" ] }, { "cell_type": "code", "execution_count": 42, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934954Z", "start_time": "2024-05-16T13:59:41.934946Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.580618Z", "iopub.status.idle": "2025-03-20T20:24:16.580770Z", "shell.execute_reply": "2025-03-20T20:24:16.580699Z", "shell.execute_reply.started": "2025-03-20T20:24:16.580690Z" } }, "outputs": [], "source": [ "# val_df[[\"request_id\", \"metadata\", \"updated_at\", \"user_id\", \"preference\"]].head()" ] }, { "cell_type": "code", "execution_count": 43, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.935620Z", "start_time": "2024-05-16T13:59:41.935613Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.581281Z", "iopub.status.idle": "2025-03-20T20:24:16.581446Z", "shell.execute_reply": "2025-03-20T20:24:16.581371Z", "shell.execute_reply.started": "2025-03-20T20:24:16.581363Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 123248/123248 [00:04<00:00, 28161.50it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1,079 hours of 123248 clips, 7.703 nodes, 1283.8333333333333 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": 45, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936268Z", "start_time": "2024-05-16T13:59:41.936260Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.581914Z", "iopub.status.idle": "2025-03-20T20:24:16.582069Z", "shell.execute_reply": "2025-03-20T20:24:16.581996Z", "shell.execute_reply.started": "2025-03-20T20:24:16.581988Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t_data_memmap is set to: 6016\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 1246/1246 [00:23<00:00, 53.47it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 1246 clips, 0 different prompts\n", "19 hours of False\n", "18 hours of True\n", "infill: 36.4 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": 46, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.582805Z", "iopub.status.idle": "2025-03-20T20:24:16.582967Z", "shell.execute_reply": "2025-03-20T20:24:16.582890Z", "shell.execute_reply.started": "2025-03-20T20:24:16.582883Z" } }, "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": 47, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936964Z", "start_time": "2024-05-16T13:59:41.936957Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.583517Z", "iopub.status.idle": "2025-03-20T20:24:16.583667Z", "shell.execute_reply": "2025-03-20T20:24:16.583598Z", "shell.execute_reply.started": "2025-03-20T20:24:16.583591Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "t_data_memmap is set to: 6016\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|▉ | 11349/123248 [03:27<29:58, 62.23it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "267042, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/e45c39ac-5e66-4f4b-8ba4-d553ffdf08d6.npz.\n", "WTF --> 267043, skip, preference: True, 90e6b53d-7a83-459f-8863-14dab1b7892e, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|▉ | 11450/123248 [03:29<31:31, 59.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "269640, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/e42ccfec-693b-433c-a815-e97cfbf78b87.npz.\n", "WTF --> 269641, skip, preference: True, 35a5e3b0-3643-4339-a0bc-4598e079b7de, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|▉ | 11958/123248 [03:38<29:33, 62.76it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "281726, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/8b282f67-0d39-4c96-9d83-ea7d1c3db7a4.npz.\n", "WTF --> 281727, skip, preference: True, 05bcb4e1-be23-49f9-8b2f-d496e16b0944, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|█ | 12767/123248 [03:52<30:11, 61.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "301418, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4b8b4277-1b8d-44e5-8c07-5ed05f31786a.npz.\n", "WTF --> 301419, skip, preference: True, 8d2026fd-75d5-44ec-ba5a-49c4889b9664, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|█ | 12955/123248 [03:55<31:44, 57.92it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "306448, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/c7a6c4cc-d4b5-459c-92ac-8350910a4200.npz.\n", "WTF --> 306449, skip, preference: True, 01d9944a-02f3-4789-b016-a5eaf70a2be2, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|█▏ | 14115/123248 [04:16<30:18, 60.00it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "236164, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/2f176b3f-ef12-4179-aee5-556756deae58.npz.\n", "WTF --> 236165, skip, preference: True, 9a5c7e2c-2698-423a-9688-836fe9f78058, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|█▍ | 18454/123248 [05:33<29:19, 59.55it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "434818, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/2c74927d-a411-4cf8-963a-ae1d446adcd5.npz.\n", "WTF --> 434819, skip, preference: True, bc8ee5e7-8a6f-4082-87d7-441a20d6920a, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|█▌ | 18894/123248 [05:41<27:53, 62.37it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "446072, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/03a60051-0deb-4a9a-a890-59bf7334828a.npz.\n", "WTF --> 446073, skip, preference: True, c074f5d3-0875-4bf8-910d-03c715e11c2c, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|█▌ | 19444/123248 [05:50<28:23, 60.95it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "460090, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/03df0f52-9ea5-44a2-b96d-d5f849bc4781.npz.\n", "WTF --> 460091, skip, preference: True, 7ff2d228-6c47-48e8-9d72-3de01d2a7df0, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|█▋ | 20543/123248 [06:10<28:35, 59.87it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "345890, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/8dddfd98-f72b-47c5-a5b5-637e3e3f6e5a.npz.\n", "WTF --> 345891, skip, preference: True, 539f7741-6451-4eab-a55c-e32946a685ec, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|█▋ | 20588/123248 [06:11<27:46, 61.59it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "346776, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/012190e5-f8ba-491e-a873-1af722d9d0ed.npz.\n", "WTF --> 346777, skip, preference: True, 8515d72b-d90a-4752-8b3f-7050219cd31c, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|█▋ | 21412/123248 [06:25<26:20, 64.45it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "507616, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/0f167b33-4aa5-40d6-a29f-54605c594a6b.npz.\n", "WTF --> 507617, skip, preference: True, f9813bca-8804-4bcd-a1f6-88460f5a2366, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|█▊ | 22718/123248 [06:47<26:44, 62.67it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "538500, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/1b348407-fe5d-428f-8080-0db5f559a14d.npz.\n", "WTF --> 538501, skip, preference: True, 26d5f282-db01-446b-af60-329bba4a8d38, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|██ | 24765/123248 [07:23<26:10, 62.73it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "417078, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/22af1130-3df2-4798-87bf-d002d0e5bdb2.npz.\n", "WTF --> 417079, skip, preference: True, c25c2fac-5f9a-4a67-9f49-93dbc19c36d0, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|██ | 25254/123248 [07:31<26:02, 62.72it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "600144, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/fa09c0f0-0ce4-4490-9cca-0d4902a8d879.npz.\n", "WTF --> 600145, skip, preference: True, 1103e243-e35c-4887-a748-04e9e1f2b8f7, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|██ | 25311/123248 [07:32<26:02, 62.67it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "601146, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/0d3a1912-f38a-4c43-8424-ba7d5b9e64f6.npz.\n", "WTF --> 601147, skip, preference: True, 56d334d0-0c43-46b0-b09b-eddab6f954e1, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|██▏ | 26727/123248 [07:57<25:52, 62.16it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "633788, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/72b745b1-adb0-4dee-8127-354ef500348f.npz.\n", "WTF --> 633789, skip, preference: True, eca9ad37-2945-49b3-b672-8a9073f8aef8, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|██▎ | 28850/123248 [08:33<25:12, 62.41it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "485554, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/f23bf59e-143e-44ab-bb2c-749914a0015d.npz.\n", "WTF --> 485555, skip, preference: True, bf776438-653a-4a89-a9f4-1c230b31cc4d, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|██▍ | 29469/123248 [08:44<25:18, 61.74it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "698740, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/b616162d-5ba3-4bd3-ad23-1821b0638dfb.npz.\n", "WTF --> 698741, skip, preference: True, e0e2e373-1c18-4fed-bd53-bff9e83bbfd9, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|██▌ | 30848/123248 [09:07<24:34, 62.65it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "732012, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/ec745d69-2366-4a58-8478-ac891559dd96.npz.\n", "WTF --> 732013, skip, preference: True, 3f9f3465-e12a-4ac1-b700-afbcf39ea5d0, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|██▋ | 33491/123248 [10:19<23:15, 64.33it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "797278, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/a855b474-ff2e-496e-a794-ef240760eae4.npz.\n", "WTF --> 797279, skip, preference: True, b6dc68fa-f048-4432-860c-1b88d0645306, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|██▋ | 33812/123248 [10:25<24:42, 60.32it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "804184, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/ded922d9-1f6a-45ac-b229-94805103470f.npz.\n", "WTF --> 804185, skip, preference: True, 1a0fcb2f-d8fc-40e5-8e94-4f176516aaaf, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|███ | 37106/123248 [11:25<23:02, 62.32it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "880106, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/3218f11c-e7a7-4832-b2e6-253a8990b11e.npz.\n", "WTF --> 880107, skip, preference: True, d9e9f67e-d61b-4078-a006-f47c18bac6d1, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|███ | 37260/123248 [11:28<22:33, 63.55it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "884132, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/111af734-aab3-4b4e-84eb-f8633f34ba10.npz.\n", "WTF --> 884133, skip, preference: True, e42fdf32-c1d0-4918-a064-93c980f8c5cc, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|███ | 38244/123248 [11:46<22:40, 62.47it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "907928, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/07ccc1e4-0941-4961-9ad1-a76b1468d1cf.npz.\n", "WTF --> 907929, skip, preference: True, a18029dd-961b-4843-be98-4cceef863abd, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|███▏ | 39049/123248 [12:05<22:08, 63.37it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "928890, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/73879327-c5b6-4ce1-ad60-6050a2c809c1.npz.\n", "WTF --> 928891, skip, preference: True, d41ba42d-e133-4b3e-8689-e6ad5eef51dd, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|███▏ | 40042/123248 [12:22<22:20, 62.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "954156, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/62c96d47-3b0d-4df8-8a88-39b298bc6c37.npz.\n", "WTF --> 954157, skip, preference: True, 719354be-a261-4682-908f-5027b686d8e3, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|████ | 50524/123248 [15:45<19:15, 62.95it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1208532, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4b528cdc-35f9-4771-b9a0-0fd01df03444.npz.\n", "WTF --> 1208533, skip, preference: True, 774d13a4-5254-43d5-82ae-366bc5c30a81, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|████▏ | 51025/123248 [15:54<20:36, 58.41it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1221256, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4809e637-e5e2-432e-91c0-1f9102e4b97f.npz.\n", "WTF --> 1221257, skip, preference: True, e6019ae0-68d6-41f7-b8ba-e98c65d30e04, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|████▉ | 60661/123248 [19:41<16:21, 63.78it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1449406, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/aff63273-3b91-4550-87d4-e03291ed90dc.npz.\n", "WTF --> 1449407, skip, preference: True, 849194aa-eb75-4869-85ae-c42253ee3629, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|█████ | 62504/123248 [20:12<16:37, 60.89it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1495592, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/bf756fd9-5bf1-4e54-b4e9-00673f772d51.npz.\n", "WTF --> 1495593, skip, preference: True, 5bfb5599-f1cc-4639-9a19-0ebfe773331f, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|█████ | 62682/123248 [20:15<16:12, 62.25it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1499854, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/15490ee6-f701-4d02-9904-8cf2f703349d.npz.\n", "WTF --> 1499855, skip, preference: True, 6bc6f973-6945-4dc6-8995-9ab5771069c7, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|█████▍ | 66381/123248 [21:22<14:57, 63.38it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1589074, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/aecaca0d-24ee-40f4-be04-ac9bfcfec3bf.npz.\n", "WTF --> 1589075, skip, preference: True, acbca1bb-484b-4bb0-937a-8a0902095730, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|█████▌ | 68099/123248 [21:51<15:01, 61.14it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1629514, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/66b09f9f-7e30-426d-8a31-d26d91f25ec0.npz.\n", "WTF --> 1629515, skip, preference: True, 75840620-6987-4e09-b060-79f369850298, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|█████▌ | 68518/123248 [21:58<14:25, 63.20it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1639618, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/f8d2467d-3f92-4d4d-8d59-7d9517a33fcc.npz.\n", "WTF --> 1639619, skip, preference: True, 9dad199e-e573-4f2e-8040-2498a638297e, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|█████▋ | 69608/123248 [22:17<14:23, 62.12it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1665454, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/42312d6c-fa1d-4b5c-80ed-2bbeb39c2869.npz.\n", "WTF --> 1665455, skip, preference: True, 9341ad47-7b08-4d61-9a28-734fc6a1a37c, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|█████▊ | 71327/123248 [22:47<13:54, 62.19it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1708162, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/57f69434-ca7b-4815-b1ef-43b2c9fc13a6.npz.\n", "WTF --> 1708163, skip, preference: True, 26bdbd4c-b761-4474-9ef5-603ce90f3520, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|█████▊ | 72311/123248 [23:04<13:12, 64.27it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1732146, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/40c4f04c-3ee8-4e52-b171-3acff70ed0bf.npz.\n", "WTF --> 1732147, skip, preference: True, ebac32eb-e986-43cc-9095-4d50f05748df, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|█████▉ | 73544/123248 [23:25<13:27, 61.58it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1760520, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/de80ade6-a6a4-4fa3-92a7-4d64d4d41a10.npz.\n", "WTF --> 1760521, skip, preference: True, 4ebbf909-8190-4d92-847f-86788357b0e9, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|██████ | 75030/123248 [23:52<12:52, 62.45it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1795670, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/fa3cfa42-18c6-400a-9dcc-c4f88e695072.npz.\n", "WTF --> 1795671, skip, preference: True, 5320f788-77ed-44c6-8618-ce060162b6e7, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|██████ | 75210/123248 [23:55<12:57, 61.81it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1799908, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/bf8372dd-0d5b-4a7c-8b4b-fb793e8edb14.npz.\n", "WTF --> 1799909, skip, preference: True, 70c998a5-c5a5-46dd-84cd-c28081d38b9f, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|██████▏ | 76304/123248 [24:14<12:35, 62.13it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1825206, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/a8b14db3-0cd2-43eb-ab49-f0299538b0cb.npz.\n", "WTF --> 1825207, skip, preference: True, 9c36744b-bd71-4dbb-992d-60853a889544, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|██████▎ | 77556/123248 [24:38<12:13, 62.25it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1853810, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/fb6a54a1-1a1f-4ab6-a2a1-5975a0ef1a66.npz.\n", "WTF --> 1853811, skip, preference: True, 8567a22d-33ad-4240-9b12-6b89be6ce804, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|██████▎ | 77935/123248 [24:45<13:04, 57.79it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1863158, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/8baa060d-914b-4045-b826-bf96bc48493c.npz.\n", "WTF --> 1863159, skip, preference: True, d415ba4b-38dd-44e0-9c0e-365e81b37389, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|██████▍ | 78639/123248 [24:58<37:08, 20.02it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "1881510, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4d5be30b-404c-4f1d-8ebd-5c4661ca819f.npz.\n", "WTF --> 1881511, skip, preference: True, f5253d4c-ef09-4215-9e03-60df4b4256c9, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|██████▍ | 80062/123248 [25:23<11:18, 63.63it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1915486, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/a5254c3a-9a52-4667-920c-b2da59899873.npz.\n", "WTF --> 1915487, skip, preference: True, 9391fef0-296e-4bbf-b355-46d1b6bbea53, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|██████▋ | 81783/123248 [25:54<11:00, 62.81it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1957544, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/b3583555-fa44-46a2-83a5-7b245d8fe73e.npz.\n", "WTF --> 1957545, skip, preference: True, f6308203-26b2-4aed-b442-f683cbf2fe35, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|██████▊ | 84030/123248 [26:34<10:55, 59.79it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2013968, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/cffae1e3-5a05-4db1-b59b-c3d4c1562e63.npz.\n", "WTF --> 2013969, skip, preference: True, 5f9aad87-4c21-4610-8d31-b3f3a8d68c4d, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|███████ | 87151/123248 [27:27<09:42, 61.97it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "1486796, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/233c39fd-7a7c-4484-9f12-e8132061a41d.npz.\n", "WTF --> 1486797, skip, preference: True, d984ee29-f547-44f8-837b-999308310e6b, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|███████ | 87309/123248 [27:29<09:25, 63.50it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2093420, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/b83d0a66-016a-4393-9450-e1aa56438482.npz.\n", "WTF --> 2093421, skip, preference: True, 834fc805-5871-460c-bda6-3e5af927f12f, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|███████▎ | 89580/123248 [28:10<08:47, 63.87it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2150100, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/9008be67-a795-402f-9f31-f5cf8cfcb052.npz.\n", "WTF --> 2150101, skip, preference: True, b894bc6c-1086-450d-9590-04756806c325, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|████████▏ | 101563/123248 [31:37<05:54, 61.18it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2434376, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/295dab62-90a6-4cff-bc14-1ca526dadac0.npz.\n", "WTF --> 2434377, skip, preference: True, f7113fe5-afd6-4e50-a429-2bb41ea2a076, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|████████▎ | 102564/123248 [31:54<05:30, 62.62it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2456824, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/4cb4a6de-e7b2-4349-9ad8-465603d23540.npz.\n", "WTF --> 2456825, skip, preference: True, ec028870-4395-4429-ba17-1063b0de5c7e, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|████████▌ | 104764/123248 [32:31<05:03, 60.95it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2509570, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/7bacbcb7-8260-4496-b8cc-c4d4db6cc0ab.npz.\n", "WTF --> 2509571, skip, preference: True, c59cf741-2abd-4ccd-bad0-4e41d4b1b109, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|████████▌ | 105030/123248 [32:36<04:45, 63.79it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2516078, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/179dbb0b-aaa5-4c54-a294-27973477c1ff.npz.\n", "WTF --> 2516079, skip, preference: True, 846a0d37-557a-473d-9b02-cddd81853ea8, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|████████▌ | 105190/123248 [32:38<04:41, 64.13it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2520812, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/c8bd425a-bc76-429c-8865-7211598a54ed.npz.\n", "WTF --> 2520813, skip, preference: True, 42bd4e79-1852-4814-8456-ee0a79c192fa, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|████████▌ | 105360/123248 [32:41<04:42, 63.24it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2525456, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/6bbec2f1-a856-42a8-add8-8dcf7d2bb4b0.npz.\n", "WTF --> 2525457, skip, preference: True, a87dcde8-09ff-478d-a0f4-2f2865f7a8cf, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|████████▊ | 108319/123248 [33:35<03:55, 63.30it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2594272, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/9de9078b-59fc-44e4-b560-bbe49d8940e9.npz.\n", "WTF --> 2594273, skip, preference: True, 51cdbfc3-34b0-47c0-983a-0186798d6600, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|████████▊ | 108729/123248 [33:42<03:45, 64.27it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2603978, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/fabd0673-c394-42c1-8518-61b3ae66145a.npz.\n", "WTF --> 2603979, skip, preference: True, 1b09d9dc-fe0a-494b-9c3b-f8c5049d8aa5, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|████████▉ | 110922/123248 [34:19<03:14, 63.22it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2655388, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/14847c82-4900-4516-9440-96b2815cde2d.npz.\n", "WTF --> 2655389, skip, preference: True, d778ef28-1f97-4a72-9d2c-438f06c98a65, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|█████████ | 111502/123248 [34:28<03:06, 62.83it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2669688, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/308b4091-32b7-4bee-846f-0e4dab37f7a5.npz.\n", "WTF --> 2669689, skip, preference: True, bc432aa2-cc98-4168-bd65-ee77f2f072c1, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|█████████▏| 113410/123248 [35:01<02:41, 60.79it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2716330, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/a434fa5e-28c7-4ea5-820b-21b7e5d752d2.npz.\n", "WTF --> 2716331, skip, preference: True, dd0a7265-cb21-4bf3-a0f4-977e7ab7dc5a, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|█████████▏| 113710/123248 [35:06<02:35, 61.47it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2724626, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/9c66727a-7134-46b5-abaf-de360a1572e6.npz.\n", "WTF --> 2724627, skip, preference: True, 0801c575-8563-4975-8fad-b2f5b42631db, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|█████████▏| 113805/123248 [35:07<02:36, 60.21it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2727010, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/9c7c42e6-2733-4cf3-86e2-c476043040a5.npz.\n", "WTF --> 2727011, skip, preference: True, 7eb6796a-3265-4f59-ace4-c8ffd5ecab50, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|█████████▎| 115131/123248 [35:31<02:26, 55.45it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2757990, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/aaeea91d-5c9a-46db-9c32-6ba3f1e3c377.npz.\n", "WTF --> 2757991, skip, preference: True, 77f7d5fc-6b50-4994-9e6b-6311b5a2c1ef, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|█████████▎| 115534/123248 [35:38<02:02, 62.82it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2766994, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/6d8920ec-8682-492e-8126-640b5d6bede1.npz.\n", "WTF --> 2766995, skip, preference: True, 92606537-ccbd-42d6-bd4b-bf0c49dfe523, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|█████████▌| 118389/123248 [36:26<01:18, 61.66it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2831896, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/425d7085-f2f4-46bc-83a1-6b9182629c62.npz.\n", "WTF --> 2831897, skip, preference: True, 66c7ba7e-0fdc-4477-ad21-cfaaf97f9c36, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|█████████▋| 118860/123248 [36:34<01:07, 64.58it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2843638, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/4b70a815-c60c-4446-9ee1-0f837977551a.npz.\n", "WTF --> 2843639, skip, preference: True, a73e3a5c-901b-4fe5-98ed-209291335d5c, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|█████████▊| 121106/123248 [37:13<00:33, 64.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2062828, 'full_arr is not a file in the archive', infill, /app/suno/data/dpo/30b_npz/9ab4b856-e426-4ffe-96c4-b9d19b8504bc.npz.\n", "WTF --> 2062829, skip, preference: True, 67f1bef1-b8b7-4eca-bd9f-500761f5cbeb, task: infill.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|█████████▊| 121164/123248 [37:14<00:32, 65.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2896722, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/bdbcb196-ac09-4578-9480-022af7f66c97.npz.\n", "WTF --> 2896723, skip, preference: True, 629f376f-7621-4a7f-bbc6-a2c72d564e56, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|█████████▉| 121743/123248 [37:23<00:23, 65.37it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "2910744, 'full_arr is not a file in the archive', infill_intro, /app/suno/data/dpo/30b_npz/e6df418c-da4e-4e13-959d-c18949c5dcd4.npz.\n", "WTF --> 2910745, skip, preference: True, ab046f04-12f8-4374-99c7-7c5ab8c1d918, task: infill_intro.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████| 123248/123248 [37:52<00:00, 54.24it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 123106 clips, 0 different prompts\n", "1,830 hours of False\n", "1,751 hours of True\n", "infill: 3581.5 hours\n", "🚨 Error infill: 60\n", "🚨 Error infill_intro: 11\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": 48, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.937879Z", "start_time": "2024-05-16T13:59:41.937870Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.584153Z", "iopub.status.idle": "2025-03-20T20:24:16.584309Z", "shell.execute_reply": "2025-03-20T20:24:16.584235Z", "shell.execute_reply.started": "2025-03-20T20:24:16.584228Z" } }, "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": 49, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.584819Z", "iopub.status.idle": "2025-03-20T20:24:16.584970Z", "shell.execute_reply": "2025-03-20T20:24:16.584898Z", "shell.execute_reply.started": "2025-03-20T20:24:16.584891Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Counter({'infill': 1246})\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": 50, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.938629Z", "start_time": "2024-05-16T13:59:41.938621Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.585492Z", "iopub.status.idle": "2025-03-20T20:24:16.585641Z", "shell.execute_reply": "2025-03-20T20:24:16.585573Z", "shell.execute_reply.started": "2025-03-20T20:24:16.585565Z" } }, "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": 51, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939205Z", "start_time": "2024-05-16T13:59:41.939198Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.586546Z", "iopub.status.idle": "2025-03-20T20:24:16.586724Z", "shell.execute_reply": "2025-03-20T20:24:16.586636Z", "shell.execute_reply.started": "2025-03-20T20:24:16.586628Z" } }, "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": 52, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939977Z", "start_time": "2024-05-16T13:59:41.939969Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.587036Z", "iopub.status.idle": "2025-03-20T20:24:16.587186Z", "shell.execute_reply": "2025-03-20T20:24:16.587113Z", "shell.execute_reply.started": "2025-03-20T20:24:16.587106Z" } }, "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": 53, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.940610Z", "start_time": "2024-05-16T13:59:41.940603Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.587651Z", "iopub.status.idle": "2025-03-20T20:24:16.587794Z", "shell.execute_reply": "2025-03-20T20:24:16.587726Z", "shell.execute_reply.started": "2025-03-20T20:24:16.587720Z" } }, "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": 54, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941167Z", "start_time": "2024-05-16T13:59:41.941159Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.588318Z", "iopub.status.idle": "2025-03-20T20:24:16.588472Z", "shell.execute_reply": "2025-03-20T20:24:16.588401Z", "shell.execute_reply.started": "2025-03-20T20:24:16.588394Z" } }, "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": 55, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941801Z", "start_time": "2024-05-16T13:59:41.941793Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.589012Z", "iopub.status.idle": "2025-03-20T20:24:16.589165Z", "shell.execute_reply": "2025-03-20T20:24:16.589095Z", "shell.execute_reply.started": "2025-03-20T20:24:16.589088Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "623 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": 56, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.942520Z", "start_time": "2024-05-16T13:59:41.942511Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.589697Z", "iopub.status.idle": "2025-03-20T20:24:16.589847Z", "shell.execute_reply": "2025-03-20T20:24:16.589779Z", "shell.execute_reply.started": "2025-03-20T20:24:16.589771Z" } }, "outputs": [], "source": [ "train_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_tr.json\"))" ] }, { "cell_type": "code", "execution_count": 57, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.943072Z", "start_time": "2024-05-16T13:59:41.943065Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.590471Z", "iopub.status.idle": "2025-03-20T20:24:16.590624Z", "shell.execute_reply": "2025-03-20T20:24:16.590552Z", "shell.execute_reply.started": "2025-03-20T20:24:16.590545Z" } }, "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)" ] }, { "cell_type": "code", "execution_count": 58, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.944246Z", "start_time": "2024-05-16T13:59:41.944237Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.590959Z", "iopub.status.idle": "2025-03-20T20:24:16.591116Z", "shell.execute_reply": "2025-03-20T20:24:16.591041Z", "shell.execute_reply.started": "2025-03-20T20:24:16.591033Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "total samples 123106 (123248, 154)\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": 59, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945249Z", "start_time": "2024-05-16T13:59:41.945241Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.591751Z", "iopub.status.idle": "2025-03-20T20:24:16.591911Z", "shell.execute_reply": "2025-03-20T20:24:16.591838Z", "shell.execute_reply.started": "2025-03-20T20:24:16.591830Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1 epoch per batch 4, total 1923.53125\n" ] } ], "source": [ "print(\"1 epoch per batch 4, total\", total_iters / 8 / 2 / 4)" ] }, { "cell_type": "code", "execution_count": 60, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945972Z", "start_time": "2024-05-16T13:59:41.945964Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.592475Z", "iopub.status.idle": "2025-03-20T20:24:16.592628Z", "shell.execute_reply": "2025-03-20T20:24:16.592557Z", "shell.execute_reply.started": "2025-03-20T20:24:16.592549Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Submitted batch job 5086\n" ] } ], "source": [ "!cd /home/tony/Work/tony/slurm/30b_dpo && sbatch sbatch_ipo_30b" ] }, { "cell_type": "code", "execution_count": 61, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.593100Z", "iopub.status.idle": "2025-03-20T20:24:16.593451Z", "shell.execute_reply": "2025-03-20T20:24:16.593371Z", "shell.execute_reply.started": "2025-03-20T20:24:16.593363Z" } }, "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_13b_v4_t6.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": 62, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.946562Z", "start_time": "2024-05-16T13:59:41.946555Z" }, "execution": { "iopub.status.busy": "2025-03-20T20:24:16.594007Z", "iopub.status.idle": "2025-03-20T20:24:16.594168Z", "shell.execute_reply": "2025-03-20T20:24:16.594092Z", "shell.execute_reply.started": "2025-03-20T20:24:16.594085Z" } }, "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": 63, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.594741Z", "iopub.status.idle": "2025-03-20T20:24:16.594898Z", "shell.execute_reply": "2025-03-20T20:24:16.594827Z", "shell.execute_reply.started": "2025-03-20T20:24:16.594820Z" } }, "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": 64, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.595472Z", "iopub.status.idle": "2025-03-20T20:24:16.595620Z", "shell.execute_reply": "2025-03-20T20:24:16.595552Z", "shell.execute_reply.started": "2025-03-20T20:24:16.595545Z" } }, "outputs": [], "source": [ "# train_metas = read_jsonl(os.path.join(OUT_DATA_DIR, f\"meta_tr.jsonl\"))" ] }, { "cell_type": "code", "execution_count": 65, "metadata": { "execution": { "iopub.status.busy": "2025-03-20T20:24:16.596229Z", "iopub.status.idle": "2025-03-20T20:24:16.596383Z", "shell.execute_reply": "2025-03-20T20:24:16.596311Z", "shell.execute_reply.started": "2025-03-20T20:24:16.596303Z" } }, "outputs": [ { "data": { "text/plain": [ "dict_keys(['perference_0', 'perference_1'])" ] }, "execution_count": 65, "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 }