{ "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": "2024-10-29T23:30:32.976786Z", "iopub.status.busy": "2024-10-29T23:30:32.976607Z", "iopub.status.idle": "2024-10-29T23:30:35.564695Z", "shell.execute_reply": "2024-10-29T23:30:35.564213Z", "shell.execute_reply.started": "2024-10-29T23:30:32.976771Z" } }, "outputs": [], "source": [ "import ast\n", "import os\n", "import shutil\n", "import sys\n", "from collections import defaultdict\n", "\n", "import numpy as np\n", "import pandas as pd\n", "from preference_data_preparation_4min_30b_task 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)" ] }, { "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": "2024-10-29T23:30:35.565542Z", "iopub.status.busy": "2024-10-29T23:30:35.565326Z", "iopub.status.idle": "2024-10-29T23:30:35.598453Z", "shell.execute_reply": "2024-10-29T23:30:35.598073Z", "shell.execute_reply.started": "2024-10-29T23:30:35.565528Z" } }, "outputs": [], "source": [ "OUT_DATA_DIR = \"/app/suno/data/dpo/13b_s29_v6/\"\n", "os.makedirs(OUT_DATA_DIR, exist_ok=True)\n", "shutil.copyfile(\n", " \"/app/suno/data/dpo/7v_v20_full/tokenizer_60k.json\",\n", " os.path.join(OUT_DATA_DIR, \"tokenizer_60k.json\"),\n", ")\n", "NPZ_DIR = \"/app/suno/data/dpo/13b_s8_v29_npz\"" ] }, { "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": "2024-10-29T23:30:35.599193Z", "iopub.status.busy": "2024-10-29T23:30:35.598971Z", "iopub.status.idle": "2024-10-29T23:30:39.765736Z", "shell.execute_reply": "2024-10-29T23:30:39.765228Z", "shell.execute_reply.started": "2024-10-29T23:30:35.599181Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Preference data shape (163440, 68)\n" ] } ], "source": [ "# df = pd.read_csv(\n", "# \"/home/tony/Data/Preference/13b_v0/interesting_clips_v3p5_s_8_20240813.csv\"\n", "# ) # , engine='python')\n", "df = pd.read_pickle(\n", " \"/home/tony/Data/Preference/13b_v1/interesting_clips_13b_s8_v29_20241029_full.pkl\"\n", ") # , engine='python')\n", "print(\"Preference data shape\", df.shape)" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.199480Z", "start_time": "2024-05-16T13:58:53.963687Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:39.766581Z", "iopub.status.busy": "2024-10-29T23:30:39.766390Z", "iopub.status.idle": "2024-10-29T23:30:40.052555Z", "shell.execute_reply": "2024-10-29T23:30:40.052059Z", "shell.execute_reply.started": "2024-10-29T23:30:39.766567Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "173406\n", "173406\n", "pre-downloaded df (163440, 68)\n", "downloaded df (163440, 68)\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", "if \"cycle\" in NPZ_DIR:\n", " # hack in the cycle label\n", " df[\"s3_id\"] += \"_gen_cycle\"\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": 5, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.467253Z", "start_time": "2024-05-16T13:58:56.207647Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:40.053372Z", "iopub.status.busy": "2024-10-29T23:30:40.053190Z", "iopub.status.idle": "2024-10-29T23:30:40.092327Z", "shell.execute_reply": "2024-10-29T23:30:40.091948Z", "shell.execute_reply.started": "2024-10-29T23:30:40.053359Z" } }, "outputs": [ { "data": { "text/plain": [ "is_13b\n", "True 163440\n", "Name: count, dtype: int64" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"is_13b\"] = df[\"model_name\"].str.contains(\"v3p5\")\n", "df[\"is_13b\"].value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# LET's do the data prep" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.592883Z", "start_time": "2024-05-16T13:58:56.470781Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:40.093851Z", "iopub.status.busy": "2024-10-29T23:30:40.093612Z", "iopub.status.idle": "2024-10-29T23:30:40.149254Z", "shell.execute_reply": "2024-10-29T23:30:40.148796Z", "shell.execute_reply.started": "2024-10-29T23:30:40.093838Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "preference model_name \n", "False chirp-v3p5-engine-s-29 81720\n", "True chirp-v3p5-engine-s-29 81720\n", "Name: count, dtype: int64\n", "(163440, 69)\n", "(163440, 69)\n" ] } ], "source": [ "## for 13b this is easy for now\n", "print(df.groupby([\"preference\"])[\"model_name\"].value_counts())\n", "print(df.shape)\n", "df = df[df[\"model_name\"].isin([\"chirp-v3p5-engine-s-29\"])]\n", "print(df.shape)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:58:56.909539Z", "start_time": "2024-05-16T13:58:56.595736Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:40.150097Z", "iopub.status.busy": "2024-10-29T23:30:40.149847Z", "iopub.status.idle": "2024-10-29T23:30:40.276699Z", "shell.execute_reply": "2024-10-29T23:30:40.276225Z", "shell.execute_reply.started": "2024-10-29T23:30:40.150083Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(163440, 69)\n", "(163440, 69)\n", "preference model_name \n", "False chirp-v3p5-engine-s-29 81720\n", "True chirp-v3p5-engine-s-29 81720\n", "Name: count, dtype: int64\n" ] } ], "source": [ "print(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(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": 8, "metadata": { "execution": { "iopub.execute_input": "2024-10-29T23:30:40.277457Z", "iopub.status.busy": "2024-10-29T23:30:40.277287Z", "iopub.status.idle": "2024-10-29T23:30:40.279547Z", "shell.execute_reply": "2024-10-29T23:30:40.279227Z", "shell.execute_reply.started": "2024-10-29T23:30:40.277444Z" } }, "outputs": [], "source": [ "import json\n", "\n", "\n", "def custom_parse(x):\n", " try:\n", " return json.loads(x)\n", " except:\n", " return {}" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:36.043975Z", "start_time": "2024-05-16T13:58:56.910958Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:40.280188Z", "iopub.status.busy": "2024-10-29T23:30:40.279994Z", "iopub.status.idle": "2024-10-29T23:30:59.011963Z", "shell.execute_reply": "2024-10-29T23:30:59.011475Z", "shell.execute_reply.started": "2024-10-29T23:30:40.280177Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "unique_requests 81720\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_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())" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:36.393047Z", "start_time": "2024-05-16T13:59:36.048831Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:59.012739Z", "iopub.status.busy": "2024-10-29T23:30:59.012567Z", "iopub.status.idle": "2024-10-29T23:30:59.028988Z", "shell.execute_reply": "2024-10-29T23:30:59.028598Z", "shell.execute_reply.started": "2024-10-29T23:30:59.012726Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "unique_requests 81720\n" ] } ], "source": [ "# GPT requests are also fine for now\n", "print(\"unique_requests\", df[\"request_id\"].nunique())" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:40.799375Z", "start_time": "2024-05-16T13:59:36.394236Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:59.029724Z", "iopub.status.busy": "2024-10-29T23:30:59.029508Z", "iopub.status.idle": "2024-10-29T23:30:59.920108Z", "shell.execute_reply": "2024-10-29T23:30:59.919635Z", "shell.execute_reply.started": "2024-10-29T23:30:59.029711Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "9451\n", "good_continue_at\n", "True 163300\n", "False 140\n", "Name: count, dtype: int64\n", "\n", " Check some basics... \n", " preference\n", "False 81720\n", "True 81720\n", "Name: count, dtype: int64 is_13b\n", "True 163440\n", "Name: count, dtype: int64 model_name\n", "chirp-v3p5-engine-s-29 163440\n", "Name: count, dtype: int64 preference model_name \n", "False chirp-v3p5-engine-s-29 81720\n", "True chirp-v3p5-engine-s-29 81720\n", "Name: count, dtype: int64\n", "task\n", " 143890\n", "extend 19492\n", "infill 56\n", "artist_consistency 2\n", "Name: count, dtype: int64\n" ] } ], "source": [ "df = df.loc[:, ~df.columns.duplicated()].copy()\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", "for _, row in df[~df[\"continued_parent\"].isna()].iterrows():\n", " audio_prompt_id = row[\"continued_parent\"]\n", " if audio_prompt_id not in audio_prompt_id_to_continue_at:\n", " audio_prompt_id_to_continue_at[audio_prompt_id] = row[\"continue_at\"]\n", " else:\n", " # pick the max\n", " audio_prompt_id = max(\n", " audio_prompt_id_to_continue_at[audio_prompt_id], row[\"continue_at\"]\n", " )\n", "print(len(audio_prompt_id_to_continue_at))\n", "df[\"has_continue_and_start_continue_at\"] = df[\"s3_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_13b\"].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())" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "execution": { "iopub.execute_input": "2024-10-29T23:30:59.920973Z", "iopub.status.busy": "2024-10-29T23:30:59.920717Z", "iopub.status.idle": "2024-10-29T23:30:59.980577Z", "shell.execute_reply": "2024-10-29T23:30:59.980162Z", "shell.execute_reply.started": "2024-10-29T23:30:59.920960Z" } }, "outputs": [ { "data": { "text/plain": [ "pos_diff_preference\n", "1.0 58462\n", "2.0 23258\n", "Name: count, dtype: int64" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df[\"pos_diff_preference\"] = df[\"diff_preference\"].diff()\n", "df[df[\"preference\"]][\"pos_diff_preference\"].value_counts()" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.035167Z", "start_time": "2024-05-16T13:59:40.801098Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:30:59.981337Z", "iopub.status.busy": "2024-10-29T23:30:59.981161Z", "iopub.status.idle": "2024-10-29T23:31:00.150533Z", "shell.execute_reply": "2024-10-29T23:31:00.150053Z", "shell.execute_reply.started": "2024-10-29T23:30:59.981324Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "negative 78105 positive 35960\n", "total pair requests 81720 selected pair requests 33897 frac 0.415\n" ] } ], "source": [ "normal_pos_play_count = 5\n", "# this is lower, cause a concat is probably already ensuring that it is good\n", "concat_pos_play_count = 2\n", "# this is a filter on the concated clip\n", "concat_total_play_count = 5\n", "\n", "neg_filter_selection_mask = (\n", " (df[\"preference\"] == False) # get basics aligned\n", " & (df[\"reaction_play_count\"] >= 1) # has to be played once\n", " # & (df[\"play_count\"] <= 3) # if it is actually bad, shouldn't be listened often\n", " & (df[\"duration\"] >= 10) # can't be too short, otherwise it is obvious\n", " # & (df[\"duration\"] <= 60) # can't be badly long\n", " & (df[\"has_continue_and_start_continue_at\"].isna()) # won't have any continues\n", " & (df[\"norm_play_frac\"] <= 2.1)\n", " # & (df[\"dislike_count\"] >= 1) # this is kinda strict\n", " # & (\n", " # (df_slice[\"is_in_playlist\"] == False)\n", " # & (df_slice[\"concat_in_playlist\"] == False)\n", " # ) # can't be part of a playlist -- otherwise there are some like signal in it?\n", ")\n", "pos_filter_selectin_mask = (\n", " (df[\"preference\"] == True) # get basics aligned\n", " & (\n", " df[\"good_continue_at\"] == True\n", " ) # if continue, needs to continue off a certain percentage\n", " & (df[\"reaction_play_count\"] >= 1)\n", " & (df[\"play_rel_diff\"] >= 0) # this is more like quality assurance\n", " & (df[\"duration\"] >= 10) # can't be too short, otherwise it is obvious\n", " # & (df[\"duration\"] <= 60) # can't be badly long\n", " & (df[\"dislike_count\"] == 0) # can't have dislikes\n", " & (df[\"flag_count\"] == 0) # can't have issues\n", " & (\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\"])\n", " & (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", " # & (df[\"norm_play_frac\"] >= 1.9)\n", " # & (df[\"user_n_clips\"] >= 40) # user needs to have genereated at least 20\n", " # & (df[\"duration_rel_diff\"] < 10) # positive isn't just longer\n", " & ((df[\"task\"] == \"\") | (df[\"task\"] == \"extend\"))\n", " & (\n", " (df[\"upvote_count\"] >= 1)\n", " | (df[\"reaction_play_count\"] >= 5)\n", " | (df[\"concat_play_counts\"] >= 5)\n", " )\n", " # & (df[\"pos_diff_preference\"] == 2)\n", " # & ((0 < df[\"similarity\"]) & (df[\"similarity\"] <= 0.99))\n", " # & ((df[\"cer_diff_preference\"] < 0.5) & (df[\"cer\"] < 0.99)) # cut on hoot cer difference and abs cer\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", " \"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": 14, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.250737Z", "start_time": "2024-05-16T13:59:41.036434Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.151299Z", "iopub.status.busy": "2024-10-29T23:31:00.151133Z", "iopub.status.idle": "2024-10-29T23:31:00.273947Z", "shell.execute_reply": "2024-10-29T23:31:00.273453Z", "shell.execute_reply.started": "2024-10-29T23:31:00.151285Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " requests 33897 clips 67794 total khrs 3.391; N gpus for 1000 iters 4.237; 4 gpus for x iters 1059.281; n unique users 26208 n pro users 13876\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", "# 29 v2 requests 22572 clips 45144 total khrs 2.252; N gpus for 1000 iters 2.821; 4 gpus for x iters 705.375; n unique users 18149 n pro users 10155\n", "# 29 v4 requests 32479 clips 64958 total khrs 3.248; N gpus for 1000 iters 4.060; 4 gpus for x iters 1014.969; n unique users 25192 n pro users 13547\n", "# samve for v5" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.277006Z", "start_time": "2024-05-16T13:59:41.252105Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.274724Z", "iopub.status.busy": "2024-10-29T23:31:00.274548Z", "iopub.status.idle": "2024-10-29T23:31:00.286315Z", "shell.execute_reply": "2024-10-29T23:31:00.285924Z", "shell.execute_reply.started": "2024-10-29T23:31:00.274711Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "positive in playlist (8142, 116)\n" ] } ], "source": [ "test_mask = (df_slice[\"preference\"] == True) & (\n", " (df_slice[\"is_in_playlist\"] == True) | (df_slice[\"concat_in_playlist\"] == True)\n", ")\n", "print(\"positive in playlist\", df_slice[test_mask].shape)" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "execution": { "iopub.execute_input": "2024-10-29T23:31:00.287049Z", "iopub.status.busy": "2024-10-29T23:31:00.286836Z", "iopub.status.idle": "2024-10-29T23:31:00.315758Z", "shell.execute_reply": "2024-10-29T23:31:00.315399Z", "shell.execute_reply.started": "2024-10-29T23:31:00.287036Z" } }, "outputs": [], "source": [ "# BREAK" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.323409Z", "start_time": "2024-05-16T13:59:41.278278Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.316503Z", "iopub.status.busy": "2024-10-29T23:31:00.316282Z", "iopub.status.idle": "2024-10-29T23:31:00.353017Z", "shell.execute_reply": "2024-10-29T23:31:00.352639Z", "shell.execute_reply.started": "2024-10-29T23:31:00.316491Z" } }, "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": 18, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.392244Z", "start_time": "2024-05-16T13:59:41.324472Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.353763Z", "iopub.status.busy": "2024-10-29T23:31:00.353552Z", "iopub.status.idle": "2024-10-29T23:31:00.394322Z", "shell.execute_reply": "2024-10-29T23:31:00.393938Z", "shell.execute_reply.started": "2024-10-29T23:31:00.353752Z" } }, "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": 19, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T14:00:20.866354Z", "start_time": "2024-05-16T14:00:12.443344Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.395019Z", "iopub.status.busy": "2024-10-29T23:31:00.394871Z", "iopub.status.idle": "2024-10-29T23:31:00.436681Z", "shell.execute_reply": "2024-10-29T23:31:00.436299Z", "shell.execute_reply.started": "2024-10-29T23:31:00.395007Z" } }, "outputs": [], "source": [ "# df_slice.to_csv(\"/home/tony/Data/Preference/13b_v0/interesting_clips_v3p5_s_8_20240828_slice.csv\")\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": 20, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932296Z", "start_time": "2024-05-16T13:59:41.932287Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.437300Z", "iopub.status.busy": "2024-10-29T23:31:00.437192Z", "iopub.status.idle": "2024-10-29T23:31:00.475877Z", "shell.execute_reply": "2024-10-29T23:31:00.475479Z", "shell.execute_reply.started": "2024-10-29T23:31:00.437289Z" } }, "outputs": [], "source": [ "# don't have continue at\n", "# df_slice[df_slice[\"continue_at\"].isna()][\"request_id\"].nunique()" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.932966Z", "start_time": "2024-05-16T13:59:41.932957Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.478161Z", "iopub.status.busy": "2024-10-29T23:31:00.477899Z", "iopub.status.idle": "2024-10-29T23:31:00.521142Z", "shell.execute_reply": "2024-10-29T23:31:00.520734Z", "shell.execute_reply.started": "2024-10-29T23:31:00.478148Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "33897\n" ] } ], "source": [ "final_filtered_requests = df_slice[\"request_id\"].unique()\n", "print(len(final_filtered_requests))" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.933558Z", "start_time": "2024-05-16T13:59:41.933550Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.521884Z", "iopub.status.busy": "2024-10-29T23:31:00.521660Z", "iopub.status.idle": "2024-10-29T23:31:00.565320Z", "shell.execute_reply": "2024-10-29T23:31:00.564926Z", "shell.execute_reply.started": "2024-10-29T23:31:00.521872Z" } }, "outputs": [], "source": [ "# df_slice.to_csv(\"/home/tony/Data/Preference/7b_v2/7b_before_recode_20240412\", index=False)" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934277Z", "start_time": "2024-05-16T13:59:41.934268Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.566094Z", "iopub.status.busy": "2024-10-29T23:31:00.565872Z", "iopub.status.idle": "2024-10-29T23:31:00.736552Z", "shell.execute_reply": "2024-10-29T23:31:00.736062Z", "shell.execute_reply.started": "2024-10-29T23:31:00.566082Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "33558 339\n", "(67116, 116) (678, 116)\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\"].isin(set(train_requests))].copy()\n", "val_df = df_slice[df_slice[\"request_id\"].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": "code", "execution_count": 24, "metadata": { "execution": { "iopub.execute_input": "2024-10-29T23:31:00.737349Z", "iopub.status.busy": "2024-10-29T23:31:00.737167Z", "iopub.status.idle": "2024-10-29T23:31:00.739147Z", "shell.execute_reply": "2024-10-29T23:31:00.738823Z", "shell.execute_reply.started": "2024-10-29T23:31:00.737336Z" } }, "outputs": [], "source": [ "# BREAK" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Actually make" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.934954Z", "start_time": "2024-05-16T13:59:41.934946Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.739703Z", "iopub.status.busy": "2024-10-29T23:31:00.739594Z", "iopub.status.idle": "2024-10-29T23:31:00.779915Z", "shell.execute_reply": "2024-10-29T23:31:00.779529Z", "shell.execute_reply.started": "2024-10-29T23:31:00.739692Z" } }, "outputs": [], "source": [ "# val_df[[\"request_id\", \"metadata\", \"updated_at\", \"user_id\", \"preference\"]].head()" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.935620Z", "start_time": "2024-05-16T13:59:41.935613Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:00.780594Z", "iopub.status.busy": "2024-10-29T23:31:00.780446Z", "iopub.status.idle": "2024-10-29T23:31:02.184881Z", "shell.execute_reply": "2024-10-29T23:31:02.184395Z", "shell.execute_reply.started": "2024-10-29T23:31:00.780582Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 67116/67116 [00:01<00:00, 49483.99it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "3,358 hours of 67116 clips, 4.19475 nodes, 1048.6875 steps\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", " except:\n", " print(i, row)\n", " total_duration += row[\"duration\"]\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 / 4} steps\"\n", ")" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936268Z", "start_time": "2024-05-16T13:59:41.936260Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:02.185658Z", "iopub.status.busy": "2024-10-29T23:31:02.185476Z", "iopub.status.idle": "2024-10-29T23:31:13.294622Z", "shell.execute_reply": "2024-10-29T23:31:13.294166Z", "shell.execute_reply.started": "2024-10-29T23:31:02.185645Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████| 678/678 [00:11<00:00, 61.19it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 676 clips, 0 different prompts\n", "17 hours of False\n", "17 hours of True\n", "gen: 526.6 hours\n", "extend: 60.8 hours\n", "Error extend: 2\n", "Done\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "make_dataset(val_df, OUT_DATA_DIR, is_val=True, npz_dir=NPZ_DIR)" ] }, { "cell_type": "code", "execution_count": 28, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.936964Z", "start_time": "2024-05-16T13:59:41.936957Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:31:13.295381Z", "iopub.status.busy": "2024-10-29T23:31:13.295212Z", "iopub.status.idle": "2024-10-29T23:49:18.194944Z", "shell.execute_reply": "2024-10-29T23:49:18.194256Z", "shell.execute_reply.started": "2024-10-29T23:31:13.295368Z" } }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 67116/67116 [18:04<00:00, 61.87it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Total 67030 clips, 9 different prompts\n", "1,748 hours of False\n", "1,726 hours of True\n", "gen: 53315.3 hours\n", "extend: 4932.3 hours\n", "Error extend: 86\n", "Done\n" ] } ], "source": [ "make_dataset(train_df, OUT_DATA_DIR, is_val=False, npz_dir=NPZ_DIR)" ] }, { "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": 29, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.937879Z", "start_time": "2024-05-16T13:59:41.937870Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.196040Z", "iopub.status.busy": "2024-10-29T23:49:18.195801Z", "iopub.status.idle": "2024-10-29T23:49:18.218172Z", "shell.execute_reply": "2024-10-29T23:49:18.217613Z", "shell.execute_reply.started": "2024-10-29T23:49:18.196023Z" } }, "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, 6016, 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": 30, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.938629Z", "start_time": "2024-05-16T13:59:41.938621Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.219202Z", "iopub.status.busy": "2024-10-29T23:49:18.218907Z", "iopub.status.idle": "2024-10-29T23:49:18.245529Z", "shell.execute_reply": "2024-10-29T23:49:18.245056Z", "shell.execute_reply.started": "2024-10-29T23:49:18.219187Z" } }, "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": 31, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939205Z", "start_time": "2024-05-16T13:59:41.939198Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.246475Z", "iopub.status.busy": "2024-10-29T23:49:18.246171Z", "iopub.status.idle": "2024-10-29T23:49:18.283827Z", "shell.execute_reply": "2024-10-29T23:49:18.283316Z", "shell.execute_reply.started": "2024-10-29T23:49:18.246461Z" } }, "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": 32, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.939977Z", "start_time": "2024-05-16T13:59:41.939969Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.284757Z", "iopub.status.busy": "2024-10-29T23:49:18.284476Z", "iopub.status.idle": "2024-10-29T23:49:18.325967Z", "shell.execute_reply": "2024-10-29T23:49:18.325450Z", "shell.execute_reply.started": "2024-10-29T23:49:18.284744Z" } }, "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": 33, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.940610Z", "start_time": "2024-05-16T13:59:41.940603Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.327016Z", "iopub.status.busy": "2024-10-29T23:49:18.326655Z", "iopub.status.idle": "2024-10-29T23:49:18.367375Z", "shell.execute_reply": "2024-10-29T23:49:18.366867Z", "shell.execute_reply.started": "2024-10-29T23:49:18.327001Z" } }, "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": 34, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941167Z", "start_time": "2024-05-16T13:59:41.941159Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.368313Z", "iopub.status.busy": "2024-10-29T23:49:18.368042Z", "iopub.status.idle": "2024-10-29T23:49:18.407895Z", "shell.execute_reply": "2024-10-29T23:49:18.407377Z", "shell.execute_reply.started": "2024-10-29T23:49:18.368300Z" } }, "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": 35, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.941801Z", "start_time": "2024-05-16T13:59:41.941793Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.408891Z", "iopub.status.busy": "2024-10-29T23:49:18.408570Z", "iopub.status.idle": "2024-10-29T23:49:18.447756Z", "shell.execute_reply": "2024-10-29T23:49:18.447225Z", "shell.execute_reply.started": "2024-10-29T23:49:18.408878Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "338 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": 36, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.942520Z", "start_time": "2024-05-16T13:59:41.942511Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.448809Z", "iopub.status.busy": "2024-10-29T23:49:18.448443Z", "iopub.status.idle": "2024-10-29T23:49:18.491963Z", "shell.execute_reply": "2024-10-29T23:49:18.491432Z", "shell.execute_reply.started": "2024-10-29T23:49:18.448794Z" } }, "outputs": [], "source": [ "train_info = read_json(os.path.join(OUT_DATA_DIR, f\"info_tr.json\"))" ] }, { "cell_type": "code", "execution_count": 37, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.943072Z", "start_time": "2024-05-16T13:59:41.943065Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.493007Z", "iopub.status.busy": "2024-10-29T23:49:18.492660Z", "iopub.status.idle": "2024-10-29T23:49:18.525927Z", "shell.execute_reply": "2024-10-29T23:49:18.525433Z", "shell.execute_reply.started": "2024-10-29T23:49:18.492993Z" } }, "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": 38, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.944246Z", "start_time": "2024-05-16T13:59:41.944237Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.526907Z", "iopub.status.busy": "2024-10-29T23:49:18.526571Z", "iopub.status.idle": "2024-10-29T23:49:18.566793Z", "shell.execute_reply": "2024-10-29T23:49:18.566273Z", "shell.execute_reply.started": "2024-10-29T23:49:18.526893Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "total samples 67030 (67116, 116)\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": 39, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945249Z", "start_time": "2024-05-16T13:59:41.945241Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.567743Z", "iopub.status.busy": "2024-10-29T23:49:18.567582Z", "iopub.status.idle": "2024-10-29T23:49:18.606550Z", "shell.execute_reply": "2024-10-29T23:49:18.606030Z", "shell.execute_reply.started": "2024-10-29T23:49:18.567730Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "1 epoch per batch 4, total 1047.34375\n" ] } ], "source": [ "print(\"1 epoch per batch 4, total\", total_iters / 8 / 4 / 2)" ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.945972Z", "start_time": "2024-05-16T13:59:41.945964Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.607482Z", "iopub.status.busy": "2024-10-29T23:49:18.607212Z", "iopub.status.idle": "2024-10-29T23:49:18.903768Z", "shell.execute_reply": "2024-10-29T23:49:18.903021Z", "shell.execute_reply.started": "2024-10-29T23:49:18.607468Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Submitted batch job 1077\n" ] } ], "source": [ "!cd /home/tony/Work/tony/slurm/13b_dpo && sbatch sbatch_ipo_13b_s29" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "execution": { "iopub.execute_input": "2024-10-29T23:49:18.905040Z", "iopub.status.busy": "2024-10-29T23:49:18.904799Z", "iopub.status.idle": "2024-10-29T23:49:18.918607Z", "shell.execute_reply": "2024-10-29T23:49:18.918145Z", "shell.execute_reply.started": "2024-10-29T23:49:18.905024Z" } }, "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_v3p5data_s29.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": 42, "metadata": { "ExecuteTime": { "end_time": "2024-05-16T13:59:41.946562Z", "start_time": "2024-05-16T13:59:41.946555Z" }, "execution": { "iopub.execute_input": "2024-10-29T23:49:18.919511Z", "iopub.status.busy": "2024-10-29T23:49:18.919226Z", "iopub.status.idle": "2024-10-29T23:49:18.950038Z", "shell.execute_reply": "2024-10-29T23:49:18.949574Z", "shell.execute_reply.started": "2024-10-29T23:49:18.919497Z" } }, "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)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "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": "3.10.14" }, "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 }