Spaces:
Build error
Build error
File size: 8,181 Bytes
51ff9e5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"import pandas as pd\n",
"from tqdm import tqdm\n",
"\n",
"tqdm.pandas()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 1. Load raw data and convert to training data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import gzip\n",
"import json\n",
"\n",
"from tqdm import tqdm\n",
"\n",
"FILE_PATHS = [\n",
" 'YOURPATH-no-hint-train-t05-run_1/output.with_completions.jsonl.gz',\n",
" 'YOURPATH-no-hint-train-t05-run_2/output.with_completions.jsonl.gz',\n",
"]\n",
"\n",
"# More memory efficient for large files\n",
"# Initialize lists to store the data\n",
"data = []\n",
"\n",
"\n",
"# Read file line by line\n",
"for FILE_PATH in FILE_PATHS:\n",
" with gzip.open(FILE_PATH, 'rb') as f: # Use 'rb' for gzipped files\n",
" for i, line in tqdm(\n",
" enumerate(f), desc=f'Processing {FILE_PATH.split(\"/\")[-1]}'\n",
" ):\n",
" # Parse only the fields we need\n",
" raw_data = json.loads(line)\n",
" data.append(\n",
" {\n",
" 'resolved': raw_data['report']['resolved'],\n",
" 'messages': raw_data['raw_completions']['messages']\n",
" if raw_data['raw_completions'] is not None\n",
" else None,\n",
" 'git_patch': raw_data['test_result'].get('git_patch', ''),\n",
" 'tools': raw_data['raw_completions']['tools']\n",
" if raw_data['raw_completions'] is not None\n",
" and 'tools' in raw_data['raw_completions']\n",
" else None,\n",
" }\n",
" )\n",
"\n",
"# Convert to DataFrame after collecting all data\n",
"df = pd.DataFrame(data)\n",
"print(f'#total amount of data={len(df)}')\n",
"df = df[~df['messages'].isna()]\n",
"print(f'#total amount of data after removing nan={len(df)}')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Filter"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def _contains_multiple_tool_calls(messages: list[dict]) -> bool:\n",
" return any(\n",
" message.get('tool_calls') and len(message['tool_calls']) > 1\n",
" for message in messages\n",
" )\n",
"\n",
"\n",
"df['contains_multiple_tool_calls'] = df['messages'].apply(_contains_multiple_tool_calls)\n",
"display(df.groupby(['contains_multiple_tool_calls'])['resolved'].sum())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import copy\n",
"\n",
"# Convert function calling messages to non-function calling messages\n",
"from openhands.llm.fn_call_converter import (\n",
" FunctionCallConversionError,\n",
" convert_fncall_messages_to_non_fncall_messages,\n",
" convert_from_multiple_tool_calls_to_single_tool_call_messages,\n",
")\n",
"\n",
"total_failed = 0\n",
"\n",
"\n",
"def _convert_messages(messages: list[dict], tools: list[dict]) -> list[dict]:\n",
" global total_failed\n",
" message_copy = copy.deepcopy(messages)\n",
" for message in message_copy:\n",
" if message['content'] is None:\n",
" message['content'] = ''\n",
" try:\n",
" return convert_fncall_messages_to_non_fncall_messages(\n",
" message_copy, tools, add_in_context_learning_example=False\n",
" )\n",
" except FunctionCallConversionError:\n",
" total_failed += 1\n",
" # print(f'Failed to convert messages: {messages}\\nTools: {tools}')\n",
" # traceback.print_exc()\n",
" return None\n",
"\n",
"\n",
"df['converted_messages'] = df.apply(\n",
" lambda row: convert_from_multiple_tool_calls_to_single_tool_call_messages(\n",
" row['messages'], ignore_final_tool_result=True\n",
" ),\n",
" axis=1,\n",
")\n",
"df['nonfncall_messages'] = df.apply(\n",
" lambda row: _convert_messages(row['converted_messages'], row['tools']), axis=1\n",
")\n",
"print('total nan', df['nonfncall_messages'].isna().sum())\n",
"df = df[~df['nonfncall_messages'].isna()]\n",
"print(f'Total failed: {total_failed}')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Tokenization"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pandarallel import pandarallel\n",
"from transformers import AutoTokenizer\n",
"\n",
"os.environ['TOKENIZERS_PARALLELISM'] = 'false'\n",
"pandarallel.initialize(progress_bar=True, verbose=1, nb_workers=16)\n",
"tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen2.5-7B-Instruct')\n",
"df['n_tokens'] = df['rm_conv'].parallel_apply(\n",
" lambda x: len(tokenizer.apply_chat_template(x))\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"print(f'BEFORE: #total={len(df)}')\n",
"df_selected = df[df['n_tokens'] < 131072]\n",
"print(f'AFTER(truncated to 128k): #total={len(df_selected)}')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_selected['n_tokens'].describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# ecdf of n_tokens\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"display(df.groupby(['resolved'])['n_tokens'].describe())\n",
"sns.ecdfplot(x='n_tokens', data=df, hue='resolved')\n",
"plt.show()\n",
"\n",
"print(f'#total={len(df)}')\n",
"df_selected = df[df['n_tokens'] < 131072]\n",
"print(f'#selected={len(df_selected)}')\n",
"display(df_selected.groupby(['resolved'])['n_tokens'].describe())\n",
"sns.ecdfplot(x='n_tokens', data=df_selected, hue='resolved')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_selected[~df_selected['resolved']]['n_tokens'].describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_selected['resolved'].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_selected.groupby(['resolved'])['n_tokens'].describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Save Resolved Messages for SFT"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df_selected[df_selected['resolved']][['nonfncall_messages']].rename(\n",
" columns={'nonfncall_messages': 'messages'}\n",
").to_json(\n",
" os.path.join(\n",
" 'YOUR_OUTPUT_FOLDER',\n",
" f'policy_traj_128k_swegym_{df_selected[\"resolved\"].value_counts()[True]}i.jsonl',\n",
" ),\n",
" lines=True,\n",
" orient='records',\n",
")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "openhands-ai-CPy6G0pU-py3.12",
"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": "3.12.8"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|