mirror/computer
1
0
Fork 0
mirror of https://github.com/trycua/computer.git synced 2026-01-05 21:09:58 -06:00
Code Issues Packages Projects Releases Wiki Activity

added simple task id

Browse Source
This commit is contained in:
Dillon DuPont
2025-08-27 13:28:24 -04:00
parent 61a442da56
commit 3c502354a8
1 changed files with 6 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
notebooks/eval_osworld.ipynb
View File

@@ -57,17 +57,9 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\Users\\dillo\\miniconda3\\envs\\cua\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"name": "stdout",
"output_type": "stream",
@@ -76,7 +68,7 @@
"\u001b[90m╔═════════════════════════════════════════════════════════════════╗\u001b[0m\n",
"\u001b[90m║\u001b[0m 🚀 See your agent live at: \u001b[90m║\u001b[0m\n",
"\u001b[90m╟─────────────────────────────────────────────────────────────────╢\u001b[0m\n",
"\u001b[90m║\u001b[0m \u001b[1m\u001b[33mhttps://app.hud.so/trace/60b2956b-8520-4225-93d3-22ea2ff0253b\u001b[0m \u001b[90m║\u001b[0m\n",
"\u001b[90m║\u001b[0m \u001b[1m\u001b[33mhttps://app.hud.so/trace/7fa015b7-75b9-45df-accf-66b1d8895fe9\u001b[0m \u001b[90m║\u001b[0m\n",
"\u001b[90m╚═════════════════════════════════════════════════════════════════╝\u001b[0m\n",
"\n",
"Running: Calculate from the RawData tab the z-scores from the mean close price for each row. Return, starting in ANSWER!A1 and descending to ANSWER!A5, the 5 dates with the greatest absolute value of standard deviations from the mean\n"
@@ -86,7 +78,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2025-08-27 13:10:52,780 - agent.ComputerAgent - INFO - LLM processing started with 1 messages\n",
"2025-08-27 13:22:49,324 - agent.ComputerAgent - INFO - LLM processing started with 1 messages\n",
"Step failed: 'dict' object has no attribute 'id'\n"
]
},
@@ -96,7 +88,7 @@
"text": [
"✅ Reward: 0.0\n",
"\n",
"\u001b[92m✓ Trace complete!\u001b[0m \u001b[2mView at:\u001b[0m \u001b[1m\u001b[33mhttps://app.hud.so/trace/60b2956b-8520-4225-93d3-22ea2ff0253b\u001b[0m\n",
"\u001b[92m✓ Trace complete!\u001b[0m \u001b[2mView at:\u001b[0m \u001b[1m\u001b[33mhttps://app.hud.so/trace/7fa015b7-75b9-45df-accf-66b1d8895fe9\u001b[0m\n",
"\n"
]
}
@@ -107,8 +99,9 @@
"# Quick single-task smoke test on OSWorld-Verified-XLang\n",
"# You can swap \"hud-evals/OSWorld-Verified-XLang\" -> \"hud-evals/SheetBench-V2\" to test SheetBench.\n",
"await run_single_task(\n",
" dataset=\"hud-evals/SheetBench-50\",\n",
" dataset=\"hud-evals/OSWorld-Verified-XLang\",\n",
" model=\"openai/computer-use-preview\", # or any supported model string\n",
" task_id=155 # open last tab task (easy)\n",
")"
]
},