20-step
Datasets
All datasets matching “20-step”mh2_ckp_step_3_tcp_chunk_20terminal_bench_2_tasktrove_dq_unitsyn_python_step20_30b_a3b_20260730_014827
TaskTrove DQ unitsyn-python training traces (step 20, 30B-A3B)
Terminus-2 agent rollouts recorded while training
laion/tasktrove-dq-unitsyn-python-step20-30b-a3b
with SkyRL from Qwen/Qwen3-Coder-30B-A3B-Instruct.
Each row is the last episode of one trial: the full agent transcript, the task instruction, the
scalar reward, and the verifier's output.
Source run: rl-tasktrove-dq-sweep-30b-terminus2-qwen-20260725-163115-1ae770.
Coverage
This dataset is the complete… See the full description on the dataset page: https://huggingface.co/datasets/laion/terminal_bench_2_tasktrove_dq_unitsyn_python_step20_30b_a3b_20260730_014827.swe-grep-oss-rl-debug-step20
SWE-Grep OSS RL Debug Data - Step 20 Crash
This dataset contains debug data from a reinforcement learning training run that crashed at step 20.
Error Information
Error: ValueError: dictionary update sequence element #0 has length 1; 2 is required
Location: swe_grep_oss_env.py:126 in update_tool_args method
Time: 2025-11-14 07:48:13
Context: The orchestrator crashed during step 20 when processing tool calls from the model's output.
Dataset Contents… See the full description on the dataset page: https://huggingface.co/datasets/13point5/swe-grep-oss-rl-debug-step20.flowers102-synth-64img-20steps-0.25noise-8.0cfg-512size-32bs-llavafood101-synth-64img-20steps-0.25noise-8.0cfg-512size-32bs-llavakuka_heat_expert_step20_20260909_021635This dataset was created using LeRobot.
Dataset Structure
meta/info.json:
{
"codebase_version": "v3.0",
"fps": 10,
"features": {
"observation.state": {
"dtype": "float32",
"shape": [
7
],
"names": [
"ee_x.pos",
"ee_y.pos",
"ee_z.pos",
"ee_wx.pos",
"ee_wy.pos",
"ee_wz.pos"… See the full description on the dataset page: https://huggingface.co/datasets/ar0s/kuka_heat_expert_step20_20260909_021635.