Dataset Card for Evaluation run of TheBloke/VicUnlocked-30B-LoRA-HF

Dataset Description

Dataset Overview

The dataset was automatically created during the evaluation run of the model TheBloke/VicUnlocked-30B-LoRA-HF on the Open LLM Leaderboard.

It contains three configurations, each corresponding to an evaluation task.

The dataset was created from two runs. In each run, the results are stored as a specific split within each configuration, with the split name using the run timestamp. The "train" split always points to the latest results.

An additional configuration "results" stores the aggregated results of all runs (and is used to compute and display aggregate metrics on the Open LLM Leaderboard).

Example of loading run details: python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_TheBloke__VicUnlocked-30B-LoRA-HF", "harness_winogrande_5", split="train")

Latest Results

The following are the latest results from the run on 2023-10-23T04:52:45.302158: python { "all": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460696, "f1": 0.0645071308724832, "f1_stderr": 0.0013899526153663272, "acc": 0.46941968306093984, "acc_stderr": 0.01051121334026367 }, "harness|drop|3": { "em": 0.001363255033557047, "em_stderr": 0.0003778609196460696, "f1": 0.0645071308724832, "f1_stderr": 0.0013899526153663272 }, "harness|gsm8k|5": { "acc": 0.14404852160727824, "acc_stderr": 0.009672110973065282 }, "harness|winogrande|5": { "acc": 0.7947908445146015, "acc_stderr": 0.011350315707462056 } }