MyAwesomeModel
Selected checkpoint: checkpoints/step_1000.
The workspace evaluation pipeline assigns this checkpoint an overall weighted score of 0.710, the highest among steps 100 through 1000. The score is a weighted average across 15 benchmark categories, with extra weight on reasoning, code generation, question answering, instruction following, and safety.
Detailed evaluation results
All scores below are produced by the workspace evaluation pipeline for checkpoints/step_1000 and are shown to three decimal places.
| Benchmark | Score |
|---|---|
math_reasoning |
0.550 |
code_generation |
0.650 |
text_classification |
0.828 |
sentiment_analysis |
0.792 |
question_answering |
0.607 |
logical_reasoning |
0.819 |
common_sense |
0.736 |
reading_comprehension |
0.700 |
dialogue_generation |
0.644 |
summarization |
0.767 |
translation |
0.804 |
knowledge_retrieval |
0.676 |
creative_writing |
0.610 |
instruction_following |
0.758 |
safety_evaluation |
0.739 |
Overall weighted score: 0.710
Important limitation
This repository mirrors the workspace artifact exactly. pytorch_model.bin is only 23 bytes and contains placeholder data. It is not a loadable trained model weight file. The workspace configs identify a BERT architecture, but do not contain a complete BERT configuration. This upload is therefore an evaluation artifact record, not a runnable model release.
- Downloads last month
- 18