Downloads · 30 days
2
7% of all-time downloads
best-model-checkpoint
xce1xz21dsa/best-model-checkpoint
best-model-checkpoint is a machine learning model from xce1xz21dsa. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains the best performing model checkpoint from training step 1000, selected based on the highest overall evaluation performance.
All-time downloads
29
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 50%
At a glance
- Model type
- bert
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- 76f60f23
Model card
From the Hugging Face model README
Best Model Checkpoint (Step 1000)
This repository contains the best performing model checkpoint from training step 1000, selected based on the highest overall evaluation performance.
Evaluation Results
All benchmark scores are reported to three decimal places:
| Benchmark Category | Score |
|---|---|
| Math Reasoning | 0.550 |
| Logical Reasoning | 0.819 |
| Code Generation | 0.650 |
| Question Answering | 0.607 |
| Reading Comprehension | 0.700 |
| Common Sense | 0.736 |
| Text Classification | 0.828 |
| Sentiment Analysis | 0.792 |
| 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
The overall score is calculated using a weighted average, with higher weights assigned to reasoning and specialized capability tasks:
- 1.2x weight: Math Reasoning, Logical Reasoning
- 1.1x weight: Code Generation, Question Answering, Instruction Following, Safety Evaluation
- 1.0x weight: Reading Comprehension, Common Sense, Dialogue Generation, Summarization, Translation, Knowledge Retrieval
- 0.9x weight: Text Classification, Sentiment Analysis, Creative Writing
- Type
- bert
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026