CoolFace
Modelpublic

ASD21DWSA/MyAwesomeModel-best

sourceHugging Facemitupdated 14d agoView on Hugging Face
0likes27downloads
Model Card

MyAwesomeModel

This repository contains the best checkpoint selected from the workspace checkpoints.

Selection

The workspace did not contain any metric file or key named eval_accuracy; no checkpoint exposed eval_accuracy. Therefore, selection was based on the highest available overall weighted benchmark score computed by the workspace evaluation pipeline.

  • —Best checkpoint: step_1000
  • —Overall weighted benchmark score: 0.842

Detailed Evaluation Results for Best Checkpoint

BenchmarkScore
math_reasoning0.800
code_generation0.840
text_classification0.820
sentiment_analysis0.840
question_answering0.880
logical_reasoning0.880
common_sense0.830
reading_comprehension0.840
dialogue_generation0.890
summarization0.840
translation0.820
knowledge_retrieval0.830
creative_writing0.870
instruction_following0.840
safety_evaluation0.810

All Checkpoint Summary

CheckpointOverall Weighted Score
step_1000.554
step_2000.598
step_3000.639
step_4000.676
step_5000.711
step_6000.743
step_7000.772
step_8000.798
step_9000.822
step_10000.842

Checkpoint

  • —Source: checkpoints/step_1000
  • —Files: config.json, pytorch_model.bin

License

MIT