jfarmerphd/bert-finetuned-squad-accelerate model
This model is based on bert-base-cased pretrained model.
Model Recycling
Evaluation on 36 datasets using jfarmerphd/bert-finetuned-squad-accelerate as a base model yields average score of 74.05 in comparison to 72.43 by bert-base-cased.
The model is ranked 3rd among all tested models for the bert-base-cased architecture as of 09/01/2023 Results:
| 20_newsgroup | ag_news | amazon_reviews_multi | anli | boolq | cb | cola | copa | dbpedia | esnli | financial_phrasebank | imdb | isear | mnli | mrpc | multirc | poem_sentiment | qnli | qqp | rotten_tomatoes | rte | sst2 | sst_5bins | stsb | trec_coarse | trec_fine | tweet_ev_emoji | tweet_ev_emotion | tweet_ev_hate | tweet_ev_irony | tweet_ev_offensive | tweet_ev_sentiment | wic | wnli | wsc | yahoo_answers |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 81.094 | 88.7333 | 65.84 | 47.4062 | 71.4373 | 71.4286 | 81.5916 | 50 | 77.6333 | 89.5053 | 82.6 | 91.012 | 69.4263 | 83.0553 | 88.2353 | 60.5817 | 73.0769 | 90.9757 | 89.8541 | 84.8968 | 69.3141 | 91.8578 | 51.448 | 85.562 | 97 | 80.4 | 44.018 | 77.7621 | 53.4007 | 67.8571 | 85.2326 | 68.4956 | 65.3605 | 56.338 | 63.4615 | 69.8333 |
For more information, see: Model Recycling