RERobbins/qg_T5_nq model
This model is based on google/t5-v1_1-base pretrained model.
Model Recycling
Evaluation on 36 datasets using RERobbins/qg_T5_nq as a base model yields average score of 77.20 in comparison to 68.82 by google/t5-v1_1-base.
The model is ranked 2nd among all tested models for the google/t5-v1_1-base architecture as of 18/01/2023 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 87.0685 | 89.7 | 66.78 | 51.125 | 77.9205 | 85.7143 | 79.5781 | 49 | 77.4 | 90.8897 | 87.4 | 93.788 | 73.6636 | 87.3881 | 87.7451 | 61.5099 | 84.6154 | 93.0441 | 88.2958 | 89.6811 | 75.4513 | 94.2661 | 56.6063 | 87.3921 | 98 | 92 | 47.02 | 82.1956 | 53.6027 | 77.2959 | 84.6512 | 71.4425 | 69.4357 | 53.5211 | 60.5769 | 73.3667 |
For more information, see: Model Recycling