RERobbins/qg_T5_triviaqa model
This model is based on google/t5-v1_1-base pretrained model.
Model Recycling
Evaluation on 36 datasets using RERobbins/qg_T5_triviaqa as a base model yields average score of 76.82 in comparison to 68.82 by google/t5-v1_1-base.
The model is ranked 3rd 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 87.6261 | 89.7333 | 67.14 | 53.1563 | 74.0979 | 82.1429 | 79.0029 | 56 | 77.6333 | 90.7471 | 86.1 | 93.8 | 72.4902 | 88.1204 | 87.0098 | 57.2814 | 87.5 | 93.3004 | 90.1187 | 90.1501 | 72.2022 | 94.2661 | 56.8778 | 87.2745 | 98 | 91.8 | 46.95 | 81.6327 | 53.367 | 76.6582 | 85.5814 | 71.0029 | 66.6144 | 49.2958 | 56.7308 | 74.0667 |
For more information, see: Model Recycling