Evaluation results for mariolinml/deberta-v3-base_MNLI_10_19_v0 model as a base model for other tasks
#1
by
eladven
- opened
README.md
CHANGED
|
@@ -50,3 +50,17 @@ The following hyperparameters were used during training:
|
|
| 50 |
- Pytorch 1.12.1+cu113
|
| 51 |
- Datasets 2.6.1
|
| 52 |
- Tokenizers 0.13.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
- Pytorch 1.12.1+cu113
|
| 51 |
- Datasets 2.6.1
|
| 52 |
- Tokenizers 0.13.1
|
| 53 |
+
|
| 54 |
+
## Model Recycling
|
| 55 |
+
|
| 56 |
+
[Evaluation on 36 datasets](https://ibm.github.io/model-recycling/model_gain_chart?avg=0.71&mnli_lp=nan&20_newsgroup=-0.57&ag_news=-0.21&amazon_reviews_multi=-0.12&anli=1.28&boolq=-1.15&cb=7.14&cola=-1.72&copa=10.60&dbpedia=0.00&esnli=-0.81&financial_phrasebank=2.42&imdb=-0.12&isear=-0.48&mnli=-0.06&mrpc=-0.97&multirc=2.12&poem_sentiment=1.73&qnli=0.25&qqp=0.08&rotten_tomatoes=-0.65&rte=3.21&sst2=0.12&sst_5bins=0.48&stsb=1.46&trec_coarse=-0.16&trec_fine=0.78&tweet_ev_emoji=-0.67&tweet_ev_emotion=0.29&tweet_ev_hate=-0.22&tweet_ev_irony=0.03&tweet_ev_offensive=-0.76&tweet_ev_sentiment=-0.54&wic=-1.15&wnli=4.44&wsc=-0.63&yahoo_answers=0.10&model_name=mariolinml%2Fdeberta-v3-base_MNLI_10_19_v0&base_name=microsoft%2Fdeberta-v3-base) using mariolinml/deberta-v3-base_MNLI_10_19_v0 as a base model yields average score of 79.75 in comparison to 79.04 by microsoft/deberta-v3-base.
|
| 57 |
+
|
| 58 |
+
The model is ranked 3rd among all tested models for the microsoft/deberta-v3-base architecture as of 22/01/2023
|
| 59 |
+
Results:
|
| 60 |
+
|
| 61 |
+
| 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 |
|
| 62 |
+
|---------------:|----------:|-----------------------:|--------:|--------:|--------:|--------:|-------:|----------:|--------:|-----------------------:|-------:|--------:|--------:|--------:|----------:|-----------------:|-------:|--------:|------------------:|--------:|--------:|------------:|--------:|--------------:|------------:|-----------------:|-------------------:|----------------:|-----------------:|---------------------:|---------------------:|--------:|--------:|--------:|----------------:|
|
| 63 |
+
| 85.8471 | 90.2333 | 66.74 | 60.0625 | 81.8349 | 82.1429 | 84.8514 | 69 | 79.4333 | 91.1136 | 86.9 | 94.372 | 71.382 | 89.7172 | 88.2353 | 64.3771 | 88.4615 | 93.758 | 91.8699 | 89.7749 | 85.5596 | 95.1835 | 57.4661 | 91.7396 | 97.6 | 91.8 | 45.526 | 84.2365 | 55.9933 | 79.8469 | 84.3023 | 71.2634 | 70.0627 | 74.6479 | 63.4615 | 72.1333 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
For more information, see: [Model Recycling](https://ibm.github.io/model-recycling/)
|