Evaluation results for jmassot/bert-base-uncased-issues-128 model as a base model for other tasks
#1
by
eladven
- opened
README.md
CHANGED
|
@@ -69,3 +69,17 @@ The following hyperparameters were used during training:
|
|
| 69 |
- Pytorch 1.11.0+cu113
|
| 70 |
- Datasets 1.16.1
|
| 71 |
- Tokenizers 0.10.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
- Pytorch 1.11.0+cu113
|
| 70 |
- Datasets 1.16.1
|
| 71 |
- Tokenizers 0.10.1
|
| 72 |
+
|
| 73 |
+
## Model Recycling
|
| 74 |
+
|
| 75 |
+
[Evaluation on 36 datasets](https://ibm.github.io/model-recycling/model_gain_chart?avg=1.50&mnli_lp=nan&20_newsgroup=1.15&ag_news=0.14&amazon_reviews_multi=-0.06&anli=0.80&boolq=2.51&cb=7.05&cola=0.82&copa=9.55&dbpedia=0.44&esnli=0.64&financial_phrasebank=10.97&imdb=-0.14&isear=-0.04&mnli=-0.16&mrpc=1.35&multirc=1.23&poem_sentiment=0.63&qnli=0.53&qqp=-0.54&rotten_tomatoes=0.42&rte=4.64&sst2=0.00&sst_5bins=0.01&stsb=0.57&trec_coarse=0.54&trec_fine=8.67&tweet_ev_emoji=0.40&tweet_ev_emotion=0.45&tweet_ev_hate=0.18&tweet_ev_irony=-0.80&tweet_ev_offensive=-0.25&tweet_ev_sentiment=0.54&wic=-0.87&wnli=1.55&wsc=1.35&yahoo_answers=-0.32&model_name=jmassot%2Fbert-base-uncased-issues-128&base_name=bert-base-uncased) using jmassot/bert-base-uncased-issues-128 as a base model yields average score of 73.70 in comparison to 72.20 by bert-base-uncased.
|
| 76 |
+
|
| 77 |
+
The model is ranked 3rd among all tested models for the bert-base-uncased architecture as of 21/12/2022
|
| 78 |
+
Results:
|
| 79 |
+
|
| 80 |
+
| 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 |
+
|---------------:|----------:|-----------------------:|-------:|--------:|--------:|--------:|-------:|----------:|--------:|-----------------------:|-------:|--------:|--------:|--------:|----------:|-----------------:|--------:|--------:|------------------:|--------:|--------:|------------:|--------:|--------------:|------------:|-----------------:|-------------------:|----------------:|-----------------:|---------------------:|---------------------:|--------:|--------:|--------:|----------------:|
|
| 82 |
+
| 84.2007 | 89.7333 | 65.86 | 47.75 | 71.4679 | 71.4286 | 82.6462 | 59 | 78.6 | 90.34 | 79.5 | 91.432 | 69.0352 | 83.5639 | 83.3333 | 61.2005 | 67.3077 | 90.4082 | 89.7353 | 85.272 | 64.6209 | 91.9725 | 52.8054 | 86.4351 | 96.6 | 77 | 36.41 | 80.3659 | 53.0303 | 66.9643 | 85.1163 | 70.0179 | 62.3824 | 52.1127 | 63.4615 | 72 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
For more information, see: [Model Recycling](https://ibm.github.io/model-recycling/)
|