Evaluation results for andreaparker/flan-t5-base-samsum model as a base model for other tasks
Browse filesAs part of a research effort to identify high quality models in Huggingface that can serve as base models for further finetuning, we evaluated this by finetuning on 36 datasets. The model ranks 2nd among all tested models for the google/t5-v1_1-base architecture as of 07/02/2023.
To share this information with others in your model card, please add the following evaluation results to your README.md page.
For more information please see https://ibm.github.io/model-recycling/ or contact me.
Best regards,
Elad Venezian
eladv@il.ibm.com
IBM Research AI
README.md
CHANGED
|
@@ -91,3 +91,17 @@ Our score (Rouge 1 score of 47.4798) puts this model's performance between fourt
|
|
| 91 |
|
| 92 |
|
| 93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
|
| 93 |
|
| 94 |
+
|
| 95 |
+
## Model Recycling
|
| 96 |
+
|
| 97 |
+
[Evaluation on 36 datasets](https://ibm.github.io/model-recycling/model_gain_chart?avg=9.04&mnli_lp=nan&20_newsgroup=3.55&ag_news=1.66&amazon_reviews_multi=0.19&anli=14.53&boolq=16.60&cb=24.91&cola=10.35&copa=25.50&dbpedia=5.73&esnli=5.31&financial_phrasebank=19.96&imdb=0.05&isear=0.59&mnli=11.74&mrpc=15.89&multirc=5.99&poem_sentiment=23.27&qnli=3.93&qqp=5.54&rotten_tomatoes=3.54&rte=23.90&sst2=-0.14&sst_5bins=5.12&stsb=20.58&trec_coarse=4.15&trec_fine=10.93&tweet_ev_emoji=12.87&tweet_ev_emotion=6.02&tweet_ev_hate=-0.04&tweet_ev_irony=7.12&tweet_ev_offensive=2.16&tweet_ev_sentiment=-0.00&wic=12.03&wnli=9.44&wsc=9.37&yahoo_answers=3.04&model_name=andreaparker%2Fflan-t5-base-samsum&base_name=google%2Ft5-v1_1-base) using andreaparker/flan-t5-base-samsum as a base model yields average score of 77.86 in comparison to 68.82 by google/t5-v1_1-base.
|
| 98 |
+
|
| 99 |
+
The model is ranked 2nd among all tested models for the google/t5-v1_1-base architecture as of 07/02/2023
|
| 100 |
+
Results:
|
| 101 |
+
|
| 102 |
+
| 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 |
|
| 103 |
+
|---------------:|----------:|-----------------------:|--------:|--------:|--------:|--------:|-------:|----------:|--------:|-----------------------:|-------:|--------:|--------:|--------:|----------:|-----------------:|--------:|--------:|------------------:|--------:|-------:|------------:|--------:|--------------:|------------:|-----------------:|-------------------:|----------------:|-----------------:|---------------------:|---------------------:|--------:|-------:|--------:|----------------:|
|
| 104 |
+
| 86.4312 | 89.8333 | 67.1 | 52.5937 | 82.1713 | 80.3571 | 80.5369 | 66 | 76.5 | 90.8897 | 86.7 | 93.044 | 71.6428 | 87.2457 | 88.7255 | 62.1287 | 91.3462 | 93.3004 | 89.1393 | 89.5872 | 84.4765 | 93.578 | 56.9683 | 89.3674 | 97.4 | 93 | 46.334 | 81.6327 | 51.4815 | 74.7449 | 84.7674 | 69.8795 | 67.8683 | 56.338 | 57.6923 | 72.3 |
|
| 105 |
+
|
| 106 |
+
|
| 107 |
+
For more information, see: [Model Recycling](https://ibm.github.io/model-recycling/)
|