Update README.md

README.md

@@ -238,13 +238,14 @@ You can also load other tasks (see next paragraph) or further fine-tune the enco
 import tasknet as tn
 pipe = tn.load_pipeline('sileod/deberta-v3-base-tasksource-nli','glue/sst2') # works for 500+ tasksource tasks
 pipe(['That movie was great !', 'Awful movie.'])
-
-# [{'label': 'positive', 'score': 0.9956129789352417}, {'label': 'negative', 'score': 0.9967049956321716}]
+# [{'label': 'positive', 'score': 0.9956}, {'label': 'negative', 'score': 0.9967}]
 ```
 
+The list of tasks is available in model config.json.
+
 
 ## Evaluation
-This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to IBM model recycling evaluation.
+This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
 Results:
 [Evaluation on 36 datasets](https://ibm.github.io/model-recycling/model_gain_chart?avg=1.41&mnli_lp=nan&20_newsgroup=0.63&ag_news=0.46&amazon_reviews_multi=-0.40&anli=0.94&boolq=2.55&cb=10.71&cola=0.49&copa=10.60&dbpedia=0.10&esnli=-0.25&financial_phrasebank=1.31&imdb=-0.17&isear=0.63&mnli=0.42&mrpc=-0.23&multirc=1.73&poem_sentiment=0.77&qnli=0.12&qqp=-0.05&rotten_tomatoes=0.67&rte=2.13&sst2=0.01&sst_5bins=-0.02&stsb=1.39&trec_coarse=0.24&trec_fine=0.18&tweet_ev_emoji=0.62&tweet_ev_emotion=0.43&tweet_ev_hate=1.84&tweet_ev_irony=1.43&tweet_ev_offensive=0.17&tweet_ev_sentiment=0.08&wic=-1.78&wnli=3.03&wsc=9.95&yahoo_answers=0.17&model_name=sileod%2Fdeberta-v3-base_tasksource-420&base_name=microsoft%2Fdeberta-v3-base) using sileod/deberta-v3-base_tasksource-420 as a base model yields average score of 80.45 in comparison to 79.04 by microsoft/deberta-v3-base.
 
@@ -254,20 +255,18 @@ Results:
 |---------------:|----------:|-----------------------:|--------:|--------:|--------:|--------:|-------:|----------:|--------:|-----------------------:|-------:|--------:|--------:|--------:|----------:|-----------------:|--------:|--------:|------------------:|--------:|--------:|------------:|--------:|--------------:|------------:|-----------------:|-------------------:|----------------:|-----------------:|---------------------:|---------------------:|--------:|--------:|--------:|----------------:|
 |         87.042 |      90.9 |                  66.46 | 59.7188 | 85.5352 | 85.7143 | 87.0566 |     69 |   79.5333 | 91.6735 |                   85.8 | 94.324 | 72.4902 | 90.2055 | 88.9706 |   63.9851 |             87.5 | 93.6299 | 91.7363 |           91.0882 | 84.4765 | 95.0688 |     56.9683 | 91.6654 |            98 |        91.2 |           46.814 |            84.3772 |         58.0471 |            81.25 |              85.2326 |              71.8821 | 69.4357 | 73.2394 | 74.0385 |            72.2 |
 
-
 For more information, see: [Model Recycling](https://ibm.github.io/model-recycling/)
 
 ### Software and training details
 https://github.com/sileod/tasksource/ \
 https://github.com/sileod/tasknet/ \
-Training took 7 days on RTX6000 24GB gpu.
 Training code: https://colab.research.google.com/drive/1iB4Oxl9_B5W3ZDzXoWJN-olUbqLBxgQS?usp=sharing
+Training took 7 days on RTX6000 24GB gpu.
 
 This is the shared model with the MNLI classifier on top. Its encoder was trained on many datasets including bigbench, Anthropic rlhf, anli... alongside many NLI and classification tasks with one shared encoder.
 Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched.
 The number of examples per task was capped to 64k. The model was trained for 45k steps with a batch size of 384, and a peak learning rate of 2e-5.
 
-The list of tasks is available in model config.
 
 # Citation