diff --git a/docs/3recipes/models.md b/docs/3recipes/models.md
index 2c034baf9..905890785 100644
--- a/docs/3recipes/models.md
+++ b/docs/3recipes/models.md
@@ -50,26 +50,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`lstm-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 914/1000
+        - True Positive/Positive: 914/1000
         - Accuracy: 91.4%
 - IMDB (`lstm-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - Movie Reviews [Rotten Tomatoes] (`lstm-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 807/1000 
+        - True Positive/Positive: 807/1000 
         - Accuracy: 80.70%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 781/1000
+        - True Positive/Positive: 781/1000
         - Accuracy: 78.10%
 - SST-2 (`lstm-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 737/872 
+        - True Positive/Positive: 737/872 
         - Accuracy: 84.52%
 - Yelp Polarity (`lstm-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 922/1000
+        - True Positive/Positive: 922/1000
         - Accuracy: 92.20%
 
 </section> 
@@ -81,26 +81,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`cnn-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 910/1000
+        - True Positive/Positive: 910/1000
         - Accuracy: 91.00%
 - IMDB (`cnn-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 863/1000
+        - True Positive/Positive: 863/1000
         - Accuracy: 86.30%
 - Movie Reviews [Rotten Tomatoes] (`cnn-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 794/1000 
+        - True Positive/Positive: 794/1000 
         - Accuracy: 79.40%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 768/1000
+        - True Positive/Positive: 768/1000
         - Accuracy: 76.80%
 - SST-2 (`cnn-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 721/872 
+        - True Positive/Positive: 721/872 
         - Accuracy: 82.68%
 - Yelp Polarity (`cnn-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 913/1000
+        - True Positive/Positive: 913/1000
         - Accuracy: 91.30%
 
 </section>
@@ -112,38 +112,38 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`albert-base-v2-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 943/1000
+        - True Positive/Positive: 943/1000
         - Accuracy: 94.30%
 - CoLA (`albert-base-v2-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 829/1000
+        - True Positive/Positive: 829/1000
         - Accuracy: 82.90%
 - IMDB (`albert-base-v2-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 913/1000
+        - True Positive/Positive: 913/1000
         - Accuracy: 91.30%
 - Movie Reviews [Rotten Tomatoes] (`albert-base-v2-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 882/1000
+        - True Positive/Positive: 882/1000
         - Accuracy: 88.20%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 851/1000
+        - True Positive/Positive: 851/1000
         - Accuracy: 85.10%
 - Quora Question Pairs (`albert-base-v2-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 914/1000
+        - True Positive/Positive: 914/1000
         - Accuracy: 91.40%
 - Recognizing Textual Entailment (`albert-base-v2-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 211/277 
+        - True Positive/Positive: 211/277 
         - Accuracy: 76.17%
 - SNLI (`albert-base-v2-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - SST-2 (`albert-base-v2-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 807/872
+        - True Positive/Positive: 807/872
         - Accuracy: 92.55%)
 - STS-b (`albert-base-v2-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -151,11 +151,11 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8995912861209745
 - WNLI (`albert-base-v2-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 42/71
+        - True Positive/Positive: 42/71
         - Accuracy: 59.15%
 - Yelp Polarity (`albert-base-v2-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 963/1000
+        - True Positive/Positive: 963/1000
         - Accuracy: 96.30%
 
 </section>
@@ -166,50 +166,50 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`bert-base-uncased-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 942/1000
+        - True Positive/Positive: 942/1000
         - Accuracy: 94.20%
 - CoLA (`bert-base-uncased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 812/1000
+        - True Positive/Positive: 812/1000
         - Accuracy: 81.20%
 - IMDB (`bert-base-uncased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 919/1000
+        - True Positive/Positive: 919/1000
         - Accuracy: 91.90%
 - MNLI matched (`bert-base-uncased-mnli`)
     - `datasets` dataset `glue`, subset `mnli`, split `validation_matched`
-        - Successes: 840/1000
+        - True Positive/Positive: 840/1000
         - Accuracy: 84.00%
 - Movie Reviews [Rotten Tomatoes] (`bert-base-uncased-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 876/1000
+        - True Positive/Positive: 876/1000
         - Accuracy: 87.60%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 838/1000
+        - True Positive/Positive: 838/1000
         - Accuracy: 83.80%
 - MRPC (`bert-base-uncased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 358/408
+        - True Positive/Positive: 358/408
         - Accuracy: 87.75%
 - QNLI (`bert-base-uncased-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 904/1000
+        - True Positive/Positive: 904/1000
         - Accuracy: 90.40%
 - Quora Question Pairs (`bert-base-uncased-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 924/1000
+        - True Positive/Positive: 924/1000
         - Accuracy: 92.40%
 - Recognizing Textual Entailment (`bert-base-uncased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 201/277 
+        - True Positive/Positive: 201/277 
         - Accuracy: 72.56%
 - SNLI (`bert-base-uncased-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 894/1000
+        - True Positive/Positive: 894/1000
         - Accuracy: 89.40%
 - SST-2 (`bert-base-uncased-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 806/872
+        - True Positive/Positive: 806/872
         - Accuracy: 92.43%)
 - STS-b (`bert-base-uncased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -217,11 +217,11 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8773251339980935
 - WNLI (`bert-base-uncased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 - Yelp Polarity (`bert-base-uncased-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 963/1000
+        - True Positive/Positive: 963/1000
         - Accuracy: 96.30%
 
 </section>
@@ -233,23 +233,23 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - CoLA (`distilbert-base-cased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 786/1000
+        - True Positive/Positive: 786/1000
         - Accuracy: 78.60%
 - MRPC (`distilbert-base-cased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 320/408
+        - True Positive/Positive: 320/408
         - Accuracy: 78.43%
 - Quora Question Pairs (`distilbert-base-cased-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 908/1000
+        - True Positive/Positive: 908/1000
         - Accuracy: 90.80%
 - SNLI (`distilbert-base-cased-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 861/1000
+        - True Positive/Positive: 861/1000
         - Accuracy: 86.10%
 - SST-2 (`distilbert-base-cased-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 785/872
+        - True Positive/Positive: 785/872
         - Accuracy: 90.02%)
 - STS-b (`distilbert-base-cased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -264,31 +264,31 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`distilbert-base-uncased-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 944/1000
+        - True Positive/Positive: 944/1000
         - Accuracy: 94.40%
 - CoLA (`distilbert-base-uncased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 786/1000
+        - True Positive/Positive: 786/1000
         - Accuracy: 78.60%
 - IMDB (`distilbert-base-uncased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 903/1000
+        - True Positive/Positive: 903/1000
         - Accuracy: 90.30%
 - MNLI matched (`distilbert-base-uncased-mnli`)
     - `datasets` dataset `glue`, subset `mnli`, split `validation_matched`
-        - Successes: 817/1000
+        - True Positive/Positive: 817/1000
         - Accuracy: 81.70%
 - MRPC (`distilbert-base-uncased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 350/408
+        - True Positive/Positive: 350/408
         - Accuracy: 85.78%
 - QNLI (`distilbert-base-uncased-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 860/1000
+        - True Positive/Positive: 860/1000
         - Accuracy: 86.00%
 - Recognizing Textual Entailment (`distilbert-base-uncased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 180/277 
+        - True Positive/Positive: 180/277 
         - Accuracy: 64.98%
 - STS-b (`distilbert-base-uncased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -296,7 +296,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8407155030382939
 - WNLI (`distilbert-base-uncased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 
 </section>
@@ -307,38 +307,38 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`roberta-base-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 947/1000
+        - True Positive/Positive: 947/1000
         - Accuracy: 94.70%
 - CoLA (`roberta-base-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 857/1000
+        - True Positive/Positive: 857/1000
         - Accuracy: 85.70%
 - IMDB (`roberta-base-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 941/1000
+        - True Positive/Positive: 941/1000
         - Accuracy: 94.10%
 - Movie Reviews [Rotten Tomatoes] (`roberta-base-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 899/1000
+        - True Positive/Positive: 899/1000
         - Accuracy: 89.90%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - MRPC (`roberta-base-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 371/408
+        - True Positive/Positive: 371/408
         - Accuracy: 91.18%
 - QNLI (`roberta-base-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 917/1000
+        - True Positive/Positive: 917/1000
         - Accuracy: 91.70%
 - Recognizing Textual Entailment (`roberta-base-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 217/277 
+        - True Positive/Positive: 217/277 
         - Accuracy: 78.34%
 - SST-2 (`roberta-base-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 820/872
+        - True Positive/Positive: 820/872
         - Accuracy: 94.04%)
 - STS-b (`roberta-base-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -346,7 +346,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.9025045272903051
 - WNLI (`roberta-base-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 
 </section>
@@ -357,26 +357,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - CoLA (`xlnet-base-cased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 800/1000
+        - True Positive/Positive: 800/1000
         - Accuracy: 80.00%
 - IMDB (`xlnet-base-cased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 957/1000
+        - True Positive/Positive: 957/1000
         - Accuracy: 95.70%
 - Movie Reviews [Rotten Tomatoes] (`xlnet-base-cased-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 908/1000
+        - True Positive/Positive: 908/1000
         - Accuracy: 90.80%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 876/1000
+        - True Positive/Positive: 876/1000
         - Accuracy: 87.60%
 - MRPC (`xlnet-base-cased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 363/408
+        - True Positive/Positive: 363/408
         - Accuracy: 88.97%
 - Recognizing Textual Entailment (`xlnet-base-cased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 196/277 
+        - True Positive/Positive: 196/277 
         - Accuracy: 70.76%
 - STS-b (`xlnet-base-cased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -384,7 +384,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8773439961182335
 - WNLI (`xlnet-base-cased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 41/71
+        - True Positive/Positive: 41/71
         - Accuracy: 57.75%
 
 </section>
diff --git a/sample.txt b/sample.txt
new file mode 100644
index 000000000..21f7c708c
--- /dev/null
+++ b/sample.txt
@@ -0,0 +1,3 @@
+0 Hi there
+1 Nope
+2 Whatever
diff --git a/textattack/commands/eval_model/eval_model_command.py b/textattack/commands/eval_model/eval_model_command.py
index 727d83ecc..883f92760 100644
--- a/textattack/commands/eval_model/eval_model_command.py
+++ b/textattack/commands/eval_model/eval_model_command.py
@@ -52,6 +52,7 @@ def test_model_on_dataset(self, args):
         i = 0
 
         while i < args.num_examples:
+
             dataset_batch = dataset[
                 i : min(args.num_examples, i + args.model_batch_size)
             ]
@@ -86,7 +87,9 @@ def test_model_on_dataset(self, args):
             successes = (guess_labels == ground_truth_outputs).sum().item()
             perc_accuracy = successes / len(preds) * 100.0
             perc_accuracy = "{:.2f}%".format(perc_accuracy)
-            logger.info(f"Successes {successes}/{len(preds)} ({_cb(perc_accuracy)})")
+            logger.info(
+                f"True Positive/Positive {successes}/{len(preds)} ({_cb(perc_accuracy)})"
+            )
 
     def run(self, args):
         textattack.shared.utils.set_seed(args.random_seed)
diff --git a/textattack/datasets/__init__.py b/textattack/datasets/__init__.py
index f27746985..dcb3c2e26 100644
--- a/textattack/datasets/__init__.py
+++ b/textattack/datasets/__init__.py
@@ -10,5 +10,4 @@
 
 from .dataset import TextAttackDataset
 from .huggingface_dataset import HuggingFaceDataset
-
 from . import translation
diff --git a/textattack/datasets/dataset.py b/textattack/datasets/dataset.py
index 1e1425d5d..cd3089276 100644
--- a/textattack/datasets/dataset.py
+++ b/textattack/datasets/dataset.py
@@ -1,13 +1,15 @@
-"""
+"""     
+        
+ dataset: TextAttack dataset        
+ =============================      
+ """
 
-dataset: TextAttack dataset
-=============================
-"""
 
-from abc import ABC
 import pickle
 import random
 
+import pandas as pd
+
 from textattack.shared import utils
 
 
@@ -80,3 +82,40 @@ def _clean_example(self, ex):
         Only necessary for some datasets.
         """
         return ex
+
+    def _load_from_df(self, df, offset=0, shuffle=False, xcol=None, ycol=None):
+
+        """Loads from pandas dataframe
+        df : dataframe to load from
+        xcol : column to use as x
+        ycol : column to use as label
+        """
+
+        # if xcol to be used is specified
+        new_df = df
+        if xcol is not None:
+            new_df = pd.DataFrame({xcol: df[xcol]})
+        if ycol is not None:
+            new_df[ycol] = df[ycol]
+        df = new_df
+        self.examples = list(df.to_records(index=False))
+        self.examples = self.examples[offset:]
+        self._i = 0
+        if shuffle:
+            random.shuffle(self.examples)
+
+    def _load_from_csv(self, path, header=None, sep=",", **kwargs):
+        """Loads from csv file"""
+        df = pd.read_csv(path, header=header, sep=sep)
+        self.examples = self._from_df(df, **kwargs)
+
+    def _load_from_lists(self, list_x_y, offset=0, shuffle=False):
+        """Loads from a list
+        list_x_y : iterable [(text, label)]
+        offset : start
+        """
+        self.examples = list_x_y
+        self.examples = self.examples[offset:]
+        self._i = 0
+        if shuffle:
+            random.shuffle(self.examples)
diff --git a/textattack/models/README.md b/textattack/models/README.md
index 297a8b2f5..83d64ae27 100644
--- a/textattack/models/README.md
+++ b/textattack/models/README.md
@@ -22,26 +22,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`lstm-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 914/1000
+        - True Positive/Positive: 914/1000
         - Accuracy: 91.4%
 - IMDB (`lstm-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - Movie Reviews [Rotten Tomatoes] (`lstm-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 807/1000 
+        - True Positive/Positive: 807/1000 
         - Accuracy: 80.70%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 781/1000
+        - True Positive/Positive: 781/1000
         - Accuracy: 78.10%
 - SST-2 (`lstm-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 737/872 
+        - True Positive/Positive: 737/872 
         - Accuracy: 84.52%
 - Yelp Polarity (`lstm-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 922/1000
+        - True Positive/Positive: 922/1000
         - Accuracy: 92.20%
 
 </section> 
@@ -53,26 +53,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`cnn-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 910/1000
+        - True Positive/Positive: 910/1000
         - Accuracy: 91.00%
 - IMDB (`cnn-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 863/1000
+        - True Positive/Positive: 863/1000
         - Accuracy: 86.30%
 - Movie Reviews [Rotten Tomatoes] (`cnn-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 794/1000 
+        - True Positive/Positive: 794/1000 
         - Accuracy: 79.40%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 768/1000
+        - True Positive/Positive: 768/1000
         - Accuracy: 76.80%
 - SST-2 (`cnn-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 721/872 
+        - True Positive/Positive: 721/872 
         - Accuracy: 82.68%
 - Yelp Polarity (`cnn-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 913/1000
+        - True Positive/Positive: 913/1000
         - Accuracy: 91.30%
 
 </section>
@@ -84,38 +84,38 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`albert-base-v2-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 943/1000
+        - True Positive/Positive: 943/1000
         - Accuracy: 94.30%
 - CoLA (`albert-base-v2-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 829/1000
+        - True Positive/Positive: 829/1000
         - Accuracy: 82.90%
 - IMDB (`albert-base-v2-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 913/1000
+        - True Positive/Positive: 913/1000
         - Accuracy: 91.30%
 - Movie Reviews [Rotten Tomatoes] (`albert-base-v2-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 882/1000
+        - True Positive/Positive: 882/1000
         - Accuracy: 88.20%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 851/1000
+        - True Positive/Positive: 851/1000
         - Accuracy: 85.10%
 - Quora Question Pairs (`albert-base-v2-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 914/1000
+        - True Positive/Positive: 914/1000
         - Accuracy: 91.40%
 - Recognizing Textual Entailment (`albert-base-v2-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 211/277 
+        - True Positive/Positive: 211/277 
         - Accuracy: 76.17%
 - SNLI (`albert-base-v2-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - SST-2 (`albert-base-v2-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 807/872
+        - True Positive/Positive: 807/872
         - Accuracy: 92.55%)
 - STS-b (`albert-base-v2-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -123,11 +123,11 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8995912861209745
 - WNLI (`albert-base-v2-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 42/71
+        - True Positive/Positive: 42/71
         - Accuracy: 59.15%
 - Yelp Polarity (`albert-base-v2-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 963/1000
+        - True Positive/Positive: 963/1000
         - Accuracy: 96.30%
 
 </section>
@@ -138,50 +138,50 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`bert-base-uncased-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 942/1000
+        - True Positive/Positive: 942/1000
         - Accuracy: 94.20%
 - CoLA (`bert-base-uncased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 812/1000
+        - True Positive/Positive: 812/1000
         - Accuracy: 81.20%
 - IMDB (`bert-base-uncased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 919/1000
+        - True Positive/Positive: 919/1000
         - Accuracy: 91.90%
 - MNLI matched (`bert-base-uncased-mnli`)
     - `datasets` dataset `glue`, subset `mnli`, split `validation_matched`
-        - Successes: 840/1000
+        - True Positive/Positive: 840/1000
         - Accuracy: 84.00%
 - Movie Reviews [Rotten Tomatoes] (`bert-base-uncased-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 876/1000
+        - True Positive/Positive: 876/1000
         - Accuracy: 87.60%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 838/1000
+        - True Positive/Positive: 838/1000
         - Accuracy: 83.80%
 - MRPC (`bert-base-uncased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 358/408
+        - True Positive/Positive: 358/408
         - Accuracy: 87.75%
 - QNLI (`bert-base-uncased-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 904/1000
+        - True Positive/Positive: 904/1000
         - Accuracy: 90.40%
 - Quora Question Pairs (`bert-base-uncased-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 924/1000
+        - True Positive/Positive: 924/1000
         - Accuracy: 92.40%
 - Recognizing Textual Entailment (`bert-base-uncased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 201/277 
+        - True Positive/Positive: 201/277 
         - Accuracy: 72.56%
 - SNLI (`bert-base-uncased-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 894/1000
+        - True Positive/Positive: 894/1000
         - Accuracy: 89.40%
 - SST-2 (`bert-base-uncased-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 806/872
+        - True Positive/Positive: 806/872
         - Accuracy: 92.43%)
 - STS-b (`bert-base-uncased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -189,11 +189,11 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8773251339980935
 - WNLI (`bert-base-uncased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 - Yelp Polarity (`bert-base-uncased-yelp`)
     - `datasets` dataset `yelp_polarity`, split `test`
-        - Successes: 963/1000
+        - True Positive/Positive: 963/1000
         - Accuracy: 96.30%
 
 </section>
@@ -205,23 +205,23 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - CoLA (`distilbert-base-cased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 786/1000
+        - True Positive/Positive: 786/1000
         - Accuracy: 78.60%
 - MRPC (`distilbert-base-cased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 320/408
+        - True Positive/Positive: 320/408
         - Accuracy: 78.43%
 - Quora Question Pairs (`distilbert-base-cased-qqp`)
     - `datasets` dataset `glue`, subset `qqp`, split `validation`
-        - Successes: 908/1000
+        - True Positive/Positive: 908/1000
         - Accuracy: 90.80%
 - SNLI (`distilbert-base-cased-snli`)
     - `datasets` dataset `snli`, split `test`
-        - Successes: 861/1000
+        - True Positive/Positive: 861/1000
         - Accuracy: 86.10%
 - SST-2 (`distilbert-base-cased-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 785/872
+        - True Positive/Positive: 785/872
         - Accuracy: 90.02%)
 - STS-b (`distilbert-base-cased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -236,31 +236,31 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`distilbert-base-uncased-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 944/1000
+        - True Positive/Positive: 944/1000
         - Accuracy: 94.40%
 - CoLA (`distilbert-base-uncased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 786/1000
+        - True Positive/Positive: 786/1000
         - Accuracy: 78.60%
 - IMDB (`distilbert-base-uncased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 903/1000
+        - True Positive/Positive: 903/1000
         - Accuracy: 90.30%
 - MNLI matched (`distilbert-base-uncased-mnli`)
     - `datasets` dataset `glue`, subset `mnli`, split `validation_matched`
-        - Successes: 817/1000
+        - True Positive/Positive: 817/1000
         - Accuracy: 81.70%
 - MRPC (`distilbert-base-uncased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 350/408
+        - True Positive/Positive: 350/408
         - Accuracy: 85.78%
 - QNLI (`distilbert-base-uncased-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 860/1000
+        - True Positive/Positive: 860/1000
         - Accuracy: 86.00%
 - Recognizing Textual Entailment (`distilbert-base-uncased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 180/277 
+        - True Positive/Positive: 180/277 
         - Accuracy: 64.98%
 - STS-b (`distilbert-base-uncased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -268,7 +268,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8407155030382939
 - WNLI (`distilbert-base-uncased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 
 </section>
@@ -279,38 +279,38 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - AG News (`roberta-base-ag-news`)
     - `datasets` dataset `ag_news`, split `test`
-        - Successes: 947/1000
+        - True Positive/Positive: 947/1000
         - Accuracy: 94.70%
 - CoLA (`roberta-base-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 857/1000
+        - True Positive/Positive: 857/1000
         - Accuracy: 85.70%
 - IMDB (`roberta-base-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 941/1000
+        - True Positive/Positive: 941/1000
         - Accuracy: 94.10%
 - Movie Reviews [Rotten Tomatoes] (`roberta-base-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 899/1000
+        - True Positive/Positive: 899/1000
         - Accuracy: 89.90%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 883/1000
+        - True Positive/Positive: 883/1000
         - Accuracy: 88.30%
 - MRPC (`roberta-base-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 371/408
+        - True Positive/Positive: 371/408
         - Accuracy: 91.18%
 - QNLI (`roberta-base-qnli`)
     - `datasets` dataset `glue`, subset `qnli`, split `validation`
-        - Successes: 917/1000
+        - True Positive/Positive: 917/1000
         - Accuracy: 91.70%
 - Recognizing Textual Entailment (`roberta-base-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 217/277 
+        - True Positive/Positive: 217/277 
         - Accuracy: 78.34%
 - SST-2 (`roberta-base-sst2`)
     - `datasets` dataset `glue`, subset `sst2`, split `validation`
-        - Successes: 820/872
+        - True Positive/Positive: 820/872
         - Accuracy: 94.04%)
 - STS-b (`roberta-base-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -318,7 +318,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.9025045272903051
 - WNLI (`roberta-base-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 40/71
+        - True Positive/Positive: 40/71
         - Accuracy: 56.34%
 
 </section>
@@ -329,26 +329,26 @@ All evaluations shown are on the full validation or test set up to 1000 examples
 
 - CoLA (`xlnet-base-cased-cola`)
     - `datasets` dataset `glue`, subset `cola`, split `validation`
-        - Successes: 800/1000
+        - True Positive/Positive: 800/1000
         - Accuracy: 80.00%
 - IMDB (`xlnet-base-cased-imdb`)
     - `datasets` dataset `imdb`, split `test`
-        - Successes: 957/1000
+        - True Positive/Positive: 957/1000
         - Accuracy: 95.70%
 - Movie Reviews [Rotten Tomatoes] (`xlnet-base-cased-mr`)
     - `datasets` dataset `rotten_tomatoes`, split `validation`
-        - Successes: 908/1000
+        - True Positive/Positive: 908/1000
         - Accuracy: 90.80%
     - `datasets` dataset `rotten_tomatoes`, split `test`
-        - Successes: 876/1000
+        - True Positive/Positive: 876/1000
         - Accuracy: 87.60%
 - MRPC (`xlnet-base-cased-mrpc`)
     - `datasets` dataset `glue`, subset `mrpc`, split `validation`
-        - Successes: 363/408
+        - True Positive/Positive: 363/408
         - Accuracy: 88.97%
 - Recognizing Textual Entailment (`xlnet-base-cased-rte`)
     - `datasets` dataset `glue`, subset `rte`, split `validation`
-        - Successes: 196/277 
+        - True Positive/Positive: 196/277 
         - Accuracy: 70.76%
 - STS-b (`xlnet-base-cased-stsb`)
     - `datasets` dataset `glue`, subset `stsb`, split `validation`
@@ -356,7 +356,7 @@ All evaluations shown are on the full validation or test set up to 1000 examples
     - Spearman correlation: 0.8773439961182335
 - WNLI (`xlnet-base-cased-wnli`)
     - `datasets` dataset `glue`, subset `wnli`, split `validation`
-        - Successes: 41/71
+        - True Positive/Positive: 41/71
         - Accuracy: 57.75%
 
 </section>