add score

README.md

@@ -99,5 +99,21 @@ print(result[0]['summary_text'])
 
 # Results
 
-- note that while the dataset has three subsets (chapter, book, paragraph) - see the [paper](https://arxiv.org/abs/2105.08209). the scores below are run in aggregate
-- full eval results soon
+- note that while the dataset has three subsets (chapter, book, paragraph) - see the [paper](https://arxiv.org/abs/2105.08209). the scores below are run in aggregate. The paper has some benchmark scores listed, which this model competes with.
+- note that eval generations are run & computed at a length of 128 tokens.
+
+
+```
+{
+    "eval_gen_len": 126.7581,
+    "eval_loss": 3.732882499694824,
+    "eval_rouge1": 31.1471,
+    "eval_rouge2": 4.9621,
+    "eval_rougeL": 16.867,
+    "eval_rougeLsum": 28.0703,
+    "eval_runtime": 6083.71,
+    "eval_samples_per_second": 0.244,
+    "eval_steps_per_second": 0.244
+}
+
+```