Update README.md

README.md

@@ -25,10 +25,27 @@ More information needed
 
 ## Training and evaluation data
 
-More information needed
+Instruction Tuned on the ropes task here: https://huggingface.co/datasets/adambjorn/UnrelatedForgettingOverhead/viewer/ropes
 
 ## Training procedure
 
+Given a set of prompts:
+
+``` python
+prompts = [
+        "Given the following background and situation, answer the question: ",
+        "Based on the background information and the current situation, what is the answer to the question? ",
+        "Considering the background and the described situation, provide an answer to this question: ",
+    ]
+```
+
+Each example is concatenated with the prompt, background, situation, question and answer:
+
+``` python
+input_text = f"{prompt}Background: {background} Situation: {situation} Question: {question} Answer: {answer_text}."
+```
+
+
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -45,7 +62,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+Final results: {'loss': 0.024, 'grad_norm': 1.3331243991851807, 'learning_rate': 8.000000000000001e-07, 'epoch': 10.0}
 
+Average results: {'train_runtime': 862.219, 'train_samples_per_second': 2.32, 'train_steps_per_second': 0.58, 'train_loss': 0.4160269268453121, 'epoch': 10.0}
 
 ### Framework versions