Update README.md

README.md

@@ -47,11 +47,14 @@ The model was trained on one A100 GPU with following hyperparameters:
 |        `max_lr`        |          1e-4          |
 |        `scheduler`        |          linear          |
 |        `total_batch_size`        |          256 (~130K tokens per step)          |
+|        `num_epochs`        |          4          |
 
+More details about finetuning can be found in the technical report
 
 # Fine-tuning data
 
-For this model we used 15K exmaples of Kotlin Exercices dataset {TODO: link!}. For more information about the dataset follow th link.
+For this model we used 15K exmaples of Kotlin Exercices dataset {TODO: link!}. Every example follows HumanEval like format. In total dataset contains about 3.5M tokens. 
+For more information about the dataset follow the link.
 
 # Evaluation 
 
@@ -62,4 +65,8 @@ Fine-tuned model:
 |         **Model name**           |             **Kotlin HumanEval Pass Rate**              |             **Kotlin Completion**              |
 |:---------------------------:|:----------------------------------------:|:----------------------------------------:|
 |           `base model`            |           26.89            |           0.388            |
-|        `fine-tuned model`        |          42.24         |          0.344          |
+|        `fine-tuned model`        |          42.24         |          0.344          |
+
+# Ethical Considerations and Limitations
+
+Code Llama and its variants are a new technology that carries risks with use. The testing conducted to date could not cover all scenarios. For these reasons, as with all LLMs, Kexer's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of Kexer, developers should perform safety testing and tuning tailored to their specific applications of the model.