Update README.md

README.md

@@ -1,16 +1,16 @@
 ---
 license: other
-library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
-datasets:
-- generator
 model-index:
 - name: Llama3-stanford-encyclopedia-philosophy-QA
   results: []
+language:
+- en
+pipeline_tag: text-generation
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,23 +18,23 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Llama3-stanford-encyclopedia-philosophy-QA
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.9202
+This model is a Qlora finetune of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the [Stanford Encyclopedia of Philosophy-instruct](https://huggingface.co/datasets/ruggsea/stanford-encyclopedia-of-philosophy_instruct) dataset. It is meant for answering philosophical questions in a more formal tone.
 
 ## Model description
 
-More information needed
+The model was trained with the following system prompt:
+```
+"You are an expert and informative yet accessible Philosophy university professor. Students will pose you philosophical questions, answer them in a correct and rigorous but not to obscure way."
+```  
 
-## Intended uses & limitations
+Furthermore, the chat dataset was formatted using the Llama3-instruct chat format:
+```
+<|begin_of_text|><|start_header_id|>system<|end_header_id|>
 
-More information needed
+{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
 
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
+{{ user_message }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+```
 
 ### Training hyperparameters
 
@@ -52,16 +52,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.9641        | 0.3529 | 15   | 1.9525          |
-| 1.9096        | 0.7059 | 30   | 1.9184          |
-| 1.8421        | 1.0588 | 45   | 1.9071          |
-| 1.7913        | 1.4118 | 60   | 1.8996          |
-| 1.7812        | 1.7647 | 75   | 1.8928          |
-| 1.6468        | 2.1176 | 90   | 1.9158          |
-| 1.5843        | 2.4706 | 105  | 1.9286          |
-| 1.5829        | 2.8235 | 120  | 1.9202          |
 
 
 ### Framework versions