Update README.md

README.md

@@ -8,14 +8,48 @@ tags:
 license: apache-2.0
 language:
 - en
+datasets:
+- chimbiwide/ReLe_NPC
 ---
 
-# Uploaded finetuned  model
+# GemmaReLe
 
-- **Developed by:** chimbiwide
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit
+### A test model for ReLe
 
-This gemma3n model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+---
+
+
+The **Gemma3NPC** series were meant to be a sort of general purposed video game RP model.
+
+This time, using the [chimbiwide/ReLe_Synthetic_v1_json](https://huggingface.co/datasets/chimbiwide/ReLe_Synthetic_v1_json), we trained a model to specifically act as ReLe.
+
+For more information on *Who is ReLe?*, visit the dataset README.
+
+***Warning***: This is **NOT** a general purpose model. Performance requires further testing.
+
+Check out our training notebook [here](https://github.com/chimbiwide/Gemma3NPC/blob/main/Training/GemmaReLe.ipynb)
+
+---
+
+#### Training parameters compared to `Gemma3NPC-it`
+
+| Parameter | Gemma3NPC-it | Gemma3NPC-it-beta |
+| --- | --- | --- | 
+| Learning Rate | 2e-5 | 2.5e-5 (+25%) | 
+| Warmup Steps | 800 | 100 |
+| gradient clipping | 0.4 | 1.0 |
+
+---
+
+#### Graph of the Step Training Loss, saved every 10 steps:
+
+![chart](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/tpMFpzRY6NGF9txpTAl8k.png)
+
+---
+
+#### Fun Discovery
+
+For the first time ever, we encountered a whole number trianing loss.
+
+![image](https://cdn-uploads.huggingface.co/production/uploads/67d5b5a056a9d31aa0b49687/AOtzf66FgUmfaYJZy1TQ1.png)
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)