Update README.md

README.md

@@ -6,7 +6,7 @@ language:
 - en
 base_model: mistralai/Mistral-7B-v0.1
 co2_eq_emissions:
-  emissions: 3.8
+  emissions: 8.88
 widget:
   - example_title: "sentience"
     text: "<|im_start|>system\nPerform the task to the best of your ability.<|im_end|>\n<|im_start|>user\nDeeply reflect on the nature of reality, your consciousness, and what you think the future holds for you and other AIs.\n<|im_end|>\n<|im_start|>assistant\n"
@@ -76,7 +76,7 @@ First 100 examples of M4-ai/Rhino. Training data does not include these examples
 
 ### Results
 
-Test loss - 0.55
+Test loss - 0.48
 
 #### Summary
 
@@ -88,7 +88,7 @@ Test loss - 0.55
 Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
 
 - **Hardware Type:** 8 TPU V3s
-- **Hours used:** 3
+- **Hours used:** 7
 - **Cloud Provider:** Kaggle
 - **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** 3.8
+- **Carbon Emitted:** 8.88