Update README.md

README.md

@@ -37,6 +37,8 @@ Phi3 was trained using [torchtune](https://github.com/pytorch/torchtune) and the
 tune run lora_finetune_distributed.py --config mini_lora.yaml 
 ```
 
+You can see a full Weights & Biases run [here](https://api.wandb.ai/links/jcummings/hkey76vj).
+
 ### Training Data
 
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
@@ -45,13 +47,12 @@ This model was finetuned on the following datasets:
 
 * TIGER-Lab/MATH-plus: An advanced math-specific dataset with 894k samples.
 
-
 #### Hardware
 
 4 x NVIDIA A100 GPUs
 
 Max VRAM used per GPU: 29 GB
-Real time: 12 hours
+Real time: 10 hours
 
 ## Evaluation
 
@@ -64,7 +65,6 @@ tune run eleuther_eval --config eleuther_evaluation \
           batch_size=32 
 ```
 
-
 |               Tasks                |Version|Filter|n-shot|  Metric   |Value |   |Stderr|
 |------------------------------------|-------|------|-----:|-----------|-----:|---|-----:|
 |minerva_math                        |N/A    |none  |     4|exact_match|0.1670|±  |0.0051|
@@ -76,7 +76,8 @@ tune run eleuther_eval --config eleuther_evaluation \
 | - minerva_math_prealgebra          |      1|none  |     4|exact_match|0.3077|±  |0.0156|
 | - minerva_math_precalc             |      1|none  |     4|exact_match|0.0623|±  |0.0104|
 
+This shows a large improvement over the base Phi3 Mini model.
 
 ## Model Card Contact
 
-[More Information Needed]
+Drop me a line at @official_j3rck