Update README.md

README.md

@@ -15,11 +15,7 @@ pipeline_tag: text-generation
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-Phi-3 Mini 4k Instruct model finetuned on math datasets.
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+Math majors - who needs em? This model can answer any math questions you have.
 
 ## How to Get Started with the Model
 
@@ -35,7 +31,7 @@ model = AutoModelForCausalLM.from_pretrained("jrc/phi3-mini-math", trust_remote_
 
 ## Training Details
 
-Phi3 was trained using [torchtune]() and the training script + config file are located in this repository.
+Phi3 was trained using [torchtune](https://github.com/pytorch/torchtune) and the training script + config file are located in this repository.
 
 ```bash
 tune run lora_finetune_distributed.py --config mini_lora.yaml 
@@ -45,11 +41,17 @@ tune run lora_finetune_distributed.py --config mini_lora.yaml
 
 <!-- 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. -->
 
-[More Information Needed]
+This model was finetuned on the following datasets:
+
+* TIGER-Lab/MATH-plus: An advanced math-specific dataset with 894k samples.
+
 
-### Training Procedure
+#### Hardware
+
+4 x NVIDIA A100 GPUs
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Max VRAM used per GPU: 29 GB
+Real time: 12 hours
 
 ## Evaluation
 
@@ -75,15 +77,6 @@ tune run eleuther_eval --config eleuther_evaluation \
 | - minerva_math_precalc             |      1|none  |     4|exact_match|0.0623|±  |0.0104|
 
 
-
-## Technical Specifications [optional]
-
-#### Hardware
-
-4 x NVIDIA A100 GPUs
-
-Max VRAM used per GPU: 29 GB
-
 ## Model Card Contact
 
 [More Information Needed]