Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- microsoft/orca-math-word-problems-200k
|
5 |
+
- ise-uiuc/Magicoder-Evol-Instruct-110K
|
6 |
+
- Vezora/Tested-22k-Python-Alpaca
|
7 |
+
---
|
8 |
+
# Datacard for Custom Trained Model
|
9 |
+
|
10 |
+
## Model Description
|
11 |
+
This model is an experimental AI trained on three distinct datasets focusing on logical reasoning, mathematics, and programming. The training process involved fine-tuning from the last layer (31) backward with a gradually decreasing learning rate. The primary goal is to address and rectify the common 'INSTINST' bug observed in leaderboard models through targeted training on the latest layers.
|
12 |
+
|
13 |
+
## Datasets Used for Training
|
14 |
+
- `microsoft/orca-math-word-problems-200k`: A large-scale dataset of mathematical word problems aimed at enhancing the model's numerical reasoning and problem-solving capabilities.
|
15 |
+
- `ise-uiuc/Magicoder-Evol-Instruct-110K`: A dataset designed to improve code generation and understanding, contributing to the model's programming language proficiency.
|
16 |
+
- `sahil2801/CodeAlpaca-20k`: A dataset focused on programming challenges to further refine the model's coding and logical reasoning skills.
|
17 |
+
|
18 |
+
Each dataset contributed 20,000 data points to the training process, ensuring a balanced representation of logic, mathematics, and programming tasks.
|
19 |
+
|
20 |
+
## Training Environment
|
21 |
+
- The model was trained on Kaggle's free GPU environment, allowing for cost-effective fine-tuning and experimentation.
|
22 |
+
- Users interested in replicating or extending this training can find the Kaggle notebook in my profile or request it directly for collaborative purposes.
|
23 |
+
|
24 |
+
## Preliminary Results
|
25 |
+
- The model shows promising results in solving logical puzzles and mathematical problems, especially those with misleading or non-obvious solutions that it initially struggled with.
|
26 |
+
- Ongoing experiments aim to quantify the impact of targeted training on the model's reasoning capabilities across different domains.
|
27 |
+
|
28 |
+
## Invitation for Collaboration
|
29 |
+
- Feedback, suggestions, and collaborative efforts are highly encouraged to further refine and evaluate the model.
|
30 |
+
- If interested in contributing or experimenting with this model, please feel free to reach out or access the code directly from my Kaggle profile.
|
31 |
+
|
32 |
+
## Contact Information
|
33 |
+
- For any inquiries, suggestions, or collaboration proposals, please contact [Your Name] at [Your Email].
|