Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: marin-community/delphi-1e23-25Bparams-628Btokens
|
| 3 |
+
tags: [math, reasoning, grpo, reinforcement-learning, simplerl]
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Delphi-25B-SimpleRL-Math
|
| 7 |
+
|
| 8 |
+
GRPO RL fine-tune of the Marin **Delphi-25B** base model (`marin-community/delphi-1e23-25Bparams-628Btokens`, Qwen3 architecture, compute-optimal 1e23-FLOP point) using the **SimpleRL-Zoo** zero-RL recipe on hard competition math (hkust-nlp `simplelr_qwen_level3to5`, MATH levels 3-5).
|
| 9 |
+
|
| 10 |
+
This is the **step-160** checkpoint (20 epochs). Training reward on the hard-math distribution rose from ~4% to ~29%.
|
| 11 |
+
|
| 12 |
+
## Recipe
|
| 13 |
+
- GRPO, rule-based boxed-answer reward (`math_verify`), `kl_loss_coef=1e-3`, `rollout.n=8`, lr 5e-7.
|
| 14 |
+
- **Rollout temperature 0.5** (not the recipe default of 1.0 — a temperature sweep showed the reward signal collapses above ~0.5 for this weak base on hard math).
|
| 15 |
+
- Seeded with a **3-shot prompt** (a base model needs demonstrations, not a bare instruction). The model expects this exact prompt format and stops at `<|im_end|>`.
|
| 16 |
+
|
| 17 |
+
## Prompt format (3-shot prefix, then your problem)
|
| 18 |
+
```
|
| 19 |
+
<|im_start|>system
|
| 20 |
+
You are a helpful assistant.<|im_end|>
|
| 21 |
+
<|im_start|>user
|
| 22 |
+
A positive integer less than 100 leaves remainder 1 when divided by 6 and remainder 4 when divided by 7. Find the sum of all such integers.
|
| 23 |
+
Please reason step by step, and put your final answer within \boxed{}.<|im_end|>
|
| 24 |
+
<|im_start|>assistant
|
| 25 |
+
We need x ≡ 1 (mod 6) and x ≡ 4 (mod 7). The numbers that are 1 mod 6 are 1, 7, 13, 19, 25, ...; the smallest of these that is also 4 mod 7 is 25, since 25 = 6·4+1 and 25 = 7·3+4. Solutions repeat every lcm(6,7) = 42, so the values below 100 are 25 and 67. Their sum is 25 + 67 = 92.
|
| 26 |
+
The final answer is \boxed{92}.<|im_end|>
|
| 27 |
+
<|im_start|>user
|
| 28 |
+
A club has 4 times as many seniors as juniors and twice as many sophomores as juniors. If there are 42 members in total and only these three groups, how many seniors are there?
|
| 29 |
+
Please reason step by step, and put your final answer within \boxed{}.<|im_end|>
|
| 30 |
+
<|im_start|>assistant
|
| 31 |
+
Let the number of juniors be x. Then the number of seniors is 4x and the number of sophomores is 2x. The total is x + 4x + 2x = 7x = 42, so x = 6. The number of seniors is 4x = 24.
|
| 32 |
+
The final answer is \boxed{24}.<|im_end|>
|
| 33 |
+
<|im_start|>user
|
| 34 |
+
A right square pyramid has base edge 10 and lateral edge 13. Find the total area of its four triangular faces.
|
| 35 |
+
Please reason step by step, and put your final answer within \boxed{}.<|im_end|>
|
| 36 |
+
<|im_start|>assistant
|
| 37 |
+
The slant height runs from the apex to the midpoint of a base edge, not to a corner. Half the base edge is 5 and the lateral edge is 13, so the slant height is √(13² − 5²) = √(169 − 25) = √144 = 12. Each triangular face has area ½ · 10 · 12 = 60, and there are four faces, so the total area is 4 · 60 = 240.
|
| 38 |
+
The final answer is \boxed{240}.<|im_end|><|im_start|>user
|
| 39 |
+
{your problem}
|
| 40 |
+
Please reason step by step, and put your final answer within \boxed{}.<|im_end|>
|
| 41 |
+
<|im_start|>assistant
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
Research checkpoint; inherits the base model license.
|