The total number of FLOPs required to train GPT‑3 is approximately 3.15 × 10²³.

Step‑by‑step reasoning:

1. Model size: GPT‑3 has 175 billion (1.75 × 10¹¹) trainable parameters.

2. Training data: According to the paper abstract, the model was trained on 300 billion (3 × 10¹¹) tokens.

3. FLOPs per token for training a transformer:

   • Forward pass: each parameter is used in one multiply‑add operation → ~2 FLOPs per parameter → 2 N FLOPs per token.
   • Backward pass (gradient computation): roughly twice the forward cost → ~4 N FLOPs per token.
   • Total: ~6 N FLOPs per token.
     This approximation is standard for large transformer models and neglects small overheads like attention quadratic terms (which add only ~1–2% for GPT‑3’s sequence length).

4. Calculation:
   Total FLOPs ≈ 6 × (1.75 × 10¹¹) × (3 × 10¹¹)
   = 6 × 5.25 × 10²²
   = 3.15 × 10²³.

5. Consistency check: The GPT‑3 paper reports a training compute of 3,640 PF‑days. Converting:
   1 PF‑day = 10¹⁵ FLOP/s × 86400 s = 8.64 × 10¹⁹ FLOPs.
   3,640 PF‑days = 3,640 × 8.64 × 10¹⁹ ≈ 3.14 × 10²³ FLOPs, matching the estimate.

Thus, the total FLOPs required to train GPT‑3 is about 3.15 × 10²³.

Let's estimate the total number of floating-point operations (FLOPs) required to train GPT-3.

Step 1: Recall GPT-3 scale

From published sources (I won't look this up now, as instructed):

• GPT-3 (175B) has about 175 billion parameters.
• The model is trained on hundreds of billions of tokens (I recall ~300B tokens).

Step 2: FLOPs per token per parameter

When training a transformer, roughly 2 forward passes and 1 backward pass per token (combined), and the number of FLOPs per parameter per token is about 6 (this is a number I remember from general literature).

But to be more precise, the convention is: Training one token requires about 2 FLOPs per parameter (one forward and one backward pass, with backward generally being twice as expensive as forward). Sometimes the estimate is 2, 3, 6, or even more, depending on if you count both, under what assumptions (optimizer steps, auxiliary computations, etc.), but 4 or 6 is standard.

Let's use 6 FLOPs/parameter/token (a commonly cited "rule of thumb").

Step 3: Compute FLOPs

Formula

[ \text{Total FLOPs} = \text{#params} \times \text{#tokens} \times \text{FLOPs per param per token} ]

Plug in numbers:

• #params ≈ 175 × 10⁹
• #tokens ≈ 300 × 10⁹
• FLOPs per param per token ≈ 6

[ \text{Total FLOPs} = 175 \times 10^9 \times 300 \times 10^9 \times 6 ]

Let's multiply:

• (175 \times 300 = 52,500)
• (52,500 \times 6 = 315,000)
• (10^9 \times 10^9 = 10^{18})

So,

[ \text{Total FLOPs} = 315{,}000 \times 10^{18} = 3.15 \times 10^{23} \text{ FLOPs} ]

Step 4: Order of Magnitude & Re-check

People sometimes write (3 \times 10^{23}) for GPT-3, so our estimate matches the ballpark.

Step 5: Summary Sentence

Estimate:
It would take approximately (3 \times 10^{23}) FLOPs to train GPT-3 (175B parameters, 300B tokens, 6 FLOPs/param/token).

Assumptions:

• 175B parameters
• 300B tokens
• 6 FLOPs per parameter per token

---

In summary:

Estimated total training compute for GPT-3: (\boxed{sim3 \times 10^{23}}) FLOPs
(based on 175B parameters, 300B tokens, 6 FLOPs/parameter/token)

Sally has 1 sister.

Here is the breakdown:

1. Since the brothers are all siblings, they share the same sisters.
2. If each brother has 2 sisters, that means there are 2 girls in total in the family.
3. Sally is one of those girls.
4. Therefore, the other girl is Sally's only sister.

Let's break down the problem:

• Sally is a girl.
• She has 3 brothers.
• Each brother has 2 sisters.

Let's name the siblings:

• Sally (girl)
• Brother 1
• Brother 2
• Brother 3

Now, the key: Each brother has 2 sisters.

Since Sally is one of the sisters, let's see if there are more:

Suppose there is only one girl (Sally) in the family.

• Then each brother would have only 1 sister: Sally.
• But the problem says they have 2 sisters each.

Thus, Sally must have one sister (since the brothers must have 2 sisters). Let's call this other sister "Anna".

So the siblings are:

• Sally (girl)
• Anna (girl)
• Brother 1
• Brother 2
• Brother 3

Now, each brother has 2 sisters: Sally and Anna.

So, how many sisters does Sally have?

• Sally's sisters = 1 (Anna).

Final Answer:

Sally has 1 sister.