Quiz collegato alla guida · Difficile Livello
Quiz sulle dimensioni critiche dei lotti
Esplora le dimensioni critiche dei batch attraverso il conteggio degli aggiornamenti, gli esempi elaborati, il rumore del gradiente, i confronti del tempo necessario per raggiungere il target e i limiti hardware pratici.
Domanda 1 di 8
Which behavior characterizes batches far beyond a training problem’s critical batch scale?
Anteprima di ogni domanda8 domande
Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.
- Which behavior characterizes batches far beyond a training problem’s critical batch scale?
- Additional examples per update give diminishing reductions in required updates
- Training becomes mathematically impossible
- The model always stops fitting in memory
- Each batch doubling must halve elapsed time
- Why is the largest batch that fits in memory not necessarily the critical batch size?
- Memory capacity determines every gradient statistic
- Memory fit and optimization efficiency describe different constraints
- Critical batch size counts only storage bytes
- A fitting batch always minimizes time to target
- At a fixed batch of 256 and 4,000 updates, how many examples are processed?
- 4,256
- 15.625
- 1,024,000
- 512,000
- In the worked comparison, increasing the batch from 256 to 512 changes required updates from 4,000 to 2,200. What happens to processed examples?
- They fall by 45%
- They are unchanged
- They double
- They rise from 1,024,000 to 1,126,400, a 10% increase
- Which measurement is still needed before concluding that fewer training updates saved elapsed time?
- Actual update or full-run timings on the intended hardware
- Only the checkpoint filename
- Contano solo i parametri
- Only the first batch’s loss
- What statistic did the cited large-batch research connect with the largest useful batch range?
- The number of output classes alone
- Gradient noise scale
- The checkpoint file extension
- The number of evaluation reports
- Why should a batch-size comparison state a common performance target?
- The target makes every learning rate equivalent
- It prevents batches from using different amounts of memory
- It lets runs be compared by the resources needed to reach the same goal
- It guarantees every run reaches the global optimum
- Why might a team revisit its batch size later in training?
- The number of bytes in a token always doubles
- A fixed batch stops being legal after one epoch
- Every later batch must be larger
- The useful critical scale can shift with training progress and the target loss