Kuyera Mitemo yeNeural Networks Quiz

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

1. What pattern did Kaplan et al. report for language-model loss as model size, data, or compute increased?
   • Approximate power-law relationships over the tested ranges
   • A sudden guaranteed drop to zero
   • A fixed increase in loss for every larger model
   • Random oscillation with no measurable trend
2. Ndezvipi zviyero zvitatu izvo mitemo yekutanga yekuyera ine chekuita nekurasikirwa?
   • Batch size, dropout, uye epochs
   • Model paramita, saizi yedataset, uye compute
   • Chiyero chekudzidza, kuora kwehuremu, uye kudzika
   • GPU kuverenga, ndangariro, uye latency
3. How can a scaling-law fit help when planning a larger training run?
   • It guarantees the final benchmark score
   • It eliminates the need for validation
   • It can inform an extrapolation from smaller experiments, subject to the tested setup
   • It predicts results exactly for any dataset or architecture
4. Ko izwi risingaperi (risingadzoreki) muchiyero chekurasikirwa kwemutemo formula rinomiririrei?
   • A software bug
   • Chiyero chekudzidza
   • Nhamba yeGPUs
   • Iyo yemukati entropy yedata iyo isina modhi inogona kukunda
5. Why can absolute loss reductions become smaller as compute keeps increasing under a power-law fit?
   • The reducible loss term shrinks while the loss approaches its floor
   • The data is removed after each compute increase
   • The model stops using parameters
   • Power laws require loss to increase over time
6. Ndeapi maitiro ari kusunda munda kupfuura nyore 'kukura kuri nani' kuyera?
   • maGPU ave akasununguka
   • Kushomeka kwedata remhando yepamusoro pamwe nesimba uye mari inogumira
   • Mavara asingaverengeki emhando yepamusoro arikuoneka
   • Kurasika macurves kushanduka kuita mitsetse yakatwasuka
7. What did the original Kaplan study say about architecture details such as width and depth within its tested range?
   • They always dominated model size, data, and compute
   • They made loss independent of data
   • They had relatively small effects compared with the studied scaling variables
   • They guaranteed the same performance for all architectures
8. What compute-allocation tendency did the original Kaplan paper report?
   • Every model should be trained to zero loss
   • Small models always use less compute at equal loss
   • Training data has no effect on compute allocation
   • Large models could be more sample-efficient and compute-efficient training could stop before convergence