gpt-3 VS automl

Are generative AI models useful for learning a language, and if so which languages? Over 90% of ChatGPT's training data was in English. The remaining 10% of data was split unevenly between 100+ languages. This suggests that the quality of the outputs will vary from language to language.

I have doubts it was extensively trained on German data. Who knows about GPT4, but GPT3 is ~92% of English and ~1.5% of German, which means it saw more "die, motherfucker, die" than on "die Mutter".

(https://github.com/openai/gpt-3/blob/master/dataset_statisti...)

Catalan was 0.018 % of GPT-3's training corpus. https://github.com/openai/gpt-3/blob/master/dataset_statistics/languages_by_word_count.csv.

>Certainly it is pleasing that they are not just doing Hindi, but some of these languages must be represented online by a very small corpus of text indeed. I wonder how effectively an LLM can be trained on such a small training set for any given language?

as long as it's not the main language it doesn't really matter. Besides English(92.6%), the biggest language by representation (word count) is taken up by french at 1.8%. Most of the languages GPT-3 knows are sitting at <0.2% representation.

https://github.com/openai/gpt-3/blob/master/dataset_statisti...

Competence in the main language will bleed into the rest.

And from skimming their GH page, it seems it'd be costly to host as well

I'm using Google Brain's EfficientDet repo to train an object detector. What hyperparameters should I choose to increase accuracy for small objects.

EfficientDet-D0 has comparable accuracy as YOLOv3.

Code for https://arxiv.org/abs/2104.00298 found: https://github.com/google/automl/efficientnetv2

7 Min Read | Paper (CoAtNet) | Paper (EfficientNetV2) | Google blog | Code

Abstract: This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of- the-art models while being up to 6.8x smaller. > Our training can be further sped up by progressively increasing the image size during training, but it often causes a drop in accuracy. To compensate for this accuracy drop, we propose to adaptively adjust regularization (e.g., dropout and data augmentation) as well, such that we can achieve both fast training and good accuracy. > With progressive learning, our EfficientNetV2 significantly outperforms previous models on ImageNet and CIFAR/Cars/Flowers datasets. By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.3% top-1 accuracy on ImageNet ILSVRC2012, outperforming the recent ViT by 2.0% accuracy while training 5x-11x faster using the same computing resources. Code will be available at this https URL.