What Should Baby Models Read? Exploring Sample-Efficient Data Composition on Model Performance

• URL: http://arxiv.org/abs/2411.06672v1
• Date: Mon, 11 Nov 2024 02:37:21 GMT
• Title: What Should Baby Models Read? Exploring Sample-Efficient Data Composition on Model Performance
• Authors: Hong Meng Yam, Nathan J Paek,
• Abstract summary: We evaluate several dataset sources, including child-directed speech (CHILDES), classic books (Gutenberg), synthetic data (TinyStories) and a mix of these across different model sizes. Our experiments show that smaller models (e.g., GPT2-97M, GPT2-705M, Llama-360M) perform better when trained on more complex and rich datasets like Gutenberg.
• Score: 0.0
• License:
• Abstract: We explore the impact of pre-training data composition on the performance of small language models in a sample-efficient setting. Using datasets limited to 10 million words, we evaluate several dataset sources, including child-directed speech (CHILDES), classic books (Gutenberg), synthetic data (TinyStories), and a mix of these (Mix) across different model sizes ranging from 18 million to 705 million parameters. Our experiments show that smaller models (e.g., GPT2-97M, GPT2-705M, Llama-360M) perform better when trained on more complex and rich datasets like Gutenberg. Models trained on the CHILDES and TinyStories datasets underperformed across all model sizes. These findings suggest that the optimal dataset for sample efficient training depends on the model size, and that neither child-directed speech nor simplified stories are optimal for language models of all sizes. We highlight the importance of considering both dataset composition and model capacity for effective sample efficient language model training.

Related papers

• Target-Aware Language Modeling via Granular Data Sampling [25.957424920194914]
  Language model pretraining generally targets a broad range of use cases and incorporates data from diverse sources. A cost-effective and straightforward approach is sampling with low-dimensional data features. We show that pretrained models perform on par with the full RefinedWeb data and outperform randomly selected samples for model sizes ranging from 125M to 1.5B.
  arXiv  Detail & Related papers  (2024-09-23T04:52:17Z)
• InkubaLM: A small language model for low-resource African languages [9.426968756845389]
  InkubaLM is a small language model with 0.4 billion parameters. It achieves performance comparable to models with significantly larger parameter counts. It demonstrates remarkable consistency across multiple languages.
  arXiv  Detail & Related papers  (2024-08-30T05:42:31Z)
• Is Child-Directed Speech Effective Training Data for Language Models? [34.46268640655943]
  We train GPT-2 and RoBERTa models on 29M words of English child-directed speech. We test whether the global developmental ordering or the local discourse ordering of children's training data supports high performance relative to other datasets. These findings support the hypothesis that, rather than proceeding from better data, the child's learning algorithm is substantially more data-efficient than current language modeling techniques.
  arXiv  Detail & Related papers  (2024-08-07T08:18:51Z)
• Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models [39.65879784788677]
  We introduce a novel training data selection based on the learning percentage of the samples. We assert that current language models possess the capability to autonomously select high-quality training data. Our paper introduces a novel approach to training data selection, showcasing a more efficient alternative.
  arXiv  Detail & Related papers  (2024-02-16T03:39:37Z)
• Text Alignment Is An Efficient Unified Model for Massive NLP Tasks [24.069447197357164]
  Next-word prediction is often not an efficient formulation for many NLP tasks. We propose text alignment as an efficient unified model for a wide range of crucial tasks. Our model delivers on par or even superior performance with much smaller model sizes.
  arXiv  Detail & Related papers  (2023-07-06T02:28:31Z)
• Joint Adaptive Representations for Image-Language Learning [59.40890927221377]
  We propose a recipe for image-language learning, which produces effective models, outperforming bigger and more expensive ones, often trained on orders of magnitude larger datasets. Our key finding is the joint learning of a compact vision and language representation, which adaptively and iteratively fuses the multi-modal features. With only 40M training examples and with 39 GFLOPs our lightweight model outperforms many times larger state-of-the-art models of 2-20x more FLOPs and using bigger datasets some of which with close to 1B training examples.
  arXiv  Detail & Related papers  (2023-05-31T15:02:02Z)
• TRAK: Attributing Model Behavior at Scale [79.56020040993947]
  We present TRAK (Tracing with Randomly-trained After Kernel), a data attribution method that is both effective and computationally tractable for large-scale, differenti models.
  arXiv  Detail & Related papers  (2023-03-24T17:56:22Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals [151.3601429216877]
  We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. We propose a recipe, namely "Model generated dEnoising TRaining Objective" (METRO) The resultant models, METRO-LM, consisting of up to 5.4 billion parameters, achieve new state-of-the-art on the GLUE, SuperGLUE, and SQuAD benchmarks.
  arXiv  Detail & Related papers  (2022-04-13T21:39:15Z)
• Efficient Large Scale Language Modeling with Mixtures of Experts [61.45159383372181]
  Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive MoE language models scale in comparison with dense models in a wide range of settings.
  arXiv  Detail & Related papers  (2021-12-20T17:05:11Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.