Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT

• URL: http://arxiv.org/abs/2501.00241v1
• Date: Tue, 31 Dec 2024 03:16:15 GMT
• Title: Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT
• Authors: Giuliano Lorenzoni, Ivens Portugal, Paulo Alencar, Donald Cowan,
• Abstract summary: This study evaluates fine-tuning strategies for text classification using the DistilBERT model.<n>We examine the influence of hyper parameters such as learning rate, batch size, and epochs on accuracy, F1-score, and loss.
• Score: 0.9249657468385781
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study evaluates fine-tuning strategies for text classification using the DistilBERT model, specifically the distilbert-base-uncased-finetuned-sst-2-english variant. Through structured experiments, we examine the influence of hyperparameters such as learning rate, batch size, and epochs on accuracy, F1-score, and loss. Polynomial regression analyses capture foundational and incremental impacts of these hyperparameters, focusing on fine-tuning adjustments relative to a baseline model. Results reveal variability in metrics due to hyperparameter configurations, showing trade-offs among performance metrics. For example, a higher learning rate reduces loss in relative analysis (p=0.027) but challenges accuracy improvements. Meanwhile, batch size significantly impacts accuracy and F1-score in absolute regression (p=0.028 and p=0.005) but has limited influence on loss optimization (p=0.170). The interaction between epochs and batch size maximizes F1-score (p=0.001), underscoring the importance of hyperparameter interplay. These findings highlight the need for fine-tuning strategies addressing non-linear hyperparameter interactions to balance performance across metrics. Such variability and metric trade-offs are relevant for tasks beyond text classification, including NLP and computer vision. This analysis informs fine-tuning strategies for large language models and promotes adaptive designs for broader model applicability.

Related papers

• Cultural Alignment in Large Language Models Using Soft Prompt Tuning [3.4373727078460665]
  Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. We propose a parameter efficient strategy that combines soft prompt tuning, which freezes the model parameters while modifying the input prompt embeddings, with Differential Evolution (DE) Our method demonstrates significant improvements in LLama-3-8B-Instruct's cultural dimensions across multiple regions.
  arXiv  Detail & Related papers  (2025-03-20T12:34:01Z)
• Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models [10.517704202614091]
  sparse Mixture-of-Experts (MoEs) allow scaling the number of parameters without proportionally increasing the FLOPs per example. We investigate how varying the sparsity level, i.e., the fraction of inactive parameters, impacts model's performance during pretraining and downstream few-shot evaluation.
  arXiv  Detail & Related papers  (2025-01-21T18:51:15Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
  We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA) Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%. DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
  arXiv  Detail & Related papers  (2024-10-02T07:14:26Z)
• Variable Importance in High-Dimensional Settings Requires Grouping [19.095605415846187]
  Conditional Permutation Importance (CPI) bypasses PI's limitations in such cases. Grouping variables statistically via clustering or some prior knowledge gains some power back. We show that the approach extended with stacking controls the type-I error even with highly-correlated groups.
  arXiv  Detail & Related papers  (2023-12-18T00:21:47Z)
• Deeper Understanding of Black-box Predictions via Generalized Influence Functions [6.649753747542211]
  Influence functions (IFs) elucidate how data changes model. Increasing size and non- interpretity in large-scale models make IFs inaccurate. We introduce generalized IFs, precisely estimating target parameters' influence while nullifying nuisance gradient changes on fixed parameters.
  arXiv  Detail & Related papers  (2023-12-09T14:17:12Z)
• Linked shrinkage to improve estimation of interaction effects in regression models [0.0]
  We develop an estimator that adapts well to two-way interaction terms in a regression model. We evaluate the potential of the model for inference, which is notoriously hard for selection strategies. Our models can be very competitive to a more advanced machine learner, like random forest, even for fairly large sample sizes.
  arXiv  Detail & Related papers  (2023-09-25T10:03:39Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models [19.640997611256168]
  We propose AlphaTuning, consisting of post-training quantization of the pre-trained language model and fine-tuning only some parts of quantized parameters for a target task. Specifically, AlphaTuning works by employing binary-coding quantization, which factorizes the full-precision parameters into binary parameters and a separate set of scaling factors. We demonstrate that AlphaTuning, when applied to GPT-2 and OPT, performs competitively with full fine-tuning on a variety of downstream tasks while achieving >10x compression ratio under 4-bit quantization and >1,000x reduction in the number of trainable parameters.
  arXiv  Detail & Related papers  (2022-10-08T00:36:00Z)
• On Parametric Optimal Execution and Machine Learning Surrogates [3.077531983369872]
  We investigate optimal order execution problems in discrete time with instantaneous price impact and resilience. We develop a numerical algorithm based on dynamic programming and deep learning.
  arXiv  Detail & Related papers  (2022-04-18T22:40:14Z)
• Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data [66.11139091362078]
  We provide the first model selection results on large pretrained Transformers from Huggingface using generalization metrics. Despite their niche status, we find that metrics derived from the heavy-tail (HT) perspective are particularly useful in NLP tasks.
  arXiv  Detail & Related papers  (2022-02-06T20:07:35Z)
• Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metrics [61.49826776409194]
  We analyze a corpus of models made publicly-available for a contest to predict the generalization accuracy of neural network (NN) models. We identify what amounts to a Simpson's paradox: where "scale" metrics perform well overall but perform poorly on sub partitions of the data. We present two novel shape metrics, one data-independent, and the other data-dependent, which can predict trends in the test accuracy of a series of NNs.
  arXiv  Detail & Related papers  (2021-06-01T19:19:49Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Rethinking the Hyperparameters for Fine-tuning [78.15505286781293]
  Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyper parameters. This paper re-examines several common practices of setting hyper parameters for fine-tuning.
  arXiv  Detail & Related papers  (2020-02-19T18:59:52Z)

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.