--- title: Understanding Training Loss in Mini-Batch Training description: In mini-batch training with PyTorch and PyTorch Lightning, the epoch training loss is not the total accumulated error across all samples. Instead, it is the... canonical: https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Understanding Training Loss in Mini-Batch Training | daily.dev og:description: In mini-batch training with PyTorch and PyTorch Lightning, the epoch training loss is not the total accumulated error across all samples. Instead, it is the... og:url: https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5 og:image: https://api.daily.dev/og/posts/oLXnW57o5.png og:image:alt: Understanding Training Loss in Mini-Batch Training og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Understanding Training Loss in Mini-Batch Training **[Medium](https://daily.dev/sources/medium_js)** · 3 min read · 0 upvotes · 0 comments ## Summary In mini-batch training with PyTorch and PyTorch Lightning, the epoch training loss is not the total accumulated error across all samples. Instead, it is the average of the individual batch losses computed during that epoch. The post explains loss functions (MSE, MAE, BCE), how datasets are divided into batches, and the step-by-step training procedure per batch including forward pass, loss calculation, backpropagation, and weight update. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Optimization: Gradient Descent to Adam](https://daily.dev/posts/optimization-gradient-descent-to-adam-ymvhymxv0) · Medium · 0 upvotes · 0 comments - [Training with PyTorch Lightning: Structured MLOps Development](https://daily.dev/posts/training-with-pytorch-lightning-structured-mlops-development-bxyyc6oaz) · PyImageSearch · 1 upvotes · 0 comments - [\*\*PyTorch Stochastic Gradient Optimization Technique\*\*](https://daily.dev/posts/pytorch-stochastic-gradient-optimization-technique--pslwbz3wc) · SitePoint · 1 upvotes · 1 comments - [Backpropagation Explained for Beginners \(Part 1\): Building the Intuition](https://daily.dev/posts/backpropagation-explained-for-beginners-part-1-building-the-intuition-219g21wnz) · Towards Data Science · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#deep-learning](https://daily.dev/tags/deep-learning), [#pytorch](https://daily.dev/tags/pytorch) [View this post on daily.dev](https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Understanding Training Loss in Mini-Batch Training","url":"https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5"},"datePublished":"2026-08-01T22:36:07.848Z","dateModified":"2026-08-01T22:37:40.817Z","description":"In mini-batch training with PyTorch and PyTorch Lightning, the epoch training loss is not the total accumulated error across all samples. Instead, it is the...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/08c65bd7e0b7d3ba69c5901e0ebffd92?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/08c65bd7e0b7d3ba69c5901e0ebffd92?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/understanding-training-loss-in-mini-batch-training-olxnw57o5","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,deep-learning,pytorch","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"Understanding Training Loss in Mini-Batch Training"}]} ```