{"id":2670,"date":"2023-07-17T14:20:42","date_gmt":"2023-07-17T08:50:42","guid":{"rendered":"https:\/\/www.analyticsvidhya.com\/datahack-summit-2023\/?page_id=2670"},"modified":"2023-07-19T19:09:33","modified_gmt":"2023-07-19T13:39:33","slug":"to-train-fine-tune-prompt-engineer-or-not-is-the-question","status":"publish","type":"page","link":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/","title":{"rendered":"To Train, Fine-Tune, Prompt Engineer or Not is the Question!"},"content":{"rendered":"<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.<\/span><\/p>\n<p><strong>Key Takeaways:<\/strong><\/p>\n<ul>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Training:<br \/>\n<\/span><\/p>\n<ul>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Training LLMs requires a large dataset of text and code.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Training can take weeks or months, depending on the size of the dataset and the model architecture.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Training can be expensive, depending on the hardware used.<\/span><\/li>\n<li>Training can lead to the best performance, but it is not always necessary.<\/li>\n<\/ul>\n<\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Fine-tuning:<br \/>\n<\/span><\/p>\n<ul>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Fine-tuning LLMs requires a small dataset of labeled data.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Fine-tuning can take hours or days, depending on the size of the dataset and the model architecture.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Fine-tuning is less expensive than training, but it can still be costly.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\"><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Fine-tuning can lead to significant improvements in performance, but it is not always necessary.<\/span><\/span><\/li>\n<\/ul>\n<\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Prompt Engineering:<br \/>\n<\/span><\/p>\n<ul>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Prompt engineering does not require any training data.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Prompt engineering can be done quickly and easily.<br \/>\n<\/span><\/li>\n<li><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">Prompt engineering is the least expensive approach to using LLMs.<\/span><\/li>\n<li>Prompt engineering can be less reliable than training or fine-tuning.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span data-sheets-value=\"{&quot;1&quot;:2,&quot;2&quot;:&quot;This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least time-consuming and expensive approach, but it can be less reliable.\\n\\nKey Takeaways:\\n\\nTraining:\\nTraining LLMs requires a large dataset of text and code.\\nTraining can take weeks or months, depending on the size of the dataset and the model architecture.\\nTraining can be expensive, depending on the hardware used.\\nTraining can lead to the best performance, but it is not always necessary.\\n\\nFine-tuning:\\nFine-tuning LLMs requires a small dataset of labeled data.\\nFine-tuning can take hours or days, depending on the size of the dataset and the model architecture.\\nFine-tuning is less expensive than training, but it can still be costly.\\nFine-tuning can lead to significant improvements in performance, but it is not always necessary.\\n\\nPrompt Engineering:\\nPrompt engineering does not require any training data.\\nPrompt engineering can be done quickly and easily.\\nPrompt engineering is the least expensive approach to using LLMs.\\nPrompt engineering can be less reliable than training or fine-tuning.\\n\\n\\nThis session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.&quot;}\" data-sheets-userformat=\"{&quot;2&quot;:1023,&quot;3&quot;:{&quot;1&quot;:0},&quot;4&quot;:{&quot;1&quot;:2,&quot;2&quot;:16777215},&quot;5&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;6&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;7&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;8&quot;:{&quot;1&quot;:[{&quot;1&quot;:2,&quot;2&quot;:0,&quot;5&quot;:{&quot;1&quot;:2,&quot;2&quot;:0}},{&quot;1&quot;:0,&quot;2&quot;:0,&quot;3&quot;:3},{&quot;1&quot;:1,&quot;2&quot;:0,&quot;4&quot;:1}]},&quot;9&quot;:1,&quot;10&quot;:1,&quot;11&quot;:3,&quot;12&quot;:0}\">This session concludes by discussing the trade-offs between the three approaches to using LLMs. The best approach depends on the specific task at hand and the resources available.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2671,"parent":1126,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"session-details.php","meta":[],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v20.7 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023\" \/>\n<meta property=\"og:description\" content=\"This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/\" \/>\n<meta property=\"og:site_name\" content=\"DataHack Summit 2023\" \/>\n<meta property=\"article:modified_time\" content=\"2023-07-19T13:39:33+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/07\/s-not-in-question.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"500\" \/>\n\t<meta property=\"og:image:height\" content=\"250\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/\",\"name\":\"To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023\",\"isPartOf\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\"},\"datePublished\":\"2023-07-17T08:50:42+00:00\",\"dateModified\":\"2023-07-19T13:39:33+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Session\",\"item\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"To Train, Fine-Tune, Prompt Engineer or Not is the Question!\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website\",\"url\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/\",\"name\":\"DataHack Summit 2023\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/","og_locale":"en_US","og_type":"article","og_title":"To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023","og_description":"This session discusses the three main approaches to using large language models (LLMs): training, fine-tuning, and prompt engineering. Training is the most time-consuming and expensive approach, but it can lead to the best performance. Fine-tuning is less time-consuming and expensive, but it can still lead to significant improvements in performance. Prompt engineering is the least [&hellip;]","og_url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/","og_site_name":"DataHack Summit 2023","article_modified_time":"2023-07-19T13:39:33+00:00","og_image":[{"url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-content\/uploads\/2023\/07\/s-not-in-question.jpg","width":500,"height":250,"type":"image\/jpeg"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/","name":"To Train, Fine-Tune, Prompt Engineer or Not is the Question! - DataHack Summit 2023","isPartOf":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website"},"datePublished":"2023-07-17T08:50:42+00:00","dateModified":"2023-07-19T13:39:33+00:00","breadcrumb":{"@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/to-train-fine-tune-prompt-engineer-or-not-is-the-question\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/"},{"@type":"ListItem","position":2,"name":"Session","item":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/session\/"},{"@type":"ListItem","position":3,"name":"To Train, Fine-Tune, Prompt Engineer or Not is the Question!"}]},{"@type":"WebSite","@id":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/#website","url":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/","name":"DataHack Summit 2023","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2670"}],"collection":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/comments?post=2670"}],"version-history":[{"count":4,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2670\/revisions"}],"predecessor-version":[{"id":2926,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/2670\/revisions\/2926"}],"up":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/pages\/1126"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media\/2671"}],"wp:attachment":[{"href":"https:\/\/www.analyticsvidhya.com\/dhs-2023\/wp-json\/wp\/v2\/media?parent=2670"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}