apply google/generative-ai-docs#616

Author: bebechien

docs/functiongemma/finetuning-with-functiongemma.ipynb

@@ -80,9 +80,9 @@
       "source": [
         "This guide demonstrates how to fine-tune FunctionGemma for tool calling.\n",
         "\n",
-        "While FunctionGemma is natively capable of calling tools. But true capability comes from two distinct skills: the mechanical knowledge of how to use a tool (syntax) and the cognitive ability to interpret *why* and *when* to use it (intent).\n",
+        "While FunctionGemma is natively capable of calling tools, true capability comes from two distinct skills: the mechanical knowledge of how to use a tool (syntax) and the cognitive ability to interpret *why* and *when* to use it (intent).\n",
         "\n",
-        "Models, especially smaller ones, have fewer parameters available to retain complex intent understanding. This is why we need to fine-tune them\n",
+        "Models, especially smaller ones, have fewer parameters available to retain complex intent understanding. This is why we need to fine-tune them.\n",
         "\n",
         "Common use cases for fine-tuning tool calling include:\n",
         "\n",
@@ -134,7 +134,7 @@
         "id": "3raKuRFXEDNm"
       },
       "source": [
-        "> _Note: If you are using a GPU with Ampere architecture (such as NVIDIA L4) or newer, you can use Flash attention. Flash Attention is a method that significantly speeds computations up and reduces memory usage from quadratic to linear in sequence length, leading to acelerating training up to 3x. Learn more at [FlashAttention](https://github.com/Dao-AILab/flash-attention/tree/main)._\n",
+        "> _Note: If you are using a GPU with Ampere architecture (such as NVIDIA L4) or newer, you can use Flash attention. Flash Attention is a method that significantly speeds computations up and reduces memory usage from quadratic to linear in sequence length, leading to accelerating training up to 3x. Learn more at [FlashAttention](https://github.com/Dao-AILab/flash-attention/tree/main)._\n",
         "\n",
         "Before you can start training, you have to make sure that you accepted the terms of use for Gemma. You can accept the license on [Hugging Face](http://huggingface.co/google/functiongemma-270m-it) by clicking on the **Agree** and access repository button on the model page at: http://huggingface.co/google/functiongemma-270m-it\n",
         "\n",
@@ -924,7 +924,7 @@
       "source": [
         "To plot the training and validation losses, you would typically extract these values from the `TrainerState` object or the logs generated during training.\n",
         "\n",
-        "Libraries like Matplotlib can then be used to visualize these values over training steps or epochs. The x-asis would represent the training steps or epochs, and the y-axis would represent the corresponding loss values."
+        "Libraries like Matplotlib can then be used to visualize these values over training steps or epochs. The x-axis would represent the training steps or epochs, and the y-axis would represent the corresponding loss values."
       ]
     },
     {
@@ -1059,7 +1059,7 @@
         }
       ],
       "source": [
-        "check_success_rate()\n"
+        "check_success_rate()"
       ]
     },
     {
@@ -1087,7 +1087,7 @@
         "Check out the following docs next:\n",
         "\n",
         "- [Full function calling sequence with FunctionGemma](https://ai.google.dev/gemma/docs/functiongemma/full-function-calling-sequence-with-functiongemma)\n",
-        "- [Finetune FunctionGemma for Mobile Actions](https://github.com/google-gemini/gemma-cookbook/blob/main/FunctionGemma/%5BFunctionGemma%5DFinetune_FunctionGemma_270M_for_Mobile_Actions_with_Hugging_Face.ipynb) in the Gemma Cookbook\n"
+        "- [Fine-tune FunctionGemma for Mobile Actions](https://github.com/google-gemini/gemma-cookbook/blob/main/FunctionGemma/%5BFunctionGemma%5DFinetune_FunctionGemma_270M_for_Mobile_Actions_with_Hugging_Face.ipynb) in the Gemma Cookbook\n"
       ]
     }
   ],