Fixed broken bookmark, incorrect usage for Davinci

Author: DenKenMSFT

articles/cognitive-services/openai/concepts/models.md

@@ -21,7 +21,7 @@ The service provides access to many different models, grouped by family and capa
 |--|--|
 | [GPT-3](#gpt-3-models) | A series of models that can understand and generate natural language. |
 | [Codex](#codex-models) | A series of models that can understand and generate code, including translating natural language to code. |
-| [Embeddings](#embedding-models) | A set of models that can understand and use embeddings. An embedding is a special format of data representation that can be easily utilized by machine learning models and algorithms. The embedding is an information dense representation of the semantic meaning of a piece of text. Currently, we offer three families of Embeddings models for different functionalities: text search, text similarity, and code search. |
+| [Embeddings](#embeddings-models) | A set of models that can understand and use embeddings. An embedding is a special format of data representation that can be easily utilized by machine learning models and algorithms. The embedding is an information dense representation of the semantic meaning of a piece of text. Currently, we offer three families of Embeddings models for different functionalities: text search, text similarity, and code search. |
 
 ## Model capabilities
 

articles/cognitive-services/openai/quotas-limits.md

@@ -32,7 +32,7 @@ The following sections provide you with a quick guide to the quotas and limits t
 | Max Files per resource | 50 |
 | Total size of all files per resource | 1 GB| 
 | Max training job time (job will fail if exceeded) | 120 hours |
-| Max training job size (tokens in training file * # of epochs) | **Ada**: 4-M tokens <br> **Babbage**: 4-M tokens <br> **Curie**: 4-M tokens <br> **Cushman**: 4-M tokens <br> **DaVinci**: 500 K |
+| Max training job size (tokens in training file * # of epochs) | **Ada**: 4-M tokens <br> **Babbage**: 4-M tokens <br> **Curie**: 4-M tokens <br> **Cushman**: 4-M tokens <br> **Davinci**: 500 K |
 
 
 ### General best practices to mitigate throttling during autoscaling

articles/cognitive-services/openai/reference.md

@@ -427,7 +427,7 @@ POST https://{your-resource-name}.openai.azure.com/openai/fine-tunes?api-version
 | validation_file| string | no | null | The ID of an uploaded file that contains validation data. <br> If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. Your train and validation data should be mutually exclusive. <br><br> Your dataset must be formatted as a JSONL file, where each validation example is a JSON object with the keys "prompt" and "completion". Additionally, you must upload your file with the purpose fine-tune. |
 | batch_size | integer | no | null | The batch size to use for training. The batch size is the number of training examples used to train a single forward and backward pass. <br><br> By default, the batch size will be dynamically configured to be ~0.2% of the number of examples in the training set, capped at 256 - in general, we've found that larger batch sizes tend to work better for larger datasets.
 | learning_rate_multiplier | number (double) | no | null | The learning rate multiplier to use for training. The fine-tuning learning rate is the original learning rate used for pre-training multiplied by this value.<br><br> We recommend experimenting with values in the range 0.02 to 0.2 to see what produces the best results. |
-| n_epochs |  integer | no | 4 for `ada`, `babbage`, `curie`. 1 for `DaVinci` | The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. |
+| n_epochs |  integer | no | 4 for `ada`, `babbage`, `curie`. 1 for `davinci` | The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. |
 | prompt_loss_weight | number (double) | no | 0.1 | The weight to use for loss on the prompt tokens. This controls how much the model tries to learn to generate the prompt (as compared to the completion, which always has a weight of 1.0), and can add a stabilizing effect to training when completions are short. <br><br> |
 | compute_classification_metrics | boolean | no | false | If set, we calculate classification-specific metrics such as accuracy and F-1 score using the validation set at the end of every epoch. |
 | classification_n_classes | integer | no | null | The number of classes in a classification task. This parameter is required for multiclass classification |