diff --git a/README.md b/README.md
index bd5a544b5..87095a7c1 100644
--- a/README.md
+++ b/README.md
@@ -18,7 +18,8 @@ yarn add openai
 
 ## Usage
 
-The full API of this library can be found in [API.md file](https://github.com/openai/openai-node/blob/master/api.md). The code below shows how to get started using the chat completions API.
+> [!IMPORTANT]
+> Previous versions of this SDK used a `Configuration` class. See the [v3 to v4 migration guide](https://github.com/openai/openai-node/discussions/217).
 
 ```js
 import OpenAI from 'openai';
@@ -39,9 +40,6 @@ async function main() {
 main();
 ```
 
-> [!IMPORTANT]
-> Previous versions of this SDK used a `Configuration` class. See the [v3 to v4 migration guide](https://github.com/openai/openai-node/discussions/217).
-
 ## Streaming Responses
 
 We provide support for streaming responses using Server Sent Events (SSE).
diff --git a/tests/api-resources/fine-tunes.test.ts b/tests/api-resources/fine-tunes.test.ts
index 8b4a6df45..48429a90a 100644
--- a/tests/api-resources/fine-tunes.test.ts
+++ b/tests/api-resources/fine-tunes.test.ts
@@ -21,7 +21,7 @@ describe('resource fineTunes', () => {
     const response = await openai.fineTunes.create({
       training_file: 'file-abc123',
       batch_size: 0,
-      classification_betas: [0, 0, 0],
+      classification_betas: [0.6, 1, 1.5, 2],
       classification_n_classes: 0,
       classification_positive_class: 'string',
       compute_classification_metrics: true,