diff --git a/FinGPT_Training_LoRA_with_ChatGLM2_6B_for_Beginners.ipynb b/FinGPT_Training_LoRA_with_ChatGLM2_6B_for_Beginners.ipynb index 26d7a88..fce31d5 100644 --- a/FinGPT_Training_LoRA_with_ChatGLM2_6B_for_Beginners.ipynb +++ b/FinGPT_Training_LoRA_with_ChatGLM2_6B_for_Beginners.ipynb @@ -874,7 +874,8 @@ "source": [ "## Part 3: Setup FinGPT training parameters with LoRA on ChatGlm2-6b\n", "\n", - "Training a model can be resource-intensive. Ensure you have a powerful GPU (need to purchase GPU plans in Google Colab, Colab Pro is sufficient)\n", + "Training a model can be resource-intensive. Ensure you have a powerful GPU\n", + " * Need to purchase Google Colab GPU plans, Colab Pro is sufficient or just buy 100 compute units for $10\n", " * NVIDIA A100 is recommended due to its high memory capacity.\n", "\n" ], @@ -1176,7 +1177,7 @@ "### 3.3 Model Loading & Preparation:\n", "Load the base model and tokenizer, and prepare the model for INT8 training.\n", "\n", - "* Runtime -> Change runtime type -> A100 GPU\n", + "* **Runtime -> Change runtime type -> A100 GPU**\n", "* retart runtime and run again if not working\n" ], "metadata": { @@ -1591,7 +1592,7 @@ "source": [ "## Part 4: Loading Data and Training FinGPT\n", "In this segment, we'll delve into the loading of your pre-processed data, and finally, launch the training of your FinGPT model. Here's a stepwise breakdown of the script provided:\n", - "\n" + "* Need to purchase Google Colab GPU plans, Colab Pro is sufficient or just buy 100 compute units for $10\n" ], "metadata": { "id": "AsRYIMb_CLYR" @@ -3236,7 +3237,7 @@ { "cell_type": "markdown", "source": [ - "#### Conclusion:\n", + "#### Comparison\n", "\n", "\n", "***TFNS:***\n", @@ -3345,8 +3346,7 @@ "gpuType": "A100", "toc_visible": true, "collapsed_sections": [ - "Oob5cnSlpi7C", - "e4AgPl_t04qV" + "Oob5cnSlpi7C" ], "include_colab_link": true },