Upload korscideberta-abstractcls.ipynb

korscideberta-abstractcls.ipynb

@@ -684,15 +684,6 @@
     "#### 파인튜닝 및 모델 업로드 완료"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "K1SWtSpJ1WpZ"
-   },
-   "source": [
-    "Putting it all together, we can finally instantiate the Trainer by passing all required components. We'll use the `\"validation\"` split as the held-out dataset during training."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -787,17 +778,6 @@
     "The Trainer is ready to go 🚀 You can start training by calling `trainer.train()`."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "CaLVY2nfmcgS"
-   },
-   "source": [
-    "Cool, we see that the model seems to learn something! Training loss and validation loss is going down and the accuracy also ends up being well over random chance (20%). Interestingly, we see accuracy of around **58.6 %** already after 5000 steps which doesn't improve that much anymore afterward. Choosing a bigger model or training for longer would have probably given better results here, but that's good enough for our hypothetical use case!\n",
-    "\n",
-    "Alright, finally let's upload the model checkpoint to the Hub."
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {
@@ -812,15 +792,6 @@
     "Let's dive into evaluating the model 🤿."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "wvefwWDdwkl4"
-   },
-   "source": [
-    "The model has been uploaded to the Hub under [`deberta_v3_amazon_reviews`](https://huggingface.co/patrickvonplaten/deberta_v3_amazon_reviews) after training, so in a first step, let's download it from there again. If this notebook is run all at once the following cell will simply load the model from the cache."
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 21,