Store model config.

Finetune BERT.ipynb

@@ -14,11 +14,11 @@
    "id": "73e72549-69f2-46b5-b0f5-655777139972",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:15:28.938894Z",
-     "iopub.status.busy": "2025-01-22T00:15:28.938077Z",
-     "iopub.status.idle": "2025-01-22T00:15:34.317293Z",
-     "shell.execute_reply": "2025-01-22T00:15:34.316942Z",
-     "shell.execute_reply.started": "2025-01-22T00:15:28.938839Z"
+     "iopub.execute_input": "2025-01-22T14:28:40.399621Z",
+     "iopub.status.busy": "2025-01-22T14:28:40.398151Z",
+     "iopub.status.idle": "2025-01-22T14:28:43.463152Z",
+     "shell.execute_reply": "2025-01-22T14:28:43.462919Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:40.399562Z"
     }
    },
    "outputs": [],
@@ -45,11 +45,11 @@
    "id": "07e0787e-c72b-41f3-baba-43cef3f8d6f8",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:15:34.318082Z",
-     "iopub.status.busy": "2025-01-22T00:15:34.317923Z",
-     "iopub.status.idle": "2025-01-22T00:15:34.320079Z",
-     "shell.execute_reply": "2025-01-22T00:15:34.319851Z",
-     "shell.execute_reply.started": "2025-01-22T00:15:34.318073Z"
+     "iopub.execute_input": "2025-01-22T14:28:43.463941Z",
+     "iopub.status.busy": "2025-01-22T14:28:43.463805Z",
+     "iopub.status.idle": "2025-01-22T14:28:43.465644Z",
+     "shell.execute_reply": "2025-01-22T14:28:43.465423Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:43.463933Z"
     }
    },
    "outputs": [],
@@ -67,15 +67,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 3,
    "id": "d4b79fb9-5e70-4600-8885-94bc0a6e917c",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:18:10.466025Z",
-     "iopub.status.busy": "2025-01-22T00:18:10.465289Z",
-     "iopub.status.idle": "2025-01-22T00:18:10.482505Z",
-     "shell.execute_reply": "2025-01-22T00:18:10.481605Z",
-     "shell.execute_reply.started": "2025-01-22T00:18:10.465973Z"
+     "iopub.execute_input": "2025-01-22T14:28:44.578819Z",
+     "iopub.status.busy": "2025-01-22T14:28:44.578158Z",
+     "iopub.status.idle": "2025-01-22T14:28:44.594834Z",
+     "shell.execute_reply": "2025-01-22T14:28:44.594043Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:44.578767Z"
     }
    },
    "outputs": [],
@@ -131,6 +131,8 @@
     "    def __init__(self, num_labels=8, bert_variety=\"bert-base-uncased\"):\n",
     "        super().__init__()\n",
     "        self.bert = BertModel.from_pretrained(bert_variety)\n",
+    "        self.config = self.bert.config\n",
+    "        self.config.num_labels = num_labels\n",
     "        self.dropout = nn.Dropout(0.05)\n",
     "        self.classifier = nn.Linear(self.bert.pooler.dense.out_features, num_labels)\n",
     "\n",
@@ -193,15 +195,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 4,
    "id": "07131bce-23ad-4787-8622-cce401f3e5ce",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:18:10.964716Z",
-     "iopub.status.busy": "2025-01-22T00:18:10.963608Z",
-     "iopub.status.idle": "2025-01-22T00:18:10.971834Z",
-     "shell.execute_reply": "2025-01-22T00:18:10.970949Z",
-     "shell.execute_reply.started": "2025-01-22T00:18:10.964671Z"
+     "iopub.execute_input": "2025-01-22T14:28:45.024103Z",
+     "iopub.status.busy": "2025-01-22T14:28:45.023645Z",
+     "iopub.status.idle": "2025-01-22T14:28:45.056500Z",
+     "shell.execute_reply": "2025-01-22T14:28:45.056070Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:45.024069Z"
     }
    },
    "outputs": [],
@@ -217,15 +219,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 5,
    "id": "695bc080-bbd7-4937-af5b-50db1c936500",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:18:11.117610Z",
-     "iopub.status.busy": "2025-01-22T00:18:11.117201Z",
-     "iopub.status.idle": "2025-01-22T00:18:11.128421Z",
-     "shell.execute_reply": "2025-01-22T00:18:11.127145Z",
-     "shell.execute_reply.started": "2025-01-22T00:18:11.117580Z"
+     "iopub.execute_input": "2025-01-22T14:28:45.268069Z",
+     "iopub.status.busy": "2025-01-22T14:28:45.267170Z",
+     "iopub.status.idle": "2025-01-22T14:28:45.279492Z",
+     "shell.execute_reply": "2025-01-22T14:28:45.278723Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:45.268003Z"
     }
    },
    "outputs": [],
@@ -321,15 +323,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 6,
    "id": "34a7c310-c486-4db1-b94d-4363c3d3df5b",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:18:31.584691Z",
-     "iopub.status.busy": "2025-01-22T00:18:31.584113Z",
-     "iopub.status.idle": "2025-01-22T00:18:38.462642Z",
-     "shell.execute_reply": "2025-01-22T00:18:38.462384Z",
-     "shell.execute_reply.started": "2025-01-22T00:18:31.584650Z"
+     "iopub.execute_input": "2025-01-22T14:28:46.360995Z",
+     "iopub.status.busy": "2025-01-22T14:28:46.360044Z",
+     "iopub.status.idle": "2025-01-22T14:28:53.023176Z",
+     "shell.execute_reply": "2025-01-22T14:28:53.022848Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:46.360953Z"
     }
    },
    "outputs": [
@@ -337,10 +339,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2025-01-21 19:18:35 Epoch  0/3 done. Loss: Train 2.184, Test 2.190; and Acc: Train 0.131, Test 0.129\n",
-      "2025-01-21 19:18:36 Epoch  1/3 done. Loss: Train 1.979, Test 2.002; and Acc: Train 0.244, Test 0.222\n",
-      "2025-01-21 19:18:37 Epoch  2/3 done. Loss: Train 1.915, Test 1.949; and Acc: Train 0.277, Test 0.258\n",
-      "2025-01-21 19:18:38 Epoch  3/3 done. Loss: Train 1.873, Test 1.917; and Acc: Train 0.276, Test 0.259\n"
+      "2025-01-22 09:28:49 Epoch  0/3 done. Loss: Train 2.131, Test 2.135; and Acc: Train 0.118, Test 0.118\n",
+      "2025-01-22 09:28:50 Epoch  1/3 done. Loss: Train 1.952, Test 1.978; and Acc: Train 0.281, Test 0.261\n",
+      "2025-01-22 09:28:51 Epoch  2/3 done. Loss: Train 1.905, Test 1.943; and Acc: Train 0.304, Test 0.275\n",
+      "2025-01-22 09:28:53 Epoch  3/3 done. Loss: Train 1.862, Test 1.904; and Acc: Train 0.321, Test 0.283\n"
      ]
     }
    ],
@@ -356,16 +358,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 7,
    "id": "0aedfcca-843e-4f4c-8062-3e4625161bcc",
    "metadata": {
     "editable": true,
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:18:46.417009Z",
-     "iopub.status.busy": "2025-01-22T00:18:46.416419Z",
-     "iopub.status.idle": "2025-01-22T00:18:46.529320Z",
-     "shell.execute_reply": "2025-01-22T00:18:46.529078Z",
-     "shell.execute_reply.started": "2025-01-22T00:18:46.416962Z"
+     "iopub.execute_input": "2025-01-22T14:28:55.671186Z",
+     "iopub.status.busy": "2025-01-22T14:28:55.670403Z",
+     "iopub.status.idle": "2025-01-22T14:28:55.789941Z",
+     "shell.execute_reply": "2025-01-22T14:28:55.789679Z",
+     "shell.execute_reply.started": "2025-01-22T14:28:55.671131Z"
     },
     "slideshow": {
      "slide_type": ""
@@ -377,7 +379,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2025-01-21 19:18:46 Predictions: tensor([0, 0, 0, 0, 0, 0, 0], device='mps:0')\n"
+      "2025-01-22 09:28:55 Predictions: tensor([0, 0, 0, 0, 0, 0, 0], device='mps:0')\n"
      ]
     }
    ],
@@ -427,7 +429,11 @@
     "acc 0.954, energy 0.736 Wh, emissions 0.272 gco2eq\n",
     "\n",
     "[bert-base some hp tuning](https://huggingface.co/datasets/frugal-ai-challenge/public-leaderboard-text/blob/main/submissions/Nonnormalizable_20250120_231350.json):\\\n",
-    "acc 0.707, energy 0.803 Wh, emissions 0.296 gco2eq\n"
+    "acc 0.707, energy 0.803 Wh, emissions 0.296 gco2eq\n",
+    "\n",
+    "bert-tiny, Nvidia 1xL40S:\n",
+    "\n",
+    "bert-tiny, "
    ]
   },
   {
@@ -445,15 +451,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 9,
    "id": "37794952-703c-466c-9d26-ee6cb2834246",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:19:05.789872Z",
-     "iopub.status.busy": "2025-01-22T00:19:05.789108Z",
-     "iopub.status.idle": "2025-01-22T00:19:05.796074Z",
-     "shell.execute_reply": "2025-01-22T00:19:05.794974Z",
-     "shell.execute_reply.started": "2025-01-22T00:19:05.789815Z"
+     "iopub.execute_input": "2025-01-22T14:29:24.691783Z",
+     "iopub.status.busy": "2025-01-22T14:29:24.691195Z",
+     "iopub.status.idle": "2025-01-22T14:29:24.696800Z",
+     "shell.execute_reply": "2025-01-22T14:29:24.695895Z",
+     "shell.execute_reply.started": "2025-01-22T14:29:24.691745Z"
     }
    },
    "outputs": [],
@@ -468,15 +474,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 10,
    "id": "28354e8c-886a-4523-8968-8c688c13f6a3",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:19:06.183379Z",
-     "iopub.status.busy": "2025-01-22T00:19:06.182544Z",
-     "iopub.status.idle": "2025-01-22T00:21:02.201321Z",
-     "shell.execute_reply": "2025-01-22T00:21:02.201016Z",
-     "shell.execute_reply.started": "2025-01-22T00:19:06.183320Z"
+     "iopub.execute_input": "2025-01-22T14:29:25.202258Z",
+     "iopub.status.busy": "2025-01-22T14:29:25.201292Z",
+     "iopub.status.idle": "2025-01-22T14:31:22.271954Z",
+     "shell.execute_reply": "2025-01-22T14:31:22.271647Z",
+     "shell.execute_reply.started": "2025-01-22T14:29:25.202215Z"
     }
    },
    "outputs": [
@@ -484,22 +490,22 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2025-01-21 19:19:11 Epoch  0/15 done. Loss: Train 2.055, Test 2.058; and Acc: Train 0.189, Test 0.191\n",
-      "2025-01-21 19:19:19 Epoch  1/15 done. Loss: Train 1.772, Test 1.805; and Acc: Train 0.354, Test 0.321\n",
-      "2025-01-21 19:19:26 Epoch  2/15 done. Loss: Train 1.530, Test 1.578; and Acc: Train 0.468, Test 0.446\n",
-      "2025-01-21 19:19:33 Epoch  3/15 done. Loss: Train 1.373, Test 1.437; and Acc: Train 0.518, Test 0.500\n",
-      "2025-01-21 19:19:41 Epoch  4/15 done. Loss: Train 1.254, Test 1.353; and Acc: Train 0.572, Test 0.541\n",
-      "2025-01-21 19:19:48 Epoch  5/15 done. Loss: Train 1.159, Test 1.289; and Acc: Train 0.597, Test 0.568\n",
-      "2025-01-21 19:19:55 Epoch  6/15 done. Loss: Train 1.068, Test 1.241; and Acc: Train 0.634, Test 0.567\n",
-      "2025-01-21 19:20:03 Epoch  7/15 done. Loss: Train 0.988, Test 1.199; and Acc: Train 0.668, Test 0.589\n",
-      "2025-01-21 19:20:10 Epoch  8/15 done. Loss: Train 0.911, Test 1.176; and Acc: Train 0.700, Test 0.587\n",
-      "2025-01-21 19:20:18 Epoch  9/15 done. Loss: Train 0.858, Test 1.169; and Acc: Train 0.721, Test 0.587\n",
-      "2025-01-21 19:20:25 Epoch 10/15 done. Loss: Train 0.782, Test 1.151; and Acc: Train 0.747, Test 0.599\n",
-      "2025-01-21 19:20:32 Epoch 11/15 done. Loss: Train 0.717, Test 1.143; and Acc: Train 0.771, Test 0.604\n",
-      "2025-01-21 19:20:40 Epoch 12/15 done. Loss: Train 0.657, Test 1.135; and Acc: Train 0.794, Test 0.610\n",
-      "2025-01-21 19:20:47 Epoch 13/15 done. Loss: Train 0.612, Test 1.147; and Acc: Train 0.819, Test 0.597\n",
-      "2025-01-21 19:20:54 Epoch 14/15 done. Loss: Train 0.553, Test 1.152; and Acc: Train 0.835, Test 0.599\n",
-      "2025-01-21 19:21:02 Epoch 15/15 done. Loss: Train 0.509, Test 1.166; and Acc: Train 0.857, Test 0.597\n"
+      "2025-01-22 09:29:31 Epoch  0/15 done. Loss: Train 2.104, Test 2.111; and Acc: Train 0.114, Test 0.097\n",
+      "2025-01-22 09:29:38 Epoch  1/15 done. Loss: Train 1.778, Test 1.814; and Acc: Train 0.353, Test 0.329\n",
+      "2025-01-22 09:29:45 Epoch  2/15 done. Loss: Train 1.555, Test 1.605; and Acc: Train 0.443, Test 0.422\n",
+      "2025-01-22 09:29:53 Epoch  3/15 done. Loss: Train 1.388, Test 1.451; and Acc: Train 0.519, Test 0.491\n",
+      "2025-01-22 09:30:00 Epoch  4/15 done. Loss: Train 1.274, Test 1.362; and Acc: Train 0.555, Test 0.523\n",
+      "2025-01-22 09:30:07 Epoch  5/15 done. Loss: Train 1.179, Test 1.300; and Acc: Train 0.588, Test 0.540\n",
+      "2025-01-22 09:30:15 Epoch  6/15 done. Loss: Train 1.097, Test 1.259; and Acc: Train 0.632, Test 0.550\n",
+      "2025-01-22 09:30:22 Epoch  7/15 done. Loss: Train 1.026, Test 1.225; and Acc: Train 0.659, Test 0.567\n",
+      "2025-01-22 09:30:30 Epoch  8/15 done. Loss: Train 0.947, Test 1.196; and Acc: Train 0.683, Test 0.580\n",
+      "2025-01-22 09:30:37 Epoch  9/15 done. Loss: Train 0.879, Test 1.176; and Acc: Train 0.717, Test 0.586\n",
+      "2025-01-22 09:30:44 Epoch 10/15 done. Loss: Train 0.817, Test 1.155; and Acc: Train 0.735, Test 0.600\n",
+      "2025-01-22 09:30:52 Epoch 11/15 done. Loss: Train 0.757, Test 1.148; and Acc: Train 0.763, Test 0.599\n",
+      "2025-01-22 09:30:59 Epoch 12/15 done. Loss: Train 0.700, Test 1.139; and Acc: Train 0.786, Test 0.603\n",
+      "2025-01-22 09:31:07 Epoch 13/15 done. Loss: Train 0.636, Test 1.137; and Acc: Train 0.806, Test 0.599\n",
+      "2025-01-22 09:31:14 Epoch 14/15 done. Loss: Train 0.582, Test 1.128; and Acc: Train 0.823, Test 0.604\n",
+      "2025-01-22 09:31:22 Epoch 15/15 done. Loss: Train 0.535, Test 1.134; and Acc: Train 0.837, Test 0.618\n"
      ]
     }
    ],
@@ -520,235 +526,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 12,
    "id": "ec2516f9-79f2-4ae1-ab9a-9a51a7a50587",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:23:23.018234Z",
-     "iopub.status.busy": "2025-01-22T00:23:23.017592Z",
-     "iopub.status.idle": "2025-01-22T00:23:23.049365Z",
-     "shell.execute_reply": "2025-01-22T00:23:23.048870Z",
-     "shell.execute_reply.started": "2025-01-22T00:23:23.018186Z"
+     "iopub.execute_input": "2025-01-22T14:31:42.946851Z",
+     "iopub.status.busy": "2025-01-22T14:31:42.946191Z",
+     "iopub.status.idle": "2025-01-22T14:31:42.970151Z",
+     "shell.execute_reply": "2025-01-22T14:31:42.969731Z",
+     "shell.execute_reply.started": "2025-01-22T14:31:42.946804Z"
     },
     "scrolled": true
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "---\n",
-      "base_model: google/bert_uncased_L-2_H-128_A-2\n",
-      "datasets:\n",
-      "- QuotaClimat/frugalaichallenge-text-train\n",
-      "language:\n",
-      "- en\n",
-      "license: apache-2.0\n",
-      "model_name: frugal-ai-text-bert-tiny\n",
-      "pipeline_tag: text-classification\n",
-      "tags:\n",
-      "- model_hub_mixin\n",
-      "- pytorch_model_hub_mixin\n",
-      "- climate\n",
-      "---\n",
-      "\n",
-      "# Model Card for Model ID\n",
-      "\n",
-      "<!-- Provide a quick summary of what the model is/does. -->\n",
-      "\n",
-      "Classify text into 8 categories of climate misinformation.\n",
-      "\n",
-      "## Model Details\n",
-      "\n",
-      "### Model Description\n",
-      "\n",
-      "<!-- Provide a longer summary of what this model is. -->\n",
-      "\n",
-      "Fine trained BERT for classifying climate information as part of the Frugal AI Challenge, for submission to https://huggingface.co/frugal-ai-challenge and scoring on accuracy and efficiency. Trainied on only the non-evaluation 80% of the data, so it's (non-cheating) score will be lower.\n",
-      "\n",
-      "- **Developed by:** Andre Bach\n",
-      "- **Funded by [optional]:** N/A\n",
-      "- **Shared by [optional]:** Andre Bach\n",
-      "- **Model type:** Text classification\n",
-      "- **Language(s) (NLP):** ['en']\n",
-      "- **License:** apache-2.0\n",
-      "- **Finetuned from model [optional]:** google/bert_uncased_L-2_H-128_A-2\n",
-      "\n",
-      "### Model Sources [optional]\n",
-      "\n",
-      "<!-- Provide the basic links for the model. -->\n",
-      "\n",
-      "- **Repository:** frugal-ai-text-bert-tiny\n",
-      "- **Paper [optional]:** [More Information Needed]\n",
-      "- **Demo [optional]:** [More Information Needed]\n",
-      "\n",
-      "## Uses\n",
-      "\n",
-      "<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->\n",
-      "\n",
-      "### Direct Use\n",
-      "\n",
-      "<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "### Downstream Use [optional]\n",
-      "\n",
-      "<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "### Out-of-Scope Use\n",
-      "\n",
-      "<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Bias, Risks, and Limitations\n",
-      "\n",
-      "<!-- This section is meant to convey both technical and sociotechnical limitations. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "### Recommendations\n",
-      "\n",
-      "<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->\n",
-      "\n",
-      "Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.\n",
-      "\n",
-      "## How to Get Started with the Model\n",
-      "\n",
-      "Use the code below to get started with the model.\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Training Details\n",
-      "\n",
-      "### Training Data\n",
-      "\n",
-      "<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "### Training Procedure\n",
-      "\n",
-      "<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->\n",
-      "\n",
-      "#### Preprocessing [optional]\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "\n",
-      "#### Training Hyperparameters\n",
-      "\n",
-      "- **Training regime:** {'max_dataset_size': 'full', 'bert_variety': 'google/bert_uncased_L-2_H-128_A-2', 'max_length': 256, 'num_epochs': 15, 'batch_size': 16} <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->\n",
-      "\n",
-      "#### Speeds, Sizes, Times [optional]\n",
-      "\n",
-      "<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Evaluation\n",
-      "\n",
-      "<!-- This section describes the evaluation protocols and provides the results. -->\n",
-      "\n",
-      "### Testing Data, Factors & Metrics\n",
-      "\n",
-      "#### Testing Data\n",
-      "\n",
-      "<!-- This should link to a Dataset Card if possible. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "#### Factors\n",
-      "\n",
-      "<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "#### Metrics\n",
-      "\n",
-      "<!-- These are the evaluation metrics being used, ideally with a description of why. -->\n",
-      "\n",
-      "{'train_loss': 0.5085738757594687, 'train_acc': 0.8565270935960592, 'test_loss': 1.1659069603139705, 'test_acc': 0.5972108285479901}\n",
-      "\n",
-      "### Results\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "#### Summary\n",
-      "\n",
-      "\n",
-      "\n",
-      "## Model Examination [optional]\n",
-      "\n",
-      "<!-- Relevant interpretability work for the model goes here -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Environmental Impact\n",
-      "\n",
-      "<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->\n",
-      "\n",
-      "Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).\n",
-      "\n",
-      "- **Hardware Type:** [More Information Needed]\n",
-      "- **Hours used:** [More Information Needed]\n",
-      "- **Cloud Provider:** [More Information Needed]\n",
-      "- **Compute Region:** [More Information Needed]\n",
-      "- **Carbon Emitted:** [More Information Needed]\n",
-      "\n",
-      "## Technical Specifications [optional]\n",
-      "\n",
-      "### Model Architecture and Objective\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "### Compute Infrastructure\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "#### Hardware\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "#### Software\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Citation [optional]\n",
-      "\n",
-      "<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->\n",
-      "\n",
-      "**BibTeX:**\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "**APA:**\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Glossary [optional]\n",
-      "\n",
-      "<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## More Information [optional]\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Model Card Authors [optional]\n",
-      "\n",
-      "[More Information Needed]\n",
-      "\n",
-      "## Model Card Contact\n",
-      "\n",
-      "[More Information Needed]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "model_and_repo_name = \"frugal-ai-text-bert-tiny\"\n",
     "card_data = ModelCardData(\n",
@@ -773,20 +563,20 @@
     "    testing_metrics=testing_metrics,\n",
     ")\n",
     "# print(card_data.to_yaml())\n",
-    "print(card)"
+    "# print(card)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 13,
    "id": "29d3bbf9-ab2a-48e2-a550-e16da5025720",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:23:51.131078Z",
-     "iopub.status.busy": "2025-01-22T00:23:51.130578Z",
-     "iopub.status.idle": "2025-01-22T00:23:51.135440Z",
-     "shell.execute_reply": "2025-01-22T00:23:51.134263Z",
-     "shell.execute_reply.started": "2025-01-22T00:23:51.131042Z"
+     "iopub.execute_input": "2025-01-22T14:31:44.266203Z",
+     "iopub.status.busy": "2025-01-22T14:31:44.265638Z",
+     "iopub.status.idle": "2025-01-22T14:31:44.271280Z",
+     "shell.execute_reply": "2025-01-22T14:31:44.270441Z",
+     "shell.execute_reply.started": "2025-01-22T14:31:44.266162Z"
     }
    },
    "outputs": [],
@@ -797,15 +587,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 14,
    "id": "e3b099c6-6b98-473b-8797-5032213b9fcb",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:24:18.616547Z",
-     "iopub.status.busy": "2025-01-22T00:24:18.615990Z",
-     "iopub.status.idle": "2025-01-22T00:24:18.669435Z",
-     "shell.execute_reply": "2025-01-22T00:24:18.669063Z",
-     "shell.execute_reply.started": "2025-01-22T00:24:18.616509Z"
+     "iopub.execute_input": "2025-01-22T14:31:45.670794Z",
+     "iopub.status.busy": "2025-01-22T14:31:45.670345Z",
+     "iopub.status.idle": "2025-01-22T14:31:45.731173Z",
+     "shell.execute_reply": "2025-01-22T14:31:45.730818Z",
+     "shell.execute_reply.started": "2025-01-22T14:31:45.670769Z"
     }
    },
    "outputs": [
@@ -813,7 +603,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2025-01-21 19:24:18 Predictions: tensor([0, 0, 3, 1, 2, 6, 6], device='mps:0')\n"
+      "2025-01-22 09:31:45 Predictions: tensor([0, 0, 3, 1, 2, 4, 6], device='mps:0')\n"
      ]
     }
    ],
@@ -846,123 +636,47 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 18,
    "id": "befb94b5-88bf-40fc-8b26-cf373d1256e0",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2025-01-22T00:24:41.153062Z",
-     "iopub.status.busy": "2025-01-22T00:24:41.152049Z",
-     "iopub.status.idle": "2025-01-22T00:24:43.436376Z",
-     "shell.execute_reply": "2025-01-22T00:24:43.435250Z",
-     "shell.execute_reply.started": "2025-01-22T00:24:41.153018Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ef4fd0b071034f7d9cba6aa0ab69d148",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "model.safetensors:   0%|          | 0.00/17.6M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/plain": [
-       "CommitInfo(commit_url='https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny/commit/512fbc46e1cfc7456f4e9f2331a30d66a9052d88', commit_message='Push model using huggingface_hub.', commit_description='', oid='512fbc46e1cfc7456f4e9f2331a30d66a9052d88', pr_url=None, repo_url=RepoUrl('https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny', endpoint='https://huggingface.co', repo_type='model', repo_id='Nonnormalizable/frugal-ai-text-bert-tiny'), pr_revision=None, pr_num=None)"
-      ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "model_final.push_to_hub(model_and_repo_name)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "id": "251ef9ee-8ba3-495f-8fe6-a93aa63168ce",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-01-22T00:24:48.887758Z",
-     "iopub.status.busy": "2025-01-22T00:24:48.887178Z",
-     "iopub.status.idle": "2025-01-22T00:24:49.581460Z",
-     "shell.execute_reply": "2025-01-22T00:24:49.580127Z",
-     "shell.execute_reply.started": "2025-01-22T00:24:48.887716Z"
+     "iopub.execute_input": "2025-01-22T14:37:57.412327Z",
+     "iopub.status.busy": "2025-01-22T14:37:57.411779Z",
+     "iopub.status.idle": "2025-01-22T14:37:59.349630Z",
+     "shell.execute_reply": "2025-01-22T14:37:59.348338Z",
+     "shell.execute_reply.started": "2025-01-22T14:37:57.412288Z"
     }
    },
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f3f6ee50ec314983a492ab7f4f5ef1bc",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "README.md:   0%|          | 0.00/320 [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "No files have been modified since last commit. Skipping to prevent empty commit.\n"
+     ]
     },
     {
      "data": {
       "text/plain": [
-       "CommitInfo(commit_url='https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny/commit/1870eebdb54a6a636d7dd32a5d923abc8d1baaec', commit_message='Upload tokenizer', commit_description='', oid='1870eebdb54a6a636d7dd32a5d923abc8d1baaec', pr_url=None, repo_url=RepoUrl('https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny', endpoint='https://huggingface.co', repo_type='model', repo_id='Nonnormalizable/frugal-ai-text-bert-tiny'), pr_revision=None, pr_num=None)"
+       "CommitInfo(commit_url='https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny/commit/69d445f90562fc738f12cfb37908fccef8925f5c', commit_message='Upload README.md with huggingface_hub', commit_description='', oid='69d445f90562fc738f12cfb37908fccef8925f5c', pr_url=None, repo_url=RepoUrl('https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny', endpoint='https://huggingface.co', repo_type='model', repo_id='Nonnormalizable/frugal-ai-text-bert-tiny'), pr_revision=None, pr_num=None)"
       ]
      },
-     "execution_count": 36,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "tokenizer_final.push_to_hub(model_and_repo_name)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "id": "863d3553-89a6-4188-a8d0-eaa0b6bccb6c",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2025-01-22T00:25:24.402856Z",
-     "iopub.status.busy": "2025-01-22T00:25:24.402275Z",
-     "iopub.status.idle": "2025-01-22T00:25:25.011133Z",
-     "shell.execute_reply": "2025-01-22T00:25:25.009553Z",
-     "shell.execute_reply.started": "2025-01-22T00:25:24.402817Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "CommitInfo(commit_url='https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny/commit/62d658978d97614f10c3d69b6595a0fb6b8a2d4c', commit_message='Upload README.md with huggingface_hub', commit_description='', oid='62d658978d97614f10c3d69b6595a0fb6b8a2d4c', pr_url=None, repo_url=RepoUrl('https://huggingface.co/Nonnormalizable/frugal-ai-text-bert-tiny', endpoint='https://huggingface.co', repo_type='model', repo_id='Nonnormalizable/frugal-ai-text-bert-tiny'), pr_revision=None, pr_num=None)"
-      ]
-     },
-     "execution_count": 38,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "model_final.push_to_hub(model_and_repo_name)\n",
+    "tokenizer_final.push_to_hub(model_and_repo_name)\n",
+    "model_final.config.push_to_hub(model_and_repo_name)\n",
     "card.push_to_hub(f\"Nonnormalizable/{model_and_repo_name}\")"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2c22cc30-7578-4aad-b7db-1ffe4954c46c",
+   "id": "f6df5d6b-2d24-4759-937b-7935ac01dba7",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -989,7 +703,7 @@
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {
     "state": {
-     "05dc5be1c7754da082079d8c8fdd3a2a": {
+     "04362bf5ea1540e69a8ed37243e960fe": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
       "model_name": "HTMLStyleModel",
@@ -999,59 +713,29 @@
        "text_color": null
       }
      },
-     "07fc7cde058940a29aba80b9b1f18247": {
+     "1a82e23ee0b44ec78b0bb2175f2e938a": {
       "model_module": "@jupyter-widgets/base",
       "model_module_version": "2.0.0",
       "model_name": "LayoutModel",
       "state": {}
      },
-     "14a18f1cb1f244b28fa35c504023c27d": {
+     "3058e249f3a24b89a0946db9d46692cd": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
       "model_name": "HTMLModel",
       "state": {
-       "layout": "IPY_MODEL_07fc7cde058940a29aba80b9b1f18247",
-       "style": "IPY_MODEL_05dc5be1c7754da082079d8c8fdd3a2a",
-       "value": "model.safetensors: 100%"
-      }
-     },
-     "1aedcea94f5a43919f4b0dd14eb54ab0": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "FloatProgressModel",
-      "state": {
-       "bar_style": "success",
-       "layout": "IPY_MODEL_3a0167722aae49eb87c0cc1a0b381a7c",
-       "max": 320,
-       "style": "IPY_MODEL_75738a2d58574271b291cf982f86074a",
-       "value": 320
-      }
-     },
-     "350a27df5da248b3b06dbad6b28bc789": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "FloatProgressModel",
-      "state": {
-       "bar_style": "success",
-       "layout": "IPY_MODEL_eaf57ba3273f42d4900ce2ebae398892",
-       "max": 17552376,
-       "style": "IPY_MODEL_aa86a038e70b43368dd5ccb65b653f86",
-       "value": 17552376
+       "layout": "IPY_MODEL_1a82e23ee0b44ec78b0bb2175f2e938a",
+       "style": "IPY_MODEL_04362bf5ea1540e69a8ed37243e960fe",
+       "value": " 17.6M/17.6M [00:00&lt;00:00, 30.6MB/s]"
       }
      },
-     "3a0167722aae49eb87c0cc1a0b381a7c": {
+     "4bcb44aa9960417da7c3e374f5015413": {
       "model_module": "@jupyter-widgets/base",
       "model_module_version": "2.0.0",
       "model_name": "LayoutModel",
       "state": {}
      },
-     "40d60079070e4bd2b81fbcfd695cd759": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "605845a520ee426fa2330ded19d8a617": {
+     "572a4d1b74044da7a90c58c311a87eff": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
       "model_name": "HTMLStyleModel",
@@ -1061,57 +745,19 @@
        "text_color": null
       }
      },
-     "7402f6bafb5f485e9f172cdf017572c7": {
+     "575da4c5a0b147989fc3444c95d5483b": {
       "model_module": "@jupyter-widgets/base",
       "model_module_version": "2.0.0",
       "model_name": "LayoutModel",
       "state": {}
      },
-     "75738a2d58574271b291cf982f86074a": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "ProgressStyleModel",
-      "state": {
-       "description_width": ""
-      }
-     },
-     "7a56b64874594d50bb09ee06bb656e54": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "HTMLStyleModel",
-      "state": {
-       "description_width": "",
-       "font_size": null,
-       "text_color": null
-      }
-     },
-     "7bc93085c8f54642b6005f0f701772fa": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "HTMLStyleModel",
-      "state": {
-       "description_width": "",
-       "font_size": null,
-       "text_color": null
-      }
-     },
-     "8bdfbdb11197418d894a54ec6d487906": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "HTMLModel",
-      "state": {
-       "layout": "IPY_MODEL_ae882ab226794053a4f906ac3b5e49b9",
-       "style": "IPY_MODEL_605845a520ee426fa2330ded19d8a617",
-       "value": " 17.6M/17.6M [00:00&lt;00:00, 27.8MB/s]"
-      }
-     },
-     "9a5aac888e72447fa2f379cd3e25a11c": {
+     "8f403fa494c246c9af5ee00397ac6cf5": {
       "model_module": "@jupyter-widgets/base",
       "model_module_version": "2.0.0",
       "model_name": "LayoutModel",
       "state": {}
      },
-     "aa86a038e70b43368dd5ccb65b653f86": {
+     "916778013b8d48d9acddd42e8b874c22": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
       "model_name": "ProgressStyleModel",
@@ -1119,68 +765,39 @@
        "description_width": ""
       }
      },
-     "acfe7063ca0f4ea6acd6f308071f4418": {
+     "9c74511b86c240a9afb83e5dcd16b03b": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
-      "model_name": "HTMLModel",
+      "model_name": "FloatProgressModel",
       "state": {
-       "layout": "IPY_MODEL_9a5aac888e72447fa2f379cd3e25a11c",
-       "style": "IPY_MODEL_7bc93085c8f54642b6005f0f701772fa",
-       "value": "README.md: 100%"
+       "bar_style": "success",
+       "layout": "IPY_MODEL_575da4c5a0b147989fc3444c95d5483b",
+       "max": 17552376,
+       "style": "IPY_MODEL_916778013b8d48d9acddd42e8b874c22",
+       "value": 17552376
       }
      },
-     "ae882ab226794053a4f906ac3b5e49b9": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "d84082e3eb2e4ababf340e8262c5489c": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "eaf57ba3273f42d4900ce2ebae398892": {
-      "model_module": "@jupyter-widgets/base",
-      "model_module_version": "2.0.0",
-      "model_name": "LayoutModel",
-      "state": {}
-     },
-     "ef4fd0b071034f7d9cba6aa0ab69d148": {
+     "9fb53962769d48e6a7ee640072ff1908": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
-      "model_name": "HBoxModel",
+      "model_name": "HTMLModel",
       "state": {
-       "children": [
-        "IPY_MODEL_14a18f1cb1f244b28fa35c504023c27d",
-        "IPY_MODEL_350a27df5da248b3b06dbad6b28bc789",
-        "IPY_MODEL_8bdfbdb11197418d894a54ec6d487906"
-       ],
-       "layout": "IPY_MODEL_7402f6bafb5f485e9f172cdf017572c7"
+       "layout": "IPY_MODEL_4bcb44aa9960417da7c3e374f5015413",
+       "style": "IPY_MODEL_572a4d1b74044da7a90c58c311a87eff",
+       "value": "model.safetensors: 100%"
       }
      },
-     "f3f6ee50ec314983a492ab7f4f5ef1bc": {
+     "eb84b40edbab4e9d91fd6283b144492f": {
       "model_module": "@jupyter-widgets/controls",
       "model_module_version": "2.0.0",
       "model_name": "HBoxModel",
       "state": {
        "children": [
-        "IPY_MODEL_acfe7063ca0f4ea6acd6f308071f4418",
-        "IPY_MODEL_1aedcea94f5a43919f4b0dd14eb54ab0",
-        "IPY_MODEL_f8f939982d7542969718ad06c692c488"
+        "IPY_MODEL_9fb53962769d48e6a7ee640072ff1908",
+        "IPY_MODEL_9c74511b86c240a9afb83e5dcd16b03b",
+        "IPY_MODEL_3058e249f3a24b89a0946db9d46692cd"
        ],
-       "layout": "IPY_MODEL_d84082e3eb2e4ababf340e8262c5489c"
-      }
-     },
-     "f8f939982d7542969718ad06c692c488": {
-      "model_module": "@jupyter-widgets/controls",
-      "model_module_version": "2.0.0",
-      "model_name": "HTMLModel",
-      "state": {
-       "layout": "IPY_MODEL_40d60079070e4bd2b81fbcfd695cd759",
-       "style": "IPY_MODEL_7a56b64874594d50bb09ee06bb656e54",
-       "value": " 320/320 [00:00&lt;00:00, 25.4kB/s]"
+       "layout": "IPY_MODEL_8f403fa494c246c9af5ee00397ac6cf5"
       }
      }
     },