updating prompt to include team name and abbreviations

test_pretrained.ipynb

@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -26,9 +26,9 @@
       "Total dataset examples: 1044\n",
       "\n",
       "\n",
-      "List the full names of all teams founded in the 1980s.\n",
-      "SELECT full_name FROM team WHERE year_founded BETWEEN 1980 AND 1989;\n",
-      "Dallas Mavericks, Miami Heat, Minnesota Timberwolves, Orlando Magic, Charlotte Hornets\n"
+      "What is the highest combined pts in any game involving the Miami Heat?\n",
+      "SELECT MAX(pts_home + pts_away) FROM game WHERE team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat';\n",
+      "290.0\n"
      ]
     }
    ],
@@ -56,9 +56,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
     "import torch\n",
@@ -80,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -189,6 +198,44 @@
     ");\n",
     "\n",
     "\n",
+    "Team Name Information\n",
+    "In the plaintext user questions, only the full team names will be used, but in the queries you may use the full team names or the abbreviations. \n",
+    "The full team names can be used with the game table, while the abbreviations should be used with the other_stats table.\n",
+    "Notice they are separated by the | character in the following list:\n",
+    "\n",
+    "Atlanta Hawks|ATL\n",
+    "Boston Celtics|BOS\n",
+    "Cleveland Cavaliers|CLE\n",
+    "New Orleans Pelicans|NOP\n",
+    "Chicago Bulls|CHI\n",
+    "Dallas Mavericks|DAL\n",
+    "Denver Nuggets|DEN\n",
+    "Golden State Warriors|GSW\n",
+    "Houston Rockets|HOU\n",
+    "Los Angeles Clippers|LAC\n",
+    "Los Angeles Lakers|LAL\n",
+    "Miami Heat|MIA\n",
+    "Milwaukee Bucks|MIL\n",
+    "Minnesota Timberwolves|MIN\n",
+    "Brooklyn Nets|BKN\n",
+    "New York Knicks|NYK\n",
+    "Orlando Magic|ORL\n",
+    "Indiana Pacers|IND\n",
+    "Philadelphia 76ers|PHI\n",
+    "Phoenix Suns|PHX\n",
+    "Portland Trail Blazers|POR\n",
+    "Sacramento Kings|SAC\n",
+    "San Antonio Spurs|SAS\n",
+    "Oklahoma City Thunder|OKC\n",
+    "Toronto Raptors|TOR\n",
+    "Utah Jazz|UTA\n",
+    "Memphis Grizzlies|MEM\n",
+    "Washington Wizards|WAS\n",
+    "Detroit Pistons|DET\n",
+    "Charlotte Hornets|CHA\n",
+    "\n",
+    "\n",
+    "\n",
     "Query Guidelines\n",
     "Use team_name_home and team_name_away to match teams.\n",
     "\n",
@@ -238,7 +285,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -248,7 +295,10 @@
       "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\generation\\configuration_utils.py:634: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
       "  warnings.warn(\n",
       "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
-      "Setting `pad_token_id` to `eos_token_id`:32021 for open-end generation.\n"
+      "Setting `pad_token_id` to `eos_token_id`:32021 for open-end generation.\n",
+      "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
+      "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\integrations\\sdpa_attention.py:53: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\\actions-runner\\_work\\pytorch\\pytorch\\builder\\windows\\pytorch\\aten\\src\\ATen\\native\\transformers\\cuda\\sdp_utils.cpp:555.)\n",
+      "  attn_output = torch.nn.functional.scaled_dot_product_attention(\n"
      ]
     },
     {
@@ -256,9 +306,9 @@
      "output_type": "stream",
      "text": [
       "SQLite:\n",
-      "SELECT full_name \n",
-      "FROM team \n",
-      "WHERE year_founded BETWEEN 1980 AND 1989;\n",
+      "SELECT MAX(pts_home + pts_away) \n",
+      "FROM game \n",
+      "WHERE (team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat');\n",
       "\n"
      ]
     }
@@ -283,7 +333,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -291,11 +341,7 @@
      "output_type": "stream",
      "text": [
       "cleaned\n",
-      "('Dallas Mavericks',)\n",
-      "('Miami Heat',)\n",
-      "('Minnesota Timberwolves',)\n",
-      "('Orlando Magic',)\n",
-      "('Charlotte Hornets',)\n"
+      "(290.0,)\n"
      ]
     }
    ],
@@ -329,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 76,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -344,18 +390,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "How many games did the Indiana Pacers win at home with more than 15 fast break points in 1996?\n",
-      "SELECT COUNT(*) as wins  FROM other_stats os  JOIN game g ON os.game_id = g.game_id  WHERE g.team_name_home = 'Indiana Pacers' AND g.wl_home = 'W' AND os.pts_fb_home > 15 AND g.season_id = '21996';\n",
-      "7.0\n",
+      "What is the average number of reb in away games by the Detroit Pistons?\n",
+      "SELECT AVG(reb_away) FROM game WHERE team_name_away = 'Detroit Pistons';\n",
+      "42.10948081264108\n",
       "SQLite:\n",
-      "SELECT COUNT(*) \n",
+      "SELECT AVG(reb_away) \n",
       "FROM game \n",
-      "WHERE wl_home = 'W' \n",
-      "AND season_id = '2196' \n",
-      "AND pts_fb_home > 15;\n",
+      "WHERE team_name_away = 'Detroit Pistons';\n",
       "\n",
-      "SQL matched? False\n",
-      "Result matched? False\n"
+      "[(42.10948081264108,)]\n",
+      "SQL matched? True\n",
+      "Result matched? True\n"
      ]
     }
    ],