"
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [ 2/6066 : < :, Epoch 0.00/3]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Step | \n",
+ " Training Loss | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [ 2/12132 : < :, Epoch 0.00/3]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Step | \n",
+ " Training Loss | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ],
+ "text/html": [
+ "\n",
+ " \n",
+ " \n",
+ "
\n",
+ " [24261/24261 4:52:22, Epoch 3/3]\n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " Step | \n",
+ " Training Loss | \n",
+ "
\n",
+ " \n",
+ " \n",
+ " \n",
+ " 500 | \n",
+ " 3.320700 | \n",
+ "
\n",
+ " \n",
+ " 1000 | \n",
+ " 3.173000 | \n",
+ "
\n",
+ " \n",
+ " 1500 | \n",
+ " 3.142500 | \n",
+ "
\n",
+ " \n",
+ " 2000 | \n",
+ " 3.070900 | \n",
+ "
\n",
+ " \n",
+ " 2500 | \n",
+ " 3.083600 | \n",
+ "
\n",
+ " \n",
+ " 3000 | \n",
+ " 3.057900 | \n",
+ "
\n",
+ " \n",
+ " 3500 | \n",
+ " 3.005900 | \n",
+ "
\n",
+ " \n",
+ " 4000 | \n",
+ " 3.016900 | \n",
+ "
\n",
+ " \n",
+ " 4500 | \n",
+ " 3.012300 | \n",
+ "
\n",
+ " \n",
+ " 5000 | \n",
+ " 2.957100 | \n",
+ "
\n",
+ " \n",
+ " 5500 | \n",
+ " 2.958700 | \n",
+ "
\n",
+ " \n",
+ " 6000 | \n",
+ " 2.976900 | \n",
+ "
\n",
+ " \n",
+ " 6500 | \n",
+ " 2.959700 | \n",
+ "
\n",
+ " \n",
+ " 7000 | \n",
+ " 2.975100 | \n",
+ "
\n",
+ " \n",
+ " 7500 | \n",
+ " 2.951100 | \n",
+ "
\n",
+ " \n",
+ " 8000 | \n",
+ " 2.945200 | \n",
+ "
\n",
+ " \n",
+ " 8500 | \n",
+ " 2.849600 | \n",
+ "
\n",
+ " \n",
+ " 9000 | \n",
+ " 2.722500 | \n",
+ "
\n",
+ " \n",
+ " 9500 | \n",
+ " 2.854400 | \n",
+ "
\n",
+ " \n",
+ " 10000 | \n",
+ " 2.782700 | \n",
+ "
\n",
+ " \n",
+ " 10500 | \n",
+ " 2.845900 | \n",
+ "
\n",
+ " \n",
+ " 11000 | \n",
+ " 2.803300 | \n",
+ "
\n",
+ " \n",
+ " 11500 | \n",
+ " 2.797800 | \n",
+ "
\n",
+ " \n",
+ " 12000 | \n",
+ " 2.827400 | \n",
+ "
\n",
+ " \n",
+ " 12500 | \n",
+ " 2.757800 | \n",
+ "
\n",
+ " \n",
+ " 13000 | \n",
+ " 2.823600 | \n",
+ "
\n",
+ " \n",
+ " 13500 | \n",
+ " 2.827200 | \n",
+ "
\n",
+ " \n",
+ " 14000 | \n",
+ " 2.832400 | \n",
+ "
\n",
+ " \n",
+ " 14500 | \n",
+ " 2.839800 | \n",
+ "
\n",
+ " \n",
+ " 15000 | \n",
+ " 2.783400 | \n",
+ "
\n",
+ " \n",
+ " 15500 | \n",
+ " 2.774200 | \n",
+ "
\n",
+ " \n",
+ " 16000 | \n",
+ " 2.785500 | \n",
+ "
\n",
+ " \n",
+ " 16500 | \n",
+ " 2.793600 | \n",
+ "
\n",
+ " \n",
+ " 17000 | \n",
+ " 2.801200 | \n",
+ "
\n",
+ " \n",
+ " 17500 | \n",
+ " 2.812800 | \n",
+ "
\n",
+ " \n",
+ " 18000 | \n",
+ " 2.813300 | \n",
+ "
\n",
+ " \n",
+ " 18500 | \n",
+ " 2.804800 | \n",
+ "
\n",
+ " \n",
+ " 19000 | \n",
+ " 2.777800 | \n",
+ "
\n",
+ " \n",
+ " 19500 | \n",
+ " 2.761100 | \n",
+ "
\n",
+ " \n",
+ " 20000 | \n",
+ " 2.832700 | \n",
+ "
\n",
+ " \n",
+ " 20500 | \n",
+ " 2.868300 | \n",
+ "
\n",
+ " \n",
+ " 21000 | \n",
+ " 2.757300 | \n",
+ "
\n",
+ " \n",
+ " 21500 | \n",
+ " 2.763300 | \n",
+ "
\n",
+ " \n",
+ " 22000 | \n",
+ " 2.817900 | \n",
+ "
\n",
+ " \n",
+ " 22500 | \n",
+ " 2.775300 | \n",
+ "
\n",
+ " \n",
+ " 23000 | \n",
+ " 2.796400 | \n",
+ "
\n",
+ " \n",
+ " 23500 | \n",
+ " 2.798700 | \n",
+ "
\n",
+ " \n",
+ " 24000 | \n",
+ " 2.778000 | \n",
+ "
\n",
+ " \n",
+ "
"
+ ]
+ },
+ "metadata": {}
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "TrainOutput(global_step=24261, training_loss=2.8796593968087287, metrics={'train_runtime': 17543.4268, 'train_samples_per_second': 2.766, 'train_steps_per_second': 1.383, 'total_flos': 3.65470024955904e+16, 'train_loss': 2.8796593968087287, 'epoch': 3.0})"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 8
+ }
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# Save the model"
+ ],
+ "metadata": {
+ "id": "mDOXSmts1J-G"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "trainer.model.save_pretrained('se_flan-t5_v2')\n",
+ "tokenizer.save_pretrained('se_flan-t5_v2')"
+ ],
+ "metadata": {
+ "id": "RN9rhtHw1KC9",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "7f939af3-3fc2-406d-cf5c-d1cb558ba61d"
+ },
+ "execution_count": 9,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "('se_flan-t5_v2/tokenizer_config.json',\n",
+ " 'se_flan-t5_v2/special_tokens_map.json',\n",
+ " 'se_flan-t5_v2/tokenizer.json')"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 9
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "!rm -r /content/drive/MyDrive/se; mkdir /content/drive/MyDrive/se\n",
+ "!cp -r se_flan-t5_v2 /content/drive/MyDrive/se"
+ ],
+ "metadata": {
+ "id": "FPUZs3SZPQ4z",
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "outputId": "3dd3dd4f-65df-413c-ba5f-ec64a8244b83"
+ },
+ "execution_count": 10,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "rm: cannot remove '/content/drive/MyDrive/se': No such file or directory\n"
+ ]
+ }
+ ]
+ }
+ ]
+}
\ No newline at end of file