Step | \n", - "Training Loss | \n", - "Validation Loss | \n", - "
---|---|---|
50 | \n", - "10.368600 | \n", - "9.695271 | \n", - "
100 | \n", - "9.660800 | \n", - "9.591634 | \n", - "
150 | \n", - "9.634500 | \n", - "9.585637 | \n", - "
200 | \n", - "9.623000 | \n", - "9.583360 | \n", - "
250 | \n", - "9.613100 | \n", - "9.582972 | \n", - "
"
- ]
- },
- "metadata": {}
- },
- {
- "output_type": "execute_result",
- "data": {
- "text/plain": [
- "TrainOutput(global_step=266, training_loss=9.771246601764421, metrics={'train_runtime': 96.2756, 'train_samples_per_second': 88.164, 'train_steps_per_second': 2.763, 'total_flos': 279368589901824.0, 'train_loss': 9.771246601764421, 'epoch': 1.0})"
- ]
- },
- "metadata": {},
- "execution_count": 5
- }
- ]
- },
- {
- "cell_type": "code",
- "source": [
- "trainer.evaluate()"
- ],
- "metadata": {
- "id": "grVjJRyP8Cvo",
- "colab": {
- "base_uri": "https://localhost:8080/",
- "height": 124
- },
- "outputId": "14d33957-ccc6-4fd6-db88-6aa977c83cf9"
- },
- "execution_count": 6,
- "outputs": [
- {
- "output_type": "display_data",
- "data": {
- "text/plain": [
- "