{ "metadata": { "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python", "version": "3.10.14", "mimetype": "text/x-python", "codemirror_mode": { "name": "ipython", "version": 3 }, "pygments_lexer": "ipython3", "nbconvert_exporter": "python", "file_extension": ".py" }, "kaggle": { "accelerator": "none", "dataSources": [], "isInternetEnabled": true, "language": "python", "sourceType": "notebook", "isGpuEnabled": false }, "colab": { "provenance": [], "gpuType": "T4", "include_colab_link": true }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "b00fe124433743228b82a7888f7c5ddb": { "model_module": "@jupyter-widgets/controls", "model_name": "VBoxModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "VBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "VBoxView", "box_style": "", "children": [ "IPY_MODEL_37ad83404faa4e59bcfa43484840676c", "IPY_MODEL_9d37eb7f8d5e477aba536b619a2c52bf", "IPY_MODEL_5a49ff98fcf14b2ab80c863bfcaaa930", "IPY_MODEL_9b2e5ce3d9c746608b81918247794ff1" ], "layout": "IPY_MODEL_b092e73a983a4f0cb94cdb464dca593d" } }, "d8e61bb27d494dc584f7bda4d58c3430": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_94c57c86d5c04955a3e85a5c0bbb0910", "placeholder": "", "style": "IPY_MODEL_074fcc794e364584acd80c7267c4d672", "value": "
/content/wandb/run-20240927_093400-ni8m6pjv
"
],
"text/plain": [
"Step | \n", "Training Loss | \n", "Validation Loss | \n", "Bleu | \n", "Gen Len | \n", "
---|---|---|---|---|
500 | \n", "21.636200 | \n", "9.776628 | \n", "0.000000 | \n", "2.001900 | \n", "
1000 | \n", "10.103400 | \n", "6.105016 | \n", "0.000000 | \n", "2.077900 | \n", "
1500 | \n", "6.830800 | \n", "5.081259 | \n", "0.000000 | \n", "3.811600 | \n", "
2000 | \n", "6.003100 | \n", "4.702793 | \n", "0.000000 | \n", "4.237300 | \n", "
\n", "
Step | \n", "Training Loss | \n", "Validation Loss | \n", "Bleu | \n", "Gen Len | \n", "
---|---|---|---|---|
500 | \n", "21.636200 | \n", "9.776628 | \n", "0.000000 | \n", "2.001900 | \n", "
1000 | \n", "10.103400 | \n", "6.105016 | \n", "0.000000 | \n", "2.077900 | \n", "
1500 | \n", "6.830800 | \n", "5.081259 | \n", "0.000000 | \n", "3.811600 | \n", "
2000 | \n", "6.003100 | \n", "4.702793 | \n", "0.000000 | \n", "4.237300 | \n", "
2500 | \n", "5.690200 | \n", "4.469123 | \n", "0.000000 | \n", "4.700000 | \n", "
3000 | \n", "5.443100 | \n", "4.274406 | \n", "0.000000 | \n", "4.808300 | \n", "
3500 | \n", "5.265300 | \n", "4.121417 | \n", "0.000000 | \n", "4.749400 | \n", "
4000 | \n", "5.128500 | \n", "3.989708 | \n", "0.000000 | \n", "4.782300 | \n", "
4500 | \n", "5.007200 | \n", "3.885391 | \n", "0.000000 | \n", "4.805100 | \n", "
5000 | \n", "4.909600 | \n", "3.787640 | \n", "0.000000 | \n", "4.874800 | \n", "
5500 | \n", "4.836000 | \n", "3.715750 | \n", "0.000000 | \n", "4.855500 | \n", "
6000 | \n", "4.733000 | \n", "3.640963 | \n", "0.000000 | \n", "4.962000 | \n", "
6500 | \n", "4.673500 | \n", "3.587330 | \n", "0.000000 | \n", "5.011600 | \n", "
7000 | \n", "4.623800 | \n", "3.531883 | \n", "0.000000 | \n", "5.068300 | \n", "
7500 | \n", "4.567400 | \n", "3.481622 | \n", "0.000000 | \n", "5.108500 | \n", "
8000 | \n", "4.523200 | \n", "3.445404 | \n", "0.000000 | \n", "5.092700 | \n", "
8500 | \n", "4.464000 | \n", "3.413630 | \n", "0.000000 | \n", "5.132700 | \n", "
\n", "