diff --git "a/OO_Fine_Tune.ipynb" "b/OO_Fine_Tune.ipynb"
new file mode 100644--- /dev/null
+++ "b/OO_Fine_Tune.ipynb"
@@ -0,0 +1,19595 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "Ay9HJhbH03Kx",
+ "outputId": "4170bd29-744e-42f9-b9ae-7b3a68a987f3"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Requirement already satisfied: datasets in ./.venv/lib/python3.10/site-packages (2.14.5)\n",
+ "Requirement already satisfied: ipywidgets in ./.venv/lib/python3.10/site-packages (8.1.0)\n",
+ "Requirement already satisfied: transformers[torch] in ./.venv/lib/python3.10/site-packages (4.33.1)\n",
+ "Requirement already satisfied: evaluate in ./.venv/lib/python3.10/site-packages (0.4.0)\n",
+ "Requirement already satisfied: scikit-learn in ./.venv/lib/python3.10/site-packages (1.3.0)\n",
+ "Requirement already satisfied: ray[tune] in ./.venv/lib/python3.10/site-packages (2.6.3)\n",
+ "Requirement already satisfied: wandb in ./.venv/lib/python3.10/site-packages (0.15.10)\n",
+ "Requirement already satisfied: hyperopt in ./.venv/lib/python3.10/site-packages (0.2.7)\n",
+ "Requirement already satisfied: numpy>=1.17 in ./.venv/lib/python3.10/site-packages (from datasets) (1.25.2)\n",
+ "Requirement already satisfied: pyarrow>=8.0.0 in ./.venv/lib/python3.10/site-packages (from datasets) (13.0.0)\n",
+ "Requirement already satisfied: dill<0.3.8,>=0.3.0 in ./.venv/lib/python3.10/site-packages (from datasets) (0.3.7)\n",
+ "Requirement already satisfied: pandas in ./.venv/lib/python3.10/site-packages (from datasets) (2.1.0)\n",
+ "Requirement already satisfied: requests>=2.19.0 in ./.venv/lib/python3.10/site-packages (from datasets) (2.31.0)\n",
+ "Requirement already satisfied: tqdm>=4.62.1 in ./.venv/lib/python3.10/site-packages (from datasets) (4.66.1)\n",
+ "Requirement already satisfied: xxhash in ./.venv/lib/python3.10/site-packages (from datasets) (3.3.0)\n",
+ "Requirement already satisfied: multiprocess in ./.venv/lib/python3.10/site-packages (from datasets) (0.70.15)\n",
+ "Requirement already satisfied: fsspec[http]<2023.9.0,>=2023.1.0 in ./.venv/lib/python3.10/site-packages (from datasets) (2023.6.0)\n",
+ "Requirement already satisfied: aiohttp in ./.venv/lib/python3.10/site-packages (from datasets) (3.8.5)\n",
+ "Requirement already satisfied: huggingface-hub<1.0.0,>=0.14.0 in ./.venv/lib/python3.10/site-packages (from datasets) (0.16.4)\n",
+ "Requirement already satisfied: packaging in ./.venv/lib/python3.10/site-packages (from datasets) (23.1)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in ./.venv/lib/python3.10/site-packages (from datasets) (6.0.1)\n",
+ "Requirement already satisfied: comm>=0.1.3 in ./.venv/lib/python3.10/site-packages (from ipywidgets) (0.1.4)\n",
+ "Requirement already satisfied: ipython>=6.1.0 in ./.venv/lib/python3.10/site-packages (from ipywidgets) (8.15.0)\n",
+ "Requirement already satisfied: traitlets>=4.3.1 in ./.venv/lib/python3.10/site-packages (from ipywidgets) (5.9.0)\n",
+ "Requirement already satisfied: widgetsnbextension~=4.0.7 in ./.venv/lib/python3.10/site-packages (from ipywidgets) (4.0.8)\n",
+ "Requirement already satisfied: jupyterlab-widgets~=3.0.7 in ./.venv/lib/python3.10/site-packages (from ipywidgets) (3.0.8)\n",
+ "Requirement already satisfied: filelock in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (3.12.3)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (2023.8.8)\n",
+ "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (0.13.3)\n",
+ "Requirement already satisfied: safetensors>=0.3.1 in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (0.3.3)\n",
+ "Requirement already satisfied: torch!=1.12.0,>=1.10 in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (2.0.1)\n",
+ "Requirement already satisfied: accelerate>=0.20.3 in ./.venv/lib/python3.10/site-packages (from transformers[torch]) (0.22.0)\n",
+ "Requirement already satisfied: responses<0.19 in ./.venv/lib/python3.10/site-packages (from evaluate) (0.18.0)\n",
+ "Requirement already satisfied: scipy>=1.5.0 in ./.venv/lib/python3.10/site-packages (from scikit-learn) (1.11.2)\n",
+ "Requirement already satisfied: joblib>=1.1.1 in ./.venv/lib/python3.10/site-packages (from scikit-learn) (1.3.2)\n",
+ "Requirement already satisfied: threadpoolctl>=2.0.0 in ./.venv/lib/python3.10/site-packages (from scikit-learn) (3.2.0)\n",
+ "Requirement already satisfied: click>=7.0 in ./.venv/lib/python3.10/site-packages (from ray[tune]) (8.1.7)\n",
+ "Requirement already satisfied: jsonschema in ./.venv/lib/python3.10/site-packages (from ray[tune]) (4.19.0)\n",
+ "Requirement already satisfied: msgpack<2.0.0,>=1.0.0 in ./.venv/lib/python3.10/site-packages (from ray[tune]) (1.0.5)\n",
+ "Requirement already satisfied: protobuf!=3.19.5,>=3.15.3 in ./.venv/lib/python3.10/site-packages (from ray[tune]) (4.24.2)\n",
+ "Requirement already satisfied: aiosignal in ./.venv/lib/python3.10/site-packages (from ray[tune]) (1.3.1)\n",
+ "Requirement already satisfied: frozenlist in ./.venv/lib/python3.10/site-packages (from ray[tune]) (1.4.0)\n",
+ "Requirement already satisfied: grpcio>=1.42.0 in ./.venv/lib/python3.10/site-packages (from ray[tune]) (1.57.0)\n",
+ "Requirement already satisfied: tensorboardX>=1.9 in ./.venv/lib/python3.10/site-packages (from ray[tune]) (2.6.2.2)\n",
+ "Requirement already satisfied: GitPython!=3.1.29,>=1.0.0 in ./.venv/lib/python3.10/site-packages (from wandb) (3.1.35)\n",
+ "Requirement already satisfied: psutil>=5.0.0 in ./.venv/lib/python3.10/site-packages (from wandb) (5.9.5)\n",
+ "Requirement already satisfied: sentry-sdk>=1.0.0 in ./.venv/lib/python3.10/site-packages (from wandb) (1.30.0)\n",
+ "Requirement already satisfied: docker-pycreds>=0.4.0 in ./.venv/lib/python3.10/site-packages (from wandb) (0.4.0)\n",
+ "Requirement already satisfied: pathtools in ./.venv/lib/python3.10/site-packages (from wandb) (0.1.2)\n",
+ "Requirement already satisfied: setproctitle in ./.venv/lib/python3.10/site-packages (from wandb) (1.3.2)\n",
+ "Requirement already satisfied: setuptools in ./.venv/lib/python3.10/site-packages (from wandb) (59.6.0)\n",
+ "Requirement already satisfied: appdirs>=1.4.3 in ./.venv/lib/python3.10/site-packages (from wandb) (1.4.4)\n",
+ "Requirement already satisfied: six in ./.venv/lib/python3.10/site-packages (from hyperopt) (1.16.0)\n",
+ "Requirement already satisfied: networkx>=2.2 in ./.venv/lib/python3.10/site-packages (from hyperopt) (3.1)\n",
+ "Requirement already satisfied: future in ./.venv/lib/python3.10/site-packages (from hyperopt) (0.18.3)\n",
+ "Requirement already satisfied: cloudpickle in ./.venv/lib/python3.10/site-packages (from hyperopt) (2.2.1)\n",
+ "Requirement already satisfied: py4j in ./.venv/lib/python3.10/site-packages (from hyperopt) (0.10.9.7)\n",
+ "Requirement already satisfied: attrs>=17.3.0 in ./.venv/lib/python3.10/site-packages (from aiohttp->datasets) (23.1.0)\n",
+ "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in ./.venv/lib/python3.10/site-packages (from aiohttp->datasets) (3.2.0)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in ./.venv/lib/python3.10/site-packages (from aiohttp->datasets) (6.0.4)\n",
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.venv/lib/python3.10/site-packages (from aiohttp->datasets) (4.0.3)\n",
+ "Requirement already satisfied: yarl<2.0,>=1.0 in ./.venv/lib/python3.10/site-packages (from aiohttp->datasets) (1.9.2)\n",
+ "Requirement already satisfied: gitdb<5,>=4.0.1 in ./.venv/lib/python3.10/site-packages (from GitPython!=3.1.29,>=1.0.0->wandb) (4.0.10)\n",
+ "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.venv/lib/python3.10/site-packages (from huggingface-hub<1.0.0,>=0.14.0->datasets) (4.7.1)\n",
+ "Requirement already satisfied: backcall in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.2.0)\n",
+ "Requirement already satisfied: decorator in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (5.1.1)\n",
+ "Requirement already satisfied: jedi>=0.16 in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.19.0)\n",
+ "Requirement already satisfied: matplotlib-inline in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.1.6)\n",
+ "Requirement already satisfied: pickleshare in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.7.5)\n",
+ "Requirement already satisfied: prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30 in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (3.0.39)\n",
+ "Requirement already satisfied: pygments>=2.4.0 in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (2.16.1)\n",
+ "Requirement already satisfied: stack-data in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (0.6.2)\n",
+ "Requirement already satisfied: exceptiongroup in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (1.1.3)\n",
+ "Requirement already satisfied: pexpect>4.3 in ./.venv/lib/python3.10/site-packages (from ipython>=6.1.0->ipywidgets) (4.8.0)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in ./.venv/lib/python3.10/site-packages (from requests>=2.19.0->datasets) (3.4)\n",
+ "Requirement already satisfied: urllib3<3,>=1.21.1 in ./.venv/lib/python3.10/site-packages (from requests>=2.19.0->datasets) (2.0.4)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in ./.venv/lib/python3.10/site-packages (from requests>=2.19.0->datasets) (2023.7.22)\n",
+ "Requirement already satisfied: sympy in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (1.12)\n",
+ "Requirement already satisfied: jinja2 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (3.1.2)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.7.99)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.7.99)\n",
+ "Requirement already satisfied: nvidia-cuda-cupti-cu11==11.7.101 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.7.101)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (8.5.0.96)\n",
+ "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.10.3.66)\n",
+ "Requirement already satisfied: nvidia-cufft-cu11==10.9.0.58 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (10.9.0.58)\n",
+ "Requirement already satisfied: nvidia-curand-cu11==10.2.10.91 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (10.2.10.91)\n",
+ "Requirement already satisfied: nvidia-cusolver-cu11==11.4.0.1 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.4.0.1)\n",
+ "Requirement already satisfied: nvidia-cusparse-cu11==11.7.4.91 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.7.4.91)\n",
+ "Requirement already satisfied: nvidia-nccl-cu11==2.14.3 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (2.14.3)\n",
+ "Requirement already satisfied: nvidia-nvtx-cu11==11.7.91 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (11.7.91)\n",
+ "Requirement already satisfied: triton==2.0.0 in ./.venv/lib/python3.10/site-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (2.0.0)\n",
+ "Requirement already satisfied: wheel in ./.venv/lib/python3.10/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch!=1.12.0,>=1.10->transformers[torch]) (0.41.2)\n",
+ "Requirement already satisfied: cmake in ./.venv/lib/python3.10/site-packages (from triton==2.0.0->torch!=1.12.0,>=1.10->transformers[torch]) (3.27.4.1)\n",
+ "Requirement already satisfied: lit in ./.venv/lib/python3.10/site-packages (from triton==2.0.0->torch!=1.12.0,>=1.10->transformers[torch]) (16.0.6)\n",
+ "Requirement already satisfied: jsonschema-specifications>=2023.03.6 in ./.venv/lib/python3.10/site-packages (from jsonschema->ray[tune]) (2023.7.1)\n",
+ "Requirement already satisfied: referencing>=0.28.4 in ./.venv/lib/python3.10/site-packages (from jsonschema->ray[tune]) (0.30.2)\n",
+ "Requirement already satisfied: rpds-py>=0.7.1 in ./.venv/lib/python3.10/site-packages (from jsonschema->ray[tune]) (0.10.2)\n",
+ "Requirement already satisfied: python-dateutil>=2.8.2 in ./.venv/lib/python3.10/site-packages (from pandas->datasets) (2.8.2)\n",
+ "Requirement already satisfied: pytz>=2020.1 in ./.venv/lib/python3.10/site-packages (from pandas->datasets) (2023.3.post1)\n",
+ "Requirement already satisfied: tzdata>=2022.1 in ./.venv/lib/python3.10/site-packages (from pandas->datasets) (2023.3)\n",
+ "Requirement already satisfied: smmap<6,>=3.0.1 in ./.venv/lib/python3.10/site-packages (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb) (5.0.0)\n",
+ "Requirement already satisfied: parso<0.9.0,>=0.8.3 in ./.venv/lib/python3.10/site-packages (from jedi>=0.16->ipython>=6.1.0->ipywidgets) (0.8.3)\n",
+ "Requirement already satisfied: ptyprocess>=0.5 in ./.venv/lib/python3.10/site-packages (from pexpect>4.3->ipython>=6.1.0->ipywidgets) (0.7.0)\n",
+ "Requirement already satisfied: wcwidth in ./.venv/lib/python3.10/site-packages (from prompt-toolkit!=3.0.37,<3.1.0,>=3.0.30->ipython>=6.1.0->ipywidgets) (0.2.6)\n",
+ "Requirement already satisfied: MarkupSafe>=2.0 in ./.venv/lib/python3.10/site-packages (from jinja2->torch!=1.12.0,>=1.10->transformers[torch]) (2.1.3)\n",
+ "Requirement already satisfied: executing>=1.2.0 in ./.venv/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (1.2.0)\n",
+ "Requirement already satisfied: asttokens>=2.1.0 in ./.venv/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (2.4.0)\n",
+ "Requirement already satisfied: pure-eval in ./.venv/lib/python3.10/site-packages (from stack-data->ipython>=6.1.0->ipywidgets) (0.2.2)\n",
+ "Requirement already satisfied: mpmath>=0.19 in ./.venv/lib/python3.10/site-packages (from sympy->torch!=1.12.0,>=1.10->transformers[torch]) (1.3.0)\n"
+ ]
+ }
+ ],
+ "source": [
+ "!pip install datasets ipywidgets transformers[torch] evaluate scikit-learn ray[tune] wandb hyperopt"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 359,
+ "referenced_widgets": [
+ "b79e9c0aa7f442a5956eeb03f684a357",
+ "97b0c3827a2040a3b8c81cad7e2f9d78",
+ "291adaefb7fb4122b8101076d3412d95",
+ "549a797c9e584a49b82f95448513e742",
+ "9aa90b4b549345fcafe4b6344532ce7a",
+ "f2a14fe11c1f4e34af19958071f9c0cb",
+ "92ae36322f5f41b1ba0c3d012eaa274d",
+ "cccfa6f765a74fe89d777bab68332fca",
+ "0d89dabdf49146d19c5ec6170c5b8efb",
+ "b81730ef186548e0924c5add62503e93",
+ "169801107d4c426faddda35cdc784e1d",
+ "75820af3aa214f3eb1e85c937fccd189",
+ "a00fcad40d6e45cf9717d6203676d646",
+ "337dfd3562d743f79487582f03f3f396",
+ "1e4e36eb6f004f9c9d6101fc81a53983",
+ "606d9c327bc04b74ac676b9340acb3df",
+ "df03b594bba94ca781b2f68f10d8f928"
+ ]
+ },
+ "id": "hpFXbjdecnzZ",
+ "outputId": "b62c1bc5-76cf-4c58-c896-e2068781df1f"
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "ab399e5a1fb845fba2388706b9185da4",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='
"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Create sweep with ID: 1wpa6h8x\n",
+ "Sweep URL: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 97sjboe5 with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 3.662189175786302e-06\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 116.0448051231694\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d4bd69d393c4413797b7c485efe34924",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011113103355455678, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_174218-97sjboe5
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run blooming-sweep-1 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/97sjboe5"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "fd553a88b1264208b7fb0b2dd4ec3c28",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run blooming-sweep-1 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/97sjboe5
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_174218-97sjboe5/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "908e5241bc9f47f0b8c2a6f8fc40b9de",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011113186266771258, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_174227-97sjboe5
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run blooming-sweep-1 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/97sjboe5"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "c734e68260404dc3a26f2d988930c94b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/116 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 6.103648626310503e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.5967, 'learning_rate': 3.4255130171363674e-06, 'epoch': 0.0}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "640000d0bc684bb29f0dc7f496c4fd36",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 1.1420423984527588, 'eval_accuracy': 0.29442877291960506, 'eval_best_accuracy': 0.29442877291960506, 'eval_runtime': 43.6455, 'eval_samples_per_second': 64.978, 'eval_steps_per_second': 8.134, 'epoch': 0.0}\n",
+ "{'loss': 0.5195, 'learning_rate': 2.4954298136066424e-06, 'epoch': 0.0}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "378008c8e80d400b999cda714e1bbedd",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 1.1290498971939087, 'eval_accuracy': 0.29442877291960506, 'eval_best_accuracy': 0.29442877291960506, 'eval_runtime': 44.5542, 'eval_samples_per_second': 63.653, 'eval_steps_per_second': 7.968, 'epoch': 0.0}\n",
+ "{'loss': 0.5312, 'learning_rate': 1.2652552419261767e-06, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "dba49254c776457f9dd76fef9123087a",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 1.1247342824935913, 'eval_accuracy': 0.29442877291960506, 'eval_best_accuracy': 0.29442877291960506, 'eval_runtime': 45.1478, 'eval_samples_per_second': 62.816, 'eval_steps_per_second': 7.863, 'epoch': 0.01}\n",
+ "{'loss': 0.5725, 'learning_rate': 2.906797968799817e-07, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "440ce64b0bfa4a26bdc326cb757b21f2",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.9865888953208923, 'eval_accuracy': 0.3039492242595205, 'eval_best_accuracy': 0.3039492242595205, 'eval_runtime': 45.5047, 'eval_samples_per_second': 62.323, 'eval_steps_per_second': 7.801, 'epoch': 0.01}\n",
+ "{'train_runtime': 235.2118, 'train_samples_per_second': 3.945, 'train_steps_per_second': 0.493, 'train_loss': 0.5501209374131828, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "400b7d42812648789114dccb378367fa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▁▁█ |
eval/best_accuracy | ▁▁▁█ |
eval/loss | █▇▇▁ |
eval/runtime | ▁▄▇█ |
eval/samples_per_second | █▅▂▁ |
eval/steps_per_second | █▅▂▁ |
train/epoch | ▁▁▁▁▁█████ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▂█▆▃▁ |
train/loss | █▃▁▁▃ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.30395 |
eval/best_accuracy | 0.30395 |
eval/loss | 0.98659 |
eval/runtime | 45.5047 |
eval/samples_per_second | 62.323 |
eval/steps_per_second | 7.801 |
train/epoch | 0.01 |
train/global_step | 116 |
train/learning_rate | 0.0 |
train/loss | 0.5725 |
train/total_flos | 122929745952768.0 |
train/train_loss | 0.55012 |
train/train_runtime | 235.2118 |
train/train_samples_per_second | 3.945 |
train/train_steps_per_second | 0.493 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run blooming-sweep-1 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/97sjboe5
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_174227-97sjboe5/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: ezujfbw7 with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 1.4727353172197592e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 412.7211411729937\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_174628-ezujfbw7
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run toasty-sweep-2 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/ezujfbw7"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "06467774783e4754bfaca4f9d76eab66",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run toasty-sweep-2 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/ezujfbw7
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_174628-ezujfbw7/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2de004e7641645039096e3b4623d465c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112626366795868, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_174637-ezujfbw7
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run toasty-sweep-2 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/ezujfbw7"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "4a27d9ffa3ba4623bd1e607a780fe291",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/412 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 7.013025320094091e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.5008, 'learning_rate': 1.383241195883423e-05, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "599f0610b01f42d39796dd1c7813638c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.3737761676311493, 'eval_accuracy': 0.8600141043723555, 'eval_best_accuracy': 0.8600141043723555, 'eval_runtime': 45.5464, 'eval_samples_per_second': 62.266, 'eval_steps_per_second': 7.794, 'epoch': 0.01}\n",
+ "{'loss': 0.2668, 'learning_rate': 1.0270216174518492e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "41f5dc95b2e9411ca61f8953051f0601",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.41451194882392883, 'eval_accuracy': 0.8370944992947814, 'eval_best_accuracy': 0.8600141043723555, 'eval_runtime': 46.026, 'eval_samples_per_second': 61.617, 'eval_steps_per_second': 7.713, 'epoch': 0.02}\n",
+ "{'loss': 0.1703, 'learning_rate': 5.4625797196668375e-06, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "6990da332271462cbab308ee4499c970",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4792698323726654, 'eval_accuracy': 0.8631875881523272, 'eval_best_accuracy': 0.8631875881523272, 'eval_runtime': 46.1546, 'eval_samples_per_second': 61.446, 'eval_steps_per_second': 7.692, 'epoch': 0.02}\n",
+ "{'loss': 0.1601, 'learning_rate': 1.4695557220190025e-06, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "37e31d230cec41b4b2f41dbab98ddd49",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.47410309314727783, 'eval_accuracy': 0.8723554301833568, 'eval_best_accuracy': 0.8723554301833568, 'eval_runtime': 45.9606, 'eval_samples_per_second': 61.705, 'eval_steps_per_second': 7.724, 'epoch': 0.03}\n",
+ "{'train_runtime': 355.9155, 'train_samples_per_second': 9.261, 'train_steps_per_second': 1.158, 'train_loss': 0.24877792886159952, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "eb2f3a9d7fdc402ea1687560db1f06b3",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▆▁▆█ |
eval/best_accuracy | ▁▁▃█ |
eval/loss | ▁▄██ |
eval/runtime | ▁▇█▆ |
eval/samples_per_second | █▂▁▃ |
eval/steps_per_second | █▂▁▃ |
train/epoch | ▁▃▃▅▅▅▅▆▆█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▁ |
train/loss | █▅▂▁▁ |
train/total_flos | ��� |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.87236 |
eval/best_accuracy | 0.87236 |
eval/loss | 0.4741 |
eval/runtime | 45.9606 |
eval/samples_per_second | 61.705 |
eval/steps_per_second | 7.724 |
train/epoch | 0.04 |
train/global_step | 412 |
train/learning_rate | 0.0 |
train/loss | 0.1601 |
train/total_flos | 436612545970176.0 |
train/train_loss | 0.24878 |
train/train_runtime | 355.9155 |
train/train_samples_per_second | 9.261 |
train/train_steps_per_second | 1.158 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run toasty-sweep-2 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/ezujfbw7
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_174637-ezujfbw7/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: 1snmzbiz with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 2.6553046922432375e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 366.1063867116238\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_175238-1snmzbiz
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run dulcet-sweep-3 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/1snmzbiz"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "9c29bfcb89af473d8816ed46287b9de7",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.006 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=0.531781…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run dulcet-sweep-3 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/1snmzbiz
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_175238-1snmzbiz/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "c787a0ca336c46c2bf5a2122afc52a57",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112738155578781, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_175246-1snmzbiz
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run dulcet-sweep-3 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/1snmzbiz"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "790a1dbdf7cd47c6af6b7f48bcf395ed",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/366 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 1.3975287853911775e-06, 'epoch': 0.0}\n",
+ "{'loss': 0.4564, 'learning_rate': 2.494081216813203e-05, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b3a1e77e7b5d4ba8bf1f87487d28c264",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.3517608344554901, 'eval_accuracy': 0.8515514809590973, 'eval_best_accuracy': 0.8515514809590973, 'eval_runtime': 45.5707, 'eval_samples_per_second': 62.233, 'eval_steps_per_second': 7.79, 'epoch': 0.01}\n",
+ "{'loss': 0.2602, 'learning_rate': 1.848189503086128e-05, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3dca591a69794e5e9781aeb6491b0068",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.7612928152084351, 'eval_accuracy': 0.8444992947813822, 'eval_best_accuracy': 0.8515514809590973, 'eval_runtime': 45.7832, 'eval_samples_per_second': 61.944, 'eval_steps_per_second': 7.754, 'epoch': 0.01}\n",
+ "{'loss': 0.1803, 'learning_rate': 9.772627026752322e-06, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "18741ffbe1bd444b9a7f82f9697fe805",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4611336886882782, 'eval_accuracy': 0.8712976022566996, 'eval_best_accuracy': 0.8712976022566996, 'eval_runtime': 45.8945, 'eval_samples_per_second': 61.794, 'eval_steps_per_second': 7.735, 'epoch': 0.02}\n",
+ "{'loss': 0.0991, 'learning_rate': 2.578139720449474e-06, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "039182dd50f345a6b38a622ae8ced132",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.45402804017066956, 'eval_accuracy': 0.8758815232722144, 'eval_best_accuracy': 0.8758815232722144, 'eval_runtime': 45.927, 'eval_samples_per_second': 61.75, 'eval_steps_per_second': 7.73, 'epoch': 0.03}\n",
+ "{'train_runtime': 336.8267, 'train_samples_per_second': 8.693, 'train_steps_per_second': 1.087, 'train_loss': 0.22382783889770508, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "1671cf9e00f647ce811a48627b2028ba",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▃▁▇█ |
eval/best_accuracy | ▁▁▇█ |
eval/loss | ▁█▃▃ |
eval/runtime | ▁▅▇█ |
eval/samples_per_second | █▄▂▁ |
eval/steps_per_second | █▄▂▁ |
train/epoch | ▁▃▃▃▃▅▅▆▆█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▃▁ |
train/loss | █▅▃▂▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.87588 |
eval/best_accuracy | 0.87588 |
eval/loss | 0.45403 |
eval/runtime | 45.927 |
eval/samples_per_second | 61.75 |
eval/steps_per_second | 7.73 |
train/epoch | 0.04 |
train/global_step | 366 |
train/learning_rate | 0.0 |
train/loss | 0.0991 |
train/total_flos | 387864543264768.0 |
train/train_loss | 0.22383 |
train/train_runtime | 336.8267 |
train/train_samples_per_second | 8.693 |
train/train_steps_per_second | 1.087 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run dulcet-sweep-3 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/1snmzbiz
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_175246-1snmzbiz/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: zislhxig with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 2.7061350795742976e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 492.6120506548938\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_175829-zislhxig
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run rich-sweep-4 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/zislhxig"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2fbf5ad069d94ecdb616433e72c971fe",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run rich-sweep-4 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/zislhxig
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_175829-zislhxig/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "9e58e34c87d64213bb169c841b70ef09",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112159044326593, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_175837-zislhxig
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run rich-sweep-4 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/zislhxig"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3d0fc32565134c9da011fa60e10371b3",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/492 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 1.082454031829719e-06, 'epoch': 0.0}\n",
+ "{'loss': 0.4464, 'learning_rate': 2.5419130002244076e-05, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "578096a09ea84c5ab1be41647b450f4e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.39300262928009033, 'eval_accuracy': 0.8212270803949224, 'eval_best_accuracy': 0.8212270803949224, 'eval_runtime': 45.5551, 'eval_samples_per_second': 62.254, 'eval_steps_per_second': 7.793, 'epoch': 0.01}\n",
+ "{'loss': 0.223, 'learning_rate': 1.8886806457529346e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "ce24c880c49d4f9a8abbb93fddb0c3dc",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4684779644012451, 'eval_accuracy': 0.866361071932299, 'eval_best_accuracy': 0.866361071932299, 'eval_runtime': 45.9251, 'eval_samples_per_second': 61.753, 'eval_steps_per_second': 7.73, 'epoch': 0.02}\n",
+ "{'loss': 0.0966, 'learning_rate': 1.0065326676908548e-05, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "26dd7ef73fe249b5ab84e8a1697a80fc",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4274778664112091, 'eval_accuracy': 0.8949224259520452, 'eval_best_accuracy': 0.8949224259520452, 'eval_runtime': 45.8927, 'eval_samples_per_second': 61.796, 'eval_steps_per_second': 7.735, 'epoch': 0.03}\n",
+ "{'loss': 0.1083, 'learning_rate': 2.7249018865082767e-06, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "934092f766324185847418e3e24871ca",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5640350580215454, 'eval_accuracy': 0.864950634696756, 'eval_best_accuracy': 0.8949224259520452, 'eval_runtime': 46.0188, 'eval_samples_per_second': 61.627, 'eval_steps_per_second': 7.714, 'epoch': 0.04}\n",
+ "{'train_runtime': 386.4211, 'train_samples_per_second': 10.186, 'train_steps_per_second': 1.273, 'train_loss': 0.20810224757931098, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▅█▅ |
eval/best_accuracy | ▁▅██ |
eval/loss | ▁▄▂█ |
eval/runtime | ▁▇▆█ |
eval/samples_per_second | █▂▃▁ |
eval/steps_per_second | █▂▃▁ |
train/epoch | ▁▂▂▄▄▅▅▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▁ |
train/loss | █▅▂▁▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.86495 |
eval/best_accuracy | 0.89492 |
eval/loss | 0.56404 |
eval/runtime | 46.0188 |
eval/samples_per_second | 61.627 |
eval/steps_per_second | 7.714 |
train/epoch | 0.05 |
train/global_step | 492 |
train/learning_rate | 0.0 |
train/loss | 0.1083 |
train/total_flos | 521391681110016.0 |
train/train_loss | 0.2081 |
train/train_runtime | 386.4211 |
train/train_samples_per_second | 10.186 |
train/train_steps_per_second | 1.273 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run rich-sweep-4 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/zislhxig
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_175837-zislhxig/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: myfgg3jt with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 7.434428008752932e-06\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 656.8099612953338\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_180511-myfgg3jt
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run young-sweep-5 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/myfgg3jt"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d3c544814429409ab5d1c518e33c6fdc",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run young-sweep-5 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/myfgg3jt
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_180511-myfgg3jt/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "09f91d8a79244c4b9efc5e17f12ff4cb",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.01111549857774258, max=1.0)…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_180519-myfgg3jt
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run young-sweep-5 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/myfgg3jt"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "bbbde9f835784b049d7d08dc3237d0ef",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/656 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 2.2528569723493736e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.5016, 'learning_rate': 6.980754940607634e-06, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "cab173b3eaf641ad94585c4f6d66a3e2",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5031077265739441, 'eval_accuracy': 0.7806770098730607, 'eval_best_accuracy': 0.7806770098730607, 'eval_runtime': 45.6922, 'eval_samples_per_second': 62.068, 'eval_steps_per_second': 7.769, 'epoch': 0.01}\n",
+ "{'loss': 0.2674, 'learning_rate': 5.185063702547212e-06, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f7643129ab00426697a081f9559dd8d2",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.48900747299194336, 'eval_accuracy': 0.8533145275035261, 'eval_best_accuracy': 0.8533145275035261, 'eval_runtime': 45.9138, 'eval_samples_per_second': 61.768, 'eval_steps_per_second': 7.732, 'epoch': 0.03}\n",
+ "{'loss': 0.1823, 'learning_rate': 2.762674521436141e-06, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "a23b0a37ad9a410db92141c6dc8c2251",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.47831806540489197, 'eval_accuracy': 0.866361071932299, 'eval_best_accuracy': 0.866361071932299, 'eval_runtime': 45.985, 'eval_samples_per_second': 61.672, 'eval_steps_per_second': 7.72, 'epoch': 0.04}\n",
+ "{'loss': 0.2063, 'learning_rate': 7.478256567926397e-07, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2ca20a6125bc42e788b9b6cb0755f084",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.47905150055885315, 'eval_accuracy': 0.8709449929478138, 'eval_best_accuracy': 0.8709449929478138, 'eval_runtime': 46.0672, 'eval_samples_per_second': 61.562, 'eval_steps_per_second': 7.706, 'epoch': 0.05}\n",
+ "{'train_runtime': 451.0846, 'train_samples_per_second': 11.634, 'train_steps_per_second': 1.454, 'train_loss': 0.2680025725829892, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▇██ |
eval/best_accuracy | ▁▇██ |
eval/loss | █▄▁▁ |
eval/runtime | ▁▅▆█ |
eval/samples_per_second | █▄▃▁ |
eval/steps_per_second | █▄▃▁ |
train/epoch | ▁▂▂▅▅▆▆▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▅▂▁▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.87094 |
eval/best_accuracy | 0.87094 |
eval/loss | 0.47905 |
eval/runtime | 46.0672 |
eval/samples_per_second | 61.562 |
eval/steps_per_second | 7.706 |
train/epoch | 0.06 |
train/global_step | 656 |
train/learning_rate | 0.0 |
train/loss | 0.2063 |
train/total_flos | 695188908146688.0 |
train/train_loss | 0.268 |
train/train_runtime | 451.0846 |
train/train_samples_per_second | 11.634 |
train/train_steps_per_second | 1.454 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run young-sweep-5 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/myfgg3jt
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_180519-myfgg3jt/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Sweep Agent: Waiting for job.\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Job received.\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: uakeqy2o with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 2.386135927313411e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 887.5577347480429\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_181305-uakeqy2o
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run northern-sweep-6 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/uakeqy2o"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "c73340fc556b41a8b032ce98aabea848",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run northern-sweep-6 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/uakeqy2o
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_181305-uakeqy2o/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "5d618ef5884c489cb7ae43ed9afa0cb7",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011116341788793862, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_181313-uakeqy2o
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run northern-sweep-6 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/uakeqy2o"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "674c00f139c546ddbc594d6d0bb09fe0",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/887 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 5.302524282918692e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.3788, 'learning_rate': 2.2422283922793875e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "cb41a53e72ff44de9447cf2e63170027",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.6187645792961121, 'eval_accuracy': 0.8469675599435825, 'eval_best_accuracy': 0.8469675599435825, 'eval_runtime': 45.6516, 'eval_samples_per_second': 62.123, 'eval_steps_per_second': 7.776, 'epoch': 0.02}\n",
+ "{'loss': 0.1456, 'learning_rate': 1.669097516003374e-05, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "5ee847ce85f64ece9603c01e60ae462e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.6571812629699707, 'eval_accuracy': 0.8519040902679831, 'eval_best_accuracy': 0.8519040902679831, 'eval_runtime': 45.9539, 'eval_samples_per_second': 61.714, 'eval_steps_per_second': 7.725, 'epoch': 0.04}\n",
+ "{'loss': 0.17, 'learning_rate': 8.936054419349463e-06, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f24124d54f42485d968a18dc5b7bf8aa",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4925839304924011, 'eval_accuracy': 0.8797602256699577, 'eval_best_accuracy': 0.8797602256699577, 'eval_runtime': 46.0116, 'eval_samples_per_second': 61.637, 'eval_steps_per_second': 7.715, 'epoch': 0.05}\n",
+ "{'loss': 0.1162, 'learning_rate': 2.4541553700878304e-06, 'epoch': 0.07}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d75ece13809047cca5d00738bbaae9bb",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.3302706778049469, 'eval_accuracy': 0.9160789844851904, 'eval_best_accuracy': 0.9160789844851904, 'eval_runtime': 46.0755, 'eval_samples_per_second': 61.551, 'eval_steps_per_second': 7.705, 'epoch': 0.07}\n",
+ "{'train_runtime': 540.5231, 'train_samples_per_second': 13.128, 'train_steps_per_second': 1.641, 'train_loss': 0.18107375216994775, 'epoch': 0.09}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▁▄█ |
eval/best_accuracy | ▁▁▄█ |
eval/loss | ▇█▄▁ |
eval/runtime | ▁▆▇█ |
eval/samples_per_second | █▃▂▁ |
eval/steps_per_second | █▃▂▁ |
train/epoch | ▁▃▃▄▄▅▅▆▆█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▄▁▂▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.91608 |
eval/best_accuracy | 0.91608 |
eval/loss | 0.33027 |
eval/runtime | 46.0755 |
eval/samples_per_second | 61.551 |
eval/steps_per_second | 7.705 |
train/epoch | 0.09 |
train/global_step | 887 |
train/learning_rate | 0.0 |
train/loss | 0.1162 |
train/total_flos | 939988660862976.0 |
train/train_loss | 0.18107 |
train/train_runtime | 540.5231 |
train/train_samples_per_second | 13.128 |
train/train_steps_per_second | 1.641 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run northern-sweep-6 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/uakeqy2o
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_181313-uakeqy2o/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: vp9ymyaw with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 6.4818465481420485e-06\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 987.027502299798\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_182223-vp9ymyaw
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run cool-sweep-7 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vp9ymyaw"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3b2854acf17d43c2863110f71ee84678",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run cool-sweep-7 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vp9ymyaw
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_182223-vp9ymyaw/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f5e66144d0a8421b845e51a7e249b67f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011116606299927096, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_182231-vp9ymyaw
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run cool-sweep-7 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vp9ymyaw"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7785439066ab45a19bf739befe79d579",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/987 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 1.2963693096284098e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.4625, 'learning_rate': 6.090957981256211e-06, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f9cd29cf299d4c548a2d81c7ba75bf7f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.3664630353450775, 'eval_accuracy': 0.8455571227080395, 'eval_best_accuracy': 0.8455571227080395, 'eval_runtime': 45.829, 'eval_samples_per_second': 61.882, 'eval_steps_per_second': 7.746, 'epoch': 0.02}\n",
+ "{'loss': 0.2142, 'learning_rate': 4.534926715424102e-06, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "eb971eecb7ba44178fca21b3475ecf84",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5564488172531128, 'eval_accuracy': 0.8564880112834978, 'eval_best_accuracy': 0.8564880112834978, 'eval_runtime': 46.047, 'eval_samples_per_second': 61.589, 'eval_steps_per_second': 7.71, 'epoch': 0.04}\n",
+ "{'loss': 0.2086, 'learning_rate': 2.429256335438124e-06, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "da754018fcee4bf6a39c1ddee80fbabd",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5895119905471802, 'eval_accuracy': 0.8575458392101551, 'eval_best_accuracy': 0.8575458392101551, 'eval_runtime': 46.0542, 'eval_samples_per_second': 61.58, 'eval_steps_per_second': 7.708, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (failed 1). Press Control-C to abort syncing."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▇█ |
eval/best_accuracy | ▁▇█ |
eval/loss | ▁▇█ |
eval/runtime | ▁██ |
eval/samples_per_second | █▁▁ |
eval/steps_per_second | █▁▁ |
train/epoch | ▁▃▃▆▆██ |
train/global_step | ▁▃▃▆▆██ |
train/learning_rate | ▁█▆▄ |
train/loss | █▄▁▁ |
Run summary:
eval/accuracy | 0.85755 |
eval/best_accuracy | 0.85755 |
eval/loss | 0.58951 |
eval/runtime | 46.0542 |
eval/samples_per_second | 61.58 |
eval/steps_per_second | 7.708 |
train/epoch | 0.06 |
train/global_step | 594 |
train/learning_rate | 0.0 |
train/loss | 0.2086 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run cool-sweep-7 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vp9ymyaw
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_182231-vp9ymyaw/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: sf7gbffb with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 4.8471494836128023e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 971.9909302500764\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_183011-sf7gbffb
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run trim-sweep-8 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/sf7gbffb"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d06a8a7dec4e45fe8a176a330f4462d8",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run trim-sweep-8 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/sf7gbffb
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_183011-sf7gbffb/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "7d232d84c1234d269f7495e496d902c4",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112438822359157, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_183020-sf7gbffb
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run trim-sweep-8 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/sf7gbffb"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "24b7b3ef5b4d4e4ebff17993a0436f9e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/971 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 9.892141803291432e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.3471, 'learning_rate': 4.553388022261812e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d63aef9529fe445f905b50bc6904d056",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.26049190759658813, 'eval_accuracy': 0.9171368124118476, 'eval_best_accuracy': 0.9171368124118476, 'eval_runtime': 45.9111, 'eval_samples_per_second': 61.772, 'eval_steps_per_second': 7.732, 'epoch': 0.02}\n",
+ "{'loss': 0.1506, 'learning_rate': 3.3871532644324455e-05, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "8dd8c04b5caf4da09cfaead567ac9d29",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4304882884025574, 'eval_accuracy': 0.8681241184767278, 'eval_best_accuracy': 0.9171368124118476, 'eval_runtime': 46.0872, 'eval_samples_per_second': 61.535, 'eval_steps_per_second': 7.703, 'epoch': 0.04}\n",
+ "{'loss': 0.1625, 'learning_rate': 1.810943396737081e-05, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "744fe420d6214eb582c6f06f861d7ef9",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.2744184136390686, 'eval_accuracy': 0.9111424541607899, 'eval_best_accuracy': 0.9171368124118476, 'eval_runtime': 46.1108, 'eval_samples_per_second': 61.504, 'eval_steps_per_second': 7.699, 'epoch': 0.06}\n",
+ "{'loss': 0.0966, 'learning_rate': 4.953906494574466e-06, 'epoch': 0.08}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e73316cf7eaa407190e7c8d77572d70f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.30896759033203125, 'eval_accuracy': 0.9118476727785614, 'eval_best_accuracy': 0.9171368124118476, 'eval_runtime': 46.0962, 'eval_samples_per_second': 61.524, 'eval_steps_per_second': 7.701, 'epoch': 0.08}\n",
+ "{'train_runtime': 575.4106, 'train_samples_per_second': 13.5, 'train_steps_per_second': 1.687, 'train_loss': 0.17252054126083421, 'epoch': 0.1}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | █▁▇▇ |
eval/best_accuracy | ▁▁▁▁ |
eval/loss | ▁█▂▃ |
eval/runtime | ▁▇█▇ |
eval/samples_per_second | █▂▁▂ |
eval/steps_per_second | █▂▁▁ |
train/epoch | ▁▂▂▄▄▅▅▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▄▂▂▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.91185 |
eval/best_accuracy | 0.91714 |
eval/loss | 0.30897 |
eval/runtime | 46.0962 |
eval/samples_per_second | 61.524 |
eval/steps_per_second | 7.701 |
train/epoch | 0.1 |
train/global_step | 971 |
train/learning_rate | 0.0 |
train/loss | 0.0966 |
train/total_flos | 1230357198716928.0 |
train/train_loss | 0.17252 |
train/train_runtime | 575.4106 |
train/train_samples_per_second | 13.5 |
train/train_steps_per_second | 1.687 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run trim-sweep-8 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/sf7gbffb
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_183020-sf7gbffb/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: snct1auc with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 3.407783628903858e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 887.417779049362\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "a44faf540f9641e49817b10016fd0439",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.01111364626671679, max=1.0)…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_184002-snct1auc
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run treasured-sweep-9 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/snct1auc"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "44f4cc18311141adb5d71000c9e3f7b9",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run treasured-sweep-9 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/snct1auc
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_184002-snct1auc/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "04d8d890676a48668171194a732e6126",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112464211085657, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_184011-snct1auc
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run treasured-sweep-9 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/snct1auc"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "a00c3346489d4b2b9444fbcafbe072ba",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/887 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 7.57285250867524e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.3711, 'learning_rate': 3.202260659172201e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "52cf80d9548c4870998cbc64bc9e1a14",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.6673237085342407, 'eval_accuracy': 0.8469675599435825, 'eval_best_accuracy': 0.8469675599435825, 'eval_runtime': 45.8938, 'eval_samples_per_second': 61.795, 'eval_steps_per_second': 7.735, 'epoch': 0.02}\n",
+ "{'loss': 0.1387, 'learning_rate': 2.3837381286507506e-05, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2c5d7f0aa8974feca7e2bfba48252671",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.7773379683494568, 'eval_accuracy': 0.8557827926657263, 'eval_best_accuracy': 0.8557827926657263, 'eval_runtime': 46.0497, 'eval_samples_per_second': 61.586, 'eval_steps_per_second': 7.709, 'epoch': 0.04}\n",
+ "{'loss': 0.182, 'learning_rate': 1.2762114516895786e-05, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f3f7fa3d8d5d4500a74043fe3a3aecf0",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5509341359138489, 'eval_accuracy': 0.8730606488011283, 'eval_best_accuracy': 0.8730606488011283, 'eval_runtime': 46.5282, 'eval_samples_per_second': 60.952, 'eval_steps_per_second': 7.63, 'epoch': 0.05}\n",
+ "{'loss': 0.1089, 'learning_rate': 3.5049262689691333e-06, 'epoch': 0.07}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e5e444bf70274b50a21c379de53aeeea",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.47849220037460327, 'eval_accuracy': 0.8896332863187588, 'eval_best_accuracy': 0.8896332863187588, 'eval_runtime': 46.8442, 'eval_samples_per_second': 60.541, 'eval_steps_per_second': 7.578, 'epoch': 0.07}\n",
+ "{'train_runtime': 545.3395, 'train_samples_per_second': 13.012, 'train_steps_per_second': 1.627, 'train_loss': 0.17847960212991365, 'epoch': 0.09}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▁▂▅█ |
eval/best_accuracy | ▁▂▅█ |
eval/loss | ▅█▃▁ |
eval/runtime | ▁▂▆█ |
eval/samples_per_second | █▇▃▁ |
eval/steps_per_second | █▇▃▁ |
train/epoch | ▁▃▃▄▄▅▅▆▆█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▄▁▂▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.88963 |
eval/best_accuracy | 0.88963 |
eval/loss | 0.47849 |
eval/runtime | 46.8442 |
eval/samples_per_second | 60.541 |
eval/steps_per_second | 7.578 |
train/epoch | 0.09 |
train/global_step | 887 |
train/learning_rate | 0.0 |
train/loss | 0.1089 |
train/total_flos | 939988660862976.0 |
train/train_loss | 0.17848 |
train/train_runtime | 545.3395 |
train/train_samples_per_second | 13.012 |
train/train_steps_per_second | 1.627 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run treasured-sweep-9 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/snct1auc
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_184011-snct1auc/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: wxqoee18 with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 2.6401926255766613e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 747.8252978281836\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3150167bdf8c40b8a7b7d73954c40108",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.01111317927780975, max=1.0)…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_184924-wxqoee18
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run bright-sweep-10 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/wxqoee18"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "5a76389b84d54100be3cb681fef0ab9c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run bright-sweep-10 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/wxqoee18
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_184924-wxqoee18/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "aea03a48f3f340189746cffdcba3f08a",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011113307522221779, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_184933-wxqoee18
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run bright-sweep-10 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/wxqoee18"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "3ad3e45391ee4117ad8baa62638e6e12",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/747 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 6.947875330464898e-07, 'epoch': 0.0}\n",
+ "{'loss': 0.3981, 'learning_rate': 2.4809398114091033e-05, 'epoch': 0.01}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e16edb0b3bc5433ba0814d468301aa61",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5910525918006897, 'eval_accuracy': 0.830394922425952, 'eval_best_accuracy': 0.830394922425952, 'eval_runtime': 46.4597, 'eval_samples_per_second': 61.042, 'eval_steps_per_second': 7.641, 'epoch': 0.01}\n",
+ "{'loss': 0.1528, 'learning_rate': 1.8461407528970736e-05, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2346274cba0d48188873599326718199",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5033357739448547, 'eval_accuracy': 0.8815232722143864, 'eval_best_accuracy': 0.8815232722143864, 'eval_runtime': 46.8648, 'eval_samples_per_second': 60.515, 'eval_steps_per_second': 7.575, 'epoch': 0.03}\n",
+ "{'loss': 0.1569, 'learning_rate': 9.873845086441979e-06, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b47e39b546e743c6990adb2ee7631024",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.8672884106636047, 'eval_accuracy': 0.7940761636107193, 'eval_best_accuracy': 0.8815232722143864, 'eval_runtime': 46.8113, 'eval_samples_per_second': 60.584, 'eval_steps_per_second': 7.584, 'epoch': 0.04}\n",
+ "{'loss': 0.112, 'learning_rate': 2.7027637173274e-06, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "e2cfdd3bca414fc6bbfe972e1b4b435c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5296059846878052, 'eval_accuracy': 0.8677715091678421, 'eval_best_accuracy': 0.8815232722143864, 'eval_runtime': 46.9711, 'eval_samples_per_second': 60.378, 'eval_steps_per_second': 7.558, 'epoch': 0.06}\n",
+ "{'train_runtime': 494.9315, 'train_samples_per_second': 12.074, 'train_steps_per_second': 1.509, 'train_loss': 0.18492630495125031, 'epoch': 0.07}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▄█▁▇ |
eval/best_accuracy | ▁███ |
eval/loss | ▃▁█▂ |
eval/runtime | ▁▇▆█ |
eval/samples_per_second | █▂▃▁ |
eval/steps_per_second | █▂▃▁ |
train/epoch | ▁▂▂▄▄▅▅▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▄▁▁▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.86777 |
eval/best_accuracy | 0.88152 |
eval/loss | 0.52961 |
eval/runtime | 46.9711 |
eval/samples_per_second | 60.378 |
eval/steps_per_second | 7.558 |
train/epoch | 0.07 |
train/global_step | 747 |
train/learning_rate | 0.0 |
train/loss | 0.112 |
train/total_flos | 791625174368256.0 |
train/train_loss | 0.18493 |
train/train_runtime | 494.9315 |
train/train_samples_per_second | 12.074 |
train/train_steps_per_second | 1.509 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run bright-sweep-10 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/wxqoee18
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_184933-wxqoee18/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: bvycb14r with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 5.6321196194785554e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 838.610531284139\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_185756-bvycb14r
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run ruby-sweep-11 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/bvycb14r"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "40f2c177bade4bcb8dd186129d905f61",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run ruby-sweep-11 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/bvycb14r
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_185756-bvycb14r/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "87ab7dfa41ea4d5b87269afa91c4fa2a",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112281988931095, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_185805-bvycb14r
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run ruby-sweep-11 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/bvycb14r"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "fec039bf9a5f42ab951b2fbcb98c5f22",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/838 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 1.3409808617806083e-06, 'epoch': 0.0}\n",
+ "{'loss': 0.3703, 'learning_rate': 5.291038114189561e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "826fcef7b92f4b1e934969c00414a306",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.20273464918136597, 'eval_accuracy': 0.9255994358251057, 'eval_best_accuracy': 0.9255994358251057, 'eval_runtime': 46.6761, 'eval_samples_per_second': 60.759, 'eval_steps_per_second': 7.606, 'epoch': 0.02}\n",
+ "{'loss': 0.1612, 'learning_rate': 3.9397537262271715e-05, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "996701036be64eaa9d748541bf05dbce",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.8588054776191711, 'eval_accuracy': 0.8381523272214386, 'eval_best_accuracy': 0.9255994358251057, 'eval_runtime': 46.804, 'eval_samples_per_second': 60.593, 'eval_steps_per_second': 7.585, 'epoch': 0.03}\n",
+ "{'loss': 0.1845, 'learning_rate': 2.1122899604753682e-05, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "5ec1640f8dc2454799620d7b444fa090",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5415298938751221, 'eval_accuracy': 0.8543723554301833, 'eval_best_accuracy': 0.9255994358251057, 'eval_runtime': 46.4784, 'eval_samples_per_second': 61.018, 'eval_steps_per_second': 7.638, 'epoch': 0.05}\n",
+ "{'loss': 0.0957, 'learning_rate': 5.830574870819477e-06, 'epoch': 0.07}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "c9a68848e5c643ffb3a4ac3c9b2ba86c",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4882190227508545, 'eval_accuracy': 0.8744710860366713, 'eval_best_accuracy': 0.9255994358251057, 'eval_runtime': 46.4193, 'eval_samples_per_second': 61.095, 'eval_steps_per_second': 7.648, 'epoch': 0.07}\n",
+ "{'train_runtime': 528.4803, 'train_samples_per_second': 12.685, 'train_steps_per_second': 1.586, 'train_loss': 0.18534580107804985, 'epoch': 0.08}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | █▁▂▄ |
eval/best_accuracy | ▁▁▁▁ |
eval/loss | ▁█▅▄ |
eval/runtime | ▆█▂▁ |
eval/samples_per_second | ▃▁▇█ |
eval/steps_per_second | ▃▁▇█ |
train/epoch | ▁▃▃▄▄▅▅▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▄▂▂▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.87447 |
eval/best_accuracy | 0.9256 |
eval/loss | 0.48822 |
eval/runtime | 46.4193 |
eval/samples_per_second | 61.095 |
eval/steps_per_second | 7.648 |
train/epoch | 0.08 |
train/global_step | 838 |
train/learning_rate | 1e-05 |
train/loss | 0.0957 |
train/total_flos | 888061440589824.0 |
train/train_loss | 0.18535 |
train/train_runtime | 528.4803 |
train/train_samples_per_second | 12.685 |
train/train_steps_per_second | 1.586 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run ruby-sweep-11 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/bvycb14r
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_185805-bvycb14r/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: hk2674vn with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 6.228935072387667e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 989.8172473373054\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "2e6a6da405e2417398c69bcbfdcf9838",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011113473766696795, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_190700-hk2674vn
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run playful-sweep-12 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/hk2674vn"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "19bb48a097724f24a4ece05b175eebbe",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.003 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=1.0, max…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run playful-sweep-12 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/hk2674vn
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_190700-hk2674vn/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "a95d176915fa420192046d7a717e0ffc",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112434533424675, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_190709-hk2674vn
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run playful-sweep-12 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/hk2674vn"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "94458e8bf1744c57b863b5aac3ed4ad0",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/989 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 1.2457870144775334e-06, 'epoch': 0.0}\n",
+ "{'loss': 0.3391, 'learning_rate': 5.8548640204133266e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "20c7757c7995462397fde01e9258fbd3",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4350177049636841, 'eval_accuracy': 0.9026798307475318, 'eval_best_accuracy': 0.9026798307475318, 'eval_runtime': 46.0577, 'eval_samples_per_second': 61.575, 'eval_steps_per_second': 7.708, 'epoch': 0.02}\n",
+ "{'loss': 0.157, 'learning_rate': 4.365032646520272e-05, 'epoch': 0.04}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "fc1237b2b3d94533a529764e480a2025",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.6273585557937622, 'eval_accuracy': 0.8737658674188998, 'eval_best_accuracy': 0.9026798307475318, 'eval_runtime': 46.2176, 'eval_samples_per_second': 61.362, 'eval_steps_per_second': 7.681, 'epoch': 0.04}\n",
+ "{'loss': 0.1531, 'learning_rate': 2.3461900578746113e-05, 'epoch': 0.06}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "74f1eca2317f4a468a8f2ba664044a6b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5168933272361755, 'eval_accuracy': 0.8903385049365303, 'eval_best_accuracy': 0.9026798307475318, 'eval_runtime': 46.274, 'eval_samples_per_second': 61.287, 'eval_steps_per_second': 7.672, 'epoch': 0.06}\n",
+ "{'loss': 0.1143, 'learning_rate': 6.523424644648482e-06, 'epoch': 0.08}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "c99876d60b3945f6a0cade066fb64806",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4572402536869049, 'eval_accuracy': 0.8885754583921015, 'eval_best_accuracy': 0.9026798307475318, 'eval_runtime': 46.27, 'eval_samples_per_second': 61.292, 'eval_steps_per_second': 7.672, 'epoch': 0.08}\n",
+ "{'train_runtime': 584.3615, 'train_samples_per_second': 13.54, 'train_steps_per_second': 1.692, 'train_loss': 0.16910074212794599, 'epoch': 0.1}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | █▁▅▅ |
eval/best_accuracy | ▁▁▁▁ |
eval/loss | ▁█▄▂ |
eval/runtime | ▁▆██ |
eval/samples_per_second | █▃▁▁ |
eval/steps_per_second | █▃▁▁ |
train/epoch | ▁▂▂▄▄▅▅▇▇█ |
train/global_step | ▁▂▂▄▄▅▅▇▇█ |
train/learning_rate | ▁█▆▄▂ |
train/loss | █▃▁▁▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.88858 |
eval/best_accuracy | 0.90268 |
eval/loss | 0.45724 |
eval/runtime | 46.27 |
eval/samples_per_second | 61.292 |
eval/steps_per_second | 7.672 |
train/epoch | 0.1 |
train/global_step | 989 |
train/learning_rate | 1e-05 |
train/loss | 0.1143 |
train/total_flos | 1048082058166272.0 |
train/train_loss | 0.1691 |
train/train_runtime | 584.3615 |
train/train_samples_per_second | 13.54 |
train/train_steps_per_second | 1.692 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run playful-sweep-12 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/hk2674vn
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_190709-hk2674vn/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: vcs6pri7 with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 8.50853544698239e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 840.2753140015418\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "d3a24a6d0c674c67b61e365c4e9430df",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011114901488892631, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_191702-vcs6pri7
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run snowy-sweep-13 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vcs6pri7"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Trying to set _wandb in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set assignments in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Trying to set metric in the hyperparameter search but there is no corresponding field in `TrainingArguments`.\n",
+ "Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at huggingface/CodeBERTa-small-v1 and are newly initialized: ['classifier.out_proj.weight', 'classifier.out_proj.bias', 'classifier.dense.bias', 'classifier.dense.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "53c649cf979748ba98ee0656f86156c4",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.006 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=0.531875…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run snowy-sweep-13 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vcs6pri7
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_191702-vcs6pri7/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Ignored wandb.init() arg project when running a sweep.\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "717058152b64434e95ddc5663e322928",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.011112331688895614, max=1.0…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_191710-vcs6pri7
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run snowy-sweep-13 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vcs6pri7"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'learning_rate' was locked by 'sweep' (ignored update).\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Config item 'max_steps' was locked by 'sweep' (ignored update).\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "b3c512fa49f4469093c316540f023fdc",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/840 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'loss': 0.7452, 'learning_rate': 2.025841773091045e-06, 'epoch': 0.0}\n",
+ "{'loss': 0.3437, 'learning_rate': 7.995784516906686e-05, 'epoch': 0.02}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "79543516f8c44f768bff8e6ce5e81a2e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.5343457460403442, 'eval_accuracy': 0.8846967559943583, 'eval_best_accuracy': 0.8846967559943583, 'eval_runtime': 45.9468, 'eval_samples_per_second': 61.724, 'eval_steps_per_second': 7.726, 'epoch': 0.02}\n",
+ "{'loss': 0.1933, 'learning_rate': 5.9631876032664127e-05, 'epoch': 0.03}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "013c7ee84d064e8990277849f1bab52b",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.7699891328811646, 'eval_accuracy': 0.8526093088857546, 'eval_best_accuracy': 0.8846967559943583, 'eval_runtime': 46.1321, 'eval_samples_per_second': 61.476, 'eval_steps_per_second': 7.695, 'epoch': 0.03}\n",
+ "{'loss': 0.1912, 'learning_rate': 3.209906738962581e-05, 'epoch': 0.05}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "dff6eb4d393b483e9a12fac6785e0f37",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4289516806602478, 'eval_accuracy': 0.889280677009873, 'eval_best_accuracy': 0.889280677009873, 'eval_runtime': 46.2607, 'eval_samples_per_second': 61.305, 'eval_steps_per_second': 7.674, 'epoch': 0.05}\n",
+ "{'loss': 0.1068, 'learning_rate': 8.970527250667182e-06, 'epoch': 0.07}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "f977a56d7dd14a32b4f672216da5fa7e",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.4503030776977539, 'eval_accuracy': 0.8875176304654443, 'eval_best_accuracy': 0.889280677009873, 'eval_runtime': 46.199, 'eval_samples_per_second': 61.387, 'eval_steps_per_second': 7.684, 'epoch': 0.07}\n",
+ "{'loss': 0.1172, 'learning_rate': 0.0, 'epoch': 0.08}\n"
+ ]
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "de925bf0c0ed459d965a93fce2267bd4",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ " 0%| | 0/355 [00:00, ?it/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "{'eval_loss': 0.3944683074951172, 'eval_accuracy': 0.8966854724964739, 'eval_best_accuracy': 0.8966854724964739, 'eval_runtime': 46.2602, 'eval_samples_per_second': 61.305, 'eval_steps_per_second': 7.674, 'epoch': 0.08}\n",
+ "{'train_runtime': 571.7473, 'train_samples_per_second': 11.753, 'train_steps_per_second': 1.469, 'train_loss': 0.1909053745723906, 'epoch': 0.08}\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Waiting for W&B process to finish... (success)."
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "ae02fe1eb9a94183a7ac1218366c1638",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(Label(value='0.003 MB of 0.004 MB uploaded (0.000 MB deduped)\\r'), FloatProgress(value=0.589535…"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ "Run history:
eval/accuracy | ▆▁▇▇█ |
eval/best_accuracy | ▁▁▄▄█ |
eval/loss | ▄█▂▂▁ |
eval/runtime | ▁▅█▇█ |
eval/samples_per_second | █▄▁▂▁ |
eval/steps_per_second | █▄▁▂▁ |
train/epoch | ▁▃▃▄▄▅▅▇▇███ |
train/global_step | ▁▂▂▄▄▅▅▇▇███ |
train/learning_rate | ▁█▆▄▂▁ |
train/loss | █▄▂▂▁▁ |
train/total_flos | ▁ |
train/train_loss | ▁ |
train/train_runtime | ▁ |
train/train_samples_per_second | ▁ |
train/train_steps_per_second | ▁ |
Run summary:
eval/accuracy | 0.89669 |
eval/best_accuracy | 0.89669 |
eval/loss | 0.39447 |
eval/runtime | 46.2602 |
eval/samples_per_second | 61.305 |
eval/steps_per_second | 7.674 |
train/epoch | 0.08 |
train/global_step | 840 |
train/learning_rate | 0.0 |
train/loss | 0.1172 |
train/total_flos | 890180918968320.0 |
train/train_loss | 0.19091 |
train/train_runtime | 571.7473 |
train/train_samples_per_second | 11.753 |
train/train_steps_per_second | 1.469 |
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run snowy-sweep-13 at: https://wandb.ai/eschwartz/OO_Fine_Tune/runs/vcs6pri7
Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Find logs at: ./wandb/run-20230908_191710-vcs6pri7/logs
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Sweep Agent: Waiting for job.\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Job received.\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: Agent Starting Run: qhmfwd1q with config:\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tlearning_rate: 7.727778638808646e-05\n",
+ "\u001b[34m\u001b[1mwandb\u001b[0m: \tmax_steps: 660.5416419065895\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "Tracking run with wandb version 0.15.10"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Run data is saved locally in /home/ed/Downloads/OO-Fine-Tune/wandb/run-20230908_192656-qhmfwd1q
"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "Syncing run bright-sweep-14 to Weights & Biases (docs)
Sweep page: https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View project at https://wandb.ai/eschwartz/OO_Fine_Tune"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View sweep at https://wandb.ai/eschwartz/OO_Fine_Tune/sweeps/1wpa6h8x"
+ ],
+ "text/plain": [
+ ""
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ " View run at