From 5bd6636ed1b3c15e5a98a32d945a7c81215ff859 Mon Sep 17 00:00:00 2001 From: Fedor Vitiugin Date: Thu, 25 Sep 2025 18:27:37 +0300 Subject: [PATCH 1/2] training args update --- ex4_parameters.ipynb | 1342 +++++++++++++++++++++--------------------- 1 file changed, 672 insertions(+), 670 deletions(-) diff --git a/ex4_parameters.ipynb b/ex4_parameters.ipynb index 81d79e3..50eede3 100644 --- a/ex4_parameters.ipynb +++ b/ex4_parameters.ipynb @@ -3,8 +3,8 @@ { "cell_type": "markdown", "metadata": { - "id": "view-in-github", - "colab_type": "text" + "colab_type": "text", + "id": "view-in-github" }, "source": [ "\"Open" @@ -12,96 +12,78 @@ }, { "cell_type": "markdown", - "source": [ - "# Setup" - ], "metadata": { "id": "wo13ZXoZYB6J" - } + }, + "source": [ + "# Setup" + ] }, { "cell_type": "code", - "source": [ - "!pip3 install -q transformers datasets evaluate accelerate" - ], + "execution_count": 6, "metadata": { "id": "4pquj9Xoxaza" }, - "execution_count": 6, - "outputs": [] + "outputs": [], + "source": [ + "!pip3 install -q transformers datasets evaluate accelerate" + ] }, { "cell_type": "code", + "execution_count": 7, + "metadata": { + "id": "cQ63zw6BY7tn" + }, + "outputs": [], "source": [ "from pprint import pprint\n", "import logging\n", "\n", "logging.disable(logging.INFO)" - ], - "metadata": { - "id": "cQ63zw6BY7tn" - }, - "execution_count": 7, - "outputs": [] + ] }, { "cell_type": "markdown", + "metadata": { + "id": "W4x7GbT2ZKUJ" + }, "source": [ "---\n", "# Download and prepare data" - ], - "metadata": { - "id": "W4x7GbT2ZKUJ" - } + ] }, { "cell_type": "code", + "execution_count": 8, + "metadata": { + "id": "5DKskTuoyCf-" + }, + "outputs": [], "source": [ "import datasets\n", "\n", "dataset = datasets.load_dataset('imdb')\n", "dataset = dataset.shuffle() #This is never a bad idea, datasets may have ordering to them, which is not what we want\n", "del dataset[\"unsupervised\"] # Delete the unlabeled part of the dataset to make things faster" - ], - "metadata": { - "id": "5DKskTuoyCf-" - }, - "execution_count": 8, - "outputs": [] + ] }, { "cell_type": "markdown", + "metadata": { + "id": "8KF9UtzUbrBA" + }, "source": [ "---\n", "\n", "# Tokenize and vectorize data" - ], - "metadata": { - "id": "8KF9UtzUbrBA" - } + ] }, { "cell_type": "code", - "source": [ - "import transformers\n", - "\n", - "model_name = \"bert-base-cased\"\n", - "tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)\n", - "\n", - "# Define a simple function that applies the tokenizer\n", - "def tokenize(example):\n", - " return tokenizer(\n", - " example[\"text\"],\n", - " max_length=128,\n", - " truncation=True,\n", - " )\n", - "\n", - "# Apply the tokenizer to the whole dataset using .map()\n", - "dataset = dataset.map(tokenize)" - ], + "execution_count": 9, "metadata": { - "id": "wjrAGcFtymJF", - "outputId": "9a35e1d5-c074-4598-828f-71326bf24f87", "colab": { "base_uri": "https://localhost:8080/", "height": 137, @@ -129,63 +111,86 @@ "1bdf39342f314fbba05e0a0d066f2a0f", "432f18bd11114415bd5fb91cce8de324" ] - } + }, + "id": "wjrAGcFtymJF", + "outputId": "9a35e1d5-c074-4598-828f-71326bf24f87" }, - "execution_count": 9, "outputs": [ { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n", " warnings.warn(\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "Map: 0%| | 0/25000 [00:00" - ], "text/html": [ "\n", "
\n", @@ -470,16 +425,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -488,13 +443,17 @@ " [3125/3125 00:14]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -502,18 +461,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 5e-06 Accuracy: 0.5\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -563,16 +518,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -581,13 +536,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -595,18 +554,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 5e-05 Accuracy: 0.52612\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -656,16 +611,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -674,13 +629,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -688,18 +647,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.0005 Accuracy: 0.65312\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -749,16 +704,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -767,13 +722,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -781,18 +740,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.005 Accuracy: 0.72672\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -842,16 +797,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -860,13 +815,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -874,18 +833,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.005 Accuracy: 0.72672\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -935,16 +890,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -953,13 +908,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -967,18 +926,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.05 Accuracy: 0.7134\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -1028,16 +983,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -1046,48 +1001,91 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.5 Accuracy: 0.5198\n" ] } + ], + "source": [ + "for lr in [0.000005, 0.00005, 0.0005, 0.005, 0.05, 0.5]:\n", + "\n", + " # create the model\n", + " config = BasicConfig(\n", + " vocab_size = tokenizer.vocab_size,\n", + " num_labels = len(set(dataset['train']['label'])),\n", + " embedding_dim = 64,\n", + " filter_size = 3,\n", + " num_filters = 10,\n", + " )\n", + "\n", + " model = SimpleCNN(config)\n", + "\n", + " # Set training arguments\n", + " trainer_args = transformers.TrainingArguments(\n", + " \"checkpoints\",\n", + " eval_strategy=\"steps\",\n", + " logging_strategy=\"steps\",\n", + " load_best_model_at_end=True,\n", + " eval_steps=500,\n", + " logging_steps=500,\n", + " learning_rate=lr, # <--- parameter goes here\n", + " per_device_train_batch_size=8,\n", + " max_steps=2500,\n", + " report_to=\"none\", # skip wandb login\n", + " )\n", + "\n", + " trainer = transformers.Trainer(\n", + " model=model,\n", + " args=trainer_args,\n", + " train_dataset=dataset[\"train\"],\n", + " eval_dataset=dataset[\"test\"],\n", + " compute_metrics=compute_accuracy,\n", + " data_collator=data_collator,\n", + " callbacks=[transformers.EarlyStoppingCallback(early_stopping_patience=5), LogSavingCallback()]\n", + " )\n", + "\n", + " trainer.train()\n", + " eval_results = trainer.evaluate(dataset[\"test\"])\n", + " print('Learning rate:', lr, 'Accuracy:', eval_results['eval_accuracy'])" ] }, { "cell_type": "markdown", + "metadata": { + "id": "KL6N5tz1mddD" + }, "source": [ "---\n", "# Hyperparameter search – Second option\n", "\n", "* Hyperparameter search using [Optuna](https://optuna.org/)" - ], - "metadata": { - "id": "KL6N5tz1mddD" - } + ] }, { "cell_type": "code", - "source": [ - "!pip install optuna" - ], + "execution_count": 13, "metadata": { - "id": "Hes_HBvOmrKD", - "outputId": "1e5f78e0-116b-4a95-f731-a4efcfd2a353", "colab": { "base_uri": "https://localhost:8080/" - } + }, + "id": "Hes_HBvOmrKD", + "outputId": "1e5f78e0-116b-4a95-f731-a4efcfd2a353" }, - "execution_count": 13, "outputs": [ { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Collecting optuna\n", " Downloading optuna-4.0.0-py3-none-any.whl.metadata (16 kB)\n", @@ -1116,75 +1114,26 @@ "Successfully installed Mako-1.3.5 alembic-1.13.2 colorlog-6.8.2 optuna-4.0.0\n" ] } + ], + "source": [ + "!pip install optuna" ] }, { "cell_type": "code", - "source": [ - "import optuna\n", - "\n", - "def objective(trial):\n", - " # Define the search space for hyperparameters\n", - " learning_rate = trial.suggest_float(\"learning_rate\", 5e-4, 5e-2, log=True)\n", - " num_filters = trial.suggest_categorical(\"num_filters\", [10, 16, 24])\n", - "\n", - " # create the model\n", - " config = BasicConfig(\n", - " vocab_size = tokenizer.vocab_size,\n", - " num_labels = len(set(dataset['train']['label'])),\n", - " embedding_dim = 64,\n", - " filter_size = 3,\n", - " num_filters = num_filters, # <--- parameter goes here\n", - " )\n", - "\n", - " model = SimpleCNN(config)\n", - "\n", - " # Set training arguments\n", - " trainer_args = transformers.TrainingArguments(\n", - " \"checkpoints\",\n", - " evaluation_strategy=\"steps\",\n", - " logging_strategy=\"steps\",\n", - " load_best_model_at_end=True,\n", - " eval_steps=500,\n", - " logging_steps=500,\n", - " learning_rate=learning_rate, # <--- parameter goes here\n", - " per_device_train_batch_size=8,\n", - " max_steps=2500,\n", - " )\n", - "\n", - " trainer = transformers.Trainer(\n", - " model=model,\n", - " args=trainer_args,\n", - " train_dataset=dataset[\"train\"],\n", - " eval_dataset=dataset[\"test\"],\n", - " compute_metrics=compute_accuracy,\n", - " data_collator=data_collator,\n", - " callbacks=[transformers.EarlyStoppingCallback(early_stopping_patience=5), LogSavingCallback()]\n", - " )\n", - "\n", - " trainer.train()\n", - " eval_results = trainer.evaluate(dataset[\"test\"])\n", - " print('Learning rate:', learning_rate, 'Filters:', num_filters, 'Accuracy:', eval_results['eval_accuracy'])\n", - " return eval_results['eval_accuracy']\n", - "\n", - "\n", - "\n", - "study = optuna.create_study(direction=\"maximize\")\n", - "study.optimize(objective, n_trials=3) # <--- How many trials we run, more would be needed in real case!" - ], + "execution_count": null, "metadata": { - "id": "Ag66TkGumvSU", - "outputId": "1d0ad2ac-4874-41ef-db7f-c873b23468f1", "colab": { "base_uri": "https://localhost:8080/", "height": 962 - } + }, + "id": "Ag66TkGumvSU", + "outputId": "1d0ad2ac-4874-41ef-db7f-c873b23468f1" }, - "execution_count": 18, "outputs": [ { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -1192,11 +1141,7 @@ ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -1246,16 +1191,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -1264,13 +1209,17 @@ " [3125/3125 00:13]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -1278,18 +1227,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.0032891344286570525 Filters: 10 Accuracy: 0.72072\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -1339,16 +1284,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -1357,13 +1302,17 @@ " [3125/3125 00:12]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stderr", + "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", " warnings.warn(\n", @@ -1371,18 +1320,14 @@ ] }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.002434791974958158 Filters: 16 Accuracy: 0.73228\n" ] }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "
\n", @@ -1432,16 +1377,16 @@ " \n", " \n", "

" + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "display_data", "data": { - "text/plain": [ - "" - ], "text/html": [ "\n", "

\n", @@ -1450,29 +1395,87 @@ " [3125/3125 00:13]\n", "
\n", " " + ], + "text/plain": [ + "" ] }, - "metadata": {} + "metadata": {}, + "output_type": "display_data" }, { - "output_type": "stream", "name": "stdout", + "output_type": "stream", "text": [ "Learning rate: 0.03601436163120907 Filters: 24 Accuracy: 0.7332\n" ] } + ], + "source": [ + "import optuna\n", + "\n", + "def objective(trial):\n", + " # Define the search space for hyperparameters\n", + " learning_rate = trial.suggest_float(\"learning_rate\", 5e-4, 5e-2, log=True)\n", + " num_filters = trial.suggest_categorical(\"num_filters\", [10, 16, 24])\n", + "\n", + " # create the model\n", + " config = BasicConfig(\n", + " vocab_size = tokenizer.vocab_size,\n", + " num_labels = len(set(dataset['train']['label'])),\n", + " embedding_dim = 64,\n", + " filter_size = 3,\n", + " num_filters = num_filters, # <--- parameter goes here\n", + " )\n", + "\n", + " model = SimpleCNN(config)\n", + "\n", + " # Set training arguments\n", + " trainer_args = transformers.TrainingArguments(\n", + " \"checkpoints\",\n", + " eval_strategy=\"steps\",\n", + " logging_strategy=\"steps\",\n", + " load_best_model_at_end=True,\n", + " eval_steps=500,\n", + " logging_steps=500,\n", + " learning_rate=learning_rate, # <--- parameter goes here\n", + " per_device_train_batch_size=8,\n", + " max_steps=2500,\n", + " report_to=\"none\", # skip wandb login\n", + " )\n", + "\n", + " trainer = transformers.Trainer(\n", + " model=model,\n", + " args=trainer_args,\n", + " train_dataset=dataset[\"train\"],\n", + " eval_dataset=dataset[\"test\"],\n", + " compute_metrics=compute_accuracy,\n", + " data_collator=data_collator,\n", + " callbacks=[transformers.EarlyStoppingCallback(early_stopping_patience=5), LogSavingCallback()]\n", + " )\n", + "\n", + " trainer.train()\n", + " eval_results = trainer.evaluate(dataset[\"test\"])\n", + " print('Learning rate:', learning_rate, 'Filters:', num_filters, 'Accuracy:', eval_results['eval_accuracy'])\n", + " return eval_results['eval_accuracy']\n", + "\n", + "\n", + "\n", + "study = optuna.create_study(direction=\"maximize\")\n", + "study.optimize(objective, n_trials=3) # <--- How many trials we run, more would be needed in real case!" ] } ], "metadata": { + "accelerator": "GPU", "colab": { "collapsed_sections": [ "wo13ZXoZYB6J" ], - "name": "hf_trainer_cnn.ipynb", - "provenance": [], "gpuType": "T4", - "include_colab_link": true + "include_colab_link": true, + "name": "hf_trainer_cnn.ipynb", + "provenance": [] }, "kernelspec": { "display_name": "Python 3", @@ -1483,98 +1486,25 @@ }, "widgets": { "application/vnd.jupyter.widget-state+json": { - "6a6875eea30b4a64b87996f30d6b9b0e": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_ca38330d9fee4f6eb3db8dd7c62d3b86", - "IPY_MODEL_ac737737ea08455dbcad7d813b3ba794", - "IPY_MODEL_f80427bc9bb34432a15c110c41552f1d" - ], - "layout": "IPY_MODEL_d2f642b153b441b39d3e13c8dc291de5" - } - }, - "ca38330d9fee4f6eb3db8dd7c62d3b86": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_976a880692e2476c8bf9e0f6a6822129", - "placeholder": "​", - "style": "IPY_MODEL_bec81b91b5bd4dd9a425ab7c65ccbb3c", - "value": "Map: 100%" - } - }, - "ac737737ea08455dbcad7d813b3ba794": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_f05ac4f5a4d44ec2b659a467f037978d", - "max": 25000, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_fa20945c5d7a4089abba70a393de4173", - "value": 25000 - } - }, - "f80427bc9bb34432a15c110c41552f1d": { + "0485ff6f20ec4e3bb225c942ba914ef0": { "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", "state": { - "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "DescriptionStyleModel", "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_2f7a6c1f2e3a49c1b2b9df8b263e4437", - "placeholder": "​", - "style": "IPY_MODEL_eec6fa9095a141ef95285777a970a390", - "value": " 25000/25000 [01:33<00:00, 204.73 examples/s]" + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" } }, - "d2f642b153b441b39d3e13c8dc291de5": { + "1bdf39342f314fbba05e0a0d066f2a0f": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -1623,10 +1553,34 @@ "width": null } }, - "976a880692e2476c8bf9e0f6a6822129": { + "1c4288674e7245e9b4697b55950731ef": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "FloatProgressModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_6c8d2ad0ffce4d2081369030a4c4304d", + "max": 4203, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_db761c9a410f4b8bb1b2ec88fb0b847a", + "value": 4203 + } + }, + "2f7a6c1f2e3a49c1b2b9df8b263e4437": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -1675,10 +1629,10 @@ "width": null } }, - "bec81b91b5bd4dd9a425ab7c65ccbb3c": { + "432f18bd11114415bd5fb91cce8de324": { "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -1690,10 +1644,31 @@ "description_width": "" } }, - "f05ac4f5a4d44ec2b659a467f037978d": { + "484ce987ce134017a6444a883f483eb1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_8a578b9edde748a9bee19f220e90bcf7", + "placeholder": "​", + "style": "IPY_MODEL_0485ff6f20ec4e3bb225c942ba914ef0", + "value": "Map: 100%" + } + }, + "61a2564e98294a3b98f202ecb051e1ce": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -1742,26 +1717,31 @@ "width": null } }, - "fa20945c5d7a4089abba70a393de4173": { + "63f44a1307c44b9e80d33f556bf6c862": { "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", + "model_name": "HTMLModel", "state": { + "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", + "_model_name": "HTMLModel", "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_1bdf39342f314fbba05e0a0d066f2a0f", + "placeholder": "​", + "style": "IPY_MODEL_432f18bd11114415bd5fb91cce8de324", + "value": " 25000/25000 [01:06<00:00, 786.87 examples/s]" } }, - "2f7a6c1f2e3a49c1b2b9df8b263e4437": { + "646fc70d8d214df5905d0783193312fa": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -1810,25 +1790,10 @@ "width": null } }, - "eec6fa9095a141ef95285777a970a390": { + "6a6875eea30b4a64b87996f30d6b9b0e": { "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "6d68fd610b8c48f08ee6f56101119802": { - "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", - "model_module_version": "1.5.0", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -1840,83 +1805,17 @@ "_view_name": "HBoxView", "box_style": "", "children": [ - "IPY_MODEL_484ce987ce134017a6444a883f483eb1", - "IPY_MODEL_d0d203490e554fe5b62a2aca06ec2b85", - "IPY_MODEL_63f44a1307c44b9e80d33f556bf6c862" + "IPY_MODEL_ca38330d9fee4f6eb3db8dd7c62d3b86", + "IPY_MODEL_ac737737ea08455dbcad7d813b3ba794", + "IPY_MODEL_f80427bc9bb34432a15c110c41552f1d" ], - "layout": "IPY_MODEL_fd91bdfb63c9476195d08b56fcf8f503" - } - }, - "484ce987ce134017a6444a883f483eb1": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_8a578b9edde748a9bee19f220e90bcf7", - "placeholder": "​", - "style": "IPY_MODEL_0485ff6f20ec4e3bb225c942ba914ef0", - "value": "Map: 100%" - } - }, - "d0d203490e554fe5b62a2aca06ec2b85": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_646fc70d8d214df5905d0783193312fa", - "max": 25000, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_958792a865f94e04afac06938ab615f9", - "value": 25000 - } - }, - "63f44a1307c44b9e80d33f556bf6c862": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_1bdf39342f314fbba05e0a0d066f2a0f", - "placeholder": "​", - "style": "IPY_MODEL_432f18bd11114415bd5fb91cce8de324", - "value": " 25000/25000 [01:06<00:00, 786.87 examples/s]" + "layout": "IPY_MODEL_d2f642b153b441b39d3e13c8dc291de5" } }, - "fd91bdfb63c9476195d08b56fcf8f503": { + "6c8d2ad0ffce4d2081369030a4c4304d": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -1965,10 +1864,32 @@ "width": null } }, - "8a578b9edde748a9bee19f220e90bcf7": { + "6d68fd610b8c48f08ee6f56101119802": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_484ce987ce134017a6444a883f483eb1", + "IPY_MODEL_d0d203490e554fe5b62a2aca06ec2b85", + "IPY_MODEL_63f44a1307c44b9e80d33f556bf6c862" + ], + "layout": "IPY_MODEL_fd91bdfb63c9476195d08b56fcf8f503" + } + }, + "7a10fc4726e6413397d474c3b5f187b9": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2017,10 +1938,10 @@ "width": null } }, - "0485ff6f20ec4e3bb225c942ba914ef0": { + "82de00af0c6140c49a1ab5868158b93b": { "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -2032,10 +1953,10 @@ "description_width": "" } }, - "646fc70d8d214df5905d0783193312fa": { + "8a578b9edde748a9bee19f220e90bcf7": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2086,8 +2007,8 @@ }, "958792a865f94e04afac06938ab615f9": { "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -2100,10 +2021,10 @@ "description_width": "" } }, - "1bdf39342f314fbba05e0a0d066f2a0f": { + "976a880692e2476c8bf9e0f6a6822129": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2152,47 +2073,86 @@ "width": null } }, - "432f18bd11114415bd5fb91cce8de324": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", + "ab20b48f72ce4486a08ccea3f4624486": { + "model_module": "@jupyter-widgets/base", + "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", + "_model_module": "@jupyter-widgets/base", + "_model_module_version": "1.2.0", + "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" + "_view_name": "LayoutView", + "align_content": null, + "align_items": null, + "align_self": null, + "border": null, + "bottom": null, + "display": null, + "flex": null, + "flex_flow": null, + "grid_area": null, + "grid_auto_columns": null, + "grid_auto_flow": null, + "grid_auto_rows": null, + "grid_column": null, + "grid_gap": null, + "grid_row": null, + "grid_template_areas": null, + "grid_template_columns": null, + "grid_template_rows": null, + "height": null, + "justify_content": null, + "justify_items": null, + "left": null, + "margin": null, + "max_height": null, + "max_width": null, + "min_height": null, + "min_width": null, + "object_fit": null, + "object_position": null, + "order": null, + "overflow": null, + "overflow_x": null, + "overflow_y": null, + "padding": null, + "right": null, + "top": null, + "visibility": null, + "width": null } }, - "ee04263c2ef846e5b1ba93ad687e37b1": { + "ac737737ea08455dbcad7d813b3ba794": { "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_bde5f2c9b4ef4e8c82fddbdb83a67a1e", - "IPY_MODEL_1c4288674e7245e9b4697b55950731ef", - "IPY_MODEL_eb5b4d35582542d1bdd0296817db1daf" - ], - "layout": "IPY_MODEL_61a2564e98294a3b98f202ecb051e1ce" + "_view_name": "ProgressView", + "bar_style": "success", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_f05ac4f5a4d44ec2b659a467f037978d", + "max": 25000, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_fa20945c5d7a4089abba70a393de4173", + "value": 25000 } }, "bde5f2c9b4ef4e8c82fddbdb83a67a1e": { "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", "model_module_version": "1.5.0", + "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", @@ -2210,55 +2170,85 @@ "value": "Downloading builder script: 100%" } }, - "1c4288674e7245e9b4697b55950731ef": { + "bec81b91b5bd4dd9a425ab7c65ccbb3c": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "ca38330d9fee4f6eb3db8dd7c62d3b86": { "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", "model_module_version": "1.5.0", + "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", + "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", + "_view_name": "HTMLView", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_6c8d2ad0ffce4d2081369030a4c4304d", - "max": 4203, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_db761c9a410f4b8bb1b2ec88fb0b847a", - "value": 4203 + "layout": "IPY_MODEL_976a880692e2476c8bf9e0f6a6822129", + "placeholder": "​", + "style": "IPY_MODEL_bec81b91b5bd4dd9a425ab7c65ccbb3c", + "value": "Map: 100%" } }, - "eb5b4d35582542d1bdd0296817db1daf": { + "ca67aa97ba124742a9c3688e03f21f96": { "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "DescriptionStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "description_width": "" + } + }, + "d0d203490e554fe5b62a2aca06ec2b85": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", + "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", - "_view_name": "HTMLView", + "_view_name": "ProgressView", + "bar_style": "success", "description": "", "description_tooltip": null, - "layout": "IPY_MODEL_7a10fc4726e6413397d474c3b5f187b9", - "placeholder": "​", - "style": "IPY_MODEL_82de00af0c6140c49a1ab5868158b93b", - "value": " 4.20k/4.20k [00:00<00:00, 182kB/s]" + "layout": "IPY_MODEL_646fc70d8d214df5905d0783193312fa", + "max": 25000, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_958792a865f94e04afac06938ab615f9", + "value": 25000 } }, - "61a2564e98294a3b98f202ecb051e1ce": { + "d2f642b153b441b39d3e13c8dc291de5": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2307,62 +2297,69 @@ "width": null } }, - "ab20b48f72ce4486a08ccea3f4624486": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", + "db761c9a410f4b8bb1b2ec88fb0b847a": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null + "_view_name": "StyleView", + "bar_color": null, + "description_width": "" } }, - "ca67aa97ba124742a9c3688e03f21f96": { + "eb5b4d35582542d1bdd0296817db1daf": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_7a10fc4726e6413397d474c3b5f187b9", + "placeholder": "​", + "style": "IPY_MODEL_82de00af0c6140c49a1ab5868158b93b", + "value": " 4.20k/4.20k [00:00<00:00, 182kB/s]" + } + }, + "ee04263c2ef846e5b1ba93ad687e37b1": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "HBoxModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HBoxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HBoxView", + "box_style": "", + "children": [ + "IPY_MODEL_bde5f2c9b4ef4e8c82fddbdb83a67a1e", + "IPY_MODEL_1c4288674e7245e9b4697b55950731ef", + "IPY_MODEL_eb5b4d35582542d1bdd0296817db1daf" + ], + "layout": "IPY_MODEL_61a2564e98294a3b98f202ecb051e1ce" + } + }, + "eec6fa9095a141ef95285777a970a390": { "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", + "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -2374,10 +2371,10 @@ "description_width": "" } }, - "6c8d2ad0ffce4d2081369030a4c4304d": { + "f05ac4f5a4d44ec2b659a467f037978d": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2426,10 +2423,31 @@ "width": null } }, - "db761c9a410f4b8bb1b2ec88fb0b847a": { + "f80427bc9bb34432a15c110c41552f1d": { "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", + "model_name": "HTMLModel", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "HTMLModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "HTMLView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_2f7a6c1f2e3a49c1b2b9df8b263e4437", + "placeholder": "​", + "style": "IPY_MODEL_eec6fa9095a141ef95285777a970a390", + "value": " 25000/25000 [01:33<00:00, 204.73 examples/s]" + } + }, + "fa20945c5d7a4089abba70a393de4173": { + "model_module": "@jupyter-widgets/controls", + "model_module_version": "1.5.0", + "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", @@ -2442,10 +2460,10 @@ "description_width": "" } }, - "7a10fc4726e6413397d474c3b5f187b9": { + "fd91bdfb63c9476195d08b56fcf8f503": { "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", "model_module_version": "1.2.0", + "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", @@ -2493,26 +2511,10 @@ "visibility": null, "width": null } - }, - "82de00af0c6140c49a1ab5868158b93b": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } } } - }, - "accelerator": "GPU" + } }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +} From 6888715d2da5d0344a1523ee8d5a46f3ef6c8023 Mon Sep 17 00:00:00 2001 From: Fedor Vitiugin Date: Thu, 25 Sep 2025 18:31:19 +0300 Subject: [PATCH 2/2] cleared outputs --- ex4_parameters.ipynb | 1040 +----------------------------------------- 1 file changed, 12 insertions(+), 1028 deletions(-) diff --git a/ex4_parameters.ipynb b/ex4_parameters.ipynb index 50eede3..a030193 100644 --- a/ex4_parameters.ipynb +++ b/ex4_parameters.ipynb @@ -21,7 +21,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": null, "metadata": { "id": "4pquj9Xoxaza" }, @@ -32,7 +32,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": null, "metadata": { "id": "cQ63zw6BY7tn" }, @@ -56,7 +56,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": null, "metadata": { "id": "5DKskTuoyCf-" }, @@ -82,7 +82,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", @@ -115,44 +115,7 @@ "id": "wjrAGcFtymJF", "outputId": "9a35e1d5-c074-4598-828f-71326bf24f87" }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n", - " warnings.warn(\n" - ] - }, - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "6a6875eea30b4a64b87996f30d6b9b0e", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "Map: 0%| | 0/25000 [00:00\n", - " \n", - " \n", - " [2500/2500 03:13, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.9646000.9642760.500000
10000.9600000.9376270.500000
15000.9492000.9196020.500000
20000.9160000.9094440.500000
25000.9066000.9062300.500000

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:14]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 5e-06 Accuracy: 0.5\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 02:34, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6967000.6956650.509920
10000.6956000.6938030.518040
15000.6934000.6927340.523360
20000.6918000.6918760.525560
25000.6918000.6916650.526120

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 5e-05 Accuracy: 0.52612\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 02:58, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6881000.6736490.578840
10000.6642000.6522780.599360
15000.6380000.6298750.639240
20000.6194000.6197520.647800
25000.6168000.6166340.653120

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.0005 Accuracy: 0.65312\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 02:25, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6865000.6372280.626240
10000.6159000.6649380.622760
15000.5826000.5749180.701320
20000.5491000.5612850.706720
25000.5492000.5347740.726720

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.005 Accuracy: 0.72672\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 03:04, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6865000.6372280.626240
10000.6159000.6649380.622760
15000.5826000.5749180.701320
20000.5491000.5612850.706720
25000.5492000.5347740.726720

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.005 Accuracy: 0.72672\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 02:27, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5001.3320001.0476780.551920
10001.2468000.8840910.574600
15000.9887000.7300610.610720
20000.8373000.8308930.609360
25000.6146000.5718520.713400

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.05 Accuracy: 0.7134\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 02:33, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
500373.884900464.3896790.501080
1000434.300200237.6393590.523120
1500248.097100204.1300960.504400
2000118.08420035.6789820.493760
250030.1166001.6548390.519800

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.5 Accuracy: 0.5198\n" - ] - } - ], + "outputs": [], "source": [ "for lr in [0.000005, 0.00005, 0.0005, 0.005, 0.05, 0.5]:\n", "\n", @@ -1074,7 +370,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" @@ -1082,39 +378,7 @@ "id": "Hes_HBvOmrKD", "outputId": "1e5f78e0-116b-4a95-f731-a4efcfd2a353" }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Collecting optuna\n", - " Downloading optuna-4.0.0-py3-none-any.whl.metadata (16 kB)\n", - "Collecting alembic>=1.5.0 (from optuna)\n", - " Downloading alembic-1.13.2-py3-none-any.whl.metadata (7.4 kB)\n", - "Collecting colorlog (from optuna)\n", - " Downloading colorlog-6.8.2-py3-none-any.whl.metadata (10 kB)\n", - "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from optuna) (1.26.4)\n", - "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from optuna) (24.1)\n", - "Requirement already satisfied: sqlalchemy>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from optuna) (2.0.34)\n", - "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from optuna) (4.66.5)\n", - "Requirement already satisfied: PyYAML in /usr/local/lib/python3.10/dist-packages (from optuna) (6.0.2)\n", - "Collecting Mako (from alembic>=1.5.0->optuna)\n", - " Downloading Mako-1.3.5-py3-none-any.whl.metadata (2.9 kB)\n", - "Requirement already satisfied: typing-extensions>=4 in /usr/local/lib/python3.10/dist-packages (from alembic>=1.5.0->optuna) (4.12.2)\n", - "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.10/dist-packages (from sqlalchemy>=1.3.0->optuna) (3.1.0)\n", - "Requirement already satisfied: MarkupSafe>=0.9.2 in /usr/local/lib/python3.10/dist-packages (from Mako->alembic>=1.5.0->optuna) (2.1.5)\n", - "Downloading optuna-4.0.0-py3-none-any.whl (362 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m362.8/362.8 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading alembic-1.13.2-py3-none-any.whl (232 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m233.0/233.0 kB\u001b[0m \u001b[31m16.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hDownloading colorlog-6.8.2-py3-none-any.whl (11 kB)\n", - "Downloading Mako-1.3.5-py3-none-any.whl (78 kB)\n", - "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.6/78.6 kB\u001b[0m \u001b[31m5.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", - "\u001b[?25hInstalling collected packages: Mako, colorlog, alembic, optuna\n", - "Successfully installed Mako-1.3.5 alembic-1.13.2 colorlog-6.8.2 optuna-4.0.0\n" - ] - } - ], + "outputs": [], "source": [ "!pip install optuna" ] @@ -1130,287 +394,7 @@ "id": "Ag66TkGumvSU", "outputId": "1d0ad2ac-4874-41ef-db7f-c873b23468f1" }, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 03:21, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6722000.6116830.656320
10000.6090000.6377740.634880
15000.5757000.5796350.694880
20000.5529000.5610090.709440
25000.5433000.5464720.720720

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:13]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.0032891344286570525 Filters: 10 Accuracy: 0.72072\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 03:13, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5000.6851000.6367670.627360
10000.6069000.6145090.656960
15000.5654000.5562620.711400
20000.5218000.5342690.724560
25000.5216000.5228140.732280

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:12]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1525: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of πŸ€— Transformers. Use `eval_strategy` instead\n", - " warnings.warn(\n", - "max_steps is given, it will override any value given in num_train_epochs\n" - ] - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.002434791974958158 Filters: 16 Accuracy: 0.73228\n" - ] - }, - { - "data": { - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [2500/2500 03:04, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining LossValidation LossAccuracy
5001.6043000.8831120.592320
10001.5142001.5274170.613640
15001.3915000.8028370.654840
20000.7695000.6607510.682480
25000.6183000.5367510.733200

" - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "text/html": [ - "\n", - "

\n", - " \n", - " \n", - " [3125/3125 00:13]\n", - "
\n", - " " - ], - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Learning rate: 0.03601436163120907 Filters: 24 Accuracy: 0.7332\n" - ] - } - ], + "outputs": [], "source": [ "import optuna\n", "\n",