Upload 6 files

Browse files

Files changed (6) hide show

config.json +26 -0
osiria_minilm_l6_h384_italian_qa_evaluation.ipynb +839 -0
pytorch_model.bin +3 -0
special_tokens_map.json +15 -0
tokenizer.json +0 -0
tokenizer_config.json +19 -0

config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 30498
+}

osiria_minilm_l6_h384_italian_qa_evaluation.ipynb ADDED Viewed

	@@ -0,0 +1,839 @@

+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "accelerator": "GPU"
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# osiria/minilm-italian-l6-h384-question-answering\n",
+        "## test set metrics"
+      ],
+      "metadata": {
+        "id": "oub2ir8ZDkrH"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "02K9xO6Gvto1",
+        "outputId": "3f72da34-6228-451a-c656-3f9fbb358e7f"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting git+https://github.com/huggingface/transformers\n",
+            "  Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-zw2jat5c\n",
+            "  Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-zw2jat5c\n",
+            "  Resolved https://github.com/huggingface/transformers to commit df5c5c62ae253055336f5bb0828ca8e3e15ab6bd\n",
+            "  Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
+            "  Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
+            "  Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (3.13.1)\n",
+            "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.19.4)\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (1.23.5)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (23.2)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (6.0.1)\n",
+            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (2023.6.3)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (2.31.0)\n",
+            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.15.0)\n",
+            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.4.1)\n",
+            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (4.66.1)\n",
+            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers==4.36.0.dev0) (2023.6.0)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers==4.36.0.dev0) (4.5.0)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (3.6)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (2023.11.17)\n",
+            "Building wheels for collected packages: transformers\n",
+            "  Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
+            "  Created wheel for transformers: filename=transformers-4.36.0.dev0-py3-none-any.whl size=8195433 sha256=8bf5185dab843815883ed25caa99c87242dfa4ee86bdfdc0be3e42a6cfa8a17c\n",
+            "  Stored in directory: /tmp/pip-ephem-wheel-cache-_xtobubu/wheels/c0/14/d6/6c9a5582d2ac191ec0a483be151a4495fe1eb2a6706ca49f1b\n",
+            "Successfully built transformers\n",
+            "Installing collected packages: transformers\n",
+            "  Attempting uninstall: transformers\n",
+            "    Found existing installation: transformers 4.35.2\n",
+            "    Uninstalling transformers-4.35.2:\n",
+            "      Successfully uninstalled transformers-4.35.2\n",
+            "Successfully installed transformers-4.36.0.dev0\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install git+https://github.com/huggingface/transformers"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install datasets"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "VKgybrUswa1q",
+        "outputId": "033a0aae-2528-4994-90b0-06c6d01bfdb3"
+      },
+      "execution_count": 2,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting datasets\n",
+            "  Downloading datasets-2.15.0-py3-none-any.whl (521 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.2/521.2 kB\u001b[0m \u001b[31m3.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.23.5)\n",
+            "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n",
+            "Collecting pyarrow-hotfix (from datasets)\n",
+            "  Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
+            "Collecting dill<0.3.8,>=0.3.0 (from datasets)\n",
+            "  Downloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n",
+            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n",
+            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.1)\n",
+            "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n",
+            "Collecting multiprocess (from datasets)\n",
+            "  Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: fsspec[http]<=2023.10.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n",
+            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.1)\n",
+            "Requirement already satisfied: huggingface-hub>=0.18.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.19.4)\n",
+            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.2)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n",
+            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n",
+            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\n",
+            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.3)\n",
+            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.0)\n",
+            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
+            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.18.0->datasets) (3.13.1)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.18.0->datasets) (4.5.0)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.6)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2023.11.17)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.3.post1)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n",
+            "Installing collected packages: pyarrow-hotfix, dill, multiprocess, datasets\n",
+            "Successfully installed datasets-2.15.0 dill-0.3.7 multiprocess-0.70.15 pyarrow-hotfix-0.6\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install accelerate"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "xYEW0Hjqz2lo",
+        "outputId": "a0e36c52-c360-4a01-8618-1489551286f8"
+      },
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting accelerate\n",
+            "  Downloading accelerate-0.25.0-py3-none-any.whl (265 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m265.7/265.7 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.23.5)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.2)\n",
+            "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n",
+            "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n",
+            "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.1.0+cu118)\n",
+            "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.19.4)\n",
+            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.1)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.13.1)\n",
+            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (4.5.0)\n",
+            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n",
+            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.2.1)\n",
+            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.2)\n",
+            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2023.6.0)\n",
+            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.1.0)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2.31.0)\n",
+            "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.66.1)\n",
+            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.3)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.6)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2023.11.17)\n",
+            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n",
+            "Installing collected packages: accelerate\n",
+            "Successfully installed accelerate-0.25.0\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install evaluate"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9OFz3JdR0cQ_",
+        "outputId": "137e11b1-d6ce-4ba7-89b9-1ce61fac9964"
+      },
+      "execution_count": 4,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Collecting evaluate\n",
+            "  Downloading evaluate-0.4.1-py3-none-any.whl (84 kB)\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m965.1 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25hRequirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.15.0)\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.23.5)\n",
+            "Requirement already satisfied: dill in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.3.7)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.5.3)\n",
+            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.31.0)\n",
+            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from evaluate) (4.66.1)\n",
+            "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from evaluate) (3.4.1)\n",
+            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.70.15)\n",
+            "Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2023.6.0)\n",
+            "Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.19.4)\n",
+            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from evaluate) (23.2)\n",
+            "Collecting responses<0.19 (from evaluate)\n",
+            "  Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n",
+            "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (9.0.0)\n",
+            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (0.6)\n",
+            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.9.1)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (6.0.1)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (3.13.1)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.5.0)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.6)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2023.11.17)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2023.3.post1)\n",
+            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (23.1.0)\n",
+            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.0.4)\n",
+            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.9.3)\n",
+            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.0)\n",
+            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.1)\n",
+            "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (4.0.3)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->evaluate) (1.16.0)\n",
+            "Installing collected packages: responses, evaluate\n",
+            "Successfully installed evaluate-0.4.1 responses-0.18.0\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/run_qa.py\n",
+        "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/trainer_qa.py\n",
+        "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/utils_qa.py"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "JJhpBNwpxOTK",
+        "outputId": "e656d5a0-4f25-4e7b-8200-039389ad88ae"
+      },
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "--2023-12-09 13:04:52--  https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/run_qa.py\n",
+            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
+            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 32883 (32K) [text/plain]\n",
+            "Saving to: ‘run_qa.py’\n",
+            "\n",
+            "\rrun_qa.py             0%[                    ]       0  --.-KB/s               \rrun_qa.py           100%[===================>]  32.11K  --.-KB/s    in 0.01s   \n",
+            "\n",
+            "2023-12-09 13:04:52 (3.06 MB/s) - ‘run_qa.py’ saved [32883/32883]\n",
+            "\n",
+            "--2023-12-09 13:04:52--  https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/trainer_qa.py\n",
+            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n",
+            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 6253 (6.1K) [text/plain]\n",
+            "Saving to: ‘trainer_qa.py’\n",
+            "\n",
+            "trainer_qa.py       100%[===================>]   6.11K  --.-KB/s    in 0s      \n",
+            "\n",
+            "2023-12-09 13:04:52 (95.6 MB/s) - ‘trainer_qa.py’ saved [6253/6253]\n",
+            "\n",
+            "--2023-12-09 13:04:52--  https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/utils_qa.py\n",
+            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.108.133, 185.199.109.133, ...\n",
+            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 22777 (22K) [text/plain]\n",
+            "Saving to: ‘utils_qa.py’\n",
+            "\n",
+            "utils_qa.py         100%[===================>]  22.24K  --.-KB/s    in 0.001s  \n",
+            "\n",
+            "2023-12-09 13:04:52 (14.6 MB/s) - ‘utils_qa.py’ saved [22777/22777]\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!ls"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Loa6y9XqzXJ4",
+        "outputId": "0aa57423-b1a3-4961-b7ce-8eeb9b7ea175"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "run_qa.py  sample_data\ttrainer_qa.py  utils_qa.py\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!mkdir eval_results"
+      ],
+      "metadata": {
+        "id": "QDNxV31P0reW"
+      },
+      "execution_count": 7,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!python -m run_qa --model_name_or_path osiria/minilm-italian-l6-h384-question-answering --dataset_name squad_it --do_predict --per_device_eval_batch_size=5 --output_dir eval_results"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "B5O5Lom8x_c4",
+        "outputId": "285a1739-b358-4127-8429-5437f35682ae"
+      },
+      "execution_count": 8,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "2023-12-09 13:05:00.034232: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
+            "2023-12-09 13:05:00.034295: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
+            "2023-12-09 13:05:00.034336: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
+            "2023-12-09 13:05:01.133400: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n",
+            "12/09/2023 13:05:04 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False\n",
+            "12/09/2023 13:05:04 - INFO - __main__ - Training/evaluation parameters TrainingArguments(\n",
+            "_n_gpu=1,\n",
+            "adafactor=False,\n",
+            "adam_beta1=0.9,\n",
+            "adam_beta2=0.999,\n",
+            "adam_epsilon=1e-08,\n",
+            "auto_find_batch_size=False,\n",
+            "bf16=False,\n",
+            "bf16_full_eval=False,\n",
+            "data_seed=None,\n",
+            "dataloader_drop_last=False,\n",
+            "dataloader_num_workers=0,\n",
+            "dataloader_persistent_workers=False,\n",
+            "dataloader_pin_memory=True,\n",
+            "ddp_backend=None,\n",
+            "ddp_broadcast_buffers=None,\n",
+            "ddp_bucket_cap_mb=None,\n",
+            "ddp_find_unused_parameters=None,\n",
+            "ddp_timeout=1800,\n",
+            "debug=[],\n",
+            "deepspeed=None,\n",
+            "disable_tqdm=False,\n",
+            "dispatch_batches=None,\n",
+            "do_eval=False,\n",
+            "do_predict=True,\n",
+            "do_train=False,\n",
+            "eval_accumulation_steps=None,\n",
+            "eval_delay=0,\n",
+            "eval_steps=None,\n",
+            "evaluation_strategy=no,\n",
+            "fp16=False,\n",
+            "fp16_backend=auto,\n",
+            "fp16_full_eval=False,\n",
+            "fp16_opt_level=O1,\n",
+            "fsdp=[],\n",
+            "fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},\n",
+            "fsdp_min_num_params=0,\n",
+            "fsdp_transformer_layer_cls_to_wrap=None,\n",
+            "full_determinism=False,\n",
+            "gradient_accumulation_steps=1,\n",
+            "gradient_checkpointing=False,\n",
+            "gradient_checkpointing_kwargs=None,\n",
+            "greater_is_better=None,\n",
+            "group_by_length=False,\n",
+            "half_precision_backend=auto,\n",
+            "hub_always_push=False,\n",
+            "hub_model_id=None,\n",
+            "hub_private_repo=False,\n",
+            "hub_strategy=every_save,\n",
+            "hub_token=<HUB_TOKEN>,\n",
+            "ignore_data_skip=False,\n",
+            "include_inputs_for_metrics=False,\n",
+            "include_num_input_tokens_seen=False,\n",
+            "include_tokens_per_second=False,\n",
+            "jit_mode_eval=False,\n",
+            "label_names=None,\n",
+            "label_smoothing_factor=0.0,\n",
+            "learning_rate=5e-05,\n",
+            "length_column_name=length,\n",
+            "load_best_model_at_end=False,\n",
+            "local_rank=0,\n",
+            "log_level=passive,\n",
+            "log_level_replica=warning,\n",
+            "log_on_each_node=True,\n",
+            "logging_dir=eval_results/runs/Dec09_13-05-04_f36df394933d,\n",
+            "logging_first_step=False,\n",
+            "logging_nan_inf_filter=True,\n",
+            "logging_steps=500,\n",
+            "logging_strategy=steps,\n",
+            "lr_scheduler_kwargs={},\n",
+            "lr_scheduler_type=linear,\n",
+            "max_grad_norm=1.0,\n",
+            "max_steps=-1,\n",
+            "metric_for_best_model=None,\n",
+            "mp_parameters=,\n",
+            "neftune_noise_alpha=None,\n",
+            "no_cuda=False,\n",
+            "num_train_epochs=3.0,\n",
+            "optim=adamw_torch,\n",
+            "optim_args=None,\n",
+            "output_dir=eval_results,\n",
+            "overwrite_output_dir=False,\n",
+            "past_index=-1,\n",
+            "per_device_eval_batch_size=5,\n",
+            "per_device_train_batch_size=8,\n",
+            "prediction_loss_only=False,\n",
+            "push_to_hub=False,\n",
+            "push_to_hub_model_id=None,\n",
+            "push_to_hub_organization=None,\n",
+            "push_to_hub_token=<PUSH_TO_HUB_TOKEN>,\n",
+            "ray_scope=last,\n",
+            "remove_unused_columns=True,\n",
+            "report_to=['tensorboard'],\n",
+            "resume_from_checkpoint=None,\n",
+            "run_name=eval_results,\n",
+            "save_on_each_node=False,\n",
+            "save_only_model=False,\n",
+            "save_safetensors=True,\n",
+            "save_steps=500,\n",
+            "save_strategy=steps,\n",
+            "save_total_limit=None,\n",
+            "seed=42,\n",
+            "skip_memory_metrics=True,\n",
+            "split_batches=False,\n",
+            "tf32=None,\n",
+            "torch_compile=False,\n",
+            "torch_compile_backend=None,\n",
+            "torch_compile_mode=None,\n",
+            "torchdynamo=None,\n",
+            "tpu_metrics_debug=False,\n",
+            "tpu_num_cores=None,\n",
+            "use_cpu=False,\n",
+            "use_ipex=False,\n",
+            "use_legacy_prediction_loop=False,\n",
+            "use_mps_device=False,\n",
+            "warmup_ratio=0.0,\n",
+            "warmup_steps=0,\n",
+            "weight_decay=0.0,\n",
+            ")\n",
+            "https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py.incomplete\n",
+            "12/09/2023 13:05:04 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py.incomplete\n",
+            "Downloading builder script: 100% 4.74k/4.74k [00:00<00:00, 17.6MB/s]\n",
+            "storing https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py in cache at /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n",
+            "12/09/2023 13:05:04 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py in cache at /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n",
+            "creating metadata file for /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n",
+            "12/09/2023 13:05:04 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n",
+            "https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d.incomplete\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d.incomplete\n",
+            "Downloading metadata: 100% 2.51k/2.51k [00:00<00:00, 13.8MB/s]\n",
+            "storing https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json in cache at /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json in cache at /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n",
+            "creating metadata file for /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n",
+            "https://huggingface.co/datasets/squad_it/resolve/main/README.md not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb.incomplete\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/README.md not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb.incomplete\n",
+            "Downloading readme: 100% 7.27k/7.27k [00:00<00:00, 32.7MB/s]\n",
+            "storing https://huggingface.co/datasets/squad_it/resolve/main/README.md in cache at /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/README.md in cache at /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n",
+            "creating metadata file for /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n",
+            "12/09/2023 13:05:05 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n",
+            "Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/squad_it/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71\n",
+            "12/09/2023 13:05:05 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/squad_it/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71\n",
+            "Generating dataset squad_it (/root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71)\n",
+            "12/09/2023 13:05:05 - INFO - datasets.builder - Generating dataset squad_it (/root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71)\n",
+            "Downloading and preparing dataset squad_it/default to /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71...\n",
+            "12/09/2023 13:05:05 - INFO - datasets.builder - Downloading and preparing dataset squad_it/default to /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71...\n",
+            "Dataset not on Hf google storage. Downloading and preparing it from source\n",
+            "12/09/2023 13:05:05 - INFO - datasets.builder - Dataset not on Hf google storage. Downloading and preparing it from source\n",
+            "Downloading data files:   0% 0/2 [00:00<?, ?it/s]https://github.com/crux82/squad-it/raw/master/SQuAD_it-train.json.gz not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b.incomplete\n",
+            "12/09/2023 13:05:06 - INFO - datasets.utils.file_utils - https://github.com/crux82/squad-it/raw/master/SQuAD_it-train.json.gz not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b.incomplete\n",
+            "\n",
+            "Downloading data:   0% 0.00/7.73M [00:00<?, ?B/s]\u001b[A\n",
+            "Downloading data: 100% 7.73M/7.73M [00:00<00:00, 57.4MB/s]\n",
+            "storing https://github.com/crux82/squad-it/raw/master/SQuAD_it-train.json.gz in cache at /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b\n",
+            "12/09/2023 13:05:07 - INFO - datasets.utils.file_utils - storing https://github.com/crux82/squad-it/raw/master/SQuAD_it-train.json.gz in cache at /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b\n",
+            "creating metadata file for /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b\n",
+            "12/09/2023 13:05:07 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/44ac0548c3284061d1356ff7f5212fe42b923b0aa0854c886ce93dfeb7ab629b\n",
+            "Downloading data files:  50% 1/2 [00:01<00:01,  1.55s/it]https://github.com/crux82/squad-it/raw/master/SQuAD_it-test.json.gz not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f.incomplete\n",
+            "12/09/2023 13:05:07 - INFO - datasets.utils.file_utils - https://github.com/crux82/squad-it/raw/master/SQuAD_it-test.json.gz not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f.incomplete\n",
+            "\n",
+            "Downloading data: 100% 1.05M/1.05M [00:00<00:00, 15.8MB/s]\n",
+            "storing https://github.com/crux82/squad-it/raw/master/SQuAD_it-test.json.gz in cache at /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f\n",
+            "12/09/2023 13:05:08 - INFO - datasets.utils.file_utils - storing https://github.com/crux82/squad-it/raw/master/SQuAD_it-test.json.gz in cache at /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f\n",
+            "creating metadata file for /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f\n",
+            "12/09/2023 13:05:08 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/e560a4a54eb929ce542e945627942afca80859dcbf499866a59984eb9026d31f\n",
+            "Downloading data files: 100% 2/2 [00:02<00:00,  1.20s/it]\n",
+            "Downloading took 0.0 min\n",
+            "12/09/2023 13:05:08 - INFO - datasets.download.download_manager - Downloading took 0.0 min\n",
+            "Checksum Computation took 0.0 min\n",
+            "12/09/2023 13:05:08 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min\n",
+            "Extracting data files: 100% 2/2 [00:00<00:00,  8.59it/s]\n",
+            "Generating train split\n",
+            "12/09/2023 13:05:08 - INFO - datasets.builder - Generating train split\n",
+            "Generating train split: 100% 54159/54159 [00:06<00:00, 8532.57 examples/s] \n",
+            "Generating test split\n",
+            "12/09/2023 13:05:14 - INFO - datasets.builder - Generating test split\n",
+            "Generating test split: 100% 7609/7609 [00:00<00:00, 11548.29 examples/s]\n",
+            "All the splits matched successfully.\n",
+            "12/09/2023 13:05:15 - INFO - datasets.utils.info_utils - All the splits matched successfully.\n",
+            "Dataset squad_it downloaded and prepared to /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71. Subsequent calls will reuse this data.\n",
+            "12/09/2023 13:05:15 - INFO - datasets.builder - Dataset squad_it downloaded and prepared to /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71. Subsequent calls will reuse this data.\n",
+            "config.json: 100% 652/652 [00:00<00:00, 3.76MB/s]\n",
+            "[INFO|configuration_utils.py:739] 2023-12-09 13:05:15,608 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--osiria--minilm-italian-l6-h384-question-answering/snapshots/1faf21988c80be33048fe9d3e0bb98aafec858bb/config.json\n",
+            "[INFO|configuration_utils.py:802] 2023-12-09 13:05:15,613 >> Model config XLMRobertaConfig {\n",
+            "  \"_name_or_path\": \"osiria/minilm-italian-l6-h384-question-answering\",\n",
+            "  \"architectures\": [\n",
+            "    \"XLMRobertaForQuestionAnswering\"\n",
+            "  ],\n",
+            "  \"attention_probs_dropout_prob\": 0.1,\n",
+            "  \"bos_token_id\": 0,\n",
+            "  \"classifier_dropout\": null,\n",
+            "  \"eos_token_id\": 2,\n",
+            "  \"hidden_act\": \"gelu\",\n",
+            "  \"hidden_dropout_prob\": 0.1,\n",
+            "  \"hidden_size\": 384,\n",
+            "  \"initializer_range\": 0.02,\n",
+            "  \"intermediate_size\": 1536,\n",
+            "  \"layer_norm_eps\": 1e-05,\n",
+            "  \"max_position_embeddings\": 514,\n",
+            "  \"model_type\": \"xlm-roberta\",\n",
+            "  \"num_attention_heads\": 12,\n",
+            "  \"num_hidden_layers\": 6,\n",
+            "  \"pad_token_id\": 1,\n",
+            "  \"position_embedding_type\": \"absolute\",\n",
+            "  \"torch_dtype\": \"float32\",\n",
+            "  \"transformers_version\": \"4.36.0.dev0\",\n",
+            "  \"type_vocab_size\": 1,\n",
+            "  \"use_cache\": true,\n",
+            "  \"vocab_size\": 30498\n",
+            "}\n",
+            "\n",
+            "tokenizer_config.json: 100% 418/418 [00:00<00:00, 2.73MB/s]\n",
+            "tokenizer.json: 100% 1.39M/1.39M [00:00<00:00, 18.7MB/s]\n",
+            "special_tokens_map.json: 100% 280/280 [00:00<00:00, 1.75MB/s]\n",
+            "[INFO|tokenization_utils_base.py:2026] 2023-12-09 13:05:16,227 >> loading file sentencepiece.bpe.model from cache at None\n",
+            "[INFO|tokenization_utils_base.py:2026] 2023-12-09 13:05:16,227 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--osiria--minilm-italian-l6-h384-question-answering/snapshots/1faf21988c80be33048fe9d3e0bb98aafec858bb/tokenizer.json\n",
+            "[INFO|tokenization_utils_base.py:2026] 2023-12-09 13:05:16,227 >> loading file added_tokens.json from cache at None\n",
+            "[INFO|tokenization_utils_base.py:2026] 2023-12-09 13:05:16,227 >> loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--osiria--minilm-italian-l6-h384-question-answering/snapshots/1faf21988c80be33048fe9d3e0bb98aafec858bb/special_tokens_map.json\n",
+            "[INFO|tokenization_utils_base.py:2026] 2023-12-09 13:05:16,228 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--osiria--minilm-italian-l6-h384-question-answering/snapshots/1faf21988c80be33048fe9d3e0bb98aafec858bb/tokenizer_config.json\n",
+            "pytorch_model.bin: 100% 90.3M/90.3M [00:01<00:00, 57.7MB/s]\n",
+            "[INFO|modeling_utils.py:3299] 2023-12-09 13:05:18,490 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--osiria--minilm-italian-l6-h384-question-answering/snapshots/1faf21988c80be33048fe9d3e0bb98aafec858bb/pytorch_model.bin\n",
+            "[INFO|modeling_utils.py:4139] 2023-12-09 13:05:18,858 >> All model checkpoint weights were used when initializing XLMRobertaForQuestionAnswering.\n",
+            "\n",
+            "[INFO|modeling_utils.py:4147] 2023-12-09 13:05:18,858 >> All the weights of XLMRobertaForQuestionAnswering were initialized from the model checkpoint at osiria/minilm-italian-l6-h384-question-answering.\n",
+            "If your task is similar to the task the model of the checkpoint was trained on, you can already use XLMRobertaForQuestionAnswering for predictions without further training.\n",
+            "Running tokenizer on prediction dataset:   0% 0/7609 [00:00<?, ? examples/s]Caching processed dataset at /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71/cache-817e084ce623e156.arrow\n",
+            "12/09/2023 13:05:19 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71/cache-817e084ce623e156.arrow\n",
+            "Running tokenizer on prediction dataset: 100% 7609/7609 [00:08<00:00, 880.77 examples/s]\n",
+            "Downloading builder script: 100% 4.53k/4.53k [00:00<00:00, 18.0MB/s]\n",
+            "Downloading extra modules: 100% 3.32k/3.32k [00:00<00:00, 17.0MB/s]\n",
+            "12/09/2023 13:05:33 - INFO - __main__ - *** Predict ***\n",
+            "[INFO|trainer.py:712] 2023-12-09 13:05:33,267 >> The following columns in the test set don't have a corresponding argument in `XLMRobertaForQuestionAnswering.forward` and have been ignored: offset_mapping, example_id. If offset_mapping, example_id are not expected by `XLMRobertaForQuestionAnswering.forward`,  you can safely ignore this message.\n",
+            "[INFO|trainer.py:3154] 2023-12-09 13:05:33,270 >> ***** Running Prediction *****\n",
+            "[INFO|trainer.py:3156] 2023-12-09 13:05:33,270 >>   Num examples = 7988\n",
+            "[INFO|trainer.py:3159] 2023-12-09 13:05:33,270 >>   Batch size = 5\n",
+            "100% 1598/1598 [00:38<00:00, 43.23it/s]12/09/2023 13:06:23 - INFO - utils_qa - Post-processing 7609 example predictions split into 7988 features.\n",
+            "\n",
+            "  0% 0/7609 [00:00<?, ?it/s]\u001b[A\n",
+            "  1% 41/7609 [00:00<00:18, 401.05it/s]\u001b[A\n",
+            "  1% 82/7609 [00:00<00:20, 373.83it/s]\u001b[A\n",
+            "  2% 120/7609 [00:00<00:19, 375.54it/s]\u001b[A\n",
+            "  2% 158/7609 [00:00<00:19, 373.21it/s]\u001b[A\n",
+            "  3% 196/7609 [00:00<00:19, 375.08it/s]\u001b[A\n",
+            "  3% 237/7609 [00:00<00:19, 385.93it/s]\u001b[A\n",
+            "  4% 277/7609 [00:00<00:18, 389.16it/s]\u001b[A\n",
+            "  4% 316/7609 [00:00<00:19, 373.73it/s]\u001b[A\n",
+            "  5% 354/7609 [00:00<00:19, 371.48it/s]\u001b[A\n",
+            "  5% 394/7609 [00:01<00:19, 379.36it/s]\u001b[A\n",
+            "  6% 433/7609 [00:01<00:19, 373.82it/s]\u001b[A\n",
+            "  6% 474/7609 [00:01<00:18, 384.33it/s]\u001b[A\n",
+            "  7% 513/7609 [00:01<00:18, 382.05it/s]\u001b[A\n",
+            "  7% 552/7609 [00:01<00:19, 361.93it/s]\u001b[A\n",
+            "100% 1598/1598 [00:49<00:00, 43.23it/s]\n",
+            "  8% 634/7609 [00:01<00:18, 383.75it/s]\u001b[A\n",
+            "  9% 674/7609 [00:01<00:17, 385.73it/s]\u001b[A\n",
+            "  9% 715/7609 [00:01<00:17, 391.92it/s]\u001b[A\n",
+            " 10% 755/7609 [00:01<00:17, 384.72it/s]\u001b[A\n",
+            " 10% 795/7609 [00:02<00:17, 387.04it/s]\u001b[A\n",
+            " 11% 834/7609 [00:02<00:17, 377.84it/s]\u001b[A\n",
+            " 11% 872/7609 [00:02<00:17, 377.50it/s]\u001b[A\n",
+            " 12% 910/7609 [00:02<00:17, 373.54it/s]\u001b[A\n",
+            " 12% 948/7609 [00:02<00:17, 371.87it/s]\u001b[A\n",
+            " 13% 988/7609 [00:02<00:17, 378.28it/s]\u001b[A\n",
+            " 14% 1029/7609 [00:02<00:17, 385.26it/s]\u001b[A\n",
+            " 14% 1070/7609 [00:02<00:16, 390.90it/s]\u001b[A\n",
+            " 15% 1110/7609 [00:02<00:16, 388.54it/s]\u001b[A\n",
+            " 15% 1149/7609 [00:03<00:16, 382.61it/s]\u001b[A\n",
+            " 16% 1188/7609 [00:03<00:17, 367.95it/s]\u001b[A\n",
+            " 16% 1229/7609 [00:03<00:16, 378.84it/s]\u001b[A\n",
+            " 17% 1268/7609 [00:03<00:16, 380.23it/s]\u001b[A\n",
+            " 17% 1308/7609 [00:03<00:16, 383.91it/s]\u001b[A\n",
+            " 18% 1347/7609 [00:03<00:16, 378.43it/s]\u001b[A\n",
+            " 18% 1385/7609 [00:03<00:16, 374.90it/s]\u001b[A\n",
+            " 19% 1424/7609 [00:03<00:16, 376.95it/s]\u001b[A\n",
+            " 19% 1462/7609 [00:03<00:16, 370.65it/s]\u001b[A\n",
+            " 20% 1500/7609 [00:03<00:17, 350.38it/s]\u001b[A\n",
+            " 20% 1538/7609 [00:04<00:16, 358.03it/s]\u001b[A\n",
+            " 21% 1579/7609 [00:04<00:16, 370.54it/s]\u001b[A\n",
+            " 21% 1617/7609 [00:04<00:16, 357.26it/s]\u001b[A\n",
+            " 22% 1653/7609 [00:04<00:16, 355.85it/s]\u001b[A\n",
+            " 22% 1689/7609 [00:04<00:16, 356.50it/s]\u001b[A\n",
+            " 23% 1729/7609 [00:04<00:15, 368.06it/s]\u001b[A\n",
+            " 23% 1766/7609 [00:04<00:16, 362.43it/s]\u001b[A\n",
+            " 24% 1806/7609 [00:04<00:15, 371.78it/s]\u001b[A\n",
+            " 24% 1844/7609 [00:04<00:15, 374.09it/s]\u001b[A\n",
+            " 25% 1884/7609 [00:05<00:15, 379.97it/s]\u001b[A\n",
+            " 25% 1924/7609 [00:05<00:14, 383.62it/s]\u001b[A\n",
+            " 26% 1963/7609 [00:05<00:15, 354.44it/s]\u001b[A\n",
+            " 26% 1999/7609 [00:05<00:17, 317.18it/s]\u001b[A\n",
+            " 27% 2032/7609 [00:05<00:21, 265.40it/s]\u001b[A\n",
+            " 27% 2066/7609 [00:05<00:19, 280.18it/s]\u001b[A\n",
+            " 28% 2096/7609 [00:05<00:25, 214.52it/s]\u001b[A\n",
+            " 28% 2122/7609 [00:06<00:24, 223.59it/s]\u001b[A\n",
+            " 28% 2162/7609 [00:06<00:20, 263.47it/s]\u001b[A\n",
+            " 29% 2196/7609 [00:06<00:19, 281.93it/s]\u001b[A\n",
+            " 29% 2232/7609 [00:06<00:17, 301.40it/s]\u001b[A\n",
+            " 30% 2265/7609 [00:06<00:18, 295.49it/s]\u001b[A\n",
+            " 30% 2303/7609 [00:06<00:16, 317.40it/s]\u001b[A\n",
+            " 31% 2341/7609 [00:06<00:15, 334.53it/s]\u001b[A\n",
+            " 31% 2381/7609 [00:06<00:14, 353.03it/s]\u001b[A\n",
+            " 32% 2420/7609 [00:06<00:14, 362.45it/s]\u001b[A\n",
+            " 32% 2460/7609 [00:06<00:13, 368.51it/s]\u001b[A\n",
+            " 33% 2498/7609 [00:07<00:14, 349.37it/s]\u001b[A\n",
+            " 33% 2540/7609 [00:07<00:13, 366.50it/s]\u001b[A\n",
+            " 34% 2579/7609 [00:07<00:13, 370.66it/s]\u001b[A\n",
+            " 34% 2617/7609 [00:07<00:14, 351.73it/s]\u001b[A\n",
+            " 35% 2657/7609 [00:07<00:13, 363.13it/s]\u001b[A\n",
+            " 35% 2694/7609 [00:07<00:13, 356.81it/s]\u001b[A\n",
+            " 36% 2731/7609 [00:07<00:13, 359.78it/s]\u001b[A\n",
+            " 36% 2772/7609 [00:07<00:12, 373.10it/s]\u001b[A\n",
+            " 37% 2813/7609 [00:07<00:12, 382.65it/s]\u001b[A\n",
+            " 37% 2852/7609 [00:07<00:12, 382.80it/s]\u001b[A\n",
+            " 38% 2894/7609 [00:08<00:12, 392.22it/s]\u001b[A\n",
+            " 39% 2937/7609 [00:08<00:11, 402.25it/s]\u001b[A\n",
+            " 39% 2978/7609 [00:08<00:11, 393.04it/s]\u001b[A\n",
+            " 40% 3018/7609 [00:08<00:11, 389.48it/s]\u001b[A\n",
+            " 40% 3058/7609 [00:08<00:12, 378.03it/s]\u001b[A\n",
+            " 41% 3096/7609 [00:08<00:12, 370.92it/s]\u001b[A\n",
+            " 41% 3134/7609 [00:08<00:12, 360.59it/s]\u001b[A\n",
+            " 42% 3173/7609 [00:08<00:12, 366.35it/s]\u001b[A\n",
+            " 42% 3210/7609 [00:08<00:12, 361.80it/s]\u001b[A\n",
+            " 43% 3247/7609 [00:09<00:12, 357.73it/s]\u001b[A\n",
+            " 43% 3285/7609 [00:09<00:11, 363.47it/s]\u001b[A\n",
+            " 44% 3322/7609 [00:09<00:11, 363.00it/s]\u001b[A\n",
+            " 44% 3360/7609 [00:09<00:11, 367.90it/s]\u001b[A\n",
+            " 45% 3399/7609 [00:09<00:11, 373.00it/s]\u001b[A\n",
+            " 45% 3439/7609 [00:09<00:10, 380.60it/s]\u001b[A\n",
+            " 46% 3478/7609 [00:09<00:12, 336.39it/s]\u001b[A\n",
+            " 46% 3513/7609 [00:09<00:13, 296.52it/s]\u001b[A\n",
+            " 47% 3545/7609 [00:10<00:14, 272.10it/s]\u001b[A\n",
+            " 47% 3574/7609 [00:10<00:15, 259.31it/s]\u001b[A\n",
+            " 47% 3601/7609 [00:10<00:16, 248.17it/s]\u001b[A\n",
+            " 48% 3627/7609 [00:10<00:17, 227.36it/s]\u001b[A\n",
+            " 48% 3651/7609 [00:10<00:17, 220.80it/s]\u001b[A\n",
+            " 48% 3674/7609 [00:10<00:18, 218.57it/s]\u001b[A\n",
+            " 49% 3697/7609 [00:10<00:17, 218.89it/s]\u001b[A\n",
+            " 49% 3720/7609 [00:10<00:17, 216.68it/s]\u001b[A\n",
+            " 49% 3742/7609 [00:10<00:18, 210.65it/s]\u001b[A\n",
+            " 49% 3764/7609 [00:11<00:18, 209.35it/s]\u001b[A\n",
+            " 50% 3786/7609 [00:11<00:18, 211.83it/s]\u001b[A\n",
+            " 50% 3809/7609 [00:11<00:17, 214.51it/s]\u001b[A\n",
+            " 50% 3834/7609 [00:11<00:16, 222.59it/s]\u001b[A\n",
+            " 51% 3858/7609 [00:11<00:16, 225.59it/s]\u001b[A\n",
+            " 51% 3881/7609 [00:11<00:16, 222.47it/s]\u001b[A\n",
+            " 51% 3904/7609 [00:11<00:16, 222.57it/s]\u001b[A\n",
+            " 52% 3927/7609 [00:11<00:16, 221.91it/s]\u001b[A\n",
+            " 52% 3950/7609 [00:11<00:16, 223.75it/s]\u001b[A\n",
+            " 52% 3973/7609 [00:11<00:16, 218.35it/s]\u001b[A\n",
+            " 53% 3995/7609 [00:12<00:16, 217.07it/s]\u001b[A\n",
+            " 53% 4017/7609 [00:12<00:16, 214.83it/s]\u001b[A\n",
+            " 53% 4040/7609 [00:12<00:16, 219.00it/s]\u001b[A\n",
+            " 53% 4062/7609 [00:12<00:17, 205.86it/s]\u001b[A\n",
+            " 54% 4083/7609 [00:12<00:17, 206.14it/s]\u001b[A\n",
+            " 54% 4104/7609 [00:12<00:17, 196.27it/s]\u001b[A\n",
+            " 54% 4127/7609 [00:12<00:17, 204.40it/s]\u001b[A\n",
+            " 55% 4151/7609 [00:12<00:16, 213.31it/s]\u001b[A\n",
+            " 55% 4174/7609 [00:12<00:15, 218.00it/s]\u001b[A\n",
+            " 55% 4196/7609 [00:13<00:15, 217.17it/s]\u001b[A\n",
+            " 55% 4219/7609 [00:13<00:15, 219.75it/s]\u001b[A\n",
+            " 56% 4242/7609 [00:13<00:15, 218.32it/s]\u001b[A\n",
+            " 56% 4264/7609 [00:13<00:15, 218.25it/s]\u001b[A\n",
+            " 56% 4286/7609 [00:13<00:15, 216.53it/s]\u001b[A\n",
+            " 57% 4310/7609 [00:13<00:14, 221.19it/s]\u001b[A\n",
+            " 57% 4344/7609 [00:13<00:12, 254.04it/s]\u001b[A\n",
+            " 58% 4380/7609 [00:13<00:11, 285.06it/s]\u001b[A\n",
+            " 58% 4424/7609 [00:13<00:09, 329.34it/s]\u001b[A\n",
+            " 59% 4458/7609 [00:13<00:09, 324.38it/s]\u001b[A\n",
+            " 59% 4502/7609 [00:14<00:08, 356.17it/s]\u001b[A\n",
+            " 60% 4543/7609 [00:14<00:08, 370.47it/s]\u001b[A\n",
+            " 60% 4583/7609 [00:14<00:08, 376.88it/s]\u001b[A\n",
+            " 61% 4623/7609 [00:14<00:07, 383.12it/s]\u001b[A\n",
+            " 61% 4666/7609 [00:14<00:07, 394.89it/s]\u001b[A\n",
+            " 62% 4707/7609 [00:14<00:07, 399.20it/s]\u001b[A\n",
+            " 62% 4751/7609 [00:14<00:06, 408.94it/s]\u001b[A\n",
+            " 63% 4792/7609 [00:14<00:07, 390.51it/s]\u001b[A\n",
+            " 64% 4834/7609 [00:14<00:06, 398.83it/s]\u001b[A\n",
+            " 64% 4875/7609 [00:15<00:06, 394.43it/s]\u001b[A\n",
+            " 65% 4916/7609 [00:15<00:06, 398.01it/s]\u001b[A\n",
+            " 65% 4956/7609 [00:15<00:07, 377.41it/s]\u001b[A\n",
+            " 66% 4998/7609 [00:15<00:06, 388.68it/s]\u001b[A\n",
+            " 66% 5038/7609 [00:15<00:06, 386.58it/s]\u001b[A\n",
+            " 67% 5077/7609 [00:15<00:06, 386.95it/s]\u001b[A\n",
+            " 67% 5118/7609 [00:15<00:06, 393.49it/s]\u001b[A\n",
+            " 68% 5158/7609 [00:16<00:11, 222.22it/s]\u001b[A\n",
+            " 68% 5200/7609 [00:16<00:09, 259.28it/s]\u001b[A\n",
+            " 69% 5242/7609 [00:16<00:08, 292.90it/s]\u001b[A\n",
+            " 69% 5282/7609 [00:16<00:07, 316.37it/s]\u001b[A\n",
+            " 70% 5322/7609 [00:16<00:06, 334.94it/s]\u001b[A\n",
+            " 70% 5362/7609 [00:16<00:06, 350.70it/s]\u001b[A\n",
+            " 71% 5401/7609 [00:16<00:06, 355.94it/s]\u001b[A\n",
+            " 72% 5443/7609 [00:16<00:05, 371.93it/s]\u001b[A\n",
+            " 72% 5482/7609 [00:16<00:05, 368.15it/s]\u001b[A\n",
+            " 73% 5522/7609 [00:16<00:05, 376.18it/s]\u001b[A\n",
+            " 73% 5563/7609 [00:17<00:05, 384.39it/s]\u001b[A\n",
+            " 74% 5605/7609 [00:17<00:05, 392.32it/s]\u001b[A\n",
+            " 74% 5645/7609 [00:17<00:04, 393.87it/s]\u001b[A\n",
+            " 75% 5687/7609 [00:17<00:04, 399.15it/s]\u001b[A\n",
+            " 75% 5728/7609 [00:17<00:04, 399.67it/s]\u001b[A\n",
+            " 76% 5769/7609 [00:17<00:04, 401.90it/s]\u001b[A\n",
+            " 76% 5815/7609 [00:17<00:04, 417.79it/s]\u001b[A\n",
+            " 77% 5857/7609 [00:17<00:04, 412.49it/s]\u001b[A\n",
+            " 78% 5899/7609 [00:17<00:04, 396.45it/s]\u001b[A\n",
+            " 78% 5939/7609 [00:17<00:04, 397.23it/s]\u001b[A\n",
+            " 79% 5979/7609 [00:18<00:04, 380.92it/s]\u001b[A\n",
+            " 79% 6019/7609 [00:18<00:04, 384.73it/s]\u001b[A\n",
+            " 80% 6060/7609 [00:18<00:03, 390.43it/s]\u001b[A\n",
+            " 80% 6100/7609 [00:18<00:03, 389.08it/s]\u001b[A\n",
+            " 81% 6139/7609 [00:18<00:04, 357.51it/s]\u001b[A\n",
+            " 81% 6176/7609 [00:18<00:04, 343.01it/s]\u001b[A\n",
+            " 82% 6219/7609 [00:18<00:03, 366.55it/s]\u001b[A\n",
+            " 82% 6261/7609 [00:18<00:03, 380.56it/s]\u001b[A\n",
+            " 83% 6302/7609 [00:18<00:03, 387.32it/s]\u001b[A\n",
+            " 83% 6342/7609 [00:19<00:03, 387.59it/s]\u001b[A\n",
+            " 84% 6385/7609 [00:19<00:03, 399.56it/s]\u001b[A\n",
+            " 84% 6429/7609 [00:19<00:02, 409.05it/s]\u001b[A\n",
+            " 85% 6471/7609 [00:19<00:02, 410.40it/s]\u001b[A\n",
+            " 86% 6513/7609 [00:19<00:02, 412.63it/s]\u001b[A\n",
+            " 86% 6555/7609 [00:19<00:02, 410.10it/s]\u001b[A\n",
+            " 87% 6597/7609 [00:19<00:02, 411.45it/s]\u001b[A\n",
+            " 87% 6639/7609 [00:19<00:02, 400.74it/s]\u001b[A\n",
+            " 88% 6680/7609 [00:19<00:02, 381.14it/s]\u001b[A\n",
+            " 88% 6720/7609 [00:19<00:02, 383.86it/s]\u001b[A\n",
+            " 89% 6759/7609 [00:20<00:02, 382.16it/s]\u001b[A\n",
+            " 89% 6798/7609 [00:20<00:02, 379.85it/s]\u001b[A\n",
+            " 90% 6837/7609 [00:20<00:02, 374.69it/s]\u001b[A\n",
+            " 90% 6875/7609 [00:20<00:02, 361.02it/s]\u001b[A\n",
+            " 91% 6917/7609 [00:20<00:01, 375.71it/s]\u001b[A\n",
+            " 91% 6959/7609 [00:20<00:01, 386.62it/s]\u001b[A\n",
+            " 92% 7001/7609 [00:20<00:01, 393.89it/s]\u001b[A\n",
+            " 93% 7041/7609 [00:20<00:01, 392.62it/s]\u001b[A\n",
+            " 93% 7081/7609 [00:20<00:01, 363.88it/s]\u001b[A\n",
+            " 94% 7118/7609 [00:21<00:01, 357.49it/s]\u001b[A\n",
+            " 94% 7155/7609 [00:21<00:01, 351.27it/s]\u001b[A\n",
+            " 95% 7193/7609 [00:21<00:01, 355.56it/s]\u001b[A\n",
+            " 95% 7232/7609 [00:21<00:01, 361.94it/s]\u001b[A\n",
+            " 96% 7269/7609 [00:21<00:00, 362.41it/s]\u001b[A\n",
+            " 96% 7311/7609 [00:21<00:00, 377.50it/s]\u001b[A\n",
+            " 97% 7349/7609 [00:21<00:00, 364.61it/s]\u001b[A\n",
+            " 97% 7389/7609 [00:21<00:00, 374.59it/s]\u001b[A\n",
+            " 98% 7429/7609 [00:21<00:00, 377.78it/s]\u001b[A\n",
+            " 98% 7467/7609 [00:22<00:00, 360.20it/s]\u001b[A\n",
+            " 99% 7504/7609 [00:22<00:00, 353.22it/s]\u001b[A\n",
+            " 99% 7540/7609 [00:22<00:00, 343.34it/s]\u001b[A\n",
+            "100% 7575/7609 [00:22<00:00, 335.47it/s]\u001b[A\n",
+            "100% 7609/7609 [00:22<00:00, 338.94it/s]\n",
+            "12/09/2023 13:06:45 - INFO - utils_qa - Saving predictions to eval_results/predict_predictions.json.\n",
+            "12/09/2023 13:06:45 - INFO - utils_qa - Saving nbest_preds to eval_results/predict_nbest_predictions.json.\n",
+            "***** predict metrics *****\n",
+            "  predict_samples         =       7988\n",
+            "  test_exact_match        =    60.7307\n",
+            "  test_f1                 =    72.4316\n",
+            "  test_runtime            = 0:00:40.66\n",
+            "  test_samples_per_second =    196.422\n",
+            "  test_steps_per_second   =     39.294\n",
+            "[INFO|modelcard.py:452] 2023-12-09 13:06:49,887 >> Dropping the following result as it does not have all the necessary fields:\n",
+            "{'task': {'name': 'Question Answering', 'type': 'question-answering'}, 'dataset': {'name': 'squad_it', 'type': 'squad_it'}}\n",
+            "100% 1598/1598 [01:14<00:00, 21.57it/s]\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "ij8YkY0xyNXI"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fec99672ee8429584c79e03f6ed4a8357870a2b4d54d939fb277a3cd9edbb141
+size 90262889

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}