End of training

e5_interleaving-cl.ipynb

@@ -125,20 +125,20 @@
  "Requirement already satisfied: torch in ./.local/lib/python3.8/site-packages (1.13.0)\n",
  "Requirement already satisfied: torchaudio in ./.local/lib/python3.8/site-packages (0.13.0)\n",
  "Requirement already satisfied: torchvision in ./.local/lib/python3.8/site-packages (0.14.0)\n",
+ "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
+ "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch) (8.5.0.96)\n",
  "Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in ./.local/lib/python3.8/site-packages (from torch) (11.10.3.66)\n",
- "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
  "Requirement already satisfied: typing-extensions in ./.local/lib/python3.8/site-packages (from torch) (4.4.0)\n",
- "Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in ./.local/lib/python3.8/site-packages (from torch) (8.5.0.96)\n",
- "Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
- "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (45.2.0)\n",
+ "Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in ./.local/lib/python3.8/site-packages (from torch) (11.7.99)\n",
  "Requirement already satisfied: wheel in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.34.2)\n",
- "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from torchvision) (2.28.1)\n",
+ "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (45.2.0)\n",
  "Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /usr/lib/python3/dist-packages (from torchvision) (7.0.0)\n",
+ "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from torchvision) (2.28.1)\n",
  "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from torchvision) (1.23.5)\n",
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (1.26.13)\n",
  "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->torchvision) (2019.11.28)\n",
- "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->torchvision) (2.8)\n",
- "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (2.1.1)\n"
+ "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (2.1.1)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->torchvision) (1.26.13)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->torchvision) (2.8)\n"
  ]
  }
  ],
@@ -200,7 +200,7 @@
  "name": "stdout",
  "output_type": "stream",
  "text": [
- "Tue Dec 13 19:10:09 2022 \n",
+ "Tue Dec 13 21:26:01 2022 \n",
  "+-----------------------------------------------------------------------------+\n",
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
  "|-------------------------------+----------------------+----------------------+\n",
@@ -209,7 +209,7 @@
  "| | | MIG M. |\n",
  "|===============================+======================+======================|\n",
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
- "| N/A 31C P0 46W / 400W | 0MiB / 40960MiB | 0% Default |\n",
+ "| N/A 41C P0 50W / 400W | 0MiB / 40960MiB | 0% Default |\n",
  "| | | Disabled |\n",
  "+-------------------------------+----------------------+----------------------+\n",
  " \n",
@@ -260,42 +260,43 @@
  "name": "stdout",
  "output_type": "stream",
  "text": [
- "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
- "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
- "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
- "Get:4 https://packages.cloud.google.com/apt cloud-sdk InRelease [6751 B] \n",
- "Hit:5 http://archive.lambdalabs.com/ubuntu focal InRelease \n",
- "Get:6 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \n",
- "Hit:7 https://packages.microsoft.com/repos/azure-cli focal InRelease \n",
- "Get:8 https://packages.cloud.google.com/apt cloud-sdk/main amd64 Packages [368 kB]\n",
+ "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
+ "Hit:2 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
+ "Get:3 https://packages.cloud.google.com/apt cloud-sdk InRelease [6751 B] \n",
+ "Hit:4 http://archive.lambdalabs.com/ubuntu focal InRelease \n",
+ "Hit:5 https://download.docker.com/linux/ubuntu focal InRelease \n",
+ "Hit:6 https://packages.microsoft.com/repos/azure-cli focal InRelease \n",
+ "Hit:7 http://archive.ubuntu.com/ubuntu focal InRelease \n",
+ "Get:8 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \n",
  "Ign:9 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \n",
- "Hit:10 http://archive.ubuntu.com/ubuntu focal InRelease \n",
+ "Get:10 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \n",
  "Hit:11 https://pkg.cloudflare.com/cloudflared focal InRelease \n",
- "Get:12 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \n",
- "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \n",
+ "Err:12 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \n",
  " 404 Not Found [IP: 185.125.190.52 80]\n",
- "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
- "Get:15 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB]\n",
- "Reading package lists... Done \n",
+ "Hit:13 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
+ "Get:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB] \n",
+ "Get:15 http://archive.ubuntu.com/ubuntu focal-updates/main amd64 Packages [2269 kB]\n",
+ "Get:16 http://archive.ubuntu.com/ubuntu focal-updates/universe amd64 Packages [1009 kB]\n",
+ "Reading package lists... Done \n",
  "E: The repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\n",
  "N: Updating from such a repository can't be done securely, and is therefore disabled by default.\n",
  "N: See apt-secure(8) manpage for repository creation and user configuration details.\n",
- "Hit:1 https://download.docker.com/linux/ubuntu focal InRelease\n",
- "Get:2 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
- "Hit:3 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
+ "Get:1 https://nvidia.github.io/libnvidia-container/stable/ubuntu18.04/amd64 InRelease [1484 B]\n",
+ "Hit:2 https://nvidia.github.io/nvidia-container-runtime/stable/ubuntu18.04/amd64 InRelease\n",
+ "Hit:3 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\u001b[33m\n",
  "Hit:4 http://archive.lambdalabs.com/ubuntu focal InRelease \u001b[0m\n",
- "Get:5 http://security.ubuntu.com/ubuntu focal-security InRelease [114 kB] \u001b[0m\u001b[33m\n",
- "Hit:6 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\u001b[33m\n",
- "Hit:7 https://packages.cloud.google.com/apt cloud-sdk InRelease \u001b[0m\u001b[33m\n",
- "Ign:8 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\n",
- "Hit:9 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\u001b[33m\n",
- "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\u001b[33m\n",
- "Get:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease [114 kB] \u001b[0m\n",
- "Err:12 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
+ "Hit:5 https://download.docker.com/linux/ubuntu focal InRelease \u001b[0m\n",
+ "Ign:6 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal InRelease \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
+ "Hit:7 http://archive.ubuntu.com/ubuntu focal InRelease \u001b[0m\n",
+ "Hit:8 https://packages.microsoft.com/repos/azure-cli focal InRelease \u001b[0m\n",
+ "Hit:9 http://security.ubuntu.com/ubuntu focal-security InRelease \u001b[0m\n",
+ "Hit:10 https://pkg.cloudflare.com/cloudflared focal InRelease \u001b[0m\u001b[33m\u001b[33m\n",
+ "Hit:11 http://archive.ubuntu.com/ubuntu focal-updates InRelease \u001b[0m\n",
+ "Hit:12 http://archive.ubuntu.com/ubuntu focal-backports InRelease \u001b[0m \u001b[0m\u001b[33m\u001b[33m\u001b[33m\n",
+ "Err:13 http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release\n",
  " 404 Not Found [IP: 185.125.190.52 80]\n",
- "Hit:13 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease \n",
- "Get:14 http://archive.ubuntu.com/ubuntu focal-backports InRelease [108 kB]\n",
- "Reading package lists... Done \u001b[0m33m\u001b[33m\u001b[33m\n",
+ "Hit:14 https://ppa.launchpadcontent.net/deadsnakes/ppa/ubuntu focal InRelease\n",
+ "Reading package lists... Done\u001b[33m\u001b[33m\n",
  "\u001b[1;31mE: \u001b[0mThe repository 'http://ppa.launchpad.net/jonathonf/ffmpeg-4/ubuntu focal Release' does not have a Release file.\u001b[0m\n",
  "\u001b[33mN: \u001b[0mUpdating from such a repository can't be done securely, and is therefore disabled by default.\u001b[0m\n",
  "\u001b[33mN: \u001b[0mSee apt-secure(8) manpage for repository creation and user configuration details.\u001b[0m\n",
@@ -346,33 +347,33 @@
  "text": [
  "Defaulting to user installation because normal site-packages is not writeable\n",
  "Collecting git+https://github.com/huggingface/datasets\n",
- " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-4yfcrkqv\n",
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-4yfcrkqv\n",
+ " Cloning https://github.com/huggingface/datasets to /tmp/pip-req-build-ju8bkpld\n",
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/datasets /tmp/pip-req-build-ju8bkpld\n",
  " Resolved https://github.com/huggingface/datasets to commit c902456677116a081f762fa2b4aad13a0aa04d6e\n",
  " Installing build dependencies ... \u001b[?25ldone\n",
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
  "\u001b[?25hRequirement already satisfied: dill<0.3.7 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.3.6)\n",
+ "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
+ "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.23.5)\n",
+ "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
  "Requirement already satisfied: packaging in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (22.0)\n",
  "Requirement already satisfied: xxhash in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.1.0)\n",
- "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (3.8.3)\n",
- "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.23.5)\n",
- "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
- "Requirement already satisfied: fsspec[http]>=2021.11.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2022.11.0)\n",
- "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\n",
+ "Requirement already satisfied: pyarrow>=6.0.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
  "Requirement already satisfied: responses<0.19 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.18.0)\n",
+ "Requirement already satisfied: multiprocess in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.70.14)\n",
+ "Requirement already satisfied: fsspec[http]>=2021.11.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2022.11.0)\n",
+ "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (1.5.1)\n",
  "Requirement already satisfied: tqdm>=4.62.1 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (4.64.1)\n",
- "Requirement already satisfied: pyarrow>=6.0.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (10.0.1)\n",
- "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (2.28.1)\n",
+ "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from datasets==2.7.1.dev0) (5.3.1)\n",
  "Requirement already satisfied: huggingface-hub<1.0.0,>=0.2.0 in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.11.1)\n",
- "Requirement already satisfied: multiprocess in ./.local/lib/python3.8/site-packages (from datasets==2.7.1.dev0) (0.70.14)\n",
- "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (2.1.1)\n",
- "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
- "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.3)\n",
- "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.1)\n",
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.8.2)\n",
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (4.0.2)\n",
+ "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.1)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (6.0.3)\n",
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets==2.7.1.dev0) (19.3.0)\n",
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (4.0.2)\n",
+ "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (2.1.1)\n",
+ "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->datasets==2.7.1.dev0) (1.3.3)\n",
  "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (3.0.12)\n",
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.2.0->datasets==2.7.1.dev0) (4.4.0)\n",
  "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->datasets==2.7.1.dev0) (2019.11.28)\n",
@@ -383,49 +384,49 @@
  "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.1->pandas->datasets==2.7.1.dev0) (1.14.0)\n",
  "Defaulting to user installation because normal site-packages is not writeable\n",
  "Collecting git+https://github.com/huggingface/transformers\n",
- " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-kaly439h\n",
- " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-kaly439h\n",
- " Resolved https://github.com/huggingface/transformers to commit ba9da49aa298345022f35a0b7be44ce4c72b85c2\n",
+ " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-9scgt3ru\n",
+ " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-9scgt3ru\n",
+ " Resolved https://github.com/huggingface/transformers to commit d994473b05a83ea398d9f10ca458855df095e22d\n",
  " Installing build dependencies ... \u001b[?25ldone\n",
  "\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
  "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
- "\u001b[?25hRequirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
- "Requirement already satisfied: regex!=2019.12.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
- "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.13.2)\n",
+ "\u001b[?25hRequirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.13.2)\n",
+ "Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.11.1)\n",
+ "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (22.0)\n",
  "Requirement already satisfied: numpy>=1.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (1.23.5)\n",
+ "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
  "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (5.3.1)\n",
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2.28.1)\n",
- "Requirement already satisfied: huggingface-hub<1.0,>=0.10.0 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (0.11.1)\n",
+ "Requirement already satisfied: regex!=2019.12.17 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (2022.10.31)\n",
  "Requirement already satisfied: tqdm>=4.27 in ./.local/lib/python3.8/site-packages (from transformers==4.26.0.dev0) (4.64.1)\n",
- "Requirement already satisfied: filelock in /usr/lib/python3/dist-packages (from transformers==4.26.0.dev0) (3.0.12)\n",
  "Requirement already satisfied: typing-extensions>=3.7.4.3 in ./.local/lib/python3.8/site-packages (from huggingface-hub<1.0,>=0.10.0->transformers==4.26.0.dev0) (4.4.0)\n",
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (1.26.13)\n",
- "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2019.11.28)\n",
- "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2.8)\n",
  "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (2.1.1)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2.8)\n",
+ "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests->transformers==4.26.0.dev0) (2019.11.28)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->transformers==4.26.0.dev0) (1.26.13)\n",
  "Defaulting to user installation because normal site-packages is not writeable\n",
  "Requirement already satisfied: librosa in ./.local/lib/python3.8/site-packages (0.9.2)\n",
+ "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
  "Requirement already satisfied: joblib>=0.14 in ./.local/lib/python3.8/site-packages (from librosa) (1.2.0)\n",
+ "Requirement already satisfied: soundfile>=0.10.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.11.0)\n",
+ "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.23.5)\n",
+ "Requirement already satisfied: pooch>=1.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.6.0)\n",
  "Requirement already satisfied: decorator>=4.0.10 in /usr/lib/python3/dist-packages (from librosa) (4.4.2)\n",
- "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
- "Requirement already satisfied: numba>=0.45.1 in ./.local/lib/python3.8/site-packages (from librosa) (0.56.4)\n",
  "Requirement already satisfied: audioread>=2.1.9 in ./.local/lib/python3.8/site-packages (from librosa) (3.0.0)\n",
- "Requirement already satisfied: pooch>=1.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.6.0)\n",
+ "Requirement already satisfied: numba>=0.45.1 in ./.local/lib/python3.8/site-packages (from librosa) (0.56.4)\n",
+ "Requirement already satisfied: scipy>=1.2.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.9.3)\n",
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from librosa) (22.0)\n",
- "Requirement already satisfied: numpy>=1.17.0 in ./.local/lib/python3.8/site-packages (from librosa) (1.23.5)\n",
- "Requirement already satisfied: scikit-learn>=0.19.1 in /usr/lib/python3/dist-packages (from librosa) (0.22.2.post1)\n",
  "Requirement already satisfied: resampy>=0.2.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.4.2)\n",
- "Requirement already satisfied: soundfile>=0.10.2 in ./.local/lib/python3.8/site-packages (from librosa) (0.11.0)\n",
  "Requirement already satisfied: setuptools in /usr/lib/python3/dist-packages (from numba>=0.45.1->librosa) (45.2.0)\n",
- "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\n",
  "Requirement already satisfied: llvmlite<0.40,>=0.39.0dev0 in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (0.39.1)\n",
- "Requirement already satisfied: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\n",
+ "Requirement already satisfied: importlib-metadata in ./.local/lib/python3.8/site-packages (from numba>=0.45.1->librosa) (5.0.0)\n",
  "Requirement already satisfied: requests>=2.19.0 in ./.local/lib/python3.8/site-packages (from pooch>=1.0->librosa) (2.28.1)\n",
+ "Requirement already satisfied: appdirs>=1.3.0 in /usr/lib/python3/dist-packages (from pooch>=1.0->librosa) (1.4.3)\n",
  "Requirement already satisfied: cffi>=1.0 in /usr/lib/python3/dist-packages (from soundfile>=0.10.2->librosa) (1.14.0)\n",
- "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (1.26.13)\n",
  "Requirement already satisfied: certifi>=2017.4.17 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2019.11.28)\n",
- "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.1.1)\n",
  "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.8)\n",
+ "Requirement already satisfied: charset-normalizer<3,>=2 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (2.1.1)\n",
+ "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests>=2.19.0->pooch>=1.0->librosa) (1.26.13)\n",
  "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->numba>=0.45.1->librosa) (1.0.0)\n",
  "Defaulting to user installation because normal site-packages is not writeable\n",
  "Requirement already satisfied: jiwer in ./.local/lib/python3.8/site-packages (2.5.1)\n",
@@ -433,59 +434,59 @@
  "Requirement already satisfied: rapidfuzz<3.0.0,>=2.3.0 in ./.local/lib/python3.8/site-packages (from levenshtein==0.20.2->jiwer) (2.13.6)\n",
  "Defaulting to user installation because normal site-packages is not writeable\n",
  "Requirement already satisfied: gradio in ./.local/lib/python3.8/site-packages (3.13.0)\n",
- "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
- "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
- "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
- "Requirement already satisfied: pillow in /usr/lib/python3/dist-packages (from gradio) (7.0.0)\n",
- "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
+ "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
  "Requirement already satisfied: aiohttp in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
- "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
- "Requirement already satisfied: fsspec in ./.local/lib/python3.8/site-packages (from gradio) (2022.11.0)\n",
- "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
  "Requirement already satisfied: pandas in ./.local/lib/python3.8/site-packages (from gradio) (1.5.1)\n",
- "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
- "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
- "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
- "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
- "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
- "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
  "Requirement already satisfied: pydub in ./.local/lib/python3.8/site-packages (from gradio) (0.25.1)\n",
+ "Requirement already satisfied: websockets>=10.0 in ./.local/lib/python3.8/site-packages (from gradio) (10.4)\n",
+ "Requirement already satisfied: httpx in ./.local/lib/python3.8/site-packages (from gradio) (0.23.1)\n",
+ "Requirement already satisfied: pillow in /usr/lib/python3/dist-packages (from gradio) (7.0.0)\n",
+ "Requirement already satisfied: uvicorn in ./.local/lib/python3.8/site-packages (from gradio) (0.20.0)\n",
+ "Requirement already satisfied: paramiko in ./.local/lib/python3.8/site-packages (from gradio) (2.12.0)\n",
+ "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
  "Requirement already satisfied: h11<0.13,>=0.11 in ./.local/lib/python3.8/site-packages (from gradio) (0.12.0)\n",
- "Requirement already satisfied: pyyaml in /usr/lib/python3/dist-packages (from gradio) (5.3.1)\n",
  "Requirement already satisfied: requests in ./.local/lib/python3.8/site-packages (from gradio) (2.28.1)\n",
+ "Requirement already satisfied: fsspec in ./.local/lib/python3.8/site-packages (from gradio) (2022.11.0)\n",
+ "Requirement already satisfied: orjson in ./.local/lib/python3.8/site-packages (from gradio) (3.8.3)\n",
+ "Requirement already satisfied: python-multipart in ./.local/lib/python3.8/site-packages (from gradio) (0.0.5)\n",
+ "Requirement already satisfied: pydantic in ./.local/lib/python3.8/site-packages (from gradio) (1.10.2)\n",
+ "Requirement already satisfied: markdown-it-py[linkify,plugins] in ./.local/lib/python3.8/site-packages (from gradio) (2.1.0)\n",
+ "Requirement already satisfied: ffmpy in ./.local/lib/python3.8/site-packages (from gradio) (0.3.0)\n",
+ "Requirement already satisfied: fastapi in ./.local/lib/python3.8/site-packages (from gradio) (0.88.0)\n",
+ "Requirement already satisfied: jinja2 in ./.local/lib/python3.8/site-packages (from gradio) (3.1.2)\n",
+ "Requirement already satisfied: matplotlib in ./.local/lib/python3.8/site-packages (from gradio) (3.5.3)\n",
  "Requirement already satisfied: pycryptodome in ./.local/lib/python3.8/site-packages (from gradio) (3.16.0)\n",
- "Requirement already satisfied: numpy in ./.local/lib/python3.8/site-packages (from gradio) (1.23.5)\n",
- "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\n",
- "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (4.0.2)\n",
+ "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.1)\n",
+ "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (6.0.3)\n",
  "Requirement already satisfied: frozenlist>=1.1.1 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.3)\n",
  "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->gradio) (19.3.0)\n",
- "Requirement already satisfied: multidict<7.0,>=4.5 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (6.0.3)\n",
+ "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (4.0.2)\n",
+ "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (2.1.1)\n",
  "Requirement already satisfied: yarl<2.0,>=1.0 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.8.2)\n",
- "Requirement already satisfied: aiosignal>=1.1.2 in ./.local/lib/python3.8/site-packages (from aiohttp->gradio) (1.3.1)\n",
  "Requirement already satisfied: starlette==0.22.0 in ./.local/lib/python3.8/site-packages (from fastapi->gradio) (0.22.0)\n",
  "Requirement already satisfied: typing-extensions>=3.10.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (4.4.0)\n",
  "Requirement already satisfied: anyio<5,>=3.4.0 in ./.local/lib/python3.8/site-packages (from starlette==0.22.0->fastapi->gradio) (3.6.2)\n",
- "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
- "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx->gradio) (2019.11.28)\n",
  "Requirement already satisfied: rfc3986[idna2008]<2,>=1.3 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.5.0)\n",
  "Requirement already satisfied: sniffio in ./.local/lib/python3.8/site-packages (from httpx->gradio) (1.3.0)\n",
+ "Requirement already satisfied: certifi in /usr/lib/python3/dist-packages (from httpx->gradio) (2019.11.28)\n",
+ "Requirement already satisfied: httpcore<0.17.0,>=0.15.0 in ./.local/lib/python3.8/site-packages (from httpx->gradio) (0.15.0)\n",
  "Requirement already satisfied: MarkupSafe>=2.0 in ./.local/lib/python3.8/site-packages (from jinja2->gradio) (2.1.1)\n",
  "Requirement already satisfied: mdurl~=0.1 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.1.2)\n",
- "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
  "Requirement already satisfied: linkify-it-py~=1.0 in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (1.0.3)\n",
- "Requirement already satisfied: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
+ "Requirement already satisfied: mdit-py-plugins in ./.local/lib/python3.8/site-packages (from markdown-it-py[linkify,plugins]->gradio) (0.3.3)\n",
+ "Requirement already satisfied: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
  "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (1.0.1)\n",
- "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\n",
  "Requirement already satisfied: packaging>=20.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (22.0)\n",
- "Requirement already satisfied: python-dateutil>=2.7 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (2.8.2)\n",
  "Requirement already satisfied: cycler>=0.10 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (0.10.0)\n",
+ "Requirement already satisfied: pyparsing>=2.2.1 in /usr/lib/python3/dist-packages (from matplotlib->gradio) (2.4.6)\n",
+ "Requirement already satisfied: fonttools>=4.22.0 in ./.local/lib/python3.8/site-packages (from matplotlib->gradio) (4.38.0)\n",
  "Requirement already satisfied: pytz>=2020.1 in ./.local/lib/python3.8/site-packages (from pandas->gradio) (2022.5)\n",
+ "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
  "Requirement already satisfied: six in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.14.0)\n",
  "Requirement already satisfied: pynacl>=1.0.1 in /usr/lib/python3/dist-packages (from paramiko->gradio) (1.3.0)\n",
- "Requirement already satisfied: bcrypt>=3.1.3 in ./.local/lib/python3.8/site-packages (from paramiko->gradio) (4.0.1)\n",
  "Requirement already satisfied: cryptography>=2.5 in /usr/lib/python3/dist-packages (from paramiko->gradio) (2.8)\n",
- "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->gradio) (2.8)\n",
  "Requirement already satisfied: urllib3<1.27,>=1.21.1 in ./.local/lib/python3.8/site-packages (from requests->gradio) (1.26.13)\n",
+ "Requirement already satisfied: idna<4,>=2.5 in /usr/lib/python3/dist-packages (from requests->gradio) (2.8)\n",
  "Requirement already satisfied: click>=7.0 in /usr/lib/python3/dist-packages (from uvicorn->gradio) (7.0)\n",
  "Requirement already satisfied: uc-micro-py in ./.local/lib/python3.8/site-packages (from linkify-it-py~=1.0->markdown-it-py[linkify,plugins]->gradio) (1.0.1)\n",
  "Defaulting to user installation because normal site-packages is not writeable\n",
@@ -554,7 +555,7 @@
  {
  "data": {
  "application/vnd.jupyter.widget-view+json": {
- "model_id": "1ac74505b6d84e499c03b22286c4baa9",
+ "model_id": "ad867c59abb44253a78ca06b8853a84d",
  "version_major": 2,
  "version_minor": 0
  },
@@ -713,7 +714,7 @@
  " all_datasets = []\n",
  " # iterate over the datasets we want to interleave\n",
  " for i, dataset_name in enumerate(dataset_names):\n",
- " dataset = load_dataset(dataset_name, dataset_config_names[i], split=splits[i], streaming=True, **kwargs)\n",
+ " dataset = load_dataset(dataset_name, dataset_config_names[i], split=splits[i], streaming=False, **kwargs)\n",
  " # resample to specified sampling rate\n",
  " dataset = dataset.cast_column(\"audio\", Audio(sampling_rate))\n",
  " # normalise columns to [\"audio\", \"sentence\"]\n",
@@ -738,16 +739,7 @@
  "id": "qOwlctMhNmCG",
  "tags": []
  },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
- "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n"
- ]
- }
- ],
+ "outputs": [],
  "source": [
  "ds = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
  "\n"
@@ -770,23 +762,13 @@
  "metadata": {
  "id": "imRHJOpm4V_j"
  },
- "outputs": [
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n",
- "Found cached dataset fleurs (/home/ubuntu/.cache/huggingface/datasets/google___fleurs/el_gr/2.0.0/aabb39fb29739c495517ac904e2886819b6e344702f0a5b5283cb178b087c94a)\n",
- "Found cached dataset common_voice_11_0 (/home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f)\n"
- ]
- }
- ],
+ "outputs": [],
  "source": [
  "from datasets import IterableDatasetDict\n",
  "raw_datasets = IterableDatasetDict()\n",
  "\n",
  "raw_datasets[\"train\"] = load_multiple_streaming_datasets(dataset_names, dataset_config_names=dataset_config_names, text_column_names=text_column_names, use_auth_token=True)\n",
- "raw_datasets[\"test\"] = load_dataset(\"mozilla-foundation/common_voice_11_0\", \"el\", split=\"test\", streaming=True, use_auth_token=True)\n",
+ "raw_datasets[\"test\"] = load_dataset(\"mozilla-foundation/common_voice_11_0\", \"el\", split=\"test\", streaming=False, use_auth_token=True)\n",
  "\n",
  "\n",
  "#raw_datasets = raw_datasets.remove_columns([\"accent\", \"age\", \"client_id\", \"down_votes\", \"gender\", \"locale\", \"path\", \"segment\", \"up_votes\"])\n",
@@ -1013,29 +995,7 @@
  "metadata": {
  "id": "a37a7cdb-9013-427f-8de9-6a8d0e9dc684"
  },
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "5eb200f925f84e14bc08341ee8620fd9",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- " 0%| | 0/6430 [00:00<?, ?ex/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Loading cached processed dataset at /home/ubuntu/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/el/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-52a8b70c074fdab6.arrow\n"
- ]
- }
- ],
+ "outputs": [],
  "source": [
  "vectorized_datasets = raw_datasets.map(prepare_dataset, remove_columns=list(next(iter(raw_datasets.values())).features)).with_format(\"torch\")"
  ]
@@ -1052,32 +1012,12 @@
  },
  {
  "cell_type": "code",
- "execution_count": 24,
+ "execution_count": 17,
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c",
  "metadata": {
  "id": "1b145699-acfc-4b1d-93a2-a2ad3d62674c"
  },
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "{'input_features': tensor([[-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
- " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
- " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
- " ...,\n",
- " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
- " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154],\n",
- " [-0.8154, -0.8154, -0.8154, ..., -0.8154, -0.8154, -0.8154]]), 'input_length': tensor(6.6000), 'labels': tensor([50258, 50281, 50359, 50363, 7068, 26263, 11383, 3596, 2080, 3659,\n",
- " 10073, 30599, 5691, 6744, 8828, 11658, 3371, 17321, 30320, 11383,\n",
- " 3659, 5337, 4339, 20511, 4915, 3371, 33908, 44035, 3721, 19264,\n",
- " 25090, 7597, 17928, 24841, 8385, 3835, 4903, 2080, 2805, 8385,\n",
- " 3721, 39320, 8335, 3596, 21457, 4339, 5074, 1800, 8715, 6956,\n",
- " 1800, 5958, 14836, 8385, 1800, 34079, 8385, 16946, 8066, 5733,\n",
- " 24296, 9137, 9903, 50257])}\n"
- ]
- }
- ],
+ "outputs": [],
  "source": [
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].shuffle(\n",
  " #buffer_size=500,\n",
@@ -1100,7 +1040,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 25,
+ "execution_count": 18,
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6",
  "metadata": {
  "id": "01cb25ef-4bb0-4325-9461-f59198acadf6"
@@ -1125,27 +1065,12 @@
  },
  {
  "cell_type": "code",
- "execution_count": 26,
+ "execution_count": 19,
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac",
  "metadata": {
  "id": "333f7f6e-6053-4d3b-8924-c733c79b82ac"
  },
- "outputs": [
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "aefbdf517ed24020b4fd372739f37e5f",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- " 0%| | 0/7 [00:00<?, ?ba/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
+ "outputs": [],
  "source": [
  "vectorized_datasets[\"train\"] = vectorized_datasets[\"train\"].filter(\n",
  " is_audio_in_length_range,\n",
@@ -1220,7 +1145,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 27,
+ "execution_count": 20,
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5",
  "metadata": {
  "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
@@ -1272,7 +1197,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 28,
+ "execution_count": 21,
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42",
  "metadata": {
  "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
@@ -1305,7 +1230,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 29,
+ "execution_count": 22,
  "id": "b22b4011-f31f-4b57-b684-c52332f92890",
  "metadata": {
  "colab": {
@@ -1356,7 +1281,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 30,
+ "execution_count": 23,
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb",
  "metadata": {
  "id": "a11d1bfc-9e28-460f-a287-72d8f7bc1acb"
@@ -1405,7 +1330,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 31,
+ "execution_count": 24,
  "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f",
  "metadata": {
  "colab": {
@@ -1443,21 +1368,7 @@
  {
  "data": {
  "application/vnd.jupyter.widget-view+json": {
- "model_id": "27fec52020a2407fa93dd57e98de8fc9",
- "version_major": 2,
- "version_minor": 0
- },
- "text/plain": [
- "Downloading: 0%| | 0.00/1.04k [00:00<?, ?B/s]"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- },
- {
- "data": {
- "application/vnd.jupyter.widget-view+json": {
- "model_id": "f8c10225aa194c909eeb19170ac75d1f",
+ "model_id": "18e0d00451ec4e10b1cea9b9d3748384",
  "version_major": 2,
  "version_minor": 0
  },
@@ -1490,7 +1401,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 32,
+ "execution_count": 25,
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f",
  "metadata": {
  "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
@@ -1527,7 +1438,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 33,
+ "execution_count": 26,
  "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a",
  "metadata": {
  "colab": {
@@ -1570,7 +1481,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 34,
+ "execution_count": 27,
  "id": "o72eOpGzD_sK",
  "metadata": {
  "colab": {
@@ -1584,7 +1495,7 @@
  "name": "stdout",
  "output_type": "stream",
  "text": [
- "Tue Dec 13 19:33:07 2022 \n",
+ "Tue Dec 13 21:29:08 2022 \n",
  "+-----------------------------------------------------------------------------+\n",
  "| NVIDIA-SMI 515.65.01 Driver Version: 515.65.01 CUDA Version: 11.7 |\n",
  "|-------------------------------+----------------------+----------------------+\n",
@@ -1593,7 +1504,7 @@
  "| | | MIG M. |\n",
  "|===============================+======================+======================|\n",
  "| 0 NVIDIA A100-SXM... On | 00000000:06:00.0 Off | 0 |\n",
- "| N/A 31C P0 46W / 400W | 2MiB / 40960MiB | 0% Default |\n",
+ "| N/A 32C P0 47W / 400W | 2MiB / 40960MiB | 0% Default |\n",
  "| | | Disabled |\n",
  "+-------------------------------+----------------------+----------------------+\n",
  " \n",
@@ -1634,7 +1545,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 35,
+ "execution_count": 28,
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2",
  "metadata": {
  "id": "3ac16b62-b3c0-4c68-8f3d-9ecf471534b2"
@@ -1667,7 +1578,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 36,
+ "execution_count": 29,
  "id": "d546d7fe-0543-479a-b708-2ebabec19493",
  "metadata": {
  "colab": {
@@ -2281,7 +2192,7 @@
  },
  {
  "cell_type": "code",
- "execution_count": 37,
+ "execution_count": 30,
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672",
  "metadata": {
  "id": "a1ccb9ed-cbc8-4419-91c0-651e9424b672"
@@ -2374,21 +2285,22 @@
  "name": "stderr",
  "output_type": "stream",
  "text": [
- "Loading model from ./whisper-medium-el/checkpoint-3000.\n",
- "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
+ "Loading model from ./whisper-medium-el/checkpoint-4000.\n",
  "/home/ubuntu/.local/lib/python3.8/site-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
  " warnings.warn(\n",
  "***** Running training *****\n",
- " Num examples = 6428\n",
- " Num Epochs = 25\n",
+ " Num examples = 160000\n",
+ " Num Epochs = 9223372036854775807\n",
  " Instantaneous batch size per device = 32\n",
  " Total train batch size (w. parallel, distributed & accumulation) = 32\n",
  " Gradient Accumulation steps = 1\n",
  " Total optimization steps = 5000\n",
  " Number of trainable parameters = 763857920\n",
  " Continuing training from checkpoint, will skip to saved global_step\n",
- " Continuing training from epoch 14\n",
- " Continuing training from global step 3000\n"
+ " Continuing training from epoch 0\n",
+ " Continuing training from global step 4000\n",
+ "Reading metadata...: 1914it [00:00, 4074.06it/s]\n",
+ "The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n"
  ]
  },
  {
@@ -2397,8 +2309,8 @@
  "\n",
  " <div>\n",
  " \n",
- " <progress value='4122' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
- " [4122/5000 1:52:06 < 1:27:52, 0.17 it/s, Epoch 19.58/25]\n",
+ " <progress value='4012' max='5000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [4012/5000 01:11 < 1:57:29, 0.14 it/s, Epoch 0.00/9223372036854775807]\n",
  " </div>\n",
  " <table border=\"1\" class=\"dataframe\">\n",
  " <thead>\n",
@@ -2406,16 +2318,9 @@
  " <th>Step</th>\n",
  " <th>Training Loss</th>\n",
  " <th>Validation Loss</th>\n",
- " <th>Wer</th>\n",
  " </tr>\n",
  " </thead>\n",
  " <tbody>\n",
- " <tr>\n",
- " <td>4000</td>\n",
- " <td>0.000300</td>\n",
- " <td>0.367278</td>\n",
- " <td>11.534175</td>\n",
- " </tr>\n",
  " </tbody>\n",
  "</table><p>"
  ],
@@ -2425,27 +2330,6 @@
  },
  "metadata": {},
  "output_type": "display_data"
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: path, input_length, gender, accent, up_votes, client_id, locale, age, segment, down_votes. If path, input_length, gender, accent, up_votes, client_id, locale, age, segment, down_votes are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message.\n",
- "***** Running Evaluation *****\n",
- " Num examples = 1696\n",
- " Batch size = 16\n",
- "Saving model checkpoint to ./whisper-medium-el/checkpoint-4000\n",
- "Configuration saved in ./whisper-medium-el/checkpoint-4000/config.json\n",
- "Model weights saved in ./whisper-medium-el/checkpoint-4000/pytorch_model.bin\n",
- "Feature extractor saved in ./whisper-medium-el/checkpoint-4000/preprocessor_config.json\n",
- "tokenizer config file saved in ./whisper-medium-el/checkpoint-4000/tokenizer_config.json\n",
- "Special tokens file saved in ./whisper-medium-el/checkpoint-4000/special_tokens_map.json\n",
- "added tokens file saved in ./whisper-medium-el/checkpoint-4000/added_tokens.json\n",
- "Feature extractor saved in ./whisper-medium-el/preprocessor_config.json\n",
- "tokenizer config file saved in ./whisper-medium-el/tokenizer_config.json\n",
- "Special tokens file saved in ./whisper-medium-el/special_tokens_map.json\n",
- "added tokens file saved in ./whisper-medium-el/added_tokens.json\n"
- ]
  }
  ],
  "source": [

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb25d05dcb2d400df9f2d8b8019e39d601abd96db1d8851edcb5dea2546d6882
+oid sha256:8f7fdd05661053c2949f2de6138c02cb1fe501fbe43efcf806797c3e43cbf808
 size 3055754841

runs/Dec13_21-29-08_129-146-102-49/1670966960.518305/events.out.tfevents.1670966960.129-146-102-49.882304.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652c159c0a7bbc04d6c208c74e4668602cb677b0fc2d296735cd23cd3d391b2b
+size 5916

runs/Dec13_21-29-08_129-146-102-49/events.out.tfevents.1670966960.129-146-102-49.882304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c6d5d76a7999c988e99742cae5b57c5aa438dc6403c604611d0c8fd18754328
+size 5603

runs/Dec13_21-57-38_129-146-102-49/1670968669.9597044/events.out.tfevents.1670968669.129-146-102-49.882304.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8668bd5e2470303db22eb81688526a881371c3506fdfeed7a6b32abc5192a1e
+size 5916

runs/Dec13_21-57-38_129-146-102-49/events.out.tfevents.1670968669.129-146-102-49.882304.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a61ed2fa7d6d2ac64d6e063e35f8b5541406347236af61ace7e3f08422daea
+size 4348

runs/Dec13_22-18-00_129-146-102-49/1670969892.775061/events.out.tfevents.1670969892.129-146-102-49.1014402.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51450fedd70a8ed8e04dbdda335b86fff15a62346527cf67bef861a20bf39cde
+size 5916

runs/Dec13_22-18-00_129-146-102-49/1670995449.379962/events.out.tfevents.1670995449.129-146-102-49.1014402.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ad24d679255e97efd512a0e6ec44b3d1b3f9d6b9fd69a929d4f4b65635093f
+size 5916

runs/Dec13_22-18-00_129-146-102-49/events.out.tfevents.1670969892.129-146-102-49.1014402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af928d9b3e795892da6df5ac604d6bb4c9799d8fbae2048212044a62e879c0fc
+size 15254

runs/Dec14_05-46-08_129-146-102-49/1670996781.2697837/events.out.tfevents.1670996781.129-146-102-49.1113148.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1b3e632cba6fe6e654853b87efedea97668491d8e6906fb42ebf1c6b1f013cc
+size 5916

runs/Dec14_05-46-08_129-146-102-49/events.out.tfevents.1670996781.129-146-102-49.1113148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243ca82c57c99466d5246efd3eb4dd017e04c059b7b31d2befe0ea6f22a39214
+size 10946

runs/Dec14_09-33-49_129-146-102-49/1671010439.939292/events.out.tfevents.1671010439.129-146-102-49.1212260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3fea8291dc179c7503abc25f7377b71002351df3b2639e4e6228b997b64d90
+size 5916

runs/Dec14_09-33-49_129-146-102-49/events.out.tfevents.1671010439.129-146-102-49.1212260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ccb9309b9bb866e6e16f7627e4a4b88a932cd62d0f847514e94d0e2208d3716
+size 4347

runs/Dec14_10-24-09_129-146-102-49/1671013461.8981154/events.out.tfevents.1671013461.129-146-102-49.1508853.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af188c00a280a385bf7ede8ce3aea5fdf554d81e0aa7cab21884c04bcf42eb5e
+size 5916

runs/Dec14_10-24-09_129-146-102-49/events.out.tfevents.1671013461.129-146-102-49.1508853.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10f8350f1923948412c9c14188fa5cb649b2bf9081f63941e3fcf5ba378701a
+size 10945

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6bd23b820fb512afe9dc750c92419a54a859d6f1861d7b20b0b9f155340657b
+oid sha256:eeadae68908ede5e3241ff2195c01ad92b5ee3a7db47d3a44b664270809ad8db
 size 3643