Training in progress, step 400

fine-tune-atco2-non-streaming.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "8308975c",
+   "id": "153b977f",
    "metadata": {
     "id": "75b58048-7d14-4fc6-8085-1fc08c81b4a6"
    },
@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "002e5c77",
+   "id": "37b4b092",
    "metadata": {
     "id": "fbfa8ad5-4cdc-4512-9058-836cbbf65e1a"
    },
@@ -25,7 +25,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "293972e5",
+   "id": "3dc16bdb",
    "metadata": {
     "id": "afe0d503-ae4e-4aa7-9af4-dbcba52db41e"
    },
@@ -35,7 +35,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c197e7a9",
+   "id": "a0ed696e",
    "metadata": {
     "id": "9ae91ed4-9c3e-4ade-938e-f4c2dcfbfdc0"
    },
@@ -67,7 +67,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3e9d693e",
+   "id": "f9040bc6",
    "metadata": {
     "id": "e59b91d6-be24-4b5e-bb38-4977ea143a72"
    },
@@ -86,7 +86,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e5d2f792",
+   "id": "9770f95f",
    "metadata": {
     "id": "21b6316e-8a55-4549-a154-66d3da2ab74a"
    },
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0bd16c3d",
+   "id": "47ccc69a",
    "metadata": {
     "id": "3a680dfc-cbba-4f6c-8a1f-e1a5ff3f123a"
    },
@@ -127,7 +127,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "38d1e3d5",
+   "id": "20eb5cf7",
    "metadata": {
     "id": "b219c9dd-39b6-4a95-b2a1-3f547a1e7bc0"
    },
@@ -137,7 +137,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "fb6a5797",
+   "id": "b7ef7008",
    "metadata": {
     "id": "674429c5-0ab4-4adf-975b-621bb69eca38"
    },
@@ -155,7 +155,7 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "de423e45",
+   "id": "e4beab8c",
    "metadata": {
     "id": "a2787582-554f-44ce-9f38-4180a5ed6b44"
    },
@@ -171,7 +171,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "8f4df3c7",
+   "id": "a89ec3cc",
    "metadata": {},
    "outputs": [
     {
@@ -212,7 +212,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "998a5233",
+   "id": "6db3c688",
    "metadata": {
     "id": "d5c7c3d6-7197-41e7-a088-49b753c1681f"
    },
@@ -227,7 +227,7 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "d834bfb6",
+   "id": "4b53aecf",
    "metadata": {
     "id": "20ba635d-518c-47ac-97ee-3cad25f1e0ce"
    },
@@ -257,7 +257,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "589c1cf1",
+   "id": "88a8bfef",
    "metadata": {
     "id": "2d63b2d2-f68a-4d74-b7f1-5127f6d16605"
    },
@@ -267,7 +267,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "92e9bda0",
+   "id": "30f77c0c",
    "metadata": {
     "id": "601c3099-1026-439e-93e2-5635b3ba5a73"
    },
@@ -287,7 +287,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e8f68ff5",
+   "id": "ca870a25",
    "metadata": {
     "id": "560332eb-3558-41a1-b500-e83a9f695f84"
    },
@@ -297,7 +297,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ba59d5f0",
+   "id": "a1757ecc",
    "metadata": {
     "id": "32ec8068-0bd7-412d-b662-0edb9d1e7365"
    },
@@ -309,7 +309,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2b18e72b",
+   "id": "aad089dc",
    "metadata": {
     "id": "589d9ec1-d12b-4b64-93f7-04c63997da19"
    },
@@ -324,7 +324,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d6d354ea",
+   "id": "b42ff657",
    "metadata": {
     "id": "b2ef54d5-b946-4c1d-9fdc-adc5d01b46aa"
    },
@@ -335,7 +335,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "c6452e65",
+   "id": "47a93901",
    "metadata": {
     "id": "bc77d7bb-f9e2-47f5-b663-30f7a4321ce5"
    },
@@ -348,7 +348,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "82d0ac42",
+   "id": "22723907",
    "metadata": {
     "id": "93748af7-b917-4ecf-a0c8-7d89077ff9cb"
    },
@@ -358,7 +358,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6db15460",
+   "id": "4c94068f",
    "metadata": {
     "id": "2bc82609-a9fb-447a-a2af-99597c864029"
    },
@@ -372,7 +372,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "31c3f1fd",
+   "id": "c5ed14b7",
    "metadata": {
     "id": "c7b07f9b-ae0e-4f89-98f0-0c50d432eab6",
     "outputId": "5c004b44-86e7-4e00-88be-39e0af5eed69"
@@ -386,7 +386,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "41e76f9a",
+   "id": "fe3ec4d1",
    "metadata": {
     "id": "d2ef23f3-f4a8-483a-a2dc-080a7496cb1b"
    },
@@ -396,7 +396,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "09603bd4",
+   "id": "06729f05",
    "metadata": {
     "id": "5ff67654-5a29-4bb8-a69d-0228946c6f8d"
    },
@@ -412,7 +412,7 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "1cb92985",
+   "id": "e6d869dd",
    "metadata": {
     "id": "77d9f0c5-8607-4642-a8ac-c3ab2e223ea6"
    },
@@ -425,7 +425,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d9528e54",
+   "id": "c8a0f5f5",
    "metadata": {
     "id": "381acd09-0b0f-4d04-9eb3-f028ac0e5f2c"
    },
@@ -435,7 +435,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2972da25",
+   "id": "eb000f50",
    "metadata": {
     "id": "9649bf01-2e8a-45e5-8fca-441c13637b8f"
    },
@@ -447,7 +447,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "8ab54822",
+   "id": "8de557eb",
    "metadata": {
     "id": "6e6b0ec5-0c94-4e2c-ae24-c791be1b2255"
    },
@@ -467,7 +467,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1988343b",
+   "id": "add2d161",
    "metadata": {
     "id": "5a679f05-063d-41b3-9b58-4fc9c6ccf4fd"
    },
@@ -486,7 +486,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "f78f28f2",
+   "id": "67b39dba",
    "metadata": {
     "id": "f12e2e57-156f-417b-8cfb-69221cc198e8"
    },
@@ -499,7 +499,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4aa7d5d9",
+   "id": "82db95dd",
    "metadata": {
     "id": "00382a3e-abec-4cdd-a54c-d1aaa3ea4707"
    },
@@ -511,7 +511,7 @@
   {
    "cell_type": "code",
    "execution_count": 9,
-   "id": "f50a2edb",
+   "id": "2f58e84d",
    "metadata": {
     "id": "87122d71-289a-466a-afcf-fa354b18946b"
    },
@@ -531,7 +531,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e1d471fe",
+   "id": "a0a36ce6",
    "metadata": {},
    "source": [
     "We'll define our pre-processing strategy. We advise that you **do not** lower-case the transcriptions or remove punctuation unless mixing different datasets. This will enable you to fine-tune Whisper models that can predict punctuation and casing. Later, you will see how we can evaluate the predictions without punctuation or casing, so that the models benefit from the WER improvement obtained by normalising the transcriptions while still predicting fully formatted transcriptions."
@@ -540,7 +540,7 @@
   {
    "cell_type": "code",
    "execution_count": 10,
-   "id": "756e987b",
+   "id": "c580eca9",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -554,7 +554,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "246c0ec3",
+   "id": "75220c6e",
    "metadata": {},
    "source": [
     "Now we can write a function to prepare our data ready for the model:\n",
@@ -567,7 +567,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "b66341cd",
+   "id": "2b19b3b4",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -594,7 +594,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6e81112a",
+   "id": "b780de3a",
    "metadata": {
     "id": "70b319fb-2439-4ef6-a70d-a47bf41c4a13"
    },
@@ -605,7 +605,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "de797232",
+   "id": "33df4a27",
    "metadata": {
     "id": "7b73ab39-ffaf-4b9e-86e5-782963c6134b"
    },
@@ -841,7 +841,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ff5ca53b",
+   "id": "28280b1e",
    "metadata": {},
    "source": [
     "Finally, we filter any training data with audio samples longer than 30s. These samples would otherwise be truncated by the Whisper feature-extractor which could affect the stability of training. We define a function that returns `True` for samples that are less than 30s, and `False` for those that are longer:"
@@ -850,7 +850,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "d99b0f59",
+   "id": "74917d17",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -862,7 +862,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "99b7eb7e",
+   "id": "ad72b009",
    "metadata": {},
    "source": [
     "We apply our filter function to all samples of our training dataset through 🤗 Datasets' `.filter` method:"
@@ -871,7 +871,7 @@
   {
    "cell_type": "code",
    "execution_count": 14,
-   "id": "2944ce59",
+   "id": "ff62b10c",
    "metadata": {},
    "outputs": [
     {
@@ -891,7 +891,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0162b42e",
+   "id": "63f649b4",
    "metadata": {
     "id": "263a5a58-0239-4a25-b0df-c625fc9c5810"
    },
@@ -901,7 +901,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a02f599b",
+   "id": "f6da5590",
    "metadata": {
     "id": "a693e768-c5a6-453f-89a1-b601dcf7daf7"
    },
@@ -924,7 +924,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1e170a70",
+   "id": "7e49d443",
    "metadata": {
     "id": "8d230e6d-624c-400a-bbf5-fa660881df25"
    },
@@ -934,7 +934,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "54e0500b",
+   "id": "a7af1a62",
    "metadata": {
     "id": "04def221-0637-4a69-b242-d3f0c1d0ee78"
    },
@@ -960,7 +960,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "88b48f61",
+   "id": "6742bdde",
    "metadata": {
     "id": "8326221e-ec13-4731-bb4e-51e5fc1486c5"
    },
@@ -1001,7 +1001,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e77fd74a",
+   "id": "6a5bfad2",
    "metadata": {
     "id": "3cae7dbf-8a50-456e-a3a8-7fd005390f86"
    },
@@ -1012,7 +1012,7 @@
   {
    "cell_type": "code",
    "execution_count": 16,
-   "id": "9d5293a5",
+   "id": "d349c47c",
    "metadata": {
     "id": "fc834702-c0d3-4a96-b101-7b87be32bf42"
    },
@@ -1023,7 +1023,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "ab5dfc21",
+   "id": "2fb9bd9f",
    "metadata": {
     "id": "d62bb2ab-750a-45e7-82e9-61d6f4805698"
    },
@@ -1033,7 +1033,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "85ca98b1",
+   "id": "eb620cc8",
    "metadata": {
     "id": "66fee1a7-a44c-461e-b047-c3917221572e"
    },
@@ -1045,7 +1045,7 @@
   {
    "cell_type": "code",
    "execution_count": 17,
-   "id": "c20575d7",
+   "id": "a0cc7e31",
    "metadata": {
     "id": "b22b4011-f31f-4b57-b684-c52332f92890"
    },
@@ -1058,7 +1058,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b3cd5b3d",
+   "id": "2b750f0c",
    "metadata": {
     "id": "4f32cab6-31f0-4cb9-af4c-40ba0f5fc508"
    },
@@ -1078,7 +1078,7 @@
   {
    "cell_type": "code",
    "execution_count": 18,
-   "id": "8b3b9e6e",
+   "id": "cf3da153",
    "metadata": {
     "id": "23959a70-22d0-4ffe-9fa1-72b61e75bb52"
    },
@@ -1109,7 +1109,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "aa47a845",
+   "id": "3c40ea30",
    "metadata": {
     "id": "daf2a825-6d9f-4a23-b145-c37c0039075b"
    },
@@ -1119,7 +1119,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d8d3980c",
+   "id": "0763fedb",
    "metadata": {
     "id": "437a97fa-4864-476b-8abc-f28b8166cfa5"
    },
@@ -1131,7 +1131,7 @@
   {
    "cell_type": "code",
    "execution_count": 19,
-   "id": "66fb8109",
+   "id": "8b6d0fcc",
    "metadata": {
     "id": "5a10cc4b-07ec-4ebd-ac1d-7c601023594f"
    },
@@ -1144,7 +1144,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "6488d605",
+   "id": "516a3a07",
    "metadata": {
     "id": "a15ead5f-2277-4a39-937b-585c2497b2df"
    },
@@ -1155,7 +1155,7 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "id": "bb9b6538",
+   "id": "dad8cf04",
    "metadata": {
     "id": "62038ba3-88ed-4fce-84db-338f50dcd04f"
    },
@@ -1168,7 +1168,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8c8ac68d",
+   "id": "4e4ad9cb",
    "metadata": {
     "id": "2178dea4-80ca-47b6-b6ea-ba1915c90c06"
    },
@@ -1178,7 +1178,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3ff54dd4",
+   "id": "af61b4bd",
    "metadata": {
     "id": "c21af1e9-0188-4134-ac82-defc7bdcc436"
    },
@@ -1189,7 +1189,7 @@
   {
    "cell_type": "code",
    "execution_count": 21,
-   "id": "3c698301",
+   "id": "a9e18890",
    "metadata": {
     "id": "0ae3e9af-97b7-4aa0-ae85-20b23b5bcb3a"
    },
@@ -1223,7 +1223,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f4e63b34",
+   "id": "0a7aacb7",
    "metadata": {
     "id": "b3a944d8-3112-4552-82a0-be25988b3857"
    },
@@ -1234,7 +1234,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b109c728",
+   "id": "038105a5",
    "metadata": {
     "id": "bac29114-d226-4f54-97cf-8718c9f94e1e"
    },
@@ -1246,7 +1246,7 @@
   {
    "cell_type": "code",
    "execution_count": 22,
-   "id": "119edab5",
+   "id": "6df38176",
    "metadata": {
     "id": "d546d7fe-0543-479a-b708-2ebabec19493"
    },
@@ -1277,7 +1277,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b7228116",
+   "id": "d6f06247",
    "metadata": {
     "id": "uOrRhDGtN5S4"
    },
@@ -1288,7 +1288,7 @@
   {
    "cell_type": "code",
    "execution_count": 23,
-   "id": "fabad1e6",
+   "id": "3158c8e0",
    "metadata": {
     "id": "-2zQwMfEOBJq"
    },
@@ -1310,7 +1310,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8feb0de8",
+   "id": "20d51bc5",
    "metadata": {
     "id": "7f404cf9-4345-468c-8196-4bd101d9bd51"
    },
@@ -1320,7 +1320,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "1a63a349",
+   "id": "b1bac1cc",
    "metadata": {
     "id": "5e8b8d56-5a70-4f68-bd2e-f0752d0bd112"
    },
@@ -1337,7 +1337,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bc1ba2fe",
+   "id": "449b7807",
    "metadata": {
     "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de"
    },
@@ -1365,8 +1365,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='301' max='500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [301/500 1:46:59 < 1:11:12, 0.05 it/s, Epoch 6.38/11]\n",
+       "      <progress value='351' max='500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [351/500 2:07:16 < 54:20, 0.05 it/s, Epoch 7.45/11]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -1415,7 +1415,13 @@
        "      <td>18.134172</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
-       "</table><p>"
+       "</table><p>\n",
+       "    <div>\n",
+       "      \n",
+       "      <progress value='52' max='56' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [52/56 01:34 < 00:07, 0.54 it/s]\n",
+       "    </div>\n",
+       "    "
       ],
       "text/plain": [
        "<IPython.core.display.HTML object>"
@@ -1466,7 +1472,11 @@
       "Configuration saved in ./checkpoint-300/config.json\n",
       "Model weights saved in ./checkpoint-300/pytorch_model.bin\n",
       "Feature extractor saved in ./checkpoint-300/preprocessor_config.json\n",
-      "Feature extractor saved in ./preprocessor_config.json\n"
+      "Feature extractor saved in ./preprocessor_config.json\n",
+      "The following columns in the evaluation 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",
+      "***** Running Evaluation *****\n",
+      "  Num examples = 56\n",
+      "  Batch size = 1\n"
      ]
     }
    ],
@@ -1477,7 +1487,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "aa6aa51c",
+   "id": "06dc5477",
    "metadata": {
     "id": "c704f91e-241b-48c9-b8e0-f0da396a9663"
    },
@@ -1495,7 +1505,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "049805cf",
+   "id": "2385c318",
    "metadata": {
     "id": "090d676a-f944-4297-a938-a40eda0b2b68"
    },
@@ -1506,7 +1516,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "b014da90",
+   "id": "79cdaf1a",
    "metadata": {
     "id": "d7030622-caf7-4039-939b-6195cdaa2585"
    },
@@ -1517,7 +1527,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "61f78720",
+   "id": "fc5763f7",
    "metadata": {
     "id": "ca743fbd-602c-48d4-ba8d-a2fe60af64ba"
    },
@@ -1527,7 +1537,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c5d37e16",
+   "id": "78fc1970",
    "metadata": {
     "id": "7f737783-2870-4e35-aa11-86a42d7d997a"
    },

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de2e9a057a78b661960fe361039e46b708d14f8b441499a4cbee1ddb5ae92f5e
+oid sha256:d578355b6f15b04766cc526e98fb03f0c91df1e63339b2781585fd3c767247fe
 size 3055754841

runs/Dec10_19-43-08_28bc7e304ae9/events.out.tfevents.1670701396.28bc7e304ae9.29234.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff9b841276431c9b975b3d2df6f580f374598cc181a22b0568a9627ce8638feb
-size 8048
+oid sha256:f4ea206346175b73b7dea8dc1b9f371b42fe52eedd5e5ef7a22c21736207a756
+size 9312