diff --git "a/notebooks/finetuning_commafixer_with_LoRa.ipynb" "b/notebooks/finetuning_commafixer_with_LoRa.ipynb"
--- "a/notebooks/finetuning_commafixer_with_LoRa.ipynb"
+++ "b/notebooks/finetuning_commafixer_with_LoRa.ipynb"
@@ -1,59 +1,55 @@
{
- "cells":[
+ "cells": [
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"## Fine-tuning RoBERTa large for token classification\n",
"\n",
"Treats fixing commas as a NER problem, where for each token we predict whether a comma should be inserted after it. We assume input data has no commas, which ensures the input distribution is the same for the model, regardless of the types of mistakes users could make. The model would then restore the commas and leave the rest of the text intact."
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"dyUJpYnHWmCybknBwWLe5Z",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "dyUJpYnHWmCybknBwWLe5Z",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"import torch\n",
"torch.cuda.is_available()"
],
- "execution_count":1,
- "outputs":[
+ "execution_count": 1,
+ "outputs": [
{
- "data":{
- "text\/plain":[
+ "data": {
+ "text/plain": [
"True"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"dwzLkm8DtZ6gwwOBT2Y7rM",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"9tLzdz03okTFWD3Vy0h4vS"
+ "metadata": {
+ "datalore": {
+ "node_id": "dwzLkm8DtZ6gwwOBT2Y7rM",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "9tLzdz03okTFWD3Vy0h4vS"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"from datasets import load_dataset\n",
"from transformers import (\n",
" AutoModelForTokenClassification,\n",
@@ -69,209 +65,203 @@
"import re\n",
"import evaluate"
],
- "execution_count":2,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"kmU9kledu94gR9zgAN1Ga5",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"h8AdYv2Y3tw7Yb4W3IGoxc"
+ "execution_count": 2,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "kmU9kledu94gR9zgAN1Ga5",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "h8AdYv2Y3tw7Yb4W3IGoxc"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"model_checkpoint = \"roberta-large\""
],
- "execution_count":3,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"t1hpVurdN6Ji6IPIUFlqnB",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"sGTotT7rOtZWKTPgVm4gX6"
+ "execution_count": 3,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "t1hpVurdN6Ji6IPIUFlqnB",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "sGTotT7rOtZWKTPgVm4gX6"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"We will use the wikitext dataset, since it is large and has more diverse texts than, e.g., books, with fairly a lot of commas."
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"1L9Lgn5UOmYdIAB9VCLOUx",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "1L9Lgn5UOmYdIAB9VCLOUx",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"wikitext = load_dataset('wikitext', 'wikitext-103-v1') # TODO we should only load part of it, too big to train on whole anyway"
],
- "execution_count":4,
- "outputs":[
+ "execution_count": 4,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"b49ef90878574db2b0ee3e832b51f0e1"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "b49ef90878574db2b0ee3e832b51f0e1"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"EzocdU7ZnKbRTA6Qyb2eui"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "EzocdU7ZnKbRTA6Qyb2eui"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"b73ea2c1d22f48a588d04f63ae856ad6"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "b73ea2c1d22f48a588d04f63ae856ad6"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"5EyBntpe2omeh7zplkVxbz"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "5EyBntpe2omeh7zplkVxbz"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"4df35e53a0cc41118cf794e623c9e1ae"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "4df35e53a0cc41118cf794e623c9e1ae"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"YPtbQNg3pL68UM9OfASsNu"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "YPtbQNg3pL68UM9OfASsNu"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"d4f75e8ad8ae4b729303ccbe2283de3c"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "d4f75e8ad8ae4b729303ccbe2283de3c"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"mYXcmC0ka6gJT8jwrSYZGF"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "mYXcmC0ka6gJT8jwrSYZGF"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"10f1853410664a0b9cc9ea8693a64807"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "10f1853410664a0b9cc9ea8693a64807"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"tvLSuVyurIDaBZbUl4aC8p"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "tvLSuVyurIDaBZbUl4aC8p"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"f2d9c2140b3f4e068382f63a376c8cb1"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "f2d9c2140b3f4e068382f63a376c8cb1"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"SjJATq4Bu7Rd02ryJBysxk"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "SjJATq4Bu7Rd02ryJBysxk"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"f69e84b3b9634448b0141e11236366c3"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "f69e84b3b9634448b0141e11236366c3"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"kLgRm1cp86gQOV4nvn0nsn"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "kLgRm1cp86gQOV4nvn0nsn"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"cmS6SmnZ5bCm9dS4HcW3yj",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"yuWdT9AFjYlOMQTPOZZIUT"
+ "metadata": {
+ "datalore": {
+ "node_id": "cmS6SmnZ5bCm9dS4HcW3yj",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "yuWdT9AFjYlOMQTPOZZIUT"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"wikitext"
],
- "execution_count":5,
- "outputs":[
+ "execution_count": 5,
+ "outputs": [
{
- "data":{
- "text\/plain":[
+ "data": {
+ "text/plain": [
"DatasetDict({\n",
" test: Dataset({\n",
" features: ['text'],\n",
@@ -288,44 +278,40 @@
"})"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"gL2NZUdQOETnRVwSrzZMK6",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"gE1CBjdhArw5iApIeceEYR"
+ "metadata": {
+ "datalore": {
+ "node_id": "gL2NZUdQOETnRVwSrzZMK6",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "gE1CBjdhArw5iApIeceEYR"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"### Preprocessing"
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"TEOArfY5ox2vtfEeWFofK8",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "TEOArfY5ox2vtfEeWFofK8",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"label_list = [\n",
" \"O\",\n",
" \"B-COMMA\",\n",
@@ -339,42 +325,38 @@
" \"B-COMMA\": 1\n",
"}"
],
- "execution_count":6,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"mtshTbrO5e9UwX0mQbohcf",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"pW8zIwKks0yGy8XVO6sU9T"
+ "execution_count": 6,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "mtshTbrO5e9UwX0mQbohcf",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "pW8zIwKks0yGy8XVO6sU9T"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"Wikitext is already space tokenized. We use that information, remove commas from the data and append a COMMA tag to the preceding token."
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"cwIAYXqprU9uW3eS1d7ii6",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "cwIAYXqprU9uW3eS1d7ii6",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"def map_wikitext(x) -> dict:\n",
" tokens = x[\"text\"].split()\n",
" new_tokens, labels = [], []\n",
@@ -389,212 +371,205 @@
" new_tokens.append(token)\n",
" return {'tokens': new_tokens, 'tags': labels}"
],
- "execution_count":7,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"HD0Jlp59AnlQFmXvPheL48",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"u4ni0ncMGCkPMDSQTb2Fjz"
+ "execution_count": 7,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "HD0Jlp59AnlQFmXvPheL48",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "u4ni0ncMGCkPMDSQTb2Fjz"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"wikitext[\"train\"][3]"
],
- "execution_count":8,
- "outputs":[
+ "execution_count": 8,
+ "outputs": [
{
- "data":{
- "text\/plain":[
+ "data": {
+ "text/plain": [
"{'text': ' Senjō no Valkyria 3 : <unk> Chronicles ( Japanese : 戦場のヴァルキュリア3 , lit . Valkyria of the Battlefield 3 ) , commonly referred to as Valkyria Chronicles III outside Japan , is a tactical role @-@ playing video game developed by Sega and Media.Vision for the PlayStation Portable . Released in January 2011 in Japan , it is the third game in the Valkyria series . Employing the same fusion of tactical and real @-@ time gameplay as its predecessors , the story runs parallel to the first game and follows the \" Nameless \" , a penal military unit serving the nation of Gallia during the Second Europan War who perform secret black operations and are pitted against the Imperial unit \" <unk> Raven \" . \\n'}"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"vURwu7beQTkZL5mzHlfAjT",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"i6bHaRjA1inmjze1Y7w5KP"
+ "metadata": {
+ "datalore": {
+ "node_id": "vURwu7beQTkZL5mzHlfAjT",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "i6bHaRjA1inmjze1Y7w5KP"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"Other than mapping, we also filter empty texts (25% in wikitext), and very long paragraphs. We print texts starting with a comma, and remove the initial comma since we cannot represent it and assume no sentene should start with a comma."
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"YjN1hYHVnzLmr0byD0haSW",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "YjN1hYHVnzLmr0byD0haSW",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"wikitext_mapped = wikitext.filter(lambda x: x[\"text\"] and len(x[\"text\"].split()) < 512).map(map_wikitext)"
],
- "execution_count":9,
- "outputs":[
+ "execution_count": 9,
+ "outputs": [
{
- "name":"stdout",
- "text":[
+ "name": "stdout",
+ "text": [
" , \n",
"\n",
- " , the slight increase in comparison loop efficiency does not compensate for the extra iteration . Knuth 1998 gives a value of \n",
- "\n"
+ " , the slight increase in comparison loop efficiency does not compensate for the extra iteration . Knuth 1998 gives a value of \n"
],
- "output_type":"stream"
+ "output_type": "stream"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"4570a228ecd043198331a1378d9f9621"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "4570a228ecd043198331a1378d9f9621"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"zkpNXnOddd31KKr2PbuQbu"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "zkpNXnOddd31KKr2PbuQbu"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"73a77fce14294f9d9d1de72cbdb93bac"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "73a77fce14294f9d9d1de72cbdb93bac"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"oMvc26V11XATUcJL3MpaSx"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "oMvc26V11XATUcJL3MpaSx"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"85c2b88a530b4b10b836185d0fbc4f38"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "85c2b88a530b4b10b836185d0fbc4f38"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"3oLW1dUwUPqA7rzPEXv5I8"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "3oLW1dUwUPqA7rzPEXv5I8"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"9024a3a6a42c4bc3b0afdc30557ad09d"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "9024a3a6a42c4bc3b0afdc30557ad09d"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"MRLrkIa0FFrxwmmKmV2Hc2"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "MRLrkIa0FFrxwmmKmV2Hc2"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"1e08db6867a44093b73a3d78f92612d6"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "1e08db6867a44093b73a3d78f92612d6"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"3eCfbu6IspjzG6HvvX24Td"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "3eCfbu6IspjzG6HvvX24Td"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"e26308dff4c3457794b8cca3bb455485"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "e26308dff4c3457794b8cca3bb455485"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"JxGyWtrVY3EqxihT5S21Z6"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "JxGyWtrVY3EqxihT5S21Z6"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"prJX5QZg1VmAX6pN0mnyom",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"48CMjhbFyYMCFfudw3NWLS"
+ "metadata": {
+ "datalore": {
+ "node_id": "prJX5QZg1VmAX6pN0mnyom",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "48CMjhbFyYMCFfudw3NWLS"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"wikitext_mapped[\"train\"][1]"
],
- "execution_count":10,
- "outputs":[
+ "execution_count": 10,
+ "outputs": [
{
- "data":{
- "text\/plain":[
+ "data": {
+ "text/plain": [
"{'text': ' Senjō no Valkyria 3 : <unk> Chronicles ( Japanese : 戦場のヴァルキュリア3 , lit . Valkyria of the Battlefield 3 ) , commonly referred to as Valkyria Chronicles III outside Japan , is a tactical role @-@ playing video game developed by Sega and Media.Vision for the PlayStation Portable . Released in January 2011 in Japan , it is the third game in the Valkyria series . Employing the same fusion of tactical and real @-@ time gameplay as its predecessors , the story runs parallel to the first game and follows the \" Nameless \" , a penal military unit serving the nation of Gallia during the Second Europan War who perform secret black operations and are pitted against the Imperial unit \" <unk> Raven \" . \\n',\n",
" 'tokens': ['Senjō',\n",
" 'no',\n",
@@ -840,81 +815,76 @@
" 0]}"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"DCZXZMrMQzYcH8CUXHrd1E",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"jCn3aXRNlHZ54hwSvCOPY1"
+ "metadata": {
+ "datalore": {
+ "node_id": "DCZXZMrMQzYcH8CUXHrd1E",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "jCn3aXRNlHZ54hwSvCOPY1"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
-
- ],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"ucTrLhx3rypOaFAVs5dAeO",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "cell_type": "markdown",
+ "source": [],
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "ucTrLhx3rypOaFAVs5dAeO",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"seqeval = evaluate.load(\"seqeval\")"
],
- "execution_count":11,
- "outputs":[
+ "execution_count": 11,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"789a5c3db5704cd288d1e9f55d758813"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "789a5c3db5704cd288d1e9f55d758813"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"K630mpF3l5do8ry0ZFvxvF"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "K630mpF3l5do8ry0ZFvxvF"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"tW4ZovAZV62tVCQ5pZtFd0",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"u9kmEPsjJjMXH8QxYxCkzI"
+ "metadata": {
+ "datalore": {
+ "node_id": "tW4ZovAZV62tVCQ5pZtFd0",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "u9kmEPsjJjMXH8QxYxCkzI"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
+ "# TODO only compute for B-COMMA, not overall\n",
"def compute_metrics(p):\n",
" predictions, labels = p\n",
" predictions = np.argmax(predictions, axis=2)\n",
@@ -936,142 +906,136 @@
" \"accuracy\": results[\"overall_accuracy\"],\n",
" }"
],
- "execution_count":12,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"rRWP0oFCa1osvkitTVt0mM",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"w9WiJH27gOJfWxpv8b8zZU"
+ "execution_count": 12,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "rRWP0oFCa1osvkitTVt0mM",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "w9WiJH27gOJfWxpv8b8zZU"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"tokenizer = AutoTokenizer.from_pretrained('roberta-large', add_prefix_space=True)\n",
"tokenizer"
],
- "execution_count":13,
- "outputs":[
+ "execution_count": 13,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"980c254886c1489197bd9ca70d207508"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "980c254886c1489197bd9ca70d207508"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"nF2Su6O3raZwjaNRPC85xu"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "nF2Su6O3raZwjaNRPC85xu"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"d260f0b9f950478c907b62576ddac227"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "d260f0b9f950478c907b62576ddac227"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"dEDwPE4KTC0tVSGuAcl72X"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "dEDwPE4KTC0tVSGuAcl72X"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"a656fa8f2d91428eb812643b8227dc16"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "a656fa8f2d91428eb812643b8227dc16"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"w7Ii5jWzd4jT9idw2faCzz"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "w7Ii5jWzd4jT9idw2faCzz"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"396a09f765c74d01a69abd7c2b4c6dfc"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "396a09f765c74d01a69abd7c2b4c6dfc"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"n3ZrIydi6O5i4meoL30arw"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "n3ZrIydi6O5i4meoL30arw"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "text\/plain":[
- "RobertaTokenizerFast(name_or_path='roberta-large', vocab_size=50265, model_max_length=512, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '<\/s>', 'unk_token': '<unk>', 'sep_token': '<\/s>', 'pad_token': '<pad>', 'cls_token': '<s>', 'mask_token': AddedToken(\"<mask>\", rstrip=False, lstrip=True, single_word=False, normalized=False)}, clean_up_tokenization_spaces=True)"
+ "data": {
+ "text/plain": [
+ "RobertaTokenizerFast(name_or_path='roberta-large', vocab_size=50265, model_max_length=512, is_fast=True, padding_side='right', truncation_side='right', special_tokens={'bos_token': '<s>', 'eos_token': '</s>', 'unk_token': '<unk>', 'sep_token': '</s>', 'pad_token': '<pad>', 'cls_token': '<s>', 'mask_token': AddedToken(\"<mask>\", rstrip=False, lstrip=True, single_word=False, normalized=False)}, clean_up_tokenization_spaces=True)"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"NJFxvxn5BnPxJcgxtURDRo",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"KFRHM0usfnGQnFdbZihU7B"
+ "metadata": {
+ "datalore": {
+ "node_id": "NJFxvxn5BnPxJcgxtURDRo",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "KFRHM0usfnGQnFdbZihU7B"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"We need to map the space-tokenized wikitext to the roberta tokenization, together with the token tags. -100 is ignored by PyTorch during gradient computation, and is commonly used for special tokens (<CLS> and such) and additional tokens that appear in the middle of words due to wordpiece tokenization."
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"I0EKhbKB1hQPTOpfNyatvD",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "I0EKhbKB1hQPTOpfNyatvD",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"def tokenize_and_align_labels(examples):\n",
" tokenized_inputs = tokenizer(examples[\"tokens\"], truncation=True, is_split_into_words=True)\n",
"\n",
@@ -1093,125 +1057,121 @@
" tokenized_inputs[\"labels\"] = labels\n",
" return tokenized_inputs"
],
- "execution_count":14,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"39laMNR7YdJWePIs3R1jgF",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"Uegyfkvr1Grti6ZGTnIIEw"
+ "execution_count": 14,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "39laMNR7YdJWePIs3R1jgF",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "Uegyfkvr1Grti6ZGTnIIEw"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"tokenized_wikitext = wikitext_mapped.map(tokenize_and_align_labels, batched=True)"
],
- "execution_count":15,
- "outputs":[
+ "execution_count": 15,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"d1c9b314cd8f4bddbc673a01c7f8d371"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "d1c9b314cd8f4bddbc673a01c7f8d371"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"40xVPDkPm35WbYnvA1y8Ts"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "40xVPDkPm35WbYnvA1y8Ts"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"ec21ec40a59449edb8f7d9b8c36c9263"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "ec21ec40a59449edb8f7d9b8c36c9263"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"bTYqFsVN6Du01ntyrDTYIO"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "bTYqFsVN6Du01ntyrDTYIO"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"40fde6fe7da148ecaed3eb5df360c348"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "40fde6fe7da148ecaed3eb5df360c348"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"JZhIN2xMwaecKDza6S8uZV"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "JZhIN2xMwaecKDza6S8uZV"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"Cxvaj6ae2iDlWrNtdzFvtR",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"trpuWhYCfTALVnH0ffydT9"
+ "metadata": {
+ "datalore": {
+ "node_id": "Cxvaj6ae2iDlWrNtdzFvtR",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "trpuWhYCfTALVnH0ffydT9"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"tokenized_wikitext = tokenized_wikitext.remove_columns('text')"
],
- "execution_count":16,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"ZRFAWku3LxAczcB8WGMM8A",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"7NEFb43JKeUw4DZjeR1Qe8"
+ "execution_count": 16,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "ZRFAWku3LxAczcB8WGMM8A",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "7NEFb43JKeUw4DZjeR1Qe8"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"for input_id, label in zip(tokenized_wikitext[\"train\"][1]['input_ids'], tokenized_wikitext[\"train\"][1]['labels']):\n",
" print(tokenizer.convert_ids_to_tokens(input_id), id2label[label])"
],
- "execution_count":17,
- "outputs":[
+ "execution_count": 17,
+ "outputs": [
{
- "name":"stdout",
- "text":[
+ "name": "stdout",
+ "text": [
"<s> -100\n",
"ĠSen 0\n",
"j -100\n",
@@ -1367,202 +1327,192 @@
"ĠRaven 0\n",
"Ġ\" 0\n",
"Ġ. 0\n",
- "<\/s> -100\n"
+ "</s> -100\n"
],
- "output_type":"stream"
+ "output_type": "stream"
}
],
- "metadata":{
- "datalore":{
- "node_id":"yFJf4KbWqy5NZBDOa5CUJ7",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"PeaXXWTbo8nx301q3J7LYT"
+ "metadata": {
+ "datalore": {
+ "node_id": "yFJf4KbWqy5NZBDOa5CUJ7",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "PeaXXWTbo8nx301q3J7LYT"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"The collator automatically handles padding the tokens and labels inside batches"
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"VWf2JoJ24cwXU3AclqyUcM",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "VWf2JoJ24cwXU3AclqyUcM",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"data_collator = DataCollatorForTokenClassification(tokenizer=tokenizer)"
],
- "execution_count":18,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"zswKKFPLgf53urFtHqKcTk",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"Tx4nI6q73aLba0qtxPM3HO"
+ "execution_count": 18,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "zswKKFPLgf53urFtHqKcTk",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "Tx4nI6q73aLba0qtxPM3HO"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"### Training"
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"JOUeiDhDqOWHLSWnNxMUb8",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "JOUeiDhDqOWHLSWnNxMUb8",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"\n",
"model = AutoModelForTokenClassification.from_pretrained(\n",
" model_checkpoint, num_labels=len(label_list), id2label=id2label, label2id=label2id\n",
")"
],
- "execution_count":19,
- "outputs":[
+ "execution_count": 19,
+ "outputs": [
{
- "name":"stderr",
- "text":[
+ "name": "stderr",
+ "text": [
"Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at roberta-large and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
],
- "output_type":"stream"
+ "output_type": "stream"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"02c337abd8a14ec1a9b812b83c5996f7"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "02c337abd8a14ec1a9b812b83c5996f7"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"BKS3VlmQIh5accoRARgGYI"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "BKS3VlmQIh5accoRARgGYI"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"rbqrUuMV3GkVdI2xPui57k",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"ej3yZyRCtCDWey9uBUDZ8i"
+ "metadata": {
+ "datalore": {
+ "node_id": "rbqrUuMV3GkVdI2xPui57k",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "ej3yZyRCtCDWey9uBUDZ8i"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"peft_config = LoraConfig(\n",
" task_type=TaskType.TOKEN_CLS, inference_mode=False, r=16, lora_alpha=16, lora_dropout=0.1, bias=\"all\"\n",
")"
],
- "execution_count":20,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"2OJ85GJzkPEfzNF1FZOsWr",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"rPZGw8diH0GN6aP7FKP8ca"
+ "execution_count": 20,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "2OJ85GJzkPEfzNF1FZOsWr",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "rPZGw8diH0GN6aP7FKP8ca"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"model = get_peft_model(model, peft_config)\n",
"model.print_trainable_parameters()"
],
- "execution_count":21,
- "outputs":[
+ "execution_count": 21,
+ "outputs": [
{
- "name":"stdout",
- "text":[
+ "name": "stdout",
+ "text": [
"trainable params: 1,848,324 || all params: 355,887,108 || trainable%: 0.519356829301049\n"
],
- "output_type":"stream"
+ "output_type": "stream"
}
],
- "metadata":{
- "datalore":{
- "node_id":"unCtyhS3AGHsrOijLzaXZI",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"9b8k4ntwhjIkmCPW6b5sUf"
+ "metadata": {
+ "datalore": {
+ "node_id": "unCtyhS3AGHsrOijLzaXZI",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "9b8k4ntwhjIkmCPW6b5sUf"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"lr = 1e-3\n",
"batch_size = 8"
],
- "execution_count":22,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"xY131yxZKOOEzt1z0XWzQS",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"Q4UIhvaDzVEpSjVk1zzHDy"
+ "execution_count": 22,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "xY131yxZKOOEzt1z0XWzQS",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "Q4UIhvaDzVEpSjVk1zzHDy"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"training_args = TrainingArguments(\n",
" output_dir=\"roberta-large-lora-token-classification\",\n",
" learning_rate=lr,\n",
@@ -1581,25 +1531,23 @@
" load_best_model_at_end=True,\n",
")"
],
- "execution_count":23,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"ZPXLuGOcwlGRrrSv3yuRcc",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"sgKkzWyaxUFUAVeYMkmETq"
+ "execution_count": 23,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "ZPXLuGOcwlGRrrSv3yuRcc",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "sgKkzWyaxUFUAVeYMkmETq"
}
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"trainer = Trainer(\n",
" model=model,\n",
" args=training_args,\n",
@@ -1612,22 +1560,22 @@
"\n",
"trainer.train()"
],
- "execution_count":24,
- "outputs":[
+ "execution_count": 24,
+ "outputs": [
{
- "name":"stderr",
- "text":[
- "\/opt\/python\/envs\/default\/lib\/python3.8\/site-packages\/transformers\/optimization.py:411: 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",
+ "name": "stderr",
+ "text": [
+ "/opt/python/envs/default/lib/python3.8/site-packages/transformers/optimization.py:411: 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",
"You're using a RobertaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
],
- "output_type":"stream"
+ "output_type": "stream"
},
{
- "ename":"KeyboardInterrupt",
- "evalue":"KeyboardInterrupt: ",
- "traceback":[
- "\u001b[0;31m---------------------------------------------------------------------------",
+ "ename": "KeyboardInterrupt",
+ "evalue": "KeyboardInterrupt: ",
+ "traceback": [
+ "\u001B[0;31m---------------------------------------------------------------------------",
"Traceback (most recent call last)",
" at line 11 in <module>",
" at line 1539 in train(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)",
@@ -1638,511 +1586,507 @@
" at line 200 in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)",
"KeyboardInterrupt: "
],
- "output_type":"error"
+ "output_type": "error"
},
{
- "data":{
- "text\/html":[
+ "data": {
+ "text/html": [
"\n",
" <div>\n",
" \n",
- " <progress value='4605' max='20000' style='width:300px; height:20px; vertical-align: middle;'><\/progress>\n",
- " [ 4605\/20000 5:12:54 < 17:26:33, 0.25 it\/s, Epoch 0.13\/1]\n",
- " <\/div>\n",
+ " <progress value='4605' max='20000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [ 4605/20000 5:12:54 < 17:26:33, 0.25 it/s, Epoch 0.13/1]\n",
+ " </div>\n",
" <table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: left;\">\n",
- " <th>Step<\/th>\n",
- " <th>Training Loss<\/th>\n",
- " <th>Validation Loss<\/th>\n",
- " <th>Precision<\/th>\n",
- " <th>Recall<\/th>\n",
- " <th>F1<\/th>\n",
- " <th>Accuracy<\/th>\n",
- " <\/tr>\n",
- " <\/thead>\n",
+ " <th>Step</th>\n",
+ " <th>Training Loss</th>\n",
+ " <th>Validation Loss</th>\n",
+ " <th>Precision</th>\n",
+ " <th>Recall</th>\n",
+ " <th>F1</th>\n",
+ " <th>Accuracy</th>\n",
+ " </tr>\n",
+ " </thead>\n",
" <tbody>\n",
" <tr>\n",
- " <td>100<\/td>\n",
- " <td>0.082400<\/td>\n",
- " <td>0.071184<\/td>\n",
- " <td>0.738182<\/td>\n",
- " <td>0.753200<\/td>\n",
- " <td>0.745615<\/td>\n",
- " <td>0.973547<\/td>\n",
- " <\/tr>\n",
+ " <td>100</td>\n",
+ " <td>0.082400</td>\n",
+ " <td>0.071184</td>\n",
+ " <td>0.738182</td>\n",
+ " <td>0.753200</td>\n",
+ " <td>0.745615</td>\n",
+ " <td>0.973547</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>200<\/td>\n",
- " <td>0.062200<\/td>\n",
- " <td>0.051519<\/td>\n",
- " <td>0.803700<\/td>\n",
- " <td>0.850525<\/td>\n",
- " <td>0.826450<\/td>\n",
- " <td>0.981614<\/td>\n",
- " <\/tr>\n",
+ " <td>200</td>\n",
+ " <td>0.062200</td>\n",
+ " <td>0.051519</td>\n",
+ " <td>0.803700</td>\n",
+ " <td>0.850525</td>\n",
+ " <td>0.826450</td>\n",
+ " <td>0.981614</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>300<\/td>\n",
- " <td>0.049100<\/td>\n",
- " <td>0.044637<\/td>\n",
- " <td>0.821739<\/td>\n",
- " <td>0.858548<\/td>\n",
- " <td>0.839740<\/td>\n",
- " <td>0.983133<\/td>\n",
- " <\/tr>\n",
+ " <td>300</td>\n",
+ " <td>0.049100</td>\n",
+ " <td>0.044637</td>\n",
+ " <td>0.821739</td>\n",
+ " <td>0.858548</td>\n",
+ " <td>0.839740</td>\n",
+ " <td>0.983133</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>400<\/td>\n",
- " <td>0.046000<\/td>\n",
- " <td>0.043286<\/td>\n",
- " <td>0.827163<\/td>\n",
- " <td>0.855683<\/td>\n",
- " <td>0.841181<\/td>\n",
- " <td>0.983369<\/td>\n",
- " <\/tr>\n",
+ " <td>400</td>\n",
+ " <td>0.046000</td>\n",
+ " <td>0.043286</td>\n",
+ " <td>0.827163</td>\n",
+ " <td>0.855683</td>\n",
+ " <td>0.841181</td>\n",
+ " <td>0.983369</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>500<\/td>\n",
- " <td>0.049700<\/td>\n",
- " <td>0.043400<\/td>\n",
- " <td>0.815975<\/td>\n",
- " <td>0.873257<\/td>\n",
- " <td>0.843645<\/td>\n",
- " <td>0.983340<\/td>\n",
- " <\/tr>\n",
+ " <td>500</td>\n",
+ " <td>0.049700</td>\n",
+ " <td>0.043400</td>\n",
+ " <td>0.815975</td>\n",
+ " <td>0.873257</td>\n",
+ " <td>0.843645</td>\n",
+ " <td>0.983340</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>600<\/td>\n",
- " <td>0.047900<\/td>\n",
- " <td>0.043947<\/td>\n",
- " <td>0.790265<\/td>\n",
- " <td>0.908691<\/td>\n",
- " <td>0.845351<\/td>\n",
- " <td>0.982887<\/td>\n",
- " <\/tr>\n",
+ " <td>600</td>\n",
+ " <td>0.047900</td>\n",
+ " <td>0.043947</td>\n",
+ " <td>0.790265</td>\n",
+ " <td>0.908691</td>\n",
+ " <td>0.845351</td>\n",
+ " <td>0.982887</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>700<\/td>\n",
- " <td>0.042500<\/td>\n",
- " <td>0.040706<\/td>\n",
- " <td>0.846508<\/td>\n",
- " <td>0.843840<\/td>\n",
- " <td>0.845171<\/td>\n",
- " <td>0.984087<\/td>\n",
- " <\/tr>\n",
+ " <td>700</td>\n",
+ " <td>0.042500</td>\n",
+ " <td>0.040706</td>\n",
+ " <td>0.846508</td>\n",
+ " <td>0.843840</td>\n",
+ " <td>0.845171</td>\n",
+ " <td>0.984087</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>800<\/td>\n",
- " <td>0.045500<\/td>\n",
- " <td>0.040963<\/td>\n",
- " <td>0.845999<\/td>\n",
- " <td>0.845272<\/td>\n",
- " <td>0.845636<\/td>\n",
- " <td>0.984116<\/td>\n",
- " <\/tr>\n",
+ " <td>800</td>\n",
+ " <td>0.045500</td>\n",
+ " <td>0.040963</td>\n",
+ " <td>0.845999</td>\n",
+ " <td>0.845272</td>\n",
+ " <td>0.845636</td>\n",
+ " <td>0.984116</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>900<\/td>\n",
- " <td>0.050000<\/td>\n",
- " <td>0.042453<\/td>\n",
- " <td>0.852265<\/td>\n",
- " <td>0.831996<\/td>\n",
- " <td>0.842009<\/td>\n",
- " <td>0.983929<\/td>\n",
- " <\/tr>\n",
+ " <td>900</td>\n",
+ " <td>0.050000</td>\n",
+ " <td>0.042453</td>\n",
+ " <td>0.852265</td>\n",
+ " <td>0.831996</td>\n",
+ " <td>0.842009</td>\n",
+ " <td>0.983929</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1000<\/td>\n",
- " <td>0.050800<\/td>\n",
- " <td>0.042836<\/td>\n",
- " <td>0.860358<\/td>\n",
- " <td>0.803247<\/td>\n",
- " <td>0.830822<\/td>\n",
- " <td>0.983163<\/td>\n",
- " <\/tr>\n",
+ " <td>1000</td>\n",
+ " <td>0.050800</td>\n",
+ " <td>0.042836</td>\n",
+ " <td>0.860358</td>\n",
+ " <td>0.803247</td>\n",
+ " <td>0.830822</td>\n",
+ " <td>0.983163</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1100<\/td>\n",
- " <td>0.049100<\/td>\n",
- " <td>0.043222<\/td>\n",
- " <td>0.805093<\/td>\n",
- " <td>0.896753<\/td>\n",
- " <td>0.848455<\/td>\n",
- " <td>0.983512<\/td>\n",
- " <\/tr>\n",
+ " <td>1100</td>\n",
+ " <td>0.049100</td>\n",
+ " <td>0.043222</td>\n",
+ " <td>0.805093</td>\n",
+ " <td>0.896753</td>\n",
+ " <td>0.848455</td>\n",
+ " <td>0.983512</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1200<\/td>\n",
- " <td>0.043400<\/td>\n",
- " <td>0.043033<\/td>\n",
- " <td>0.872473<\/td>\n",
- " <td>0.803725<\/td>\n",
- " <td>0.836689<\/td>\n",
- " <td>0.983851<\/td>\n",
- " <\/tr>\n",
+ " <td>1200</td>\n",
+ " <td>0.043400</td>\n",
+ " <td>0.043033</td>\n",
+ " <td>0.872473</td>\n",
+ " <td>0.803725</td>\n",
+ " <td>0.836689</td>\n",
+ " <td>0.983851</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1300<\/td>\n",
- " <td>0.043900<\/td>\n",
- " <td>0.039672<\/td>\n",
- " <td>0.849282<\/td>\n",
- " <td>0.847660<\/td>\n",
- " <td>0.848470<\/td>\n",
- " <td>0.984416<\/td>\n",
- " <\/tr>\n",
+ " <td>1300</td>\n",
+ " <td>0.043900</td>\n",
+ " <td>0.039672</td>\n",
+ " <td>0.849282</td>\n",
+ " <td>0.847660</td>\n",
+ " <td>0.848470</td>\n",
+ " <td>0.984416</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1400<\/td>\n",
- " <td>0.049900<\/td>\n",
- " <td>0.041815<\/td>\n",
- " <td>0.885053<\/td>\n",
- " <td>0.788348<\/td>\n",
- " <td>0.833906<\/td>\n",
- " <td>0.983836<\/td>\n",
- " <\/tr>\n",
+ " <td>1400</td>\n",
+ " <td>0.049900</td>\n",
+ " <td>0.041815</td>\n",
+ " <td>0.885053</td>\n",
+ " <td>0.788348</td>\n",
+ " <td>0.833906</td>\n",
+ " <td>0.983836</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1500<\/td>\n",
- " <td>0.044700<\/td>\n",
- " <td>0.041055<\/td>\n",
- " <td>0.849876<\/td>\n",
- " <td>0.850525<\/td>\n",
- " <td>0.850200<\/td>\n",
- " <td>0.984573<\/td>\n",
- " <\/tr>\n",
+ " <td>1500</td>\n",
+ " <td>0.044700</td>\n",
+ " <td>0.041055</td>\n",
+ " <td>0.849876</td>\n",
+ " <td>0.850525</td>\n",
+ " <td>0.850200</td>\n",
+ " <td>0.984573</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1600<\/td>\n",
- " <td>0.045100<\/td>\n",
- " <td>0.040592<\/td>\n",
- " <td>0.847970<\/td>\n",
- " <td>0.853964<\/td>\n",
- " <td>0.850957<\/td>\n",
- " <td>0.984603<\/td>\n",
- " <\/tr>\n",
+ " <td>1600</td>\n",
+ " <td>0.045100</td>\n",
+ " <td>0.040592</td>\n",
+ " <td>0.847970</td>\n",
+ " <td>0.853964</td>\n",
+ " <td>0.850957</td>\n",
+ " <td>0.984603</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1700<\/td>\n",
- " <td>0.042900<\/td>\n",
- " <td>0.040426<\/td>\n",
- " <td>0.837404<\/td>\n",
- " <td>0.871156<\/td>\n",
- " <td>0.853946<\/td>\n",
- " <td>0.984662<\/td>\n",
- " <\/tr>\n",
+ " <td>1700</td>\n",
+ " <td>0.042900</td>\n",
+ " <td>0.040426</td>\n",
+ " <td>0.837404</td>\n",
+ " <td>0.871156</td>\n",
+ " <td>0.853946</td>\n",
+ " <td>0.984662</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1800<\/td>\n",
- " <td>0.044800<\/td>\n",
- " <td>0.041155<\/td>\n",
- " <td>0.807739<\/td>\n",
- " <td>0.897230<\/td>\n",
- " <td>0.850136<\/td>\n",
- " <td>0.983718<\/td>\n",
- " <\/tr>\n",
+ " <td>1800</td>\n",
+ " <td>0.044800</td>\n",
+ " <td>0.041155</td>\n",
+ " <td>0.807739</td>\n",
+ " <td>0.897230</td>\n",
+ " <td>0.850136</td>\n",
+ " <td>0.983718</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>1900<\/td>\n",
- " <td>0.050600<\/td>\n",
- " <td>0.039829<\/td>\n",
- " <td>0.866008<\/td>\n",
- " <td>0.829035<\/td>\n",
- " <td>0.847119<\/td>\n",
- " <td>0.984598<\/td>\n",
- " <\/tr>\n",
+ " <td>1900</td>\n",
+ " <td>0.050600</td>\n",
+ " <td>0.039829</td>\n",
+ " <td>0.866008</td>\n",
+ " <td>0.829035</td>\n",
+ " <td>0.847119</td>\n",
+ " <td>0.984598</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2000<\/td>\n",
- " <td>0.046400<\/td>\n",
- " <td>0.039029<\/td>\n",
- " <td>0.847822<\/td>\n",
- " <td>0.855110<\/td>\n",
- " <td>0.851450<\/td>\n",
- " <td>0.984642<\/td>\n",
- " <\/tr>\n",
+ " <td>2000</td>\n",
+ " <td>0.046400</td>\n",
+ " <td>0.039029</td>\n",
+ " <td>0.847822</td>\n",
+ " <td>0.855110</td>\n",
+ " <td>0.851450</td>\n",
+ " <td>0.984642</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2100<\/td>\n",
- " <td>0.044200<\/td>\n",
- " <td>0.038947<\/td>\n",
- " <td>0.846089<\/td>\n",
- " <td>0.858453<\/td>\n",
- " <td>0.852226<\/td>\n",
- " <td>0.984677<\/td>\n",
- " <\/tr>\n",
+ " <td>2100</td>\n",
+ " <td>0.044200</td>\n",
+ " <td>0.038947</td>\n",
+ " <td>0.846089</td>\n",
+ " <td>0.858453</td>\n",
+ " <td>0.852226</td>\n",
+ " <td>0.984677</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2200<\/td>\n",
- " <td>0.039900<\/td>\n",
- " <td>0.039619<\/td>\n",
- " <td>0.824704<\/td>\n",
- " <td>0.879370<\/td>\n",
- " <td>0.851160<\/td>\n",
- " <td>0.984170<\/td>\n",
- " <\/tr>\n",
+ " <td>2200</td>\n",
+ " <td>0.039900</td>\n",
+ " <td>0.039619</td>\n",
+ " <td>0.824704</td>\n",
+ " <td>0.879370</td>\n",
+ " <td>0.851160</td>\n",
+ " <td>0.984170</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2300<\/td>\n",
- " <td>0.045400<\/td>\n",
- " <td>0.040354<\/td>\n",
- " <td>0.817536<\/td>\n",
- " <td>0.889685<\/td>\n",
- " <td>0.852086<\/td>\n",
- " <td>0.984102<\/td>\n",
- " <\/tr>\n",
+ " <td>2300</td>\n",
+ " <td>0.045400</td>\n",
+ " <td>0.040354</td>\n",
+ " <td>0.817536</td>\n",
+ " <td>0.889685</td>\n",
+ " <td>0.852086</td>\n",
+ " <td>0.984102</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2400<\/td>\n",
- " <td>0.045100<\/td>\n",
- " <td>0.040709<\/td>\n",
- " <td>0.810662<\/td>\n",
- " <td>0.884527<\/td>\n",
- " <td>0.845985<\/td>\n",
- " <td>0.983423<\/td>\n",
- " <\/tr>\n",
+ " <td>2400</td>\n",
+ " <td>0.045100</td>\n",
+ " <td>0.040709</td>\n",
+ " <td>0.810662</td>\n",
+ " <td>0.884527</td>\n",
+ " <td>0.845985</td>\n",
+ " <td>0.983423</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2500<\/td>\n",
- " <td>0.043700<\/td>\n",
- " <td>0.040959<\/td>\n",
- " <td>0.829169<\/td>\n",
- " <td>0.878032<\/td>\n",
- " <td>0.852902<\/td>\n",
- " <td>0.984411<\/td>\n",
- " <\/tr>\n",
+ " <td>2500</td>\n",
+ " <td>0.043700</td>\n",
+ " <td>0.040959</td>\n",
+ " <td>0.829169</td>\n",
+ " <td>0.878032</td>\n",
+ " <td>0.852902</td>\n",
+ " <td>0.984411</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2600<\/td>\n",
- " <td>0.041000<\/td>\n",
- " <td>0.039487<\/td>\n",
- " <td>0.823321<\/td>\n",
- " <td>0.887488<\/td>\n",
- " <td>0.854201<\/td>\n",
- " <td>0.984406<\/td>\n",
- " <\/tr>\n",
+ " <td>2600</td>\n",
+ " <td>0.041000</td>\n",
+ " <td>0.039487</td>\n",
+ " <td>0.823321</td>\n",
+ " <td>0.887488</td>\n",
+ " <td>0.854201</td>\n",
+ " <td>0.984406</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2700<\/td>\n",
- " <td>0.046600<\/td>\n",
- " <td>0.041066<\/td>\n",
- " <td>0.819955<\/td>\n",
- " <td>0.875167<\/td>\n",
- " <td>0.846662<\/td>\n",
- " <td>0.983684<\/td>\n",
- " <\/tr>\n",
+ " <td>2700</td>\n",
+ " <td>0.046600</td>\n",
+ " <td>0.041066</td>\n",
+ " <td>0.819955</td>\n",
+ " <td>0.875167</td>\n",
+ " <td>0.846662</td>\n",
+ " <td>0.983684</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2800<\/td>\n",
- " <td>0.047400<\/td>\n",
- " <td>0.039801<\/td>\n",
- " <td>0.836634<\/td>\n",
- " <td>0.871633<\/td>\n",
- " <td>0.853775<\/td>\n",
- " <td>0.984632<\/td>\n",
- " <\/tr>\n",
+ " <td>2800</td>\n",
+ " <td>0.047400</td>\n",
+ " <td>0.039801</td>\n",
+ " <td>0.836634</td>\n",
+ " <td>0.871633</td>\n",
+ " <td>0.853775</td>\n",
+ " <td>0.984632</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>2900<\/td>\n",
- " <td>0.045500<\/td>\n",
- " <td>0.038757<\/td>\n",
- " <td>0.845130<\/td>\n",
- " <td>0.855301<\/td>\n",
- " <td>0.850185<\/td>\n",
- " <td>0.984485<\/td>\n",
- " <\/tr>\n",
+ " <td>2900</td>\n",
+ " <td>0.045500</td>\n",
+ " <td>0.038757</td>\n",
+ " <td>0.845130</td>\n",
+ " <td>0.855301</td>\n",
+ " <td>0.850185</td>\n",
+ " <td>0.984485</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3000<\/td>\n",
- " <td>0.044300<\/td>\n",
- " <td>0.039374<\/td>\n",
- " <td>0.823618<\/td>\n",
- " <td>0.885291<\/td>\n",
- " <td>0.853342<\/td>\n",
- " <td>0.984338<\/td>\n",
- " <\/tr>\n",
+ " <td>3000</td>\n",
+ " <td>0.044300</td>\n",
+ " <td>0.039374</td>\n",
+ " <td>0.823618</td>\n",
+ " <td>0.885291</td>\n",
+ " <td>0.853342</td>\n",
+ " <td>0.984338</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3100<\/td>\n",
- " <td>0.042900<\/td>\n",
- " <td>0.041226<\/td>\n",
- " <td>0.812402<\/td>\n",
- " <td>0.890926<\/td>\n",
- " <td>0.849854<\/td>\n",
- " <td>0.983797<\/td>\n",
- " <\/tr>\n",
+ " <td>3100</td>\n",
+ " <td>0.042900</td>\n",
+ " <td>0.041226</td>\n",
+ " <td>0.812402</td>\n",
+ " <td>0.890926</td>\n",
+ " <td>0.849854</td>\n",
+ " <td>0.983797</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3200<\/td>\n",
- " <td>0.043900<\/td>\n",
- " <td>0.038550<\/td>\n",
- " <td>0.852317<\/td>\n",
- " <td>0.848329<\/td>\n",
- " <td>0.850318<\/td>\n",
- " <td>0.984628<\/td>\n",
- " <\/tr>\n",
+ " <td>3200</td>\n",
+ " <td>0.043900</td>\n",
+ " <td>0.038550</td>\n",
+ " <td>0.852317</td>\n",
+ " <td>0.848329</td>\n",
+ " <td>0.850318</td>\n",
+ " <td>0.984628</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3300<\/td>\n",
- " <td>0.042000<\/td>\n",
- " <td>0.040701<\/td>\n",
- " <td>0.822446<\/td>\n",
- " <td>0.882617<\/td>\n",
- " <td>0.851470<\/td>\n",
- " <td>0.984151<\/td>\n",
- " <\/tr>\n",
+ " <td>3300</td>\n",
+ " <td>0.042000</td>\n",
+ " <td>0.040701</td>\n",
+ " <td>0.822446</td>\n",
+ " <td>0.882617</td>\n",
+ " <td>0.851470</td>\n",
+ " <td>0.984151</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3400<\/td>\n",
- " <td>0.042000<\/td>\n",
- " <td>0.040563<\/td>\n",
- " <td>0.825961<\/td>\n",
- " <td>0.873926<\/td>\n",
- " <td>0.849267<\/td>\n",
- " <td>0.984033<\/td>\n",
- " <\/tr>\n",
+ " <td>3400</td>\n",
+ " <td>0.042000</td>\n",
+ " <td>0.040563</td>\n",
+ " <td>0.825961</td>\n",
+ " <td>0.873926</td>\n",
+ " <td>0.849267</td>\n",
+ " <td>0.984033</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3500<\/td>\n",
- " <td>0.048000<\/td>\n",
- " <td>0.039690<\/td>\n",
- " <td>0.857677<\/td>\n",
- " <td>0.832283<\/td>\n",
- " <td>0.844789<\/td>\n",
- " <td>0.984259<\/td>\n",
- " <\/tr>\n",
+ " <td>3500</td>\n",
+ " <td>0.048000</td>\n",
+ " <td>0.039690</td>\n",
+ " <td>0.857677</td>\n",
+ " <td>0.832283</td>\n",
+ " <td>0.844789</td>\n",
+ " <td>0.984259</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3600<\/td>\n",
- " <td>0.044000<\/td>\n",
- " <td>0.039875<\/td>\n",
- " <td>0.819356<\/td>\n",
- " <td>0.884623<\/td>\n",
- " <td>0.850739<\/td>\n",
- " <td>0.984023<\/td>\n",
- " <\/tr>\n",
+ " <td>3600</td>\n",
+ " <td>0.044000</td>\n",
+ " <td>0.039875</td>\n",
+ " <td>0.819356</td>\n",
+ " <td>0.884623</td>\n",
+ " <td>0.850739</td>\n",
+ " <td>0.984023</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3700<\/td>\n",
- " <td>0.043300<\/td>\n",
- " <td>0.039658<\/td>\n",
- " <td>0.872338<\/td>\n",
- " <td>0.817765<\/td>\n",
- " <td>0.844171<\/td>\n",
- " <td>0.984460<\/td>\n",
- " <\/tr>\n",
+ " <td>3700</td>\n",
+ " <td>0.043300</td>\n",
+ " <td>0.039658</td>\n",
+ " <td>0.872338</td>\n",
+ " <td>0.817765</td>\n",
+ " <td>0.844171</td>\n",
+ " <td>0.984460</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3800<\/td>\n",
- " <td>0.046400<\/td>\n",
- " <td>0.039144<\/td>\n",
- " <td>0.815661<\/td>\n",
- " <td>0.890449<\/td>\n",
- " <td>0.851416<\/td>\n",
- " <td>0.984003<\/td>\n",
- " <\/tr>\n",
+ " <td>3800</td>\n",
+ " <td>0.046400</td>\n",
+ " <td>0.039144</td>\n",
+ " <td>0.815661</td>\n",
+ " <td>0.890449</td>\n",
+ " <td>0.851416</td>\n",
+ " <td>0.984003</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>3900<\/td>\n",
- " <td>0.038300<\/td>\n",
- " <td>0.039964<\/td>\n",
- " <td>0.845676<\/td>\n",
- " <td>0.858357<\/td>\n",
- " <td>0.851969<\/td>\n",
- " <td>0.984647<\/td>\n",
- " <\/tr>\n",
+ " <td>3900</td>\n",
+ " <td>0.038300</td>\n",
+ " <td>0.039964</td>\n",
+ " <td>0.845676</td>\n",
+ " <td>0.858357</td>\n",
+ " <td>0.851969</td>\n",
+ " <td>0.984647</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4000<\/td>\n",
- " <td>0.050700<\/td>\n",
- " <td>0.038739<\/td>\n",
- " <td>0.836861<\/td>\n",
- " <td>0.864756<\/td>\n",
- " <td>0.850580<\/td>\n",
- " <td>0.984362<\/td>\n",
- " <\/tr>\n",
+ " <td>4000</td>\n",
+ " <td>0.050700</td>\n",
+ " <td>0.038739</td>\n",
+ " <td>0.836861</td>\n",
+ " <td>0.864756</td>\n",
+ " <td>0.850580</td>\n",
+ " <td>0.984362</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4100<\/td>\n",
- " <td>0.042500<\/td>\n",
- " <td>0.038863<\/td>\n",
- " <td>0.843916<\/td>\n",
- " <td>0.867049<\/td>\n",
- " <td>0.855326<\/td>\n",
- " <td>0.984903<\/td>\n",
- " <\/tr>\n",
+ " <td>4100</td>\n",
+ " <td>0.042500</td>\n",
+ " <td>0.038863</td>\n",
+ " <td>0.843916</td>\n",
+ " <td>0.867049</td>\n",
+ " <td>0.855326</td>\n",
+ " <td>0.984903</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4200<\/td>\n",
- " <td>0.040000<\/td>\n",
- " <td>0.039741<\/td>\n",
- " <td>0.810694<\/td>\n",
- " <td>0.897803<\/td>\n",
- " <td>0.852028<\/td>\n",
- " <td>0.983949<\/td>\n",
- " <\/tr>\n",
+ " <td>4200</td>\n",
+ " <td>0.040000</td>\n",
+ " <td>0.039741</td>\n",
+ " <td>0.810694</td>\n",
+ " <td>0.897803</td>\n",
+ " <td>0.852028</td>\n",
+ " <td>0.983949</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4300<\/td>\n",
- " <td>0.040800<\/td>\n",
- " <td>0.038387<\/td>\n",
- " <td>0.878170<\/td>\n",
- " <td>0.806877<\/td>\n",
- " <td>0.841015<\/td>\n",
- " <td>0.984298<\/td>\n",
- " <\/tr>\n",
+ " <td>4300</td>\n",
+ " <td>0.040800</td>\n",
+ " <td>0.038387</td>\n",
+ " <td>0.878170</td>\n",
+ " <td>0.806877</td>\n",
+ " <td>0.841015</td>\n",
+ " <td>0.984298</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4400<\/td>\n",
- " <td>0.044800<\/td>\n",
- " <td>0.038518<\/td>\n",
- " <td>0.862983<\/td>\n",
- " <td>0.836772<\/td>\n",
- " <td>0.849675<\/td>\n",
- " <td>0.984760<\/td>\n",
- " <\/tr>\n",
+ " <td>4400</td>\n",
+ " <td>0.044800</td>\n",
+ " <td>0.038518</td>\n",
+ " <td>0.862983</td>\n",
+ " <td>0.836772</td>\n",
+ " <td>0.849675</td>\n",
+ " <td>0.984760</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4500<\/td>\n",
- " <td>0.042700<\/td>\n",
- " <td>0.039114<\/td>\n",
- " <td>0.875372<\/td>\n",
- " <td>0.815759<\/td>\n",
- " <td>0.844515<\/td>\n",
- " <td>0.984539<\/td>\n",
- " <\/tr>\n",
+ " <td>4500</td>\n",
+ " <td>0.042700</td>\n",
+ " <td>0.039114</td>\n",
+ " <td>0.875372</td>\n",
+ " <td>0.815759</td>\n",
+ " <td>0.844515</td>\n",
+ " <td>0.984539</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4600<\/td>\n",
- " <td>0.040000<\/td>\n",
- " <td>0.039947<\/td>\n",
- " <td>0.857752<\/td>\n",
- " <td>0.845463<\/td>\n",
- " <td>0.851563<\/td>\n",
- " <td>0.984829<\/td>\n",
- " <\/tr>\n",
+ " <td>4600</td>\n",
+ " <td>0.040000</td>\n",
+ " <td>0.039947</td>\n",
+ " <td>0.857752</td>\n",
+ " <td>0.845463</td>\n",
+ " <td>0.851563</td>\n",
+ " <td>0.984829</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4604<\/td>\n",
- " <td>0.040000<\/td>\n",
- " <td>0.039423<\/td>\n",
- " <td>0.858057<\/td>\n",
- " <td>0.845272<\/td>\n",
- " <td>0.851617<\/td>\n",
- " <td>0.984839<\/td>\n",
- " <\/tr>\n",
+ " <td>4604</td>\n",
+ " <td>0.040000</td>\n",
+ " <td>0.039423</td>\n",
+ " <td>0.858057</td>\n",
+ " <td>0.845272</td>\n",
+ " <td>0.851617</td>\n",
+ " <td>0.984839</td>\n",
+ " </tr>\n",
" <tr>\n",
- " <td>4604<\/td>\n",
- " <td>0.040000<\/td>\n",
- " <td>0.037630<\/td>\n",
- " <td>0.847159<\/td>\n",
- " <td>0.851430<\/td>\n",
- " <td>0.849289<\/td>\n",
- " <td>0.984868<\/td>\n",
- " <\/tr>\n",
- " <\/tbody>\n",
- "<\/table><p>"
+ " <td>4604</td>\n",
+ " <td>0.040000</td>\n",
+ " <td>0.037630</td>\n",
+ " <td>0.847159</td>\n",
+ " <td>0.851430</td>\n",
+ " <td>0.849289</td>\n",
+ " <td>0.984868</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table><p>"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"ONnqviSgLxFGZ6VsodfzN7",
- "type":"CODE",
- "hide_input_from_viewers":false,
- "hide_output_from_viewers":false,
- "report_properties":{
- "rowId":"pMxR5mn4hMefEjvfv5e39e"
+ "metadata": {
+ "datalore": {
+ "node_id": "ONnqviSgLxFGZ6VsodfzN7",
+ "type": "CODE",
+ "hide_input_from_viewers": false,
+ "hide_output_from_viewers": false,
+ "report_properties": {
+ "rowId": "pMxR5mn4hMefEjvfv5e39e"
}
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"### Saving and evaluating the model"
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"H8JNhgIpWGBMp6DTrCC4WC",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "H8JNhgIpWGBMp6DTrCC4WC",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"trainer.evaluate(tokenized_wikitext[\"test\"])"
],
- "execution_count":26,
- "outputs":[
+ "execution_count": 26,
+ "outputs": [
{
- "data":{
- "text\/plain":[
+ "data": {
+ "text/plain": [
"{'eval_loss': 0.037630438804626465,\n",
" 'eval_precision': 0.8471585502984171,\n",
" 'eval_recall': 0.8514300617230288,\n",
@@ -2150,140 +2094,132 @@
" 'eval_accuracy': 0.9848677451373048}"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"EdtPuNsMTuWUVQ3AqwHeDh",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "metadata": {
+ "datalore": {
+ "node_id": "EdtPuNsMTuWUVQ3AqwHeDh",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"from huggingface_hub import notebook_login\n",
"\n",
"notebook_login()"
],
- "execution_count":27,
- "outputs":[
+ "execution_count": 27,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"aee257c0976d425da20f443a3973cf36"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "aee257c0976d425da20f443a3973cf36"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"WzG1d54t7f6rHW8IyvyquW"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "WzG1d54t7f6rHW8IyvyquW"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"B6WEXUADh8XfyBBfHBk309",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "metadata": {
+ "datalore": {
+ "node_id": "B6WEXUADh8XfyBBfHBk309",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
- "hub_name = \"klasocki\/roberta-large-lora-ner-comma-fixer\""
- ],
- "execution_count":28,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"Dyz7jkJX7CngtBG5SfJB47",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "cell_type": "code",
+ "source": [
+ "hub_name = \"klasocki/roberta-large-lora-ner-comma-fixer\""
+ ],
+ "execution_count": 28,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "Dyz7jkJX7CngtBG5SfJB47",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"model.push_to_hub(hub_name)"
],
- "execution_count":29,
- "outputs":[
+ "execution_count": 29,
+ "outputs": [
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"2609923ebe3d473eaebc5126eb653fd6"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "2609923ebe3d473eaebc5126eb653fd6"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"c03DMHM7RodIRbeCxJUgzo"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "c03DMHM7RodIRbeCxJUgzo"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "text\/plain":[
- "CommitInfo(commit_url='https:\/\/huggingface.co\/klasocki\/roberta-large-lora-ner-comma-fixer\/commit\/b6e99b176b6814a75e841edcfaa8fef649feaf31', commit_message='Upload model', commit_description='', oid='b6e99b176b6814a75e841edcfaa8fef649feaf31', pr_url=None, pr_revision=None, pr_num=None)"
+ "data": {
+ "text/plain": [
+ "CommitInfo(commit_url='https://huggingface.co/klasocki/roberta-large-lora-ner-comma-fixer/commit/b6e99b176b6814a75e841edcfaa8fef649feaf31', commit_message='Upload model', commit_description='', oid='b6e99b176b6814a75e841edcfaa8fef649feaf31', pr_url=None, pr_revision=None, pr_num=None)"
]
},
- "metadata":{
-
- },
- "output_type":"display_data"
+ "metadata": {},
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"bvJvzxpWWmNcRzwP5CJpkc",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "metadata": {
+ "datalore": {
+ "node_id": "bvJvzxpWWmNcRzwP5CJpkc",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"markdown",
- "source":[
+ "cell_type": "markdown",
+ "source": [
"### Inference"
],
- "attachments":{
-
- },
- "metadata":{
- "datalore":{
- "node_id":"XTrG9hb1fhJ5oV8J3Nm26w",
- "type":"MD",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "attachments": {},
+ "metadata": {
+ "datalore": {
+ "node_id": "XTrG9hb1fhJ5oV8J3Nm26w",
+ "type": "MD",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"peft_model_id = hub_name\n",
"config = PeftConfig.from_pretrained(peft_model_id)\n",
"inference_model = AutoModelForTokenClassification.from_pretrained(\n",
@@ -2292,82 +2228,80 @@
"tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)\n",
"model = PeftModel.from_pretrained(inference_model, peft_model_id)"
],
- "execution_count":30,
- "outputs":[
+ "execution_count": 30,
+ "outputs": [
{
- "name":"stderr",
- "text":[
+ "name": "stderr",
+ "text": [
"Some weights of RobertaForTokenClassification were not initialized from the model checkpoint at roberta-large and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
],
- "output_type":"stream"
+ "output_type": "stream"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"ea85d240073e4115b74c2c2f76a976de"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "ea85d240073e4115b74c2c2f76a976de"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"oRXbz3MAjR4qE4rpRi3lNV"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "oRXbz3MAjR4qE4rpRi3lNV"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
},
{
- "data":{
- "application\/vnd.jupyter.widget-view+json":{
- "version_major":2,
- "version_minor":0,
- "model_id":"6bba9f6fa84a49c5b402fcc40b9c3a20"
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "model_id": "6bba9f6fa84a49c5b402fcc40b9c3a20"
}
},
- "metadata":{
- "application\/vnd.jupyter.widget-view+json":{
- "datalore":{
- "widget_id":"oOD8zOJnD3w3IRrLQzSxrm"
+ "metadata": {
+ "application/vnd.jupyter.widget-view+json": {
+ "datalore": {
+ "widget_id": "oOD8zOJnD3w3IRrLQzSxrm"
}
}
},
- "output_type":"display_data"
+ "output_type": "display_data"
}
],
- "metadata":{
- "datalore":{
- "node_id":"4Vxwl8BqSlNJ4tt4aQKyu7",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "metadata": {
+ "datalore": {
+ "node_id": "4Vxwl8BqSlNJ4tt4aQKyu7",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"text = \"This text should have commas here here and there however it does not.\"\n",
"inputs = tokenizer(text, return_tensors=\"pt\")"
],
- "execution_count":34,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"vBfrIMnQntSHs406eTmIvN",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "execution_count": 34,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "vBfrIMnQntSHs406eTmIvN",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
+ "cell_type": "code",
+ "source": [
"with torch.no_grad():\n",
" logits = model(**inputs).logits\n",
"\n",
@@ -2377,11 +2311,11 @@
"for token, prediction in zip(tokens, predictions[0].numpy()):\n",
" print((token, model.config.id2label[prediction]))"
],
- "execution_count":35,
- "outputs":[
+ "execution_count": 35,
+ "outputs": [
{
- "name":"stdout",
- "text":[
+ "name": "stdout",
+ "text": [
"('<s>', 'O')\n",
"('This', 'O')\n",
"('Ġtext', 'O')\n",
@@ -2398,296 +2332,274 @@
"('Ġdoes', 'O')\n",
"('Ġnot', 'O')\n",
"('.', 'O')\n",
- "('<\/s>', 'O')\n"
+ "('</s>', 'O')\n"
],
- "output_type":"stream"
+ "output_type": "stream"
}
],
- "metadata":{
- "datalore":{
- "node_id":"jlEMGCI1ZpLhX3dBpF7DrB",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "metadata": {
+ "datalore": {
+ "node_id": "jlEMGCI1ZpLhX3dBpF7DrB",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
},
{
- "cell_type":"code",
- "source":[
-
- ],
- "execution_count":null,
- "outputs":[
-
- ],
- "metadata":{
- "datalore":{
- "node_id":"pWxG1H7AcqZqzJ543WdvMH",
- "type":"CODE",
- "hide_input_from_viewers":true,
- "hide_output_from_viewers":true
+ "cell_type": "code",
+ "source": [],
+ "execution_count": null,
+ "outputs": [],
+ "metadata": {
+ "datalore": {
+ "node_id": "pWxG1H7AcqZqzJ543WdvMH",
+ "type": "CODE",
+ "hide_input_from_viewers": true,
+ "hide_output_from_viewers": true
}
}
}
],
- "metadata":{
- "widgets":{
- "application\/vnd.jupyter.widget-state+json":{
- "version_major":2,
- "version_minor":0,
- "state":{
- "1dfa3596c41a47239cd42acaffa03ddc":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "c6b4f1a655334da1976a7bb87d9739a2":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "cd790e68b269453e9ab5b9a961a64279":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_1dfa3596c41a47239cd42acaffa03ddc",
- "style":"IPY_MODEL_c6b4f1a655334da1976a7bb87d9739a2",
- "value":"Token is valid (permission: write)."
- }
- },
- "b6f37cc798714f57b51bcd8284fe5cf3":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "5fab119f434047038d02b468858f9565":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "81734d38280d4abdb9acc5295c143cc9":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_b6f37cc798714f57b51bcd8284fe5cf3",
- "style":"IPY_MODEL_5fab119f434047038d02b468858f9565",
- "value":"\u001b[1m\u001b[31mCannot authenticate through git-credential as no helper is defined on your machine."
- }
- },
- "22220074fffd4176b02ec067dd3b5ae8":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "c4ab8887bd204069bb783ff6e8ae7723":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "43ba6d98d5a849188b48919aa6494396":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_22220074fffd4176b02ec067dd3b5ae8",
- "style":"IPY_MODEL_c4ab8887bd204069bb783ff6e8ae7723",
- "value":"You might have to re-authenticate when pushing to the Hugging Face Hub."
- }
- },
- "e0a3c0f366ba468e9cb4aded19c802b4":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "2bbcd517c13a47fb88dd1ec65120abd1":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "ce593c77612d4e7395f6a9b880f84460":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_e0a3c0f366ba468e9cb4aded19c802b4",
- "style":"IPY_MODEL_2bbcd517c13a47fb88dd1ec65120abd1",
- "value":"Run the following command in your terminal in case you want to set the 'store' credential helper as default."
- }
- },
- "53609e0450164573a5604a184e504349":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "96288508db244ae390d26c1cf739ff73":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "242cefc7ee344b64ae38e8d17d756437":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_53609e0450164573a5604a184e504349",
- "style":"IPY_MODEL_96288508db244ae390d26c1cf739ff73",
- "value":"git config --global credential.helper store"
- }
- },
- "10df0fb54e6c40e7bfd704e051792c5c":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "1b4886b66e8a4041b3782bc1387e8ec8":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "c27034c532f9404fb5319286abdeb0a8":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_10df0fb54e6c40e7bfd704e051792c5c",
- "style":"IPY_MODEL_1b4886b66e8a4041b3782bc1387e8ec8",
- "value":"Read https:\/\/git-scm.com\/book\/en\/v2\/Git-Tools-Credential-Storage for more details.\u001b[0m"
- }
- },
- "7c0fd075376144b790c33685d4c71e31":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "4ed78afe8cfe41d4be4204980b287005":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "32b669c3e94547d984bd0cddfef27b47":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_7c0fd075376144b790c33685d4c71e31",
- "style":"IPY_MODEL_4ed78afe8cfe41d4be4204980b287005",
- "value":"Token has not been saved to git credential helper."
- }
- },
- "9386980fa9684653a205701b24f4c3d7":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "44aadab07124477781bcb65fe9e681ba":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "15ddc7ac585c49ae8aae232b176ddc7d":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_9386980fa9684653a205701b24f4c3d7",
- "style":"IPY_MODEL_44aadab07124477781bcb65fe9e681ba",
- "value":"Your token has been saved to \/home\/datalore\/.cache\/huggingface\/token"
- }
- },
- "41e8c5786b2041b3b34410041bc9f88f":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "f949e7e6496747b396e00d0a23de8b64":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "74e374e308fe451ba997207ca19244f3":{
- "model_name":"LabelModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_41e8c5786b2041b3b34410041bc9f88f",
- "style":"IPY_MODEL_f949e7e6496747b396e00d0a23de8b64",
- "value":"Login successful"
- }
- },
- "20fc5c16124b4e6a805073c5de94b74a":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
- "align_items":"center",
- "display":"flex",
- "flex_flow":"column",
- "width":"50%"
- }
- },
- "aee257c0976d425da20f443a3973cf36":{
- "model_name":"VBoxModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "children":[
+ "metadata": {
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "version_major": 2,
+ "version_minor": 0,
+ "state": {
+ "1dfa3596c41a47239cd42acaffa03ddc": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "c6b4f1a655334da1976a7bb87d9739a2": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "cd790e68b269453e9ab5b9a961a64279": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_1dfa3596c41a47239cd42acaffa03ddc",
+ "style": "IPY_MODEL_c6b4f1a655334da1976a7bb87d9739a2",
+ "value": "Token is valid (permission: write)."
+ }
+ },
+ "b6f37cc798714f57b51bcd8284fe5cf3": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "5fab119f434047038d02b468858f9565": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "81734d38280d4abdb9acc5295c143cc9": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_b6f37cc798714f57b51bcd8284fe5cf3",
+ "style": "IPY_MODEL_5fab119f434047038d02b468858f9565",
+ "value": "\u001B[1m\u001B[31mCannot authenticate through git-credential as no helper is defined on your machine."
+ }
+ },
+ "22220074fffd4176b02ec067dd3b5ae8": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "c4ab8887bd204069bb783ff6e8ae7723": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "43ba6d98d5a849188b48919aa6494396": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_22220074fffd4176b02ec067dd3b5ae8",
+ "style": "IPY_MODEL_c4ab8887bd204069bb783ff6e8ae7723",
+ "value": "You might have to re-authenticate when pushing to the Hugging Face Hub."
+ }
+ },
+ "e0a3c0f366ba468e9cb4aded19c802b4": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "2bbcd517c13a47fb88dd1ec65120abd1": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "ce593c77612d4e7395f6a9b880f84460": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_e0a3c0f366ba468e9cb4aded19c802b4",
+ "style": "IPY_MODEL_2bbcd517c13a47fb88dd1ec65120abd1",
+ "value": "Run the following command in your terminal in case you want to set the 'store' credential helper as default."
+ }
+ },
+ "53609e0450164573a5604a184e504349": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "96288508db244ae390d26c1cf739ff73": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "242cefc7ee344b64ae38e8d17d756437": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_53609e0450164573a5604a184e504349",
+ "style": "IPY_MODEL_96288508db244ae390d26c1cf739ff73",
+ "value": "git config --global credential.helper store"
+ }
+ },
+ "10df0fb54e6c40e7bfd704e051792c5c": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "1b4886b66e8a4041b3782bc1387e8ec8": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "c27034c532f9404fb5319286abdeb0a8": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_10df0fb54e6c40e7bfd704e051792c5c",
+ "style": "IPY_MODEL_1b4886b66e8a4041b3782bc1387e8ec8",
+ "value": "Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.\u001B[0m"
+ }
+ },
+ "7c0fd075376144b790c33685d4c71e31": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "4ed78afe8cfe41d4be4204980b287005": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "32b669c3e94547d984bd0cddfef27b47": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_7c0fd075376144b790c33685d4c71e31",
+ "style": "IPY_MODEL_4ed78afe8cfe41d4be4204980b287005",
+ "value": "Token has not been saved to git credential helper."
+ }
+ },
+ "9386980fa9684653a205701b24f4c3d7": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "44aadab07124477781bcb65fe9e681ba": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "15ddc7ac585c49ae8aae232b176ddc7d": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_9386980fa9684653a205701b24f4c3d7",
+ "style": "IPY_MODEL_44aadab07124477781bcb65fe9e681ba",
+ "value": "Your token has been saved to /home/datalore/.cache/huggingface/token"
+ }
+ },
+ "41e8c5786b2041b3b34410041bc9f88f": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "f949e7e6496747b396e00d0a23de8b64": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "74e374e308fe451ba997207ca19244f3": {
+ "model_name": "LabelModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_41e8c5786b2041b3b34410041bc9f88f",
+ "style": "IPY_MODEL_f949e7e6496747b396e00d0a23de8b64",
+ "value": "Login successful"
+ }
+ },
+ "20fc5c16124b4e6a805073c5de94b74a": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {
+ "align_items": "center",
+ "display": "flex",
+ "flex_flow": "column",
+ "width": "50%"
+ }
+ },
+ "aee257c0976d425da20f443a3973cf36": {
+ "model_name": "VBoxModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "children": [
"IPY_MODEL_cd790e68b269453e9ab5b9a961a64279",
"IPY_MODEL_81734d38280d4abdb9acc5295c143cc9",
"IPY_MODEL_43ba6d98d5a849188b48919aa6494396",
@@ -2698,328 +2610,302 @@
"IPY_MODEL_15ddc7ac585c49ae8aae232b176ddc7d",
"IPY_MODEL_74e374e308fe451ba997207ca19244f3"
],
- "layout":"IPY_MODEL_20fc5c16124b4e6a805073c5de94b74a"
- }
- },
- "ba6b997bc4f749368bcf3c7d75e59dd1":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "b53ebb5e12084d9fa25195fc22715ac8":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "9a00dc77ccb844faa7a7f66a2f58b942":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_ba6b997bc4f749368bcf3c7d75e59dd1",
- "style":"IPY_MODEL_b53ebb5e12084d9fa25195fc22715ac8",
- "value":"adapter_model.bin: 100%"
- }
- },
- "eb326383bb0f4da9935c37eb85073a40":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "6c4558d629c34e689df32a021745ead8":{
- "model_name":"ProgressStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "791c2cbe9ba643139fbc4119efeed65a":{
- "model_name":"FloatProgressModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "bar_style":"success",
- "layout":"IPY_MODEL_eb326383bb0f4da9935c37eb85073a40",
- "max":7490973,
- "style":"IPY_MODEL_6c4558d629c34e689df32a021745ead8",
- "value":7490973
- }
- },
- "3b922c305a7d48bab391317cd657f8d5":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "1440148cee1e4c8486a2abebbc7faa23":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "e6529cb132894cfab125b482198822b8":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_3b922c305a7d48bab391317cd657f8d5",
- "style":"IPY_MODEL_1440148cee1e4c8486a2abebbc7faa23",
- "value":" 7.49M\/7.49M [00:04<00:00, 2.26MB\/s]"
- }
- },
- "872fe87fd82c40a89442998ff471b881":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "2609923ebe3d473eaebc5126eb653fd6":{
- "model_name":"HBoxModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "children":[
+ "layout": "IPY_MODEL_20fc5c16124b4e6a805073c5de94b74a"
+ }
+ },
+ "ba6b997bc4f749368bcf3c7d75e59dd1": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "b53ebb5e12084d9fa25195fc22715ac8": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "9a00dc77ccb844faa7a7f66a2f58b942": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_ba6b997bc4f749368bcf3c7d75e59dd1",
+ "style": "IPY_MODEL_b53ebb5e12084d9fa25195fc22715ac8",
+ "value": "adapter_model.bin: 100%"
+ }
+ },
+ "eb326383bb0f4da9935c37eb85073a40": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "6c4558d629c34e689df32a021745ead8": {
+ "model_name": "ProgressStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "791c2cbe9ba643139fbc4119efeed65a": {
+ "model_name": "FloatProgressModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "bar_style": "success",
+ "layout": "IPY_MODEL_eb326383bb0f4da9935c37eb85073a40",
+ "max": 7490973,
+ "style": "IPY_MODEL_6c4558d629c34e689df32a021745ead8",
+ "value": 7490973
+ }
+ },
+ "3b922c305a7d48bab391317cd657f8d5": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "1440148cee1e4c8486a2abebbc7faa23": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "e6529cb132894cfab125b482198822b8": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_3b922c305a7d48bab391317cd657f8d5",
+ "style": "IPY_MODEL_1440148cee1e4c8486a2abebbc7faa23",
+ "value": " 7.49M/7.49M [00:04<00:00, 2.26MB/s]"
+ }
+ },
+ "872fe87fd82c40a89442998ff471b881": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "2609923ebe3d473eaebc5126eb653fd6": {
+ "model_name": "HBoxModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "children": [
"IPY_MODEL_9a00dc77ccb844faa7a7f66a2f58b942",
"IPY_MODEL_791c2cbe9ba643139fbc4119efeed65a",
"IPY_MODEL_e6529cb132894cfab125b482198822b8"
],
- "layout":"IPY_MODEL_872fe87fd82c40a89442998ff471b881"
- }
- },
- "335387903ecb43a586d049bed0fbc012":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "1837a2056268420cb2d90e740c606892":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "e1ee514268c34c298c2641d22457816c":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_335387903ecb43a586d049bed0fbc012",
- "style":"IPY_MODEL_1837a2056268420cb2d90e740c606892",
- "value":"Downloading (…)\/adapter_config.json: 100%"
- }
- },
- "5c843a2afc054e7ab2531cc530da226a":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "f42fd48e69eb43188397bd5a2cda9a30":{
- "model_name":"ProgressStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "8cb66793a8d54b1ab3ecc65157bcd6a9":{
- "model_name":"FloatProgressModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "bar_style":"success",
- "layout":"IPY_MODEL_5c843a2afc054e7ab2531cc530da226a",
- "max":432,
- "style":"IPY_MODEL_f42fd48e69eb43188397bd5a2cda9a30",
- "value":432
- }
- },
- "75fdf0dad626469ab2d138711d72cf08":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "f21e9954b48c4ee288f3782755daaf1e":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "2580697cd74a4e5d8024a7a1e7ad114c":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_75fdf0dad626469ab2d138711d72cf08",
- "style":"IPY_MODEL_f21e9954b48c4ee288f3782755daaf1e",
- "value":" 432\/432 [00:00<00:00, 28.6kB\/s]"
- }
- },
- "d2f6e2c8392e4f18ac06dd3d0de6acf1":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "ea85d240073e4115b74c2c2f76a976de":{
- "model_name":"HBoxModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "children":[
+ "layout": "IPY_MODEL_872fe87fd82c40a89442998ff471b881"
+ }
+ },
+ "335387903ecb43a586d049bed0fbc012": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "1837a2056268420cb2d90e740c606892": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "e1ee514268c34c298c2641d22457816c": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_335387903ecb43a586d049bed0fbc012",
+ "style": "IPY_MODEL_1837a2056268420cb2d90e740c606892",
+ "value": "Downloading (…)/adapter_config.json: 100%"
+ }
+ },
+ "5c843a2afc054e7ab2531cc530da226a": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "f42fd48e69eb43188397bd5a2cda9a30": {
+ "model_name": "ProgressStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "8cb66793a8d54b1ab3ecc65157bcd6a9": {
+ "model_name": "FloatProgressModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "bar_style": "success",
+ "layout": "IPY_MODEL_5c843a2afc054e7ab2531cc530da226a",
+ "max": 432,
+ "style": "IPY_MODEL_f42fd48e69eb43188397bd5a2cda9a30",
+ "value": 432
+ }
+ },
+ "75fdf0dad626469ab2d138711d72cf08": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "f21e9954b48c4ee288f3782755daaf1e": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "2580697cd74a4e5d8024a7a1e7ad114c": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_75fdf0dad626469ab2d138711d72cf08",
+ "style": "IPY_MODEL_f21e9954b48c4ee288f3782755daaf1e",
+ "value": " 432/432 [00:00<00:00, 28.6kB/s]"
+ }
+ },
+ "d2f6e2c8392e4f18ac06dd3d0de6acf1": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "ea85d240073e4115b74c2c2f76a976de": {
+ "model_name": "HBoxModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "children": [
"IPY_MODEL_e1ee514268c34c298c2641d22457816c",
"IPY_MODEL_8cb66793a8d54b1ab3ecc65157bcd6a9",
"IPY_MODEL_2580697cd74a4e5d8024a7a1e7ad114c"
],
- "layout":"IPY_MODEL_d2f6e2c8392e4f18ac06dd3d0de6acf1"
- }
- },
- "026ed0e099e04df2864a36ca00c8a695":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "80cede5c3d1d44fc80b1e87d60c4d200":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "34ad5085cda04eff80e9b5314be98c41":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_026ed0e099e04df2864a36ca00c8a695",
- "style":"IPY_MODEL_80cede5c3d1d44fc80b1e87d60c4d200",
- "value":"Downloading adapter_model.bin: 100%"
- }
- },
- "1ec286d338ec4457980391951d3cc025":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "5d0e68b8382645bcb9da308ecf025089":{
- "model_name":"ProgressStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "b0f2185867c94543a4491b0ecb047bc4":{
- "model_name":"FloatProgressModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "bar_style":"success",
- "layout":"IPY_MODEL_1ec286d338ec4457980391951d3cc025",
- "max":7490973,
- "style":"IPY_MODEL_5d0e68b8382645bcb9da308ecf025089",
- "value":7490973
- }
- },
- "7d5e8608d98441328ec9187e23ea34a4":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "bb5b3e305f9d409cb0916be9ec52d921":{
- "model_name":"DescriptionStyleModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "description_width":""
- }
- },
- "e619f8cac6b04b1dbe7075c74f8e37fc":{
- "model_name":"HTMLModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "layout":"IPY_MODEL_7d5e8608d98441328ec9187e23ea34a4",
- "style":"IPY_MODEL_bb5b3e305f9d409cb0916be9ec52d921",
- "value":" 7.49M\/7.49M [00:00<00:00, 13.5MB\/s]"
- }
- },
- "c0bc4d0adacc4f75b1341c772811a50a":{
- "model_name":"LayoutModel",
- "model_module":"@jupyter-widgets\/base",
- "model_module_version":"1.2.0",
- "state":{
-
- }
- },
- "6bba9f6fa84a49c5b402fcc40b9c3a20":{
- "model_name":"HBoxModel",
- "model_module":"@jupyter-widgets\/controls",
- "model_module_version":"1.5.0",
- "state":{
- "children":[
+ "layout": "IPY_MODEL_d2f6e2c8392e4f18ac06dd3d0de6acf1"
+ }
+ },
+ "026ed0e099e04df2864a36ca00c8a695": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "80cede5c3d1d44fc80b1e87d60c4d200": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "34ad5085cda04eff80e9b5314be98c41": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_026ed0e099e04df2864a36ca00c8a695",
+ "style": "IPY_MODEL_80cede5c3d1d44fc80b1e87d60c4d200",
+ "value": "Downloading adapter_model.bin: 100%"
+ }
+ },
+ "1ec286d338ec4457980391951d3cc025": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "5d0e68b8382645bcb9da308ecf025089": {
+ "model_name": "ProgressStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "b0f2185867c94543a4491b0ecb047bc4": {
+ "model_name": "FloatProgressModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "bar_style": "success",
+ "layout": "IPY_MODEL_1ec286d338ec4457980391951d3cc025",
+ "max": 7490973,
+ "style": "IPY_MODEL_5d0e68b8382645bcb9da308ecf025089",
+ "value": 7490973
+ }
+ },
+ "7d5e8608d98441328ec9187e23ea34a4": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "bb5b3e305f9d409cb0916be9ec52d921": {
+ "model_name": "DescriptionStyleModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "description_width": ""
+ }
+ },
+ "e619f8cac6b04b1dbe7075c74f8e37fc": {
+ "model_name": "HTMLModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "layout": "IPY_MODEL_7d5e8608d98441328ec9187e23ea34a4",
+ "style": "IPY_MODEL_bb5b3e305f9d409cb0916be9ec52d921",
+ "value": " 7.49M/7.49M [00:00<00:00, 13.5MB/s]"
+ }
+ },
+ "c0bc4d0adacc4f75b1341c772811a50a": {
+ "model_name": "LayoutModel",
+ "model_module": "@jupyter-widgets/base",
+ "model_module_version": "1.2.0",
+ "state": {}
+ },
+ "6bba9f6fa84a49c5b402fcc40b9c3a20": {
+ "model_name": "HBoxModel",
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "state": {
+ "children": [
"IPY_MODEL_34ad5085cda04eff80e9b5314be98c41",
"IPY_MODEL_b0f2185867c94543a4491b0ecb047bc4",
"IPY_MODEL_e619f8cac6b04b1dbe7075c74f8e37fc"
],
- "layout":"IPY_MODEL_c0bc4d0adacc4f75b1341c772811a50a"
+ "layout": "IPY_MODEL_c0bc4d0adacc4f75b1341c772811a50a"
}
}
}
}
},
- "kernelspec":{
- "display_name":"Python",
- "language":"python",
- "name":"python"
+ "kernelspec": {
+ "display_name": "Python",
+ "language": "python",
+ "name": "python"
},
- "datalore":{
- "computation_mode":"JUPYTER",
- "package_manager":"pip",
- "base_environment":"default",
- "packages":[
-
- ],
- "report_row_ids":[
+ "datalore": {
+ "computation_mode": "JUPYTER",
+ "package_manager": "pip",
+ "base_environment": "default",
+ "packages": [],
+ "report_row_ids": [
"9tLzdz03okTFWD3Vy0h4vS",
"h8AdYv2Y3tw7Yb4W3IGoxc",
"sGTotT7rOtZWKTPgVm4gX6",
@@ -3045,9 +2931,9 @@
"sgKkzWyaxUFUAVeYMkmETq",
"pMxR5mn4hMefEjvfv5e39e"
],
- "version":3
+ "version": 3
}
},
- "nbformat":4,
- "nbformat_minor":4
-}
\ No newline at end of file
+ "nbformat": 4,
+ "nbformat_minor": 4
+}