kmchiti's picture
Training in progress, step 5000, checkpoint
d73e0f8 verified
raw
history blame
4.14 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\\\\\|\\/|:|~|@|\\?|>>?|\\*|\\$|\\%[0-9]{2}|[0-9])"
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<bos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<eos>",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {
"<bos>": {
"id": "<bos>",
"ids": [
2
],
"tokens": [
"<bos>"
]
},
"<eos>": {
"id": "<eos>",
"ids": [
3
],
"tokens": [
"<eos>"
]
}
}
},
"decoder": {
"type": "BPEDecoder",
"suffix": "</w>"
},
"model": {
"type": "WordLevel",
"vocab": {
"<unk>": 0,
"<pad>": 1,
"<bos>": 2,
"<eos>": 3,
"[C]": 4,
"[Ring1]": 5,
"[Branch1]": 6,
"[N]": 7,
"[=Branch1]": 8,
"[=C]": 9,
"[=O]": 10,
"[O]": 11,
"[Branch2]": 12,
"[Ring2]": 13,
"[C@H1]": 14,
"[C@@H1]": 15,
"[=N]": 16,
"[S]": 17,
"[F]": 18,
"[#Branch1]": 19,
"[=Branch2]": 20,
"[#C]": 21,
"[P]": 22,
"[#Branch2]": 23,
"[=Ring1]": 24,
"[Cl]": 25,
"[NH1]": 26,
"[C@]": 27,
"[C@@]": 28,
"[Br]": 29,
"[/C]": 30,
"[#N]": 31,
"[=Ring2]": 32,
"[O-1]": 33,
"[N+1]": 34,
"[=N+1]": 35,
"[I]": 36,
"[=N-1]": 37,
"[S@]": 38,
"[=S]": 39,
"[S@@]": 40,
"[N-1]": 41,
"[Si]": 42,
"[/C@H1]": 43,
"[/Cl]": 44,
"[/C@@H1]": 45,
"[S+1]": 46,
"[=S@]": 47,
"[=S@@]": 48,
"[B]": 49,
"[/Br]": 50,
"[/S]": 51,
"[P@]": 52,
"[/F]": 53,
"[P@@]": 54,
"[N@]": 55,
"[/N]": 56,
"[/O]": 57,
"[/N+1]": 58,
"[N@@]": 59,
"[=P]": 60,
"[/I]": 61,
"[B-1]": 62,
"[NH1+1]": 63,
"[N@@H1+1]": 64,
"[NH2+1]": 65,
"[N@H1+1]": 66,
"[OH0]": 67,
"[NH3+1]": 68,
"[PH1]": 69,
"[Si@]": 70,
"[Si@@]": 71,
"[/S@@]": 72,
"[=NH1+1]": 73,
"[N@+1]": 74,
"[/S@]": 75,
"[N@@+1]": 76,
"[/P]": 77,
"[Sn]": 78,
"[=Se]": 79,
".": 80,
"[Cl-1]": 81,
"[#N+1]": 82,
"[=NH2+1]": 83,
"[/C@]": 84,
"[C-1]": 85,
"[=S+1]": 86,
"[CH0]": 87,
"[NH0]": 88,
"[=P@@]": 89,
"[S@@+1]": 90,
"[=NH0]": 91,
"[=P@]": 92,
"[/C@@]": 93,
"[/O-1]": 94,
"[=O+1]": 95,
"[Si@H1]": 96,
"[/Si]": 97,
"[=SH1]": 98,
"[O+1]": 99,
"[P+1]": 100,
"[P@@H1]": 101,
"[SH1]": 102,
"[Si@@H1]": 103
},
"unk_token": "<unk>"
}
}