Training in progress, epoch 1
Browse files- config.json +130 -0
- model.safetensors +3 -0
- runs/Oct11_12-35-36_ip-172-16-44-211.eu-west-1.compute.internal/events.out.tfevents.1728650138.ip-172-16-44-211.eu-west-1.compute.internal.22361.0 +3 -0
- runs/Oct14_04-57-52_ip-172-16-40-248.eu-west-1.compute.internal/events.out.tfevents.1728881882.ip-172-16-40-248.eu-west-1.compute.internal.2492.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "O",
|
| 13 |
+
"1": "B-FIRSTNAME",
|
| 14 |
+
"2": "I-FIRSTNAME",
|
| 15 |
+
"3": "B-MIDDLENAME",
|
| 16 |
+
"4": "B-LASTNAME",
|
| 17 |
+
"5": "I-LASTNAME",
|
| 18 |
+
"6": "B-COMPANYNAME",
|
| 19 |
+
"7": "I-COMPANYNAME",
|
| 20 |
+
"8": "B-EMAIL",
|
| 21 |
+
"9": "I-EMAIL",
|
| 22 |
+
"10": "B-URL",
|
| 23 |
+
"11": "I-URL",
|
| 24 |
+
"12": "B-ACCOUNTNAME",
|
| 25 |
+
"13": "I-ACCOUNTNAME",
|
| 26 |
+
"14": "B-IBAN",
|
| 27 |
+
"15": "I-IBAN",
|
| 28 |
+
"16": "B-ACCOUNTNUMBER",
|
| 29 |
+
"17": "I-ACCOUNTNUMBER",
|
| 30 |
+
"18": "B-STREETADDRESS",
|
| 31 |
+
"19": "I-STREETADDRESS",
|
| 32 |
+
"20": "B-CITY",
|
| 33 |
+
"21": "I-CITY",
|
| 34 |
+
"22": "B-USERNAME",
|
| 35 |
+
"23": "I-USERNAME",
|
| 36 |
+
"24": "B-CREDITCARDNUMBER",
|
| 37 |
+
"25": "I-CREDITCARDNUMBER",
|
| 38 |
+
"26": "B-STATE",
|
| 39 |
+
"27": "B-BUILDINGNUMBER",
|
| 40 |
+
"28": "I-BUILDINGNUMBER",
|
| 41 |
+
"29": "I-STATE",
|
| 42 |
+
"30": "B-COUNTY",
|
| 43 |
+
"31": "B-PHONENUMBER",
|
| 44 |
+
"32": "I-PHONENUMBER",
|
| 45 |
+
"33": "B-SECONDARYADDRESS",
|
| 46 |
+
"34": "I-SECONDARYADDRESS",
|
| 47 |
+
"35": "B-CREDITCARDISSUER",
|
| 48 |
+
"36": "I-CREDITCARDISSUER",
|
| 49 |
+
"37": "B-CREDITCARDCVV",
|
| 50 |
+
"38": "I-CREDITCARDCVV",
|
| 51 |
+
"39": "B-STREET",
|
| 52 |
+
"40": "I-STREET",
|
| 53 |
+
"41": "B-PIN",
|
| 54 |
+
"42": "I-PIN",
|
| 55 |
+
"43": "I-MIDDLENAME",
|
| 56 |
+
"44": "B-FULLNAME",
|
| 57 |
+
"45": "I-FULLNAME",
|
| 58 |
+
"46": "B-NAME",
|
| 59 |
+
"47": "I-NAME",
|
| 60 |
+
"48": "B-NUMBER",
|
| 61 |
+
"49": "I-NUMBER",
|
| 62 |
+
"50": "I-COUNTY"
|
| 63 |
+
},
|
| 64 |
+
"initializer_range": 0.02,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"B-ACCOUNTNAME": 12,
|
| 67 |
+
"B-ACCOUNTNUMBER": 16,
|
| 68 |
+
"B-BUILDINGNUMBER": 27,
|
| 69 |
+
"B-CITY": 20,
|
| 70 |
+
"B-COMPANYNAME": 6,
|
| 71 |
+
"B-COUNTY": 30,
|
| 72 |
+
"B-CREDITCARDCVV": 37,
|
| 73 |
+
"B-CREDITCARDISSUER": 35,
|
| 74 |
+
"B-CREDITCARDNUMBER": 24,
|
| 75 |
+
"B-EMAIL": 8,
|
| 76 |
+
"B-FIRSTNAME": 1,
|
| 77 |
+
"B-FULLNAME": 44,
|
| 78 |
+
"B-IBAN": 14,
|
| 79 |
+
"B-LASTNAME": 4,
|
| 80 |
+
"B-MIDDLENAME": 3,
|
| 81 |
+
"B-NAME": 46,
|
| 82 |
+
"B-NUMBER": 48,
|
| 83 |
+
"B-PHONENUMBER": 31,
|
| 84 |
+
"B-PIN": 41,
|
| 85 |
+
"B-SECONDARYADDRESS": 33,
|
| 86 |
+
"B-STATE": 26,
|
| 87 |
+
"B-STREET": 39,
|
| 88 |
+
"B-STREETADDRESS": 18,
|
| 89 |
+
"B-URL": 10,
|
| 90 |
+
"B-USERNAME": 22,
|
| 91 |
+
"I-ACCOUNTNAME": 13,
|
| 92 |
+
"I-ACCOUNTNUMBER": 17,
|
| 93 |
+
"I-BUILDINGNUMBER": 28,
|
| 94 |
+
"I-CITY": 21,
|
| 95 |
+
"I-COMPANYNAME": 7,
|
| 96 |
+
"I-COUNTY": 50,
|
| 97 |
+
"I-CREDITCARDCVV": 38,
|
| 98 |
+
"I-CREDITCARDISSUER": 36,
|
| 99 |
+
"I-CREDITCARDNUMBER": 25,
|
| 100 |
+
"I-EMAIL": 9,
|
| 101 |
+
"I-FIRSTNAME": 2,
|
| 102 |
+
"I-FULLNAME": 45,
|
| 103 |
+
"I-IBAN": 15,
|
| 104 |
+
"I-LASTNAME": 5,
|
| 105 |
+
"I-MIDDLENAME": 43,
|
| 106 |
+
"I-NAME": 47,
|
| 107 |
+
"I-NUMBER": 49,
|
| 108 |
+
"I-PHONENUMBER": 32,
|
| 109 |
+
"I-PIN": 42,
|
| 110 |
+
"I-SECONDARYADDRESS": 34,
|
| 111 |
+
"I-STATE": 29,
|
| 112 |
+
"I-STREET": 40,
|
| 113 |
+
"I-STREETADDRESS": 19,
|
| 114 |
+
"I-URL": 11,
|
| 115 |
+
"I-USERNAME": 23,
|
| 116 |
+
"O": 0
|
| 117 |
+
},
|
| 118 |
+
"max_position_embeddings": 512,
|
| 119 |
+
"model_type": "distilbert",
|
| 120 |
+
"n_heads": 12,
|
| 121 |
+
"n_layers": 6,
|
| 122 |
+
"pad_token_id": 0,
|
| 123 |
+
"qa_dropout": 0.1,
|
| 124 |
+
"seq_classif_dropout": 0.2,
|
| 125 |
+
"sinusoidal_pos_embds": false,
|
| 126 |
+
"tie_weights_": true,
|
| 127 |
+
"torch_dtype": "float32",
|
| 128 |
+
"transformers_version": "4.45.2",
|
| 129 |
+
"vocab_size": 30522
|
| 130 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef8fc3138c24ca8dde984e4519a307416ed72122a4e6e7b0d8587830b9acc093
|
| 3 |
+
size 265620748
|
runs/Oct11_12-35-36_ip-172-16-44-211.eu-west-1.compute.internal/events.out.tfevents.1728650138.ip-172-16-44-211.eu-west-1.compute.internal.22361.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66fcd570c1640fba82f5f0e77406dd1457be10eb06e67767908b43c207803cb8
|
| 3 |
+
size 7710
|
runs/Oct14_04-57-52_ip-172-16-40-248.eu-west-1.compute.internal/events.out.tfevents.1728881882.ip-172-16-40-248.eu-west-1.compute.internal.2492.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48d04350409aa3dd79679c31421ee4237cfce8a25a2b2210f554b88f86e469ce
|
| 3 |
+
size 9612
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2cac04090c38ce92654649db5150bc365354ff7f87c0b00017e56ca75fceece
|
| 3 |
+
size 5304
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|