dmargutierrez commited on
Commit
d425938
·
1 Parent(s): aae20cd

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,121 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-BUILDING",
16
+ "2": "I-BUILDING",
17
+ "3": "B-CITY",
18
+ "4": "I-CITY",
19
+ "5": "B-COUNTRY",
20
+ "6": "I-COUNTRY",
21
+ "7": "B-PLACE",
22
+ "8": "I-PLACE",
23
+ "9": "B-TERRITORY",
24
+ "10": "I-TERRITORY",
25
+ "11": "I-UNIT",
26
+ "12": "B-UNIT",
27
+ "13": "B-VALUE",
28
+ "14": "I-VALUE",
29
+ "15": "B-YEAR",
30
+ "16": "I-YEAR",
31
+ "17": "B-STANDARD ABBREVIATION",
32
+ "18": "I-STANDARD ABBREVIATION",
33
+ "19": "B-MONTH",
34
+ "20": "I-MONTH",
35
+ "21": "B-DAY",
36
+ "22": "I-DAY",
37
+ "23": "B-AGE",
38
+ "24": "I-AGE",
39
+ "25": "B-ETHNIC CATEGORY",
40
+ "26": "I-ETHNIC CATEGORY",
41
+ "27": "B-FAMILY NAME",
42
+ "28": "I-FAMILY NAME",
43
+ "29": "B-INITIAL NAME",
44
+ "30": "I-INITIAL NAME",
45
+ "31": "B-MARITAL STATUS",
46
+ "32": "I-MARITAL STATUS",
47
+ "33": "B-PROFESSION",
48
+ "34": "I-PROFESSION",
49
+ "35": "B-ROLE",
50
+ "36": "I-ROLE",
51
+ "37": "B-NATIONALITY",
52
+ "38": "I-NATIONALITY",
53
+ "39": "B-TITLE",
54
+ "40": "I-TITLE",
55
+ "41": "B-URL",
56
+ "42": "I-URL",
57
+ "43": "B-TYPE",
58
+ "44": "I-TYPE"
59
+ },
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "B-AGE": 23,
64
+ "B-BUILDING": 1,
65
+ "B-CITY": 3,
66
+ "B-COUNTRY": 5,
67
+ "B-DAY": 21,
68
+ "B-ETHNIC CATEGORY": 25,
69
+ "B-FAMILY NAME": 27,
70
+ "B-INITIAL NAME": 29,
71
+ "B-MARITAL STATUS": 31,
72
+ "B-MONTH": 19,
73
+ "B-NATIONALITY": 37,
74
+ "B-PLACE": 7,
75
+ "B-PROFESSION": 33,
76
+ "B-ROLE": 35,
77
+ "B-STANDARD ABBREVIATION": 17,
78
+ "B-TERRITORY": 9,
79
+ "B-TITLE": 39,
80
+ "B-TYPE": 43,
81
+ "B-UNIT": 12,
82
+ "B-URL": 41,
83
+ "B-VALUE": 13,
84
+ "B-YEAR": 15,
85
+ "I-AGE": 24,
86
+ "I-BUILDING": 2,
87
+ "I-CITY": 4,
88
+ "I-COUNTRY": 6,
89
+ "I-DAY": 22,
90
+ "I-ETHNIC CATEGORY": 26,
91
+ "I-FAMILY NAME": 28,
92
+ "I-INITIAL NAME": 30,
93
+ "I-MARITAL STATUS": 32,
94
+ "I-MONTH": 20,
95
+ "I-NATIONALITY": 38,
96
+ "I-PLACE": 8,
97
+ "I-PROFESSION": 34,
98
+ "I-ROLE": 36,
99
+ "I-STANDARD ABBREVIATION": 18,
100
+ "I-TERRITORY": 10,
101
+ "I-TITLE": 40,
102
+ "I-TYPE": 44,
103
+ "I-UNIT": 11,
104
+ "I-URL": 42,
105
+ "I-VALUE": 14,
106
+ "I-YEAR": 16,
107
+ "O": 0
108
+ },
109
+ "layer_norm_eps": 1e-05,
110
+ "max_position_embeddings": 514,
111
+ "model_type": "roberta",
112
+ "num_attention_heads": 12,
113
+ "num_hidden_layers": 12,
114
+ "pad_token_id": 1,
115
+ "position_embedding_type": "absolute",
116
+ "torch_dtype": "bfloat16",
117
+ "transformers_version": "4.26.0",
118
+ "type_vocab_size": 1,
119
+ "use_cache": true,
120
+ "vocab_size": 50265
121
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c39167d66009034e9b0211ab810f2d592aae2179563c56fd9e6a08b478df8f
3
+ size 248252013
runs/Mar20_10-51-54_t1-45-bhs5/1679309521.5728636/events.out.tfevents.1679309521.t1-45-bhs5.6639.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1bf765a6b72670d28028ac0c4634c18255b85a1092ebe63989ef5d6f6488609
3
+ size 5692
runs/Mar20_10-51-54_t1-45-bhs5/events.out.tfevents.1679309521.t1-45-bhs5.6639.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1773f03031b5ec7ada4352480e6c93406c41a3000bfc4140706a8a3b6ff4476
3
+ size 6849
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33464575a725d8afff65a231720f5424f032777682d23bd9172487dc7581883
3
+ size 3515
vocab.json ADDED
The diff for this file is too large to render. See raw diff