ricardo-filho commited on
Commit
53e4d18
1 Parent(s): 299db13

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "finetuning_task": "ner",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "B-AerospaceManufacturer",
13
+ "1": "B-AnatomicalStructure",
14
+ "2": "B-ArtWork",
15
+ "3": "B-Artist",
16
+ "4": "B-Athlete",
17
+ "5": "B-CarManufacturer",
18
+ "6": "B-Cleric",
19
+ "7": "B-Clothing",
20
+ "8": "B-Disease",
21
+ "9": "B-Drink",
22
+ "10": "B-Facility",
23
+ "11": "B-Food",
24
+ "12": "B-HumanSettlement",
25
+ "13": "B-MedicalProcedure",
26
+ "14": "B-Medication/Vaccine",
27
+ "15": "B-MusicalGRP",
28
+ "16": "B-MusicalWork",
29
+ "17": "B-ORG",
30
+ "18": "B-OtherLOC",
31
+ "19": "B-OtherPER",
32
+ "20": "B-OtherPROD",
33
+ "21": "B-Politician",
34
+ "22": "B-PrivateCorp",
35
+ "23": "B-PublicCorp",
36
+ "24": "B-Scientist",
37
+ "25": "B-Software",
38
+ "26": "B-SportsGRP",
39
+ "27": "B-SportsManager",
40
+ "28": "B-Station",
41
+ "29": "B-Symptom",
42
+ "30": "B-Vehicle",
43
+ "31": "B-VisualWork",
44
+ "32": "B-WrittenWork",
45
+ "33": "I-AerospaceManufacturer",
46
+ "34": "I-AnatomicalStructure",
47
+ "35": "I-ArtWork",
48
+ "36": "I-Artist",
49
+ "37": "I-Athlete",
50
+ "38": "I-CarManufacturer",
51
+ "39": "I-Cleric",
52
+ "40": "I-Clothing",
53
+ "41": "I-Disease",
54
+ "42": "I-Drink",
55
+ "43": "I-Facility",
56
+ "44": "I-Food",
57
+ "45": "I-HumanSettlement",
58
+ "46": "I-MedicalProcedure",
59
+ "47": "I-Medication/Vaccine",
60
+ "48": "I-MusicalGRP",
61
+ "49": "I-MusicalWork",
62
+ "50": "I-ORG",
63
+ "51": "I-OtherLOC",
64
+ "52": "I-OtherPER",
65
+ "53": "I-OtherPROD",
66
+ "54": "I-Politician",
67
+ "55": "I-PrivateCorp",
68
+ "56": "I-PublicCorp",
69
+ "57": "I-Scientist",
70
+ "58": "I-Software",
71
+ "59": "I-SportsGRP",
72
+ "60": "I-SportsManager",
73
+ "61": "I-Station",
74
+ "62": "I-Symptom",
75
+ "63": "I-Vehicle",
76
+ "64": "I-VisualWork",
77
+ "65": "I-WrittenWork",
78
+ "66": "O"
79
+ },
80
+ "initializer_range": 0.02,
81
+ "intermediate_size": 3072,
82
+ "label2id": {
83
+ "B-AerospaceManufacturer": 0,
84
+ "B-AnatomicalStructure": 1,
85
+ "B-ArtWork": 2,
86
+ "B-Artist": 3,
87
+ "B-Athlete": 4,
88
+ "B-CarManufacturer": 5,
89
+ "B-Cleric": 6,
90
+ "B-Clothing": 7,
91
+ "B-Disease": 8,
92
+ "B-Drink": 9,
93
+ "B-Facility": 10,
94
+ "B-Food": 11,
95
+ "B-HumanSettlement": 12,
96
+ "B-MedicalProcedure": 13,
97
+ "B-Medication/Vaccine": 14,
98
+ "B-MusicalGRP": 15,
99
+ "B-MusicalWork": 16,
100
+ "B-ORG": 17,
101
+ "B-OtherLOC": 18,
102
+ "B-OtherPER": 19,
103
+ "B-OtherPROD": 20,
104
+ "B-Politician": 21,
105
+ "B-PrivateCorp": 22,
106
+ "B-PublicCorp": 23,
107
+ "B-Scientist": 24,
108
+ "B-Software": 25,
109
+ "B-SportsGRP": 26,
110
+ "B-SportsManager": 27,
111
+ "B-Station": 28,
112
+ "B-Symptom": 29,
113
+ "B-Vehicle": 30,
114
+ "B-VisualWork": 31,
115
+ "B-WrittenWork": 32,
116
+ "I-AerospaceManufacturer": 33,
117
+ "I-AnatomicalStructure": 34,
118
+ "I-ArtWork": 35,
119
+ "I-Artist": 36,
120
+ "I-Athlete": 37,
121
+ "I-CarManufacturer": 38,
122
+ "I-Cleric": 39,
123
+ "I-Clothing": 40,
124
+ "I-Disease": 41,
125
+ "I-Drink": 42,
126
+ "I-Facility": 43,
127
+ "I-Food": 44,
128
+ "I-HumanSettlement": 45,
129
+ "I-MedicalProcedure": 46,
130
+ "I-Medication/Vaccine": 47,
131
+ "I-MusicalGRP": 48,
132
+ "I-MusicalWork": 49,
133
+ "I-ORG": 50,
134
+ "I-OtherLOC": 51,
135
+ "I-OtherPER": 52,
136
+ "I-OtherPROD": 53,
137
+ "I-Politician": 54,
138
+ "I-PrivateCorp": 55,
139
+ "I-PublicCorp": 56,
140
+ "I-Scientist": 57,
141
+ "I-Software": 58,
142
+ "I-SportsGRP": 59,
143
+ "I-SportsManager": 60,
144
+ "I-Station": 61,
145
+ "I-Symptom": 62,
146
+ "I-Vehicle": 63,
147
+ "I-VisualWork": 64,
148
+ "I-WrittenWork": 65,
149
+ "O": 66
150
+ },
151
+ "layer_norm_eps": 1e-07,
152
+ "max_position_embeddings": 512,
153
+ "max_relative_positions": -1,
154
+ "model_type": "deberta-v2",
155
+ "norm_rel_ebd": "layer_norm",
156
+ "num_attention_heads": 12,
157
+ "num_hidden_layers": 12,
158
+ "pad_token_id": 0,
159
+ "pooler_dropout": 0,
160
+ "pooler_hidden_act": "gelu",
161
+ "pooler_hidden_size": 768,
162
+ "pos_att_type": [
163
+ "p2c",
164
+ "c2p"
165
+ ],
166
+ "position_biased_input": false,
167
+ "position_buckets": 256,
168
+ "relative_attention": true,
169
+ "share_att_key": true,
170
+ "torch_dtype": "float32",
171
+ "transformers_version": "4.26.0.dev0",
172
+ "type_vocab_size": 0,
173
+ "vocab_size": 251000
174
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9991329d6ae666722dc84a0d2c37695684ad6336c21f54afa6e474932e78a072
3
+ size 1113152687
runs/Dec02_15-19-38_3b641fa2dfc3/1669994438.9674773/events.out.tfevents.1669994438.3b641fa2dfc3.480.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63102defcdab247e462f441ecc9bb6063a5c744b6e565c6379c74b86413672d
3
+ size 5535
runs/Dec02_15-19-38_3b641fa2dfc3/events.out.tfevents.1669994438.3b641fa2dfc3.480.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92418fa60f870290f61f8c0ac36ed52ed187cfd51f20c631e260f84af014fb6c
3
+ size 22512
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6d6b3f684e192d7f7db2ed0f86d6387c71afb19e06d9cc52006af99ca779f0
3
+ size 16331399
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "eos_token": "[SEP]",
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "name_or_path": "microsoft/mdeberta-v3-base",
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "special_tokens_map_file": null,
13
+ "split_by_punct": false,
14
+ "tokenizer_class": "DebertaV2Tokenizer",
15
+ "unk_token": "[UNK]",
16
+ "vocab_type": "spm"
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7cdf3c3bb29e3768cb1b115462b128bb19e92b71c177bb4c04e0ba5cd796f94
3
+ size 3439