amalnuaimi
commited on
Commit
•
078dce8
1
Parent(s):
2d217f1
Training in progress, step 500
Browse files- config.json +196 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
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": "Book/description",
|
15 |
+
"1": "Book/name",
|
16 |
+
"2": "BookFormatType",
|
17 |
+
"3": "Boolean",
|
18 |
+
"4": "Brand",
|
19 |
+
"5": "CategoryCode",
|
20 |
+
"6": "CoordinateAT",
|
21 |
+
"7": "Country",
|
22 |
+
"8": "CreativeWork",
|
23 |
+
"9": "CreativeWork/name",
|
24 |
+
"10": "CreativeWorkSeries",
|
25 |
+
"11": "Date",
|
26 |
+
"12": "DateTime",
|
27 |
+
"13": "DayOfWeek",
|
28 |
+
"14": "DeliveryMethod",
|
29 |
+
"15": "Distance",
|
30 |
+
"16": "Duration",
|
31 |
+
"17": "EducationalOccupationalCredential",
|
32 |
+
"18": "Energy",
|
33 |
+
"19": "Event/description",
|
34 |
+
"20": "Event/name",
|
35 |
+
"21": "EventAttendanceModeEnumeration",
|
36 |
+
"22": "EventStatusType",
|
37 |
+
"23": "GenderType",
|
38 |
+
"24": "Hotel/description",
|
39 |
+
"25": "Hotel/name",
|
40 |
+
"26": "IdentifierAT",
|
41 |
+
"27": "ItemAvailability",
|
42 |
+
"28": "ItemList",
|
43 |
+
"29": "JobPosting/description",
|
44 |
+
"30": "JobPosting/name",
|
45 |
+
"31": "Language",
|
46 |
+
"32": "LocalBusiness/name",
|
47 |
+
"33": "LocationFeatureSpecification",
|
48 |
+
"34": "Mass",
|
49 |
+
"35": "MonetaryAmount",
|
50 |
+
"36": "Movie/description",
|
51 |
+
"37": "Movie/name",
|
52 |
+
"38": "Museum/name",
|
53 |
+
"39": "MusicAlbum/name",
|
54 |
+
"40": "MusicArtistAT",
|
55 |
+
"41": "MusicRecording/name",
|
56 |
+
"42": "Number",
|
57 |
+
"43": "OccupationalExperienceRequirements",
|
58 |
+
"44": "OfferItemCondition",
|
59 |
+
"45": "Organization",
|
60 |
+
"46": "Person/name",
|
61 |
+
"47": "Photograph",
|
62 |
+
"48": "Place/name",
|
63 |
+
"49": "PostalAddress",
|
64 |
+
"50": "Product/description",
|
65 |
+
"51": "Product/name",
|
66 |
+
"52": "ProductModel",
|
67 |
+
"53": "QuantitativeValue",
|
68 |
+
"54": "Rating",
|
69 |
+
"55": "Recipe/description",
|
70 |
+
"56": "Recipe/name",
|
71 |
+
"57": "Restaurant/name",
|
72 |
+
"58": "RestrictedDiet",
|
73 |
+
"59": "Review",
|
74 |
+
"60": "SportsEvent/name",
|
75 |
+
"61": "SportsTeam",
|
76 |
+
"62": "TVEpisode/name",
|
77 |
+
"63": "Time",
|
78 |
+
"64": "URL",
|
79 |
+
"65": "addressLocality",
|
80 |
+
"66": "addressRegion",
|
81 |
+
"67": "category",
|
82 |
+
"68": "currency",
|
83 |
+
"69": "email",
|
84 |
+
"70": "faxNumber",
|
85 |
+
"71": "openingHours",
|
86 |
+
"72": "paymentAccepted",
|
87 |
+
"73": "postalCode",
|
88 |
+
"74": "price",
|
89 |
+
"75": "priceRange",
|
90 |
+
"76": "streetAddress",
|
91 |
+
"77": "telephone",
|
92 |
+
"78": "unitCode",
|
93 |
+
"79": "unitText",
|
94 |
+
"80": "weight",
|
95 |
+
"81": "workHours"
|
96 |
+
},
|
97 |
+
"initializer_range": 0.02,
|
98 |
+
"intermediate_size": 3072,
|
99 |
+
"label2id": {
|
100 |
+
"Book/description": 0,
|
101 |
+
"Book/name": 1,
|
102 |
+
"BookFormatType": 2,
|
103 |
+
"Boolean": 3,
|
104 |
+
"Brand": 4,
|
105 |
+
"CategoryCode": 5,
|
106 |
+
"CoordinateAT": 6,
|
107 |
+
"Country": 7,
|
108 |
+
"CreativeWork": 8,
|
109 |
+
"CreativeWork/name": 9,
|
110 |
+
"CreativeWorkSeries": 10,
|
111 |
+
"Date": 11,
|
112 |
+
"DateTime": 12,
|
113 |
+
"DayOfWeek": 13,
|
114 |
+
"DeliveryMethod": 14,
|
115 |
+
"Distance": 15,
|
116 |
+
"Duration": 16,
|
117 |
+
"EducationalOccupationalCredential": 17,
|
118 |
+
"Energy": 18,
|
119 |
+
"Event/description": 19,
|
120 |
+
"Event/name": 20,
|
121 |
+
"EventAttendanceModeEnumeration": 21,
|
122 |
+
"EventStatusType": 22,
|
123 |
+
"GenderType": 23,
|
124 |
+
"Hotel/description": 24,
|
125 |
+
"Hotel/name": 25,
|
126 |
+
"IdentifierAT": 26,
|
127 |
+
"ItemAvailability": 27,
|
128 |
+
"ItemList": 28,
|
129 |
+
"JobPosting/description": 29,
|
130 |
+
"JobPosting/name": 30,
|
131 |
+
"Language": 31,
|
132 |
+
"LocalBusiness/name": 32,
|
133 |
+
"LocationFeatureSpecification": 33,
|
134 |
+
"Mass": 34,
|
135 |
+
"MonetaryAmount": 35,
|
136 |
+
"Movie/description": 36,
|
137 |
+
"Movie/name": 37,
|
138 |
+
"Museum/name": 38,
|
139 |
+
"MusicAlbum/name": 39,
|
140 |
+
"MusicArtistAT": 40,
|
141 |
+
"MusicRecording/name": 41,
|
142 |
+
"Number": 42,
|
143 |
+
"OccupationalExperienceRequirements": 43,
|
144 |
+
"OfferItemCondition": 44,
|
145 |
+
"Organization": 45,
|
146 |
+
"Person/name": 46,
|
147 |
+
"Photograph": 47,
|
148 |
+
"Place/name": 48,
|
149 |
+
"PostalAddress": 49,
|
150 |
+
"Product/description": 50,
|
151 |
+
"Product/name": 51,
|
152 |
+
"ProductModel": 52,
|
153 |
+
"QuantitativeValue": 53,
|
154 |
+
"Rating": 54,
|
155 |
+
"Recipe/description": 55,
|
156 |
+
"Recipe/name": 56,
|
157 |
+
"Restaurant/name": 57,
|
158 |
+
"RestrictedDiet": 58,
|
159 |
+
"Review": 59,
|
160 |
+
"SportsEvent/name": 60,
|
161 |
+
"SportsTeam": 61,
|
162 |
+
"TVEpisode/name": 62,
|
163 |
+
"Time": 63,
|
164 |
+
"URL": 64,
|
165 |
+
"addressLocality": 65,
|
166 |
+
"addressRegion": 66,
|
167 |
+
"category": 67,
|
168 |
+
"currency": 68,
|
169 |
+
"email": 69,
|
170 |
+
"faxNumber": 70,
|
171 |
+
"openingHours": 71,
|
172 |
+
"paymentAccepted": 72,
|
173 |
+
"postalCode": 73,
|
174 |
+
"price": 74,
|
175 |
+
"priceRange": 75,
|
176 |
+
"streetAddress": 76,
|
177 |
+
"telephone": 77,
|
178 |
+
"unitCode": 78,
|
179 |
+
"unitText": 79,
|
180 |
+
"weight": 80,
|
181 |
+
"workHours": 81
|
182 |
+
},
|
183 |
+
"layer_norm_eps": 1e-05,
|
184 |
+
"max_position_embeddings": 514,
|
185 |
+
"model_type": "roberta",
|
186 |
+
"num_attention_heads": 12,
|
187 |
+
"num_hidden_layers": 12,
|
188 |
+
"pad_token_id": 1,
|
189 |
+
"position_embedding_type": "absolute",
|
190 |
+
"problem_type": "single_label_classification",
|
191 |
+
"torch_dtype": "float32",
|
192 |
+
"transformers_version": "4.35.0",
|
193 |
+
"type_vocab_size": 1,
|
194 |
+
"use_cache": true,
|
195 |
+
"vocab_size": 50265
|
196 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6b83a7ea50f091373f9823247e10db7a811d39e4e4fadd37caf45d806f67217
|
3 |
+
size 498858904
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c550cf26f1a65334c18883ae6a8deabe6cf8c8862fd8a102c2653dc301d8e16e
|
3 |
+
size 4536
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|