Julien Simon commited on
Commit
57b4887
1 Parent(s): 0b26e69

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-*/
config.json ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xlm-v-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
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": "Afrikaans",
15
+ "1": "Amharic",
16
+ "2": "Arabic",
17
+ "3": "Assamese",
18
+ "4": "Asturian",
19
+ "5": "Azerbaijani",
20
+ "6": "Belarusian",
21
+ "7": "Bulgarian",
22
+ "8": "Bengali",
23
+ "9": "Bosnian",
24
+ "10": "Catalan",
25
+ "11": "Cebuano",
26
+ "12": "Sorani-Kurdish",
27
+ "13": "Mandarin Chinese",
28
+ "14": "Czech",
29
+ "15": "Welsh",
30
+ "16": "Danish",
31
+ "17": "German",
32
+ "18": "Greek",
33
+ "19": "English",
34
+ "20": "Spanish",
35
+ "21": "Estonian",
36
+ "22": "Persian",
37
+ "23": "Fula",
38
+ "24": "Finnish",
39
+ "25": "Filipino",
40
+ "26": "French",
41
+ "27": "Irish",
42
+ "28": "Galician",
43
+ "29": "Gujarati",
44
+ "30": "Hausa",
45
+ "31": "Hebrew",
46
+ "32": "Hindi",
47
+ "33": "Croatian",
48
+ "34": "Hungarian",
49
+ "35": "Armenian",
50
+ "36": "Indonesian",
51
+ "37": "Igbo",
52
+ "38": "Icelandic",
53
+ "39": "Italian",
54
+ "40": "Japanese",
55
+ "41": "Javanese",
56
+ "42": "Georgian",
57
+ "43": "Kamba",
58
+ "44": "Kabuverdianu",
59
+ "45": "Kazakh",
60
+ "46": "Khmer",
61
+ "47": "Kannada",
62
+ "48": "Korean",
63
+ "49": "Kyrgyz",
64
+ "50": "Luxembourgish",
65
+ "51": "Ganda",
66
+ "52": "Lingala",
67
+ "53": "Lao",
68
+ "54": "Lithuanian",
69
+ "55": "Luo",
70
+ "56": "Latvian",
71
+ "57": "Maori",
72
+ "58": "Macedonian",
73
+ "59": "Malayalam",
74
+ "60": "Mongolian",
75
+ "61": "Marathi",
76
+ "62": "Malay",
77
+ "63": "Maltese",
78
+ "64": "Burmese",
79
+ "65": "Norwegian",
80
+ "66": "Nepali",
81
+ "67": "Dutch",
82
+ "68": "Northern-Sotho",
83
+ "69": "Nyanja",
84
+ "70": "Occitan",
85
+ "71": "Oromo",
86
+ "72": "Oriya",
87
+ "73": "Punjabi",
88
+ "74": "Polish",
89
+ "75": "Pashto",
90
+ "76": "Portuguese",
91
+ "77": "Romanian",
92
+ "78": "Russian",
93
+ "79": "Sindhi",
94
+ "80": "Slovak",
95
+ "81": "Slovenian",
96
+ "82": "Shona",
97
+ "83": "Somali",
98
+ "84": "Serbian",
99
+ "85": "Swedish",
100
+ "86": "Swahili",
101
+ "87": "Tamil",
102
+ "88": "Telugu",
103
+ "89": "Tajik",
104
+ "90": "Thai",
105
+ "91": "Turkish",
106
+ "92": "Ukrainian",
107
+ "93": "Umbundu",
108
+ "94": "Urdu",
109
+ "95": "Uzbek",
110
+ "96": "Vietnamese",
111
+ "97": "Wolof",
112
+ "98": "Xhosa",
113
+ "99": "Yoruba",
114
+ "100": "Cantonese Chinese",
115
+ "101": "Zulu"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "label2id": {
120
+ "Afrikaans": 0,
121
+ "Amharic": 1,
122
+ "Arabic": 2,
123
+ "Armenian": 35,
124
+ "Assamese": 3,
125
+ "Asturian": 4,
126
+ "Azerbaijani": 5,
127
+ "Belarusian": 6,
128
+ "Bengali": 8,
129
+ "Bosnian": 9,
130
+ "Bulgarian": 7,
131
+ "Burmese": 64,
132
+ "Cantonese Chinese": 100,
133
+ "Catalan": 10,
134
+ "Cebuano": 11,
135
+ "Croatian": 33,
136
+ "Czech": 14,
137
+ "Danish": 16,
138
+ "Dutch": 67,
139
+ "English": 19,
140
+ "Estonian": 21,
141
+ "Filipino": 25,
142
+ "Finnish": 24,
143
+ "French": 26,
144
+ "Fula": 23,
145
+ "Galician": 28,
146
+ "Ganda": 51,
147
+ "Georgian": 42,
148
+ "German": 17,
149
+ "Greek": 18,
150
+ "Gujarati": 29,
151
+ "Hausa": 30,
152
+ "Hebrew": 31,
153
+ "Hindi": 32,
154
+ "Hungarian": 34,
155
+ "Icelandic": 38,
156
+ "Igbo": 37,
157
+ "Indonesian": 36,
158
+ "Irish": 27,
159
+ "Italian": 39,
160
+ "Japanese": 40,
161
+ "Javanese": 41,
162
+ "Kabuverdianu": 44,
163
+ "Kamba": 43,
164
+ "Kannada": 47,
165
+ "Kazakh": 45,
166
+ "Khmer": 46,
167
+ "Korean": 48,
168
+ "Kyrgyz": 49,
169
+ "Lao": 53,
170
+ "Latvian": 56,
171
+ "Lingala": 52,
172
+ "Lithuanian": 54,
173
+ "Luo": 55,
174
+ "Luxembourgish": 50,
175
+ "Macedonian": 58,
176
+ "Malay": 62,
177
+ "Malayalam": 59,
178
+ "Maltese": 63,
179
+ "Mandarin Chinese": 13,
180
+ "Maori": 57,
181
+ "Marathi": 61,
182
+ "Mongolian": 60,
183
+ "Nepali": 66,
184
+ "Northern-Sotho": 68,
185
+ "Norwegian": 65,
186
+ "Nyanja": 69,
187
+ "Occitan": 70,
188
+ "Oriya": 72,
189
+ "Oromo": 71,
190
+ "Pashto": 75,
191
+ "Persian": 22,
192
+ "Polish": 74,
193
+ "Portuguese": 76,
194
+ "Punjabi": 73,
195
+ "Romanian": 77,
196
+ "Russian": 78,
197
+ "Serbian": 84,
198
+ "Shona": 82,
199
+ "Sindhi": 79,
200
+ "Slovak": 80,
201
+ "Slovenian": 81,
202
+ "Somali": 83,
203
+ "Sorani-Kurdish": 12,
204
+ "Spanish": 20,
205
+ "Swahili": 86,
206
+ "Swedish": 85,
207
+ "Tajik": 89,
208
+ "Tamil": 87,
209
+ "Telugu": 88,
210
+ "Thai": 90,
211
+ "Turkish": 91,
212
+ "Ukrainian": 92,
213
+ "Umbundu": 93,
214
+ "Urdu": 94,
215
+ "Uzbek": 95,
216
+ "Vietnamese": 96,
217
+ "Welsh": 15,
218
+ "Wolof": 97,
219
+ "Xhosa": 98,
220
+ "Yoruba": 99,
221
+ "Zulu": 101
222
+ },
223
+ "layer_norm_eps": 1e-05,
224
+ "max_position_embeddings": 514,
225
+ "model_type": "xlm-roberta",
226
+ "num_attention_heads": 12,
227
+ "num_hidden_layers": 12,
228
+ "pad_token_id": 1,
229
+ "position_embedding_type": "absolute",
230
+ "problem_type": "single_label_classification",
231
+ "torch_dtype": "float32",
232
+ "transformers_version": "4.26.0",
233
+ "type_vocab_size": 1,
234
+ "use_cache": true,
235
+ "vocab_size": 901629
236
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130f9a1c098b9f9d137297b53e4d63c46c17de44564d9c338b90009d5ce9b8db
3
+ size 3114359925
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab892eef4554b6ef5a5289833a4dcb99b9001472a939160299a7d0fa603e27ad
3
+ size 61333547
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "facebook/xlm-v-base",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d425c6ef778369a06302e6e97593ebb8cd22a365f759bdac3b78813603f78e5
3
+ size 3515