simoneteglia commited on
Commit
d34d96d
1 Parent(s): 8e892f1

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-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": "bulgarian",
15
+ "1": "polish",
16
+ "2": "pushto",
17
+ "3": "kyrgyz",
18
+ "4": "malay",
19
+ "5": "kazak",
20
+ "6": "hungarian",
21
+ "7": "armenian",
22
+ "8": "kashmiri",
23
+ "9": "romanian",
24
+ "10": "tajik",
25
+ "11": "dutch",
26
+ "12": "english",
27
+ "13": "finnish",
28
+ "14": "welsh",
29
+ "15": "lithuanian",
30
+ "16": "portoguese",
31
+ "17": "belarusian",
32
+ "18": "maltese",
33
+ "19": "dhivehi",
34
+ "20": "malayan",
35
+ "21": "german",
36
+ "22": "sinhala",
37
+ "23": "azerbaijani",
38
+ "24": "uzbek",
39
+ "25": "lao",
40
+ "26": "greek",
41
+ "27": "nepali",
42
+ "28": "slovak",
43
+ "29": "french",
44
+ "30": "italian",
45
+ "31": "albanian",
46
+ "32": "label",
47
+ "33": "mongolian",
48
+ "34": "estonian",
49
+ "35": "swahili",
50
+ "36": "burmese",
51
+ "37": "slovene",
52
+ "38": "faroese",
53
+ "39": "turkmen",
54
+ "40": "danish",
55
+ "41": "maori",
56
+ "42": "georgian",
57
+ "43": "spanish",
58
+ "44": "swedish",
59
+ "45": "latvian",
60
+ "46": "czech"
61
+ },
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 3072,
64
+ "label2id": {
65
+ "albanian": 31,
66
+ "armenian": 7,
67
+ "azerbaijani": 23,
68
+ "belarusian": 17,
69
+ "bulgarian": 0,
70
+ "burmese": 36,
71
+ "czech": 46,
72
+ "danish": 40,
73
+ "dhivehi": 19,
74
+ "dutch": 11,
75
+ "english": 12,
76
+ "estonian": 34,
77
+ "faroese": 38,
78
+ "finnish": 13,
79
+ "french": 29,
80
+ "georgian": 42,
81
+ "german": 21,
82
+ "greek": 26,
83
+ "hungarian": 6,
84
+ "italian": 30,
85
+ "kashmiri": 8,
86
+ "kazak": 5,
87
+ "kyrgyz": 3,
88
+ "label": 32,
89
+ "lao": 25,
90
+ "latvian": 45,
91
+ "lithuanian": 15,
92
+ "malay": 4,
93
+ "malayan": 20,
94
+ "maltese": 18,
95
+ "maori": 41,
96
+ "mongolian": 33,
97
+ "nepali": 27,
98
+ "polish": 1,
99
+ "portoguese": 16,
100
+ "pushto": 2,
101
+ "romanian": 9,
102
+ "sinhala": 22,
103
+ "slovak": 28,
104
+ "slovene": 37,
105
+ "spanish": 43,
106
+ "swahili": 35,
107
+ "swedish": 44,
108
+ "tajik": 10,
109
+ "turkmen": 39,
110
+ "uzbek": 24,
111
+ "welsh": 14
112
+ },
113
+ "layer_norm_eps": 1e-05,
114
+ "max_position_embeddings": 514,
115
+ "model_type": "xlm-roberta",
116
+ "num_attention_heads": 12,
117
+ "num_hidden_layers": 12,
118
+ "output_past": true,
119
+ "pad_token_id": 1,
120
+ "position_embedding_type": "absolute",
121
+ "problem_type": "single_label_classification",
122
+ "torch_dtype": "float32",
123
+ "transformers_version": "4.28.0",
124
+ "type_vocab_size": 1,
125
+ "use_cache": true,
126
+ "vocab_size": 250002
127
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8b12533e11fe0e8ea625a2d350a5d8d21ed820361154e1397eb441791963d3
3
+ size 1112392565
runs/Jun21_09-13-24_79f4267dcf00/1687338813.5663834/events.out.tfevents.1687338813.79f4267dcf00.1352.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:231c2b6dc620bd608b28e6d8f450340847a5c3f08918cb7c78435e483dc74493
3
+ size 5949
runs/Jun21_09-13-24_79f4267dcf00/events.out.tfevents.1687338813.79f4267dcf00.1352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cb833b806314ea62d8315f6bb0e8980b4464604e4e92182c59fdc23730f393
3
+ size 7405
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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 sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 512,
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b144954a24983c753408ba33b78fbe7382cc5fc70bfd43cafb6eae6a82340565
3
+ size 3643