jerryKakooza commited on
Commit
6ac1aa1
1 Parent(s): a103e40

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Arabic",
15
+ "1": "Basque",
16
+ "10": "Dutch",
17
+ "11": "English",
18
+ "12": "Esperanto",
19
+ "13": "Estonian",
20
+ "14": "French",
21
+ "15": "Frisian",
22
+ "16": "Georgian",
23
+ "17": "German",
24
+ "18": "Greek",
25
+ "19": "Hakha_Chin",
26
+ "2": "Breton",
27
+ "20": "Indonesian",
28
+ "21": "Interlingua",
29
+ "22": "Italian",
30
+ "23": "Japanese",
31
+ "24": "Kabyle",
32
+ "25": "Kinyarwanda",
33
+ "26": "Kyrgyz",
34
+ "27": "Latvian",
35
+ "28": "Maltese",
36
+ "29": "Mangolian",
37
+ "3": "Catalan",
38
+ "30": "Persian",
39
+ "31": "Polish",
40
+ "32": "Portuguese",
41
+ "33": "Romanian",
42
+ "34": "Romansh_Sursilvan",
43
+ "35": "Russian",
44
+ "36": "Sakha",
45
+ "37": "Slovenian",
46
+ "38": "Spanish",
47
+ "39": "Swedish",
48
+ "4": "Chinese_China",
49
+ "40": "Tamil",
50
+ "41": "Tatar",
51
+ "42": "Turkish",
52
+ "43": "Ukranian",
53
+ "44": "Welsh",
54
+ "5": "Chinese_Hongkong",
55
+ "6": "Chinese_Taiwan",
56
+ "7": "Chuvash",
57
+ "8": "Czech",
58
+ "9": "Dhivehi"
59
+ },
60
+ "initializer_range": 0.02,
61
+ "intermediate_size": 3072,
62
+ "label2id": {
63
+ "Arabic": "0",
64
+ "Basque": "1",
65
+ "Breton": "2",
66
+ "Catalan": "3",
67
+ "Chinese_China": "4",
68
+ "Chinese_Hongkong": "5",
69
+ "Chinese_Taiwan": "6",
70
+ "Chuvash": "7",
71
+ "Czech": "8",
72
+ "Dhivehi": "9",
73
+ "Dutch": "10",
74
+ "English": "11",
75
+ "Esperanto": "12",
76
+ "Estonian": "13",
77
+ "French": "14",
78
+ "Frisian": "15",
79
+ "Georgian": "16",
80
+ "German": "17",
81
+ "Greek": "18",
82
+ "Hakha_Chin": "19",
83
+ "Indonesian": "20",
84
+ "Interlingua": "21",
85
+ "Italian": "22",
86
+ "Japanese": "23",
87
+ "Kabyle": "24",
88
+ "Kinyarwanda": "25",
89
+ "Kyrgyz": "26",
90
+ "Latvian": "27",
91
+ "Maltese": "28",
92
+ "Mangolian": "29",
93
+ "Persian": "30",
94
+ "Polish": "31",
95
+ "Portuguese": "32",
96
+ "Romanian": "33",
97
+ "Romansh_Sursilvan": "34",
98
+ "Russian": "35",
99
+ "Sakha": "36",
100
+ "Slovenian": "37",
101
+ "Spanish": "38",
102
+ "Swedish": "39",
103
+ "Tamil": "40",
104
+ "Tatar": "41",
105
+ "Turkish": "42",
106
+ "Ukranian": "43",
107
+ "Welsh": "44"
108
+ },
109
+ "layer_norm_eps": 1e-05,
110
+ "max_position_embeddings": 514,
111
+ "model_type": "xlm-roberta",
112
+ "num_attention_heads": 12,
113
+ "num_hidden_layers": 12,
114
+ "output_past": true,
115
+ "pad_token_id": 1,
116
+ "position_embedding_type": "absolute",
117
+ "problem_type": "single_label_classification",
118
+ "torch_dtype": "float32",
119
+ "transformers_version": "4.18.0",
120
+ "type_vocab_size": 1,
121
+ "use_cache": true,
122
+ "vocab_size": 250002
123
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1866dc84b62fd05dac26da81978547be8e6d26b3eff11dd464a4b74272073e90
3
+ size 1112384621
runs/May03_06-42-41_126df7cbfa2b/1651560180.5838637/events.out.tfevents.1651560180.126df7cbfa2b.71.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41758eba73b20a0d48135c1b6c99bc7e3662d2fd8e92ec337db4c0fa4e8270da
3
+ size 4984
runs/May03_06-42-41_126df7cbfa2b/events.out.tfevents.1651560180.126df7cbfa2b.71.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6ed96b797c211364cb4ecfefb5cd0419fa1fc3d5952b7a9ef99cec3199d46a8
3
+ size 12781
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 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
3
+ size 17082660
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9bb56f1a77099116d2dcffb0295b64ec03c392453cfd63555c0ec7a17b4390
3
+ size 3183