Upload 8 files
Browse files- README.md +63 -0
- config.json +123 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- common_language
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: language-detection-fine-tuned-on-xlm-roberta-base
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Text Classification
|
14 |
+
type: text-classification
|
15 |
+
dataset:
|
16 |
+
name: common_language
|
17 |
+
type: common_language
|
18 |
+
args: full
|
19 |
+
metrics:
|
20 |
+
- name: Accuracy
|
21 |
+
type: accuracy
|
22 |
+
value: 0.9738386718094919
|
23 |
+
---
|
24 |
+
|
25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
26 |
+
should probably proofread and complete it, then remove this comment. -->
|
27 |
+
|
28 |
+
# language-detection-fine-tuned-on-xlm-roberta-base
|
29 |
+
|
30 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the [common_language](https://huggingface.co/datasets/common_language) dataset.
|
31 |
+
It achieves the following results on the evaluation set:
|
32 |
+
- Loss: 0.1886
|
33 |
+
- Accuracy: 0.9738
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 3e-05
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 1
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 1
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
52 |
+
| 0.1 | 1.0 | 22194 | 0.1886 | 0.9738 |
|
53 |
+
|
54 |
+
|
55 |
+
### Framework versions
|
56 |
+
|
57 |
+
- Transformers 4.12.5
|
58 |
+
- Pytorch 1.10.0+cu111
|
59 |
+
- Datasets 1.15.1
|
60 |
+
- Tokenizers 0.10.3
|
61 |
+
|
62 |
+
### Notebook
|
63 |
+
[notebook](https://github.com/IvanLauLinTiong/language-detector/blob/main/xlm_roberta_base_commonlanguage_language_detector.ipynb)
|
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": "4.12.5",
|
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:c90871c97e98322a362545b87907d2601663c5de52b11c362ade644d421ff011
|
3 |
+
size 1112398381
|
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
The diff for this file is too large to render.
See raw diff
|
|
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 sha256:870ec4661581f2601077a00efdd2cbcfdda1f0085e27e0efe756ac96a809d112
|
3 |
+
size 3055
|