Hugging Face's logo

saadlohani
/
polystring-lid

Token Classification
Transformers
ONNX
Safetensors
xlm-roberta
Generated from Trainer
Model card Files
xet
 Community
saadlohani commited on
Commit
f812ae9
·
verified ·
1 Parent(s): ea82445

Fine-tuned XLM-R for polystring LID

Browse files
Files changed (4) hide show
  1. README.md +5 -5
  2. config.json +98 -26
  3. model.safetensors +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.2006
22
- - F1: 0.8465
23
 
24
  ## Model description
25
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 |
56
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
57
- | 0.3803 | 1.0 | 9433 | 0.3599 | 0.7831 |
58
- | 0.2825 | 2.0 | 18866 | 0.2654 | 0.8170 |
59
- | 0.2098 | 3.0 | 28299 | 0.2006 | 0.8465 |
60
 
61
 
62
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1267
22
+ - F1: 0.8848
23
 
24
  ## Model description
25
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | F1 |
56
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
57
+ | 0.3134 | 1.0 | 18838 | 0.2941 | 0.8119 |
58
+ | 0.1935 | 2.0 | 37676 | 0.1807 | 0.8551 |
59
+ | 0.1357 | 3.0 | 56514 | 0.1267 | 0.8848 |
60
 
61
 
62
  ### Framework versions
config.json CHANGED
@@ -13,38 +13,110 @@
13
  "id2label": {
14
  "0": "en",
15
  "1": "es",
16
- "2": "hi",
17
- "3": "ar",
18
- "4": "ne",
19
- "5": "fr",
20
- "6": "de",
21
- "7": "tr",
22
- "8": "tl",
23
- "9": "sw",
24
- "10": "ur",
25
- "11": "NE",
26
- "12": "OTHER",
27
- "13": "MIX",
28
- "14": "AMB"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  },
30
  "initializer_range": 0.02,
31
  "intermediate_size": 3072,
32
  "label2id": {
33
- "AMB": 14,
34
- "MIX": 13,
35
- "NE": 11,
36
- "OTHER": 12,
37
- "ar": 3,
38
- "de": 6,
 
 
 
 
 
 
39
  "en": 0,
40
  "es": 1,
41
- "fr": 5,
42
- "hi": 2,
43
- "ne": 4,
44
- "sw": 9,
45
- "tl": 8,
46
- "tr": 7,
47
- "ur": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  },
49
  "layer_norm_eps": 1e-05,
50
  "max_position_embeddings": 514,
 
13
  "id2label": {
14
  "0": "en",
15
  "1": "es",
16
+ "2": "fr",
17
+ "3": "de",
18
+ "4": "pt",
19
+ "5": "it",
20
+ "6": "nl",
21
+ "7": "pl",
22
+ "8": "ro",
23
+ "9": "sv",
24
+ "10": "no",
25
+ "11": "da",
26
+ "12": "fi",
27
+ "13": "cs",
28
+ "14": "sk",
29
+ "15": "hu",
30
+ "16": "hr",
31
+ "17": "ca",
32
+ "18": "tr",
33
+ "19": "id",
34
+ "20": "ms",
35
+ "21": "tl",
36
+ "22": "sw",
37
+ "23": "vi",
38
+ "24": "af",
39
+ "25": "ar",
40
+ "26": "fa",
41
+ "27": "ur",
42
+ "28": "hi",
43
+ "29": "ur-Latn",
44
+ "30": "bn",
45
+ "31": "ta",
46
+ "32": "te",
47
+ "33": "ml",
48
+ "34": "mr",
49
+ "35": "gu",
50
+ "36": "kn",
51
+ "37": "pa",
52
+ "38": "ne",
53
+ "39": "si",
54
+ "40": "ru",
55
+ "41": "uk",
56
+ "42": "bg",
57
+ "43": "sr",
58
+ "44": "zh",
59
+ "45": "ja",
60
+ "46": "ko",
61
+ "47": "NE",
62
+ "48": "OTHER",
63
+ "49": "MIX",
64
+ "50": "AMB"
65
  },
66
  "initializer_range": 0.02,
67
  "intermediate_size": 3072,
68
  "label2id": {
69
+ "AMB": 50,
70
+ "MIX": 49,
71
+ "NE": 47,
72
+ "OTHER": 48,
73
+ "af": 24,
74
+ "ar": 25,
75
+ "bg": 42,
76
+ "bn": 30,
77
+ "ca": 17,
78
+ "cs": 13,
79
+ "da": 11,
80
+ "de": 3,
81
  "en": 0,
82
  "es": 1,
83
+ "fa": 26,
84
+ "fi": 12,
85
+ "fr": 2,
86
+ "gu": 35,
87
+ "hi": 28,
88
+ "hr": 16,
89
+ "hu": 15,
90
+ "id": 19,
91
+ "it": 5,
92
+ "ja": 45,
93
+ "kn": 36,
94
+ "ko": 46,
95
+ "ml": 33,
96
+ "mr": 34,
97
+ "ms": 20,
98
+ "ne": 38,
99
+ "nl": 6,
100
+ "no": 10,
101
+ "pa": 37,
102
+ "pl": 7,
103
+ "pt": 4,
104
+ "ro": 8,
105
+ "ru": 40,
106
+ "si": 39,
107
+ "sk": 14,
108
+ "sr": 43,
109
+ "sv": 9,
110
+ "sw": 22,
111
+ "ta": 31,
112
+ "te": 32,
113
+ "tl": 21,
114
+ "tr": 18,
115
+ "uk": 41,
116
+ "ur": 27,
117
+ "ur-Latn": 29,
118
+ "vi": 23,
119
+ "zh": 44
120
  },
121
  "layer_norm_eps": 1e-05,
122
  "max_position_embeddings": 514,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66cea55c23f43813c4a6885bbf060034057b6dcb444cb77ec07b15d3085fae93
3
- size 1109882412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed5cd20ab2b2426f519e968656223cc7e67ceb0b514713da980c416aef1f7b0c
3
+ size 1109993156
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1afa441a3e130c27573258fd49889505712512d136086905e56e2f61d9db87
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e7a3220ca7223cdb4ccf2af46c36b3dcfec231ffeae845e02215ab33c77d7b8
3
  size 5841