Hugging Face's logo

tmtryggingar
/
payment-codes-classifier-dev

Text Classification
Transformers
ONNX
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
asibasi25 commited on
Commit
4abe28d
·
verified ·
1 Parent(s): 389c14b

Training complete

Browse files
Files changed (16) hide show
  1. README.md +67 -0
  2. config.json +115 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. onnx/config.json +147 -0
  6. onnx/merges.txt +0 -0
  7. onnx/model.onnx +3 -0
  8. onnx/special_tokens_map.json +51 -0
  9. onnx/tokenizer.json +0 -0
  10. onnx/tokenizer_config.json +58 -0
  11. onnx/vocab.json +0 -0
  12. special_tokens_map.json +51 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +58 -0
  15. training_args.bin +3 -0
  16. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-4.0
4
+ base_model: mideind/IceBERT-large
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - f1
10
+ model-index:
11
+ - name: payment-codes-classifier-dev
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # payment-codes-classifier-dev
19
+
20
+ This model is a fine-tuned version of [mideind/IceBERT-large](https://huggingface.co/mideind/IceBERT-large) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0475
23
+ - Accuracy: 0.9795
24
+ - F1: 0.9777
25
+
26
+ ## Model description
27
+
28
+ More information needed
29
+
30
+ ## Intended uses & limitations
31
+
32
+ More information needed
33
+
34
+ ## Training and evaluation data
35
+
36
+ More information needed
37
+
38
+ ## Training procedure
39
+
40
+ ### Training hyperparameters
41
+
42
+ The following hyperparameters were used during training:
43
+ - learning_rate: 3e-05
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
+ - seed: 42
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_ratio: 0.06
50
+ - num_epochs: 4
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
56
+ | 0.1007 | 1.0 | 1413 | 0.0601 | 0.9728 | 0.9654 |
57
+ | 0.0494 | 2.0 | 2826 | 0.0715 | 0.9710 | 0.9643 |
58
+ | 0.0316 | 3.0 | 4239 | 0.0549 | 0.9759 | 0.9718 |
59
+ | 0.0141 | 4.0 | 5652 | 0.0540 | 0.9791 | 0.9769 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.55.4
65
+ - Pytorch 2.8.0
66
+ - Datasets 4.3.0
67
+ - Tokenizers 0.21.4
config.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "AKS",
15
+ "1": "VIN-02",
16
+ "2": "EFV",
17
+ "3": "F\u00d6R",
18
+ "4": "GLE",
19
+ "5": "MEP",
20
+ "6": "T\u00c6K",
21
+ "7": "EFN",
22
+ "8": "EIG",
23
+ "9": "M\u00c1L",
24
+ "10": "PLA",
25
+ "11": "R\u00c9T",
26
+ "12": "RY\u00d0",
27
+ "13": "VAR",
28
+ "14": "VIN",
29
+ "15": "FRA",
30
+ "16": "\u00cdSE",
31
+ "17": "L\u00c6K",
32
+ "18": "FLU",
33
+ "19": "VI\u00d0",
34
+ "20": "BIG",
35
+ "21": "UBK",
36
+ "22": "B\u00cdL",
37
+ "23": "FRA-02",
38
+ "24": "TJ\u00d3",
39
+ "25": "SAM",
40
+ "26": "ANN",
41
+ "27": "RIT",
42
+ "28": "\u00d6RM",
43
+ "29": "GEY",
44
+ "30": "SAB",
45
+ "31": "VNT",
46
+ "32": "\u00daRS",
47
+ "33": "TRY",
48
+ "34": "END-01",
49
+ "35": "KIL",
50
+ "36": "AFT",
51
+ "37": "MUN",
52
+ "38": "HJ\u00d3",
53
+ "39": "S\u00c1L",
54
+ "40": "SAL",
55
+ "41": "UMV"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "label2id": {
60
+ "AFT": 36,
61
+ "AKS": 0,
62
+ "ANN": 26,
63
+ "BIG": 20,
64
+ "B\u00cdL": 22,
65
+ "EFN": 7,
66
+ "EFV": 2,
67
+ "EIG": 8,
68
+ "END-01": 34,
69
+ "FLU": 18,
70
+ "FRA": 15,
71
+ "FRA-02": 23,
72
+ "F\u00d6R": 3,
73
+ "GEY": 29,
74
+ "GLE": 4,
75
+ "HJ\u00d3": 38,
76
+ "KIL": 35,
77
+ "L\u00c6K": 17,
78
+ "MEP": 5,
79
+ "MUN": 37,
80
+ "M\u00c1L": 9,
81
+ "PLA": 10,
82
+ "RIT": 27,
83
+ "RY\u00d0": 12,
84
+ "R\u00c9T": 11,
85
+ "SAB": 30,
86
+ "SAL": 40,
87
+ "SAM": 25,
88
+ "S\u00c1L": 39,
89
+ "TJ\u00d3": 24,
90
+ "TRY": 33,
91
+ "T\u00c6K": 6,
92
+ "UBK": 21,
93
+ "UMV": 41,
94
+ "VAR": 13,
95
+ "VIN": 14,
96
+ "VIN-02": 1,
97
+ "VI\u00d0": 19,
98
+ "VNT": 31,
99
+ "\u00cdSE": 16,
100
+ "\u00d6RM": 28,
101
+ "\u00daRS": 32
102
+ },
103
+ "layer_norm_eps": 1e-05,
104
+ "max_position_embeddings": 514,
105
+ "model_type": "roberta",
106
+ "num_attention_heads": 16,
107
+ "num_hidden_layers": 24,
108
+ "pad_token_id": 1,
109
+ "position_embedding_type": "absolute",
110
+ "torch_dtype": "float32",
111
+ "transformers_version": "4.55.4",
112
+ "type_vocab_size": 1,
113
+ "use_cache": true,
114
+ "vocab_size": 50000
115
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdee2a2424057e7072109ba3b08736990775a89a9ef1a49ebabc5b0d195014f6
3
+ size 1420573976
onnx/config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "AKS",
15
+ "1": "EFN",
16
+ "2": "M\u00c1L",
17
+ "3": "PLA",
18
+ "4": "VIN",
19
+ "5": "R\u00c9T",
20
+ "6": "RY\u00d0",
21
+ "7": "VAR",
22
+ "8": "EIG",
23
+ "9": "VIN-02",
24
+ "10": "L\u00c6K",
25
+ "11": "AFT",
26
+ "12": "RIT",
27
+ "13": "\u00d6RM",
28
+ "14": "ANN",
29
+ "15": "FLU",
30
+ "16": "GEY",
31
+ "17": "FRA",
32
+ "18": "\u00cdSE",
33
+ "19": "FRA-02",
34
+ "20": "\u00cdSA",
35
+ "21": "VI\u00d0",
36
+ "22": "B\u00cdL",
37
+ "23": "\u00daRS",
38
+ "24": "L\u00c6K-04",
39
+ "25": "SAM",
40
+ "26": "F\u00d6R",
41
+ "27": "BIG",
42
+ "28": "UBK",
43
+ "29": "TJ\u00d3",
44
+ "30": "\u00daTL",
45
+ "31": "GLE",
46
+ "32": "MEP",
47
+ "33": "EFV",
48
+ "34": "T\u00c6K",
49
+ "35": "AUG",
50
+ "36": "SAB",
51
+ "37": "\u00deRI",
52
+ "38": "KAU",
53
+ "39": "LEI",
54
+ "40": "L\u00d6G",
55
+ "41": "V\u00c9L",
56
+ "42": "END",
57
+ "43": "END-01",
58
+ "44": "SJ\u00da",
59
+ "45": "END-03",
60
+ "46": "SKO",
61
+ "47": "MAT",
62
+ "48": "HRE",
63
+ "49": "RAR",
64
+ "50": "VNT",
65
+ "51": "TRY",
66
+ "52": "KIL",
67
+ "53": "MUN",
68
+ "54": "HJ\u00d3",
69
+ "55": "S\u00c1L",
70
+ "56": "SAL",
71
+ "57": "UMV"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 4096,
75
+ "label2id": {
76
+ "AFT": 11,
77
+ "AKS": 0,
78
+ "ANN": 14,
79
+ "AUG": 35,
80
+ "BIG": 27,
81
+ "B\u00cdL": 22,
82
+ "EFN": 1,
83
+ "EFV": 33,
84
+ "EIG": 8,
85
+ "END": 42,
86
+ "END-01": 43,
87
+ "END-03": 45,
88
+ "FLU": 15,
89
+ "FRA": 17,
90
+ "FRA-02": 19,
91
+ "F\u00d6R": 26,
92
+ "GEY": 16,
93
+ "GLE": 31,
94
+ "HJ\u00d3": 54,
95
+ "HRE": 48,
96
+ "KAU": 38,
97
+ "KIL": 52,
98
+ "LEI": 39,
99
+ "L\u00c6K": 10,
100
+ "L\u00c6K-04": 24,
101
+ "L\u00d6G": 40,
102
+ "MAT": 47,
103
+ "MEP": 32,
104
+ "MUN": 53,
105
+ "M\u00c1L": 2,
106
+ "PLA": 3,
107
+ "RAR": 49,
108
+ "RIT": 12,
109
+ "RY\u00d0": 6,
110
+ "R\u00c9T": 5,
111
+ "SAB": 36,
112
+ "SAL": 56,
113
+ "SAM": 25,
114
+ "SJ\u00da": 44,
115
+ "SKO": 46,
116
+ "S\u00c1L": 55,
117
+ "TJ\u00d3": 29,
118
+ "TRY": 51,
119
+ "T\u00c6K": 34,
120
+ "UBK": 28,
121
+ "UMV": 57,
122
+ "VAR": 7,
123
+ "VIN": 4,
124
+ "VIN-02": 9,
125
+ "VI\u00d0": 21,
126
+ "VNT": 50,
127
+ "V\u00c9L": 41,
128
+ "\u00cdSA": 20,
129
+ "\u00cdSE": 18,
130
+ "\u00d6RM": 13,
131
+ "\u00daRS": 23,
132
+ "\u00daTL": 30,
133
+ "\u00deRI": 37
134
+ },
135
+ "layer_norm_eps": 1e-05,
136
+ "max_position_embeddings": 514,
137
+ "model_type": "roberta",
138
+ "num_attention_heads": 16,
139
+ "num_hidden_layers": 24,
140
+ "pad_token_id": 1,
141
+ "position_embedding_type": "absolute",
142
+ "torch_dtype": "float32",
143
+ "transformers_version": "4.55.4",
144
+ "type_vocab_size": 1,
145
+ "use_cache": true,
146
+ "vocab_size": 50000
147
+ }
onnx/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caca61d3f0d888346bc6387482f96f3bffbd7842b55b1b52a70d202975f32f64
3
+ size 1421025770
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
onnx/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44a2cab0381b7208445b81419a484b4591c759e748e7a396db7c7a2a40fcdab6
3
+ size 5841
vocab.json ADDED
The diff for this file is too large to render. See raw diff