vedantjumle commited on
Commit
7cfe156
·
1 Parent(s): 1a34dcd

Training in progress epoch 0

Browse files
Files changed (6) hide show
  1. README.md +7 -9
  2. added_tokens.json +7 -0
  3. config.json +122 -302
  4. tf_model.h5 +2 -2
  5. tokenizer.json +6 -1
  6. tokenizer_config.json +43 -0
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- license: apache-2.0
3
- base_model: distilbert-base-uncased
4
  tags:
5
  - generated_from_keras_callback
6
  model-index:
@@ -13,11 +11,11 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  # vedantjumle/indo-ml-final-test-bert
15
 
16
- This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.0932
19
- - Validation Loss: 0.5714
20
- - Train Accuracy: 0.8533
21
  - Epoch: 0
22
 
23
  ## Model description
@@ -44,12 +42,12 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
  |:----------:|:---------------:|:--------------:|:-----:|
47
- | 0.0932 | 0.5714 | 0.8533 | 0 |
48
 
49
 
50
  ### Framework versions
51
 
52
- - Transformers 4.33.2
53
  - TensorFlow 2.13.0
54
  - Datasets 2.14.5
55
- - Tokenizers 0.13.3
 
1
  ---
 
 
2
  tags:
3
  - generated_from_keras_callback
4
  model-index:
 
11
 
12
  # vedantjumle/indo-ml-final-test-bert
13
 
14
+ This model was trained from scratch on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: nan
17
+ - Validation Loss: nan
18
+ - Train Accuracy: 0.0067
19
  - Epoch: 0
20
 
21
  ## Model description
 
42
 
43
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
44
  |:----------:|:---------------:|:--------------:|:-----:|
45
+ | nan | nan | 0.0067 | 0 |
46
 
47
 
48
  ### Framework versions
49
 
50
+ - Transformers 4.34.0
51
  - TensorFlow 2.13.0
52
  - Datasets 2.14.5
53
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
@@ -9,309 +9,129 @@
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
- "accept reservations": 0,
13
- "account blocked": 1,
14
- "alarm": 2,
15
- "application status": 3,
16
- "apr": 4,
17
- "are you a bot": 5,
18
- "balance": 6,
19
- "bill balance": 7,
20
- "bill due": 8,
21
- "book flight": 9,
22
- "book hotel": 10,
23
- "calculator": 11,
24
- "calendar": 12,
25
- "calendar update": 13,
26
- "calories": 14,
27
- "cancel": 15,
28
- "cancel reservation": 16,
29
- "car rental": 17,
30
- "card declined": 18,
31
- "carry on": 19,
32
- "change accent": 20,
33
- "change ai name": 21,
34
- "change language": 22,
35
- "change speed": 23,
36
- "change user name": 24,
37
- "change volume": 25,
38
- "confirm reservation": 26,
39
- "cook time": 27,
40
- "credit limit": 28,
41
- "credit limit change": 29,
42
- "credit score": 30,
43
- "current location": 31,
44
- "damaged card": 32,
45
- "date": 33,
46
- "definition": 34,
47
- "direct deposit": 35,
48
- "directions": 36,
49
- "distance": 37,
50
- "do you have pets": 38,
51
- "exchange rate": 39,
52
- "expiration date": 40,
53
- "find phone": 41,
54
- "flight status": 42,
55
- "flip coin": 43,
56
- "food last": 44,
57
- "freeze account": 45,
58
- "fun fact": 46,
59
- "gas": 47,
60
- "gas type": 48,
61
- "goodbye": 49,
62
- "greeting": 50,
63
- "how busy": 51,
64
- "how old are you": 52,
65
- "improve credit score": 53,
66
- "income": 54,
67
- "ingredient substitution": 55,
68
- "ingredients list": 56,
69
- "insurance": 57,
70
- "insurance change": 58,
71
- "interest rate": 59,
72
- "international fees": 60,
73
- "international visa": 61,
74
- "jump start": 62,
75
- "last maintenance": 63,
76
- "lost luggage": 64,
77
- "make call": 65,
78
- "maybe": 66,
79
- "meal suggestion": 67,
80
- "meaning of life": 68,
81
- "measurement conversion": 69,
82
- "meeting schedule": 70,
83
- "min payment": 71,
84
- "mpg": 72,
85
- "new card": 73,
86
- "next holiday": 74,
87
- "next song": 75,
88
- "no": 76,
89
- "nutrition info": 77,
90
- "oil change how": 78,
91
- "oil change when": 79,
92
- "order": 80,
93
- "order checks": 81,
94
- "order status": 82,
95
- "pay bill": 83,
96
- "payday": 84,
97
- "pin change": 85,
98
- "play music": 86,
99
- "plug type": 87,
100
- "pto balance": 88,
101
- "pto request": 89,
102
- "pto request status": 90,
103
- "pto used": 91,
104
- "recipe": 92,
105
- "redeem rewards": 93,
106
- "reminder": 94,
107
- "reminder update": 95,
108
- "repeat": 96,
109
- "replacement card duration": 97,
110
- "report fraud": 98,
111
- "report lost card": 99,
112
- "reset settings": 100,
113
- "restaurant reservation": 101,
114
- "restaurant reviews": 102,
115
- "restaurant suggestion": 103,
116
- "rewards balance": 104,
117
- "roll dice": 105,
118
- "rollover 401k": 106,
119
- "routing": 107,
120
- "schedule maintenance": 108,
121
- "schedule meeting": 109,
122
- "share location": 110,
123
- "shopping list": 111,
124
- "shopping list update": 112,
125
- "smart home": 113,
126
- "spelling": 114,
127
- "spending history": 115,
128
- "sync device": 116,
129
- "taxes": 117,
130
- "tell joke": 118,
131
- "text": 119,
132
- "thank you": 120,
133
- "time": 121,
134
- "timer": 122,
135
- "timezone": 123,
136
- "tire change": 124,
137
- "tire pressure": 125,
138
- "todo list": 126,
139
- "todo list update": 127,
140
- "traffic": 128,
141
- "transactions": 129,
142
- "transfer": 130,
143
- "translate": 131,
144
- "travel alert": 132,
145
- "travel notification": 133,
146
- "travel suggestion": 134,
147
- "uber": 135,
148
- "update playlist": 136,
149
- "user name": 137,
150
- "vaccines": 138,
151
- "w2": 139,
152
- "weather": 140,
153
- "what are your hobbies": 141,
154
- "what can i ask you": 142,
155
- "what is your name": 143,
156
- "what song": 144,
157
- "where are you from": 145,
158
- "whisper mode": 146,
159
- "who do you work for": 147,
160
- "who made you": 148,
161
- "yes": 149
162
  },
163
  "initializer_range": 0.02,
164
  "label2id": {
165
- "0": "accept reservations",
166
- "1": "account blocked",
167
- "2": "alarm",
168
- "3": "application status",
169
- "4": "apr",
170
- "5": "are you a bot",
171
- "6": "balance",
172
- "7": "bill balance",
173
- "8": "bill due",
174
- "9": "book flight",
175
- "10": "book hotel",
176
- "11": "calculator",
177
- "12": "calendar",
178
- "13": "calendar update",
179
- "14": "calories",
180
- "15": "cancel",
181
- "16": "cancel reservation",
182
- "17": "car rental",
183
- "18": "card declined",
184
- "19": "carry on",
185
- "20": "change accent",
186
- "21": "change ai name",
187
- "22": "change language",
188
- "23": "change speed",
189
- "24": "change user name",
190
- "25": "change volume",
191
- "26": "confirm reservation",
192
- "27": "cook time",
193
- "28": "credit limit",
194
- "29": "credit limit change",
195
- "30": "credit score",
196
- "31": "current location",
197
- "32": "damaged card",
198
- "33": "date",
199
- "34": "definition",
200
- "35": "direct deposit",
201
- "36": "directions",
202
- "37": "distance",
203
- "38": "do you have pets",
204
- "39": "exchange rate",
205
- "40": "expiration date",
206
- "41": "find phone",
207
- "42": "flight status",
208
- "43": "flip coin",
209
- "44": "food last",
210
- "45": "freeze account",
211
- "46": "fun fact",
212
- "47": "gas",
213
- "48": "gas type",
214
- "49": "goodbye",
215
- "50": "greeting",
216
- "51": "how busy",
217
- "52": "how old are you",
218
- "53": "improve credit score",
219
- "54": "income",
220
- "55": "ingredient substitution",
221
- "56": "ingredients list",
222
- "57": "insurance",
223
- "58": "insurance change",
224
- "59": "interest rate",
225
- "60": "international fees",
226
- "61": "international visa",
227
- "62": "jump start",
228
- "63": "last maintenance",
229
- "64": "lost luggage",
230
- "65": "make call",
231
- "66": "maybe",
232
- "67": "meal suggestion",
233
- "68": "meaning of life",
234
- "69": "measurement conversion",
235
- "70": "meeting schedule",
236
- "71": "min payment",
237
- "72": "mpg",
238
- "73": "new card",
239
- "74": "next holiday",
240
- "75": "next song",
241
- "76": "no",
242
- "77": "nutrition info",
243
- "78": "oil change how",
244
- "79": "oil change when",
245
- "80": "order",
246
- "81": "order checks",
247
- "82": "order status",
248
- "83": "pay bill",
249
- "84": "payday",
250
- "85": "pin change",
251
- "86": "play music",
252
- "87": "plug type",
253
- "88": "pto balance",
254
- "89": "pto request",
255
- "90": "pto request status",
256
- "91": "pto used",
257
- "92": "recipe",
258
- "93": "redeem rewards",
259
- "94": "reminder",
260
- "95": "reminder update",
261
- "96": "repeat",
262
- "97": "replacement card duration",
263
- "98": "report fraud",
264
- "99": "report lost card",
265
- "100": "reset settings",
266
- "101": "restaurant reservation",
267
- "102": "restaurant reviews",
268
- "103": "restaurant suggestion",
269
- "104": "rewards balance",
270
- "105": "roll dice",
271
- "106": "rollover 401k",
272
- "107": "routing",
273
- "108": "schedule maintenance",
274
- "109": "schedule meeting",
275
- "110": "share location",
276
- "111": "shopping list",
277
- "112": "shopping list update",
278
- "113": "smart home",
279
- "114": "spelling",
280
- "115": "spending history",
281
- "116": "sync device",
282
- "117": "taxes",
283
- "118": "tell joke",
284
- "119": "text",
285
- "120": "thank you",
286
- "121": "time",
287
- "122": "timer",
288
- "123": "timezone",
289
- "124": "tire change",
290
- "125": "tire pressure",
291
- "126": "todo list",
292
- "127": "todo list update",
293
- "128": "traffic",
294
- "129": "transactions",
295
- "130": "transfer",
296
- "131": "translate",
297
- "132": "travel alert",
298
- "133": "travel notification",
299
- "134": "travel suggestion",
300
- "135": "uber",
301
- "136": "update playlist",
302
- "137": "user name",
303
- "138": "vaccines",
304
- "139": "w2",
305
- "140": "weather",
306
- "141": "what are your hobbies",
307
- "142": "what can i ask you",
308
- "143": "what is your name",
309
- "144": "what song",
310
- "145": "where are you from",
311
- "146": "whisper mode",
312
- "147": "who do you work for",
313
- "148": "who made you",
314
- "149": "yes"
315
  },
316
  "max_position_embeddings": 512,
317
  "model_type": "distilbert",
@@ -322,6 +142,6 @@
322
  "seq_classif_dropout": 0.2,
323
  "sinusoidal_pos_embds": false,
324
  "tie_weights_": true,
325
- "transformers_version": "4.33.2",
326
  "vocab_size": 30522
327
  }
 
1
  {
2
+ "_name_or_path": "./transformers-models/bert",
3
  "activation": "gelu",
4
  "architectures": [
5
  "DistilBertForSequenceClassification"
 
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
  "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20",
33
+ "21": "LABEL_21",
34
+ "22": "LABEL_22",
35
+ "23": "LABEL_23",
36
+ "24": "LABEL_24",
37
+ "25": "LABEL_25",
38
+ "26": "LABEL_26",
39
+ "27": "LABEL_27",
40
+ "28": "LABEL_28",
41
+ "29": "LABEL_29",
42
+ "30": "LABEL_30",
43
+ "31": "LABEL_31",
44
+ "32": "LABEL_32",
45
+ "33": "LABEL_33",
46
+ "34": "LABEL_34",
47
+ "35": "LABEL_35",
48
+ "36": "LABEL_36",
49
+ "37": "LABEL_37",
50
+ "38": "LABEL_38",
51
+ "39": "LABEL_39",
52
+ "40": "LABEL_40",
53
+ "41": "LABEL_41",
54
+ "42": "LABEL_42",
55
+ "43": "LABEL_43",
56
+ "44": "LABEL_44",
57
+ "45": "LABEL_45",
58
+ "46": "LABEL_46",
59
+ "47": "LABEL_47",
60
+ "48": "LABEL_48",
61
+ "49": "LABEL_49",
62
+ "50": "LABEL_50",
63
+ "51": "LABEL_51",
64
+ "52": "LABEL_52",
65
+ "53": "LABEL_53",
66
+ "54": "LABEL_54",
67
+ "55": "LABEL_55",
68
+ "56": "LABEL_56",
69
+ "57": "LABEL_57",
70
+ "58": "LABEL_58",
71
+ "59": "LABEL_59"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
  },
73
  "initializer_range": 0.02,
74
  "label2id": {
75
+ "LABEL_0": 0,
76
+ "LABEL_1": 1,
77
+ "LABEL_10": 10,
78
+ "LABEL_11": 11,
79
+ "LABEL_12": 12,
80
+ "LABEL_13": 13,
81
+ "LABEL_14": 14,
82
+ "LABEL_15": 15,
83
+ "LABEL_16": 16,
84
+ "LABEL_17": 17,
85
+ "LABEL_18": 18,
86
+ "LABEL_19": 19,
87
+ "LABEL_2": 2,
88
+ "LABEL_20": 20,
89
+ "LABEL_21": 21,
90
+ "LABEL_22": 22,
91
+ "LABEL_23": 23,
92
+ "LABEL_24": 24,
93
+ "LABEL_25": 25,
94
+ "LABEL_26": 26,
95
+ "LABEL_27": 27,
96
+ "LABEL_28": 28,
97
+ "LABEL_29": 29,
98
+ "LABEL_3": 3,
99
+ "LABEL_30": 30,
100
+ "LABEL_31": 31,
101
+ "LABEL_32": 32,
102
+ "LABEL_33": 33,
103
+ "LABEL_34": 34,
104
+ "LABEL_35": 35,
105
+ "LABEL_36": 36,
106
+ "LABEL_37": 37,
107
+ "LABEL_38": 38,
108
+ "LABEL_39": 39,
109
+ "LABEL_4": 4,
110
+ "LABEL_40": 40,
111
+ "LABEL_41": 41,
112
+ "LABEL_42": 42,
113
+ "LABEL_43": 43,
114
+ "LABEL_44": 44,
115
+ "LABEL_45": 45,
116
+ "LABEL_46": 46,
117
+ "LABEL_47": 47,
118
+ "LABEL_48": 48,
119
+ "LABEL_49": 49,
120
+ "LABEL_5": 5,
121
+ "LABEL_50": 50,
122
+ "LABEL_51": 51,
123
+ "LABEL_52": 52,
124
+ "LABEL_53": 53,
125
+ "LABEL_54": 54,
126
+ "LABEL_55": 55,
127
+ "LABEL_56": 56,
128
+ "LABEL_57": 57,
129
+ "LABEL_58": 58,
130
+ "LABEL_59": 59,
131
+ "LABEL_6": 6,
132
+ "LABEL_7": 7,
133
+ "LABEL_8": 8,
134
+ "LABEL_9": 9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  },
136
  "max_position_embeddings": 512,
137
  "model_type": "distilbert",
 
142
  "seq_classif_dropout": 0.2,
143
  "sinusoidal_pos_embds": false,
144
  "tie_weights_": true,
145
+ "transformers_version": "4.34.0",
146
  "vocab_size": 30522
147
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5342773a182ad20109ced71e7d394451feb20481bf39d01b2f5862d31c8ba87a
3
- size 268409800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d31050c82458dcccd678f88fe40acd7692d14e03cc4f39bb50ca873d3ed2c7
3
+ size 268133320
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -1,4 +1,47 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
  "do_lower_case": true,
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
  "clean_up_tokenization_spaces": true,
46
  "cls_token": "[CLS]",
47
  "do_lower_case": true,