vedantjumle commited on
Commit
6649878
1 Parent(s): c595fa7

Training in progress epoch 0

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: roberta-base
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: vedantjumle/roberta-clinc150-1
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
12
+ probably proofread and complete it, then remove this comment. -->
13
+
14
+ # vedantjumle/roberta-clinc150-1
15
+
16
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 3.0163
19
+ - Validation Loss: 1.0789
20
+ - Train Accuracy: 0.9396
21
+ - Epoch: 0
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 12640, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
41
+ - training_precision: float32
42
+
43
+ ### Training results
44
+
45
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
+ |:----------:|:---------------:|:--------------:|:-----:|
47
+ | 3.0163 | 1.0789 | 0.9396 | 0 |
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.34.0
53
+ - TensorFlow 2.13.0
54
+ - Datasets 2.14.5
55
+ - Tokenizers 0.14.1
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<mask>": 50264,
4
+ "<pad>": 1,
5
+ "<s>": 0,
6
+ "<unk>": 3
7
+ }
config.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.2,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10",
25
+ "11": "LABEL_11",
26
+ "12": "LABEL_12",
27
+ "13": "LABEL_13",
28
+ "14": "LABEL_14",
29
+ "15": "LABEL_15",
30
+ "16": "LABEL_16",
31
+ "17": "LABEL_17",
32
+ "18": "LABEL_18",
33
+ "19": "LABEL_19",
34
+ "20": "LABEL_20",
35
+ "21": "LABEL_21",
36
+ "22": "LABEL_22",
37
+ "23": "LABEL_23",
38
+ "24": "LABEL_24",
39
+ "25": "LABEL_25",
40
+ "26": "LABEL_26",
41
+ "27": "LABEL_27",
42
+ "28": "LABEL_28",
43
+ "29": "LABEL_29",
44
+ "30": "LABEL_30",
45
+ "31": "LABEL_31",
46
+ "32": "LABEL_32",
47
+ "33": "LABEL_33",
48
+ "34": "LABEL_34",
49
+ "35": "LABEL_35",
50
+ "36": "LABEL_36",
51
+ "37": "LABEL_37",
52
+ "38": "LABEL_38",
53
+ "39": "LABEL_39",
54
+ "40": "LABEL_40",
55
+ "41": "LABEL_41",
56
+ "42": "LABEL_42",
57
+ "43": "LABEL_43",
58
+ "44": "LABEL_44",
59
+ "45": "LABEL_45",
60
+ "46": "LABEL_46",
61
+ "47": "LABEL_47",
62
+ "48": "LABEL_48",
63
+ "49": "LABEL_49",
64
+ "50": "LABEL_50",
65
+ "51": "LABEL_51",
66
+ "52": "LABEL_52",
67
+ "53": "LABEL_53",
68
+ "54": "LABEL_54",
69
+ "55": "LABEL_55",
70
+ "56": "LABEL_56",
71
+ "57": "LABEL_57",
72
+ "58": "LABEL_58",
73
+ "59": "LABEL_59",
74
+ "60": "LABEL_60",
75
+ "61": "LABEL_61",
76
+ "62": "LABEL_62",
77
+ "63": "LABEL_63",
78
+ "64": "LABEL_64",
79
+ "65": "LABEL_65",
80
+ "66": "LABEL_66",
81
+ "67": "LABEL_67",
82
+ "68": "LABEL_68",
83
+ "69": "LABEL_69",
84
+ "70": "LABEL_70",
85
+ "71": "LABEL_71",
86
+ "72": "LABEL_72",
87
+ "73": "LABEL_73",
88
+ "74": "LABEL_74",
89
+ "75": "LABEL_75",
90
+ "76": "LABEL_76",
91
+ "77": "LABEL_77",
92
+ "78": "LABEL_78",
93
+ "79": "LABEL_79",
94
+ "80": "LABEL_80",
95
+ "81": "LABEL_81",
96
+ "82": "LABEL_82",
97
+ "83": "LABEL_83",
98
+ "84": "LABEL_84",
99
+ "85": "LABEL_85",
100
+ "86": "LABEL_86",
101
+ "87": "LABEL_87",
102
+ "88": "LABEL_88",
103
+ "89": "LABEL_89",
104
+ "90": "LABEL_90",
105
+ "91": "LABEL_91",
106
+ "92": "LABEL_92",
107
+ "93": "LABEL_93",
108
+ "94": "LABEL_94",
109
+ "95": "LABEL_95",
110
+ "96": "LABEL_96",
111
+ "97": "LABEL_97",
112
+ "98": "LABEL_98",
113
+ "99": "LABEL_99",
114
+ "100": "LABEL_100",
115
+ "101": "LABEL_101",
116
+ "102": "LABEL_102",
117
+ "103": "LABEL_103",
118
+ "104": "LABEL_104",
119
+ "105": "LABEL_105",
120
+ "106": "LABEL_106",
121
+ "107": "LABEL_107",
122
+ "108": "LABEL_108",
123
+ "109": "LABEL_109",
124
+ "110": "LABEL_110",
125
+ "111": "LABEL_111",
126
+ "112": "LABEL_112",
127
+ "113": "LABEL_113",
128
+ "114": "LABEL_114",
129
+ "115": "LABEL_115",
130
+ "116": "LABEL_116",
131
+ "117": "LABEL_117",
132
+ "118": "LABEL_118",
133
+ "119": "LABEL_119",
134
+ "120": "LABEL_120",
135
+ "121": "LABEL_121",
136
+ "122": "LABEL_122",
137
+ "123": "LABEL_123",
138
+ "124": "LABEL_124",
139
+ "125": "LABEL_125",
140
+ "126": "LABEL_126",
141
+ "127": "LABEL_127",
142
+ "128": "LABEL_128",
143
+ "129": "LABEL_129",
144
+ "130": "LABEL_130",
145
+ "131": "LABEL_131",
146
+ "132": "LABEL_132",
147
+ "133": "LABEL_133",
148
+ "134": "LABEL_134",
149
+ "135": "LABEL_135",
150
+ "136": "LABEL_136",
151
+ "137": "LABEL_137",
152
+ "138": "LABEL_138",
153
+ "139": "LABEL_139",
154
+ "140": "LABEL_140",
155
+ "141": "LABEL_141",
156
+ "142": "LABEL_142",
157
+ "143": "LABEL_143",
158
+ "144": "LABEL_144",
159
+ "145": "LABEL_145",
160
+ "146": "LABEL_146",
161
+ "147": "LABEL_147",
162
+ "148": "LABEL_148",
163
+ "149": "LABEL_149"
164
+ },
165
+ "initializer_range": 0.02,
166
+ "intermediate_size": 3072,
167
+ "label2id": {
168
+ "LABEL_0": 0,
169
+ "LABEL_1": 1,
170
+ "LABEL_10": 10,
171
+ "LABEL_100": 100,
172
+ "LABEL_101": 101,
173
+ "LABEL_102": 102,
174
+ "LABEL_103": 103,
175
+ "LABEL_104": 104,
176
+ "LABEL_105": 105,
177
+ "LABEL_106": 106,
178
+ "LABEL_107": 107,
179
+ "LABEL_108": 108,
180
+ "LABEL_109": 109,
181
+ "LABEL_11": 11,
182
+ "LABEL_110": 110,
183
+ "LABEL_111": 111,
184
+ "LABEL_112": 112,
185
+ "LABEL_113": 113,
186
+ "LABEL_114": 114,
187
+ "LABEL_115": 115,
188
+ "LABEL_116": 116,
189
+ "LABEL_117": 117,
190
+ "LABEL_118": 118,
191
+ "LABEL_119": 119,
192
+ "LABEL_12": 12,
193
+ "LABEL_120": 120,
194
+ "LABEL_121": 121,
195
+ "LABEL_122": 122,
196
+ "LABEL_123": 123,
197
+ "LABEL_124": 124,
198
+ "LABEL_125": 125,
199
+ "LABEL_126": 126,
200
+ "LABEL_127": 127,
201
+ "LABEL_128": 128,
202
+ "LABEL_129": 129,
203
+ "LABEL_13": 13,
204
+ "LABEL_130": 130,
205
+ "LABEL_131": 131,
206
+ "LABEL_132": 132,
207
+ "LABEL_133": 133,
208
+ "LABEL_134": 134,
209
+ "LABEL_135": 135,
210
+ "LABEL_136": 136,
211
+ "LABEL_137": 137,
212
+ "LABEL_138": 138,
213
+ "LABEL_139": 139,
214
+ "LABEL_14": 14,
215
+ "LABEL_140": 140,
216
+ "LABEL_141": 141,
217
+ "LABEL_142": 142,
218
+ "LABEL_143": 143,
219
+ "LABEL_144": 144,
220
+ "LABEL_145": 145,
221
+ "LABEL_146": 146,
222
+ "LABEL_147": 147,
223
+ "LABEL_148": 148,
224
+ "LABEL_149": 149,
225
+ "LABEL_15": 15,
226
+ "LABEL_16": 16,
227
+ "LABEL_17": 17,
228
+ "LABEL_18": 18,
229
+ "LABEL_19": 19,
230
+ "LABEL_2": 2,
231
+ "LABEL_20": 20,
232
+ "LABEL_21": 21,
233
+ "LABEL_22": 22,
234
+ "LABEL_23": 23,
235
+ "LABEL_24": 24,
236
+ "LABEL_25": 25,
237
+ "LABEL_26": 26,
238
+ "LABEL_27": 27,
239
+ "LABEL_28": 28,
240
+ "LABEL_29": 29,
241
+ "LABEL_3": 3,
242
+ "LABEL_30": 30,
243
+ "LABEL_31": 31,
244
+ "LABEL_32": 32,
245
+ "LABEL_33": 33,
246
+ "LABEL_34": 34,
247
+ "LABEL_35": 35,
248
+ "LABEL_36": 36,
249
+ "LABEL_37": 37,
250
+ "LABEL_38": 38,
251
+ "LABEL_39": 39,
252
+ "LABEL_4": 4,
253
+ "LABEL_40": 40,
254
+ "LABEL_41": 41,
255
+ "LABEL_42": 42,
256
+ "LABEL_43": 43,
257
+ "LABEL_44": 44,
258
+ "LABEL_45": 45,
259
+ "LABEL_46": 46,
260
+ "LABEL_47": 47,
261
+ "LABEL_48": 48,
262
+ "LABEL_49": 49,
263
+ "LABEL_5": 5,
264
+ "LABEL_50": 50,
265
+ "LABEL_51": 51,
266
+ "LABEL_52": 52,
267
+ "LABEL_53": 53,
268
+ "LABEL_54": 54,
269
+ "LABEL_55": 55,
270
+ "LABEL_56": 56,
271
+ "LABEL_57": 57,
272
+ "LABEL_58": 58,
273
+ "LABEL_59": 59,
274
+ "LABEL_6": 6,
275
+ "LABEL_60": 60,
276
+ "LABEL_61": 61,
277
+ "LABEL_62": 62,
278
+ "LABEL_63": 63,
279
+ "LABEL_64": 64,
280
+ "LABEL_65": 65,
281
+ "LABEL_66": 66,
282
+ "LABEL_67": 67,
283
+ "LABEL_68": 68,
284
+ "LABEL_69": 69,
285
+ "LABEL_7": 7,
286
+ "LABEL_70": 70,
287
+ "LABEL_71": 71,
288
+ "LABEL_72": 72,
289
+ "LABEL_73": 73,
290
+ "LABEL_74": 74,
291
+ "LABEL_75": 75,
292
+ "LABEL_76": 76,
293
+ "LABEL_77": 77,
294
+ "LABEL_78": 78,
295
+ "LABEL_79": 79,
296
+ "LABEL_8": 8,
297
+ "LABEL_80": 80,
298
+ "LABEL_81": 81,
299
+ "LABEL_82": 82,
300
+ "LABEL_83": 83,
301
+ "LABEL_84": 84,
302
+ "LABEL_85": 85,
303
+ "LABEL_86": 86,
304
+ "LABEL_87": 87,
305
+ "LABEL_88": 88,
306
+ "LABEL_89": 89,
307
+ "LABEL_9": 9,
308
+ "LABEL_90": 90,
309
+ "LABEL_91": 91,
310
+ "LABEL_92": 92,
311
+ "LABEL_93": 93,
312
+ "LABEL_94": 94,
313
+ "LABEL_95": 95,
314
+ "LABEL_96": 96,
315
+ "LABEL_97": 97,
316
+ "LABEL_98": 98,
317
+ "LABEL_99": 99
318
+ },
319
+ "layer_norm_eps": 1e-05,
320
+ "max_position_embeddings": 514,
321
+ "model_type": "roberta",
322
+ "num_attention_heads": 12,
323
+ "num_hidden_layers": 12,
324
+ "pad_token_id": 1,
325
+ "position_embedding_type": "absolute",
326
+ "transformers_version": "4.34.0",
327
+ "type_vocab_size": 1,
328
+ "use_cache": true,
329
+ "vocab_size": 50265
330
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e308ed1018fe1bdd7cab83f30e822f8e5b1889fabfdbe0f8cfa9599dbb5b5099
3
+ size 499332928
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": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [],
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff