vedantjumle commited on
Commit
67c3304
1 Parent(s): 8db596e

Training in progress epoch 0

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlnet-large-cased
4
+ tags:
5
+ - generated_from_keras_callback
6
+ model-index:
7
+ - name: vedantjumle/xlnet-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/xlnet-1
15
+
16
+ This model is a fine-tuned version of [xlnet-large-cased](https://huggingface.co/xlnet-large-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Train Loss: 5.1007
19
+ - Validation Loss: 4.9565
20
+ - Train Accuracy: 0.0133
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': 6000, '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
+ | 5.1007 | 4.9565 | 0.0133 | 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 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<cls>": 3,
4
+ "<eod>": 7,
5
+ "<eop>": 8,
6
+ "<mask>": 6,
7
+ "<pad>": 5,
8
+ "<s>": 1,
9
+ "<sep>": 4,
10
+ "<unk>": 0
11
+ }
config.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlnet-large-cased",
3
+ "architectures": [
4
+ "XLNetForSequenceClassification"
5
+ ],
6
+ "attn_type": "bi",
7
+ "bi_data": false,
8
+ "bos_token_id": 1,
9
+ "clamp_len": -1,
10
+ "d_head": 64,
11
+ "d_inner": 4096,
12
+ "d_model": 1024,
13
+ "dropout": 0.1,
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1",
20
+ "2": "LABEL_2",
21
+ "3": "LABEL_3",
22
+ "4": "LABEL_4",
23
+ "5": "LABEL_5",
24
+ "6": "LABEL_6",
25
+ "7": "LABEL_7",
26
+ "8": "LABEL_8",
27
+ "9": "LABEL_9",
28
+ "10": "LABEL_10",
29
+ "11": "LABEL_11",
30
+ "12": "LABEL_12",
31
+ "13": "LABEL_13",
32
+ "14": "LABEL_14",
33
+ "15": "LABEL_15",
34
+ "16": "LABEL_16",
35
+ "17": "LABEL_17",
36
+ "18": "LABEL_18",
37
+ "19": "LABEL_19",
38
+ "20": "LABEL_20",
39
+ "21": "LABEL_21",
40
+ "22": "LABEL_22",
41
+ "23": "LABEL_23",
42
+ "24": "LABEL_24",
43
+ "25": "LABEL_25",
44
+ "26": "LABEL_26",
45
+ "27": "LABEL_27",
46
+ "28": "LABEL_28",
47
+ "29": "LABEL_29",
48
+ "30": "LABEL_30",
49
+ "31": "LABEL_31",
50
+ "32": "LABEL_32",
51
+ "33": "LABEL_33",
52
+ "34": "LABEL_34",
53
+ "35": "LABEL_35",
54
+ "36": "LABEL_36",
55
+ "37": "LABEL_37",
56
+ "38": "LABEL_38",
57
+ "39": "LABEL_39",
58
+ "40": "LABEL_40",
59
+ "41": "LABEL_41",
60
+ "42": "LABEL_42",
61
+ "43": "LABEL_43",
62
+ "44": "LABEL_44",
63
+ "45": "LABEL_45",
64
+ "46": "LABEL_46",
65
+ "47": "LABEL_47",
66
+ "48": "LABEL_48",
67
+ "49": "LABEL_49",
68
+ "50": "LABEL_50",
69
+ "51": "LABEL_51",
70
+ "52": "LABEL_52",
71
+ "53": "LABEL_53",
72
+ "54": "LABEL_54",
73
+ "55": "LABEL_55",
74
+ "56": "LABEL_56",
75
+ "57": "LABEL_57",
76
+ "58": "LABEL_58",
77
+ "59": "LABEL_59",
78
+ "60": "LABEL_60",
79
+ "61": "LABEL_61",
80
+ "62": "LABEL_62",
81
+ "63": "LABEL_63",
82
+ "64": "LABEL_64",
83
+ "65": "LABEL_65",
84
+ "66": "LABEL_66",
85
+ "67": "LABEL_67",
86
+ "68": "LABEL_68",
87
+ "69": "LABEL_69",
88
+ "70": "LABEL_70",
89
+ "71": "LABEL_71",
90
+ "72": "LABEL_72",
91
+ "73": "LABEL_73",
92
+ "74": "LABEL_74",
93
+ "75": "LABEL_75",
94
+ "76": "LABEL_76",
95
+ "77": "LABEL_77",
96
+ "78": "LABEL_78",
97
+ "79": "LABEL_79",
98
+ "80": "LABEL_80",
99
+ "81": "LABEL_81",
100
+ "82": "LABEL_82",
101
+ "83": "LABEL_83",
102
+ "84": "LABEL_84",
103
+ "85": "LABEL_85",
104
+ "86": "LABEL_86",
105
+ "87": "LABEL_87",
106
+ "88": "LABEL_88",
107
+ "89": "LABEL_89",
108
+ "90": "LABEL_90",
109
+ "91": "LABEL_91",
110
+ "92": "LABEL_92",
111
+ "93": "LABEL_93",
112
+ "94": "LABEL_94",
113
+ "95": "LABEL_95",
114
+ "96": "LABEL_96",
115
+ "97": "LABEL_97",
116
+ "98": "LABEL_98",
117
+ "99": "LABEL_99",
118
+ "100": "LABEL_100",
119
+ "101": "LABEL_101",
120
+ "102": "LABEL_102",
121
+ "103": "LABEL_103",
122
+ "104": "LABEL_104",
123
+ "105": "LABEL_105",
124
+ "106": "LABEL_106",
125
+ "107": "LABEL_107",
126
+ "108": "LABEL_108",
127
+ "109": "LABEL_109",
128
+ "110": "LABEL_110",
129
+ "111": "LABEL_111",
130
+ "112": "LABEL_112",
131
+ "113": "LABEL_113",
132
+ "114": "LABEL_114",
133
+ "115": "LABEL_115",
134
+ "116": "LABEL_116",
135
+ "117": "LABEL_117",
136
+ "118": "LABEL_118",
137
+ "119": "LABEL_119",
138
+ "120": "LABEL_120",
139
+ "121": "LABEL_121",
140
+ "122": "LABEL_122",
141
+ "123": "LABEL_123",
142
+ "124": "LABEL_124",
143
+ "125": "LABEL_125",
144
+ "126": "LABEL_126",
145
+ "127": "LABEL_127",
146
+ "128": "LABEL_128",
147
+ "129": "LABEL_129",
148
+ "130": "LABEL_130",
149
+ "131": "LABEL_131",
150
+ "132": "LABEL_132",
151
+ "133": "LABEL_133",
152
+ "134": "LABEL_134",
153
+ "135": "LABEL_135",
154
+ "136": "LABEL_136",
155
+ "137": "LABEL_137",
156
+ "138": "LABEL_138",
157
+ "139": "LABEL_139",
158
+ "140": "LABEL_140",
159
+ "141": "LABEL_141",
160
+ "142": "LABEL_142",
161
+ "143": "LABEL_143",
162
+ "144": "LABEL_144",
163
+ "145": "LABEL_145",
164
+ "146": "LABEL_146",
165
+ "147": "LABEL_147",
166
+ "148": "LABEL_148",
167
+ "149": "LABEL_149"
168
+ },
169
+ "initializer_range": 0.02,
170
+ "label2id": {
171
+ "LABEL_0": 0,
172
+ "LABEL_1": 1,
173
+ "LABEL_10": 10,
174
+ "LABEL_100": 100,
175
+ "LABEL_101": 101,
176
+ "LABEL_102": 102,
177
+ "LABEL_103": 103,
178
+ "LABEL_104": 104,
179
+ "LABEL_105": 105,
180
+ "LABEL_106": 106,
181
+ "LABEL_107": 107,
182
+ "LABEL_108": 108,
183
+ "LABEL_109": 109,
184
+ "LABEL_11": 11,
185
+ "LABEL_110": 110,
186
+ "LABEL_111": 111,
187
+ "LABEL_112": 112,
188
+ "LABEL_113": 113,
189
+ "LABEL_114": 114,
190
+ "LABEL_115": 115,
191
+ "LABEL_116": 116,
192
+ "LABEL_117": 117,
193
+ "LABEL_118": 118,
194
+ "LABEL_119": 119,
195
+ "LABEL_12": 12,
196
+ "LABEL_120": 120,
197
+ "LABEL_121": 121,
198
+ "LABEL_122": 122,
199
+ "LABEL_123": 123,
200
+ "LABEL_124": 124,
201
+ "LABEL_125": 125,
202
+ "LABEL_126": 126,
203
+ "LABEL_127": 127,
204
+ "LABEL_128": 128,
205
+ "LABEL_129": 129,
206
+ "LABEL_13": 13,
207
+ "LABEL_130": 130,
208
+ "LABEL_131": 131,
209
+ "LABEL_132": 132,
210
+ "LABEL_133": 133,
211
+ "LABEL_134": 134,
212
+ "LABEL_135": 135,
213
+ "LABEL_136": 136,
214
+ "LABEL_137": 137,
215
+ "LABEL_138": 138,
216
+ "LABEL_139": 139,
217
+ "LABEL_14": 14,
218
+ "LABEL_140": 140,
219
+ "LABEL_141": 141,
220
+ "LABEL_142": 142,
221
+ "LABEL_143": 143,
222
+ "LABEL_144": 144,
223
+ "LABEL_145": 145,
224
+ "LABEL_146": 146,
225
+ "LABEL_147": 147,
226
+ "LABEL_148": 148,
227
+ "LABEL_149": 149,
228
+ "LABEL_15": 15,
229
+ "LABEL_16": 16,
230
+ "LABEL_17": 17,
231
+ "LABEL_18": 18,
232
+ "LABEL_19": 19,
233
+ "LABEL_2": 2,
234
+ "LABEL_20": 20,
235
+ "LABEL_21": 21,
236
+ "LABEL_22": 22,
237
+ "LABEL_23": 23,
238
+ "LABEL_24": 24,
239
+ "LABEL_25": 25,
240
+ "LABEL_26": 26,
241
+ "LABEL_27": 27,
242
+ "LABEL_28": 28,
243
+ "LABEL_29": 29,
244
+ "LABEL_3": 3,
245
+ "LABEL_30": 30,
246
+ "LABEL_31": 31,
247
+ "LABEL_32": 32,
248
+ "LABEL_33": 33,
249
+ "LABEL_34": 34,
250
+ "LABEL_35": 35,
251
+ "LABEL_36": 36,
252
+ "LABEL_37": 37,
253
+ "LABEL_38": 38,
254
+ "LABEL_39": 39,
255
+ "LABEL_4": 4,
256
+ "LABEL_40": 40,
257
+ "LABEL_41": 41,
258
+ "LABEL_42": 42,
259
+ "LABEL_43": 43,
260
+ "LABEL_44": 44,
261
+ "LABEL_45": 45,
262
+ "LABEL_46": 46,
263
+ "LABEL_47": 47,
264
+ "LABEL_48": 48,
265
+ "LABEL_49": 49,
266
+ "LABEL_5": 5,
267
+ "LABEL_50": 50,
268
+ "LABEL_51": 51,
269
+ "LABEL_52": 52,
270
+ "LABEL_53": 53,
271
+ "LABEL_54": 54,
272
+ "LABEL_55": 55,
273
+ "LABEL_56": 56,
274
+ "LABEL_57": 57,
275
+ "LABEL_58": 58,
276
+ "LABEL_59": 59,
277
+ "LABEL_6": 6,
278
+ "LABEL_60": 60,
279
+ "LABEL_61": 61,
280
+ "LABEL_62": 62,
281
+ "LABEL_63": 63,
282
+ "LABEL_64": 64,
283
+ "LABEL_65": 65,
284
+ "LABEL_66": 66,
285
+ "LABEL_67": 67,
286
+ "LABEL_68": 68,
287
+ "LABEL_69": 69,
288
+ "LABEL_7": 7,
289
+ "LABEL_70": 70,
290
+ "LABEL_71": 71,
291
+ "LABEL_72": 72,
292
+ "LABEL_73": 73,
293
+ "LABEL_74": 74,
294
+ "LABEL_75": 75,
295
+ "LABEL_76": 76,
296
+ "LABEL_77": 77,
297
+ "LABEL_78": 78,
298
+ "LABEL_79": 79,
299
+ "LABEL_8": 8,
300
+ "LABEL_80": 80,
301
+ "LABEL_81": 81,
302
+ "LABEL_82": 82,
303
+ "LABEL_83": 83,
304
+ "LABEL_84": 84,
305
+ "LABEL_85": 85,
306
+ "LABEL_86": 86,
307
+ "LABEL_87": 87,
308
+ "LABEL_88": 88,
309
+ "LABEL_89": 89,
310
+ "LABEL_9": 9,
311
+ "LABEL_90": 90,
312
+ "LABEL_91": 91,
313
+ "LABEL_92": 92,
314
+ "LABEL_93": 93,
315
+ "LABEL_94": 94,
316
+ "LABEL_95": 95,
317
+ "LABEL_96": 96,
318
+ "LABEL_97": 97,
319
+ "LABEL_98": 98,
320
+ "LABEL_99": 99
321
+ },
322
+ "layer_norm_eps": 1e-12,
323
+ "mem_len": null,
324
+ "model_type": "xlnet",
325
+ "n_head": 16,
326
+ "n_layer": 24,
327
+ "pad_token_id": 5,
328
+ "reuse_len": null,
329
+ "same_length": false,
330
+ "start_n_top": 5,
331
+ "summary_activation": "tanh",
332
+ "summary_last_dropout": 0.1,
333
+ "summary_type": "last",
334
+ "summary_use_proj": true,
335
+ "task_specific_params": {
336
+ "text-generation": {
337
+ "do_sample": true,
338
+ "max_length": 250
339
+ }
340
+ },
341
+ "transformers_version": "4.34.0",
342
+ "untie_r": true,
343
+ "use_mems_eval": true,
344
+ "use_mems_train": false,
345
+ "vocab_size": 32000
346
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": "<mask>",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "<sep>",
12
+ "unk_token": "<unk>"
13
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5da53b805f30f72cf62e3e17835c5c9ee80702e7b663a6b45ad7da13e6c16df
3
+ size 1446280280
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<cls>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<eod>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<eop>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<eop>",
78
+ "<eod>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": true,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "eos_token": "</s>",
85
+ "keep_accents": false,
86
+ "mask_token": "<mask>",
87
+ "model_max_length": 1000000000000000019884624838656,
88
+ "pad_token": "<pad>",
89
+ "remove_space": true,
90
+ "sep_token": "<sep>",
91
+ "tokenizer_class": "XLNetTokenizer",
92
+ "unk_token": "<unk>"
93
+ }