Hugging Face's logo

MJ199999
/
gpt3_model

Text Generation
Transformers
TensorFlow
gpt2
generated_from_keras_callback
Model card Files
xet
Community
1
MJ199999 commited on
Commit
4fc716f
·
1 Parent(s): 949b5e5

add model

Browse files
Files changed (3) hide show
  1. README.md +204 -504
  2. config.json +1 -1
  3. tf_model.h5 +2 -2
README.md CHANGED
@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [MJ199999/gpt3_model](https://huggingface.co/MJ199999/gpt3_model) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Train Loss: 0.5845
17
- - Train Lr: 9.999999e-06
18
- - Epoch: 499
19
 
20
  ## Model description
21
 
@@ -34,513 +34,213 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - optimizer: {'name': 'Adagrad', 'learning_rate': 9.999999e-06, 'decay': 0.0, 'initial_accumulator_value': 0.1, 'epsilon': 1e-07}
38
  - training_precision: float32
39
 
40
  ### Training results
41
 
42
  | Train Loss | Train Lr | Epoch |
43
  |:----------:|:------------:|:-----:|
44
- | 6.2880 | 0.01 | 0 |
45
- | 5.7606 | 0.01 | 1 |
46
- | 5.1576 | 0.01 | 2 |
47
- | 4.3108 | 0.01 | 3 |
48
- | 3.5814 | 0.01 | 4 |
49
- | 3.0632 | 0.01 | 5 |
50
- | 2.7176 | 0.01 | 6 |
51
- | 2.4443 | 0.01 | 7 |
52
- | 2.2514 | 0.01 | 8 |
53
- | 2.0976 | 0.01 | 9 |
54
- | 1.9442 | 0.01 | 10 |
55
- | 1.8267 | 0.01 | 11 |
56
- | 1.7501 | 0.01 | 12 |
57
- | 1.6662 | 0.01 | 13 |
58
- | 1.5683 | 0.01 | 14 |
59
- | 1.4911 | 0.01 | 15 |
60
- | 1.4178 | 0.01 | 16 |
61
- | 1.3575 | 0.01 | 17 |
62
- | 1.2840 | 0.01 | 18 |
63
- | 1.2293 | 0.01 | 19 |
64
- | 1.1635 | 0.01 | 20 |
65
- | 1.1338 | 0.01 | 21 |
66
- | 1.1031 | 0.01 | 22 |
67
- | 1.0701 | 0.01 | 23 |
68
- | 1.0398 | 0.01 | 24 |
69
- | 1.0211 | 0.01 | 25 |
70
- | 1.0005 | 0.01 | 26 |
71
- | 0.9744 | 0.01 | 27 |
72
- | 0.9637 | 0.01 | 28 |
73
- | 0.9429 | 0.01 | 29 |
74
- | 0.9272 | 0.01 | 30 |
75
- | 0.9216 | 0.01 | 31 |
76
- | 0.9131 | 0.01 | 32 |
77
- | 0.9008 | 0.01 | 33 |
78
- | 0.8897 | 0.01 | 34 |
79
- | 0.8916 | 0.01 | 35 |
80
- | 0.8700 | 0.01 | 36 |
81
- | 0.8633 | 0.01 | 37 |
82
- | 0.8630 | 0.01 | 38 |
83
- | 0.8583 | 0.01 | 39 |
84
- | 0.8512 | 0.01 | 40 |
85
- | 0.8424 | 0.01 | 41 |
86
- | 0.8403 | 0.01 | 42 |
87
- | 0.8285 | 0.01 | 43 |
88
- | 0.8285 | 0.01 | 44 |
89
- | 0.8238 | 0.01 | 45 |
90
- | 0.8100 | 0.01 | 46 |
91
- | 0.8149 | 0.01 | 47 |
92
- | 0.8067 | 0.01 | 48 |
93
- | 0.8109 | 0.01 | 49 |
94
- | 0.8055 | 0.01 | 50 |
95
- | 0.7995 | 0.01 | 51 |
96
- | 0.7915 | 0.01 | 52 |
97
- | 0.7938 | 0.01 | 53 |
98
- | 0.7876 | 0.01 | 54 |
99
- | 0.7864 | 0.01 | 55 |
100
- | 0.7795 | 0.01 | 56 |
101
- | 0.7841 | 0.01 | 57 |
102
- | 0.7803 | 0.01 | 58 |
103
- | 0.7713 | 0.01 | 59 |
104
- | 0.7694 | 0.01 | 60 |
105
- | 0.7726 | 0.01 | 61 |
106
- | 0.7648 | 0.01 | 62 |
107
- | 0.7661 | 0.01 | 63 |
108
- | 0.7584 | 0.01 | 64 |
109
- | 0.7646 | 0.01 | 65 |
110
- | 0.7544 | 0.01 | 66 |
111
- | 0.7532 | 0.01 | 67 |
112
- | 0.7516 | 0.01 | 68 |
113
- | 0.7482 | 0.01 | 69 |
114
- | 0.7489 | 0.01 | 70 |
115
- | 0.7455 | 0.01 | 71 |
116
- | 0.7456 | 0.01 | 72 |
117
- | 0.7486 | 0.01 | 73 |
118
- | 0.7413 | 0.01 | 74 |
119
- | 0.7467 | 0.01 | 75 |
120
- | 0.7406 | 0.01 | 76 |
121
- | 0.7387 | 0.01 | 77 |
122
- | 0.7367 | 0.01 | 78 |
123
- | 0.7378 | 0.01 | 79 |
124
- | 0.7330 | 0.01 | 80 |
125
- | 0.7299 | 0.01 | 81 |
126
- | 0.7290 | 0.01 | 82 |
127
- | 0.7293 | 0.01 | 83 |
128
- | 0.7226 | 0.01 | 84 |
129
- | 0.7222 | 0.01 | 85 |
130
- | 0.7186 | 0.01 | 86 |
131
- | 0.7244 | 0.01 | 87 |
132
- | 0.7205 | 0.01 | 88 |
133
- | 0.7207 | 0.01 | 89 |
134
- | 0.7211 | 0.01 | 90 |
135
- | 0.7225 | 0.01 | 91 |
136
- | 0.7147 | 0.01 | 92 |
137
- | 0.7131 | 0.01 | 93 |
138
- | 0.7083 | 0.01 | 94 |
139
- | 0.7110 | 0.01 | 95 |
140
- | 0.7114 | 0.01 | 96 |
141
- | 0.7141 | 0.01 | 97 |
142
- | 0.7108 | 0.01 | 98 |
143
- | 0.7126 | 0.01 | 99 |
144
- | 0.7075 | 0.01 | 100 |
145
- | 0.7071 | 0.01 | 101 |
146
- | 0.6950 | 0.01 | 102 |
147
- | 0.7033 | 0.01 | 103 |
148
- | 0.6956 | 0.01 | 104 |
149
- | 0.7001 | 0.01 | 105 |
150
- | 0.6964 | 0.01 | 106 |
151
- | 0.6935 | 0.01 | 107 |
152
- | 0.6916 | 0.01 | 108 |
153
- | 0.7012 | 0.01 | 109 |
154
- | 0.6924 | 0.01 | 110 |
155
- | 0.6933 | 0.01 | 111 |
156
- | 0.6919 | 0.01 | 112 |
157
- | 0.6920 | 0.01 | 113 |
158
- | 0.6923 | 0.01 | 114 |
159
- | 0.6824 | 0.01 | 115 |
160
- | 0.6885 | 0.01 | 116 |
161
- | 0.6905 | 0.01 | 117 |
162
- | 0.6862 | 0.01 | 118 |
163
- | 0.6857 | 0.01 | 119 |
164
- | 0.6827 | 0.01 | 120 |
165
- | 0.6880 | 0.01 | 121 |
166
- | 0.6816 | 0.01 | 122 |
167
- | 0.6843 | 0.01 | 123 |
168
- | 0.6751 | 0.01 | 124 |
169
- | 0.6836 | 0.01 | 125 |
170
- | 0.6762 | 0.01 | 126 |
171
- | 0.6797 | 0.01 | 127 |
172
- | 0.6840 | 0.01 | 128 |
173
- | 0.6793 | 0.01 | 129 |
174
- | 0.6745 | 0.01 | 130 |
175
- | 0.6804 | 0.01 | 131 |
176
- | 0.6762 | 0.01 | 132 |
177
- | 0.6777 | 0.01 | 133 |
178
- | 0.6709 | 0.01 | 134 |
179
- | 0.6759 | 0.01 | 135 |
180
- | 0.6739 | 0.01 | 136 |
181
- | 0.6772 | 0.01 | 137 |
182
- | 0.6720 | 0.01 | 138 |
183
- | 0.6757 | 0.01 | 139 |
184
- | 0.6623 | 0.01 | 140 |
185
- | 0.6710 | 0.01 | 141 |
186
- | 0.6704 | 0.01 | 142 |
187
- | 0.6673 | 0.01 | 143 |
188
- | 0.6684 | 0.01 | 144 |
189
- | 0.6700 | 0.01 | 145 |
190
- | 0.6681 | 0.01 | 146 |
191
- | 0.6685 | 0.01 | 147 |
192
- | 0.6688 | 0.01 | 148 |
193
- | 0.6602 | 0.01 | 149 |
194
- | 0.6611 | 0.01 | 150 |
195
- | 0.6651 | 0.01 | 151 |
196
- | 0.6656 | 0.01 | 152 |
197
- | 0.6639 | 0.01 | 153 |
198
- | 0.6596 | 0.01 | 154 |
199
- | 0.6707 | 0.01 | 155 |
200
- | 0.6702 | 0.01 | 156 |
201
- | 0.6616 | 0.01 | 157 |
202
- | 0.6675 | 0.01 | 158 |
203
- | 0.6574 | 0.01 | 159 |
204
- | 0.6606 | 0.01 | 160 |
205
- | 0.6550 | 0.01 | 161 |
206
- | 0.6605 | 0.01 | 162 |
207
- | 0.6612 | 0.01 | 163 |
208
- | 0.6597 | 0.01 | 164 |
209
- | 0.6566 | 0.01 | 165 |
210
- | 0.6579 | 0.01 | 166 |
211
- | 0.6535 | 0.01 | 167 |
212
- | 0.6550 | 0.01 | 168 |
213
- | 0.6531 | 0.01 | 169 |
214
- | 0.6579 | 0.01 | 170 |
215
- | 0.6592 | 0.01 | 171 |
216
- | 0.6597 | 0.01 | 172 |
217
- | 0.6556 | 0.01 | 173 |
218
- | 0.6558 | 0.01 | 174 |
219
- | 0.6529 | 0.01 | 175 |
220
- | 0.6572 | 0.01 | 176 |
221
- | 0.6530 | 0.01 | 177 |
222
- | 0.6564 | 0.01 | 178 |
223
- | 0.6513 | 0.01 | 179 |
224
- | 0.6511 | 0.01 | 180 |
225
- | 0.6564 | 0.01 | 181 |
226
- | 0.6494 | 0.01 | 182 |
227
- | 0.6518 | 0.01 | 183 |
228
- | 0.6521 | 0.01 | 184 |
229
- | 0.6513 | 0.01 | 185 |
230
- | 0.6490 | 0.01 | 186 |
231
- | 0.6479 | 0.01 | 187 |
232
- | 0.6446 | 0.01 | 188 |
233
- | 0.6478 | 0.01 | 189 |
234
- | 0.6475 | 0.01 | 190 |
235
- | 0.6440 | 0.01 | 191 |
236
- | 0.6479 | 0.01 | 192 |
237
- | 0.6479 | 0.01 | 193 |
238
- | 0.6469 | 0.01 | 194 |
239
- | 0.6477 | 0.01 | 195 |
240
- | 0.6470 | 0.01 | 196 |
241
- | 0.6398 | 0.01 | 197 |
242
- | 0.6440 | 0.01 | 198 |
243
- | 0.6434 | 0.01 | 199 |
244
- | 0.6017 | 0.0009999999 | 200 |
245
- | 0.6024 | 0.0009999999 | 201 |
246
- | 0.5955 | 0.0009999999 | 202 |
247
- | 0.5990 | 0.0009999999 | 203 |
248
- | 0.5967 | 0.0009999999 | 204 |
249
- | 0.5994 | 0.0009999999 | 205 |
250
- | 0.5956 | 0.0009999999 | 206 |
251
- | 0.5982 | 0.0009999999 | 207 |
252
- | 0.5931 | 0.0009999999 | 208 |
253
- | 0.5974 | 0.0009999999 | 209 |
254
- | 0.5947 | 0.0009999999 | 210 |
255
- | 0.5957 | 0.0009999999 | 211 |
256
- | 0.5972 | 0.0009999999 | 212 |
257
- | 0.5922 | 0.0009999999 | 213 |
258
- | 0.5977 | 0.0009999999 | 214 |
259
- | 0.5925 | 0.0009999999 | 215 |
260
- | 0.5922 | 0.0009999999 | 216 |
261
- | 0.5965 | 0.0009999999 | 217 |
262
- | 0.5949 | 0.0009999999 | 218 |
263
- | 0.5950 | 0.0009999999 | 219 |
264
- | 0.5972 | 0.0009999999 | 220 |
265
- | 0.5936 | 0.0009999999 | 221 |
266
- | 0.5909 | 0.0009999999 | 222 |
267
- | 0.5920 | 0.0009999999 | 223 |
268
- | 0.5923 | 0.0009999999 | 224 |
269
- | 0.5895 | 0.0009999999 | 225 |
270
- | 0.5932 | 0.0009999999 | 226 |
271
- | 0.5915 | 0.0009999999 | 227 |
272
- | 0.5967 | 0.0009999999 | 228 |
273
- | 0.5935 | 0.0009999999 | 229 |
274
- | 0.5957 | 0.0009999999 | 230 |
275
- | 0.5926 | 0.0009999999 | 231 |
276
- | 0.5938 | 0.0009999999 | 232 |
277
- | 0.5921 | 0.0009999999 | 233 |
278
- | 0.5943 | 0.0009999999 | 234 |
279
- | 0.5939 | 0.0009999999 | 235 |
280
- | 0.5951 | 0.0009999999 | 236 |
281
- | 0.5918 | 0.0009999999 | 237 |
282
- | 0.5942 | 0.0009999999 | 238 |
283
- | 0.5919 | 0.0009999999 | 239 |
284
- | 0.5950 | 0.0009999999 | 240 |
285
- | 0.5921 | 0.0009999999 | 241 |
286
- | 0.5919 | 0.0009999999 | 242 |
287
- | 0.5930 | 0.0009999999 | 243 |
288
- | 0.5893 | 0.0009999999 | 244 |
289
- | 0.5912 | 0.0009999999 | 245 |
290
- | 0.5911 | 0.0009999999 | 246 |
291
- | 0.5903 | 0.0009999999 | 247 |
292
- | 0.5913 | 0.0009999999 | 248 |
293
- | 0.5916 | 0.0009999999 | 249 |
294
- | 0.5912 | 0.0009999999 | 250 |
295
- | 0.5893 | 0.0009999999 | 251 |
296
- | 0.5917 | 0.0009999999 | 252 |
297
- | 0.5930 | 0.0009999999 | 253 |
298
- | 0.5891 | 0.0009999999 | 254 |
299
- | 0.5901 | 0.0009999999 | 255 |
300
- | 0.5894 | 0.0009999999 | 256 |
301
- | 0.5908 | 0.0009999999 | 257 |
302
- | 0.5904 | 0.0009999999 | 258 |
303
- | 0.5890 | 0.0009999999 | 259 |
304
- | 0.5913 | 0.0009999999 | 260 |
305
- | 0.5896 | 0.0009999999 | 261 |
306
- | 0.5876 | 0.0009999999 | 262 |
307
- | 0.5914 | 0.0009999999 | 263 |
308
- | 0.5882 | 0.0009999999 | 264 |
309
- | 0.5926 | 0.0009999999 | 265 |
310
- | 0.5926 | 0.0009999999 | 266 |
311
- | 0.5929 | 0.0009999999 | 267 |
312
- | 0.5915 | 0.0009999999 | 268 |
313
- | 0.5896 | 0.0009999999 | 269 |
314
- | 0.5900 | 0.0009999999 | 270 |
315
- | 0.5910 | 0.0009999999 | 271 |
316
- | 0.5935 | 0.0009999999 | 272 |
317
- | 0.5914 | 0.0009999999 | 273 |
318
- | 0.5885 | 0.0009999999 | 274 |
319
- | 0.5907 | 0.0009999999 | 275 |
320
- | 0.5911 | 0.0009999999 | 276 |
321
- | 0.5878 | 0.0009999999 | 277 |
322
- | 0.5908 | 0.0009999999 | 278 |
323
- | 0.5928 | 0.0009999999 | 279 |
324
- | 0.5957 | 0.0009999999 | 280 |
325
- | 0.5901 | 0.0009999999 | 281 |
326
- | 0.5899 | 0.0009999999 | 282 |
327
- | 0.5906 | 0.0009999999 | 283 |
328
- | 0.5911 | 0.0009999999 | 284 |
329
- | 0.5935 | 0.0009999999 | 285 |
330
- | 0.5860 | 0.0009999999 | 286 |
331
- | 0.5863 | 0.0009999999 | 287 |
332
- | 0.5866 | 0.0009999999 | 288 |
333
- | 0.5916 | 0.0009999999 | 289 |
334
- | 0.5914 | 0.0009999999 | 290 |
335
- | 0.5866 | 0.0009999999 | 291 |
336
- | 0.5904 | 0.0009999999 | 292 |
337
- | 0.5917 | 0.0009999999 | 293 |
338
- | 0.5864 | 0.0009999999 | 294 |
339
- | 0.5857 | 0.0009999999 | 295 |
340
- | 0.5902 | 0.0009999999 | 296 |
341
- | 0.5874 | 0.0009999999 | 297 |
342
- | 0.5912 | 0.0009999999 | 298 |
343
- | 0.5904 | 0.0009999999 | 299 |
344
- | 0.5847 | 9.999999e-05 | 300 |
345
- | 0.5861 | 9.999999e-05 | 301 |
346
- | 0.5844 | 9.999999e-05 | 302 |
347
- | 0.5896 | 9.999999e-05 | 303 |
348
- | 0.5837 | 9.999999e-05 | 304 |
349
- | 0.5847 | 9.999999e-05 | 305 |
350
- | 0.5854 | 9.999999e-05 | 306 |
351
- | 0.5854 | 9.999999e-05 | 307 |
352
- | 0.5865 | 9.999999e-05 | 308 |
353
- | 0.5862 | 9.999999e-05 | 309 |
354
- | 0.5857 | 9.999999e-05 | 310 |
355
- | 0.5811 | 9.999999e-05 | 311 |
356
- | 0.5843 | 9.999999e-05 | 312 |
357
- | 0.5860 | 9.999999e-05 | 313 |
358
- | 0.5874 | 9.999999e-05 | 314 |
359
- | 0.5847 | 9.999999e-05 | 315 |
360
- | 0.5834 | 9.999999e-05 | 316 |
361
- | 0.5879 | 9.999999e-05 | 317 |
362
- | 0.5826 | 9.999999e-05 | 318 |
363
- | 0.5857 | 9.999999e-05 | 319 |
364
- | 0.5861 | 9.999999e-05 | 320 |
365
- | 0.5859 | 9.999999e-05 | 321 |
366
- | 0.5833 | 9.999999e-05 | 322 |
367
- | 0.5847 | 9.999999e-05 | 323 |
368
- | 0.5873 | 9.999999e-05 | 324 |
369
- | 0.5856 | 9.999999e-05 | 325 |
370
- | 0.5865 | 9.999999e-05 | 326 |
371
- | 0.5870 | 9.999999e-05 | 327 |
372
- | 0.5842 | 9.999999e-05 | 328 |
373
- | 0.5824 | 9.999999e-05 | 329 |
374
- | 0.5832 | 9.999999e-05 | 330 |
375
- | 0.5888 | 9.999999e-05 | 331 |
376
- | 0.5857 | 9.999999e-05 | 332 |
377
- | 0.5851 | 9.999999e-05 | 333 |
378
- | 0.5866 | 9.999999e-05 | 334 |
379
- | 0.5844 | 9.999999e-05 | 335 |
380
- | 0.5806 | 9.999999e-05 | 336 |
381
- | 0.5869 | 9.999999e-05 | 337 |
382
- | 0.5842 | 9.999999e-05 | 338 |
383
- | 0.5871 | 9.999999e-05 | 339 |
384
- | 0.5843 | 9.999999e-05 | 340 |
385
- | 0.5837 | 9.999999e-05 | 341 |
386
- | 0.5830 | 9.999999e-05 | 342 |
387
- | 0.5839 | 9.999999e-05 | 343 |
388
- | 0.5831 | 9.999999e-05 | 344 |
389
- | 0.5834 | 9.999999e-05 | 345 |
390
- | 0.5844 | 9.999999e-05 | 346 |
391
- | 0.5828 | 9.999999e-05 | 347 |
392
- | 0.5871 | 9.999999e-05 | 348 |
393
- | 0.5871 | 9.999999e-05 | 349 |
394
- | 0.5881 | 9.999999e-05 | 350 |
395
- | 0.5828 | 9.999999e-05 | 351 |
396
- | 0.5857 | 9.999999e-05 | 352 |
397
- | 0.5855 | 9.999999e-05 | 353 |
398
- | 0.5879 | 9.999999e-05 | 354 |
399
- | 0.5828 | 9.999999e-05 | 355 |
400
- | 0.5868 | 9.999999e-05 | 356 |
401
- | 0.5865 | 9.999999e-05 | 357 |
402
- | 0.5858 | 9.999999e-05 | 358 |
403
- | 0.5857 | 9.999999e-05 | 359 |
404
- | 0.5860 | 9.999999e-05 | 360 |
405
- | 0.5860 | 9.999999e-05 | 361 |
406
- | 0.5852 | 9.999999e-05 | 362 |
407
- | 0.5845 | 9.999999e-05 | 363 |
408
- | 0.5831 | 9.999999e-05 | 364 |
409
- | 0.5878 | 9.999999e-05 | 365 |
410
- | 0.5877 | 9.999999e-05 | 366 |
411
- | 0.5892 | 9.999999e-05 | 367 |
412
- | 0.5845 | 9.999999e-05 | 368 |
413
- | 0.5878 | 9.999999e-05 | 369 |
414
- | 0.5831 | 9.999999e-05 | 370 |
415
- | 0.5841 | 9.999999e-05 | 371 |
416
- | 0.5856 | 9.999999e-05 | 372 |
417
- | 0.5902 | 9.999999e-05 | 373 |
418
- | 0.5850 | 9.999999e-05 | 374 |
419
- | 0.5850 | 9.999999e-05 | 375 |
420
- | 0.5864 | 9.999999e-05 | 376 |
421
- | 0.5855 | 9.999999e-05 | 377 |
422
- | 0.5850 | 9.999999e-05 | 378 |
423
- | 0.5877 | 9.999999e-05 | 379 |
424
- | 0.5836 | 9.999999e-05 | 380 |
425
- | 0.5787 | 9.999999e-05 | 381 |
426
- | 0.5847 | 9.999999e-05 | 382 |
427
- | 0.5818 | 9.999999e-05 | 383 |
428
- | 0.5854 | 9.999999e-05 | 384 |
429
- | 0.5829 | 9.999999e-05 | 385 |
430
- | 0.5841 | 9.999999e-05 | 386 |
431
- | 0.5855 | 9.999999e-05 | 387 |
432
- | 0.5830 | 9.999999e-05 | 388 |
433
- | 0.5861 | 9.999999e-05 | 389 |
434
- | 0.5833 | 9.999999e-05 | 390 |
435
- | 0.5850 | 9.999999e-05 | 391 |
436
- | 0.5832 | 9.999999e-05 | 392 |
437
- | 0.5837 | 9.999999e-05 | 393 |
438
- | 0.5830 | 9.999999e-05 | 394 |
439
- | 0.5871 | 9.999999e-05 | 395 |
440
- | 0.5858 | 9.999999e-05 | 396 |
441
- | 0.5840 | 9.999999e-05 | 397 |
442
- | 0.5827 | 9.999999e-05 | 398 |
443
- | 0.5860 | 9.999999e-05 | 399 |
444
- | 0.5847 | 9.999999e-06 | 400 |
445
- | 0.5800 | 9.999999e-06 | 401 |
446
- | 0.5867 | 9.999999e-06 | 402 |
447
- | 0.5842 | 9.999999e-06 | 403 |
448
- | 0.5865 | 9.999999e-06 | 404 |
449
- | 0.5828 | 9.999999e-06 | 405 |
450
- | 0.5832 | 9.999999e-06 | 406 |
451
- | 0.5840 | 9.999999e-06 | 407 |
452
- | 0.5841 | 9.999999e-06 | 408 |
453
- | 0.5876 | 9.999999e-06 | 409 |
454
- | 0.5856 | 9.999999e-06 | 410 |
455
- | 0.5789 | 9.999999e-06 | 411 |
456
- | 0.5846 | 9.999999e-06 | 412 |
457
- | 0.5850 | 9.999999e-06 | 413 |
458
- | 0.5847 | 9.999999e-06 | 414 |
459
- | 0.5845 | 9.999999e-06 | 415 |
460
- | 0.5854 | 9.999999e-06 | 416 |
461
- | 0.5857 | 9.999999e-06 | 417 |
462
- | 0.5842 | 9.999999e-06 | 418 |
463
- | 0.5842 | 9.999999e-06 | 419 |
464
- | 0.5795 | 9.999999e-06 | 420 |
465
- | 0.5859 | 9.999999e-06 | 421 |
466
- | 0.5848 | 9.999999e-06 | 422 |
467
- | 0.5812 | 9.999999e-06 | 423 |
468
- | 0.5850 | 9.999999e-06 | 424 |
469
- | 0.5855 | 9.999999e-06 | 425 |
470
- | 0.5863 | 9.999999e-06 | 426 |
471
- | 0.5847 | 9.999999e-06 | 427 |
472
- | 0.5858 | 9.999999e-06 | 428 |
473
- | 0.5868 | 9.999999e-06 | 429 |
474
- | 0.5789 | 9.999999e-06 | 430 |
475
- | 0.5853 | 9.999999e-06 | 431 |
476
- | 0.5822 | 9.999999e-06 | 432 |
477
- | 0.5817 | 9.999999e-06 | 433 |
478
- | 0.5844 | 9.999999e-06 | 434 |
479
- | 0.5849 | 9.999999e-06 | 435 |
480
- | 0.5835 | 9.999999e-06 | 436 |
481
- | 0.5868 | 9.999999e-06 | 437 |
482
- | 0.5831 | 9.999999e-06 | 438 |
483
- | 0.5859 | 9.999999e-06 | 439 |
484
- | 0.5818 | 9.999999e-06 | 440 |
485
- | 0.5833 | 9.999999e-06 | 441 |
486
- | 0.5888 | 9.999999e-06 | 442 |
487
- | 0.5878 | 9.999999e-06 | 443 |
488
- | 0.5847 | 9.999999e-06 | 444 |
489
- | 0.5816 | 9.999999e-06 | 445 |
490
- | 0.5864 | 9.999999e-06 | 446 |
491
- | 0.5829 | 9.999999e-06 | 447 |
492
- | 0.5835 | 9.999999e-06 | 448 |
493
- | 0.5848 | 9.999999e-06 | 449 |
494
- | 0.5852 | 9.999999e-06 | 450 |
495
- | 0.5800 | 9.999999e-06 | 451 |
496
- | 0.5834 | 9.999999e-06 | 452 |
497
- | 0.5856 | 9.999999e-06 | 453 |
498
- | 0.5866 | 9.999999e-06 | 454 |
499
- | 0.5844 | 9.999999e-06 | 455 |
500
- | 0.5846 | 9.999999e-06 | 456 |
501
- | 0.5840 | 9.999999e-06 | 457 |
502
- | 0.5857 | 9.999999e-06 | 458 |
503
- | 0.5854 | 9.999999e-06 | 459 |
504
- | 0.5836 | 9.999999e-06 | 460 |
505
- | 0.5859 | 9.999999e-06 | 461 |
506
- | 0.5866 | 9.999999e-06 | 462 |
507
- | 0.5835 | 9.999999e-06 | 463 |
508
- | 0.5866 | 9.999999e-06 | 464 |
509
- | 0.5843 | 9.999999e-06 | 465 |
510
- | 0.5868 | 9.999999e-06 | 466 |
511
- | 0.5877 | 9.999999e-06 | 467 |
512
- | 0.5841 | 9.999999e-06 | 468 |
513
- | 0.5858 | 9.999999e-06 | 469 |
514
- | 0.5847 | 9.999999e-06 | 470 |
515
- | 0.5855 | 9.999999e-06 | 471 |
516
- | 0.5832 | 9.999999e-06 | 472 |
517
- | 0.5807 | 9.999999e-06 | 473 |
518
- | 0.5818 | 9.999999e-06 | 474 |
519
- | 0.5868 | 9.999999e-06 | 475 |
520
- | 0.5856 | 9.999999e-06 | 476 |
521
- | 0.5821 | 9.999999e-06 | 477 |
522
- | 0.5791 | 9.999999e-06 | 478 |
523
- | 0.5847 | 9.999999e-06 | 479 |
524
- | 0.5881 | 9.999999e-06 | 480 |
525
- | 0.5821 | 9.999999e-06 | 481 |
526
- | 0.5844 | 9.999999e-06 | 482 |
527
- | 0.5873 | 9.999999e-06 | 483 |
528
- | 0.5854 | 9.999999e-06 | 484 |
529
- | 0.5868 | 9.999999e-06 | 485 |
530
- | 0.5810 | 9.999999e-06 | 486 |
531
- | 0.5874 | 9.999999e-06 | 487 |
532
- | 0.5849 | 9.999999e-06 | 488 |
533
- | 0.5887 | 9.999999e-06 | 489 |
534
- | 0.5870 | 9.999999e-06 | 490 |
535
- | 0.5846 | 9.999999e-06 | 491 |
536
- | 0.5800 | 9.999999e-06 | 492 |
537
- | 0.5850 | 9.999999e-06 | 493 |
538
- | 0.5857 | 9.999999e-06 | 494 |
539
- | 0.5849 | 9.999999e-06 | 495 |
540
- | 0.5818 | 9.999999e-06 | 496 |
541
- | 0.5849 | 9.999999e-06 | 497 |
542
- | 0.5861 | 9.999999e-06 | 498 |
543
- | 0.5845 | 9.999999e-06 | 499 |
544
 
545
 
546
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [MJ199999/gpt3_model](https://huggingface.co/MJ199999/gpt3_model) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Train Loss: 0.9684
17
+ - Train Lr: 0.0009999999
18
+ - Epoch: 199
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - optimizer: {'name': 'Adagrad', 'learning_rate': 0.0009999999, 'decay': 0.0, 'initial_accumulator_value': 0.1, 'epsilon': 1e-07}
38
  - training_precision: float32
39
 
40
  ### Training results
41
 
42
  | Train Loss | Train Lr | Epoch |
43
  |:----------:|:------------:|:-----:|
44
+ | 6.9783 | 0.01 | 0 |
45
+ | 5.7078 | 0.01 | 1 |
46
+ | 5.1313 | 0.01 | 2 |
47
+ | 4.4967 | 0.01 | 3 |
48
+ | 3.9272 | 0.01 | 4 |
49
+ | 3.4594 | 0.01 | 5 |
50
+ | 3.0591 | 0.01 | 6 |
51
+ | 2.7073 | 0.01 | 7 |
52
+ | 2.4512 | 0.01 | 8 |
53
+ | 2.2231 | 0.01 | 9 |
54
+ | 2.0833 | 0.01 | 10 |
55
+ | 1.9429 | 0.01 | 11 |
56
+ | 1.8434 | 0.01 | 12 |
57
+ | 1.7522 | 0.01 | 13 |
58
+ | 1.6928 | 0.01 | 14 |
59
+ | 1.6394 | 0.01 | 15 |
60
+ | 1.5898 | 0.01 | 16 |
61
+ | 1.5477 | 0.01 | 17 |
62
+ | 1.5130 | 0.01 | 18 |
63
+ | 1.4822 | 0.01 | 19 |
64
+ | 1.4550 | 0.01 | 20 |
65
+ | 1.4375 | 0.01 | 21 |
66
+ | 1.4096 | 0.01 | 22 |
67
+ | 1.3952 | 0.01 | 23 |
68
+ | 1.3756 | 0.01 | 24 |
69
+ | 1.3603 | 0.01 | 25 |
70
+ | 1.3422 | 0.01 | 26 |
71
+ | 1.3329 | 0.01 | 27 |
72
+ | 1.3221 | 0.01 | 28 |
73
+ | 1.3155 | 0.01 | 29 |
74
+ | 1.3007 | 0.01 | 30 |
75
+ | 1.2915 | 0.01 | 31 |
76
+ | 1.2869 | 0.01 | 32 |
77
+ | 1.2744 | 0.01 | 33 |
78
+ | 1.2710 | 0.01 | 34 |
79
+ | 1.2578 | 0.01 | 35 |
80
+ | 1.2550 | 0.01 | 36 |
81
+ | 1.2458 | 0.01 | 37 |
82
+ | 1.2373 | 0.01 | 38 |
83
+ | 1.2364 | 0.01 | 39 |
84
+ | 1.2332 | 0.01 | 40 |
85
+ | 1.2177 | 0.01 | 41 |
86
+ | 1.2164 | 0.01 | 42 |
87
+ | 1.2176 | 0.01 | 43 |
88
+ | 1.2129 | 0.01 | 44 |
89
+ | 1.2088 | 0.01 | 45 |
90
+ | 1.2067 | 0.01 | 46 |
91
+ | 1.2013 | 0.01 | 47 |
92
+ | 1.1933 | 0.01 | 48 |
93
+ | 1.1920 | 0.01 | 49 |
94
+ | 1.1873 | 0.01 | 50 |
95
+ | 1.1831 | 0.01 | 51 |
96
+ | 1.1795 | 0.01 | 52 |
97
+ | 1.1777 | 0.01 | 53 |
98
+ | 1.1749 | 0.01 | 54 |
99
+ | 1.1719 | 0.01 | 55 |
100
+ | 1.1622 | 0.01 | 56 |
101
+ | 1.1621 | 0.01 | 57 |
102
+ | 1.1591 | 0.01 | 58 |
103
+ | 1.1582 | 0.01 | 59 |
104
+ | 1.1620 | 0.01 | 60 |
105
+ | 1.1528 | 0.01 | 61 |
106
+ | 1.1536 | 0.01 | 62 |
107
+ | 1.1479 | 0.01 | 63 |
108
+ | 1.1458 | 0.01 | 64 |
109
+ | 1.1429 | 0.01 | 65 |
110
+ | 1.1415 | 0.01 | 66 |
111
+ | 1.1452 | 0.01 | 67 |
112
+ | 1.1398 | 0.01 | 68 |
113
+ | 1.1360 | 0.01 | 69 |
114
+ | 1.1367 | 0.01 | 70 |
115
+ | 1.1303 | 0.01 | 71 |
116
+ | 1.1339 | 0.01 | 72 |
117
+ | 1.1298 | 0.01 | 73 |
118
+ | 1.1295 | 0.01 | 74 |
119
+ | 1.1240 | 0.01 | 75 |
120
+ | 1.1255 | 0.01 | 76 |
121
+ | 1.1218 | 0.01 | 77 |
122
+ | 1.1208 | 0.01 | 78 |
123
+ | 1.1214 | 0.01 | 79 |
124
+ | 1.1187 | 0.01 | 80 |
125
+ | 1.1186 | 0.01 | 81 |
126
+ | 1.1144 | 0.01 | 82 |
127
+ | 1.1126 | 0.01 | 83 |
128
+ | 1.1144 | 0.01 | 84 |
129
+ | 1.1124 | 0.01 | 85 |
130
+ | 1.1098 | 0.01 | 86 |
131
+ | 1.1112 | 0.01 | 87 |
132
+ | 1.1074 | 0.01 | 88 |
133
+ | 1.1061 | 0.01 | 89 |
134
+ | 1.1029 | 0.01 | 90 |
135
+ | 1.1058 | 0.01 | 91 |
136
+ | 1.1011 | 0.01 | 92 |
137
+ | 1.1054 | 0.01 | 93 |
138
+ | 1.0961 | 0.01 | 94 |
139
+ | 1.0991 | 0.01 | 95 |
140
+ | 1.0947 | 0.01 | 96 |
141
+ | 1.0995 | 0.01 | 97 |
142
+ | 1.0927 | 0.01 | 98 |
143
+ | 1.0952 | 0.01 | 99 |
144
+ | 1.0940 | 0.01 | 100 |
145
+ | 1.0883 | 0.01 | 101 |
146
+ | 1.0889 | 0.01 | 102 |
147
+ | 1.0934 | 0.01 | 103 |
148
+ | 1.0910 | 0.01 | 104 |
149
+ | 1.0883 | 0.01 | 105 |
150
+ | 1.0819 | 0.01 | 106 |
151
+ | 1.0851 | 0.01 | 107 |
152
+ | 1.0841 | 0.01 | 108 |
153
+ | 1.0817 | 0.01 | 109 |
154
+ | 1.0828 | 0.01 | 110 |
155
+ | 1.0821 | 0.01 | 111 |
156
+ | 1.0813 | 0.01 | 112 |
157
+ | 1.0800 | 0.01 | 113 |
158
+ | 1.0784 | 0.01 | 114 |
159
+ | 1.0780 | 0.01 | 115 |
160
+ | 1.0769 | 0.01 | 116 |
161
+ | 1.0795 | 0.01 | 117 |
162
+ | 1.0772 | 0.01 | 118 |
163
+ | 1.0753 | 0.01 | 119 |
164
+ | 1.0767 | 0.01 | 120 |
165
+ | 1.0764 | 0.01 | 121 |
166
+ | 1.0734 | 0.01 | 122 |
167
+ | 1.0755 | 0.01 | 123 |
168
+ | 1.0756 | 0.01 | 124 |
169
+ | 1.0717 | 0.01 | 125 |
170
+ | 1.0712 | 0.01 | 126 |
171
+ | 1.0688 | 0.01 | 127 |
172
+ | 1.0701 | 0.01 | 128 |
173
+ | 1.0672 | 0.01 | 129 |
174
+ | 1.0687 | 0.01 | 130 |
175
+ | 1.0683 | 0.01 | 131 |
176
+ | 1.0652 | 0.01 | 132 |
177
+ | 1.0659 | 0.01 | 133 |
178
+ | 1.0662 | 0.01 | 134 |
179
+ | 1.0644 | 0.01 | 135 |
180
+ | 1.0601 | 0.01 | 136 |
181
+ | 1.0605 | 0.01 | 137 |
182
+ | 1.0622 | 0.01 | 138 |
183
+ | 1.0622 | 0.01 | 139 |
184
+ | 1.0592 | 0.01 | 140 |
185
+ | 1.0624 | 0.01 | 141 |
186
+ | 1.0578 | 0.01 | 142 |
187
+ | 1.0618 | 0.01 | 143 |
188
+ | 1.0591 | 0.01 | 144 |
189
+ | 1.0573 | 0.01 | 145 |
190
+ | 1.0576 | 0.01 | 146 |
191
+ | 1.0590 | 0.01 | 147 |
192
+ | 1.0570 | 0.01 | 148 |
193
+ | 1.0539 | 0.01 | 149 |
194
+ | 0.9785 | 0.0009999999 | 150 |
195
+ | 0.9782 | 0.0009999999 | 151 |
196
+ | 0.9751 | 0.0009999999 | 152 |
197
+ | 0.9738 | 0.0009999999 | 153 |
198
+ | 0.9747 | 0.0009999999 | 154 |
199
+ | 0.9723 | 0.0009999999 | 155 |
200
+ | 0.9721 | 0.0009999999 | 156 |
201
+ | 0.9726 | 0.0009999999 | 157 |
202
+ | 0.9718 | 0.0009999999 | 158 |
203
+ | 0.9716 | 0.0009999999 | 159 |
204
+ | 0.9730 | 0.0009999999 | 160 |
205
+ | 0.9711 | 0.0009999999 | 161 |
206
+ | 0.9711 | 0.0009999999 | 162 |
207
+ | 0.9721 | 0.0009999999 | 163 |
208
+ | 0.9718 | 0.0009999999 | 164 |
209
+ | 0.9688 | 0.0009999999 | 165 |
210
+ | 0.9713 | 0.0009999999 | 166 |
211
+ | 0.9736 | 0.0009999999 | 167 |
212
+ | 0.9711 | 0.0009999999 | 168 |
213
+ | 0.9700 | 0.0009999999 | 169 |
214
+ | 0.9680 | 0.0009999999 | 170 |
215
+ | 0.9692 | 0.0009999999 | 171 |
216
+ | 0.9692 | 0.0009999999 | 172 |
217
+ | 0.9718 | 0.0009999999 | 173 |
218
+ | 0.9679 | 0.0009999999 | 174 |
219
+ | 0.9716 | 0.0009999999 | 175 |
220
+ | 0.9703 | 0.0009999999 | 176 |
221
+ | 0.9655 | 0.0009999999 | 177 |
222
+ | 0.9680 | 0.0009999999 | 178 |
223
+ | 0.9685 | 0.0009999999 | 179 |
224
+ | 0.9663 | 0.0009999999 | 180 |
225
+ | 0.9690 | 0.0009999999 | 181 |
226
+ | 0.9683 | 0.0009999999 | 182 |
227
+ | 0.9681 | 0.0009999999 | 183 |
228
+ | 0.9688 | 0.0009999999 | 184 |
229
+ | 0.9658 | 0.0009999999 | 185 |
230
+ | 0.9699 | 0.0009999999 | 186 |
231
+ | 0.9666 | 0.0009999999 | 187 |
232
+ | 0.9690 | 0.0009999999 | 188 |
233
+ | 0.9700 | 0.0009999999 | 189 |
234
+ | 0.9675 | 0.0009999999 | 190 |
235
+ | 0.9691 | 0.0009999999 | 191 |
236
+ | 0.9671 | 0.0009999999 | 192 |
237
+ | 0.9692 | 0.0009999999 | 193 |
238
+ | 0.9692 | 0.0009999999 | 194 |
239
+ | 0.9653 | 0.0009999999 | 195 |
240
+ | 0.9668 | 0.0009999999 | 196 |
241
+ | 0.9684 | 0.0009999999 | 197 |
242
+ | 0.9682 | 0.0009999999 | 198 |
243
+ | 0.9684 | 0.0009999999 | 199 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
244
 
245
 
246
  ### Framework versions
config.json CHANGED
@@ -30,5 +30,5 @@
30
  "summary_use_proj": true,
31
  "transformers_version": "4.21.3",
32
  "use_cache": true,
33
- "vocab_size": 51200
34
  }
 
30
  "summary_use_proj": true,
31
  "transformers_version": "4.21.3",
32
  "use_cache": true,
33
+ "vocab_size": 51202
34
  }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31fa567c7e05f8285efe3e08377c5f041fd269bc024f182b8137fa4f5a7035f8
3
- size 4650580080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aefdac0796093d4c4bd26411b52a4cd872c0fbdf0002c78eb4bb4f2c00fbe03
3
+ size 5043830472