pijarcandra22 commited on
Commit
53d35a4
·
verified ·
1 Parent(s): b3e8584

Model save

Browse files
Files changed (1) hide show
  1. README.md +102 -2
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3420
20
 
21
  ## Model description
22
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
- - num_epochs: 100
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
@@ -148,6 +148,106 @@ The following hyperparameters were used during training:
148
  | 0.422 | 98.0 | 105546 | 0.3423 |
149
  | 0.4214 | 99.0 | 106623 | 0.3421 |
150
  | 0.4226 | 100.0 | 107700 | 0.3420 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
 
152
 
153
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.2374
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 200
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
 
148
  | 0.422 | 98.0 | 105546 | 0.3423 |
149
  | 0.4214 | 99.0 | 106623 | 0.3421 |
150
  | 0.4226 | 100.0 | 107700 | 0.3420 |
151
+ | 0.4283 | 101.0 | 108777 | 0.3452 |
152
+ | 0.4295 | 102.0 | 109854 | 0.3435 |
153
+ | 0.4289 | 103.0 | 110931 | 0.3413 |
154
+ | 0.4239 | 104.0 | 112008 | 0.3399 |
155
+ | 0.4205 | 105.0 | 113085 | 0.3377 |
156
+ | 0.4198 | 106.0 | 114162 | 0.3344 |
157
+ | 0.4163 | 107.0 | 115239 | 0.3338 |
158
+ | 0.4157 | 108.0 | 116316 | 0.3303 |
159
+ | 0.4119 | 109.0 | 117393 | 0.3275 |
160
+ | 0.4116 | 110.0 | 118470 | 0.3239 |
161
+ | 0.4085 | 111.0 | 119547 | 0.3215 |
162
+ | 0.4055 | 112.0 | 120624 | 0.3192 |
163
+ | 0.4056 | 113.0 | 121701 | 0.3184 |
164
+ | 0.4031 | 114.0 | 122778 | 0.3181 |
165
+ | 0.4 | 115.0 | 123855 | 0.3144 |
166
+ | 0.3978 | 116.0 | 124932 | 0.3120 |
167
+ | 0.3949 | 117.0 | 126009 | 0.3108 |
168
+ | 0.3941 | 118.0 | 127086 | 0.3074 |
169
+ | 0.3908 | 119.0 | 128163 | 0.3075 |
170
+ | 0.3888 | 120.0 | 129240 | 0.3038 |
171
+ | 0.3889 | 121.0 | 130317 | 0.3013 |
172
+ | 0.3875 | 122.0 | 131394 | 0.2988 |
173
+ | 0.3849 | 123.0 | 132471 | 0.2983 |
174
+ | 0.3821 | 124.0 | 133548 | 0.2960 |
175
+ | 0.3805 | 125.0 | 134625 | 0.2965 |
176
+ | 0.38 | 126.0 | 135702 | 0.2960 |
177
+ | 0.3789 | 127.0 | 136779 | 0.2923 |
178
+ | 0.3768 | 128.0 | 137856 | 0.2921 |
179
+ | 0.3749 | 129.0 | 138933 | 0.2891 |
180
+ | 0.3715 | 130.0 | 140010 | 0.2873 |
181
+ | 0.3716 | 131.0 | 141087 | 0.2862 |
182
+ | 0.367 | 132.0 | 142164 | 0.2852 |
183
+ | 0.3674 | 133.0 | 143241 | 0.2822 |
184
+ | 0.3667 | 134.0 | 144318 | 0.2825 |
185
+ | 0.3656 | 135.0 | 145395 | 0.2801 |
186
+ | 0.3645 | 136.0 | 146472 | 0.2777 |
187
+ | 0.3643 | 137.0 | 147549 | 0.2786 |
188
+ | 0.3615 | 138.0 | 148626 | 0.2750 |
189
+ | 0.36 | 139.0 | 149703 | 0.2747 |
190
+ | 0.3605 | 140.0 | 150780 | 0.2737 |
191
+ | 0.3558 | 141.0 | 151857 | 0.2726 |
192
+ | 0.357 | 142.0 | 152934 | 0.2697 |
193
+ | 0.3553 | 143.0 | 154011 | 0.2699 |
194
+ | 0.3557 | 144.0 | 155088 | 0.2693 |
195
+ | 0.3537 | 145.0 | 156165 | 0.2680 |
196
+ | 0.352 | 146.0 | 157242 | 0.2665 |
197
+ | 0.3499 | 147.0 | 158319 | 0.2666 |
198
+ | 0.3511 | 148.0 | 159396 | 0.2637 |
199
+ | 0.3483 | 149.0 | 160473 | 0.2636 |
200
+ | 0.3479 | 150.0 | 161550 | 0.2621 |
201
+ | 0.3466 | 151.0 | 162627 | 0.2600 |
202
+ | 0.3448 | 152.0 | 163704 | 0.2610 |
203
+ | 0.345 | 153.0 | 164781 | 0.2594 |
204
+ | 0.3439 | 154.0 | 165858 | 0.2595 |
205
+ | 0.3411 | 155.0 | 166935 | 0.2579 |
206
+ | 0.3414 | 156.0 | 168012 | 0.2583 |
207
+ | 0.3408 | 157.0 | 169089 | 0.2563 |
208
+ | 0.3393 | 158.0 | 170166 | 0.2550 |
209
+ | 0.34 | 159.0 | 171243 | 0.2559 |
210
+ | 0.3382 | 160.0 | 172320 | 0.2534 |
211
+ | 0.3379 | 161.0 | 173397 | 0.2520 |
212
+ | 0.3337 | 162.0 | 174474 | 0.2519 |
213
+ | 0.3356 | 163.0 | 175551 | 0.2523 |
214
+ | 0.333 | 164.0 | 176628 | 0.2502 |
215
+ | 0.3325 | 165.0 | 177705 | 0.2505 |
216
+ | 0.3326 | 166.0 | 178782 | 0.2497 |
217
+ | 0.3328 | 167.0 | 179859 | 0.2482 |
218
+ | 0.3305 | 168.0 | 180936 | 0.2495 |
219
+ | 0.3312 | 169.0 | 182013 | 0.2472 |
220
+ | 0.3302 | 170.0 | 183090 | 0.2471 |
221
+ | 0.3286 | 171.0 | 184167 | 0.2457 |
222
+ | 0.3288 | 172.0 | 185244 | 0.2456 |
223
+ | 0.3284 | 173.0 | 186321 | 0.2463 |
224
+ | 0.3285 | 174.0 | 187398 | 0.2440 |
225
+ | 0.327 | 175.0 | 188475 | 0.2434 |
226
+ | 0.3264 | 176.0 | 189552 | 0.2430 |
227
+ | 0.3264 | 177.0 | 190629 | 0.2435 |
228
+ | 0.3248 | 178.0 | 191706 | 0.2422 |
229
+ | 0.3233 | 179.0 | 192783 | 0.2419 |
230
+ | 0.324 | 180.0 | 193860 | 0.2420 |
231
+ | 0.3247 | 181.0 | 194937 | 0.2410 |
232
+ | 0.3235 | 182.0 | 196014 | 0.2405 |
233
+ | 0.3235 | 183.0 | 197091 | 0.2405 |
234
+ | 0.3219 | 184.0 | 198168 | 0.2402 |
235
+ | 0.3219 | 185.0 | 199245 | 0.2397 |
236
+ | 0.3212 | 186.0 | 200322 | 0.2404 |
237
+ | 0.3215 | 187.0 | 201399 | 0.2387 |
238
+ | 0.3203 | 188.0 | 202476 | 0.2393 |
239
+ | 0.3207 | 189.0 | 203553 | 0.2392 |
240
+ | 0.3205 | 190.0 | 204630 | 0.2387 |
241
+ | 0.3188 | 191.0 | 205707 | 0.2382 |
242
+ | 0.3182 | 192.0 | 206784 | 0.2382 |
243
+ | 0.3209 | 193.0 | 207861 | 0.2383 |
244
+ | 0.3199 | 194.0 | 208938 | 0.2379 |
245
+ | 0.3191 | 195.0 | 210015 | 0.2376 |
246
+ | 0.3174 | 196.0 | 211092 | 0.2377 |
247
+ | 0.3158 | 197.0 | 212169 | 0.2376 |
248
+ | 0.3188 | 198.0 | 213246 | 0.2378 |
249
+ | 0.3181 | 199.0 | 214323 | 0.2373 |
250
+ | 0.3181 | 200.0 | 215400 | 0.2374 |
251
 
252
 
253
  ### Framework versions