update model card README.md
Browse files
README.md
CHANGED
@@ -13,8 +13,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
# distilroberta-base-finetuned-wikitext2
|
14 |
|
15 |
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
16 |
-
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.0244
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -43,88 +41,6 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
-
| 0.0983 | 1.0 | 11 | 0.0699 |
|
49 |
-
| 0.0481 | 2.0 | 22 | 0.0476 |
|
50 |
-
| 0.0367 | 3.0 | 33 | 0.0445 |
|
51 |
-
| 0.0264 | 4.0 | 44 | 0.0423 |
|
52 |
-
| 0.0336 | 5.0 | 55 | 0.0390 |
|
53 |
-
| 0.025 | 6.0 | 66 | 0.0410 |
|
54 |
-
| 0.0141 | 7.0 | 77 | 0.0425 |
|
55 |
-
| 0.0121 | 8.0 | 88 | 0.0371 |
|
56 |
-
| 0.0075 | 9.0 | 99 | 0.0293 |
|
57 |
-
| 0.011 | 10.0 | 110 | 0.0344 |
|
58 |
-
| 0.012 | 11.0 | 121 | 0.0304 |
|
59 |
-
| 0.0029 | 12.0 | 132 | 0.0313 |
|
60 |
-
| 0.0026 | 13.0 | 143 | 0.0303 |
|
61 |
-
| 0.0004 | 14.0 | 154 | 0.0298 |
|
62 |
-
| 0.0008 | 15.0 | 165 | 0.0288 |
|
63 |
-
| 0.0002 | 16.0 | 176 | 0.0286 |
|
64 |
-
| 0.0003 | 17.0 | 187 | 0.0319 |
|
65 |
-
| 0.0004 | 18.0 | 198 | 0.0332 |
|
66 |
-
| 0.0003 | 19.0 | 209 | 0.0423 |
|
67 |
-
| 0.0011 | 20.0 | 220 | 0.0244 |
|
68 |
-
| 0.0002 | 21.0 | 231 | 0.0255 |
|
69 |
-
| 0.0003 | 22.0 | 242 | 0.0264 |
|
70 |
-
| 0.0003 | 23.0 | 253 | 0.0239 |
|
71 |
-
| 0.0001 | 24.0 | 264 | 0.0216 |
|
72 |
-
| 0.0001 | 25.0 | 275 | 0.0212 |
|
73 |
-
| 0.0002 | 26.0 | 286 | 0.0222 |
|
74 |
-
| 0.0001 | 27.0 | 297 | 0.0226 |
|
75 |
-
| 0.0004 | 28.0 | 308 | 0.0214 |
|
76 |
-
| 0.0001 | 29.0 | 319 | 0.0223 |
|
77 |
-
| 0.0001 | 30.0 | 330 | 0.0228 |
|
78 |
-
| 0.0001 | 31.0 | 341 | 0.0225 |
|
79 |
-
| 0.0002 | 32.0 | 352 | 0.0222 |
|
80 |
-
| 0.0001 | 33.0 | 363 | 0.0233 |
|
81 |
-
| 0.0003 | 34.0 | 374 | 0.0340 |
|
82 |
-
| 0.0002 | 35.0 | 385 | 0.0321 |
|
83 |
-
| 0.0001 | 36.0 | 396 | 0.0203 |
|
84 |
-
| 0.0004 | 37.0 | 407 | 0.0205 |
|
85 |
-
| 0.0002 | 38.0 | 418 | 0.0270 |
|
86 |
-
| 0.0001 | 39.0 | 429 | 0.0204 |
|
87 |
-
| 0.0001 | 40.0 | 440 | 0.0187 |
|
88 |
-
| 0.0002 | 41.0 | 451 | 0.0223 |
|
89 |
-
| 0.0002 | 42.0 | 462 | 0.0279 |
|
90 |
-
| 0.0001 | 43.0 | 473 | 0.0302 |
|
91 |
-
| 0.0001 | 44.0 | 484 | 0.0286 |
|
92 |
-
| 0.0001 | 45.0 | 495 | 0.0202 |
|
93 |
-
| 0.0001 | 46.0 | 506 | 0.0219 |
|
94 |
-
| 0.0001 | 47.0 | 517 | 0.0227 |
|
95 |
-
| 0.0001 | 48.0 | 528 | 0.0234 |
|
96 |
-
| 0.0001 | 49.0 | 539 | 0.0235 |
|
97 |
-
| 0.0001 | 50.0 | 550 | 0.0234 |
|
98 |
-
| 0.0001 | 51.0 | 561 | 0.0234 |
|
99 |
-
| 0.0001 | 52.0 | 572 | 0.0233 |
|
100 |
-
| 0.0001 | 53.0 | 583 | 0.0237 |
|
101 |
-
| 0.0001 | 54.0 | 594 | 0.0238 |
|
102 |
-
| 0.0001 | 55.0 | 605 | 0.0237 |
|
103 |
-
| 0.0001 | 56.0 | 616 | 0.0236 |
|
104 |
-
| 0.0001 | 57.0 | 627 | 0.0238 |
|
105 |
-
| 0.0 | 58.0 | 638 | 0.0236 |
|
106 |
-
| 0.0 | 59.0 | 649 | 0.0235 |
|
107 |
-
| 0.0001 | 60.0 | 660 | 0.0236 |
|
108 |
-
| 0.0001 | 61.0 | 671 | 0.0236 |
|
109 |
-
| 0.0 | 62.0 | 682 | 0.0235 |
|
110 |
-
| 0.0001 | 63.0 | 693 | 0.0302 |
|
111 |
-
| 0.0001 | 64.0 | 704 | 0.0304 |
|
112 |
-
| 0.0001 | 65.0 | 715 | 0.0239 |
|
113 |
-
| 0.0 | 66.0 | 726 | 0.0231 |
|
114 |
-
| 0.0001 | 67.0 | 737 | 0.0229 |
|
115 |
-
| 0.0001 | 68.0 | 748 | 0.0228 |
|
116 |
-
| 0.0 | 69.0 | 759 | 0.0226 |
|
117 |
-
| 0.0004 | 70.0 | 770 | 0.0226 |
|
118 |
-
| 0.0001 | 71.0 | 781 | 0.0232 |
|
119 |
-
| 0.0001 | 72.0 | 792 | 0.0235 |
|
120 |
-
| 0.0001 | 73.0 | 803 | 0.0236 |
|
121 |
-
| 0.0002 | 74.0 | 814 | 0.0237 |
|
122 |
-
| 0.0001 | 75.0 | 825 | 0.0238 |
|
123 |
-
| 0.0001 | 76.0 | 836 | 0.0241 |
|
124 |
-
| 0.0 | 77.0 | 847 | 0.0244 |
|
125 |
-
| 0.0001 | 78.0 | 858 | 0.0244 |
|
126 |
-
| 0.0001 | 79.0 | 869 | 0.0244 |
|
127 |
-
| 0.0001 | 80.0 | 880 | 0.0244 |
|
128 |
|
129 |
|
130 |
### Framework versions
|
|
|
13 |
# distilroberta-base-finetuned-wikitext2
|
14 |
|
15 |
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
|
|
|
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
41 |
|
42 |
### Training results
|
43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
|
46 |
### Framework versions
|