Badri96 commited on
Commit
7c26f45
·
1 Parent(s): 8ab35d2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +157 -157
README.md CHANGED
@@ -16,12 +16,12 @@ 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: 0.5014
20
- - Rouge1: 80.7007
21
- - Rouge2: 77.7055
22
- - Rougel: 80.6074
23
- - Rougelsum: 80.6599
24
- - Gen Len: 14.1896
25
 
26
  ## Model description
27
 
@@ -53,161 +53,161 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
- | No log | 1.0 | 113 | 0.7017 | 81.0635 | 78.1449 | 80.9667 | 80.9999 | 15.6275 |
57
- | No log | 2.0 | 226 | 0.6517 | 81.5783 | 78.7335 | 81.4946 | 81.5291 | 15.4715 |
58
- | No log | 3.0 | 339 | 0.6311 | 81.4871 | 78.6306 | 81.4069 | 81.44 | 15.5134 |
59
- | No log | 4.0 | 452 | 0.6078 | 81.6796 | 78.8341 | 81.5944 | 81.64 | 15.4631 |
60
- | 0.6475 | 5.0 | 565 | 0.5847 | 81.8427 | 78.9953 | 81.7052 | 81.7742 | 15.3725 |
61
- | 0.6475 | 6.0 | 678 | 0.5570 | 81.8141 | 79.0095 | 81.7339 | 81.7697 | 15.4094 |
62
- | 0.6475 | 7.0 | 791 | 0.5455 | 81.8302 | 79.0095 | 81.7133 | 81.7556 | 15.3305 |
63
- | 0.6475 | 8.0 | 904 | 0.5472 | 81.5207 | 78.6763 | 81.4138 | 81.4554 | 15.448 |
64
- | 0.5443 | 9.0 | 1017 | 0.5397 | 81.609 | 78.7549 | 81.5048 | 81.5431 | 15.3993 |
65
- | 0.5443 | 10.0 | 1130 | 0.5218 | 81.7084 | 78.8713 | 81.589 | 81.6424 | 15.3205 |
66
- | 0.5443 | 11.0 | 1243 | 0.5151 | 81.6273 | 78.7934 | 81.5383 | 81.5747 | 15.2819 |
67
- | 0.5443 | 12.0 | 1356 | 0.5115 | 81.5657 | 78.7177 | 81.4516 | 81.5064 | 15.2735 |
68
- | 0.5443 | 13.0 | 1469 | 0.5102 | 81.661 | 78.8428 | 81.5591 | 81.6111 | 15.2701 |
69
- | 0.4895 | 14.0 | 1582 | 0.4960 | 81.6266 | 78.8455 | 81.5429 | 81.6015 | 15.203 |
70
- | 0.4895 | 15.0 | 1695 | 0.4943 | 81.6268 | 78.8026 | 81.5438 | 81.5988 | 15.1258 |
71
- | 0.4895 | 16.0 | 1808 | 0.4980 | 81.5377 | 78.7069 | 81.4363 | 81.498 | 15.1946 |
72
- | 0.4895 | 17.0 | 1921 | 0.4976 | 81.5423 | 78.718 | 81.4204 | 81.5051 | 15.1594 |
73
- | 0.4467 | 18.0 | 2034 | 0.4883 | 81.7449 | 78.9661 | 81.6413 | 81.6727 | 15.0117 |
74
- | 0.4467 | 19.0 | 2147 | 0.4792 | 81.794 | 78.9978 | 81.6831 | 81.7207 | 15.0134 |
75
- | 0.4467 | 20.0 | 2260 | 0.4920 | 81.6468 | 78.8409 | 81.5271 | 81.6153 | 15.1057 |
76
- | 0.4467 | 21.0 | 2373 | 0.4857 | 81.5938 | 78.7878 | 81.4819 | 81.566 | 15.151 |
77
- | 0.4467 | 22.0 | 2486 | 0.4792 | 81.4496 | 78.6376 | 81.3382 | 81.4158 | 14.9782 |
78
- | 0.4161 | 23.0 | 2599 | 0.4779 | 81.5665 | 78.7694 | 81.4498 | 81.5344 | 14.9513 |
79
- | 0.4161 | 24.0 | 2712 | 0.4797 | 81.4723 | 78.6709 | 81.3661 | 81.4269 | 14.8138 |
80
- | 0.4161 | 25.0 | 2825 | 0.4709 | 81.553 | 78.7384 | 81.425 | 81.4748 | 14.6879 |
81
- | 0.4161 | 26.0 | 2938 | 0.4795 | 81.5805 | 78.7845 | 81.4766 | 81.558 | 14.995 |
82
- | 0.3947 | 27.0 | 3051 | 0.4758 | 81.7247 | 78.9725 | 81.6286 | 81.6803 | 14.9698 |
83
- | 0.3947 | 28.0 | 3164 | 0.4743 | 81.6758 | 78.8846 | 81.5553 | 81.5847 | 14.7886 |
84
- | 0.3947 | 29.0 | 3277 | 0.4754 | 81.6295 | 78.8514 | 81.5224 | 81.5945 | 14.8809 |
85
- | 0.3947 | 30.0 | 3390 | 0.4670 | 81.8742 | 79.1251 | 81.7733 | 81.8371 | 14.7164 |
86
- | 0.3747 | 31.0 | 3503 | 0.4697 | 81.1859 | 78.2891 | 81.0554 | 81.1109 | 14.599 |
87
- | 0.3747 | 32.0 | 3616 | 0.4605 | 81.2226 | 78.37 | 81.1093 | 81.1929 | 14.4295 |
88
- | 0.3747 | 33.0 | 3729 | 0.4619 | 81.5644 | 78.7933 | 81.4874 | 81.5347 | 14.6292 |
89
- | 0.3747 | 34.0 | 3842 | 0.4731 | 81.5654 | 78.7905 | 81.4349 | 81.5054 | 14.7332 |
90
- | 0.3747 | 35.0 | 3955 | 0.4719 | 81.5362 | 78.7503 | 81.4438 | 81.4998 | 14.7601 |
91
- | 0.3526 | 36.0 | 4068 | 0.4612 | 81.0437 | 78.1436 | 80.8987 | 80.9643 | 14.5419 |
92
- | 0.3526 | 37.0 | 4181 | 0.4585 | 81.0643 | 78.1093 | 80.949 | 81.0109 | 14.396 |
93
- | 0.3526 | 38.0 | 4294 | 0.4683 | 81.4959 | 78.6976 | 81.3977 | 81.4736 | 14.6762 |
94
- | 0.3526 | 39.0 | 4407 | 0.4668 | 81.7042 | 78.881 | 81.6316 | 81.6639 | 14.6091 |
95
- | 0.3414 | 40.0 | 4520 | 0.4636 | 81.4618 | 78.6496 | 81.416 | 81.4417 | 14.5738 |
96
- | 0.3414 | 41.0 | 4633 | 0.4676 | 81.6793 | 78.8615 | 81.6185 | 81.6472 | 14.6913 |
97
- | 0.3414 | 42.0 | 4746 | 0.4693 | 81.6687 | 78.8342 | 81.5855 | 81.6019 | 14.6695 |
98
- | 0.3414 | 43.0 | 4859 | 0.4651 | 81.4768 | 78.6564 | 81.3981 | 81.4409 | 14.5084 |
99
- | 0.3414 | 44.0 | 4972 | 0.4689 | 81.6287 | 78.7968 | 81.5322 | 81.5729 | 14.6023 |
100
- | 0.3234 | 45.0 | 5085 | 0.4699 | 81.954 | 79.17 | 81.9092 | 81.9191 | 14.7198 |
101
- | 0.3234 | 46.0 | 5198 | 0.4705 | 81.8616 | 79.0683 | 81.7918 | 81.8077 | 14.7114 |
102
- | 0.3234 | 47.0 | 5311 | 0.4703 | 81.5751 | 78.7179 | 81.4925 | 81.5411 | 14.599 |
103
- | 0.3234 | 48.0 | 5424 | 0.4680 | 81.4306 | 78.575 | 81.3146 | 81.3871 | 14.5352 |
104
- | 0.3099 | 49.0 | 5537 | 0.4675 | 81.4833 | 78.6257 | 81.4105 | 81.4534 | 14.5201 |
105
- | 0.3099 | 50.0 | 5650 | 0.4733 | 81.4002 | 78.5302 | 81.3347 | 81.3813 | 14.6812 |
106
- | 0.3099 | 51.0 | 5763 | 0.4635 | 81.4009 | 78.5798 | 81.3473 | 81.3775 | 14.4631 |
107
- | 0.3099 | 52.0 | 5876 | 0.4620 | 81.218 | 78.3388 | 81.1651 | 81.1896 | 14.349 |
108
- | 0.3099 | 53.0 | 5989 | 0.4729 | 81.5851 | 78.7074 | 81.5011 | 81.4991 | 14.6594 |
109
- | 0.3063 | 54.0 | 6102 | 0.4678 | 81.2912 | 78.393 | 81.2207 | 81.2278 | 14.4933 |
110
- | 0.3063 | 55.0 | 6215 | 0.4667 | 80.9283 | 77.9825 | 80.8417 | 80.8696 | 14.3977 |
111
- | 0.3063 | 56.0 | 6328 | 0.4675 | 81.3406 | 78.4054 | 81.2216 | 81.2743 | 14.495 |
112
- | 0.3063 | 57.0 | 6441 | 0.4697 | 81.2394 | 78.3552 | 81.1557 | 81.1731 | 14.6158 |
113
- | 0.2896 | 58.0 | 6554 | 0.4682 | 81.0372 | 78.102 | 80.9262 | 80.9711 | 14.4597 |
114
- | 0.2896 | 59.0 | 6667 | 0.4657 | 81.2605 | 78.3426 | 81.1561 | 81.2182 | 14.3708 |
115
- | 0.2896 | 60.0 | 6780 | 0.4721 | 81.276 | 78.3497 | 81.1652 | 81.2267 | 14.406 |
116
- | 0.2896 | 61.0 | 6893 | 0.4675 | 81.3411 | 78.3745 | 81.2103 | 81.2746 | 14.396 |
117
- | 0.2804 | 62.0 | 7006 | 0.4733 | 81.3682 | 78.4648 | 81.302 | 81.3236 | 14.4748 |
118
- | 0.2804 | 63.0 | 7119 | 0.4715 | 81.2726 | 78.3662 | 81.2123 | 81.2368 | 14.4161 |
119
- | 0.2804 | 64.0 | 7232 | 0.4737 | 81.2864 | 78.3979 | 81.2227 | 81.2527 | 14.4144 |
120
- | 0.2804 | 65.0 | 7345 | 0.4715 | 81.0116 | 78.0709 | 80.9134 | 80.9608 | 14.3775 |
121
- | 0.2804 | 66.0 | 7458 | 0.4740 | 81.1628 | 78.2809 | 81.0923 | 81.1558 | 14.4346 |
122
- | 0.2762 | 67.0 | 7571 | 0.4721 | 81.0565 | 78.1141 | 80.9377 | 80.9888 | 14.349 |
123
- | 0.2762 | 68.0 | 7684 | 0.4796 | 81.2601 | 78.3608 | 81.1735 | 81.2214 | 14.443 |
124
- | 0.2762 | 69.0 | 7797 | 0.4794 | 81.3713 | 78.487 | 81.2873 | 81.3322 | 14.4178 |
125
- | 0.2762 | 70.0 | 7910 | 0.4795 | 81.0543 | 78.1194 | 80.9682 | 80.998 | 14.4178 |
126
- | 0.2719 | 71.0 | 8023 | 0.4753 | 80.9782 | 78.0445 | 80.8792 | 80.9066 | 14.1997 |
127
- | 0.2719 | 72.0 | 8136 | 0.4760 | 81.0655 | 78.154 | 80.9788 | 81.0196 | 14.2718 |
128
- | 0.2719 | 73.0 | 8249 | 0.4787 | 80.9442 | 78.0216 | 80.8511 | 80.897 | 14.2919 |
129
- | 0.2719 | 74.0 | 8362 | 0.4731 | 80.8758 | 77.9381 | 80.7821 | 80.815 | 14.2164 |
130
- | 0.2719 | 75.0 | 8475 | 0.4783 | 81.2242 | 78.3252 | 81.1301 | 81.1913 | 14.2768 |
131
- | 0.2569 | 76.0 | 8588 | 0.4781 | 80.896 | 77.994 | 80.8191 | 80.8648 | 14.302 |
132
- | 0.2569 | 77.0 | 8701 | 0.4809 | 81.0472 | 78.1495 | 80.9702 | 81.0179 | 14.3389 |
133
- | 0.2569 | 78.0 | 8814 | 0.4785 | 80.857 | 77.9309 | 80.7693 | 80.8419 | 14.2836 |
134
- | 0.2569 | 79.0 | 8927 | 0.4792 | 80.8755 | 77.9471 | 80.7841 | 80.8473 | 14.2752 |
135
- | 0.2534 | 80.0 | 9040 | 0.4758 | 80.9519 | 78.027 | 80.8659 | 80.9368 | 14.2517 |
136
- | 0.2534 | 81.0 | 9153 | 0.4787 | 80.9038 | 77.9536 | 80.8368 | 80.8828 | 14.25 |
137
- | 0.2534 | 82.0 | 9266 | 0.4798 | 81.1017 | 78.1787 | 81.0284 | 81.0777 | 14.2483 |
138
- | 0.2534 | 83.0 | 9379 | 0.4831 | 81.0515 | 78.1389 | 80.9934 | 81.0426 | 14.2198 |
139
- | 0.2534 | 84.0 | 9492 | 0.4817 | 81.1362 | 78.163 | 81.0576 | 81.0864 | 14.1946 |
140
- | 0.2486 | 85.0 | 9605 | 0.4806 | 81.0428 | 78.0945 | 80.9782 | 81.0162 | 14.2265 |
141
- | 0.2486 | 86.0 | 9718 | 0.4801 | 80.9022 | 77.928 | 80.8127 | 80.864 | 14.1426 |
142
- | 0.2486 | 87.0 | 9831 | 0.4819 | 80.956 | 77.9852 | 80.8694 | 80.9226 | 14.1275 |
143
- | 0.2486 | 88.0 | 9944 | 0.4885 | 80.839 | 77.8582 | 80.7267 | 80.8084 | 14.3171 |
144
- | 0.2465 | 89.0 | 10057 | 0.4819 | 81.0608 | 78.1257 | 80.9626 | 81.0143 | 14.1896 |
145
- | 0.2465 | 90.0 | 10170 | 0.4873 | 81.0464 | 78.0723 | 80.9607 | 80.9865 | 14.2013 |
146
- | 0.2465 | 91.0 | 10283 | 0.4856 | 80.7067 | 77.6649 | 80.5788 | 80.6093 | 14.0654 |
147
- | 0.2465 | 92.0 | 10396 | 0.4899 | 80.9094 | 77.9167 | 80.8127 | 80.86 | 14.2215 |
148
- | 0.2419 | 93.0 | 10509 | 0.4866 | 80.9372 | 77.97 | 80.8497 | 80.9018 | 14.2081 |
149
- | 0.2419 | 94.0 | 10622 | 0.4875 | 80.9954 | 78.0346 | 80.9023 | 80.974 | 14.1728 |
150
- | 0.2419 | 95.0 | 10735 | 0.4937 | 80.8705 | 77.8797 | 80.7692 | 80.8243 | 14.2483 |
151
- | 0.2419 | 96.0 | 10848 | 0.4880 | 81.0544 | 78.1088 | 80.9748 | 81.0183 | 14.1628 |
152
- | 0.2419 | 97.0 | 10961 | 0.4891 | 81.1135 | 78.1525 | 81.0185 | 81.0669 | 14.1678 |
153
- | 0.2335 | 98.0 | 11074 | 0.4964 | 80.8705 | 77.9064 | 80.7832 | 80.8326 | 14.2399 |
154
- | 0.2335 | 99.0 | 11187 | 0.4877 | 81.1125 | 78.1294 | 81.0186 | 81.0378 | 14.0839 |
155
- | 0.2335 | 100.0 | 11300 | 0.4847 | 81.1092 | 78.1097 | 80.9936 | 81.0366 | 14.0789 |
156
- | 0.2335 | 101.0 | 11413 | 0.4879 | 81.0236 | 78.0498 | 80.9249 | 80.9553 | 14.0956 |
157
- | 0.2361 | 102.0 | 11526 | 0.4921 | 80.9856 | 78.0236 | 80.8902 | 80.9409 | 14.1795 |
158
- | 0.2361 | 103.0 | 11639 | 0.4847 | 80.9714 | 77.9627 | 80.8699 | 80.895 | 14.0268 |
159
- | 0.2361 | 104.0 | 11752 | 0.4931 | 80.919 | 77.9621 | 80.8217 | 80.891 | 14.1779 |
160
- | 0.2361 | 105.0 | 11865 | 0.4938 | 80.9723 | 78.0063 | 80.8732 | 80.9379 | 14.1745 |
161
- | 0.2361 | 106.0 | 11978 | 0.4908 | 80.8576 | 77.8395 | 80.7702 | 80.7915 | 14.1007 |
162
- | 0.2308 | 107.0 | 12091 | 0.4940 | 80.9458 | 77.9603 | 80.8364 | 80.9107 | 14.1879 |
163
- | 0.2308 | 108.0 | 12204 | 0.4927 | 80.9133 | 77.9714 | 80.8193 | 80.8528 | 14.1628 |
164
- | 0.2308 | 109.0 | 12317 | 0.4952 | 80.945 | 77.9819 | 80.8344 | 80.8928 | 14.1728 |
165
- | 0.2308 | 110.0 | 12430 | 0.4982 | 81.0463 | 78.0845 | 80.9462 | 81.0033 | 14.2097 |
166
- | 0.2243 | 111.0 | 12543 | 0.4939 | 80.9735 | 78.0194 | 80.8741 | 80.9072 | 14.1258 |
167
- | 0.2243 | 112.0 | 12656 | 0.4961 | 81.0462 | 78.1007 | 80.9367 | 80.9864 | 14.146 |
168
- | 0.2243 | 113.0 | 12769 | 0.4941 | 80.9121 | 77.9411 | 80.807 | 80.8565 | 14.1628 |
169
- | 0.2243 | 114.0 | 12882 | 0.4944 | 80.9982 | 78.0371 | 80.8733 | 80.9343 | 14.1477 |
170
- | 0.2243 | 115.0 | 12995 | 0.4961 | 81.0267 | 78.0677 | 80.9131 | 80.9631 | 14.1359 |
171
- | 0.2249 | 116.0 | 13108 | 0.4984 | 81.0128 | 78.0579 | 80.9284 | 80.9694 | 14.1493 |
172
- | 0.2249 | 117.0 | 13221 | 0.4970 | 81.047 | 78.0835 | 80.9454 | 80.9865 | 14.1493 |
173
- | 0.2249 | 118.0 | 13334 | 0.4990 | 81.044 | 78.0909 | 80.9446 | 80.9882 | 14.1527 |
174
- | 0.2249 | 119.0 | 13447 | 0.4982 | 80.9678 | 77.9996 | 80.8533 | 80.9005 | 14.1695 |
175
- | 0.2215 | 120.0 | 13560 | 0.4988 | 81.0083 | 78.0452 | 80.8916 | 80.9318 | 14.1577 |
176
- | 0.2215 | 121.0 | 13673 | 0.4987 | 80.9856 | 78.0095 | 80.8751 | 80.9184 | 14.1762 |
177
- | 0.2215 | 122.0 | 13786 | 0.4963 | 81.0485 | 78.0746 | 80.9287 | 80.9704 | 14.1141 |
178
- | 0.2215 | 123.0 | 13899 | 0.4992 | 80.9563 | 77.9916 | 80.8543 | 80.9064 | 14.1678 |
179
- | 0.2237 | 124.0 | 14012 | 0.4977 | 80.933 | 77.9485 | 80.8164 | 80.8626 | 14.1292 |
180
- | 0.2237 | 125.0 | 14125 | 0.4984 | 80.9305 | 77.9496 | 80.8289 | 80.8819 | 14.1544 |
181
- | 0.2237 | 126.0 | 14238 | 0.4977 | 80.9771 | 78.0336 | 80.8843 | 80.9234 | 14.099 |
182
- | 0.2237 | 127.0 | 14351 | 0.4979 | 80.9985 | 78.0357 | 80.8735 | 80.9143 | 14.1141 |
183
- | 0.2237 | 128.0 | 14464 | 0.5004 | 80.9629 | 78.0026 | 80.8532 | 80.8912 | 14.1174 |
184
- | 0.2155 | 129.0 | 14577 | 0.5002 | 81.0203 | 78.047 | 80.9066 | 80.9457 | 14.1191 |
185
- | 0.2155 | 130.0 | 14690 | 0.5001 | 80.8454 | 77.8526 | 80.7384 | 80.7702 | 14.193 |
186
- | 0.2155 | 131.0 | 14803 | 0.5022 | 80.8198 | 77.8412 | 80.7083 | 80.7616 | 14.2081 |
187
- | 0.2155 | 132.0 | 14916 | 0.5002 | 80.9561 | 77.9824 | 80.8435 | 80.8732 | 14.1275 |
188
- | 0.2164 | 133.0 | 15029 | 0.5000 | 80.9442 | 77.975 | 80.8337 | 80.8632 | 14.1292 |
189
- | 0.2164 | 134.0 | 15142 | 0.4997 | 80.9475 | 77.9751 | 80.8352 | 80.8692 | 14.1292 |
190
- | 0.2164 | 135.0 | 15255 | 0.5007 | 80.9746 | 78.0002 | 80.8605 | 80.8938 | 14.1309 |
191
- | 0.2164 | 136.0 | 15368 | 0.5018 | 80.8197 | 77.8293 | 80.7192 | 80.7516 | 14.1946 |
192
- | 0.2164 | 137.0 | 15481 | 0.5030 | 80.7727 | 77.7707 | 80.6702 | 80.7192 | 14.198 |
193
- | 0.2242 | 138.0 | 15594 | 0.5022 | 80.7727 | 77.7707 | 80.6702 | 80.7192 | 14.198 |
194
- | 0.2242 | 139.0 | 15707 | 0.5021 | 80.773 | 77.7684 | 80.6588 | 80.7279 | 14.2114 |
195
- | 0.2242 | 140.0 | 15820 | 0.5023 | 80.7706 | 77.7618 | 80.6533 | 80.7225 | 14.2131 |
196
- | 0.2242 | 141.0 | 15933 | 0.5017 | 80.7715 | 77.7674 | 80.6643 | 80.7168 | 14.1997 |
197
- | 0.2186 | 142.0 | 16046 | 0.5018 | 80.7657 | 77.7612 | 80.6611 | 80.7103 | 14.1997 |
198
- | 0.2186 | 143.0 | 16159 | 0.5016 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
199
- | 0.2186 | 144.0 | 16272 | 0.5019 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
200
- | 0.2186 | 145.0 | 16385 | 0.5014 | 80.752 | 77.7585 | 80.6707 | 80.7102 | 14.1795 |
201
- | 0.2186 | 146.0 | 16498 | 0.5014 | 80.752 | 77.7585 | 80.6707 | 80.7102 | 14.1795 |
202
- | 0.2114 | 147.0 | 16611 | 0.5015 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
203
- | 0.2114 | 148.0 | 16724 | 0.5015 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
204
- | 0.2114 | 149.0 | 16837 | 0.5014 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
205
- | 0.2114 | 150.0 | 16950 | 0.5014 | 80.7007 | 77.7055 | 80.6074 | 80.6599 | 14.1896 |
206
 
207
 
208
  ### Framework versions
209
 
210
- - Transformers 4.25.1
211
  - Pytorch 1.13.1+cu116
212
  - Datasets 2.8.0
213
  - Tokenizers 0.13.2
 
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: 0.5052
20
+ - Rouge1: 80.9236
21
+ - Rouge2: 77.7423
22
+ - Rougel: 80.8206
23
+ - Rougelsum: 80.7904
24
+ - Gen Len: 14.1779
25
 
26
  ## Model description
27
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
55
  |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
56
+ | No log | 1.0 | 113 | 0.7382 | 80.9417 | 77.9703 | 80.8186 | 80.8086 | 15.6544 |
57
+ | No log | 2.0 | 226 | 0.6697 | 81.2867 | 78.3445 | 81.1465 | 81.1451 | 15.5822 |
58
+ | No log | 3.0 | 339 | 0.6425 | 81.5712 | 78.652 | 81.4339 | 81.429 | 15.4832 |
59
+ | No log | 4.0 | 452 | 0.6141 | 81.5345 | 78.6093 | 81.388 | 81.3867 | 15.505 |
60
+ | 0.7038 | 5.0 | 565 | 0.5946 | 81.62 | 78.694 | 81.4761 | 81.4744 | 15.4732 |
61
+ | 0.7038 | 6.0 | 678 | 0.5735 | 81.7125 | 78.8199 | 81.5754 | 81.551 | 15.4581 |
62
+ | 0.7038 | 7.0 | 791 | 0.5605 | 81.8192 | 78.9325 | 81.6858 | 81.667 | 15.4346 |
63
+ | 0.7038 | 8.0 | 904 | 0.5514 | 81.7373 | 78.844 | 81.6007 | 81.5835 | 15.4413 |
64
+ | 0.5643 | 9.0 | 1017 | 0.5391 | 81.5611 | 78.6177 | 81.4249 | 81.4344 | 15.4262 |
65
+ | 0.5643 | 10.0 | 1130 | 0.5404 | 81.5494 | 78.6031 | 81.4109 | 81.4118 | 15.4446 |
66
+ | 0.5643 | 11.0 | 1243 | 0.5246 | 81.5887 | 78.6553 | 81.4472 | 81.4576 | 15.3792 |
67
+ | 0.5643 | 12.0 | 1356 | 0.5211 | 81.6154 | 78.7039 | 81.4767 | 81.4889 | 15.3557 |
68
+ | 0.5643 | 13.0 | 1469 | 0.5153 | 81.6735 | 78.788 | 81.5512 | 81.5444 | 15.344 |
69
+ | 0.4973 | 14.0 | 1582 | 0.5177 | 81.5925 | 78.6616 | 81.455 | 81.4675 | 15.3658 |
70
+ | 0.4973 | 15.0 | 1695 | 0.5045 | 81.6449 | 78.765 | 81.4978 | 81.5067 | 15.307 |
71
+ | 0.4973 | 16.0 | 1808 | 0.4992 | 81.7112 | 78.837 | 81.566 | 81.5376 | 15.2064 |
72
+ | 0.4973 | 17.0 | 1921 | 0.4959 | 81.6909 | 78.7936 | 81.5424 | 81.5077 | 15.2164 |
73
+ | 0.4552 | 18.0 | 2034 | 0.4911 | 81.6722 | 78.7767 | 81.52 | 81.4903 | 15.1695 |
74
+ | 0.4552 | 19.0 | 2147 | 0.4913 | 81.4996 | 78.5783 | 81.3478 | 81.3389 | 15.104 |
75
+ | 0.4552 | 20.0 | 2260 | 0.4955 | 81.6108 | 78.6825 | 81.4466 | 81.4314 | 15.1661 |
76
+ | 0.4552 | 21.0 | 2373 | 0.4836 | 81.6953 | 78.8207 | 81.55 | 81.5406 | 14.9849 |
77
+ | 0.4552 | 22.0 | 2486 | 0.4912 | 81.4975 | 78.556 | 81.3561 | 81.3342 | 15.1426 |
78
+ | 0.4228 | 23.0 | 2599 | 0.4792 | 81.6605 | 78.7533 | 81.5012 | 81.471 | 14.9664 |
79
+ | 0.4228 | 24.0 | 2712 | 0.4810 | 81.5406 | 78.6191 | 81.3824 | 81.3599 | 15.0503 |
80
+ | 0.4228 | 25.0 | 2825 | 0.4839 | 81.4879 | 78.5515 | 81.3279 | 81.3133 | 15.0587 |
81
+ | 0.4228 | 26.0 | 2938 | 0.4845 | 81.5023 | 78.5901 | 81.3549 | 81.3302 | 15.057 |
82
+ | 0.3956 | 27.0 | 3051 | 0.4786 | 81.6587 | 78.7411 | 81.5187 | 81.4889 | 14.9631 |
83
+ | 0.3956 | 28.0 | 3164 | 0.4773 | 81.6287 | 78.7009 | 81.4895 | 81.466 | 14.7886 |
84
+ | 0.3956 | 29.0 | 3277 | 0.4748 | 81.4407 | 78.4122 | 81.2952 | 81.2883 | 14.8993 |
85
+ | 0.3956 | 30.0 | 3390 | 0.4683 | 81.4844 | 78.5229 | 81.3286 | 81.3511 | 14.7819 |
86
+ | 0.3737 | 31.0 | 3503 | 0.4731 | 81.7914 | 78.903 | 81.64 | 81.6607 | 14.9966 |
87
+ | 0.3737 | 32.0 | 3616 | 0.4700 | 81.6727 | 78.7654 | 81.5206 | 81.5445 | 14.9312 |
88
+ | 0.3737 | 33.0 | 3729 | 0.4643 | 81.5736 | 78.5754 | 81.3911 | 81.4012 | 14.6326 |
89
+ | 0.3737 | 34.0 | 3842 | 0.4696 | 81.4427 | 78.4461 | 81.2729 | 81.2969 | 14.745 |
90
+ | 0.3737 | 35.0 | 3955 | 0.4716 | 81.1949 | 78.1713 | 81.0269 | 81.0426 | 14.8221 |
91
+ | 0.3583 | 36.0 | 4068 | 0.4624 | 81.3071 | 78.3268 | 81.1715 | 81.1617 | 14.4513 |
92
+ | 0.3583 | 37.0 | 4181 | 0.4714 | 81.3177 | 78.4078 | 81.1883 | 81.1841 | 14.7097 |
93
+ | 0.3583 | 38.0 | 4294 | 0.4728 | 81.5287 | 78.5252 | 81.3597 | 81.3845 | 14.844 |
94
+ | 0.3583 | 39.0 | 4407 | 0.4713 | 81.4634 | 78.4771 | 81.3509 | 81.3556 | 14.6695 |
95
+ | 0.3375 | 40.0 | 4520 | 0.4654 | 81.3832 | 78.3693 | 81.27 | 81.2685 | 14.5872 |
96
+ | 0.3375 | 41.0 | 4633 | 0.4648 | 81.399 | 78.4073 | 81.2825 | 81.2871 | 14.5151 |
97
+ | 0.3375 | 42.0 | 4746 | 0.4693 | 81.2007 | 78.1701 | 81.0741 | 81.0933 | 14.6141 |
98
+ | 0.3375 | 43.0 | 4859 | 0.4684 | 81.3907 | 78.361 | 81.2693 | 81.281 | 14.604 |
99
+ | 0.3375 | 44.0 | 4972 | 0.4771 | 81.1561 | 78.1279 | 81.0488 | 81.0601 | 14.6711 |
100
+ | 0.3267 | 45.0 | 5085 | 0.4703 | 81.3129 | 78.2699 | 81.1668 | 81.1773 | 14.5956 |
101
+ | 0.3267 | 46.0 | 5198 | 0.4712 | 81.4137 | 78.3788 | 81.2652 | 81.2705 | 14.5721 |
102
+ | 0.3267 | 47.0 | 5311 | 0.4687 | 81.3712 | 78.3504 | 81.2388 | 81.2591 | 14.6074 |
103
+ | 0.3267 | 48.0 | 5424 | 0.4721 | 81.3684 | 78.3556 | 81.2373 | 81.2642 | 14.6258 |
104
+ | 0.3129 | 49.0 | 5537 | 0.4689 | 81.6204 | 78.6147 | 81.4938 | 81.4771 | 14.5218 |
105
+ | 0.3129 | 50.0 | 5650 | 0.4708 | 81.5402 | 78.5868 | 81.447 | 81.4244 | 14.5101 |
106
+ | 0.3129 | 51.0 | 5763 | 0.4749 | 81.4549 | 78.4157 | 81.3345 | 81.3205 | 14.5101 |
107
+ | 0.3129 | 52.0 | 5876 | 0.4738 | 81.6945 | 78.7128 | 81.5816 | 81.5629 | 14.5872 |
108
+ | 0.3129 | 53.0 | 5989 | 0.4746 | 81.3836 | 78.3179 | 81.2516 | 81.2246 | 14.5856 |
109
+ | 0.3042 | 54.0 | 6102 | 0.4744 | 81.298 | 78.2619 | 81.1852 | 81.1574 | 14.7047 |
110
+ | 0.3042 | 55.0 | 6215 | 0.4759 | 81.4363 | 78.391 | 81.3187 | 81.2923 | 14.6158 |
111
+ | 0.3042 | 56.0 | 6328 | 0.4758 | 81.5105 | 78.5076 | 81.3797 | 81.3731 | 14.5554 |
112
+ | 0.3042 | 57.0 | 6441 | 0.4689 | 81.2123 | 78.1772 | 81.0949 | 81.0764 | 14.4748 |
113
+ | 0.2998 | 58.0 | 6554 | 0.4747 | 81.6333 | 78.6042 | 81.4941 | 81.4904 | 14.5101 |
114
+ | 0.2998 | 59.0 | 6667 | 0.4725 | 81.6537 | 78.6223 | 81.5245 | 81.5257 | 14.4161 |
115
+ | 0.2998 | 60.0 | 6780 | 0.4801 | 81.3813 | 78.3235 | 81.2512 | 81.2563 | 14.6158 |
116
+ | 0.2998 | 61.0 | 6893 | 0.4743 | 81.3165 | 78.2823 | 81.1662 | 81.1994 | 14.5285 |
117
+ | 0.2832 | 62.0 | 7006 | 0.4755 | 81.2354 | 78.1809 | 81.1195 | 81.1213 | 14.5336 |
118
+ | 0.2832 | 63.0 | 7119 | 0.4775 | 81.1219 | 78.0462 | 80.9896 | 81.0102 | 14.448 |
119
+ | 0.2832 | 64.0 | 7232 | 0.4722 | 81.0257 | 77.9035 | 80.9074 | 80.8735 | 14.3003 |
120
+ | 0.2832 | 65.0 | 7345 | 0.4741 | 81.285 | 78.2194 | 81.1585 | 81.1539 | 14.3658 |
121
+ | 0.2832 | 66.0 | 7458 | 0.4798 | 81.2418 | 78.1978 | 81.1122 | 81.1268 | 14.5067 |
122
+ | 0.2752 | 67.0 | 7571 | 0.4815 | 81.3733 | 78.3196 | 81.2313 | 81.2293 | 14.4513 |
123
+ | 0.2752 | 68.0 | 7684 | 0.4777 | 81.0844 | 77.9982 | 80.957 | 80.9482 | 14.4581 |
124
+ | 0.2752 | 69.0 | 7797 | 0.4793 | 81.0963 | 78.0424 | 80.9662 | 80.9684 | 14.3893 |
125
+ | 0.2752 | 70.0 | 7910 | 0.4802 | 81.2234 | 78.1559 | 81.087 | 81.0938 | 14.3993 |
126
+ | 0.2669 | 71.0 | 8023 | 0.4755 | 81.2257 | 78.1822 | 81.08 | 81.1022 | 14.3876 |
127
+ | 0.2669 | 72.0 | 8136 | 0.4759 | 81.2805 | 78.2107 | 81.126 | 81.1468 | 14.4346 |
128
+ | 0.2669 | 73.0 | 8249 | 0.4779 | 81.1905 | 78.121 | 81.0565 | 81.0748 | 14.3943 |
129
+ | 0.2669 | 74.0 | 8362 | 0.4815 | 81.1247 | 78.0522 | 80.9739 | 81.0007 | 14.4111 |
130
+ | 0.2669 | 75.0 | 8475 | 0.4830 | 81.1285 | 78.0634 | 81.0054 | 81.0045 | 14.5034 |
131
+ | 0.261 | 76.0 | 8588 | 0.4789 | 81.2387 | 78.188 | 81.125 | 81.136 | 14.4211 |
132
+ | 0.261 | 77.0 | 8701 | 0.4862 | 81.3435 | 78.278 | 81.1996 | 81.2035 | 14.5168 |
133
+ | 0.261 | 78.0 | 8814 | 0.4863 | 81.3371 | 78.3136 | 81.2554 | 81.2382 | 14.4782 |
134
+ | 0.261 | 79.0 | 8927 | 0.4784 | 81.1271 | 78.0047 | 81.01 | 80.9843 | 14.2886 |
135
+ | 0.258 | 80.0 | 9040 | 0.4800 | 81.1415 | 78.0391 | 81.0219 | 81.0241 | 14.4597 |
136
+ | 0.258 | 81.0 | 9153 | 0.4816 | 81.1872 | 78.0736 | 81.1054 | 81.0675 | 14.2936 |
137
+ | 0.258 | 82.0 | 9266 | 0.4807 | 81.0866 | 77.9625 | 80.9849 | 80.9571 | 14.3339 |
138
+ | 0.258 | 83.0 | 9379 | 0.4900 | 81.2124 | 78.068 | 81.1026 | 81.0832 | 14.5772 |
139
+ | 0.258 | 84.0 | 9492 | 0.4860 | 80.9619 | 77.8208 | 80.8175 | 80.8004 | 14.3792 |
140
+ | 0.2502 | 85.0 | 9605 | 0.4867 | 80.8774 | 77.6973 | 80.7715 | 80.7376 | 14.3809 |
141
+ | 0.2502 | 86.0 | 9718 | 0.4839 | 81.05 | 77.9158 | 80.9472 | 80.9093 | 14.2248 |
142
+ | 0.2502 | 87.0 | 9831 | 0.4848 | 81.0625 | 77.9091 | 80.9571 | 80.9084 | 14.1997 |
143
+ | 0.2502 | 88.0 | 9944 | 0.4877 | 81.0991 | 77.9899 | 80.9932 | 80.9683 | 14.2601 |
144
+ | 0.2474 | 89.0 | 10057 | 0.4897 | 80.9609 | 77.7993 | 80.8264 | 80.8124 | 14.3255 |
145
+ | 0.2474 | 90.0 | 10170 | 0.4934 | 80.9773 | 77.8069 | 80.8548 | 80.866 | 14.3758 |
146
+ | 0.2474 | 91.0 | 10283 | 0.4872 | 81.2931 | 78.1574 | 81.1455 | 81.1423 | 14.2399 |
147
+ | 0.2474 | 92.0 | 10396 | 0.4891 | 81.0594 | 77.9078 | 80.9195 | 80.8975 | 14.2718 |
148
+ | 0.2381 | 93.0 | 10509 | 0.4866 | 81.0643 | 77.8887 | 80.923 | 80.8931 | 14.2953 |
149
+ | 0.2381 | 94.0 | 10622 | 0.4899 | 80.9436 | 77.7681 | 80.7827 | 80.8023 | 14.3792 |
150
+ | 0.2381 | 95.0 | 10735 | 0.4919 | 80.9423 | 77.7285 | 80.7917 | 80.7957 | 14.344 |
151
+ | 0.2381 | 96.0 | 10848 | 0.4853 | 81.2386 | 78.1291 | 81.1439 | 81.105 | 14.0906 |
152
+ | 0.2381 | 97.0 | 10961 | 0.4895 | 80.9959 | 77.8653 | 80.9033 | 80.8615 | 14.1393 |
153
+ | 0.2386 | 98.0 | 11074 | 0.4943 | 80.9335 | 77.7741 | 80.7675 | 80.8043 | 14.448 |
154
+ | 0.2386 | 99.0 | 11187 | 0.4902 | 81.0964 | 77.9268 | 80.9458 | 80.9464 | 14.2349 |
155
+ | 0.2386 | 100.0 | 11300 | 0.4853 | 80.8586 | 77.7339 | 80.7803 | 80.7335 | 13.943 |
156
+ | 0.2386 | 101.0 | 11413 | 0.4912 | 80.6762 | 77.4834 | 80.5409 | 80.5325 | 14.1477 |
157
+ | 0.2344 | 102.0 | 11526 | 0.4942 | 80.977 | 77.791 | 80.8131 | 80.8096 | 14.2164 |
158
+ | 0.2344 | 103.0 | 11639 | 0.4949 | 81.0275 | 77.8661 | 80.8811 | 80.8817 | 14.2433 |
159
+ | 0.2344 | 104.0 | 11752 | 0.4965 | 80.9943 | 77.8388 | 80.8502 | 80.8638 | 14.3054 |
160
+ | 0.2344 | 105.0 | 11865 | 0.4977 | 80.9401 | 77.7718 | 80.8032 | 80.8088 | 14.2685 |
161
+ | 0.2344 | 106.0 | 11978 | 0.4978 | 80.8843 | 77.7078 | 80.7456 | 80.7642 | 14.2836 |
162
+ | 0.2308 | 107.0 | 12091 | 0.4959 | 80.9197 | 77.7614 | 80.7987 | 80.7784 | 14.1879 |
163
+ | 0.2308 | 108.0 | 12204 | 0.4990 | 80.9442 | 77.7809 | 80.802 | 80.8031 | 14.3205 |
164
+ | 0.2308 | 109.0 | 12317 | 0.4981 | 81.0209 | 77.8307 | 80.8791 | 80.8808 | 14.1745 |
165
+ | 0.2308 | 110.0 | 12430 | 0.4964 | 81.0007 | 77.8126 | 80.8601 | 80.8628 | 14.1862 |
166
+ | 0.2251 | 111.0 | 12543 | 0.4982 | 81.1569 | 78.0036 | 81.0121 | 81.0245 | 14.156 |
167
+ | 0.2251 | 112.0 | 12656 | 0.5007 | 80.943 | 77.8043 | 80.8299 | 80.8042 | 14.0973 |
168
+ | 0.2251 | 113.0 | 12769 | 0.5020 | 80.7853 | 77.6064 | 80.681 | 80.6658 | 14.1829 |
169
+ | 0.2251 | 114.0 | 12882 | 0.5030 | 80.6903 | 77.511 | 80.5685 | 80.5686 | 14.2131 |
170
+ | 0.2251 | 115.0 | 12995 | 0.4960 | 80.9882 | 77.8412 | 80.8845 | 80.8523 | 14.0017 |
171
+ | 0.2248 | 116.0 | 13108 | 0.4986 | 80.8176 | 77.6388 | 80.6951 | 80.6879 | 14.1862 |
172
+ | 0.2248 | 117.0 | 13221 | 0.5014 | 80.736 | 77.5128 | 80.602 | 80.5839 | 14.2919 |
173
+ | 0.2248 | 118.0 | 13334 | 0.5009 | 80.6648 | 77.4574 | 80.5425 | 80.5224 | 14.2332 |
174
+ | 0.2248 | 119.0 | 13447 | 0.5009 | 80.8501 | 77.7096 | 80.7352 | 80.725 | 14.1611 |
175
+ | 0.2243 | 120.0 | 13560 | 0.5021 | 80.8173 | 77.6548 | 80.7106 | 80.6926 | 14.0889 |
176
+ | 0.2243 | 121.0 | 13673 | 0.5016 | 80.8348 | 77.6589 | 80.708 | 80.683 | 14.1711 |
177
+ | 0.2243 | 122.0 | 13786 | 0.5023 | 80.6496 | 77.4382 | 80.533 | 80.5026 | 14.2064 |
178
+ | 0.2243 | 123.0 | 13899 | 0.4998 | 80.6583 | 77.4496 | 80.5485 | 80.5204 | 14.1913 |
179
+ | 0.2142 | 124.0 | 14012 | 0.5014 | 80.5638 | 77.3928 | 80.4991 | 80.4625 | 14.1225 |
180
+ | 0.2142 | 125.0 | 14125 | 0.5030 | 80.7874 | 77.604 | 80.6831 | 80.6587 | 14.2164 |
181
+ | 0.2142 | 126.0 | 14238 | 0.5032 | 80.9277 | 77.7346 | 80.8072 | 80.7807 | 14.2634 |
182
+ | 0.2142 | 127.0 | 14351 | 0.5007 | 81.0126 | 77.8484 | 80.8985 | 80.863 | 14.2148 |
183
+ | 0.2142 | 128.0 | 14464 | 0.5007 | 80.9762 | 77.8094 | 80.8922 | 80.8298 | 14.1493 |
184
+ | 0.2239 | 129.0 | 14577 | 0.5044 | 80.8472 | 77.6598 | 80.7277 | 80.7076 | 14.2584 |
185
+ | 0.2239 | 130.0 | 14690 | 0.5031 | 80.8751 | 77.6917 | 80.7714 | 80.7508 | 14.203 |
186
+ | 0.2239 | 131.0 | 14803 | 0.5021 | 80.9744 | 77.8231 | 80.8951 | 80.855 | 14.0872 |
187
+ | 0.2239 | 132.0 | 14916 | 0.5018 | 81.0396 | 77.8871 | 80.9528 | 80.9048 | 14.0721 |
188
+ | 0.2138 | 133.0 | 15029 | 0.5014 | 81.0898 | 77.9465 | 81.0044 | 80.9586 | 14.0487 |
189
+ | 0.2138 | 134.0 | 15142 | 0.5035 | 81.0916 | 77.944 | 80.9968 | 80.9505 | 14.0688 |
190
+ | 0.2138 | 135.0 | 15255 | 0.5049 | 80.8588 | 77.6669 | 80.7619 | 80.7194 | 14.1896 |
191
+ | 0.2138 | 136.0 | 15368 | 0.5039 | 80.9967 | 77.8126 | 80.8943 | 80.8637 | 14.1711 |
192
+ | 0.2138 | 137.0 | 15481 | 0.5041 | 80.9967 | 77.8126 | 80.8943 | 80.8637 | 14.1711 |
193
+ | 0.2151 | 138.0 | 15594 | 0.5034 | 80.9967 | 77.8126 | 80.8943 | 80.8637 | 14.1711 |
194
+ | 0.2151 | 139.0 | 15707 | 0.5045 | 80.9686 | 77.7817 | 80.8589 | 80.8296 | 14.1745 |
195
+ | 0.2151 | 140.0 | 15820 | 0.5046 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
196
+ | 0.2151 | 141.0 | 15933 | 0.5043 | 80.942 | 77.7729 | 80.8456 | 80.8138 | 14.1779 |
197
+ | 0.2189 | 142.0 | 16046 | 0.5038 | 80.8252 | 77.6444 | 80.7124 | 80.7108 | 14.1409 |
198
+ | 0.2189 | 143.0 | 16159 | 0.5045 | 80.8402 | 77.663 | 80.7251 | 80.7201 | 14.1342 |
199
+ | 0.2189 | 144.0 | 16272 | 0.5044 | 80.8252 | 77.6444 | 80.7124 | 80.7108 | 14.1409 |
200
+ | 0.2189 | 145.0 | 16385 | 0.5051 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
201
+ | 0.2189 | 146.0 | 16498 | 0.5052 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
202
+ | 0.2167 | 147.0 | 16611 | 0.5052 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
203
+ | 0.2167 | 148.0 | 16724 | 0.5050 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
204
+ | 0.2167 | 149.0 | 16837 | 0.5051 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
205
+ | 0.2167 | 150.0 | 16950 | 0.5052 | 80.9236 | 77.7423 | 80.8206 | 80.7904 | 14.1779 |
206
 
207
 
208
  ### Framework versions
209
 
210
+ - Transformers 4.26.0
211
  - Pytorch 1.13.1+cu116
212
  - Datasets 2.8.0
213
  - Tokenizers 0.13.2