Hugging Face's logo

devagonal
/
flan-t5-rouge-squad-qg-test

Transformers
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
devagonal commited on
Commit
8eacbed
·
verified ·
1 Parent(s): 4a961de

End of training

Browse files
Files changed (3) hide show
  1. README.md +114 -167
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.5009
22
- - Rouge1: 0.3621
23
- - Rouge2: 0.1184
24
- - Rougel: 0.3287
25
- - Rougelsum: 0.3462
26
 
27
  ## Model description
28
 
@@ -41,7 +41,7 @@ More information needed
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
- - learning_rate: 5e-05
45
  - train_batch_size: 80
46
  - eval_batch_size: 80
47
  - seed: 42
@@ -49,172 +49,119 @@ The following hyperparameters were used during training:
49
  - total_train_batch_size: 320
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
- - num_epochs: 240
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
- | 66.9288 | 1.0 | 3 | 33.7988 | 0.0551 | 0.0152 | 0.0495 | 0.0510 |
59
- | 59.6537 | 2.0 | 6 | 29.7133 | 0.0863 | 0.0288 | 0.0779 | 0.0784 |
60
- | 54.5151 | 3.0 | 9 | 26.4569 | 0.0872 | 0.0311 | 0.0804 | 0.0807 |
61
- | 48.8589 | 4.0 | 12 | 23.4380 | 0.0708 | 0.0229 | 0.0659 | 0.0658 |
62
- | 44.4884 | 5.0 | 15 | 20.4291 | 0.0583 | 0.0180 | 0.0540 | 0.0540 |
63
- | 39.3563 | 6.0 | 18 | 17.1085 | 0.0723 | 0.0338 | 0.0726 | 0.0728 |
64
- | 34.7597 | 7.0 | 21 | 13.4356 | 0.0852 | 0.0386 | 0.0855 | 0.0851 |
65
- | 29.4129 | 8.0 | 24 | 10.0105 | 0.0817 | 0.0409 | 0.0819 | 0.0815 |
66
- | 24.5644 | 9.0 | 27 | 8.2052 | 0.0705 | 0.0389 | 0.0707 | 0.0706 |
67
- | 21.5519 | 10.0 | 30 | 7.8246 | 0.0762 | 0.0414 | 0.0764 | 0.0765 |
68
- | 19.2726 | 11.0 | 33 | 7.5980 | 0.0787 | 0.0424 | 0.0791 | 0.0790 |
69
- | 17.3549 | 12.0 | 36 | 7.3363 | 0.0785 | 0.0402 | 0.0756 | 0.0773 |
70
- | 15.8209 | 13.0 | 39 | 6.9108 | 0.0872 | 0.0409 | 0.0845 | 0.0863 |
71
- | 14.5875 | 14.0 | 42 | 6.1713 | 0.0922 | 0.0408 | 0.0868 | 0.0895 |
72
- | 13.5069 | 15.0 | 45 | 5.3704 | 0.0929 | 0.0439 | 0.0875 | 0.0903 |
73
- | 12.4587 | 16.0 | 48 | 4.9043 | 0.1013 | 0.0468 | 0.0908 | 0.0959 |
74
- | 11.6791 | 17.0 | 51 | 4.6937 | 0.0824 | 0.0343 | 0.0760 | 0.0798 |
75
- | 11.0218 | 18.0 | 54 | 4.5524 | 0.0815 | 0.0354 | 0.0749 | 0.0788 |
76
- | 10.5096 | 19.0 | 57 | 4.4352 | 0.0970 | 0.0482 | 0.0920 | 0.0943 |
77
- | 10.1003 | 20.0 | 60 | 4.3319 | 0.1052 | 0.0550 | 0.0965 | 0.1012 |
78
- | 9.6825 | 21.0 | 63 | 4.2356 | 0.1114 | 0.0538 | 0.0982 | 0.1041 |
79
- | 9.4799 | 22.0 | 66 | 4.1426 | 0.1047 | 0.0402 | 0.0885 | 0.0945 |
80
- | 9.2102 | 23.0 | 69 | 4.0519 | 0.1029 | 0.0434 | 0.0912 | 0.0954 |
81
- | 8.9439 | 24.0 | 72 | 3.9594 | 0.1152 | 0.0489 | 0.1022 | 0.1065 |
82
- | 8.6772 | 25.0 | 75 | 3.8612 | 0.1088 | 0.0477 | 0.0967 | 0.1009 |
83
- | 8.4874 | 26.0 | 78 | 3.7557 | 0.1088 | 0.0477 | 0.0967 | 0.1009 |
84
- | 8.2661 | 27.0 | 81 | 3.6442 | 0.1165 | 0.0437 | 0.0990 | 0.1045 |
85
- | 8.0701 | 28.0 | 84 | 3.5346 | 0.1117 | 0.0412 | 0.0949 | 0.1007 |
86
- | 7.8707 | 29.0 | 87 | 3.4394 | 0.1329 | 0.0445 | 0.1090 | 0.1159 |
87
- | 7.7254 | 30.0 | 90 | 3.3626 | 0.1104 | 0.0414 | 0.0911 | 0.0980 |
88
- | 7.5449 | 31.0 | 93 | 3.3007 | 0.0924 | 0.0331 | 0.0760 | 0.0830 |
89
- | 7.3488 | 32.0 | 96 | 3.2475 | 0.0924 | 0.0331 | 0.0760 | 0.0830 |
90
- | 7.2399 | 33.0 | 99 | 3.1974 | 0.0960 | 0.0334 | 0.0784 | 0.0858 |
91
- | 7.0881 | 34.0 | 102 | 3.1462 | 0.0862 | 0.0295 | 0.0721 | 0.0770 |
92
- | 6.9073 | 35.0 | 105 | 3.0910 | 0.0911 | 0.0303 | 0.0764 | 0.0813 |
93
- | 6.7932 | 36.0 | 108 | 3.0312 | 0.0900 | 0.0303 | 0.0753 | 0.0803 |
94
- | 6.678 | 37.0 | 111 | 2.9675 | 0.0994 | 0.0305 | 0.0841 | 0.0889 |
95
- | 6.545 | 38.0 | 114 | 2.9005 | 0.1020 | 0.0308 | 0.0866 | 0.0914 |
96
- | 6.4258 | 39.0 | 117 | 2.8311 | 0.1132 | 0.0332 | 0.0951 | 0.1021 |
97
- | 6.2931 | 40.0 | 120 | 2.7622 | 0.1110 | 0.0370 | 0.0937 | 0.0980 |
98
- | 6.214 | 41.0 | 123 | 2.6961 | 0.1107 | 0.0379 | 0.0911 | 0.0972 |
99
- | 6.1124 | 42.0 | 126 | 2.6322 | 0.1002 | 0.0351 | 0.0838 | 0.0890 |
100
- | 5.9876 | 43.0 | 129 | 2.5725 | 0.0968 | 0.0337 | 0.0814 | 0.0862 |
101
- | 5.8969 | 44.0 | 132 | 2.5156 | 0.1051 | 0.0355 | 0.0890 | 0.0934 |
102
- | 5.7859 | 45.0 | 135 | 2.4613 | 0.0860 | 0.0284 | 0.0749 | 0.0781 |
103
- | 5.711 | 46.0 | 138 | 2.4089 | 0.1101 | 0.0406 | 0.0920 | 0.0982 |
104
- | 5.5932 | 47.0 | 141 | 2.3577 | 0.1124 | 0.0403 | 0.0930 | 0.0992 |
105
- | 5.4643 | 48.0 | 144 | 2.3062 | 0.0857 | 0.0273 | 0.0691 | 0.0753 |
106
- | 5.4375 | 49.0 | 147 | 2.2532 | 0.0947 | 0.0293 | 0.0773 | 0.0850 |
107
- | 5.2916 | 50.0 | 150 | 2.2018 | 0.1058 | 0.0316 | 0.0864 | 0.0943 |
108
- | 5.1871 | 51.0 | 153 | 2.1514 | 0.1162 | 0.0344 | 0.0938 | 0.1026 |
109
- | 5.1168 | 52.0 | 156 | 2.1027 | 0.1421 | 0.0435 | 0.1148 | 0.1271 |
110
- | 5.043 | 53.0 | 159 | 2.0563 | 0.1605 | 0.0477 | 0.1335 | 0.1467 |
111
- | 4.9621 | 54.0 | 162 | 2.0120 | 0.1754 | 0.0552 | 0.1493 | 0.1613 |
112
- | 4.9053 | 55.0 | 165 | 1.9677 | 0.2178 | 0.0705 | 0.1942 | 0.2049 |
113
- | 4.7798 | 56.0 | 168 | 1.9239 | 0.2518 | 0.0831 | 0.2273 | 0.2388 |
114
- | 4.6627 | 57.0 | 171 | 1.8797 | 0.2917 | 0.0943 | 0.2651 | 0.2774 |
115
- | 4.5903 | 58.0 | 174 | 1.8363 | 0.3039 | 0.0970 | 0.2741 | 0.2878 |
116
- | 4.5531 | 59.0 | 177 | 1.7930 | 0.3277 | 0.1010 | 0.2970 | 0.3102 |
117
- | 4.5054 | 60.0 | 180 | 1.7507 | 0.3321 | 0.1014 | 0.3008 | 0.3155 |
118
- | 4.4274 | 61.0 | 183 | 1.7098 | 0.3309 | 0.1017 | 0.2990 | 0.3153 |
119
- | 4.3133 | 62.0 | 186 | 1.6712 | 0.3300 | 0.1049 | 0.3007 | 0.3161 |
120
- | 4.2436 | 63.0 | 189 | 1.6360 | 0.3300 | 0.1049 | 0.3007 | 0.3161 |
121
- | 4.2303 | 64.0 | 192 | 1.6021 | 0.3300 | 0.1049 | 0.3007 | 0.3161 |
122
- | 4.1181 | 65.0 | 195 | 1.5679 | 0.3423 | 0.1073 | 0.3105 | 0.3258 |
123
- | 4.0503 | 66.0 | 198 | 1.5340 | 0.3481 | 0.1140 | 0.3125 | 0.3321 |
124
- | 4.0148 | 67.0 | 201 | 1.4996 | 0.3483 | 0.1141 | 0.3129 | 0.3322 |
125
- | 3.9164 | 68.0 | 204 | 1.4663 | 0.3562 | 0.1173 | 0.3165 | 0.3405 |
126
- | 3.867 | 69.0 | 207 | 1.4332 | 0.3554 | 0.1184 | 0.3163 | 0.3408 |
127
- | 3.8008 | 70.0 | 210 | 1.4003 | 0.3583 | 0.1189 | 0.3190 | 0.3432 |
128
- | 3.716 | 71.0 | 213 | 1.3684 | 0.3583 | 0.1189 | 0.3190 | 0.3432 |
129
- | 3.6532 | 72.0 | 216 | 1.3377 | 0.3583 | 0.1189 | 0.3190 | 0.3432 |
130
- | 3.6215 | 73.0 | 219 | 1.3098 | 0.3570 | 0.1186 | 0.3214 | 0.3413 |
131
- | 3.5856 | 74.0 | 222 | 1.2829 | 0.3572 | 0.1186 | 0.3214 | 0.3416 |
132
- | 3.4981 | 75.0 | 225 | 1.2570 | 0.3571 | 0.1207 | 0.3254 | 0.3415 |
133
- | 3.4572 | 76.0 | 228 | 1.2316 | 0.3571 | 0.1207 | 0.3254 | 0.3415 |
134
- | 3.3903 | 77.0 | 231 | 1.2067 | 0.3571 | 0.1207 | 0.3254 | 0.3415 |
135
- | 3.3244 | 78.0 | 234 | 1.1825 | 0.3575 | 0.1209 | 0.3256 | 0.3419 |
136
- | 3.2392 | 79.0 | 237 | 1.1582 | 0.3570 | 0.1210 | 0.3250 | 0.3413 |
137
- | 3.2641 | 80.0 | 240 | 1.1332 | 0.3570 | 0.1210 | 0.3250 | 0.3413 |
138
- | 3.2098 | 81.0 | 243 | 1.1080 | 0.3570 | 0.1210 | 0.3250 | 0.3413 |
139
- | 3.1245 | 82.0 | 246 | 1.0849 | 0.3564 | 0.1212 | 0.3242 | 0.3410 |
140
- | 3.1093 | 83.0 | 249 | 1.0630 | 0.3540 | 0.1187 | 0.3216 | 0.3379 |
141
- | 3.0442 | 84.0 | 252 | 1.0425 | 0.3555 | 0.1201 | 0.3231 | 0.3400 |
142
- | 2.9806 | 85.0 | 255 | 1.0222 | 0.3562 | 0.1207 | 0.3243 | 0.3407 |
143
- | 2.9729 | 86.0 | 258 | 1.0026 | 0.3562 | 0.1207 | 0.3243 | 0.3407 |
144
- | 2.9332 | 87.0 | 261 | 0.9840 | 0.3562 | 0.1207 | 0.3243 | 0.3407 |
145
- | 2.86 | 88.0 | 264 | 0.9659 | 0.3543 | 0.1188 | 0.3225 | 0.3389 |
146
- | 2.8624 | 89.0 | 267 | 0.9484 | 0.3519 | 0.1174 | 0.3224 | 0.3376 |
147
- | 2.7783 | 90.0 | 270 | 0.9307 | 0.3519 | 0.1174 | 0.3224 | 0.3376 |
148
- | 2.7553 | 91.0 | 273 | 0.9131 | 0.3499 | 0.1174 | 0.3206 | 0.3360 |
149
- | 2.7504 | 92.0 | 276 | 0.8960 | 0.3499 | 0.1174 | 0.3206 | 0.3360 |
150
- | 2.6618 | 93.0 | 279 | 0.8795 | 0.3499 | 0.1174 | 0.3206 | 0.3360 |
151
- | 2.6374 | 94.0 | 282 | 0.8637 | 0.3499 | 0.1174 | 0.3206 | 0.3360 |
152
- | 2.6088 | 95.0 | 285 | 0.8494 | 0.3495 | 0.1149 | 0.3176 | 0.3346 |
153
- | 2.5952 | 96.0 | 288 | 0.8364 | 0.3495 | 0.1149 | 0.3176 | 0.3346 |
154
- | 2.5346 | 97.0 | 291 | 0.8235 | 0.3495 | 0.1149 | 0.3176 | 0.3346 |
155
- | 2.5347 | 98.0 | 294 | 0.8108 | 0.3485 | 0.1150 | 0.3178 | 0.3342 |
156
- | 2.4983 | 99.0 | 297 | 0.7977 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
157
- | 2.4029 | 100.0 | 300 | 0.7842 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
158
- | 2.3776 | 101.0 | 303 | 0.7708 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
159
- | 2.4159 | 102.0 | 306 | 0.7582 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
160
- | 2.3694 | 103.0 | 309 | 0.7462 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
161
- | 2.3445 | 104.0 | 312 | 0.7352 | 0.3459 | 0.1132 | 0.3145 | 0.3313 |
162
- | 2.3314 | 105.0 | 315 | 0.7246 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
163
- | 2.3162 | 106.0 | 318 | 0.7142 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
164
- | 2.2031 | 107.0 | 321 | 0.7045 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
165
- | 2.2205 | 108.0 | 324 | 0.6955 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
166
- | 2.1966 | 109.0 | 327 | 0.6866 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
167
- | 2.1647 | 110.0 | 330 | 0.6781 | 0.3493 | 0.1134 | 0.3167 | 0.3335 |
168
- | 2.1735 | 111.0 | 333 | 0.6703 | 0.3528 | 0.1131 | 0.3192 | 0.3375 |
169
- | 2.1282 | 112.0 | 336 | 0.6621 | 0.3528 | 0.1131 | 0.3192 | 0.3375 |
170
- | 2.128 | 113.0 | 339 | 0.6539 | 0.3528 | 0.1131 | 0.3192 | 0.3375 |
171
- | 2.0928 | 114.0 | 342 | 0.6461 | 0.3528 | 0.1131 | 0.3192 | 0.3375 |
172
- | 2.1138 | 115.0 | 345 | 0.6380 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
173
- | 2.0628 | 116.0 | 348 | 0.6300 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
174
- | 2.1074 | 117.0 | 351 | 0.6225 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
175
- | 2.0309 | 118.0 | 354 | 0.6154 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
176
- | 2.0194 | 119.0 | 357 | 0.6086 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
177
- | 2.003 | 120.0 | 360 | 0.6025 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
178
- | 1.9763 | 121.0 | 363 | 0.5971 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
179
- | 1.9839 | 122.0 | 366 | 0.5924 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
180
- | 1.9457 | 123.0 | 369 | 0.5875 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
181
- | 1.9712 | 124.0 | 372 | 0.5831 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
182
- | 1.8996 | 125.0 | 375 | 0.5784 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
183
- | 1.9026 | 126.0 | 378 | 0.5735 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
184
- | 1.8806 | 127.0 | 381 | 0.5687 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
185
- | 1.9003 | 128.0 | 384 | 0.5641 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
186
- | 1.856 | 129.0 | 387 | 0.5596 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
187
- | 1.8529 | 130.0 | 390 | 0.5552 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
188
- | 1.7915 | 131.0 | 393 | 0.5510 | 0.3528 | 0.1133 | 0.3197 | 0.3374 |
189
- | 1.8471 | 132.0 | 396 | 0.5469 | 0.3606 | 0.1154 | 0.3268 | 0.3445 |
190
- | 1.8399 | 133.0 | 399 | 0.5432 | 0.3606 | 0.1154 | 0.3268 | 0.3445 |
191
- | 1.8121 | 134.0 | 402 | 0.5400 | 0.3606 | 0.1154 | 0.3268 | 0.3445 |
192
- | 1.77 | 135.0 | 405 | 0.5370 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
193
- | 1.8023 | 136.0 | 408 | 0.5344 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
194
- | 1.7561 | 137.0 | 411 | 0.5318 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
195
- | 1.7662 | 138.0 | 414 | 0.5292 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
196
- | 1.7538 | 139.0 | 417 | 0.5264 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
197
- | 1.7416 | 140.0 | 420 | 0.5239 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
198
- | 1.7705 | 141.0 | 423 | 0.5215 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
199
- | 1.6753 | 142.0 | 426 | 0.5193 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
200
- | 1.7438 | 143.0 | 429 | 0.5173 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
201
- | 1.7012 | 144.0 | 432 | 0.5155 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
202
- | 1.7532 | 145.0 | 435 | 0.5138 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
203
- | 1.7072 | 146.0 | 438 | 0.5121 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
204
- | 1.7409 | 147.0 | 441 | 0.5106 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
205
- | 1.685 | 148.0 | 444 | 0.5092 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
206
- | 1.7463 | 149.0 | 447 | 0.5079 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
207
- | 1.6827 | 150.0 | 450 | 0.5067 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
208
- | 1.7278 | 151.0 | 453 | 0.5056 | 0.3606 | 0.1155 | 0.3272 | 0.3445 |
209
- | 1.6815 | 152.0 | 456 | 0.5046 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
210
- | 1.6731 | 153.0 | 459 | 0.5037 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
211
- | 1.7415 | 154.0 | 462 | 0.5030 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
212
- | 1.6871 | 155.0 | 465 | 0.5024 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
213
- | 1.7124 | 156.0 | 468 | 0.5019 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
214
- | 1.6678 | 157.0 | 471 | 0.5015 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
215
- | 1.7196 | 158.0 | 474 | 0.5012 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
216
- | 1.6954 | 159.0 | 477 | 0.5010 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
217
- | 1.705 | 160.0 | 480 | 0.5009 | 0.3621 | 0.1184 | 0.3287 | 0.3462 |
218
 
219
 
220
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4416
22
+ - Rouge1: 0.3489
23
+ - Rouge2: 0.1081
24
+ - Rougel: 0.3225
25
+ - Rougelsum: 0.3335
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 0.0005
45
  - train_batch_size: 80
46
  - eval_batch_size: 80
47
  - seed: 42
 
49
  - total_train_batch_size: 320
50
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 160
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
57
  |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
58
+ | 41.7986 | 1.0 | 3 | 14.9730 | 0.0645 | 0.0187 | 0.0619 | 0.0626 |
59
+ | 18.0367 | 2.0 | 6 | 6.4506 | 0.0696 | 0.0369 | 0.0673 | 0.0690 |
60
+ | 11.6807 | 3.0 | 9 | 4.8843 | 0.1134 | 0.0385 | 0.0991 | 0.1016 |
61
+ | 9.5977 | 4.0 | 12 | 4.1902 | 0.0615 | 0.0227 | 0.0529 | 0.0562 |
62
+ | 8.382 | 5.0 | 15 | 3.7084 | 0.0108 | 0.0017 | 0.0108 | 0.0107 |
63
+ | 7.3099 | 6.0 | 18 | 3.1393 | 0.0334 | 0.0139 | 0.0321 | 0.0319 |
64
+ | 6.2255 | 7.0 | 21 | 2.6959 | 0.0484 | 0.0206 | 0.0471 | 0.0478 |
65
+ | 5.3866 | 8.0 | 24 | 2.2886 | 0.0942 | 0.0388 | 0.0902 | 0.0928 |
66
+ | 4.4362 | 9.0 | 27 | 1.6919 | 0.1476 | 0.0517 | 0.1244 | 0.1336 |
67
+ | 3.5819 | 10.0 | 30 | 1.2444 | 0.2204 | 0.0785 | 0.1939 | 0.2064 |
68
+ | 2.7713 | 11.0 | 33 | 0.9173 | 0.3423 | 0.1261 | 0.3144 | 0.3277 |
69
+ | 2.1415 | 12.0 | 36 | 0.6726 | 0.3756 | 0.1188 | 0.3440 | 0.3607 |
70
+ | 1.6248 | 13.0 | 39 | 0.4801 | 0.3757 | 0.1220 | 0.3387 | 0.3573 |
71
+ | 1.3172 | 14.0 | 42 | 0.3892 | 0.3855 | 0.1316 | 0.3478 | 0.3655 |
72
+ | 1.0707 | 15.0 | 45 | 0.3425 | 0.3863 | 0.1358 | 0.3514 | 0.3691 |
73
+ | 0.8661 | 16.0 | 48 | 0.3104 | 0.3820 | 0.1376 | 0.3447 | 0.3624 |
74
+ | 0.7925 | 17.0 | 51 | 0.2946 | 0.3937 | 0.1408 | 0.3620 | 0.3738 |
75
+ | 0.6878 | 18.0 | 54 | 0.2863 | 0.3893 | 0.1375 | 0.3568 | 0.3672 |
76
+ | 0.6841 | 19.0 | 57 | 0.2810 | 0.3959 | 0.1427 | 0.3635 | 0.3731 |
77
+ | 0.6014 | 20.0 | 60 | 0.2782 | 0.3991 | 0.1447 | 0.3663 | 0.3794 |
78
+ | 0.5921 | 21.0 | 63 | 0.2786 | 0.4018 | 0.1467 | 0.3696 | 0.3841 |
79
+ | 0.5582 | 22.0 | 66 | 0.2776 | 0.3967 | 0.1414 | 0.3618 | 0.3767 |
80
+ | 0.5268 | 23.0 | 69 | 0.2785 | 0.3984 | 0.1479 | 0.3669 | 0.3822 |
81
+ | 0.4784 | 24.0 | 72 | 0.2796 | 0.4031 | 0.1519 | 0.3709 | 0.3851 |
82
+ | 0.4378 | 25.0 | 75 | 0.2831 | 0.4001 | 0.1501 | 0.3667 | 0.3805 |
83
+ | 0.4395 | 26.0 | 78 | 0.2876 | 0.4015 | 0.1522 | 0.3691 | 0.3811 |
84
+ | 0.4269 | 27.0 | 81 | 0.2897 | 0.4055 | 0.1455 | 0.3747 | 0.3845 |
85
+ | 0.3955 | 28.0 | 84 | 0.2925 | 0.3912 | 0.1330 | 0.3595 | 0.3694 |
86
+ | 0.3876 | 29.0 | 87 | 0.2976 | 0.3881 | 0.1354 | 0.3592 | 0.3677 |
87
+ | 0.3593 | 30.0 | 90 | 0.3008 | 0.3875 | 0.1374 | 0.3580 | 0.3686 |
88
+ | 0.3477 | 31.0 | 93 | 0.3038 | 0.3792 | 0.1303 | 0.3507 | 0.3609 |
89
+ | 0.3368 | 32.0 | 96 | 0.3079 | 0.3854 | 0.1331 | 0.3601 | 0.3677 |
90
+ | 0.3019 | 33.0 | 99 | 0.3134 | 0.3820 | 0.1272 | 0.3524 | 0.3633 |
91
+ | 0.3141 | 34.0 | 102 | 0.3202 | 0.3733 | 0.1229 | 0.3431 | 0.3541 |
92
+ | 0.2914 | 35.0 | 105 | 0.3233 | 0.3814 | 0.1257 | 0.3514 | 0.3638 |
93
+ | 0.2817 | 36.0 | 108 | 0.3250 | 0.3822 | 0.1316 | 0.3563 | 0.3636 |
94
+ | 0.2875 | 37.0 | 111 | 0.3280 | 0.3898 | 0.1405 | 0.3650 | 0.3737 |
95
+ | 0.267 | 38.0 | 114 | 0.3343 | 0.3878 | 0.1353 | 0.3616 | 0.3708 |
96
+ | 0.264 | 39.0 | 117 | 0.3375 | 0.3761 | 0.1182 | 0.3484 | 0.3589 |
97
+ | 0.2519 | 40.0 | 120 | 0.3372 | 0.3781 | 0.1228 | 0.3504 | 0.3606 |
98
+ | 0.2508 | 41.0 | 123 | 0.3382 | 0.3810 | 0.1244 | 0.3538 | 0.3635 |
99
+ | 0.2373 | 42.0 | 126 | 0.3460 | 0.3805 | 0.1230 | 0.3533 | 0.3632 |
100
+ | 0.2316 | 43.0 | 129 | 0.3533 | 0.3692 | 0.1125 | 0.3396 | 0.3514 |
101
+ | 0.2271 | 44.0 | 132 | 0.3552 | 0.3576 | 0.1133 | 0.3313 | 0.3394 |
102
+ | 0.2133 | 45.0 | 135 | 0.3565 | 0.3643 | 0.1244 | 0.3401 | 0.3481 |
103
+ | 0.2167 | 46.0 | 138 | 0.3602 | 0.3683 | 0.1245 | 0.3408 | 0.3490 |
104
+ | 0.2119 | 47.0 | 141 | 0.3647 | 0.3694 | 0.1278 | 0.3399 | 0.3493 |
105
+ | 0.1976 | 48.0 | 144 | 0.3677 | 0.3590 | 0.1194 | 0.3322 | 0.3414 |
106
+ | 0.2133 | 49.0 | 147 | 0.3720 | 0.3531 | 0.1115 | 0.3275 | 0.3351 |
107
+ | 0.1923 | 50.0 | 150 | 0.3746 | 0.3621 | 0.1189 | 0.3339 | 0.3413 |
108
+ | 0.1854 | 51.0 | 153 | 0.3760 | 0.3707 | 0.1280 | 0.3438 | 0.3528 |
109
+ | 0.1872 | 52.0 | 156 | 0.3767 | 0.3635 | 0.1219 | 0.3358 | 0.3463 |
110
+ | 0.1827 | 53.0 | 159 | 0.3790 | 0.3657 | 0.1196 | 0.3384 | 0.3494 |
111
+ | 0.1801 | 54.0 | 162 | 0.3833 | 0.3611 | 0.1195 | 0.3276 | 0.3426 |
112
+ | 0.1787 | 55.0 | 165 | 0.3903 | 0.3595 | 0.1202 | 0.3285 | 0.3411 |
113
+ | 0.1713 | 56.0 | 168 | 0.3923 | 0.3566 | 0.1179 | 0.3258 | 0.3379 |
114
+ | 0.1626 | 57.0 | 171 | 0.3941 | 0.3497 | 0.1152 | 0.3185 | 0.3325 |
115
+ | 0.1599 | 58.0 | 174 | 0.3922 | 0.3605 | 0.1216 | 0.3305 | 0.3448 |
116
+ | 0.1603 | 59.0 | 177 | 0.3929 | 0.3478 | 0.1079 | 0.3188 | 0.3329 |
117
+ | 0.1794 | 60.0 | 180 | 0.3958 | 0.3455 | 0.1057 | 0.3179 | 0.3319 |
118
+ | 0.1626 | 61.0 | 183 | 0.3997 | 0.3481 | 0.1078 | 0.3203 | 0.3320 |
119
+ | 0.1433 | 62.0 | 186 | 0.4019 | 0.3529 | 0.1129 | 0.3278 | 0.3386 |
120
+ | 0.1489 | 63.0 | 189 | 0.4008 | 0.3446 | 0.1137 | 0.3220 | 0.3291 |
121
+ | 0.1595 | 64.0 | 192 | 0.4009 | 0.3579 | 0.1159 | 0.3345 | 0.3421 |
122
+ | 0.1557 | 65.0 | 195 | 0.4044 | 0.3506 | 0.1165 | 0.3269 | 0.3342 |
123
+ | 0.1435 | 66.0 | 198 | 0.4094 | 0.3404 | 0.1082 | 0.3159 | 0.3257 |
124
+ | 0.1427 | 67.0 | 201 | 0.4140 | 0.3450 | 0.1103 | 0.3193 | 0.3301 |
125
+ | 0.1494 | 68.0 | 204 | 0.4163 | 0.3421 | 0.1090 | 0.3198 | 0.3276 |
126
+ | 0.1493 | 69.0 | 207 | 0.4137 | 0.3481 | 0.1101 | 0.3230 | 0.3318 |
127
+ | 0.14 | 70.0 | 210 | 0.4107 | 0.3438 | 0.1083 | 0.3193 | 0.3277 |
128
+ | 0.1338 | 71.0 | 213 | 0.4107 | 0.3432 | 0.1068 | 0.3199 | 0.3270 |
129
+ | 0.1302 | 72.0 | 216 | 0.4134 | 0.3573 | 0.1097 | 0.3317 | 0.3428 |
130
+ | 0.1354 | 73.0 | 219 | 0.4162 | 0.3525 | 0.1092 | 0.3270 | 0.3376 |
131
+ | 0.1379 | 74.0 | 222 | 0.4193 | 0.3402 | 0.1069 | 0.3177 | 0.3249 |
132
+ | 0.1272 | 75.0 | 225 | 0.4233 | 0.3397 | 0.1059 | 0.3173 | 0.3244 |
133
+ | 0.1331 | 76.0 | 228 | 0.4248 | 0.3364 | 0.1021 | 0.3149 | 0.3223 |
134
+ | 0.1211 | 77.0 | 231 | 0.4258 | 0.3459 | 0.1076 | 0.3235 | 0.3312 |
135
+ | 0.1324 | 78.0 | 234 | 0.4267 | 0.3488 | 0.1066 | 0.3257 | 0.3335 |
136
+ | 0.1275 | 79.0 | 237 | 0.4272 | 0.3458 | 0.1165 | 0.3201 | 0.3301 |
137
+ | 0.1265 | 80.0 | 240 | 0.4279 | 0.3519 | 0.1188 | 0.3288 | 0.3366 |
138
+ | 0.1227 | 81.0 | 243 | 0.4293 | 0.3458 | 0.1093 | 0.3261 | 0.3317 |
139
+ | 0.1213 | 82.0 | 246 | 0.4323 | 0.3437 | 0.1051 | 0.3189 | 0.3288 |
140
+ | 0.1275 | 83.0 | 249 | 0.4347 | 0.3457 | 0.1065 | 0.3212 | 0.3318 |
141
+ | 0.1233 | 84.0 | 252 | 0.4346 | 0.3491 | 0.1048 | 0.3235 | 0.3337 |
142
+ | 0.1168 | 85.0 | 255 | 0.4349 | 0.3450 | 0.1035 | 0.3208 | 0.3314 |
143
+ | 0.1184 | 86.0 | 258 | 0.4347 | 0.3480 | 0.1050 | 0.3255 | 0.3336 |
144
+ | 0.1246 | 87.0 | 261 | 0.4336 | 0.3483 | 0.1058 | 0.3272 | 0.3347 |
145
+ | 0.1167 | 88.0 | 264 | 0.4333 | 0.3470 | 0.1065 | 0.3269 | 0.3343 |
146
+ | 0.1203 | 89.0 | 267 | 0.4334 | 0.3494 | 0.1112 | 0.3278 | 0.3351 |
147
+ | 0.1139 | 90.0 | 270 | 0.4339 | 0.3460 | 0.1114 | 0.3253 | 0.3314 |
148
+ | 0.1202 | 91.0 | 273 | 0.4341 | 0.3497 | 0.1103 | 0.3252 | 0.3352 |
149
+ | 0.1174 | 92.0 | 276 | 0.4344 | 0.3497 | 0.1103 | 0.3252 | 0.3352 |
150
+ | 0.1164 | 93.0 | 279 | 0.4350 | 0.3504 | 0.1099 | 0.3249 | 0.3365 |
151
+ | 0.1114 | 94.0 | 282 | 0.4357 | 0.3445 | 0.1073 | 0.3188 | 0.3299 |
152
+ | 0.1094 | 95.0 | 285 | 0.4368 | 0.3455 | 0.1076 | 0.3197 | 0.3308 |
153
+ | 0.114 | 96.0 | 288 | 0.4376 | 0.3483 | 0.1105 | 0.3236 | 0.3336 |
154
+ | 0.1147 | 97.0 | 291 | 0.4381 | 0.3458 | 0.1099 | 0.3207 | 0.3303 |
155
+ | 0.116 | 98.0 | 294 | 0.4386 | 0.3458 | 0.1099 | 0.3207 | 0.3303 |
156
+ | 0.1187 | 99.0 | 297 | 0.4393 | 0.3499 | 0.1100 | 0.3234 | 0.3341 |
157
+ | 0.1112 | 100.0 | 300 | 0.4399 | 0.3519 | 0.1146 | 0.3260 | 0.3368 |
158
+ | 0.1124 | 101.0 | 303 | 0.4404 | 0.3519 | 0.1146 | 0.3260 | 0.3368 |
159
+ | 0.117 | 102.0 | 306 | 0.4408 | 0.3489 | 0.1081 | 0.3225 | 0.3335 |
160
+ | 0.1101 | 103.0 | 309 | 0.4412 | 0.3489 | 0.1081 | 0.3225 | 0.3335 |
161
+ | 0.1135 | 104.0 | 312 | 0.4415 | 0.3472 | 0.1075 | 0.3208 | 0.3311 |
162
+ | 0.1141 | 105.0 | 315 | 0.4416 | 0.3489 | 0.1081 | 0.3225 | 0.3335 |
163
+ | 0.1201 | 106.0 | 318 | 0.4416 | 0.3489 | 0.1081 | 0.3225 | 0.3335 |
164
+ | 0.2258 | 106.8 | 320 | 0.4416 | 0.3489 | 0.1081 | 0.3225 | 0.3335 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165
 
166
 
167
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e8c16fdb482868f69788a62113bbd834c6633e9f26f67ae4d09d489aac695b8
3
  size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b743102833d290f35e9f7b0131bc84fdb434945088cafcd15157ad61bab7603
3
  size 307867048
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7d41e5e551363e6c27b84703bc9285ab834dcd035a37348ebad2cdea191e8f
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1acb0dfc573cb37c5e73de80b48f409ce5379778d9a002f0614d2aa3e5da8a
3
  size 5496