Arthur-Tsai commited on
Commit
5dfdca3
·
verified ·
1 Parent(s): 4459ddc

End of training

Browse files
README.md CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 22.2305
20
- - Accuracy: 0.9179
21
- - Macro F1: 0.8014
22
 
23
  ## Model description
24
 
@@ -44,233 +44,211 @@ The following hyperparameters were used during training:
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 6733
47
- - training_steps: 134674
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
52
  |:-------------:|:--------:|:-----:|:---------------:|:--------:|:--------:|
53
- | 36.8897 | 0.0013 | 174 | 58.9440 | 0.0707 | 0.0303 |
54
- | 17.415 | 1.0013 | 348 | 131.9342 | 0.3079 | 0.0778 |
55
- | 8.3841 | 2.0013 | 522 | 228.1804 | 0.4973 | 0.1274 |
56
- | 7.3153 | 3.0013 | 696 | 218.3890 | 0.5375 | 0.1337 |
57
- | 6.3897 | 4.0013 | 870 | 188.3552 | 0.5540 | 0.1386 |
58
- | 5.8067 | 5.0013 | 1044 | 163.3696 | 0.5748 | 0.1434 |
59
- | 4.985 | 6.0012 | 1218 | 96.3250 | 0.5695 | 0.1476 |
60
- | 4.4898 | 7.0012 | 1392 | 74.6840 | 0.5976 | 0.1597 |
61
- | 3.9475 | 8.0012 | 1566 | 54.5193 | 0.6169 | 0.1663 |
62
- | 3.662 | 9.0012 | 1740 | 45.3757 | 0.6341 | 0.1844 |
63
- | 3.465 | 10.0012 | 1914 | 41.7936 | 0.6305 | 0.1899 |
64
- | 3.2974 | 11.0012 | 2088 | 31.6148 | 0.6422 | 0.2126 |
65
- | 3.1647 | 12.0012 | 2262 | 34.3374 | 0.6440 | 0.2263 |
66
- | 3.2056 | 13.0012 | 2436 | 29.9489 | 0.6537 | 0.2433 |
67
- | 3.0134 | 14.0012 | 2610 | 26.0430 | 0.6687 | 0.2676 |
68
- | 2.9392 | 15.0012 | 2784 | 27.7054 | 0.6719 | 0.2785 |
69
- | 2.8061 | 16.0012 | 2958 | 26.6424 | 0.6745 | 0.3018 |
70
- | 2.7161 | 17.0012 | 3132 | 26.9671 | 0.6926 | 0.3189 |
71
- | 2.7101 | 18.0012 | 3306 | 27.6575 | 0.7136 | 0.3490 |
72
- | 2.6402 | 19.0012 | 3480 | 26.8896 | 0.7116 | 0.3516 |
73
- | 2.4746 | 20.0011 | 3654 | 25.7571 | 0.7114 | 0.3728 |
74
- | 2.3949 | 21.0011 | 3828 | 26.8391 | 0.7122 | 0.3940 |
75
- | 2.3161 | 22.0011 | 4002 | 25.0259 | 0.7582 | 0.4063 |
76
- | 2.321 | 23.0011 | 4176 | 28.5269 | 0.7603 | 0.4159 |
77
- | 2.1638 | 24.0011 | 4350 | 26.5361 | 0.7642 | 0.4407 |
78
- | 2.099 | 25.0011 | 4524 | 26.3485 | 0.7612 | 0.4327 |
79
- | 1.9656 | 26.0011 | 4698 | 29.0458 | 0.7779 | 0.4578 |
80
- | 1.9366 | 27.0011 | 4872 | 27.1165 | 0.7844 | 0.4737 |
81
- | 1.8128 | 28.0011 | 5046 | 29.7469 | 0.7692 | 0.4387 |
82
- | 1.8242 | 29.0011 | 5220 | 30.8209 | 0.7866 | 0.4907 |
83
- | 1.7638 | 30.0011 | 5394 | 26.3221 | 0.7905 | 0.4855 |
84
- | 1.6806 | 31.0011 | 5568 | 32.9942 | 0.7979 | 0.5075 |
85
- | 1.6499 | 32.0011 | 5742 | 31.1818 | 0.8034 | 0.5078 |
86
- | 1.507 | 33.0010 | 5916 | 24.1132 | 0.7990 | 0.5121 |
87
- | 1.4489 | 34.0010 | 6090 | 31.3519 | 0.7981 | 0.5200 |
88
- | 1.5266 | 35.0010 | 6264 | 34.7897 | 0.7992 | 0.5244 |
89
- | 1.387 | 36.0010 | 6438 | 26.2433 | 0.8099 | 0.5088 |
90
- | 1.3086 | 37.0010 | 6612 | 29.4355 | 0.8104 | 0.5342 |
91
- | 1.3534 | 38.0010 | 6786 | 34.3157 | 0.8166 | 0.5568 |
92
- | 1.2653 | 39.0010 | 6960 | 30.9298 | 0.8321 | 0.5690 |
93
- | 1.1277 | 40.0010 | 7134 | 29.7929 | 0.8344 | 0.5749 |
94
- | 1.1287 | 41.0010 | 7308 | 37.8217 | 0.8383 | 0.5842 |
95
- | 1.0651 | 42.0010 | 7482 | 33.6487 | 0.8493 | 0.5919 |
96
- | 1.0488 | 43.0010 | 7656 | 35.6326 | 0.8561 | 0.5998 |
97
- | 0.96 | 44.0010 | 7830 | 34.7891 | 0.8498 | 0.6022 |
98
- | 0.8912 | 45.0010 | 8004 | 36.0511 | 0.8551 | 0.6014 |
99
- | 0.9091 | 46.0010 | 8178 | 37.5957 | 0.8629 | 0.6118 |
100
- | 0.8304 | 47.0009 | 8352 | 42.3991 | 0.8597 | 0.6177 |
101
- | 0.7917 | 48.0009 | 8526 | 45.5854 | 0.8612 | 0.6191 |
102
- | 0.7743 | 49.0009 | 8700 | 45.6580 | 0.8574 | 0.6206 |
103
- | 0.7307 | 50.0009 | 8874 | 42.1980 | 0.8693 | 0.6341 |
104
- | 0.8023 | 51.0009 | 9048 | 43.2497 | 0.8747 | 0.6388 |
105
- | 0.6793 | 52.0009 | 9222 | 50.5001 | 0.8717 | 0.6443 |
106
- | 0.6295 | 53.0009 | 9396 | 43.5139 | 0.8679 | 0.6425 |
107
- | 0.6244 | 54.0009 | 9570 | 49.4621 | 0.8700 | 0.6410 |
108
- | 0.6053 | 55.0009 | 9744 | 45.1292 | 0.8712 | 0.6465 |
109
- | 0.5456 | 56.0009 | 9918 | 47.7468 | 0.8745 | 0.6481 |
110
- | 0.512 | 57.0009 | 10092 | 47.5651 | 0.8823 | 0.6644 |
111
- | 0.5543 | 58.0009 | 10266 | 46.7669 | 0.8849 | 0.6705 |
112
- | 0.5162 | 59.0009 | 10440 | 45.2046 | 0.8771 | 0.6730 |
113
- | 0.507 | 60.0008 | 10614 | 47.6766 | 0.8885 | 0.6798 |
114
- | 0.4834 | 61.0008 | 10788 | 44.7151 | 0.8877 | 0.6777 |
115
- | 0.4726 | 62.0008 | 10962 | 44.9125 | 0.8874 | 0.6759 |
116
- | 0.4472 | 63.0008 | 11136 | 45.8125 | 0.8892 | 0.6848 |
117
- | 0.4252 | 64.0008 | 11310 | 46.2853 | 0.8892 | 0.6932 |
118
- | 0.4328 | 65.0008 | 11484 | 43.6157 | 0.8776 | 0.6876 |
119
- | 0.4036 | 66.0008 | 11658 | 45.5207 | 0.8910 | 0.6957 |
120
- | 0.4059 | 67.0008 | 11832 | 44.9229 | 0.8947 | 0.6921 |
121
- | 0.3883 | 68.0008 | 12006 | 42.3161 | 0.8953 | 0.7015 |
122
- | 0.3723 | 69.0008 | 12180 | 42.0889 | 0.8889 | 0.6998 |
123
- | 0.3633 | 70.0008 | 12354 | 41.9702 | 0.8937 | 0.7007 |
124
- | 0.344 | 71.0008 | 12528 | 44.7303 | 0.8922 | 0.7011 |
125
- | 0.3811 | 72.0008 | 12702 | 40.4741 | 0.8956 | 0.7062 |
126
- | 0.3355 | 73.0007 | 12876 | 41.3522 | 0.8935 | 0.7078 |
127
- | 0.3291 | 74.0007 | 13050 | 39.9633 | 0.9013 | 0.7151 |
128
- | 0.3145 | 75.0007 | 13224 | 38.8315 | 0.9003 | 0.7181 |
129
- | 0.314 | 76.0007 | 13398 | 36.1396 | 0.8986 | 0.7180 |
130
- | 0.3076 | 77.0007 | 13572 | 37.6565 | 0.9034 | 0.7185 |
131
- | 0.2904 | 78.0007 | 13746 | 37.7939 | 0.8978 | 0.7179 |
132
- | 0.2786 | 79.0007 | 13920 | 34.3669 | 0.8999 | 0.7187 |
133
- | 0.2981 | 80.0007 | 14094 | 35.4609 | 0.9040 | 0.7318 |
134
- | 0.2776 | 81.0007 | 14268 | 32.6305 | 0.9024 | 0.7319 |
135
- | 0.2675 | 82.0007 | 14442 | 33.6086 | 0.9010 | 0.7235 |
136
- | 0.2625 | 83.0007 | 14616 | 29.9289 | 0.9019 | 0.7292 |
137
- | 0.2523 | 84.0007 | 14790 | 29.3959 | 0.8990 | 0.7236 |
138
- | 0.2709 | 85.0007 | 14964 | 31.8332 | 0.8988 | 0.7286 |
139
- | 0.2599 | 86.0007 | 15138 | 29.0299 | 0.9039 | 0.7397 |
140
- | 0.2561 | 87.0006 | 15312 | 31.9355 | 0.8983 | 0.7235 |
141
- | 0.2345 | 88.0006 | 15486 | 28.9463 | 0.9080 | 0.7377 |
142
- | 0.2343 | 89.0006 | 15660 | 31.4445 | 0.9035 | 0.7370 |
143
- | 0.2321 | 90.0006 | 15834 | 34.5653 | 0.9021 | 0.7419 |
144
- | 0.2479 | 91.0006 | 16008 | 28.6009 | 0.9044 | 0.7381 |
145
- | 0.2467 | 92.0006 | 16182 | 30.3260 | 0.9068 | 0.7479 |
146
- | 0.2358 | 93.0006 | 16356 | 28.6181 | 0.9023 | 0.7474 |
147
- | 0.2262 | 94.0006 | 16530 | 32.0329 | 0.9042 | 0.7455 |
148
- | 0.2141 | 95.0006 | 16704 | 27.8669 | 0.9065 | 0.7391 |
149
- | 0.2227 | 96.0006 | 16878 | 26.7895 | 0.9067 | 0.7486 |
150
- | 0.2218 | 97.0006 | 17052 | 27.5840 | 0.9074 | 0.7492 |
151
- | 0.2067 | 98.0006 | 17226 | 29.1753 | 0.8990 | 0.7445 |
152
- | 0.2014 | 99.0006 | 17400 | 28.1573 | 0.9025 | 0.7413 |
153
- | 0.1908 | 100.0005 | 17574 | 28.7326 | 0.9028 | 0.7467 |
154
- | 0.232 | 101.0005 | 17748 | 28.0963 | 0.9081 | 0.7477 |
155
- | 0.2105 | 102.0005 | 17922 | 27.2407 | 0.9148 | 0.7621 |
156
- | 0.196 | 103.0005 | 18096 | 27.7501 | 0.9070 | 0.7486 |
157
- | 0.1956 | 104.0005 | 18270 | 26.0193 | 0.9078 | 0.7525 |
158
- | 0.1965 | 105.0005 | 18444 | 27.6509 | 0.9057 | 0.7456 |
159
- | 0.1894 | 106.0005 | 18618 | 29.5254 | 0.9103 | 0.7604 |
160
- | 0.2029 | 107.0005 | 18792 | 30.4686 | 0.9061 | 0.7544 |
161
- | 0.1964 | 108.0005 | 18966 | 29.0120 | 0.9160 | 0.7725 |
162
- | 0.2035 | 109.0005 | 19140 | 23.9827 | 0.9065 | 0.7608 |
163
- | 0.1774 | 110.0005 | 19314 | 27.0304 | 0.9070 | 0.7542 |
164
- | 0.1831 | 111.0005 | 19488 | 28.0709 | 0.9111 | 0.7627 |
165
- | 0.1739 | 112.0005 | 19662 | 28.6017 | 0.9105 | 0.7613 |
166
- | 0.1791 | 113.0005 | 19836 | 25.0117 | 0.9098 | 0.7622 |
167
- | 0.1743 | 114.0004 | 20010 | 27.2863 | 0.9070 | 0.7559 |
168
- | 0.1889 | 115.0004 | 20184 | 27.2484 | 0.9077 | 0.7599 |
169
- | 0.1847 | 116.0004 | 20358 | 27.9157 | 0.9108 | 0.7689 |
170
- | 0.1863 | 117.0004 | 20532 | 27.3783 | 0.9092 | 0.7664 |
171
- | 0.1855 | 118.0004 | 20706 | 24.0478 | 0.9096 | 0.7654 |
172
- | 0.173 | 119.0004 | 20880 | 28.2592 | 0.9102 | 0.7719 |
173
- | 0.1827 | 120.0004 | 21054 | 26.4806 | 0.9136 | 0.7735 |
174
- | 0.1563 | 121.0004 | 21228 | 26.4771 | 0.9085 | 0.7656 |
175
- | 0.1635 | 122.0004 | 21402 | 27.6845 | 0.9088 | 0.7667 |
176
- | 0.1632 | 123.0004 | 21576 | 26.5298 | 0.9115 | 0.7735 |
177
- | 0.1659 | 124.0004 | 21750 | 27.4644 | 0.9102 | 0.7755 |
178
- | 0.167 | 125.0004 | 21924 | 28.6199 | 0.9079 | 0.7673 |
179
- | 0.1669 | 126.0004 | 22098 | 26.2487 | 0.9131 | 0.7717 |
180
- | 0.1649 | 127.0003 | 22272 | 25.7411 | 0.9071 | 0.7630 |
181
- | 0.1636 | 128.0003 | 22446 | 27.9678 | 0.9152 | 0.7757 |
182
- | 0.1662 | 129.0003 | 22620 | 29.1964 | 0.9127 | 0.7721 |
183
- | 0.1646 | 130.0003 | 22794 | 27.4540 | 0.9099 | 0.7677 |
184
- | 0.1614 | 131.0003 | 22968 | 28.4644 | 0.9078 | 0.7678 |
185
- | 0.15 | 132.0003 | 23142 | 30.0667 | 0.9025 | 0.7650 |
186
- | 0.1651 | 133.0003 | 23316 | 26.3396 | 0.9126 | 0.7749 |
187
- | 0.1574 | 134.0003 | 23490 | 26.7058 | 0.9059 | 0.7654 |
188
- | 0.1448 | 135.0003 | 23664 | 24.4675 | 0.9100 | 0.7735 |
189
- | 0.1522 | 136.0003 | 23838 | 27.5182 | 0.9121 | 0.7696 |
190
- | 0.1534 | 137.0003 | 24012 | 25.0229 | 0.9137 | 0.7741 |
191
- | 0.1564 | 138.0003 | 24186 | 22.2633 | 0.9111 | 0.7721 |
192
- | 0.1477 | 139.0003 | 24360 | 24.1703 | 0.9080 | 0.7768 |
193
- | 0.1425 | 140.0003 | 24534 | 22.9845 | 0.9066 | 0.7742 |
194
- | 0.148 | 141.0002 | 24708 | 24.5434 | 0.9071 | 0.7715 |
195
- | 0.1515 | 142.0002 | 24882 | 25.3716 | 0.9079 | 0.7771 |
196
- | 0.1446 | 143.0002 | 25056 | 23.9298 | 0.9136 | 0.7771 |
197
- | 0.1577 | 144.0002 | 25230 | 23.5104 | 0.9046 | 0.7730 |
198
- | 0.1458 | 145.0002 | 25404 | 22.6059 | 0.9106 | 0.7716 |
199
- | 0.1576 | 146.0002 | 25578 | 25.9200 | 0.9136 | 0.7801 |
200
- | 0.1478 | 147.0002 | 25752 | 26.5335 | 0.9102 | 0.7799 |
201
- | 0.1432 | 148.0002 | 25926 | 22.1442 | 0.9123 | 0.7766 |
202
- | 0.1453 | 149.0002 | 26100 | 22.0882 | 0.9064 | 0.7742 |
203
- | 0.1417 | 150.0002 | 26274 | 24.0154 | 0.9134 | 0.7822 |
204
- | 0.1366 | 151.0002 | 26448 | 23.7317 | 0.9079 | 0.7757 |
205
- | 0.1444 | 152.0002 | 26622 | 26.0509 | 0.9124 | 0.7805 |
206
- | 0.1363 | 153.0002 | 26796 | 27.0661 | 0.9092 | 0.7753 |
207
- | 0.1379 | 154.0001 | 26970 | 23.5876 | 0.9107 | 0.7820 |
208
- | 0.1401 | 155.0001 | 27144 | 27.4420 | 0.9111 | 0.7744 |
209
- | 0.1357 | 156.0001 | 27318 | 23.2410 | 0.9113 | 0.7798 |
210
- | 0.1388 | 157.0001 | 27492 | 23.3522 | 0.9092 | 0.7791 |
211
- | 0.14 | 158.0001 | 27666 | 23.8235 | 0.9070 | 0.7783 |
212
- | 0.1373 | 159.0001 | 27840 | 23.9633 | 0.9053 | 0.7767 |
213
- | 0.1322 | 160.0001 | 28014 | 25.2702 | 0.9128 | 0.7815 |
214
- | 0.137 | 161.0001 | 28188 | 24.1548 | 0.9110 | 0.7849 |
215
- | 0.1345 | 162.0001 | 28362 | 25.3524 | 0.9133 | 0.7891 |
216
- | 0.1395 | 163.0001 | 28536 | 23.2992 | 0.9075 | 0.7826 |
217
- | 0.134 | 164.0001 | 28710 | 24.8827 | 0.9173 | 0.7874 |
218
- | 0.1304 | 165.0001 | 28884 | 26.5549 | 0.9125 | 0.7822 |
219
- | 0.1336 | 166.0001 | 29058 | 23.3420 | 0.9180 | 0.7895 |
220
- | 0.1235 | 167.0001 | 29232 | 25.2007 | 0.9082 | 0.7831 |
221
- | 0.1311 | 168.0000 | 29406 | 22.8321 | 0.9145 | 0.7880 |
222
- | 0.1288 | 169.0000 | 29580 | 23.9222 | 0.9140 | 0.7840 |
223
- | 0.1259 | 170.0000 | 29754 | 22.1552 | 0.9088 | 0.7797 |
224
- | 0.1292 | 171.0000 | 29928 | 22.6555 | 0.9133 | 0.7830 |
225
- | 0.1284 | 172.0000 | 30102 | 25.8185 | 0.9104 | 0.7889 |
226
- | 0.1292 | 173.0000 | 30276 | 24.9292 | 0.9119 | 0.7889 |
227
- | 0.1264 | 173.0013 | 30450 | 26.0689 | 0.9150 | 0.7910 |
228
- | 0.133 | 174.0013 | 30624 | 25.3730 | 0.9049 | 0.7845 |
229
- | 0.1227 | 175.0013 | 30798 | 25.6720 | 0.9055 | 0.7807 |
230
- | 0.1299 | 176.0013 | 30972 | 22.2758 | 0.9117 | 0.7877 |
231
- | 0.1293 | 177.0013 | 31146 | 23.5661 | 0.9150 | 0.7883 |
232
- | 0.1296 | 178.0013 | 31320 | 24.4382 | 0.9121 | 0.7878 |
233
- | 0.1318 | 179.0013 | 31494 | 23.3907 | 0.9066 | 0.7868 |
234
- | 0.1328 | 180.0012 | 31668 | 23.1094 | 0.9118 | 0.7870 |
235
- | 0.1217 | 181.0012 | 31842 | 24.3687 | 0.9107 | 0.7852 |
236
- | 0.1203 | 182.0012 | 32016 | 22.5907 | 0.9123 | 0.7914 |
237
- | 0.1249 | 183.0012 | 32190 | 25.5700 | 0.9140 | 0.7917 |
238
- | 0.1235 | 184.0012 | 32364 | 19.8990 | 0.9183 | 0.8010 |
239
- | 0.1225 | 185.0012 | 32538 | 25.0416 | 0.9083 | 0.7840 |
240
- | 0.1242 | 186.0012 | 32712 | 24.3324 | 0.9159 | 0.7955 |
241
- | 0.1209 | 187.0012 | 32886 | 24.6332 | 0.9081 | 0.7851 |
242
- | 0.1235 | 188.0012 | 33060 | 24.0019 | 0.9151 | 0.7957 |
243
- | 0.1148 | 189.0012 | 33234 | 23.7111 | 0.9078 | 0.7918 |
244
- | 0.1236 | 190.0012 | 33408 | 21.0879 | 0.9114 | 0.7871 |
245
- | 0.1196 | 191.0012 | 33582 | 21.5855 | 0.9102 | 0.7908 |
246
- | 0.1241 | 192.0012 | 33756 | 20.3491 | 0.9140 | 0.7886 |
247
- | 0.1205 | 193.0012 | 33930 | 23.5627 | 0.9073 | 0.7871 |
248
- | 0.1168 | 194.0011 | 34104 | 23.6264 | 0.9116 | 0.7838 |
249
- | 0.1187 | 195.0011 | 34278 | 25.1882 | 0.9146 | 0.7923 |
250
- | 0.1188 | 196.0011 | 34452 | 24.8468 | 0.9098 | 0.7912 |
251
- | 0.1191 | 197.0011 | 34626 | 22.9641 | 0.9166 | 0.7942 |
252
- | 0.1173 | 198.0011 | 34800 | 22.6648 | 0.9123 | 0.7819 |
253
- | 0.1162 | 199.0011 | 34974 | 22.3425 | 0.9179 | 0.8014 |
254
- | 0.1268 | 200.0011 | 35148 | 21.0849 | 0.9141 | 0.7886 |
255
- | 0.1176 | 201.0011 | 35322 | 22.5339 | 0.9085 | 0.7850 |
256
- | 0.1166 | 202.0011 | 35496 | 21.6219 | 0.9108 | 0.7845 |
257
- | 0.112 | 203.0011 | 35670 | 22.4102 | 0.9110 | 0.7950 |
258
- | 0.1204 | 204.0011 | 35844 | 19.5659 | 0.9099 | 0.7899 |
259
- | 0.1194 | 205.0011 | 36018 | 19.9143 | 0.9148 | 0.7951 |
260
- | 0.1158 | 206.0011 | 36192 | 20.8213 | 0.9130 | 0.7963 |
261
- | 0.1143 | 207.0010 | 36366 | 22.3063 | 0.9092 | 0.7917 |
262
- | 0.1101 | 208.0010 | 36540 | 20.6140 | 0.9133 | 0.7916 |
263
- | 0.1091 | 209.0010 | 36714 | 18.7691 | 0.9155 | 0.7984 |
264
- | 0.1193 | 210.0010 | 36888 | 19.4397 | 0.9125 | 0.7924 |
265
- | 0.1186 | 211.0010 | 37062 | 21.5441 | 0.9118 | 0.7962 |
266
- | 0.1174 | 212.0010 | 37236 | 22.6313 | 0.9120 | 0.7928 |
267
- | 0.1188 | 213.0010 | 37410 | 22.9306 | 0.9117 | 0.7955 |
268
- | 0.1174 | 214.0010 | 37584 | 22.2580 | 0.9151 | 0.8004 |
269
- | 0.1049 | 215.0010 | 37758 | 23.2098 | 0.9153 | 0.7952 |
270
- | 0.1095 | 216.0010 | 37932 | 23.5414 | 0.9120 | 0.7960 |
271
- | 0.1125 | 217.0010 | 38106 | 21.5315 | 0.9148 | 0.7935 |
272
- | 0.1076 | 218.0010 | 38280 | 22.7590 | 0.9094 | 0.7975 |
273
- | 0.1063 | 219.0010 | 38454 | 23.7711 | 0.9133 | 0.7988 |
274
 
275
 
276
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 23.4559
20
+ - Accuracy: 0.9009
21
+ - Macro F1: 0.7754
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 6733
47
+ - training_steps: 134675
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
52
  |:-------------:|:--------:|:-----:|:---------------:|:--------:|:--------:|
53
+ | 66.0414 | 0.0013 | 169 | 45.5066 | 0.0791 | 0.0371 |
54
+ | 30.5662 | 1.0012 | 338 | 99.4357 | 0.1782 | 0.0575 |
55
+ | 9.1897 | 2.0012 | 507 | 276.6117 | 0.4840 | 0.1240 |
56
+ | 7.9539 | 3.0012 | 676 | 256.6143 | 0.5310 | 0.1318 |
57
+ | 7.2233 | 4.0012 | 845 | 254.0057 | 0.5582 | 0.1359 |
58
+ | 6.4464 | 5.0012 | 1014 | 207.8995 | 0.5727 | 0.1422 |
59
+ | 5.9043 | 6.0012 | 1183 | 166.3576 | 0.5842 | 0.1478 |
60
+ | 5.0332 | 7.0012 | 1352 | 96.2979 | 0.6022 | 0.1554 |
61
+ | 4.4072 | 8.0012 | 1521 | 66.5764 | 0.6113 | 0.1644 |
62
+ | 4.0547 | 9.0012 | 1690 | 45.1445 | 0.6179 | 0.1757 |
63
+ | 3.6737 | 10.0012 | 1859 | 33.9848 | 0.6223 | 0.1869 |
64
+ | 3.4285 | 11.0012 | 2028 | 31.1288 | 0.6459 | 0.2052 |
65
+ | 3.3623 | 12.0012 | 2197 | 24.5134 | 0.6210 | 0.2039 |
66
+ | 3.2019 | 13.0012 | 2366 | 23.5971 | 0.6475 | 0.2292 |
67
+ | 3.0474 | 14.0012 | 2535 | 21.7608 | 0.6667 | 0.2426 |
68
+ | 3.0552 | 15.0011 | 2704 | 20.3118 | 0.6611 | 0.2503 |
69
+ | 2.9144 | 16.0011 | 2873 | 19.2699 | 0.6816 | 0.2742 |
70
+ | 2.9418 | 17.0011 | 3042 | 20.1576 | 0.6801 | 0.2907 |
71
+ | 2.7112 | 18.0011 | 3211 | 19.1844 | 0.7020 | 0.3090 |
72
+ | 2.5652 | 19.0011 | 3380 | 19.4100 | 0.7243 | 0.3361 |
73
+ | 2.3628 | 20.0011 | 3549 | 19.0781 | 0.7325 | 0.3545 |
74
+ | 2.3024 | 21.0011 | 3718 | 18.4727 | 0.7443 | 0.3494 |
75
+ | 2.2622 | 22.0011 | 3887 | 19.9322 | 0.7593 | 0.4018 |
76
+ | 2.189 | 23.0011 | 4056 | 20.8379 | 0.7550 | 0.4059 |
77
+ | 2.093 | 24.0011 | 4225 | 20.2433 | 0.7665 | 0.4171 |
78
+ | 2.0585 | 25.0011 | 4394 | 21.6619 | 0.7683 | 0.4442 |
79
+ | 2.0054 | 26.0011 | 4563 | 23.0844 | 0.7739 | 0.4619 |
80
+ | 1.8643 | 27.0011 | 4732 | 22.4391 | 0.7855 | 0.4724 |
81
+ | 1.7645 | 28.0010 | 4901 | 22.5446 | 0.7847 | 0.4661 |
82
+ | 1.776 | 29.0010 | 5070 | 22.9436 | 0.7882 | 0.4698 |
83
+ | 1.658 | 30.0010 | 5239 | 23.9009 | 0.8001 | 0.4911 |
84
+ | 1.6649 | 31.0010 | 5408 | 24.1088 | 0.7925 | 0.4939 |
85
+ | 1.5606 | 32.0010 | 5577 | 24.0639 | 0.7965 | 0.4992 |
86
+ | 1.5835 | 33.0010 | 5746 | 27.6865 | 0.7960 | 0.5065 |
87
+ | 1.5307 | 34.0010 | 5915 | 26.1341 | 0.8099 | 0.5216 |
88
+ | 1.4567 | 35.0010 | 6084 | 26.4864 | 0.7881 | 0.4945 |
89
+ | 1.46 | 36.0010 | 6253 | 26.8242 | 0.8048 | 0.5327 |
90
+ | 1.4324 | 37.0010 | 6422 | 28.5602 | 0.8077 | 0.5220 |
91
+ | 1.2899 | 38.0010 | 6591 | 26.0987 | 0.7862 | 0.5082 |
92
+ | 1.3499 | 39.0010 | 6760 | 27.9458 | 0.8167 | 0.5399 |
93
+ | 1.2951 | 40.0010 | 6929 | 28.6402 | 0.8161 | 0.5581 |
94
+ | 1.2006 | 41.0010 | 7098 | 30.9283 | 0.8068 | 0.5419 |
95
+ | 1.1768 | 42.0009 | 7267 | 29.9452 | 0.8166 | 0.5349 |
96
+ | 1.0844 | 43.0009 | 7436 | 31.9286 | 0.8216 | 0.5637 |
97
+ | 1.1184 | 44.0009 | 7605 | 31.6431 | 0.8192 | 0.5678 |
98
+ | 1.0171 | 45.0009 | 7774 | 34.1279 | 0.8292 | 0.5808 |
99
+ | 0.9654 | 46.0009 | 7943 | 33.3439 | 0.8203 | 0.5461 |
100
+ | 0.9352 | 47.0009 | 8112 | 32.3734 | 0.8273 | 0.5743 |
101
+ | 0.8802 | 48.0009 | 8281 | 35.9858 | 0.8295 | 0.5827 |
102
+ | 0.8829 | 49.0009 | 8450 | 34.7353 | 0.8400 | 0.5957 |
103
+ | 0.8364 | 50.0009 | 8619 | 37.2584 | 0.8285 | 0.5889 |
104
+ | 0.7836 | 51.0009 | 8788 | 37.0566 | 0.8385 | 0.5995 |
105
+ | 0.838 | 52.0009 | 8957 | 33.9240 | 0.8421 | 0.5938 |
106
+ | 0.7214 | 53.0009 | 9126 | 33.5447 | 0.8275 | 0.5900 |
107
+ | 0.6711 | 54.0009 | 9295 | 38.6074 | 0.8452 | 0.6030 |
108
+ | 0.6888 | 55.0008 | 9464 | 36.8002 | 0.8458 | 0.6030 |
109
+ | 0.6462 | 56.0008 | 9633 | 37.6874 | 0.8487 | 0.6123 |
110
+ | 0.6886 | 57.0008 | 9802 | 42.6646 | 0.8540 | 0.6198 |
111
+ | 0.6321 | 58.0008 | 9971 | 38.9915 | 0.8402 | 0.6065 |
112
+ | 0.6019 | 59.0008 | 10140 | 40.9144 | 0.8540 | 0.6343 |
113
+ | 0.6194 | 60.0008 | 10309 | 43.9793 | 0.8545 | 0.6289 |
114
+ | 0.5537 | 61.0008 | 10478 | 41.7022 | 0.8542 | 0.6267 |
115
+ | 0.5573 | 62.0008 | 10647 | 44.5065 | 0.8596 | 0.6349 |
116
+ | 0.5019 | 63.0008 | 10816 | 43.7206 | 0.8564 | 0.6373 |
117
+ | 0.5022 | 64.0008 | 10985 | 43.4715 | 0.8606 | 0.6509 |
118
+ | 0.5034 | 65.0008 | 11154 | 41.7094 | 0.8629 | 0.6459 |
119
+ | 0.4845 | 66.0008 | 11323 | 42.9534 | 0.8630 | 0.6464 |
120
+ | 0.4515 | 67.0008 | 11492 | 42.9021 | 0.8673 | 0.6529 |
121
+ | 0.441 | 68.0007 | 11661 | 47.7305 | 0.8646 | 0.6474 |
122
+ | 0.4571 | 69.0007 | 11830 | 42.0647 | 0.8671 | 0.6584 |
123
+ | 0.418 | 70.0007 | 11999 | 42.9740 | 0.8662 | 0.6581 |
124
+ | 0.4027 | 71.0007 | 12168 | 40.8415 | 0.8664 | 0.6519 |
125
+ | 0.4095 | 72.0007 | 12337 | 42.2218 | 0.8760 | 0.6685 |
126
+ | 0.431 | 73.0007 | 12506 | 39.4808 | 0.8721 | 0.6755 |
127
+ | 0.3972 | 74.0007 | 12675 | 42.3933 | 0.8684 | 0.6679 |
128
+ | 0.3785 | 75.0007 | 12844 | 40.0500 | 0.8677 | 0.6757 |
129
+ | 0.3619 | 76.0007 | 13013 | 35.4613 | 0.8707 | 0.6718 |
130
+ | 0.3676 | 77.0007 | 13182 | 40.6240 | 0.8786 | 0.6812 |
131
+ | 0.3345 | 78.0007 | 13351 | 37.6601 | 0.8776 | 0.6810 |
132
+ | 0.3298 | 79.0007 | 13520 | 39.3323 | 0.8762 | 0.6814 |
133
+ | 0.3288 | 80.0007 | 13689 | 40.3533 | 0.8729 | 0.6793 |
134
+ | 0.3235 | 81.0007 | 13858 | 37.6332 | 0.8773 | 0.6813 |
135
+ | 0.3313 | 82.0006 | 14027 | 36.5068 | 0.8788 | 0.6929 |
136
+ | 0.3058 | 83.0006 | 14196 | 32.8040 | 0.8792 | 0.6933 |
137
+ | 0.2905 | 84.0006 | 14365 | 34.4625 | 0.8746 | 0.6881 |
138
+ | 0.3013 | 85.0006 | 14534 | 34.0483 | 0.8826 | 0.6953 |
139
+ | 0.2914 | 86.0006 | 14703 | 33.4755 | 0.8753 | 0.6959 |
140
+ | 0.3073 | 87.0006 | 14872 | 31.7930 | 0.8820 | 0.6961 |
141
+ | 0.297 | 88.0006 | 15041 | 31.7794 | 0.8793 | 0.6982 |
142
+ | 0.2662 | 89.0006 | 15210 | 32.3469 | 0.8864 | 0.6976 |
143
+ | 0.2752 | 90.0006 | 15379 | 32.7825 | 0.8810 | 0.6953 |
144
+ | 0.2714 | 91.0006 | 15548 | 31.0861 | 0.8825 | 0.6944 |
145
+ | 0.2714 | 92.0006 | 15717 | 34.0008 | 0.8850 | 0.6998 |
146
+ | 0.2784 | 93.0006 | 15886 | 32.7341 | 0.8837 | 0.7031 |
147
+ | 0.2631 | 94.0006 | 16055 | 29.4409 | 0.8867 | 0.7077 |
148
+ | 0.261 | 95.0005 | 16224 | 32.4728 | 0.8865 | 0.7021 |
149
+ | 0.2545 | 96.0005 | 16393 | 31.5098 | 0.8877 | 0.7165 |
150
+ | 0.258 | 97.0005 | 16562 | 32.7634 | 0.8871 | 0.7119 |
151
+ | 0.2527 | 98.0005 | 16731 | 31.0803 | 0.8808 | 0.6998 |
152
+ | 0.2303 | 99.0005 | 16900 | 28.9657 | 0.8836 | 0.7045 |
153
+ | 0.2496 | 100.0005 | 17069 | 29.9879 | 0.8861 | 0.7109 |
154
+ | 0.2392 | 101.0005 | 17238 | 27.7134 | 0.8827 | 0.7140 |
155
+ | 0.2373 | 102.0005 | 17407 | 26.7523 | 0.8856 | 0.7191 |
156
+ | 0.2317 | 103.0005 | 17576 | 28.4120 | 0.8877 | 0.7191 |
157
+ | 0.2287 | 104.0005 | 17745 | 29.3574 | 0.8919 | 0.7252 |
158
+ | 0.2271 | 105.0005 | 17914 | 27.6639 | 0.8865 | 0.7145 |
159
+ | 0.2066 | 106.0005 | 18083 | 28.6502 | 0.8939 | 0.7310 |
160
+ | 0.2074 | 107.0005 | 18252 | 26.7771 | 0.8801 | 0.7141 |
161
+ | 0.2268 | 108.0005 | 18421 | 27.9603 | 0.8860 | 0.7210 |
162
+ | 0.2279 | 109.0004 | 18590 | 28.8001 | 0.8911 | 0.7285 |
163
+ | 0.205 | 110.0004 | 18759 | 28.3425 | 0.8912 | 0.7269 |
164
+ | 0.2197 | 111.0004 | 18928 | 27.3474 | 0.8896 | 0.7213 |
165
+ | 0.2013 | 112.0004 | 19097 | 25.8196 | 0.8875 | 0.7290 |
166
+ | 0.1999 | 113.0004 | 19266 | 24.0100 | 0.8889 | 0.7223 |
167
+ | 0.1955 | 114.0004 | 19435 | 26.0019 | 0.8908 | 0.7231 |
168
+ | 0.2012 | 115.0004 | 19604 | 23.3148 | 0.8928 | 0.7309 |
169
+ | 0.1774 | 116.0004 | 19773 | 26.7032 | 0.8909 | 0.7245 |
170
+ | 0.1962 | 117.0004 | 19942 | 26.8682 | 0.8914 | 0.7331 |
171
+ | 0.1892 | 118.0004 | 20111 | 25.5151 | 0.8932 | 0.7340 |
172
+ | 0.1819 | 119.0004 | 20280 | 24.1410 | 0.8929 | 0.7354 |
173
+ | 0.1864 | 120.0004 | 20449 | 26.2352 | 0.8900 | 0.7310 |
174
+ | 0.1875 | 121.0004 | 20618 | 24.9018 | 0.8939 | 0.7375 |
175
+ | 0.2116 | 122.0003 | 20787 | 24.9070 | 0.8956 | 0.7388 |
176
+ | 0.1708 | 123.0003 | 20956 | 27.1748 | 0.8923 | 0.7337 |
177
+ | 0.1869 | 124.0003 | 21125 | 23.9289 | 0.8982 | 0.7437 |
178
+ | 0.1766 | 125.0003 | 21294 | 23.8033 | 0.8883 | 0.7387 |
179
+ | 0.1819 | 126.0003 | 21463 | 25.1713 | 0.8915 | 0.7372 |
180
+ | 0.1686 | 127.0003 | 21632 | 25.0575 | 0.8924 | 0.7404 |
181
+ | 0.1851 | 128.0003 | 21801 | 23.3824 | 0.8950 | 0.7412 |
182
+ | 0.1719 | 129.0003 | 21970 | 25.3546 | 0.8915 | 0.7403 |
183
+ | 0.1818 | 130.0003 | 22139 | 26.4819 | 0.8975 | 0.7443 |
184
+ | 0.158 | 131.0003 | 22308 | 24.6600 | 0.8929 | 0.7399 |
185
+ | 0.1756 | 132.0003 | 22477 | 25.5931 | 0.8956 | 0.7443 |
186
+ | 0.1665 | 133.0003 | 22646 | 22.5771 | 0.8881 | 0.7420 |
187
+ | 0.1605 | 134.0003 | 22815 | 23.8450 | 0.8959 | 0.7390 |
188
+ | 0.1707 | 135.0003 | 22984 | 23.1730 | 0.8963 | 0.7517 |
189
+ | 0.1546 | 136.0002 | 23153 | 24.5749 | 0.8961 | 0.7431 |
190
+ | 0.1656 | 137.0002 | 23322 | 24.1979 | 0.8946 | 0.7417 |
191
+ | 0.1591 | 138.0002 | 23491 | 22.9945 | 0.8976 | 0.7500 |
192
+ | 0.1804 | 139.0002 | 23660 | 25.5153 | 0.8931 | 0.7361 |
193
+ | 0.1626 | 140.0002 | 23829 | 24.8896 | 0.8966 | 0.7452 |
194
+ | 0.1495 | 141.0002 | 23998 | 23.6014 | 0.8951 | 0.7465 |
195
+ | 0.1728 | 142.0002 | 24167 | 25.7735 | 0.9003 | 0.7579 |
196
+ | 0.154 | 143.0002 | 24336 | 25.9609 | 0.8995 | 0.7498 |
197
+ | 0.1514 | 144.0002 | 24505 | 24.4235 | 0.8939 | 0.7455 |
198
+ | 0.1542 | 145.0002 | 24674 | 25.9741 | 0.8960 | 0.7557 |
199
+ | 0.1498 | 146.0002 | 24843 | 21.3591 | 0.8964 | 0.7473 |
200
+ | 0.1538 | 147.0002 | 25012 | 23.4223 | 0.8987 | 0.7596 |
201
+ | 0.1526 | 148.0002 | 25181 | 23.0419 | 0.8962 | 0.7535 |
202
+ | 0.1514 | 149.0001 | 25350 | 27.1732 | 0.8960 | 0.7513 |
203
+ | 0.1397 | 150.0001 | 25519 | 24.8274 | 0.8945 | 0.7536 |
204
+ | 0.1494 | 151.0001 | 25688 | 24.9705 | 0.8975 | 0.7579 |
205
+ | 0.1458 | 152.0001 | 25857 | 22.6088 | 0.8950 | 0.7519 |
206
+ | 0.1508 | 153.0001 | 26026 | 23.9277 | 0.8997 | 0.7597 |
207
+ | 0.142 | 154.0001 | 26195 | 25.4502 | 0.8994 | 0.7547 |
208
+ | 0.1483 | 155.0001 | 26364 | 24.4340 | 0.9014 | 0.7618 |
209
+ | 0.1549 | 156.0001 | 26533 | 25.2582 | 0.8981 | 0.7560 |
210
+ | 0.1345 | 157.0001 | 26702 | 26.6040 | 0.8970 | 0.7553 |
211
+ | 0.1442 | 158.0001 | 26871 | 24.3967 | 0.8945 | 0.7487 |
212
+ | 0.1452 | 159.0001 | 27040 | 25.1539 | 0.9011 | 0.7601 |
213
+ | 0.143 | 160.0001 | 27209 | 22.0844 | 0.8970 | 0.7583 |
214
+ | 0.1401 | 161.0001 | 27378 | 23.5366 | 0.8954 | 0.7534 |
215
+ | 0.1393 | 162.0001 | 27547 | 25.5086 | 0.8989 | 0.7612 |
216
+ | 0.1448 | 163.0000 | 27716 | 25.0967 | 0.8936 | 0.7555 |
217
+ | 0.143 | 164.0000 | 27885 | 25.3139 | 0.8979 | 0.7568 |
218
+ | 0.1411 | 165.0000 | 28054 | 24.6007 | 0.8957 | 0.7472 |
219
+ | 0.129 | 166.0000 | 28223 | 25.6638 | 0.9022 | 0.7647 |
220
+ | 0.1426 | 167.0000 | 28392 | 24.0550 | 0.8939 | 0.7521 |
221
+ | 0.1364 | 168.0000 | 28561 | 25.6411 | 0.8995 | 0.7631 |
222
+ | 0.1298 | 168.0013 | 28730 | 25.5864 | 0.8996 | 0.7623 |
223
+ | 0.134 | 169.0013 | 28899 | 23.7979 | 0.9030 | 0.7671 |
224
+ | 0.1336 | 170.0012 | 29068 | 21.3434 | 0.9014 | 0.7587 |
225
+ | 0.1353 | 171.0012 | 29237 | 23.2426 | 0.8999 | 0.7584 |
226
+ | 0.1304 | 172.0012 | 29406 | 23.6527 | 0.8982 | 0.7601 |
227
+ | 0.1343 | 173.0012 | 29575 | 21.5944 | 0.8996 | 0.7654 |
228
+ | 0.1333 | 174.0012 | 29744 | 24.0355 | 0.8995 | 0.7599 |
229
+ | 0.1353 | 175.0012 | 29913 | 23.6080 | 0.8994 | 0.7611 |
230
+ | 0.1231 | 176.0012 | 30082 | 21.9364 | 0.9040 | 0.7669 |
231
+ | 0.1242 | 177.0012 | 30251 | 23.4691 | 0.9009 | 0.7754 |
232
+ | 0.1305 | 178.0012 | 30420 | 24.9832 | 0.8961 | 0.7599 |
233
+ | 0.1262 | 179.0012 | 30589 | 23.1082 | 0.9026 | 0.7725 |
234
+ | 0.1386 | 180.0012 | 30758 | 20.7883 | 0.8968 | 0.7614 |
235
+ | 0.1365 | 181.0012 | 30927 | 21.9420 | 0.9010 | 0.7693 |
236
+ | 0.1277 | 182.0012 | 31096 | 23.0758 | 0.8988 | 0.7588 |
237
+ | 0.1289 | 183.0012 | 31265 | 25.0762 | 0.8994 | 0.7637 |
238
+ | 0.124 | 184.0011 | 31434 | 24.0734 | 0.9019 | 0.7713 |
239
+ | 0.1236 | 185.0011 | 31603 | 25.2106 | 0.9018 | 0.7680 |
240
+ | 0.1327 | 186.0011 | 31772 | 21.5374 | 0.9038 | 0.7711 |
241
+ | 0.1174 | 187.0011 | 31941 | 24.6814 | 0.9022 | 0.7684 |
242
+ | 0.1207 | 188.0011 | 32110 | 23.4494 | 0.9009 | 0.7702 |
243
+ | 0.1224 | 189.0011 | 32279 | 24.9296 | 0.8943 | 0.7568 |
244
+ | 0.1237 | 190.0011 | 32448 | 25.2705 | 0.8981 | 0.7645 |
245
+ | 0.1224 | 191.0011 | 32617 | 24.9507 | 0.8991 | 0.7689 |
246
+ | 0.124 | 192.0011 | 32786 | 25.1499 | 0.9016 | 0.7693 |
247
+ | 0.1216 | 193.0011 | 32955 | 23.5471 | 0.9003 | 0.7703 |
248
+ | 0.1134 | 194.0011 | 33124 | 23.3804 | 0.8946 | 0.7629 |
249
+ | 0.1209 | 195.0011 | 33293 | 23.8075 | 0.9011 | 0.7709 |
250
+ | 0.1157 | 196.0011 | 33462 | 27.0996 | 0.8993 | 0.7643 |
251
+ | 0.1214 | 197.0010 | 33631 | 24.5687 | 0.8963 | 0.7633 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
252
 
253
 
254
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aec243d411499ee7690a0a2aa91c8788d7d67ffa6adebce6a359a969e03e6f00
3
  size 126037432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91900d37f80e11b1fecae84b5f99e7898d9cc4ee32de4b0eeb6a40e38d94376a
3
  size 126037432
runs/4-by=2006-psr=0.1/events.out.tfevents.1747471591.yara2.3569921.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:864a40df74beb39c31a68b2db31a041c95e38085d643f3e8ecb42f8d34f16700
3
+ size 470