Hugging Face's logo

Arthur-Tsai
/
histv4_ftis_pretrain_tssp-smlm_0329

Transformers
TensorBoard
Safetensors
hierarchical-sentence-transformer-v2
Generated from Trainer
Model card Files
xet
 Metrics Community
Arthur-Tsai commited on
Commit
c8b5899
·
verified ·
1 Parent(s): f5c8cae

End of training

Browse files
Files changed (3) hide show
  1. README.md +132 -233
  2. model.safetensors +1 -1
  3. runs/0-sample_rate=1.0/events.out.tfevents.1743435435.ana2.1612913.1 +3 -0
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [Arthur-Tsai/histv4_pretrain_tssp-smlm](https://huggingface.co/Arthur-Tsai/histv4_pretrain_tssp-smlm) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.6272
21
- - Accuracy: 0.8771
22
- - Macro F1: 0.7080
23
 
24
  ## Model description
25
 
@@ -44,241 +44,140 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - lr_scheduler_warmup_steps: 6725
48
- - training_steps: 134500
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
53
  |:-------------:|:--------:|:-----:|:---------------:|:--------:|:--------:|
54
- | 38.9524 | 1.0002 | 100 | 25.4702 | 0.0504 | 0.0260 |
55
- | 23.6969 | 2.0005 | 200 | 14.6119 | 0.0610 | 0.0284 |
56
- | 11.4531 | 4.0002 | 300 | 8.3989 | 0.2494 | 0.0798 |
57
- | 7.7719 | 5.0004 | 400 | 6.9395 | 0.5031 | 0.1306 |
58
- | 6.7875 | 7.0002 | 500 | 6.4866 | 0.5527 | 0.1471 |
59
- | 6.2386 | 8.0004 | 600 | 5.7786 | 0.5771 | 0.1541 |
60
- | 5.8795 | 10.0001 | 700 | 5.5945 | 0.5915 | 0.1560 |
61
- | 5.4314 | 11.0004 | 800 | 4.9156 | 0.6040 | 0.1660 |
62
- | 5.0565 | 13.0001 | 900 | 4.2589 | 0.6115 | 0.1720 |
63
- | 4.6784 | 14.0004 | 1000 | 4.0632 | 0.6228 | 0.1730 |
64
- | 4.3903 | 16.0001 | 1100 | 3.4836 | 0.6337 | 0.1879 |
65
- | 3.7652 | 17.0003 | 1200 | 3.3140 | 0.6314 | 0.1917 |
66
- | 3.5554 | 19.0001 | 1300 | 2.9970 | 0.6519 | 0.1959 |
67
- | 3.2164 | 20.0003 | 1400 | 2.7557 | 0.6619 | 0.2037 |
68
- | 2.9022 | 22.0000 | 1500 | 2.5274 | 0.6746 | 0.2158 |
69
- | 2.745 | 23.0003 | 1600 | 2.3551 | 0.6914 | 0.2315 |
70
- | 2.4721 | 24.0005 | 1700 | 2.3607 | 0.6932 | 0.2416 |
71
- | 2.3065 | 26.0002 | 1800 | 2.1845 | 0.7110 | 0.2545 |
72
- | 2.3132 | 27.0005 | 1900 | 2.1555 | 0.7144 | 0.2547 |
73
- | 2.069 | 29.0002 | 2000 | 2.0353 | 0.7229 | 0.2781 |
74
- | 2.065 | 30.0004 | 2100 | 2.0333 | 0.7239 | 0.2881 |
75
- | 1.9441 | 32.0002 | 2200 | 2.0021 | 0.7312 | 0.2978 |
76
- | 1.8603 | 33.0004 | 2300 | 2.0704 | 0.7178 | 0.2966 |
77
- | 1.8589 | 35.0001 | 2400 | 1.8634 | 0.7422 | 0.3310 |
78
- | 1.6732 | 36.0004 | 2500 | 1.8567 | 0.7467 | 0.3422 |
79
- | 1.6328 | 38.0001 | 2600 | 1.8362 | 0.7482 | 0.3485 |
80
- | 1.5936 | 39.0004 | 2700 | 1.7911 | 0.7518 | 0.3736 |
81
- | 1.5476 | 41.0001 | 2800 | 1.9220 | 0.7432 | 0.3484 |
82
- | 1.4547 | 42.0003 | 2900 | 1.7732 | 0.7573 | 0.3823 |
83
- | 1.4111 | 44.0001 | 3000 | 1.8029 | 0.7605 | 0.3851 |
84
- | 1.3497 | 45.0003 | 3100 | 1.7707 | 0.7684 | 0.4061 |
85
- | 1.3677 | 47.0000 | 3200 | 1.8070 | 0.7547 | 0.4303 |
86
- | 1.2558 | 48.0003 | 3300 | 1.7805 | 0.7701 | 0.4153 |
87
- | 1.2228 | 49.0005 | 3400 | 1.6754 | 0.7754 | 0.4497 |
88
- | 1.1783 | 51.0002 | 3500 | 1.7035 | 0.7715 | 0.4393 |
89
- | 1.1714 | 52.0005 | 3600 | 1.6420 | 0.7765 | 0.4683 |
90
- | 1.1496 | 54.0002 | 3700 | 1.6010 | 0.7833 | 0.4685 |
91
- | 1.0547 | 55.0004 | 3800 | 1.6716 | 0.7833 | 0.4689 |
92
- | 1.0515 | 57.0002 | 3900 | 1.6513 | 0.7878 | 0.4839 |
93
- | 1.0019 | 58.0004 | 4000 | 1.6623 | 0.7865 | 0.4932 |
94
- | 0.9517 | 60.0001 | 4100 | 1.5528 | 0.7887 | 0.4999 |
95
- | 0.9249 | 61.0004 | 4200 | 1.5528 | 0.7949 | 0.5063 |
96
- | 0.9072 | 63.0001 | 4300 | 1.5955 | 0.7973 | 0.5230 |
97
- | 0.8861 | 64.0004 | 4400 | 1.5772 | 0.8012 | 0.5267 |
98
- | 0.8687 | 66.0001 | 4500 | 1.5187 | 0.8063 | 0.5236 |
99
- | 0.8164 | 67.0003 | 4600 | 1.6058 | 0.8023 | 0.5409 |
100
- | 0.7923 | 69.0001 | 4700 | 1.5692 | 0.7978 | 0.5416 |
101
- | 0.8065 | 70.0003 | 4800 | 1.6526 | 0.7905 | 0.5321 |
102
- | 0.771 | 72.0000 | 4900 | 1.6163 | 0.7966 | 0.5340 |
103
- | 0.7377 | 73.0003 | 5000 | 1.5363 | 0.8146 | 0.5564 |
104
- | 0.7194 | 74.0005 | 5100 | 1.5270 | 0.8135 | 0.5648 |
105
- | 0.706 | 76.0002 | 5200 | 1.5804 | 0.8068 | 0.5563 |
106
- | 0.6827 | 77.0005 | 5300 | 1.5398 | 0.8132 | 0.5569 |
107
- | 0.6852 | 79.0002 | 5400 | 1.4756 | 0.8228 | 0.5733 |
108
- | 0.6333 | 80.0004 | 5500 | 1.4959 | 0.8216 | 0.5766 |
109
- | 0.6288 | 82.0002 | 5600 | 1.4462 | 0.8282 | 0.5843 |
110
- | 0.6165 | 83.0004 | 5700 | 1.5467 | 0.8237 | 0.5788 |
111
- | 0.6153 | 85.0001 | 5800 | 1.5207 | 0.8249 | 0.5832 |
112
- | 0.593 | 86.0004 | 5900 | 1.5168 | 0.8303 | 0.5918 |
113
- | 0.5669 | 88.0001 | 6000 | 1.4940 | 0.8296 | 0.5837 |
114
- | 0.5583 | 89.0004 | 6100 | 1.4895 | 0.8305 | 0.5964 |
115
- | 0.5479 | 91.0001 | 6200 | 1.5508 | 0.8360 | 0.5961 |
116
- | 0.5385 | 92.0003 | 6300 | 1.4987 | 0.8331 | 0.6056 |
117
- | 0.5191 | 94.0001 | 6400 | 1.5468 | 0.8353 | 0.6039 |
118
- | 0.5123 | 95.0003 | 6500 | 1.5690 | 0.8292 | 0.6087 |
119
- | 0.531 | 97.0000 | 6600 | 1.4221 | 0.8345 | 0.6110 |
120
- | 0.5194 | 98.0003 | 6700 | 1.4363 | 0.8365 | 0.6105 |
121
- | 0.4885 | 99.0005 | 6800 | 1.5579 | 0.8297 | 0.6109 |
122
- | 0.4672 | 101.0002 | 6900 | 1.5172 | 0.8405 | 0.6117 |
123
- | 0.4791 | 102.0005 | 7000 | 1.5465 | 0.8386 | 0.6122 |
124
- | 0.4622 | 104.0002 | 7100 | 1.5033 | 0.8428 | 0.6198 |
125
- | 0.4392 | 105.0004 | 7200 | 1.5061 | 0.8426 | 0.6205 |
126
- | 0.4486 | 107.0002 | 7300 | 1.5635 | 0.8389 | 0.6164 |
127
- | 0.4339 | 108.0004 | 7400 | 1.4260 | 0.8519 | 0.6348 |
128
- | 0.4256 | 110.0001 | 7500 | 1.6025 | 0.8448 | 0.6298 |
129
- | 0.4162 | 111.0004 | 7600 | 1.5331 | 0.8441 | 0.6327 |
130
- | 0.413 | 113.0001 | 7700 | 1.4859 | 0.8494 | 0.6238 |
131
- | 0.4146 | 114.0004 | 7800 | 1.5788 | 0.8483 | 0.6327 |
132
- | 0.4176 | 116.0001 | 7900 | 1.5794 | 0.8472 | 0.6314 |
133
- | 0.4125 | 117.0003 | 8000 | 1.4955 | 0.8475 | 0.6425 |
134
- | 0.389 | 119.0001 | 8100 | 1.4970 | 0.8532 | 0.6406 |
135
- | 0.3935 | 120.0003 | 8200 | 1.4477 | 0.8519 | 0.6439 |
136
- | 0.3701 | 122.0000 | 8300 | 1.5302 | 0.8543 | 0.6438 |
137
- | 0.3757 | 123.0003 | 8400 | 1.4896 | 0.8518 | 0.6472 |
138
- | 0.379 | 124.0005 | 8500 | 1.4589 | 0.8550 | 0.6523 |
139
- | 0.3589 | 126.0002 | 8600 | 1.5369 | 0.8579 | 0.6485 |
140
- | 0.3608 | 127.0005 | 8700 | 1.4789 | 0.8541 | 0.6527 |
141
- | 0.3575 | 129.0002 | 8800 | 1.5673 | 0.8578 | 0.6559 |
142
- | 0.353 | 130.0004 | 8900 | 1.4892 | 0.8562 | 0.6547 |
143
- | 0.345 | 132.0002 | 9000 | 1.5182 | 0.8525 | 0.6513 |
144
- | 0.3454 | 133.0004 | 9100 | 1.4917 | 0.8561 | 0.6524 |
145
- | 0.3398 | 135.0001 | 9200 | 1.5004 | 0.8580 | 0.6574 |
146
- | 0.3424 | 136.0004 | 9300 | 1.5002 | 0.8590 | 0.6582 |
147
- | 0.3444 | 138.0001 | 9400 | 1.5448 | 0.8581 | 0.6599 |
148
- | 0.3344 | 139.0004 | 9500 | 1.5231 | 0.8541 | 0.6645 |
149
- | 0.3341 | 141.0001 | 9600 | 1.5717 | 0.8594 | 0.6650 |
150
- | 0.3259 | 142.0003 | 9700 | 1.5598 | 0.8583 | 0.6637 |
151
- | 0.3243 | 144.0001 | 9800 | 1.6004 | 0.8595 | 0.6602 |
152
- | 0.3236 | 145.0003 | 9900 | 1.5481 | 0.8547 | 0.6693 |
153
- | 0.3212 | 147.0000 | 10000 | 1.4696 | 0.8637 | 0.6698 |
154
- | 0.3137 | 148.0003 | 10100 | 1.5725 | 0.8518 | 0.6746 |
155
- | 0.3205 | 149.0005 | 10200 | 1.4266 | 0.8621 | 0.6686 |
156
- | 0.3102 | 151.0002 | 10300 | 1.5743 | 0.8642 | 0.6709 |
157
- | 0.3129 | 152.0005 | 10400 | 1.5302 | 0.8644 | 0.6710 |
158
- | 0.3094 | 154.0002 | 10500 | 1.5116 | 0.8609 | 0.6730 |
159
- | 0.3058 | 155.0004 | 10600 | 1.5835 | 0.8608 | 0.6707 |
160
- | 0.3063 | 157.0002 | 10700 | 1.6110 | 0.8623 | 0.6706 |
161
- | 0.2969 | 158.0004 | 10800 | 1.6587 | 0.8589 | 0.6674 |
162
- | 0.3022 | 160.0001 | 10900 | 1.7630 | 0.8604 | 0.6698 |
163
- | 0.2979 | 161.0004 | 11000 | 1.5528 | 0.8608 | 0.6727 |
164
- | 0.3002 | 163.0001 | 11100 | 1.5465 | 0.8646 | 0.6708 |
165
- | 0.2979 | 164.0004 | 11200 | 1.6061 | 0.8666 | 0.6769 |
166
- | 0.2908 | 166.0001 | 11300 | 1.6029 | 0.8643 | 0.6738 |
167
- | 0.2912 | 167.0003 | 11400 | 1.5405 | 0.8678 | 0.6776 |
168
- | 0.2898 | 169.0001 | 11500 | 1.5441 | 0.8702 | 0.6845 |
169
- | 0.2907 | 170.0003 | 11600 | 1.5258 | 0.8683 | 0.6799 |
170
- | 0.2893 | 172.0000 | 11700 | 1.5444 | 0.8645 | 0.6779 |
171
- | 0.2848 | 173.0003 | 11800 | 1.5946 | 0.8637 | 0.6753 |
172
- | 0.2864 | 174.0005 | 11900 | 1.5291 | 0.8652 | 0.6777 |
173
- | 0.2896 | 176.0002 | 12000 | 1.5473 | 0.8646 | 0.6805 |
174
- | 0.2889 | 177.0005 | 12100 | 1.6414 | 0.8661 | 0.6792 |
175
- | 0.2821 | 179.0002 | 12200 | 1.6235 | 0.8649 | 0.6800 |
176
- | 0.2824 | 180.0004 | 12300 | 1.5445 | 0.8639 | 0.6777 |
177
- | 0.2774 | 182.0002 | 12400 | 1.6450 | 0.8679 | 0.6823 |
178
- | 0.2776 | 183.0004 | 12500 | 1.7040 | 0.8655 | 0.6769 |
179
- | 0.2801 | 185.0001 | 12600 | 1.6475 | 0.8629 | 0.6785 |
180
- | 0.2745 | 186.0004 | 12700 | 1.5569 | 0.8650 | 0.6776 |
181
- | 0.2791 | 188.0001 | 12800 | 1.6554 | 0.8638 | 0.6848 |
182
- | 0.2753 | 189.0004 | 12900 | 1.5796 | 0.8674 | 0.6844 |
183
- | 0.2753 | 191.0001 | 13000 | 1.6561 | 0.8665 | 0.6847 |
184
- | 0.2757 | 192.0003 | 13100 | 1.5725 | 0.8691 | 0.6885 |
185
- | 0.2715 | 194.0001 | 13200 | 1.6434 | 0.8690 | 0.6917 |
186
- | 0.2743 | 195.0003 | 13300 | 1.6730 | 0.8696 | 0.6889 |
187
- | 0.2685 | 197.0000 | 13400 | 1.5647 | 0.8695 | 0.6848 |
188
- | 0.2697 | 198.0003 | 13500 | 1.5948 | 0.8686 | 0.6880 |
189
- | 0.2794 | 199.0005 | 13600 | 1.5314 | 0.8673 | 0.6841 |
190
- | 0.2706 | 201.0002 | 13700 | 1.6055 | 0.8679 | 0.6886 |
191
- | 0.266 | 202.0005 | 13800 | 1.5865 | 0.8692 | 0.6932 |
192
- | 0.2689 | 204.0002 | 13900 | 1.6282 | 0.8688 | 0.6869 |
193
- | 0.2674 | 205.0004 | 14000 | 1.5943 | 0.8685 | 0.6874 |
194
- | 0.27 | 207.0002 | 14100 | 1.6560 | 0.8677 | 0.6895 |
195
- | 0.264 | 208.0004 | 14200 | 1.7276 | 0.8624 | 0.6788 |
196
- | 0.2613 | 210.0001 | 14300 | 1.6798 | 0.8738 | 0.6871 |
197
- | 0.2623 | 211.0004 | 14400 | 1.5849 | 0.8712 | 0.6891 |
198
- | 0.2665 | 213.0001 | 14500 | 1.6706 | 0.8664 | 0.6868 |
199
- | 0.2624 | 214.0004 | 14600 | 1.6687 | 0.8698 | 0.6905 |
200
- | 0.2579 | 216.0001 | 14700 | 1.5432 | 0.8698 | 0.6934 |
201
- | 0.2672 | 217.0003 | 14800 | 1.6244 | 0.8655 | 0.6922 |
202
- | 0.2673 | 219.0001 | 14900 | 1.5026 | 0.8725 | 0.6950 |
203
- | 0.2657 | 220.0003 | 15000 | 1.6586 | 0.8727 | 0.6918 |
204
- | 0.2598 | 222.0000 | 15100 | 1.6447 | 0.8727 | 0.6933 |
205
- | 0.2621 | 223.0003 | 15200 | 1.6158 | 0.8728 | 0.6933 |
206
- | 0.256 | 224.0005 | 15300 | 1.7035 | 0.8689 | 0.6918 |
207
- | 0.2578 | 226.0002 | 15400 | 1.5341 | 0.8719 | 0.6948 |
208
- | 0.2552 | 227.0005 | 15500 | 1.6572 | 0.8703 | 0.6918 |
209
- | 0.2551 | 229.0002 | 15600 | 1.6068 | 0.8718 | 0.6934 |
210
- | 0.263 | 230.0004 | 15700 | 1.7440 | 0.8718 | 0.6940 |
211
- | 0.2567 | 232.0002 | 15800 | 1.5865 | 0.8709 | 0.6954 |
212
- | 0.2538 | 233.0004 | 15900 | 1.6325 | 0.8691 | 0.6933 |
213
- | 0.2534 | 235.0001 | 16000 | 1.5723 | 0.8693 | 0.6930 |
214
- | 0.254 | 236.0004 | 16100 | 1.6220 | 0.8703 | 0.6946 |
215
- | 0.2509 | 238.0001 | 16200 | 1.7125 | 0.8702 | 0.6885 |
216
- | 0.2513 | 239.0004 | 16300 | 1.7017 | 0.8709 | 0.6957 |
217
- | 0.2567 | 241.0001 | 16400 | 1.6581 | 0.8710 | 0.6996 |
218
- | 0.2579 | 242.0003 | 16500 | 1.6368 | 0.8703 | 0.6962 |
219
- | 0.2665 | 244.0001 | 16600 | 1.5685 | 0.8659 | 0.6928 |
220
- | 0.2625 | 245.0003 | 16700 | 1.6895 | 0.8724 | 0.6972 |
221
- | 0.2539 | 247.0000 | 16800 | 1.5884 | 0.8696 | 0.6958 |
222
- | 0.252 | 248.0003 | 16900 | 1.6708 | 0.8731 | 0.6944 |
223
- | 0.2476 | 249.0005 | 17000 | 1.6286 | 0.8729 | 0.6983 |
224
- | 0.2486 | 251.0002 | 17100 | 1.6925 | 0.8751 | 0.6943 |
225
- | 0.2503 | 252.0005 | 17200 | 1.5907 | 0.8755 | 0.6992 |
226
- | 0.2489 | 254.0002 | 17300 | 1.7195 | 0.8715 | 0.6970 |
227
- | 0.2457 | 255.0004 | 17400 | 1.6367 | 0.8765 | 0.6995 |
228
- | 0.2517 | 257.0002 | 17500 | 1.7663 | 0.8649 | 0.6946 |
229
- | 0.2414 | 258.0004 | 17600 | 1.6841 | 0.8766 | 0.7006 |
230
- | 0.2462 | 260.0001 | 17700 | 1.6303 | 0.8748 | 0.7017 |
231
- | 0.2433 | 261.0004 | 17800 | 1.6469 | 0.8727 | 0.6942 |
232
- | 0.2461 | 263.0001 | 17900 | 1.6379 | 0.8717 | 0.6962 |
233
- | 0.245 | 264.0004 | 18000 | 1.6443 | 0.8724 | 0.6975 |
234
- | 0.2463 | 266.0001 | 18100 | 1.6377 | 0.8761 | 0.7015 |
235
- | 0.2433 | 267.0003 | 18200 | 1.7548 | 0.8707 | 0.6976 |
236
- | 0.2398 | 269.0001 | 18300 | 1.5549 | 0.8749 | 0.6991 |
237
- | 0.242 | 270.0003 | 18400 | 1.6925 | 0.8761 | 0.7021 |
238
- | 0.2429 | 272.0000 | 18500 | 1.7503 | 0.8728 | 0.6992 |
239
- | 0.2428 | 273.0003 | 18600 | 1.6138 | 0.8748 | 0.7017 |
240
- | 0.2442 | 274.0005 | 18700 | 1.5828 | 0.8755 | 0.7033 |
241
- | 0.25 | 276.0002 | 18800 | 1.7209 | 0.8717 | 0.6960 |
242
- | 0.2441 | 277.0005 | 18900 | 1.6307 | 0.8765 | 0.7056 |
243
- | 0.2414 | 279.0002 | 19000 | 1.6609 | 0.8761 | 0.7029 |
244
- | 0.2371 | 280.0004 | 19100 | 1.7170 | 0.8741 | 0.7019 |
245
- | 0.2385 | 282.0002 | 19200 | 1.7016 | 0.8744 | 0.7018 |
246
- | 0.2385 | 283.0004 | 19300 | 1.6805 | 0.8741 | 0.7021 |
247
- | 0.2422 | 285.0001 | 19400 | 1.7424 | 0.8719 | 0.6973 |
248
- | 0.2403 | 286.0004 | 19500 | 1.7255 | 0.8725 | 0.6975 |
249
- | 0.2439 | 288.0001 | 19600 | 1.7645 | 0.8719 | 0.6959 |
250
- | 0.2414 | 289.0004 | 19700 | 1.7827 | 0.8757 | 0.7025 |
251
- | 0.2403 | 291.0001 | 19800 | 1.5922 | 0.8786 | 0.7042 |
252
- | 0.233 | 292.0003 | 19900 | 1.8774 | 0.8749 | 0.6993 |
253
- | 0.2357 | 294.0001 | 20000 | 1.6462 | 0.8756 | 0.6989 |
254
- | 0.2468 | 295.0003 | 20100 | 1.6571 | 0.8753 | 0.7041 |
255
- | 0.236 | 297.0000 | 20200 | 1.6926 | 0.8752 | 0.6999 |
256
- | 0.2341 | 298.0003 | 20300 | 1.7504 | 0.8770 | 0.7051 |
257
- | 0.2359 | 299.0005 | 20400 | 1.6860 | 0.8764 | 0.7001 |
258
- | 0.2377 | 301.0002 | 20500 | 1.6689 | 0.8746 | 0.6998 |
259
- | 0.2336 | 302.0005 | 20600 | 1.6257 | 0.8787 | 0.7081 |
260
- | 0.2329 | 304.0002 | 20700 | 1.6803 | 0.8759 | 0.7018 |
261
- | 0.236 | 305.0004 | 20800 | 1.7152 | 0.8783 | 0.7088 |
262
- | 0.2379 | 307.0002 | 20900 | 1.5757 | 0.8736 | 0.7013 |
263
- | 0.2394 | 308.0004 | 21000 | 1.7066 | 0.8751 | 0.7040 |
264
- | 0.2363 | 310.0001 | 21100 | 1.7033 | 0.8803 | 0.7075 |
265
- | 0.2428 | 311.0004 | 21200 | 1.6994 | 0.8762 | 0.6980 |
266
- | 0.2371 | 313.0001 | 21300 | 1.7504 | 0.8715 | 0.7021 |
267
- | 0.2293 | 314.0004 | 21400 | 1.6403 | 0.8751 | 0.7059 |
268
- | 0.2334 | 316.0001 | 21500 | 1.5695 | 0.8773 | 0.7026 |
269
- | 0.2306 | 317.0003 | 21600 | 1.7150 | 0.8767 | 0.7070 |
270
- | 0.236 | 319.0001 | 21700 | 1.5758 | 0.8797 | 0.7065 |
271
- | 0.2327 | 320.0003 | 21800 | 1.8039 | 0.8766 | 0.7069 |
272
- | 0.2327 | 322.0000 | 21900 | 1.7379 | 0.8748 | 0.7044 |
273
- | 0.2322 | 323.0003 | 22000 | 1.6924 | 0.8750 | 0.7028 |
274
- | 0.2348 | 324.0005 | 22100 | 1.6629 | 0.8749 | 0.7059 |
275
- | 0.2318 | 326.0002 | 22200 | 1.7193 | 0.8753 | 0.7054 |
276
- | 0.2308 | 327.0005 | 22300 | 1.7255 | 0.8752 | 0.7033 |
277
- | 0.2294 | 329.0002 | 22400 | 1.7101 | 0.8773 | 0.7029 |
278
- | 0.2292 | 330.0004 | 22500 | 1.7855 | 0.8745 | 0.7036 |
279
- | 0.2304 | 332.0002 | 22600 | 1.7470 | 0.8733 | 0.6953 |
280
- | 0.2359 | 333.0004 | 22700 | 1.6935 | 0.8764 | 0.7015 |
281
- | 0.2287 | 335.0001 | 22800 | 1.6621 | 0.8769 | 0.7041 |
282
 
283
 
284
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [Arthur-Tsai/histv4_pretrain_tssp-smlm](https://huggingface.co/Arthur-Tsai/histv4_pretrain_tssp-smlm) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6648
21
+ - Accuracy: 0.9701
22
+ - Macro F1: 0.9279
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 6733
48
+ - training_steps: 134675
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
53
  |:-------------:|:--------:|:-----:|:---------------:|:--------:|:--------:|
54
+ | 6.1814 | 0.0050 | 673 | 5.5662 | 0.5889 | 0.1547 |
55
+ | 3.493 | 1.0050 | 1346 | 2.8356 | 0.6560 | 0.2007 |
56
+ | 2.2738 | 2.0050 | 2019 | 2.0311 | 0.7206 | 0.2727 |
57
+ | 1.8894 | 3.0050 | 2692 | 1.6718 | 0.7628 | 0.3672 |
58
+ | 1.5981 | 4.0050 | 3365 | 1.4073 | 0.8069 | 0.4541 |
59
+ | 1.4813 | 5.0050 | 4038 | 1.2843 | 0.8245 | 0.5214 |
60
+ | 1.2253 | 6.0050 | 4711 | 1.0820 | 0.8590 | 0.5802 |
61
+ | 1.1132 | 7.0049 | 5384 | 1.0108 | 0.8738 | 0.6193 |
62
+ | 1.0131 | 8.0049 | 6057 | 0.9750 | 0.8674 | 0.6359 |
63
+ | 0.924 | 9.0049 | 6730 | 0.8751 | 0.8956 | 0.6899 |
64
+ | 0.8099 | 10.0049 | 7403 | 0.7859 | 0.9042 | 0.6947 |
65
+ | 0.7125 | 11.0049 | 8076 | 0.7251 | 0.9188 | 0.7355 |
66
+ | 0.7119 | 12.0049 | 8749 | 0.6956 | 0.9247 | 0.7625 |
67
+ | 0.657 | 13.0049 | 9422 | 0.6414 | 0.9327 | 0.7860 |
68
+ | 0.6067 | 14.0049 | 10095 | 0.6120 | 0.9409 | 0.8006 |
69
+ | 0.6006 | 15.0049 | 10768 | 0.5977 | 0.9408 | 0.8023 |
70
+ | 0.5399 | 16.0049 | 11441 | 0.6003 | 0.9448 | 0.8254 |
71
+ | 0.4939 | 17.0049 | 12114 | 0.6105 | 0.9439 | 0.8215 |
72
+ | 0.5075 | 18.0049 | 12787 | 0.5745 | 0.9483 | 0.8326 |
73
+ | 0.4736 | 19.0049 | 13460 | 0.5954 | 0.9501 | 0.8352 |
74
+ | 0.4643 | 20.0048 | 14133 | 0.5645 | 0.9522 | 0.8460 |
75
+ | 0.4683 | 21.0048 | 14806 | 0.5745 | 0.9518 | 0.8533 |
76
+ | 0.4654 | 22.0048 | 15479 | 0.5191 | 0.9573 | 0.8671 |
77
+ | 0.4271 | 23.0048 | 16152 | 0.5669 | 0.9539 | 0.8525 |
78
+ | 0.408 | 24.0048 | 16825 | 0.5903 | 0.9567 | 0.8668 |
79
+ | 0.3991 | 25.0048 | 17498 | 0.5830 | 0.9580 | 0.8776 |
80
+ | 0.3606 | 26.0048 | 18171 | 0.5854 | 0.9571 | 0.8759 |
81
+ | 0.3948 | 27.0048 | 18844 | 0.5952 | 0.9583 | 0.8769 |
82
+ | 0.3691 | 28.0048 | 19517 | 0.6049 | 0.9546 | 0.8726 |
83
+ | 0.3651 | 29.0048 | 20190 | 0.6013 | 0.9597 | 0.8870 |
84
+ | 0.3589 | 30.0048 | 20863 | 0.5842 | 0.9585 | 0.8801 |
85
+ | 0.3601 | 31.0048 | 21536 | 0.5945 | 0.9593 | 0.8886 |
86
+ | 0.3502 | 32.0048 | 22209 | 0.5607 | 0.9620 | 0.8935 |
87
+ | 0.3693 | 33.0048 | 22882 | 0.6231 | 0.9635 | 0.8874 |
88
+ | 0.3292 | 34.0047 | 23555 | 0.5569 | 0.9626 | 0.8892 |
89
+ | 0.3451 | 35.0047 | 24228 | 0.5738 | 0.9652 | 0.8999 |
90
+ | 0.3247 | 36.0047 | 24901 | 0.5274 | 0.9646 | 0.8876 |
91
+ | 0.3214 | 37.0047 | 25574 | 0.5932 | 0.9639 | 0.8955 |
92
+ | 0.3111 | 38.0047 | 26247 | 0.6105 | 0.9623 | 0.8991 |
93
+ | 0.326 | 39.0047 | 26920 | 0.5824 | 0.9643 | 0.8998 |
94
+ | 0.3243 | 40.0047 | 27593 | 0.6213 | 0.9633 | 0.9029 |
95
+ | 0.3068 | 41.0047 | 28266 | 0.5972 | 0.9647 | 0.9026 |
96
+ | 0.3022 | 42.0047 | 28939 | 0.5485 | 0.9660 | 0.9091 |
97
+ | 0.3055 | 43.0047 | 29612 | 0.5928 | 0.9667 | 0.8992 |
98
+ | 0.2979 | 44.0047 | 30285 | 0.6059 | 0.9645 | 0.9037 |
99
+ | 0.301 | 45.0047 | 30958 | 0.5866 | 0.9661 | 0.9073 |
100
+ | 0.3043 | 46.0047 | 31631 | 0.6022 | 0.9644 | 0.9019 |
101
+ | 0.2982 | 47.0046 | 32304 | 0.5707 | 0.9675 | 0.9077 |
102
+ | 0.2852 | 48.0046 | 32977 | 0.6089 | 0.9632 | 0.9036 |
103
+ | 0.2967 | 49.0046 | 33650 | 0.6050 | 0.9657 | 0.8864 |
104
+ | 0.297 | 50.0046 | 34323 | 0.6383 | 0.9638 | 0.9099 |
105
+ | 0.2865 | 51.0046 | 34996 | 0.6180 | 0.9669 | 0.9101 |
106
+ | 0.2992 | 52.0046 | 35669 | 0.5531 | 0.9645 | 0.9085 |
107
+ | 0.2805 | 53.0046 | 36342 | 0.6031 | 0.9661 | 0.9055 |
108
+ | 0.2839 | 54.0046 | 37015 | 0.6427 | 0.9639 | 0.9068 |
109
+ | 0.2754 | 55.0046 | 37688 | 0.6178 | 0.9679 | 0.9135 |
110
+ | 0.2818 | 56.0046 | 38361 | 0.6087 | 0.9667 | 0.9143 |
111
+ | 0.2719 | 57.0046 | 39034 | 0.6322 | 0.9670 | 0.9051 |
112
+ | 0.2768 | 58.0046 | 39707 | 0.6345 | 0.9677 | 0.9157 |
113
+ | 0.2709 | 59.0046 | 40380 | 0.5874 | 0.9699 | 0.9189 |
114
+ | 0.2836 | 60.0046 | 41053 | 0.5807 | 0.9685 | 0.9195 |
115
+ | 0.2708 | 61.0045 | 41726 | 0.5494 | 0.9703 | 0.9196 |
116
+ | 0.2669 | 62.0045 | 42399 | 0.6052 | 0.9665 | 0.9137 |
117
+ | 0.2701 | 63.0045 | 43072 | 0.6167 | 0.9646 | 0.9113 |
118
+ | 0.2659 | 64.0045 | 43745 | 0.5991 | 0.9689 | 0.9155 |
119
+ | 0.2598 | 65.0045 | 44418 | 0.5505 | 0.9700 | 0.9157 |
120
+ | 0.2701 | 66.0045 | 45091 | 0.5899 | 0.9688 | 0.9194 |
121
+ | 0.2757 | 67.0045 | 45764 | 0.6226 | 0.9680 | 0.9167 |
122
+ | 0.2728 | 68.0045 | 46437 | 0.5976 | 0.9677 | 0.9174 |
123
+ | 0.2661 | 69.0045 | 47110 | 0.6157 | 0.9667 | 0.8972 |
124
+ | 0.2646 | 70.0045 | 47783 | 0.6418 | 0.9657 | 0.9163 |
125
+ | 0.2621 | 71.0045 | 48456 | 0.6507 | 0.9692 | 0.9189 |
126
+ | 0.2628 | 72.0045 | 49129 | 0.6470 | 0.9660 | 0.9151 |
127
+ | 0.2652 | 73.0045 | 49802 | 0.6170 | 0.9668 | 0.9205 |
128
+ | 0.2604 | 74.0044 | 50475 | 0.6195 | 0.9697 | 0.9175 |
129
+ | 0.2547 | 75.0044 | 51148 | 0.5727 | 0.9683 | 0.9215 |
130
+ | 0.2639 | 76.0044 | 51821 | 0.6014 | 0.9694 | 0.9207 |
131
+ | 0.2539 | 77.0044 | 52494 | 0.6089 | 0.9686 | 0.9161 |
132
+ | 0.2586 | 78.0044 | 53167 | 0.6274 | 0.9688 | 0.9185 |
133
+ | 0.258 | 79.0044 | 53840 | 0.6107 | 0.9694 | 0.9234 |
134
+ | 0.2513 | 80.0044 | 54513 | 0.5746 | 0.9708 | 0.9223 |
135
+ | 0.2593 | 81.0044 | 55186 | 0.5986 | 0.9686 | 0.9236 |
136
+ | 0.2556 | 82.0044 | 55859 | 0.6483 | 0.9670 | 0.9232 |
137
+ | 0.2542 | 83.0044 | 56532 | 0.6052 | 0.9666 | 0.9201 |
138
+ | 0.2543 | 84.0044 | 57205 | 0.6558 | 0.9684 | 0.9230 |
139
+ | 0.2541 | 85.0044 | 57878 | 0.6251 | 0.9669 | 0.9206 |
140
+ | 0.2459 | 86.0044 | 58551 | 0.5984 | 0.9692 | 0.9224 |
141
+ | 0.247 | 87.0044 | 59224 | 0.6171 | 0.9693 | 0.9261 |
142
+ | 0.2477 | 88.0043 | 59897 | 0.6986 | 0.9679 | 0.9229 |
143
+ | 0.2476 | 89.0043 | 60570 | 0.7201 | 0.9691 | 0.9246 |
144
+ | 0.2447 | 90.0043 | 61243 | 0.6508 | 0.9693 | 0.9275 |
145
+ | 0.2441 | 91.0043 | 61916 | 0.6397 | 0.9672 | 0.9204 |
146
+ | 0.2446 | 92.0043 | 62589 | 0.6003 | 0.9683 | 0.9230 |
147
+ | 0.2479 | 93.0043 | 63262 | 0.5893 | 0.9704 | 0.9240 |
148
+ | 0.2508 | 94.0043 | 63935 | 0.5721 | 0.9689 | 0.9296 |
149
+ | 0.2429 | 95.0043 | 64608 | 0.6701 | 0.9704 | 0.9291 |
150
+ | 0.2415 | 96.0043 | 65281 | 0.5967 | 0.9695 | 0.9262 |
151
+ | 0.245 | 97.0043 | 65954 | 0.6655 | 0.9711 | 0.9277 |
152
+ | 0.2415 | 98.0043 | 66627 | 0.5518 | 0.9692 | 0.9240 |
153
+ | 0.2414 | 99.0043 | 67300 | 0.6633 | 0.9691 | 0.9257 |
154
+ | 0.2456 | 100.0043 | 67973 | 0.6249 | 0.9707 | 0.9305 |
155
+ | 0.2386 | 101.0042 | 68646 | 0.5712 | 0.9699 | 0.9274 |
156
+ | 0.2428 | 102.0042 | 69319 | 0.6618 | 0.9702 | 0.9296 |
157
+ | 0.242 | 103.0042 | 69992 | 0.5995 | 0.9685 | 0.9248 |
158
+ | 0.2353 | 104.0042 | 70665 | 0.6375 | 0.9706 | 0.9271 |
159
+ | 0.242 | 105.0042 | 71338 | 0.6279 | 0.9710 | 0.9265 |
160
+ | 0.2388 | 106.0042 | 72011 | 0.6067 | 0.9708 | 0.9346 |
161
+ | 0.2375 | 107.0042 | 72684 | 0.6514 | 0.9713 | 0.9297 |
162
+ | 0.2378 | 108.0042 | 73357 | 0.6535 | 0.9699 | 0.9246 |
163
+ | 0.2341 | 109.0042 | 74030 | 0.6010 | 0.9710 | 0.9053 |
164
+ | 0.2383 | 110.0042 | 74703 | 0.6420 | 0.9692 | 0.9271 |
165
+ | 0.2418 | 111.0042 | 75376 | 0.5911 | 0.9724 | 0.9336 |
166
+ | 0.2366 | 112.0042 | 76049 | 0.6536 | 0.9706 | 0.9234 |
167
+ | 0.2388 | 113.0042 | 76722 | 0.6341 | 0.9693 | 0.9238 |
168
+ | 0.2365 | 114.0042 | 77395 | 0.6533 | 0.9703 | 0.9260 |
169
+ | 0.2346 | 115.0041 | 78068 | 0.5889 | 0.9712 | 0.9324 |
170
+ | 0.2371 | 116.0041 | 78741 | 0.6251 | 0.9706 | 0.9295 |
171
+ | 0.2367 | 117.0041 | 79414 | 0.5921 | 0.9706 | 0.9284 |
172
+ | 0.2405 | 118.0041 | 80087 | 0.5847 | 0.9695 | 0.9314 |
173
+ | 0.2357 | 119.0041 | 80760 | 0.6325 | 0.9706 | 0.9259 |
174
+ | 0.2347 | 120.0041 | 81433 | 0.6381 | 0.9710 | 0.9276 |
175
+ | 0.2369 | 121.0041 | 82106 | 0.6613 | 0.9696 | 0.9274 |
176
+ | 0.2388 | 122.0041 | 82779 | 0.6684 | 0.9719 | 0.9309 |
177
+ | 0.2327 | 123.0041 | 83452 | 0.6534 | 0.9703 | 0.9251 |
178
+ | 0.2353 | 124.0041 | 84125 | 0.6549 | 0.9724 | 0.9321 |
179
+ | 0.237 | 125.0041 | 84798 | 0.6008 | 0.9720 | 0.9334 |
180
+ | 0.2353 | 126.0041 | 85471 | 0.6333 | 0.9706 | 0.9288 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
181
 
182
 
183
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d12f832df6f25197452f89c4f1a13f8dcbcb29175874fa4788ac9b538fffdb89
3
  size 127238056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5b8851b1ef0cbb19782fdc61f6144c51ce6b004af2447b4ec31bdc9a439bc0
3
  size 127238056
runs/0-sample_rate=1.0/events.out.tfevents.1743435435.ana2.1612913.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87930535e9ce2895dd130bdc1930257f7a1afa29575e0dd4ae7951e27d05dcd
3
+ size 470