update model card README.md
Browse files
README.md
CHANGED
@@ -13,12 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
This model is a fine-tuned version of [recobo/chemical-bert-uncased](https://huggingface.co/recobo/chemical-bert-uncased) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
-
-
|
17 |
-
- eval_runtime: 1.2451
|
18 |
-
- eval_samples_per_second: 321.256
|
19 |
-
- eval_steps_per_second: 5.622
|
20 |
-
- epoch: 51.0
|
21 |
-
- step: 3213
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -46,6 +41,212 @@ The following hyperparameters were used during training:
|
|
46 |
- num_epochs: 200
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
### Framework versions
|
50 |
|
51 |
- Transformers 4.24.0
|
|
|
13 |
|
14 |
This model is a fine-tuned version of [recobo/chemical-bert-uncased](https://huggingface.co/recobo/chemical-bert-uncased) on the None dataset.
|
15 |
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 0.7104
|
|
|
|
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
41 |
- num_epochs: 200
|
42 |
- mixed_precision_training: Native AMP
|
43 |
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 3.5876 | 1.0 | 63 | 2.7997 |
|
49 |
+
| 2.7843 | 2.0 | 126 | 2.3734 |
|
50 |
+
| 2.418 | 3.0 | 189 | 2.1510 |
|
51 |
+
| 2.2247 | 4.0 | 252 | 1.9822 |
|
52 |
+
| 2.062 | 5.0 | 315 | 1.8463 |
|
53 |
+
| 1.9875 | 6.0 | 378 | 1.8293 |
|
54 |
+
| 1.9034 | 7.0 | 441 | 1.7666 |
|
55 |
+
| 1.7818 | 8.0 | 504 | 1.6783 |
|
56 |
+
| 1.7131 | 9.0 | 567 | 1.5754 |
|
57 |
+
| 1.6793 | 10.0 | 630 | 1.5480 |
|
58 |
+
| 1.5773 | 11.0 | 693 | 1.4568 |
|
59 |
+
| 1.5391 | 12.0 | 756 | 1.5101 |
|
60 |
+
| 1.5049 | 13.0 | 819 | 1.4340 |
|
61 |
+
| 1.4476 | 14.0 | 882 | 1.4046 |
|
62 |
+
| 1.4032 | 15.0 | 945 | 1.3593 |
|
63 |
+
| 1.395 | 16.0 | 1008 | 1.3689 |
|
64 |
+
| 1.3353 | 17.0 | 1071 | 1.3350 |
|
65 |
+
| 1.3122 | 18.0 | 1134 | 1.2863 |
|
66 |
+
| 1.3036 | 19.0 | 1197 | 1.3690 |
|
67 |
+
| 1.2644 | 20.0 | 1260 | 1.1904 |
|
68 |
+
| 1.222 | 21.0 | 1323 | 1.1986 |
|
69 |
+
| 1.2091 | 22.0 | 1386 | 1.1650 |
|
70 |
+
| 1.2007 | 23.0 | 1449 | 1.1949 |
|
71 |
+
| 1.1456 | 24.0 | 1512 | 1.1649 |
|
72 |
+
| 1.1426 | 25.0 | 1575 | 1.1498 |
|
73 |
+
| 1.0883 | 26.0 | 1638 | 1.1489 |
|
74 |
+
| 1.0915 | 27.0 | 1701 | 1.1179 |
|
75 |
+
| 1.0635 | 28.0 | 1764 | 1.0726 |
|
76 |
+
| 1.0899 | 29.0 | 1827 | 1.1107 |
|
77 |
+
| 1.0251 | 30.0 | 1890 | 1.0944 |
|
78 |
+
| 1.0387 | 31.0 | 1953 | 1.0488 |
|
79 |
+
| 1.0037 | 32.0 | 2016 | 1.0679 |
|
80 |
+
| 1.0101 | 33.0 | 2079 | 1.0272 |
|
81 |
+
| 0.9595 | 34.0 | 2142 | 1.0158 |
|
82 |
+
| 0.9661 | 35.0 | 2205 | 1.0316 |
|
83 |
+
| 0.9535 | 36.0 | 2268 | 1.0086 |
|
84 |
+
| 0.9269 | 37.0 | 2331 | 1.0221 |
|
85 |
+
| 0.9395 | 38.0 | 2394 | 0.9626 |
|
86 |
+
| 0.9105 | 39.0 | 2457 | 0.9903 |
|
87 |
+
| 0.8888 | 40.0 | 2520 | 0.9892 |
|
88 |
+
| 0.9316 | 41.0 | 2583 | 0.9786 |
|
89 |
+
| 0.8804 | 42.0 | 2646 | 0.9938 |
|
90 |
+
| 0.8589 | 43.0 | 2709 | 1.0105 |
|
91 |
+
| 0.8573 | 44.0 | 2772 | 0.9729 |
|
92 |
+
| 0.8566 | 45.0 | 2835 | 0.9972 |
|
93 |
+
| 0.8392 | 46.0 | 2898 | 1.0085 |
|
94 |
+
| 0.8363 | 47.0 | 2961 | 0.9336 |
|
95 |
+
| 0.8184 | 48.0 | 3024 | 0.9886 |
|
96 |
+
| 0.7964 | 49.0 | 3087 | 0.9661 |
|
97 |
+
| 0.8025 | 50.0 | 3150 | 0.8956 |
|
98 |
+
| 0.8156 | 51.0 | 3213 | 0.9415 |
|
99 |
+
| 0.7906 | 52.0 | 3276 | 0.9381 |
|
100 |
+
| 0.7783 | 53.0 | 3339 | 0.9445 |
|
101 |
+
| 0.7696 | 54.0 | 3402 | 0.8859 |
|
102 |
+
| 0.763 | 55.0 | 3465 | 0.8851 |
|
103 |
+
| 0.7638 | 56.0 | 3528 | 0.9128 |
|
104 |
+
| 0.7576 | 57.0 | 3591 | 0.8629 |
|
105 |
+
| 0.757 | 58.0 | 3654 | 0.8917 |
|
106 |
+
| 0.7232 | 59.0 | 3717 | 0.8956 |
|
107 |
+
| 0.7327 | 60.0 | 3780 | 0.8727 |
|
108 |
+
| 0.7321 | 61.0 | 3843 | 0.8558 |
|
109 |
+
| 0.7131 | 62.0 | 3906 | 0.8876 |
|
110 |
+
| 0.696 | 63.0 | 3969 | 0.8872 |
|
111 |
+
| 0.6996 | 64.0 | 4032 | 0.7758 |
|
112 |
+
| 0.6807 | 65.0 | 4095 | 0.8657 |
|
113 |
+
| 0.6899 | 66.0 | 4158 | 0.8813 |
|
114 |
+
| 0.6873 | 67.0 | 4221 | 0.8488 |
|
115 |
+
| 0.6681 | 68.0 | 4284 | 0.8865 |
|
116 |
+
| 0.6758 | 69.0 | 4347 | 0.8447 |
|
117 |
+
| 0.6626 | 70.0 | 4410 | 0.8421 |
|
118 |
+
| 0.6535 | 71.0 | 4473 | 0.8313 |
|
119 |
+
| 0.6505 | 72.0 | 4536 | 0.8636 |
|
120 |
+
| 0.6654 | 73.0 | 4599 | 0.8433 |
|
121 |
+
| 0.6363 | 74.0 | 4662 | 0.7666 |
|
122 |
+
| 0.6395 | 75.0 | 4725 | 0.8882 |
|
123 |
+
| 0.6206 | 76.0 | 4788 | 0.8409 |
|
124 |
+
| 0.6365 | 77.0 | 4851 | 0.8807 |
|
125 |
+
| 0.6325 | 78.0 | 4914 | 0.8012 |
|
126 |
+
| 0.6142 | 79.0 | 4977 | 0.7705 |
|
127 |
+
| 0.6108 | 80.0 | 5040 | 0.8270 |
|
128 |
+
| 0.62 | 81.0 | 5103 | 0.8552 |
|
129 |
+
| 0.6188 | 82.0 | 5166 | 0.8377 |
|
130 |
+
| 0.6024 | 83.0 | 5229 | 0.7985 |
|
131 |
+
| 0.631 | 84.0 | 5292 | 0.8352 |
|
132 |
+
| 0.5871 | 85.0 | 5355 | 0.8086 |
|
133 |
+
| 0.6014 | 86.0 | 5418 | 0.8129 |
|
134 |
+
| 0.5842 | 87.0 | 5481 | 0.8649 |
|
135 |
+
| 0.5837 | 88.0 | 5544 | 0.8269 |
|
136 |
+
| 0.5958 | 89.0 | 5607 | 0.8407 |
|
137 |
+
| 0.564 | 90.0 | 5670 | 0.7906 |
|
138 |
+
| 0.5748 | 91.0 | 5733 | 0.7393 |
|
139 |
+
| 0.5918 | 92.0 | 5796 | 0.8445 |
|
140 |
+
| 0.5682 | 93.0 | 5859 | 0.8073 |
|
141 |
+
| 0.5497 | 94.0 | 5922 | 0.8165 |
|
142 |
+
| 0.5606 | 95.0 | 5985 | 0.7638 |
|
143 |
+
| 0.5593 | 96.0 | 6048 | 0.7929 |
|
144 |
+
| 0.5556 | 97.0 | 6111 | 0.7991 |
|
145 |
+
| 0.5604 | 98.0 | 6174 | 0.7417 |
|
146 |
+
| 0.5503 | 99.0 | 6237 | 0.8070 |
|
147 |
+
| 0.5561 | 100.0 | 6300 | 0.7845 |
|
148 |
+
| 0.5344 | 101.0 | 6363 | 0.7933 |
|
149 |
+
| 0.5209 | 102.0 | 6426 | 0.7741 |
|
150 |
+
| 0.5337 | 103.0 | 6489 | 0.7760 |
|
151 |
+
| 0.5437 | 104.0 | 6552 | 0.7634 |
|
152 |
+
| 0.5165 | 105.0 | 6615 | 0.7543 |
|
153 |
+
| 0.5343 | 106.0 | 6678 | 0.7661 |
|
154 |
+
| 0.5155 | 107.0 | 6741 | 0.7953 |
|
155 |
+
| 0.512 | 108.0 | 6804 | 0.8253 |
|
156 |
+
| 0.5259 | 109.0 | 6867 | 0.7570 |
|
157 |
+
| 0.5045 | 110.0 | 6930 | 0.7977 |
|
158 |
+
| 0.5115 | 111.0 | 6993 | 0.7598 |
|
159 |
+
| 0.5134 | 112.0 | 7056 | 0.7680 |
|
160 |
+
| 0.5076 | 113.0 | 7119 | 0.7696 |
|
161 |
+
| 0.5126 | 114.0 | 7182 | 0.7451 |
|
162 |
+
| 0.4963 | 115.0 | 7245 | 0.7923 |
|
163 |
+
| 0.5032 | 116.0 | 7308 | 0.7842 |
|
164 |
+
| 0.5137 | 117.0 | 7371 | 0.7239 |
|
165 |
+
| 0.488 | 118.0 | 7434 | 0.8188 |
|
166 |
+
| 0.4938 | 119.0 | 7497 | 0.7479 |
|
167 |
+
| 0.4866 | 120.0 | 7560 | 0.7761 |
|
168 |
+
| 0.4901 | 121.0 | 7623 | 0.7930 |
|
169 |
+
| 0.4877 | 122.0 | 7686 | 0.7733 |
|
170 |
+
| 0.4858 | 123.0 | 7749 | 0.7492 |
|
171 |
+
| 0.4813 | 124.0 | 7812 | 0.7645 |
|
172 |
+
| 0.4817 | 125.0 | 7875 | 0.7938 |
|
173 |
+
| 0.4822 | 126.0 | 7938 | 0.7253 |
|
174 |
+
| 0.4771 | 127.0 | 8001 | 0.7481 |
|
175 |
+
| 0.4769 | 128.0 | 8064 | 0.7402 |
|
176 |
+
| 0.4666 | 129.0 | 8127 | 0.7993 |
|
177 |
+
| 0.474 | 130.0 | 8190 | 0.7653 |
|
178 |
+
| 0.4718 | 131.0 | 8253 | 0.7524 |
|
179 |
+
| 0.4682 | 132.0 | 8316 | 0.7129 |
|
180 |
+
| 0.4698 | 133.0 | 8379 | 0.7806 |
|
181 |
+
| 0.4669 | 134.0 | 8442 | 0.7237 |
|
182 |
+
| 0.4401 | 135.0 | 8505 | 0.7185 |
|
183 |
+
| 0.4656 | 136.0 | 8568 | 0.7542 |
|
184 |
+
| 0.4569 | 137.0 | 8631 | 0.7412 |
|
185 |
+
| 0.4751 | 138.0 | 8694 | 0.7740 |
|
186 |
+
| 0.4474 | 139.0 | 8757 | 0.7636 |
|
187 |
+
| 0.4652 | 140.0 | 8820 | 0.7958 |
|
188 |
+
| 0.4539 | 141.0 | 8883 | 0.7410 |
|
189 |
+
| 0.4452 | 142.0 | 8946 | 0.7652 |
|
190 |
+
| 0.4516 | 143.0 | 9009 | 0.7337 |
|
191 |
+
| 0.4423 | 144.0 | 9072 | 0.7601 |
|
192 |
+
| 0.4542 | 145.0 | 9135 | 0.7692 |
|
193 |
+
| 0.4328 | 146.0 | 9198 | 0.7528 |
|
194 |
+
| 0.4503 | 147.0 | 9261 | 0.7673 |
|
195 |
+
| 0.4416 | 148.0 | 9324 | 0.7193 |
|
196 |
+
| 0.447 | 149.0 | 9387 | 0.7517 |
|
197 |
+
| 0.4434 | 150.0 | 9450 | 0.7241 |
|
198 |
+
| 0.4374 | 151.0 | 9513 | 0.7281 |
|
199 |
+
| 0.4334 | 152.0 | 9576 | 0.7150 |
|
200 |
+
| 0.4209 | 153.0 | 9639 | 0.7531 |
|
201 |
+
| 0.4405 | 154.0 | 9702 | 0.7252 |
|
202 |
+
| 0.4384 | 155.0 | 9765 | 0.7367 |
|
203 |
+
| 0.4265 | 156.0 | 9828 | 0.7111 |
|
204 |
+
| 0.4386 | 157.0 | 9891 | 0.7215 |
|
205 |
+
| 0.4276 | 158.0 | 9954 | 0.7119 |
|
206 |
+
| 0.4289 | 159.0 | 10017 | 0.7587 |
|
207 |
+
| 0.4415 | 160.0 | 10080 | 0.7935 |
|
208 |
+
| 0.4315 | 161.0 | 10143 | 0.7574 |
|
209 |
+
| 0.4227 | 162.0 | 10206 | 0.7296 |
|
210 |
+
| 0.4352 | 163.0 | 10269 | 0.7145 |
|
211 |
+
| 0.4108 | 164.0 | 10332 | 0.7133 |
|
212 |
+
| 0.433 | 165.0 | 10395 | 0.7369 |
|
213 |
+
| 0.4336 | 166.0 | 10458 | 0.7471 |
|
214 |
+
| 0.4016 | 167.0 | 10521 | 0.7329 |
|
215 |
+
| 0.4164 | 168.0 | 10584 | 0.7331 |
|
216 |
+
| 0.4182 | 169.0 | 10647 | 0.7449 |
|
217 |
+
| 0.4136 | 170.0 | 10710 | 0.7365 |
|
218 |
+
| 0.4183 | 171.0 | 10773 | 0.7248 |
|
219 |
+
| 0.4225 | 172.0 | 10836 | 0.7346 |
|
220 |
+
| 0.4294 | 173.0 | 10899 | 0.7099 |
|
221 |
+
| 0.4113 | 174.0 | 10962 | 0.7264 |
|
222 |
+
| 0.4216 | 175.0 | 11025 | 0.6822 |
|
223 |
+
| 0.4208 | 176.0 | 11088 | 0.7198 |
|
224 |
+
| 0.407 | 177.0 | 11151 | 0.7266 |
|
225 |
+
| 0.4164 | 178.0 | 11214 | 0.7466 |
|
226 |
+
| 0.4112 | 179.0 | 11277 | 0.7409 |
|
227 |
+
| 0.4067 | 180.0 | 11340 | 0.7058 |
|
228 |
+
| 0.4297 | 181.0 | 11403 | 0.6918 |
|
229 |
+
| 0.4137 | 182.0 | 11466 | 0.7432 |
|
230 |
+
| 0.4102 | 183.0 | 11529 | 0.7272 |
|
231 |
+
| 0.4184 | 184.0 | 11592 | 0.7309 |
|
232 |
+
| 0.4049 | 185.0 | 11655 | 0.7215 |
|
233 |
+
| 0.4097 | 186.0 | 11718 | 0.7375 |
|
234 |
+
| 0.419 | 187.0 | 11781 | 0.7575 |
|
235 |
+
| 0.4122 | 188.0 | 11844 | 0.7481 |
|
236 |
+
| 0.4089 | 189.0 | 11907 | 0.7790 |
|
237 |
+
| 0.4094 | 190.0 | 11970 | 0.7547 |
|
238 |
+
| 0.4107 | 191.0 | 12033 | 0.7390 |
|
239 |
+
| 0.4044 | 192.0 | 12096 | 0.7472 |
|
240 |
+
| 0.4065 | 193.0 | 12159 | 0.7283 |
|
241 |
+
| 0.4172 | 194.0 | 12222 | 0.7112 |
|
242 |
+
| 0.4124 | 195.0 | 12285 | 0.7470 |
|
243 |
+
| 0.4026 | 196.0 | 12348 | 0.7067 |
|
244 |
+
| 0.4179 | 197.0 | 12411 | 0.7259 |
|
245 |
+
| 0.4027 | 198.0 | 12474 | 0.7328 |
|
246 |
+
| 0.4101 | 199.0 | 12537 | 0.6891 |
|
247 |
+
| 0.3969 | 200.0 | 12600 | 0.7104 |
|
248 |
+
|
249 |
+
|
250 |
### Framework versions
|
251 |
|
252 |
- Transformers 4.24.0
|