Commit
·
e96c6be
1
Parent(s):
d781e63
Update README.md
Browse files
README.md
CHANGED
|
@@ -73,23 +73,48 @@ The following hyperparameters were used during training:
|
|
| 73 |
|
| 74 |
### Training results
|
| 75 |
|
| 76 |
-
Step
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
|
| 95 |
### Framework versions
|
|
|
|
| 73 |
|
| 74 |
### Training results
|
| 75 |
|
| 76 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 77 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 78 |
+
| No log | 10.0 | 100 | 0.5238 | 0.8366 | 0.886 | 0.8606 | 0.8410 |
|
| 79 |
+
| No log | 20.0 | 200 | 0.6930 | 0.8751 | 0.8965 | 0.8857 | 0.8322 |
|
| 80 |
+
| No log | 30.0 | 300 | 0.7784 | 0.8902 | 0.908 | 0.8990 | 0.8414 |
|
| 81 |
+
| No log | 40.0 | 400 | 0.9056 | 0.8916 | 0.905 | 0.8983 | 0.8364 |
|
| 82 |
+
| 0.2429 | 50.0 | 500 | 1.0016 | 0.8954 | 0.9075 | 0.9014 | 0.8298 |
|
| 83 |
+
| 0.2429 | 60.0 | 600 | 1.0097 | 0.8899 | 0.897 | 0.8934 | 0.8294 |
|
| 84 |
+
| 0.2429 | 70.0 | 700 | 1.0722 | 0.9035 | 0.9085 | 0.9060 | 0.8315 |
|
| 85 |
+
| 0.2429 | 80.0 | 800 | 1.0884 | 0.8905 | 0.9105 | 0.9004 | 0.8269 |
|
| 86 |
+
| 0.2429 | 90.0 | 900 | 1.1292 | 0.8938 | 0.909 | 0.9013 | 0.8279 |
|
| 87 |
+
| 0.0098 | 100.0 | 1000 | 1.1164 | 0.9026 | 0.913 | 0.9078 | 0.8330 |
|
| 88 |
+
| No log | 10.0 | 100 | 0.5238 | 0.8366 | 0.886 | 0.8606 | 0.8410 |
|
| 89 |
+
| No log | 20.0 | 200 | 0.6930 | 0.8751 | 0.8965 | 0.8857 | 0.8322 |
|
| 90 |
+
| No log | 30.0 | 300 | 0.7784 | 0.8902 | 0.908 | 0.8990 | 0.8414 |
|
| 91 |
+
| No log | 40.0 | 400 | 0.9056 | 0.8916 | 0.905 | 0.8983 | 0.8364 |
|
| 92 |
+
| 0.2429 | 50.0 | 500 | 1.0016 | 0.8954 | 0.9075 | 0.9014 | 0.8298 |
|
| 93 |
+
| 0.2429 | 60.0 | 600 | 1.0097 | 0.8899 | 0.897 | 0.8934 | 0.8294 |
|
| 94 |
+
| 0.2429 | 70.0 | 700 | 1.0722 | 0.9035 | 0.9085 | 0.9060 | 0.8315 |
|
| 95 |
+
| 0.2429 | 80.0 | 800 | 1.0884 | 0.8905 | 0.9105 | 0.9004 | 0.8269 |
|
| 96 |
+
| 0.2429 | 90.0 | 900 | 1.1292 | 0.8938 | 0.909 | 0.9013 | 0.8279 |
|
| 97 |
+
| 0.0098 | 100.0 | 1000 | 1.1164 | 0.9026 | 0.913 | 0.9078 | 0.8330 |
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
[4000/4000 20:34, Epoch 53/54]
|
| 101 |
+
Step Training Loss Validation Loss Precision Recall F1 Accuracy
|
| 102 |
+
250 No log 0.435449 0.854588 0.902136 0.877719 0.835968
|
| 103 |
+
500 0.505800 0.611310 0.869822 0.876304 0.873051 0.839177
|
| 104 |
+
750 0.505800 0.635022 0.879886 0.917039 0.898078 0.853085
|
| 105 |
+
1000 0.097000 0.765935 0.900818 0.929459 0.914914 0.860097
|
| 106 |
+
1250 0.097000 0.887739 0.885533 0.903130 0.894245 0.842625
|
| 107 |
+
1500 0.029900 0.948754 0.898018 0.923000 0.910338 0.843575
|
| 108 |
+
1750 0.029900 1.102811 0.900433 0.929955 0.914956 0.840128
|
| 109 |
+
2000 0.009700 1.039040 0.901415 0.917536 0.909404 0.852728
|
| 110 |
+
2250 0.009700 1.044235 0.904716 0.924491 0.914496 0.849519
|
| 111 |
+
2500 0.002500 1.013194 0.913086 0.918530 0.915800 0.849637
|
| 112 |
+
2750 0.002500 1.017520 0.908605 0.928465 0.918428 0.854986
|
| 113 |
+
3000 0.000900 1.029559 0.914216 0.926478 0.920306 0.859384
|
| 114 |
+
3250 0.000900 1.038318 0.918177 0.930949 0.924519 0.859979
|
| 115 |
+
3500 0.000800 1.045578 0.914216 0.926478 0.920306 0.858552
|
| 116 |
+
3750 0.000800 1.040568 0.913894 0.927968 0.920877 0.858433
|
| 117 |
+
4000 0.000700 1.041146 0.913894 0.927968 0.920877 0.8585528552
|
| 118 |
|
| 119 |
|
| 120 |
### Framework versions
|