End of training
Browse files
README.md
CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Accuracy: 0.
|
25 |
-
- F1: 0.
|
26 |
-
- Precision: 0.
|
27 |
-
- Recall: 0.
|
28 |
- Learning Rate: 0.0
|
29 |
|
30 |
## Model description
|
@@ -56,106 +56,106 @@ The following hyperparameters were used during training:
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Rate |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
|
59 |
-
| No log | 1.0 |
|
60 |
-
| No log | 2.0 |
|
61 |
-
| No log | 3.0 |
|
62 |
-
| No log | 4.0 |
|
63 |
-
| No log | 5.0 |
|
64 |
-
| No log | 6.0 |
|
65 |
-
| No log | 7.0 |
|
66 |
-
| No log | 8.0 |
|
67 |
-
| No log | 9.0 |
|
68 |
-
| No log | 10.0 |
|
69 |
-
| No log | 11.0 |
|
70 |
-
| No log | 12.0 |
|
71 |
-
| No log | 13.0 |
|
72 |
-
| No log | 14.0 |
|
73 |
-
| No log | 15.0 |
|
74 |
-
| No log | 16.0 |
|
75 |
-
| No log | 17.0 |
|
76 |
-
| No log | 18.0 |
|
77 |
-
| No log | 19.0 |
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
-
| 0.
|
122 |
-
| 0.
|
123 |
-
| 0.
|
124 |
-
| 0.
|
125 |
-
| 0.
|
126 |
-
| 0.
|
127 |
-
| 0.
|
128 |
-
| 0.
|
129 |
-
| 0.
|
130 |
-
| 0.
|
131 |
-
| 0.
|
132 |
-
| 0.
|
133 |
-
| 0.
|
134 |
-
| 0.
|
135 |
-
| 0.
|
136 |
-
| 0.
|
137 |
-
| 0.
|
138 |
-
| 0.
|
139 |
-
| 0.
|
140 |
-
| 0.
|
141 |
-
| 0.
|
142 |
-
| 0.
|
143 |
-
| 0.
|
144 |
-
| 0.
|
145 |
-
| 0.
|
146 |
-
| 0.
|
147 |
-
| 0.
|
148 |
-
| 0.
|
149 |
-
| 0.
|
150 |
-
| 0.
|
151 |
-
| 0.
|
152 |
-
| 0.
|
153 |
-
| 0.
|
154 |
-
| 0.
|
155 |
-
| 0.
|
156 |
-
| 0.
|
157 |
-
| 0.
|
158 |
-
| 0.
|
159 |
|
160 |
|
161 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.0299
|
24 |
+
- Accuracy: 0.0075
|
25 |
+
- F1: 0.0127
|
26 |
+
- Precision: 0.0064
|
27 |
+
- Recall: 0.8358
|
28 |
- Learning Rate: 0.0
|
29 |
|
30 |
## Model description
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Rate |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:------:|
|
59 |
+
| No log | 1.0 | 26 | 0.5156 | 0.0531 | 0.0154 | 0.0078 | 0.9701 | 0.0000 |
|
60 |
+
| No log | 2.0 | 52 | 0.3270 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
61 |
+
| No log | 3.0 | 78 | 0.1951 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
62 |
+
| No log | 4.0 | 104 | 0.1153 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
63 |
+
| No log | 5.0 | 130 | 0.0759 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
64 |
+
| No log | 6.0 | 156 | 0.0584 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
65 |
+
| No log | 7.0 | 182 | 0.0503 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
66 |
+
| No log | 8.0 | 208 | 0.0462 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
67 |
+
| No log | 9.0 | 234 | 0.0440 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
68 |
+
| No log | 10.0 | 260 | 0.0427 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
69 |
+
| No log | 11.0 | 286 | 0.0419 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
70 |
+
| No log | 12.0 | 312 | 0.0413 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
71 |
+
| No log | 13.0 | 338 | 0.0410 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
72 |
+
| No log | 14.0 | 364 | 0.0407 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
73 |
+
| No log | 15.0 | 390 | 0.0405 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
74 |
+
| No log | 16.0 | 416 | 0.0403 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
75 |
+
| No log | 17.0 | 442 | 0.0402 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
76 |
+
| No log | 18.0 | 468 | 0.0400 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
77 |
+
| No log | 19.0 | 494 | 0.0399 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
78 |
+
| 0.1144 | 20.0 | 520 | 0.0397 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
79 |
+
| 0.1144 | 21.0 | 546 | 0.0388 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
80 |
+
| 0.1144 | 22.0 | 572 | 0.0388 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
81 |
+
| 0.1144 | 23.0 | 598 | 0.0387 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
82 |
+
| 0.1144 | 24.0 | 624 | 0.0375 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
83 |
+
| 0.1144 | 25.0 | 650 | 0.0376 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
84 |
+
| 0.1144 | 26.0 | 676 | 0.0369 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
85 |
+
| 0.1144 | 27.0 | 702 | 0.0367 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
86 |
+
| 0.1144 | 28.0 | 728 | 0.0373 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
87 |
+
| 0.1144 | 29.0 | 754 | 0.0362 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
88 |
+
| 0.1144 | 30.0 | 780 | 0.0361 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
89 |
+
| 0.1144 | 31.0 | 806 | 0.0358 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
90 |
+
| 0.1144 | 32.0 | 832 | 0.0355 | 0.0077 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
91 |
+
| 0.1144 | 33.0 | 858 | 0.0329 | 0.0073 | 0.0145 | 0.0073 | 0.9552 | 0.0000 |
|
92 |
+
| 0.1144 | 34.0 | 884 | 0.0327 | 0.0078 | 0.0152 | 0.0077 | 1.0 | 0.0000 |
|
93 |
+
| 0.1144 | 35.0 | 910 | 0.0328 | 0.0074 | 0.0147 | 0.0074 | 0.9701 | 0.0000 |
|
94 |
+
| 0.1144 | 36.0 | 936 | 0.0324 | 0.0075 | 0.0147 | 0.0074 | 0.9701 | 0.0000 |
|
95 |
+
| 0.1144 | 37.0 | 962 | 0.0316 | 0.0075 | 0.0147 | 0.0074 | 0.9701 | 0.0000 |
|
96 |
+
| 0.1144 | 38.0 | 988 | 0.0326 | 0.0075 | 0.0145 | 0.0073 | 0.9552 | 0.0000 |
|
97 |
+
| 0.029 | 39.0 | 1014 | 0.0312 | 0.0074 | 0.0145 | 0.0073 | 0.9552 | 0.0000 |
|
98 |
+
| 0.029 | 40.0 | 1040 | 0.0313 | 0.0072 | 0.0141 | 0.0071 | 0.9254 | 0.0000 |
|
99 |
+
| 0.029 | 41.0 | 1066 | 0.0320 | 0.0073 | 0.0143 | 0.0072 | 0.9403 | 0.0000 |
|
100 |
+
| 0.029 | 42.0 | 1092 | 0.0316 | 0.0074 | 0.0145 | 0.0073 | 0.9552 | 0.0000 |
|
101 |
+
| 0.029 | 43.0 | 1118 | 0.0310 | 0.0072 | 0.0136 | 0.0069 | 0.8955 | 0.0000 |
|
102 |
+
| 0.029 | 44.0 | 1144 | 0.0311 | 0.0072 | 0.0141 | 0.0071 | 0.9254 | 0.0000 |
|
103 |
+
| 0.029 | 45.0 | 1170 | 0.0310 | 0.0072 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
104 |
+
| 0.029 | 46.0 | 1196 | 0.0312 | 0.0071 | 0.0134 | 0.0067 | 0.8806 | 0.0000 |
|
105 |
+
| 0.029 | 47.0 | 1222 | 0.0308 | 0.0071 | 0.0134 | 0.0067 | 0.8806 | 0.0000 |
|
106 |
+
| 0.029 | 48.0 | 1248 | 0.0312 | 0.0072 | 0.0136 | 0.0069 | 0.8955 | 0.0000 |
|
107 |
+
| 0.029 | 49.0 | 1274 | 0.0309 | 0.0073 | 0.0136 | 0.0069 | 0.8955 | 0.0000 |
|
108 |
+
| 0.029 | 50.0 | 1300 | 0.0307 | 0.0070 | 0.0129 | 0.0065 | 0.8507 | 1e-05 |
|
109 |
+
| 0.029 | 51.0 | 1326 | 0.0303 | 0.0071 | 0.0134 | 0.0067 | 0.8806 | 0.0000 |
|
110 |
+
| 0.029 | 52.0 | 1352 | 0.0307 | 0.0073 | 0.0134 | 0.0067 | 0.8806 | 0.0000 |
|
111 |
+
| 0.029 | 53.0 | 1378 | 0.0309 | 0.0073 | 0.0134 | 0.0067 | 0.8806 | 0.0000 |
|
112 |
+
| 0.029 | 54.0 | 1404 | 0.0312 | 0.0072 | 0.0136 | 0.0069 | 0.8955 | 0.0000 |
|
113 |
+
| 0.029 | 55.0 | 1430 | 0.0303 | 0.0073 | 0.0136 | 0.0069 | 0.8955 | 9e-06 |
|
114 |
+
| 0.029 | 56.0 | 1456 | 0.0300 | 0.0071 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
115 |
+
| 0.029 | 57.0 | 1482 | 0.0301 | 0.0069 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
116 |
+
| 0.0205 | 58.0 | 1508 | 0.0302 | 0.0072 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
117 |
+
| 0.0205 | 59.0 | 1534 | 0.0303 | 0.0071 | 0.0129 | 0.0065 | 0.8507 | 0.0000 |
|
118 |
+
| 0.0205 | 60.0 | 1560 | 0.0308 | 0.0073 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
119 |
+
| 0.0205 | 61.0 | 1586 | 0.0309 | 0.0074 | 0.0136 | 0.0069 | 0.8955 | 0.0000 |
|
120 |
+
| 0.0205 | 62.0 | 1612 | 0.0306 | 0.0078 | 0.0130 | 0.0065 | 0.8507 | 0.0000 |
|
121 |
+
| 0.0205 | 63.0 | 1638 | 0.0308 | 0.0077 | 0.0130 | 0.0065 | 0.8507 | 0.0000 |
|
122 |
+
| 0.0205 | 64.0 | 1664 | 0.0303 | 0.0071 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
123 |
+
| 0.0205 | 65.0 | 1690 | 0.0312 | 0.0077 | 0.0132 | 0.0066 | 0.8657 | 7e-06 |
|
124 |
+
| 0.0205 | 66.0 | 1716 | 0.0304 | 0.0073 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
125 |
+
| 0.0205 | 67.0 | 1742 | 0.0305 | 0.0073 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
126 |
+
| 0.0205 | 68.0 | 1768 | 0.0304 | 0.0074 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
127 |
+
| 0.0205 | 69.0 | 1794 | 0.0306 | 0.0072 | 0.0129 | 0.0065 | 0.8507 | 0.0000 |
|
128 |
+
| 0.0205 | 70.0 | 1820 | 0.0314 | 0.0080 | 0.0134 | 0.0068 | 0.8806 | 6e-06 |
|
129 |
+
| 0.0205 | 71.0 | 1846 | 0.0314 | 0.0075 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
130 |
+
| 0.0205 | 72.0 | 1872 | 0.0307 | 0.0075 | 0.0132 | 0.0066 | 0.8657 | 0.0000 |
|
131 |
+
| 0.0205 | 73.0 | 1898 | 0.0300 | 0.0075 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
132 |
+
| 0.0205 | 74.0 | 1924 | 0.0301 | 0.0072 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
133 |
+
| 0.0205 | 75.0 | 1950 | 0.0297 | 0.0075 | 0.0132 | 0.0066 | 0.8657 | 5e-06 |
|
134 |
+
| 0.0205 | 76.0 | 1976 | 0.0306 | 0.0075 | 0.0130 | 0.0065 | 0.8507 | 0.0000 |
|
135 |
+
| 0.016 | 77.0 | 2002 | 0.0299 | 0.0073 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
136 |
+
| 0.016 | 78.0 | 2028 | 0.0301 | 0.0074 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
137 |
+
| 0.016 | 79.0 | 2054 | 0.0301 | 0.0078 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
138 |
+
| 0.016 | 80.0 | 2080 | 0.0306 | 0.0078 | 0.0130 | 0.0065 | 0.8507 | 0.0000 |
|
139 |
+
| 0.016 | 81.0 | 2106 | 0.0302 | 0.0073 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
140 |
+
| 0.016 | 82.0 | 2132 | 0.0305 | 0.0073 | 0.0129 | 0.0065 | 0.8507 | 0.0000 |
|
141 |
+
| 0.016 | 83.0 | 2158 | 0.0303 | 0.0073 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
142 |
+
| 0.016 | 84.0 | 2184 | 0.0302 | 0.0072 | 0.0129 | 0.0065 | 0.8507 | 0.0000 |
|
143 |
+
| 0.016 | 85.0 | 2210 | 0.0302 | 0.0072 | 0.0127 | 0.0064 | 0.8358 | 3e-06 |
|
144 |
+
| 0.016 | 86.0 | 2236 | 0.0299 | 0.0072 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
145 |
+
| 0.016 | 87.0 | 2262 | 0.0296 | 0.0069 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
146 |
+
| 0.016 | 88.0 | 2288 | 0.0299 | 0.0073 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
147 |
+
| 0.016 | 89.0 | 2314 | 0.0297 | 0.0072 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
148 |
+
| 0.016 | 90.0 | 2340 | 0.0296 | 0.0073 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
149 |
+
| 0.016 | 91.0 | 2366 | 0.0299 | 0.0071 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
150 |
+
| 0.016 | 92.0 | 2392 | 0.0293 | 0.0071 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
151 |
+
| 0.016 | 93.0 | 2418 | 0.0301 | 0.0073 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
152 |
+
| 0.016 | 94.0 | 2444 | 0.0294 | 0.0071 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
153 |
+
| 0.016 | 95.0 | 2470 | 0.0296 | 0.0072 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
154 |
+
| 0.016 | 96.0 | 2496 | 0.0298 | 0.0074 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
155 |
+
| 0.0136 | 97.0 | 2522 | 0.0299 | 0.0073 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
156 |
+
| 0.0136 | 98.0 | 2548 | 0.0298 | 0.0074 | 0.0125 | 0.0063 | 0.8209 | 0.0000 |
|
157 |
+
| 0.0136 | 99.0 | 2574 | 0.0299 | 0.0075 | 0.0127 | 0.0064 | 0.8358 | 0.0000 |
|
158 |
+
| 0.0136 | 100.0 | 2600 | 0.0299 | 0.0075 | 0.0127 | 0.0064 | 0.8358 | 0.0 |
|
159 |
|
160 |
|
161 |
### Framework versions
|