End of training
Browse files- README.md +5 -5
- all_results.json +17 -0
- eval_results.json +12 -0
- predict_results.txt +539 -0
- train_results.json +8 -0
- trainer_state.json +264 -0
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 [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) 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 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.4359
|
| 24 |
+
- Accuracy: 0.8513
|
| 25 |
+
- F1: 0.7386
|
| 26 |
+
- Precision: 0.6570
|
| 27 |
+
- Recall: 0.8433
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 13.0,
|
| 3 |
+
"eval_accuracy": 0.8513011152416357,
|
| 4 |
+
"eval_f1": 0.7385620915032679,
|
| 5 |
+
"eval_loss": 0.43591225147247314,
|
| 6 |
+
"eval_precision": 0.6569767441860465,
|
| 7 |
+
"eval_recall": 0.8432835820895522,
|
| 8 |
+
"eval_runtime": 2.1114,
|
| 9 |
+
"eval_samples": 268,
|
| 10 |
+
"eval_samples_per_second": 254.812,
|
| 11 |
+
"eval_steps_per_second": 4.263,
|
| 12 |
+
"train_loss": 0.2951739639471221,
|
| 13 |
+
"train_runtime": 432.0494,
|
| 14 |
+
"train_samples": 1878,
|
| 15 |
+
"train_samples_per_second": 434.673,
|
| 16 |
+
"train_steps_per_second": 13.656
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 13.0,
|
| 3 |
+
"eval_accuracy": 0.8513011152416357,
|
| 4 |
+
"eval_f1": 0.7385620915032679,
|
| 5 |
+
"eval_loss": 0.43591225147247314,
|
| 6 |
+
"eval_precision": 0.6569767441860465,
|
| 7 |
+
"eval_recall": 0.8432835820895522,
|
| 8 |
+
"eval_runtime": 2.1114,
|
| 9 |
+
"eval_samples": 268,
|
| 10 |
+
"eval_samples_per_second": 254.812,
|
| 11 |
+
"eval_steps_per_second": 4.263
|
| 12 |
+
}
|
predict_results.txt
ADDED
|
@@ -0,0 +1,539 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
index prediction
|
| 2 |
+
0 1
|
| 3 |
+
1 0
|
| 4 |
+
2 0
|
| 5 |
+
3 0
|
| 6 |
+
4 1
|
| 7 |
+
5 0
|
| 8 |
+
6 1
|
| 9 |
+
7 1
|
| 10 |
+
8 0
|
| 11 |
+
9 0
|
| 12 |
+
10 0
|
| 13 |
+
11 0
|
| 14 |
+
12 1
|
| 15 |
+
13 0
|
| 16 |
+
14 0
|
| 17 |
+
15 1
|
| 18 |
+
16 1
|
| 19 |
+
17 0
|
| 20 |
+
18 1
|
| 21 |
+
19 0
|
| 22 |
+
20 0
|
| 23 |
+
21 0
|
| 24 |
+
22 0
|
| 25 |
+
23 1
|
| 26 |
+
24 0
|
| 27 |
+
25 0
|
| 28 |
+
26 1
|
| 29 |
+
27 1
|
| 30 |
+
28 1
|
| 31 |
+
29 0
|
| 32 |
+
30 0
|
| 33 |
+
31 1
|
| 34 |
+
32 1
|
| 35 |
+
33 1
|
| 36 |
+
34 0
|
| 37 |
+
35 0
|
| 38 |
+
36 0
|
| 39 |
+
37 0
|
| 40 |
+
38 0
|
| 41 |
+
39 0
|
| 42 |
+
40 0
|
| 43 |
+
41 0
|
| 44 |
+
42 0
|
| 45 |
+
43 0
|
| 46 |
+
44 0
|
| 47 |
+
45 0
|
| 48 |
+
46 0
|
| 49 |
+
47 0
|
| 50 |
+
48 0
|
| 51 |
+
49 0
|
| 52 |
+
50 1
|
| 53 |
+
51 0
|
| 54 |
+
52 0
|
| 55 |
+
53 0
|
| 56 |
+
54 0
|
| 57 |
+
55 0
|
| 58 |
+
56 0
|
| 59 |
+
57 0
|
| 60 |
+
58 0
|
| 61 |
+
59 0
|
| 62 |
+
60 0
|
| 63 |
+
61 1
|
| 64 |
+
62 0
|
| 65 |
+
63 1
|
| 66 |
+
64 0
|
| 67 |
+
65 0
|
| 68 |
+
66 0
|
| 69 |
+
67 0
|
| 70 |
+
68 0
|
| 71 |
+
69 0
|
| 72 |
+
70 0
|
| 73 |
+
71 1
|
| 74 |
+
72 1
|
| 75 |
+
73 1
|
| 76 |
+
74 0
|
| 77 |
+
75 0
|
| 78 |
+
76 1
|
| 79 |
+
77 0
|
| 80 |
+
78 0
|
| 81 |
+
79 0
|
| 82 |
+
80 0
|
| 83 |
+
81 0
|
| 84 |
+
82 0
|
| 85 |
+
83 1
|
| 86 |
+
84 1
|
| 87 |
+
85 0
|
| 88 |
+
86 1
|
| 89 |
+
87 0
|
| 90 |
+
88 1
|
| 91 |
+
89 0
|
| 92 |
+
90 0
|
| 93 |
+
91 0
|
| 94 |
+
92 1
|
| 95 |
+
93 0
|
| 96 |
+
94 1
|
| 97 |
+
95 0
|
| 98 |
+
96 1
|
| 99 |
+
97 0
|
| 100 |
+
98 0
|
| 101 |
+
99 1
|
| 102 |
+
100 0
|
| 103 |
+
101 0
|
| 104 |
+
102 0
|
| 105 |
+
103 0
|
| 106 |
+
104 0
|
| 107 |
+
105 1
|
| 108 |
+
106 0
|
| 109 |
+
107 0
|
| 110 |
+
108 1
|
| 111 |
+
109 0
|
| 112 |
+
110 0
|
| 113 |
+
111 1
|
| 114 |
+
112 0
|
| 115 |
+
113 0
|
| 116 |
+
114 1
|
| 117 |
+
115 0
|
| 118 |
+
116 0
|
| 119 |
+
117 0
|
| 120 |
+
118 0
|
| 121 |
+
119 1
|
| 122 |
+
120 0
|
| 123 |
+
121 0
|
| 124 |
+
122 0
|
| 125 |
+
123 0
|
| 126 |
+
124 1
|
| 127 |
+
125 0
|
| 128 |
+
126 0
|
| 129 |
+
127 0
|
| 130 |
+
128 0
|
| 131 |
+
129 0
|
| 132 |
+
130 1
|
| 133 |
+
131 0
|
| 134 |
+
132 0
|
| 135 |
+
133 0
|
| 136 |
+
134 0
|
| 137 |
+
135 0
|
| 138 |
+
136 1
|
| 139 |
+
137 0
|
| 140 |
+
138 0
|
| 141 |
+
139 0
|
| 142 |
+
140 1
|
| 143 |
+
141 0
|
| 144 |
+
142 1
|
| 145 |
+
143 0
|
| 146 |
+
144 1
|
| 147 |
+
145 0
|
| 148 |
+
146 0
|
| 149 |
+
147 1
|
| 150 |
+
148 1
|
| 151 |
+
149 0
|
| 152 |
+
150 1
|
| 153 |
+
151 0
|
| 154 |
+
152 0
|
| 155 |
+
153 0
|
| 156 |
+
154 0
|
| 157 |
+
155 0
|
| 158 |
+
156 0
|
| 159 |
+
157 0
|
| 160 |
+
158 1
|
| 161 |
+
159 0
|
| 162 |
+
160 0
|
| 163 |
+
161 0
|
| 164 |
+
162 0
|
| 165 |
+
163 1
|
| 166 |
+
164 0
|
| 167 |
+
165 1
|
| 168 |
+
166 0
|
| 169 |
+
167 1
|
| 170 |
+
168 0
|
| 171 |
+
169 0
|
| 172 |
+
170 0
|
| 173 |
+
171 1
|
| 174 |
+
172 0
|
| 175 |
+
173 0
|
| 176 |
+
174 1
|
| 177 |
+
175 0
|
| 178 |
+
176 0
|
| 179 |
+
177 1
|
| 180 |
+
178 0
|
| 181 |
+
179 1
|
| 182 |
+
180 1
|
| 183 |
+
181 0
|
| 184 |
+
182 1
|
| 185 |
+
183 0
|
| 186 |
+
184 0
|
| 187 |
+
185 1
|
| 188 |
+
186 1
|
| 189 |
+
187 1
|
| 190 |
+
188 0
|
| 191 |
+
189 0
|
| 192 |
+
190 0
|
| 193 |
+
191 0
|
| 194 |
+
192 1
|
| 195 |
+
193 0
|
| 196 |
+
194 0
|
| 197 |
+
195 0
|
| 198 |
+
196 0
|
| 199 |
+
197 0
|
| 200 |
+
198 1
|
| 201 |
+
199 0
|
| 202 |
+
200 0
|
| 203 |
+
201 0
|
| 204 |
+
202 1
|
| 205 |
+
203 1
|
| 206 |
+
204 0
|
| 207 |
+
205 1
|
| 208 |
+
206 1
|
| 209 |
+
207 0
|
| 210 |
+
208 0
|
| 211 |
+
209 0
|
| 212 |
+
210 0
|
| 213 |
+
211 0
|
| 214 |
+
212 1
|
| 215 |
+
213 0
|
| 216 |
+
214 0
|
| 217 |
+
215 0
|
| 218 |
+
216 1
|
| 219 |
+
217 0
|
| 220 |
+
218 1
|
| 221 |
+
219 0
|
| 222 |
+
220 0
|
| 223 |
+
221 0
|
| 224 |
+
222 0
|
| 225 |
+
223 1
|
| 226 |
+
224 0
|
| 227 |
+
225 0
|
| 228 |
+
226 1
|
| 229 |
+
227 0
|
| 230 |
+
228 1
|
| 231 |
+
229 0
|
| 232 |
+
230 0
|
| 233 |
+
231 1
|
| 234 |
+
232 1
|
| 235 |
+
233 0
|
| 236 |
+
234 1
|
| 237 |
+
235 0
|
| 238 |
+
236 0
|
| 239 |
+
237 1
|
| 240 |
+
238 0
|
| 241 |
+
239 0
|
| 242 |
+
240 1
|
| 243 |
+
241 0
|
| 244 |
+
242 0
|
| 245 |
+
243 0
|
| 246 |
+
244 0
|
| 247 |
+
245 0
|
| 248 |
+
246 0
|
| 249 |
+
247 0
|
| 250 |
+
248 0
|
| 251 |
+
249 1
|
| 252 |
+
250 0
|
| 253 |
+
251 0
|
| 254 |
+
252 0
|
| 255 |
+
253 0
|
| 256 |
+
254 1
|
| 257 |
+
255 0
|
| 258 |
+
256 0
|
| 259 |
+
257 1
|
| 260 |
+
258 0
|
| 261 |
+
259 1
|
| 262 |
+
260 1
|
| 263 |
+
261 0
|
| 264 |
+
262 0
|
| 265 |
+
263 0
|
| 266 |
+
264 0
|
| 267 |
+
265 1
|
| 268 |
+
266 1
|
| 269 |
+
267 0
|
| 270 |
+
268 0
|
| 271 |
+
269 0
|
| 272 |
+
270 0
|
| 273 |
+
271 1
|
| 274 |
+
272 1
|
| 275 |
+
273 0
|
| 276 |
+
274 0
|
| 277 |
+
275 0
|
| 278 |
+
276 0
|
| 279 |
+
277 0
|
| 280 |
+
278 1
|
| 281 |
+
279 1
|
| 282 |
+
280 0
|
| 283 |
+
281 1
|
| 284 |
+
282 0
|
| 285 |
+
283 0
|
| 286 |
+
284 0
|
| 287 |
+
285 0
|
| 288 |
+
286 0
|
| 289 |
+
287 0
|
| 290 |
+
288 0
|
| 291 |
+
289 0
|
| 292 |
+
290 0
|
| 293 |
+
291 0
|
| 294 |
+
292 1
|
| 295 |
+
293 0
|
| 296 |
+
294 1
|
| 297 |
+
295 0
|
| 298 |
+
296 0
|
| 299 |
+
297 1
|
| 300 |
+
298 1
|
| 301 |
+
299 1
|
| 302 |
+
300 0
|
| 303 |
+
301 1
|
| 304 |
+
302 0
|
| 305 |
+
303 1
|
| 306 |
+
304 1
|
| 307 |
+
305 0
|
| 308 |
+
306 1
|
| 309 |
+
307 0
|
| 310 |
+
308 0
|
| 311 |
+
309 0
|
| 312 |
+
310 0
|
| 313 |
+
311 0
|
| 314 |
+
312 0
|
| 315 |
+
313 1
|
| 316 |
+
314 0
|
| 317 |
+
315 0
|
| 318 |
+
316 0
|
| 319 |
+
317 0
|
| 320 |
+
318 1
|
| 321 |
+
319 0
|
| 322 |
+
320 0
|
| 323 |
+
321 1
|
| 324 |
+
322 0
|
| 325 |
+
323 0
|
| 326 |
+
324 1
|
| 327 |
+
325 1
|
| 328 |
+
326 1
|
| 329 |
+
327 0
|
| 330 |
+
328 0
|
| 331 |
+
329 0
|
| 332 |
+
330 0
|
| 333 |
+
331 1
|
| 334 |
+
332 0
|
| 335 |
+
333 0
|
| 336 |
+
334 0
|
| 337 |
+
335 0
|
| 338 |
+
336 0
|
| 339 |
+
337 0
|
| 340 |
+
338 1
|
| 341 |
+
339 0
|
| 342 |
+
340 1
|
| 343 |
+
341 1
|
| 344 |
+
342 0
|
| 345 |
+
343 0
|
| 346 |
+
344 0
|
| 347 |
+
345 0
|
| 348 |
+
346 1
|
| 349 |
+
347 0
|
| 350 |
+
348 1
|
| 351 |
+
349 0
|
| 352 |
+
350 0
|
| 353 |
+
351 0
|
| 354 |
+
352 0
|
| 355 |
+
353 1
|
| 356 |
+
354 0
|
| 357 |
+
355 0
|
| 358 |
+
356 0
|
| 359 |
+
357 0
|
| 360 |
+
358 1
|
| 361 |
+
359 1
|
| 362 |
+
360 1
|
| 363 |
+
361 0
|
| 364 |
+
362 1
|
| 365 |
+
363 1
|
| 366 |
+
364 0
|
| 367 |
+
365 0
|
| 368 |
+
366 1
|
| 369 |
+
367 0
|
| 370 |
+
368 1
|
| 371 |
+
369 0
|
| 372 |
+
370 0
|
| 373 |
+
371 1
|
| 374 |
+
372 0
|
| 375 |
+
373 1
|
| 376 |
+
374 0
|
| 377 |
+
375 0
|
| 378 |
+
376 0
|
| 379 |
+
377 0
|
| 380 |
+
378 1
|
| 381 |
+
379 0
|
| 382 |
+
380 1
|
| 383 |
+
381 0
|
| 384 |
+
382 1
|
| 385 |
+
383 0
|
| 386 |
+
384 1
|
| 387 |
+
385 0
|
| 388 |
+
386 0
|
| 389 |
+
387 1
|
| 390 |
+
388 1
|
| 391 |
+
389 0
|
| 392 |
+
390 1
|
| 393 |
+
391 0
|
| 394 |
+
392 1
|
| 395 |
+
393 0
|
| 396 |
+
394 1
|
| 397 |
+
395 0
|
| 398 |
+
396 0
|
| 399 |
+
397 0
|
| 400 |
+
398 0
|
| 401 |
+
399 0
|
| 402 |
+
400 1
|
| 403 |
+
401 0
|
| 404 |
+
402 0
|
| 405 |
+
403 1
|
| 406 |
+
404 0
|
| 407 |
+
405 1
|
| 408 |
+
406 1
|
| 409 |
+
407 0
|
| 410 |
+
408 0
|
| 411 |
+
409 0
|
| 412 |
+
410 0
|
| 413 |
+
411 1
|
| 414 |
+
412 0
|
| 415 |
+
413 0
|
| 416 |
+
414 0
|
| 417 |
+
415 0
|
| 418 |
+
416 0
|
| 419 |
+
417 1
|
| 420 |
+
418 0
|
| 421 |
+
419 1
|
| 422 |
+
420 1
|
| 423 |
+
421 0
|
| 424 |
+
422 1
|
| 425 |
+
423 1
|
| 426 |
+
424 1
|
| 427 |
+
425 0
|
| 428 |
+
426 1
|
| 429 |
+
427 0
|
| 430 |
+
428 0
|
| 431 |
+
429 0
|
| 432 |
+
430 0
|
| 433 |
+
431 0
|
| 434 |
+
432 0
|
| 435 |
+
433 1
|
| 436 |
+
434 1
|
| 437 |
+
435 0
|
| 438 |
+
436 1
|
| 439 |
+
437 0
|
| 440 |
+
438 0
|
| 441 |
+
439 0
|
| 442 |
+
440 0
|
| 443 |
+
441 1
|
| 444 |
+
442 0
|
| 445 |
+
443 0
|
| 446 |
+
444 0
|
| 447 |
+
445 0
|
| 448 |
+
446 0
|
| 449 |
+
447 0
|
| 450 |
+
448 1
|
| 451 |
+
449 0
|
| 452 |
+
450 0
|
| 453 |
+
451 1
|
| 454 |
+
452 0
|
| 455 |
+
453 0
|
| 456 |
+
454 0
|
| 457 |
+
455 0
|
| 458 |
+
456 1
|
| 459 |
+
457 0
|
| 460 |
+
458 0
|
| 461 |
+
459 0
|
| 462 |
+
460 0
|
| 463 |
+
461 0
|
| 464 |
+
462 0
|
| 465 |
+
463 1
|
| 466 |
+
464 1
|
| 467 |
+
465 0
|
| 468 |
+
466 1
|
| 469 |
+
467 1
|
| 470 |
+
468 0
|
| 471 |
+
469 0
|
| 472 |
+
470 0
|
| 473 |
+
471 1
|
| 474 |
+
472 0
|
| 475 |
+
473 0
|
| 476 |
+
474 0
|
| 477 |
+
475 1
|
| 478 |
+
476 0
|
| 479 |
+
477 0
|
| 480 |
+
478 0
|
| 481 |
+
479 0
|
| 482 |
+
480 1
|
| 483 |
+
481 1
|
| 484 |
+
482 0
|
| 485 |
+
483 0
|
| 486 |
+
484 0
|
| 487 |
+
485 0
|
| 488 |
+
486 1
|
| 489 |
+
487 1
|
| 490 |
+
488 1
|
| 491 |
+
489 0
|
| 492 |
+
490 0
|
| 493 |
+
491 0
|
| 494 |
+
492 0
|
| 495 |
+
493 1
|
| 496 |
+
494 1
|
| 497 |
+
495 1
|
| 498 |
+
496 1
|
| 499 |
+
497 0
|
| 500 |
+
498 0
|
| 501 |
+
499 0
|
| 502 |
+
500 0
|
| 503 |
+
501 0
|
| 504 |
+
502 0
|
| 505 |
+
503 0
|
| 506 |
+
504 0
|
| 507 |
+
505 0
|
| 508 |
+
506 0
|
| 509 |
+
507 0
|
| 510 |
+
508 0
|
| 511 |
+
509 0
|
| 512 |
+
510 0
|
| 513 |
+
511 0
|
| 514 |
+
512 0
|
| 515 |
+
513 0
|
| 516 |
+
514 0
|
| 517 |
+
515 0
|
| 518 |
+
516 1
|
| 519 |
+
517 1
|
| 520 |
+
518 0
|
| 521 |
+
519 0
|
| 522 |
+
520 0
|
| 523 |
+
521 1
|
| 524 |
+
522 1
|
| 525 |
+
523 0
|
| 526 |
+
524 0
|
| 527 |
+
525 0
|
| 528 |
+
526 0
|
| 529 |
+
527 1
|
| 530 |
+
528 0
|
| 531 |
+
529 1
|
| 532 |
+
530 1
|
| 533 |
+
531 0
|
| 534 |
+
532 1
|
| 535 |
+
533 1
|
| 536 |
+
534 0
|
| 537 |
+
535 1
|
| 538 |
+
536 1
|
| 539 |
+
537 1
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 13.0,
|
| 3 |
+
"train_loss": 0.2951739639471221,
|
| 4 |
+
"train_runtime": 432.0494,
|
| 5 |
+
"train_samples": 1878,
|
| 6 |
+
"train_samples_per_second": 434.673,
|
| 7 |
+
"train_steps_per_second": 13.656
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,264 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7894736842105264,
|
| 3 |
+
"best_model_checkpoint": "outputs/xlm-roberta-base-twitter-indonesia-sarcastic/checkpoint-590",
|
| 4 |
+
"epoch": 13.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 767,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"learning_rate": 9.997697221833061e-06,
|
| 14 |
+
"loss": 0.5641,
|
| 15 |
+
"step": 59
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.75,
|
| 20 |
+
"eval_f1": 0.0,
|
| 21 |
+
"eval_loss": 0.5259643793106079,
|
| 22 |
+
"eval_precision": 0.0,
|
| 23 |
+
"eval_recall": 0.0,
|
| 24 |
+
"eval_runtime": 1.0571,
|
| 25 |
+
"eval_samples_per_second": 253.522,
|
| 26 |
+
"eval_steps_per_second": 4.73,
|
| 27 |
+
"step": 59
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"learning_rate": 9.990465155165683e-06,
|
| 32 |
+
"loss": 0.5317,
|
| 33 |
+
"step": 118
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_accuracy": 0.75,
|
| 38 |
+
"eval_f1": 0.0,
|
| 39 |
+
"eval_loss": 0.5029988288879395,
|
| 40 |
+
"eval_precision": 0.0,
|
| 41 |
+
"eval_recall": 0.0,
|
| 42 |
+
"eval_runtime": 1.053,
|
| 43 |
+
"eval_samples_per_second": 254.519,
|
| 44 |
+
"eval_steps_per_second": 4.748,
|
| 45 |
+
"step": 118
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.0,
|
| 49 |
+
"learning_rate": 9.978555124138569e-06,
|
| 50 |
+
"loss": 0.4995,
|
| 51 |
+
"step": 177
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.0,
|
| 55 |
+
"eval_accuracy": 0.75,
|
| 56 |
+
"eval_f1": 0.0,
|
| 57 |
+
"eval_loss": 0.4655507504940033,
|
| 58 |
+
"eval_precision": 0.0,
|
| 59 |
+
"eval_recall": 0.0,
|
| 60 |
+
"eval_runtime": 1.0523,
|
| 61 |
+
"eval_samples_per_second": 254.669,
|
| 62 |
+
"eval_steps_per_second": 4.751,
|
| 63 |
+
"step": 177
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.0,
|
| 67 |
+
"learning_rate": 9.961568226140335e-06,
|
| 68 |
+
"loss": 0.4599,
|
| 69 |
+
"step": 236
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_accuracy": 0.7686567164179104,
|
| 74 |
+
"eval_f1": 0.6025641025641025,
|
| 75 |
+
"eval_loss": 0.4502911865711212,
|
| 76 |
+
"eval_precision": 0.5280898876404494,
|
| 77 |
+
"eval_recall": 0.7014925373134329,
|
| 78 |
+
"eval_runtime": 1.057,
|
| 79 |
+
"eval_samples_per_second": 253.552,
|
| 80 |
+
"eval_steps_per_second": 4.73,
|
| 81 |
+
"step": 236
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"learning_rate": 9.93968485932029e-06,
|
| 86 |
+
"loss": 0.4082,
|
| 87 |
+
"step": 295
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 5.0,
|
| 91 |
+
"eval_accuracy": 0.8470149253731343,
|
| 92 |
+
"eval_f1": 0.6434782608695653,
|
| 93 |
+
"eval_loss": 0.378521591424942,
|
| 94 |
+
"eval_precision": 0.7708333333333334,
|
| 95 |
+
"eval_recall": 0.5522388059701493,
|
| 96 |
+
"eval_runtime": 1.0544,
|
| 97 |
+
"eval_samples_per_second": 254.183,
|
| 98 |
+
"eval_steps_per_second": 4.742,
|
| 99 |
+
"step": 295
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.0,
|
| 103 |
+
"learning_rate": 9.912926619919478e-06,
|
| 104 |
+
"loss": 0.3274,
|
| 105 |
+
"step": 354
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.0,
|
| 109 |
+
"eval_accuracy": 0.8619402985074627,
|
| 110 |
+
"eval_f1": 0.6991869918699187,
|
| 111 |
+
"eval_loss": 0.3604646623134613,
|
| 112 |
+
"eval_precision": 0.7678571428571429,
|
| 113 |
+
"eval_recall": 0.6417910447761194,
|
| 114 |
+
"eval_runtime": 1.0555,
|
| 115 |
+
"eval_samples_per_second": 253.908,
|
| 116 |
+
"eval_steps_per_second": 4.737,
|
| 117 |
+
"step": 354
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 7.0,
|
| 121 |
+
"learning_rate": 9.881895849126432e-06,
|
| 122 |
+
"loss": 0.2621,
|
| 123 |
+
"step": 413
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 7.0,
|
| 127 |
+
"eval_accuracy": 0.8619402985074627,
|
| 128 |
+
"eval_f1": 0.6837606837606838,
|
| 129 |
+
"eval_loss": 0.3764938712120056,
|
| 130 |
+
"eval_precision": 0.8,
|
| 131 |
+
"eval_recall": 0.5970149253731343,
|
| 132 |
+
"eval_runtime": 1.0562,
|
| 133 |
+
"eval_samples_per_second": 253.732,
|
| 134 |
+
"eval_steps_per_second": 4.734,
|
| 135 |
+
"step": 413
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"learning_rate": 9.845553233485602e-06,
|
| 140 |
+
"loss": 0.2332,
|
| 141 |
+
"step": 472
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.0,
|
| 145 |
+
"eval_accuracy": 0.8768656716417911,
|
| 146 |
+
"eval_f1": 0.759124087591241,
|
| 147 |
+
"eval_loss": 0.34082189202308655,
|
| 148 |
+
"eval_precision": 0.7428571428571429,
|
| 149 |
+
"eval_recall": 0.7761194029850746,
|
| 150 |
+
"eval_runtime": 1.0525,
|
| 151 |
+
"eval_samples_per_second": 254.642,
|
| 152 |
+
"eval_steps_per_second": 4.751,
|
| 153 |
+
"step": 472
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.0,
|
| 157 |
+
"learning_rate": 9.804428641814051e-06,
|
| 158 |
+
"loss": 0.1579,
|
| 159 |
+
"step": 531
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 9.0,
|
| 163 |
+
"eval_accuracy": 0.8731343283582089,
|
| 164 |
+
"eval_f1": 0.7213114754098361,
|
| 165 |
+
"eval_loss": 0.43820273876190186,
|
| 166 |
+
"eval_precision": 0.8,
|
| 167 |
+
"eval_recall": 0.6567164179104478,
|
| 168 |
+
"eval_runtime": 1.055,
|
| 169 |
+
"eval_samples_per_second": 254.04,
|
| 170 |
+
"eval_steps_per_second": 4.74,
|
| 171 |
+
"step": 531
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 10.0,
|
| 175 |
+
"learning_rate": 9.75856265911873e-06,
|
| 176 |
+
"loss": 0.1467,
|
| 177 |
+
"step": 590
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 10.0,
|
| 181 |
+
"eval_accuracy": 0.8805970149253731,
|
| 182 |
+
"eval_f1": 0.7894736842105264,
|
| 183 |
+
"eval_loss": 0.38548171520233154,
|
| 184 |
+
"eval_precision": 0.7058823529411765,
|
| 185 |
+
"eval_recall": 0.8955223880597015,
|
| 186 |
+
"eval_runtime": 1.053,
|
| 187 |
+
"eval_samples_per_second": 254.501,
|
| 188 |
+
"eval_steps_per_second": 4.748,
|
| 189 |
+
"step": 590
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 11.0,
|
| 193 |
+
"learning_rate": 9.708000549587091e-06,
|
| 194 |
+
"loss": 0.098,
|
| 195 |
+
"step": 649
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 11.0,
|
| 199 |
+
"eval_accuracy": 0.8805970149253731,
|
| 200 |
+
"eval_f1": 0.7500000000000001,
|
| 201 |
+
"eval_loss": 0.46932676434516907,
|
| 202 |
+
"eval_precision": 0.7868852459016393,
|
| 203 |
+
"eval_recall": 0.7164179104477612,
|
| 204 |
+
"eval_runtime": 1.058,
|
| 205 |
+
"eval_samples_per_second": 253.305,
|
| 206 |
+
"eval_steps_per_second": 4.726,
|
| 207 |
+
"step": 649
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.0,
|
| 211 |
+
"learning_rate": 9.653766360237254e-06,
|
| 212 |
+
"loss": 0.0929,
|
| 213 |
+
"step": 708
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.0,
|
| 217 |
+
"eval_accuracy": 0.8805970149253731,
|
| 218 |
+
"eval_f1": 0.7333333333333334,
|
| 219 |
+
"eval_loss": 0.6206381916999817,
|
| 220 |
+
"eval_precision": 0.8301886792452831,
|
| 221 |
+
"eval_recall": 0.6567164179104478,
|
| 222 |
+
"eval_runtime": 1.0526,
|
| 223 |
+
"eval_samples_per_second": 254.603,
|
| 224 |
+
"eval_steps_per_second": 4.75,
|
| 225 |
+
"step": 708
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 13.0,
|
| 229 |
+
"learning_rate": 9.594043625628571e-06,
|
| 230 |
+
"loss": 0.0555,
|
| 231 |
+
"step": 767
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 13.0,
|
| 235 |
+
"eval_accuracy": 0.8843283582089553,
|
| 236 |
+
"eval_f1": 0.7633587786259542,
|
| 237 |
+
"eval_loss": 0.7134280800819397,
|
| 238 |
+
"eval_precision": 0.78125,
|
| 239 |
+
"eval_recall": 0.746268656716418,
|
| 240 |
+
"eval_runtime": 1.054,
|
| 241 |
+
"eval_samples_per_second": 254.279,
|
| 242 |
+
"eval_steps_per_second": 4.744,
|
| 243 |
+
"step": 767
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 13.0,
|
| 247 |
+
"step": 767,
|
| 248 |
+
"total_flos": 1605898326389760.0,
|
| 249 |
+
"train_loss": 0.2951739639471221,
|
| 250 |
+
"train_runtime": 432.0494,
|
| 251 |
+
"train_samples_per_second": 434.673,
|
| 252 |
+
"train_steps_per_second": 13.656
|
| 253 |
+
}
|
| 254 |
+
],
|
| 255 |
+
"logging_steps": 500,
|
| 256 |
+
"max_steps": 5900,
|
| 257 |
+
"num_input_tokens_seen": 0,
|
| 258 |
+
"num_train_epochs": 100,
|
| 259 |
+
"save_steps": 500,
|
| 260 |
+
"total_flos": 1605898326389760.0,
|
| 261 |
+
"train_batch_size": 32,
|
| 262 |
+
"trial_name": null,
|
| 263 |
+
"trial_params": null
|
| 264 |
+
}
|