GianniCatBug commited on
Commit
125e87e
1 Parent(s): efd28aa

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.17726608804294042,
4
+ "train_runtime": 592.7547,
5
+ "train_samples": 1120,
6
+ "train_samples_per_second": 9.447,
7
+ "train_steps_per_second": 1.181
8
+ }
predict_results_fake-news.txt ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ index prediction
2
+ 0 1
3
+ 1 0
4
+ 2 1
5
+ 3 1
6
+ 4 1
7
+ 5 1
8
+ 6 1
9
+ 7 1
10
+ 8 0
11
+ 9 0
12
+ 10 0
13
+ 11 0
14
+ 12 0
15
+ 13 0
16
+ 14 1
17
+ 15 0
18
+ 16 0
19
+ 17 0
20
+ 18 1
21
+ 19 0
22
+ 20 0
23
+ 21 1
24
+ 22 1
25
+ 23 0
26
+ 24 1
27
+ 25 1
28
+ 26 1
29
+ 27 1
30
+ 28 0
31
+ 29 1
32
+ 30 0
33
+ 31 0
34
+ 32 1
35
+ 33 1
36
+ 34 1
37
+ 35 1
38
+ 36 0
39
+ 37 1
40
+ 38 0
41
+ 39 0
42
+ 40 0
43
+ 41 1
44
+ 42 0
45
+ 43 1
46
+ 44 0
47
+ 45 0
48
+ 46 1
49
+ 47 0
50
+ 48 0
51
+ 49 1
52
+ 50 0
53
+ 51 1
54
+ 52 0
55
+ 53 1
56
+ 54 1
57
+ 55 1
58
+ 56 0
59
+ 57 1
60
+ 58 1
61
+ 59 1
62
+ 60 1
63
+ 61 1
64
+ 62 1
65
+ 63 0
66
+ 64 1
67
+ 65 0
68
+ 66 1
69
+ 67 0
70
+ 68 0
71
+ 69 1
72
+ 70 0
73
+ 71 0
74
+ 72 1
75
+ 73 1
76
+ 74 1
77
+ 75 0
78
+ 76 1
79
+ 77 1
80
+ 78 0
81
+ 79 1
82
+ 80 1
83
+ 81 0
84
+ 82 1
85
+ 83 1
86
+ 84 1
87
+ 85 1
88
+ 86 0
89
+ 87 1
90
+ 88 0
91
+ 89 1
92
+ 90 0
93
+ 91 1
94
+ 92 1
95
+ 93 1
96
+ 94 0
97
+ 95 0
98
+ 96 1
99
+ 97 0
100
+ 98 1
101
+ 99 1
102
+ 100 1
103
+ 101 0
104
+ 102 0
105
+ 103 0
106
+ 104 1
107
+ 105 1
108
+ 106 0
109
+ 107 1
110
+ 108 0
111
+ 109 1
112
+ 110 0
113
+ 111 0
114
+ 112 1
115
+ 113 0
116
+ 114 1
117
+ 115 1
118
+ 116 0
119
+ 117 0
120
+ 118 0
121
+ 119 0
122
+ 120 0
123
+ 121 1
124
+ 122 0
125
+ 123 1
126
+ 124 1
127
+ 125 1
128
+ 126 0
129
+ 127 1
130
+ 128 1
131
+ 129 0
132
+ 130 0
133
+ 131 1
134
+ 132 0
135
+ 133 0
136
+ 134 1
137
+ 135 1
138
+ 136 1
139
+ 137 1
140
+ 138 0
141
+ 139 0
142
+ 140 0
143
+ 141 0
144
+ 142 0
145
+ 143 0
146
+ 144 1
147
+ 145 0
148
+ 146 0
149
+ 147 1
150
+ 148 1
151
+ 149 0
152
+ 150 0
153
+ 151 1
154
+ 152 0
155
+ 153 1
156
+ 154 0
157
+ 155 0
158
+ 156 1
159
+ 157 1
160
+ 158 1
161
+ 159 1
162
+ 160 1
163
+ 161 0
164
+ 162 0
165
+ 163 0
166
+ 164 1
167
+ 165 1
168
+ 166 0
169
+ 167 0
170
+ 168 0
171
+ 169 1
172
+ 170 1
173
+ 171 1
174
+ 172 1
175
+ 173 1
176
+ 174 1
177
+ 175 0
178
+ 176 0
179
+ 177 1
180
+ 178 0
181
+ 179 1
182
+ 180 0
183
+ 181 1
184
+ 182 1
185
+ 183 0
186
+ 184 1
187
+ 185 1
188
+ 186 0
189
+ 187 0
190
+ 188 1
191
+ 189 0
192
+ 190 0
193
+ 191 0
194
+ 192 0
195
+ 193 1
196
+ 194 0
197
+ 195 1
198
+ 196 0
199
+ 197 1
200
+ 198 0
201
+ 199 1
202
+ 200 0
203
+ 201 1
204
+ 202 1
205
+ 203 1
206
+ 204 0
207
+ 205 1
208
+ 206 0
209
+ 207 0
210
+ 208 0
211
+ 209 0
212
+ 210 1
213
+ 211 0
214
+ 212 0
215
+ 213 0
216
+ 214 0
217
+ 215 1
218
+ 216 0
219
+ 217 0
220
+ 218 1
221
+ 219 1
222
+ 220 1
223
+ 221 0
224
+ 222 1
225
+ 223 0
226
+ 224 0
227
+ 225 0
228
+ 226 1
229
+ 227 1
230
+ 228 0
231
+ 229 1
232
+ 230 0
233
+ 231 0
234
+ 232 1
235
+ 233 0
236
+ 234 1
237
+ 235 0
238
+ 236 1
239
+ 237 0
240
+ 238 0
241
+ 239 1
runs/Jul06_19-21-20_90e918c9e50b/events.out.tfevents.1688671931.90e918c9e50b.1577.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc2951bb01280e9dd257102dceb14e073d90a00c8f7001df8e6406959d01808
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.17726608804294042,
4
+ "train_runtime": 592.7547,
5
+ "train_samples": 1120,
6
+ "train_samples_per_second": 9.447,
7
+ "train_steps_per_second": 1.181
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8968609865470851,
3
+ "best_model_checkpoint": "models/fake-news-bert-base-spanish-wwm-cased/checkpoint-420",
4
+ "epoch": 5.0,
5
+ "global_step": 700,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.6000000000000003e-05,
13
+ "loss": 0.5098,
14
+ "step": 140
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_f1": 0.7340425531914895,
19
+ "eval_loss": 0.49776777625083923,
20
+ "eval_runtime": 7.7757,
21
+ "eval_samples_per_second": 30.865,
22
+ "eval_steps_per_second": 3.858,
23
+ "step": 140
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "learning_rate": 1.2e-05,
28
+ "loss": 0.2473,
29
+ "step": 280
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_f1": 0.8828828828828829,
34
+ "eval_loss": 0.38877564668655396,
35
+ "eval_runtime": 7.9886,
36
+ "eval_samples_per_second": 30.043,
37
+ "eval_steps_per_second": 3.755,
38
+ "step": 280
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 8.000000000000001e-06,
43
+ "loss": 0.0908,
44
+ "step": 420
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_f1": 0.8968609865470851,
49
+ "eval_loss": 0.44203802943229675,
50
+ "eval_runtime": 7.8011,
51
+ "eval_samples_per_second": 30.765,
52
+ "eval_steps_per_second": 3.846,
53
+ "step": 420
54
+ },
55
+ {
56
+ "epoch": 4.0,
57
+ "learning_rate": 4.000000000000001e-06,
58
+ "loss": 0.0332,
59
+ "step": 560
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_f1": 0.8796296296296298,
64
+ "eval_loss": 0.5603806376457214,
65
+ "eval_runtime": 7.8247,
66
+ "eval_samples_per_second": 30.672,
67
+ "eval_steps_per_second": 3.834,
68
+ "step": 560
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "learning_rate": 0.0,
73
+ "loss": 0.0052,
74
+ "step": 700
75
+ },
76
+ {
77
+ "epoch": 5.0,
78
+ "eval_f1": 0.8956521739130435,
79
+ "eval_loss": 0.5154075622558594,
80
+ "eval_runtime": 7.8067,
81
+ "eval_samples_per_second": 30.743,
82
+ "eval_steps_per_second": 3.843,
83
+ "step": 700
84
+ },
85
+ {
86
+ "epoch": 5.0,
87
+ "step": 700,
88
+ "total_flos": 1473421910016000.0,
89
+ "train_loss": 0.17726608804294042,
90
+ "train_runtime": 592.7547,
91
+ "train_samples_per_second": 9.447,
92
+ "train_steps_per_second": 1.181
93
+ }
94
+ ],
95
+ "max_steps": 700,
96
+ "num_train_epochs": 5,
97
+ "total_flos": 1473421910016000.0,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }