Hugging Face's logo

ruanchaves
/
bert-large-portuguese-cased-assin-similarity

Text Classification
Transformers
PyTorch
Portuguese
bert
Model card Files Community
1
ruanchaves commited on
Commit
b4d616d
·
1 Parent(s): 48abdf9

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +277 -0
trainer_state.json ADDED
@@ -0,0 +1,277 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.9984,
5
+ "global_step": 6240,
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
+ "eval_loss": 0.2721790075302124,
13
+ "eval_mse": 0.2721790075302124,
14
+ "eval_runtime": 13.7261,
15
+ "eval_samples_per_second": 72.854,
16
+ "eval_steps_per_second": 9.107,
17
+ "step": 312
18
+ },
19
+ {
20
+ "epoch": 1.6,
21
+ "learning_rate": 3.4640443499072686e-05,
22
+ "loss": 0.2992,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_loss": 0.24081240594387054,
28
+ "eval_mse": 0.24081240594387054,
29
+ "eval_runtime": 13.7912,
30
+ "eval_samples_per_second": 72.51,
31
+ "eval_steps_per_second": 9.064,
32
+ "step": 624
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_loss": 0.22090023756027222,
37
+ "eval_mse": 0.22090023756027222,
38
+ "eval_runtime": 13.7775,
39
+ "eval_samples_per_second": 72.582,
40
+ "eval_steps_per_second": 9.073,
41
+ "step": 936
42
+ },
43
+ {
44
+ "epoch": 3.2,
45
+ "learning_rate": 3.1622983263961825e-05,
46
+ "loss": 0.1095,
47
+ "step": 1000
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_loss": 0.18391327559947968,
52
+ "eval_mse": 0.18391327559947968,
53
+ "eval_runtime": 13.7422,
54
+ "eval_samples_per_second": 72.769,
55
+ "eval_steps_per_second": 9.096,
56
+ "step": 1248
57
+ },
58
+ {
59
+ "epoch": 4.81,
60
+ "learning_rate": 2.860552302885096e-05,
61
+ "loss": 0.0676,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "eval_loss": 0.1835608184337616,
67
+ "eval_mse": 0.1835608184337616,
68
+ "eval_runtime": 13.7549,
69
+ "eval_samples_per_second": 72.702,
70
+ "eval_steps_per_second": 9.088,
71
+ "step": 1560
72
+ },
73
+ {
74
+ "epoch": 6.0,
75
+ "eval_loss": 0.1830635964870453,
76
+ "eval_mse": 0.1830635964870453,
77
+ "eval_runtime": 13.799,
78
+ "eval_samples_per_second": 72.469,
79
+ "eval_steps_per_second": 9.059,
80
+ "step": 1872
81
+ },
82
+ {
83
+ "epoch": 6.41,
84
+ "learning_rate": 2.5588062793740103e-05,
85
+ "loss": 0.0507,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "eval_loss": 0.18448784947395325,
91
+ "eval_mse": 0.18448786437511444,
92
+ "eval_runtime": 13.7961,
93
+ "eval_samples_per_second": 72.484,
94
+ "eval_steps_per_second": 9.061,
95
+ "step": 2184
96
+ },
97
+ {
98
+ "epoch": 8.0,
99
+ "eval_loss": 0.18527822196483612,
100
+ "eval_mse": 0.18527822196483612,
101
+ "eval_runtime": 13.7973,
102
+ "eval_samples_per_second": 72.478,
103
+ "eval_steps_per_second": 9.06,
104
+ "step": 2496
105
+ },
106
+ {
107
+ "epoch": 8.01,
108
+ "learning_rate": 2.257060255862924e-05,
109
+ "loss": 0.0402,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 9.0,
114
+ "eval_loss": 0.18943239748477936,
115
+ "eval_mse": 0.18943239748477936,
116
+ "eval_runtime": 13.7202,
117
+ "eval_samples_per_second": 72.885,
118
+ "eval_steps_per_second": 9.111,
119
+ "step": 2808
120
+ },
121
+ {
122
+ "epoch": 9.61,
123
+ "learning_rate": 1.9553142323518382e-05,
124
+ "loss": 0.0327,
125
+ "step": 3000
126
+ },
127
+ {
128
+ "epoch": 10.0,
129
+ "eval_loss": 0.17714717984199524,
130
+ "eval_mse": 0.17714717984199524,
131
+ "eval_runtime": 13.7644,
132
+ "eval_samples_per_second": 72.651,
133
+ "eval_steps_per_second": 9.081,
134
+ "step": 3120
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_loss": 0.18594859540462494,
139
+ "eval_mse": 0.18594858050346375,
140
+ "eval_runtime": 13.6617,
141
+ "eval_samples_per_second": 73.197,
142
+ "eval_steps_per_second": 9.15,
143
+ "step": 3432
144
+ },
145
+ {
146
+ "epoch": 11.22,
147
+ "learning_rate": 1.6535682088407518e-05,
148
+ "loss": 0.0268,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 12.0,
153
+ "eval_loss": 0.18873579800128937,
154
+ "eval_mse": 0.18873581290245056,
155
+ "eval_runtime": 13.705,
156
+ "eval_samples_per_second": 72.966,
157
+ "eval_steps_per_second": 9.121,
158
+ "step": 3744
159
+ },
160
+ {
161
+ "epoch": 12.82,
162
+ "learning_rate": 1.3518221853296657e-05,
163
+ "loss": 0.0211,
164
+ "step": 4000
165
+ },
166
+ {
167
+ "epoch": 13.0,
168
+ "eval_loss": 0.19864311814308167,
169
+ "eval_mse": 0.19864313304424286,
170
+ "eval_runtime": 13.7757,
171
+ "eval_samples_per_second": 72.592,
172
+ "eval_steps_per_second": 9.074,
173
+ "step": 4056
174
+ },
175
+ {
176
+ "epoch": 14.0,
177
+ "eval_loss": 0.17751657962799072,
178
+ "eval_mse": 0.17751657962799072,
179
+ "eval_runtime": 13.7818,
180
+ "eval_samples_per_second": 72.56,
181
+ "eval_steps_per_second": 9.07,
182
+ "step": 4368
183
+ },
184
+ {
185
+ "epoch": 14.42,
186
+ "learning_rate": 1.0500761618185796e-05,
187
+ "loss": 0.0161,
188
+ "step": 4500
189
+ },
190
+ {
191
+ "epoch": 15.0,
192
+ "eval_loss": 0.1854146122932434,
193
+ "eval_mse": 0.1854146122932434,
194
+ "eval_runtime": 13.8239,
195
+ "eval_samples_per_second": 72.339,
196
+ "eval_steps_per_second": 9.042,
197
+ "step": 4680
198
+ },
199
+ {
200
+ "epoch": 16.0,
201
+ "eval_loss": 0.1844572126865387,
202
+ "eval_mse": 0.1844572275876999,
203
+ "eval_runtime": 13.7435,
204
+ "eval_samples_per_second": 72.762,
205
+ "eval_steps_per_second": 9.095,
206
+ "step": 4992
207
+ },
208
+ {
209
+ "epoch": 16.03,
210
+ "learning_rate": 7.483301383074935e-06,
211
+ "loss": 0.0126,
212
+ "step": 5000
213
+ },
214
+ {
215
+ "epoch": 17.0,
216
+ "eval_loss": 0.18561576306819916,
217
+ "eval_mse": 0.18561576306819916,
218
+ "eval_runtime": 13.7414,
219
+ "eval_samples_per_second": 72.773,
220
+ "eval_steps_per_second": 9.097,
221
+ "step": 5304
222
+ },
223
+ {
224
+ "epoch": 17.63,
225
+ "learning_rate": 4.465841147964074e-06,
226
+ "loss": 0.01,
227
+ "step": 5500
228
+ },
229
+ {
230
+ "epoch": 18.0,
231
+ "eval_loss": 0.17724011838436127,
232
+ "eval_mse": 0.17724011838436127,
233
+ "eval_runtime": 13.7177,
234
+ "eval_samples_per_second": 72.898,
235
+ "eval_steps_per_second": 9.112,
236
+ "step": 5616
237
+ },
238
+ {
239
+ "epoch": 19.0,
240
+ "eval_loss": 0.18078790605068207,
241
+ "eval_mse": 0.18078790605068207,
242
+ "eval_runtime": 13.8059,
243
+ "eval_samples_per_second": 72.433,
244
+ "eval_steps_per_second": 9.054,
245
+ "step": 5928
246
+ },
247
+ {
248
+ "epoch": 19.23,
249
+ "learning_rate": 1.4483809128532133e-06,
250
+ "loss": 0.008,
251
+ "step": 6000
252
+ },
253
+ {
254
+ "epoch": 20.0,
255
+ "eval_loss": 0.18189798295497894,
256
+ "eval_mse": 0.18189798295497894,
257
+ "eval_runtime": 13.7884,
258
+ "eval_samples_per_second": 72.524,
259
+ "eval_steps_per_second": 9.066,
260
+ "step": 6240
261
+ },
262
+ {
263
+ "epoch": 20.0,
264
+ "step": 6240,
265
+ "total_flos": 2.3296341506770944e+16,
266
+ "train_loss": 0.05592835318201628,
267
+ "train_runtime": 6478.1274,
268
+ "train_samples_per_second": 15.437,
269
+ "train_steps_per_second": 0.963
270
+ }
271
+ ],
272
+ "max_steps": 6240,
273
+ "num_train_epochs": 20,
274
+ "total_flos": 2.3296341506770944e+16,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }