Hugging Face's logo

ruanchaves
/
bert-large-portuguese-cased-faquad-nli

Text Classification
Transformers
PyTorch
Portuguese
bert
Model card Files Community
ruanchaves commited on
Commit
73ddb05
·
1 Parent(s): 7ae0430

Upload trainer_state.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. trainer_state.json +247 -0
trainer_state.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.997442455242968,
5
+ "global_step": 3900,
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_accuracy": 0.9274965524673462,
13
+ "eval_loss": 0.23106738924980164,
14
+ "eval_runtime": 10.0851,
15
+ "eval_samples_per_second": 72.483,
16
+ "eval_steps_per_second": 9.122,
17
+ "step": 195
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.9165526628494263,
22
+ "eval_loss": 0.3205892741680145,
23
+ "eval_runtime": 10.086,
24
+ "eval_samples_per_second": 72.477,
25
+ "eval_steps_per_second": 9.122,
26
+ "step": 390
27
+ },
28
+ {
29
+ "epoch": 2.56,
30
+ "learning_rate": 1.2754443842729812e-05,
31
+ "loss": 0.1729,
32
+ "step": 500
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.9274965524673462,
37
+ "eval_loss": 0.360751748085022,
38
+ "eval_runtime": 9.9443,
39
+ "eval_samples_per_second": 73.509,
40
+ "eval_steps_per_second": 9.251,
41
+ "step": 585
42
+ },
43
+ {
44
+ "epoch": 4.0,
45
+ "eval_accuracy": 0.9233925938606262,
46
+ "eval_loss": 0.4383067190647125,
47
+ "eval_runtime": 10.0596,
48
+ "eval_samples_per_second": 72.667,
49
+ "eval_steps_per_second": 9.145,
50
+ "step": 780
51
+ },
52
+ {
53
+ "epoch": 5.0,
54
+ "eval_accuracy": 0.9206566214561462,
55
+ "eval_loss": 0.5189540982246399,
56
+ "eval_runtime": 10.0775,
57
+ "eval_samples_per_second": 72.538,
58
+ "eval_steps_per_second": 9.129,
59
+ "step": 975
60
+ },
61
+ {
62
+ "epoch": 5.13,
63
+ "learning_rate": 1.0878790336446016e-05,
64
+ "loss": 0.0589,
65
+ "step": 1000
66
+ },
67
+ {
68
+ "epoch": 6.0,
69
+ "eval_accuracy": 0.9233925938606262,
70
+ "eval_loss": 0.5728073716163635,
71
+ "eval_runtime": 9.9637,
72
+ "eval_samples_per_second": 73.366,
73
+ "eval_steps_per_second": 9.233,
74
+ "step": 1170
75
+ },
76
+ {
77
+ "epoch": 7.0,
78
+ "eval_accuracy": 0.9274965524673462,
79
+ "eval_loss": 0.5684310793876648,
80
+ "eval_runtime": 10.2744,
81
+ "eval_samples_per_second": 71.148,
82
+ "eval_steps_per_second": 8.954,
83
+ "step": 1365
84
+ },
85
+ {
86
+ "epoch": 7.69,
87
+ "learning_rate": 9.003136830162221e-06,
88
+ "loss": 0.0171,
89
+ "step": 1500
90
+ },
91
+ {
92
+ "epoch": 8.0,
93
+ "eval_accuracy": 0.9261285662651062,
94
+ "eval_loss": 0.5847771167755127,
95
+ "eval_runtime": 10.1261,
96
+ "eval_samples_per_second": 72.189,
97
+ "eval_steps_per_second": 9.085,
98
+ "step": 1560
99
+ },
100
+ {
101
+ "epoch": 9.0,
102
+ "eval_accuracy": 0.928864598274231,
103
+ "eval_loss": 0.5692142248153687,
104
+ "eval_runtime": 10.1226,
105
+ "eval_samples_per_second": 72.214,
106
+ "eval_steps_per_second": 9.089,
107
+ "step": 1755
108
+ },
109
+ {
110
+ "epoch": 10.0,
111
+ "eval_accuracy": 0.9261285662651062,
112
+ "eval_loss": 0.6423346400260925,
113
+ "eval_runtime": 10.1278,
114
+ "eval_samples_per_second": 72.178,
115
+ "eval_steps_per_second": 9.084,
116
+ "step": 1950
117
+ },
118
+ {
119
+ "epoch": 10.26,
120
+ "learning_rate": 7.1274833238784245e-06,
121
+ "loss": 0.0094,
122
+ "step": 2000
123
+ },
124
+ {
125
+ "epoch": 11.0,
126
+ "eval_accuracy": 0.9274965524673462,
127
+ "eval_loss": 0.6332233548164368,
128
+ "eval_runtime": 10.2523,
129
+ "eval_samples_per_second": 71.301,
130
+ "eval_steps_per_second": 8.974,
131
+ "step": 2145
132
+ },
133
+ {
134
+ "epoch": 12.0,
135
+ "eval_accuracy": 0.9316005706787109,
136
+ "eval_loss": 0.6691190600395203,
137
+ "eval_runtime": 10.205,
138
+ "eval_samples_per_second": 71.631,
139
+ "eval_steps_per_second": 9.015,
140
+ "step": 2340
141
+ },
142
+ {
143
+ "epoch": 12.82,
144
+ "learning_rate": 5.2518298175946285e-06,
145
+ "loss": 0.0015,
146
+ "step": 2500
147
+ },
148
+ {
149
+ "epoch": 13.0,
150
+ "eval_accuracy": 0.930232584476471,
151
+ "eval_loss": 0.6589073538780212,
152
+ "eval_runtime": 10.1851,
153
+ "eval_samples_per_second": 71.771,
154
+ "eval_steps_per_second": 9.033,
155
+ "step": 2535
156
+ },
157
+ {
158
+ "epoch": 14.0,
159
+ "eval_accuracy": 0.928864598274231,
160
+ "eval_loss": 0.6745939254760742,
161
+ "eval_runtime": 10.1553,
162
+ "eval_samples_per_second": 71.982,
163
+ "eval_steps_per_second": 9.059,
164
+ "step": 2730
165
+ },
166
+ {
167
+ "epoch": 15.0,
168
+ "eval_accuracy": 0.9357045292854309,
169
+ "eval_loss": 0.6391911506652832,
170
+ "eval_runtime": 10.1864,
171
+ "eval_samples_per_second": 71.762,
172
+ "eval_steps_per_second": 9.032,
173
+ "step": 2925
174
+ },
175
+ {
176
+ "epoch": 15.38,
177
+ "learning_rate": 3.376176311310833e-06,
178
+ "loss": 0.0002,
179
+ "step": 3000
180
+ },
181
+ {
182
+ "epoch": 16.0,
183
+ "eval_accuracy": 0.928864598274231,
184
+ "eval_loss": 0.6711709499359131,
185
+ "eval_runtime": 10.0882,
186
+ "eval_samples_per_second": 72.461,
187
+ "eval_steps_per_second": 9.12,
188
+ "step": 3120
189
+ },
190
+ {
191
+ "epoch": 17.0,
192
+ "eval_accuracy": 0.9343365430831909,
193
+ "eval_loss": 0.6648762226104736,
194
+ "eval_runtime": 9.9723,
195
+ "eval_samples_per_second": 73.303,
196
+ "eval_steps_per_second": 9.226,
197
+ "step": 3315
198
+ },
199
+ {
200
+ "epoch": 17.95,
201
+ "learning_rate": 1.5005228050270366e-06,
202
+ "loss": 0.0,
203
+ "step": 3500
204
+ },
205
+ {
206
+ "epoch": 18.0,
207
+ "eval_accuracy": 0.930232584476471,
208
+ "eval_loss": 0.6720365881919861,
209
+ "eval_runtime": 10.1302,
210
+ "eval_samples_per_second": 72.16,
211
+ "eval_steps_per_second": 9.082,
212
+ "step": 3510
213
+ },
214
+ {
215
+ "epoch": 19.0,
216
+ "eval_accuracy": 0.9316005706787109,
217
+ "eval_loss": 0.6750090718269348,
218
+ "eval_runtime": 10.1546,
219
+ "eval_samples_per_second": 71.987,
220
+ "eval_steps_per_second": 9.06,
221
+ "step": 3705
222
+ },
223
+ {
224
+ "epoch": 20.0,
225
+ "eval_accuracy": 0.9316005706787109,
226
+ "eval_loss": 0.6705575585365295,
227
+ "eval_runtime": 10.275,
228
+ "eval_samples_per_second": 71.144,
229
+ "eval_steps_per_second": 8.954,
230
+ "step": 3900
231
+ },
232
+ {
233
+ "epoch": 20.0,
234
+ "step": 3900,
235
+ "total_flos": 1.4573542659723264e+16,
236
+ "train_loss": 0.03345794048399115,
237
+ "train_runtime": 4631.396,
238
+ "train_samples_per_second": 13.508,
239
+ "train_steps_per_second": 0.842
240
+ }
241
+ ],
242
+ "max_steps": 3900,
243
+ "num_train_epochs": 20,
244
+ "total_flos": 1.4573542659723264e+16,
245
+ "trial_name": null,
246
+ "trial_params": null
247
+ }