Hugging Face's logo

ruanchaves
/
bert-base-portuguese-cased-assin-entailment

Text Classification
Transformers
PyTorch
Portuguese
bert
Model card Files Community
1
ruanchaves commited on
Commit
0ef1bfd
·
1 Parent(s): 25448d3

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_accuracy": 0.8989999890327454,
13
+ "eval_loss": 0.2822728157043457,
14
+ "eval_runtime": 4.6919,
15
+ "eval_samples_per_second": 213.134,
16
+ "eval_steps_per_second": 26.642,
17
+ "step": 312
18
+ },
19
+ {
20
+ "epoch": 1.6,
21
+ "learning_rate": 3.107842707402845e-05,
22
+ "loss": 0.3203,
23
+ "step": 500
24
+ },
25
+ {
26
+ "epoch": 2.0,
27
+ "eval_accuracy": 0.9089999794960022,
28
+ "eval_loss": 0.3380243480205536,
29
+ "eval_runtime": 4.8701,
30
+ "eval_samples_per_second": 205.334,
31
+ "eval_steps_per_second": 25.667,
32
+ "step": 624
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.9240000247955322,
37
+ "eval_loss": 0.3920462727546692,
38
+ "eval_runtime": 4.7219,
39
+ "eval_samples_per_second": 211.777,
40
+ "eval_steps_per_second": 26.472,
41
+ "step": 936
42
+ },
43
+ {
44
+ "epoch": 3.2,
45
+ "learning_rate": 2.8371247015315168e-05,
46
+ "loss": 0.1019,
47
+ "step": 1000
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.9200000166893005,
52
+ "eval_loss": 0.47628748416900635,
53
+ "eval_runtime": 4.8792,
54
+ "eval_samples_per_second": 204.953,
55
+ "eval_steps_per_second": 25.619,
56
+ "step": 1248
57
+ },
58
+ {
59
+ "epoch": 4.81,
60
+ "learning_rate": 2.5664066956601888e-05,
61
+ "loss": 0.033,
62
+ "step": 1500
63
+ },
64
+ {
65
+ "epoch": 5.0,
66
+ "eval_accuracy": 0.9309999942779541,
67
+ "eval_loss": 0.4591754674911499,
68
+ "eval_runtime": 4.8857,
69
+ "eval_samples_per_second": 204.677,
70
+ "eval_steps_per_second": 25.585,
71
+ "step": 1560
72
+ },
73
+ {
74
+ "epoch": 6.0,
75
+ "eval_accuracy": 0.9160000085830688,
76
+ "eval_loss": 0.555105447769165,
77
+ "eval_runtime": 4.7722,
78
+ "eval_samples_per_second": 209.547,
79
+ "eval_steps_per_second": 26.193,
80
+ "step": 1872
81
+ },
82
+ {
83
+ "epoch": 6.41,
84
+ "learning_rate": 2.295688689788861e-05,
85
+ "loss": 0.0122,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "eval_accuracy": 0.9200000166893005,
91
+ "eval_loss": 0.6067560315132141,
92
+ "eval_runtime": 4.772,
93
+ "eval_samples_per_second": 209.555,
94
+ "eval_steps_per_second": 26.194,
95
+ "step": 2184
96
+ },
97
+ {
98
+ "epoch": 8.0,
99
+ "eval_accuracy": 0.9120000004768372,
100
+ "eval_loss": 0.6876145601272583,
101
+ "eval_runtime": 4.7132,
102
+ "eval_samples_per_second": 212.168,
103
+ "eval_steps_per_second": 26.521,
104
+ "step": 2496
105
+ },
106
+ {
107
+ "epoch": 8.01,
108
+ "learning_rate": 2.024970683917533e-05,
109
+ "loss": 0.0158,
110
+ "step": 2500
111
+ },
112
+ {
113
+ "epoch": 9.0,
114
+ "eval_accuracy": 0.9129999876022339,
115
+ "eval_loss": 0.7302923798561096,
116
+ "eval_runtime": 4.7376,
117
+ "eval_samples_per_second": 211.078,
118
+ "eval_steps_per_second": 26.385,
119
+ "step": 2808
120
+ },
121
+ {
122
+ "epoch": 9.61,
123
+ "learning_rate": 1.754252678046205e-05,
124
+ "loss": 0.0063,
125
+ "step": 3000
126
+ },
127
+ {
128
+ "epoch": 10.0,
129
+ "eval_accuracy": 0.9259999990463257,
130
+ "eval_loss": 0.6355671286582947,
131
+ "eval_runtime": 4.6719,
132
+ "eval_samples_per_second": 214.047,
133
+ "eval_steps_per_second": 26.756,
134
+ "step": 3120
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_accuracy": 0.9210000038146973,
139
+ "eval_loss": 0.6988717913627625,
140
+ "eval_runtime": 4.8916,
141
+ "eval_samples_per_second": 204.431,
142
+ "eval_steps_per_second": 25.554,
143
+ "step": 3432
144
+ },
145
+ {
146
+ "epoch": 11.22,
147
+ "learning_rate": 1.483534672174877e-05,
148
+ "loss": 0.0043,
149
+ "step": 3500
150
+ },
151
+ {
152
+ "epoch": 12.0,
153
+ "eval_accuracy": 0.9190000295639038,
154
+ "eval_loss": 0.7033405900001526,
155
+ "eval_runtime": 4.8604,
156
+ "eval_samples_per_second": 205.746,
157
+ "eval_steps_per_second": 25.718,
158
+ "step": 3744
159
+ },
160
+ {
161
+ "epoch": 12.82,
162
+ "learning_rate": 1.2128166663035492e-05,
163
+ "loss": 0.0047,
164
+ "step": 4000
165
+ },
166
+ {
167
+ "epoch": 13.0,
168
+ "eval_accuracy": 0.9070000052452087,
169
+ "eval_loss": 0.840012788772583,
170
+ "eval_runtime": 4.9023,
171
+ "eval_samples_per_second": 203.986,
172
+ "eval_steps_per_second": 25.498,
173
+ "step": 4056
174
+ },
175
+ {
176
+ "epoch": 14.0,
177
+ "eval_accuracy": 0.9190000295639038,
178
+ "eval_loss": 0.7390091419219971,
179
+ "eval_runtime": 4.8503,
180
+ "eval_samples_per_second": 206.175,
181
+ "eval_steps_per_second": 25.772,
182
+ "step": 4368
183
+ },
184
+ {
185
+ "epoch": 14.42,
186
+ "learning_rate": 9.420986604322212e-06,
187
+ "loss": 0.0035,
188
+ "step": 4500
189
+ },
190
+ {
191
+ "epoch": 15.0,
192
+ "eval_accuracy": 0.9169999957084656,
193
+ "eval_loss": 0.7360817790031433,
194
+ "eval_runtime": 4.876,
195
+ "eval_samples_per_second": 205.084,
196
+ "eval_steps_per_second": 25.636,
197
+ "step": 4680
198
+ },
199
+ {
200
+ "epoch": 16.0,
201
+ "eval_accuracy": 0.9229999780654907,
202
+ "eval_loss": 0.7316659688949585,
203
+ "eval_runtime": 4.8948,
204
+ "eval_samples_per_second": 204.299,
205
+ "eval_steps_per_second": 25.537,
206
+ "step": 4992
207
+ },
208
+ {
209
+ "epoch": 16.03,
210
+ "learning_rate": 6.713806545608932e-06,
211
+ "loss": 0.002,
212
+ "step": 5000
213
+ },
214
+ {
215
+ "epoch": 17.0,
216
+ "eval_accuracy": 0.9139999747276306,
217
+ "eval_loss": 0.8043374419212341,
218
+ "eval_runtime": 4.6508,
219
+ "eval_samples_per_second": 215.017,
220
+ "eval_steps_per_second": 26.877,
221
+ "step": 5304
222
+ },
223
+ {
224
+ "epoch": 17.63,
225
+ "learning_rate": 4.006626486895653e-06,
226
+ "loss": 0.0,
227
+ "step": 5500
228
+ },
229
+ {
230
+ "epoch": 18.0,
231
+ "eval_accuracy": 0.9129999876022339,
232
+ "eval_loss": 0.8095300197601318,
233
+ "eval_runtime": 4.7921,
234
+ "eval_samples_per_second": 208.677,
235
+ "eval_steps_per_second": 26.085,
236
+ "step": 5616
237
+ },
238
+ {
239
+ "epoch": 19.0,
240
+ "eval_accuracy": 0.9120000004768372,
241
+ "eval_loss": 0.7782994508743286,
242
+ "eval_runtime": 4.7356,
243
+ "eval_samples_per_second": 211.168,
244
+ "eval_steps_per_second": 26.396,
245
+ "step": 5928
246
+ },
247
+ {
248
+ "epoch": 19.23,
249
+ "learning_rate": 1.2994464281823743e-06,
250
+ "loss": 0.0007,
251
+ "step": 6000
252
+ },
253
+ {
254
+ "epoch": 20.0,
255
+ "eval_accuracy": 0.9139999747276306,
256
+ "eval_loss": 0.7657350897789001,
257
+ "eval_runtime": 4.8181,
258
+ "eval_samples_per_second": 207.551,
259
+ "eval_steps_per_second": 25.944,
260
+ "step": 6240
261
+ },
262
+ {
263
+ "epoch": 20.0,
264
+ "step": 6240,
265
+ "total_flos": 6577309216364544.0,
266
+ "train_loss": 0.04045970406598197,
267
+ "train_runtime": 2296.6324,
268
+ "train_samples_per_second": 43.542,
269
+ "train_steps_per_second": 2.717
270
+ }
271
+ ],
272
+ "max_steps": 6240,
273
+ "num_train_epochs": 20,
274
+ "total_flos": 6577309216364544.0,
275
+ "trial_name": null,
276
+ "trial_params": null
277
+ }