Hugging Face's logo

JulesGo
/
bert-secabilite-regressor

Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
Community
bert-secabilite-regressor
File size: 6,599 Bytes 
424a177
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
 
{
  "best_global_step": 864,
  "best_metric": 0.02581467106938362,
  "best_model_checkpoint": "./bert-secabilite-regressor/checkpoint-864",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 864,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.18632853031158447,
      "learning_rate": 2.8298611111111113e-05,
      "loss": 0.1324,
      "step": 50
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.16045570373535156,
      "learning_rate": 2.65625e-05,
      "loss": 0.0928,
      "step": 100
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.0562266930937767,
      "eval_mae": 0.19059279561042786,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.056342288851737976,
      "eval_runtime": 3.1074,
      "eval_samples_per_second": 277.724,
      "eval_steps_per_second": 34.756,
      "step": 108
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 0.14682810008525848,
      "learning_rate": 2.4826388888888888e-05,
      "loss": 0.0641,
      "step": 150
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.1716427206993103,
      "learning_rate": 2.3090277777777777e-05,
      "loss": 0.0531,
      "step": 200
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.03785160928964615,
      "eval_mae": 0.1461946666240692,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.03801807761192322,
      "eval_runtime": 2.9858,
      "eval_samples_per_second": 289.032,
      "eval_steps_per_second": 36.171,
      "step": 216
    },
    {
      "epoch": 2.314814814814815,
      "grad_norm": 0.13463342189788818,
      "learning_rate": 2.135416666666667e-05,
      "loss": 0.0465,
      "step": 250
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.12161467969417572,
      "learning_rate": 1.961805555555556e-05,
      "loss": 0.0427,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.03144295513629913,
      "eval_mae": 0.1291944533586502,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.031581759452819824,
      "eval_runtime": 2.9834,
      "eval_samples_per_second": 289.266,
      "eval_steps_per_second": 36.2,
      "step": 324
    },
    {
      "epoch": 3.240740740740741,
      "grad_norm": 0.12704914808273315,
      "learning_rate": 1.7881944444444445e-05,
      "loss": 0.0387,
      "step": 350
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 0.09777373820543289,
      "learning_rate": 1.6145833333333334e-05,
      "loss": 0.037,
      "step": 400
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.028512364253401756,
      "eval_mae": 0.12053852528333664,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.02863851748406887,
      "eval_runtime": 2.8921,
      "eval_samples_per_second": 298.403,
      "eval_steps_per_second": 37.344,
      "step": 432
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 0.11912214756011963,
      "learning_rate": 1.4409722222222223e-05,
      "loss": 0.035,
      "step": 450
    },
    {
      "epoch": 4.62962962962963,
      "grad_norm": 0.09360779076814651,
      "learning_rate": 1.2673611111111112e-05,
      "loss": 0.0342,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.027181362733244896,
      "eval_mae": 0.11569906771183014,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.027303453534841537,
      "eval_runtime": 2.9849,
      "eval_samples_per_second": 289.119,
      "eval_steps_per_second": 36.182,
      "step": 540
    },
    {
      "epoch": 5.092592592592593,
      "grad_norm": 0.10609101504087448,
      "learning_rate": 1.09375e-05,
      "loss": 0.0327,
      "step": 550
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.10040564835071564,
      "learning_rate": 9.201388888888889e-06,
      "loss": 0.0321,
      "step": 600
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.026255721226334572,
      "eval_mae": 0.11266371607780457,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.026374226436018944,
      "eval_runtime": 3.0505,
      "eval_samples_per_second": 282.907,
      "eval_steps_per_second": 35.404,
      "step": 648
    },
    {
      "epoch": 6.018518518518518,
      "grad_norm": 0.08536071330308914,
      "learning_rate": 7.4652777777777775e-06,
      "loss": 0.0321,
      "step": 650
    },
    {
      "epoch": 6.481481481481482,
      "grad_norm": 0.10104560106992722,
      "learning_rate": 5.729166666666667e-06,
      "loss": 0.031,
      "step": 700
    },
    {
      "epoch": 6.944444444444445,
      "grad_norm": 0.1454145610332489,
      "learning_rate": 3.993055555555556e-06,
      "loss": 0.0311,
      "step": 750
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.025880420580506325,
      "eval_mae": 0.11090163141489029,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.025996480137109756,
      "eval_runtime": 2.9444,
      "eval_samples_per_second": 293.101,
      "eval_steps_per_second": 36.68,
      "step": 756
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.10250015556812286,
      "learning_rate": 2.2569444444444443e-06,
      "loss": 0.0304,
      "step": 800
    },
    {
      "epoch": 7.87037037037037,
      "grad_norm": 0.08759289234876633,
      "learning_rate": 5.208333333333334e-07,
      "loss": 0.0306,
      "step": 850
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.025699105113744736,
      "eval_mae": 0.110326386988163,
      "eval_model_preparation_time": 0.0006,
      "eval_mse": 0.02581467106938362,
      "eval_runtime": 2.9499,
      "eval_samples_per_second": 292.55,
      "eval_steps_per_second": 36.611,
      "step": 864
    },
    {
      "epoch": 8.0,
      "step": 864,
      "total_flos": 145178794745856.0,
      "train_loss": 0.046594451285070844,
      "train_runtime": 251.4219,
      "train_samples_per_second": 109.744,
      "train_steps_per_second": 3.436
    }
  ],
  "logging_steps": 50,
  "max_steps": 864,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 145178794745856.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}