File size: 7,950 Bytes
eb22acc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
{
  "best_metric": 0.9882958046457017,
  "best_model_checkpoint": "distilhubert-finetuned-cry-detector/checkpoint-700",
  "epoch": 18.6046511627907,
  "eval_steps": 100,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1627906976744187,
      "grad_norm": 0.9607858657836914,
      "learning_rate": 1.744186046511628e-05,
      "loss": 0.6124,
      "step": 50
    },
    {
      "epoch": 2.3255813953488373,
      "grad_norm": 2.0142862796783447,
      "learning_rate": 2.997578868976474e-05,
      "loss": 0.3124,
      "step": 100
    },
    {
      "epoch": 2.3255813953488373,
      "eval_accuracy": 0.9641025641025641,
      "eval_confusion_matrix": [
        [
          948,
          22
        ],
        [
          27,
          368
        ]
      ],
      "eval_f1": 0.9640343817214121,
      "eval_loss": 0.2739163041114807,
      "eval_precision": 0.9639973701512163,
      "eval_recall": 0.9641025641025641,
      "eval_runtime": 3.48,
      "eval_samples_per_second": 392.238,
      "eval_steps_per_second": 6.322,
      "step": 100
    },
    {
      "epoch": 3.488372093023256,
      "grad_norm": 1.6254416704177856,
      "learning_rate": 2.9496736466239833e-05,
      "loss": 0.2509,
      "step": 150
    },
    {
      "epoch": 4.651162790697675,
      "grad_norm": 1.0478523969650269,
      "learning_rate": 2.8422656841613377e-05,
      "loss": 0.2337,
      "step": 200
    },
    {
      "epoch": 4.651162790697675,
      "eval_accuracy": 0.9736263736263736,
      "eval_confusion_matrix": [
        [
          950,
          20
        ],
        [
          16,
          379
        ]
      ],
      "eval_f1": 0.9736655604528286,
      "eval_loss": 0.23845618963241577,
      "eval_precision": 0.9737247242968067,
      "eval_recall": 0.9736263736263736,
      "eval_runtime": 3.3782,
      "eval_samples_per_second": 404.066,
      "eval_steps_per_second": 6.512,
      "step": 200
    },
    {
      "epoch": 5.813953488372093,
      "grad_norm": 0.19202682375907898,
      "learning_rate": 2.679763606999547e-05,
      "loss": 0.213,
      "step": 250
    },
    {
      "epoch": 6.976744186046512,
      "grad_norm": 3.5125396251678467,
      "learning_rate": 2.4688374121322346e-05,
      "loss": 0.2064,
      "step": 300
    },
    {
      "epoch": 6.976744186046512,
      "eval_accuracy": 0.9831501831501831,
      "eval_confusion_matrix": [
        [
          958,
          12
        ],
        [
          11,
          384
        ]
      ],
      "eval_f1": 0.9831564891330211,
      "eval_loss": 0.2294875830411911,
      "eval_precision": 0.983164066755398,
      "eval_recall": 0.9831501831501831,
      "eval_runtime": 3.421,
      "eval_samples_per_second": 399.01,
      "eval_steps_per_second": 6.431,
      "step": 300
    },
    {
      "epoch": 8.13953488372093,
      "grad_norm": 0.06433115154504776,
      "learning_rate": 2.218144694035814e-05,
      "loss": 0.2044,
      "step": 350
    },
    {
      "epoch": 9.30232558139535,
      "grad_norm": 0.1391066163778305,
      "learning_rate": 1.9379752884171956e-05,
      "loss": 0.2023,
      "step": 400
    },
    {
      "epoch": 9.30232558139535,
      "eval_accuracy": 0.9868131868131869,
      "eval_confusion_matrix": [
        [
          957,
          13
        ],
        [
          5,
          390
        ]
      ],
      "eval_f1": 0.9868519842367506,
      "eval_loss": 0.22771421074867249,
      "eval_precision": 0.986971783497838,
      "eval_recall": 0.9868131868131869,
      "eval_runtime": 3.414,
      "eval_samples_per_second": 399.822,
      "eval_steps_per_second": 6.444,
      "step": 400
    },
    {
      "epoch": 10.465116279069768,
      "grad_norm": 0.03317234292626381,
      "learning_rate": 1.6398289196234188e-05,
      "loss": 0.201,
      "step": 450
    },
    {
      "epoch": 11.627906976744185,
      "grad_norm": 0.0141974575817585,
      "learning_rate": 1.3359431874331888e-05,
      "loss": 0.2003,
      "step": 500
    },
    {
      "epoch": 11.627906976744185,
      "eval_accuracy": 0.9875457875457876,
      "eval_confusion_matrix": [
        [
          960,
          10
        ],
        [
          7,
          388
        ]
      ],
      "eval_f1": 0.9875597008648797,
      "eval_loss": 0.22541972994804382,
      "eval_precision": 0.9875850990732533,
      "eval_recall": 0.9875457875457876,
      "eval_runtime": 3.4267,
      "eval_samples_per_second": 398.347,
      "eval_steps_per_second": 6.42,
      "step": 500
    },
    {
      "epoch": 12.790697674418604,
      "grad_norm": 0.020028484985232353,
      "learning_rate": 1.0387912673007252e-05,
      "loss": 0.2005,
      "step": 550
    },
    {
      "epoch": 13.953488372093023,
      "grad_norm": 0.013127407990396023,
      "learning_rate": 7.605699412521431e-06,
      "loss": 0.2002,
      "step": 600
    },
    {
      "epoch": 13.953488372093023,
      "eval_accuracy": 0.9875457875457876,
      "eval_confusion_matrix": [
        [
          959,
          11
        ],
        [
          6,
          389
        ]
      ],
      "eval_f1": 0.9875688610221299,
      "eval_loss": 0.2259330302476883,
      "eval_precision": 0.9876237449942113,
      "eval_recall": 0.9875457875457876,
      "eval_runtime": 3.3216,
      "eval_samples_per_second": 410.95,
      "eval_steps_per_second": 6.623,
      "step": 600
    },
    {
      "epoch": 15.116279069767442,
      "grad_norm": 0.016032038256525993,
      "learning_rate": 5.126989735188782e-06,
      "loss": 0.2012,
      "step": 650
    },
    {
      "epoch": 16.27906976744186,
      "grad_norm": 0.012081542983651161,
      "learning_rate": 3.0535237934100274e-06,
      "loss": 0.1994,
      "step": 700
    },
    {
      "epoch": 16.27906976744186,
      "eval_accuracy": 0.9882783882783883,
      "eval_confusion_matrix": [
        [
          960,
          10
        ],
        [
          6,
          389
        ]
      ],
      "eval_f1": 0.9882958046457017,
      "eval_loss": 0.22554340958595276,
      "eval_precision": 0.9883336307004172,
      "eval_recall": 0.9882783882783883,
      "eval_runtime": 3.3839,
      "eval_samples_per_second": 403.383,
      "eval_steps_per_second": 6.501,
      "step": 700
    },
    {
      "epoch": 17.441860465116278,
      "grad_norm": 0.015530905686318874,
      "learning_rate": 1.470408262986479e-06,
      "loss": 0.2008,
      "step": 750
    },
    {
      "epoch": 18.6046511627907,
      "grad_norm": 0.03649911284446716,
      "learning_rate": 4.4262308763892087e-07,
      "loss": 0.1997,
      "step": 800
    },
    {
      "epoch": 18.6046511627907,
      "eval_accuracy": 0.9882783882783883,
      "eval_confusion_matrix": [
        [
          960,
          10
        ],
        [
          6,
          389
        ]
      ],
      "eval_f1": 0.9882958046457017,
      "eval_loss": 0.22540099918842316,
      "eval_precision": 0.9883336307004172,
      "eval_recall": 0.9882783882783883,
      "eval_runtime": 3.38,
      "eval_samples_per_second": 403.852,
      "eval_steps_per_second": 6.509,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.001
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.31074598563328e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}