MattyB95 commited on
Commit
7f94a3e
1 Parent(s): 0cd045c

End of training

Browse files
all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Test_accuracy": 0.9999745993040209,
3
+ "Test_f1": 0.9999792612870445,
4
+ "Test_loss": 0.00039089631172828376,
5
+ "Test_precision": 0.9999585234342596,
6
+ "Test_recall": 1.0,
7
+ "Test_runtime": 1463.7698,
8
+ "Test_samples_per_second": 53.791,
9
+ "Test_steps_per_second": 6.724,
10
+ "Validation_accuracy": 1.0,
11
+ "Validation_f1": 1.0,
12
+ "Validation_loss": 1.1657784459995213e-10,
13
+ "Validation_precision": 1.0,
14
+ "Validation_recall": 1.0,
15
+ "Validation_runtime": 1009.7065,
16
+ "Validation_samples_per_second": 77.981,
17
+ "Validation_steps_per_second": 9.748,
18
+ "epoch": 3.0,
19
+ "train_loss": 0.0,
20
+ "train_runtime": 0.1481,
21
+ "train_samples_per_second": 4784789.707,
22
+ "train_steps_per_second": 598108.842
23
+ }
config.json CHANGED
@@ -25,6 +25,7 @@
25
  "num_channels": 3,
26
  "num_hidden_layers": 12,
27
  "patch_size": 16,
 
28
  "qkv_bias": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.37.0"
 
25
  "num_channels": 3,
26
  "num_hidden_layers": 12,
27
  "patch_size": 16,
28
+ "problem_type": "single_label_classification",
29
  "qkv_bias": true,
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.37.0"
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Validation_accuracy": 1.0,
3
+ "Validation_f1": 1.0,
4
+ "Validation_loss": 1.1657784459995213e-10,
5
+ "Validation_precision": 1.0,
6
+ "Validation_recall": 1.0,
7
+ "Validation_runtime": 1009.7065,
8
+ "Validation_samples_per_second": 77.981,
9
+ "Validation_steps_per_second": 9.748,
10
+ "epoch": 3.0
11
+ }
runs/Jan23_14-39-00_Phoenix/events.out.tfevents.1706022240.Phoenix.26932.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512507491263330261bc57bd8842ef0a647c0efa57c09ecfcc2b8614a11a790d
3
+ size 1194
test_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Test_accuracy": 0.9999745993040209,
3
+ "Test_f1": 0.9999792612870445,
4
+ "Test_loss": 0.00039089631172828376,
5
+ "Test_precision": 0.9999585234342596,
6
+ "Test_recall": 1.0,
7
+ "Test_runtime": 1463.7698,
8
+ "Test_samples_per_second": 53.791,
9
+ "Test_steps_per_second": 6.724,
10
+ "epoch": 3.0
11
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.0,
4
+ "train_runtime": 0.1481,
5
+ "train_samples_per_second": 4784789.707,
6
+ "train_steps_per_second": 598108.842
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.1657784459995213e-10,
3
+ "best_model_checkpoint": "D:/AlanTuringInstitute/res/Transformers/VIT-VoxCelebSpoof-ConstantQ-Synthetic-Voice-Detection-New\\checkpoint-88581",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 88581,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "learning_rate": 4.97177724342692e-05,
14
+ "loss": 0.0285,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 4.94355448685384e-05,
20
+ "loss": 0.0089,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.05,
25
+ "learning_rate": 4.91533173028076e-05,
26
+ "loss": 0.0061,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.07,
31
+ "learning_rate": 4.8871089737076805e-05,
32
+ "loss": 0.0004,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.08,
37
+ "learning_rate": 4.8588862171346e-05,
38
+ "loss": 0.0002,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.1,
43
+ "learning_rate": 4.8306634605615204e-05,
44
+ "loss": 0.0001,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "learning_rate": 4.80244070398844e-05,
50
+ "loss": 0.0118,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "learning_rate": 4.77421794741536e-05,
56
+ "loss": 0.0001,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.15,
61
+ "learning_rate": 4.74599519084228e-05,
62
+ "loss": 0.0106,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.17,
67
+ "learning_rate": 4.717772434269201e-05,
68
+ "loss": 0.0076,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.19,
73
+ "learning_rate": 4.68954967769612e-05,
74
+ "loss": 0.0001,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.2,
79
+ "learning_rate": 4.6613269211230405e-05,
80
+ "loss": 0.0048,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.22,
85
+ "learning_rate": 4.6331041645499604e-05,
86
+ "loss": 0.0137,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.24,
91
+ "learning_rate": 4.60488140797688e-05,
92
+ "loss": 0.0018,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.25,
97
+ "learning_rate": 4.5766586514038e-05,
98
+ "loss": 0.0001,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.27,
103
+ "learning_rate": 4.54843589483072e-05,
104
+ "loss": 0.0001,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.29,
109
+ "learning_rate": 4.52021313825764e-05,
110
+ "loss": 0.0014,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.3,
115
+ "learning_rate": 4.49199038168456e-05,
116
+ "loss": 0.0,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.32,
121
+ "learning_rate": 4.4637676251114805e-05,
122
+ "loss": 0.0074,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.34,
127
+ "learning_rate": 4.4355448685384e-05,
128
+ "loss": 0.0052,
129
+ "step": 10000
130
+ },
131
+ {
132
+ "epoch": 0.36,
133
+ "learning_rate": 4.40732211196532e-05,
134
+ "loss": 0.0,
135
+ "step": 10500
136
+ },
137
+ {
138
+ "epoch": 0.37,
139
+ "learning_rate": 4.37909935539224e-05,
140
+ "loss": 0.0,
141
+ "step": 11000
142
+ },
143
+ {
144
+ "epoch": 0.39,
145
+ "learning_rate": 4.35087659881916e-05,
146
+ "loss": 0.0,
147
+ "step": 11500
148
+ },
149
+ {
150
+ "epoch": 0.41,
151
+ "learning_rate": 4.32265384224608e-05,
152
+ "loss": 0.0,
153
+ "step": 12000
154
+ },
155
+ {
156
+ "epoch": 0.42,
157
+ "learning_rate": 4.294431085673e-05,
158
+ "loss": 0.0145,
159
+ "step": 12500
160
+ },
161
+ {
162
+ "epoch": 0.44,
163
+ "learning_rate": 4.26620832909992e-05,
164
+ "loss": 0.003,
165
+ "step": 13000
166
+ },
167
+ {
168
+ "epoch": 0.46,
169
+ "learning_rate": 4.2379855725268404e-05,
170
+ "loss": 0.0049,
171
+ "step": 13500
172
+ },
173
+ {
174
+ "epoch": 0.47,
175
+ "learning_rate": 4.20976281595376e-05,
176
+ "loss": 0.0,
177
+ "step": 14000
178
+ },
179
+ {
180
+ "epoch": 0.49,
181
+ "learning_rate": 4.18154005938068e-05,
182
+ "loss": 0.0032,
183
+ "step": 14500
184
+ },
185
+ {
186
+ "epoch": 0.51,
187
+ "learning_rate": 4.1533173028076e-05,
188
+ "loss": 0.0,
189
+ "step": 15000
190
+ },
191
+ {
192
+ "epoch": 0.52,
193
+ "learning_rate": 4.12509454623452e-05,
194
+ "loss": 0.0066,
195
+ "step": 15500
196
+ },
197
+ {
198
+ "epoch": 0.54,
199
+ "learning_rate": 4.09687178966144e-05,
200
+ "loss": 0.0001,
201
+ "step": 16000
202
+ },
203
+ {
204
+ "epoch": 0.56,
205
+ "learning_rate": 4.06864903308836e-05,
206
+ "loss": 0.0,
207
+ "step": 16500
208
+ },
209
+ {
210
+ "epoch": 0.58,
211
+ "learning_rate": 4.04042627651528e-05,
212
+ "loss": 0.0,
213
+ "step": 17000
214
+ },
215
+ {
216
+ "epoch": 0.59,
217
+ "learning_rate": 4.0122035199422e-05,
218
+ "loss": 0.0,
219
+ "step": 17500
220
+ },
221
+ {
222
+ "epoch": 0.61,
223
+ "learning_rate": 3.98398076336912e-05,
224
+ "loss": 0.0,
225
+ "step": 18000
226
+ },
227
+ {
228
+ "epoch": 0.63,
229
+ "learning_rate": 3.9557580067960395e-05,
230
+ "loss": 0.0,
231
+ "step": 18500
232
+ },
233
+ {
234
+ "epoch": 0.64,
235
+ "learning_rate": 3.92753525022296e-05,
236
+ "loss": 0.0,
237
+ "step": 19000
238
+ },
239
+ {
240
+ "epoch": 0.66,
241
+ "learning_rate": 3.89931249364988e-05,
242
+ "loss": 0.0,
243
+ "step": 19500
244
+ },
245
+ {
246
+ "epoch": 0.68,
247
+ "learning_rate": 3.8710897370768e-05,
248
+ "loss": 0.0,
249
+ "step": 20000
250
+ },
251
+ {
252
+ "epoch": 0.69,
253
+ "learning_rate": 3.84286698050372e-05,
254
+ "loss": 0.0,
255
+ "step": 20500
256
+ },
257
+ {
258
+ "epoch": 0.71,
259
+ "learning_rate": 3.8146442239306404e-05,
260
+ "loss": 0.0,
261
+ "step": 21000
262
+ },
263
+ {
264
+ "epoch": 0.73,
265
+ "learning_rate": 3.7864214673575596e-05,
266
+ "loss": 0.0,
267
+ "step": 21500
268
+ },
269
+ {
270
+ "epoch": 0.75,
271
+ "learning_rate": 3.75819871078448e-05,
272
+ "loss": 0.0,
273
+ "step": 22000
274
+ },
275
+ {
276
+ "epoch": 0.76,
277
+ "learning_rate": 3.7299759542114e-05,
278
+ "loss": 0.0,
279
+ "step": 22500
280
+ },
281
+ {
282
+ "epoch": 0.78,
283
+ "learning_rate": 3.70175319763832e-05,
284
+ "loss": 0.0,
285
+ "step": 23000
286
+ },
287
+ {
288
+ "epoch": 0.8,
289
+ "learning_rate": 3.67353044106524e-05,
290
+ "loss": 0.0153,
291
+ "step": 23500
292
+ },
293
+ {
294
+ "epoch": 0.81,
295
+ "learning_rate": 3.64530768449216e-05,
296
+ "loss": 0.0,
297
+ "step": 24000
298
+ },
299
+ {
300
+ "epoch": 0.83,
301
+ "learning_rate": 3.61708492791908e-05,
302
+ "loss": 0.003,
303
+ "step": 24500
304
+ },
305
+ {
306
+ "epoch": 0.85,
307
+ "learning_rate": 3.5888621713459997e-05,
308
+ "loss": 0.0,
309
+ "step": 25000
310
+ },
311
+ {
312
+ "epoch": 0.86,
313
+ "learning_rate": 3.56063941477292e-05,
314
+ "loss": 0.0027,
315
+ "step": 25500
316
+ },
317
+ {
318
+ "epoch": 0.88,
319
+ "learning_rate": 3.5324166581998395e-05,
320
+ "loss": 0.0013,
321
+ "step": 26000
322
+ },
323
+ {
324
+ "epoch": 0.9,
325
+ "learning_rate": 3.50419390162676e-05,
326
+ "loss": 0.0012,
327
+ "step": 26500
328
+ },
329
+ {
330
+ "epoch": 0.91,
331
+ "learning_rate": 3.47597114505368e-05,
332
+ "loss": 0.0,
333
+ "step": 27000
334
+ },
335
+ {
336
+ "epoch": 0.93,
337
+ "learning_rate": 3.4477483884806e-05,
338
+ "loss": 0.0029,
339
+ "step": 27500
340
+ },
341
+ {
342
+ "epoch": 0.95,
343
+ "learning_rate": 3.41952563190752e-05,
344
+ "loss": 0.0,
345
+ "step": 28000
346
+ },
347
+ {
348
+ "epoch": 0.97,
349
+ "learning_rate": 3.3913028753344404e-05,
350
+ "loss": 0.0,
351
+ "step": 28500
352
+ },
353
+ {
354
+ "epoch": 0.98,
355
+ "learning_rate": 3.3630801187613596e-05,
356
+ "loss": 0.0,
357
+ "step": 29000
358
+ },
359
+ {
360
+ "epoch": 1.0,
361
+ "learning_rate": 3.33485736218828e-05,
362
+ "loss": 0.0,
363
+ "step": 29500
364
+ },
365
+ {
366
+ "epoch": 1.0,
367
+ "eval_accuracy": 0.9999364982600524,
368
+ "eval_f1": 0.999947989806002,
369
+ "eval_loss": 0.0006085448549129069,
370
+ "eval_precision": 0.9998959850218432,
371
+ "eval_recall": 1.0,
372
+ "eval_runtime": 1435.9957,
373
+ "eval_samples_per_second": 54.832,
374
+ "eval_steps_per_second": 6.854,
375
+ "step": 29527
376
+ },
377
+ {
378
+ "epoch": 1.02,
379
+ "learning_rate": 3.3066346056152e-05,
380
+ "loss": 0.0,
381
+ "step": 30000
382
+ },
383
+ {
384
+ "epoch": 1.03,
385
+ "learning_rate": 3.27841184904212e-05,
386
+ "loss": 0.0,
387
+ "step": 30500
388
+ },
389
+ {
390
+ "epoch": 1.05,
391
+ "learning_rate": 3.25018909246904e-05,
392
+ "loss": 0.0051,
393
+ "step": 31000
394
+ },
395
+ {
396
+ "epoch": 1.07,
397
+ "learning_rate": 3.22196633589596e-05,
398
+ "loss": 0.0,
399
+ "step": 31500
400
+ },
401
+ {
402
+ "epoch": 1.08,
403
+ "learning_rate": 3.19374357932288e-05,
404
+ "loss": 0.0,
405
+ "step": 32000
406
+ },
407
+ {
408
+ "epoch": 1.1,
409
+ "learning_rate": 3.1655208227497996e-05,
410
+ "loss": 0.0,
411
+ "step": 32500
412
+ },
413
+ {
414
+ "epoch": 1.12,
415
+ "learning_rate": 3.1372980661767195e-05,
416
+ "loss": 0.0,
417
+ "step": 33000
418
+ },
419
+ {
420
+ "epoch": 1.13,
421
+ "learning_rate": 3.1090753096036394e-05,
422
+ "loss": 0.0103,
423
+ "step": 33500
424
+ },
425
+ {
426
+ "epoch": 1.15,
427
+ "learning_rate": 3.08085255303056e-05,
428
+ "loss": 0.0,
429
+ "step": 34000
430
+ },
431
+ {
432
+ "epoch": 1.17,
433
+ "learning_rate": 3.05262979645748e-05,
434
+ "loss": 0.0,
435
+ "step": 34500
436
+ },
437
+ {
438
+ "epoch": 1.19,
439
+ "learning_rate": 3.0244070398843998e-05,
440
+ "loss": 0.0,
441
+ "step": 35000
442
+ },
443
+ {
444
+ "epoch": 1.2,
445
+ "learning_rate": 2.9961842833113197e-05,
446
+ "loss": 0.0,
447
+ "step": 35500
448
+ },
449
+ {
450
+ "epoch": 1.22,
451
+ "learning_rate": 2.96796152673824e-05,
452
+ "loss": 0.0051,
453
+ "step": 36000
454
+ },
455
+ {
456
+ "epoch": 1.24,
457
+ "learning_rate": 2.9397387701651595e-05,
458
+ "loss": 0.0039,
459
+ "step": 36500
460
+ },
461
+ {
462
+ "epoch": 1.25,
463
+ "learning_rate": 2.9115160135920798e-05,
464
+ "loss": 0.0011,
465
+ "step": 37000
466
+ },
467
+ {
468
+ "epoch": 1.27,
469
+ "learning_rate": 2.8832932570189997e-05,
470
+ "loss": 0.0,
471
+ "step": 37500
472
+ },
473
+ {
474
+ "epoch": 1.29,
475
+ "learning_rate": 2.85507050044592e-05,
476
+ "loss": 0.0027,
477
+ "step": 38000
478
+ },
479
+ {
480
+ "epoch": 1.3,
481
+ "learning_rate": 2.8268477438728395e-05,
482
+ "loss": 0.0,
483
+ "step": 38500
484
+ },
485
+ {
486
+ "epoch": 1.32,
487
+ "learning_rate": 2.7986249872997594e-05,
488
+ "loss": 0.0,
489
+ "step": 39000
490
+ },
491
+ {
492
+ "epoch": 1.34,
493
+ "learning_rate": 2.7704022307266797e-05,
494
+ "loss": 0.0,
495
+ "step": 39500
496
+ },
497
+ {
498
+ "epoch": 1.35,
499
+ "learning_rate": 2.7421794741535996e-05,
500
+ "loss": 0.0,
501
+ "step": 40000
502
+ },
503
+ {
504
+ "epoch": 1.37,
505
+ "learning_rate": 2.7139567175805198e-05,
506
+ "loss": 0.0,
507
+ "step": 40500
508
+ },
509
+ {
510
+ "epoch": 1.39,
511
+ "learning_rate": 2.6857339610074394e-05,
512
+ "loss": 0.0,
513
+ "step": 41000
514
+ },
515
+ {
516
+ "epoch": 1.41,
517
+ "learning_rate": 2.6575112044343596e-05,
518
+ "loss": 0.0019,
519
+ "step": 41500
520
+ },
521
+ {
522
+ "epoch": 1.42,
523
+ "learning_rate": 2.6292884478612795e-05,
524
+ "loss": 0.0,
525
+ "step": 42000
526
+ },
527
+ {
528
+ "epoch": 1.44,
529
+ "learning_rate": 2.6010656912881998e-05,
530
+ "loss": 0.0039,
531
+ "step": 42500
532
+ },
533
+ {
534
+ "epoch": 1.46,
535
+ "learning_rate": 2.5728429347151194e-05,
536
+ "loss": 0.0,
537
+ "step": 43000
538
+ },
539
+ {
540
+ "epoch": 1.47,
541
+ "learning_rate": 2.54462017814204e-05,
542
+ "loss": 0.0,
543
+ "step": 43500
544
+ },
545
+ {
546
+ "epoch": 1.49,
547
+ "learning_rate": 2.5163974215689595e-05,
548
+ "loss": 0.0043,
549
+ "step": 44000
550
+ },
551
+ {
552
+ "epoch": 1.51,
553
+ "learning_rate": 2.4881746649958794e-05,
554
+ "loss": 0.0,
555
+ "step": 44500
556
+ },
557
+ {
558
+ "epoch": 1.52,
559
+ "learning_rate": 2.4599519084227997e-05,
560
+ "loss": 0.0,
561
+ "step": 45000
562
+ },
563
+ {
564
+ "epoch": 1.54,
565
+ "learning_rate": 2.4317291518497196e-05,
566
+ "loss": 0.0026,
567
+ "step": 45500
568
+ },
569
+ {
570
+ "epoch": 1.56,
571
+ "learning_rate": 2.4035063952766395e-05,
572
+ "loss": 0.0,
573
+ "step": 46000
574
+ },
575
+ {
576
+ "epoch": 1.57,
577
+ "learning_rate": 2.3752836387035597e-05,
578
+ "loss": 0.0011,
579
+ "step": 46500
580
+ },
581
+ {
582
+ "epoch": 1.59,
583
+ "learning_rate": 2.3470608821304796e-05,
584
+ "loss": 0.0,
585
+ "step": 47000
586
+ },
587
+ {
588
+ "epoch": 1.61,
589
+ "learning_rate": 2.3188381255573995e-05,
590
+ "loss": 0.0026,
591
+ "step": 47500
592
+ },
593
+ {
594
+ "epoch": 1.63,
595
+ "learning_rate": 2.2906153689843194e-05,
596
+ "loss": 0.0,
597
+ "step": 48000
598
+ },
599
+ {
600
+ "epoch": 1.64,
601
+ "learning_rate": 2.2623926124112397e-05,
602
+ "loss": 0.0,
603
+ "step": 48500
604
+ },
605
+ {
606
+ "epoch": 1.66,
607
+ "learning_rate": 2.2341698558381596e-05,
608
+ "loss": 0.0,
609
+ "step": 49000
610
+ },
611
+ {
612
+ "epoch": 1.68,
613
+ "learning_rate": 2.2059470992650795e-05,
614
+ "loss": 0.0,
615
+ "step": 49500
616
+ },
617
+ {
618
+ "epoch": 1.69,
619
+ "learning_rate": 2.1777243426919997e-05,
620
+ "loss": 0.0046,
621
+ "step": 50000
622
+ },
623
+ {
624
+ "epoch": 1.71,
625
+ "learning_rate": 2.1495015861189193e-05,
626
+ "loss": 0.001,
627
+ "step": 50500
628
+ },
629
+ {
630
+ "epoch": 1.73,
631
+ "learning_rate": 2.1212788295458396e-05,
632
+ "loss": 0.0,
633
+ "step": 51000
634
+ },
635
+ {
636
+ "epoch": 1.74,
637
+ "learning_rate": 2.0930560729727595e-05,
638
+ "loss": 0.0,
639
+ "step": 51500
640
+ },
641
+ {
642
+ "epoch": 1.76,
643
+ "learning_rate": 2.0648333163996794e-05,
644
+ "loss": 0.0,
645
+ "step": 52000
646
+ },
647
+ {
648
+ "epoch": 1.78,
649
+ "learning_rate": 2.0366105598265993e-05,
650
+ "loss": 0.002,
651
+ "step": 52500
652
+ },
653
+ {
654
+ "epoch": 1.79,
655
+ "learning_rate": 2.0083878032535195e-05,
656
+ "loss": 0.0,
657
+ "step": 53000
658
+ },
659
+ {
660
+ "epoch": 1.81,
661
+ "learning_rate": 1.9801650466804394e-05,
662
+ "loss": 0.0,
663
+ "step": 53500
664
+ },
665
+ {
666
+ "epoch": 1.83,
667
+ "learning_rate": 1.9519422901073593e-05,
668
+ "loss": 0.0,
669
+ "step": 54000
670
+ },
671
+ {
672
+ "epoch": 1.85,
673
+ "learning_rate": 1.9237195335342796e-05,
674
+ "loss": 0.0,
675
+ "step": 54500
676
+ },
677
+ {
678
+ "epoch": 1.86,
679
+ "learning_rate": 1.8954967769611995e-05,
680
+ "loss": 0.0029,
681
+ "step": 55000
682
+ },
683
+ {
684
+ "epoch": 1.88,
685
+ "learning_rate": 1.8672740203881194e-05,
686
+ "loss": 0.0012,
687
+ "step": 55500
688
+ },
689
+ {
690
+ "epoch": 1.9,
691
+ "learning_rate": 1.8390512638150396e-05,
692
+ "loss": 0.0,
693
+ "step": 56000
694
+ },
695
+ {
696
+ "epoch": 1.91,
697
+ "learning_rate": 1.8108285072419596e-05,
698
+ "loss": 0.0,
699
+ "step": 56500
700
+ },
701
+ {
702
+ "epoch": 1.93,
703
+ "learning_rate": 1.7826057506688795e-05,
704
+ "loss": 0.0061,
705
+ "step": 57000
706
+ },
707
+ {
708
+ "epoch": 1.95,
709
+ "learning_rate": 1.7543829940957997e-05,
710
+ "loss": 0.0,
711
+ "step": 57500
712
+ },
713
+ {
714
+ "epoch": 1.96,
715
+ "learning_rate": 1.7261602375227193e-05,
716
+ "loss": 0.0,
717
+ "step": 58000
718
+ },
719
+ {
720
+ "epoch": 1.98,
721
+ "learning_rate": 1.6979374809496392e-05,
722
+ "loss": 0.0,
723
+ "step": 58500
724
+ },
725
+ {
726
+ "epoch": 2.0,
727
+ "learning_rate": 1.6697147243765594e-05,
728
+ "loss": 0.0,
729
+ "step": 59000
730
+ },
731
+ {
732
+ "epoch": 2.0,
733
+ "eval_accuracy": 0.9999618989560314,
734
+ "eval_f1": 0.9999687912865272,
735
+ "eval_loss": 0.00020190977375023067,
736
+ "eval_precision": 1.0,
737
+ "eval_recall": 0.9999375845209612,
738
+ "eval_runtime": 608.8036,
739
+ "eval_samples_per_second": 129.332,
740
+ "eval_steps_per_second": 16.168,
741
+ "step": 59054
742
+ },
743
+ {
744
+ "epoch": 2.02,
745
+ "learning_rate": 1.6414919678034793e-05,
746
+ "loss": 0.0,
747
+ "step": 59500
748
+ },
749
+ {
750
+ "epoch": 2.03,
751
+ "learning_rate": 1.6132692112303992e-05,
752
+ "loss": 0.0,
753
+ "step": 60000
754
+ },
755
+ {
756
+ "epoch": 2.05,
757
+ "learning_rate": 1.5850464546573195e-05,
758
+ "loss": 0.0,
759
+ "step": 60500
760
+ },
761
+ {
762
+ "epoch": 2.07,
763
+ "learning_rate": 1.5568236980842394e-05,
764
+ "loss": 0.0,
765
+ "step": 61000
766
+ },
767
+ {
768
+ "epoch": 2.08,
769
+ "learning_rate": 1.5286009415111593e-05,
770
+ "loss": 0.0,
771
+ "step": 61500
772
+ },
773
+ {
774
+ "epoch": 2.1,
775
+ "learning_rate": 1.5003781849380794e-05,
776
+ "loss": 0.0,
777
+ "step": 62000
778
+ },
779
+ {
780
+ "epoch": 2.12,
781
+ "learning_rate": 1.4721554283649993e-05,
782
+ "loss": 0.0,
783
+ "step": 62500
784
+ },
785
+ {
786
+ "epoch": 2.13,
787
+ "learning_rate": 1.4439326717919194e-05,
788
+ "loss": 0.0,
789
+ "step": 63000
790
+ },
791
+ {
792
+ "epoch": 2.15,
793
+ "learning_rate": 1.4157099152188394e-05,
794
+ "loss": 0.0033,
795
+ "step": 63500
796
+ },
797
+ {
798
+ "epoch": 2.17,
799
+ "learning_rate": 1.3874871586457593e-05,
800
+ "loss": 0.0,
801
+ "step": 64000
802
+ },
803
+ {
804
+ "epoch": 2.18,
805
+ "learning_rate": 1.3592644020726794e-05,
806
+ "loss": 0.0,
807
+ "step": 64500
808
+ },
809
+ {
810
+ "epoch": 2.2,
811
+ "learning_rate": 1.3310416454995995e-05,
812
+ "loss": 0.0,
813
+ "step": 65000
814
+ },
815
+ {
816
+ "epoch": 2.22,
817
+ "learning_rate": 1.3028188889265194e-05,
818
+ "loss": 0.0,
819
+ "step": 65500
820
+ },
821
+ {
822
+ "epoch": 2.24,
823
+ "learning_rate": 1.2745961323534391e-05,
824
+ "loss": 0.0,
825
+ "step": 66000
826
+ },
827
+ {
828
+ "epoch": 2.25,
829
+ "learning_rate": 1.2463733757803594e-05,
830
+ "loss": 0.0,
831
+ "step": 66500
832
+ },
833
+ {
834
+ "epoch": 2.27,
835
+ "learning_rate": 1.2181506192072793e-05,
836
+ "loss": 0.0,
837
+ "step": 67000
838
+ },
839
+ {
840
+ "epoch": 2.29,
841
+ "learning_rate": 1.1899278626341992e-05,
842
+ "loss": 0.0,
843
+ "step": 67500
844
+ },
845
+ {
846
+ "epoch": 2.3,
847
+ "learning_rate": 1.1617051060611193e-05,
848
+ "loss": 0.0,
849
+ "step": 68000
850
+ },
851
+ {
852
+ "epoch": 2.32,
853
+ "learning_rate": 1.1334823494880392e-05,
854
+ "loss": 0.0,
855
+ "step": 68500
856
+ },
857
+ {
858
+ "epoch": 2.34,
859
+ "learning_rate": 1.1052595929149593e-05,
860
+ "loss": 0.0,
861
+ "step": 69000
862
+ },
863
+ {
864
+ "epoch": 2.35,
865
+ "learning_rate": 1.0770368363418792e-05,
866
+ "loss": 0.0,
867
+ "step": 69500
868
+ },
869
+ {
870
+ "epoch": 2.37,
871
+ "learning_rate": 1.0488140797687992e-05,
872
+ "loss": 0.0,
873
+ "step": 70000
874
+ },
875
+ {
876
+ "epoch": 2.39,
877
+ "learning_rate": 1.0205913231957193e-05,
878
+ "loss": 0.0,
879
+ "step": 70500
880
+ },
881
+ {
882
+ "epoch": 2.4,
883
+ "learning_rate": 9.923685666226392e-06,
884
+ "loss": 0.0,
885
+ "step": 71000
886
+ },
887
+ {
888
+ "epoch": 2.42,
889
+ "learning_rate": 9.641458100495591e-06,
890
+ "loss": 0.0,
891
+ "step": 71500
892
+ },
893
+ {
894
+ "epoch": 2.44,
895
+ "learning_rate": 9.359230534764792e-06,
896
+ "loss": 0.0,
897
+ "step": 72000
898
+ },
899
+ {
900
+ "epoch": 2.46,
901
+ "learning_rate": 9.077002969033991e-06,
902
+ "loss": 0.0,
903
+ "step": 72500
904
+ },
905
+ {
906
+ "epoch": 2.47,
907
+ "learning_rate": 8.794775403303192e-06,
908
+ "loss": 0.0,
909
+ "step": 73000
910
+ },
911
+ {
912
+ "epoch": 2.49,
913
+ "learning_rate": 8.512547837572393e-06,
914
+ "loss": 0.0,
915
+ "step": 73500
916
+ },
917
+ {
918
+ "epoch": 2.51,
919
+ "learning_rate": 8.230320271841592e-06,
920
+ "loss": 0.0,
921
+ "step": 74000
922
+ },
923
+ {
924
+ "epoch": 2.52,
925
+ "learning_rate": 7.948092706110793e-06,
926
+ "loss": 0.0,
927
+ "step": 74500
928
+ },
929
+ {
930
+ "epoch": 2.54,
931
+ "learning_rate": 7.665865140379992e-06,
932
+ "loss": 0.0,
933
+ "step": 75000
934
+ },
935
+ {
936
+ "epoch": 2.56,
937
+ "learning_rate": 7.383637574649191e-06,
938
+ "loss": 0.0,
939
+ "step": 75500
940
+ },
941
+ {
942
+ "epoch": 2.57,
943
+ "learning_rate": 7.1014100089183914e-06,
944
+ "loss": 0.0,
945
+ "step": 76000
946
+ },
947
+ {
948
+ "epoch": 2.59,
949
+ "learning_rate": 6.819182443187591e-06,
950
+ "loss": 0.0,
951
+ "step": 76500
952
+ },
953
+ {
954
+ "epoch": 2.61,
955
+ "learning_rate": 6.536954877456791e-06,
956
+ "loss": 0.0,
957
+ "step": 77000
958
+ },
959
+ {
960
+ "epoch": 2.62,
961
+ "learning_rate": 6.254727311725991e-06,
962
+ "loss": 0.0,
963
+ "step": 77500
964
+ },
965
+ {
966
+ "epoch": 2.64,
967
+ "learning_rate": 5.972499745995191e-06,
968
+ "loss": 0.0,
969
+ "step": 78000
970
+ },
971
+ {
972
+ "epoch": 2.66,
973
+ "learning_rate": 5.690272180264391e-06,
974
+ "loss": 0.0,
975
+ "step": 78500
976
+ },
977
+ {
978
+ "epoch": 2.68,
979
+ "learning_rate": 5.408044614533591e-06,
980
+ "loss": 0.0,
981
+ "step": 79000
982
+ },
983
+ {
984
+ "epoch": 2.69,
985
+ "learning_rate": 5.125817048802791e-06,
986
+ "loss": 0.0,
987
+ "step": 79500
988
+ },
989
+ {
990
+ "epoch": 2.71,
991
+ "learning_rate": 4.843589483071991e-06,
992
+ "loss": 0.0,
993
+ "step": 80000
994
+ },
995
+ {
996
+ "epoch": 2.73,
997
+ "learning_rate": 4.561361917341191e-06,
998
+ "loss": 0.0,
999
+ "step": 80500
1000
+ },
1001
+ {
1002
+ "epoch": 2.74,
1003
+ "learning_rate": 4.279134351610391e-06,
1004
+ "loss": 0.0,
1005
+ "step": 81000
1006
+ },
1007
+ {
1008
+ "epoch": 2.76,
1009
+ "learning_rate": 3.9969067858795905e-06,
1010
+ "loss": 0.0,
1011
+ "step": 81500
1012
+ },
1013
+ {
1014
+ "epoch": 2.78,
1015
+ "learning_rate": 3.7146792201487904e-06,
1016
+ "loss": 0.0,
1017
+ "step": 82000
1018
+ },
1019
+ {
1020
+ "epoch": 2.79,
1021
+ "learning_rate": 3.4324516544179904e-06,
1022
+ "loss": 0.0,
1023
+ "step": 82500
1024
+ },
1025
+ {
1026
+ "epoch": 2.81,
1027
+ "learning_rate": 3.1502240886871903e-06,
1028
+ "loss": 0.0,
1029
+ "step": 83000
1030
+ },
1031
+ {
1032
+ "epoch": 2.83,
1033
+ "learning_rate": 2.86799652295639e-06,
1034
+ "loss": 0.0,
1035
+ "step": 83500
1036
+ },
1037
+ {
1038
+ "epoch": 2.84,
1039
+ "learning_rate": 2.5857689572255905e-06,
1040
+ "loss": 0.0,
1041
+ "step": 84000
1042
+ },
1043
+ {
1044
+ "epoch": 2.86,
1045
+ "learning_rate": 2.30354139149479e-06,
1046
+ "loss": 0.0,
1047
+ "step": 84500
1048
+ },
1049
+ {
1050
+ "epoch": 2.88,
1051
+ "learning_rate": 2.0213138257639904e-06,
1052
+ "loss": 0.0,
1053
+ "step": 85000
1054
+ },
1055
+ {
1056
+ "epoch": 2.9,
1057
+ "learning_rate": 1.73908626003319e-06,
1058
+ "loss": 0.0,
1059
+ "step": 85500
1060
+ },
1061
+ {
1062
+ "epoch": 2.91,
1063
+ "learning_rate": 1.45685869430239e-06,
1064
+ "loss": 0.0,
1065
+ "step": 86000
1066
+ },
1067
+ {
1068
+ "epoch": 2.93,
1069
+ "learning_rate": 1.17463112857159e-06,
1070
+ "loss": 0.0,
1071
+ "step": 86500
1072
+ },
1073
+ {
1074
+ "epoch": 2.95,
1075
+ "learning_rate": 8.924035628407898e-07,
1076
+ "loss": 0.0,
1077
+ "step": 87000
1078
+ },
1079
+ {
1080
+ "epoch": 2.96,
1081
+ "learning_rate": 6.101759971099898e-07,
1082
+ "loss": 0.0,
1083
+ "step": 87500
1084
+ },
1085
+ {
1086
+ "epoch": 2.98,
1087
+ "learning_rate": 3.279484313791897e-07,
1088
+ "loss": 0.0,
1089
+ "step": 88000
1090
+ },
1091
+ {
1092
+ "epoch": 3.0,
1093
+ "learning_rate": 4.572086564838961e-08,
1094
+ "loss": 0.0,
1095
+ "step": 88500
1096
+ },
1097
+ {
1098
+ "epoch": 3.0,
1099
+ "eval_accuracy": 1.0,
1100
+ "eval_f1": 1.0,
1101
+ "eval_loss": 1.1657784459995213e-10,
1102
+ "eval_precision": 1.0,
1103
+ "eval_recall": 1.0,
1104
+ "eval_runtime": 631.213,
1105
+ "eval_samples_per_second": 124.741,
1106
+ "eval_steps_per_second": 15.594,
1107
+ "step": 88581
1108
+ },
1109
+ {
1110
+ "epoch": 3.0,
1111
+ "step": 88581,
1112
+ "total_flos": 5.491361355252602e+19,
1113
+ "train_loss": 0.0,
1114
+ "train_runtime": 0.1481,
1115
+ "train_samples_per_second": 4784789.707,
1116
+ "train_steps_per_second": 598108.842
1117
+ }
1118
+ ],
1119
+ "logging_steps": 500,
1120
+ "max_steps": 88581,
1121
+ "num_input_tokens_seen": 0,
1122
+ "num_train_epochs": 3,
1123
+ "save_steps": 500,
1124
+ "total_flos": 5.491361355252602e+19,
1125
+ "train_batch_size": 8,
1126
+ "trial_name": null,
1127
+ "trial_params": null
1128
+ }