dima806 commited on
Commit
8af0dda
1 Parent(s): e7be807

Delete checkpoint-695

Browse files
checkpoint-695/config.json DELETED
@@ -1,125 +0,0 @@
1
- {
2
- "_name_or_path": "facebook/wav2vec2-base-960h",
3
- "activation_dropout": 0.1,
4
- "adapter_kernel_size": 3,
5
- "adapter_stride": 2,
6
- "add_adapter": false,
7
- "apply_spec_augment": true,
8
- "architectures": [
9
- "Wav2Vec2ForSequenceClassification"
10
- ],
11
- "attention_dropout": 0.1,
12
- "bos_token_id": 1,
13
- "classifier_proj_size": 256,
14
- "codevector_dim": 256,
15
- "contrastive_logits_temperature": 0.1,
16
- "conv_bias": false,
17
- "conv_dim": [
18
- 512,
19
- 512,
20
- 512,
21
- 512,
22
- 512,
23
- 512,
24
- 512
25
- ],
26
- "conv_kernel": [
27
- 10,
28
- 3,
29
- 3,
30
- 3,
31
- 3,
32
- 2,
33
- 2
34
- ],
35
- "conv_stride": [
36
- 5,
37
- 2,
38
- 2,
39
- 2,
40
- 2,
41
- 2,
42
- 2
43
- ],
44
- "ctc_loss_reduction": "sum",
45
- "ctc_zero_infinity": false,
46
- "diversity_loss_weight": 0.1,
47
- "do_stable_layer_norm": false,
48
- "eos_token_id": 2,
49
- "feat_extract_activation": "gelu",
50
- "feat_extract_dropout": 0.0,
51
- "feat_extract_norm": "group",
52
- "feat_proj_dropout": 0.1,
53
- "feat_quantizer_dropout": 0.0,
54
- "final_dropout": 0.1,
55
- "gradient_checkpointing": false,
56
- "hidden_act": "gelu",
57
- "hidden_dropout": 0.1,
58
- "hidden_dropout_prob": 0.1,
59
- "hidden_size": 768,
60
- "id2label": {
61
- "0": "english",
62
- "1": "spanish",
63
- "2": "arabic",
64
- "3": "french",
65
- "4": "mandarin",
66
- "5": "other"
67
- },
68
- "initializer_range": 0.02,
69
- "intermediate_size": 3072,
70
- "label2id": {
71
- "LABEL_0": 0,
72
- "LABEL_1": 1,
73
- "LABEL_2": 2,
74
- "LABEL_3": 3,
75
- "LABEL_4": 4,
76
- "LABEL_5": 5
77
- },
78
- "layer_norm_eps": 1e-05,
79
- "layerdrop": 0.1,
80
- "mask_feature_length": 10,
81
- "mask_feature_min_masks": 0,
82
- "mask_feature_prob": 0.0,
83
- "mask_time_length": 10,
84
- "mask_time_min_masks": 2,
85
- "mask_time_prob": 0.05,
86
- "model_type": "wav2vec2",
87
- "num_adapter_layers": 3,
88
- "num_attention_heads": 12,
89
- "num_codevector_groups": 2,
90
- "num_codevectors_per_group": 320,
91
- "num_conv_pos_embedding_groups": 16,
92
- "num_conv_pos_embeddings": 128,
93
- "num_feat_extract_layers": 7,
94
- "num_hidden_layers": 12,
95
- "num_negatives": 100,
96
- "output_hidden_size": 768,
97
- "pad_token_id": 0,
98
- "proj_codevector_dim": 256,
99
- "tdnn_dilation": [
100
- 1,
101
- 2,
102
- 3,
103
- 1,
104
- 1
105
- ],
106
- "tdnn_dim": [
107
- 512,
108
- 512,
109
- 512,
110
- 512,
111
- 1500
112
- ],
113
- "tdnn_kernel": [
114
- 5,
115
- 3,
116
- 3,
117
- 1,
118
- 1
119
- ],
120
- "torch_dtype": "float32",
121
- "transformers_version": "4.28.1",
122
- "use_weighted_layer_sum": false,
123
- "vocab_size": 32,
124
- "xvector_output_dim": 512
125
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-695/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3ded0c54d2eb952a3b68a02a7c60240e58928974418cd780d43b7070b9a7112
3
- size 756685669
 
 
 
 
checkpoint-695/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "do_normalize": true,
3
- "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
- "feature_size": 1,
5
- "padding_side": "right",
6
- "padding_value": 0.0,
7
- "return_attention_mask": false,
8
- "sampling_rate": 16000
9
- }
 
 
 
 
 
 
 
 
 
 
checkpoint-695/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c39a436f10426d9f30843c637101d637d050836a05a10041db01193ebd739d68
3
- size 378352659
 
 
 
 
checkpoint-695/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3620f8162240cc823d230f969fd0e97550304168751de787cb259af44a361c93
3
- size 14567
 
 
 
 
checkpoint-695/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3845579a5796eeb11ab64cc8e56c28b873bbb1e1427d9e32588941fa78f923e
3
- size 623
 
 
 
 
checkpoint-695/trainer_state.json DELETED
@@ -1,4196 +0,0 @@
1
- {
2
- "best_metric": 1.560390591621399,
3
- "best_model_checkpoint": "multiple_accent_classification/checkpoint-695",
4
- "epoch": 1.0,
5
- "global_step": 695,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.0,
12
- "learning_rate": 2.0000000000000002e-07,
13
- "loss": 1.7809,
14
- "step": 1
15
- },
16
- {
17
- "epoch": 0.0,
18
- "learning_rate": 4.0000000000000003e-07,
19
- "loss": 1.7236,
20
- "step": 2
21
- },
22
- {
23
- "epoch": 0.0,
24
- "learning_rate": 6.000000000000001e-07,
25
- "loss": 1.8205,
26
- "step": 3
27
- },
28
- {
29
- "epoch": 0.01,
30
- "learning_rate": 8.000000000000001e-07,
31
- "loss": 1.7999,
32
- "step": 4
33
- },
34
- {
35
- "epoch": 0.01,
36
- "learning_rate": 1.0000000000000002e-06,
37
- "loss": 1.8185,
38
- "step": 5
39
- },
40
- {
41
- "epoch": 0.01,
42
- "learning_rate": 1.2000000000000002e-06,
43
- "loss": 1.7794,
44
- "step": 6
45
- },
46
- {
47
- "epoch": 0.01,
48
- "learning_rate": 1.4000000000000001e-06,
49
- "loss": 1.782,
50
- "step": 7
51
- },
52
- {
53
- "epoch": 0.01,
54
- "learning_rate": 1.6000000000000001e-06,
55
- "loss": 1.7723,
56
- "step": 8
57
- },
58
- {
59
- "epoch": 0.01,
60
- "learning_rate": 1.8000000000000001e-06,
61
- "loss": 1.8171,
62
- "step": 9
63
- },
64
- {
65
- "epoch": 0.01,
66
- "learning_rate": 2.0000000000000003e-06,
67
- "loss": 1.8095,
68
- "step": 10
69
- },
70
- {
71
- "epoch": 0.02,
72
- "learning_rate": 2.2e-06,
73
- "loss": 1.7817,
74
- "step": 11
75
- },
76
- {
77
- "epoch": 0.02,
78
- "learning_rate": 2.4000000000000003e-06,
79
- "loss": 1.8079,
80
- "step": 12
81
- },
82
- {
83
- "epoch": 0.02,
84
- "learning_rate": 2.6e-06,
85
- "loss": 1.8265,
86
- "step": 13
87
- },
88
- {
89
- "epoch": 0.02,
90
- "learning_rate": 2.8000000000000003e-06,
91
- "loss": 1.6441,
92
- "step": 14
93
- },
94
- {
95
- "epoch": 0.02,
96
- "learning_rate": 3e-06,
97
- "loss": 1.8041,
98
- "step": 15
99
- },
100
- {
101
- "epoch": 0.02,
102
- "learning_rate": 3.2000000000000003e-06,
103
- "loss": 1.8014,
104
- "step": 16
105
- },
106
- {
107
- "epoch": 0.02,
108
- "learning_rate": 3.4000000000000005e-06,
109
- "loss": 1.7949,
110
- "step": 17
111
- },
112
- {
113
- "epoch": 0.03,
114
- "learning_rate": 3.6000000000000003e-06,
115
- "loss": 1.8021,
116
- "step": 18
117
- },
118
- {
119
- "epoch": 0.03,
120
- "learning_rate": 3.8000000000000005e-06,
121
- "loss": 1.9434,
122
- "step": 19
123
- },
124
- {
125
- "epoch": 0.03,
126
- "learning_rate": 4.000000000000001e-06,
127
- "loss": 1.7863,
128
- "step": 20
129
- },
130
- {
131
- "epoch": 0.03,
132
- "learning_rate": 4.2000000000000004e-06,
133
- "loss": 1.7931,
134
- "step": 21
135
- },
136
- {
137
- "epoch": 0.03,
138
- "learning_rate": 4.4e-06,
139
- "loss": 1.7781,
140
- "step": 22
141
- },
142
- {
143
- "epoch": 0.03,
144
- "learning_rate": 4.600000000000001e-06,
145
- "loss": 1.7805,
146
- "step": 23
147
- },
148
- {
149
- "epoch": 0.03,
150
- "learning_rate": 4.800000000000001e-06,
151
- "loss": 1.7841,
152
- "step": 24
153
- },
154
- {
155
- "epoch": 0.04,
156
- "learning_rate": 5e-06,
157
- "loss": 1.7882,
158
- "step": 25
159
- },
160
- {
161
- "epoch": 0.04,
162
- "learning_rate": 5.2e-06,
163
- "loss": 1.7881,
164
- "step": 26
165
- },
166
- {
167
- "epoch": 0.04,
168
- "learning_rate": 5.400000000000001e-06,
169
- "loss": 1.7823,
170
- "step": 27
171
- },
172
- {
173
- "epoch": 0.04,
174
- "learning_rate": 5.600000000000001e-06,
175
- "loss": 1.7948,
176
- "step": 28
177
- },
178
- {
179
- "epoch": 0.04,
180
- "learning_rate": 5.8e-06,
181
- "loss": 1.7905,
182
- "step": 29
183
- },
184
- {
185
- "epoch": 0.04,
186
- "learning_rate": 6e-06,
187
- "loss": 1.8093,
188
- "step": 30
189
- },
190
- {
191
- "epoch": 0.04,
192
- "learning_rate": 6.200000000000001e-06,
193
- "loss": 1.7993,
194
- "step": 31
195
- },
196
- {
197
- "epoch": 0.05,
198
- "learning_rate": 6.4000000000000006e-06,
199
- "loss": 1.8261,
200
- "step": 32
201
- },
202
- {
203
- "epoch": 0.05,
204
- "learning_rate": 6.600000000000001e-06,
205
- "loss": 1.8076,
206
- "step": 33
207
- },
208
- {
209
- "epoch": 0.05,
210
- "learning_rate": 6.800000000000001e-06,
211
- "loss": 1.7184,
212
- "step": 34
213
- },
214
- {
215
- "epoch": 0.05,
216
- "learning_rate": 7e-06,
217
- "loss": 1.7999,
218
- "step": 35
219
- },
220
- {
221
- "epoch": 0.05,
222
- "learning_rate": 7.2000000000000005e-06,
223
- "loss": 1.8002,
224
- "step": 36
225
- },
226
- {
227
- "epoch": 0.05,
228
- "learning_rate": 7.4e-06,
229
- "loss": 1.7983,
230
- "step": 37
231
- },
232
- {
233
- "epoch": 0.05,
234
- "learning_rate": 7.600000000000001e-06,
235
- "loss": 1.7646,
236
- "step": 38
237
- },
238
- {
239
- "epoch": 0.06,
240
- "learning_rate": 7.800000000000002e-06,
241
- "loss": 1.7974,
242
- "step": 39
243
- },
244
- {
245
- "epoch": 0.06,
246
- "learning_rate": 8.000000000000001e-06,
247
- "loss": 1.7775,
248
- "step": 40
249
- },
250
- {
251
- "epoch": 0.06,
252
- "learning_rate": 8.2e-06,
253
- "loss": 1.7991,
254
- "step": 41
255
- },
256
- {
257
- "epoch": 0.06,
258
- "learning_rate": 8.400000000000001e-06,
259
- "loss": 1.7888,
260
- "step": 42
261
- },
262
- {
263
- "epoch": 0.06,
264
- "learning_rate": 8.6e-06,
265
- "loss": 1.7765,
266
- "step": 43
267
- },
268
- {
269
- "epoch": 0.06,
270
- "learning_rate": 8.8e-06,
271
- "loss": 1.7836,
272
- "step": 44
273
- },
274
- {
275
- "epoch": 0.06,
276
- "learning_rate": 9e-06,
277
- "loss": 1.7949,
278
- "step": 45
279
- },
280
- {
281
- "epoch": 0.07,
282
- "learning_rate": 9.200000000000002e-06,
283
- "loss": 1.7724,
284
- "step": 46
285
- },
286
- {
287
- "epoch": 0.07,
288
- "learning_rate": 9.4e-06,
289
- "loss": 1.8043,
290
- "step": 47
291
- },
292
- {
293
- "epoch": 0.07,
294
- "learning_rate": 9.600000000000001e-06,
295
- "loss": 1.7796,
296
- "step": 48
297
- },
298
- {
299
- "epoch": 0.07,
300
- "learning_rate": 9.800000000000001e-06,
301
- "loss": 1.7891,
302
- "step": 49
303
- },
304
- {
305
- "epoch": 0.07,
306
- "learning_rate": 1e-05,
307
- "loss": 1.7836,
308
- "step": 50
309
- },
310
- {
311
- "epoch": 0.07,
312
- "learning_rate": 9.998550724637682e-06,
313
- "loss": 1.8004,
314
- "step": 51
315
- },
316
- {
317
- "epoch": 0.07,
318
- "learning_rate": 9.997101449275363e-06,
319
- "loss": 1.7932,
320
- "step": 52
321
- },
322
- {
323
- "epoch": 0.08,
324
- "learning_rate": 9.995652173913044e-06,
325
- "loss": 1.8642,
326
- "step": 53
327
- },
328
- {
329
- "epoch": 0.08,
330
- "learning_rate": 9.994202898550725e-06,
331
- "loss": 1.7733,
332
- "step": 54
333
- },
334
- {
335
- "epoch": 0.08,
336
- "learning_rate": 9.992753623188408e-06,
337
- "loss": 1.8387,
338
- "step": 55
339
- },
340
- {
341
- "epoch": 0.08,
342
- "learning_rate": 9.991304347826087e-06,
343
- "loss": 1.8016,
344
- "step": 56
345
- },
346
- {
347
- "epoch": 0.08,
348
- "learning_rate": 9.98985507246377e-06,
349
- "loss": 1.8028,
350
- "step": 57
351
- },
352
- {
353
- "epoch": 0.08,
354
- "learning_rate": 9.98840579710145e-06,
355
- "loss": 1.7867,
356
- "step": 58
357
- },
358
- {
359
- "epoch": 0.08,
360
- "learning_rate": 9.986956521739132e-06,
361
- "loss": 1.8025,
362
- "step": 59
363
- },
364
- {
365
- "epoch": 0.09,
366
- "learning_rate": 9.985507246376813e-06,
367
- "loss": 1.8052,
368
- "step": 60
369
- },
370
- {
371
- "epoch": 0.09,
372
- "learning_rate": 9.984057971014494e-06,
373
- "loss": 1.7862,
374
- "step": 61
375
- },
376
- {
377
- "epoch": 0.09,
378
- "learning_rate": 9.982608695652175e-06,
379
- "loss": 1.7925,
380
- "step": 62
381
- },
382
- {
383
- "epoch": 0.09,
384
- "learning_rate": 9.981159420289856e-06,
385
- "loss": 1.8018,
386
- "step": 63
387
- },
388
- {
389
- "epoch": 0.09,
390
- "learning_rate": 9.979710144927537e-06,
391
- "loss": 1.7766,
392
- "step": 64
393
- },
394
- {
395
- "epoch": 0.09,
396
- "learning_rate": 9.978260869565218e-06,
397
- "loss": 1.7993,
398
- "step": 65
399
- },
400
- {
401
- "epoch": 0.09,
402
- "learning_rate": 9.9768115942029e-06,
403
- "loss": 1.8006,
404
- "step": 66
405
- },
406
- {
407
- "epoch": 0.1,
408
- "learning_rate": 9.97536231884058e-06,
409
- "loss": 1.789,
410
- "step": 67
411
- },
412
- {
413
- "epoch": 0.1,
414
- "learning_rate": 9.973913043478262e-06,
415
- "loss": 1.7795,
416
- "step": 68
417
- },
418
- {
419
- "epoch": 0.1,
420
- "learning_rate": 9.972463768115943e-06,
421
- "loss": 1.7781,
422
- "step": 69
423
- },
424
- {
425
- "epoch": 0.1,
426
- "learning_rate": 9.971014492753624e-06,
427
- "loss": 1.773,
428
- "step": 70
429
- },
430
- {
431
- "epoch": 0.1,
432
- "learning_rate": 9.969565217391305e-06,
433
- "loss": 1.7694,
434
- "step": 71
435
- },
436
- {
437
- "epoch": 0.1,
438
- "learning_rate": 9.968115942028986e-06,
439
- "loss": 1.7751,
440
- "step": 72
441
- },
442
- {
443
- "epoch": 0.11,
444
- "learning_rate": 9.966666666666667e-06,
445
- "loss": 1.7843,
446
- "step": 73
447
- },
448
- {
449
- "epoch": 0.11,
450
- "learning_rate": 9.965217391304348e-06,
451
- "loss": 1.7965,
452
- "step": 74
453
- },
454
- {
455
- "epoch": 0.11,
456
- "learning_rate": 9.96376811594203e-06,
457
- "loss": 1.9398,
458
- "step": 75
459
- },
460
- {
461
- "epoch": 0.11,
462
- "learning_rate": 9.962318840579712e-06,
463
- "loss": 1.7804,
464
- "step": 76
465
- },
466
- {
467
- "epoch": 0.11,
468
- "learning_rate": 9.960869565217393e-06,
469
- "loss": 1.7993,
470
- "step": 77
471
- },
472
- {
473
- "epoch": 0.11,
474
- "learning_rate": 9.959420289855072e-06,
475
- "loss": 1.8129,
476
- "step": 78
477
- },
478
- {
479
- "epoch": 0.11,
480
- "learning_rate": 9.957971014492755e-06,
481
- "loss": 1.7988,
482
- "step": 79
483
- },
484
- {
485
- "epoch": 0.12,
486
- "learning_rate": 9.956521739130436e-06,
487
- "loss": 1.8938,
488
- "step": 80
489
- },
490
- {
491
- "epoch": 0.12,
492
- "learning_rate": 9.955072463768117e-06,
493
- "loss": 1.7894,
494
- "step": 81
495
- },
496
- {
497
- "epoch": 0.12,
498
- "learning_rate": 9.953623188405798e-06,
499
- "loss": 1.7984,
500
- "step": 82
501
- },
502
- {
503
- "epoch": 0.12,
504
- "learning_rate": 9.952173913043479e-06,
505
- "loss": 1.8354,
506
- "step": 83
507
- },
508
- {
509
- "epoch": 0.12,
510
- "learning_rate": 9.95072463768116e-06,
511
- "loss": 1.7562,
512
- "step": 84
513
- },
514
- {
515
- "epoch": 0.12,
516
- "learning_rate": 9.949275362318841e-06,
517
- "loss": 1.7773,
518
- "step": 85
519
- },
520
- {
521
- "epoch": 0.12,
522
- "learning_rate": 9.947826086956522e-06,
523
- "loss": 1.7774,
524
- "step": 86
525
- },
526
- {
527
- "epoch": 0.13,
528
- "learning_rate": 9.946376811594205e-06,
529
- "loss": 1.7808,
530
- "step": 87
531
- },
532
- {
533
- "epoch": 0.13,
534
- "learning_rate": 9.944927536231886e-06,
535
- "loss": 1.7769,
536
- "step": 88
537
- },
538
- {
539
- "epoch": 0.13,
540
- "learning_rate": 9.943478260869565e-06,
541
- "loss": 1.8332,
542
- "step": 89
543
- },
544
- {
545
- "epoch": 0.13,
546
- "learning_rate": 9.942028985507248e-06,
547
- "loss": 1.7777,
548
- "step": 90
549
- },
550
- {
551
- "epoch": 0.13,
552
- "learning_rate": 9.940579710144929e-06,
553
- "loss": 1.8006,
554
- "step": 91
555
- },
556
- {
557
- "epoch": 0.13,
558
- "learning_rate": 9.93913043478261e-06,
559
- "loss": 1.8033,
560
- "step": 92
561
- },
562
- {
563
- "epoch": 0.13,
564
- "learning_rate": 9.93768115942029e-06,
565
- "loss": 1.7584,
566
- "step": 93
567
- },
568
- {
569
- "epoch": 0.14,
570
- "learning_rate": 9.936231884057972e-06,
571
- "loss": 1.8261,
572
- "step": 94
573
- },
574
- {
575
- "epoch": 0.14,
576
- "learning_rate": 9.934782608695653e-06,
577
- "loss": 1.8463,
578
- "step": 95
579
- },
580
- {
581
- "epoch": 0.14,
582
- "learning_rate": 9.933333333333334e-06,
583
- "loss": 1.7987,
584
- "step": 96
585
- },
586
- {
587
- "epoch": 0.14,
588
- "learning_rate": 9.931884057971015e-06,
589
- "loss": 1.7971,
590
- "step": 97
591
- },
592
- {
593
- "epoch": 0.14,
594
- "learning_rate": 9.930434782608697e-06,
595
- "loss": 1.8483,
596
- "step": 98
597
- },
598
- {
599
- "epoch": 0.14,
600
- "learning_rate": 9.928985507246378e-06,
601
- "loss": 1.8237,
602
- "step": 99
603
- },
604
- {
605
- "epoch": 0.14,
606
- "learning_rate": 9.927536231884058e-06,
607
- "loss": 1.8163,
608
- "step": 100
609
- },
610
- {
611
- "epoch": 0.15,
612
- "learning_rate": 9.92608695652174e-06,
613
- "loss": 1.7806,
614
- "step": 101
615
- },
616
- {
617
- "epoch": 0.15,
618
- "learning_rate": 9.924637681159421e-06,
619
- "loss": 1.7938,
620
- "step": 102
621
- },
622
- {
623
- "epoch": 0.15,
624
- "learning_rate": 9.923188405797102e-06,
625
- "loss": 1.7786,
626
- "step": 103
627
- },
628
- {
629
- "epoch": 0.15,
630
- "learning_rate": 9.921739130434783e-06,
631
- "loss": 1.7904,
632
- "step": 104
633
- },
634
- {
635
- "epoch": 0.15,
636
- "learning_rate": 9.920289855072464e-06,
637
- "loss": 1.7967,
638
- "step": 105
639
- },
640
- {
641
- "epoch": 0.15,
642
- "learning_rate": 9.918840579710145e-06,
643
- "loss": 1.807,
644
- "step": 106
645
- },
646
- {
647
- "epoch": 0.15,
648
- "learning_rate": 9.917391304347826e-06,
649
- "loss": 1.8079,
650
- "step": 107
651
- },
652
- {
653
- "epoch": 0.16,
654
- "learning_rate": 9.915942028985507e-06,
655
- "loss": 1.8145,
656
- "step": 108
657
- },
658
- {
659
- "epoch": 0.16,
660
- "learning_rate": 9.91449275362319e-06,
661
- "loss": 1.7979,
662
- "step": 109
663
- },
664
- {
665
- "epoch": 0.16,
666
- "learning_rate": 9.913043478260871e-06,
667
- "loss": 1.7861,
668
- "step": 110
669
- },
670
- {
671
- "epoch": 0.16,
672
- "learning_rate": 9.911594202898552e-06,
673
- "loss": 1.7905,
674
- "step": 111
675
- },
676
- {
677
- "epoch": 0.16,
678
- "learning_rate": 9.910144927536233e-06,
679
- "loss": 1.8235,
680
- "step": 112
681
- },
682
- {
683
- "epoch": 0.16,
684
- "learning_rate": 9.908695652173914e-06,
685
- "loss": 1.8008,
686
- "step": 113
687
- },
688
- {
689
- "epoch": 0.16,
690
- "learning_rate": 9.907246376811595e-06,
691
- "loss": 1.7062,
692
- "step": 114
693
- },
694
- {
695
- "epoch": 0.17,
696
- "learning_rate": 9.905797101449276e-06,
697
- "loss": 1.7784,
698
- "step": 115
699
- },
700
- {
701
- "epoch": 0.17,
702
- "learning_rate": 9.904347826086957e-06,
703
- "loss": 1.7804,
704
- "step": 116
705
- },
706
- {
707
- "epoch": 0.17,
708
- "learning_rate": 9.902898550724638e-06,
709
- "loss": 1.7892,
710
- "step": 117
711
- },
712
- {
713
- "epoch": 0.17,
714
- "learning_rate": 9.901449275362319e-06,
715
- "loss": 1.7925,
716
- "step": 118
717
- },
718
- {
719
- "epoch": 0.17,
720
- "learning_rate": 9.9e-06,
721
- "loss": 1.8087,
722
- "step": 119
723
- },
724
- {
725
- "epoch": 0.17,
726
- "learning_rate": 9.898550724637683e-06,
727
- "loss": 1.7866,
728
- "step": 120
729
- },
730
- {
731
- "epoch": 0.17,
732
- "learning_rate": 9.897101449275364e-06,
733
- "loss": 1.77,
734
- "step": 121
735
- },
736
- {
737
- "epoch": 0.18,
738
- "learning_rate": 9.895652173913045e-06,
739
- "loss": 1.8127,
740
- "step": 122
741
- },
742
- {
743
- "epoch": 0.18,
744
- "learning_rate": 9.894202898550726e-06,
745
- "loss": 1.7999,
746
- "step": 123
747
- },
748
- {
749
- "epoch": 0.18,
750
- "learning_rate": 9.892753623188407e-06,
751
- "loss": 1.7879,
752
- "step": 124
753
- },
754
- {
755
- "epoch": 0.18,
756
- "learning_rate": 9.891304347826088e-06,
757
- "loss": 1.8021,
758
- "step": 125
759
- },
760
- {
761
- "epoch": 0.18,
762
- "learning_rate": 9.889855072463769e-06,
763
- "loss": 1.7853,
764
- "step": 126
765
- },
766
- {
767
- "epoch": 0.18,
768
- "learning_rate": 9.88840579710145e-06,
769
- "loss": 1.7957,
770
- "step": 127
771
- },
772
- {
773
- "epoch": 0.18,
774
- "learning_rate": 9.886956521739132e-06,
775
- "loss": 1.7958,
776
- "step": 128
777
- },
778
- {
779
- "epoch": 0.19,
780
- "learning_rate": 9.885507246376812e-06,
781
- "loss": 1.7858,
782
- "step": 129
783
- },
784
- {
785
- "epoch": 0.19,
786
- "learning_rate": 9.884057971014493e-06,
787
- "loss": 1.7753,
788
- "step": 130
789
- },
790
- {
791
- "epoch": 0.19,
792
- "learning_rate": 9.882608695652175e-06,
793
- "loss": 1.7965,
794
- "step": 131
795
- },
796
- {
797
- "epoch": 0.19,
798
- "learning_rate": 9.881159420289856e-06,
799
- "loss": 1.784,
800
- "step": 132
801
- },
802
- {
803
- "epoch": 0.19,
804
- "learning_rate": 9.879710144927537e-06,
805
- "loss": 1.7682,
806
- "step": 133
807
- },
808
- {
809
- "epoch": 0.19,
810
- "learning_rate": 9.878260869565218e-06,
811
- "loss": 1.7961,
812
- "step": 134
813
- },
814
- {
815
- "epoch": 0.19,
816
- "learning_rate": 9.8768115942029e-06,
817
- "loss": 1.7959,
818
- "step": 135
819
- },
820
- {
821
- "epoch": 0.2,
822
- "learning_rate": 9.87536231884058e-06,
823
- "loss": 1.7965,
824
- "step": 136
825
- },
826
- {
827
- "epoch": 0.2,
828
- "learning_rate": 9.873913043478261e-06,
829
- "loss": 1.7975,
830
- "step": 137
831
- },
832
- {
833
- "epoch": 0.2,
834
- "learning_rate": 9.872463768115942e-06,
835
- "loss": 1.7583,
836
- "step": 138
837
- },
838
- {
839
- "epoch": 0.2,
840
- "learning_rate": 9.871014492753625e-06,
841
- "loss": 1.8122,
842
- "step": 139
843
- },
844
- {
845
- "epoch": 0.2,
846
- "learning_rate": 9.869565217391304e-06,
847
- "loss": 1.773,
848
- "step": 140
849
- },
850
- {
851
- "epoch": 0.2,
852
- "learning_rate": 9.868115942028986e-06,
853
- "loss": 1.7903,
854
- "step": 141
855
- },
856
- {
857
- "epoch": 0.2,
858
- "learning_rate": 9.866666666666668e-06,
859
- "loss": 1.7876,
860
- "step": 142
861
- },
862
- {
863
- "epoch": 0.21,
864
- "learning_rate": 9.865217391304348e-06,
865
- "loss": 1.7727,
866
- "step": 143
867
- },
868
- {
869
- "epoch": 0.21,
870
- "learning_rate": 9.86376811594203e-06,
871
- "loss": 1.7971,
872
- "step": 144
873
- },
874
- {
875
- "epoch": 0.21,
876
- "learning_rate": 9.862318840579711e-06,
877
- "loss": 1.7969,
878
- "step": 145
879
- },
880
- {
881
- "epoch": 0.21,
882
- "learning_rate": 9.860869565217392e-06,
883
- "loss": 1.7716,
884
- "step": 146
885
- },
886
- {
887
- "epoch": 0.21,
888
- "learning_rate": 9.859420289855073e-06,
889
- "loss": 1.7936,
890
- "step": 147
891
- },
892
- {
893
- "epoch": 0.21,
894
- "learning_rate": 9.857971014492754e-06,
895
- "loss": 1.8433,
896
- "step": 148
897
- },
898
- {
899
- "epoch": 0.21,
900
- "learning_rate": 9.856521739130435e-06,
901
- "loss": 1.7925,
902
- "step": 149
903
- },
904
- {
905
- "epoch": 0.22,
906
- "learning_rate": 9.855072463768118e-06,
907
- "loss": 1.7885,
908
- "step": 150
909
- },
910
- {
911
- "epoch": 0.22,
912
- "learning_rate": 9.853623188405797e-06,
913
- "loss": 1.7897,
914
- "step": 151
915
- },
916
- {
917
- "epoch": 0.22,
918
- "learning_rate": 9.852173913043478e-06,
919
- "loss": 1.7979,
920
- "step": 152
921
- },
922
- {
923
- "epoch": 0.22,
924
- "learning_rate": 9.850724637681161e-06,
925
- "loss": 1.7937,
926
- "step": 153
927
- },
928
- {
929
- "epoch": 0.22,
930
- "learning_rate": 9.84927536231884e-06,
931
- "loss": 1.8094,
932
- "step": 154
933
- },
934
- {
935
- "epoch": 0.22,
936
- "learning_rate": 9.847826086956523e-06,
937
- "loss": 1.7972,
938
- "step": 155
939
- },
940
- {
941
- "epoch": 0.22,
942
- "learning_rate": 9.846376811594204e-06,
943
- "loss": 1.7988,
944
- "step": 156
945
- },
946
- {
947
- "epoch": 0.23,
948
- "learning_rate": 9.844927536231885e-06,
949
- "loss": 1.8043,
950
- "step": 157
951
- },
952
- {
953
- "epoch": 0.23,
954
- "learning_rate": 9.843478260869566e-06,
955
- "loss": 1.7802,
956
- "step": 158
957
- },
958
- {
959
- "epoch": 0.23,
960
- "learning_rate": 9.842028985507247e-06,
961
- "loss": 1.8084,
962
- "step": 159
963
- },
964
- {
965
- "epoch": 0.23,
966
- "learning_rate": 9.840579710144928e-06,
967
- "loss": 1.7994,
968
- "step": 160
969
- },
970
- {
971
- "epoch": 0.23,
972
- "learning_rate": 9.83913043478261e-06,
973
- "loss": 1.7958,
974
- "step": 161
975
- },
976
- {
977
- "epoch": 0.23,
978
- "learning_rate": 9.83768115942029e-06,
979
- "loss": 1.799,
980
- "step": 162
981
- },
982
- {
983
- "epoch": 0.23,
984
- "learning_rate": 9.836231884057973e-06,
985
- "loss": 1.8047,
986
- "step": 163
987
- },
988
- {
989
- "epoch": 0.24,
990
- "learning_rate": 9.834782608695654e-06,
991
- "loss": 1.792,
992
- "step": 164
993
- },
994
- {
995
- "epoch": 0.24,
996
- "learning_rate": 9.833333333333333e-06,
997
- "loss": 1.7957,
998
- "step": 165
999
- },
1000
- {
1001
- "epoch": 0.24,
1002
- "learning_rate": 9.831884057971016e-06,
1003
- "loss": 1.8003,
1004
- "step": 166
1005
- },
1006
- {
1007
- "epoch": 0.24,
1008
- "learning_rate": 9.830434782608697e-06,
1009
- "loss": 1.7996,
1010
- "step": 167
1011
- },
1012
- {
1013
- "epoch": 0.24,
1014
- "learning_rate": 9.828985507246378e-06,
1015
- "loss": 1.7828,
1016
- "step": 168
1017
- },
1018
- {
1019
- "epoch": 0.24,
1020
- "learning_rate": 9.827536231884059e-06,
1021
- "loss": 1.806,
1022
- "step": 169
1023
- },
1024
- {
1025
- "epoch": 0.24,
1026
- "learning_rate": 9.82608695652174e-06,
1027
- "loss": 1.7795,
1028
- "step": 170
1029
- },
1030
- {
1031
- "epoch": 0.25,
1032
- "learning_rate": 9.82463768115942e-06,
1033
- "loss": 1.7812,
1034
- "step": 171
1035
- },
1036
- {
1037
- "epoch": 0.25,
1038
- "learning_rate": 9.823188405797103e-06,
1039
- "loss": 1.7793,
1040
- "step": 172
1041
- },
1042
- {
1043
- "epoch": 0.25,
1044
- "learning_rate": 9.821739130434783e-06,
1045
- "loss": 1.7826,
1046
- "step": 173
1047
- },
1048
- {
1049
- "epoch": 0.25,
1050
- "learning_rate": 9.820289855072465e-06,
1051
- "loss": 1.794,
1052
- "step": 174
1053
- },
1054
- {
1055
- "epoch": 0.25,
1056
- "learning_rate": 9.818840579710146e-06,
1057
- "loss": 1.8022,
1058
- "step": 175
1059
- },
1060
- {
1061
- "epoch": 0.25,
1062
- "learning_rate": 9.817391304347826e-06,
1063
- "loss": 1.8022,
1064
- "step": 176
1065
- },
1066
- {
1067
- "epoch": 0.25,
1068
- "learning_rate": 9.815942028985508e-06,
1069
- "loss": 1.7854,
1070
- "step": 177
1071
- },
1072
- {
1073
- "epoch": 0.26,
1074
- "learning_rate": 9.81449275362319e-06,
1075
- "loss": 1.8071,
1076
- "step": 178
1077
- },
1078
- {
1079
- "epoch": 0.26,
1080
- "learning_rate": 9.81304347826087e-06,
1081
- "loss": 1.7822,
1082
- "step": 179
1083
- },
1084
- {
1085
- "epoch": 0.26,
1086
- "learning_rate": 9.811594202898551e-06,
1087
- "loss": 1.7871,
1088
- "step": 180
1089
- },
1090
- {
1091
- "epoch": 0.26,
1092
- "learning_rate": 9.810144927536232e-06,
1093
- "loss": 1.818,
1094
- "step": 181
1095
- },
1096
- {
1097
- "epoch": 0.26,
1098
- "learning_rate": 9.808695652173913e-06,
1099
- "loss": 1.7898,
1100
- "step": 182
1101
- },
1102
- {
1103
- "epoch": 0.26,
1104
- "learning_rate": 9.807246376811596e-06,
1105
- "loss": 1.7978,
1106
- "step": 183
1107
- },
1108
- {
1109
- "epoch": 0.26,
1110
- "learning_rate": 9.805797101449275e-06,
1111
- "loss": 1.7966,
1112
- "step": 184
1113
- },
1114
- {
1115
- "epoch": 0.27,
1116
- "learning_rate": 9.804347826086958e-06,
1117
- "loss": 1.7753,
1118
- "step": 185
1119
- },
1120
- {
1121
- "epoch": 0.27,
1122
- "learning_rate": 9.802898550724639e-06,
1123
- "loss": 1.7773,
1124
- "step": 186
1125
- },
1126
- {
1127
- "epoch": 0.27,
1128
- "learning_rate": 9.801449275362318e-06,
1129
- "loss": 1.7989,
1130
- "step": 187
1131
- },
1132
- {
1133
- "epoch": 0.27,
1134
- "learning_rate": 9.800000000000001e-06,
1135
- "loss": 1.778,
1136
- "step": 188
1137
- },
1138
- {
1139
- "epoch": 0.27,
1140
- "learning_rate": 9.798550724637682e-06,
1141
- "loss": 1.7772,
1142
- "step": 189
1143
- },
1144
- {
1145
- "epoch": 0.27,
1146
- "learning_rate": 9.797101449275363e-06,
1147
- "loss": 1.7873,
1148
- "step": 190
1149
- },
1150
- {
1151
- "epoch": 0.27,
1152
- "learning_rate": 9.795652173913044e-06,
1153
- "loss": 1.784,
1154
- "step": 191
1155
- },
1156
- {
1157
- "epoch": 0.28,
1158
- "learning_rate": 9.794202898550725e-06,
1159
- "loss": 1.8003,
1160
- "step": 192
1161
- },
1162
- {
1163
- "epoch": 0.28,
1164
- "learning_rate": 9.792753623188406e-06,
1165
- "loss": 1.8156,
1166
- "step": 193
1167
- },
1168
- {
1169
- "epoch": 0.28,
1170
- "learning_rate": 9.791304347826089e-06,
1171
- "loss": 1.7934,
1172
- "step": 194
1173
- },
1174
- {
1175
- "epoch": 0.28,
1176
- "learning_rate": 9.789855072463768e-06,
1177
- "loss": 1.8066,
1178
- "step": 195
1179
- },
1180
- {
1181
- "epoch": 0.28,
1182
- "learning_rate": 9.78840579710145e-06,
1183
- "loss": 1.7851,
1184
- "step": 196
1185
- },
1186
- {
1187
- "epoch": 0.28,
1188
- "learning_rate": 9.786956521739132e-06,
1189
- "loss": 1.7973,
1190
- "step": 197
1191
- },
1192
- {
1193
- "epoch": 0.28,
1194
- "learning_rate": 9.785507246376813e-06,
1195
- "loss": 1.7799,
1196
- "step": 198
1197
- },
1198
- {
1199
- "epoch": 0.29,
1200
- "learning_rate": 9.784057971014494e-06,
1201
- "loss": 1.7895,
1202
- "step": 199
1203
- },
1204
- {
1205
- "epoch": 0.29,
1206
- "learning_rate": 9.782608695652175e-06,
1207
- "loss": 1.7787,
1208
- "step": 200
1209
- },
1210
- {
1211
- "epoch": 0.29,
1212
- "learning_rate": 9.781159420289856e-06,
1213
- "loss": 1.8015,
1214
- "step": 201
1215
- },
1216
- {
1217
- "epoch": 0.29,
1218
- "learning_rate": 9.779710144927537e-06,
1219
- "loss": 1.8044,
1220
- "step": 202
1221
- },
1222
- {
1223
- "epoch": 0.29,
1224
- "learning_rate": 9.778260869565218e-06,
1225
- "loss": 1.8018,
1226
- "step": 203
1227
- },
1228
- {
1229
- "epoch": 0.29,
1230
- "learning_rate": 9.776811594202899e-06,
1231
- "loss": 1.7978,
1232
- "step": 204
1233
- },
1234
- {
1235
- "epoch": 0.29,
1236
- "learning_rate": 9.77536231884058e-06,
1237
- "loss": 1.7901,
1238
- "step": 205
1239
- },
1240
- {
1241
- "epoch": 0.3,
1242
- "learning_rate": 9.77391304347826e-06,
1243
- "loss": 1.796,
1244
- "step": 206
1245
- },
1246
- {
1247
- "epoch": 0.3,
1248
- "learning_rate": 9.772463768115943e-06,
1249
- "loss": 1.7673,
1250
- "step": 207
1251
- },
1252
- {
1253
- "epoch": 0.3,
1254
- "learning_rate": 9.771014492753624e-06,
1255
- "loss": 1.7454,
1256
- "step": 208
1257
- },
1258
- {
1259
- "epoch": 0.3,
1260
- "learning_rate": 9.769565217391305e-06,
1261
- "loss": 1.7707,
1262
- "step": 209
1263
- },
1264
- {
1265
- "epoch": 0.3,
1266
- "learning_rate": 9.768115942028986e-06,
1267
- "loss": 1.8148,
1268
- "step": 210
1269
- },
1270
- {
1271
- "epoch": 0.3,
1272
- "learning_rate": 9.766666666666667e-06,
1273
- "loss": 1.7759,
1274
- "step": 211
1275
- },
1276
- {
1277
- "epoch": 0.31,
1278
- "learning_rate": 9.765217391304348e-06,
1279
- "loss": 1.7986,
1280
- "step": 212
1281
- },
1282
- {
1283
- "epoch": 0.31,
1284
- "learning_rate": 9.76376811594203e-06,
1285
- "loss": 1.7843,
1286
- "step": 213
1287
- },
1288
- {
1289
- "epoch": 0.31,
1290
- "learning_rate": 9.76231884057971e-06,
1291
- "loss": 1.7875,
1292
- "step": 214
1293
- },
1294
- {
1295
- "epoch": 0.31,
1296
- "learning_rate": 9.760869565217393e-06,
1297
- "loss": 1.7955,
1298
- "step": 215
1299
- },
1300
- {
1301
- "epoch": 0.31,
1302
- "learning_rate": 9.759420289855072e-06,
1303
- "loss": 1.7922,
1304
- "step": 216
1305
- },
1306
- {
1307
- "epoch": 0.31,
1308
- "learning_rate": 9.757971014492753e-06,
1309
- "loss": 1.7892,
1310
- "step": 217
1311
- },
1312
- {
1313
- "epoch": 0.31,
1314
- "learning_rate": 9.756521739130436e-06,
1315
- "loss": 1.7968,
1316
- "step": 218
1317
- },
1318
- {
1319
- "epoch": 0.32,
1320
- "learning_rate": 9.755072463768117e-06,
1321
- "loss": 1.7844,
1322
- "step": 219
1323
- },
1324
- {
1325
- "epoch": 0.32,
1326
- "learning_rate": 9.753623188405798e-06,
1327
- "loss": 1.7768,
1328
- "step": 220
1329
- },
1330
- {
1331
- "epoch": 0.32,
1332
- "learning_rate": 9.75217391304348e-06,
1333
- "loss": 1.7621,
1334
- "step": 221
1335
- },
1336
- {
1337
- "epoch": 0.32,
1338
- "learning_rate": 9.75072463768116e-06,
1339
- "loss": 1.7873,
1340
- "step": 222
1341
- },
1342
- {
1343
- "epoch": 0.32,
1344
- "learning_rate": 9.749275362318841e-06,
1345
- "loss": 1.801,
1346
- "step": 223
1347
- },
1348
- {
1349
- "epoch": 0.32,
1350
- "learning_rate": 9.747826086956522e-06,
1351
- "loss": 1.7861,
1352
- "step": 224
1353
- },
1354
- {
1355
- "epoch": 0.32,
1356
- "learning_rate": 9.746376811594203e-06,
1357
- "loss": 1.7778,
1358
- "step": 225
1359
- },
1360
- {
1361
- "epoch": 0.33,
1362
- "learning_rate": 9.744927536231886e-06,
1363
- "loss": 1.773,
1364
- "step": 226
1365
- },
1366
- {
1367
- "epoch": 0.33,
1368
- "learning_rate": 9.743478260869565e-06,
1369
- "loss": 1.8384,
1370
- "step": 227
1371
- },
1372
- {
1373
- "epoch": 0.33,
1374
- "learning_rate": 9.742028985507246e-06,
1375
- "loss": 1.7723,
1376
- "step": 228
1377
- },
1378
- {
1379
- "epoch": 0.33,
1380
- "learning_rate": 9.740579710144929e-06,
1381
- "loss": 1.7699,
1382
- "step": 229
1383
- },
1384
- {
1385
- "epoch": 0.33,
1386
- "learning_rate": 9.73913043478261e-06,
1387
- "loss": 1.7861,
1388
- "step": 230
1389
- },
1390
- {
1391
- "epoch": 0.33,
1392
- "learning_rate": 9.737681159420291e-06,
1393
- "loss": 1.8091,
1394
- "step": 231
1395
- },
1396
- {
1397
- "epoch": 0.33,
1398
- "learning_rate": 9.736231884057972e-06,
1399
- "loss": 1.8037,
1400
- "step": 232
1401
- },
1402
- {
1403
- "epoch": 0.34,
1404
- "learning_rate": 9.734782608695653e-06,
1405
- "loss": 1.7961,
1406
- "step": 233
1407
- },
1408
- {
1409
- "epoch": 0.34,
1410
- "learning_rate": 9.733333333333334e-06,
1411
- "loss": 1.7821,
1412
- "step": 234
1413
- },
1414
- {
1415
- "epoch": 0.34,
1416
- "learning_rate": 9.731884057971015e-06,
1417
- "loss": 1.7605,
1418
- "step": 235
1419
- },
1420
- {
1421
- "epoch": 0.34,
1422
- "learning_rate": 9.730434782608696e-06,
1423
- "loss": 1.7963,
1424
- "step": 236
1425
- },
1426
- {
1427
- "epoch": 0.34,
1428
- "learning_rate": 9.728985507246379e-06,
1429
- "loss": 1.8122,
1430
- "step": 237
1431
- },
1432
- {
1433
- "epoch": 0.34,
1434
- "learning_rate": 9.727536231884058e-06,
1435
- "loss": 1.7776,
1436
- "step": 238
1437
- },
1438
- {
1439
- "epoch": 0.34,
1440
- "learning_rate": 9.726086956521739e-06,
1441
- "loss": 1.7968,
1442
- "step": 239
1443
- },
1444
- {
1445
- "epoch": 0.35,
1446
- "learning_rate": 9.724637681159422e-06,
1447
- "loss": 1.8013,
1448
- "step": 240
1449
- },
1450
- {
1451
- "epoch": 0.35,
1452
- "learning_rate": 9.723188405797103e-06,
1453
- "loss": 1.7907,
1454
- "step": 241
1455
- },
1456
- {
1457
- "epoch": 0.35,
1458
- "learning_rate": 9.721739130434784e-06,
1459
- "loss": 1.7574,
1460
- "step": 242
1461
- },
1462
- {
1463
- "epoch": 0.35,
1464
- "learning_rate": 9.720289855072465e-06,
1465
- "loss": 1.7799,
1466
- "step": 243
1467
- },
1468
- {
1469
- "epoch": 0.35,
1470
- "learning_rate": 9.718840579710146e-06,
1471
- "loss": 1.7939,
1472
- "step": 244
1473
- },
1474
- {
1475
- "epoch": 0.35,
1476
- "learning_rate": 9.717391304347827e-06,
1477
- "loss": 1.7531,
1478
- "step": 245
1479
- },
1480
- {
1481
- "epoch": 0.35,
1482
- "learning_rate": 9.715942028985508e-06,
1483
- "loss": 1.7878,
1484
- "step": 246
1485
- },
1486
- {
1487
- "epoch": 0.36,
1488
- "learning_rate": 9.714492753623189e-06,
1489
- "loss": 1.7804,
1490
- "step": 247
1491
- },
1492
- {
1493
- "epoch": 0.36,
1494
- "learning_rate": 9.713043478260871e-06,
1495
- "loss": 1.79,
1496
- "step": 248
1497
- },
1498
- {
1499
- "epoch": 0.36,
1500
- "learning_rate": 9.71159420289855e-06,
1501
- "loss": 1.8005,
1502
- "step": 249
1503
- },
1504
- {
1505
- "epoch": 0.36,
1506
- "learning_rate": 9.710144927536233e-06,
1507
- "loss": 1.7805,
1508
- "step": 250
1509
- },
1510
- {
1511
- "epoch": 0.36,
1512
- "learning_rate": 9.708695652173914e-06,
1513
- "loss": 1.7825,
1514
- "step": 251
1515
- },
1516
- {
1517
- "epoch": 0.36,
1518
- "learning_rate": 9.707246376811595e-06,
1519
- "loss": 1.822,
1520
- "step": 252
1521
- },
1522
- {
1523
- "epoch": 0.36,
1524
- "learning_rate": 9.705797101449276e-06,
1525
- "loss": 1.7619,
1526
- "step": 253
1527
- },
1528
- {
1529
- "epoch": 0.37,
1530
- "learning_rate": 9.704347826086957e-06,
1531
- "loss": 1.7642,
1532
- "step": 254
1533
- },
1534
- {
1535
- "epoch": 0.37,
1536
- "learning_rate": 9.702898550724638e-06,
1537
- "loss": 1.7656,
1538
- "step": 255
1539
- },
1540
- {
1541
- "epoch": 0.37,
1542
- "learning_rate": 9.701449275362321e-06,
1543
- "loss": 1.7751,
1544
- "step": 256
1545
- },
1546
- {
1547
- "epoch": 0.37,
1548
- "learning_rate": 9.7e-06,
1549
- "loss": 1.7816,
1550
- "step": 257
1551
- },
1552
- {
1553
- "epoch": 0.37,
1554
- "learning_rate": 9.698550724637681e-06,
1555
- "loss": 1.752,
1556
- "step": 258
1557
- },
1558
- {
1559
- "epoch": 0.37,
1560
- "learning_rate": 9.697101449275364e-06,
1561
- "loss": 1.7537,
1562
- "step": 259
1563
- },
1564
- {
1565
- "epoch": 0.37,
1566
- "learning_rate": 9.695652173913043e-06,
1567
- "loss": 1.7902,
1568
- "step": 260
1569
- },
1570
- {
1571
- "epoch": 0.38,
1572
- "learning_rate": 9.694202898550726e-06,
1573
- "loss": 1.8062,
1574
- "step": 261
1575
- },
1576
- {
1577
- "epoch": 0.38,
1578
- "learning_rate": 9.692753623188407e-06,
1579
- "loss": 1.6422,
1580
- "step": 262
1581
- },
1582
- {
1583
- "epoch": 0.38,
1584
- "learning_rate": 9.691304347826088e-06,
1585
- "loss": 1.7912,
1586
- "step": 263
1587
- },
1588
- {
1589
- "epoch": 0.38,
1590
- "learning_rate": 9.689855072463769e-06,
1591
- "loss": 1.7721,
1592
- "step": 264
1593
- },
1594
- {
1595
- "epoch": 0.38,
1596
- "learning_rate": 9.68840579710145e-06,
1597
- "loss": 1.7612,
1598
- "step": 265
1599
- },
1600
- {
1601
- "epoch": 0.38,
1602
- "learning_rate": 9.686956521739131e-06,
1603
- "loss": 1.7566,
1604
- "step": 266
1605
- },
1606
- {
1607
- "epoch": 0.38,
1608
- "learning_rate": 9.685507246376812e-06,
1609
- "loss": 1.8152,
1610
- "step": 267
1611
- },
1612
- {
1613
- "epoch": 0.39,
1614
- "learning_rate": 9.684057971014493e-06,
1615
- "loss": 1.7972,
1616
- "step": 268
1617
- },
1618
- {
1619
- "epoch": 0.39,
1620
- "learning_rate": 9.682608695652174e-06,
1621
- "loss": 1.8002,
1622
- "step": 269
1623
- },
1624
- {
1625
- "epoch": 0.39,
1626
- "learning_rate": 9.681159420289857e-06,
1627
- "loss": 1.7958,
1628
- "step": 270
1629
- },
1630
- {
1631
- "epoch": 0.39,
1632
- "learning_rate": 9.679710144927536e-06,
1633
- "loss": 1.7978,
1634
- "step": 271
1635
- },
1636
- {
1637
- "epoch": 0.39,
1638
- "learning_rate": 9.678260869565219e-06,
1639
- "loss": 1.7986,
1640
- "step": 272
1641
- },
1642
- {
1643
- "epoch": 0.39,
1644
- "learning_rate": 9.6768115942029e-06,
1645
- "loss": 1.813,
1646
- "step": 273
1647
- },
1648
- {
1649
- "epoch": 0.39,
1650
- "learning_rate": 9.67536231884058e-06,
1651
- "loss": 1.7639,
1652
- "step": 274
1653
- },
1654
- {
1655
- "epoch": 0.4,
1656
- "learning_rate": 9.673913043478262e-06,
1657
- "loss": 1.7617,
1658
- "step": 275
1659
- },
1660
- {
1661
- "epoch": 0.4,
1662
- "learning_rate": 9.672463768115943e-06,
1663
- "loss": 1.794,
1664
- "step": 276
1665
- },
1666
- {
1667
- "epoch": 0.4,
1668
- "learning_rate": 9.671014492753624e-06,
1669
- "loss": 1.7577,
1670
- "step": 277
1671
- },
1672
- {
1673
- "epoch": 0.4,
1674
- "learning_rate": 9.669565217391305e-06,
1675
- "loss": 1.7905,
1676
- "step": 278
1677
- },
1678
- {
1679
- "epoch": 0.4,
1680
- "learning_rate": 9.668115942028986e-06,
1681
- "loss": 1.7782,
1682
- "step": 279
1683
- },
1684
- {
1685
- "epoch": 0.4,
1686
- "learning_rate": 9.666666666666667e-06,
1687
- "loss": 1.7855,
1688
- "step": 280
1689
- },
1690
- {
1691
- "epoch": 0.4,
1692
- "learning_rate": 9.66521739130435e-06,
1693
- "loss": 1.7611,
1694
- "step": 281
1695
- },
1696
- {
1697
- "epoch": 0.41,
1698
- "learning_rate": 9.663768115942029e-06,
1699
- "loss": 1.7801,
1700
- "step": 282
1701
- },
1702
- {
1703
- "epoch": 0.41,
1704
- "learning_rate": 9.662318840579711e-06,
1705
- "loss": 1.8409,
1706
- "step": 283
1707
- },
1708
- {
1709
- "epoch": 0.41,
1710
- "learning_rate": 9.660869565217392e-06,
1711
- "loss": 1.7867,
1712
- "step": 284
1713
- },
1714
- {
1715
- "epoch": 0.41,
1716
- "learning_rate": 9.659420289855073e-06,
1717
- "loss": 1.7686,
1718
- "step": 285
1719
- },
1720
- {
1721
- "epoch": 0.41,
1722
- "learning_rate": 9.657971014492754e-06,
1723
- "loss": 1.7582,
1724
- "step": 286
1725
- },
1726
- {
1727
- "epoch": 0.41,
1728
- "learning_rate": 9.656521739130435e-06,
1729
- "loss": 1.7462,
1730
- "step": 287
1731
- },
1732
- {
1733
- "epoch": 0.41,
1734
- "learning_rate": 9.655072463768116e-06,
1735
- "loss": 1.7532,
1736
- "step": 288
1737
- },
1738
- {
1739
- "epoch": 0.42,
1740
- "learning_rate": 9.653623188405797e-06,
1741
- "loss": 1.7801,
1742
- "step": 289
1743
- },
1744
- {
1745
- "epoch": 0.42,
1746
- "learning_rate": 9.652173913043478e-06,
1747
- "loss": 1.7927,
1748
- "step": 290
1749
- },
1750
- {
1751
- "epoch": 0.42,
1752
- "learning_rate": 9.650724637681161e-06,
1753
- "loss": 1.7035,
1754
- "step": 291
1755
- },
1756
- {
1757
- "epoch": 0.42,
1758
- "learning_rate": 9.649275362318842e-06,
1759
- "loss": 1.8057,
1760
- "step": 292
1761
- },
1762
- {
1763
- "epoch": 0.42,
1764
- "learning_rate": 9.647826086956521e-06,
1765
- "loss": 1.8014,
1766
- "step": 293
1767
- },
1768
- {
1769
- "epoch": 0.42,
1770
- "learning_rate": 9.646376811594204e-06,
1771
- "loss": 1.7877,
1772
- "step": 294
1773
- },
1774
- {
1775
- "epoch": 0.42,
1776
- "learning_rate": 9.644927536231885e-06,
1777
- "loss": 1.7719,
1778
- "step": 295
1779
- },
1780
- {
1781
- "epoch": 0.43,
1782
- "learning_rate": 9.643478260869566e-06,
1783
- "loss": 1.8537,
1784
- "step": 296
1785
- },
1786
- {
1787
- "epoch": 0.43,
1788
- "learning_rate": 9.642028985507247e-06,
1789
- "loss": 1.8251,
1790
- "step": 297
1791
- },
1792
- {
1793
- "epoch": 0.43,
1794
- "learning_rate": 9.640579710144928e-06,
1795
- "loss": 1.7511,
1796
- "step": 298
1797
- },
1798
- {
1799
- "epoch": 0.43,
1800
- "learning_rate": 9.639130434782609e-06,
1801
- "loss": 1.7622,
1802
- "step": 299
1803
- },
1804
- {
1805
- "epoch": 0.43,
1806
- "learning_rate": 9.63768115942029e-06,
1807
- "loss": 1.8174,
1808
- "step": 300
1809
- },
1810
- {
1811
- "epoch": 0.43,
1812
- "learning_rate": 9.636231884057971e-06,
1813
- "loss": 1.8452,
1814
- "step": 301
1815
- },
1816
- {
1817
- "epoch": 0.43,
1818
- "learning_rate": 9.634782608695654e-06,
1819
- "loss": 1.7472,
1820
- "step": 302
1821
- },
1822
- {
1823
- "epoch": 0.44,
1824
- "learning_rate": 9.633333333333335e-06,
1825
- "loss": 1.8054,
1826
- "step": 303
1827
- },
1828
- {
1829
- "epoch": 0.44,
1830
- "learning_rate": 9.631884057971014e-06,
1831
- "loss": 1.7485,
1832
- "step": 304
1833
- },
1834
- {
1835
- "epoch": 0.44,
1836
- "learning_rate": 9.630434782608697e-06,
1837
- "loss": 1.804,
1838
- "step": 305
1839
- },
1840
- {
1841
- "epoch": 0.44,
1842
- "learning_rate": 9.628985507246378e-06,
1843
- "loss": 1.7905,
1844
- "step": 306
1845
- },
1846
- {
1847
- "epoch": 0.44,
1848
- "learning_rate": 9.627536231884059e-06,
1849
- "loss": 1.7839,
1850
- "step": 307
1851
- },
1852
- {
1853
- "epoch": 0.44,
1854
- "learning_rate": 9.62608695652174e-06,
1855
- "loss": 1.8166,
1856
- "step": 308
1857
- },
1858
- {
1859
- "epoch": 0.44,
1860
- "learning_rate": 9.624637681159421e-06,
1861
- "loss": 1.7956,
1862
- "step": 309
1863
- },
1864
- {
1865
- "epoch": 0.45,
1866
- "learning_rate": 9.623188405797102e-06,
1867
- "loss": 1.7903,
1868
- "step": 310
1869
- },
1870
- {
1871
- "epoch": 0.45,
1872
- "learning_rate": 9.621739130434783e-06,
1873
- "loss": 1.7935,
1874
- "step": 311
1875
- },
1876
- {
1877
- "epoch": 0.45,
1878
- "learning_rate": 9.620289855072464e-06,
1879
- "loss": 1.7804,
1880
- "step": 312
1881
- },
1882
- {
1883
- "epoch": 0.45,
1884
- "learning_rate": 9.618840579710147e-06,
1885
- "loss": 1.8251,
1886
- "step": 313
1887
- },
1888
- {
1889
- "epoch": 0.45,
1890
- "learning_rate": 9.617391304347828e-06,
1891
- "loss": 1.8077,
1892
- "step": 314
1893
- },
1894
- {
1895
- "epoch": 0.45,
1896
- "learning_rate": 9.615942028985507e-06,
1897
- "loss": 1.804,
1898
- "step": 315
1899
- },
1900
- {
1901
- "epoch": 0.45,
1902
- "learning_rate": 9.61449275362319e-06,
1903
- "loss": 1.8511,
1904
- "step": 316
1905
- },
1906
- {
1907
- "epoch": 0.46,
1908
- "learning_rate": 9.61304347826087e-06,
1909
- "loss": 1.7939,
1910
- "step": 317
1911
- },
1912
- {
1913
- "epoch": 0.46,
1914
- "learning_rate": 9.611594202898552e-06,
1915
- "loss": 1.8087,
1916
- "step": 318
1917
- },
1918
- {
1919
- "epoch": 0.46,
1920
- "learning_rate": 9.610144927536233e-06,
1921
- "loss": 1.808,
1922
- "step": 319
1923
- },
1924
- {
1925
- "epoch": 0.46,
1926
- "learning_rate": 9.608695652173914e-06,
1927
- "loss": 1.828,
1928
- "step": 320
1929
- },
1930
- {
1931
- "epoch": 0.46,
1932
- "learning_rate": 9.607246376811595e-06,
1933
- "loss": 1.7458,
1934
- "step": 321
1935
- },
1936
- {
1937
- "epoch": 0.46,
1938
- "learning_rate": 9.605797101449276e-06,
1939
- "loss": 1.8063,
1940
- "step": 322
1941
- },
1942
- {
1943
- "epoch": 0.46,
1944
- "learning_rate": 9.604347826086957e-06,
1945
- "loss": 1.7583,
1946
- "step": 323
1947
- },
1948
- {
1949
- "epoch": 0.47,
1950
- "learning_rate": 9.60289855072464e-06,
1951
- "loss": 1.7572,
1952
- "step": 324
1953
- },
1954
- {
1955
- "epoch": 0.47,
1956
- "learning_rate": 9.60144927536232e-06,
1957
- "loss": 1.7583,
1958
- "step": 325
1959
- },
1960
- {
1961
- "epoch": 0.47,
1962
- "learning_rate": 9.600000000000001e-06,
1963
- "loss": 1.7465,
1964
- "step": 326
1965
- },
1966
- {
1967
- "epoch": 0.47,
1968
- "learning_rate": 9.598550724637682e-06,
1969
- "loss": 1.7986,
1970
- "step": 327
1971
- },
1972
- {
1973
- "epoch": 0.47,
1974
- "learning_rate": 9.597101449275363e-06,
1975
- "loss": 1.7838,
1976
- "step": 328
1977
- },
1978
- {
1979
- "epoch": 0.47,
1980
- "learning_rate": 9.595652173913044e-06,
1981
- "loss": 1.8339,
1982
- "step": 329
1983
- },
1984
- {
1985
- "epoch": 0.47,
1986
- "learning_rate": 9.594202898550725e-06,
1987
- "loss": 1.7616,
1988
- "step": 330
1989
- },
1990
- {
1991
- "epoch": 0.48,
1992
- "learning_rate": 9.592753623188406e-06,
1993
- "loss": 1.8175,
1994
- "step": 331
1995
- },
1996
- {
1997
- "epoch": 0.48,
1998
- "learning_rate": 9.591304347826087e-06,
1999
- "loss": 1.7892,
2000
- "step": 332
2001
- },
2002
- {
2003
- "epoch": 0.48,
2004
- "learning_rate": 9.589855072463768e-06,
2005
- "loss": 1.8266,
2006
- "step": 333
2007
- },
2008
- {
2009
- "epoch": 0.48,
2010
- "learning_rate": 9.58840579710145e-06,
2011
- "loss": 1.7261,
2012
- "step": 334
2013
- },
2014
- {
2015
- "epoch": 0.48,
2016
- "learning_rate": 9.586956521739132e-06,
2017
- "loss": 1.7498,
2018
- "step": 335
2019
- },
2020
- {
2021
- "epoch": 0.48,
2022
- "learning_rate": 9.585507246376813e-06,
2023
- "loss": 1.7778,
2024
- "step": 336
2025
- },
2026
- {
2027
- "epoch": 0.48,
2028
- "learning_rate": 9.584057971014494e-06,
2029
- "loss": 1.8263,
2030
- "step": 337
2031
- },
2032
- {
2033
- "epoch": 0.49,
2034
- "learning_rate": 9.582608695652175e-06,
2035
- "loss": 1.9147,
2036
- "step": 338
2037
- },
2038
- {
2039
- "epoch": 0.49,
2040
- "learning_rate": 9.581159420289856e-06,
2041
- "loss": 1.7922,
2042
- "step": 339
2043
- },
2044
- {
2045
- "epoch": 0.49,
2046
- "learning_rate": 9.579710144927537e-06,
2047
- "loss": 1.8063,
2048
- "step": 340
2049
- },
2050
- {
2051
- "epoch": 0.49,
2052
- "learning_rate": 9.578260869565218e-06,
2053
- "loss": 1.7929,
2054
- "step": 341
2055
- },
2056
- {
2057
- "epoch": 0.49,
2058
- "learning_rate": 9.576811594202899e-06,
2059
- "loss": 1.788,
2060
- "step": 342
2061
- },
2062
- {
2063
- "epoch": 0.49,
2064
- "learning_rate": 9.575362318840582e-06,
2065
- "loss": 1.7505,
2066
- "step": 343
2067
- },
2068
- {
2069
- "epoch": 0.49,
2070
- "learning_rate": 9.573913043478261e-06,
2071
- "loss": 1.7945,
2072
- "step": 344
2073
- },
2074
- {
2075
- "epoch": 0.5,
2076
- "learning_rate": 9.572463768115942e-06,
2077
- "loss": 1.8055,
2078
- "step": 345
2079
- },
2080
- {
2081
- "epoch": 0.5,
2082
- "learning_rate": 9.571014492753625e-06,
2083
- "loss": 1.7758,
2084
- "step": 346
2085
- },
2086
- {
2087
- "epoch": 0.5,
2088
- "learning_rate": 9.569565217391306e-06,
2089
- "loss": 1.7891,
2090
- "step": 347
2091
- },
2092
- {
2093
- "epoch": 0.5,
2094
- "learning_rate": 9.568115942028987e-06,
2095
- "loss": 1.7642,
2096
- "step": 348
2097
- },
2098
- {
2099
- "epoch": 0.5,
2100
- "learning_rate": 9.566666666666668e-06,
2101
- "loss": 1.8232,
2102
- "step": 349
2103
- },
2104
- {
2105
- "epoch": 0.5,
2106
- "learning_rate": 9.565217391304349e-06,
2107
- "loss": 1.802,
2108
- "step": 350
2109
- },
2110
- {
2111
- "epoch": 0.51,
2112
- "learning_rate": 9.56376811594203e-06,
2113
- "loss": 1.7589,
2114
- "step": 351
2115
- },
2116
- {
2117
- "epoch": 0.51,
2118
- "learning_rate": 9.56231884057971e-06,
2119
- "loss": 1.7147,
2120
- "step": 352
2121
- },
2122
- {
2123
- "epoch": 0.51,
2124
- "learning_rate": 9.560869565217392e-06,
2125
- "loss": 1.7982,
2126
- "step": 353
2127
- },
2128
- {
2129
- "epoch": 0.51,
2130
- "learning_rate": 9.559420289855074e-06,
2131
- "loss": 1.7565,
2132
- "step": 354
2133
- },
2134
- {
2135
- "epoch": 0.51,
2136
- "learning_rate": 9.557971014492754e-06,
2137
- "loss": 1.7405,
2138
- "step": 355
2139
- },
2140
- {
2141
- "epoch": 0.51,
2142
- "learning_rate": 9.556521739130435e-06,
2143
- "loss": 1.7587,
2144
- "step": 356
2145
- },
2146
- {
2147
- "epoch": 0.51,
2148
- "learning_rate": 9.555072463768117e-06,
2149
- "loss": 1.7871,
2150
- "step": 357
2151
- },
2152
- {
2153
- "epoch": 0.52,
2154
- "learning_rate": 9.553623188405798e-06,
2155
- "loss": 1.7503,
2156
- "step": 358
2157
- },
2158
- {
2159
- "epoch": 0.52,
2160
- "learning_rate": 9.55217391304348e-06,
2161
- "loss": 1.7435,
2162
- "step": 359
2163
- },
2164
- {
2165
- "epoch": 0.52,
2166
- "learning_rate": 9.55072463768116e-06,
2167
- "loss": 1.7851,
2168
- "step": 360
2169
- },
2170
- {
2171
- "epoch": 0.52,
2172
- "learning_rate": 9.549275362318841e-06,
2173
- "loss": 1.7478,
2174
- "step": 361
2175
- },
2176
- {
2177
- "epoch": 0.52,
2178
- "learning_rate": 9.547826086956522e-06,
2179
- "loss": 1.82,
2180
- "step": 362
2181
- },
2182
- {
2183
- "epoch": 0.52,
2184
- "learning_rate": 9.546376811594203e-06,
2185
- "loss": 1.7634,
2186
- "step": 363
2187
- },
2188
- {
2189
- "epoch": 0.52,
2190
- "learning_rate": 9.544927536231884e-06,
2191
- "loss": 1.8127,
2192
- "step": 364
2193
- },
2194
- {
2195
- "epoch": 0.53,
2196
- "learning_rate": 9.543478260869567e-06,
2197
- "loss": 1.7303,
2198
- "step": 365
2199
- },
2200
- {
2201
- "epoch": 0.53,
2202
- "learning_rate": 9.542028985507246e-06,
2203
- "loss": 1.8087,
2204
- "step": 366
2205
- },
2206
- {
2207
- "epoch": 0.53,
2208
- "learning_rate": 9.540579710144927e-06,
2209
- "loss": 1.8442,
2210
- "step": 367
2211
- },
2212
- {
2213
- "epoch": 0.53,
2214
- "learning_rate": 9.53913043478261e-06,
2215
- "loss": 1.7595,
2216
- "step": 368
2217
- },
2218
- {
2219
- "epoch": 0.53,
2220
- "learning_rate": 9.537681159420291e-06,
2221
- "loss": 1.7638,
2222
- "step": 369
2223
- },
2224
- {
2225
- "epoch": 0.53,
2226
- "learning_rate": 9.536231884057972e-06,
2227
- "loss": 1.8031,
2228
- "step": 370
2229
- },
2230
- {
2231
- "epoch": 0.53,
2232
- "learning_rate": 9.534782608695653e-06,
2233
- "loss": 1.793,
2234
- "step": 371
2235
- },
2236
- {
2237
- "epoch": 0.54,
2238
- "learning_rate": 9.533333333333334e-06,
2239
- "loss": 1.7709,
2240
- "step": 372
2241
- },
2242
- {
2243
- "epoch": 0.54,
2244
- "learning_rate": 9.531884057971015e-06,
2245
- "loss": 1.7846,
2246
- "step": 373
2247
- },
2248
- {
2249
- "epoch": 0.54,
2250
- "learning_rate": 9.530434782608696e-06,
2251
- "loss": 1.7332,
2252
- "step": 374
2253
- },
2254
- {
2255
- "epoch": 0.54,
2256
- "learning_rate": 9.528985507246377e-06,
2257
- "loss": 1.7891,
2258
- "step": 375
2259
- },
2260
- {
2261
- "epoch": 0.54,
2262
- "learning_rate": 9.52753623188406e-06,
2263
- "loss": 1.7546,
2264
- "step": 376
2265
- },
2266
- {
2267
- "epoch": 0.54,
2268
- "learning_rate": 9.526086956521739e-06,
2269
- "loss": 1.7659,
2270
- "step": 377
2271
- },
2272
- {
2273
- "epoch": 0.54,
2274
- "learning_rate": 9.524637681159422e-06,
2275
- "loss": 1.8536,
2276
- "step": 378
2277
- },
2278
- {
2279
- "epoch": 0.55,
2280
- "learning_rate": 9.523188405797103e-06,
2281
- "loss": 1.7542,
2282
- "step": 379
2283
- },
2284
- {
2285
- "epoch": 0.55,
2286
- "learning_rate": 9.521739130434784e-06,
2287
- "loss": 1.8001,
2288
- "step": 380
2289
- },
2290
- {
2291
- "epoch": 0.55,
2292
- "learning_rate": 9.520289855072465e-06,
2293
- "loss": 1.7604,
2294
- "step": 381
2295
- },
2296
- {
2297
- "epoch": 0.55,
2298
- "learning_rate": 9.518840579710146e-06,
2299
- "loss": 1.7424,
2300
- "step": 382
2301
- },
2302
- {
2303
- "epoch": 0.55,
2304
- "learning_rate": 9.517391304347827e-06,
2305
- "loss": 1.778,
2306
- "step": 383
2307
- },
2308
- {
2309
- "epoch": 0.55,
2310
- "learning_rate": 9.515942028985508e-06,
2311
- "loss": 1.8946,
2312
- "step": 384
2313
- },
2314
- {
2315
- "epoch": 0.55,
2316
- "learning_rate": 9.514492753623189e-06,
2317
- "loss": 1.7935,
2318
- "step": 385
2319
- },
2320
- {
2321
- "epoch": 0.56,
2322
- "learning_rate": 9.51304347826087e-06,
2323
- "loss": 1.817,
2324
- "step": 386
2325
- },
2326
- {
2327
- "epoch": 0.56,
2328
- "learning_rate": 9.511594202898553e-06,
2329
- "loss": 1.754,
2330
- "step": 387
2331
- },
2332
- {
2333
- "epoch": 0.56,
2334
- "learning_rate": 9.510144927536232e-06,
2335
- "loss": 1.7728,
2336
- "step": 388
2337
- },
2338
- {
2339
- "epoch": 0.56,
2340
- "learning_rate": 9.508695652173915e-06,
2341
- "loss": 1.7988,
2342
- "step": 389
2343
- },
2344
- {
2345
- "epoch": 0.56,
2346
- "learning_rate": 9.507246376811596e-06,
2347
- "loss": 1.7612,
2348
- "step": 390
2349
- },
2350
- {
2351
- "epoch": 0.56,
2352
- "learning_rate": 9.505797101449275e-06,
2353
- "loss": 1.7944,
2354
- "step": 391
2355
- },
2356
- {
2357
- "epoch": 0.56,
2358
- "learning_rate": 9.504347826086958e-06,
2359
- "loss": 1.7624,
2360
- "step": 392
2361
- },
2362
- {
2363
- "epoch": 0.57,
2364
- "learning_rate": 9.502898550724639e-06,
2365
- "loss": 1.7135,
2366
- "step": 393
2367
- },
2368
- {
2369
- "epoch": 0.57,
2370
- "learning_rate": 9.50144927536232e-06,
2371
- "loss": 1.8313,
2372
- "step": 394
2373
- },
2374
- {
2375
- "epoch": 0.57,
2376
- "learning_rate": 9.5e-06,
2377
- "loss": 1.7822,
2378
- "step": 395
2379
- },
2380
- {
2381
- "epoch": 0.57,
2382
- "learning_rate": 9.498550724637682e-06,
2383
- "loss": 1.7591,
2384
- "step": 396
2385
- },
2386
- {
2387
- "epoch": 0.57,
2388
- "learning_rate": 9.497101449275363e-06,
2389
- "loss": 1.7854,
2390
- "step": 397
2391
- },
2392
- {
2393
- "epoch": 0.57,
2394
- "learning_rate": 9.495652173913045e-06,
2395
- "loss": 1.7905,
2396
- "step": 398
2397
- },
2398
- {
2399
- "epoch": 0.57,
2400
- "learning_rate": 9.494202898550725e-06,
2401
- "loss": 1.7267,
2402
- "step": 399
2403
- },
2404
- {
2405
- "epoch": 0.58,
2406
- "learning_rate": 9.492753623188407e-06,
2407
- "loss": 1.7959,
2408
- "step": 400
2409
- },
2410
- {
2411
- "epoch": 0.58,
2412
- "learning_rate": 9.491304347826088e-06,
2413
- "loss": 1.7904,
2414
- "step": 401
2415
- },
2416
- {
2417
- "epoch": 0.58,
2418
- "learning_rate": 9.489855072463768e-06,
2419
- "loss": 1.798,
2420
- "step": 402
2421
- },
2422
- {
2423
- "epoch": 0.58,
2424
- "learning_rate": 9.48840579710145e-06,
2425
- "loss": 1.7562,
2426
- "step": 403
2427
- },
2428
- {
2429
- "epoch": 0.58,
2430
- "learning_rate": 9.486956521739131e-06,
2431
- "loss": 1.7432,
2432
- "step": 404
2433
- },
2434
- {
2435
- "epoch": 0.58,
2436
- "learning_rate": 9.485507246376812e-06,
2437
- "loss": 1.7399,
2438
- "step": 405
2439
- },
2440
- {
2441
- "epoch": 0.58,
2442
- "learning_rate": 9.484057971014493e-06,
2443
- "loss": 1.834,
2444
- "step": 406
2445
- },
2446
- {
2447
- "epoch": 0.59,
2448
- "learning_rate": 9.482608695652174e-06,
2449
- "loss": 1.7601,
2450
- "step": 407
2451
- },
2452
- {
2453
- "epoch": 0.59,
2454
- "learning_rate": 9.481159420289855e-06,
2455
- "loss": 1.7044,
2456
- "step": 408
2457
- },
2458
- {
2459
- "epoch": 0.59,
2460
- "learning_rate": 9.479710144927538e-06,
2461
- "loss": 1.7983,
2462
- "step": 409
2463
- },
2464
- {
2465
- "epoch": 0.59,
2466
- "learning_rate": 9.478260869565217e-06,
2467
- "loss": 1.7584,
2468
- "step": 410
2469
- },
2470
- {
2471
- "epoch": 0.59,
2472
- "learning_rate": 9.4768115942029e-06,
2473
- "loss": 1.7515,
2474
- "step": 411
2475
- },
2476
- {
2477
- "epoch": 0.59,
2478
- "learning_rate": 9.475362318840581e-06,
2479
- "loss": 1.7249,
2480
- "step": 412
2481
- },
2482
- {
2483
- "epoch": 0.59,
2484
- "learning_rate": 9.473913043478262e-06,
2485
- "loss": 1.7837,
2486
- "step": 413
2487
- },
2488
- {
2489
- "epoch": 0.6,
2490
- "learning_rate": 9.472463768115943e-06,
2491
- "loss": 1.7713,
2492
- "step": 414
2493
- },
2494
- {
2495
- "epoch": 0.6,
2496
- "learning_rate": 9.471014492753624e-06,
2497
- "loss": 1.7265,
2498
- "step": 415
2499
- },
2500
- {
2501
- "epoch": 0.6,
2502
- "learning_rate": 9.469565217391305e-06,
2503
- "loss": 1.7714,
2504
- "step": 416
2505
- },
2506
- {
2507
- "epoch": 0.6,
2508
- "learning_rate": 9.468115942028986e-06,
2509
- "loss": 1.6978,
2510
- "step": 417
2511
- },
2512
- {
2513
- "epoch": 0.6,
2514
- "learning_rate": 9.466666666666667e-06,
2515
- "loss": 1.7585,
2516
- "step": 418
2517
- },
2518
- {
2519
- "epoch": 0.6,
2520
- "learning_rate": 9.46521739130435e-06,
2521
- "loss": 1.7676,
2522
- "step": 419
2523
- },
2524
- {
2525
- "epoch": 0.6,
2526
- "learning_rate": 9.46376811594203e-06,
2527
- "loss": 1.7695,
2528
- "step": 420
2529
- },
2530
- {
2531
- "epoch": 0.61,
2532
- "learning_rate": 9.46231884057971e-06,
2533
- "loss": 1.7101,
2534
- "step": 421
2535
- },
2536
- {
2537
- "epoch": 0.61,
2538
- "learning_rate": 9.460869565217393e-06,
2539
- "loss": 1.7459,
2540
- "step": 422
2541
- },
2542
- {
2543
- "epoch": 0.61,
2544
- "learning_rate": 9.459420289855074e-06,
2545
- "loss": 1.759,
2546
- "step": 423
2547
- },
2548
- {
2549
- "epoch": 0.61,
2550
- "learning_rate": 9.457971014492755e-06,
2551
- "loss": 1.7008,
2552
- "step": 424
2553
- },
2554
- {
2555
- "epoch": 0.61,
2556
- "learning_rate": 9.456521739130436e-06,
2557
- "loss": 1.7623,
2558
- "step": 425
2559
- },
2560
- {
2561
- "epoch": 0.61,
2562
- "learning_rate": 9.455072463768117e-06,
2563
- "loss": 1.7589,
2564
- "step": 426
2565
- },
2566
- {
2567
- "epoch": 0.61,
2568
- "learning_rate": 9.453623188405798e-06,
2569
- "loss": 1.6821,
2570
- "step": 427
2571
- },
2572
- {
2573
- "epoch": 0.62,
2574
- "learning_rate": 9.452173913043479e-06,
2575
- "loss": 1.7601,
2576
- "step": 428
2577
- },
2578
- {
2579
- "epoch": 0.62,
2580
- "learning_rate": 9.45072463768116e-06,
2581
- "loss": 1.6942,
2582
- "step": 429
2583
- },
2584
- {
2585
- "epoch": 0.62,
2586
- "learning_rate": 9.449275362318842e-06,
2587
- "loss": 1.6735,
2588
- "step": 430
2589
- },
2590
- {
2591
- "epoch": 0.62,
2592
- "learning_rate": 9.447826086956523e-06,
2593
- "loss": 1.6923,
2594
- "step": 431
2595
- },
2596
- {
2597
- "epoch": 0.62,
2598
- "learning_rate": 9.446376811594203e-06,
2599
- "loss": 1.643,
2600
- "step": 432
2601
- },
2602
- {
2603
- "epoch": 0.62,
2604
- "learning_rate": 9.444927536231885e-06,
2605
- "loss": 1.7404,
2606
- "step": 433
2607
- },
2608
- {
2609
- "epoch": 0.62,
2610
- "learning_rate": 9.443478260869566e-06,
2611
- "loss": 1.7223,
2612
- "step": 434
2613
- },
2614
- {
2615
- "epoch": 0.63,
2616
- "learning_rate": 9.442028985507247e-06,
2617
- "loss": 1.7114,
2618
- "step": 435
2619
- },
2620
- {
2621
- "epoch": 0.63,
2622
- "learning_rate": 9.440579710144928e-06,
2623
- "loss": 1.6646,
2624
- "step": 436
2625
- },
2626
- {
2627
- "epoch": 0.63,
2628
- "learning_rate": 9.43913043478261e-06,
2629
- "loss": 1.8709,
2630
- "step": 437
2631
- },
2632
- {
2633
- "epoch": 0.63,
2634
- "learning_rate": 9.43768115942029e-06,
2635
- "loss": 1.6551,
2636
- "step": 438
2637
- },
2638
- {
2639
- "epoch": 0.63,
2640
- "learning_rate": 9.436231884057971e-06,
2641
- "loss": 1.803,
2642
- "step": 439
2643
- },
2644
- {
2645
- "epoch": 0.63,
2646
- "learning_rate": 9.434782608695652e-06,
2647
- "loss": 1.7061,
2648
- "step": 440
2649
- },
2650
- {
2651
- "epoch": 0.63,
2652
- "learning_rate": 9.433333333333335e-06,
2653
- "loss": 1.7442,
2654
- "step": 441
2655
- },
2656
- {
2657
- "epoch": 0.64,
2658
- "learning_rate": 9.431884057971016e-06,
2659
- "loss": 1.5954,
2660
- "step": 442
2661
- },
2662
- {
2663
- "epoch": 0.64,
2664
- "learning_rate": 9.430434782608695e-06,
2665
- "loss": 1.873,
2666
- "step": 443
2667
- },
2668
- {
2669
- "epoch": 0.64,
2670
- "learning_rate": 9.428985507246378e-06,
2671
- "loss": 1.744,
2672
- "step": 444
2673
- },
2674
- {
2675
- "epoch": 0.64,
2676
- "learning_rate": 9.427536231884059e-06,
2677
- "loss": 1.7217,
2678
- "step": 445
2679
- },
2680
- {
2681
- "epoch": 0.64,
2682
- "learning_rate": 9.42608695652174e-06,
2683
- "loss": 1.8362,
2684
- "step": 446
2685
- },
2686
- {
2687
- "epoch": 0.64,
2688
- "learning_rate": 9.424637681159421e-06,
2689
- "loss": 1.5976,
2690
- "step": 447
2691
- },
2692
- {
2693
- "epoch": 0.64,
2694
- "learning_rate": 9.423188405797102e-06,
2695
- "loss": 1.7857,
2696
- "step": 448
2697
- },
2698
- {
2699
- "epoch": 0.65,
2700
- "learning_rate": 9.421739130434783e-06,
2701
- "loss": 1.8564,
2702
- "step": 449
2703
- },
2704
- {
2705
- "epoch": 0.65,
2706
- "learning_rate": 9.420289855072464e-06,
2707
- "loss": 1.6733,
2708
- "step": 450
2709
- },
2710
- {
2711
- "epoch": 0.65,
2712
- "learning_rate": 9.418840579710145e-06,
2713
- "loss": 1.7016,
2714
- "step": 451
2715
- },
2716
- {
2717
- "epoch": 0.65,
2718
- "learning_rate": 9.417391304347828e-06,
2719
- "loss": 1.6946,
2720
- "step": 452
2721
- },
2722
- {
2723
- "epoch": 0.65,
2724
- "learning_rate": 9.415942028985507e-06,
2725
- "loss": 1.7693,
2726
- "step": 453
2727
- },
2728
- {
2729
- "epoch": 0.65,
2730
- "learning_rate": 9.41449275362319e-06,
2731
- "loss": 1.9134,
2732
- "step": 454
2733
- },
2734
- {
2735
- "epoch": 0.65,
2736
- "learning_rate": 9.41304347826087e-06,
2737
- "loss": 1.8033,
2738
- "step": 455
2739
- },
2740
- {
2741
- "epoch": 0.66,
2742
- "learning_rate": 9.411594202898552e-06,
2743
- "loss": 1.8767,
2744
- "step": 456
2745
- },
2746
- {
2747
- "epoch": 0.66,
2748
- "learning_rate": 9.410144927536233e-06,
2749
- "loss": 1.8345,
2750
- "step": 457
2751
- },
2752
- {
2753
- "epoch": 0.66,
2754
- "learning_rate": 9.408695652173914e-06,
2755
- "loss": 1.7909,
2756
- "step": 458
2757
- },
2758
- {
2759
- "epoch": 0.66,
2760
- "learning_rate": 9.407246376811595e-06,
2761
- "loss": 1.7373,
2762
- "step": 459
2763
- },
2764
- {
2765
- "epoch": 0.66,
2766
- "learning_rate": 9.405797101449276e-06,
2767
- "loss": 1.7614,
2768
- "step": 460
2769
- },
2770
- {
2771
- "epoch": 0.66,
2772
- "learning_rate": 9.404347826086957e-06,
2773
- "loss": 1.7336,
2774
- "step": 461
2775
- },
2776
- {
2777
- "epoch": 0.66,
2778
- "learning_rate": 9.402898550724638e-06,
2779
- "loss": 1.7612,
2780
- "step": 462
2781
- },
2782
- {
2783
- "epoch": 0.67,
2784
- "learning_rate": 9.40144927536232e-06,
2785
- "loss": 1.6613,
2786
- "step": 463
2787
- },
2788
- {
2789
- "epoch": 0.67,
2790
- "learning_rate": 9.4e-06,
2791
- "loss": 1.6221,
2792
- "step": 464
2793
- },
2794
- {
2795
- "epoch": 0.67,
2796
- "learning_rate": 9.398550724637682e-06,
2797
- "loss": 1.6708,
2798
- "step": 465
2799
- },
2800
- {
2801
- "epoch": 0.67,
2802
- "learning_rate": 9.397101449275363e-06,
2803
- "loss": 1.7306,
2804
- "step": 466
2805
- },
2806
- {
2807
- "epoch": 0.67,
2808
- "learning_rate": 9.395652173913044e-06,
2809
- "loss": 1.6663,
2810
- "step": 467
2811
- },
2812
- {
2813
- "epoch": 0.67,
2814
- "learning_rate": 9.394202898550725e-06,
2815
- "loss": 1.6109,
2816
- "step": 468
2817
- },
2818
- {
2819
- "epoch": 0.67,
2820
- "learning_rate": 9.392753623188406e-06,
2821
- "loss": 1.7376,
2822
- "step": 469
2823
- },
2824
- {
2825
- "epoch": 0.68,
2826
- "learning_rate": 9.391304347826087e-06,
2827
- "loss": 1.6614,
2828
- "step": 470
2829
- },
2830
- {
2831
- "epoch": 0.68,
2832
- "learning_rate": 9.38985507246377e-06,
2833
- "loss": 1.7024,
2834
- "step": 471
2835
- },
2836
- {
2837
- "epoch": 0.68,
2838
- "learning_rate": 9.38840579710145e-06,
2839
- "loss": 1.7758,
2840
- "step": 472
2841
- },
2842
- {
2843
- "epoch": 0.68,
2844
- "learning_rate": 9.38695652173913e-06,
2845
- "loss": 1.8538,
2846
- "step": 473
2847
- },
2848
- {
2849
- "epoch": 0.68,
2850
- "learning_rate": 9.385507246376813e-06,
2851
- "loss": 1.7568,
2852
- "step": 474
2853
- },
2854
- {
2855
- "epoch": 0.68,
2856
- "learning_rate": 9.384057971014492e-06,
2857
- "loss": 1.671,
2858
- "step": 475
2859
- },
2860
- {
2861
- "epoch": 0.68,
2862
- "learning_rate": 9.382608695652175e-06,
2863
- "loss": 1.7339,
2864
- "step": 476
2865
- },
2866
- {
2867
- "epoch": 0.69,
2868
- "learning_rate": 9.381159420289856e-06,
2869
- "loss": 1.8321,
2870
- "step": 477
2871
- },
2872
- {
2873
- "epoch": 0.69,
2874
- "learning_rate": 9.379710144927537e-06,
2875
- "loss": 1.7613,
2876
- "step": 478
2877
- },
2878
- {
2879
- "epoch": 0.69,
2880
- "learning_rate": 9.378260869565218e-06,
2881
- "loss": 1.7558,
2882
- "step": 479
2883
- },
2884
- {
2885
- "epoch": 0.69,
2886
- "learning_rate": 9.3768115942029e-06,
2887
- "loss": 1.7601,
2888
- "step": 480
2889
- },
2890
- {
2891
- "epoch": 0.69,
2892
- "learning_rate": 9.37536231884058e-06,
2893
- "loss": 1.6581,
2894
- "step": 481
2895
- },
2896
- {
2897
- "epoch": 0.69,
2898
- "learning_rate": 9.373913043478263e-06,
2899
- "loss": 1.7532,
2900
- "step": 482
2901
- },
2902
- {
2903
- "epoch": 0.69,
2904
- "learning_rate": 9.372463768115942e-06,
2905
- "loss": 1.8625,
2906
- "step": 483
2907
- },
2908
- {
2909
- "epoch": 0.7,
2910
- "learning_rate": 9.371014492753623e-06,
2911
- "loss": 1.7552,
2912
- "step": 484
2913
- },
2914
- {
2915
- "epoch": 0.7,
2916
- "learning_rate": 9.369565217391306e-06,
2917
- "loss": 1.6593,
2918
- "step": 485
2919
- },
2920
- {
2921
- "epoch": 0.7,
2922
- "learning_rate": 9.368115942028985e-06,
2923
- "loss": 1.7272,
2924
- "step": 486
2925
- },
2926
- {
2927
- "epoch": 0.7,
2928
- "learning_rate": 9.366666666666668e-06,
2929
- "loss": 1.6921,
2930
- "step": 487
2931
- },
2932
- {
2933
- "epoch": 0.7,
2934
- "learning_rate": 9.365217391304349e-06,
2935
- "loss": 1.9005,
2936
- "step": 488
2937
- },
2938
- {
2939
- "epoch": 0.7,
2940
- "learning_rate": 9.36376811594203e-06,
2941
- "loss": 1.6615,
2942
- "step": 489
2943
- },
2944
- {
2945
- "epoch": 0.71,
2946
- "learning_rate": 9.362318840579711e-06,
2947
- "loss": 1.6557,
2948
- "step": 490
2949
- },
2950
- {
2951
- "epoch": 0.71,
2952
- "learning_rate": 9.360869565217392e-06,
2953
- "loss": 1.7617,
2954
- "step": 491
2955
- },
2956
- {
2957
- "epoch": 0.71,
2958
- "learning_rate": 9.359420289855073e-06,
2959
- "loss": 1.6262,
2960
- "step": 492
2961
- },
2962
- {
2963
- "epoch": 0.71,
2964
- "learning_rate": 9.357971014492756e-06,
2965
- "loss": 1.6038,
2966
- "step": 493
2967
- },
2968
- {
2969
- "epoch": 0.71,
2970
- "learning_rate": 9.356521739130435e-06,
2971
- "loss": 1.7017,
2972
- "step": 494
2973
- },
2974
- {
2975
- "epoch": 0.71,
2976
- "learning_rate": 9.355072463768116e-06,
2977
- "loss": 1.6771,
2978
- "step": 495
2979
- },
2980
- {
2981
- "epoch": 0.71,
2982
- "learning_rate": 9.353623188405799e-06,
2983
- "loss": 1.7926,
2984
- "step": 496
2985
- },
2986
- {
2987
- "epoch": 0.72,
2988
- "learning_rate": 9.352173913043478e-06,
2989
- "loss": 1.7765,
2990
- "step": 497
2991
- },
2992
- {
2993
- "epoch": 0.72,
2994
- "learning_rate": 9.35072463768116e-06,
2995
- "loss": 1.6132,
2996
- "step": 498
2997
- },
2998
- {
2999
- "epoch": 0.72,
3000
- "learning_rate": 9.349275362318842e-06,
3001
- "loss": 1.7929,
3002
- "step": 499
3003
- },
3004
- {
3005
- "epoch": 0.72,
3006
- "learning_rate": 9.347826086956523e-06,
3007
- "loss": 1.7747,
3008
- "step": 500
3009
- },
3010
- {
3011
- "epoch": 0.72,
3012
- "learning_rate": 9.346376811594204e-06,
3013
- "loss": 1.7371,
3014
- "step": 501
3015
- },
3016
- {
3017
- "epoch": 0.72,
3018
- "learning_rate": 9.344927536231885e-06,
3019
- "loss": 1.7765,
3020
- "step": 502
3021
- },
3022
- {
3023
- "epoch": 0.72,
3024
- "learning_rate": 9.343478260869566e-06,
3025
- "loss": 1.7343,
3026
- "step": 503
3027
- },
3028
- {
3029
- "epoch": 0.73,
3030
- "learning_rate": 9.342028985507248e-06,
3031
- "loss": 1.7641,
3032
- "step": 504
3033
- },
3034
- {
3035
- "epoch": 0.73,
3036
- "learning_rate": 9.340579710144928e-06,
3037
- "loss": 1.66,
3038
- "step": 505
3039
- },
3040
- {
3041
- "epoch": 0.73,
3042
- "learning_rate": 9.33913043478261e-06,
3043
- "loss": 1.4669,
3044
- "step": 506
3045
- },
3046
- {
3047
- "epoch": 0.73,
3048
- "learning_rate": 9.337681159420291e-06,
3049
- "loss": 1.6771,
3050
- "step": 507
3051
- },
3052
- {
3053
- "epoch": 0.73,
3054
- "learning_rate": 9.33623188405797e-06,
3055
- "loss": 1.7796,
3056
- "step": 508
3057
- },
3058
- {
3059
- "epoch": 0.73,
3060
- "learning_rate": 9.334782608695653e-06,
3061
- "loss": 1.6644,
3062
- "step": 509
3063
- },
3064
- {
3065
- "epoch": 0.73,
3066
- "learning_rate": 9.333333333333334e-06,
3067
- "loss": 1.6729,
3068
- "step": 510
3069
- },
3070
- {
3071
- "epoch": 0.74,
3072
- "learning_rate": 9.331884057971015e-06,
3073
- "loss": 1.5036,
3074
- "step": 511
3075
- },
3076
- {
3077
- "epoch": 0.74,
3078
- "learning_rate": 9.330434782608696e-06,
3079
- "loss": 1.7212,
3080
- "step": 512
3081
- },
3082
- {
3083
- "epoch": 0.74,
3084
- "learning_rate": 9.328985507246377e-06,
3085
- "loss": 1.7362,
3086
- "step": 513
3087
- },
3088
- {
3089
- "epoch": 0.74,
3090
- "learning_rate": 9.327536231884058e-06,
3091
- "loss": 1.7772,
3092
- "step": 514
3093
- },
3094
- {
3095
- "epoch": 0.74,
3096
- "learning_rate": 9.32608695652174e-06,
3097
- "loss": 1.6804,
3098
- "step": 515
3099
- },
3100
- {
3101
- "epoch": 0.74,
3102
- "learning_rate": 9.32463768115942e-06,
3103
- "loss": 1.6967,
3104
- "step": 516
3105
- },
3106
- {
3107
- "epoch": 0.74,
3108
- "learning_rate": 9.323188405797103e-06,
3109
- "loss": 1.9051,
3110
- "step": 517
3111
- },
3112
- {
3113
- "epoch": 0.75,
3114
- "learning_rate": 9.321739130434784e-06,
3115
- "loss": 1.7633,
3116
- "step": 518
3117
- },
3118
- {
3119
- "epoch": 0.75,
3120
- "learning_rate": 9.320289855072463e-06,
3121
- "loss": 1.5182,
3122
- "step": 519
3123
- },
3124
- {
3125
- "epoch": 0.75,
3126
- "learning_rate": 9.318840579710146e-06,
3127
- "loss": 1.7184,
3128
- "step": 520
3129
- },
3130
- {
3131
- "epoch": 0.75,
3132
- "learning_rate": 9.317391304347827e-06,
3133
- "loss": 2.2586,
3134
- "step": 521
3135
- },
3136
- {
3137
- "epoch": 0.75,
3138
- "learning_rate": 9.315942028985508e-06,
3139
- "loss": 1.5746,
3140
- "step": 522
3141
- },
3142
- {
3143
- "epoch": 0.75,
3144
- "learning_rate": 9.314492753623189e-06,
3145
- "loss": 1.8775,
3146
- "step": 523
3147
- },
3148
- {
3149
- "epoch": 0.75,
3150
- "learning_rate": 9.31304347826087e-06,
3151
- "loss": 1.607,
3152
- "step": 524
3153
- },
3154
- {
3155
- "epoch": 0.76,
3156
- "learning_rate": 9.311594202898551e-06,
3157
- "loss": 1.8892,
3158
- "step": 525
3159
- },
3160
- {
3161
- "epoch": 0.76,
3162
- "learning_rate": 9.310144927536232e-06,
3163
- "loss": 1.7163,
3164
- "step": 526
3165
- },
3166
- {
3167
- "epoch": 0.76,
3168
- "learning_rate": 9.308695652173913e-06,
3169
- "loss": 1.7406,
3170
- "step": 527
3171
- },
3172
- {
3173
- "epoch": 0.76,
3174
- "learning_rate": 9.307246376811596e-06,
3175
- "loss": 1.8209,
3176
- "step": 528
3177
- },
3178
- {
3179
- "epoch": 0.76,
3180
- "learning_rate": 9.305797101449277e-06,
3181
- "loss": 2.2019,
3182
- "step": 529
3183
- },
3184
- {
3185
- "epoch": 0.76,
3186
- "learning_rate": 9.304347826086956e-06,
3187
- "loss": 1.6532,
3188
- "step": 530
3189
- },
3190
- {
3191
- "epoch": 0.76,
3192
- "learning_rate": 9.302898550724639e-06,
3193
- "loss": 1.7642,
3194
- "step": 531
3195
- },
3196
- {
3197
- "epoch": 0.77,
3198
- "learning_rate": 9.30144927536232e-06,
3199
- "loss": 1.734,
3200
- "step": 532
3201
- },
3202
- {
3203
- "epoch": 0.77,
3204
- "learning_rate": 9.3e-06,
3205
- "loss": 1.7189,
3206
- "step": 533
3207
- },
3208
- {
3209
- "epoch": 0.77,
3210
- "learning_rate": 9.298550724637682e-06,
3211
- "loss": 1.6603,
3212
- "step": 534
3213
- },
3214
- {
3215
- "epoch": 0.77,
3216
- "learning_rate": 9.297101449275363e-06,
3217
- "loss": 1.8562,
3218
- "step": 535
3219
- },
3220
- {
3221
- "epoch": 0.77,
3222
- "learning_rate": 9.295652173913044e-06,
3223
- "loss": 1.5545,
3224
- "step": 536
3225
- },
3226
- {
3227
- "epoch": 0.77,
3228
- "learning_rate": 9.294202898550725e-06,
3229
- "loss": 1.7548,
3230
- "step": 537
3231
- },
3232
- {
3233
- "epoch": 0.77,
3234
- "learning_rate": 9.292753623188406e-06,
3235
- "loss": 1.6227,
3236
- "step": 538
3237
- },
3238
- {
3239
- "epoch": 0.78,
3240
- "learning_rate": 9.291304347826088e-06,
3241
- "loss": 1.5726,
3242
- "step": 539
3243
- },
3244
- {
3245
- "epoch": 0.78,
3246
- "learning_rate": 9.28985507246377e-06,
3247
- "loss": 1.8771,
3248
- "step": 540
3249
- },
3250
- {
3251
- "epoch": 0.78,
3252
- "learning_rate": 9.28840579710145e-06,
3253
- "loss": 1.773,
3254
- "step": 541
3255
- },
3256
- {
3257
- "epoch": 0.78,
3258
- "learning_rate": 9.286956521739131e-06,
3259
- "loss": 1.7309,
3260
- "step": 542
3261
- },
3262
- {
3263
- "epoch": 0.78,
3264
- "learning_rate": 9.285507246376812e-06,
3265
- "loss": 1.5423,
3266
- "step": 543
3267
- },
3268
- {
3269
- "epoch": 0.78,
3270
- "learning_rate": 9.284057971014493e-06,
3271
- "loss": 1.7325,
3272
- "step": 544
3273
- },
3274
- {
3275
- "epoch": 0.78,
3276
- "learning_rate": 9.282608695652174e-06,
3277
- "loss": 1.8245,
3278
- "step": 545
3279
- },
3280
- {
3281
- "epoch": 0.79,
3282
- "learning_rate": 9.281159420289855e-06,
3283
- "loss": 1.8336,
3284
- "step": 546
3285
- },
3286
- {
3287
- "epoch": 0.79,
3288
- "learning_rate": 9.279710144927536e-06,
3289
- "loss": 1.6275,
3290
- "step": 547
3291
- },
3292
- {
3293
- "epoch": 0.79,
3294
- "learning_rate": 9.278260869565217e-06,
3295
- "loss": 1.7493,
3296
- "step": 548
3297
- },
3298
- {
3299
- "epoch": 0.79,
3300
- "learning_rate": 9.276811594202898e-06,
3301
- "loss": 1.7878,
3302
- "step": 549
3303
- },
3304
- {
3305
- "epoch": 0.79,
3306
- "learning_rate": 9.275362318840581e-06,
3307
- "loss": 1.8985,
3308
- "step": 550
3309
- },
3310
- {
3311
- "epoch": 0.79,
3312
- "learning_rate": 9.273913043478262e-06,
3313
- "loss": 1.5902,
3314
- "step": 551
3315
- },
3316
- {
3317
- "epoch": 0.79,
3318
- "learning_rate": 9.272463768115943e-06,
3319
- "loss": 1.6755,
3320
- "step": 552
3321
- },
3322
- {
3323
- "epoch": 0.8,
3324
- "learning_rate": 9.271014492753624e-06,
3325
- "loss": 1.4542,
3326
- "step": 553
3327
- },
3328
- {
3329
- "epoch": 0.8,
3330
- "learning_rate": 9.269565217391305e-06,
3331
- "loss": 2.0015,
3332
- "step": 554
3333
- },
3334
- {
3335
- "epoch": 0.8,
3336
- "learning_rate": 9.268115942028986e-06,
3337
- "loss": 1.6533,
3338
- "step": 555
3339
- },
3340
- {
3341
- "epoch": 0.8,
3342
- "learning_rate": 9.266666666666667e-06,
3343
- "loss": 1.3897,
3344
- "step": 556
3345
- },
3346
- {
3347
- "epoch": 0.8,
3348
- "learning_rate": 9.265217391304348e-06,
3349
- "loss": 1.5342,
3350
- "step": 557
3351
- },
3352
- {
3353
- "epoch": 0.8,
3354
- "learning_rate": 9.263768115942031e-06,
3355
- "loss": 1.5419,
3356
- "step": 558
3357
- },
3358
- {
3359
- "epoch": 0.8,
3360
- "learning_rate": 9.26231884057971e-06,
3361
- "loss": 1.6568,
3362
- "step": 559
3363
- },
3364
- {
3365
- "epoch": 0.81,
3366
- "learning_rate": 9.260869565217391e-06,
3367
- "loss": 1.6842,
3368
- "step": 560
3369
- },
3370
- {
3371
- "epoch": 0.81,
3372
- "learning_rate": 9.259420289855074e-06,
3373
- "loss": 1.6922,
3374
- "step": 561
3375
- },
3376
- {
3377
- "epoch": 0.81,
3378
- "learning_rate": 9.257971014492755e-06,
3379
- "loss": 1.7124,
3380
- "step": 562
3381
- },
3382
- {
3383
- "epoch": 0.81,
3384
- "learning_rate": 9.256521739130436e-06,
3385
- "loss": 1.6837,
3386
- "step": 563
3387
- },
3388
- {
3389
- "epoch": 0.81,
3390
- "learning_rate": 9.255072463768117e-06,
3391
- "loss": 1.6708,
3392
- "step": 564
3393
- },
3394
- {
3395
- "epoch": 0.81,
3396
- "learning_rate": 9.253623188405798e-06,
3397
- "loss": 1.6237,
3398
- "step": 565
3399
- },
3400
- {
3401
- "epoch": 0.81,
3402
- "learning_rate": 9.252173913043479e-06,
3403
- "loss": 1.6164,
3404
- "step": 566
3405
- },
3406
- {
3407
- "epoch": 0.82,
3408
- "learning_rate": 9.25072463768116e-06,
3409
- "loss": 2.0735,
3410
- "step": 567
3411
- },
3412
- {
3413
- "epoch": 0.82,
3414
- "learning_rate": 9.249275362318841e-06,
3415
- "loss": 1.7095,
3416
- "step": 568
3417
- },
3418
- {
3419
- "epoch": 0.82,
3420
- "learning_rate": 9.247826086956524e-06,
3421
- "loss": 1.6885,
3422
- "step": 569
3423
- },
3424
- {
3425
- "epoch": 0.82,
3426
- "learning_rate": 9.246376811594203e-06,
3427
- "loss": 1.6518,
3428
- "step": 570
3429
- },
3430
- {
3431
- "epoch": 0.82,
3432
- "learning_rate": 9.244927536231884e-06,
3433
- "loss": 1.6327,
3434
- "step": 571
3435
- },
3436
- {
3437
- "epoch": 0.82,
3438
- "learning_rate": 9.243478260869567e-06,
3439
- "loss": 1.6598,
3440
- "step": 572
3441
- },
3442
- {
3443
- "epoch": 0.82,
3444
- "learning_rate": 9.242028985507248e-06,
3445
- "loss": 1.6891,
3446
- "step": 573
3447
- },
3448
- {
3449
- "epoch": 0.83,
3450
- "learning_rate": 9.240579710144929e-06,
3451
- "loss": 1.6103,
3452
- "step": 574
3453
- },
3454
- {
3455
- "epoch": 0.83,
3456
- "learning_rate": 9.23913043478261e-06,
3457
- "loss": 1.5785,
3458
- "step": 575
3459
- },
3460
- {
3461
- "epoch": 0.83,
3462
- "learning_rate": 9.23768115942029e-06,
3463
- "loss": 1.9188,
3464
- "step": 576
3465
- },
3466
- {
3467
- "epoch": 0.83,
3468
- "learning_rate": 9.236231884057972e-06,
3469
- "loss": 1.575,
3470
- "step": 577
3471
- },
3472
- {
3473
- "epoch": 0.83,
3474
- "learning_rate": 9.234782608695653e-06,
3475
- "loss": 2.0226,
3476
- "step": 578
3477
- },
3478
- {
3479
- "epoch": 0.83,
3480
- "learning_rate": 9.233333333333334e-06,
3481
- "loss": 1.6416,
3482
- "step": 579
3483
- },
3484
- {
3485
- "epoch": 0.83,
3486
- "learning_rate": 9.231884057971016e-06,
3487
- "loss": 1.7377,
3488
- "step": 580
3489
- },
3490
- {
3491
- "epoch": 0.84,
3492
- "learning_rate": 9.230434782608696e-06,
3493
- "loss": 1.5323,
3494
- "step": 581
3495
- },
3496
- {
3497
- "epoch": 0.84,
3498
- "learning_rate": 9.228985507246377e-06,
3499
- "loss": 1.6688,
3500
- "step": 582
3501
- },
3502
- {
3503
- "epoch": 0.84,
3504
- "learning_rate": 9.22753623188406e-06,
3505
- "loss": 1.6499,
3506
- "step": 583
3507
- },
3508
- {
3509
- "epoch": 0.84,
3510
- "learning_rate": 9.22608695652174e-06,
3511
- "loss": 1.6245,
3512
- "step": 584
3513
- },
3514
- {
3515
- "epoch": 0.84,
3516
- "learning_rate": 9.224637681159421e-06,
3517
- "loss": 1.7317,
3518
- "step": 585
3519
- },
3520
- {
3521
- "epoch": 0.84,
3522
- "learning_rate": 9.223188405797102e-06,
3523
- "loss": 1.6601,
3524
- "step": 586
3525
- },
3526
- {
3527
- "epoch": 0.84,
3528
- "learning_rate": 9.221739130434783e-06,
3529
- "loss": 1.6956,
3530
- "step": 587
3531
- },
3532
- {
3533
- "epoch": 0.85,
3534
- "learning_rate": 9.220289855072464e-06,
3535
- "loss": 1.6712,
3536
- "step": 588
3537
- },
3538
- {
3539
- "epoch": 0.85,
3540
- "learning_rate": 9.218840579710145e-06,
3541
- "loss": 1.6764,
3542
- "step": 589
3543
- },
3544
- {
3545
- "epoch": 0.85,
3546
- "learning_rate": 9.217391304347826e-06,
3547
- "loss": 1.7504,
3548
- "step": 590
3549
- },
3550
- {
3551
- "epoch": 0.85,
3552
- "learning_rate": 9.215942028985509e-06,
3553
- "loss": 1.6428,
3554
- "step": 591
3555
- },
3556
- {
3557
- "epoch": 0.85,
3558
- "learning_rate": 9.214492753623188e-06,
3559
- "loss": 1.9458,
3560
- "step": 592
3561
- },
3562
- {
3563
- "epoch": 0.85,
3564
- "learning_rate": 9.213043478260871e-06,
3565
- "loss": 1.6619,
3566
- "step": 593
3567
- },
3568
- {
3569
- "epoch": 0.85,
3570
- "learning_rate": 9.211594202898552e-06,
3571
- "loss": 1.5026,
3572
- "step": 594
3573
- },
3574
- {
3575
- "epoch": 0.86,
3576
- "learning_rate": 9.210144927536233e-06,
3577
- "loss": 1.9632,
3578
- "step": 595
3579
- },
3580
- {
3581
- "epoch": 0.86,
3582
- "learning_rate": 9.208695652173914e-06,
3583
- "loss": 1.8338,
3584
- "step": 596
3585
- },
3586
- {
3587
- "epoch": 0.86,
3588
- "learning_rate": 9.207246376811595e-06,
3589
- "loss": 1.5195,
3590
- "step": 597
3591
- },
3592
- {
3593
- "epoch": 0.86,
3594
- "learning_rate": 9.205797101449276e-06,
3595
- "loss": 1.9442,
3596
- "step": 598
3597
- },
3598
- {
3599
- "epoch": 0.86,
3600
- "learning_rate": 9.204347826086957e-06,
3601
- "loss": 1.6933,
3602
- "step": 599
3603
- },
3604
- {
3605
- "epoch": 0.86,
3606
- "learning_rate": 9.202898550724638e-06,
3607
- "loss": 1.6615,
3608
- "step": 600
3609
- },
3610
- {
3611
- "epoch": 0.86,
3612
- "learning_rate": 9.201449275362319e-06,
3613
- "loss": 1.3086,
3614
- "step": 601
3615
- },
3616
- {
3617
- "epoch": 0.87,
3618
- "learning_rate": 9.200000000000002e-06,
3619
- "loss": 1.6395,
3620
- "step": 602
3621
- },
3622
- {
3623
- "epoch": 0.87,
3624
- "learning_rate": 9.198550724637681e-06,
3625
- "loss": 1.692,
3626
- "step": 603
3627
- },
3628
- {
3629
- "epoch": 0.87,
3630
- "learning_rate": 9.197101449275364e-06,
3631
- "loss": 1.3012,
3632
- "step": 604
3633
- },
3634
- {
3635
- "epoch": 0.87,
3636
- "learning_rate": 9.195652173913045e-06,
3637
- "loss": 1.4745,
3638
- "step": 605
3639
- },
3640
- {
3641
- "epoch": 0.87,
3642
- "learning_rate": 9.194202898550726e-06,
3643
- "loss": 1.665,
3644
- "step": 606
3645
- },
3646
- {
3647
- "epoch": 0.87,
3648
- "learning_rate": 9.192753623188407e-06,
3649
- "loss": 1.9095,
3650
- "step": 607
3651
- },
3652
- {
3653
- "epoch": 0.87,
3654
- "learning_rate": 9.191304347826088e-06,
3655
- "loss": 1.9521,
3656
- "step": 608
3657
- },
3658
- {
3659
- "epoch": 0.88,
3660
- "learning_rate": 9.189855072463769e-06,
3661
- "loss": 1.7353,
3662
- "step": 609
3663
- },
3664
- {
3665
- "epoch": 0.88,
3666
- "learning_rate": 9.18840579710145e-06,
3667
- "loss": 1.6643,
3668
- "step": 610
3669
- },
3670
- {
3671
- "epoch": 0.88,
3672
- "learning_rate": 9.18695652173913e-06,
3673
- "loss": 1.4785,
3674
- "step": 611
3675
- },
3676
- {
3677
- "epoch": 0.88,
3678
- "learning_rate": 9.185507246376812e-06,
3679
- "loss": 1.6211,
3680
- "step": 612
3681
- },
3682
- {
3683
- "epoch": 0.88,
3684
- "learning_rate": 9.184057971014494e-06,
3685
- "loss": 1.9069,
3686
- "step": 613
3687
- },
3688
- {
3689
- "epoch": 0.88,
3690
- "learning_rate": 9.182608695652174e-06,
3691
- "loss": 1.7239,
3692
- "step": 614
3693
- },
3694
- {
3695
- "epoch": 0.88,
3696
- "learning_rate": 9.181159420289856e-06,
3697
- "loss": 1.918,
3698
- "step": 615
3699
- },
3700
- {
3701
- "epoch": 0.89,
3702
- "learning_rate": 9.179710144927537e-06,
3703
- "loss": 1.3954,
3704
- "step": 616
3705
- },
3706
- {
3707
- "epoch": 0.89,
3708
- "learning_rate": 9.178260869565218e-06,
3709
- "loss": 1.6497,
3710
- "step": 617
3711
- },
3712
- {
3713
- "epoch": 0.89,
3714
- "learning_rate": 9.1768115942029e-06,
3715
- "loss": 1.7112,
3716
- "step": 618
3717
- },
3718
- {
3719
- "epoch": 0.89,
3720
- "learning_rate": 9.17536231884058e-06,
3721
- "loss": 1.3031,
3722
- "step": 619
3723
- },
3724
- {
3725
- "epoch": 0.89,
3726
- "learning_rate": 9.173913043478261e-06,
3727
- "loss": 1.6014,
3728
- "step": 620
3729
- },
3730
- {
3731
- "epoch": 0.89,
3732
- "learning_rate": 9.172463768115942e-06,
3733
- "loss": 1.5809,
3734
- "step": 621
3735
- },
3736
- {
3737
- "epoch": 0.89,
3738
- "learning_rate": 9.171014492753623e-06,
3739
- "loss": 1.6354,
3740
- "step": 622
3741
- },
3742
- {
3743
- "epoch": 0.9,
3744
- "learning_rate": 9.169565217391304e-06,
3745
- "loss": 1.5894,
3746
- "step": 623
3747
- },
3748
- {
3749
- "epoch": 0.9,
3750
- "learning_rate": 9.168115942028987e-06,
3751
- "loss": 1.5135,
3752
- "step": 624
3753
- },
3754
- {
3755
- "epoch": 0.9,
3756
- "learning_rate": 9.166666666666666e-06,
3757
- "loss": 1.802,
3758
- "step": 625
3759
- },
3760
- {
3761
- "epoch": 0.9,
3762
- "learning_rate": 9.165217391304349e-06,
3763
- "loss": 1.8681,
3764
- "step": 626
3765
- },
3766
- {
3767
- "epoch": 0.9,
3768
- "learning_rate": 9.16376811594203e-06,
3769
- "loss": 1.3531,
3770
- "step": 627
3771
- },
3772
- {
3773
- "epoch": 0.9,
3774
- "learning_rate": 9.162318840579711e-06,
3775
- "loss": 1.4468,
3776
- "step": 628
3777
- },
3778
- {
3779
- "epoch": 0.91,
3780
- "learning_rate": 9.160869565217392e-06,
3781
- "loss": 1.6508,
3782
- "step": 629
3783
- },
3784
- {
3785
- "epoch": 0.91,
3786
- "learning_rate": 9.159420289855073e-06,
3787
- "loss": 1.2979,
3788
- "step": 630
3789
- },
3790
- {
3791
- "epoch": 0.91,
3792
- "learning_rate": 9.157971014492754e-06,
3793
- "loss": 1.7596,
3794
- "step": 631
3795
- },
3796
- {
3797
- "epoch": 0.91,
3798
- "learning_rate": 9.156521739130435e-06,
3799
- "loss": 1.7862,
3800
- "step": 632
3801
- },
3802
- {
3803
- "epoch": 0.91,
3804
- "learning_rate": 9.155072463768116e-06,
3805
- "loss": 1.7375,
3806
- "step": 633
3807
- },
3808
- {
3809
- "epoch": 0.91,
3810
- "learning_rate": 9.153623188405799e-06,
3811
- "loss": 1.6296,
3812
- "step": 634
3813
- },
3814
- {
3815
- "epoch": 0.91,
3816
- "learning_rate": 9.15217391304348e-06,
3817
- "loss": 1.8474,
3818
- "step": 635
3819
- },
3820
- {
3821
- "epoch": 0.92,
3822
- "learning_rate": 9.150724637681159e-06,
3823
- "loss": 1.5052,
3824
- "step": 636
3825
- },
3826
- {
3827
- "epoch": 0.92,
3828
- "learning_rate": 9.149275362318842e-06,
3829
- "loss": 1.6135,
3830
- "step": 637
3831
- },
3832
- {
3833
- "epoch": 0.92,
3834
- "learning_rate": 9.147826086956523e-06,
3835
- "loss": 1.7252,
3836
- "step": 638
3837
- },
3838
- {
3839
- "epoch": 0.92,
3840
- "learning_rate": 9.146376811594204e-06,
3841
- "loss": 1.7536,
3842
- "step": 639
3843
- },
3844
- {
3845
- "epoch": 0.92,
3846
- "learning_rate": 9.144927536231885e-06,
3847
- "loss": 1.469,
3848
- "step": 640
3849
- },
3850
- {
3851
- "epoch": 0.92,
3852
- "learning_rate": 9.143478260869566e-06,
3853
- "loss": 1.6801,
3854
- "step": 641
3855
- },
3856
- {
3857
- "epoch": 0.92,
3858
- "learning_rate": 9.142028985507247e-06,
3859
- "loss": 1.6273,
3860
- "step": 642
3861
- },
3862
- {
3863
- "epoch": 0.93,
3864
- "learning_rate": 9.140579710144928e-06,
3865
- "loss": 1.6722,
3866
- "step": 643
3867
- },
3868
- {
3869
- "epoch": 0.93,
3870
- "learning_rate": 9.139130434782609e-06,
3871
- "loss": 1.7045,
3872
- "step": 644
3873
- },
3874
- {
3875
- "epoch": 0.93,
3876
- "learning_rate": 9.137681159420292e-06,
3877
- "loss": 1.4982,
3878
- "step": 645
3879
- },
3880
- {
3881
- "epoch": 0.93,
3882
- "learning_rate": 9.136231884057973e-06,
3883
- "loss": 1.6666,
3884
- "step": 646
3885
- },
3886
- {
3887
- "epoch": 0.93,
3888
- "learning_rate": 9.134782608695652e-06,
3889
- "loss": 1.4154,
3890
- "step": 647
3891
- },
3892
- {
3893
- "epoch": 0.93,
3894
- "learning_rate": 9.133333333333335e-06,
3895
- "loss": 1.4674,
3896
- "step": 648
3897
- },
3898
- {
3899
- "epoch": 0.93,
3900
- "learning_rate": 9.131884057971016e-06,
3901
- "loss": 1.6787,
3902
- "step": 649
3903
- },
3904
- {
3905
- "epoch": 0.94,
3906
- "learning_rate": 9.130434782608697e-06,
3907
- "loss": 1.7374,
3908
- "step": 650
3909
- },
3910
- {
3911
- "epoch": 0.94,
3912
- "learning_rate": 9.128985507246378e-06,
3913
- "loss": 2.0465,
3914
- "step": 651
3915
- },
3916
- {
3917
- "epoch": 0.94,
3918
- "learning_rate": 9.127536231884059e-06,
3919
- "loss": 1.6424,
3920
- "step": 652
3921
- },
3922
- {
3923
- "epoch": 0.94,
3924
- "learning_rate": 9.12608695652174e-06,
3925
- "loss": 1.6249,
3926
- "step": 653
3927
- },
3928
- {
3929
- "epoch": 0.94,
3930
- "learning_rate": 9.12463768115942e-06,
3931
- "loss": 1.6703,
3932
- "step": 654
3933
- },
3934
- {
3935
- "epoch": 0.94,
3936
- "learning_rate": 9.123188405797102e-06,
3937
- "loss": 1.8832,
3938
- "step": 655
3939
- },
3940
- {
3941
- "epoch": 0.94,
3942
- "learning_rate": 9.121739130434784e-06,
3943
- "loss": 1.6985,
3944
- "step": 656
3945
- },
3946
- {
3947
- "epoch": 0.95,
3948
- "learning_rate": 9.120289855072465e-06,
3949
- "loss": 1.9327,
3950
- "step": 657
3951
- },
3952
- {
3953
- "epoch": 0.95,
3954
- "learning_rate": 9.118840579710145e-06,
3955
- "loss": 1.6431,
3956
- "step": 658
3957
- },
3958
- {
3959
- "epoch": 0.95,
3960
- "learning_rate": 9.117391304347827e-06,
3961
- "loss": 1.3707,
3962
- "step": 659
3963
- },
3964
- {
3965
- "epoch": 0.95,
3966
- "learning_rate": 9.115942028985508e-06,
3967
- "loss": 1.671,
3968
- "step": 660
3969
- },
3970
- {
3971
- "epoch": 0.95,
3972
- "learning_rate": 9.11449275362319e-06,
3973
- "loss": 1.6511,
3974
- "step": 661
3975
- },
3976
- {
3977
- "epoch": 0.95,
3978
- "learning_rate": 9.11304347826087e-06,
3979
- "loss": 2.3661,
3980
- "step": 662
3981
- },
3982
- {
3983
- "epoch": 0.95,
3984
- "learning_rate": 9.111594202898551e-06,
3985
- "loss": 1.4736,
3986
- "step": 663
3987
- },
3988
- {
3989
- "epoch": 0.96,
3990
- "learning_rate": 9.110144927536232e-06,
3991
- "loss": 1.702,
3992
- "step": 664
3993
- },
3994
- {
3995
- "epoch": 0.96,
3996
- "learning_rate": 9.108695652173913e-06,
3997
- "loss": 1.6404,
3998
- "step": 665
3999
- },
4000
- {
4001
- "epoch": 0.96,
4002
- "learning_rate": 9.107246376811594e-06,
4003
- "loss": 1.7918,
4004
- "step": 666
4005
- },
4006
- {
4007
- "epoch": 0.96,
4008
- "learning_rate": 9.105797101449277e-06,
4009
- "loss": 1.6485,
4010
- "step": 667
4011
- },
4012
- {
4013
- "epoch": 0.96,
4014
- "learning_rate": 9.104347826086958e-06,
4015
- "loss": 1.6458,
4016
- "step": 668
4017
- },
4018
- {
4019
- "epoch": 0.96,
4020
- "learning_rate": 9.102898550724639e-06,
4021
- "loss": 1.73,
4022
- "step": 669
4023
- },
4024
- {
4025
- "epoch": 0.96,
4026
- "learning_rate": 9.10144927536232e-06,
4027
- "loss": 1.6779,
4028
- "step": 670
4029
- },
4030
- {
4031
- "epoch": 0.97,
4032
- "learning_rate": 9.100000000000001e-06,
4033
- "loss": 1.7368,
4034
- "step": 671
4035
- },
4036
- {
4037
- "epoch": 0.97,
4038
- "learning_rate": 9.098550724637682e-06,
4039
- "loss": 1.6192,
4040
- "step": 672
4041
- },
4042
- {
4043
- "epoch": 0.97,
4044
- "learning_rate": 9.097101449275363e-06,
4045
- "loss": 1.6573,
4046
- "step": 673
4047
- },
4048
- {
4049
- "epoch": 0.97,
4050
- "learning_rate": 9.095652173913044e-06,
4051
- "loss": 1.6685,
4052
- "step": 674
4053
- },
4054
- {
4055
- "epoch": 0.97,
4056
- "learning_rate": 9.094202898550725e-06,
4057
- "loss": 1.6459,
4058
- "step": 675
4059
- },
4060
- {
4061
- "epoch": 0.97,
4062
- "learning_rate": 9.092753623188406e-06,
4063
- "loss": 1.96,
4064
- "step": 676
4065
- },
4066
- {
4067
- "epoch": 0.97,
4068
- "learning_rate": 9.091304347826087e-06,
4069
- "loss": 1.2422,
4070
- "step": 677
4071
- },
4072
- {
4073
- "epoch": 0.98,
4074
- "learning_rate": 9.08985507246377e-06,
4075
- "loss": 1.2432,
4076
- "step": 678
4077
- },
4078
- {
4079
- "epoch": 0.98,
4080
- "learning_rate": 9.08840579710145e-06,
4081
- "loss": 2.4282,
4082
- "step": 679
4083
- },
4084
- {
4085
- "epoch": 0.98,
4086
- "learning_rate": 9.086956521739132e-06,
4087
- "loss": 1.651,
4088
- "step": 680
4089
- },
4090
- {
4091
- "epoch": 0.98,
4092
- "learning_rate": 9.085507246376813e-06,
4093
- "loss": 1.6602,
4094
- "step": 681
4095
- },
4096
- {
4097
- "epoch": 0.98,
4098
- "learning_rate": 9.084057971014494e-06,
4099
- "loss": 1.4327,
4100
- "step": 682
4101
- },
4102
- {
4103
- "epoch": 0.98,
4104
- "learning_rate": 9.082608695652175e-06,
4105
- "loss": 1.4728,
4106
- "step": 683
4107
- },
4108
- {
4109
- "epoch": 0.98,
4110
- "learning_rate": 9.081159420289856e-06,
4111
- "loss": 1.677,
4112
- "step": 684
4113
- },
4114
- {
4115
- "epoch": 0.99,
4116
- "learning_rate": 9.079710144927537e-06,
4117
- "loss": 1.7016,
4118
- "step": 685
4119
- },
4120
- {
4121
- "epoch": 0.99,
4122
- "learning_rate": 9.07826086956522e-06,
4123
- "loss": 1.7507,
4124
- "step": 686
4125
- },
4126
- {
4127
- "epoch": 0.99,
4128
- "learning_rate": 9.076811594202899e-06,
4129
- "loss": 1.5511,
4130
- "step": 687
4131
- },
4132
- {
4133
- "epoch": 0.99,
4134
- "learning_rate": 9.07536231884058e-06,
4135
- "loss": 1.4525,
4136
- "step": 688
4137
- },
4138
- {
4139
- "epoch": 0.99,
4140
- "learning_rate": 9.073913043478262e-06,
4141
- "loss": 1.6997,
4142
- "step": 689
4143
- },
4144
- {
4145
- "epoch": 0.99,
4146
- "learning_rate": 9.072463768115943e-06,
4147
- "loss": 1.6878,
4148
- "step": 690
4149
- },
4150
- {
4151
- "epoch": 0.99,
4152
- "learning_rate": 9.071014492753624e-06,
4153
- "loss": 1.6826,
4154
- "step": 691
4155
- },
4156
- {
4157
- "epoch": 1.0,
4158
- "learning_rate": 9.069565217391305e-06,
4159
- "loss": 1.4774,
4160
- "step": 692
4161
- },
4162
- {
4163
- "epoch": 1.0,
4164
- "learning_rate": 9.068115942028986e-06,
4165
- "loss": 1.7614,
4166
- "step": 693
4167
- },
4168
- {
4169
- "epoch": 1.0,
4170
- "learning_rate": 9.066666666666667e-06,
4171
- "loss": 1.6491,
4172
- "step": 694
4173
- },
4174
- {
4175
- "epoch": 1.0,
4176
- "learning_rate": 9.065217391304348e-06,
4177
- "loss": 1.3832,
4178
- "step": 695
4179
- },
4180
- {
4181
- "epoch": 1.0,
4182
- "eval_accuracy": 0.3107913669064748,
4183
- "eval_loss": 1.560390591621399,
4184
- "eval_roc_auc": 0.7616650252630864,
4185
- "eval_runtime": 84.9159,
4186
- "eval_samples_per_second": 8.185,
4187
- "eval_steps_per_second": 2.049,
4188
- "step": 695
4189
- }
4190
- ],
4191
- "max_steps": 6950,
4192
- "num_train_epochs": 10,
4193
- "total_flos": 2.01838354884096e+17,
4194
- "trial_name": null,
4195
- "trial_params": null
4196
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-695/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e586ffec83af94e0cf9ea31750e6c3ca1bf1ee016bdd398b7fe339f74b71c58
3
- size 3567