lemms commited on
Commit
53beb3c
·
verified ·
1 Parent(s): 3b6973d

Delete llm\models\small-extended-9k\training_log.json with huggingface_hub

Browse files
llm//models//small-extended-9k//training_log.json DELETED
@@ -1,812 +0,0 @@
1
- [
2
- {
3
- "step": 100,
4
- "loss": 7.657252192497253,
5
- "perplexity": 2115.935250373028,
6
- "learning_rate": 0.00015150000000000019,
7
- "step_time": 9.368009328842163,
8
- "tokens_per_second": 109.30817466708918,
9
- "memory_mb": 756.6015625
10
- },
11
- {
12
- "step": 200,
13
- "loss": 7.487581491470337,
14
- "perplexity": 1785.7280665447065,
15
- "learning_rate": 0.0002999999999999999,
16
- "step_time": 10.94300365447998,
17
- "tokens_per_second": 93.57577063229641,
18
- "memory_mb": 730.99609375
19
- },
20
- {
21
- "step": 300,
22
- "loss": 7.163171410560608,
23
- "perplexity": 1290.9987344513497,
24
- "learning_rate": 0.00029794904665665113,
25
- "step_time": 8.949450016021729,
26
- "tokens_per_second": 114.42043904002891,
27
- "memory_mb": 733.89453125
28
- },
29
- {
30
- "step": 400,
31
- "loss": 6.677380561828613,
32
- "perplexity": 794.2359329078598,
33
- "learning_rate": 0.00029185850380610337,
34
- "step_time": 8.572781324386597,
35
- "tokens_per_second": 119.44781527169884,
36
- "memory_mb": 827.69140625
37
- },
38
- {
39
- "step": 500,
40
- "loss": 6.8126842975616455,
41
- "perplexity": 909.3083881764071,
42
- "learning_rate": 0.0002819134295109075,
43
- "step_time": 8.801953315734863,
44
- "tokens_per_second": 116.33781312716582,
45
- "memory_mb": 849.21484375
46
- },
47
- {
48
- "step": 600,
49
- "loss": 6.901162624359131,
50
- "perplexity": 993.4290292468936,
51
- "learning_rate": 0.0002684159998210713,
52
- "step_time": 8.660848379135132,
53
- "tokens_per_second": 118.23322094714423,
54
- "memory_mb": 734.16015625
55
- },
56
- {
57
- "step": 700,
58
- "loss": 6.6995872259140015,
59
- "perplexity": 812.0705542959239,
60
- "learning_rate": 0.0002517763273076916,
61
- "step_time": 9.10423469543457,
62
- "tokens_per_second": 112.47513209578146,
63
- "memory_mb": 734.64453125
64
- },
65
- {
66
- "step": 800,
67
- "loss": 6.729204297065735,
68
- "perplexity": 836.4814103649661,
69
- "learning_rate": 0.00023250000000000793,
70
- "step_time": 8.646829605102539,
71
- "tokens_per_second": 118.42490794495734,
72
- "memory_mb": 733.84765625
73
- },
74
- {
75
- "step": 900,
76
- "loss": 6.801577568054199,
77
- "perplexity": 899.2648246887062,
78
- "learning_rate": 0.00021117271934897237,
79
- "step_time": 8.66753602027893,
80
- "tokens_per_second": 118.14199532649263,
81
- "memory_mb": 839.50390625
82
- },
83
- {
84
- "step": 1000,
85
- "loss": 6.5149312019348145,
86
- "perplexity": 675.1475110828569,
87
- "learning_rate": 0.00018844250398504186,
88
- "step_time": 9.189276933670044,
89
- "tokens_per_second": 111.43423006961567,
90
- "memory_mb": 734.55078125
91
- },
92
- {
93
- "step": 1100,
94
- "loss": 6.551132082939148,
95
- "perplexity": 700.0362244642821,
96
- "learning_rate": 0.00016500000000000537,
97
- "step_time": 8.517168760299683,
98
- "tokens_per_second": 120.22774572379963,
99
- "memory_mb": 913.80078125
100
- },
101
- {
102
- "step": 1200,
103
- "loss": 6.6684452295303345,
104
- "perplexity": 787.170782663513,
105
- "learning_rate": 0.00014155749601496882,
106
- "step_time": 9.400139570236206,
107
- "tokens_per_second": 108.93455276369572,
108
- "memory_mb": 968.5859375
109
- },
110
- {
111
- "step": 1300,
112
- "loss": 6.406905889511108,
113
- "perplexity": 606.0156976890383,
114
- "learning_rate": 0.00011882728065103813,
115
- "step_time": 8.490540981292725,
116
- "tokens_per_second": 120.6048003603289,
117
- "memory_mb": 979.359375
118
- },
119
- {
120
- "step": 1400,
121
- "loss": 6.3421419858932495,
122
- "perplexity": 568.011682273887,
123
- "learning_rate": 9.750000000000261e-05,
124
- "step_time": 10.675879955291748,
125
- "tokens_per_second": 95.91715196201983,
126
- "memory_mb": 733.6328125
127
- },
128
- {
129
- "step": 1500,
130
- "loss": 6.335531115531921,
131
- "perplexity": 564.2690154518974,
132
- "learning_rate": 7.822367269231907e-05,
133
- "step_time": 8.945564270019531,
134
- "tokens_per_second": 114.47014062957085,
135
- "memory_mb": 994.3515625
136
- },
137
- {
138
- "step": 1600,
139
- "loss": 6.629261136054993,
140
- "perplexity": 756.9227010883292,
141
- "learning_rate": 6.158400017893925e-05,
142
- "step_time": 10.422486782073975,
143
- "tokens_per_second": 98.2491051714468,
144
- "memory_mb": 730.56640625
145
- },
146
- {
147
- "step": 1700,
148
- "loss": 6.302608251571655,
149
- "perplexity": 545.9941446328027,
150
- "learning_rate": 4.808657048910149e-05,
151
- "step_time": 9.476832628250122,
152
- "tokens_per_second": 108.05297932006208,
153
- "memory_mb": 745.43359375
154
- },
155
- {
156
- "step": 1800,
157
- "loss": 6.266754984855652,
158
- "perplexity": 526.765240241726,
159
- "learning_rate": 3.8141496193902704e-05,
160
- "step_time": 8.648972511291504,
161
- "tokens_per_second": 118.3955664864394,
162
- "memory_mb": 1009.6484375
163
- },
164
- {
165
- "step": 1900,
166
- "loss": 6.480456352233887,
167
- "perplexity": 652.268542568135,
168
- "learning_rate": 3.2050953343351995e-05,
169
- "step_time": 8.593879699707031,
170
- "tokens_per_second": 119.15456531639704,
171
- "memory_mb": 735.796875
172
- },
173
- {
174
- "step": 2000,
175
- "loss": 5.975515604019165,
176
- "perplexity": 393.6710271356782,
177
- "learning_rate": 2.9999999999999997e-05,
178
- "step_time": 8.94594669342041,
179
- "tokens_per_second": 114.46524723349116,
180
- "memory_mb": 729.84375
181
- },
182
- {
183
- "step": 2100,
184
- "loss": 6.554613709449768,
185
- "perplexity": 702.4777368926921,
186
- "learning_rate": 3.205095334333285e-05,
187
- "step_time": 9.199656009674072,
188
- "tokens_per_second": 111.3085096794047,
189
- "memory_mb": 752.64453125
190
- },
191
- {
192
- "step": 2200,
193
- "loss": 6.471360206604004,
194
- "perplexity": 646.3623155888199,
195
- "learning_rate": 3.814149619382671e-05,
196
- "step_time": 8.654725313186646,
197
- "tokens_per_second": 118.3168688715975,
198
- "memory_mb": 735.9375
199
- },
200
- {
201
- "step": 2300,
202
- "loss": 6.382450699806213,
203
- "perplexity": 591.3752163574818,
204
- "learning_rate": 4.808657048893273e-05,
205
- "step_time": 8.75070834159851,
206
- "tokens_per_second": 117.01909834340836,
207
- "memory_mb": 776.53125
208
- },
209
- {
210
- "step": 2400,
211
- "loss": 5.957324385643005,
212
- "perplexity": 386.5744152212925,
213
- "learning_rate": 6.158400017864459e-05,
214
- "step_time": 8.642782926559448,
215
- "tokens_per_second": 118.4803562349376,
216
- "memory_mb": 923.15234375
217
- },
218
- {
219
- "step": 2500,
220
- "loss": 6.218142509460449,
221
- "perplexity": 501.7703322170689,
222
- "learning_rate": 7.822367269186924e-05,
223
- "step_time": 9.567925691604614,
224
- "tokens_per_second": 107.0242425585004,
225
- "memory_mb": 1050.1875
226
- },
227
- {
228
- "step": 2600,
229
- "loss": 6.314482092857361,
230
- "perplexity": 552.515834581567,
231
- "learning_rate": 9.749999999937299e-05,
232
- "step_time": 8.212730169296265,
233
- "tokens_per_second": 124.68448115199003,
234
- "memory_mb": 738.69921875
235
- },
236
- {
237
- "step": 2700,
238
- "loss": 6.240906238555908,
239
- "perplexity": 513.3234937600264,
240
- "learning_rate": 0.00011882728065020969,
241
- "step_time": 8.88506555557251,
242
- "tokens_per_second": 115.24957172181702,
243
- "memory_mb": 739.125
244
- },
245
- {
246
- "step": 2800,
247
- "loss": 6.308051347732544,
248
- "perplexity": 548.9741461252174,
249
- "learning_rate": 0.0001415574960139285,
250
- "step_time": 9.43014669418335,
251
- "tokens_per_second": 108.58791842884247,
252
- "memory_mb": 732.40234375
253
- },
254
- {
255
- "step": 2900,
256
- "loss": 6.410398960113525,
257
- "perplexity": 608.136254778883,
258
- "learning_rate": 0.00016499999999874617,
259
- "step_time": 8.674461603164673,
260
- "tokens_per_second": 118.0476722182294,
261
- "memory_mb": 733.71484375
262
- },
263
- {
264
- "step": 3000,
265
- "loss": 6.160744071006775,
266
- "perplexity": 473.7804700263767,
267
- "learning_rate": 0.0001884425039835638,
268
- "step_time": 9.056138277053833,
269
- "tokens_per_second": 113.07247843096432,
270
- "memory_mb": 803.75390625
271
- },
272
- {
273
- "step": 3100,
274
- "loss": 6.270610332489014,
275
- "perplexity": 528.8000232415734,
276
- "learning_rate": 0.0002111727193472824,
277
- "step_time": 9.650378227233887,
278
- "tokens_per_second": 106.10983071214939,
279
- "memory_mb": 790.328125
280
- },
281
- {
282
- "step": 3200,
283
- "loss": 6.4413875341415405,
284
- "perplexity": 627.2765639068664,
285
- "learning_rate": 0.00023249999999811922,
286
- "step_time": 8.436410665512085,
287
- "tokens_per_second": 121.37863371043517,
288
- "memory_mb": 940.3671875
289
- },
290
- {
291
- "step": 3300,
292
- "loss": 6.163665413856506,
293
- "perplexity": 475.1665688640195,
294
- "learning_rate": 0.0002517763273056231,
295
- "step_time": 10.011188507080078,
296
- "tokens_per_second": 102.28555773131335,
297
- "memory_mb": 747.43359375
298
- },
299
- {
300
- "step": 3400,
301
- "loss": 6.067382216453552,
302
- "perplexity": 431.5494984476535,
303
- "learning_rate": 0.00026841599981884787,
304
- "step_time": 8.671327114105225,
305
- "tokens_per_second": 118.0903437876665,
306
- "memory_mb": 970.37109375
307
- },
308
- {
309
- "step": 3500,
310
- "loss": 6.14486300945282,
311
- "perplexity": 466.3157638357051,
312
- "learning_rate": 0.0002819134295085615,
313
- "step_time": 8.194751024246216,
314
- "tokens_per_second": 124.95803679333764,
315
- "memory_mb": 736.890625
316
- },
317
- {
318
- "step": 3600,
319
- "loss": 6.448354721069336,
320
- "perplexity": 631.6621769355031,
321
- "learning_rate": 0.00029185850380367053,
322
- "step_time": 8.76004934310913,
323
- "tokens_per_second": 116.89431872955184,
324
- "memory_mb": 781.22265625
325
- },
326
- {
327
- "step": 3700,
328
- "loss": 6.149544358253479,
329
- "perplexity": 468.5038682213576,
330
- "learning_rate": 0.00029794904665416755,
331
- "step_time": 11.995165824890137,
332
- "tokens_per_second": 85.36772354369505,
333
- "memory_mb": 836.3046875
334
- },
335
- {
336
- "step": 3800,
337
- "loss": 6.083824634552002,
338
- "perplexity": 438.70387214992155,
339
- "learning_rate": 0.0002999999999975028,
340
- "step_time": 8.194983720779419,
341
- "tokens_per_second": 124.95448861033346,
342
- "memory_mb": 766.9453125
343
- },
344
- {
345
- "step": 3900,
346
- "loss": 6.295181512832642,
347
- "perplexity": 541.954209109435,
348
- "learning_rate": 0.0002979490466541723,
349
- "step_time": 9.617033004760742,
350
- "tokens_per_second": 106.47774625428518,
351
- "memory_mb": 837.29296875
352
- },
353
- {
354
- "step": 4000,
355
- "loss": 5.752694249153137,
356
- "perplexity": 315.038309582537,
357
- "learning_rate": 0.0002918585038036804,
358
- "step_time": 10.153574228286743,
359
- "tokens_per_second": 100.85118569845567,
360
- "memory_mb": 729.46484375
361
- },
362
- {
363
- "step": 4100,
364
- "loss": 6.129071950912476,
365
- "perplexity": 459.00997915951336,
366
- "learning_rate": 0.00028191342950857645,
367
- "step_time": 16.923099994659424,
368
- "tokens_per_second": 121.01801683180422,
369
- "memory_mb": 866.20703125
370
- },
371
- {
372
- "step": 4200,
373
- "loss": 5.725140452384949,
374
- "perplexity": 306.4763075489217,
375
- "learning_rate": 0.0002684159998188649,
376
- "step_time": 16.08098530769348,
377
- "tokens_per_second": 127.35538033357905,
378
- "memory_mb": 856.5625
379
- },
380
- {
381
- "step": 4300,
382
- "loss": 5.917757749557495,
383
- "perplexity": 371.57760903139615,
384
- "learning_rate": 0.00025177632730563935,
385
- "step_time": 16.5029239654541,
386
- "tokens_per_second": 124.09922049493284,
387
- "memory_mb": 856.58203125
388
- },
389
- {
390
- "step": 4400,
391
- "loss": 5.828692674636841,
392
- "perplexity": 339.9140102647636,
393
- "learning_rate": 0.00023249999999813424,
394
- "step_time": 15.03031873703003,
395
- "tokens_per_second": 136.25792212605347,
396
- "memory_mb": 856.58203125
397
- },
398
- {
399
- "step": 4500,
400
- "loss": 5.768530249595642,
401
- "perplexity": 320.0669682230316,
402
- "learning_rate": 0.0002111727193472959,
403
- "step_time": 15.095525026321411,
404
- "tokens_per_second": 135.66934548013344,
405
- "memory_mb": 856.58203125
406
- },
407
- {
408
- "step": 4600,
409
- "loss": 5.824233174324036,
410
- "perplexity": 338.40153857021943,
411
- "learning_rate": 0.00018844250398357548,
412
- "step_time": 15.770112752914429,
413
- "tokens_per_second": 129.86590724416445,
414
- "memory_mb": 856.6796875
415
- },
416
- {
417
- "step": 4700,
418
- "loss": 5.592358708381653,
419
- "perplexity": 268.3678753241069,
420
- "learning_rate": 0.00016499999999875585,
421
- "step_time": 15.393234729766846,
422
- "tokens_per_second": 133.04546029169921,
423
- "memory_mb": 856.6015625
424
- },
425
- {
426
- "step": 4800,
427
- "loss": 5.626398682594299,
428
- "perplexity": 277.6603717835579,
429
- "learning_rate": 0.0001415574960139364,
430
- "step_time": 15.054797887802124,
431
- "tokens_per_second": 136.03636629750804,
432
- "memory_mb": 856.6796875
433
- },
434
- {
435
- "step": 4900,
436
- "loss": 5.718711733818054,
437
- "perplexity": 304.5123771619807,
438
- "learning_rate": 0.00011882728065021638,
439
- "step_time": 16.42769432067871,
440
- "tokens_per_second": 124.66752546168553,
441
- "memory_mb": 856.62890625
442
- },
443
- {
444
- "step": 5000,
445
- "loss": 5.441234588623047,
446
- "perplexity": 230.7268604519411,
447
- "learning_rate": 9.749999999937817e-05,
448
- "step_time": 15.495960474014282,
449
- "tokens_per_second": 132.16347598681364,
450
- "memory_mb": 856.71875
451
- },
452
- {
453
- "step": 5100,
454
- "loss": 5.574064016342163,
455
- "perplexity": 263.50280585799544,
456
- "learning_rate": 7.822367269187295e-05,
457
- "step_time": 15.050865411758423,
458
- "tokens_per_second": 136.07190975211358,
459
- "memory_mb": 856.67578125
460
- },
461
- {
462
- "step": 5200,
463
- "loss": 5.486729264259338,
464
- "perplexity": 241.4661419404157,
465
- "learning_rate": 6.158400017864684e-05,
466
- "step_time": 14.95394515991211,
467
- "tokens_per_second": 136.95382576968316,
468
- "memory_mb": 856.74609375
469
- },
470
- {
471
- "step": 5300,
472
- "loss": 5.643607139587402,
473
- "perplexity": 282.47982711304775,
474
- "learning_rate": 4.808657048893407e-05,
475
- "step_time": 14.74146294593811,
476
- "tokens_per_second": 138.927866759948,
477
- "memory_mb": 856.828125
478
- },
479
- {
480
- "step": 5400,
481
- "loss": 5.773634672164917,
482
- "perplexity": 321.7049020761921,
483
- "learning_rate": 3.8141496193827305e-05,
484
- "step_time": 14.770179033279419,
485
- "tokens_per_second": 138.6577640924697,
486
- "memory_mb": 856.73046875
487
- },
488
- {
489
- "step": 5500,
490
- "loss": 5.430219531059265,
491
- "perplexity": 228.19933676762415,
492
- "learning_rate": 3.2050953343333e-05,
493
- "step_time": 17.394481897354126,
494
- "tokens_per_second": 117.7384881070543,
495
- "memory_mb": 856.4453125
496
- },
497
- {
498
- "step": 5600,
499
- "loss": 5.905840158462524,
500
- "perplexity": 367.17558190769864,
501
- "learning_rate": 2.9999999999999997e-05,
502
- "step_time": 14.9873046875,
503
- "tokens_per_second": 136.64898677265916,
504
- "memory_mb": 856.71875
505
- },
506
- {
507
- "step": 5700,
508
- "loss": 5.61777663230896,
509
- "perplexity": 275.27666109950576,
510
- "learning_rate": 3.205095334333272e-05,
511
- "step_time": 16.493826627731323,
512
- "tokens_per_second": 124.16766868136386,
513
- "memory_mb": 856.71875
514
- },
515
- {
516
- "step": 5800,
517
- "loss": 5.823711514472961,
518
- "perplexity": 338.2250541104363,
519
- "learning_rate": 3.814149619382621e-05,
520
- "step_time": 15.767404556274414,
521
- "tokens_per_second": 129.88821290724272,
522
- "memory_mb": 856.7265625
523
- },
524
- {
525
- "step": 5900,
526
- "loss": 5.767146706581116,
527
- "perplexity": 319.6244479984378,
528
- "learning_rate": 4.808657048893161e-05,
529
- "step_time": 14.995726346969604,
530
- "tokens_per_second": 136.57224415900788,
531
- "memory_mb": 857.28125
532
- },
533
- {
534
- "step": 6000,
535
- "loss": 5.632080435752869,
536
- "perplexity": 279.242459738446,
537
- "learning_rate": 6.158400017864261e-05,
538
- "step_time": 15.532944679260254,
539
- "tokens_per_second": 131.84879250452173,
540
- "memory_mb": 857.25
541
- },
542
- {
543
- "step": 6100,
544
- "loss": 5.641765594482422,
545
- "perplexity": 281.9601064615597,
546
- "learning_rate": 7.822367269186639e-05,
547
- "step_time": 13.042147397994995,
548
- "tokens_per_second": 157.02935548135613,
549
- "memory_mb": 3038.3984375
550
- },
551
- {
552
- "step": 6200,
553
- "loss": 5.216195583343506,
554
- "perplexity": 184.23195401529154,
555
- "learning_rate": 9.749999999936928e-05,
556
- "step_time": 13.716249227523804,
557
- "tokens_per_second": 149.3119559165174,
558
- "memory_mb": 3027.03515625
559
- },
560
- {
561
- "step": 6300,
562
- "loss": 5.537067532539368,
563
- "perplexity": 253.93225847719265,
564
- "learning_rate": 0.00011882728065020474,
565
- "step_time": 13.56373405456543,
566
- "tokens_per_second": 150.99086960575298,
567
- "memory_mb": 3029.5546875
568
- },
569
- {
570
- "step": 6400,
571
- "loss": 5.462532162666321,
572
- "perplexity": 235.69348362718267,
573
- "learning_rate": 0.0001415574960139221,
574
- "step_time": 15.235360145568848,
575
- "tokens_per_second": 134.4241278468008,
576
- "memory_mb": 3029.3984375
577
- },
578
- {
579
- "step": 6500,
580
- "loss": 5.461255669593811,
581
- "perplexity": 235.39281446997174,
582
- "learning_rate": 0.00016499999999873858,
583
- "step_time": 14.625237941741943,
584
- "tokens_per_second": 140.03190978211683,
585
- "memory_mb": 3029.7421875
586
- },
587
- {
588
- "step": 6600,
589
- "loss": 5.543500542640686,
590
- "perplexity": 255.571072864111,
591
- "learning_rate": 0.00018844250398355512,
592
- "step_time": 13.293677568435669,
593
- "tokens_per_second": 154.0581971735755,
594
- "memory_mb": 3025.90234375
595
- },
596
- {
597
- "step": 6700,
598
- "loss": 5.326942205429077,
599
- "perplexity": 205.80769336539043,
600
- "learning_rate": 0.0002111727193472727,
601
- "step_time": 13.689483880996704,
602
- "tokens_per_second": 149.60388702768896,
603
- "memory_mb": 3032.14453125
604
- },
605
- {
606
- "step": 6800,
607
- "loss": 5.4400506019592285,
608
- "perplexity": 230.4538445816494,
609
- "learning_rate": 0.00023249999999810797,
610
- "step_time": 13.920767545700073,
611
- "tokens_per_second": 147.11832470994733,
612
- "memory_mb": 3033.22265625
613
- },
614
- {
615
- "step": 6900,
616
- "loss": 5.562488794326782,
617
- "perplexity": 260.47028727589134,
618
- "learning_rate": 0.0002517763273056109,
619
- "step_time": 13.11566162109375,
620
- "tokens_per_second": 156.1491946930247,
621
- "memory_mb": 3030.31640625
622
- },
623
- {
624
- "step": 7000,
625
- "loss": 5.337615728378296,
626
- "perplexity": 208.01615155187662,
627
- "learning_rate": 0.00026841599981883453,
628
- "step_time": 13.812754154205322,
629
- "tokens_per_second": 148.2687650222517,
630
- "memory_mb": 3030.01171875
631
- },
632
- {
633
- "step": 7100,
634
- "loss": 5.591769337654114,
635
- "perplexity": 268.20975375486825,
636
- "learning_rate": 4.0863750705554176e-05,
637
- "step_time": 22.385777473449707,
638
- "tokens_per_second": 91.48665943941405,
639
- "memory_mb": 778.03515625
640
- },
641
- {
642
- "step": 7200,
643
- "loss": 5.491156101226807,
644
- "perplexity": 242.5374426712762,
645
- "learning_rate": 3.860829246363548e-05,
646
- "step_time": 23.257835626602173,
647
- "tokens_per_second": 88.0563450907491,
648
- "memory_mb": 766.17578125
649
- },
650
- {
651
- "step": 7300,
652
- "loss": 5.590375304222107,
653
- "perplexity": 267.83612088021056,
654
- "learning_rate": 3.660737030015427e-05,
655
- "step_time": 22.15459370613098,
656
- "tokens_per_second": 92.4413251339944,
657
- "memory_mb": 765.515625
658
- },
659
- {
660
- "step": 7400,
661
- "loss": 5.408857345581055,
662
- "perplexity": 223.37619999638744,
663
- "learning_rate": 3.486501380605981e-05,
664
- "step_time": 22.82973575592041,
665
- "tokens_per_second": 89.70756481353028,
666
- "memory_mb": 762.5078125
667
- },
668
- {
669
- "step": 7500,
670
- "loss": 5.681139707565308,
671
- "perplexity": 293.2834969372769,
672
- "learning_rate": 3.338473185545381e-05,
673
- "step_time": 23.581167221069336,
674
- "tokens_per_second": 86.848966414612,
675
- "memory_mb": 762.328125
676
- },
677
- {
678
- "step": 7600,
679
- "loss": 5.239741921424866,
680
- "perplexity": 188.6214169770699,
681
- "learning_rate": 3.2169505539184994e-05,
682
- "step_time": 24.760926008224487,
683
- "tokens_per_second": 82.71096159003685,
684
- "memory_mb": 765.65625
685
- },
686
- {
687
- "step": 7700,
688
- "loss": 5.552804112434387,
689
- "perplexity": 257.95989121628156,
690
- "learning_rate": 3.122178216132881e-05,
691
- "step_time": 21.644299030303955,
692
- "tokens_per_second": 94.62075889510751,
693
- "memory_mb": 766.9921875
694
- },
695
- {
696
- "step": 7800,
697
- "loss": 5.3391993045806885,
698
- "perplexity": 208.34582193938436,
699
- "learning_rate": 3.054347031064272e-05,
700
- "step_time": 21.552024602890015,
701
- "tokens_per_second": 95.02587518971994,
702
- "memory_mb": 768.30078125
703
- },
704
- {
705
- "step": 7900,
706
- "loss": 5.07136607170105,
707
- "perplexity": 159.39191947680405,
708
- "learning_rate": 3.0135936016922528e-05,
709
- "step_time": 25.795836448669434,
710
- "tokens_per_second": 79.3926571861808,
711
- "memory_mb": 766.03125
712
- },
713
- {
714
- "step": 8000,
715
- "loss": 5.289915561676025,
716
- "perplexity": 198.32667833002583,
717
- "learning_rate": 2.9999999999999997e-05,
718
- "step_time": 20.64373207092285,
719
- "tokens_per_second": 99.20686787466366,
720
- "memory_mb": 770.73046875
721
- },
722
- {
723
- "step": 8100,
724
- "loss": 5.472690582275391,
725
- "perplexity": 238.09995923313426,
726
- "learning_rate": 2.9999999999999997e-05,
727
- "step_time": 20.021532773971558,
728
- "tokens_per_second": 102.28987076666009,
729
- "memory_mb": 782.06640625
730
- },
731
- {
732
- "step": 8200,
733
- "loss": 5.381044268608093,
734
- "perplexity": 217.24902334669338,
735
- "learning_rate": 2.9999999999999997e-05,
736
- "step_time": 19.268752336502075,
737
- "tokens_per_second": 106.28607209405757,
738
- "memory_mb": 772.1875
739
- },
740
- {
741
- "step": 8300,
742
- "loss": 5.509163498878479,
743
- "perplexity": 246.94447131857976,
744
- "learning_rate": 2.9999999999999997e-05,
745
- "step_time": 21.33850598335266,
746
- "tokens_per_second": 95.97672871745365,
747
- "memory_mb": 773.4140625
748
- },
749
- {
750
- "step": 8400,
751
- "loss": 5.361395001411438,
752
- "perplexity": 213.0219051308242,
753
- "learning_rate": 2.9999999999999997e-05,
754
- "step_time": 19.24502682685852,
755
- "tokens_per_second": 106.41710289235836,
756
- "memory_mb": 771.12890625
757
- },
758
- {
759
- "step": 8500,
760
- "loss": 5.601587295532227,
761
- "perplexity": 270.8559949054038,
762
- "learning_rate": 2.9999999999999997e-05,
763
- "step_time": 19.78052020072937,
764
- "tokens_per_second": 103.53620527757828,
765
- "memory_mb": 788.19140625
766
- },
767
- {
768
- "step": 8600,
769
- "loss": 5.177438259124756,
770
- "perplexity": 177.22821619925446,
771
- "learning_rate": 2.9999999999999997e-05,
772
- "step_time": 19.43180513381958,
773
- "tokens_per_second": 105.39422281646966,
774
- "memory_mb": 768.90625
775
- },
776
- {
777
- "step": 8700,
778
- "loss": 5.507565855979919,
779
- "perplexity": 246.5502572281615,
780
- "learning_rate": 2.9999999999999997e-05,
781
- "step_time": 20.27060604095459,
782
- "tokens_per_second": 101.03299308675011,
783
- "memory_mb": 770.671875
784
- },
785
- {
786
- "step": 8800,
787
- "loss": 5.28560483455658,
788
- "perplexity": 197.47358618400258,
789
- "learning_rate": 2.9999999999999997e-05,
790
- "step_time": 18.91090226173401,
791
- "tokens_per_second": 108.29731821649273,
792
- "memory_mb": 780.921875
793
- },
794
- {
795
- "step": 8900,
796
- "loss": 5.001006722450256,
797
- "perplexity": 148.56264519463585,
798
- "learning_rate": 2.9999999999999997e-05,
799
- "step_time": 18.08107566833496,
800
- "tokens_per_second": 113.26759743540164,
801
- "memory_mb": 782.58203125
802
- },
803
- {
804
- "step": 9000,
805
- "loss": 5.228554844856262,
806
- "perplexity": 186.5230539013194,
807
- "learning_rate": 2.9999999999999997e-05,
808
- "step_time": 19.203582286834717,
809
- "tokens_per_second": 106.64676878563616,
810
- "memory_mb": 775.125
811
- }
812
- ]