ctemplin/Llama-3.2-1B-PythonProgrammer
017
1{
2 "best_metric": null,
3 "best_model_checkpoint": null,
4 "epoch": 1.0,
5 "eval_steps": 500,
6 "global_step": 6250,
7 "is_hyper_param_search": false,
8 "is_local_process_zero": true,
9 "is_world_process_zero": true,
10 "log_history": [
11 {
12 "epoch": 0.008,
13 "grad_norm": 0.24006609618663788,
14 "learning_rate": 0.0001984,
15 "loss": 1.0243,
16 "step": 50
17 },
18 {
19 "epoch": 0.016,
20 "grad_norm": 0.21576859056949615,
21 "learning_rate": 0.0001968,
22 "loss": 0.9669,
23 "step": 100
24 },
25 {
26 "epoch": 0.024,
27 "grad_norm": 0.20258210599422455,
28 "learning_rate": 0.0001952,
29 "loss": 0.9397,
30 "step": 150
31 },
32 {
33 "epoch": 0.032,
34 "grad_norm": 0.2684886157512665,
35 "learning_rate": 0.00019360000000000002,
36 "loss": 0.8793,
37 "step": 200
38 },
39 {
40 "epoch": 0.04,
41 "grad_norm": 0.22625429928302765,
42 "learning_rate": 0.000192,
43 "loss": 0.9209,
44 "step": 250
45 },
46 {
47 "epoch": 0.048,
48 "grad_norm": 0.25748205184936523,
49 "learning_rate": 0.0001904,
50 "loss": 0.8553,
51 "step": 300
52 },
53 {
54 "epoch": 0.056,
55 "grad_norm": 0.24440611898899078,
56 "learning_rate": 0.0001888,
57 "loss": 0.9141,
58 "step": 350
59 },
60 {
61 "epoch": 0.064,
62 "grad_norm": 0.24657492339611053,
63 "learning_rate": 0.00018720000000000002,
64 "loss": 0.8973,
65 "step": 400
66 },
67 {
68 "epoch": 0.072,
69 "grad_norm": 0.21331937611103058,
70 "learning_rate": 0.0001856,
71 "loss": 0.8836,
72 "step": 450
73 },
74 {
75 "epoch": 0.08,
76 "grad_norm": 0.23378247022628784,
77 "learning_rate": 0.00018400000000000003,
78 "loss": 0.8992,
79 "step": 500
80 },
81 {
82 "epoch": 0.088,
83 "grad_norm": 0.21668757498264313,
84 "learning_rate": 0.00018240000000000002,
85 "loss": 0.8479,
86 "step": 550
87 },
88 {
89 "epoch": 0.096,
90 "grad_norm": 0.22808493673801422,
91 "learning_rate": 0.0001808,
92 "loss": 0.8805,
93 "step": 600
94 },
95 {
96 "epoch": 0.104,
97 "grad_norm": 0.2394104301929474,
98 "learning_rate": 0.00017920000000000002,
99 "loss": 0.8633,
100 "step": 650
101 },
102 {
103 "epoch": 0.112,
104 "grad_norm": 0.22561711072921753,
105 "learning_rate": 0.0001776,
106 "loss": 0.8766,
107 "step": 700
108 },
109 {
110 "epoch": 0.12,
111 "grad_norm": 0.29312923550605774,
112 "learning_rate": 0.00017600000000000002,
113 "loss": 0.891,
114 "step": 750
115 },
116 {
117 "epoch": 0.128,
118 "grad_norm": 0.21683369576931,
119 "learning_rate": 0.0001744,
120 "loss": 0.8473,
121 "step": 800
122 },
123 {
124 "epoch": 0.136,
125 "grad_norm": 0.2582944929599762,
126 "learning_rate": 0.0001728,
127 "loss": 0.8949,
128 "step": 850
129 },
130 {
131 "epoch": 0.144,
132 "grad_norm": 0.2305222898721695,
133 "learning_rate": 0.00017120000000000001,
134 "loss": 0.8535,
135 "step": 900
136 },
137 {
138 "epoch": 0.152,
139 "grad_norm": 0.2317700982093811,
140 "learning_rate": 0.0001696,
141 "loss": 0.8677,
142 "step": 950
143 },
144 {
145 "epoch": 0.16,
146 "grad_norm": 0.2534327208995819,
147 "learning_rate": 0.000168,
148 "loss": 0.8662,
149 "step": 1000
150 },
151 {
152 "epoch": 0.168,
153 "grad_norm": 0.2503647208213806,
154 "learning_rate": 0.0001664,
155 "loss": 0.8606,
156 "step": 1050
157 },
158 {
159 "epoch": 0.176,
160 "grad_norm": 0.2579597234725952,
161 "learning_rate": 0.0001648,
162 "loss": 0.833,
163 "step": 1100
164 },
165 {
166 "epoch": 0.184,
167 "grad_norm": 0.2581159472465515,
168 "learning_rate": 0.0001632,
169 "loss": 0.8415,
170 "step": 1150
171 },
172 {
173 "epoch": 0.192,
174 "grad_norm": 0.24251115322113037,
175 "learning_rate": 0.00016160000000000002,
176 "loss": 0.8484,
177 "step": 1200
178 },
179 {
180 "epoch": 0.2,
181 "grad_norm": 0.28298044204711914,
182 "learning_rate": 0.00016,
183 "loss": 0.8405,
184 "step": 1250
185 },
186 {
187 "epoch": 0.208,
188 "grad_norm": 0.2423146665096283,
189 "learning_rate": 0.00015840000000000003,
190 "loss": 0.8315,
191 "step": 1300
192 },
193 {
194 "epoch": 0.216,
195 "grad_norm": 0.22693276405334473,
196 "learning_rate": 0.00015680000000000002,
197 "loss": 0.8757,
198 "step": 1350
199 },
200 {
201 "epoch": 0.224,
202 "grad_norm": 0.24105730652809143,
203 "learning_rate": 0.0001552,
204 "loss": 0.8485,
205 "step": 1400
206 },
207 {
208 "epoch": 0.232,
209 "grad_norm": 0.22538623213768005,
210 "learning_rate": 0.00015360000000000002,
211 "loss": 0.8946,
212 "step": 1450
213 },
214 {
215 "epoch": 0.24,
216 "grad_norm": 0.2406863272190094,
217 "learning_rate": 0.000152,
218 "loss": 0.8389,
219 "step": 1500
220 },
221 {
222 "epoch": 0.248,
223 "grad_norm": 0.2680400311946869,
224 "learning_rate": 0.0001504,
225 "loss": 0.8283,
226 "step": 1550
227 },
228 {
229 "epoch": 0.256,
230 "grad_norm": 0.2538231909275055,
231 "learning_rate": 0.0001488,
232 "loss": 0.8384,
233 "step": 1600
234 },
235 {
236 "epoch": 0.264,
237 "grad_norm": 0.26007387042045593,
238 "learning_rate": 0.0001472,
239 "loss": 0.8589,
240 "step": 1650
241 },
242 {
243 "epoch": 0.272,
244 "grad_norm": 0.2680321931838989,
245 "learning_rate": 0.00014560000000000002,
246 "loss": 0.8872,
247 "step": 1700
248 },
249 {
250 "epoch": 0.28,
251 "grad_norm": 0.2379782646894455,
252 "learning_rate": 0.000144,
253 "loss": 0.8483,
254 "step": 1750
255 },
256 {
257 "epoch": 0.288,
258 "grad_norm": 0.2729997932910919,
259 "learning_rate": 0.0001424,
260 "loss": 0.8381,
261 "step": 1800
262 },
263 {
264 "epoch": 0.296,
265 "grad_norm": 0.24824947118759155,
266 "learning_rate": 0.0001408,
267 "loss": 0.8274,
268 "step": 1850
269 },
270 {
271 "epoch": 0.304,
272 "grad_norm": 0.26121681928634644,
273 "learning_rate": 0.0001392,
274 "loss": 0.8491,
275 "step": 1900
276 },
277 {
278 "epoch": 0.312,
279 "grad_norm": 0.24737513065338135,
280 "learning_rate": 0.00013759999999999998,
281 "loss": 0.8416,
282 "step": 1950
283 },
284 {
285 "epoch": 0.32,
286 "grad_norm": 0.2495298683643341,
287 "learning_rate": 0.00013600000000000003,
288 "loss": 0.829,
289 "step": 2000
290 },
291 {
292 "epoch": 0.328,
293 "grad_norm": 0.25478219985961914,
294 "learning_rate": 0.00013440000000000001,
295 "loss": 0.8247,
296 "step": 2050
297 },
298 {
299 "epoch": 0.336,
300 "grad_norm": 0.24906663596630096,
301 "learning_rate": 0.0001328,
302 "loss": 0.853,
303 "step": 2100
304 },
305 {
306 "epoch": 0.344,
307 "grad_norm": 0.2297120839357376,
308 "learning_rate": 0.00013120000000000002,
309 "loss": 0.8289,
310 "step": 2150
311 },
312 {
313 "epoch": 0.352,
314 "grad_norm": 0.2441694438457489,
315 "learning_rate": 0.0001296,
316 "loss": 0.8592,
317 "step": 2200
318 },
319 {
320 "epoch": 0.36,
321 "grad_norm": 0.2818741202354431,
322 "learning_rate": 0.00012800000000000002,
323 "loss": 0.8065,
324 "step": 2250
325 },
326 {
327 "epoch": 0.368,
328 "grad_norm": 0.2782455086708069,
329 "learning_rate": 0.0001264,
330 "loss": 0.8333,
331 "step": 2300
332 },
333 {
334 "epoch": 0.376,
335 "grad_norm": 0.3333749771118164,
336 "learning_rate": 0.0001248,
337 "loss": 0.8714,
338 "step": 2350
339 },
340 {
341 "epoch": 0.384,
342 "grad_norm": 0.38234880566596985,
343 "learning_rate": 0.0001232,
344 "loss": 0.8206,
345 "step": 2400
346 },
347 {
348 "epoch": 0.392,
349 "grad_norm": 0.2502688765525818,
350 "learning_rate": 0.0001216,
351 "loss": 0.8561,
352 "step": 2450
353 },
354 {
355 "epoch": 0.4,
356 "grad_norm": 0.2759045958518982,
357 "learning_rate": 0.00012,
358 "loss": 0.858,
359 "step": 2500
360 },
361 {
362 "epoch": 0.408,
363 "grad_norm": 0.3138297200202942,
364 "learning_rate": 0.0001184,
365 "loss": 0.8148,
366 "step": 2550
367 },
368 {
369 "epoch": 0.416,
370 "grad_norm": 0.27893930673599243,
371 "learning_rate": 0.00011679999999999999,
372 "loss": 0.8181,
373 "step": 2600
374 },
375 {
376 "epoch": 0.424,
377 "grad_norm": 0.2226714789867401,
378 "learning_rate": 0.0001152,
379 "loss": 0.8326,
380 "step": 2650
381 },
382 {
383 "epoch": 0.432,
384 "grad_norm": 0.23976224660873413,
385 "learning_rate": 0.0001136,
386 "loss": 0.8205,
387 "step": 2700
388 },
389 {
390 "epoch": 0.44,
391 "grad_norm": 0.23596003651618958,
392 "learning_rate": 0.00011200000000000001,
393 "loss": 0.8336,
394 "step": 2750
395 },
396 {
397 "epoch": 0.448,
398 "grad_norm": 0.2597508430480957,
399 "learning_rate": 0.00011040000000000001,
400 "loss": 0.8202,
401 "step": 2800
402 },
403 {
404 "epoch": 0.456,
405 "grad_norm": 0.2530119717121124,
406 "learning_rate": 0.00010880000000000002,
407 "loss": 0.8193,
408 "step": 2850
409 },
410 {
411 "epoch": 0.464,
412 "grad_norm": 0.267026424407959,
413 "learning_rate": 0.00010720000000000002,
414 "loss": 0.8272,
415 "step": 2900
416 },
417 {
418 "epoch": 0.472,
419 "grad_norm": 0.3313164710998535,
420 "learning_rate": 0.0001056,
421 "loss": 0.829,
422 "step": 2950
423 },
424 {
425 "epoch": 0.48,
426 "grad_norm": 0.24725987017154694,
427 "learning_rate": 0.00010400000000000001,
428 "loss": 0.8204,
429 "step": 3000
430 },
431 {
432 "epoch": 0.488,
433 "grad_norm": 0.3102189302444458,
434 "learning_rate": 0.00010240000000000001,
435 "loss": 0.8344,
436 "step": 3050
437 },
438 {
439 "epoch": 0.496,
440 "grad_norm": 0.2404993623495102,
441 "learning_rate": 0.00010080000000000001,
442 "loss": 0.8172,
443 "step": 3100
444 },
445 {
446 "epoch": 0.504,
447 "grad_norm": 0.24549129605293274,
448 "learning_rate": 9.92e-05,
449 "loss": 0.833,
450 "step": 3150
451 },
452 {
453 "epoch": 0.512,
454 "grad_norm": 0.2698763906955719,
455 "learning_rate": 9.76e-05,
456 "loss": 0.8206,
457 "step": 3200
458 },
459 {
460 "epoch": 0.52,
461 "grad_norm": 0.26306065917015076,
462 "learning_rate": 9.6e-05,
463 "loss": 0.8517,
464 "step": 3250
465 },
466 {
467 "epoch": 0.528,
468 "grad_norm": 0.2710007429122925,
469 "learning_rate": 9.44e-05,
470 "loss": 0.8115,
471 "step": 3300
472 },
473 {
474 "epoch": 0.536,
475 "grad_norm": 0.2536482810974121,
476 "learning_rate": 9.28e-05,
477 "loss": 0.8196,
478 "step": 3350
479 },
480 {
481 "epoch": 0.544,
482 "grad_norm": 0.28047412633895874,
483 "learning_rate": 9.120000000000001e-05,
484 "loss": 0.8134,
485 "step": 3400
486 },
487 {
488 "epoch": 0.552,
489 "grad_norm": 0.2554551661014557,
490 "learning_rate": 8.960000000000001e-05,
491 "loss": 0.8085,
492 "step": 3450
493 },
494 {
495 "epoch": 0.56,
496 "grad_norm": 0.2920052707195282,
497 "learning_rate": 8.800000000000001e-05,
498 "loss": 0.8155,
499 "step": 3500
500 },
501 {
502 "epoch": 0.568,
503 "grad_norm": 0.2649592161178589,
504 "learning_rate": 8.64e-05,
505 "loss": 0.8123,
506 "step": 3550
507 },
508 {
509 "epoch": 0.576,
510 "grad_norm": 0.2757607102394104,
511 "learning_rate": 8.48e-05,
512 "loss": 0.8182,
513 "step": 3600
514 },
515 {
516 "epoch": 0.584,
517 "grad_norm": 0.2552868127822876,
518 "learning_rate": 8.32e-05,
519 "loss": 0.8155,
520 "step": 3650
521 },
522 {
523 "epoch": 0.592,
524 "grad_norm": 0.24389928579330444,
525 "learning_rate": 8.16e-05,
526 "loss": 0.7927,
527 "step": 3700
528 },
529 {
530 "epoch": 0.6,
531 "grad_norm": 0.2750285565853119,
532 "learning_rate": 8e-05,
533 "loss": 0.8362,
534 "step": 3750
535 },
536 {
537 "epoch": 0.608,
538 "grad_norm": 0.27113068103790283,
539 "learning_rate": 7.840000000000001e-05,
540 "loss": 0.8225,
541 "step": 3800
542 },
543 {
544 "epoch": 0.616,
545 "grad_norm": 0.25137266516685486,
546 "learning_rate": 7.680000000000001e-05,
547 "loss": 0.8049,
548 "step": 3850
549 },
550 {
551 "epoch": 0.624,
552 "grad_norm": 0.26775482296943665,
553 "learning_rate": 7.52e-05,
554 "loss": 0.8059,
555 "step": 3900
556 },
557 {
558 "epoch": 0.632,
559 "grad_norm": 0.24626025557518005,
560 "learning_rate": 7.36e-05,
561 "loss": 0.8036,
562 "step": 3950
563 },
564 {
565 "epoch": 0.64,
566 "grad_norm": 0.2576785385608673,
567 "learning_rate": 7.2e-05,
568 "loss": 0.828,
569 "step": 4000
570 },
571 {
572 "epoch": 0.648,
573 "grad_norm": 0.28320208191871643,
574 "learning_rate": 7.04e-05,
575 "loss": 0.8015,
576 "step": 4050
577 },
578 {
579 "epoch": 0.656,
580 "grad_norm": 0.292799711227417,
581 "learning_rate": 6.879999999999999e-05,
582 "loss": 0.8165,
583 "step": 4100
584 },
585 {
586 "epoch": 0.664,
587 "grad_norm": 0.2561057507991791,
588 "learning_rate": 6.720000000000001e-05,
589 "loss": 0.8035,
590 "step": 4150
591 },
592 {
593 "epoch": 0.672,
594 "grad_norm": 0.318015456199646,
595 "learning_rate": 6.560000000000001e-05,
596 "loss": 0.7909,
597 "step": 4200
598 },
599 {
600 "epoch": 0.68,
601 "grad_norm": 0.2850799858570099,
602 "learning_rate": 6.400000000000001e-05,
603 "loss": 0.8111,
604 "step": 4250
605 },
606 {
607 "epoch": 0.688,
608 "grad_norm": 0.3318442404270172,
609 "learning_rate": 6.24e-05,
610 "loss": 0.8216,
611 "step": 4300
612 },
613 {
614 "epoch": 0.696,
615 "grad_norm": 0.24898533523082733,
616 "learning_rate": 6.08e-05,
617 "loss": 0.79,
618 "step": 4350
619 },
620 {
621 "epoch": 0.704,
622 "grad_norm": 0.2550944685935974,
623 "learning_rate": 5.92e-05,
624 "loss": 0.7977,
625 "step": 4400
626 },
627 {
628 "epoch": 0.712,
629 "grad_norm": 0.33275166153907776,
630 "learning_rate": 5.76e-05,
631 "loss": 0.808,
632 "step": 4450
633 },
634 {
635 "epoch": 0.72,
636 "grad_norm": 0.2537584900856018,
637 "learning_rate": 5.6000000000000006e-05,
638 "loss": 0.8177,
639 "step": 4500
640 },
641 {
642 "epoch": 0.728,
643 "grad_norm": 0.2836528420448303,
644 "learning_rate": 5.440000000000001e-05,
645 "loss": 0.797,
646 "step": 4550
647 },
648 {
649 "epoch": 0.736,
650 "grad_norm": 0.24697652459144592,
651 "learning_rate": 5.28e-05,
652 "loss": 0.8047,
653 "step": 4600
654 },
655 {
656 "epoch": 0.744,
657 "grad_norm": 0.2920159101486206,
658 "learning_rate": 5.1200000000000004e-05,
659 "loss": 0.793,
660 "step": 4650
661 },
662 {
663 "epoch": 0.752,
664 "grad_norm": 0.24589219689369202,
665 "learning_rate": 4.96e-05,
666 "loss": 0.8218,
667 "step": 4700
668 },
669 {
670 "epoch": 0.76,
671 "grad_norm": 0.28507670760154724,
672 "learning_rate": 4.8e-05,
673 "loss": 0.8143,
674 "step": 4750
675 },
676 {
677 "epoch": 0.768,
678 "grad_norm": 0.22233684360980988,
679 "learning_rate": 4.64e-05,
680 "loss": 0.8108,
681 "step": 4800
682 },
683 {
684 "epoch": 0.776,
685 "grad_norm": 0.24076737463474274,
686 "learning_rate": 4.4800000000000005e-05,
687 "loss": 0.8077,
688 "step": 4850
689 },
690 {
691 "epoch": 0.784,
692 "grad_norm": 0.24421195685863495,
693 "learning_rate": 4.32e-05,
694 "loss": 0.8102,
695 "step": 4900
696 },
697 {
698 "epoch": 0.792,
699 "grad_norm": 0.26924577355384827,
700 "learning_rate": 4.16e-05,
701 "loss": 0.827,
702 "step": 4950
703 },
704 {
705 "epoch": 0.8,
706 "grad_norm": 0.3362084627151489,
707 "learning_rate": 4e-05,
708 "loss": 0.8222,
709 "step": 5000
710 },
711 {
712 "epoch": 0.808,
713 "grad_norm": 0.28752413392066956,
714 "learning_rate": 3.8400000000000005e-05,
715 "loss": 0.8209,
716 "step": 5050
717 },
718 {
719 "epoch": 0.816,
720 "grad_norm": 0.3482488989830017,
721 "learning_rate": 3.68e-05,
722 "loss": 0.8077,
723 "step": 5100
724 },
725 {
726 "epoch": 0.824,
727 "grad_norm": 0.2573867738246918,
728 "learning_rate": 3.52e-05,
729 "loss": 0.8089,
730 "step": 5150
731 },
732 {
733 "epoch": 0.832,
734 "grad_norm": 0.27762147784233093,
735 "learning_rate": 3.3600000000000004e-05,
736 "loss": 0.7974,
737 "step": 5200
738 },
739 {
740 "epoch": 0.84,
741 "grad_norm": 0.30096402764320374,
742 "learning_rate": 3.2000000000000005e-05,
743 "loss": 0.8051,
744 "step": 5250
745 },
746 {
747 "epoch": 0.848,
748 "grad_norm": 0.25133249163627625,
749 "learning_rate": 3.04e-05,
750 "loss": 0.8179,
751 "step": 5300
752 },
753 {
754 "epoch": 0.856,
755 "grad_norm": 0.26828518509864807,
756 "learning_rate": 2.88e-05,
757 "loss": 0.8136,
758 "step": 5350
759 },
760 {
761 "epoch": 0.864,
762 "grad_norm": 0.2636822462081909,
763 "learning_rate": 2.7200000000000004e-05,
764 "loss": 0.8122,
765 "step": 5400
766 },
767 {
768 "epoch": 0.872,
769 "grad_norm": 0.29320311546325684,
770 "learning_rate": 2.5600000000000002e-05,
771 "loss": 0.8294,
772 "step": 5450
773 },
774 {
775 "epoch": 0.88,
776 "grad_norm": 0.25704631209373474,
777 "learning_rate": 2.4e-05,
778 "loss": 0.8278,
779 "step": 5500
780 },
781 {
782 "epoch": 0.888,
783 "grad_norm": 0.3402651250362396,
784 "learning_rate": 2.2400000000000002e-05,
785 "loss": 0.8084,
786 "step": 5550
787 },
788 {
789 "epoch": 0.896,
790 "grad_norm": 0.24089041352272034,
791 "learning_rate": 2.08e-05,
792 "loss": 0.8014,
793 "step": 5600
794 },
795 {
796 "epoch": 0.904,
797 "grad_norm": 0.3702704608440399,
798 "learning_rate": 1.9200000000000003e-05,
799 "loss": 0.804,
800 "step": 5650
801 },
802 {
803 "epoch": 0.912,
804 "grad_norm": 0.295099675655365,
805 "learning_rate": 1.76e-05,
806 "loss": 0.8098,
807 "step": 5700
808 },
809 {
810 "epoch": 0.92,
811 "grad_norm": 0.24626977741718292,
812 "learning_rate": 1.6000000000000003e-05,
813 "loss": 0.8051,
814 "step": 5750
815 },
816 {
817 "epoch": 0.928,
818 "grad_norm": 0.27932465076446533,
819 "learning_rate": 1.44e-05,
820 "loss": 0.8031,
821 "step": 5800
822 },
823 {
824 "epoch": 0.936,
825 "grad_norm": 0.27001097798347473,
826 "learning_rate": 1.2800000000000001e-05,
827 "loss": 0.8068,
828 "step": 5850
829 },
830 {
831 "epoch": 0.944,
832 "grad_norm": 0.2695982754230499,
833 "learning_rate": 1.1200000000000001e-05,
834 "loss": 0.8047,
835 "step": 5900
836 },
837 {
838 "epoch": 0.952,
839 "grad_norm": 0.27733317017555237,
840 "learning_rate": 9.600000000000001e-06,
841 "loss": 0.8238,
842 "step": 5950
843 },
844 {
845 "epoch": 0.96,
846 "grad_norm": 0.25620317459106445,
847 "learning_rate": 8.000000000000001e-06,
848 "loss": 0.78,
849 "step": 6000
850 },
851 {
852 "epoch": 0.968,
853 "grad_norm": 0.24671310186386108,
854 "learning_rate": 6.4000000000000006e-06,
855 "loss": 0.8233,
856 "step": 6050
857 },
858 {
859 "epoch": 0.976,
860 "grad_norm": 0.2986748516559601,
861 "learning_rate": 4.800000000000001e-06,
862 "loss": 0.8183,
863 "step": 6100
864 },
865 {
866 "epoch": 0.984,
867 "grad_norm": 0.28886911273002625,
868 "learning_rate": 3.2000000000000003e-06,
869 "loss": 0.7884,
870 "step": 6150
871 },
872 {
873 "epoch": 0.992,
874 "grad_norm": 0.27886465191841125,
875 "learning_rate": 1.6000000000000001e-06,
876 "loss": 0.7885,
877 "step": 6200
878 },
879 {
880 "epoch": 1.0,
881 "grad_norm": 0.260232537984848,
882 "learning_rate": 0.0,
883 "loss": 0.7775,
884 "step": 6250
885 }
886 ],
887 "logging_steps": 50,
888 "max_steps": 6250,
889 "num_input_tokens_seen": 0,
890 "num_train_epochs": 1,
891 "save_steps": 500,
892 "stateful_callbacks": {
893 "TrainerControl": {
894 "args": {
895 "should_epoch_stop": false,
896 "should_evaluate": false,
897 "should_log": false,
898 "should_save": true,
899 "should_training_stop": true
900 },
901 "attributes": {}
902 }
903 },
904 "total_flos": 3.2752831434633216e+17,
905 "train_batch_size": 2,
906 "trial_name": null,
907 "trial_params": null
908}
909