BitCPM-CANN-8B-unquantized/example/gpu_sft.csv

1	step	train/loss	train/grad_norm	train/learning_rate	train/epoch	train/train_runtime	train/train_samples_per_second	train/train_steps_per_second	train/total_flos	train/train_loss
2	2	1.1492999792099	0.6216375231742859	1.9999999949504854e-06	0.0004617871018126607
3	4	1.0979000329971313	0.681877851486206	3.999999989900971e-06	0.0009235742036253214
4	6	1.1269999742507935	0.784303605556488	6.000000212225132e-06	0.001385361305437982
5	8	1.0542000532150269	0.8737029433250427	7.999999979801942e-06	0.0018471484072506428
6	10	1.2440999746322632	0.7068291902542114	9.999999747378752e-06	0.0023089356254786253
7	12	1.2925000190734863	0.6821666955947876	1.2000000424450263e-05	0.002770722610875964
8	14	1.0843000411987305	0.525643527507782	1.4000000192027073e-05	0.0032325098291039467
9	16	1.0961999893188477	0.43757057189941406	1.5999999959603883e-05	0.0036942968145012856
10	18	1.0614999532699585	0.46141618490219116	1.8000000636675395e-05	0.004156084265559912
11	20	1.332900047302246	0.715879499912262	1.9999999494757503e-05	0.004617871250957251
12	22	1.2070000171661377	0.5926885008811951	1.996917308133561e-05	0.0050796582363545895
13	24	1.2043999433517456	0.5833240747451782	1.9876883015967906e-05	0.005541445221751928
14	26	1.0740000009536743	0.44734400510787964	1.9723698642337695e-05	0.0060032326728105545
15	28	1.1162999868392944	0.3701137900352478	1.9510565834934823e-05	0.006465019658207893
16	30	1.0454000234603882	0.43832680583000183	1.9238796085119247e-05	0.006926806643605232
17	32	1.124899983406067	0.4591037631034851	1.8910064682131633e-05	0.007388593629002571
18	34	1.0686999559402466	0.3873400390148163	1.8526401618146338e-05	0.00785038061439991
19	36	1.0291999578475952	0.40313437581062317	1.8090169760398567e-05	0.008312168531119823
20	38	1.1052000522613525	0.3735405504703522	1.7604059394216165e-05	0.008773955516517162
21	40	1.1555999517440796	0.3818407654762268	1.7071068214136176e-05	0.009235742501914501
22	42	1.0235999822616577	0.4255191683769226	1.6494481315021403e-05	0.00969752948731184
23	44	1.0364999771118164	0.4794503152370453	1.5877853002166376e-05	0.010159316472709179
24	46	1.1344000101089478	0.37273937463760376	1.5224985872919206e-05	0.010621103458106518
25	48	1.0866999626159668	0.417492538690567	1.453990535082994e-05	0.011082890443503857
26	50	1.1038000583648682	0.35408055782318115	1.3826834219798911e-05	0.01154467836022377
27	52	1.1478999853134155	0.3930828273296356	1.3090169886709191e-05	0.012006465345621109
28	54	1.1858999729156494	0.3965947926044464	1.2334453458606731e-05	0.012468252331018448
29	56	1.0096999406814575	0.3860221207141876	1.1564344276848715e-05	0.012930039316415787
30	58	1.114799976348877	0.44393691420555115	1.0784590813273098e-05	0.013391826301813126
31	60	1.079300045967102	0.3605058789253235	9.999999747378752e-06	0.013853613287210464
32	62	1.1766999959945679	0.40689122676849365	9.215408681484405e-06	0.014315400272607803
33	64	1.1075999736785889	0.4002344310283661	8.435655217908788e-06	0.014777187258005142
34	66	1.1866999864578247	0.46947163343429565	7.665546036150772e-06	0.015238975174725056
35	68	1.0311000347137451	0.3296957314014435	6.909830062795663e-06	0.01570076122879982
36	70	1.1088999509811401	0.33858785033226013	6.173165729705943e-06	0.01616254821419716
37	72	1.0720000267028809	0.3967427909374237	5.460095053422265e-06	0.016624337062239647
38	74	1.1460000276565552	0.41202062368392944	4.7750145313329995e-06	0.017086124047636986
39	76	1.0425000190734863	0.38334518671035767	4.1221474020858295e-06	0.017547911033034325
40	78	0.9154000282287598	0.40649303793907166	3.505519543978153e-06	0.018009698018431664
41	80	1.1110999584197998	0.35371580719947815	2.9289321901160292e-06	0.018471485003829002
42	82	1.1672999858856201	0.3381657302379608	2.3959403279150138e-06	0.01893327198922634
43	84	1.2374000549316406	0.3815234303474426	1.909829961732612e-06	0.01939505897462368
44	86	1.2151000499725342	0.38446080684661865	1.4735983313585166e-06	0.01985684596002102
45	88	1.163100004196167	0.40419140458106995	1.0899348126258701e-06	0.020318632945418358
46	90	1.1883000135421753	0.4011874198913574	7.612046601934708e-07	0.020780419930815697
47	92	1.1526999473571777	0.3836020231246948	4.894348535344761e-07	0.021242206916213036
48	94	1.15339994430542	0.452364057302475	2.7630079557638965e-07	0.021703993901610374
49	96	1.062000036239624	0.3502688705921173	1.2311659247643547e-07	0.022165780887007713
50	98	1.0271999835968018	0.4022065997123718	3.0826662111849146e-08	0.022627567872405052
51	100	1.0283000469207764	0.38241174817085266	0.0	0.02308935672044754	183.9481964111328	8.697999954223633	0.5440000295639038	1862467846144.0	1.1177252531051636