deepseek-coder-EHR-reviewer / trainer_state.json
Dudeman523's picture
Upload folder using huggingface_hub
7d43d33 verified
Raw
History Blame Contribute Delete
21.4 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 130,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08,
"grad_norm": 0.28953391313552856,
"learning_rate": 0.0,
"loss": 1.5722,
"step": 1
},
{
"epoch": 0.16,
"grad_norm": 0.8176532983779907,
"learning_rate": 5e-05,
"loss": 1.6985,
"step": 2
},
{
"epoch": 0.24,
"grad_norm": 0.3097916841506958,
"learning_rate": 0.0001,
"loss": 1.6881,
"step": 3
},
{
"epoch": 0.32,
"grad_norm": 0.2527393400669098,
"learning_rate": 0.00015000000000000001,
"loss": 1.4264,
"step": 4
},
{
"epoch": 0.4,
"grad_norm": 0.24198105931282043,
"learning_rate": 0.0002,
"loss": 1.4774,
"step": 5
},
{
"epoch": 0.48,
"grad_norm": 0.3159346282482147,
"learning_rate": 0.00019996891820008164,
"loss": 1.4202,
"step": 6
},
{
"epoch": 0.56,
"grad_norm": 0.2564707100391388,
"learning_rate": 0.00019987569212189224,
"loss": 1.269,
"step": 7
},
{
"epoch": 0.64,
"grad_norm": 0.23875507712364197,
"learning_rate": 0.00019972037971811802,
"loss": 1.2743,
"step": 8
},
{
"epoch": 0.72,
"grad_norm": 0.23356954753398895,
"learning_rate": 0.00019950307753654017,
"loss": 1.2787,
"step": 9
},
{
"epoch": 0.8,
"grad_norm": 0.19216932356357574,
"learning_rate": 0.00019922392066001722,
"loss": 1.2942,
"step": 10
},
{
"epoch": 0.88,
"grad_norm": 0.1985635757446289,
"learning_rate": 0.00019888308262251285,
"loss": 1.1964,
"step": 11
},
{
"epoch": 0.96,
"grad_norm": 0.229434996843338,
"learning_rate": 0.00019848077530122083,
"loss": 1.2045,
"step": 12
},
{
"epoch": 1.0,
"grad_norm": 0.2626841366291046,
"learning_rate": 0.00019801724878485438,
"loss": 1.1632,
"step": 13
},
{
"epoch": 1.08,
"grad_norm": 0.17352429032325745,
"learning_rate": 0.00019749279121818235,
"loss": 1.0233,
"step": 14
},
{
"epoch": 1.16,
"grad_norm": 0.17997071146965027,
"learning_rate": 0.0001969077286229078,
"loss": 1.1428,
"step": 15
},
{
"epoch": 1.24,
"grad_norm": 0.20514199137687683,
"learning_rate": 0.0001962624246950012,
"loss": 1.0458,
"step": 16
},
{
"epoch": 1.32,
"grad_norm": 0.1919875144958496,
"learning_rate": 0.0001955572805786141,
"loss": 1.0891,
"step": 17
},
{
"epoch": 1.4,
"grad_norm": 0.2113831490278244,
"learning_rate": 0.0001947927346167132,
"loss": 1.0665,
"step": 18
},
{
"epoch": 1.48,
"grad_norm": 0.2384316474199295,
"learning_rate": 0.00019396926207859084,
"loss": 1.0647,
"step": 19
},
{
"epoch": 1.56,
"grad_norm": 0.211042582988739,
"learning_rate": 0.00019308737486442045,
"loss": 1.0915,
"step": 20
},
{
"epoch": 1.6400000000000001,
"grad_norm": 0.2224583476781845,
"learning_rate": 0.00019214762118704076,
"loss": 1.0171,
"step": 21
},
{
"epoch": 1.72,
"grad_norm": 0.2714601457118988,
"learning_rate": 0.00019115058523116733,
"loss": 1.0123,
"step": 22
},
{
"epoch": 1.8,
"grad_norm": 0.2280339151620865,
"learning_rate": 0.0001900968867902419,
"loss": 1.0397,
"step": 23
},
{
"epoch": 1.88,
"grad_norm": 0.22726675868034363,
"learning_rate": 0.0001889871808811469,
"loss": 0.9798,
"step": 24
},
{
"epoch": 1.96,
"grad_norm": 0.2550331652164459,
"learning_rate": 0.00018782215733702286,
"loss": 0.9968,
"step": 25
},
{
"epoch": 2.0,
"grad_norm": 0.34511101245880127,
"learning_rate": 0.00018660254037844388,
"loss": 1.048,
"step": 26
},
{
"epoch": 2.08,
"grad_norm": 0.23089861869812012,
"learning_rate": 0.00018532908816321558,
"loss": 0.9269,
"step": 27
},
{
"epoch": 2.16,
"grad_norm": 0.24394914507865906,
"learning_rate": 0.00018400259231507717,
"loss": 0.8919,
"step": 28
},
{
"epoch": 2.24,
"grad_norm": 0.30287623405456543,
"learning_rate": 0.0001826238774315995,
"loss": 0.8256,
"step": 29
},
{
"epoch": 2.32,
"grad_norm": 0.27338889241218567,
"learning_rate": 0.00018119380057158568,
"loss": 0.835,
"step": 30
},
{
"epoch": 2.4,
"grad_norm": 0.29981502890586853,
"learning_rate": 0.00017971325072229226,
"loss": 0.8704,
"step": 31
},
{
"epoch": 2.48,
"grad_norm": 0.3309312164783478,
"learning_rate": 0.000178183148246803,
"loss": 0.789,
"step": 32
},
{
"epoch": 2.56,
"grad_norm": 0.3238545358181,
"learning_rate": 0.0001766044443118978,
"loss": 0.8849,
"step": 33
},
{
"epoch": 2.64,
"grad_norm": 0.3397984206676483,
"learning_rate": 0.00017497812029677344,
"loss": 0.8189,
"step": 34
},
{
"epoch": 2.7199999999999998,
"grad_norm": 0.35023701190948486,
"learning_rate": 0.00017330518718298264,
"loss": 0.7097,
"step": 35
},
{
"epoch": 2.8,
"grad_norm": 0.3406246304512024,
"learning_rate": 0.00017158668492597186,
"loss": 0.8693,
"step": 36
},
{
"epoch": 2.88,
"grad_norm": 0.3438313603401184,
"learning_rate": 0.00016982368180860728,
"loss": 0.8223,
"step": 37
},
{
"epoch": 2.96,
"grad_norm": 0.4065425992012024,
"learning_rate": 0.00016801727377709194,
"loss": 0.8186,
"step": 38
},
{
"epoch": 3.0,
"grad_norm": 0.4739357531070709,
"learning_rate": 0.00016616858375968595,
"loss": 0.8048,
"step": 39
},
{
"epoch": 3.08,
"grad_norm": 0.35221514105796814,
"learning_rate": 0.00016427876096865394,
"loss": 0.6978,
"step": 40
},
{
"epoch": 3.16,
"grad_norm": 0.3512212038040161,
"learning_rate": 0.00016234898018587337,
"loss": 0.6649,
"step": 41
},
{
"epoch": 3.24,
"grad_norm": 0.40452665090560913,
"learning_rate": 0.00016038044103254775,
"loss": 0.5536,
"step": 42
},
{
"epoch": 3.32,
"grad_norm": 0.42410480976104736,
"learning_rate": 0.000158374367223479,
"loss": 0.6382,
"step": 43
},
{
"epoch": 3.4,
"grad_norm": 0.4782675504684448,
"learning_rate": 0.0001563320058063622,
"loss": 0.6315,
"step": 44
},
{
"epoch": 3.48,
"grad_norm": 0.5449334383010864,
"learning_rate": 0.00015425462638657595,
"loss": 0.5778,
"step": 45
},
{
"epoch": 3.56,
"grad_norm": 0.46281757950782776,
"learning_rate": 0.0001521435203379498,
"loss": 0.6091,
"step": 46
},
{
"epoch": 3.64,
"grad_norm": 0.4751776456832886,
"learning_rate": 0.00015000000000000001,
"loss": 0.5331,
"step": 47
},
{
"epoch": 3.7199999999999998,
"grad_norm": 0.46167129278182983,
"learning_rate": 0.00014782539786213183,
"loss": 0.4681,
"step": 48
},
{
"epoch": 3.8,
"grad_norm": 0.4780837893486023,
"learning_rate": 0.0001456210657353163,
"loss": 0.672,
"step": 49
},
{
"epoch": 3.88,
"grad_norm": 0.5023096203804016,
"learning_rate": 0.00014338837391175582,
"loss": 0.5885,
"step": 50
},
{
"epoch": 3.96,
"grad_norm": 0.5084037780761719,
"learning_rate": 0.00014112871031306119,
"loss": 0.4834,
"step": 51
},
{
"epoch": 4.0,
"grad_norm": 0.674580454826355,
"learning_rate": 0.00013884347962746948,
"loss": 0.5686,
"step": 52
},
{
"epoch": 4.08,
"grad_norm": 0.43982091546058655,
"learning_rate": 0.00013653410243663952,
"loss": 0.4963,
"step": 53
},
{
"epoch": 4.16,
"grad_norm": 0.42599549889564514,
"learning_rate": 0.00013420201433256689,
"loss": 0.3999,
"step": 54
},
{
"epoch": 4.24,
"grad_norm": 0.486558198928833,
"learning_rate": 0.00013184866502516845,
"loss": 0.316,
"step": 55
},
{
"epoch": 4.32,
"grad_norm": 0.48547783493995667,
"learning_rate": 0.00012947551744109043,
"loss": 0.3903,
"step": 56
},
{
"epoch": 4.4,
"grad_norm": 0.5628557205200195,
"learning_rate": 0.00012708404681430053,
"loss": 0.3848,
"step": 57
},
{
"epoch": 4.48,
"grad_norm": 0.5618835091590881,
"learning_rate": 0.00012467573976902935,
"loss": 0.2887,
"step": 58
},
{
"epoch": 4.5600000000000005,
"grad_norm": 0.6056803464889526,
"learning_rate": 0.00012225209339563145,
"loss": 0.4522,
"step": 59
},
{
"epoch": 4.64,
"grad_norm": 0.6191115975379944,
"learning_rate": 0.00011981461431993977,
"loss": 0.4124,
"step": 60
},
{
"epoch": 4.72,
"grad_norm": 0.6690419912338257,
"learning_rate": 0.00011736481776669306,
"loss": 0.3412,
"step": 61
},
{
"epoch": 4.8,
"grad_norm": 0.6222251057624817,
"learning_rate": 0.00011490422661761744,
"loss": 0.418,
"step": 62
},
{
"epoch": 4.88,
"grad_norm": 0.5270496010780334,
"learning_rate": 0.00011243437046474853,
"loss": 0.3544,
"step": 63
},
{
"epoch": 4.96,
"grad_norm": 0.5269222259521484,
"learning_rate": 0.00010995678465958168,
"loss": 0.2764,
"step": 64
},
{
"epoch": 5.0,
"grad_norm": 0.6673203110694885,
"learning_rate": 0.00010747300935864243,
"loss": 0.3733,
"step": 65
},
{
"epoch": 5.08,
"grad_norm": 0.4564249515533447,
"learning_rate": 0.00010498458856606972,
"loss": 0.2778,
"step": 66
},
{
"epoch": 5.16,
"grad_norm": 0.4839026927947998,
"learning_rate": 0.0001024930691738073,
"loss": 0.2279,
"step": 67
},
{
"epoch": 5.24,
"grad_norm": 0.43552613258361816,
"learning_rate": 0.0001,
"loss": 0.175,
"step": 68
},
{
"epoch": 5.32,
"grad_norm": 0.46979570388793945,
"learning_rate": 9.750693082619273e-05,
"loss": 0.2543,
"step": 69
},
{
"epoch": 5.4,
"grad_norm": 0.5092229843139648,
"learning_rate": 9.501541143393028e-05,
"loss": 0.201,
"step": 70
},
{
"epoch": 5.48,
"grad_norm": 0.5519248843193054,
"learning_rate": 9.252699064135758e-05,
"loss": 0.164,
"step": 71
},
{
"epoch": 5.5600000000000005,
"grad_norm": 0.6465537548065186,
"learning_rate": 9.004321534041835e-05,
"loss": 0.2746,
"step": 72
},
{
"epoch": 5.64,
"grad_norm": 0.5870795845985413,
"learning_rate": 8.756562953525152e-05,
"loss": 0.2603,
"step": 73
},
{
"epoch": 5.72,
"grad_norm": 0.5716047883033752,
"learning_rate": 8.509577338238255e-05,
"loss": 0.202,
"step": 74
},
{
"epoch": 5.8,
"grad_norm": 0.5910769701004028,
"learning_rate": 8.263518223330697e-05,
"loss": 0.2665,
"step": 75
},
{
"epoch": 5.88,
"grad_norm": 0.5262706279754639,
"learning_rate": 8.018538568006027e-05,
"loss": 0.2061,
"step": 76
},
{
"epoch": 5.96,
"grad_norm": 0.49615827202796936,
"learning_rate": 7.774790660436858e-05,
"loss": 0.149,
"step": 77
},
{
"epoch": 6.0,
"grad_norm": 0.6431592106819153,
"learning_rate": 7.532426023097063e-05,
"loss": 0.1859,
"step": 78
},
{
"epoch": 6.08,
"grad_norm": 0.42441222071647644,
"learning_rate": 7.291595318569951e-05,
"loss": 0.1663,
"step": 79
},
{
"epoch": 6.16,
"grad_norm": 0.4150922894477844,
"learning_rate": 7.052448255890957e-05,
"loss": 0.1467,
"step": 80
},
{
"epoch": 6.24,
"grad_norm": 0.29602235555648804,
"learning_rate": 6.815133497483157e-05,
"loss": 0.0848,
"step": 81
},
{
"epoch": 6.32,
"grad_norm": 0.42598751187324524,
"learning_rate": 6.579798566743314e-05,
"loss": 0.1635,
"step": 82
},
{
"epoch": 6.4,
"grad_norm": 0.4359506368637085,
"learning_rate": 6.34658975633605e-05,
"loss": 0.1292,
"step": 83
},
{
"epoch": 6.48,
"grad_norm": 0.3560805320739746,
"learning_rate": 6.115652037253053e-05,
"loss": 0.0794,
"step": 84
},
{
"epoch": 6.5600000000000005,
"grad_norm": 0.4551486074924469,
"learning_rate": 5.887128968693887e-05,
"loss": 0.173,
"step": 85
},
{
"epoch": 6.64,
"grad_norm": 0.4439886808395386,
"learning_rate": 5.6611626088244194e-05,
"loss": 0.1145,
"step": 86
},
{
"epoch": 6.72,
"grad_norm": 0.5100005865097046,
"learning_rate": 5.43789342646837e-05,
"loss": 0.0928,
"step": 87
},
{
"epoch": 6.8,
"grad_norm": 0.5324984788894653,
"learning_rate": 5.217460213786821e-05,
"loss": 0.1449,
"step": 88
},
{
"epoch": 6.88,
"grad_norm": 0.4849751591682434,
"learning_rate": 5.000000000000002e-05,
"loss": 0.113,
"step": 89
},
{
"epoch": 6.96,
"grad_norm": 0.5481641888618469,
"learning_rate": 4.78564796620502e-05,
"loss": 0.1038,
"step": 90
},
{
"epoch": 7.0,
"grad_norm": 0.5893111824989319,
"learning_rate": 4.574537361342407e-05,
"loss": 0.1294,
"step": 91
},
{
"epoch": 7.08,
"grad_norm": 0.3522264063358307,
"learning_rate": 4.3667994193637796e-05,
"loss": 0.0949,
"step": 92
},
{
"epoch": 7.16,
"grad_norm": 0.2923271059989929,
"learning_rate": 4.1625632776521037e-05,
"loss": 0.0769,
"step": 93
},
{
"epoch": 7.24,
"grad_norm": 0.2633121907711029,
"learning_rate": 3.961955896745224e-05,
"loss": 0.0503,
"step": 94
},
{
"epoch": 7.32,
"grad_norm": 0.3277730345726013,
"learning_rate": 3.7651019814126654e-05,
"loss": 0.0855,
"step": 95
},
{
"epoch": 7.4,
"grad_norm": 0.29757440090179443,
"learning_rate": 3.5721239031346066e-05,
"loss": 0.0734,
"step": 96
},
{
"epoch": 7.48,
"grad_norm": 0.24998295307159424,
"learning_rate": 3.383141624031408e-05,
"loss": 0.0493,
"step": 97
},
{
"epoch": 7.5600000000000005,
"grad_norm": 0.394760400056839,
"learning_rate": 3.198272622290804e-05,
"loss": 0.1148,
"step": 98
},
{
"epoch": 7.64,
"grad_norm": 0.29309213161468506,
"learning_rate": 3.0176318191392726e-05,
"loss": 0.0738,
"step": 99
},
{
"epoch": 7.72,
"grad_norm": 0.29871276021003723,
"learning_rate": 2.8413315074028158e-05,
"loss": 0.0541,
"step": 100
},
{
"epoch": 7.8,
"grad_norm": 0.3551546335220337,
"learning_rate": 2.669481281701739e-05,
"loss": 0.0872,
"step": 101
},
{
"epoch": 7.88,
"grad_norm": 0.2906927466392517,
"learning_rate": 2.502187970322657e-05,
"loss": 0.0623,
"step": 102
},
{
"epoch": 7.96,
"grad_norm": 0.25703781843185425,
"learning_rate": 2.339555568810221e-05,
"loss": 0.0456,
"step": 103
},
{
"epoch": 8.0,
"grad_norm": 0.5031088590621948,
"learning_rate": 2.181685175319702e-05,
"loss": 0.1069,
"step": 104
},
{
"epoch": 8.08,
"grad_norm": 0.25756052136421204,
"learning_rate": 2.0286749277707782e-05,
"loss": 0.0645,
"step": 105
},
{
"epoch": 8.16,
"grad_norm": 0.20370423793792725,
"learning_rate": 1.880619942841435e-05,
"loss": 0.0433,
"step": 106
},
{
"epoch": 8.24,
"grad_norm": 0.19165390729904175,
"learning_rate": 1.7376122568400532e-05,
"loss": 0.0335,
"step": 107
},
{
"epoch": 8.32,
"grad_norm": 0.2646007537841797,
"learning_rate": 1.5997407684922862e-05,
"loss": 0.0591,
"step": 108
},
{
"epoch": 8.4,
"grad_norm": 0.2121558040380478,
"learning_rate": 1.467091183678444e-05,
"loss": 0.0486,
"step": 109
},
{
"epoch": 8.48,
"grad_norm": 0.18979164958000183,
"learning_rate": 1.339745962155613e-05,
"loss": 0.0349,
"step": 110
},
{
"epoch": 8.56,
"grad_norm": 0.2944222092628479,
"learning_rate": 1.2177842662977135e-05,
"loss": 0.0667,
"step": 111
},
{
"epoch": 8.64,
"grad_norm": 0.2515968978404999,
"learning_rate": 1.1012819118853147e-05,
"loss": 0.0553,
"step": 112
},
{
"epoch": 8.72,
"grad_norm": 0.3551047146320343,
"learning_rate": 9.903113209758096e-06,
"loss": 0.0369,
"step": 113
},
{
"epoch": 8.8,
"grad_norm": 0.25821536779403687,
"learning_rate": 8.849414768832687e-06,
"loss": 0.074,
"step": 114
},
{
"epoch": 8.88,
"grad_norm": 0.20208875834941864,
"learning_rate": 7.852378812959227e-06,
"loss": 0.0489,
"step": 115
},
{
"epoch": 8.96,
"grad_norm": 0.19253306090831757,
"learning_rate": 6.9126251355795864e-06,
"loss": 0.035,
"step": 116
},
{
"epoch": 9.0,
"grad_norm": 0.26008549332618713,
"learning_rate": 6.030737921409169e-06,
"loss": 0.0405,
"step": 117
},
{
"epoch": 9.08,
"grad_norm": 0.2207937240600586,
"learning_rate": 5.20726538328683e-06,
"loss": 0.0516,
"step": 118
},
{
"epoch": 9.16,
"grad_norm": 0.15153822302818298,
"learning_rate": 4.442719421385922e-06,
"loss": 0.0339,
"step": 119
},
{
"epoch": 9.24,
"grad_norm": 0.15037600696086884,
"learning_rate": 3.7375753049987973e-06,
"loss": 0.0296,
"step": 120
},
{
"epoch": 9.32,
"grad_norm": 0.21942156553268433,
"learning_rate": 3.092271377092215e-06,
"loss": 0.0523,
"step": 121
},
{
"epoch": 9.4,
"grad_norm": 0.17263451218605042,
"learning_rate": 2.5072087818176382e-06,
"loss": 0.0448,
"step": 122
},
{
"epoch": 9.48,
"grad_norm": 0.17209623754024506,
"learning_rate": 1.9827512151456173e-06,
"loss": 0.0368,
"step": 123
},
{
"epoch": 9.56,
"grad_norm": 0.19878874719142914,
"learning_rate": 1.5192246987791981e-06,
"loss": 0.0491,
"step": 124
},
{
"epoch": 9.64,
"grad_norm": 0.18710798025131226,
"learning_rate": 1.1169173774871478e-06,
"loss": 0.0554,
"step": 125
},
{
"epoch": 9.72,
"grad_norm": 0.15621885657310486,
"learning_rate": 7.760793399827937e-07,
"loss": 0.0286,
"step": 126
},
{
"epoch": 9.8,
"grad_norm": 0.2060844600200653,
"learning_rate": 4.969224634598591e-07,
"loss": 0.0536,
"step": 127
},
{
"epoch": 9.88,
"grad_norm": 0.18659313023090363,
"learning_rate": 2.7962028188198706e-07,
"loss": 0.0436,
"step": 128
},
{
"epoch": 9.96,
"grad_norm": 0.16247068345546722,
"learning_rate": 1.2430787810776555e-07,
"loss": 0.0337,
"step": 129
},
{
"epoch": 10.0,
"grad_norm": 0.20341025292873383,
"learning_rate": 3.1081799918375454e-08,
"loss": 0.0294,
"step": 130
}
],
"logging_steps": 1,
"max_steps": 130,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.699203553209549e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}