final-lora-qwen32b / trainer_state.json
lightsource's picture
Upload trainer_state.json with huggingface_hub
0421779 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7692307692307693,
"eval_steps": 500,
"global_step": 140,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005494505494505495,
"grad_norm": 0.24404513835906982,
"learning_rate": 4e-05,
"loss": 1.3921,
"step": 1
},
{
"epoch": 0.01098901098901099,
"grad_norm": 0.25437888503074646,
"learning_rate": 8e-05,
"loss": 1.3836,
"step": 2
},
{
"epoch": 0.016483516483516484,
"grad_norm": 0.26151242852211,
"learning_rate": 0.00012,
"loss": 1.4148,
"step": 3
},
{
"epoch": 0.02197802197802198,
"grad_norm": 0.22220638394355774,
"learning_rate": 0.00016,
"loss": 1.3359,
"step": 4
},
{
"epoch": 0.027472527472527472,
"grad_norm": 0.15509554743766785,
"learning_rate": 0.0002,
"loss": 1.319,
"step": 5
},
{
"epoch": 0.03296703296703297,
"grad_norm": 0.12672632932662964,
"learning_rate": 0.0001999842488663838,
"loss": 1.0436,
"step": 6
},
{
"epoch": 0.038461538461538464,
"grad_norm": 0.11594443768262863,
"learning_rate": 0.00019993700042749937,
"loss": 1.1249,
"step": 7
},
{
"epoch": 0.04395604395604396,
"grad_norm": 0.16988468170166016,
"learning_rate": 0.0001998582695676762,
"loss": 0.978,
"step": 8
},
{
"epoch": 0.04945054945054945,
"grad_norm": 0.16477666795253754,
"learning_rate": 0.00019974808108892016,
"loss": 0.8757,
"step": 9
},
{
"epoch": 0.054945054945054944,
"grad_norm": 0.16230840981006622,
"learning_rate": 0.00019960646970310027,
"loss": 0.7733,
"step": 10
},
{
"epoch": 0.06043956043956044,
"grad_norm": 0.16096125543117523,
"learning_rate": 0.00019943348002101371,
"loss": 0.6367,
"step": 11
},
{
"epoch": 0.06593406593406594,
"grad_norm": 0.17279262840747833,
"learning_rate": 0.00019922916653833248,
"loss": 0.5396,
"step": 12
},
{
"epoch": 0.07142857142857142,
"grad_norm": 0.16378775238990784,
"learning_rate": 0.0001989935936184358,
"loss": 0.4376,
"step": 13
},
{
"epoch": 0.07692307692307693,
"grad_norm": 0.16942651569843292,
"learning_rate": 0.00019872683547213446,
"loss": 0.481,
"step": 14
},
{
"epoch": 0.08241758241758242,
"grad_norm": 0.12053713202476501,
"learning_rate": 0.00019842897613429262,
"loss": 0.4296,
"step": 15
},
{
"epoch": 0.08791208791208792,
"grad_norm": 0.12406298518180847,
"learning_rate": 0.00019810010943735479,
"loss": 0.2941,
"step": 16
},
{
"epoch": 0.09340659340659341,
"grad_norm": 0.10388841480016708,
"learning_rate": 0.00019774033898178667,
"loss": 0.41,
"step": 17
},
{
"epoch": 0.0989010989010989,
"grad_norm": 0.08794189989566803,
"learning_rate": 0.00019734977810343865,
"loss": 0.3058,
"step": 18
},
{
"epoch": 0.1043956043956044,
"grad_norm": 0.09318755567073822,
"learning_rate": 0.00019692854983784235,
"loss": 0.3256,
"step": 19
},
{
"epoch": 0.10989010989010989,
"grad_norm": 0.07988230884075165,
"learning_rate": 0.0001964767868814516,
"loss": 0.3801,
"step": 20
},
{
"epoch": 0.11538461538461539,
"grad_norm": 0.06846581399440765,
"learning_rate": 0.0001959946315498402,
"loss": 0.3631,
"step": 21
},
{
"epoch": 0.12087912087912088,
"grad_norm": 0.09932168573141098,
"learning_rate": 0.0001954822357328692,
"loss": 0.4244,
"step": 22
},
{
"epoch": 0.12637362637362637,
"grad_norm": 0.07102064788341522,
"learning_rate": 0.00019493976084683813,
"loss": 0.3414,
"step": 23
},
{
"epoch": 0.13186813186813187,
"grad_norm": 0.07554670423269272,
"learning_rate": 0.00019436737778363527,
"loss": 0.3206,
"step": 24
},
{
"epoch": 0.13736263736263737,
"grad_norm": 0.06632914394140244,
"learning_rate": 0.0001937652668569028,
"loss": 0.3037,
"step": 25
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.07803873717784882,
"learning_rate": 0.00019313361774523385,
"loss": 0.285,
"step": 26
},
{
"epoch": 0.14835164835164835,
"grad_norm": 0.09491067379713058,
"learning_rate": 0.0001924726294324196,
"loss": 0.3508,
"step": 27
},
{
"epoch": 0.15384615384615385,
"grad_norm": 0.08697083592414856,
"learning_rate": 0.00019178251014476466,
"loss": 0.3275,
"step": 28
},
{
"epoch": 0.15934065934065933,
"grad_norm": 0.08148891478776932,
"learning_rate": 0.00019106347728549135,
"loss": 0.2527,
"step": 29
},
{
"epoch": 0.16483516483516483,
"grad_norm": 0.08663398027420044,
"learning_rate": 0.00019031575736625238,
"loss": 0.2488,
"step": 30
},
{
"epoch": 0.17032967032967034,
"grad_norm": 0.08816689252853394,
"learning_rate": 0.00018953958593577493,
"loss": 0.2511,
"step": 31
},
{
"epoch": 0.17582417582417584,
"grad_norm": 0.0893981084227562,
"learning_rate": 0.00018873520750565718,
"loss": 0.2498,
"step": 32
},
{
"epoch": 0.1813186813186813,
"grad_norm": 0.08614163100719452,
"learning_rate": 0.00018790287547334176,
"loss": 0.2316,
"step": 33
},
{
"epoch": 0.18681318681318682,
"grad_norm": 0.10351146012544632,
"learning_rate": 0.00018704285204228973,
"loss": 0.2733,
"step": 34
},
{
"epoch": 0.19230769230769232,
"grad_norm": 0.08243081718683243,
"learning_rate": 0.0001861554081393806,
"loss": 0.2278,
"step": 35
},
{
"epoch": 0.1978021978021978,
"grad_norm": 0.097475066781044,
"learning_rate": 0.00018524082332956428,
"loss": 0.2459,
"step": 36
},
{
"epoch": 0.2032967032967033,
"grad_norm": 0.08360479772090912,
"learning_rate": 0.00018429938572779152,
"loss": 0.2342,
"step": 37
},
{
"epoch": 0.2087912087912088,
"grad_norm": 0.09262491017580032,
"learning_rate": 0.0001833313919082515,
"loss": 0.234,
"step": 38
},
{
"epoch": 0.21428571428571427,
"grad_norm": 0.11125553399324417,
"learning_rate": 0.00018233714681094404,
"loss": 0.3167,
"step": 39
},
{
"epoch": 0.21978021978021978,
"grad_norm": 0.08724531531333923,
"learning_rate": 0.00018131696364561667,
"loss": 0.217,
"step": 40
},
{
"epoch": 0.22527472527472528,
"grad_norm": 0.08204808831214905,
"learning_rate": 0.00018027116379309638,
"loss": 0.2091,
"step": 41
},
{
"epoch": 0.23076923076923078,
"grad_norm": 0.11685692518949509,
"learning_rate": 0.0001792000767040474,
"loss": 0.2218,
"step": 42
},
{
"epoch": 0.23626373626373626,
"grad_norm": 0.10508550703525543,
"learning_rate": 0.00017810403979518681,
"loss": 0.1959,
"step": 43
},
{
"epoch": 0.24175824175824176,
"grad_norm": 0.13068167865276337,
"learning_rate": 0.00017698339834299061,
"loss": 0.1616,
"step": 44
},
{
"epoch": 0.24725274725274726,
"grad_norm": 0.1325182318687439,
"learning_rate": 0.00017583850537492387,
"loss": 0.1398,
"step": 45
},
{
"epoch": 0.25274725274725274,
"grad_norm": 0.14320158958435059,
"learning_rate": 0.0001746697215582288,
"loss": 0.2189,
"step": 46
},
{
"epoch": 0.25824175824175827,
"grad_norm": 0.11843352764844894,
"learning_rate": 0.00017347741508630672,
"loss": 0.1261,
"step": 47
},
{
"epoch": 0.26373626373626374,
"grad_norm": 0.12478692084550858,
"learning_rate": 0.00017226196156272874,
"loss": 0.2066,
"step": 48
},
{
"epoch": 0.2692307692307692,
"grad_norm": 0.11781392246484756,
"learning_rate": 0.00017102374388291183,
"loss": 0.2071,
"step": 49
},
{
"epoch": 0.27472527472527475,
"grad_norm": 0.10600878298282623,
"learning_rate": 0.0001697631521134985,
"loss": 0.203,
"step": 50
},
{
"epoch": 0.2802197802197802,
"grad_norm": 0.10019295662641525,
"learning_rate": 0.00016848058336947657,
"loss": 0.2265,
"step": 51
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.08874925225973129,
"learning_rate": 0.0001671764416890793,
"loss": 0.1193,
"step": 52
},
{
"epoch": 0.29120879120879123,
"grad_norm": 0.0978781059384346,
"learning_rate": 0.00016585113790650388,
"loss": 0.1311,
"step": 53
},
{
"epoch": 0.2967032967032967,
"grad_norm": 0.12399563938379288,
"learning_rate": 0.00016450508952248956,
"loss": 0.1398,
"step": 54
},
{
"epoch": 0.3021978021978022,
"grad_norm": 0.11917977780103683,
"learning_rate": 0.00016313872057279534,
"loss": 0.149,
"step": 55
},
{
"epoch": 0.3076923076923077,
"grad_norm": 0.1155751645565033,
"learning_rate": 0.0001617524614946192,
"loss": 0.1819,
"step": 56
},
{
"epoch": 0.3131868131868132,
"grad_norm": 0.09933874011039734,
"learning_rate": 0.0001603467489910004,
"loss": 0.0918,
"step": 57
},
{
"epoch": 0.31868131868131866,
"grad_norm": 0.1160176694393158,
"learning_rate": 0.00015892202589324835,
"loss": 0.0983,
"step": 58
},
{
"epoch": 0.3241758241758242,
"grad_norm": 0.12610028684139252,
"learning_rate": 0.0001574787410214407,
"loss": 0.1345,
"step": 59
},
{
"epoch": 0.32967032967032966,
"grad_norm": 0.09502307325601578,
"learning_rate": 0.0001560173490430346,
"loss": 0.0753,
"step": 60
},
{
"epoch": 0.33516483516483514,
"grad_norm": 0.12514734268188477,
"learning_rate": 0.0001545383103296365,
"loss": 0.1218,
"step": 61
},
{
"epoch": 0.34065934065934067,
"grad_norm": 0.10972923040390015,
"learning_rate": 0.00015304209081197425,
"loss": 0.0988,
"step": 62
},
{
"epoch": 0.34615384615384615,
"grad_norm": 0.14897628128528595,
"learning_rate": 0.0001515291618331188,
"loss": 0.1729,
"step": 63
},
{
"epoch": 0.3516483516483517,
"grad_norm": 0.10310367494821548,
"learning_rate": 0.00015000000000000001,
"loss": 0.1261,
"step": 64
},
{
"epoch": 0.35714285714285715,
"grad_norm": 0.11633659899234772,
"learning_rate": 0.00014845508703326504,
"loss": 0.1215,
"step": 65
},
{
"epoch": 0.3626373626373626,
"grad_norm": 0.12089478224515915,
"learning_rate": 0.00014689490961552513,
"loss": 0.1137,
"step": 66
},
{
"epoch": 0.36813186813186816,
"grad_norm": 0.12880107760429382,
"learning_rate": 0.00014531995923803973,
"loss": 0.1254,
"step": 67
},
{
"epoch": 0.37362637362637363,
"grad_norm": 0.10465559363365173,
"learning_rate": 0.00014373073204588556,
"loss": 0.0866,
"step": 68
},
{
"epoch": 0.3791208791208791,
"grad_norm": 0.09393016248941422,
"learning_rate": 0.00014212772868165958,
"loss": 0.0671,
"step": 69
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.09669383615255356,
"learning_rate": 0.00014051145412776535,
"loss": 0.0835,
"step": 70
},
{
"epoch": 0.3901098901098901,
"grad_norm": 0.10696904361248016,
"learning_rate": 0.00013888241754733208,
"loss": 0.1146,
"step": 71
},
{
"epoch": 0.3956043956043956,
"grad_norm": 0.18148086965084076,
"learning_rate": 0.0001372411321238166,
"loss": 0.1937,
"step": 72
},
{
"epoch": 0.4010989010989011,
"grad_norm": 0.11100444942712784,
"learning_rate": 0.00013558811489933908,
"loss": 0.1204,
"step": 73
},
{
"epoch": 0.4065934065934066,
"grad_norm": 0.08652353286743164,
"learning_rate": 0.00013392388661180303,
"loss": 0.0682,
"step": 74
},
{
"epoch": 0.41208791208791207,
"grad_norm": 0.09470050036907196,
"learning_rate": 0.0001322489715308509,
"loss": 0.0638,
"step": 75
},
{
"epoch": 0.4175824175824176,
"grad_norm": 0.11347407102584839,
"learning_rate": 0.00013056389729270738,
"loss": 0.081,
"step": 76
},
{
"epoch": 0.4230769230769231,
"grad_norm": 0.1232433095574379,
"learning_rate": 0.0001288691947339621,
"loss": 0.1186,
"step": 77
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.08470042794942856,
"learning_rate": 0.00012716539772434388,
"loss": 0.061,
"step": 78
},
{
"epoch": 0.4340659340659341,
"grad_norm": 0.10937822610139847,
"learning_rate": 0.00012545304299853977,
"loss": 0.0826,
"step": 79
},
{
"epoch": 0.43956043956043955,
"grad_norm": 0.094424307346344,
"learning_rate": 0.0001237326699871115,
"loss": 0.0689,
"step": 80
},
{
"epoch": 0.44505494505494503,
"grad_norm": 0.11375095695257187,
"learning_rate": 0.00012200482064656248,
"loss": 0.1107,
"step": 81
},
{
"epoch": 0.45054945054945056,
"grad_norm": 0.11452016979455948,
"learning_rate": 0.00012027003928860937,
"loss": 0.0886,
"step": 82
},
{
"epoch": 0.45604395604395603,
"grad_norm": 0.09138914942741394,
"learning_rate": 0.00011852887240871145,
"loss": 0.0825,
"step": 83
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.09349829703569412,
"learning_rate": 0.00011678186851391218,
"loss": 0.0853,
"step": 84
},
{
"epoch": 0.46703296703296704,
"grad_norm": 0.0957733765244484,
"learning_rate": 0.00011502957795004705,
"loss": 0.0705,
"step": 85
},
{
"epoch": 0.4725274725274725,
"grad_norm": 0.11201193928718567,
"learning_rate": 0.00011327255272837221,
"loss": 0.0782,
"step": 86
},
{
"epoch": 0.47802197802197804,
"grad_norm": 0.11689481139183044,
"learning_rate": 0.00011151134635166829,
"loss": 0.0634,
"step": 87
},
{
"epoch": 0.4835164835164835,
"grad_norm": 0.09048259258270264,
"learning_rate": 0.00010974651363987465,
"loss": 0.075,
"step": 88
},
{
"epoch": 0.489010989010989,
"grad_norm": 0.0914902612566948,
"learning_rate": 0.00010797861055530831,
"loss": 0.0697,
"step": 89
},
{
"epoch": 0.4945054945054945,
"grad_norm": 0.0922885537147522,
"learning_rate": 0.0001062081940275234,
"loss": 0.0666,
"step": 90
},
{
"epoch": 0.5,
"grad_norm": 0.08988504856824875,
"learning_rate": 0.00010443582177786564,
"loss": 0.086,
"step": 91
},
{
"epoch": 0.5054945054945055,
"grad_norm": 0.12048965692520142,
"learning_rate": 0.00010266205214377748,
"loss": 0.0905,
"step": 92
},
{
"epoch": 0.510989010989011,
"grad_norm": 0.08413669466972351,
"learning_rate": 0.0001008874439029091,
"loss": 0.059,
"step": 93
},
{
"epoch": 0.5164835164835165,
"grad_norm": 0.09707523882389069,
"learning_rate": 9.91125560970909e-05,
"loss": 0.1015,
"step": 94
},
{
"epoch": 0.521978021978022,
"grad_norm": 0.13043560087680817,
"learning_rate": 9.733794785622253e-05,
"loss": 0.0914,
"step": 95
},
{
"epoch": 0.5274725274725275,
"grad_norm": 0.10451046377420425,
"learning_rate": 9.556417822213435e-05,
"loss": 0.0904,
"step": 96
},
{
"epoch": 0.532967032967033,
"grad_norm": 0.07710960507392883,
"learning_rate": 9.379180597247661e-05,
"loss": 0.0557,
"step": 97
},
{
"epoch": 0.5384615384615384,
"grad_norm": 0.09335189312696457,
"learning_rate": 9.202138944469168e-05,
"loss": 0.0782,
"step": 98
},
{
"epoch": 0.5439560439560439,
"grad_norm": 0.07391183078289032,
"learning_rate": 9.025348636012536e-05,
"loss": 0.0616,
"step": 99
},
{
"epoch": 0.5494505494505495,
"grad_norm": 0.07584051787853241,
"learning_rate": 8.84886536483317e-05,
"loss": 0.0669,
"step": 100
},
{
"epoch": 0.554945054945055,
"grad_norm": 0.07729068398475647,
"learning_rate": 8.672744727162781e-05,
"loss": 0.0635,
"step": 101
},
{
"epoch": 0.5604395604395604,
"grad_norm": 0.0983298122882843,
"learning_rate": 8.497042204995299e-05,
"loss": 0.0556,
"step": 102
},
{
"epoch": 0.5659340659340659,
"grad_norm": 0.07858923077583313,
"learning_rate": 8.321813148608783e-05,
"loss": 0.0551,
"step": 103
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.1307792365550995,
"learning_rate": 8.147112759128859e-05,
"loss": 0.1135,
"step": 104
},
{
"epoch": 0.5769230769230769,
"grad_norm": 0.08517476916313171,
"learning_rate": 7.972996071139064e-05,
"loss": 0.053,
"step": 105
},
{
"epoch": 0.5824175824175825,
"grad_norm": 0.05371192470192909,
"learning_rate": 7.799517935343757e-05,
"loss": 0.0298,
"step": 106
},
{
"epoch": 0.5879120879120879,
"grad_norm": 0.06914077699184418,
"learning_rate": 7.626733001288851e-05,
"loss": 0.0452,
"step": 107
},
{
"epoch": 0.5934065934065934,
"grad_norm": 0.10342265665531158,
"learning_rate": 7.454695700146024e-05,
"loss": 0.0889,
"step": 108
},
{
"epoch": 0.5989010989010989,
"grad_norm": 0.0685519203543663,
"learning_rate": 7.283460227565613e-05,
"loss": 0.0588,
"step": 109
},
{
"epoch": 0.6043956043956044,
"grad_norm": 0.05628138780593872,
"learning_rate": 7.113080526603792e-05,
"loss": 0.046,
"step": 110
},
{
"epoch": 0.6098901098901099,
"grad_norm": 0.11078569293022156,
"learning_rate": 6.94361027072926e-05,
"loss": 0.0791,
"step": 111
},
{
"epoch": 0.6153846153846154,
"grad_norm": 0.05526568740606308,
"learning_rate": 6.775102846914911e-05,
"loss": 0.0559,
"step": 112
},
{
"epoch": 0.6208791208791209,
"grad_norm": 0.07777650654315948,
"learning_rate": 6.607611338819697e-05,
"loss": 0.0574,
"step": 113
},
{
"epoch": 0.6263736263736264,
"grad_norm": 0.06428060680627823,
"learning_rate": 6.441188510066091e-05,
"loss": 0.0386,
"step": 114
},
{
"epoch": 0.6318681318681318,
"grad_norm": 0.1773328185081482,
"learning_rate": 6.275886787618339e-05,
"loss": 0.1229,
"step": 115
},
{
"epoch": 0.6373626373626373,
"grad_norm": 0.05550393462181091,
"learning_rate": 6.111758245266794e-05,
"loss": 0.0414,
"step": 116
},
{
"epoch": 0.6428571428571429,
"grad_norm": 0.041509225964546204,
"learning_rate": 5.9488545872234645e-05,
"loss": 0.0341,
"step": 117
},
{
"epoch": 0.6483516483516484,
"grad_norm": 0.10156530886888504,
"learning_rate": 5.787227131834043e-05,
"loss": 0.0765,
"step": 118
},
{
"epoch": 0.6538461538461539,
"grad_norm": 0.0621609091758728,
"learning_rate": 5.626926795411447e-05,
"loss": 0.0515,
"step": 119
},
{
"epoch": 0.6593406593406593,
"grad_norm": 0.12675149738788605,
"learning_rate": 5.468004076196029e-05,
"loss": 0.0736,
"step": 120
},
{
"epoch": 0.6648351648351648,
"grad_norm": 0.06981629878282547,
"learning_rate": 5.310509038447492e-05,
"loss": 0.07,
"step": 121
},
{
"epoch": 0.6703296703296703,
"grad_norm": 0.05079374462366104,
"learning_rate": 5.1544912966734994e-05,
"loss": 0.0509,
"step": 122
},
{
"epoch": 0.6758241758241759,
"grad_norm": 0.06290542334318161,
"learning_rate": 5.000000000000002e-05,
"loss": 0.0577,
"step": 123
},
{
"epoch": 0.6813186813186813,
"grad_norm": 0.042649202048778534,
"learning_rate": 4.8470838166881226e-05,
"loss": 0.035,
"step": 124
},
{
"epoch": 0.6868131868131868,
"grad_norm": 0.07203595340251923,
"learning_rate": 4.695790918802576e-05,
"loss": 0.0706,
"step": 125
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.04454479739069939,
"learning_rate": 4.546168967036351e-05,
"loss": 0.034,
"step": 126
},
{
"epoch": 0.6978021978021978,
"grad_norm": 0.041393596678972244,
"learning_rate": 4.398265095696539e-05,
"loss": 0.0375,
"step": 127
},
{
"epoch": 0.7032967032967034,
"grad_norm": 0.047695551067590714,
"learning_rate": 4.252125897855932e-05,
"loss": 0.0402,
"step": 128
},
{
"epoch": 0.7087912087912088,
"grad_norm": 0.06419022381305695,
"learning_rate": 4.107797410675166e-05,
"loss": 0.0511,
"step": 129
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.04011767357587814,
"learning_rate": 3.965325100899961e-05,
"loss": 0.0382,
"step": 130
},
{
"epoch": 0.7197802197802198,
"grad_norm": 0.04134465754032135,
"learning_rate": 3.824753850538082e-05,
"loss": 0.0407,
"step": 131
},
{
"epoch": 0.7252747252747253,
"grad_norm": 0.05654672160744667,
"learning_rate": 3.686127942720463e-05,
"loss": 0.0505,
"step": 132
},
{
"epoch": 0.7307692307692307,
"grad_norm": 0.05311698094010353,
"learning_rate": 3.5494910477510445e-05,
"loss": 0.0514,
"step": 133
},
{
"epoch": 0.7362637362637363,
"grad_norm": 0.06260506808757782,
"learning_rate": 3.414886209349615e-05,
"loss": 0.0514,
"step": 134
},
{
"epoch": 0.7417582417582418,
"grad_norm": 0.06393005698919296,
"learning_rate": 3.282355831092072e-05,
"loss": 0.0413,
"step": 135
},
{
"epoch": 0.7472527472527473,
"grad_norm": 0.048107732087373734,
"learning_rate": 3.1519416630523444e-05,
"loss": 0.0479,
"step": 136
},
{
"epoch": 0.7527472527472527,
"grad_norm": 0.04841303825378418,
"learning_rate": 3.0236847886501542e-05,
"loss": 0.0342,
"step": 137
},
{
"epoch": 0.7582417582417582,
"grad_norm": 0.0669633001089096,
"learning_rate": 2.8976256117088195e-05,
"loss": 0.0485,
"step": 138
},
{
"epoch": 0.7637362637362637,
"grad_norm": 0.06344759464263916,
"learning_rate": 2.7738038437271284e-05,
"loss": 0.0535,
"step": 139
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.07120760530233383,
"learning_rate": 2.6522584913693294e-05,
"loss": 0.0465,
"step": 140
}
],
"logging_steps": 1,
"max_steps": 182,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 20,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.7846012682974822e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}