Koto-Small-7B-PT / trainer_state.json
Delta-Vector's picture
Upload folder using huggingface_hub
ba2efc7 verified
raw
history blame
42.1 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9968847352024922,
"eval_steps": 500,
"global_step": 240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004153686396677051,
"grad_norm": 0.46519723534584045,
"learning_rate": 0.0,
"loss": 2.1543,
"step": 1
},
{
"epoch": 0.008307372793354102,
"grad_norm": 0.43996185064315796,
"learning_rate": 2.0000000000000002e-07,
"loss": 2.1152,
"step": 2
},
{
"epoch": 0.012461059190031152,
"grad_norm": 0.4474555253982544,
"learning_rate": 4.0000000000000003e-07,
"loss": 2.187,
"step": 3
},
{
"epoch": 0.016614745586708203,
"grad_norm": 0.45517489314079285,
"learning_rate": 6.000000000000001e-07,
"loss": 2.1881,
"step": 4
},
{
"epoch": 0.020768431983385256,
"grad_norm": 0.4221073389053345,
"learning_rate": 8.000000000000001e-07,
"loss": 2.0898,
"step": 5
},
{
"epoch": 0.024922118380062305,
"grad_norm": 0.4369853734970093,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.1472,
"step": 6
},
{
"epoch": 0.029075804776739357,
"grad_norm": 0.4024302065372467,
"learning_rate": 1.2000000000000002e-06,
"loss": 2.1454,
"step": 7
},
{
"epoch": 0.033229491173416406,
"grad_norm": 0.383690744638443,
"learning_rate": 1.4000000000000001e-06,
"loss": 2.0846,
"step": 8
},
{
"epoch": 0.037383177570093455,
"grad_norm": 0.36159613728523254,
"learning_rate": 1.6000000000000001e-06,
"loss": 2.1333,
"step": 9
},
{
"epoch": 0.04153686396677051,
"grad_norm": 0.3597932755947113,
"learning_rate": 1.8000000000000001e-06,
"loss": 2.1546,
"step": 10
},
{
"epoch": 0.04569055036344756,
"grad_norm": 0.39668431878089905,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.1261,
"step": 11
},
{
"epoch": 0.04984423676012461,
"grad_norm": 0.4318128824234009,
"learning_rate": 2.2e-06,
"loss": 2.1235,
"step": 12
},
{
"epoch": 0.05399792315680166,
"grad_norm": 0.4326289892196655,
"learning_rate": 2.4000000000000003e-06,
"loss": 2.1045,
"step": 13
},
{
"epoch": 0.058151609553478714,
"grad_norm": 0.6398888826370239,
"learning_rate": 2.6e-06,
"loss": 2.1559,
"step": 14
},
{
"epoch": 0.06230529595015576,
"grad_norm": 0.3349069356918335,
"learning_rate": 2.8000000000000003e-06,
"loss": 2.1339,
"step": 15
},
{
"epoch": 0.06645898234683281,
"grad_norm": 0.3410353660583496,
"learning_rate": 3e-06,
"loss": 2.0821,
"step": 16
},
{
"epoch": 0.07061266874350987,
"grad_norm": 0.35577717423439026,
"learning_rate": 3.2000000000000003e-06,
"loss": 2.1912,
"step": 17
},
{
"epoch": 0.07476635514018691,
"grad_norm": 0.3483312427997589,
"learning_rate": 3.4000000000000005e-06,
"loss": 2.161,
"step": 18
},
{
"epoch": 0.07892004153686397,
"grad_norm": 0.33657440543174744,
"learning_rate": 3.6000000000000003e-06,
"loss": 2.1798,
"step": 19
},
{
"epoch": 0.08307372793354102,
"grad_norm": 0.3735242486000061,
"learning_rate": 3.8000000000000005e-06,
"loss": 2.1088,
"step": 20
},
{
"epoch": 0.08722741433021806,
"grad_norm": 0.46339651942253113,
"learning_rate": 4.000000000000001e-06,
"loss": 2.1467,
"step": 21
},
{
"epoch": 0.09138110072689512,
"grad_norm": 0.3805930018424988,
"learning_rate": 4.2000000000000004e-06,
"loss": 2.1484,
"step": 22
},
{
"epoch": 0.09553478712357218,
"grad_norm": 0.3923945724964142,
"learning_rate": 4.4e-06,
"loss": 2.1679,
"step": 23
},
{
"epoch": 0.09968847352024922,
"grad_norm": 0.41755327582359314,
"learning_rate": 4.600000000000001e-06,
"loss": 2.1469,
"step": 24
},
{
"epoch": 0.10384215991692627,
"grad_norm": 0.3602828085422516,
"learning_rate": 4.800000000000001e-06,
"loss": 2.2024,
"step": 25
},
{
"epoch": 0.10799584631360332,
"grad_norm": 0.3939920663833618,
"learning_rate": 5e-06,
"loss": 2.1467,
"step": 26
},
{
"epoch": 0.11214953271028037,
"grad_norm": 0.40471377968788147,
"learning_rate": 5.2e-06,
"loss": 2.1984,
"step": 27
},
{
"epoch": 0.11630321910695743,
"grad_norm": 0.34732070565223694,
"learning_rate": 5.400000000000001e-06,
"loss": 2.2007,
"step": 28
},
{
"epoch": 0.12045690550363447,
"grad_norm": 0.3753240406513214,
"learning_rate": 5.600000000000001e-06,
"loss": 2.1163,
"step": 29
},
{
"epoch": 0.12461059190031153,
"grad_norm": 0.39350414276123047,
"learning_rate": 5.8e-06,
"loss": 2.144,
"step": 30
},
{
"epoch": 0.12876427829698858,
"grad_norm": 0.3573162257671356,
"learning_rate": 6e-06,
"loss": 2.1117,
"step": 31
},
{
"epoch": 0.13291796469366562,
"grad_norm": 0.36146262288093567,
"learning_rate": 6.200000000000001e-06,
"loss": 2.1521,
"step": 32
},
{
"epoch": 0.13707165109034267,
"grad_norm": 0.43568095564842224,
"learning_rate": 6.4000000000000006e-06,
"loss": 2.1501,
"step": 33
},
{
"epoch": 0.14122533748701974,
"grad_norm": 0.45428919792175293,
"learning_rate": 6.600000000000001e-06,
"loss": 2.1042,
"step": 34
},
{
"epoch": 0.14537902388369678,
"grad_norm": 0.5019702315330505,
"learning_rate": 6.800000000000001e-06,
"loss": 2.1406,
"step": 35
},
{
"epoch": 0.14953271028037382,
"grad_norm": 0.3149745762348175,
"learning_rate": 7e-06,
"loss": 2.1663,
"step": 36
},
{
"epoch": 0.1536863966770509,
"grad_norm": 0.4449986219406128,
"learning_rate": 7.2000000000000005e-06,
"loss": 2.1463,
"step": 37
},
{
"epoch": 0.15784008307372793,
"grad_norm": 0.44423943758010864,
"learning_rate": 7.4e-06,
"loss": 2.1362,
"step": 38
},
{
"epoch": 0.16199376947040497,
"grad_norm": 0.33646464347839355,
"learning_rate": 7.600000000000001e-06,
"loss": 2.1198,
"step": 39
},
{
"epoch": 0.16614745586708204,
"grad_norm": 0.32996314764022827,
"learning_rate": 7.800000000000002e-06,
"loss": 2.1126,
"step": 40
},
{
"epoch": 0.1703011422637591,
"grad_norm": 0.4265682101249695,
"learning_rate": 8.000000000000001e-06,
"loss": 2.1239,
"step": 41
},
{
"epoch": 0.17445482866043613,
"grad_norm": 0.4570807218551636,
"learning_rate": 8.2e-06,
"loss": 2.1687,
"step": 42
},
{
"epoch": 0.1786085150571132,
"grad_norm": 0.41856175661087036,
"learning_rate": 8.400000000000001e-06,
"loss": 2.1363,
"step": 43
},
{
"epoch": 0.18276220145379024,
"grad_norm": 0.3138597905635834,
"learning_rate": 8.6e-06,
"loss": 2.0941,
"step": 44
},
{
"epoch": 0.18691588785046728,
"grad_norm": 0.4337351322174072,
"learning_rate": 8.8e-06,
"loss": 2.1599,
"step": 45
},
{
"epoch": 0.19106957424714435,
"grad_norm": 0.49772173166275024,
"learning_rate": 9e-06,
"loss": 2.1445,
"step": 46
},
{
"epoch": 0.1952232606438214,
"grad_norm": 0.3833214044570923,
"learning_rate": 9.200000000000002e-06,
"loss": 2.1087,
"step": 47
},
{
"epoch": 0.19937694704049844,
"grad_norm": 0.3490073084831238,
"learning_rate": 9.4e-06,
"loss": 2.0739,
"step": 48
},
{
"epoch": 0.2035306334371755,
"grad_norm": 0.5244693756103516,
"learning_rate": 9.600000000000001e-06,
"loss": 2.1576,
"step": 49
},
{
"epoch": 0.20768431983385255,
"grad_norm": 0.6005993485450745,
"learning_rate": 9.800000000000001e-06,
"loss": 2.0999,
"step": 50
},
{
"epoch": 0.2118380062305296,
"grad_norm": 0.6089114546775818,
"learning_rate": 1e-05,
"loss": 2.1272,
"step": 51
},
{
"epoch": 0.21599169262720663,
"grad_norm": 0.40243008732795715,
"learning_rate": 9.999316524962347e-06,
"loss": 2.1378,
"step": 52
},
{
"epoch": 0.2201453790238837,
"grad_norm": 0.3728896379470825,
"learning_rate": 9.99726628670463e-06,
"loss": 2.1483,
"step": 53
},
{
"epoch": 0.22429906542056074,
"grad_norm": 0.47435319423675537,
"learning_rate": 9.993849845741525e-06,
"loss": 2.1246,
"step": 54
},
{
"epoch": 0.2284527518172378,
"grad_norm": 0.47093838453292847,
"learning_rate": 9.989068136093873e-06,
"loss": 2.1396,
"step": 55
},
{
"epoch": 0.23260643821391486,
"grad_norm": 0.5783659815788269,
"learning_rate": 9.98292246503335e-06,
"loss": 2.0856,
"step": 56
},
{
"epoch": 0.2367601246105919,
"grad_norm": 0.4810788929462433,
"learning_rate": 9.975414512725058e-06,
"loss": 2.0802,
"step": 57
},
{
"epoch": 0.24091381100726894,
"grad_norm": 0.45532462000846863,
"learning_rate": 9.966546331768192e-06,
"loss": 2.0967,
"step": 58
},
{
"epoch": 0.245067497403946,
"grad_norm": 0.39205724000930786,
"learning_rate": 9.956320346634877e-06,
"loss": 2.164,
"step": 59
},
{
"epoch": 0.24922118380062305,
"grad_norm": 0.4362233281135559,
"learning_rate": 9.944739353007344e-06,
"loss": 2.1157,
"step": 60
},
{
"epoch": 0.2533748701973001,
"grad_norm": 0.43169429898262024,
"learning_rate": 9.931806517013612e-06,
"loss": 2.1002,
"step": 61
},
{
"epoch": 0.25752855659397716,
"grad_norm": 0.3520335257053375,
"learning_rate": 9.917525374361913e-06,
"loss": 2.1048,
"step": 62
},
{
"epoch": 0.2616822429906542,
"grad_norm": 0.4268462359905243,
"learning_rate": 9.901899829374048e-06,
"loss": 2.0897,
"step": 63
},
{
"epoch": 0.26583592938733125,
"grad_norm": 0.46526211500167847,
"learning_rate": 9.884934153917998e-06,
"loss": 2.1256,
"step": 64
},
{
"epoch": 0.2699896157840083,
"grad_norm": 0.3967600166797638,
"learning_rate": 9.86663298624003e-06,
"loss": 2.1649,
"step": 65
},
{
"epoch": 0.27414330218068533,
"grad_norm": 0.3882082998752594,
"learning_rate": 9.847001329696653e-06,
"loss": 2.1514,
"step": 66
},
{
"epoch": 0.2782969885773624,
"grad_norm": 0.3926977813243866,
"learning_rate": 9.826044551386743e-06,
"loss": 2.1225,
"step": 67
},
{
"epoch": 0.2824506749740395,
"grad_norm": 0.37442710995674133,
"learning_rate": 9.803768380684242e-06,
"loss": 2.1526,
"step": 68
},
{
"epoch": 0.2866043613707165,
"grad_norm": 0.3859005570411682,
"learning_rate": 9.780178907671788e-06,
"loss": 2.1437,
"step": 69
},
{
"epoch": 0.29075804776739356,
"grad_norm": 0.36700868606567383,
"learning_rate": 9.755282581475769e-06,
"loss": 2.0886,
"step": 70
},
{
"epoch": 0.2949117341640706,
"grad_norm": 0.32868337631225586,
"learning_rate": 9.729086208503174e-06,
"loss": 2.0149,
"step": 71
},
{
"epoch": 0.29906542056074764,
"grad_norm": 0.5018991827964783,
"learning_rate": 9.701596950580807e-06,
"loss": 2.1765,
"step": 72
},
{
"epoch": 0.3032191069574247,
"grad_norm": 0.46321091055870056,
"learning_rate": 9.672822322997305e-06,
"loss": 2.0778,
"step": 73
},
{
"epoch": 0.3073727933541018,
"grad_norm": 0.36446163058280945,
"learning_rate": 9.642770192448537e-06,
"loss": 2.1116,
"step": 74
},
{
"epoch": 0.3115264797507788,
"grad_norm": 0.5278913974761963,
"learning_rate": 9.611448774886925e-06,
"loss": 2.1583,
"step": 75
},
{
"epoch": 0.31568016614745587,
"grad_norm": 0.3852906823158264,
"learning_rate": 9.578866633275289e-06,
"loss": 2.0911,
"step": 76
},
{
"epoch": 0.31983385254413293,
"grad_norm": 0.33927422761917114,
"learning_rate": 9.545032675245814e-06,
"loss": 2.1511,
"step": 77
},
{
"epoch": 0.32398753894080995,
"grad_norm": 0.4899720251560211,
"learning_rate": 9.509956150664796e-06,
"loss": 2.1541,
"step": 78
},
{
"epoch": 0.328141225337487,
"grad_norm": 0.6482370495796204,
"learning_rate": 9.473646649103819e-06,
"loss": 2.0696,
"step": 79
},
{
"epoch": 0.3322949117341641,
"grad_norm": 0.5560997724533081,
"learning_rate": 9.43611409721806e-06,
"loss": 2.1247,
"step": 80
},
{
"epoch": 0.3364485981308411,
"grad_norm": 0.3883346915245056,
"learning_rate": 9.397368756032445e-06,
"loss": 2.098,
"step": 81
},
{
"epoch": 0.3406022845275182,
"grad_norm": 0.40563803911209106,
"learning_rate": 9.357421218136387e-06,
"loss": 2.1632,
"step": 82
},
{
"epoch": 0.34475597092419524,
"grad_norm": 0.45003846287727356,
"learning_rate": 9.31628240478787e-06,
"loss": 2.1335,
"step": 83
},
{
"epoch": 0.34890965732087226,
"grad_norm": 0.4380098581314087,
"learning_rate": 9.273963562927695e-06,
"loss": 2.0858,
"step": 84
},
{
"epoch": 0.3530633437175493,
"grad_norm": 0.3497319221496582,
"learning_rate": 9.230476262104678e-06,
"loss": 2.1274,
"step": 85
},
{
"epoch": 0.3572170301142264,
"grad_norm": 0.3552245497703552,
"learning_rate": 9.185832391312644e-06,
"loss": 2.1446,
"step": 86
},
{
"epoch": 0.3613707165109034,
"grad_norm": 0.36943352222442627,
"learning_rate": 9.140044155740102e-06,
"loss": 2.1117,
"step": 87
},
{
"epoch": 0.3655244029075805,
"grad_norm": 0.37478867173194885,
"learning_rate": 9.093124073433464e-06,
"loss": 2.1521,
"step": 88
},
{
"epoch": 0.36967808930425755,
"grad_norm": 0.3419424593448639,
"learning_rate": 9.045084971874738e-06,
"loss": 2.113,
"step": 89
},
{
"epoch": 0.37383177570093457,
"grad_norm": 0.30643460154533386,
"learning_rate": 8.995939984474624e-06,
"loss": 2.0633,
"step": 90
},
{
"epoch": 0.37798546209761164,
"grad_norm": 0.361110121011734,
"learning_rate": 8.94570254698197e-06,
"loss": 2.1143,
"step": 91
},
{
"epoch": 0.3821391484942887,
"grad_norm": 0.33192265033721924,
"learning_rate": 8.894386393810563e-06,
"loss": 2.1207,
"step": 92
},
{
"epoch": 0.3862928348909657,
"grad_norm": 0.325773149728775,
"learning_rate": 8.842005554284296e-06,
"loss": 2.1205,
"step": 93
},
{
"epoch": 0.3904465212876428,
"grad_norm": 0.4192400276660919,
"learning_rate": 8.788574348801676e-06,
"loss": 2.172,
"step": 94
},
{
"epoch": 0.39460020768431986,
"grad_norm": 0.3268410563468933,
"learning_rate": 8.734107384920771e-06,
"loss": 2.0921,
"step": 95
},
{
"epoch": 0.3987538940809969,
"grad_norm": 0.34491395950317383,
"learning_rate": 8.67861955336566e-06,
"loss": 2.112,
"step": 96
},
{
"epoch": 0.40290758047767394,
"grad_norm": 0.3280870020389557,
"learning_rate": 8.622126023955446e-06,
"loss": 2.0972,
"step": 97
},
{
"epoch": 0.407061266874351,
"grad_norm": 0.42370373010635376,
"learning_rate": 8.564642241456986e-06,
"loss": 2.1675,
"step": 98
},
{
"epoch": 0.411214953271028,
"grad_norm": 0.3967688977718353,
"learning_rate": 8.506183921362443e-06,
"loss": 2.1162,
"step": 99
},
{
"epoch": 0.4153686396677051,
"grad_norm": 0.3643606901168823,
"learning_rate": 8.446767045592829e-06,
"loss": 2.1448,
"step": 100
},
{
"epoch": 0.4195223260643821,
"grad_norm": 0.403810054063797,
"learning_rate": 8.386407858128707e-06,
"loss": 2.1694,
"step": 101
},
{
"epoch": 0.4236760124610592,
"grad_norm": 0.3851834237575531,
"learning_rate": 8.325122860569241e-06,
"loss": 2.1891,
"step": 102
},
{
"epoch": 0.42782969885773625,
"grad_norm": 0.3491027057170868,
"learning_rate": 8.262928807620843e-06,
"loss": 2.0881,
"step": 103
},
{
"epoch": 0.43198338525441327,
"grad_norm": 0.4147508442401886,
"learning_rate": 8.199842702516584e-06,
"loss": 2.1355,
"step": 104
},
{
"epoch": 0.43613707165109034,
"grad_norm": 0.3745593726634979,
"learning_rate": 8.135881792367686e-06,
"loss": 2.1862,
"step": 105
},
{
"epoch": 0.4402907580477674,
"grad_norm": 0.3806188702583313,
"learning_rate": 8.071063563448341e-06,
"loss": 2.1435,
"step": 106
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.3626170754432678,
"learning_rate": 8.005405736415127e-06,
"loss": 2.0608,
"step": 107
},
{
"epoch": 0.4485981308411215,
"grad_norm": 0.3634461760520935,
"learning_rate": 7.938926261462366e-06,
"loss": 2.1969,
"step": 108
},
{
"epoch": 0.45275181723779856,
"grad_norm": 0.3739028871059418,
"learning_rate": 7.871643313414718e-06,
"loss": 2.1048,
"step": 109
},
{
"epoch": 0.4569055036344756,
"grad_norm": 0.3855268061161041,
"learning_rate": 7.803575286758365e-06,
"loss": 2.1129,
"step": 110
},
{
"epoch": 0.46105919003115264,
"grad_norm": 0.39188092947006226,
"learning_rate": 7.734740790612137e-06,
"loss": 2.1127,
"step": 111
},
{
"epoch": 0.4652128764278297,
"grad_norm": 0.39279860258102417,
"learning_rate": 7.66515864363997e-06,
"loss": 2.1478,
"step": 112
},
{
"epoch": 0.46936656282450673,
"grad_norm": 0.42985665798187256,
"learning_rate": 7.594847868906076e-06,
"loss": 2.1444,
"step": 113
},
{
"epoch": 0.4735202492211838,
"grad_norm": 0.34920892119407654,
"learning_rate": 7.52382768867422e-06,
"loss": 2.1402,
"step": 114
},
{
"epoch": 0.47767393561786087,
"grad_norm": 0.3863445520401001,
"learning_rate": 7.452117519152542e-06,
"loss": 2.1491,
"step": 115
},
{
"epoch": 0.4818276220145379,
"grad_norm": 0.5511898398399353,
"learning_rate": 7.379736965185369e-06,
"loss": 2.1283,
"step": 116
},
{
"epoch": 0.48598130841121495,
"grad_norm": 0.36419305205345154,
"learning_rate": 7.30670581489344e-06,
"loss": 2.1416,
"step": 117
},
{
"epoch": 0.490134994807892,
"grad_norm": 0.431270569562912,
"learning_rate": 7.233044034264034e-06,
"loss": 2.1307,
"step": 118
},
{
"epoch": 0.49428868120456904,
"grad_norm": 0.4779389202594757,
"learning_rate": 7.158771761692464e-06,
"loss": 2.099,
"step": 119
},
{
"epoch": 0.4984423676012461,
"grad_norm": 0.3551599681377411,
"learning_rate": 7.083909302476453e-06,
"loss": 2.1202,
"step": 120
},
{
"epoch": 0.5025960539979232,
"grad_norm": 0.33220580220222473,
"learning_rate": 7.008477123264849e-06,
"loss": 2.1491,
"step": 121
},
{
"epoch": 0.5067497403946002,
"grad_norm": 0.39055803418159485,
"learning_rate": 6.932495846462262e-06,
"loss": 2.1445,
"step": 122
},
{
"epoch": 0.5109034267912772,
"grad_norm": 0.33877313137054443,
"learning_rate": 6.855986244591104e-06,
"loss": 2.1349,
"step": 123
},
{
"epoch": 0.5150571131879543,
"grad_norm": 0.3542743921279907,
"learning_rate": 6.778969234612583e-06,
"loss": 2.098,
"step": 124
},
{
"epoch": 0.5192107995846313,
"grad_norm": 0.35766342282295227,
"learning_rate": 6.701465872208216e-06,
"loss": 2.1363,
"step": 125
},
{
"epoch": 0.5233644859813084,
"grad_norm": 0.35533398389816284,
"learning_rate": 6.6234973460234184e-06,
"loss": 2.0558,
"step": 126
},
{
"epoch": 0.5275181723779855,
"grad_norm": 0.3273533880710602,
"learning_rate": 6.545084971874738e-06,
"loss": 2.1791,
"step": 127
},
{
"epoch": 0.5316718587746625,
"grad_norm": 0.35391753911972046,
"learning_rate": 6.466250186922325e-06,
"loss": 2.054,
"step": 128
},
{
"epoch": 0.5358255451713395,
"grad_norm": 0.295899897813797,
"learning_rate": 6.387014543809224e-06,
"loss": 2.1038,
"step": 129
},
{
"epoch": 0.5399792315680166,
"grad_norm": 0.3650350272655487,
"learning_rate": 6.3073997047691e-06,
"loss": 2.1463,
"step": 130
},
{
"epoch": 0.5441329179646937,
"grad_norm": 0.40882980823516846,
"learning_rate": 6.227427435703997e-06,
"loss": 2.1043,
"step": 131
},
{
"epoch": 0.5482866043613707,
"grad_norm": 0.3036598265171051,
"learning_rate": 6.147119600233758e-06,
"loss": 2.0616,
"step": 132
},
{
"epoch": 0.5524402907580478,
"grad_norm": 0.4223164916038513,
"learning_rate": 6.066498153718735e-06,
"loss": 2.1511,
"step": 133
},
{
"epoch": 0.5565939771547248,
"grad_norm": 0.2908646762371063,
"learning_rate": 5.985585137257401e-06,
"loss": 2.1268,
"step": 134
},
{
"epoch": 0.5607476635514018,
"grad_norm": 0.48902490735054016,
"learning_rate": 5.904402671660551e-06,
"loss": 2.1221,
"step": 135
},
{
"epoch": 0.564901349948079,
"grad_norm": 0.38439658284187317,
"learning_rate": 5.82297295140367e-06,
"loss": 2.1389,
"step": 136
},
{
"epoch": 0.569055036344756,
"grad_norm": 0.4415787160396576,
"learning_rate": 5.74131823855921e-06,
"loss": 2.0875,
"step": 137
},
{
"epoch": 0.573208722741433,
"grad_norm": 0.41299912333488464,
"learning_rate": 5.659460856710346e-06,
"loss": 2.155,
"step": 138
},
{
"epoch": 0.5773624091381101,
"grad_norm": 0.4978012144565582,
"learning_rate": 5.577423184847932e-06,
"loss": 2.0828,
"step": 139
},
{
"epoch": 0.5815160955347871,
"grad_norm": 0.3253823220729828,
"learning_rate": 5.495227651252315e-06,
"loss": 2.094,
"step": 140
},
{
"epoch": 0.5856697819314641,
"grad_norm": 0.40332135558128357,
"learning_rate": 5.412896727361663e-06,
"loss": 2.1003,
"step": 141
},
{
"epoch": 0.5898234683281413,
"grad_norm": 0.296169638633728,
"learning_rate": 5.3304529216284974e-06,
"loss": 2.1062,
"step": 142
},
{
"epoch": 0.5939771547248183,
"grad_norm": 0.35131099820137024,
"learning_rate": 5.247918773366112e-06,
"loss": 2.1015,
"step": 143
},
{
"epoch": 0.5981308411214953,
"grad_norm": 0.30257904529571533,
"learning_rate": 5.165316846586541e-06,
"loss": 2.1598,
"step": 144
},
{
"epoch": 0.6022845275181724,
"grad_norm": 0.3170335590839386,
"learning_rate": 5.082669723831793e-06,
"loss": 2.1115,
"step": 145
},
{
"epoch": 0.6064382139148494,
"grad_norm": 0.29750919342041016,
"learning_rate": 5e-06,
"loss": 2.1695,
"step": 146
},
{
"epoch": 0.6105919003115264,
"grad_norm": 0.36148592829704285,
"learning_rate": 4.917330276168208e-06,
"loss": 2.1656,
"step": 147
},
{
"epoch": 0.6147455867082036,
"grad_norm": 0.2840471863746643,
"learning_rate": 4.8346831534134595e-06,
"loss": 2.1353,
"step": 148
},
{
"epoch": 0.6188992731048806,
"grad_norm": 0.4525928795337677,
"learning_rate": 4.752081226633888e-06,
"loss": 2.1334,
"step": 149
},
{
"epoch": 0.6230529595015576,
"grad_norm": 0.2894962430000305,
"learning_rate": 4.669547078371503e-06,
"loss": 2.1364,
"step": 150
},
{
"epoch": 0.6272066458982347,
"grad_norm": 0.3974563777446747,
"learning_rate": 4.587103272638339e-06,
"loss": 2.1105,
"step": 151
},
{
"epoch": 0.6313603322949117,
"grad_norm": 0.3226485550403595,
"learning_rate": 4.504772348747687e-06,
"loss": 2.1914,
"step": 152
},
{
"epoch": 0.6355140186915887,
"grad_norm": 0.3687591254711151,
"learning_rate": 4.42257681515207e-06,
"loss": 2.107,
"step": 153
},
{
"epoch": 0.6396677050882659,
"grad_norm": 0.3422071635723114,
"learning_rate": 4.340539143289655e-06,
"loss": 2.128,
"step": 154
},
{
"epoch": 0.6438213914849429,
"grad_norm": 0.3275080621242523,
"learning_rate": 4.25868176144079e-06,
"loss": 2.1684,
"step": 155
},
{
"epoch": 0.6479750778816199,
"grad_norm": 0.3418704569339752,
"learning_rate": 4.17702704859633e-06,
"loss": 2.0611,
"step": 156
},
{
"epoch": 0.652128764278297,
"grad_norm": 0.27305227518081665,
"learning_rate": 4.0955973283394525e-06,
"loss": 2.0826,
"step": 157
},
{
"epoch": 0.656282450674974,
"grad_norm": 0.3369821012020111,
"learning_rate": 4.0144148627426e-06,
"loss": 2.1567,
"step": 158
},
{
"epoch": 0.660436137071651,
"grad_norm": 0.25910282135009766,
"learning_rate": 3.9335018462812664e-06,
"loss": 2.0637,
"step": 159
},
{
"epoch": 0.6645898234683282,
"grad_norm": 0.2668653726577759,
"learning_rate": 3.852880399766243e-06,
"loss": 2.0863,
"step": 160
},
{
"epoch": 0.6687435098650052,
"grad_norm": 0.3396942913532257,
"learning_rate": 3.7725725642960047e-06,
"loss": 2.083,
"step": 161
},
{
"epoch": 0.6728971962616822,
"grad_norm": 0.3137992024421692,
"learning_rate": 3.6926002952309015e-06,
"loss": 2.1808,
"step": 162
},
{
"epoch": 0.6770508826583593,
"grad_norm": 0.32238420844078064,
"learning_rate": 3.6129854561907786e-06,
"loss": 2.0964,
"step": 163
},
{
"epoch": 0.6812045690550363,
"grad_norm": 0.26426786184310913,
"learning_rate": 3.533749813077677e-06,
"loss": 2.0951,
"step": 164
},
{
"epoch": 0.6853582554517134,
"grad_norm": 0.2933923006057739,
"learning_rate": 3.4549150281252635e-06,
"loss": 2.041,
"step": 165
},
{
"epoch": 0.6895119418483905,
"grad_norm": 0.37952423095703125,
"learning_rate": 3.3765026539765832e-06,
"loss": 2.1749,
"step": 166
},
{
"epoch": 0.6936656282450675,
"grad_norm": 0.24741414189338684,
"learning_rate": 3.298534127791785e-06,
"loss": 2.1185,
"step": 167
},
{
"epoch": 0.6978193146417445,
"grad_norm": 0.2836434841156006,
"learning_rate": 3.2210307653874175e-06,
"loss": 2.1034,
"step": 168
},
{
"epoch": 0.7019730010384216,
"grad_norm": 0.2631160318851471,
"learning_rate": 3.1440137554088957e-06,
"loss": 2.1095,
"step": 169
},
{
"epoch": 0.7061266874350987,
"grad_norm": 0.29444393515586853,
"learning_rate": 3.06750415353774e-06,
"loss": 2.0951,
"step": 170
},
{
"epoch": 0.7102803738317757,
"grad_norm": 0.2870319187641144,
"learning_rate": 2.991522876735154e-06,
"loss": 2.0856,
"step": 171
},
{
"epoch": 0.7144340602284528,
"grad_norm": 0.25737184286117554,
"learning_rate": 2.9160906975235493e-06,
"loss": 2.1711,
"step": 172
},
{
"epoch": 0.7185877466251298,
"grad_norm": 0.25282764434814453,
"learning_rate": 2.8412282383075362e-06,
"loss": 2.1474,
"step": 173
},
{
"epoch": 0.7227414330218068,
"grad_norm": 0.25563523173332214,
"learning_rate": 2.766955965735968e-06,
"loss": 2.1576,
"step": 174
},
{
"epoch": 0.726895119418484,
"grad_norm": 0.306660920381546,
"learning_rate": 2.693294185106562e-06,
"loss": 2.094,
"step": 175
},
{
"epoch": 0.731048805815161,
"grad_norm": 0.2536129057407379,
"learning_rate": 2.6202630348146323e-06,
"loss": 2.0746,
"step": 176
},
{
"epoch": 0.735202492211838,
"grad_norm": 0.24668152630329132,
"learning_rate": 2.5478824808474613e-06,
"loss": 2.1441,
"step": 177
},
{
"epoch": 0.7393561786085151,
"grad_norm": 0.24908193945884705,
"learning_rate": 2.476172311325783e-06,
"loss": 2.1225,
"step": 178
},
{
"epoch": 0.7435098650051921,
"grad_norm": 0.26486849784851074,
"learning_rate": 2.4051521310939258e-06,
"loss": 2.09,
"step": 179
},
{
"epoch": 0.7476635514018691,
"grad_norm": 0.2715510427951813,
"learning_rate": 2.3348413563600324e-06,
"loss": 2.1207,
"step": 180
},
{
"epoch": 0.7518172377985463,
"grad_norm": 0.24639959633350372,
"learning_rate": 2.265259209387867e-06,
"loss": 2.0995,
"step": 181
},
{
"epoch": 0.7559709241952233,
"grad_norm": 0.24900901317596436,
"learning_rate": 2.1964247132416373e-06,
"loss": 2.1318,
"step": 182
},
{
"epoch": 0.7601246105919003,
"grad_norm": 0.2573296129703522,
"learning_rate": 2.1283566865852824e-06,
"loss": 2.2217,
"step": 183
},
{
"epoch": 0.7642782969885774,
"grad_norm": 0.26032745838165283,
"learning_rate": 2.061073738537635e-06,
"loss": 2.1309,
"step": 184
},
{
"epoch": 0.7684319833852544,
"grad_norm": 0.28223130106925964,
"learning_rate": 1.9945942635848745e-06,
"loss": 2.0551,
"step": 185
},
{
"epoch": 0.7725856697819314,
"grad_norm": 0.24117982387542725,
"learning_rate": 1.928936436551661e-06,
"loss": 2.1201,
"step": 186
},
{
"epoch": 0.7767393561786086,
"grad_norm": 0.23914583027362823,
"learning_rate": 1.864118207632315e-06,
"loss": 2.106,
"step": 187
},
{
"epoch": 0.7808930425752856,
"grad_norm": 0.2441292554140091,
"learning_rate": 1.8001572974834169e-06,
"loss": 2.1211,
"step": 188
},
{
"epoch": 0.7850467289719626,
"grad_norm": 0.365399569272995,
"learning_rate": 1.7370711923791567e-06,
"loss": 2.0911,
"step": 189
},
{
"epoch": 0.7892004153686397,
"grad_norm": 0.26222550868988037,
"learning_rate": 1.6748771394307584e-06,
"loss": 2.0966,
"step": 190
},
{
"epoch": 0.7933541017653167,
"grad_norm": 0.23175619542598724,
"learning_rate": 1.6135921418712959e-06,
"loss": 2.0703,
"step": 191
},
{
"epoch": 0.7975077881619937,
"grad_norm": 0.22840319573879242,
"learning_rate": 1.5532329544071712e-06,
"loss": 2.1146,
"step": 192
},
{
"epoch": 0.8016614745586709,
"grad_norm": 0.23600910604000092,
"learning_rate": 1.4938160786375571e-06,
"loss": 2.1576,
"step": 193
},
{
"epoch": 0.8058151609553479,
"grad_norm": 0.22542668879032135,
"learning_rate": 1.4353577585430152e-06,
"loss": 2.112,
"step": 194
},
{
"epoch": 0.8099688473520249,
"grad_norm": 0.24013273417949677,
"learning_rate": 1.3778739760445552e-06,
"loss": 2.0846,
"step": 195
},
{
"epoch": 0.814122533748702,
"grad_norm": 0.23736749589443207,
"learning_rate": 1.321380446634342e-06,
"loss": 2.1067,
"step": 196
},
{
"epoch": 0.818276220145379,
"grad_norm": 0.24941231310367584,
"learning_rate": 1.2658926150792321e-06,
"loss": 2.1159,
"step": 197
},
{
"epoch": 0.822429906542056,
"grad_norm": 0.25511765480041504,
"learning_rate": 1.2114256511983274e-06,
"loss": 2.0727,
"step": 198
},
{
"epoch": 0.8265835929387332,
"grad_norm": 0.2361282855272293,
"learning_rate": 1.157994445715706e-06,
"loss": 2.1016,
"step": 199
},
{
"epoch": 0.8307372793354102,
"grad_norm": 0.2490163892507553,
"learning_rate": 1.1056136061894386e-06,
"loss": 2.0666,
"step": 200
},
{
"epoch": 0.8348909657320872,
"grad_norm": 0.22846023738384247,
"learning_rate": 1.0542974530180327e-06,
"loss": 2.1226,
"step": 201
},
{
"epoch": 0.8390446521287642,
"grad_norm": 0.24738390743732452,
"learning_rate": 1.0040600155253766e-06,
"loss": 2.1018,
"step": 202
},
{
"epoch": 0.8431983385254413,
"grad_norm": 0.2896912693977356,
"learning_rate": 9.549150281252633e-07,
"loss": 2.0644,
"step": 203
},
{
"epoch": 0.8473520249221184,
"grad_norm": 0.22052256762981415,
"learning_rate": 9.068759265665384e-07,
"loss": 2.0869,
"step": 204
},
{
"epoch": 0.8515057113187954,
"grad_norm": 0.2386987954378128,
"learning_rate": 8.599558442598998e-07,
"loss": 2.0964,
"step": 205
},
{
"epoch": 0.8556593977154725,
"grad_norm": 0.22815701365470886,
"learning_rate": 8.141676086873574e-07,
"loss": 2.1012,
"step": 206
},
{
"epoch": 0.8598130841121495,
"grad_norm": 0.2326398491859436,
"learning_rate": 7.695237378953224e-07,
"loss": 2.1153,
"step": 207
},
{
"epoch": 0.8639667705088265,
"grad_norm": 0.26584866642951965,
"learning_rate": 7.260364370723044e-07,
"loss": 2.0762,
"step": 208
},
{
"epoch": 0.8681204569055037,
"grad_norm": 0.22313201427459717,
"learning_rate": 6.837175952121305e-07,
"loss": 2.0791,
"step": 209
},
{
"epoch": 0.8722741433021807,
"grad_norm": 0.23364050686359406,
"learning_rate": 6.425787818636131e-07,
"loss": 2.1801,
"step": 210
},
{
"epoch": 0.8764278296988577,
"grad_norm": 0.21921421587467194,
"learning_rate": 6.026312439675553e-07,
"loss": 2.1159,
"step": 211
},
{
"epoch": 0.8805815160955348,
"grad_norm": 0.273624986410141,
"learning_rate": 5.63885902781941e-07,
"loss": 2.0313,
"step": 212
},
{
"epoch": 0.8847352024922118,
"grad_norm": 0.21660713851451874,
"learning_rate": 5.263533508961827e-07,
"loss": 2.1475,
"step": 213
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.22784104943275452,
"learning_rate": 4.900438493352056e-07,
"loss": 2.1037,
"step": 214
},
{
"epoch": 0.893042575285566,
"grad_norm": 0.22493554651737213,
"learning_rate": 4.549673247541875e-07,
"loss": 2.1413,
"step": 215
},
{
"epoch": 0.897196261682243,
"grad_norm": 0.2319698929786682,
"learning_rate": 4.211333667247125e-07,
"loss": 2.0693,
"step": 216
},
{
"epoch": 0.90134994807892,
"grad_norm": 0.2203637659549713,
"learning_rate": 3.885512251130763e-07,
"loss": 2.1311,
"step": 217
},
{
"epoch": 0.9055036344755971,
"grad_norm": 0.22149546444416046,
"learning_rate": 3.572298075514652e-07,
"loss": 2.1418,
"step": 218
},
{
"epoch": 0.9096573208722741,
"grad_norm": 0.2249898910522461,
"learning_rate": 3.271776770026963e-07,
"loss": 2.0989,
"step": 219
},
{
"epoch": 0.9138110072689511,
"grad_norm": 0.23055027425289154,
"learning_rate": 2.984030494191942e-07,
"loss": 2.1438,
"step": 220
},
{
"epoch": 0.9179646936656283,
"grad_norm": 0.21457572281360626,
"learning_rate": 2.7091379149682683e-07,
"loss": 2.01,
"step": 221
},
{
"epoch": 0.9221183800623053,
"grad_norm": 0.21807509660720825,
"learning_rate": 2.447174185242324e-07,
"loss": 2.1072,
"step": 222
},
{
"epoch": 0.9262720664589823,
"grad_norm": 0.22586828470230103,
"learning_rate": 2.198210923282118e-07,
"loss": 2.11,
"step": 223
},
{
"epoch": 0.9304257528556594,
"grad_norm": 0.2149934321641922,
"learning_rate": 1.962316193157593e-07,
"loss": 2.1078,
"step": 224
},
{
"epoch": 0.9345794392523364,
"grad_norm": 0.2686188519001007,
"learning_rate": 1.7395544861325718e-07,
"loss": 2.1032,
"step": 225
},
{
"epoch": 0.9387331256490135,
"grad_norm": 0.21735844016075134,
"learning_rate": 1.5299867030334815e-07,
"loss": 2.1412,
"step": 226
},
{
"epoch": 0.9428868120456906,
"grad_norm": 0.2169795036315918,
"learning_rate": 1.333670137599713e-07,
"loss": 2.1258,
"step": 227
},
{
"epoch": 0.9470404984423676,
"grad_norm": 0.2194252610206604,
"learning_rate": 1.1506584608200366e-07,
"loss": 2.166,
"step": 228
},
{
"epoch": 0.9511941848390446,
"grad_norm": 0.2147681564092636,
"learning_rate": 9.810017062595322e-08,
"loss": 2.1009,
"step": 229
},
{
"epoch": 0.9553478712357217,
"grad_norm": 0.22832895815372467,
"learning_rate": 8.247462563808816e-08,
"loss": 2.1068,
"step": 230
},
{
"epoch": 0.9595015576323987,
"grad_norm": 0.2108795940876007,
"learning_rate": 6.819348298638839e-08,
"loss": 2.1595,
"step": 231
},
{
"epoch": 0.9636552440290758,
"grad_norm": 0.21970967948436737,
"learning_rate": 5.526064699265754e-08,
"loss": 2.0614,
"step": 232
},
{
"epoch": 0.9678089304257529,
"grad_norm": 0.2157040536403656,
"learning_rate": 4.367965336512403e-08,
"loss": 2.0851,
"step": 233
},
{
"epoch": 0.9719626168224299,
"grad_norm": 0.20249901711940765,
"learning_rate": 3.345366823180929e-08,
"loss": 2.1191,
"step": 234
},
{
"epoch": 0.9761163032191069,
"grad_norm": 0.22388389706611633,
"learning_rate": 2.4585487274942922e-08,
"loss": 2.0653,
"step": 235
},
{
"epoch": 0.980269989615784,
"grad_norm": 0.21466441452503204,
"learning_rate": 1.7077534966650767e-08,
"loss": 2.1259,
"step": 236
},
{
"epoch": 0.9844236760124611,
"grad_norm": 0.2480291873216629,
"learning_rate": 1.0931863906127327e-08,
"loss": 2.1256,
"step": 237
},
{
"epoch": 0.9885773624091381,
"grad_norm": 0.20534351468086243,
"learning_rate": 6.150154258476315e-09,
"loss": 2.1574,
"step": 238
},
{
"epoch": 0.9927310488058152,
"grad_norm": 0.2120267003774643,
"learning_rate": 2.7337132953697555e-09,
"loss": 2.1358,
"step": 239
},
{
"epoch": 0.9968847352024922,
"grad_norm": 0.2108861654996872,
"learning_rate": 6.834750376549793e-10,
"loss": 2.1028,
"step": 240
}
],
"logging_steps": 1,
"max_steps": 240,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 120,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4.2286664699672e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}