nttx's picture
Training in progress, step 100, checkpoint
43f8906 verified
{
"best_metric": 1.6330686807632446,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.3816793893129771,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003816793893129771,
"grad_norm": 1.1639742851257324,
"learning_rate": 1.6666666666666668e-07,
"loss": 1.7599,
"step": 1
},
{
"epoch": 0.003816793893129771,
"eval_loss": 1.690576195716858,
"eval_runtime": 10.0391,
"eval_samples_per_second": 10.957,
"eval_steps_per_second": 1.395,
"step": 1
},
{
"epoch": 0.007633587786259542,
"grad_norm": 0.9837440848350525,
"learning_rate": 3.3333333333333335e-07,
"loss": 1.7152,
"step": 2
},
{
"epoch": 0.011450381679389313,
"grad_norm": 1.191903829574585,
"learning_rate": 5.000000000000001e-07,
"loss": 1.8818,
"step": 3
},
{
"epoch": 0.015267175572519083,
"grad_norm": 1.2343465089797974,
"learning_rate": 6.666666666666667e-07,
"loss": 1.9395,
"step": 4
},
{
"epoch": 0.019083969465648856,
"grad_norm": 1.1668846607208252,
"learning_rate": 8.333333333333333e-07,
"loss": 1.9077,
"step": 5
},
{
"epoch": 0.022900763358778626,
"grad_norm": 1.2681121826171875,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.25,
"step": 6
},
{
"epoch": 0.026717557251908396,
"grad_norm": 1.410936951637268,
"learning_rate": 1.1666666666666668e-06,
"loss": 2.1375,
"step": 7
},
{
"epoch": 0.030534351145038167,
"grad_norm": 1.2283226251602173,
"learning_rate": 1.3333333333333334e-06,
"loss": 2.0093,
"step": 8
},
{
"epoch": 0.03435114503816794,
"grad_norm": 1.3780529499053955,
"learning_rate": 1.5e-06,
"loss": 2.2188,
"step": 9
},
{
"epoch": 0.03816793893129771,
"grad_norm": 1.2002503871917725,
"learning_rate": 1.6666666666666667e-06,
"loss": 2.01,
"step": 10
},
{
"epoch": 0.04198473282442748,
"grad_norm": 1.1847559213638306,
"learning_rate": 1.8333333333333333e-06,
"loss": 1.9388,
"step": 11
},
{
"epoch": 0.04580152671755725,
"grad_norm": 1.1541310548782349,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9568,
"step": 12
},
{
"epoch": 0.04961832061068702,
"grad_norm": 1.1507000923156738,
"learning_rate": 2.166666666666667e-06,
"loss": 1.9077,
"step": 13
},
{
"epoch": 0.05343511450381679,
"grad_norm": 1.1916567087173462,
"learning_rate": 2.3333333333333336e-06,
"loss": 1.9743,
"step": 14
},
{
"epoch": 0.05725190839694656,
"grad_norm": 1.2536592483520508,
"learning_rate": 2.5e-06,
"loss": 2.0885,
"step": 15
},
{
"epoch": 0.061068702290076333,
"grad_norm": 1.296707034111023,
"learning_rate": 2.666666666666667e-06,
"loss": 2.3976,
"step": 16
},
{
"epoch": 0.0648854961832061,
"grad_norm": 1.2552423477172852,
"learning_rate": 2.8333333333333335e-06,
"loss": 1.9453,
"step": 17
},
{
"epoch": 0.06870229007633588,
"grad_norm": 1.0085850954055786,
"learning_rate": 3e-06,
"loss": 1.1812,
"step": 18
},
{
"epoch": 0.07251908396946564,
"grad_norm": 1.083329200744629,
"learning_rate": 3.1666666666666667e-06,
"loss": 1.5001,
"step": 19
},
{
"epoch": 0.07633587786259542,
"grad_norm": 1.091967225074768,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.5606,
"step": 20
},
{
"epoch": 0.08015267175572519,
"grad_norm": 1.0827946662902832,
"learning_rate": 3.5e-06,
"loss": 1.5546,
"step": 21
},
{
"epoch": 0.08396946564885496,
"grad_norm": 1.137137532234192,
"learning_rate": 3.6666666666666666e-06,
"loss": 1.6243,
"step": 22
},
{
"epoch": 0.08778625954198473,
"grad_norm": 1.0543386936187744,
"learning_rate": 3.833333333333334e-06,
"loss": 1.4913,
"step": 23
},
{
"epoch": 0.0916030534351145,
"grad_norm": 1.092016577720642,
"learning_rate": 4.000000000000001e-06,
"loss": 1.4779,
"step": 24
},
{
"epoch": 0.09541984732824428,
"grad_norm": 1.1408716440200806,
"learning_rate": 4.166666666666667e-06,
"loss": 1.7049,
"step": 25
},
{
"epoch": 0.09923664122137404,
"grad_norm": 1.2250564098358154,
"learning_rate": 4.333333333333334e-06,
"loss": 1.6621,
"step": 26
},
{
"epoch": 0.10305343511450382,
"grad_norm": 1.0289937257766724,
"learning_rate": 4.5e-06,
"loss": 1.5643,
"step": 27
},
{
"epoch": 0.10687022900763359,
"grad_norm": 1.1041069030761719,
"learning_rate": 4.666666666666667e-06,
"loss": 1.4019,
"step": 28
},
{
"epoch": 0.11068702290076336,
"grad_norm": 1.0776981115341187,
"learning_rate": 4.833333333333333e-06,
"loss": 1.3278,
"step": 29
},
{
"epoch": 0.11450381679389313,
"grad_norm": 1.094165325164795,
"learning_rate": 5e-06,
"loss": 1.3775,
"step": 30
},
{
"epoch": 0.1183206106870229,
"grad_norm": 1.0802825689315796,
"learning_rate": 4.997482666353287e-06,
"loss": 1.3885,
"step": 31
},
{
"epoch": 0.12213740458015267,
"grad_norm": 1.177674651145935,
"learning_rate": 4.989935734988098e-06,
"loss": 1.4748,
"step": 32
},
{
"epoch": 0.12595419847328243,
"grad_norm": 1.188259482383728,
"learning_rate": 4.977374404419838e-06,
"loss": 1.5043,
"step": 33
},
{
"epoch": 0.1297709923664122,
"grad_norm": 1.1320470571517944,
"learning_rate": 4.959823971496575e-06,
"loss": 1.5926,
"step": 34
},
{
"epoch": 0.13358778625954199,
"grad_norm": 1.0940425395965576,
"learning_rate": 4.937319780454559e-06,
"loss": 1.3909,
"step": 35
},
{
"epoch": 0.13740458015267176,
"grad_norm": 1.0931893587112427,
"learning_rate": 4.909907151739634e-06,
"loss": 1.5625,
"step": 36
},
{
"epoch": 0.14122137404580154,
"grad_norm": 1.0794775485992432,
"learning_rate": 4.8776412907378845e-06,
"loss": 1.4332,
"step": 37
},
{
"epoch": 0.1450381679389313,
"grad_norm": 1.135691523551941,
"learning_rate": 4.8405871765993435e-06,
"loss": 1.4607,
"step": 38
},
{
"epoch": 0.14885496183206107,
"grad_norm": 1.143457055091858,
"learning_rate": 4.7988194313786275e-06,
"loss": 1.5162,
"step": 39
},
{
"epoch": 0.15267175572519084,
"grad_norm": 1.1650444269180298,
"learning_rate": 4.752422169756048e-06,
"loss": 1.5281,
"step": 40
},
{
"epoch": 0.15648854961832062,
"grad_norm": 1.0388603210449219,
"learning_rate": 4.701488829641845e-06,
"loss": 1.2957,
"step": 41
},
{
"epoch": 0.16030534351145037,
"grad_norm": 1.0882115364074707,
"learning_rate": 4.646121984004666e-06,
"loss": 1.4225,
"step": 42
},
{
"epoch": 0.16412213740458015,
"grad_norm": 1.115893840789795,
"learning_rate": 4.586433134303257e-06,
"loss": 1.3005,
"step": 43
},
{
"epoch": 0.16793893129770993,
"grad_norm": 1.2251698970794678,
"learning_rate": 4.522542485937369e-06,
"loss": 1.3565,
"step": 44
},
{
"epoch": 0.1717557251908397,
"grad_norm": 1.0498777627944946,
"learning_rate": 4.454578706170075e-06,
"loss": 1.1824,
"step": 45
},
{
"epoch": 0.17557251908396945,
"grad_norm": 1.0242071151733398,
"learning_rate": 4.382678665009028e-06,
"loss": 1.2668,
"step": 46
},
{
"epoch": 0.17938931297709923,
"grad_norm": 1.2367092370986938,
"learning_rate": 4.3069871595684795e-06,
"loss": 1.2987,
"step": 47
},
{
"epoch": 0.183206106870229,
"grad_norm": 1.0739256143569946,
"learning_rate": 4.227656622467162e-06,
"loss": 1.3642,
"step": 48
},
{
"epoch": 0.18702290076335878,
"grad_norm": 1.1677788496017456,
"learning_rate": 4.144846814849282e-06,
"loss": 1.4148,
"step": 49
},
{
"epoch": 0.19083969465648856,
"grad_norm": 0.8875530958175659,
"learning_rate": 4.058724504646834e-06,
"loss": 1.2016,
"step": 50
},
{
"epoch": 0.19083969465648856,
"eval_loss": 1.661128044128418,
"eval_runtime": 9.665,
"eval_samples_per_second": 11.381,
"eval_steps_per_second": 1.449,
"step": 50
},
{
"epoch": 0.1946564885496183,
"grad_norm": 1.1015959978103638,
"learning_rate": 3.969463130731183e-06,
"loss": 1.684,
"step": 51
},
{
"epoch": 0.1984732824427481,
"grad_norm": 1.2345702648162842,
"learning_rate": 3.8772424536302565e-06,
"loss": 1.8938,
"step": 52
},
{
"epoch": 0.20229007633587787,
"grad_norm": 1.1852645874023438,
"learning_rate": 3.782248193514766e-06,
"loss": 1.931,
"step": 53
},
{
"epoch": 0.20610687022900764,
"grad_norm": 1.2475045919418335,
"learning_rate": 3.684671656182497e-06,
"loss": 1.8701,
"step": 54
},
{
"epoch": 0.2099236641221374,
"grad_norm": 1.1556059122085571,
"learning_rate": 3.5847093477938955e-06,
"loss": 1.9697,
"step": 55
},
{
"epoch": 0.21374045801526717,
"grad_norm": 1.358068823814392,
"learning_rate": 3.4825625791348093e-06,
"loss": 2.2589,
"step": 56
},
{
"epoch": 0.21755725190839695,
"grad_norm": 1.1710163354873657,
"learning_rate": 3.3784370602033572e-06,
"loss": 1.7734,
"step": 57
},
{
"epoch": 0.22137404580152673,
"grad_norm": 1.096484661102295,
"learning_rate": 3.272542485937369e-06,
"loss": 1.6371,
"step": 58
},
{
"epoch": 0.22519083969465647,
"grad_norm": 1.4739948511123657,
"learning_rate": 3.165092113916688e-06,
"loss": 2.1153,
"step": 59
},
{
"epoch": 0.22900763358778625,
"grad_norm": 1.384578824043274,
"learning_rate": 3.056302334890786e-06,
"loss": 1.966,
"step": 60
},
{
"epoch": 0.23282442748091603,
"grad_norm": 1.6774483919143677,
"learning_rate": 2.946392236996592e-06,
"loss": 2.2578,
"step": 61
},
{
"epoch": 0.2366412213740458,
"grad_norm": 1.445744276046753,
"learning_rate": 2.835583164544139e-06,
"loss": 2.2189,
"step": 62
},
{
"epoch": 0.24045801526717558,
"grad_norm": 1.2336068153381348,
"learning_rate": 2.724098272258584e-06,
"loss": 1.7825,
"step": 63
},
{
"epoch": 0.24427480916030533,
"grad_norm": 1.2398353815078735,
"learning_rate": 2.6121620758762877e-06,
"loss": 2.1339,
"step": 64
},
{
"epoch": 0.2480916030534351,
"grad_norm": 1.156707525253296,
"learning_rate": 2.5e-06,
"loss": 1.6296,
"step": 65
},
{
"epoch": 0.25190839694656486,
"grad_norm": 0.9933611750602722,
"learning_rate": 2.3878379241237136e-06,
"loss": 1.135,
"step": 66
},
{
"epoch": 0.25572519083969464,
"grad_norm": 1.2305647134780884,
"learning_rate": 2.2759017277414165e-06,
"loss": 1.4455,
"step": 67
},
{
"epoch": 0.2595419847328244,
"grad_norm": 1.2264878749847412,
"learning_rate": 2.1644168354558623e-06,
"loss": 1.7251,
"step": 68
},
{
"epoch": 0.2633587786259542,
"grad_norm": 1.3337756395339966,
"learning_rate": 2.053607763003409e-06,
"loss": 1.5073,
"step": 69
},
{
"epoch": 0.26717557251908397,
"grad_norm": 1.3730273246765137,
"learning_rate": 1.9436976651092143e-06,
"loss": 1.8398,
"step": 70
},
{
"epoch": 0.27099236641221375,
"grad_norm": 1.2310587167739868,
"learning_rate": 1.8349078860833125e-06,
"loss": 1.6852,
"step": 71
},
{
"epoch": 0.2748091603053435,
"grad_norm": 1.199232578277588,
"learning_rate": 1.7274575140626318e-06,
"loss": 1.6795,
"step": 72
},
{
"epoch": 0.2786259541984733,
"grad_norm": 1.0422477722167969,
"learning_rate": 1.6215629397966432e-06,
"loss": 1.3898,
"step": 73
},
{
"epoch": 0.2824427480916031,
"grad_norm": 1.0897728204727173,
"learning_rate": 1.5174374208651913e-06,
"loss": 1.2757,
"step": 74
},
{
"epoch": 0.2862595419847328,
"grad_norm": 1.0364748239517212,
"learning_rate": 1.415290652206105e-06,
"loss": 1.1572,
"step": 75
},
{
"epoch": 0.2900763358778626,
"grad_norm": 1.1856975555419922,
"learning_rate": 1.3153283438175036e-06,
"loss": 1.5651,
"step": 76
},
{
"epoch": 0.29389312977099236,
"grad_norm": 1.166166067123413,
"learning_rate": 1.217751806485235e-06,
"loss": 1.3438,
"step": 77
},
{
"epoch": 0.29770992366412213,
"grad_norm": 1.2864093780517578,
"learning_rate": 1.122757546369744e-06,
"loss": 1.3476,
"step": 78
},
{
"epoch": 0.3015267175572519,
"grad_norm": 1.0975388288497925,
"learning_rate": 1.0305368692688175e-06,
"loss": 1.5129,
"step": 79
},
{
"epoch": 0.3053435114503817,
"grad_norm": 1.291794776916504,
"learning_rate": 9.412754953531664e-07,
"loss": 1.3399,
"step": 80
},
{
"epoch": 0.30916030534351147,
"grad_norm": 1.0906574726104736,
"learning_rate": 8.551531851507186e-07,
"loss": 1.3289,
"step": 81
},
{
"epoch": 0.31297709923664124,
"grad_norm": 1.090087890625,
"learning_rate": 7.723433775328385e-07,
"loss": 1.2803,
"step": 82
},
{
"epoch": 0.31679389312977096,
"grad_norm": 1.1672545671463013,
"learning_rate": 6.930128404315214e-07,
"loss": 1.4543,
"step": 83
},
{
"epoch": 0.32061068702290074,
"grad_norm": 1.1267986297607422,
"learning_rate": 6.17321334990973e-07,
"loss": 1.5009,
"step": 84
},
{
"epoch": 0.3244274809160305,
"grad_norm": 1.1521706581115723,
"learning_rate": 5.454212938299256e-07,
"loss": 1.3756,
"step": 85
},
{
"epoch": 0.3282442748091603,
"grad_norm": 1.1644761562347412,
"learning_rate": 4.774575140626317e-07,
"loss": 1.5278,
"step": 86
},
{
"epoch": 0.3320610687022901,
"grad_norm": 1.1298956871032715,
"learning_rate": 4.1356686569674344e-07,
"loss": 1.2999,
"step": 87
},
{
"epoch": 0.33587786259541985,
"grad_norm": 0.9898239374160767,
"learning_rate": 3.538780159953348e-07,
"loss": 1.082,
"step": 88
},
{
"epoch": 0.33969465648854963,
"grad_norm": 1.1410307884216309,
"learning_rate": 2.98511170358155e-07,
"loss": 1.3005,
"step": 89
},
{
"epoch": 0.3435114503816794,
"grad_norm": 1.0875471830368042,
"learning_rate": 2.4757783024395244e-07,
"loss": 1.2445,
"step": 90
},
{
"epoch": 0.3473282442748092,
"grad_norm": 1.1469016075134277,
"learning_rate": 2.0118056862137358e-07,
"loss": 1.4154,
"step": 91
},
{
"epoch": 0.3511450381679389,
"grad_norm": 1.0912964344024658,
"learning_rate": 1.59412823400657e-07,
"loss": 1.4289,
"step": 92
},
{
"epoch": 0.3549618320610687,
"grad_norm": 1.2613648176193237,
"learning_rate": 1.223587092621162e-07,
"loss": 1.3402,
"step": 93
},
{
"epoch": 0.35877862595419846,
"grad_norm": 1.010673999786377,
"learning_rate": 9.00928482603669e-08,
"loss": 1.2483,
"step": 94
},
{
"epoch": 0.36259541984732824,
"grad_norm": 1.0055451393127441,
"learning_rate": 6.268021954544095e-08,
"loss": 1.3613,
"step": 95
},
{
"epoch": 0.366412213740458,
"grad_norm": 1.0510636568069458,
"learning_rate": 4.017602850342584e-08,
"loss": 1.1731,
"step": 96
},
{
"epoch": 0.3702290076335878,
"grad_norm": 1.1609764099121094,
"learning_rate": 2.262559558016325e-08,
"loss": 1.3169,
"step": 97
},
{
"epoch": 0.37404580152671757,
"grad_norm": 1.0486476421356201,
"learning_rate": 1.006426501190233e-08,
"loss": 1.1576,
"step": 98
},
{
"epoch": 0.37786259541984735,
"grad_norm": 0.9256502985954285,
"learning_rate": 2.5173336467135266e-09,
"loss": 1.074,
"step": 99
},
{
"epoch": 0.3816793893129771,
"grad_norm": 1.0539581775665283,
"learning_rate": 0.0,
"loss": 1.1377,
"step": 100
},
{
"epoch": 0.3816793893129771,
"eval_loss": 1.6330686807632446,
"eval_runtime": 9.1587,
"eval_samples_per_second": 12.01,
"eval_steps_per_second": 1.529,
"step": 100
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.400272525983744e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}