nttx's picture
Training in progress, step 100, checkpoint
743cd39 verified
{
"best_metric": 2.5903985500335693,
"best_model_checkpoint": "miner_id_24/checkpoint-100",
"epoch": 0.03209371364384001,
"eval_steps": 50,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003209371364384001,
"grad_norm": 27.996723175048828,
"learning_rate": 5.000000000000001e-07,
"loss": 8.3536,
"step": 1
},
{
"epoch": 0.0003209371364384001,
"eval_loss": 9.608317375183105,
"eval_runtime": 113.195,
"eval_samples_per_second": 46.362,
"eval_steps_per_second": 11.591,
"step": 1
},
{
"epoch": 0.0006418742728768002,
"grad_norm": 26.085769653320312,
"learning_rate": 1.0000000000000002e-06,
"loss": 8.5873,
"step": 2
},
{
"epoch": 0.0009628114093152004,
"grad_norm": 25.967973709106445,
"learning_rate": 1.5e-06,
"loss": 8.5002,
"step": 3
},
{
"epoch": 0.0012837485457536004,
"grad_norm": 27.765409469604492,
"learning_rate": 2.0000000000000003e-06,
"loss": 8.3604,
"step": 4
},
{
"epoch": 0.0016046856821920006,
"grad_norm": 25.767414093017578,
"learning_rate": 2.5e-06,
"loss": 8.6333,
"step": 5
},
{
"epoch": 0.0019256228186304008,
"grad_norm": 26.109840393066406,
"learning_rate": 3e-06,
"loss": 8.7597,
"step": 6
},
{
"epoch": 0.002246559955068801,
"grad_norm": 25.485050201416016,
"learning_rate": 3.5e-06,
"loss": 8.9975,
"step": 7
},
{
"epoch": 0.002567497091507201,
"grad_norm": 24.807462692260742,
"learning_rate": 4.000000000000001e-06,
"loss": 8.2029,
"step": 8
},
{
"epoch": 0.0028884342279456013,
"grad_norm": 25.710582733154297,
"learning_rate": 4.5e-06,
"loss": 8.9657,
"step": 9
},
{
"epoch": 0.003209371364384001,
"grad_norm": 27.383886337280273,
"learning_rate": 5e-06,
"loss": 9.0463,
"step": 10
},
{
"epoch": 0.0035303085008224016,
"grad_norm": 26.514135360717773,
"learning_rate": 4.99847706754774e-06,
"loss": 8.4198,
"step": 11
},
{
"epoch": 0.0038512456372608015,
"grad_norm": 27.8021183013916,
"learning_rate": 4.993910125649561e-06,
"loss": 8.8458,
"step": 12
},
{
"epoch": 0.004172182773699202,
"grad_norm": 28.006664276123047,
"learning_rate": 4.986304738420684e-06,
"loss": 9.017,
"step": 13
},
{
"epoch": 0.004493119910137602,
"grad_norm": 27.38217544555664,
"learning_rate": 4.975670171853926e-06,
"loss": 9.0249,
"step": 14
},
{
"epoch": 0.004814057046576002,
"grad_norm": 29.5772705078125,
"learning_rate": 4.962019382530521e-06,
"loss": 8.8165,
"step": 15
},
{
"epoch": 0.005134994183014402,
"grad_norm": 26.28485679626465,
"learning_rate": 4.9453690018345144e-06,
"loss": 8.6984,
"step": 16
},
{
"epoch": 0.0054559313194528026,
"grad_norm": 24.394834518432617,
"learning_rate": 4.925739315689991e-06,
"loss": 8.6414,
"step": 17
},
{
"epoch": 0.0057768684558912025,
"grad_norm": 29.212730407714844,
"learning_rate": 4.903154239845798e-06,
"loss": 8.4465,
"step": 18
},
{
"epoch": 0.0060978055923296024,
"grad_norm": 27.20821762084961,
"learning_rate": 4.8776412907378845e-06,
"loss": 8.5804,
"step": 19
},
{
"epoch": 0.006418742728768002,
"grad_norm": 27.378538131713867,
"learning_rate": 4.849231551964771e-06,
"loss": 8.4343,
"step": 20
},
{
"epoch": 0.006739679865206402,
"grad_norm": 25.864442825317383,
"learning_rate": 4.817959636416969e-06,
"loss": 8.0501,
"step": 21
},
{
"epoch": 0.007060617001644803,
"grad_norm": 26.03072166442871,
"learning_rate": 4.783863644106502e-06,
"loss": 8.24,
"step": 22
},
{
"epoch": 0.007381554138083203,
"grad_norm": 27.477052688598633,
"learning_rate": 4.746985115747918e-06,
"loss": 8.0171,
"step": 23
},
{
"epoch": 0.007702491274521603,
"grad_norm": 28.43156623840332,
"learning_rate": 4.707368982147318e-06,
"loss": 8.3216,
"step": 24
},
{
"epoch": 0.008023428410960003,
"grad_norm": 26.4052677154541,
"learning_rate": 4.665063509461098e-06,
"loss": 7.8686,
"step": 25
},
{
"epoch": 0.008344365547398404,
"grad_norm": 28.45978546142578,
"learning_rate": 4.620120240391065e-06,
"loss": 8.188,
"step": 26
},
{
"epoch": 0.008665302683836803,
"grad_norm": 26.55103874206543,
"learning_rate": 4.572593931387604e-06,
"loss": 7.5533,
"step": 27
},
{
"epoch": 0.008986239820275204,
"grad_norm": 28.572845458984375,
"learning_rate": 4.522542485937369e-06,
"loss": 7.6591,
"step": 28
},
{
"epoch": 0.009307176956713605,
"grad_norm": 26.830053329467773,
"learning_rate": 4.470026884016805e-06,
"loss": 7.5189,
"step": 29
},
{
"epoch": 0.009628114093152004,
"grad_norm": 28.91061782836914,
"learning_rate": 4.415111107797445e-06,
"loss": 7.598,
"step": 30
},
{
"epoch": 0.009949051229590404,
"grad_norm": 26.380746841430664,
"learning_rate": 4.357862063693486e-06,
"loss": 7.248,
"step": 31
},
{
"epoch": 0.010269988366028803,
"grad_norm": 28.354726791381836,
"learning_rate": 4.2983495008466285e-06,
"loss": 7.2304,
"step": 32
},
{
"epoch": 0.010590925502467204,
"grad_norm": 28.017242431640625,
"learning_rate": 4.236645926147493e-06,
"loss": 7.2276,
"step": 33
},
{
"epoch": 0.010911862638905605,
"grad_norm": 27.592439651489258,
"learning_rate": 4.172826515897146e-06,
"loss": 7.1646,
"step": 34
},
{
"epoch": 0.011232799775344004,
"grad_norm": 27.620161056518555,
"learning_rate": 4.106969024216348e-06,
"loss": 6.9436,
"step": 35
},
{
"epoch": 0.011553736911782405,
"grad_norm": 26.74669647216797,
"learning_rate": 4.039153688314146e-06,
"loss": 6.539,
"step": 36
},
{
"epoch": 0.011874674048220804,
"grad_norm": 27.177555084228516,
"learning_rate": 3.969463130731183e-06,
"loss": 6.7528,
"step": 37
},
{
"epoch": 0.012195611184659205,
"grad_norm": 25.203859329223633,
"learning_rate": 3.897982258676867e-06,
"loss": 6.2012,
"step": 38
},
{
"epoch": 0.012516548321097606,
"grad_norm": 27.01671600341797,
"learning_rate": 3.824798160583012e-06,
"loss": 6.1814,
"step": 39
},
{
"epoch": 0.012837485457536005,
"grad_norm": 25.485734939575195,
"learning_rate": 3.7500000000000005e-06,
"loss": 6.5055,
"step": 40
},
{
"epoch": 0.013158422593974406,
"grad_norm": 26.390384674072266,
"learning_rate": 3.6736789069647273e-06,
"loss": 6.1332,
"step": 41
},
{
"epoch": 0.013479359730412805,
"grad_norm": 27.709156036376953,
"learning_rate": 3.595927866972694e-06,
"loss": 6.1574,
"step": 42
},
{
"epoch": 0.013800296866851205,
"grad_norm": 27.608366012573242,
"learning_rate": 3.516841607689501e-06,
"loss": 5.9933,
"step": 43
},
{
"epoch": 0.014121234003289606,
"grad_norm": 27.30472183227539,
"learning_rate": 3.436516483539781e-06,
"loss": 5.9736,
"step": 44
},
{
"epoch": 0.014442171139728005,
"grad_norm": 29.357925415039062,
"learning_rate": 3.3550503583141726e-06,
"loss": 6.0565,
"step": 45
},
{
"epoch": 0.014763108276166406,
"grad_norm": 27.473421096801758,
"learning_rate": 3.272542485937369e-06,
"loss": 6.1957,
"step": 46
},
{
"epoch": 0.015084045412604805,
"grad_norm": 28.399824142456055,
"learning_rate": 3.189093389542498e-06,
"loss": 5.8297,
"step": 47
},
{
"epoch": 0.015404982549043206,
"grad_norm": 27.2939510345459,
"learning_rate": 3.1048047389991693e-06,
"loss": 5.7787,
"step": 48
},
{
"epoch": 0.015725919685481607,
"grad_norm": 32.542903900146484,
"learning_rate": 3.019779227044398e-06,
"loss": 6.1701,
"step": 49
},
{
"epoch": 0.016046856821920006,
"grad_norm": 32.60709762573242,
"learning_rate": 2.9341204441673267e-06,
"loss": 6.9105,
"step": 50
},
{
"epoch": 0.016046856821920006,
"eval_loss": 4.4282355308532715,
"eval_runtime": 114.0485,
"eval_samples_per_second": 46.016,
"eval_steps_per_second": 11.504,
"step": 50
},
{
"epoch": 0.016367793958358405,
"grad_norm": 24.92586326599121,
"learning_rate": 2.847932752400164e-06,
"loss": 3.9654,
"step": 51
},
{
"epoch": 0.016688731094796808,
"grad_norm": 24.382604598999023,
"learning_rate": 2.761321158169134e-06,
"loss": 3.8923,
"step": 52
},
{
"epoch": 0.017009668231235207,
"grad_norm": 24.6019229888916,
"learning_rate": 2.6743911843603134e-06,
"loss": 3.6808,
"step": 53
},
{
"epoch": 0.017330605367673606,
"grad_norm": 24.33039093017578,
"learning_rate": 2.587248741756253e-06,
"loss": 3.7393,
"step": 54
},
{
"epoch": 0.01765154250411201,
"grad_norm": 24.681549072265625,
"learning_rate": 2.5e-06,
"loss": 3.5747,
"step": 55
},
{
"epoch": 0.017972479640550407,
"grad_norm": 24.564939498901367,
"learning_rate": 2.4127512582437486e-06,
"loss": 3.573,
"step": 56
},
{
"epoch": 0.018293416776988806,
"grad_norm": 23.479808807373047,
"learning_rate": 2.325608815639687e-06,
"loss": 3.4547,
"step": 57
},
{
"epoch": 0.01861435391342721,
"grad_norm": 25.647430419921875,
"learning_rate": 2.238678841830867e-06,
"loss": 3.5706,
"step": 58
},
{
"epoch": 0.018935291049865608,
"grad_norm": 23.934444427490234,
"learning_rate": 2.1520672475998374e-06,
"loss": 3.3241,
"step": 59
},
{
"epoch": 0.019256228186304007,
"grad_norm": 23.319473266601562,
"learning_rate": 2.0658795558326745e-06,
"loss": 3.3996,
"step": 60
},
{
"epoch": 0.019577165322742406,
"grad_norm": 23.8126220703125,
"learning_rate": 1.9802207729556023e-06,
"loss": 3.0784,
"step": 61
},
{
"epoch": 0.01989810245918081,
"grad_norm": 24.619556427001953,
"learning_rate": 1.895195261000831e-06,
"loss": 3.4374,
"step": 62
},
{
"epoch": 0.020219039595619208,
"grad_norm": 23.282445907592773,
"learning_rate": 1.8109066104575023e-06,
"loss": 3.1921,
"step": 63
},
{
"epoch": 0.020539976732057607,
"grad_norm": 23.131887435913086,
"learning_rate": 1.7274575140626318e-06,
"loss": 3.1839,
"step": 64
},
{
"epoch": 0.02086091386849601,
"grad_norm": 24.023595809936523,
"learning_rate": 1.6449496416858285e-06,
"loss": 2.9598,
"step": 65
},
{
"epoch": 0.02118185100493441,
"grad_norm": 23.428220748901367,
"learning_rate": 1.56348351646022e-06,
"loss": 3.1564,
"step": 66
},
{
"epoch": 0.021502788141372808,
"grad_norm": 22.029972076416016,
"learning_rate": 1.4831583923105e-06,
"loss": 2.8426,
"step": 67
},
{
"epoch": 0.02182372527781121,
"grad_norm": 23.444753646850586,
"learning_rate": 1.4040721330273063e-06,
"loss": 2.7818,
"step": 68
},
{
"epoch": 0.02214466241424961,
"grad_norm": 23.392112731933594,
"learning_rate": 1.3263210930352737e-06,
"loss": 2.8383,
"step": 69
},
{
"epoch": 0.02246559955068801,
"grad_norm": 24.041671752929688,
"learning_rate": 1.2500000000000007e-06,
"loss": 3.0414,
"step": 70
},
{
"epoch": 0.022786536687126407,
"grad_norm": 21.68594741821289,
"learning_rate": 1.1752018394169882e-06,
"loss": 2.873,
"step": 71
},
{
"epoch": 0.02310747382356481,
"grad_norm": 21.509824752807617,
"learning_rate": 1.1020177413231334e-06,
"loss": 2.7585,
"step": 72
},
{
"epoch": 0.02342841096000321,
"grad_norm": 21.97166633605957,
"learning_rate": 1.0305368692688175e-06,
"loss": 2.7142,
"step": 73
},
{
"epoch": 0.023749348096441608,
"grad_norm": 21.628463745117188,
"learning_rate": 9.608463116858544e-07,
"loss": 2.8777,
"step": 74
},
{
"epoch": 0.02407028523288001,
"grad_norm": 22.004776000976562,
"learning_rate": 8.930309757836517e-07,
"loss": 2.8746,
"step": 75
},
{
"epoch": 0.02439122236931841,
"grad_norm": 21.029932022094727,
"learning_rate": 8.271734841028553e-07,
"loss": 2.8362,
"step": 76
},
{
"epoch": 0.02471215950575681,
"grad_norm": 20.30879020690918,
"learning_rate": 7.633540738525066e-07,
"loss": 2.6938,
"step": 77
},
{
"epoch": 0.02503309664219521,
"grad_norm": 20.107864379882812,
"learning_rate": 7.016504991533727e-07,
"loss": 2.6287,
"step": 78
},
{
"epoch": 0.02535403377863361,
"grad_norm": 21.4448299407959,
"learning_rate": 6.421379363065142e-07,
"loss": 2.6291,
"step": 79
},
{
"epoch": 0.02567497091507201,
"grad_norm": 20.82808494567871,
"learning_rate": 5.848888922025553e-07,
"loss": 3.0268,
"step": 80
},
{
"epoch": 0.025995908051510412,
"grad_norm": 20.990262985229492,
"learning_rate": 5.299731159831953e-07,
"loss": 2.806,
"step": 81
},
{
"epoch": 0.02631684518794881,
"grad_norm": 19.37321662902832,
"learning_rate": 4.774575140626317e-07,
"loss": 2.5534,
"step": 82
},
{
"epoch": 0.02663778232438721,
"grad_norm": 20.37537956237793,
"learning_rate": 4.27406068612396e-07,
"loss": 2.766,
"step": 83
},
{
"epoch": 0.02695871946082561,
"grad_norm": 20.045385360717773,
"learning_rate": 3.798797596089351e-07,
"loss": 2.6121,
"step": 84
},
{
"epoch": 0.027279656597264012,
"grad_norm": 20.654422760009766,
"learning_rate": 3.3493649053890325e-07,
"loss": 2.8861,
"step": 85
},
{
"epoch": 0.02760059373370241,
"grad_norm": 20.056547164916992,
"learning_rate": 2.9263101785268253e-07,
"loss": 2.8262,
"step": 86
},
{
"epoch": 0.02792153087014081,
"grad_norm": 20.1599063873291,
"learning_rate": 2.53014884252083e-07,
"loss": 2.7126,
"step": 87
},
{
"epoch": 0.028242468006579213,
"grad_norm": 20.382301330566406,
"learning_rate": 2.1613635589349756e-07,
"loss": 3.0595,
"step": 88
},
{
"epoch": 0.02856340514301761,
"grad_norm": 20.944210052490234,
"learning_rate": 1.8204036358303173e-07,
"loss": 2.8264,
"step": 89
},
{
"epoch": 0.02888434227945601,
"grad_norm": 21.320999145507812,
"learning_rate": 1.507684480352292e-07,
"loss": 2.9996,
"step": 90
},
{
"epoch": 0.029205279415894413,
"grad_norm": 21.694704055786133,
"learning_rate": 1.223587092621162e-07,
"loss": 2.9851,
"step": 91
},
{
"epoch": 0.029526216552332812,
"grad_norm": 21.299489974975586,
"learning_rate": 9.684576015420277e-08,
"loss": 2.8274,
"step": 92
},
{
"epoch": 0.02984715368877121,
"grad_norm": 20.7717342376709,
"learning_rate": 7.426068431000883e-08,
"loss": 3.2581,
"step": 93
},
{
"epoch": 0.03016809082520961,
"grad_norm": 22.040687561035156,
"learning_rate": 5.463099816548578e-08,
"loss": 2.9888,
"step": 94
},
{
"epoch": 0.030489027961648013,
"grad_norm": 22.77414321899414,
"learning_rate": 3.798061746947995e-08,
"loss": 3.0421,
"step": 95
},
{
"epoch": 0.030809965098086412,
"grad_norm": 24.892927169799805,
"learning_rate": 2.4329828146074096e-08,
"loss": 3.1848,
"step": 96
},
{
"epoch": 0.03113090223452481,
"grad_norm": 23.968238830566406,
"learning_rate": 1.3695261579316776e-08,
"loss": 3.1579,
"step": 97
},
{
"epoch": 0.031451839370963214,
"grad_norm": 26.281328201293945,
"learning_rate": 6.089874350439507e-09,
"loss": 3.3636,
"step": 98
},
{
"epoch": 0.03177277650740161,
"grad_norm": 26.528987884521484,
"learning_rate": 1.5229324522605949e-09,
"loss": 4.1474,
"step": 99
},
{
"epoch": 0.03209371364384001,
"grad_norm": 33.00212860107422,
"learning_rate": 0.0,
"loss": 4.9432,
"step": 100
},
{
"epoch": 0.03209371364384001,
"eval_loss": 2.5903985500335693,
"eval_runtime": 114.0548,
"eval_samples_per_second": 46.013,
"eval_steps_per_second": 11.503,
"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": 1.93544513912832e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}