nttx's picture
Training in progress, step 200, checkpoint
ea13b04 verified
{
"best_metric": 0.7339931726455688,
"best_model_checkpoint": "miner_id_24/checkpoint-200",
"epoch": 0.11228070175438597,
"eval_steps": 50,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005614035087719298,
"grad_norm": 0.4464113712310791,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.0783,
"step": 1
},
{
"epoch": 0.0005614035087719298,
"eval_loss": 1.550947904586792,
"eval_runtime": 122.3583,
"eval_samples_per_second": 24.518,
"eval_steps_per_second": 12.259,
"step": 1
},
{
"epoch": 0.0011228070175438596,
"grad_norm": 0.4096737205982208,
"learning_rate": 6.666666666666667e-06,
"loss": 0.7808,
"step": 2
},
{
"epoch": 0.0016842105263157896,
"grad_norm": 0.3668423891067505,
"learning_rate": 1e-05,
"loss": 0.7447,
"step": 3
},
{
"epoch": 0.002245614035087719,
"grad_norm": 0.39215508103370667,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.8963,
"step": 4
},
{
"epoch": 0.002807017543859649,
"grad_norm": 0.43132394552230835,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.8422,
"step": 5
},
{
"epoch": 0.003368421052631579,
"grad_norm": 0.41981956362724304,
"learning_rate": 2e-05,
"loss": 0.9042,
"step": 6
},
{
"epoch": 0.003929824561403509,
"grad_norm": 0.3964403569698334,
"learning_rate": 2.3333333333333336e-05,
"loss": 0.9516,
"step": 7
},
{
"epoch": 0.004491228070175438,
"grad_norm": 0.33498990535736084,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.779,
"step": 8
},
{
"epoch": 0.0050526315789473685,
"grad_norm": 0.29876577854156494,
"learning_rate": 3e-05,
"loss": 0.7478,
"step": 9
},
{
"epoch": 0.005614035087719298,
"grad_norm": 0.29719725251197815,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.8966,
"step": 10
},
{
"epoch": 0.006175438596491228,
"grad_norm": 0.24591504037380219,
"learning_rate": 3.6666666666666666e-05,
"loss": 0.9361,
"step": 11
},
{
"epoch": 0.006736842105263158,
"grad_norm": 0.28394192457199097,
"learning_rate": 4e-05,
"loss": 0.7647,
"step": 12
},
{
"epoch": 0.007298245614035088,
"grad_norm": 0.38288387656211853,
"learning_rate": 4.3333333333333334e-05,
"loss": 0.7759,
"step": 13
},
{
"epoch": 0.007859649122807018,
"grad_norm": 0.37495705485343933,
"learning_rate": 4.666666666666667e-05,
"loss": 0.816,
"step": 14
},
{
"epoch": 0.008421052631578947,
"grad_norm": 0.40812909603118896,
"learning_rate": 5e-05,
"loss": 0.8382,
"step": 15
},
{
"epoch": 0.008982456140350877,
"grad_norm": 0.38002440333366394,
"learning_rate": 5.333333333333333e-05,
"loss": 0.8044,
"step": 16
},
{
"epoch": 0.009543859649122808,
"grad_norm": 0.33160534501075745,
"learning_rate": 5.666666666666667e-05,
"loss": 0.823,
"step": 17
},
{
"epoch": 0.010105263157894737,
"grad_norm": 0.41194266080856323,
"learning_rate": 6e-05,
"loss": 0.7865,
"step": 18
},
{
"epoch": 0.010666666666666666,
"grad_norm": 0.35672563314437866,
"learning_rate": 6.333333333333333e-05,
"loss": 0.8629,
"step": 19
},
{
"epoch": 0.011228070175438596,
"grad_norm": 0.3618670701980591,
"learning_rate": 6.666666666666667e-05,
"loss": 0.8547,
"step": 20
},
{
"epoch": 0.011789473684210527,
"grad_norm": 0.3907402753829956,
"learning_rate": 7e-05,
"loss": 0.8765,
"step": 21
},
{
"epoch": 0.012350877192982456,
"grad_norm": 0.40214502811431885,
"learning_rate": 7.333333333333333e-05,
"loss": 0.9029,
"step": 22
},
{
"epoch": 0.012912280701754385,
"grad_norm": 0.4234139025211334,
"learning_rate": 7.666666666666667e-05,
"loss": 1.0402,
"step": 23
},
{
"epoch": 0.013473684210526317,
"grad_norm": 0.4222796559333801,
"learning_rate": 8e-05,
"loss": 1.0914,
"step": 24
},
{
"epoch": 0.014035087719298246,
"grad_norm": 0.49873098731040955,
"learning_rate": 8.333333333333334e-05,
"loss": 1.144,
"step": 25
},
{
"epoch": 0.014596491228070175,
"grad_norm": 0.5681342482566833,
"learning_rate": 8.666666666666667e-05,
"loss": 1.1029,
"step": 26
},
{
"epoch": 0.015157894736842105,
"grad_norm": 0.5003555417060852,
"learning_rate": 9e-05,
"loss": 1.1661,
"step": 27
},
{
"epoch": 0.015719298245614036,
"grad_norm": 0.5160950422286987,
"learning_rate": 9.333333333333334e-05,
"loss": 1.1766,
"step": 28
},
{
"epoch": 0.016280701754385965,
"grad_norm": 0.5502928495407104,
"learning_rate": 9.666666666666667e-05,
"loss": 1.1296,
"step": 29
},
{
"epoch": 0.016842105263157894,
"grad_norm": 0.5528545379638672,
"learning_rate": 0.0001,
"loss": 1.0385,
"step": 30
},
{
"epoch": 0.017403508771929824,
"grad_norm": 0.6849154233932495,
"learning_rate": 9.999146252290264e-05,
"loss": 0.8271,
"step": 31
},
{
"epoch": 0.017964912280701753,
"grad_norm": 0.692389965057373,
"learning_rate": 9.996585300715116e-05,
"loss": 0.8881,
"step": 32
},
{
"epoch": 0.018526315789473686,
"grad_norm": 0.9055421352386475,
"learning_rate": 9.99231801983717e-05,
"loss": 0.8995,
"step": 33
},
{
"epoch": 0.019087719298245615,
"grad_norm": 0.861546516418457,
"learning_rate": 9.986345866928941e-05,
"loss": 0.6501,
"step": 34
},
{
"epoch": 0.019649122807017545,
"grad_norm": 1.2089025974273682,
"learning_rate": 9.978670881475172e-05,
"loss": 0.6468,
"step": 35
},
{
"epoch": 0.020210526315789474,
"grad_norm": 1.254661202430725,
"learning_rate": 9.96929568447637e-05,
"loss": 0.859,
"step": 36
},
{
"epoch": 0.020771929824561403,
"grad_norm": 0.9925673604011536,
"learning_rate": 9.958223477553714e-05,
"loss": 0.7599,
"step": 37
},
{
"epoch": 0.021333333333333333,
"grad_norm": 0.929550051689148,
"learning_rate": 9.94545804185573e-05,
"loss": 0.8544,
"step": 38
},
{
"epoch": 0.021894736842105262,
"grad_norm": 1.0358238220214844,
"learning_rate": 9.931003736767013e-05,
"loss": 0.9166,
"step": 39
},
{
"epoch": 0.02245614035087719,
"grad_norm": 1.7126189470291138,
"learning_rate": 9.91486549841951e-05,
"loss": 1.4532,
"step": 40
},
{
"epoch": 0.023017543859649124,
"grad_norm": 2.377314567565918,
"learning_rate": 9.89704883800683e-05,
"loss": 2.2551,
"step": 41
},
{
"epoch": 0.023578947368421053,
"grad_norm": 1.5144628286361694,
"learning_rate": 9.877559839902184e-05,
"loss": 1.5257,
"step": 42
},
{
"epoch": 0.024140350877192983,
"grad_norm": 1.193682074546814,
"learning_rate": 9.85640515958057e-05,
"loss": 1.1618,
"step": 43
},
{
"epoch": 0.024701754385964912,
"grad_norm": 1.2293355464935303,
"learning_rate": 9.833592021345937e-05,
"loss": 1.1371,
"step": 44
},
{
"epoch": 0.02526315789473684,
"grad_norm": 1.7391295433044434,
"learning_rate": 9.809128215864097e-05,
"loss": 0.9594,
"step": 45
},
{
"epoch": 0.02582456140350877,
"grad_norm": 1.3019633293151855,
"learning_rate": 9.783022097502204e-05,
"loss": 0.9934,
"step": 46
},
{
"epoch": 0.0263859649122807,
"grad_norm": 1.7207362651824951,
"learning_rate": 9.755282581475769e-05,
"loss": 1.0664,
"step": 47
},
{
"epoch": 0.026947368421052633,
"grad_norm": 1.6913920640945435,
"learning_rate": 9.725919140804099e-05,
"loss": 1.4405,
"step": 48
},
{
"epoch": 0.027508771929824562,
"grad_norm": 2.155933380126953,
"learning_rate": 9.694941803075283e-05,
"loss": 1.8355,
"step": 49
},
{
"epoch": 0.028070175438596492,
"grad_norm": 3.120522975921631,
"learning_rate": 9.662361147021779e-05,
"loss": 2.4255,
"step": 50
},
{
"epoch": 0.028070175438596492,
"eval_loss": 0.9342920184135437,
"eval_runtime": 122.4157,
"eval_samples_per_second": 24.507,
"eval_steps_per_second": 12.253,
"step": 50
},
{
"epoch": 0.02863157894736842,
"grad_norm": 0.5891591310501099,
"learning_rate": 9.628188298907782e-05,
"loss": 1.0629,
"step": 51
},
{
"epoch": 0.02919298245614035,
"grad_norm": 0.39871206879615784,
"learning_rate": 9.592434928729616e-05,
"loss": 0.7556,
"step": 52
},
{
"epoch": 0.02975438596491228,
"grad_norm": 0.37089481949806213,
"learning_rate": 9.555113246230442e-05,
"loss": 0.7065,
"step": 53
},
{
"epoch": 0.03031578947368421,
"grad_norm": 0.38295838236808777,
"learning_rate": 9.516235996730645e-05,
"loss": 0.7221,
"step": 54
},
{
"epoch": 0.030877192982456142,
"grad_norm": 0.29920482635498047,
"learning_rate": 9.475816456775313e-05,
"loss": 0.7926,
"step": 55
},
{
"epoch": 0.03143859649122807,
"grad_norm": 0.23950375616550446,
"learning_rate": 9.43386842960031e-05,
"loss": 0.793,
"step": 56
},
{
"epoch": 0.032,
"grad_norm": 0.27886685729026794,
"learning_rate": 9.39040624041849e-05,
"loss": 0.8602,
"step": 57
},
{
"epoch": 0.03256140350877193,
"grad_norm": 0.317699134349823,
"learning_rate": 9.345444731527642e-05,
"loss": 1.0003,
"step": 58
},
{
"epoch": 0.03312280701754386,
"grad_norm": 0.22910217940807343,
"learning_rate": 9.298999257241863e-05,
"loss": 0.8108,
"step": 59
},
{
"epoch": 0.03368421052631579,
"grad_norm": 0.26130184531211853,
"learning_rate": 9.251085678648072e-05,
"loss": 0.9345,
"step": 60
},
{
"epoch": 0.03424561403508772,
"grad_norm": 0.2834413945674896,
"learning_rate": 9.201720358189464e-05,
"loss": 0.885,
"step": 61
},
{
"epoch": 0.03480701754385965,
"grad_norm": 0.2586613595485687,
"learning_rate": 9.150920154077754e-05,
"loss": 0.7197,
"step": 62
},
{
"epoch": 0.03536842105263158,
"grad_norm": 0.2519567906856537,
"learning_rate": 9.098702414536107e-05,
"loss": 0.6892,
"step": 63
},
{
"epoch": 0.035929824561403506,
"grad_norm": 0.29119372367858887,
"learning_rate": 9.045084971874738e-05,
"loss": 0.7979,
"step": 64
},
{
"epoch": 0.036491228070175435,
"grad_norm": 0.26617690920829773,
"learning_rate": 8.9900861364012e-05,
"loss": 0.7058,
"step": 65
},
{
"epoch": 0.03705263157894737,
"grad_norm": 0.3442516326904297,
"learning_rate": 8.933724690167417e-05,
"loss": 0.8994,
"step": 66
},
{
"epoch": 0.0376140350877193,
"grad_norm": 0.2873605787754059,
"learning_rate": 8.876019880555649e-05,
"loss": 0.7479,
"step": 67
},
{
"epoch": 0.03817543859649123,
"grad_norm": 0.29819053411483765,
"learning_rate": 8.816991413705516e-05,
"loss": 0.7455,
"step": 68
},
{
"epoch": 0.03873684210526316,
"grad_norm": 0.3056037425994873,
"learning_rate": 8.756659447784368e-05,
"loss": 0.8467,
"step": 69
},
{
"epoch": 0.03929824561403509,
"grad_norm": 0.3602258861064911,
"learning_rate": 8.695044586103296e-05,
"loss": 0.8658,
"step": 70
},
{
"epoch": 0.03985964912280702,
"grad_norm": 0.40999269485473633,
"learning_rate": 8.632167870081121e-05,
"loss": 0.7375,
"step": 71
},
{
"epoch": 0.04042105263157895,
"grad_norm": 0.3525683879852295,
"learning_rate": 8.568050772058762e-05,
"loss": 0.8655,
"step": 72
},
{
"epoch": 0.04098245614035088,
"grad_norm": 0.4073101282119751,
"learning_rate": 8.502715187966455e-05,
"loss": 0.9714,
"step": 73
},
{
"epoch": 0.04154385964912281,
"grad_norm": 0.4740641713142395,
"learning_rate": 8.436183429846313e-05,
"loss": 0.7718,
"step": 74
},
{
"epoch": 0.042105263157894736,
"grad_norm": 0.4567849934101105,
"learning_rate": 8.368478218232787e-05,
"loss": 0.899,
"step": 75
},
{
"epoch": 0.042666666666666665,
"grad_norm": 0.439581036567688,
"learning_rate": 8.299622674393614e-05,
"loss": 0.9626,
"step": 76
},
{
"epoch": 0.043228070175438595,
"grad_norm": 0.537564218044281,
"learning_rate": 8.229640312433937e-05,
"loss": 0.8511,
"step": 77
},
{
"epoch": 0.043789473684210524,
"grad_norm": 0.5121639370918274,
"learning_rate": 8.158555031266254e-05,
"loss": 0.9197,
"step": 78
},
{
"epoch": 0.04435087719298245,
"grad_norm": 0.5545501112937927,
"learning_rate": 8.086391106448965e-05,
"loss": 0.8807,
"step": 79
},
{
"epoch": 0.04491228070175438,
"grad_norm": 0.5333970189094543,
"learning_rate": 8.013173181896283e-05,
"loss": 0.6605,
"step": 80
},
{
"epoch": 0.04547368421052632,
"grad_norm": 0.5599662065505981,
"learning_rate": 7.938926261462366e-05,
"loss": 0.5374,
"step": 81
},
{
"epoch": 0.04603508771929825,
"grad_norm": 0.599372148513794,
"learning_rate": 7.863675700402526e-05,
"loss": 0.7062,
"step": 82
},
{
"epoch": 0.04659649122807018,
"grad_norm": 0.6970666646957397,
"learning_rate": 7.787447196714427e-05,
"loss": 0.5079,
"step": 83
},
{
"epoch": 0.04715789473684211,
"grad_norm": 0.5597441792488098,
"learning_rate": 7.710266782362247e-05,
"loss": 0.6036,
"step": 84
},
{
"epoch": 0.047719298245614036,
"grad_norm": 0.6313605904579163,
"learning_rate": 7.63216081438678e-05,
"loss": 0.4645,
"step": 85
},
{
"epoch": 0.048280701754385966,
"grad_norm": 0.8942999839782715,
"learning_rate": 7.553155965904535e-05,
"loss": 0.5454,
"step": 86
},
{
"epoch": 0.048842105263157895,
"grad_norm": 0.6143205165863037,
"learning_rate": 7.473279216998895e-05,
"loss": 0.5586,
"step": 87
},
{
"epoch": 0.049403508771929824,
"grad_norm": 1.0239964723587036,
"learning_rate": 7.392557845506432e-05,
"loss": 0.6921,
"step": 88
},
{
"epoch": 0.049964912280701754,
"grad_norm": 1.09725022315979,
"learning_rate": 7.311019417701566e-05,
"loss": 1.0064,
"step": 89
},
{
"epoch": 0.05052631578947368,
"grad_norm": 1.4291660785675049,
"learning_rate": 7.228691778882693e-05,
"loss": 0.9842,
"step": 90
},
{
"epoch": 0.05108771929824561,
"grad_norm": 1.2897967100143433,
"learning_rate": 7.145603043863045e-05,
"loss": 0.9226,
"step": 91
},
{
"epoch": 0.05164912280701754,
"grad_norm": 0.8228785991668701,
"learning_rate": 7.061781587369519e-05,
"loss": 0.789,
"step": 92
},
{
"epoch": 0.05221052631578947,
"grad_norm": 0.937737226486206,
"learning_rate": 6.977256034352712e-05,
"loss": 0.6699,
"step": 93
},
{
"epoch": 0.0527719298245614,
"grad_norm": 1.0278384685516357,
"learning_rate": 6.892055250211552e-05,
"loss": 0.6023,
"step": 94
},
{
"epoch": 0.05333333333333334,
"grad_norm": 0.9393802881240845,
"learning_rate": 6.806208330935766e-05,
"loss": 0.7863,
"step": 95
},
{
"epoch": 0.053894736842105266,
"grad_norm": 1.0484689474105835,
"learning_rate": 6.719744593169641e-05,
"loss": 0.7728,
"step": 96
},
{
"epoch": 0.054456140350877195,
"grad_norm": 1.1387441158294678,
"learning_rate": 6.632693564200416e-05,
"loss": 0.8077,
"step": 97
},
{
"epoch": 0.055017543859649125,
"grad_norm": 1.6136704683303833,
"learning_rate": 6.545084971874738e-05,
"loss": 1.1051,
"step": 98
},
{
"epoch": 0.055578947368421054,
"grad_norm": 1.555825114250183,
"learning_rate": 6.456948734446624e-05,
"loss": 1.1191,
"step": 99
},
{
"epoch": 0.056140350877192984,
"grad_norm": 2.404278516769409,
"learning_rate": 6.368314950360415e-05,
"loss": 1.9483,
"step": 100
},
{
"epoch": 0.056140350877192984,
"eval_loss": 0.8115013241767883,
"eval_runtime": 122.6214,
"eval_samples_per_second": 24.466,
"eval_steps_per_second": 12.233,
"step": 100
},
{
"epoch": 0.05670175438596491,
"grad_norm": 0.4372669458389282,
"learning_rate": 6.279213887972179e-05,
"loss": 1.0286,
"step": 101
},
{
"epoch": 0.05726315789473684,
"grad_norm": 0.4397050738334656,
"learning_rate": 6.189675975213094e-05,
"loss": 0.8791,
"step": 102
},
{
"epoch": 0.05782456140350877,
"grad_norm": 0.32385021448135376,
"learning_rate": 6.099731789198344e-05,
"loss": 0.6672,
"step": 103
},
{
"epoch": 0.0583859649122807,
"grad_norm": 0.2907547950744629,
"learning_rate": 6.009412045785051e-05,
"loss": 0.6619,
"step": 104
},
{
"epoch": 0.05894736842105263,
"grad_norm": 0.31022536754608154,
"learning_rate": 5.918747589082853e-05,
"loss": 0.6714,
"step": 105
},
{
"epoch": 0.05950877192982456,
"grad_norm": 0.2706989347934723,
"learning_rate": 5.82776938092065e-05,
"loss": 0.7354,
"step": 106
},
{
"epoch": 0.06007017543859649,
"grad_norm": 0.2617419362068176,
"learning_rate": 5.736508490273188e-05,
"loss": 0.7251,
"step": 107
},
{
"epoch": 0.06063157894736842,
"grad_norm": 0.2399427741765976,
"learning_rate": 5.644996082651017e-05,
"loss": 0.7174,
"step": 108
},
{
"epoch": 0.06119298245614035,
"grad_norm": 0.2220396101474762,
"learning_rate": 5.553263409457504e-05,
"loss": 0.6251,
"step": 109
},
{
"epoch": 0.061754385964912284,
"grad_norm": 0.23411913216114044,
"learning_rate": 5.4613417973165106e-05,
"loss": 0.6905,
"step": 110
},
{
"epoch": 0.06231578947368421,
"grad_norm": 0.2873174250125885,
"learning_rate": 5.3692626373743706e-05,
"loss": 0.6993,
"step": 111
},
{
"epoch": 0.06287719298245614,
"grad_norm": 0.24679617583751678,
"learning_rate": 5.27705737457985e-05,
"loss": 0.7005,
"step": 112
},
{
"epoch": 0.06343859649122807,
"grad_norm": 0.23201341927051544,
"learning_rate": 5.184757496945726e-05,
"loss": 0.6078,
"step": 113
},
{
"epoch": 0.064,
"grad_norm": 0.2771409749984741,
"learning_rate": 5.092394524795649e-05,
"loss": 0.77,
"step": 114
},
{
"epoch": 0.06456140350877193,
"grad_norm": 0.2589285373687744,
"learning_rate": 5e-05,
"loss": 0.6893,
"step": 115
},
{
"epoch": 0.06512280701754386,
"grad_norm": 0.2741367816925049,
"learning_rate": 4.907605475204352e-05,
"loss": 0.7777,
"step": 116
},
{
"epoch": 0.06568421052631579,
"grad_norm": 0.331800639629364,
"learning_rate": 4.8152425030542766e-05,
"loss": 0.7478,
"step": 117
},
{
"epoch": 0.06624561403508772,
"grad_norm": 0.34980151057243347,
"learning_rate": 4.72294262542015e-05,
"loss": 0.6952,
"step": 118
},
{
"epoch": 0.06680701754385965,
"grad_norm": 0.32478198409080505,
"learning_rate": 4.6307373626256306e-05,
"loss": 0.7286,
"step": 119
},
{
"epoch": 0.06736842105263158,
"grad_norm": 0.36208805441856384,
"learning_rate": 4.5386582026834906e-05,
"loss": 0.8807,
"step": 120
},
{
"epoch": 0.0679298245614035,
"grad_norm": 0.37494510412216187,
"learning_rate": 4.446736590542497e-05,
"loss": 0.7629,
"step": 121
},
{
"epoch": 0.06849122807017544,
"grad_norm": 0.3828965723514557,
"learning_rate": 4.3550039173489845e-05,
"loss": 0.7838,
"step": 122
},
{
"epoch": 0.06905263157894737,
"grad_norm": 0.464336097240448,
"learning_rate": 4.2634915097268115e-05,
"loss": 0.8454,
"step": 123
},
{
"epoch": 0.0696140350877193,
"grad_norm": 0.414644718170166,
"learning_rate": 4.1722306190793495e-05,
"loss": 0.753,
"step": 124
},
{
"epoch": 0.07017543859649122,
"grad_norm": 0.4704475402832031,
"learning_rate": 4.0812524109171476e-05,
"loss": 0.8551,
"step": 125
},
{
"epoch": 0.07073684210526315,
"grad_norm": 0.5488113760948181,
"learning_rate": 3.99058795421495e-05,
"loss": 0.8103,
"step": 126
},
{
"epoch": 0.07129824561403508,
"grad_norm": 0.5949589014053345,
"learning_rate": 3.9002682108016585e-05,
"loss": 0.676,
"step": 127
},
{
"epoch": 0.07185964912280701,
"grad_norm": 0.7315034866333008,
"learning_rate": 3.8103240247869075e-05,
"loss": 0.899,
"step": 128
},
{
"epoch": 0.07242105263157894,
"grad_norm": 0.5491634011268616,
"learning_rate": 3.720786112027822e-05,
"loss": 0.5835,
"step": 129
},
{
"epoch": 0.07298245614035087,
"grad_norm": 0.5259478092193604,
"learning_rate": 3.631685049639586e-05,
"loss": 0.6361,
"step": 130
},
{
"epoch": 0.0735438596491228,
"grad_norm": 0.5950855016708374,
"learning_rate": 3.543051265553377e-05,
"loss": 0.8745,
"step": 131
},
{
"epoch": 0.07410526315789474,
"grad_norm": 0.5459845662117004,
"learning_rate": 3.4549150281252636e-05,
"loss": 0.5167,
"step": 132
},
{
"epoch": 0.07466666666666667,
"grad_norm": 0.5504123568534851,
"learning_rate": 3.367306435799584e-05,
"loss": 0.729,
"step": 133
},
{
"epoch": 0.0752280701754386,
"grad_norm": 0.5301131010055542,
"learning_rate": 3.2802554068303596e-05,
"loss": 0.54,
"step": 134
},
{
"epoch": 0.07578947368421053,
"grad_norm": 0.6610441207885742,
"learning_rate": 3.1937916690642356e-05,
"loss": 0.545,
"step": 135
},
{
"epoch": 0.07635087719298246,
"grad_norm": 0.4902953803539276,
"learning_rate": 3.107944749788449e-05,
"loss": 0.5694,
"step": 136
},
{
"epoch": 0.07691228070175439,
"grad_norm": 0.702129065990448,
"learning_rate": 3.0227439656472877e-05,
"loss": 0.4447,
"step": 137
},
{
"epoch": 0.07747368421052632,
"grad_norm": 0.7584903836250305,
"learning_rate": 2.9382184126304834e-05,
"loss": 0.589,
"step": 138
},
{
"epoch": 0.07803508771929825,
"grad_norm": 1.4466608762741089,
"learning_rate": 2.8543969561369556e-05,
"loss": 0.5408,
"step": 139
},
{
"epoch": 0.07859649122807018,
"grad_norm": 1.2781710624694824,
"learning_rate": 2.771308221117309e-05,
"loss": 0.5487,
"step": 140
},
{
"epoch": 0.07915789473684211,
"grad_norm": 0.9161723256111145,
"learning_rate": 2.688980582298435e-05,
"loss": 0.5468,
"step": 141
},
{
"epoch": 0.07971929824561404,
"grad_norm": 0.7036490440368652,
"learning_rate": 2.607442154493568e-05,
"loss": 0.631,
"step": 142
},
{
"epoch": 0.08028070175438597,
"grad_norm": 0.7849149703979492,
"learning_rate": 2.5267207830011068e-05,
"loss": 0.5692,
"step": 143
},
{
"epoch": 0.0808421052631579,
"grad_norm": 0.8792390823364258,
"learning_rate": 2.446844034095466e-05,
"loss": 0.4891,
"step": 144
},
{
"epoch": 0.08140350877192983,
"grad_norm": 0.8697530031204224,
"learning_rate": 2.3678391856132204e-05,
"loss": 0.7373,
"step": 145
},
{
"epoch": 0.08196491228070175,
"grad_norm": 0.8269962668418884,
"learning_rate": 2.2897332176377528e-05,
"loss": 0.539,
"step": 146
},
{
"epoch": 0.08252631578947368,
"grad_norm": 1.1171008348464966,
"learning_rate": 2.2125528032855724e-05,
"loss": 0.9844,
"step": 147
},
{
"epoch": 0.08308771929824561,
"grad_norm": 1.0775487422943115,
"learning_rate": 2.136324299597474e-05,
"loss": 1.0029,
"step": 148
},
{
"epoch": 0.08364912280701754,
"grad_norm": 1.273962378501892,
"learning_rate": 2.061073738537635e-05,
"loss": 1.2998,
"step": 149
},
{
"epoch": 0.08421052631578947,
"grad_norm": 1.928801417350769,
"learning_rate": 1.9868268181037185e-05,
"loss": 1.7007,
"step": 150
},
{
"epoch": 0.08421052631578947,
"eval_loss": 0.7458124756813049,
"eval_runtime": 122.7727,
"eval_samples_per_second": 24.435,
"eval_steps_per_second": 12.218,
"step": 150
},
{
"epoch": 0.0847719298245614,
"grad_norm": 0.3122590482234955,
"learning_rate": 1.9136088935510362e-05,
"loss": 0.8948,
"step": 151
},
{
"epoch": 0.08533333333333333,
"grad_norm": 0.3245391845703125,
"learning_rate": 1.8414449687337464e-05,
"loss": 0.7903,
"step": 152
},
{
"epoch": 0.08589473684210526,
"grad_norm": 0.28587210178375244,
"learning_rate": 1.7703596875660645e-05,
"loss": 0.7252,
"step": 153
},
{
"epoch": 0.08645614035087719,
"grad_norm": 0.3171529173851013,
"learning_rate": 1.700377325606388e-05,
"loss": 0.6687,
"step": 154
},
{
"epoch": 0.08701754385964912,
"grad_norm": 0.2921241223812103,
"learning_rate": 1.631521781767214e-05,
"loss": 0.6201,
"step": 155
},
{
"epoch": 0.08757894736842105,
"grad_norm": 0.26473841071128845,
"learning_rate": 1.5638165701536868e-05,
"loss": 0.6518,
"step": 156
},
{
"epoch": 0.08814035087719298,
"grad_norm": 0.33115243911743164,
"learning_rate": 1.4972848120335453e-05,
"loss": 0.8362,
"step": 157
},
{
"epoch": 0.0887017543859649,
"grad_norm": 0.2714337110519409,
"learning_rate": 1.4319492279412388e-05,
"loss": 0.6746,
"step": 158
},
{
"epoch": 0.08926315789473684,
"grad_norm": 0.2988300025463104,
"learning_rate": 1.3678321299188801e-05,
"loss": 0.7037,
"step": 159
},
{
"epoch": 0.08982456140350877,
"grad_norm": 0.31018441915512085,
"learning_rate": 1.3049554138967051e-05,
"loss": 0.7861,
"step": 160
},
{
"epoch": 0.09038596491228071,
"grad_norm": 0.2746640145778656,
"learning_rate": 1.2433405522156332e-05,
"loss": 0.7249,
"step": 161
},
{
"epoch": 0.09094736842105264,
"grad_norm": 0.2654082179069519,
"learning_rate": 1.183008586294485e-05,
"loss": 0.7455,
"step": 162
},
{
"epoch": 0.09150877192982457,
"grad_norm": 0.24473796784877777,
"learning_rate": 1.1239801194443506e-05,
"loss": 0.6227,
"step": 163
},
{
"epoch": 0.0920701754385965,
"grad_norm": 0.2504828870296478,
"learning_rate": 1.066275309832584e-05,
"loss": 0.7073,
"step": 164
},
{
"epoch": 0.09263157894736843,
"grad_norm": 0.30534666776657104,
"learning_rate": 1.0099138635988026e-05,
"loss": 0.6981,
"step": 165
},
{
"epoch": 0.09319298245614036,
"grad_norm": 0.30247023701667786,
"learning_rate": 9.549150281252633e-06,
"loss": 0.6736,
"step": 166
},
{
"epoch": 0.09375438596491228,
"grad_norm": 0.4104022979736328,
"learning_rate": 9.012975854638949e-06,
"loss": 0.754,
"step": 167
},
{
"epoch": 0.09431578947368421,
"grad_norm": 0.3200322091579437,
"learning_rate": 8.490798459222476e-06,
"loss": 0.5872,
"step": 168
},
{
"epoch": 0.09487719298245614,
"grad_norm": 0.353659063577652,
"learning_rate": 7.982796418105371e-06,
"loss": 0.8617,
"step": 169
},
{
"epoch": 0.09543859649122807,
"grad_norm": 0.3442855179309845,
"learning_rate": 7.489143213519301e-06,
"loss": 0.7441,
"step": 170
},
{
"epoch": 0.096,
"grad_norm": 0.3479902744293213,
"learning_rate": 7.010007427581378e-06,
"loss": 0.7429,
"step": 171
},
{
"epoch": 0.09656140350877193,
"grad_norm": 0.3734584152698517,
"learning_rate": 6.5455526847235825e-06,
"loss": 0.7839,
"step": 172
},
{
"epoch": 0.09712280701754386,
"grad_norm": 0.3731192648410797,
"learning_rate": 6.0959375958151045e-06,
"loss": 0.8681,
"step": 173
},
{
"epoch": 0.09768421052631579,
"grad_norm": 0.4046560525894165,
"learning_rate": 5.6613157039969055e-06,
"loss": 0.9747,
"step": 174
},
{
"epoch": 0.09824561403508772,
"grad_norm": 0.5003874897956848,
"learning_rate": 5.241835432246889e-06,
"loss": 0.7606,
"step": 175
},
{
"epoch": 0.09880701754385965,
"grad_norm": 0.5039113759994507,
"learning_rate": 4.837640032693558e-06,
"loss": 0.7671,
"step": 176
},
{
"epoch": 0.09936842105263158,
"grad_norm": 0.5854450464248657,
"learning_rate": 4.448867537695578e-06,
"loss": 0.7763,
"step": 177
},
{
"epoch": 0.09992982456140351,
"grad_norm": 0.5254133343696594,
"learning_rate": 4.075650712703849e-06,
"loss": 0.7363,
"step": 178
},
{
"epoch": 0.10049122807017544,
"grad_norm": 0.5278907418251038,
"learning_rate": 3.71811701092219e-06,
"loss": 0.7107,
"step": 179
},
{
"epoch": 0.10105263157894737,
"grad_norm": 0.6159325242042542,
"learning_rate": 3.376388529782215e-06,
"loss": 0.6757,
"step": 180
},
{
"epoch": 0.1016140350877193,
"grad_norm": 0.6477799415588379,
"learning_rate": 3.0505819692471792e-06,
"loss": 0.6614,
"step": 181
},
{
"epoch": 0.10217543859649122,
"grad_norm": 0.5958523154258728,
"learning_rate": 2.7408085919590264e-06,
"loss": 0.7575,
"step": 182
},
{
"epoch": 0.10273684210526315,
"grad_norm": 0.6421895027160645,
"learning_rate": 2.4471741852423237e-06,
"loss": 0.4513,
"step": 183
},
{
"epoch": 0.10329824561403508,
"grad_norm": 0.7550863027572632,
"learning_rate": 2.1697790249779636e-06,
"loss": 0.6119,
"step": 184
},
{
"epoch": 0.10385964912280701,
"grad_norm": 0.7374166250228882,
"learning_rate": 1.908717841359048e-06,
"loss": 0.5968,
"step": 185
},
{
"epoch": 0.10442105263157894,
"grad_norm": 0.755599319934845,
"learning_rate": 1.6640797865406288e-06,
"loss": 0.5619,
"step": 186
},
{
"epoch": 0.10498245614035087,
"grad_norm": 0.8369899988174438,
"learning_rate": 1.4359484041943038e-06,
"loss": 0.5447,
"step": 187
},
{
"epoch": 0.1055438596491228,
"grad_norm": 0.875713050365448,
"learning_rate": 1.2244016009781701e-06,
"loss": 0.5324,
"step": 188
},
{
"epoch": 0.10610526315789473,
"grad_norm": 0.8864160776138306,
"learning_rate": 1.0295116199317057e-06,
"loss": 0.5216,
"step": 189
},
{
"epoch": 0.10666666666666667,
"grad_norm": 0.9906832575798035,
"learning_rate": 8.513450158049108e-07,
"loss": 0.6048,
"step": 190
},
{
"epoch": 0.1072280701754386,
"grad_norm": 1.3534337282180786,
"learning_rate": 6.899626323298713e-07,
"loss": 0.5319,
"step": 191
},
{
"epoch": 0.10778947368421053,
"grad_norm": 1.093711256980896,
"learning_rate": 5.454195814427021e-07,
"loss": 0.4393,
"step": 192
},
{
"epoch": 0.10835087719298246,
"grad_norm": 0.874680757522583,
"learning_rate": 4.177652244628627e-07,
"loss": 0.5225,
"step": 193
},
{
"epoch": 0.10891228070175439,
"grad_norm": 0.8974077105522156,
"learning_rate": 3.0704315523631953e-07,
"loss": 0.7351,
"step": 194
},
{
"epoch": 0.10947368421052632,
"grad_norm": 0.8559723496437073,
"learning_rate": 2.1329118524827662e-07,
"loss": 0.7442,
"step": 195
},
{
"epoch": 0.11003508771929825,
"grad_norm": 0.8494490385055542,
"learning_rate": 1.3654133071059893e-07,
"loss": 0.638,
"step": 196
},
{
"epoch": 0.11059649122807018,
"grad_norm": 0.8759176731109619,
"learning_rate": 7.681980162830282e-08,
"loss": 0.8537,
"step": 197
},
{
"epoch": 0.11115789473684211,
"grad_norm": 1.0472686290740967,
"learning_rate": 3.4146992848854695e-08,
"loss": 0.909,
"step": 198
},
{
"epoch": 0.11171929824561404,
"grad_norm": 1.3545598983764648,
"learning_rate": 8.537477097364522e-09,
"loss": 1.1257,
"step": 199
},
{
"epoch": 0.11228070175438597,
"grad_norm": 1.787885069847107,
"learning_rate": 0.0,
"loss": 1.7459,
"step": 200
},
{
"epoch": 0.11228070175438597,
"eval_loss": 0.7339931726455688,
"eval_runtime": 122.6295,
"eval_samples_per_second": 24.464,
"eval_steps_per_second": 12.232,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 200,
"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": 6.579098864320512e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}