| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011740189604062106, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011740189604062105, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666668e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00011740189604062105, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2498.7293, | |
| "eval_samples_per_second": 5.741, | |
| "eval_steps_per_second": 0.718, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002348037920812421, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-07, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00035220568812186317, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004696075841624842, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005870094802031052, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.333333333333333e-07, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007044113762437263, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008218132722843474, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1666666666666668e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0009392151683249684, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0010566170643655896, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0011740189604062105, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0012914208564468316, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0014088227524874527, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015262246485280738, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.166666666666667e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0016436265445686949, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3333333333333336e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001761028440609316, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0018784303366499368, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001995832232690558, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8333333333333335e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0021132341287311792, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0022306360247718, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002348037920812421, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002465439816853042, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002582841712893663, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6666666666666666e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0027002436089342842, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.833333333333334e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0028176455049749053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0029350474010155264, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0030524492970561475, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.333333333333334e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0031698511930967686, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0032872530891373897, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.003404654985178011, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.833333333333333e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.003522056881218632, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0036394587772592525, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.997482666353287e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0037568606732998736, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.989935734988098e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0038742625693404947, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.977374404419838e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003991664465381116, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.959823971496575e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004109066361421737, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.937319780454559e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0042264682574623584, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.909907151739634e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.004343870153502979, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8776412907378845e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0044612720495436, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8405871765993435e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.004578673945584221, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7988194313786275e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.004696075841624842, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.752422169756048e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0048134777376654635, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.701488829641845e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.004930879633706084, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.646121984004666e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.005048281529746706, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.586433134303257e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.005165683425787326, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.522542485937369e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.005283085321827948, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.454578706170075e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0054004872178685685, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.382678665009028e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.00551788911390919, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3069871595684795e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.005635291009949811, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.227656622467162e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.005752692905990431, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.144846814849282e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.005870094802031053, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.058724504646834e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005870094802031053, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2500.0504, | |
| "eval_samples_per_second": 5.738, | |
| "eval_steps_per_second": 0.718, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0059874966980716735, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.969463130731183e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.006104898594112295, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8772424536302565e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.006222300490152916, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.782248193514766e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.006339702386193537, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.684671656182497e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.006457104282234158, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5847093477938955e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.006574506178274779, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4825625791348093e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0066919080743154, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3784370602033572e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.006809309970356022, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.006926711866396642, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.165092113916688e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.007044113762437264, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.056302334890786e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0071615156584778844, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.946392236996592e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.007278917554518505, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.835583164544139e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.007396319450559127, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.724098272258584e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.007513721346599747, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6121620758762877e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.007631123242640369, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0077485251386809895, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3878379241237136e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.007865927034721611, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2759017277414165e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.007983328930762233, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1644168354558623e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.008100730826802852, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.053607763003409e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.008218132722843474, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9436976651092143e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.008335534618884095, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8349078860833125e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.008452936514924717, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7274575140626318e-06, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.008570338410965337, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6215629397966432e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.008687740307005958, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5174374208651913e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.00880514220304658, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.415290652206105e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0089225440990872, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3153283438175036e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.009039945995127821, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.217751806485235e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.009157347891168443, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.122757546369744e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.009274749787209064, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0305368692688175e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.009392151683249684, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.412754953531664e-07, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.009509553579290305, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.551531851507186e-07, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.009626955475330927, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.723433775328385e-07, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.009744357371371548, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.930128404315214e-07, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.009861759267412168, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.17321334990973e-07, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.00997916116345279, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.454212938299256e-07, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.010096563059493411, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.774575140626317e-07, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.010213964955534031, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1356686569674344e-07, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.010331366851574653, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.538780159953348e-07, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.010448768747615274, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.98511170358155e-07, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.010566170643655896, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4757783024395244e-07, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.010683572539696515, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0118056862137358e-07, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.010800974435737137, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.59412823400657e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.010918376331777759, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.223587092621162e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.01103577822781838, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.00928482603669e-08, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.011153180123859, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.268021954544095e-08, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.011270582019899621, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.017602850342584e-08, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.011387983915940243, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.262559558016325e-08, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.011505385811980863, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.006426501190233e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.011622787708021484, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5173336467135266e-09, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.011740189604062106, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011740189604062106, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2503.7758, | |
| "eval_samples_per_second": 5.73, | |
| "eval_steps_per_second": 0.717, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.853187965727539e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |