| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.21499596882558453, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002149959688255845, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5000000000000002e-07, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002149959688255845, | |
| "eval_loss": NaN, | |
| "eval_runtime": 25.4332, | |
| "eval_samples_per_second": 15.413, | |
| "eval_steps_per_second": 15.413, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00429991937651169, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0064498790647675355, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-07, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00859983875302338, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010749798441279226, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-07, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012899758129535071, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-07, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015049717817790917, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0500000000000001e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01719967750604676, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.019349637194302608, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.35e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021499596882558453, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023649556570814297, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.65e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025799516259070142, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.027949475947325986, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.95e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.030099435635581834, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03224939532383768, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.25e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03439935501209352, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03654931470034937, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.55e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.038699274388605216, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04084923407686106, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8500000000000002e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.042999193765116905, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.045149153453372746, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.15e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.047299113141628595, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04944907282988444, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4500000000000004e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.051599032518140284, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05374899220639613, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.75e-06, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05589895189465197, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9e-06, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05804891158290782, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.05e-06, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06019887127116367, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06234883095941951, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.35e-06, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06449879064767536, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-06, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0666487503359312, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.65e-06, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.06879871002418704, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07094866971244289, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.95e-06, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07309862940069874, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.1e-06, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07524858908895458, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.25e-06, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07739854877721043, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4e-06, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07954850846546627, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.55e-06, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08169846815372211, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7000000000000005e-06, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08384842784197796, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.850000000000001e-06, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.08599838753023381, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08814834721848966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1499999999999996e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09029830690674549, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.3e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09244826659500134, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.45e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.09459822628325719, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.6e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.09674818597151304, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.750000000000001e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09889814565976889, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.900000000000001e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10104810534802472, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.049999999999999e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10319806503628057, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.2e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.10534802472453642, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.35e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.10749798441279226, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10749798441279226, | |
| "eval_loss": NaN, | |
| "eval_runtime": 25.4707, | |
| "eval_samples_per_second": 15.39, | |
| "eval_steps_per_second": 15.39, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.10964794410104811, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.65e-06, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.11179790378930395, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.8e-06, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1139478634775598, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.95e-06, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.11609782316581564, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.1e-06, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.11824778285407149, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.25e-06, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.12039774254232734, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.12254770223058317, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.55e-06, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.12469766191883902, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.7e-06, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.12684762160709487, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.85e-06, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.12899758129535072, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.13114754098360656, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.15e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1332975006718624, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.3e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.13544746036011826, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.450000000000001e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.13759742004837408, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.13974737973662993, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.75e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.14189733942488578, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.9e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.14404729911314162, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.005e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.14619725880139747, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.02e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.14834721848965332, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.035e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.15049717817790917, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.05e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15264713786616502, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.065e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.15479709755442086, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.08e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1569470572426767, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.095e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.15909701693093253, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.11e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.16124697661918838, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.125e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.16339693630744423, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1400000000000001e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.16554689599570008, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1550000000000001e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.16769685568395593, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1700000000000001e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.16984681537221177, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.185e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.17199677506046762, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17414673474872347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.215e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.17629669443697932, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2299999999999999e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.17844665412523517, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.245e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.18059661381349099, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.26e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.18274657350174683, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.275e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.18489653319000268, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.29e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.18704649287825853, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.305e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.18919645256651438, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.32e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.19134641225477023, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3350000000000001e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.19349637194302607, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.19564633163128192, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3650000000000001e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.19779629131953777, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3800000000000002e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.1999462510077936, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.395e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.20209621069604944, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4099999999999999e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.2042461703843053, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4249999999999999e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.20639613007256113, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.44e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.20854608976081698, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.455e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.21069604944907283, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.47e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.21284600913732868, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.485e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.21499596882558453, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21499596882558453, | |
| "eval_loss": NaN, | |
| "eval_runtime": 25.4729, | |
| "eval_samples_per_second": 15.389, | |
| "eval_steps_per_second": 15.389, | |
| "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": 2, | |
| "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": 3.17940289241088e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |