| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.006797172376291463, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.797172376291462e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.797172376291462e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 679.865, | |
| "eval_samples_per_second": 9.112, | |
| "eval_steps_per_second": 2.278, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013594344752582924, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002039151712887439, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002718868950516585, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00033985861881457316, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004078303425774878, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004758020663404024, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000543773790103317, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006117455138662316, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006797172376291463, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000747688961392061, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008156606851549756, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0008836324089178902, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009516041326808048, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010195758564437193, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001087547580206634, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011555193039695486, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012234910277324632, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001291462751495378, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0013594344752582926, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014274061990212073, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.001495377922784122, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0015633496465470365, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0016313213703099511, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0016992930940728658, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017672648178357804, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001835236541598695, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0019032082653616096, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001971179989124524, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0020391517128874386, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0021071234366503533, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002175095160413268, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0022430668841761825, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002311038607939097, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0023790103317020118, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0024469820554649264, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0025149537792278414, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.002582925502990756, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0026508972267536707, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0027188689505165853, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0027868406742795, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0028548123980424145, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.002922784121805329, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.002990755845568244, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0030587275693311584, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003126699293094073, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0031946710168569876, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0032626427406199023, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.003330614464382817, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0033985861881457315, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0033985861881457315, | |
| "eval_loss": NaN, | |
| "eval_runtime": 680.2818, | |
| "eval_samples_per_second": 9.107, | |
| "eval_steps_per_second": 2.277, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003466557911908646, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3816778784387097e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0035345296356715608, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3263454721781537e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.0036025013594344754, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2693489161088592e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.00367047308319739, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.210802993709498e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.0037384448069603046, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1508256086763372e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.0038064165307232192, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0895375474808857e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.003874388254486134, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0270622361220143e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.003942359978249048, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.004010331702011963, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8990552683500128e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.004078303425774877, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8337814009344716e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.004146275149537792, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.767835342197955e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.0042142468733007065, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7013498987264832e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.004282218597063622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6344589633551502e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.004350190320826536, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5672972455257726e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.004418162044589451, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004486133768352365, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4327027544742281e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.00455410549211528, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.36554103664485e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004622077215878194, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2986501012735174e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.004690048939641109, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2321646578020452e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0047580206634040235, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1662185990655285e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.004825992387166939, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1009447316499875e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.004893964110929853, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.004961935834692768, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729377638779859e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.005029907558455683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.104624525191147e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.005097879282218597, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.491743913236629e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.005165851005981512, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89197006290502e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.005233822729744426, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.30651083891141e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.005301794453507341, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.736545278218464e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0053697661772702555, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1832212156129045e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.005437737901033171, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.647652972118998e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.005505709624796085, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.130919110904311e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005573681348559, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6340602651970304e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.005641653072321914, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.158077042589129e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.005709624796084829, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7039280099458373e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.005777596519847743, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272527762979553e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.005845568243610658, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.0059135399673735725, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4814011941804603e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.005981511691136488, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1232680959720085e-06, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.006049483414899402, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.79106702214893e-06, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006117455138662317, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4854669814637145e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006185426862425231, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2070834117282414e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.006253398586188146, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.56476940403942e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.00632137030995106, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.341522555726971e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.006389342033713975, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.405570895622014e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.0064573137574768895, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.760813172726457e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.0065252854812398045, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.41056171020555e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.006593257205002719, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.357535734809795e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.006661228928765634, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.038559007141397e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.006729200652528548, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.510400188028116e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.006797172376291463, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.006797172376291463, | |
| "eval_loss": NaN, | |
| "eval_runtime": 680.3627, | |
| "eval_samples_per_second": 9.105, | |
| "eval_steps_per_second": 2.277, | |
| "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": 3.57749904900096e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |