| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007173343854237653, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.173343854237653e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-06, | |
| "loss": 0.3623, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.173343854237653e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 425.7627, | |
| "eval_samples_per_second": 13.787, | |
| "eval_steps_per_second": 3.448, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014346687708475305, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021520031562712958, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002869337541695061, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00035866719271188265, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9999999999999996e-06, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00043040063125425915, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005021340697966357, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005738675083390122, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006456009468813888, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007173343854237653, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.999999999999999e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007890678239661418, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008608012625085183, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009325347010508949, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3000000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010042681395932714, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.001076001578135648, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011477350166780244, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001219468455220401, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012912018937627776, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013629353323051541, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014346687708475306, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9999999999999998e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001506402209389907, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015781356479322836, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00164986908647466, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3000000000000003e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0017216025250170366, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017933359635594133, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018650694021017898, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0019368028406441663, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002008536279186543, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0020802697177289193, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002152003156271296, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022237365948136723, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9984895998119723e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002295470033356049, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.993961440992859e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0023672034718984253, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9864246426519023e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.002438936910440802, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9758943828979444e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0025106703489831783, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9623918682727355e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0025824037875255552, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0026541372260679317, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9265847744427305e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0027258706646103082, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.904352305959606e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0027976041031526847, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8792916588271762e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0028693375416950612, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8514533018536286e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0029410709802374377, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.820893297785107e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.003012804418779814, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7876731904027994e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0030845378573221907, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7518598805819542e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003156271295864567, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7135254915624213e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0032280047344069437, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.672747223702045e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00329973817294932, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0033714716114916967, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5841922957410875e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003443205050034073, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5365939734802973e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0035149384885764497, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4869080889095693e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0035866719271188266, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4352347027881003e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0035866719271188266, | |
| "eval_loss": NaN, | |
| "eval_runtime": 425.4423, | |
| "eval_samples_per_second": 13.797, | |
| "eval_steps_per_second": 3.451, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003658405365661203, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3816778784387097e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.0037301388042035796, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3263454721781537e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.003801872242745956, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2693489161088592e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0038736056812883326, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.210802993709498e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.003945339119830709, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1508256086763372e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.004017072558373086, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0895375474808857e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0040888059969154626, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0270622361220143e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.004160539435457839, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.963525491562421e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.0042322728740002155, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8990552683500128e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.004304006312542592, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8337814009344716e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0043757397510849685, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.767835342197955e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.004447473189627345, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7013498987264832e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.0045192066281697215, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6344589633551502e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.004590940066712098, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5672972455257726e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0046626735052544745, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.004734406943796851, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4327027544742281e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.0048061403823392275, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.36554103664485e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.004877873820881604, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2986501012735174e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0049496072594239805, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2321646578020452e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.005021340697966357, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1662185990655285e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0050930741365087335, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1009447316499875e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.0051648075750511105, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.036474508437579e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0052365410135934865, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.729377638779859e-06, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0053082744521358634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.104624525191147e-06, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.0053800078906782395, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.491743913236629e-06, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.0054517413292206164, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.89197006290502e-06, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.0055234747677629925, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.30651083891141e-06, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.0055952082063053694, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.736545278218464e-06, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.0056669416448477455, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.1832212156129045e-06, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.0057386750833901224, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.647652972118998e-06, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0058104085219324985, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.130919110904311e-06, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.005882141960474875, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6340602651970304e-06, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0059538753990172515, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.158077042589129e-06, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.006025608837559628, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7039280099458373e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.006097342276102005, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.272527762979553e-06, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.006169075714644381, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.86474508437579e-06, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.006240809153186758, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4814011941804603e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.006312542591729134, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1232680959720085e-06, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.006384276030271511, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.79106702214893e-06, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.006456009468813887, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4854669814637145e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.006527742907356264, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2070834117282414e-06, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.00659947634589864, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.56476940403942e-07, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.006671209784441017, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.341522555726971e-07, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.006742943222983393, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.405570895622014e-07, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.00681467666152577, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.760813172726457e-07, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.006886410100068146, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.41056171020555e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.006958143538610523, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.357535734809795e-07, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.007029876977152899, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.038559007141397e-08, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.007101610415695276, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.510400188028116e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.007173343854237653, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007173343854237653, | |
| "eval_loss": NaN, | |
| "eval_runtime": 425.6455, | |
| "eval_samples_per_second": 13.791, | |
| "eval_steps_per_second": 3.449, | |
| "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": 3.3886526320410624e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |