| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03421142661648991, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017105713308244953, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.001e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017105713308244953, | |
| "eval_loss": NaN, | |
| "eval_runtime": 235.5933, | |
| "eval_samples_per_second": 10.45, | |
| "eval_steps_per_second": 2.615, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034211426616489907, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.002e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005131713992473486, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0029999999999995e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006842285323297981, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.004e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008552856654122477, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.005e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010263427984946972, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.005999999999999e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011973999315771468, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006999999999998e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013684570646595963, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.008e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.001539514197742046, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.009e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017105713308244953, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001881628463906945, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957315789473684e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0020526855969893944, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.904631578947367e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.002223742730071844, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.851947368421052e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0023947998631542937, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.799263157894736e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002565856996236743, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.746578947368421e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027369141293191925, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.693894736842104e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002907971262401642, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.641210526315789e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.003079028395484092, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.588526315789473e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003250085528566541, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.535842105263157e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034211426616489907, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.483157894736841e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0035921997947314403, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.430473684210526e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00376325692781389, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.37778947368421e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00393431406089634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.325105263157894e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.004105371193978789, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.272421052631578e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004276428327061239, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.219736842105263e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004447485460143688, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.167052631578946e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004618542593226137, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.114368421052632e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004789599726308587, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.061684210526315e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0049606568593910366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.009e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005131713992473486, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.956315789473683e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005302771125555936, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.903631578947368e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.005473828258638385, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.850947368421052e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005644885391720835, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.798263157894736e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005815942524803284, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.745578947368422e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0059869996578857335, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.692894736842105e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006158056790968184, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.64021052631579e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.006329113924050633, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.587526315789473e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006500171057133082, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.534842105263157e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.006671228190215532, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.482157894736842e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006842285323297981, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.429473684210525e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007013342456380431, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.376789473684211e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007184399589462881, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.324105263157894e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.00735545672254533, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.271421052631579e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.00752651385562778, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.218736842105262e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007697570988710229, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.166052631578947e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00786862812179268, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.113368421052631e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008039685254875127, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.060684210526315e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.008210742387957578, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.008e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008381799521040028, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.955315789473684e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008552856654122478, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.902631578947368e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008552856654122478, | |
| "eval_loss": NaN, | |
| "eval_runtime": 233.398, | |
| "eval_samples_per_second": 10.549, | |
| "eval_steps_per_second": 2.639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008723913787204926, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.849947368421052e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.008894970920287376, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.797263157894736e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.009066028053369826, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.744578947368421e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009237085186452275, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.691894736842104e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009408142319534725, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.63921052631579e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009579199452617175, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.586526315789473e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009750256585699623, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.533842105263158e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.009921313718782073, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.481157894736841e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.010092370851864523, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.428473684210526e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.010263427984946972, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.375789473684209e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.010434485118029422, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323105263157895e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010605542251111872, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.270421052631578e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.010776599384194322, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.217736842105263e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01094765651727677, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.165052631578947e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.01111871365035922, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.11236842105263e-05, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01128977078344167, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.059684210526315e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011460827916524119, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.006999999999998e-05, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011631885049606569, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.954315789473684e-05, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.011802942182689019, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.901631578947368e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.011973999315771467, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.848947368421052e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012145056448853917, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.796263157894737e-05, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.012316113581936367, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.74357894736842e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012487170715018816, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.690894736842105e-05, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.012658227848101266, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.638210526315788e-05, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.012829284981183716, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.585526315789474e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.013000342114266164, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.532842105263157e-05, | |
| "loss": 0.0, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.013171399247348614, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.480157894736842e-05, | |
| "loss": 0.0, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.013342456380431064, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.427473684210526e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.013513513513513514, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.37478947368421e-05, | |
| "loss": 0.0, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.013684570646595963, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.322105263157894e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.013855627779678413, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.269421052631577e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.014026684912760863, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.216736842105263e-05, | |
| "loss": 0.0, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.014197742045843311, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.164052631578947e-05, | |
| "loss": 0.0, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.014368799178925761, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.111368421052631e-05, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.014539856312008211, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.058684210526315e-05, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01471091344509066, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.005999999999999e-05, | |
| "loss": 0.0, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.01488197057817311, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.953315789473684e-05, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.01505302771125556, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.9006315789473676e-05, | |
| "loss": 0.0, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.015224084844338008, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.847947368421053e-05, | |
| "loss": 0.0, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.015395141977420458, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.795263157894737e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.015566199110502908, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.742578947368421e-05, | |
| "loss": 0.0, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.01573725624358536, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6898947368421046e-05, | |
| "loss": 0.0, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.01590831337666781, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6372105263157886e-05, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.016079370509750255, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.584526315789473e-05, | |
| "loss": 0.0, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.016250427642832705, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.531842105263158e-05, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.016421484775915155, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4791578947368424e-05, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.016592541908997605, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.426473684210526e-05, | |
| "loss": 0.0, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.016763599042080055, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.37378947368421e-05, | |
| "loss": 0.0, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.016934656175162505, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.321105263157894e-05, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.017105713308244955, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017105713308244955, | |
| "eval_loss": NaN, | |
| "eval_runtime": 233.2013, | |
| "eval_samples_per_second": 10.557, | |
| "eval_steps_per_second": 2.641, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.017276770441327402, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.2157368421052626e-05, | |
| "loss": 0.0, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.017447827574409852, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.163052631578947e-05, | |
| "loss": 0.0, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.017618884707492302, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.110368421052632e-05, | |
| "loss": 0.0, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.017789941840574752, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.057684210526316e-05, | |
| "loss": 0.0, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.017960998973657202, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.005e-05, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.018132056106739652, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.9523157894736836e-05, | |
| "loss": 0.0, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.0183031132398221, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.899631578947368e-05, | |
| "loss": 0.0, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.01847417037290455, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.846947368421052e-05, | |
| "loss": 0.0, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.018645227505987, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.794263157894737e-05, | |
| "loss": 0.0, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.01881628463906945, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7415789473684206e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.0189873417721519, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.688894736842105e-05, | |
| "loss": 0.0, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.01915839890523435, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.636210526315789e-05, | |
| "loss": 0.0, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.0193294560383168, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.583526315789473e-05, | |
| "loss": 0.0, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.019500513171399246, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.530842105263158e-05, | |
| "loss": 0.0, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.019671570304481696, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.4781578947368416e-05, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.019842627437564146, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.425473684210526e-05, | |
| "loss": 0.0, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.020013684570646596, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.372789473684211e-05, | |
| "loss": 0.0, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.020184741703729046, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.320105263157895e-05, | |
| "loss": 0.0, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.020355798836811496, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2674210526315786e-05, | |
| "loss": 0.0, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.020526855969893943, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2147368421052626e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.020697913102976393, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.162052631578947e-05, | |
| "loss": 0.0, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.020868970236058843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.109368421052631e-05, | |
| "loss": 0.0, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.021040027369141293, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.056684210526316e-05, | |
| "loss": 0.0, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.021211084502223743, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.004e-05, | |
| "loss": 0.0, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.021382141635306193, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.951315789473684e-05, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.021553198768388643, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898631578947368e-05, | |
| "loss": 0.0, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.02172425590147109, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.845947368421052e-05, | |
| "loss": 0.0, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.02189531303455354, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7932631578947367e-05, | |
| "loss": 0.0, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.02206637016763599, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7405789473684206e-05, | |
| "loss": 0.0, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.02223742730071844, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6878947368421045e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02240848443380089, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.635210526315789e-05, | |
| "loss": 0.0, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.02257954156688334, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.582526315789474e-05, | |
| "loss": 0.0, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.022750598699965787, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5298421052631576e-05, | |
| "loss": 0.0, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.022921655833048237, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.477157894736842e-05, | |
| "loss": 0.0, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.023092712966130687, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.424473684210526e-05, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.023263770099213137, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.37178947368421e-05, | |
| "loss": 0.0, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.023434827232295587, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.319105263157894e-05, | |
| "loss": 0.0, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.023605884365378037, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2664210526315786e-05, | |
| "loss": 0.0, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.023776941498460488, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.213736842105263e-05, | |
| "loss": 0.0, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.023947998631542934, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.161052631578947e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.024119055764625384, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.108368421052632e-05, | |
| "loss": 0.0, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.024290112897707834, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0556842105263156e-05, | |
| "loss": 0.0, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.024461170030790284, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0029999999999995e-05, | |
| "loss": 0.0, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.024632227163872734, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9503157894736838e-05, | |
| "loss": 0.0, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.024803284296955184, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8976315789473684e-05, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.02497434143003763, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8449473684210523e-05, | |
| "loss": 0.0, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.02514539856312008, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7922631578947366e-05, | |
| "loss": 0.0, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.7395789473684212e-05, | |
| "loss": 0.0, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.02548751282928498, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.686894736842105e-05, | |
| "loss": 0.0, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.02565856996236743, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.634210526315789e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02565856996236743, | |
| "eval_loss": NaN, | |
| "eval_runtime": 233.374, | |
| "eval_samples_per_second": 10.55, | |
| "eval_steps_per_second": 2.64, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02582962709544988, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5815263157894736e-05, | |
| "loss": 0.0, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.026000684228532328, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.528842105263158e-05, | |
| "loss": 0.0, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.026171741361614778, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4761578947368418e-05, | |
| "loss": 0.0, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.026342798494697228, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.423473684210526e-05, | |
| "loss": 0.0, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.02651385562777968, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3707894736842103e-05, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.02668491276086213, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3181052631578946e-05, | |
| "loss": 0.0, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.02685596989394458, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.265421052631579e-05, | |
| "loss": 0.0, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.02702702702702703, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.212736842105263e-05, | |
| "loss": 0.0, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.027198084160109475, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1600526315789474e-05, | |
| "loss": 0.0, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.027369141293191925, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1073684210526313e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.027540198426274375, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0546842105263155e-05, | |
| "loss": 0.0, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.027711255559356825, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.002e-05, | |
| "loss": 0.0, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.027882312692439275, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.949315789473684e-05, | |
| "loss": 0.0, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.028053369825521726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8966315789473683e-05, | |
| "loss": 0.0, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.028224426958604172, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8439473684210522e-05, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.028395484091686622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.791263157894737e-05, | |
| "loss": 0.0, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.028566541224769072, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.738578947368421e-05, | |
| "loss": 0.0, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.028737598357851522, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.685894736842105e-05, | |
| "loss": 0.0, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.028908655490933972, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6332105263157893e-05, | |
| "loss": 0.0, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.029079712624016422, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5805263157894735e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.029250769757098873, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5278421052631578e-05, | |
| "loss": 0.0, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.02942182689018132, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4751578947368419e-05, | |
| "loss": 0.0, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.02959288402326377, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4224736842105262e-05, | |
| "loss": 0.0, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.02976394115634622, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3697894736842106e-05, | |
| "loss": 0.0, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.02993499828942867, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3171052631578945e-05, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03010605542251112, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.264421052631579e-05, | |
| "loss": 0.0, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.03027711255559357, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.211736842105263e-05, | |
| "loss": 0.0, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.030448169688676016, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1590526315789473e-05, | |
| "loss": 0.0, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.030619226821758466, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1063684210526316e-05, | |
| "loss": 0.0, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.030790283954840916, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0536842105263156e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.030961341087923366, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.001e-05, | |
| "loss": 0.0, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.031132398221005816, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.483157894736842e-06, | |
| "loss": 0.0, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.031303455354088267, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.956315789473684e-06, | |
| "loss": 0.0, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.03147451248717072, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.429473684210525e-06, | |
| "loss": 0.0, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.03164556962025317, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.902631578947368e-06, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03181662675333562, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.3757894736842095e-06, | |
| "loss": 0.0, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.03198768388641807, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.848947368421053e-06, | |
| "loss": 0.0, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.03215874101950051, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.322105263157895e-06, | |
| "loss": 0.0, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.03232979815258296, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7952631578947365e-06, | |
| "loss": 0.0, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.03250085528566541, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-06, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03267191241874786, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.741578947368421e-06, | |
| "loss": 0.0, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.03284296955183031, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2147368421052626e-06, | |
| "loss": 0.0, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.03301402668491276, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6878947368421047e-06, | |
| "loss": 0.0, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.03318508381799521, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1610526315789474e-06, | |
| "loss": 0.0, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.03335614095107766, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.634210526315789e-06, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.03352719808416011, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1073684210526313e-06, | |
| "loss": 0.0, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.03369825521724256, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5805263157894737e-06, | |
| "loss": 0.0, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.03386931235032501, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0536842105263156e-06, | |
| "loss": 0.0, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.03404036948340746, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.268421052631578e-07, | |
| "loss": 0.0, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.03421142661648991, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03421142661648991, | |
| "eval_loss": NaN, | |
| "eval_runtime": 232.8263, | |
| "eval_samples_per_second": 10.574, | |
| "eval_steps_per_second": 2.646, | |
| "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": 3 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.423512496546775e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |