| { | |
| "best_metric": 1.8791134357452393, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-150", | |
| "epoch": 0.084942393642113, | |
| "eval_steps": 25, | |
| "global_step": 166, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000511701166518753, | |
| "grad_norm": 0.46404364705085754, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.9735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000511701166518753, | |
| "eval_loss": 4.42933464050293, | |
| "eval_runtime": 1.5342, | |
| "eval_samples_per_second": 32.589, | |
| "eval_steps_per_second": 8.473, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001023402333037506, | |
| "grad_norm": 0.8488529324531555, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.7654, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001535103499556259, | |
| "grad_norm": 1.001631736755371, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0228, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002046804666075012, | |
| "grad_norm": 1.149634838104248, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 3.2201, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002558505832593765, | |
| "grad_norm": 1.4123715162277222, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 3.3185, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003070206999112518, | |
| "grad_norm": 1.9225883483886719, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4594, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0035819081656312713, | |
| "grad_norm": 1.8795751333236694, | |
| "learning_rate": 9.999132582169292e-05, | |
| "loss": 3.501, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004093609332150024, | |
| "grad_norm": 2.5900070667266846, | |
| "learning_rate": 9.996530663083255e-05, | |
| "loss": 3.7938, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004605310498668778, | |
| "grad_norm": 2.747680187225342, | |
| "learning_rate": 9.992195245831223e-05, | |
| "loss": 3.7944, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00511701166518753, | |
| "grad_norm": 2.346953868865967, | |
| "learning_rate": 9.986128001799077e-05, | |
| "loss": 3.8185, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005628712831706284, | |
| "grad_norm": 2.9237945079803467, | |
| "learning_rate": 9.978331270024886e-05, | |
| "loss": 3.9366, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.006140413998225036, | |
| "grad_norm": 3.622086524963379, | |
| "learning_rate": 9.96880805629717e-05, | |
| "loss": 4.2799, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00665211516474379, | |
| "grad_norm": 2.3093104362487793, | |
| "learning_rate": 9.957562031996097e-05, | |
| "loss": 1.8889, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0071638163312625425, | |
| "grad_norm": 3.3800673484802246, | |
| "learning_rate": 9.94459753267812e-05, | |
| "loss": 2.3106, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.007675517497781296, | |
| "grad_norm": 3.375108242034912, | |
| "learning_rate": 9.929919556404513e-05, | |
| "loss": 2.3937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008187218664300049, | |
| "grad_norm": 2.4301416873931885, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4152, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.008698919830818802, | |
| "grad_norm": 1.324080228805542, | |
| "learning_rate": 9.895446465943926e-05, | |
| "loss": 2.3565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.009210620997337556, | |
| "grad_norm": 1.267471194267273, | |
| "learning_rate": 9.875664641789545e-05, | |
| "loss": 2.3992, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.009722322163856307, | |
| "grad_norm": 1.367044448852539, | |
| "learning_rate": 9.85419591562117e-05, | |
| "loss": 2.4876, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01023402333037506, | |
| "grad_norm": 1.5106232166290283, | |
| "learning_rate": 9.831048564041413e-05, | |
| "loss": 2.6029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010745724496893814, | |
| "grad_norm": 1.4716838598251343, | |
| "learning_rate": 9.80623151079494e-05, | |
| "loss": 2.6521, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011257425663412568, | |
| "grad_norm": 1.2971686124801636, | |
| "learning_rate": 9.779754323328192e-05, | |
| "loss": 2.6698, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01176912682993132, | |
| "grad_norm": 1.4295047521591187, | |
| "learning_rate": 9.751627209100952e-05, | |
| "loss": 2.8462, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.012280827996450073, | |
| "grad_norm": 1.995835781097412, | |
| "learning_rate": 9.72186101165118e-05, | |
| "loss": 3.1823, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.012792529162968826, | |
| "grad_norm": 3.6110293865203857, | |
| "learning_rate": 9.690467206414616e-05, | |
| "loss": 3.855, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012792529162968826, | |
| "eval_loss": 2.3177919387817383, | |
| "eval_runtime": 1.5336, | |
| "eval_samples_per_second": 32.603, | |
| "eval_steps_per_second": 8.477, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01330423032948758, | |
| "grad_norm": 0.8223591446876526, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6149, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.013815931496006332, | |
| "grad_norm": 1.0949565172195435, | |
| "learning_rate": 9.622845807027113e-05, | |
| "loss": 2.0488, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.014327632662525085, | |
| "grad_norm": 1.1367841958999634, | |
| "learning_rate": 9.586644282212866e-05, | |
| "loss": 2.1151, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.014839333829043838, | |
| "grad_norm": 0.9595118761062622, | |
| "learning_rate": 9.548867278234998e-05, | |
| "loss": 2.1702, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.015351034995562592, | |
| "grad_norm": 0.8941548466682434, | |
| "learning_rate": 9.509529358847655e-05, | |
| "loss": 2.2371, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015862736162081344, | |
| "grad_norm": 0.9041470289230347, | |
| "learning_rate": 9.468645689567598e-05, | |
| "loss": 2.2612, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.016374437328600097, | |
| "grad_norm": 0.9832100868225098, | |
| "learning_rate": 9.426232031827588e-05, | |
| "loss": 2.3107, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01688613849511885, | |
| "grad_norm": 1.1351114511489868, | |
| "learning_rate": 9.382304736900063e-05, | |
| "loss": 2.3543, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.017397839661637604, | |
| "grad_norm": 1.2356266975402832, | |
| "learning_rate": 9.336880739593416e-05, | |
| "loss": 2.4014, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.017909540828156358, | |
| "grad_norm": 1.3643877506256104, | |
| "learning_rate": 9.28997755172329e-05, | |
| "loss": 2.5325, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01842124199467511, | |
| "grad_norm": 1.4238357543945312, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.75, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.018932943161193865, | |
| "grad_norm": 1.6282374858856201, | |
| "learning_rate": 9.191806495864812e-05, | |
| "loss": 2.8755, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.019444644327712615, | |
| "grad_norm": 0.45179080963134766, | |
| "learning_rate": 9.140576474687264e-05, | |
| "loss": 1.6157, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.019956345494231368, | |
| "grad_norm": 0.4603005051612854, | |
| "learning_rate": 9.087942941977182e-05, | |
| "loss": 1.8998, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02046804666075012, | |
| "grad_norm": 0.5871985554695129, | |
| "learning_rate": 9.033926188963352e-05, | |
| "loss": 2.0722, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020979747827268875, | |
| "grad_norm": 0.602536141872406, | |
| "learning_rate": 8.978547040132317e-05, | |
| "loss": 2.054, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02149144899378763, | |
| "grad_norm": 0.72366863489151, | |
| "learning_rate": 8.921826845200139e-05, | |
| "loss": 2.1352, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.022003150160306382, | |
| "grad_norm": 0.7915085554122925, | |
| "learning_rate": 8.863787470881686e-05, | |
| "loss": 2.0386, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.022514851326825135, | |
| "grad_norm": 0.8590556979179382, | |
| "learning_rate": 8.804451292460585e-05, | |
| "loss": 2.1996, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02302655249334389, | |
| "grad_norm": 0.9212091565132141, | |
| "learning_rate": 8.743841185163136e-05, | |
| "loss": 2.2756, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02353825365986264, | |
| "grad_norm": 0.9804298281669617, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.295, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.024049954826381392, | |
| "grad_norm": 1.0321789979934692, | |
| "learning_rate": 8.618893131455363e-05, | |
| "loss": 2.3681, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.024561655992900146, | |
| "grad_norm": 1.3598474264144897, | |
| "learning_rate": 8.554603354898238e-05, | |
| "loss": 2.4684, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0250733571594189, | |
| "grad_norm": 1.5326489210128784, | |
| "learning_rate": 8.489135970600768e-05, | |
| "loss": 2.6954, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.025585058325937653, | |
| "grad_norm": 2.6125943660736084, | |
| "learning_rate": 8.422516217485826e-05, | |
| "loss": 3.1982, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.025585058325937653, | |
| "eval_loss": 2.026942729949951, | |
| "eval_runtime": 1.535, | |
| "eval_samples_per_second": 32.573, | |
| "eval_steps_per_second": 8.469, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026096759492456406, | |
| "grad_norm": 0.4928167164325714, | |
| "learning_rate": 8.354769778736406e-05, | |
| "loss": 1.5405, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02660846065897516, | |
| "grad_norm": 0.6747775673866272, | |
| "learning_rate": 8.285922771894254e-05, | |
| "loss": 1.8902, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.027120161825493913, | |
| "grad_norm": 0.761574923992157, | |
| "learning_rate": 8.216001738791072e-05, | |
| "loss": 2.0376, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.027631862992012663, | |
| "grad_norm": 0.7025596499443054, | |
| "learning_rate": 8.14503363531613e-05, | |
| "loss": 2.0866, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.028143564158531417, | |
| "grad_norm": 0.7048724889755249, | |
| "learning_rate": 8.073045821024256e-05, | |
| "loss": 2.0865, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02865526532505017, | |
| "grad_norm": 0.8263847231864929, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.0262, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.029166966491568923, | |
| "grad_norm": 0.8577947616577148, | |
| "learning_rate": 7.926122453099503e-05, | |
| "loss": 2.1969, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.029678667658087677, | |
| "grad_norm": 1.095415711402893, | |
| "learning_rate": 7.85124354122177e-05, | |
| "loss": 2.2191, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03019036882460643, | |
| "grad_norm": 1.0914173126220703, | |
| "learning_rate": 7.775458180200932e-05, | |
| "loss": 2.2533, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.030702069991125184, | |
| "grad_norm": 1.104080080986023, | |
| "learning_rate": 7.698795586736298e-05, | |
| "loss": 2.3613, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.031213771157643937, | |
| "grad_norm": 1.2872527837753296, | |
| "learning_rate": 7.62128531571699e-05, | |
| "loss": 2.4725, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03172547232416269, | |
| "grad_norm": 1.6460251808166504, | |
| "learning_rate": 7.542957248827961e-05, | |
| "loss": 2.7487, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03223717349068144, | |
| "grad_norm": 0.5120904445648193, | |
| "learning_rate": 7.46384158303004e-05, | |
| "loss": 1.4998, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.032748874657200194, | |
| "grad_norm": 0.5734795928001404, | |
| "learning_rate": 7.383968818918426e-05, | |
| "loss": 1.8322, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03326057582371895, | |
| "grad_norm": 0.6029512286186218, | |
| "learning_rate": 7.303369748964134e-05, | |
| "loss": 1.9155, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.0337722769902377, | |
| "grad_norm": 0.6455990076065063, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.0008, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.034283978156756455, | |
| "grad_norm": 0.6918196082115173, | |
| "learning_rate": 7.140117249456176e-05, | |
| "loss": 2.0541, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.03479567932327521, | |
| "grad_norm": 0.7618705630302429, | |
| "learning_rate": 7.057526756848719e-05, | |
| "loss": 2.062, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03530738048979396, | |
| "grad_norm": 0.7683627605438232, | |
| "learning_rate": 6.97433580802762e-05, | |
| "loss": 2.0749, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.035819081656312715, | |
| "grad_norm": 0.8340547680854797, | |
| "learning_rate": 6.890576474687263e-05, | |
| "loss": 2.108, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03633078282283147, | |
| "grad_norm": 0.9197708368301392, | |
| "learning_rate": 6.80628104764508e-05, | |
| "loss": 2.1471, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03684248398935022, | |
| "grad_norm": 1.2023193836212158, | |
| "learning_rate": 6.721482024392835e-05, | |
| "loss": 2.2415, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.037354185155868976, | |
| "grad_norm": 1.1722882986068726, | |
| "learning_rate": 6.63621209656821e-05, | |
| "loss": 2.3475, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03786588632238773, | |
| "grad_norm": 1.4040749073028564, | |
| "learning_rate": 6.550504137351576e-05, | |
| "loss": 2.6166, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.038377587488906476, | |
| "grad_norm": 2.434393882751465, | |
| "learning_rate": 6.46439118879273e-05, | |
| "loss": 2.8818, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.038377587488906476, | |
| "eval_loss": 1.9559780359268188, | |
| "eval_runtime": 1.5335, | |
| "eval_samples_per_second": 32.605, | |
| "eval_steps_per_second": 8.477, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03888928865542523, | |
| "grad_norm": 0.4053546190261841, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5548, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.03940098982194398, | |
| "grad_norm": 0.550913393497467, | |
| "learning_rate": 6.291083259704596e-05, | |
| "loss": 1.8655, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.039912690988462736, | |
| "grad_norm": 0.5964261889457703, | |
| "learning_rate": 6.203955092681039e-05, | |
| "loss": 1.9327, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.04042439215498149, | |
| "grad_norm": 0.7430030107498169, | |
| "learning_rate": 6.116555537568857e-05, | |
| "loss": 2.0133, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.04093609332150024, | |
| "grad_norm": 0.7743514180183411, | |
| "learning_rate": 6.0289182885602704e-05, | |
| "loss": 2.0308, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.041447794488018996, | |
| "grad_norm": 0.8544523119926453, | |
| "learning_rate": 5.941077131483025e-05, | |
| "loss": 2.0096, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.04195949565453775, | |
| "grad_norm": 0.7836202383041382, | |
| "learning_rate": 5.8530659307753036e-05, | |
| "loss": 2.0285, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.0424711968210565, | |
| "grad_norm": 0.9040354490280151, | |
| "learning_rate": 5.7649186164303506e-05, | |
| "loss": 2.0367, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.04298289798757526, | |
| "grad_norm": 0.9767117500305176, | |
| "learning_rate": 5.6766691709158096e-05, | |
| "loss": 2.1512, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.04349459915409401, | |
| "grad_norm": 1.108844518661499, | |
| "learning_rate": 5.5883516160728274e-05, | |
| "loss": 2.2661, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.044006300320612764, | |
| "grad_norm": 1.3114573955535889, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.374, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.04451800148713152, | |
| "grad_norm": 1.5609687566757202, | |
| "learning_rate": 5.4116483839271736e-05, | |
| "loss": 2.6349, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.04502970265365027, | |
| "grad_norm": 0.42394495010375977, | |
| "learning_rate": 5.3233308290841935e-05, | |
| "loss": 1.4049, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.045541403820169024, | |
| "grad_norm": 0.524941086769104, | |
| "learning_rate": 5.235081383569649e-05, | |
| "loss": 1.8021, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.04605310498668778, | |
| "grad_norm": 0.7207713723182678, | |
| "learning_rate": 5.1469340692246995e-05, | |
| "loss": 1.8878, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.046564806153206524, | |
| "grad_norm": 0.6740505695343018, | |
| "learning_rate": 5.058922868516978e-05, | |
| "loss": 1.9676, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04707650731972528, | |
| "grad_norm": 0.71189945936203, | |
| "learning_rate": 4.9710817114397314e-05, | |
| "loss": 1.9829, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04758820848624403, | |
| "grad_norm": 0.6990759372711182, | |
| "learning_rate": 4.883444462431145e-05, | |
| "loss": 1.9317, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.048099909652762785, | |
| "grad_norm": 0.7979338765144348, | |
| "learning_rate": 4.7960449073189606e-05, | |
| "loss": 1.9789, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.04861161081928154, | |
| "grad_norm": 0.8845726847648621, | |
| "learning_rate": 4.708916740295405e-05, | |
| "loss": 2.0438, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04912331198580029, | |
| "grad_norm": 0.9462182521820068, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.0737, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.049635013152319045, | |
| "grad_norm": 1.0222724676132202, | |
| "learning_rate": 4.535608811207272e-05, | |
| "loss": 2.0986, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.0501467143188378, | |
| "grad_norm": 1.254888892173767, | |
| "learning_rate": 4.4494958626484276e-05, | |
| "loss": 2.3094, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.05065841548535655, | |
| "grad_norm": 1.4137556552886963, | |
| "learning_rate": 4.36378790343179e-05, | |
| "loss": 2.4861, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.051170116651875305, | |
| "grad_norm": 2.0688607692718506, | |
| "learning_rate": 4.278517975607167e-05, | |
| "loss": 2.9678, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.051170116651875305, | |
| "eval_loss": 1.9229816198349, | |
| "eval_runtime": 1.5335, | |
| "eval_samples_per_second": 32.605, | |
| "eval_steps_per_second": 8.477, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05168181781839406, | |
| "grad_norm": 0.40056556463241577, | |
| "learning_rate": 4.19371895235492e-05, | |
| "loss": 1.532, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.05219351898491281, | |
| "grad_norm": 0.6019428372383118, | |
| "learning_rate": 4.109423525312738e-05, | |
| "loss": 1.8149, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.052705220151431566, | |
| "grad_norm": 0.7042158842086792, | |
| "learning_rate": 4.0256641919723806e-05, | |
| "loss": 1.8967, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.05321692131795032, | |
| "grad_norm": 0.725395917892456, | |
| "learning_rate": 3.942473243151281e-05, | |
| "loss": 1.939, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.05372862248446907, | |
| "grad_norm": 0.8081313371658325, | |
| "learning_rate": 3.859882750543826e-05, | |
| "loss": 2.0155, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.054240323650987826, | |
| "grad_norm": 0.7761573195457458, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 2.0242, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.05475202481750658, | |
| "grad_norm": 0.7627308368682861, | |
| "learning_rate": 3.6966302510358666e-05, | |
| "loss": 2.0408, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.055263725984025326, | |
| "grad_norm": 0.954046905040741, | |
| "learning_rate": 3.616031181081575e-05, | |
| "loss": 2.0613, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.05577542715054408, | |
| "grad_norm": 1.0556938648223877, | |
| "learning_rate": 3.53615841696996e-05, | |
| "loss": 2.1036, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.05628712831706283, | |
| "grad_norm": 1.131365418434143, | |
| "learning_rate": 3.45704275117204e-05, | |
| "loss": 2.1926, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05679882948358159, | |
| "grad_norm": 1.4441267251968384, | |
| "learning_rate": 3.378714684283011e-05, | |
| "loss": 2.3588, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.05731053065010034, | |
| "grad_norm": 1.711294412612915, | |
| "learning_rate": 3.301204413263704e-05, | |
| "loss": 2.615, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.057822231816619094, | |
| "grad_norm": 0.3940889239311218, | |
| "learning_rate": 3.224541819799071e-05, | |
| "loss": 1.4173, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.05833393298313785, | |
| "grad_norm": 0.5546037554740906, | |
| "learning_rate": 3.1487564587782306e-05, | |
| "loss": 1.6893, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0588456341496566, | |
| "grad_norm": 0.6007658243179321, | |
| "learning_rate": 3.0738775469004985e-05, | |
| "loss": 1.8685, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.059357335316175354, | |
| "grad_norm": 0.675112247467041, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.9225, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.05986903648269411, | |
| "grad_norm": 0.7189555168151855, | |
| "learning_rate": 2.926954178975746e-05, | |
| "loss": 1.9709, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.06038073764921286, | |
| "grad_norm": 0.7457597255706787, | |
| "learning_rate": 2.854966364683872e-05, | |
| "loss": 1.9753, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.060892438815731614, | |
| "grad_norm": 0.869260847568512, | |
| "learning_rate": 2.783998261208929e-05, | |
| "loss": 2.0098, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.06140413998225037, | |
| "grad_norm": 0.9872080087661743, | |
| "learning_rate": 2.7140772281057468e-05, | |
| "loss": 2.0447, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06191584114876912, | |
| "grad_norm": 1.0225969552993774, | |
| "learning_rate": 2.645230221263596e-05, | |
| "loss": 2.0648, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.062427542315287875, | |
| "grad_norm": 1.0745333433151245, | |
| "learning_rate": 2.577483782514174e-05, | |
| "loss": 2.1066, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.06293924348180663, | |
| "grad_norm": 1.2674683332443237, | |
| "learning_rate": 2.5108640293992337e-05, | |
| "loss": 2.2943, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.06345094464832537, | |
| "grad_norm": 1.3520656824111938, | |
| "learning_rate": 2.445396645101762e-05, | |
| "loss": 2.3662, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.06396264581484414, | |
| "grad_norm": 1.9982293844223022, | |
| "learning_rate": 2.3811068685446395e-05, | |
| "loss": 2.8426, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06396264581484414, | |
| "eval_loss": 1.8993180990219116, | |
| "eval_runtime": 1.5346, | |
| "eval_samples_per_second": 32.582, | |
| "eval_steps_per_second": 8.471, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.06447434698136288, | |
| "grad_norm": 0.36793649196624756, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.4921, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.06498604814788164, | |
| "grad_norm": 0.5427601337432861, | |
| "learning_rate": 2.2561588148368657e-05, | |
| "loss": 1.8148, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.06549774931440039, | |
| "grad_norm": 0.6203567385673523, | |
| "learning_rate": 2.195548707539416e-05, | |
| "loss": 1.8883, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.06600945048091915, | |
| "grad_norm": 0.6660148501396179, | |
| "learning_rate": 2.136212529118314e-05, | |
| "loss": 1.9282, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.0665211516474379, | |
| "grad_norm": 0.7544979453086853, | |
| "learning_rate": 2.0781731547998614e-05, | |
| "loss": 1.9454, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06703285281395666, | |
| "grad_norm": 0.7683319449424744, | |
| "learning_rate": 2.0214529598676836e-05, | |
| "loss": 1.9783, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.0675445539804754, | |
| "grad_norm": 0.8448789715766907, | |
| "learning_rate": 1.966073811036649e-05, | |
| "loss": 1.9902, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.06805625514699415, | |
| "grad_norm": 0.9101701378822327, | |
| "learning_rate": 1.9120570580228186e-05, | |
| "loss": 2.0101, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.06856795631351291, | |
| "grad_norm": 1.002808928489685, | |
| "learning_rate": 1.8594235253127375e-05, | |
| "loss": 2.1164, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.06907965748003166, | |
| "grad_norm": 1.1789017915725708, | |
| "learning_rate": 1.8081935041351887e-05, | |
| "loss": 2.2391, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.06959135864655042, | |
| "grad_norm": 1.4245861768722534, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.3897, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.07010305981306916, | |
| "grad_norm": 1.6070505380630493, | |
| "learning_rate": 1.7100224482767114e-05, | |
| "loss": 2.5421, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.07061476097958792, | |
| "grad_norm": 0.4116235673427582, | |
| "learning_rate": 1.6631192604065855e-05, | |
| "loss": 1.4141, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.07112646214610667, | |
| "grad_norm": 0.5044823288917542, | |
| "learning_rate": 1.617695263099937e-05, | |
| "loss": 1.8181, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.07163816331262543, | |
| "grad_norm": 0.5927360653877258, | |
| "learning_rate": 1.573767968172413e-05, | |
| "loss": 1.8575, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07214986447914418, | |
| "grad_norm": 0.6108676791191101, | |
| "learning_rate": 1.531354310432403e-05, | |
| "loss": 1.9401, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.07266156564566294, | |
| "grad_norm": 0.6655164361000061, | |
| "learning_rate": 1.490470641152345e-05, | |
| "loss": 1.9377, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.07317326681218168, | |
| "grad_norm": 0.758387565612793, | |
| "learning_rate": 1.4511327217650046e-05, | |
| "loss": 1.9332, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.07368496797870044, | |
| "grad_norm": 0.8023284673690796, | |
| "learning_rate": 1.413355717787134e-05, | |
| "loss": 1.9804, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.07419666914521919, | |
| "grad_norm": 0.8641353249549866, | |
| "learning_rate": 1.3771541929728886e-05, | |
| "loss": 1.9505, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.07470837031173795, | |
| "grad_norm": 1.0415940284729004, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.0321, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.0752200714782567, | |
| "grad_norm": 1.1581557989120483, | |
| "learning_rate": 1.309532793585384e-05, | |
| "loss": 2.0956, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.07573177264477546, | |
| "grad_norm": 1.1987535953521729, | |
| "learning_rate": 1.2781389883488218e-05, | |
| "loss": 2.2152, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.0762434738112942, | |
| "grad_norm": 1.6775120496749878, | |
| "learning_rate": 1.248372790899049e-05, | |
| "loss": 2.586, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.07675517497781295, | |
| "grad_norm": 2.6760313510894775, | |
| "learning_rate": 1.2202456766718093e-05, | |
| "loss": 3.0532, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07675517497781295, | |
| "eval_loss": 1.8791134357452393, | |
| "eval_runtime": 1.5354, | |
| "eval_samples_per_second": 32.565, | |
| "eval_steps_per_second": 8.467, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07726687614433171, | |
| "grad_norm": 0.33062976598739624, | |
| "learning_rate": 1.1937684892050604e-05, | |
| "loss": 1.3588, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.07777857731085046, | |
| "grad_norm": 0.5277450084686279, | |
| "learning_rate": 1.168951435958588e-05, | |
| "loss": 1.7291, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.07829027847736922, | |
| "grad_norm": 0.5764089226722717, | |
| "learning_rate": 1.1458040843788312e-05, | |
| "loss": 1.8712, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.07880197964388796, | |
| "grad_norm": 0.6534531712532043, | |
| "learning_rate": 1.1243353582104556e-05, | |
| "loss": 1.9575, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.07931368081040673, | |
| "grad_norm": 0.7147605419158936, | |
| "learning_rate": 1.1045535340560744e-05, | |
| "loss": 1.9211, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.07982538197692547, | |
| "grad_norm": 0.7351657748222351, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.9539, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.08033708314344423, | |
| "grad_norm": 0.8152849674224854, | |
| "learning_rate": 1.070080443595488e-05, | |
| "loss": 2.0232, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.08084878430996298, | |
| "grad_norm": 0.9168938398361206, | |
| "learning_rate": 1.0554024673218807e-05, | |
| "loss": 1.9743, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.08136048547648174, | |
| "grad_norm": 1.0510733127593994, | |
| "learning_rate": 1.0424379680039025e-05, | |
| "loss": 2.0778, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.08187218664300049, | |
| "grad_norm": 1.2245820760726929, | |
| "learning_rate": 1.0311919437028318e-05, | |
| "loss": 2.2151, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08238388780951925, | |
| "grad_norm": 1.3239753246307373, | |
| "learning_rate": 1.0216687299751144e-05, | |
| "loss": 2.2195, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.08289558897603799, | |
| "grad_norm": 1.7548948526382446, | |
| "learning_rate": 1.0138719982009242e-05, | |
| "loss": 2.5937, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.08340729014255675, | |
| "grad_norm": 0.4118451774120331, | |
| "learning_rate": 1.007804754168779e-05, | |
| "loss": 1.4343, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.0839189913090755, | |
| "grad_norm": 0.5209285616874695, | |
| "learning_rate": 1.003469336916747e-05, | |
| "loss": 1.7331, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.08443069247559425, | |
| "grad_norm": 0.5564490556716919, | |
| "learning_rate": 1.0008674178307085e-05, | |
| "loss": 1.8639, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.084942393642113, | |
| "grad_norm": 0.6351719498634338, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9287, | |
| "step": 166 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 166, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 30, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.944151006450811e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |