| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.908943089430894, | |
| "eval_steps": 500, | |
| "global_step": 1140, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013008130081300813, | |
| "grad_norm": 230.88125753772232, | |
| "learning_rate": 5.714285714285715e-07, | |
| "loss": 8.6242, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026016260162601626, | |
| "grad_norm": 208.76444315978463, | |
| "learning_rate": 1.142857142857143e-06, | |
| "loss": 8.5102, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 216.97693342125092, | |
| "learning_rate": 1.7142857142857145e-06, | |
| "loss": 8.6752, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05203252032520325, | |
| "grad_norm": 231.45591088243566, | |
| "learning_rate": 2.285714285714286e-06, | |
| "loss": 8.4936, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06504065040650407, | |
| "grad_norm": 212.77968160229423, | |
| "learning_rate": 2.8571428571428573e-06, | |
| "loss": 7.6862, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 156.7176569348902, | |
| "learning_rate": 3.428571428571429e-06, | |
| "loss": 5.9776, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0910569105691057, | |
| "grad_norm": 90.12791665931498, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 3.2091, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1040650406504065, | |
| "grad_norm": 61.965766767519, | |
| "learning_rate": 4.571428571428572e-06, | |
| "loss": 2.3428, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 47.54431569154033, | |
| "learning_rate": 5.142857142857142e-06, | |
| "loss": 1.7836, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.13008130081300814, | |
| "grad_norm": 47.20331806396116, | |
| "learning_rate": 5.7142857142857145e-06, | |
| "loss": 1.4851, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14308943089430895, | |
| "grad_norm": 38.36570648710507, | |
| "learning_rate": 6.285714285714286e-06, | |
| "loss": 1.3206, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15609756097560976, | |
| "grad_norm": 29.066038353919424, | |
| "learning_rate": 6.857142857142858e-06, | |
| "loss": 1.1916, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16910569105691056, | |
| "grad_norm": 21.722668900948843, | |
| "learning_rate": 7.428571428571429e-06, | |
| "loss": 1.1014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1821138211382114, | |
| "grad_norm": 15.87425801890939, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.8121, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 17.587447371642845, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.9999, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.208130081300813, | |
| "grad_norm": 16.23353351483177, | |
| "learning_rate": 9.142857142857144e-06, | |
| "loss": 0.8833, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.22113821138211381, | |
| "grad_norm": 15.487688413211991, | |
| "learning_rate": 9.714285714285715e-06, | |
| "loss": 0.5773, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23414634146341465, | |
| "grad_norm": 13.566620977135004, | |
| "learning_rate": 1.0285714285714285e-05, | |
| "loss": 0.7757, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24715447154471545, | |
| "grad_norm": 12.462190186073848, | |
| "learning_rate": 1.0857142857142858e-05, | |
| "loss": 0.6909, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2601626016260163, | |
| "grad_norm": 9.863692920491205, | |
| "learning_rate": 1.1428571428571429e-05, | |
| "loss": 0.5492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2731707317073171, | |
| "grad_norm": 15.820830571242366, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.6604, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2861788617886179, | |
| "grad_norm": 12.483935396645652, | |
| "learning_rate": 1.2571428571428572e-05, | |
| "loss": 0.6353, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2991869918699187, | |
| "grad_norm": 13.167505155488156, | |
| "learning_rate": 1.3142857142857145e-05, | |
| "loss": 0.6198, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3121951219512195, | |
| "grad_norm": 11.312617034012124, | |
| "learning_rate": 1.3714285714285716e-05, | |
| "loss": 0.6247, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3252032520325203, | |
| "grad_norm": 10.440846014107416, | |
| "learning_rate": 1.4285714285714287e-05, | |
| "loss": 0.5274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3382113821138211, | |
| "grad_norm": 13.199338633996815, | |
| "learning_rate": 1.4857142857142858e-05, | |
| "loss": 0.6209, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.35121951219512193, | |
| "grad_norm": 12.032299778483855, | |
| "learning_rate": 1.542857142857143e-05, | |
| "loss": 0.653, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3642276422764228, | |
| "grad_norm": 11.866587650490903, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.4805, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3772357723577236, | |
| "grad_norm": 8.933036188530423, | |
| "learning_rate": 1.6571428571428574e-05, | |
| "loss": 0.4935, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 10.436307527405338, | |
| "learning_rate": 1.7142857142857142e-05, | |
| "loss": 0.5817, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4032520325203252, | |
| "grad_norm": 9.297670799220597, | |
| "learning_rate": 1.7714285714285717e-05, | |
| "loss": 0.4342, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.416260162601626, | |
| "grad_norm": 7.600678151452253, | |
| "learning_rate": 1.8285714285714288e-05, | |
| "loss": 0.4984, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4292682926829268, | |
| "grad_norm": 8.286210274367773, | |
| "learning_rate": 1.885714285714286e-05, | |
| "loss": 0.4809, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.44227642276422763, | |
| "grad_norm": 8.654757939781744, | |
| "learning_rate": 1.942857142857143e-05, | |
| "loss": 0.5042, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.45528455284552843, | |
| "grad_norm": 7.70000564697565, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4682926829268293, | |
| "grad_norm": 7.2151873058037115, | |
| "learning_rate": 1.999995958478429e-05, | |
| "loss": 0.4446, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4813008130081301, | |
| "grad_norm": 6.722907147890219, | |
| "learning_rate": 1.999983833946383e-05, | |
| "loss": 0.4187, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4943089430894309, | |
| "grad_norm": 6.534701787629057, | |
| "learning_rate": 1.9999636265018655e-05, | |
| "loss": 0.4235, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.5073170731707317, | |
| "grad_norm": 8.837751955851171, | |
| "learning_rate": 1.999935336308214e-05, | |
| "loss": 0.5159, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5203252032520326, | |
| "grad_norm": 8.3598460515532, | |
| "learning_rate": 1.9998989635940996e-05, | |
| "loss": 0.459, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 5.861736968755028, | |
| "learning_rate": 1.9998545086535242e-05, | |
| "loss": 0.3528, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5463414634146342, | |
| "grad_norm": 7.139988271289857, | |
| "learning_rate": 1.9998019718458194e-05, | |
| "loss": 0.4082, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.5593495934959349, | |
| "grad_norm": 7.909067319149876, | |
| "learning_rate": 1.999741353595642e-05, | |
| "loss": 0.4493, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5723577235772358, | |
| "grad_norm": 8.541027166094969, | |
| "learning_rate": 1.9996726543929717e-05, | |
| "loss": 0.4543, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 6.376818167843216, | |
| "learning_rate": 1.9995958747931083e-05, | |
| "loss": 0.4319, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5983739837398374, | |
| "grad_norm": 7.666803532320634, | |
| "learning_rate": 1.9995110154166636e-05, | |
| "loss": 0.4639, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6113821138211382, | |
| "grad_norm": 5.366689030683648, | |
| "learning_rate": 1.99941807694956e-05, | |
| "loss": 0.3108, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.624390243902439, | |
| "grad_norm": 4.76561069358933, | |
| "learning_rate": 1.9993170601430233e-05, | |
| "loss": 0.3488, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6373983739837399, | |
| "grad_norm": 5.579353151449992, | |
| "learning_rate": 1.9992079658135757e-05, | |
| "loss": 0.3292, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6504065040650406, | |
| "grad_norm": 4.529381400281467, | |
| "learning_rate": 1.9990907948430327e-05, | |
| "loss": 0.3233, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6634146341463415, | |
| "grad_norm": 4.89310755054693, | |
| "learning_rate": 1.9989655481784917e-05, | |
| "loss": 0.2976, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6764227642276422, | |
| "grad_norm": 6.094851323707289, | |
| "learning_rate": 1.998832226832327e-05, | |
| "loss": 0.3427, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6894308943089431, | |
| "grad_norm": 7.519057655874433, | |
| "learning_rate": 1.9986908318821804e-05, | |
| "loss": 0.4168, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.7024390243902439, | |
| "grad_norm": 6.734374113916692, | |
| "learning_rate": 1.998541364470954e-05, | |
| "loss": 0.3456, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.7154471544715447, | |
| "grad_norm": 5.611175619279291, | |
| "learning_rate": 1.998383825806799e-05, | |
| "loss": 0.3057, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.7284552845528456, | |
| "grad_norm": 5.415014977209956, | |
| "learning_rate": 1.9982182171631065e-05, | |
| "loss": 0.3841, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.7414634146341463, | |
| "grad_norm": 6.040329603282613, | |
| "learning_rate": 1.9980445398784998e-05, | |
| "loss": 0.3914, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7544715447154472, | |
| "grad_norm": 5.620902759656132, | |
| "learning_rate": 1.9978627953568187e-05, | |
| "loss": 0.3412, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.767479674796748, | |
| "grad_norm": 7.154464466166392, | |
| "learning_rate": 1.997672985067113e-05, | |
| "loss": 0.3879, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 6.832499040469465, | |
| "learning_rate": 1.9974751105436266e-05, | |
| "loss": 0.4399, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7934959349593496, | |
| "grad_norm": 5.90878066056323, | |
| "learning_rate": 1.997269173385788e-05, | |
| "loss": 0.3527, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.8065040650406504, | |
| "grad_norm": 6.0530816990814, | |
| "learning_rate": 1.9970551752581964e-05, | |
| "loss": 0.4588, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.8195121951219512, | |
| "grad_norm": 5.527433101647836, | |
| "learning_rate": 1.9968331178906082e-05, | |
| "loss": 0.385, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.832520325203252, | |
| "grad_norm": 4.3592020276526915, | |
| "learning_rate": 1.9966030030779216e-05, | |
| "loss": 0.2998, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.8455284552845529, | |
| "grad_norm": 5.254802387533948, | |
| "learning_rate": 1.9963648326801653e-05, | |
| "loss": 0.3382, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8585365853658536, | |
| "grad_norm": 9.281183098955887, | |
| "learning_rate": 1.996118608622481e-05, | |
| "loss": 0.394, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8715447154471545, | |
| "grad_norm": 8.38170471119074, | |
| "learning_rate": 1.9958643328951083e-05, | |
| "loss": 0.3701, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8845528455284553, | |
| "grad_norm": 6.313134696492434, | |
| "learning_rate": 1.9956020075533683e-05, | |
| "loss": 0.4177, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8975609756097561, | |
| "grad_norm": 4.348932383253668, | |
| "learning_rate": 1.995331634717649e-05, | |
| "loss": 0.2945, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.9105691056910569, | |
| "grad_norm": 4.433107884805326, | |
| "learning_rate": 1.9950532165733847e-05, | |
| "loss": 0.3633, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9235772357723577, | |
| "grad_norm": 5.362504384821112, | |
| "learning_rate": 1.994766755371042e-05, | |
| "loss": 0.2932, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.9365853658536586, | |
| "grad_norm": 5.581345628544194, | |
| "learning_rate": 1.994472253426099e-05, | |
| "loss": 0.3256, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.9495934959349593, | |
| "grad_norm": 5.942912969150186, | |
| "learning_rate": 1.9941697131190273e-05, | |
| "loss": 0.396, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9626016260162602, | |
| "grad_norm": 6.177454994439193, | |
| "learning_rate": 1.993859136895274e-05, | |
| "loss": 0.4033, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 5.3956839647398045, | |
| "learning_rate": 1.993540527265239e-05, | |
| "loss": 0.2666, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.9886178861788618, | |
| "grad_norm": 5.614670334975762, | |
| "learning_rate": 1.993213886804259e-05, | |
| "loss": 0.2943, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.0016260162601627, | |
| "grad_norm": 4.36195352952533, | |
| "learning_rate": 1.9928792181525818e-05, | |
| "loss": 0.2482, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.0146341463414634, | |
| "grad_norm": 4.4213065815641635, | |
| "learning_rate": 1.992536524015349e-05, | |
| "loss": 0.2827, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.0276422764227642, | |
| "grad_norm": 3.990647245954731, | |
| "learning_rate": 1.992185807162572e-05, | |
| "loss": 0.2666, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.040650406504065, | |
| "grad_norm": 3.861722635891494, | |
| "learning_rate": 1.9918270704291104e-05, | |
| "loss": 0.1926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.053658536585366, | |
| "grad_norm": 5.300012815448601, | |
| "learning_rate": 1.9914603167146488e-05, | |
| "loss": 0.2653, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 5.892127749110154, | |
| "learning_rate": 1.9910855489836734e-05, | |
| "loss": 0.2561, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.0796747967479674, | |
| "grad_norm": 5.396249404462623, | |
| "learning_rate": 1.9907027702654472e-05, | |
| "loss": 0.2834, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.0926829268292684, | |
| "grad_norm": 4.64475319206961, | |
| "learning_rate": 1.9903119836539877e-05, | |
| "loss": 0.2191, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.1056910569105691, | |
| "grad_norm": 6.605780905277876, | |
| "learning_rate": 1.98991319230804e-05, | |
| "loss": 0.2772, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.1186991869918699, | |
| "grad_norm": 5.909098612060078, | |
| "learning_rate": 1.9895063994510512e-05, | |
| "loss": 0.2477, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.1317073170731708, | |
| "grad_norm": 5.365729884394164, | |
| "learning_rate": 1.9890916083711463e-05, | |
| "loss": 0.2456, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.1447154471544716, | |
| "grad_norm": 4.018252159668762, | |
| "learning_rate": 1.9886688224210988e-05, | |
| "loss": 0.1861, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.1577235772357723, | |
| "grad_norm": 4.853996625324599, | |
| "learning_rate": 1.988238045018306e-05, | |
| "loss": 0.2517, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 6.643416305208953, | |
| "learning_rate": 1.9877992796447604e-05, | |
| "loss": 0.2827, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.183739837398374, | |
| "grad_norm": 6.1422339106616635, | |
| "learning_rate": 1.987352529847021e-05, | |
| "loss": 0.3496, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.1967479674796748, | |
| "grad_norm": 6.13749677489359, | |
| "learning_rate": 1.9868977992361866e-05, | |
| "loss": 0.3071, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.2097560975609756, | |
| "grad_norm": 5.168323351119836, | |
| "learning_rate": 1.9864350914878635e-05, | |
| "loss": 0.2334, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.2227642276422763, | |
| "grad_norm": 4.1938765456615, | |
| "learning_rate": 1.9859644103421384e-05, | |
| "loss": 0.2995, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.2357723577235773, | |
| "grad_norm": 5.211177152960159, | |
| "learning_rate": 1.9854857596035476e-05, | |
| "loss": 0.292, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.248780487804878, | |
| "grad_norm": 4.518477406407479, | |
| "learning_rate": 1.984999143141046e-05, | |
| "loss": 0.2276, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.2617886178861788, | |
| "grad_norm": 5.486829663924403, | |
| "learning_rate": 1.9845045648879747e-05, | |
| "loss": 0.2806, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.2747967479674798, | |
| "grad_norm": 5.215692596964664, | |
| "learning_rate": 1.9840020288420314e-05, | |
| "loss": 0.2663, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.2878048780487805, | |
| "grad_norm": 5.105134623598349, | |
| "learning_rate": 1.983491539065237e-05, | |
| "loss": 0.3274, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.3008130081300813, | |
| "grad_norm": 4.417060162706909, | |
| "learning_rate": 1.982973099683902e-05, | |
| "loss": 0.2896, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3138211382113822, | |
| "grad_norm": 3.9117691328961506, | |
| "learning_rate": 1.9824467148885942e-05, | |
| "loss": 0.2262, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.326829268292683, | |
| "grad_norm": 4.648561917684093, | |
| "learning_rate": 1.981912388934105e-05, | |
| "loss": 0.2347, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.3398373983739837, | |
| "grad_norm": 5.317602564983213, | |
| "learning_rate": 1.9813701261394136e-05, | |
| "loss": 0.3124, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.3528455284552845, | |
| "grad_norm": 4.364016353059765, | |
| "learning_rate": 1.9808199308876543e-05, | |
| "loss": 0.2752, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 4.99818282544751, | |
| "learning_rate": 1.9802618076260784e-05, | |
| "loss": 0.2777, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.3788617886178862, | |
| "grad_norm": 4.483511669693501, | |
| "learning_rate": 1.9796957608660203e-05, | |
| "loss": 0.2571, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.391869918699187, | |
| "grad_norm": 3.9121651483634716, | |
| "learning_rate": 1.9791217951828607e-05, | |
| "loss": 0.2554, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.4048780487804877, | |
| "grad_norm": 4.124381091041692, | |
| "learning_rate": 1.978539915215989e-05, | |
| "loss": 0.3098, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.4178861788617887, | |
| "grad_norm": 4.833188929280863, | |
| "learning_rate": 1.9779501256687658e-05, | |
| "loss": 0.2949, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 1.4308943089430894, | |
| "grad_norm": 4.278489655548645, | |
| "learning_rate": 1.9773524313084857e-05, | |
| "loss": 0.2002, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4439024390243902, | |
| "grad_norm": 6.2723343004180725, | |
| "learning_rate": 1.9767468369663382e-05, | |
| "loss": 0.3199, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 1.4569105691056912, | |
| "grad_norm": 4.348567811446221, | |
| "learning_rate": 1.9761333475373677e-05, | |
| "loss": 0.246, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 1.469918699186992, | |
| "grad_norm": 3.7868561454272203, | |
| "learning_rate": 1.975511967980437e-05, | |
| "loss": 0.2748, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 1.4829268292682927, | |
| "grad_norm": 5.143565989659963, | |
| "learning_rate": 1.9748827033181825e-05, | |
| "loss": 0.2796, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 1.4959349593495934, | |
| "grad_norm": 3.9447419922701115, | |
| "learning_rate": 1.9742455586369786e-05, | |
| "loss": 0.22, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.5089430894308942, | |
| "grad_norm": 4.588912104539782, | |
| "learning_rate": 1.9736005390868923e-05, | |
| "loss": 0.2845, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 1.5219512195121951, | |
| "grad_norm": 4.319670446630065, | |
| "learning_rate": 1.9729476498816455e-05, | |
| "loss": 0.203, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.534959349593496, | |
| "grad_norm": 3.971807551499835, | |
| "learning_rate": 1.9722868962985693e-05, | |
| "loss": 0.2594, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 1.5479674796747966, | |
| "grad_norm": 3.9363850698183422, | |
| "learning_rate": 1.971618283678563e-05, | |
| "loss": 0.2365, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 4.511257223022539, | |
| "learning_rate": 1.9709418174260523e-05, | |
| "loss": 0.2491, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.5739837398373984, | |
| "grad_norm": 4.886072844335961, | |
| "learning_rate": 1.970257503008942e-05, | |
| "loss": 0.239, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 1.5869918699186991, | |
| "grad_norm": 4.675630782649018, | |
| "learning_rate": 1.969565345958576e-05, | |
| "loss": 0.3074, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 5.006731738820173, | |
| "learning_rate": 1.9688653518696886e-05, | |
| "loss": 0.3073, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 1.6130081300813008, | |
| "grad_norm": 4.303983792791088, | |
| "learning_rate": 1.9681575264003635e-05, | |
| "loss": 0.2118, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 1.6260162601626016, | |
| "grad_norm": 4.448918927453546, | |
| "learning_rate": 1.9674418752719835e-05, | |
| "loss": 0.2438, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.6390243902439026, | |
| "grad_norm": 5.131140117465671, | |
| "learning_rate": 1.9667184042691877e-05, | |
| "loss": 0.2298, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 1.652032520325203, | |
| "grad_norm": 3.2399581338003407, | |
| "learning_rate": 1.9659871192398237e-05, | |
| "loss": 0.1416, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 1.665040650406504, | |
| "grad_norm": 3.511401536131484, | |
| "learning_rate": 1.9652480260948995e-05, | |
| "loss": 0.1798, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 1.678048780487805, | |
| "grad_norm": 4.63237984345691, | |
| "learning_rate": 1.9645011308085374e-05, | |
| "loss": 0.2026, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 1.6910569105691056, | |
| "grad_norm": 4.875330162486382, | |
| "learning_rate": 1.963746439417924e-05, | |
| "loss": 0.2993, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7040650406504065, | |
| "grad_norm": 3.486729559236034, | |
| "learning_rate": 1.9629839580232625e-05, | |
| "loss": 0.1391, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 1.7170731707317073, | |
| "grad_norm": 4.272470459292228, | |
| "learning_rate": 1.9622136927877226e-05, | |
| "loss": 0.2911, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 1.730081300813008, | |
| "grad_norm": 4.004111381617907, | |
| "learning_rate": 1.9614356499373918e-05, | |
| "loss": 0.2615, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 1.743089430894309, | |
| "grad_norm": 3.870300097881223, | |
| "learning_rate": 1.9606498357612236e-05, | |
| "loss": 0.2086, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 3.6842754269925213, | |
| "learning_rate": 1.959856256610988e-05, | |
| "loss": 0.2352, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.7691056910569105, | |
| "grad_norm": 4.992457315291344, | |
| "learning_rate": 1.95905491890122e-05, | |
| "loss": 0.2737, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 1.7821138211382115, | |
| "grad_norm": 3.6899274911801654, | |
| "learning_rate": 1.9582458291091664e-05, | |
| "loss": 0.174, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 1.7951219512195122, | |
| "grad_norm": 4.050726740720838, | |
| "learning_rate": 1.9574289937747347e-05, | |
| "loss": 0.2454, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 1.808130081300813, | |
| "grad_norm": 3.543669223885536, | |
| "learning_rate": 1.956604419500441e-05, | |
| "loss": 0.1782, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 1.821138211382114, | |
| "grad_norm": 3.920644016977587, | |
| "learning_rate": 1.9557721129513538e-05, | |
| "loss": 0.2294, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8341463414634145, | |
| "grad_norm": 4.439148624281575, | |
| "learning_rate": 1.9549320808550435e-05, | |
| "loss": 0.2925, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 1.8471544715447155, | |
| "grad_norm": 4.439161121958125, | |
| "learning_rate": 1.9540843300015253e-05, | |
| "loss": 0.2422, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 1.8601626016260162, | |
| "grad_norm": 5.760691734688802, | |
| "learning_rate": 1.953228867243206e-05, | |
| "loss": 0.2448, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 1.873170731707317, | |
| "grad_norm": 4.152636368976296, | |
| "learning_rate": 1.9523656994948285e-05, | |
| "loss": 0.2391, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 1.886178861788618, | |
| "grad_norm": 3.5715039772686494, | |
| "learning_rate": 1.9514948337334144e-05, | |
| "loss": 0.1995, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.8991869918699187, | |
| "grad_norm": 4.445231140655837, | |
| "learning_rate": 1.950616276998209e-05, | |
| "loss": 0.2827, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 1.9121951219512194, | |
| "grad_norm": 3.5242260861609047, | |
| "learning_rate": 1.9497300363906253e-05, | |
| "loss": 0.2037, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 1.9252032520325204, | |
| "grad_norm": 4.556876251890979, | |
| "learning_rate": 1.9488361190741836e-05, | |
| "loss": 0.2261, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 1.9382113821138212, | |
| "grad_norm": 4.176486612051313, | |
| "learning_rate": 1.947934532274456e-05, | |
| "loss": 0.2941, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 4.155824009528282, | |
| "learning_rate": 1.947025283279008e-05, | |
| "loss": 0.2782, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9642276422764229, | |
| "grad_norm": 4.283716648269924, | |
| "learning_rate": 1.946108379437338e-05, | |
| "loss": 0.2707, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 1.9772357723577236, | |
| "grad_norm": 3.748554130938304, | |
| "learning_rate": 1.94518382816082e-05, | |
| "loss": 0.2401, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 1.9902439024390244, | |
| "grad_norm": 4.366040799270219, | |
| "learning_rate": 1.9442516369226408e-05, | |
| "loss": 0.2643, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.0032520325203254, | |
| "grad_norm": 3.5008784661458128, | |
| "learning_rate": 1.9433118132577432e-05, | |
| "loss": 0.2126, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.016260162601626, | |
| "grad_norm": 3.8928484247693182, | |
| "learning_rate": 1.9423643647627625e-05, | |
| "loss": 0.1804, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.029268292682927, | |
| "grad_norm": 3.2309992540447543, | |
| "learning_rate": 1.9414092990959653e-05, | |
| "loss": 0.1824, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.042276422764228, | |
| "grad_norm": 2.8004486850259758, | |
| "learning_rate": 1.9404466239771887e-05, | |
| "loss": 0.1376, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.0552845528455284, | |
| "grad_norm": 4.04090570287216, | |
| "learning_rate": 1.9394763471877774e-05, | |
| "loss": 0.2145, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.0682926829268293, | |
| "grad_norm": 4.247108451612536, | |
| "learning_rate": 1.9384984765705202e-05, | |
| "loss": 0.2189, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.08130081300813, | |
| "grad_norm": 4.17448093795093, | |
| "learning_rate": 1.937513020029588e-05, | |
| "loss": 0.2356, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.094308943089431, | |
| "grad_norm": 3.2247564577083403, | |
| "learning_rate": 1.936519985530468e-05, | |
| "loss": 0.1848, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.107317073170732, | |
| "grad_norm": 3.6746992074200038, | |
| "learning_rate": 1.9355193810999015e-05, | |
| "loss": 0.2142, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.1203252032520323, | |
| "grad_norm": 3.535692174455577, | |
| "learning_rate": 1.934511214825817e-05, | |
| "loss": 0.176, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 3.724515733913512, | |
| "learning_rate": 1.9334954948572656e-05, | |
| "loss": 0.2109, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 4.149262557760461, | |
| "learning_rate": 1.932472229404356e-05, | |
| "loss": 0.1744, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.159349593495935, | |
| "grad_norm": 4.4628517154906095, | |
| "learning_rate": 1.931441426738187e-05, | |
| "loss": 0.2687, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 2.1723577235772358, | |
| "grad_norm": 4.0932795934488215, | |
| "learning_rate": 1.930403095190781e-05, | |
| "loss": 0.2271, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 2.1853658536585368, | |
| "grad_norm": 2.947126269214458, | |
| "learning_rate": 1.9293572431550166e-05, | |
| "loss": 0.1473, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 2.1983739837398373, | |
| "grad_norm": 3.5196607854273143, | |
| "learning_rate": 1.9283038790845612e-05, | |
| "loss": 0.1968, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.2113821138211383, | |
| "grad_norm": 3.8823015570591446, | |
| "learning_rate": 1.9272430114938018e-05, | |
| "loss": 0.1652, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.2243902439024392, | |
| "grad_norm": 3.548545585661667, | |
| "learning_rate": 1.9261746489577767e-05, | |
| "loss": 0.1511, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 2.2373983739837398, | |
| "grad_norm": 4.02995884194372, | |
| "learning_rate": 1.9250988001121068e-05, | |
| "loss": 0.1896, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.2504065040650407, | |
| "grad_norm": 3.517215015548888, | |
| "learning_rate": 1.9240154736529242e-05, | |
| "loss": 0.1959, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 2.2634146341463417, | |
| "grad_norm": 4.035966445241826, | |
| "learning_rate": 1.922924678336804e-05, | |
| "loss": 0.2133, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 2.2764227642276422, | |
| "grad_norm": 3.8693491335089663, | |
| "learning_rate": 1.9218264229806917e-05, | |
| "loss": 0.2202, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.289430894308943, | |
| "grad_norm": 3.833616161618607, | |
| "learning_rate": 1.9207207164618323e-05, | |
| "loss": 0.155, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 2.3024390243902437, | |
| "grad_norm": 3.4283946520122477, | |
| "learning_rate": 1.9196075677177e-05, | |
| "loss": 0.1617, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 2.3154471544715447, | |
| "grad_norm": 3.311159228202799, | |
| "learning_rate": 1.9184869857459233e-05, | |
| "loss": 0.2036, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 2.3284552845528457, | |
| "grad_norm": 3.4656577408210056, | |
| "learning_rate": 1.917358979604215e-05, | |
| "loss": 0.1962, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 3.996270083581475, | |
| "learning_rate": 1.9162235584102973e-05, | |
| "loss": 0.1621, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.354471544715447, | |
| "grad_norm": 2.861575747203407, | |
| "learning_rate": 1.9150807313418293e-05, | |
| "loss": 0.1435, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 2.367479674796748, | |
| "grad_norm": 3.87366838202817, | |
| "learning_rate": 1.9139305076363305e-05, | |
| "loss": 0.2592, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.3804878048780487, | |
| "grad_norm": 3.8471663369504565, | |
| "learning_rate": 1.9127728965911094e-05, | |
| "loss": 0.1688, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 2.3934959349593496, | |
| "grad_norm": 3.1610128734552982, | |
| "learning_rate": 1.911607907563186e-05, | |
| "loss": 0.1633, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 2.40650406504065, | |
| "grad_norm": 3.6510959997562575, | |
| "learning_rate": 1.9104355499692166e-05, | |
| "loss": 0.1751, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.419512195121951, | |
| "grad_norm": 2.9027919461413942, | |
| "learning_rate": 1.9092558332854186e-05, | |
| "loss": 0.1615, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 2.432520325203252, | |
| "grad_norm": 3.5763801032437277, | |
| "learning_rate": 1.9080687670474923e-05, | |
| "loss": 0.1901, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 2.4455284552845526, | |
| "grad_norm": 4.437211684445719, | |
| "learning_rate": 1.9068743608505454e-05, | |
| "loss": 0.185, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 2.4585365853658536, | |
| "grad_norm": 2.5057412891368114, | |
| "learning_rate": 1.9056726243490152e-05, | |
| "loss": 0.1432, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 2.4715447154471546, | |
| "grad_norm": 3.4687500624153844, | |
| "learning_rate": 1.9044635672565898e-05, | |
| "loss": 0.1741, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.484552845528455, | |
| "grad_norm": 3.6619841695079915, | |
| "learning_rate": 1.903247199346129e-05, | |
| "loss": 0.1753, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 2.497560975609756, | |
| "grad_norm": 3.1520059206227033, | |
| "learning_rate": 1.9020235304495877e-05, | |
| "loss": 0.1365, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 2.510569105691057, | |
| "grad_norm": 3.673031351652811, | |
| "learning_rate": 1.9007925704579346e-05, | |
| "loss": 0.2016, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 2.5235772357723576, | |
| "grad_norm": 3.46021385752599, | |
| "learning_rate": 1.8995543293210713e-05, | |
| "loss": 0.1416, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 3.9573065236715084, | |
| "learning_rate": 1.8983088170477556e-05, | |
| "loss": 0.1802, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.5495934959349595, | |
| "grad_norm": 4.484576176480101, | |
| "learning_rate": 1.8970560437055162e-05, | |
| "loss": 0.2086, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 2.56260162601626, | |
| "grad_norm": 3.648134049882013, | |
| "learning_rate": 1.8957960194205743e-05, | |
| "loss": 0.1653, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 2.575609756097561, | |
| "grad_norm": 3.958334883444762, | |
| "learning_rate": 1.894528754377761e-05, | |
| "loss": 0.1994, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 2.588617886178862, | |
| "grad_norm": 3.941838601560344, | |
| "learning_rate": 1.8932542588204334e-05, | |
| "loss": 0.2253, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 2.6016260162601625, | |
| "grad_norm": 4.3162453501502895, | |
| "learning_rate": 1.8919725430503946e-05, | |
| "loss": 0.1819, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.6146341463414635, | |
| "grad_norm": 3.3609249443688687, | |
| "learning_rate": 1.8906836174278088e-05, | |
| "loss": 0.171, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 2.6276422764227645, | |
| "grad_norm": 3.0099472226700112, | |
| "learning_rate": 1.8893874923711165e-05, | |
| "loss": 0.1484, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.640650406504065, | |
| "grad_norm": 3.6588365810612298, | |
| "learning_rate": 1.888084178356953e-05, | |
| "loss": 0.1793, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 2.653658536585366, | |
| "grad_norm": 3.8668614415295464, | |
| "learning_rate": 1.886773685920062e-05, | |
| "loss": 0.2062, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.6895178372540047, | |
| "learning_rate": 1.8854560256532098e-05, | |
| "loss": 0.1569, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.6796747967479675, | |
| "grad_norm": 3.4719914098671247, | |
| "learning_rate": 1.884131208207102e-05, | |
| "loss": 0.1918, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 2.692682926829268, | |
| "grad_norm": 2.7584556034576804, | |
| "learning_rate": 1.882799244290294e-05, | |
| "loss": 0.147, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 2.705691056910569, | |
| "grad_norm": 3.568599204142701, | |
| "learning_rate": 1.881460144669109e-05, | |
| "loss": 0.2527, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 2.71869918699187, | |
| "grad_norm": 3.5199678305621487, | |
| "learning_rate": 1.8801139201675457e-05, | |
| "loss": 0.2078, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 4.5434445365694724, | |
| "learning_rate": 1.8787605816671956e-05, | |
| "loss": 0.2356, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.7447154471544715, | |
| "grad_norm": 3.9127153096216984, | |
| "learning_rate": 1.8774001401071516e-05, | |
| "loss": 0.2082, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 2.7577235772357724, | |
| "grad_norm": 2.96128278616753, | |
| "learning_rate": 1.8760326064839222e-05, | |
| "loss": 0.134, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 2.770731707317073, | |
| "grad_norm": 3.0389228925328586, | |
| "learning_rate": 1.8746579918513404e-05, | |
| "loss": 0.1674, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 2.783739837398374, | |
| "grad_norm": 4.139309382085306, | |
| "learning_rate": 1.8732763073204755e-05, | |
| "loss": 0.2547, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 2.796747967479675, | |
| "grad_norm": 2.769960672266414, | |
| "learning_rate": 1.8718875640595432e-05, | |
| "loss": 0.1527, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.8097560975609754, | |
| "grad_norm": 3.072439635949312, | |
| "learning_rate": 1.8704917732938152e-05, | |
| "loss": 0.203, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.8227642276422764, | |
| "grad_norm": 3.062261282857323, | |
| "learning_rate": 1.8690889463055285e-05, | |
| "loss": 0.1868, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 2.8357723577235774, | |
| "grad_norm": 3.825404215100477, | |
| "learning_rate": 1.867679094433794e-05, | |
| "loss": 0.2018, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 2.848780487804878, | |
| "grad_norm": 3.126980632581835, | |
| "learning_rate": 1.8662622290745055e-05, | |
| "loss": 0.166, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 2.861788617886179, | |
| "grad_norm": 3.114972845359332, | |
| "learning_rate": 1.864838361680247e-05, | |
| "loss": 0.1551, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.87479674796748, | |
| "grad_norm": 2.8749136447110506, | |
| "learning_rate": 1.8634075037601995e-05, | |
| "loss": 0.1491, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 2.8878048780487804, | |
| "grad_norm": 3.768681045766016, | |
| "learning_rate": 1.8619696668800494e-05, | |
| "loss": 0.2277, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 2.9008130081300814, | |
| "grad_norm": 3.340623859849148, | |
| "learning_rate": 1.8605248626618942e-05, | |
| "loss": 0.1699, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 2.9138211382113823, | |
| "grad_norm": 2.482743526058305, | |
| "learning_rate": 1.8590731027841498e-05, | |
| "loss": 0.1511, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 3.687140063825773, | |
| "learning_rate": 1.8576143989814524e-05, | |
| "loss": 0.2142, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.939837398373984, | |
| "grad_norm": 4.251426921981605, | |
| "learning_rate": 1.8561487630445684e-05, | |
| "loss": 0.2114, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 2.952845528455285, | |
| "grad_norm": 3.4267551820392605, | |
| "learning_rate": 1.8546762068202967e-05, | |
| "loss": 0.192, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 2.9658536585365853, | |
| "grad_norm": 3.723861341283011, | |
| "learning_rate": 1.853196742211372e-05, | |
| "loss": 0.1479, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 2.9788617886178863, | |
| "grad_norm": 2.924455024641601, | |
| "learning_rate": 1.8517103811763713e-05, | |
| "loss": 0.1724, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 2.991869918699187, | |
| "grad_norm": 3.470083478550075, | |
| "learning_rate": 1.8502171357296144e-05, | |
| "loss": 0.1654, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.004878048780488, | |
| "grad_norm": 3.3320283803300157, | |
| "learning_rate": 1.8487170179410688e-05, | |
| "loss": 0.1182, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.017886178861789, | |
| "grad_norm": 2.7110362310580354, | |
| "learning_rate": 1.8472100399362518e-05, | |
| "loss": 0.1352, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 3.0308943089430893, | |
| "grad_norm": 3.6623049720030996, | |
| "learning_rate": 1.845696213896131e-05, | |
| "loss": 0.1553, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 3.0439024390243903, | |
| "grad_norm": 2.6391263660030106, | |
| "learning_rate": 1.844175552057028e-05, | |
| "loss": 0.1514, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 3.0569105691056913, | |
| "grad_norm": 3.739938811029931, | |
| "learning_rate": 1.8426480667105178e-05, | |
| "loss": 0.1909, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.069918699186992, | |
| "grad_norm": 3.9129123235491274, | |
| "learning_rate": 1.8411137702033306e-05, | |
| "loss": 0.1714, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 3.0829268292682928, | |
| "grad_norm": 3.9313197740251957, | |
| "learning_rate": 1.839572674937251e-05, | |
| "loss": 0.1539, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 3.0959349593495933, | |
| "grad_norm": 3.1212290402854626, | |
| "learning_rate": 1.8380247933690184e-05, | |
| "loss": 0.1193, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 3.1089430894308943, | |
| "grad_norm": 5.198294944362961, | |
| "learning_rate": 1.8364701380102267e-05, | |
| "loss": 0.1458, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 3.1219512195121952, | |
| "grad_norm": 3.0080084795066377, | |
| "learning_rate": 1.8349087214272222e-05, | |
| "loss": 0.1541, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.1349593495934958, | |
| "grad_norm": 3.6470200841876492, | |
| "learning_rate": 1.8333405562410026e-05, | |
| "loss": 0.1652, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 3.1479674796747967, | |
| "grad_norm": 2.4499275104389686, | |
| "learning_rate": 1.8317656551271138e-05, | |
| "loss": 0.1136, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 3.1609756097560977, | |
| "grad_norm": 3.7602257479905115, | |
| "learning_rate": 1.8301840308155507e-05, | |
| "loss": 0.132, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.1739837398373982, | |
| "grad_norm": 3.086338349925423, | |
| "learning_rate": 1.8285956960906502e-05, | |
| "loss": 0.1273, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 3.186991869918699, | |
| "grad_norm": 3.2621971561813603, | |
| "learning_rate": 1.8270006637909907e-05, | |
| "loss": 0.1263, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 4.095594589401213, | |
| "learning_rate": 1.8253989468092865e-05, | |
| "loss": 0.2073, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 3.2130081300813007, | |
| "grad_norm": 3.3534907822906708, | |
| "learning_rate": 1.823790558092286e-05, | |
| "loss": 0.1585, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 3.2260162601626017, | |
| "grad_norm": 2.9358944102640008, | |
| "learning_rate": 1.8221755106406636e-05, | |
| "loss": 0.1246, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 3.2390243902439027, | |
| "grad_norm": 4.424506593945267, | |
| "learning_rate": 1.8205538175089182e-05, | |
| "loss": 0.2003, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 3.252032520325203, | |
| "grad_norm": 3.8505300778971554, | |
| "learning_rate": 1.818925491805265e-05, | |
| "loss": 0.149, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.265040650406504, | |
| "grad_norm": 3.5453083967016683, | |
| "learning_rate": 1.8172905466915315e-05, | |
| "loss": 0.1333, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 3.278048780487805, | |
| "grad_norm": 3.1785634434812566, | |
| "learning_rate": 1.8156489953830488e-05, | |
| "loss": 0.089, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 3.2910569105691057, | |
| "grad_norm": 2.903838553495901, | |
| "learning_rate": 1.8140008511485474e-05, | |
| "loss": 0.1301, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 3.3040650406504066, | |
| "grad_norm": 3.1675877537773505, | |
| "learning_rate": 1.812346127310048e-05, | |
| "loss": 0.1135, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 3.317073170731707, | |
| "grad_norm": 3.1742222793253685, | |
| "learning_rate": 1.810684837242755e-05, | |
| "loss": 0.13, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.330081300813008, | |
| "grad_norm": 3.34445630131317, | |
| "learning_rate": 1.8090169943749477e-05, | |
| "loss": 0.1189, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 3.343089430894309, | |
| "grad_norm": 3.3814743110574557, | |
| "learning_rate": 1.8073426121878717e-05, | |
| "loss": 0.1098, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 3.3560975609756096, | |
| "grad_norm": 3.496641524649336, | |
| "learning_rate": 1.8056617042156307e-05, | |
| "loss": 0.1278, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 3.3691056910569106, | |
| "grad_norm": 4.9263432893902115, | |
| "learning_rate": 1.8039742840450764e-05, | |
| "loss": 0.2073, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 3.3821138211382116, | |
| "grad_norm": 3.4975911499873047, | |
| "learning_rate": 1.8022803653156983e-05, | |
| "loss": 0.1183, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.395121951219512, | |
| "grad_norm": 3.2595016394744114, | |
| "learning_rate": 1.8005799617195155e-05, | |
| "loss": 0.108, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 3.408130081300813, | |
| "grad_norm": 3.7356695595162175, | |
| "learning_rate": 1.798873087000963e-05, | |
| "loss": 0.1486, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 3.4211382113821136, | |
| "grad_norm": 3.1467257874655354, | |
| "learning_rate": 1.797159754956783e-05, | |
| "loss": 0.1671, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 3.4341463414634146, | |
| "grad_norm": 3.0572228617731048, | |
| "learning_rate": 1.7954399794359115e-05, | |
| "loss": 0.1085, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 3.4471544715447155, | |
| "grad_norm": 3.5444513803003206, | |
| "learning_rate": 1.7937137743393695e-05, | |
| "loss": 0.1809, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 3.460162601626016, | |
| "grad_norm": 4.606794240145359, | |
| "learning_rate": 1.791981153620147e-05, | |
| "loss": 0.2356, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 3.473170731707317, | |
| "grad_norm": 3.608792070604836, | |
| "learning_rate": 1.7902421312830915e-05, | |
| "loss": 0.1449, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 3.486178861788618, | |
| "grad_norm": 3.671931359892289, | |
| "learning_rate": 1.788496721384796e-05, | |
| "loss": 0.1472, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 3.4991869918699186, | |
| "grad_norm": 2.8326328693087794, | |
| "learning_rate": 1.7867449380334834e-05, | |
| "loss": 0.1061, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 3.5121951219512195, | |
| "grad_norm": 5.132149323312545, | |
| "learning_rate": 1.784986795388895e-05, | |
| "loss": 0.1955, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.5252032520325205, | |
| "grad_norm": 3.5206185617465726, | |
| "learning_rate": 1.7832223076621728e-05, | |
| "loss": 0.1273, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 3.538211382113821, | |
| "grad_norm": 4.280123868142099, | |
| "learning_rate": 1.7814514891157477e-05, | |
| "loss": 0.1533, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 3.551219512195122, | |
| "grad_norm": 4.385914570096056, | |
| "learning_rate": 1.7796743540632226e-05, | |
| "loss": 0.1689, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 3.564227642276423, | |
| "grad_norm": 4.419998955550363, | |
| "learning_rate": 1.7778909168692562e-05, | |
| "loss": 0.2096, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 3.5772357723577235, | |
| "grad_norm": 3.12280732072736, | |
| "learning_rate": 1.776101191949449e-05, | |
| "loss": 0.1383, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.5902439024390245, | |
| "grad_norm": 2.866431440107905, | |
| "learning_rate": 1.774305193770224e-05, | |
| "loss": 0.1375, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 3.6032520325203254, | |
| "grad_norm": 4.007833812240409, | |
| "learning_rate": 1.7725029368487125e-05, | |
| "loss": 0.2024, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 3.616260162601626, | |
| "grad_norm": 3.53283079500347, | |
| "learning_rate": 1.7706944357526344e-05, | |
| "loss": 0.1478, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 3.629268292682927, | |
| "grad_norm": 3.2821005608945937, | |
| "learning_rate": 1.768879705100183e-05, | |
| "loss": 0.1506, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 3.642276422764228, | |
| "grad_norm": 3.6058872672852305, | |
| "learning_rate": 1.7670587595599034e-05, | |
| "loss": 0.1186, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.6552845528455284, | |
| "grad_norm": 3.9799824031049216, | |
| "learning_rate": 1.7652316138505775e-05, | |
| "loss": 0.162, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 3.6682926829268294, | |
| "grad_norm": 2.672345057078251, | |
| "learning_rate": 1.763398282741103e-05, | |
| "loss": 0.1257, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 3.68130081300813, | |
| "grad_norm": 3.547459688343558, | |
| "learning_rate": 1.7615587810503742e-05, | |
| "loss": 0.1442, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 3.694308943089431, | |
| "grad_norm": 2.7210687319693165, | |
| "learning_rate": 1.759713123647163e-05, | |
| "loss": 0.1217, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 3.7073170731707314, | |
| "grad_norm": 3.705663104009642, | |
| "learning_rate": 1.757861325449997e-05, | |
| "loss": 0.1432, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.7203252032520324, | |
| "grad_norm": 3.469597615351064, | |
| "learning_rate": 1.7560034014270412e-05, | |
| "loss": 0.1496, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 3.7333333333333334, | |
| "grad_norm": 3.8328893728698157, | |
| "learning_rate": 1.754139366595976e-05, | |
| "loss": 0.1689, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 3.746341463414634, | |
| "grad_norm": 4.975275429057309, | |
| "learning_rate": 1.7522692360238754e-05, | |
| "loss": 0.2421, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 3.759349593495935, | |
| "grad_norm": 2.974146879840772, | |
| "learning_rate": 1.750393024827085e-05, | |
| "loss": 0.1462, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 3.772357723577236, | |
| "grad_norm": 4.523596880463953, | |
| "learning_rate": 1.7485107481711014e-05, | |
| "loss": 0.1968, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.7853658536585364, | |
| "grad_norm": 4.071673728739772, | |
| "learning_rate": 1.7466224212704476e-05, | |
| "loss": 0.1348, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 3.7983739837398374, | |
| "grad_norm": 3.2858953786050655, | |
| "learning_rate": 1.7447280593885513e-05, | |
| "loss": 0.1562, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 3.8113821138211383, | |
| "grad_norm": 3.9233724024870074, | |
| "learning_rate": 1.7428276778376216e-05, | |
| "loss": 0.1403, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 3.824390243902439, | |
| "grad_norm": 2.747841015884429, | |
| "learning_rate": 1.7409212919785246e-05, | |
| "loss": 0.1402, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 3.83739837398374, | |
| "grad_norm": 3.8222812348697195, | |
| "learning_rate": 1.7390089172206594e-05, | |
| "loss": 0.1366, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 3.850406504065041, | |
| "grad_norm": 4.019423526397215, | |
| "learning_rate": 1.7370905690218336e-05, | |
| "loss": 0.1792, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 3.8634146341463413, | |
| "grad_norm": 3.2152225121342237, | |
| "learning_rate": 1.7351662628881385e-05, | |
| "loss": 0.1304, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 3.8764227642276423, | |
| "grad_norm": 3.2204034243819124, | |
| "learning_rate": 1.7332360143738233e-05, | |
| "loss": 0.1416, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 3.8894308943089433, | |
| "grad_norm": 3.503625110107874, | |
| "learning_rate": 1.7312998390811704e-05, | |
| "loss": 0.1127, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 3.6975773220511567, | |
| "learning_rate": 1.7293577526603684e-05, | |
| "loss": 0.1455, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.915447154471545, | |
| "grad_norm": 3.346976518634114, | |
| "learning_rate": 1.727409770809385e-05, | |
| "loss": 0.196, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 3.9284552845528458, | |
| "grad_norm": 3.8370342412634466, | |
| "learning_rate": 1.7254559092738422e-05, | |
| "loss": 0.1706, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 3.9414634146341463, | |
| "grad_norm": 4.103423675177489, | |
| "learning_rate": 1.7234961838468865e-05, | |
| "loss": 0.2372, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.9544715447154473, | |
| "grad_norm": 3.646214320041045, | |
| "learning_rate": 1.7215306103690633e-05, | |
| "loss": 0.1663, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 3.9674796747967482, | |
| "grad_norm": 4.0269576046459745, | |
| "learning_rate": 1.719559204728188e-05, | |
| "loss": 0.1895, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 3.9804878048780488, | |
| "grad_norm": 3.0723205937626283, | |
| "learning_rate": 1.7175819828592177e-05, | |
| "loss": 0.1684, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 3.9934959349593497, | |
| "grad_norm": 4.069974796680754, | |
| "learning_rate": 1.715598960744121e-05, | |
| "loss": 0.1536, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 4.006504065040651, | |
| "grad_norm": 2.5484710138290745, | |
| "learning_rate": 1.7136101544117526e-05, | |
| "loss": 0.1125, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.019512195121951, | |
| "grad_norm": 2.333032908465822, | |
| "learning_rate": 1.7116155799377184e-05, | |
| "loss": 0.1198, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 4.032520325203252, | |
| "grad_norm": 2.536574837694146, | |
| "learning_rate": 1.7096152534442515e-05, | |
| "loss": 0.0875, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.045528455284553, | |
| "grad_norm": 2.9417953379935415, | |
| "learning_rate": 1.707609191100076e-05, | |
| "loss": 0.1136, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 4.058536585365854, | |
| "grad_norm": 2.7829202859441122, | |
| "learning_rate": 1.705597409120281e-05, | |
| "loss": 0.1206, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 4.071544715447154, | |
| "grad_norm": 2.946996907122881, | |
| "learning_rate": 1.7035799237661864e-05, | |
| "loss": 0.094, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 4.084552845528456, | |
| "grad_norm": 2.933920883184802, | |
| "learning_rate": 1.701556751345214e-05, | |
| "loss": 0.1369, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 4.097560975609756, | |
| "grad_norm": 2.328489359994484, | |
| "learning_rate": 1.6995279082107537e-05, | |
| "loss": 0.089, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.110569105691057, | |
| "grad_norm": 4.249940359177669, | |
| "learning_rate": 1.6974934107620322e-05, | |
| "loss": 0.1335, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 4.123577235772358, | |
| "grad_norm": 3.3688477184048575, | |
| "learning_rate": 1.6954532754439797e-05, | |
| "loss": 0.148, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 4.136585365853659, | |
| "grad_norm": 2.3848280800192208, | |
| "learning_rate": 1.693407518747098e-05, | |
| "loss": 0.0736, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 4.149593495934959, | |
| "grad_norm": 3.4356309937170484, | |
| "learning_rate": 1.6913561572073273e-05, | |
| "loss": 0.0994, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 4.16260162601626, | |
| "grad_norm": 3.6302353229969446, | |
| "learning_rate": 1.689299207405911e-05, | |
| "loss": 0.1455, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.175609756097561, | |
| "grad_norm": 5.15932930488356, | |
| "learning_rate": 1.687236685969263e-05, | |
| "loss": 0.1421, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 4.188617886178862, | |
| "grad_norm": 3.971079854170419, | |
| "learning_rate": 1.685168609568833e-05, | |
| "loss": 0.1421, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 4.201626016260162, | |
| "grad_norm": 2.696136494041647, | |
| "learning_rate": 1.6830949949209724e-05, | |
| "loss": 0.0916, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 4.214634146341464, | |
| "grad_norm": 3.4922342292960358, | |
| "learning_rate": 1.6810158587867973e-05, | |
| "loss": 0.0906, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.227642276422764, | |
| "grad_norm": 3.3614438222315144, | |
| "learning_rate": 1.678931217972055e-05, | |
| "loss": 0.119, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.240650406504065, | |
| "grad_norm": 3.607315750706837, | |
| "learning_rate": 1.6768410893269868e-05, | |
| "loss": 0.1375, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 4.253658536585366, | |
| "grad_norm": 3.84233718866814, | |
| "learning_rate": 1.674745489746193e-05, | |
| "loss": 0.1383, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 3.1526315566529286, | |
| "learning_rate": 1.6726444361684956e-05, | |
| "loss": 0.1101, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 4.279674796747967, | |
| "grad_norm": 2.83908738016638, | |
| "learning_rate": 1.6705379455768012e-05, | |
| "loss": 0.1006, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 4.2926829268292686, | |
| "grad_norm": 2.679726062118238, | |
| "learning_rate": 1.6684260349979637e-05, | |
| "loss": 0.0969, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.305691056910569, | |
| "grad_norm": 3.839596809167504, | |
| "learning_rate": 1.666308721502648e-05, | |
| "loss": 0.1139, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 4.31869918699187, | |
| "grad_norm": 4.084712815755696, | |
| "learning_rate": 1.66418602220519e-05, | |
| "loss": 0.1159, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 4.331707317073171, | |
| "grad_norm": 3.4860619920681657, | |
| "learning_rate": 1.66205795426346e-05, | |
| "loss": 0.1091, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 4.3447154471544716, | |
| "grad_norm": 2.3329325167077526, | |
| "learning_rate": 1.659924534878723e-05, | |
| "loss": 0.0749, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 4.357723577235772, | |
| "grad_norm": 2.8903925345801937, | |
| "learning_rate": 1.6577857812954994e-05, | |
| "loss": 0.1314, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 4.3707317073170735, | |
| "grad_norm": 2.8706060227172747, | |
| "learning_rate": 1.6556417108014274e-05, | |
| "loss": 0.0888, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 4.383739837398374, | |
| "grad_norm": 2.8472139371320084, | |
| "learning_rate": 1.6534923407271208e-05, | |
| "loss": 0.1146, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 4.396747967479675, | |
| "grad_norm": 3.0525773691176967, | |
| "learning_rate": 1.651337688446031e-05, | |
| "loss": 0.1263, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 4.409756097560976, | |
| "grad_norm": 3.5942000990099077, | |
| "learning_rate": 1.649177771374305e-05, | |
| "loss": 0.1628, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 4.4227642276422765, | |
| "grad_norm": 3.667395925107678, | |
| "learning_rate": 1.6470126069706456e-05, | |
| "loss": 0.1747, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.435772357723577, | |
| "grad_norm": 3.3914683707328934, | |
| "learning_rate": 1.6448422127361707e-05, | |
| "loss": 0.1241, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 4.4487804878048784, | |
| "grad_norm": 4.017952969987458, | |
| "learning_rate": 1.64266660621427e-05, | |
| "loss": 0.1639, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 4.461788617886179, | |
| "grad_norm": 2.901364733314786, | |
| "learning_rate": 1.640485804990465e-05, | |
| "loss": 0.1061, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 4.4747967479674795, | |
| "grad_norm": 3.330073088240984, | |
| "learning_rate": 1.6382998266922664e-05, | |
| "loss": 0.1212, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 4.487804878048781, | |
| "grad_norm": 2.371208101416132, | |
| "learning_rate": 1.6361086889890307e-05, | |
| "loss": 0.0857, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.5008130081300814, | |
| "grad_norm": 2.166338014502868, | |
| "learning_rate": 1.6339124095918187e-05, | |
| "loss": 0.0705, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 4.513821138211382, | |
| "grad_norm": 2.8664401269053164, | |
| "learning_rate": 1.631711006253251e-05, | |
| "loss": 0.0906, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 4.526829268292683, | |
| "grad_norm": 3.2886681184392987, | |
| "learning_rate": 1.6295044967673664e-05, | |
| "loss": 0.1185, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 4.539837398373984, | |
| "grad_norm": 3.1209823393494323, | |
| "learning_rate": 1.6272928989694764e-05, | |
| "loss": 0.1127, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 4.5528455284552845, | |
| "grad_norm": 3.3212635148917165, | |
| "learning_rate": 1.6250762307360206e-05, | |
| "loss": 0.0961, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.565853658536585, | |
| "grad_norm": 2.94052757650137, | |
| "learning_rate": 1.6228545099844244e-05, | |
| "loss": 0.142, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 4.578861788617886, | |
| "grad_norm": 2.397685311630911, | |
| "learning_rate": 1.6206277546729526e-05, | |
| "loss": 0.0774, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 4.591869918699187, | |
| "grad_norm": 3.782885891266012, | |
| "learning_rate": 1.6183959828005647e-05, | |
| "loss": 0.1314, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 4.6048780487804875, | |
| "grad_norm": 2.8084619074891726, | |
| "learning_rate": 1.6161592124067683e-05, | |
| "loss": 0.0993, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 4.617886178861789, | |
| "grad_norm": 3.40847724620437, | |
| "learning_rate": 1.6139174615714753e-05, | |
| "loss": 0.1552, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 4.630894308943089, | |
| "grad_norm": 4.226646665724407, | |
| "learning_rate": 1.611670748414855e-05, | |
| "loss": 0.128, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 4.64390243902439, | |
| "grad_norm": 2.744441703743984, | |
| "learning_rate": 1.6094190910971855e-05, | |
| "loss": 0.1068, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 4.656910569105691, | |
| "grad_norm": 3.102497457734662, | |
| "learning_rate": 1.6071625078187113e-05, | |
| "loss": 0.0928, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 4.669918699186992, | |
| "grad_norm": 2.7529187753733764, | |
| "learning_rate": 1.604901016819492e-05, | |
| "loss": 0.1082, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 4.682926829268292, | |
| "grad_norm": 3.218033171112784, | |
| "learning_rate": 1.6026346363792565e-05, | |
| "loss": 0.1297, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.695934959349594, | |
| "grad_norm": 3.5829828322480655, | |
| "learning_rate": 1.6003633848172563e-05, | |
| "loss": 0.1044, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 4.708943089430894, | |
| "grad_norm": 2.5562220404894567, | |
| "learning_rate": 1.598087280492115e-05, | |
| "loss": 0.1094, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 4.721951219512195, | |
| "grad_norm": 2.65870226083651, | |
| "learning_rate": 1.5958063418016832e-05, | |
| "loss": 0.0905, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 4.734959349593496, | |
| "grad_norm": 3.03709602885955, | |
| "learning_rate": 1.5935205871828854e-05, | |
| "loss": 0.1163, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 4.747967479674797, | |
| "grad_norm": 2.7481439619992547, | |
| "learning_rate": 1.591230035111576e-05, | |
| "loss": 0.1232, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 4.760975609756097, | |
| "grad_norm": 4.6838555592653215, | |
| "learning_rate": 1.588934704102385e-05, | |
| "loss": 0.1096, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 4.773983739837398, | |
| "grad_norm": 3.7170873971103378, | |
| "learning_rate": 1.5866346127085733e-05, | |
| "loss": 0.1269, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 4.786991869918699, | |
| "grad_norm": 2.315923572226959, | |
| "learning_rate": 1.5843297795218776e-05, | |
| "loss": 0.0945, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "grad_norm": 3.321463437238242, | |
| "learning_rate": 1.582020223172365e-05, | |
| "loss": 0.0908, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 4.8130081300813, | |
| "grad_norm": 2.657544174519707, | |
| "learning_rate": 1.5797059623282787e-05, | |
| "loss": 0.1172, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.826016260162602, | |
| "grad_norm": 3.368090622507422, | |
| "learning_rate": 1.577387015695889e-05, | |
| "loss": 0.137, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 4.839024390243902, | |
| "grad_norm": 2.901693855359267, | |
| "learning_rate": 1.5750634020193412e-05, | |
| "loss": 0.1161, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 4.852032520325203, | |
| "grad_norm": 2.6449094839962233, | |
| "learning_rate": 1.5727351400805054e-05, | |
| "loss": 0.1114, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 4.865040650406504, | |
| "grad_norm": 3.4919666907079527, | |
| "learning_rate": 1.570402248698823e-05, | |
| "loss": 0.1545, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 3.635239020195852, | |
| "learning_rate": 1.568064746731156e-05, | |
| "loss": 0.1498, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.891056910569105, | |
| "grad_norm": 3.4357399829486686, | |
| "learning_rate": 1.5657226530716334e-05, | |
| "loss": 0.1468, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 4.904065040650407, | |
| "grad_norm": 2.687904712655832, | |
| "learning_rate": 1.563375986651499e-05, | |
| "loss": 0.098, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 4.917073170731707, | |
| "grad_norm": 2.806033909498718, | |
| "learning_rate": 1.5610247664389595e-05, | |
| "loss": 0.1067, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 4.930081300813008, | |
| "grad_norm": 3.3832896563385018, | |
| "learning_rate": 1.5586690114390285e-05, | |
| "loss": 0.126, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 4.943089430894309, | |
| "grad_norm": 3.108700537124724, | |
| "learning_rate": 1.5563087406933762e-05, | |
| "loss": 0.1376, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.95609756097561, | |
| "grad_norm": 1.9568452215981411, | |
| "learning_rate": 1.553943973280172e-05, | |
| "loss": 0.0562, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 4.96910569105691, | |
| "grad_norm": 2.873350467301675, | |
| "learning_rate": 1.5515747283139333e-05, | |
| "loss": 0.114, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 4.982113821138212, | |
| "grad_norm": 3.0898926838453304, | |
| "learning_rate": 1.5492010249453694e-05, | |
| "loss": 0.1421, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 4.995121951219512, | |
| "grad_norm": 3.408492358819634, | |
| "learning_rate": 1.5468228823612268e-05, | |
| "loss": 0.1508, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 5.008130081300813, | |
| "grad_norm": 1.9243903184184463, | |
| "learning_rate": 1.5444403197841345e-05, | |
| "loss": 0.0526, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.021138211382114, | |
| "grad_norm": 3.0308761794837524, | |
| "learning_rate": 1.5420533564724495e-05, | |
| "loss": 0.0845, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 5.034146341463415, | |
| "grad_norm": 2.0471741531886707, | |
| "learning_rate": 1.5396620117200983e-05, | |
| "loss": 0.0528, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 5.047154471544715, | |
| "grad_norm": 2.2719302954774196, | |
| "learning_rate": 1.537266304856424e-05, | |
| "loss": 0.0731, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 5.060162601626017, | |
| "grad_norm": 2.059060042307859, | |
| "learning_rate": 1.5348662552460286e-05, | |
| "loss": 0.0639, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 5.073170731707317, | |
| "grad_norm": 1.5169263928736323, | |
| "learning_rate": 1.5324618822886167e-05, | |
| "loss": 0.0372, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.086178861788618, | |
| "grad_norm": 2.122396210385444, | |
| "learning_rate": 1.5300532054188382e-05, | |
| "loss": 0.0684, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 5.099186991869919, | |
| "grad_norm": 1.9924949570413217, | |
| "learning_rate": 1.527640244106133e-05, | |
| "loss": 0.0518, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 5.11219512195122, | |
| "grad_norm": 2.247674900681653, | |
| "learning_rate": 1.5252230178545704e-05, | |
| "loss": 0.0694, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 5.12520325203252, | |
| "grad_norm": 3.640325939803553, | |
| "learning_rate": 1.5228015462026955e-05, | |
| "loss": 0.0698, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 5.138211382113822, | |
| "grad_norm": 2.512435243390525, | |
| "learning_rate": 1.5203758487233677e-05, | |
| "loss": 0.0692, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 5.151219512195122, | |
| "grad_norm": 3.714473909582526, | |
| "learning_rate": 1.517945945023604e-05, | |
| "loss": 0.075, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 5.164227642276423, | |
| "grad_norm": 2.307335242680726, | |
| "learning_rate": 1.5155118547444215e-05, | |
| "loss": 0.0645, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 5.177235772357724, | |
| "grad_norm": 2.8298726702585326, | |
| "learning_rate": 1.5130735975606765e-05, | |
| "loss": 0.0848, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 5.190243902439025, | |
| "grad_norm": 1.973524301024672, | |
| "learning_rate": 1.510631193180907e-05, | |
| "loss": 0.0462, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 5.203252032520325, | |
| "grad_norm": 3.610899615291046, | |
| "learning_rate": 1.5081846613471736e-05, | |
| "loss": 0.0792, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.216260162601626, | |
| "grad_norm": 3.897198559697946, | |
| "learning_rate": 1.505734021834898e-05, | |
| "loss": 0.054, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 5.229268292682927, | |
| "grad_norm": 3.3106506865159764, | |
| "learning_rate": 1.503279294452705e-05, | |
| "loss": 0.0982, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 5.242276422764228, | |
| "grad_norm": 2.9568842405195723, | |
| "learning_rate": 1.5008204990422624e-05, | |
| "loss": 0.0582, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 5.255284552845528, | |
| "grad_norm": 3.3317136023549416, | |
| "learning_rate": 1.4983576554781193e-05, | |
| "loss": 0.0899, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 5.2682926829268295, | |
| "grad_norm": 4.055210728386033, | |
| "learning_rate": 1.4958907836675467e-05, | |
| "loss": 0.0809, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 5.28130081300813, | |
| "grad_norm": 3.089501362613283, | |
| "learning_rate": 1.4934199035503758e-05, | |
| "loss": 0.0807, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 5.294308943089431, | |
| "grad_norm": 4.266765095296973, | |
| "learning_rate": 1.4909450350988368e-05, | |
| "loss": 0.1049, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 5.307317073170732, | |
| "grad_norm": 4.9112430954409065, | |
| "learning_rate": 1.488466198317399e-05, | |
| "loss": 0.1119, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 5.3203252032520325, | |
| "grad_norm": 2.851122180017563, | |
| "learning_rate": 1.485983413242606e-05, | |
| "loss": 0.064, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 3.3103976852400057, | |
| "learning_rate": 1.4834966999429179e-05, | |
| "loss": 0.0758, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.3463414634146345, | |
| "grad_norm": 2.8833619664931063, | |
| "learning_rate": 1.4810060785185445e-05, | |
| "loss": 0.054, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 5.359349593495935, | |
| "grad_norm": 2.7217775344544184, | |
| "learning_rate": 1.4785115691012866e-05, | |
| "loss": 0.0413, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 5.3723577235772355, | |
| "grad_norm": 2.538196105810992, | |
| "learning_rate": 1.4760131918543717e-05, | |
| "loss": 0.042, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 5.385365853658537, | |
| "grad_norm": 2.9038501446090486, | |
| "learning_rate": 1.4735109669722905e-05, | |
| "loss": 0.0706, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 5.3983739837398375, | |
| "grad_norm": 3.9624551793644835, | |
| "learning_rate": 1.4710049146806348e-05, | |
| "loss": 0.0942, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 5.411382113821138, | |
| "grad_norm": 3.1893235527156354, | |
| "learning_rate": 1.4684950552359335e-05, | |
| "loss": 0.1011, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 5.424390243902439, | |
| "grad_norm": 4.161856110377288, | |
| "learning_rate": 1.4659814089254889e-05, | |
| "loss": 0.1441, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 5.43739837398374, | |
| "grad_norm": 2.045583629237472, | |
| "learning_rate": 1.463463996067212e-05, | |
| "loss": 0.0367, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 5.4504065040650405, | |
| "grad_norm": 2.933530598957382, | |
| "learning_rate": 1.46094283700946e-05, | |
| "loss": 0.0717, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 5.463414634146342, | |
| "grad_norm": 2.846028092528159, | |
| "learning_rate": 1.4584179521308703e-05, | |
| "loss": 0.0719, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.476422764227642, | |
| "grad_norm": 3.6129655373506555, | |
| "learning_rate": 1.4558893618401961e-05, | |
| "loss": 0.0996, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 5.489430894308943, | |
| "grad_norm": 4.166578019941605, | |
| "learning_rate": 1.4533570865761422e-05, | |
| "loss": 0.0876, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 5.5024390243902435, | |
| "grad_norm": 3.619734283505654, | |
| "learning_rate": 1.4508211468071985e-05, | |
| "loss": 0.1177, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 5.515447154471545, | |
| "grad_norm": 3.1796554053433117, | |
| "learning_rate": 1.4482815630314752e-05, | |
| "loss": 0.0877, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 5.528455284552845, | |
| "grad_norm": 2.703328251194239, | |
| "learning_rate": 1.4457383557765385e-05, | |
| "loss": 0.0725, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.541463414634146, | |
| "grad_norm": 2.707896933553079, | |
| "learning_rate": 1.4431915455992416e-05, | |
| "loss": 0.0744, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 5.554471544715447, | |
| "grad_norm": 3.091276570995233, | |
| "learning_rate": 1.440641153085561e-05, | |
| "loss": 0.0742, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 5.567479674796748, | |
| "grad_norm": 2.4029960605310303, | |
| "learning_rate": 1.4380871988504299e-05, | |
| "loss": 0.0511, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 5.580487804878048, | |
| "grad_norm": 2.6919229748272095, | |
| "learning_rate": 1.4355297035375704e-05, | |
| "loss": 0.083, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 5.59349593495935, | |
| "grad_norm": 2.967320389146333, | |
| "learning_rate": 1.4329686878193271e-05, | |
| "loss": 0.0698, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.60650406504065, | |
| "grad_norm": 3.0319786590172555, | |
| "learning_rate": 1.4304041723965009e-05, | |
| "loss": 0.1039, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 5.619512195121951, | |
| "grad_norm": 2.6638640692433326, | |
| "learning_rate": 1.4278361779981806e-05, | |
| "loss": 0.0846, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 5.632520325203252, | |
| "grad_norm": 4.096202236885203, | |
| "learning_rate": 1.4252647253815757e-05, | |
| "loss": 0.0688, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 5.645528455284553, | |
| "grad_norm": 2.3758807014770933, | |
| "learning_rate": 1.4226898353318483e-05, | |
| "loss": 0.0747, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 5.658536585365853, | |
| "grad_norm": 4.045292672850446, | |
| "learning_rate": 1.4201115286619464e-05, | |
| "loss": 0.1139, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 5.671544715447155, | |
| "grad_norm": 2.4680862232566003, | |
| "learning_rate": 1.4175298262124333e-05, | |
| "loss": 0.08, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 5.684552845528455, | |
| "grad_norm": 3.370892166755356, | |
| "learning_rate": 1.4149447488513217e-05, | |
| "loss": 0.1043, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 5.697560975609756, | |
| "grad_norm": 3.6989609013172413, | |
| "learning_rate": 1.4123563174739036e-05, | |
| "loss": 0.0963, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 5.710569105691057, | |
| "grad_norm": 2.7026993176086935, | |
| "learning_rate": 1.4097645530025812e-05, | |
| "loss": 0.1011, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 5.723577235772358, | |
| "grad_norm": 2.671495036637557, | |
| "learning_rate": 1.4071694763866988e-05, | |
| "loss": 0.0732, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.736585365853658, | |
| "grad_norm": 2.7556928866773465, | |
| "learning_rate": 1.4045711086023721e-05, | |
| "loss": 0.0926, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 5.74959349593496, | |
| "grad_norm": 3.069018095017195, | |
| "learning_rate": 1.4019694706523203e-05, | |
| "loss": 0.1156, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 5.76260162601626, | |
| "grad_norm": 2.621864072211424, | |
| "learning_rate": 1.3993645835656955e-05, | |
| "loss": 0.0828, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 5.775609756097561, | |
| "grad_norm": 3.428109479643195, | |
| "learning_rate": 1.3967564683979125e-05, | |
| "loss": 0.1033, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 5.788617886178862, | |
| "grad_norm": 2.474144283173875, | |
| "learning_rate": 1.3941451462304778e-05, | |
| "loss": 0.0791, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 5.801626016260163, | |
| "grad_norm": 2.7246381307154866, | |
| "learning_rate": 1.391530638170822e-05, | |
| "loss": 0.0927, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 5.814634146341463, | |
| "grad_norm": 2.1261222791476464, | |
| "learning_rate": 1.3889129653521262e-05, | |
| "loss": 0.0713, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 5.827642276422765, | |
| "grad_norm": 3.0617042801154035, | |
| "learning_rate": 1.3862921489331526e-05, | |
| "loss": 0.1068, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 5.840650406504065, | |
| "grad_norm": 2.8852311127283152, | |
| "learning_rate": 1.3836682100980739e-05, | |
| "loss": 0.0872, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 5.853658536585366, | |
| "grad_norm": 2.6420556921053784, | |
| "learning_rate": 1.3810411700563005e-05, | |
| "loss": 0.0934, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.866666666666667, | |
| "grad_norm": 2.1997468772995794, | |
| "learning_rate": 1.3784110500423104e-05, | |
| "loss": 0.0647, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 5.879674796747968, | |
| "grad_norm": 2.569366229126445, | |
| "learning_rate": 1.3757778713154772e-05, | |
| "loss": 0.088, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 5.892682926829268, | |
| "grad_norm": 2.4657362166669, | |
| "learning_rate": 1.3731416551598984e-05, | |
| "loss": 0.0738, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 5.905691056910569, | |
| "grad_norm": 2.3032390982249744, | |
| "learning_rate": 1.3705024228842223e-05, | |
| "loss": 0.0679, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 5.91869918699187, | |
| "grad_norm": 2.4116624882592665, | |
| "learning_rate": 1.3678601958214779e-05, | |
| "loss": 0.0748, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 5.931707317073171, | |
| "grad_norm": 2.9504969618150367, | |
| "learning_rate": 1.3652149953289002e-05, | |
| "loss": 0.0723, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 5.944715447154471, | |
| "grad_norm": 2.9379356263518415, | |
| "learning_rate": 1.362566842787759e-05, | |
| "loss": 0.0693, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 5.957723577235773, | |
| "grad_norm": 2.8833146911131706, | |
| "learning_rate": 1.3599157596031853e-05, | |
| "loss": 0.0791, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 5.970731707317073, | |
| "grad_norm": 2.8272697602148287, | |
| "learning_rate": 1.3572617672039994e-05, | |
| "loss": 0.0706, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 5.983739837398374, | |
| "grad_norm": 2.6799390700321526, | |
| "learning_rate": 1.3546048870425356e-05, | |
| "loss": 0.0728, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.996747967479675, | |
| "grad_norm": 5.719197939165723, | |
| "learning_rate": 1.3519451405944717e-05, | |
| "loss": 0.1236, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 6.009756097560976, | |
| "grad_norm": 2.111845499659754, | |
| "learning_rate": 1.3492825493586526e-05, | |
| "loss": 0.0448, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 6.022764227642276, | |
| "grad_norm": 2.1368142778246915, | |
| "learning_rate": 1.346617134856918e-05, | |
| "loss": 0.0385, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 6.035772357723578, | |
| "grad_norm": 2.1481116046164477, | |
| "learning_rate": 1.3439489186339283e-05, | |
| "loss": 0.0342, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 6.048780487804878, | |
| "grad_norm": 1.7270640749140826, | |
| "learning_rate": 1.3412779222569907e-05, | |
| "loss": 0.0301, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 6.061788617886179, | |
| "grad_norm": 2.0239851478698427, | |
| "learning_rate": 1.3386041673158836e-05, | |
| "loss": 0.0501, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 6.07479674796748, | |
| "grad_norm": 1.9442885149236053, | |
| "learning_rate": 1.3359276754226839e-05, | |
| "loss": 0.0402, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 6.087804878048781, | |
| "grad_norm": 2.3395885319875824, | |
| "learning_rate": 1.3332484682115916e-05, | |
| "loss": 0.0588, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 6.100813008130081, | |
| "grad_norm": 1.9512362409390018, | |
| "learning_rate": 1.3305665673387528e-05, | |
| "loss": 0.0338, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 6.1138211382113825, | |
| "grad_norm": 2.690266981810868, | |
| "learning_rate": 1.3278819944820893e-05, | |
| "loss": 0.0337, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.126829268292683, | |
| "grad_norm": 3.4250412108092454, | |
| "learning_rate": 1.3251947713411187e-05, | |
| "loss": 0.0486, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 6.139837398373984, | |
| "grad_norm": 2.6736270241738485, | |
| "learning_rate": 1.3225049196367814e-05, | |
| "loss": 0.058, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 6.152845528455284, | |
| "grad_norm": 2.520984117218317, | |
| "learning_rate": 1.319812461111265e-05, | |
| "loss": 0.0378, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 6.1658536585365855, | |
| "grad_norm": 1.9537033631580494, | |
| "learning_rate": 1.317117417527828e-05, | |
| "loss": 0.0363, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 6.178861788617886, | |
| "grad_norm": 2.310023434054684, | |
| "learning_rate": 1.314419810670624e-05, | |
| "loss": 0.0345, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 6.191869918699187, | |
| "grad_norm": 2.292477954767942, | |
| "learning_rate": 1.3117196623445253e-05, | |
| "loss": 0.0354, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 6.204878048780488, | |
| "grad_norm": 3.093112196382202, | |
| "learning_rate": 1.3090169943749475e-05, | |
| "loss": 0.0514, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 6.2178861788617885, | |
| "grad_norm": 1.7238228081457507, | |
| "learning_rate": 1.3063118286076726e-05, | |
| "loss": 0.0261, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 6.230894308943089, | |
| "grad_norm": 2.4405985722534913, | |
| "learning_rate": 1.3036041869086718e-05, | |
| "loss": 0.0308, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 6.2439024390243905, | |
| "grad_norm": 2.855561384021881, | |
| "learning_rate": 1.3008940911639302e-05, | |
| "loss": 0.0472, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.256910569105691, | |
| "grad_norm": 2.1670982199844264, | |
| "learning_rate": 1.2981815632792683e-05, | |
| "loss": 0.0415, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 6.2699186991869915, | |
| "grad_norm": 3.555690563412571, | |
| "learning_rate": 1.2954666251801662e-05, | |
| "loss": 0.0448, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 6.282926829268293, | |
| "grad_norm": 2.8659727016916157, | |
| "learning_rate": 1.2927492988115857e-05, | |
| "loss": 0.0554, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 6.2959349593495935, | |
| "grad_norm": 3.278250470071062, | |
| "learning_rate": 1.2900296061377927e-05, | |
| "loss": 0.0366, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 6.308943089430894, | |
| "grad_norm": 3.9910474066295913, | |
| "learning_rate": 1.2873075691421808e-05, | |
| "loss": 0.0343, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 6.321951219512195, | |
| "grad_norm": 3.8233856715254353, | |
| "learning_rate": 1.2845832098270925e-05, | |
| "loss": 0.0771, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 6.334959349593496, | |
| "grad_norm": 3.0294426925564943, | |
| "learning_rate": 1.2818565502136414e-05, | |
| "loss": 0.0822, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 6.3479674796747965, | |
| "grad_norm": 4.003605690459721, | |
| "learning_rate": 1.2791276123415348e-05, | |
| "loss": 0.0691, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 6.360975609756098, | |
| "grad_norm": 3.1341159493935438, | |
| "learning_rate": 1.2763964182688955e-05, | |
| "loss": 0.0689, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 6.373983739837398, | |
| "grad_norm": 4.086900629835164, | |
| "learning_rate": 1.2736629900720832e-05, | |
| "loss": 0.0673, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.386991869918699, | |
| "grad_norm": 1.9378624994658462, | |
| "learning_rate": 1.2709273498455152e-05, | |
| "loss": 0.0225, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "grad_norm": 2.1324669324753374, | |
| "learning_rate": 1.26818951970149e-05, | |
| "loss": 0.042, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 6.413008130081301, | |
| "grad_norm": 1.5886821998323448, | |
| "learning_rate": 1.265449521770007e-05, | |
| "loss": 0.0269, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 6.426016260162601, | |
| "grad_norm": 2.9030595838580413, | |
| "learning_rate": 1.262707378198587e-05, | |
| "loss": 0.0484, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 6.439024390243903, | |
| "grad_norm": 3.5977417503958535, | |
| "learning_rate": 1.2599631111520956e-05, | |
| "loss": 0.0508, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 6.452032520325203, | |
| "grad_norm": 3.6694174147590513, | |
| "learning_rate": 1.2572167428125608e-05, | |
| "loss": 0.0674, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 6.465040650406504, | |
| "grad_norm": 2.4129473140571136, | |
| "learning_rate": 1.254468295378997e-05, | |
| "loss": 0.0462, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 6.478048780487805, | |
| "grad_norm": 3.1858274317038577, | |
| "learning_rate": 1.2517177910672237e-05, | |
| "loss": 0.0552, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 6.491056910569106, | |
| "grad_norm": 2.5935148127658345, | |
| "learning_rate": 1.2489652521096852e-05, | |
| "loss": 0.0481, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 6.504065040650406, | |
| "grad_norm": 2.9450402573814567, | |
| "learning_rate": 1.2462107007552726e-05, | |
| "loss": 0.0582, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.517073170731708, | |
| "grad_norm": 2.7069332832569417, | |
| "learning_rate": 1.2434541592691443e-05, | |
| "loss": 0.0592, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 6.530081300813008, | |
| "grad_norm": 2.567349465362145, | |
| "learning_rate": 1.2406956499325429e-05, | |
| "loss": 0.0553, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 6.543089430894309, | |
| "grad_norm": 2.0895897218164396, | |
| "learning_rate": 1.2379351950426188e-05, | |
| "loss": 0.0334, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 6.55609756097561, | |
| "grad_norm": 1.8984990697792024, | |
| "learning_rate": 1.2351728169122483e-05, | |
| "loss": 0.0331, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 6.569105691056911, | |
| "grad_norm": 1.7581002434576, | |
| "learning_rate": 1.2324085378698529e-05, | |
| "loss": 0.0311, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 6.582113821138211, | |
| "grad_norm": 2.808270807082475, | |
| "learning_rate": 1.229642380259219e-05, | |
| "loss": 0.0542, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 6.595121951219512, | |
| "grad_norm": 2.5940978671200328, | |
| "learning_rate": 1.2268743664393182e-05, | |
| "loss": 0.0615, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 6.608130081300813, | |
| "grad_norm": 3.037820820822087, | |
| "learning_rate": 1.2241045187841257e-05, | |
| "loss": 0.0476, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 6.621138211382114, | |
| "grad_norm": 3.174677749036126, | |
| "learning_rate": 1.2213328596824392e-05, | |
| "loss": 0.0841, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 6.634146341463414, | |
| "grad_norm": 3.0257255090348982, | |
| "learning_rate": 1.2185594115376991e-05, | |
| "loss": 0.1044, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.647154471544716, | |
| "grad_norm": 3.4624261488209407, | |
| "learning_rate": 1.2157841967678064e-05, | |
| "loss": 0.0769, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 6.660162601626016, | |
| "grad_norm": 1.9612032892773348, | |
| "learning_rate": 1.2130072378049416e-05, | |
| "loss": 0.0304, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 6.673170731707317, | |
| "grad_norm": 2.5213552327747473, | |
| "learning_rate": 1.2102285570953842e-05, | |
| "loss": 0.0335, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 6.686178861788618, | |
| "grad_norm": 1.8981183407392777, | |
| "learning_rate": 1.2074481770993298e-05, | |
| "loss": 0.0342, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 6.699186991869919, | |
| "grad_norm": 4.290206859282562, | |
| "learning_rate": 1.2046661202907101e-05, | |
| "loss": 0.0945, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 6.712195121951219, | |
| "grad_norm": 1.8323648554205363, | |
| "learning_rate": 1.2018824091570103e-05, | |
| "loss": 0.0285, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 6.725203252032521, | |
| "grad_norm": 2.763087455511772, | |
| "learning_rate": 1.1990970661990877e-05, | |
| "loss": 0.0683, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 6.738211382113821, | |
| "grad_norm": 2.353806018174121, | |
| "learning_rate": 1.1963101139309894e-05, | |
| "loss": 0.0377, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 6.751219512195122, | |
| "grad_norm": 2.454104825810179, | |
| "learning_rate": 1.1935215748797708e-05, | |
| "loss": 0.0676, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 6.764227642276423, | |
| "grad_norm": 1.6279843510429204, | |
| "learning_rate": 1.1907314715853138e-05, | |
| "loss": 0.0348, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.777235772357724, | |
| "grad_norm": 2.6490086647572326, | |
| "learning_rate": 1.187939826600143e-05, | |
| "loss": 0.0455, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 6.790243902439024, | |
| "grad_norm": 2.0481762160031853, | |
| "learning_rate": 1.1851466624892455e-05, | |
| "loss": 0.033, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 6.803252032520325, | |
| "grad_norm": 2.094011332691674, | |
| "learning_rate": 1.1823520018298877e-05, | |
| "loss": 0.0496, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 6.816260162601626, | |
| "grad_norm": 3.246270225708711, | |
| "learning_rate": 1.1795558672114321e-05, | |
| "loss": 0.0836, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 6.829268292682927, | |
| "grad_norm": 3.006525188811639, | |
| "learning_rate": 1.176758281235155e-05, | |
| "loss": 0.0409, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.842276422764227, | |
| "grad_norm": 2.4038041178955933, | |
| "learning_rate": 1.1739592665140652e-05, | |
| "loss": 0.0479, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 6.855284552845529, | |
| "grad_norm": 2.4243653320767162, | |
| "learning_rate": 1.1711588456727187e-05, | |
| "loss": 0.0395, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 6.868292682926829, | |
| "grad_norm": 2.897618990620674, | |
| "learning_rate": 1.1683570413470384e-05, | |
| "loss": 0.0891, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 6.88130081300813, | |
| "grad_norm": 2.7286570543114737, | |
| "learning_rate": 1.16555387618413e-05, | |
| "loss": 0.0713, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 6.894308943089431, | |
| "grad_norm": 2.610695316382916, | |
| "learning_rate": 1.1627493728420978e-05, | |
| "loss": 0.0541, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.907317073170732, | |
| "grad_norm": 2.814844562765686, | |
| "learning_rate": 1.1599435539898636e-05, | |
| "loss": 0.0414, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 6.920325203252032, | |
| "grad_norm": 1.7831279324354765, | |
| "learning_rate": 1.1571364423069822e-05, | |
| "loss": 0.0286, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 6.933333333333334, | |
| "grad_norm": 1.8353679190961905, | |
| "learning_rate": 1.1543280604834581e-05, | |
| "loss": 0.0291, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 6.946341463414634, | |
| "grad_norm": 1.8813576863746508, | |
| "learning_rate": 1.151518431219563e-05, | |
| "loss": 0.0243, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 6.959349593495935, | |
| "grad_norm": 2.485555139073027, | |
| "learning_rate": 1.1487075772256517e-05, | |
| "loss": 0.0465, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 6.972357723577236, | |
| "grad_norm": 2.0103036241801204, | |
| "learning_rate": 1.145895521221978e-05, | |
| "loss": 0.0337, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 6.985365853658537, | |
| "grad_norm": 1.7855330363134008, | |
| "learning_rate": 1.143082285938512e-05, | |
| "loss": 0.0307, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 6.998373983739837, | |
| "grad_norm": 3.0176841119969025, | |
| "learning_rate": 1.1402678941147557e-05, | |
| "loss": 0.0596, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 7.0113821138211385, | |
| "grad_norm": 1.4748242874579913, | |
| "learning_rate": 1.13745236849956e-05, | |
| "loss": 0.0172, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 7.024390243902439, | |
| "grad_norm": 0.9195000087565399, | |
| "learning_rate": 1.1346357318509395e-05, | |
| "loss": 0.0176, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.03739837398374, | |
| "grad_norm": 1.9857762694373016, | |
| "learning_rate": 1.1318180069358901e-05, | |
| "loss": 0.025, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 7.050406504065041, | |
| "grad_norm": 1.0243241165825754, | |
| "learning_rate": 1.1289992165302036e-05, | |
| "loss": 0.0188, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 7.0634146341463415, | |
| "grad_norm": 1.0609924781993678, | |
| "learning_rate": 1.1261793834182843e-05, | |
| "loss": 0.014, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 7.076422764227642, | |
| "grad_norm": 1.737319207779907, | |
| "learning_rate": 1.1233585303929654e-05, | |
| "loss": 0.0232, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 7.0894308943089435, | |
| "grad_norm": 1.7478320052621348, | |
| "learning_rate": 1.1205366802553231e-05, | |
| "loss": 0.0236, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 7.102439024390244, | |
| "grad_norm": 1.7972556961794965, | |
| "learning_rate": 1.1177138558144941e-05, | |
| "loss": 0.0276, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 7.1154471544715445, | |
| "grad_norm": 2.071753371598691, | |
| "learning_rate": 1.1148900798874904e-05, | |
| "loss": 0.0212, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 7.128455284552846, | |
| "grad_norm": 1.454333842329555, | |
| "learning_rate": 1.112065375299014e-05, | |
| "loss": 0.0209, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 7.1414634146341465, | |
| "grad_norm": 2.2128806729074304, | |
| "learning_rate": 1.1092397648812746e-05, | |
| "loss": 0.0285, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 7.154471544715447, | |
| "grad_norm": 0.6146676806963332, | |
| "learning_rate": 1.1064132714738024e-05, | |
| "loss": 0.0083, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.167479674796748, | |
| "grad_norm": 1.474108395054986, | |
| "learning_rate": 1.1035859179232661e-05, | |
| "loss": 0.0162, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 7.180487804878049, | |
| "grad_norm": 1.7333842083551732, | |
| "learning_rate": 1.1007577270832864e-05, | |
| "loss": 0.0259, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 7.1934959349593495, | |
| "grad_norm": 2.6323575548170677, | |
| "learning_rate": 1.0979287218142518e-05, | |
| "loss": 0.0395, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 7.20650406504065, | |
| "grad_norm": 1.0719131678482425, | |
| "learning_rate": 1.0950989249831337e-05, | |
| "loss": 0.0124, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 7.219512195121951, | |
| "grad_norm": 1.5833243700550403, | |
| "learning_rate": 1.092268359463302e-05, | |
| "loss": 0.0099, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 7.232520325203252, | |
| "grad_norm": 2.2905756467347302, | |
| "learning_rate": 1.0894370481343406e-05, | |
| "loss": 0.0328, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 7.2455284552845525, | |
| "grad_norm": 1.3978528077488823, | |
| "learning_rate": 1.0866050138818602e-05, | |
| "loss": 0.0124, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 7.258536585365854, | |
| "grad_norm": 2.3538286947826994, | |
| "learning_rate": 1.0837722795973162e-05, | |
| "loss": 0.0223, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 7.271544715447154, | |
| "grad_norm": 1.8186330421511054, | |
| "learning_rate": 1.0809388681778223e-05, | |
| "loss": 0.0216, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 7.284552845528455, | |
| "grad_norm": 0.945401196778342, | |
| "learning_rate": 1.0781048025259648e-05, | |
| "loss": 0.0134, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.297560975609756, | |
| "grad_norm": 1.9517488407833354, | |
| "learning_rate": 1.0752701055496188e-05, | |
| "loss": 0.0129, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 7.310569105691057, | |
| "grad_norm": 1.9648390533798386, | |
| "learning_rate": 1.0724348001617626e-05, | |
| "loss": 0.0237, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 7.323577235772357, | |
| "grad_norm": 1.3295665523096223, | |
| "learning_rate": 1.0695989092802914e-05, | |
| "loss": 0.0146, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 7.336585365853659, | |
| "grad_norm": 0.8273172380539461, | |
| "learning_rate": 1.0667624558278338e-05, | |
| "loss": 0.0074, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 7.349593495934959, | |
| "grad_norm": 1.284860974532405, | |
| "learning_rate": 1.0639254627315658e-05, | |
| "loss": 0.0146, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 7.36260162601626, | |
| "grad_norm": 1.6309635277243517, | |
| "learning_rate": 1.0610879529230242e-05, | |
| "loss": 0.0169, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 7.375609756097561, | |
| "grad_norm": 1.9766783501257195, | |
| "learning_rate": 1.058249949337924e-05, | |
| "loss": 0.0459, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 7.388617886178862, | |
| "grad_norm": 0.9502632800397175, | |
| "learning_rate": 1.05541147491597e-05, | |
| "loss": 0.007, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 7.401626016260162, | |
| "grad_norm": 1.9982959250199734, | |
| "learning_rate": 1.0525725526006738e-05, | |
| "loss": 0.0201, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 7.414634146341464, | |
| "grad_norm": 2.0754641095590722, | |
| "learning_rate": 1.049733205339167e-05, | |
| "loss": 0.0186, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.427642276422764, | |
| "grad_norm": 2.0848531141884425, | |
| "learning_rate": 1.0468934560820157e-05, | |
| "loss": 0.0172, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 7.440650406504065, | |
| "grad_norm": 2.251271110215539, | |
| "learning_rate": 1.0440533277830355e-05, | |
| "loss": 0.0119, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 7.453658536585366, | |
| "grad_norm": 1.4639038307850378, | |
| "learning_rate": 1.0412128433991064e-05, | |
| "loss": 0.0123, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 7.466666666666667, | |
| "grad_norm": 1.2110922205359993, | |
| "learning_rate": 1.0383720258899864e-05, | |
| "loss": 0.0153, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 7.479674796747967, | |
| "grad_norm": 3.4877321355015356, | |
| "learning_rate": 1.0355308982181254e-05, | |
| "loss": 0.0278, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 7.492682926829268, | |
| "grad_norm": 0.7032740951581019, | |
| "learning_rate": 1.032689483348481e-05, | |
| "loss": 0.0075, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 7.505691056910569, | |
| "grad_norm": 0.8684769334973417, | |
| "learning_rate": 1.0298478042483327e-05, | |
| "loss": 0.0095, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 7.51869918699187, | |
| "grad_norm": 2.423271319680519, | |
| "learning_rate": 1.0270058838870948e-05, | |
| "loss": 0.0227, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 7.53170731707317, | |
| "grad_norm": 1.3407617488265873, | |
| "learning_rate": 1.0241637452361323e-05, | |
| "loss": 0.0115, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 7.544715447154472, | |
| "grad_norm": 1.207276254144989, | |
| "learning_rate": 1.0213214112685747e-05, | |
| "loss": 0.0141, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.557723577235772, | |
| "grad_norm": 0.5055444072299614, | |
| "learning_rate": 1.01847890495913e-05, | |
| "loss": 0.0043, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 7.570731707317073, | |
| "grad_norm": 1.7627894585314987, | |
| "learning_rate": 1.0156362492838991e-05, | |
| "loss": 0.0171, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 7.583739837398374, | |
| "grad_norm": 2.359898057520564, | |
| "learning_rate": 1.012793467220191e-05, | |
| "loss": 0.0182, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 7.596747967479675, | |
| "grad_norm": 3.3346044899148204, | |
| "learning_rate": 1.0099505817463351e-05, | |
| "loss": 0.0327, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 7.609756097560975, | |
| "grad_norm": 4.237874349630483, | |
| "learning_rate": 1.0071076158414977e-05, | |
| "loss": 0.0549, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 7.622764227642277, | |
| "grad_norm": 3.816331876941365, | |
| "learning_rate": 1.004264592485495e-05, | |
| "loss": 0.0485, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 7.635772357723577, | |
| "grad_norm": 1.6227184769502474, | |
| "learning_rate": 1.001421534658607e-05, | |
| "loss": 0.0089, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 7.648780487804878, | |
| "grad_norm": 2.299066537768556, | |
| "learning_rate": 9.985784653413931e-06, | |
| "loss": 0.0346, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 7.661788617886179, | |
| "grad_norm": 1.1559078136154577, | |
| "learning_rate": 9.957354075145053e-06, | |
| "loss": 0.0106, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 7.67479674796748, | |
| "grad_norm": 1.1595226487375585, | |
| "learning_rate": 9.928923841585025e-06, | |
| "loss": 0.0108, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.68780487804878, | |
| "grad_norm": 1.0757704349557082, | |
| "learning_rate": 9.900494182536652e-06, | |
| "loss": 0.0095, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 7.700813008130082, | |
| "grad_norm": 4.099082054983232, | |
| "learning_rate": 9.872065327798092e-06, | |
| "loss": 0.0486, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 7.713821138211382, | |
| "grad_norm": 2.292496055927853, | |
| "learning_rate": 9.84363750716101e-06, | |
| "loss": 0.0235, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 7.726829268292683, | |
| "grad_norm": 1.9178358301562846, | |
| "learning_rate": 9.815210950408703e-06, | |
| "loss": 0.0168, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 7.739837398373984, | |
| "grad_norm": 1.7570666578565255, | |
| "learning_rate": 9.786785887314255e-06, | |
| "loss": 0.0216, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 7.752845528455285, | |
| "grad_norm": 2.906135856571168, | |
| "learning_rate": 9.75836254763868e-06, | |
| "loss": 0.036, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 7.765853658536585, | |
| "grad_norm": 0.6102186666671133, | |
| "learning_rate": 9.729941161129055e-06, | |
| "loss": 0.0052, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 7.778861788617887, | |
| "grad_norm": 2.006642525644417, | |
| "learning_rate": 9.701521957516677e-06, | |
| "loss": 0.0354, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 7.791869918699187, | |
| "grad_norm": 1.6112202056054103, | |
| "learning_rate": 9.673105166515194e-06, | |
| "loss": 0.021, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 7.804878048780488, | |
| "grad_norm": 1.28486396638533, | |
| "learning_rate": 9.644691017818752e-06, | |
| "loss": 0.0113, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.897560975609756, | |
| "grad_norm": 1.1570836064474173, | |
| "learning_rate": 9.616279741100141e-06, | |
| "loss": 0.0163, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 7.9105691056910565, | |
| "grad_norm": 4.3926195896460705, | |
| "learning_rate": 9.587871566008941e-06, | |
| "loss": 0.0372, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 7.923577235772358, | |
| "grad_norm": 1.8374516838829014, | |
| "learning_rate": 9.55946672216965e-06, | |
| "loss": 0.0152, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 7.9365853658536585, | |
| "grad_norm": 1.2538360344208235, | |
| "learning_rate": 9.53106543917985e-06, | |
| "loss": 0.0079, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 7.949593495934959, | |
| "grad_norm": 1.6551949026862187, | |
| "learning_rate": 9.502667946608332e-06, | |
| "loss": 0.022, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 7.96260162601626, | |
| "grad_norm": 1.2298212750460404, | |
| "learning_rate": 9.474274473993263e-06, | |
| "loss": 0.0144, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 7.975609756097561, | |
| "grad_norm": 0.5496419989314434, | |
| "learning_rate": 9.445885250840301e-06, | |
| "loss": 0.0054, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 7.9886178861788615, | |
| "grad_norm": 1.3353474096544538, | |
| "learning_rate": 9.41750050662076e-06, | |
| "loss": 0.0112, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 8.001626016260163, | |
| "grad_norm": 1.1581286863052545, | |
| "learning_rate": 9.389120470769758e-06, | |
| "loss": 0.0091, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 8.014634146341463, | |
| "grad_norm": 1.696248770025462, | |
| "learning_rate": 9.360745372684346e-06, | |
| "loss": 0.0232, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.027642276422764, | |
| "grad_norm": 0.9635336545656762, | |
| "learning_rate": 9.332375441721664e-06, | |
| "loss": 0.0125, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 8.040650406504065, | |
| "grad_norm": 1.7995568016097954, | |
| "learning_rate": 9.304010907197088e-06, | |
| "loss": 0.0152, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 8.053658536585365, | |
| "grad_norm": 0.5218744745869878, | |
| "learning_rate": 9.275651998382377e-06, | |
| "loss": 0.0037, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 8.066666666666666, | |
| "grad_norm": 1.7593678574145648, | |
| "learning_rate": 9.247298944503813e-06, | |
| "loss": 0.0144, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 8.079674796747968, | |
| "grad_norm": 1.0242522857715741, | |
| "learning_rate": 9.218951974740354e-06, | |
| "loss": 0.0058, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 8.092682926829267, | |
| "grad_norm": 0.804026841919947, | |
| "learning_rate": 9.190611318221779e-06, | |
| "loss": 0.0043, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 8.105691056910569, | |
| "grad_norm": 0.8639328680213971, | |
| "learning_rate": 9.162277204026841e-06, | |
| "loss": 0.009, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 8.11869918699187, | |
| "grad_norm": 0.6692064656778831, | |
| "learning_rate": 9.1339498611814e-06, | |
| "loss": 0.0059, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 8.13170731707317, | |
| "grad_norm": 1.3302886569969412, | |
| "learning_rate": 9.105629518656597e-06, | |
| "loss": 0.008, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 8.144715447154471, | |
| "grad_norm": 2.7029834067969, | |
| "learning_rate": 9.07731640536698e-06, | |
| "loss": 0.0087, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.157723577235773, | |
| "grad_norm": 0.5950805638509996, | |
| "learning_rate": 9.049010750168667e-06, | |
| "loss": 0.005, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 8.170731707317072, | |
| "grad_norm": 1.473020833784232, | |
| "learning_rate": 9.020712781857485e-06, | |
| "loss": 0.0093, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 8.183739837398374, | |
| "grad_norm": 1.323143857293457, | |
| "learning_rate": 8.99242272916714e-06, | |
| "loss": 0.0077, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 8.196747967479675, | |
| "grad_norm": 0.6013128053864051, | |
| "learning_rate": 8.96414082076734e-06, | |
| "loss": 0.0055, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 8.209756097560975, | |
| "grad_norm": 0.6933361341239108, | |
| "learning_rate": 8.935867285261977e-06, | |
| "loss": 0.0038, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 8.222764227642276, | |
| "grad_norm": 0.7643716646547513, | |
| "learning_rate": 8.90760235118726e-06, | |
| "loss": 0.0059, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 8.235772357723578, | |
| "grad_norm": 1.6083959007721669, | |
| "learning_rate": 8.879346247009862e-06, | |
| "loss": 0.0183, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 8.248780487804877, | |
| "grad_norm": 1.7481203666565401, | |
| "learning_rate": 8.851099201125098e-06, | |
| "loss": 0.0124, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 8.261788617886179, | |
| "grad_norm": 2.979391453099003, | |
| "learning_rate": 8.822861441855062e-06, | |
| "loss": 0.0472, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 8.27479674796748, | |
| "grad_norm": 1.5205590984667567, | |
| "learning_rate": 8.79463319744677e-06, | |
| "loss": 0.012, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 8.28780487804878, | |
| "grad_norm": 0.45025282821354934, | |
| "learning_rate": 8.76641469607035e-06, | |
| "loss": 0.0032, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 8.300813008130081, | |
| "grad_norm": 1.6291831313222467, | |
| "learning_rate": 8.738206165817162e-06, | |
| "loss": 0.0174, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 8.313821138211383, | |
| "grad_norm": 1.8672390073053273, | |
| "learning_rate": 8.71000783469797e-06, | |
| "loss": 0.0161, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 8.326829268292682, | |
| "grad_norm": 0.6624522215545257, | |
| "learning_rate": 8.681819930641104e-06, | |
| "loss": 0.0047, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 8.339837398373984, | |
| "grad_norm": 1.2872295772729532, | |
| "learning_rate": 8.653642681490608e-06, | |
| "loss": 0.0068, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 8.352845528455285, | |
| "grad_norm": 1.9001799919981712, | |
| "learning_rate": 8.625476315004406e-06, | |
| "loss": 0.0115, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 8.365853658536585, | |
| "grad_norm": 1.1211077846124613, | |
| "learning_rate": 8.597321058852446e-06, | |
| "loss": 0.0078, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 8.378861788617886, | |
| "grad_norm": 0.5257992324029892, | |
| "learning_rate": 8.569177140614884e-06, | |
| "loss": 0.0033, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 8.391869918699188, | |
| "grad_norm": 0.9500921805600161, | |
| "learning_rate": 8.541044787780223e-06, | |
| "loss": 0.0121, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 8.404878048780487, | |
| "grad_norm": 1.590484580117083, | |
| "learning_rate": 8.512924227743482e-06, | |
| "loss": 0.0183, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.417886178861789, | |
| "grad_norm": 1.3523870862348597, | |
| "learning_rate": 8.48481568780437e-06, | |
| "loss": 0.0059, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 8.43089430894309, | |
| "grad_norm": 0.3643386165943172, | |
| "learning_rate": 8.45671939516542e-06, | |
| "loss": 0.0027, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 8.44390243902439, | |
| "grad_norm": 0.4038839717069236, | |
| "learning_rate": 8.42863557693018e-06, | |
| "loss": 0.0033, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 8.456910569105691, | |
| "grad_norm": 4.872152725527478, | |
| "learning_rate": 8.400564460101365e-06, | |
| "loss": 0.0064, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 8.469918699186993, | |
| "grad_norm": 1.566250126609204, | |
| "learning_rate": 8.372506271579022e-06, | |
| "loss": 0.0155, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 8.482926829268292, | |
| "grad_norm": 1.4695419969482413, | |
| "learning_rate": 8.3444612381587e-06, | |
| "loss": 0.0181, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 8.495934959349594, | |
| "grad_norm": 0.6092218830403479, | |
| "learning_rate": 8.316429586529616e-06, | |
| "loss": 0.004, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 8.508943089430895, | |
| "grad_norm": 0.6271026393173923, | |
| "learning_rate": 8.288411543272814e-06, | |
| "loss": 0.004, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 8.521951219512195, | |
| "grad_norm": 0.45814933354877085, | |
| "learning_rate": 8.260407334859352e-06, | |
| "loss": 0.0032, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 8.534959349593496, | |
| "grad_norm": 0.5630633751133635, | |
| "learning_rate": 8.232417187648454e-06, | |
| "loss": 0.0033, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.547967479674798, | |
| "grad_norm": 2.1864551163075236, | |
| "learning_rate": 8.204441327885682e-06, | |
| "loss": 0.0202, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 8.560975609756097, | |
| "grad_norm": 1.6493473678926696, | |
| "learning_rate": 8.176479981701124e-06, | |
| "loss": 0.0062, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 8.573983739837399, | |
| "grad_norm": 1.5925655533524505, | |
| "learning_rate": 8.148533375107547e-06, | |
| "loss": 0.0125, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 8.5869918699187, | |
| "grad_norm": 0.7658342201667933, | |
| "learning_rate": 8.120601733998573e-06, | |
| "loss": 0.0037, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "grad_norm": 0.6802727123664065, | |
| "learning_rate": 8.092685284146865e-06, | |
| "loss": 0.0058, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 8.613008130081301, | |
| "grad_norm": 0.6428487324704795, | |
| "learning_rate": 8.064784251202295e-06, | |
| "loss": 0.0034, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 8.6260162601626, | |
| "grad_norm": 1.2283433307632814, | |
| "learning_rate": 8.036898860690109e-06, | |
| "loss": 0.0078, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 8.639024390243902, | |
| "grad_norm": 1.017938353807125, | |
| "learning_rate": 8.009029338009124e-06, | |
| "loss": 0.0047, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 8.652032520325204, | |
| "grad_norm": 0.7001890029191871, | |
| "learning_rate": 7.9811759084299e-06, | |
| "loss": 0.0036, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 8.665040650406503, | |
| "grad_norm": 0.633347645128458, | |
| "learning_rate": 7.953338797092902e-06, | |
| "loss": 0.0046, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.678048780487805, | |
| "grad_norm": 1.2025605383952795, | |
| "learning_rate": 7.925518229006706e-06, | |
| "loss": 0.0093, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 8.691056910569106, | |
| "grad_norm": 2.633448780438676, | |
| "learning_rate": 7.897714429046161e-06, | |
| "loss": 0.0146, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 8.704065040650406, | |
| "grad_norm": 0.5596034491248052, | |
| "learning_rate": 7.869927621950589e-06, | |
| "loss": 0.0028, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 8.717073170731707, | |
| "grad_norm": 1.157553594361386, | |
| "learning_rate": 7.84215803232194e-06, | |
| "loss": 0.008, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 8.730081300813008, | |
| "grad_norm": 0.9018826372017152, | |
| "learning_rate": 7.814405884623012e-06, | |
| "loss": 0.0044, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 8.743089430894308, | |
| "grad_norm": 0.23290196917996137, | |
| "learning_rate": 7.786671403175613e-06, | |
| "loss": 0.0012, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 8.75609756097561, | |
| "grad_norm": 0.09872361493258511, | |
| "learning_rate": 7.758954812158748e-06, | |
| "loss": 0.0007, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 8.769105691056911, | |
| "grad_norm": 2.416464152136664, | |
| "learning_rate": 7.73125633560682e-06, | |
| "loss": 0.0334, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 8.78211382113821, | |
| "grad_norm": 1.8383531775741038, | |
| "learning_rate": 7.703576197407814e-06, | |
| "loss": 0.0129, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 8.795121951219512, | |
| "grad_norm": 0.5846243555775849, | |
| "learning_rate": 7.675914621301476e-06, | |
| "loss": 0.0046, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.808130081300813, | |
| "grad_norm": 0.20276419203159612, | |
| "learning_rate": 7.64827183087752e-06, | |
| "loss": 0.0013, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 8.821138211382113, | |
| "grad_norm": 2.250697908537039, | |
| "learning_rate": 7.620648049573815e-06, | |
| "loss": 0.0198, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 8.834146341463414, | |
| "grad_norm": 2.5506639659880697, | |
| "learning_rate": 7.593043500674576e-06, | |
| "loss": 0.0335, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 8.847154471544716, | |
| "grad_norm": 0.1760344339783254, | |
| "learning_rate": 7.565458407308562e-06, | |
| "loss": 0.0013, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 8.860162601626016, | |
| "grad_norm": 0.9878490804168167, | |
| "learning_rate": 7.5378929924472735e-06, | |
| "loss": 0.0062, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 8.873170731707317, | |
| "grad_norm": 1.2003584506062117, | |
| "learning_rate": 7.51034747890315e-06, | |
| "loss": 0.0132, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 8.886178861788618, | |
| "grad_norm": 0.6698985442501936, | |
| "learning_rate": 7.482822089327766e-06, | |
| "loss": 0.004, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 8.899186991869918, | |
| "grad_norm": 1.8608580951848903, | |
| "learning_rate": 7.455317046210029e-06, | |
| "loss": 0.0152, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 8.91219512195122, | |
| "grad_norm": 1.955648048483486, | |
| "learning_rate": 7.427832571874391e-06, | |
| "loss": 0.009, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 8.92520325203252, | |
| "grad_norm": 0.6522291760736664, | |
| "learning_rate": 7.400368888479048e-06, | |
| "loss": 0.0026, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.93821138211382, | |
| "grad_norm": 1.8126549078970746, | |
| "learning_rate": 7.372926218014131e-06, | |
| "loss": 0.0112, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 8.951219512195122, | |
| "grad_norm": 3.7519826805559906, | |
| "learning_rate": 7.345504782299933e-06, | |
| "loss": 0.039, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 8.964227642276423, | |
| "grad_norm": 2.1405391277026395, | |
| "learning_rate": 7.318104802985102e-06, | |
| "loss": 0.0029, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 8.977235772357723, | |
| "grad_norm": 3.2663905500123995, | |
| "learning_rate": 7.29072650154485e-06, | |
| "loss": 0.0133, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 8.990243902439024, | |
| "grad_norm": 1.4235721126316785, | |
| "learning_rate": 7.263370099279173e-06, | |
| "loss": 0.0075, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 9.003252032520326, | |
| "grad_norm": 1.5535694922192906, | |
| "learning_rate": 7.236035817311047e-06, | |
| "loss": 0.0094, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 9.016260162601625, | |
| "grad_norm": 0.2627479940056018, | |
| "learning_rate": 7.208723876584654e-06, | |
| "loss": 0.0017, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 9.029268292682927, | |
| "grad_norm": 0.4520005178424521, | |
| "learning_rate": 7.181434497863589e-06, | |
| "loss": 0.0019, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 9.042276422764228, | |
| "grad_norm": 0.17942256470122298, | |
| "learning_rate": 7.154167901729078e-06, | |
| "loss": 0.0014, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 9.055284552845528, | |
| "grad_norm": 0.27697334188523803, | |
| "learning_rate": 7.126924308578196e-06, | |
| "loss": 0.002, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.06829268292683, | |
| "grad_norm": 0.34183068785785425, | |
| "learning_rate": 7.099703938622076e-06, | |
| "loss": 0.0018, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 9.08130081300813, | |
| "grad_norm": 1.3803401856075173, | |
| "learning_rate": 7.072507011884146e-06, | |
| "loss": 0.0118, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 9.09430894308943, | |
| "grad_norm": 1.3568397929755587, | |
| "learning_rate": 7.045333748198342e-06, | |
| "loss": 0.006, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 9.107317073170732, | |
| "grad_norm": 0.38380133051188836, | |
| "learning_rate": 7.0181843672073195e-06, | |
| "loss": 0.0027, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 9.120325203252033, | |
| "grad_norm": 0.33699787698320505, | |
| "learning_rate": 6.9910590883607e-06, | |
| "loss": 0.0028, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 9.133333333333333, | |
| "grad_norm": 0.9219452083351827, | |
| "learning_rate": 6.963958130913285e-06, | |
| "loss": 0.0038, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 9.146341463414634, | |
| "grad_norm": 0.22872769458941739, | |
| "learning_rate": 6.936881713923278e-06, | |
| "loss": 0.0016, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 9.159349593495936, | |
| "grad_norm": 1.8659145036422158, | |
| "learning_rate": 6.909830056250527e-06, | |
| "loss": 0.0073, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 9.172357723577235, | |
| "grad_norm": 0.8714505646577918, | |
| "learning_rate": 6.882803376554752e-06, | |
| "loss": 0.0041, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 9.185365853658537, | |
| "grad_norm": 3.7669183636793786, | |
| "learning_rate": 6.855801893293765e-06, | |
| "loss": 0.0574, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.198373983739838, | |
| "grad_norm": 1.8011229635123818, | |
| "learning_rate": 6.828825824721723e-06, | |
| "loss": 0.0073, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 9.211382113821138, | |
| "grad_norm": 1.1367034179206732, | |
| "learning_rate": 6.801875388887356e-06, | |
| "loss": 0.0073, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 9.22439024390244, | |
| "grad_norm": 0.3445914797421055, | |
| "learning_rate": 6.774950803632192e-06, | |
| "loss": 0.002, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 9.23739837398374, | |
| "grad_norm": 0.3772220820545059, | |
| "learning_rate": 6.74805228658882e-06, | |
| "loss": 0.0019, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 9.25040650406504, | |
| "grad_norm": 0.6069595408777112, | |
| "learning_rate": 6.721180055179113e-06, | |
| "loss": 0.0036, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 9.263414634146342, | |
| "grad_norm": 0.18806254090946373, | |
| "learning_rate": 6.694334326612475e-06, | |
| "loss": 0.0014, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 9.276422764227643, | |
| "grad_norm": 0.6835511302578737, | |
| "learning_rate": 6.66751531788409e-06, | |
| "loss": 0.0029, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 9.289430894308943, | |
| "grad_norm": 0.7556461894159618, | |
| "learning_rate": 6.640723245773162e-06, | |
| "loss": 0.004, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 9.302439024390244, | |
| "grad_norm": 0.4976813766777833, | |
| "learning_rate": 6.613958326841163e-06, | |
| "loss": 0.0021, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 9.315447154471546, | |
| "grad_norm": 0.19880631922304534, | |
| "learning_rate": 6.587220777430097e-06, | |
| "loss": 0.0013, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 9.328455284552845, | |
| "grad_norm": 0.5526404773632339, | |
| "learning_rate": 6.560510813660719e-06, | |
| "loss": 0.0024, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 9.341463414634147, | |
| "grad_norm": 0.3618818809888966, | |
| "learning_rate": 6.533828651430823e-06, | |
| "loss": 0.0022, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 9.354471544715448, | |
| "grad_norm": 0.13968931300117193, | |
| "learning_rate": 6.507174506413476e-06, | |
| "loss": 0.0011, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 9.367479674796748, | |
| "grad_norm": 0.545676069641217, | |
| "learning_rate": 6.480548594055285e-06, | |
| "loss": 0.0028, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 9.38048780487805, | |
| "grad_norm": 0.651992152152611, | |
| "learning_rate": 6.453951129574644e-06, | |
| "loss": 0.0037, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 9.393495934959349, | |
| "grad_norm": 0.08047968696500124, | |
| "learning_rate": 6.427382327960008e-06, | |
| "loss": 0.0006, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 9.40650406504065, | |
| "grad_norm": 2.505129451573409, | |
| "learning_rate": 6.400842403968148e-06, | |
| "loss": 0.0133, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 9.419512195121952, | |
| "grad_norm": 1.971414547082271, | |
| "learning_rate": 6.374331572122413e-06, | |
| "loss": 0.0137, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 9.432520325203251, | |
| "grad_norm": 0.08388839040822257, | |
| "learning_rate": 6.3478500467109995e-06, | |
| "loss": 0.0007, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 9.445528455284553, | |
| "grad_norm": 0.14957469944874793, | |
| "learning_rate": 6.321398041785225e-06, | |
| "loss": 0.0009, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.458536585365854, | |
| "grad_norm": 0.2293748761638421, | |
| "learning_rate": 6.294975771157779e-06, | |
| "loss": 0.002, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 9.471544715447154, | |
| "grad_norm": 1.1348199558360812, | |
| "learning_rate": 6.26858344840102e-06, | |
| "loss": 0.0033, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 9.484552845528455, | |
| "grad_norm": 0.17444247050438766, | |
| "learning_rate": 6.24222128684523e-06, | |
| "loss": 0.0011, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 9.497560975609757, | |
| "grad_norm": 1.469322104576111, | |
| "learning_rate": 6.215889499576898e-06, | |
| "loss": 0.0041, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 9.510569105691056, | |
| "grad_norm": 2.4640290623372456, | |
| "learning_rate": 6.189588299436997e-06, | |
| "loss": 0.0057, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 9.523577235772358, | |
| "grad_norm": 0.3551828514072661, | |
| "learning_rate": 6.163317899019263e-06, | |
| "loss": 0.0017, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 9.536585365853659, | |
| "grad_norm": 1.9778045389994514, | |
| "learning_rate": 6.137078510668475e-06, | |
| "loss": 0.0054, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 9.549593495934959, | |
| "grad_norm": 0.1988055551588179, | |
| "learning_rate": 6.11087034647874e-06, | |
| "loss": 0.0016, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 9.56260162601626, | |
| "grad_norm": 1.1742874707944437, | |
| "learning_rate": 6.084693618291784e-06, | |
| "loss": 0.0053, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 9.575609756097561, | |
| "grad_norm": 0.5141180298405635, | |
| "learning_rate": 6.058548537695225e-06, | |
| "loss": 0.0023, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.588617886178861, | |
| "grad_norm": 0.3974291589148598, | |
| "learning_rate": 6.032435316020879e-06, | |
| "loss": 0.0031, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 9.601626016260163, | |
| "grad_norm": 0.144069333032306, | |
| "learning_rate": 6.006354164343047e-06, | |
| "loss": 0.001, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 9.614634146341464, | |
| "grad_norm": 0.0854524512610507, | |
| "learning_rate": 5.980305293476798e-06, | |
| "loss": 0.0007, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 9.627642276422764, | |
| "grad_norm": 1.0676606151474946, | |
| "learning_rate": 5.954288913976282e-06, | |
| "loss": 0.0049, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 9.640650406504065, | |
| "grad_norm": 0.22481585335882875, | |
| "learning_rate": 5.928305236133016e-06, | |
| "loss": 0.0014, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 9.653658536585366, | |
| "grad_norm": 1.5806927451491446, | |
| "learning_rate": 5.9023544699741916e-06, | |
| "loss": 0.0074, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 9.666666666666666, | |
| "grad_norm": 3.162133500470142, | |
| "learning_rate": 5.876436825260967e-06, | |
| "loss": 0.0236, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 9.679674796747967, | |
| "grad_norm": 0.6497244678275477, | |
| "learning_rate": 5.8505525114867845e-06, | |
| "loss": 0.0023, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 9.692682926829269, | |
| "grad_norm": 0.20942650687885297, | |
| "learning_rate": 5.824701737875671e-06, | |
| "loss": 0.0015, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 9.705691056910569, | |
| "grad_norm": 0.21783176506446844, | |
| "learning_rate": 5.798884713380542e-06, | |
| "loss": 0.0009, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.71869918699187, | |
| "grad_norm": 1.3397879966577473, | |
| "learning_rate": 5.773101646681519e-06, | |
| "loss": 0.0053, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 9.731707317073171, | |
| "grad_norm": 0.5629435457967111, | |
| "learning_rate": 5.747352746184246e-06, | |
| "loss": 0.0029, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 9.744715447154471, | |
| "grad_norm": 0.2655804464635928, | |
| "learning_rate": 5.721638220018195e-06, | |
| "loss": 0.0015, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 9.757723577235772, | |
| "grad_norm": 1.2625485903808695, | |
| "learning_rate": 5.695958276034992e-06, | |
| "loss": 0.0109, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 9.770731707317074, | |
| "grad_norm": 0.6053445135651991, | |
| "learning_rate": 5.67031312180673e-06, | |
| "loss": 0.0018, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 9.783739837398373, | |
| "grad_norm": 0.2216958815586712, | |
| "learning_rate": 5.644702964624298e-06, | |
| "loss": 0.0014, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 9.796747967479675, | |
| "grad_norm": 0.5151779928761385, | |
| "learning_rate": 5.6191280114957e-06, | |
| "loss": 0.0017, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 9.809756097560976, | |
| "grad_norm": 0.6574952728794218, | |
| "learning_rate": 5.593588469144393e-06, | |
| "loss": 0.0061, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 9.822764227642276, | |
| "grad_norm": 0.5715758912209028, | |
| "learning_rate": 5.5680845440075885e-06, | |
| "loss": 0.0018, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 9.835772357723577, | |
| "grad_norm": 0.1623161803252056, | |
| "learning_rate": 5.542616442234618e-06, | |
| "loss": 0.001, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.848780487804879, | |
| "grad_norm": 0.9840006400935422, | |
| "learning_rate": 5.517184369685249e-06, | |
| "loss": 0.006, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 9.861788617886178, | |
| "grad_norm": 0.24112095169278702, | |
| "learning_rate": 5.4917885319280174e-06, | |
| "loss": 0.0011, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 9.87479674796748, | |
| "grad_norm": 0.0574912432392828, | |
| "learning_rate": 5.46642913423858e-06, | |
| "loss": 0.0004, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 9.887804878048781, | |
| "grad_norm": 0.39818352891783554, | |
| "learning_rate": 5.441106381598038e-06, | |
| "loss": 0.0018, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 9.900813008130081, | |
| "grad_norm": 0.4845619747401539, | |
| "learning_rate": 5.415820478691301e-06, | |
| "loss": 0.0026, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 9.913821138211382, | |
| "grad_norm": 0.1830833298630534, | |
| "learning_rate": 5.390571629905404e-06, | |
| "loss": 0.001, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 9.926829268292684, | |
| "grad_norm": 0.47093815573108905, | |
| "learning_rate": 5.365360039327883e-06, | |
| "loss": 0.0029, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 9.939837398373983, | |
| "grad_norm": 1.1293829121916676, | |
| "learning_rate": 5.340185910745115e-06, | |
| "loss": 0.0064, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 9.952845528455285, | |
| "grad_norm": 1.1535164398174766, | |
| "learning_rate": 5.3150494476406655e-06, | |
| "loss": 0.008, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 9.965853658536584, | |
| "grad_norm": 0.6455882175180273, | |
| "learning_rate": 5.2899508531936526e-06, | |
| "loss": 0.0044, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.978861788617886, | |
| "grad_norm": 0.13020549451493543, | |
| "learning_rate": 5.2648903302771e-06, | |
| "loss": 0.0009, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 9.991869918699187, | |
| "grad_norm": 1.3934610223710313, | |
| "learning_rate": 5.2398680814562875e-06, | |
| "loss": 0.01, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 10.004878048780487, | |
| "grad_norm": 0.47932911623345126, | |
| "learning_rate": 5.214884308987136e-06, | |
| "loss": 0.0019, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 10.017886178861788, | |
| "grad_norm": 0.11341961597130322, | |
| "learning_rate": 5.189939214814558e-06, | |
| "loss": 0.0008, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 10.03089430894309, | |
| "grad_norm": 0.07014317124050574, | |
| "learning_rate": 5.165033000570825e-06, | |
| "loss": 0.0006, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 10.04390243902439, | |
| "grad_norm": 0.4939383938541964, | |
| "learning_rate": 5.14016586757394e-06, | |
| "loss": 0.002, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 10.05691056910569, | |
| "grad_norm": 0.051143749930634086, | |
| "learning_rate": 5.115338016826017e-06, | |
| "loss": 0.0004, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 10.069918699186992, | |
| "grad_norm": 0.15061806975433353, | |
| "learning_rate": 5.0905496490116355e-06, | |
| "loss": 0.0008, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 10.082926829268292, | |
| "grad_norm": 0.05789693918615477, | |
| "learning_rate": 5.065800964496248e-06, | |
| "loss": 0.0005, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 10.095934959349593, | |
| "grad_norm": 0.1742458351231767, | |
| "learning_rate": 5.041092163324537e-06, | |
| "loss": 0.0013, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.108943089430895, | |
| "grad_norm": 0.061702963689786644, | |
| "learning_rate": 5.01642344521881e-06, | |
| "loss": 0.0006, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 10.121951219512194, | |
| "grad_norm": 0.23180841253300452, | |
| "learning_rate": 4.99179500957738e-06, | |
| "loss": 0.0014, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 10.134959349593496, | |
| "grad_norm": 4.190784176626806, | |
| "learning_rate": 4.967207055472953e-06, | |
| "loss": 0.0078, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 10.147967479674797, | |
| "grad_norm": 0.08044864398385289, | |
| "learning_rate": 4.942659781651028e-06, | |
| "loss": 0.0006, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 10.160975609756097, | |
| "grad_norm": 0.08134366410064657, | |
| "learning_rate": 4.918153386528271e-06, | |
| "loss": 0.0005, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 10.173983739837398, | |
| "grad_norm": 0.3386130404211274, | |
| "learning_rate": 4.893688068190933e-06, | |
| "loss": 0.0014, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 10.1869918699187, | |
| "grad_norm": 0.07694587965043274, | |
| "learning_rate": 4.8692640243932385e-06, | |
| "loss": 0.0006, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "grad_norm": 0.20369709305033337, | |
| "learning_rate": 4.844881452555785e-06, | |
| "loss": 0.0008, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 10.2130081300813, | |
| "grad_norm": 0.2331731469796336, | |
| "learning_rate": 4.820540549763962e-06, | |
| "loss": 0.0011, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 10.226016260162602, | |
| "grad_norm": 0.050888921989665374, | |
| "learning_rate": 4.7962415127663265e-06, | |
| "loss": 0.0003, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 10.239024390243902, | |
| "grad_norm": 0.19440076973555925, | |
| "learning_rate": 4.771984537973046e-06, | |
| "loss": 0.0012, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 10.252032520325203, | |
| "grad_norm": 0.05850485970509135, | |
| "learning_rate": 4.747769821454295e-06, | |
| "loss": 0.0006, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 10.265040650406505, | |
| "grad_norm": 0.10448560046139084, | |
| "learning_rate": 4.7235975589386715e-06, | |
| "loss": 0.0009, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 10.278048780487804, | |
| "grad_norm": 0.0924812647057576, | |
| "learning_rate": 4.6994679458116165e-06, | |
| "loss": 0.0005, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 10.291056910569106, | |
| "grad_norm": 0.05976270109537895, | |
| "learning_rate": 4.675381177113837e-06, | |
| "loss": 0.0005, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 10.304065040650407, | |
| "grad_norm": 0.21102456712599046, | |
| "learning_rate": 4.651337447539716e-06, | |
| "loss": 0.0013, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 10.317073170731707, | |
| "grad_norm": 0.07346705031308397, | |
| "learning_rate": 4.627336951435762e-06, | |
| "loss": 0.0004, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 10.330081300813008, | |
| "grad_norm": 0.19520075710266213, | |
| "learning_rate": 4.603379882799018e-06, | |
| "loss": 0.001, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 10.34308943089431, | |
| "grad_norm": 0.05360207841255482, | |
| "learning_rate": 4.579466435275506e-06, | |
| "loss": 0.0004, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 10.35609756097561, | |
| "grad_norm": 0.30877901494761745, | |
| "learning_rate": 4.555596802158653e-06, | |
| "loss": 0.0012, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 10.36910569105691, | |
| "grad_norm": 0.4614215876073173, | |
| "learning_rate": 4.531771176387737e-06, | |
| "loss": 0.0015, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 10.382113821138212, | |
| "grad_norm": 0.04330375717864531, | |
| "learning_rate": 4.507989750546311e-06, | |
| "loss": 0.0004, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 10.395121951219512, | |
| "grad_norm": 0.06165414339063373, | |
| "learning_rate": 4.484252716860671e-06, | |
| "loss": 0.0004, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 10.408130081300813, | |
| "grad_norm": 0.09271709128689157, | |
| "learning_rate": 4.460560267198283e-06, | |
| "loss": 0.0006, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 10.421138211382114, | |
| "grad_norm": 0.04333394944073435, | |
| "learning_rate": 4.436912593066241e-06, | |
| "loss": 0.0003, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 10.434146341463414, | |
| "grad_norm": 0.11960246314871008, | |
| "learning_rate": 4.4133098856097146e-06, | |
| "loss": 0.0008, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 10.447154471544716, | |
| "grad_norm": 0.13175061578921837, | |
| "learning_rate": 4.389752335610405e-06, | |
| "loss": 0.0008, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 10.460162601626017, | |
| "grad_norm": 0.05315970701379665, | |
| "learning_rate": 4.366240133485012e-06, | |
| "loss": 0.0004, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 10.473170731707317, | |
| "grad_norm": 0.4637700425973471, | |
| "learning_rate": 4.342773469283671e-06, | |
| "loss": 0.0014, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 10.486178861788618, | |
| "grad_norm": 0.04958968480470787, | |
| "learning_rate": 4.319352532688444e-06, | |
| "loss": 0.0004, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.49918699186992, | |
| "grad_norm": 0.38056287228121716, | |
| "learning_rate": 4.295977513011772e-06, | |
| "loss": 0.0016, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 10.512195121951219, | |
| "grad_norm": 0.1879844427210077, | |
| "learning_rate": 4.272648599194948e-06, | |
| "loss": 0.0009, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 10.52520325203252, | |
| "grad_norm": 0.30687686213960086, | |
| "learning_rate": 4.24936597980659e-06, | |
| "loss": 0.0014, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 10.538211382113822, | |
| "grad_norm": 1.042027841255737, | |
| "learning_rate": 4.226129843041117e-06, | |
| "loss": 0.0025, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 10.551219512195122, | |
| "grad_norm": 0.24226722224286953, | |
| "learning_rate": 4.2029403767172175e-06, | |
| "loss": 0.0008, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 10.564227642276423, | |
| "grad_norm": 0.029573196433914463, | |
| "learning_rate": 4.1797977682763535e-06, | |
| "loss": 0.0003, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 10.577235772357724, | |
| "grad_norm": 0.03207686584574384, | |
| "learning_rate": 4.156702204781226e-06, | |
| "loss": 0.0003, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 10.590243902439024, | |
| "grad_norm": 0.06776985466966881, | |
| "learning_rate": 4.1336538729142716e-06, | |
| "loss": 0.0005, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 10.603252032520325, | |
| "grad_norm": 0.4331598268082103, | |
| "learning_rate": 4.110652958976151e-06, | |
| "loss": 0.0023, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 10.616260162601627, | |
| "grad_norm": 0.12176586228909014, | |
| "learning_rate": 4.087699648884248e-06, | |
| "loss": 0.0006, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 10.629268292682926, | |
| "grad_norm": 0.023639997640290365, | |
| "learning_rate": 4.06479412817115e-06, | |
| "loss": 0.0002, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 10.642276422764228, | |
| "grad_norm": 1.0793003098116523, | |
| "learning_rate": 4.041936581983171e-06, | |
| "loss": 0.0031, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 10.65528455284553, | |
| "grad_norm": 0.050689185847761324, | |
| "learning_rate": 4.019127195078848e-06, | |
| "loss": 0.0005, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 10.668292682926829, | |
| "grad_norm": 0.06105866488827697, | |
| "learning_rate": 3.996366151827438e-06, | |
| "loss": 0.0004, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 10.68130081300813, | |
| "grad_norm": 0.09274757864473174, | |
| "learning_rate": 3.973653636207437e-06, | |
| "loss": 0.0004, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 10.694308943089432, | |
| "grad_norm": 0.30895592046615056, | |
| "learning_rate": 3.950989831805083e-06, | |
| "loss": 0.0009, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 10.707317073170731, | |
| "grad_norm": 0.036528951408162195, | |
| "learning_rate": 3.9283749218128885e-06, | |
| "loss": 0.0003, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 10.720325203252033, | |
| "grad_norm": 0.2523889547985841, | |
| "learning_rate": 3.905809089028145e-06, | |
| "loss": 0.0011, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 10.733333333333333, | |
| "grad_norm": 0.06255343477291914, | |
| "learning_rate": 3.883292515851454e-06, | |
| "loss": 0.0005, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 10.746341463414634, | |
| "grad_norm": 0.0523211695671239, | |
| "learning_rate": 3.860825384285247e-06, | |
| "loss": 0.0004, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.759349593495935, | |
| "grad_norm": 0.041601465054852405, | |
| "learning_rate": 3.838407875932322e-06, | |
| "loss": 0.0004, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 10.772357723577235, | |
| "grad_norm": 0.0801657959053447, | |
| "learning_rate": 3.816040171994359e-06, | |
| "loss": 0.0006, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 10.785365853658536, | |
| "grad_norm": 0.05331580296840854, | |
| "learning_rate": 3.7937224532704752e-06, | |
| "loss": 0.0004, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 10.798373983739838, | |
| "grad_norm": 0.12791635373473556, | |
| "learning_rate": 3.7714549001557576e-06, | |
| "loss": 0.0007, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 10.811382113821137, | |
| "grad_norm": 0.367029561233173, | |
| "learning_rate": 3.7492376926397966e-06, | |
| "loss": 0.0011, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 10.824390243902439, | |
| "grad_norm": 0.059589520409157146, | |
| "learning_rate": 3.727071010305239e-06, | |
| "loss": 0.0005, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 10.83739837398374, | |
| "grad_norm": 0.08847191690003295, | |
| "learning_rate": 3.704955032326335e-06, | |
| "loss": 0.0006, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 10.85040650406504, | |
| "grad_norm": 0.1688036545392985, | |
| "learning_rate": 3.6828899374674933e-06, | |
| "loss": 0.001, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 10.863414634146341, | |
| "grad_norm": 0.04553062700432191, | |
| "learning_rate": 3.6608759040818177e-06, | |
| "loss": 0.0003, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 10.876422764227643, | |
| "grad_norm": 0.10373692909530455, | |
| "learning_rate": 3.6389131101096953e-06, | |
| "loss": 0.0005, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.889430894308942, | |
| "grad_norm": 0.15740397668819048, | |
| "learning_rate": 3.6170017330773376e-06, | |
| "loss": 0.0007, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 10.902439024390244, | |
| "grad_norm": 0.09190872520558221, | |
| "learning_rate": 3.595141950095349e-06, | |
| "loss": 0.0006, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 10.915447154471545, | |
| "grad_norm": 0.06947890757526237, | |
| "learning_rate": 3.5733339378572998e-06, | |
| "loss": 0.0004, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 10.928455284552845, | |
| "grad_norm": 0.052252610519002735, | |
| "learning_rate": 3.5515778726382967e-06, | |
| "loss": 0.0004, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 10.941463414634146, | |
| "grad_norm": 0.9351651325004157, | |
| "learning_rate": 3.529873930293546e-06, | |
| "loss": 0.0207, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 10.954471544715448, | |
| "grad_norm": 0.07147932407374252, | |
| "learning_rate": 3.508222286256955e-06, | |
| "loss": 0.0005, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 10.967479674796747, | |
| "grad_norm": 1.4479000052444952, | |
| "learning_rate": 3.4866231155396946e-06, | |
| "loss": 0.0056, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 10.980487804878049, | |
| "grad_norm": 0.24001697191680987, | |
| "learning_rate": 3.4650765927287955e-06, | |
| "loss": 0.0007, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 10.99349593495935, | |
| "grad_norm": 0.7946933804387598, | |
| "learning_rate": 3.4435828919857293e-06, | |
| "loss": 0.0023, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 11.00650406504065, | |
| "grad_norm": 0.0583487914604126, | |
| "learning_rate": 3.422142187045011e-06, | |
| "loss": 0.0004, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.019512195121951, | |
| "grad_norm": 0.0692336991994657, | |
| "learning_rate": 3.4007546512127764e-06, | |
| "loss": 0.0005, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 11.032520325203253, | |
| "grad_norm": 0.05014142713723524, | |
| "learning_rate": 3.3794204573654043e-06, | |
| "loss": 0.0004, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 11.045528455284552, | |
| "grad_norm": 0.03386760470869016, | |
| "learning_rate": 3.358139777948104e-06, | |
| "loss": 0.0003, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 11.058536585365854, | |
| "grad_norm": 0.04672681758339113, | |
| "learning_rate": 3.3369127849735237e-06, | |
| "loss": 0.0003, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 11.071544715447155, | |
| "grad_norm": 0.049940267202782294, | |
| "learning_rate": 3.3157396500203655e-06, | |
| "loss": 0.0004, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 11.084552845528455, | |
| "grad_norm": 0.18806749291579217, | |
| "learning_rate": 3.294620544231991e-06, | |
| "loss": 0.0009, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 11.097560975609756, | |
| "grad_norm": 0.04899849394667562, | |
| "learning_rate": 3.2735556383150447e-06, | |
| "loss": 0.0003, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 11.110569105691058, | |
| "grad_norm": 0.04307550472460912, | |
| "learning_rate": 3.2525451025380693e-06, | |
| "loss": 0.0004, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 11.123577235772357, | |
| "grad_norm": 0.49388859118382206, | |
| "learning_rate": 3.231589106730132e-06, | |
| "loss": 0.0076, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 11.136585365853659, | |
| "grad_norm": 0.05069730872605736, | |
| "learning_rate": 3.2106878202794513e-06, | |
| "loss": 0.0004, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 11.14959349593496, | |
| "grad_norm": 0.057858205118389204, | |
| "learning_rate": 3.1898414121320277e-06, | |
| "loss": 0.0004, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 11.16260162601626, | |
| "grad_norm": 0.029023636208937914, | |
| "learning_rate": 3.169050050790279e-06, | |
| "loss": 0.0003, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 11.175609756097561, | |
| "grad_norm": 0.03195630089651303, | |
| "learning_rate": 3.1483139043116705e-06, | |
| "loss": 0.0003, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 11.188617886178863, | |
| "grad_norm": 0.04531455132918734, | |
| "learning_rate": 3.1276331403073733e-06, | |
| "loss": 0.0004, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 11.201626016260162, | |
| "grad_norm": 0.01844463580988382, | |
| "learning_rate": 3.1070079259408934e-06, | |
| "loss": 0.0002, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 11.214634146341464, | |
| "grad_norm": 0.05339672933260151, | |
| "learning_rate": 3.086438427926729e-06, | |
| "loss": 0.0003, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 11.227642276422765, | |
| "grad_norm": 0.049322797447503446, | |
| "learning_rate": 3.06592481252902e-06, | |
| "loss": 0.0002, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 11.240650406504065, | |
| "grad_norm": 0.020868257890228357, | |
| "learning_rate": 3.0454672455602077e-06, | |
| "loss": 0.0002, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 11.253658536585366, | |
| "grad_norm": 0.024943525917216745, | |
| "learning_rate": 3.0250658923796817e-06, | |
| "loss": 0.0002, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 11.266666666666667, | |
| "grad_norm": 0.035124702260310954, | |
| "learning_rate": 3.004720917892464e-06, | |
| "loss": 0.0003, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 11.279674796747967, | |
| "grad_norm": 0.04254706825809259, | |
| "learning_rate": 2.98443248654786e-06, | |
| "loss": 0.0004, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 11.292682926829269, | |
| "grad_norm": 0.024005278793993265, | |
| "learning_rate": 2.9642007623381376e-06, | |
| "loss": 0.0002, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 11.305691056910568, | |
| "grad_norm": 1.057501147418873, | |
| "learning_rate": 2.9440259087971944e-06, | |
| "loss": 0.0057, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 11.31869918699187, | |
| "grad_norm": 0.0299414357816384, | |
| "learning_rate": 2.9239080889992454e-06, | |
| "loss": 0.0002, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 11.331707317073171, | |
| "grad_norm": 0.03690924120021281, | |
| "learning_rate": 2.90384746555749e-06, | |
| "loss": 0.0004, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 11.34471544715447, | |
| "grad_norm": 0.05208938145471617, | |
| "learning_rate": 2.883844200622816e-06, | |
| "loss": 0.0004, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 11.357723577235772, | |
| "grad_norm": 0.290281887424443, | |
| "learning_rate": 2.8638984558824777e-06, | |
| "loss": 0.0009, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 11.370731707317074, | |
| "grad_norm": 0.04915729918173791, | |
| "learning_rate": 2.8440103925587904e-06, | |
| "loss": 0.0004, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 11.383739837398373, | |
| "grad_norm": 0.06593317390602493, | |
| "learning_rate": 2.8241801714078254e-06, | |
| "loss": 0.0004, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 11.396747967479675, | |
| "grad_norm": 0.034788808154885505, | |
| "learning_rate": 2.804407952718119e-06, | |
| "loss": 0.0003, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 11.409756097560976, | |
| "grad_norm": 0.05600817228855695, | |
| "learning_rate": 2.7846938963093683e-06, | |
| "loss": 0.0004, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 11.422764227642276, | |
| "grad_norm": 0.05937485095579203, | |
| "learning_rate": 2.7650381615311384e-06, | |
| "loss": 0.0005, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 11.435772357723577, | |
| "grad_norm": 0.025121660471457082, | |
| "learning_rate": 2.745440907261582e-06, | |
| "loss": 0.0002, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 11.448780487804878, | |
| "grad_norm": 0.027086682946642057, | |
| "learning_rate": 2.7259022919061516e-06, | |
| "loss": 0.0002, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 11.461788617886178, | |
| "grad_norm": 0.03781043440974685, | |
| "learning_rate": 2.7064224733963197e-06, | |
| "loss": 0.0003, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 11.47479674796748, | |
| "grad_norm": 0.03806746386020083, | |
| "learning_rate": 2.6870016091882968e-06, | |
| "loss": 0.0003, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 11.487804878048781, | |
| "grad_norm": 0.0698792772525063, | |
| "learning_rate": 2.667639856261771e-06, | |
| "loss": 0.0004, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 11.50081300813008, | |
| "grad_norm": 0.02308277789386836, | |
| "learning_rate": 2.6483373711186213e-06, | |
| "loss": 0.0002, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 11.513821138211382, | |
| "grad_norm": 0.058620780517023637, | |
| "learning_rate": 2.629094309781669e-06, | |
| "loss": 0.0004, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 11.526829268292683, | |
| "grad_norm": 0.04634404185503362, | |
| "learning_rate": 2.6099108277934105e-06, | |
| "loss": 0.0004, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 11.539837398373983, | |
| "grad_norm": 0.02593398850907055, | |
| "learning_rate": 2.590787080214757e-06, | |
| "loss": 0.0002, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 11.552845528455284, | |
| "grad_norm": 0.027323695595300873, | |
| "learning_rate": 2.5717232216237865e-06, | |
| "loss": 0.0002, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 11.565853658536586, | |
| "grad_norm": 0.027927908013963904, | |
| "learning_rate": 2.55271940611449e-06, | |
| "loss": 0.0002, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 11.578861788617886, | |
| "grad_norm": 0.20774017342640688, | |
| "learning_rate": 2.5337757872955282e-06, | |
| "loss": 0.0004, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 11.591869918699187, | |
| "grad_norm": 0.13864879096596824, | |
| "learning_rate": 2.514892518288988e-06, | |
| "loss": 0.0007, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 11.604878048780488, | |
| "grad_norm": 0.026076672691952213, | |
| "learning_rate": 2.49606975172915e-06, | |
| "loss": 0.0002, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 11.617886178861788, | |
| "grad_norm": 0.04436392211830201, | |
| "learning_rate": 2.477307639761246e-06, | |
| "loss": 0.0004, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 11.63089430894309, | |
| "grad_norm": 0.022320285463323698, | |
| "learning_rate": 2.4586063340402412e-06, | |
| "loss": 0.0002, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 11.64390243902439, | |
| "grad_norm": 0.031220022095961104, | |
| "learning_rate": 2.43996598572959e-06, | |
| "loss": 0.0003, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 11.65691056910569, | |
| "grad_norm": 0.06035507897095567, | |
| "learning_rate": 2.421386745500034e-06, | |
| "loss": 0.0004, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 11.669918699186992, | |
| "grad_norm": 0.03710983474696094, | |
| "learning_rate": 2.4028687635283743e-06, | |
| "loss": 0.0004, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 11.682926829268293, | |
| "grad_norm": 0.049833344321699204, | |
| "learning_rate": 2.384412189496258e-06, | |
| "loss": 0.0004, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 11.695934959349593, | |
| "grad_norm": 0.06906129660585766, | |
| "learning_rate": 2.3660171725889703e-06, | |
| "loss": 0.0006, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 11.708943089430894, | |
| "grad_norm": 0.057295409850243895, | |
| "learning_rate": 2.347683861494228e-06, | |
| "loss": 0.0003, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 11.721951219512196, | |
| "grad_norm": 0.04104143179661514, | |
| "learning_rate": 2.329412404400969e-06, | |
| "loss": 0.0003, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 11.734959349593495, | |
| "grad_norm": 0.030406462955230886, | |
| "learning_rate": 2.3112029489981746e-06, | |
| "loss": 0.0003, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 11.747967479674797, | |
| "grad_norm": 0.027529253931946367, | |
| "learning_rate": 2.2930556424736574e-06, | |
| "loss": 0.0003, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 11.760975609756098, | |
| "grad_norm": 0.024338381539098602, | |
| "learning_rate": 2.274970631512878e-06, | |
| "loss": 0.0002, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 11.773983739837398, | |
| "grad_norm": 0.05105180412521588, | |
| "learning_rate": 2.2569480622977626e-06, | |
| "loss": 0.0003, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 11.7869918699187, | |
| "grad_norm": 0.04170692352890064, | |
| "learning_rate": 2.238988080505513e-06, | |
| "loss": 0.0003, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "grad_norm": 0.030129284415571365, | |
| "learning_rate": 2.221090831307441e-06, | |
| "loss": 0.0003, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 11.8130081300813, | |
| "grad_norm": 0.053205067060277646, | |
| "learning_rate": 2.2032564593677773e-06, | |
| "loss": 0.0004, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 11.826016260162602, | |
| "grad_norm": 0.04196901029871406, | |
| "learning_rate": 2.1854851088425245e-06, | |
| "loss": 0.0003, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 11.839024390243903, | |
| "grad_norm": 1.6008115113288401, | |
| "learning_rate": 2.167776923378274e-06, | |
| "loss": 0.003, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 11.852032520325203, | |
| "grad_norm": 0.08179428627670947, | |
| "learning_rate": 2.150132046111054e-06, | |
| "loss": 0.0006, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 11.865040650406504, | |
| "grad_norm": 0.045901122815486736, | |
| "learning_rate": 2.132550619665168e-06, | |
| "loss": 0.0004, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 11.878048780487806, | |
| "grad_norm": 0.04273976044021606, | |
| "learning_rate": 2.115032786152047e-06, | |
| "loss": 0.0003, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 11.891056910569105, | |
| "grad_norm": 0.03487722679277039, | |
| "learning_rate": 2.0975786871690897e-06, | |
| "loss": 0.0003, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 11.904065040650407, | |
| "grad_norm": 0.040993841061677555, | |
| "learning_rate": 2.0801884637985337e-06, | |
| "loss": 0.0003, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 11.917073170731708, | |
| "grad_norm": 0.048500935037488466, | |
| "learning_rate": 2.0628622566063063e-06, | |
| "loss": 0.0004, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 11.930081300813008, | |
| "grad_norm": 0.04576348639630146, | |
| "learning_rate": 2.045600205640885e-06, | |
| "loss": 0.0004, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 11.94308943089431, | |
| "grad_norm": 0.02565353345548741, | |
| "learning_rate": 2.0284024504321754e-06, | |
| "loss": 0.0002, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 11.95609756097561, | |
| "grad_norm": 0.04584969030642572, | |
| "learning_rate": 2.011269129990376e-06, | |
| "loss": 0.0004, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 11.96910569105691, | |
| "grad_norm": 0.19179968524650484, | |
| "learning_rate": 1.9942003828048497e-06, | |
| "loss": 0.0008, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 11.982113821138212, | |
| "grad_norm": 0.04706427979351206, | |
| "learning_rate": 1.977196346843019e-06, | |
| "loss": 0.0003, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 11.995121951219513, | |
| "grad_norm": 0.027584453796653467, | |
| "learning_rate": 1.960257159549238e-06, | |
| "loss": 0.0003, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 12.008130081300813, | |
| "grad_norm": 0.03077492388241451, | |
| "learning_rate": 1.9433829578436937e-06, | |
| "loss": 0.0003, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 12.021138211382114, | |
| "grad_norm": 0.04214761267907801, | |
| "learning_rate": 1.926573878121286e-06, | |
| "loss": 0.0004, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 12.034146341463414, | |
| "grad_norm": 0.04821007473769064, | |
| "learning_rate": 1.9098300562505266e-06, | |
| "loss": 0.0004, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 12.047154471544715, | |
| "grad_norm": 0.04150457101156769, | |
| "learning_rate": 1.8931516275724527e-06, | |
| "loss": 0.0004, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 12.060162601626017, | |
| "grad_norm": 0.02300453156783074, | |
| "learning_rate": 1.8765387268995217e-06, | |
| "loss": 0.0002, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 12.073170731707316, | |
| "grad_norm": 0.060825220544094435, | |
| "learning_rate": 1.8599914885145287e-06, | |
| "loss": 0.0004, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 12.086178861788618, | |
| "grad_norm": 0.03260378620826329, | |
| "learning_rate": 1.8435100461695131e-06, | |
| "loss": 0.0002, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 12.099186991869919, | |
| "grad_norm": 0.062443505010852336, | |
| "learning_rate": 1.8270945330846868e-06, | |
| "loss": 0.0003, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 12.112195121951219, | |
| "grad_norm": 0.04336228230253458, | |
| "learning_rate": 1.8107450819473505e-06, | |
| "loss": 0.0004, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 12.12520325203252, | |
| "grad_norm": 0.02709980396856279, | |
| "learning_rate": 1.7944618249108204e-06, | |
| "loss": 0.0002, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 12.138211382113822, | |
| "grad_norm": 0.03262436647450725, | |
| "learning_rate": 1.7782448935933649e-06, | |
| "loss": 0.0003, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 12.151219512195121, | |
| "grad_norm": 0.029557746567540205, | |
| "learning_rate": 1.7620944190771427e-06, | |
| "loss": 0.0003, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 12.164227642276423, | |
| "grad_norm": 0.012624259598801554, | |
| "learning_rate": 1.7460105319071353e-06, | |
| "loss": 0.0001, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 12.177235772357724, | |
| "grad_norm": 0.02914506084362277, | |
| "learning_rate": 1.7299933620900945e-06, | |
| "loss": 0.0003, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 12.190243902439024, | |
| "grad_norm": 0.039341397329373785, | |
| "learning_rate": 1.7140430390935003e-06, | |
| "loss": 0.0003, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 12.203252032520325, | |
| "grad_norm": 0.03480900877050601, | |
| "learning_rate": 1.6981596918444953e-06, | |
| "loss": 0.0003, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 12.216260162601627, | |
| "grad_norm": 0.01844993284555088, | |
| "learning_rate": 1.6823434487288626e-06, | |
| "loss": 0.0002, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 12.229268292682926, | |
| "grad_norm": 0.11082080083206294, | |
| "learning_rate": 1.6665944375899778e-06, | |
| "loss": 0.0004, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 12.242276422764228, | |
| "grad_norm": 0.02963595573823533, | |
| "learning_rate": 1.6509127857277784e-06, | |
| "loss": 0.0003, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 12.255284552845529, | |
| "grad_norm": 0.015490232540061447, | |
| "learning_rate": 1.6352986198977327e-06, | |
| "loss": 0.0002, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 12.268292682926829, | |
| "grad_norm": 0.036946837222196494, | |
| "learning_rate": 1.6197520663098177e-06, | |
| "loss": 0.0003, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 12.28130081300813, | |
| "grad_norm": 0.03689703560791502, | |
| "learning_rate": 1.6042732506274939e-06, | |
| "loss": 0.0003, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 12.294308943089431, | |
| "grad_norm": 0.01671065249876302, | |
| "learning_rate": 1.5888622979666978e-06, | |
| "loss": 0.0002, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 12.307317073170731, | |
| "grad_norm": 0.0296538420513258, | |
| "learning_rate": 1.573519332894824e-06, | |
| "loss": 0.0002, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 12.320325203252033, | |
| "grad_norm": 0.04370373558297985, | |
| "learning_rate": 1.5582444794297225e-06, | |
| "loss": 0.0002, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 12.333333333333334, | |
| "grad_norm": 0.03131885362602231, | |
| "learning_rate": 1.5430378610386909e-06, | |
| "loss": 0.0003, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 12.346341463414634, | |
| "grad_norm": 0.023644097457454247, | |
| "learning_rate": 1.5278996006374836e-06, | |
| "loss": 0.0002, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 12.359349593495935, | |
| "grad_norm": 0.028851288419968788, | |
| "learning_rate": 1.5128298205893144e-06, | |
| "loss": 0.0003, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 12.372357723577236, | |
| "grad_norm": 0.04344181321072099, | |
| "learning_rate": 1.4978286427038602e-06, | |
| "loss": 0.0004, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 12.385365853658536, | |
| "grad_norm": 0.031081718820231443, | |
| "learning_rate": 1.4828961882362925e-06, | |
| "loss": 0.0003, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 12.398373983739837, | |
| "grad_norm": 0.07692321943678358, | |
| "learning_rate": 1.4680325778862837e-06, | |
| "loss": 0.0007, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 12.411382113821139, | |
| "grad_norm": 0.03840200029078006, | |
| "learning_rate": 1.453237931797038e-06, | |
| "loss": 0.0003, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 12.424390243902439, | |
| "grad_norm": 0.02915687708744816, | |
| "learning_rate": 1.438512369554318e-06, | |
| "loss": 0.0002, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 12.43739837398374, | |
| "grad_norm": 0.027722748555523046, | |
| "learning_rate": 1.4238560101854815e-06, | |
| "loss": 0.0002, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 12.450406504065041, | |
| "grad_norm": 0.027711461854685253, | |
| "learning_rate": 1.4092689721585052e-06, | |
| "loss": 0.0002, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 12.463414634146341, | |
| "grad_norm": 0.026400138369060966, | |
| "learning_rate": 1.3947513733810558e-06, | |
| "loss": 0.0002, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 12.476422764227642, | |
| "grad_norm": 0.021296063658237975, | |
| "learning_rate": 1.3803033311995072e-06, | |
| "loss": 0.0002, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 12.489430894308944, | |
| "grad_norm": 0.04158455168487558, | |
| "learning_rate": 1.3659249623980075e-06, | |
| "loss": 0.0004, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 12.502439024390243, | |
| "grad_norm": 0.019533591657485316, | |
| "learning_rate": 1.3516163831975337e-06, | |
| "loss": 0.0002, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 12.515447154471545, | |
| "grad_norm": 0.023537015844786686, | |
| "learning_rate": 1.3373777092549455e-06, | |
| "loss": 0.0002, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 12.528455284552846, | |
| "grad_norm": 0.05740585106163819, | |
| "learning_rate": 1.3232090556620602e-06, | |
| "loss": 0.0005, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 12.541463414634146, | |
| "grad_norm": 0.03835919042582948, | |
| "learning_rate": 1.3091105369447166e-06, | |
| "loss": 0.0003, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 12.554471544715447, | |
| "grad_norm": 0.035260013086723926, | |
| "learning_rate": 1.2950822670618491e-06, | |
| "loss": 0.0003, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 12.567479674796749, | |
| "grad_norm": 0.12128345095801041, | |
| "learning_rate": 1.2811243594045697e-06, | |
| "loss": 0.0006, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 12.580487804878048, | |
| "grad_norm": 0.036532423074067316, | |
| "learning_rate": 1.2672369267952477e-06, | |
| "loss": 0.0002, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 12.59349593495935, | |
| "grad_norm": 0.03536480393863221, | |
| "learning_rate": 1.2534200814865993e-06, | |
| "loss": 0.0003, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 12.60650406504065, | |
| "grad_norm": 0.053240533731360416, | |
| "learning_rate": 1.23967393516078e-06, | |
| "loss": 0.0004, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 12.61951219512195, | |
| "grad_norm": 0.06059259370599514, | |
| "learning_rate": 1.2259985989284851e-06, | |
| "loss": 0.0004, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 12.632520325203252, | |
| "grad_norm": 0.039793466812882275, | |
| "learning_rate": 1.2123941833280472e-06, | |
| "loss": 0.0003, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 12.645528455284552, | |
| "grad_norm": 0.033625877863249394, | |
| "learning_rate": 1.198860798324546e-06, | |
| "loss": 0.0003, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 12.658536585365853, | |
| "grad_norm": 0.03217111320212353, | |
| "learning_rate": 1.185398553308915e-06, | |
| "loss": 0.0003, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 12.671544715447155, | |
| "grad_norm": 0.028764585766712494, | |
| "learning_rate": 1.1720075570970602e-06, | |
| "loss": 0.0002, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 12.684552845528454, | |
| "grad_norm": 0.029641836079438693, | |
| "learning_rate": 1.1586879179289833e-06, | |
| "loss": 0.0002, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 12.697560975609756, | |
| "grad_norm": 0.03960907206585507, | |
| "learning_rate": 1.1454397434679022e-06, | |
| "loss": 0.0003, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 12.710569105691057, | |
| "grad_norm": 0.023863283321871376, | |
| "learning_rate": 1.132263140799381e-06, | |
| "loss": 0.0002, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 12.723577235772357, | |
| "grad_norm": 0.05328446969958965, | |
| "learning_rate": 1.1191582164304705e-06, | |
| "loss": 0.0003, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 12.736585365853658, | |
| "grad_norm": 0.03669637650871495, | |
| "learning_rate": 1.1061250762888365e-06, | |
| "loss": 0.0003, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 12.74959349593496, | |
| "grad_norm": 0.032997154354977465, | |
| "learning_rate": 1.0931638257219179e-06, | |
| "loss": 0.0003, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 12.76260162601626, | |
| "grad_norm": 0.04054662663680875, | |
| "learning_rate": 1.080274569496057e-06, | |
| "loss": 0.0003, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 12.77560975609756, | |
| "grad_norm": 0.035856685677166364, | |
| "learning_rate": 1.0674574117956692e-06, | |
| "loss": 0.0003, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 12.788617886178862, | |
| "grad_norm": 0.04172495614914336, | |
| "learning_rate": 1.0547124562223943e-06, | |
| "loss": 0.0003, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 12.801626016260162, | |
| "grad_norm": 0.019580427416265797, | |
| "learning_rate": 1.0420398057942581e-06, | |
| "loss": 0.0002, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 12.814634146341463, | |
| "grad_norm": 0.03740389694894794, | |
| "learning_rate": 1.0294395629448394e-06, | |
| "loss": 0.0003, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 12.827642276422765, | |
| "grad_norm": 0.031803134224532056, | |
| "learning_rate": 1.0169118295224488e-06, | |
| "loss": 0.0003, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 12.840650406504064, | |
| "grad_norm": 0.03032456276841443, | |
| "learning_rate": 1.0044567067892896e-06, | |
| "loss": 0.0003, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 12.853658536585366, | |
| "grad_norm": 0.02199024409508468, | |
| "learning_rate": 9.920742954206607e-07, | |
| "loss": 0.0002, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 12.866666666666667, | |
| "grad_norm": 0.031972722797786526, | |
| "learning_rate": 9.79764695504125e-07, | |
| "loss": 0.0003, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 12.879674796747967, | |
| "grad_norm": 0.027213042256643855, | |
| "learning_rate": 9.675280065387117e-07, | |
| "loss": 0.0002, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 12.892682926829268, | |
| "grad_norm": 0.08563731214364351, | |
| "learning_rate": 9.55364327434105e-07, | |
| "loss": 0.0004, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 12.90569105691057, | |
| "grad_norm": 0.03366232448582257, | |
| "learning_rate": 9.43273756509847e-07, | |
| "loss": 0.0003, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 12.91869918699187, | |
| "grad_norm": 0.014805009601497832, | |
| "learning_rate": 9.312563914945461e-07, | |
| "loss": 0.0001, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 12.93170731707317, | |
| "grad_norm": 0.050176526307846074, | |
| "learning_rate": 9.193123295250794e-07, | |
| "loss": 0.0003, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 12.944715447154472, | |
| "grad_norm": 0.017531712275581913, | |
| "learning_rate": 9.074416671458175e-07, | |
| "loss": 0.0002, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 12.957723577235772, | |
| "grad_norm": 0.04029991292115628, | |
| "learning_rate": 8.956445003078351e-07, | |
| "loss": 0.0003, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 12.970731707317073, | |
| "grad_norm": 0.03487711795800321, | |
| "learning_rate": 8.839209243681435e-07, | |
| "loss": 0.0003, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 12.983739837398375, | |
| "grad_norm": 0.06273158241583285, | |
| "learning_rate": 8.722710340889074e-07, | |
| "loss": 0.0005, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 12.996747967479674, | |
| "grad_norm": 0.01994697874973447, | |
| "learning_rate": 8.606949236366969e-07, | |
| "loss": 0.0002, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 13.009756097560976, | |
| "grad_norm": 0.02549053991207511, | |
| "learning_rate": 8.491926865817113e-07, | |
| "loss": 0.0002, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 13.022764227642277, | |
| "grad_norm": 0.0307980889762381, | |
| "learning_rate": 8.377644158970277e-07, | |
| "loss": 0.0003, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 13.035772357723577, | |
| "grad_norm": 0.023649380232462637, | |
| "learning_rate": 8.264102039578526e-07, | |
| "loss": 0.0002, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 13.048780487804878, | |
| "grad_norm": 0.020221083840776814, | |
| "learning_rate": 8.151301425407699e-07, | |
| "loss": 0.0002, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 13.06178861788618, | |
| "grad_norm": 0.03926025654030983, | |
| "learning_rate": 8.039243228230043e-07, | |
| "loss": 0.0003, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 13.07479674796748, | |
| "grad_norm": 0.020449515371978706, | |
| "learning_rate": 7.927928353816782e-07, | |
| "loss": 0.0002, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 13.08780487804878, | |
| "grad_norm": 0.02932084253359567, | |
| "learning_rate": 7.81735770193085e-07, | |
| "loss": 0.0003, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 13.100813008130082, | |
| "grad_norm": 0.024112902281580206, | |
| "learning_rate": 7.707532166319598e-07, | |
| "loss": 0.0002, | |
| "step": 1001 | |
| }, | |
| { | |
| "epoch": 13.113821138211382, | |
| "grad_norm": 0.025977086642222053, | |
| "learning_rate": 7.598452634707576e-07, | |
| "loss": 0.0003, | |
| "step": 1002 | |
| }, | |
| { | |
| "epoch": 13.126829268292683, | |
| "grad_norm": 0.03171766941376975, | |
| "learning_rate": 7.490119988789346e-07, | |
| "loss": 0.0002, | |
| "step": 1003 | |
| }, | |
| { | |
| "epoch": 13.139837398373984, | |
| "grad_norm": 0.024337316023638367, | |
| "learning_rate": 7.382535104222366e-07, | |
| "loss": 0.0002, | |
| "step": 1004 | |
| }, | |
| { | |
| "epoch": 13.152845528455284, | |
| "grad_norm": 0.029670754329652924, | |
| "learning_rate": 7.275698850619861e-07, | |
| "loss": 0.0003, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 13.165853658536586, | |
| "grad_norm": 0.03834238404585399, | |
| "learning_rate": 7.169612091543909e-07, | |
| "loss": 0.0003, | |
| "step": 1006 | |
| }, | |
| { | |
| "epoch": 13.178861788617887, | |
| "grad_norm": 0.034469653100517236, | |
| "learning_rate": 7.064275684498357e-07, | |
| "loss": 0.0003, | |
| "step": 1007 | |
| }, | |
| { | |
| "epoch": 13.191869918699187, | |
| "grad_norm": 0.031749002558175, | |
| "learning_rate": 6.959690480921922e-07, | |
| "loss": 0.0003, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 13.204878048780488, | |
| "grad_norm": 0.025417220142589323, | |
| "learning_rate": 6.855857326181315e-07, | |
| "loss": 0.0002, | |
| "step": 1009 | |
| }, | |
| { | |
| "epoch": 13.21788617886179, | |
| "grad_norm": 0.06077297341714978, | |
| "learning_rate": 6.752777059564431e-07, | |
| "loss": 0.0005, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 13.230894308943089, | |
| "grad_norm": 0.05072001838936607, | |
| "learning_rate": 6.650450514273476e-07, | |
| "loss": 0.0004, | |
| "step": 1011 | |
| }, | |
| { | |
| "epoch": 13.24390243902439, | |
| "grad_norm": 0.03387119754903101, | |
| "learning_rate": 6.548878517418345e-07, | |
| "loss": 0.0003, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 13.256910569105692, | |
| "grad_norm": 0.10756327605409695, | |
| "learning_rate": 6.448061890009872e-07, | |
| "loss": 0.0006, | |
| "step": 1013 | |
| }, | |
| { | |
| "epoch": 13.269918699186992, | |
| "grad_norm": 0.029678540021646233, | |
| "learning_rate": 6.348001446953201e-07, | |
| "loss": 0.0002, | |
| "step": 1014 | |
| }, | |
| { | |
| "epoch": 13.282926829268293, | |
| "grad_norm": 0.04013972159611284, | |
| "learning_rate": 6.248697997041219e-07, | |
| "loss": 0.0003, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 13.295934959349594, | |
| "grad_norm": 0.019077151556142806, | |
| "learning_rate": 6.15015234294799e-07, | |
| "loss": 0.0002, | |
| "step": 1016 | |
| }, | |
| { | |
| "epoch": 13.308943089430894, | |
| "grad_norm": 0.016650919618137604, | |
| "learning_rate": 6.052365281222306e-07, | |
| "loss": 0.0001, | |
| "step": 1017 | |
| }, | |
| { | |
| "epoch": 13.321951219512195, | |
| "grad_norm": 0.020689154219598792, | |
| "learning_rate": 5.955337602281164e-07, | |
| "loss": 0.0001, | |
| "step": 1018 | |
| }, | |
| { | |
| "epoch": 13.334959349593497, | |
| "grad_norm": 0.024136957498527598, | |
| "learning_rate": 5.859070090403507e-07, | |
| "loss": 0.0002, | |
| "step": 1019 | |
| }, | |
| { | |
| "epoch": 13.347967479674796, | |
| "grad_norm": 0.029919824327203366, | |
| "learning_rate": 5.763563523723769e-07, | |
| "loss": 0.0002, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 13.360975609756098, | |
| "grad_norm": 0.034164027668019015, | |
| "learning_rate": 5.668818674225684e-07, | |
| "loss": 0.0003, | |
| "step": 1021 | |
| }, | |
| { | |
| "epoch": 13.373983739837398, | |
| "grad_norm": 0.02468655474347108, | |
| "learning_rate": 5.574836307735942e-07, | |
| "loss": 0.0002, | |
| "step": 1022 | |
| }, | |
| { | |
| "epoch": 13.386991869918699, | |
| "grad_norm": 0.043140945132677466, | |
| "learning_rate": 5.481617183918053e-07, | |
| "loss": 0.0004, | |
| "step": 1023 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "grad_norm": 0.03878222674386918, | |
| "learning_rate": 5.389162056266217e-07, | |
| "loss": 0.0003, | |
| "step": 1024 | |
| }, | |
| { | |
| "epoch": 13.4130081300813, | |
| "grad_norm": 0.025044038832899608, | |
| "learning_rate": 5.29747167209923e-07, | |
| "loss": 0.0003, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 13.426016260162601, | |
| "grad_norm": 0.019828237699485142, | |
| "learning_rate": 5.206546772554421e-07, | |
| "loss": 0.0001, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 13.439024390243903, | |
| "grad_norm": 0.021879669223526684, | |
| "learning_rate": 5.11638809258167e-07, | |
| "loss": 0.0002, | |
| "step": 1027 | |
| }, | |
| { | |
| "epoch": 13.452032520325202, | |
| "grad_norm": 0.03618577826106415, | |
| "learning_rate": 5.026996360937497e-07, | |
| "loss": 0.0003, | |
| "step": 1028 | |
| }, | |
| { | |
| "epoch": 13.465040650406504, | |
| "grad_norm": 0.060859060269609425, | |
| "learning_rate": 4.938372300179095e-07, | |
| "loss": 0.0004, | |
| "step": 1029 | |
| }, | |
| { | |
| "epoch": 13.478048780487805, | |
| "grad_norm": 0.022248539562761523, | |
| "learning_rate": 4.850516626658585e-07, | |
| "loss": 0.0002, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 13.491056910569105, | |
| "grad_norm": 0.017508560411216564, | |
| "learning_rate": 4.7634300505171706e-07, | |
| "loss": 0.0002, | |
| "step": 1031 | |
| }, | |
| { | |
| "epoch": 13.504065040650406, | |
| "grad_norm": 0.030861709855513904, | |
| "learning_rate": 4.6771132756794014e-07, | |
| "loss": 0.0003, | |
| "step": 1032 | |
| }, | |
| { | |
| "epoch": 13.517073170731708, | |
| "grad_norm": 0.031550978453916724, | |
| "learning_rate": 4.591566999847485e-07, | |
| "loss": 0.0003, | |
| "step": 1033 | |
| }, | |
| { | |
| "epoch": 13.530081300813007, | |
| "grad_norm": 0.019490216675892496, | |
| "learning_rate": 4.5067919144956786e-07, | |
| "loss": 0.0002, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 13.543089430894309, | |
| "grad_norm": 0.018780461745252785, | |
| "learning_rate": 4.4227887048646335e-07, | |
| "loss": 0.0002, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 13.55609756097561, | |
| "grad_norm": 0.023017234749854912, | |
| "learning_rate": 4.3395580499559276e-07, | |
| "loss": 0.0002, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 13.56910569105691, | |
| "grad_norm": 0.04625964724403267, | |
| "learning_rate": 4.257100622526522e-07, | |
| "loss": 0.0003, | |
| "step": 1037 | |
| }, | |
| { | |
| "epoch": 13.582113821138211, | |
| "grad_norm": 0.021183619605396154, | |
| "learning_rate": 4.1754170890833777e-07, | |
| "loss": 0.0002, | |
| "step": 1038 | |
| }, | |
| { | |
| "epoch": 13.595121951219513, | |
| "grad_norm": 0.019814070943899136, | |
| "learning_rate": 4.094508109878015e-07, | |
| "loss": 0.0002, | |
| "step": 1039 | |
| }, | |
| { | |
| "epoch": 13.608130081300812, | |
| "grad_norm": 0.10482935924047573, | |
| "learning_rate": 4.014374338901206e-07, | |
| "loss": 0.0005, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 13.621138211382114, | |
| "grad_norm": 0.029873361045492864, | |
| "learning_rate": 3.935016423877669e-07, | |
| "loss": 0.0002, | |
| "step": 1041 | |
| }, | |
| { | |
| "epoch": 13.634146341463415, | |
| "grad_norm": 0.026330571763574936, | |
| "learning_rate": 3.8564350062608614e-07, | |
| "loss": 0.0003, | |
| "step": 1042 | |
| }, | |
| { | |
| "epoch": 13.647154471544715, | |
| "grad_norm": 0.04793123621711193, | |
| "learning_rate": 3.7786307212277605e-07, | |
| "loss": 0.0004, | |
| "step": 1043 | |
| }, | |
| { | |
| "epoch": 13.660162601626016, | |
| "grad_norm": 0.029028943314858512, | |
| "learning_rate": 3.7016041976737803e-07, | |
| "loss": 0.0002, | |
| "step": 1044 | |
| }, | |
| { | |
| "epoch": 13.673170731707318, | |
| "grad_norm": 0.015808414804027004, | |
| "learning_rate": 3.6253560582076075e-07, | |
| "loss": 0.0001, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 13.686178861788617, | |
| "grad_norm": 0.04926046336983506, | |
| "learning_rate": 3.549886919146273e-07, | |
| "loss": 0.0004, | |
| "step": 1046 | |
| }, | |
| { | |
| "epoch": 13.699186991869919, | |
| "grad_norm": 0.019757178400023927, | |
| "learning_rate": 3.4751973905100656e-07, | |
| "loss": 0.0002, | |
| "step": 1047 | |
| }, | |
| { | |
| "epoch": 13.71219512195122, | |
| "grad_norm": 0.02129644550912768, | |
| "learning_rate": 3.4012880760176723e-07, | |
| "loss": 0.0002, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 13.72520325203252, | |
| "grad_norm": 0.03242801353349851, | |
| "learning_rate": 3.328159573081258e-07, | |
| "loss": 0.0003, | |
| "step": 1049 | |
| }, | |
| { | |
| "epoch": 13.738211382113821, | |
| "grad_norm": 0.02075180131439445, | |
| "learning_rate": 3.255812472801689e-07, | |
| "loss": 0.0002, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.751219512195123, | |
| "grad_norm": 0.036189659636635424, | |
| "learning_rate": 3.184247359963677e-07, | |
| "loss": 0.0003, | |
| "step": 1051 | |
| }, | |
| { | |
| "epoch": 13.764227642276422, | |
| "grad_norm": 0.038577208451691616, | |
| "learning_rate": 3.1134648130311305e-07, | |
| "loss": 0.0003, | |
| "step": 1052 | |
| }, | |
| { | |
| "epoch": 13.777235772357724, | |
| "grad_norm": 0.019578026825799153, | |
| "learning_rate": 3.0434654041424315e-07, | |
| "loss": 0.0002, | |
| "step": 1053 | |
| }, | |
| { | |
| "epoch": 13.790243902439025, | |
| "grad_norm": 0.038217555100736766, | |
| "learning_rate": 2.974249699105802e-07, | |
| "loss": 0.0003, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 13.803252032520325, | |
| "grad_norm": 0.037397444857588134, | |
| "learning_rate": 2.905818257394799e-07, | |
| "loss": 0.0002, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 13.816260162601626, | |
| "grad_norm": 0.016900876285998463, | |
| "learning_rate": 2.8381716321436936e-07, | |
| "loss": 0.0001, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 13.829268292682928, | |
| "grad_norm": 0.0203693368004702, | |
| "learning_rate": 2.771310370143099e-07, | |
| "loss": 0.0002, | |
| "step": 1057 | |
| }, | |
| { | |
| "epoch": 13.842276422764227, | |
| "grad_norm": 0.016405347132121117, | |
| "learning_rate": 2.705235011835472e-07, | |
| "loss": 0.0002, | |
| "step": 1058 | |
| }, | |
| { | |
| "epoch": 13.855284552845529, | |
| "grad_norm": 0.025549581414522154, | |
| "learning_rate": 2.639946091310786e-07, | |
| "loss": 0.0002, | |
| "step": 1059 | |
| }, | |
| { | |
| "epoch": 13.86829268292683, | |
| "grad_norm": 0.04227039234601936, | |
| "learning_rate": 2.5754441363021854e-07, | |
| "loss": 0.0004, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 13.88130081300813, | |
| "grad_norm": 0.02941832608756205, | |
| "learning_rate": 2.511729668181773e-07, | |
| "loss": 0.0003, | |
| "step": 1061 | |
| }, | |
| { | |
| "epoch": 13.894308943089431, | |
| "grad_norm": 0.023422564676835966, | |
| "learning_rate": 2.44880320195634e-07, | |
| "loss": 0.0002, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 13.907317073170733, | |
| "grad_norm": 0.027871785358745793, | |
| "learning_rate": 2.38666524626322e-07, | |
| "loss": 0.0002, | |
| "step": 1063 | |
| }, | |
| { | |
| "epoch": 13.920325203252032, | |
| "grad_norm": 0.02968460669625177, | |
| "learning_rate": 2.3253163033662097e-07, | |
| "loss": 0.0002, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 13.933333333333334, | |
| "grad_norm": 0.0565129740043272, | |
| "learning_rate": 2.264756869151441e-07, | |
| "loss": 0.0005, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 13.946341463414633, | |
| "grad_norm": 0.018101006672774193, | |
| "learning_rate": 2.2049874331234289e-07, | |
| "loss": 0.0002, | |
| "step": 1066 | |
| }, | |
| { | |
| "epoch": 13.959349593495935, | |
| "grad_norm": 0.045688843343597706, | |
| "learning_rate": 2.1460084784011293e-07, | |
| "loss": 0.0003, | |
| "step": 1067 | |
| }, | |
| { | |
| "epoch": 13.972357723577236, | |
| "grad_norm": 0.05940289947656419, | |
| "learning_rate": 2.0878204817139536e-07, | |
| "loss": 0.0003, | |
| "step": 1068 | |
| }, | |
| { | |
| "epoch": 13.985365853658536, | |
| "grad_norm": 0.021621769556400938, | |
| "learning_rate": 2.0304239133980052e-07, | |
| "loss": 0.0002, | |
| "step": 1069 | |
| }, | |
| { | |
| "epoch": 13.998373983739837, | |
| "grad_norm": 0.02309363700179012, | |
| "learning_rate": 1.973819237392205e-07, | |
| "loss": 0.0002, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 14.011382113821139, | |
| "grad_norm": 0.027500933714689976, | |
| "learning_rate": 1.9180069112346157e-07, | |
| "loss": 0.0003, | |
| "step": 1071 | |
| }, | |
| { | |
| "epoch": 14.024390243902438, | |
| "grad_norm": 0.030244307231598946, | |
| "learning_rate": 1.8629873860586567e-07, | |
| "loss": 0.0002, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 14.03739837398374, | |
| "grad_norm": 0.03019993808409305, | |
| "learning_rate": 1.8087611065895295e-07, | |
| "loss": 0.0002, | |
| "step": 1073 | |
| }, | |
| { | |
| "epoch": 14.050406504065041, | |
| "grad_norm": 0.031140680127246946, | |
| "learning_rate": 1.755328511140597e-07, | |
| "loss": 0.0003, | |
| "step": 1074 | |
| }, | |
| { | |
| "epoch": 14.06341463414634, | |
| "grad_norm": 0.04172006896705525, | |
| "learning_rate": 1.7026900316098217e-07, | |
| "loss": 0.0003, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 14.076422764227642, | |
| "grad_norm": 0.025305355483100058, | |
| "learning_rate": 1.6508460934763104e-07, | |
| "loss": 0.0002, | |
| "step": 1076 | |
| }, | |
| { | |
| "epoch": 14.089430894308943, | |
| "grad_norm": 0.06505527132645876, | |
| "learning_rate": 1.599797115796864e-07, | |
| "loss": 0.0003, | |
| "step": 1077 | |
| }, | |
| { | |
| "epoch": 14.102439024390243, | |
| "grad_norm": 0.021875170909544356, | |
| "learning_rate": 1.549543511202556e-07, | |
| "loss": 0.0002, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 14.115447154471545, | |
| "grad_norm": 0.028820932133379662, | |
| "learning_rate": 1.500085685895436e-07, | |
| "loss": 0.0002, | |
| "step": 1079 | |
| }, | |
| { | |
| "epoch": 14.128455284552846, | |
| "grad_norm": 0.06547214698811654, | |
| "learning_rate": 1.4514240396452438e-07, | |
| "loss": 0.0005, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 14.141463414634146, | |
| "grad_norm": 0.022084226183417356, | |
| "learning_rate": 1.4035589657861782e-07, | |
| "loss": 0.0002, | |
| "step": 1081 | |
| }, | |
| { | |
| "epoch": 14.154471544715447, | |
| "grad_norm": 0.030501794381445683, | |
| "learning_rate": 1.3564908512136877e-07, | |
| "loss": 0.0003, | |
| "step": 1082 | |
| }, | |
| { | |
| "epoch": 14.167479674796748, | |
| "grad_norm": 0.05544690283648963, | |
| "learning_rate": 1.3102200763813744e-07, | |
| "loss": 0.0004, | |
| "step": 1083 | |
| }, | |
| { | |
| "epoch": 14.180487804878048, | |
| "grad_norm": 0.024801402394138795, | |
| "learning_rate": 1.2647470152979068e-07, | |
| "loss": 0.0002, | |
| "step": 1084 | |
| }, | |
| { | |
| "epoch": 14.19349593495935, | |
| "grad_norm": 0.02667042819572207, | |
| "learning_rate": 1.2200720355239893e-07, | |
| "loss": 0.0002, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 14.20650406504065, | |
| "grad_norm": 0.0285111878316447, | |
| "learning_rate": 1.1761954981694301e-07, | |
| "loss": 0.0003, | |
| "step": 1086 | |
| }, | |
| { | |
| "epoch": 14.21951219512195, | |
| "grad_norm": 0.019804417639668098, | |
| "learning_rate": 1.1331177578901564e-07, | |
| "loss": 0.0002, | |
| "step": 1087 | |
| }, | |
| { | |
| "epoch": 14.232520325203252, | |
| "grad_norm": 0.01747656276935746, | |
| "learning_rate": 1.0908391628854042e-07, | |
| "loss": 0.0001, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 14.245528455284553, | |
| "grad_norm": 0.02058245422053517, | |
| "learning_rate": 1.0493600548948879e-07, | |
| "loss": 0.0002, | |
| "step": 1089 | |
| }, | |
| { | |
| "epoch": 14.258536585365853, | |
| "grad_norm": 0.03829122889093893, | |
| "learning_rate": 1.0086807691960243e-07, | |
| "loss": 0.0003, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 14.271544715447154, | |
| "grad_norm": 0.03158787600436918, | |
| "learning_rate": 9.688016346012463e-08, | |
| "loss": 0.0003, | |
| "step": 1091 | |
| }, | |
| { | |
| "epoch": 14.284552845528456, | |
| "grad_norm": 0.01894562834232925, | |
| "learning_rate": 9.297229734552937e-08, | |
| "loss": 0.0002, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 14.297560975609755, | |
| "grad_norm": 0.039139900460036486, | |
| "learning_rate": 8.914451016326931e-08, | |
| "loss": 0.0003, | |
| "step": 1093 | |
| }, | |
| { | |
| "epoch": 14.310569105691057, | |
| "grad_norm": 0.02194935008727504, | |
| "learning_rate": 8.539683285351152e-08, | |
| "loss": 0.0002, | |
| "step": 1094 | |
| }, | |
| { | |
| "epoch": 14.323577235772358, | |
| "grad_norm": 0.0316393239011527, | |
| "learning_rate": 8.172929570889553e-08, | |
| "loss": 0.0003, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 14.336585365853658, | |
| "grad_norm": 0.04169887849957978, | |
| "learning_rate": 7.814192837428126e-08, | |
| "loss": 0.0004, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 14.34959349593496, | |
| "grad_norm": 0.02965671174590213, | |
| "learning_rate": 7.463475984651248e-08, | |
| "loss": 0.0003, | |
| "step": 1097 | |
| }, | |
| { | |
| "epoch": 14.36260162601626, | |
| "grad_norm": 0.04111474695069758, | |
| "learning_rate": 7.12078184741849e-08, | |
| "loss": 0.0003, | |
| "step": 1098 | |
| }, | |
| { | |
| "epoch": 14.37560975609756, | |
| "grad_norm": 0.04266172001967759, | |
| "learning_rate": 6.786113195741406e-08, | |
| "loss": 0.0004, | |
| "step": 1099 | |
| }, | |
| { | |
| "epoch": 14.388617886178862, | |
| "grad_norm": 0.019013161463080158, | |
| "learning_rate": 6.459472734760997e-08, | |
| "loss": 0.0002, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 14.401626016260163, | |
| "grad_norm": 0.08610350627610622, | |
| "learning_rate": 6.140863104726391e-08, | |
| "loss": 0.0005, | |
| "step": 1101 | |
| }, | |
| { | |
| "epoch": 14.414634146341463, | |
| "grad_norm": 0.029853636365563475, | |
| "learning_rate": 5.830286880972758e-08, | |
| "loss": 0.0002, | |
| "step": 1102 | |
| }, | |
| { | |
| "epoch": 14.427642276422764, | |
| "grad_norm": 0.037999272268641124, | |
| "learning_rate": 5.5277465739012045e-08, | |
| "loss": 0.0003, | |
| "step": 1103 | |
| }, | |
| { | |
| "epoch": 14.440650406504066, | |
| "grad_norm": 0.029356112058825358, | |
| "learning_rate": 5.233244628958134e-08, | |
| "loss": 0.0002, | |
| "step": 1104 | |
| }, | |
| { | |
| "epoch": 14.453658536585365, | |
| "grad_norm": 0.020414043886620863, | |
| "learning_rate": 4.9467834266154756e-08, | |
| "loss": 0.0002, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 14.466666666666667, | |
| "grad_norm": 0.05295425203318339, | |
| "learning_rate": 4.6683652823513725e-08, | |
| "loss": 0.0005, | |
| "step": 1106 | |
| }, | |
| { | |
| "epoch": 14.479674796747968, | |
| "grad_norm": 0.03061975529593269, | |
| "learning_rate": 4.39799244663186e-08, | |
| "loss": 0.0003, | |
| "step": 1107 | |
| }, | |
| { | |
| "epoch": 14.492682926829268, | |
| "grad_norm": 0.03505927802669296, | |
| "learning_rate": 4.135667104892105e-08, | |
| "loss": 0.0003, | |
| "step": 1108 | |
| }, | |
| { | |
| "epoch": 14.50569105691057, | |
| "grad_norm": 0.01569899988684874, | |
| "learning_rate": 3.881391377519084e-08, | |
| "loss": 0.0001, | |
| "step": 1109 | |
| }, | |
| { | |
| "epoch": 14.51869918699187, | |
| "grad_norm": 0.04463930655495351, | |
| "learning_rate": 3.635167319834709e-08, | |
| "loss": 0.0003, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 14.53170731707317, | |
| "grad_norm": 0.01592995076247383, | |
| "learning_rate": 3.3969969220785106e-08, | |
| "loss": 0.0002, | |
| "step": 1111 | |
| }, | |
| { | |
| "epoch": 14.544715447154472, | |
| "grad_norm": 0.026599290272323235, | |
| "learning_rate": 3.166882109392089e-08, | |
| "loss": 0.0002, | |
| "step": 1112 | |
| }, | |
| { | |
| "epoch": 14.557723577235773, | |
| "grad_norm": 0.029761775138282494, | |
| "learning_rate": 2.944824741803576e-08, | |
| "loss": 0.0003, | |
| "step": 1113 | |
| }, | |
| { | |
| "epoch": 14.570731707317073, | |
| "grad_norm": 0.03744078298569363, | |
| "learning_rate": 2.7308266142119788e-08, | |
| "loss": 0.0003, | |
| "step": 1114 | |
| }, | |
| { | |
| "epoch": 14.583739837398374, | |
| "grad_norm": 0.013773818583414988, | |
| "learning_rate": 2.524889456373525e-08, | |
| "loss": 0.0001, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 14.596747967479676, | |
| "grad_norm": 0.03608666336236024, | |
| "learning_rate": 2.327014932887228e-08, | |
| "loss": 0.0003, | |
| "step": 1116 | |
| }, | |
| { | |
| "epoch": 14.609756097560975, | |
| "grad_norm": 0.02230891276147283, | |
| "learning_rate": 2.1372046431812343e-08, | |
| "loss": 0.0002, | |
| "step": 1117 | |
| }, | |
| { | |
| "epoch": 14.622764227642277, | |
| "grad_norm": 0.02345370178511967, | |
| "learning_rate": 1.9554601215003856e-08, | |
| "loss": 0.0002, | |
| "step": 1118 | |
| }, | |
| { | |
| "epoch": 14.635772357723578, | |
| "grad_norm": 0.01912942327167438, | |
| "learning_rate": 1.7817828368935642e-08, | |
| "loss": 0.0002, | |
| "step": 1119 | |
| }, | |
| { | |
| "epoch": 14.648780487804878, | |
| "grad_norm": 0.06174519769536573, | |
| "learning_rate": 1.6161741932017026e-08, | |
| "loss": 0.0004, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 14.66178861788618, | |
| "grad_norm": 0.018949965702635463, | |
| "learning_rate": 1.4586355290464593e-08, | |
| "loss": 0.0002, | |
| "step": 1121 | |
| }, | |
| { | |
| "epoch": 14.67479674796748, | |
| "grad_norm": 0.02458718649975269, | |
| "learning_rate": 1.3091681178198922e-08, | |
| "loss": 0.0002, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 14.68780487804878, | |
| "grad_norm": 0.02215083696617675, | |
| "learning_rate": 1.1677731676733584e-08, | |
| "loss": 0.0002, | |
| "step": 1123 | |
| }, | |
| { | |
| "epoch": 14.700813008130082, | |
| "grad_norm": 0.021477017570415178, | |
| "learning_rate": 1.0344518215085198e-08, | |
| "loss": 0.0002, | |
| "step": 1124 | |
| }, | |
| { | |
| "epoch": 14.713821138211383, | |
| "grad_norm": 0.04377200578845525, | |
| "learning_rate": 9.092051569674632e-09, | |
| "loss": 0.0003, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 14.726829268292683, | |
| "grad_norm": 0.028085914628265037, | |
| "learning_rate": 7.92034186424262e-09, | |
| "loss": 0.0002, | |
| "step": 1126 | |
| }, | |
| { | |
| "epoch": 14.739837398373984, | |
| "grad_norm": 0.019067828968739185, | |
| "learning_rate": 6.82939856977094e-09, | |
| "loss": 0.0002, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 14.752845528455284, | |
| "grad_norm": 0.015128591405197895, | |
| "learning_rate": 5.819230504401363e-09, | |
| "loss": 0.0001, | |
| "step": 1128 | |
| }, | |
| { | |
| "epoch": 14.765853658536585, | |
| "grad_norm": 0.02247482737283179, | |
| "learning_rate": 4.889845833364604e-09, | |
| "loss": 0.0002, | |
| "step": 1129 | |
| }, | |
| { | |
| "epoch": 14.778861788617887, | |
| "grad_norm": 0.04000762766042668, | |
| "learning_rate": 4.041252068918145e-09, | |
| "loss": 0.0003, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 14.791869918699186, | |
| "grad_norm": 0.02929267821314836, | |
| "learning_rate": 3.273456070281844e-09, | |
| "loss": 0.0003, | |
| "step": 1131 | |
| }, | |
| { | |
| "epoch": 14.804878048780488, | |
| "grad_norm": 0.016502659240903488, | |
| "learning_rate": 2.5864640435835362e-09, | |
| "loss": 0.0001, | |
| "step": 1132 | |
| }, | |
| { | |
| "epoch": 14.817886178861789, | |
| "grad_norm": 0.020456975306716727, | |
| "learning_rate": 1.9802815418101805e-09, | |
| "loss": 0.0002, | |
| "step": 1133 | |
| }, | |
| { | |
| "epoch": 14.830894308943089, | |
| "grad_norm": 0.037623013210518384, | |
| "learning_rate": 1.4549134647601215e-09, | |
| "loss": 0.0003, | |
| "step": 1134 | |
| }, | |
| { | |
| "epoch": 14.84390243902439, | |
| "grad_norm": 0.028791151142816777, | |
| "learning_rate": 1.0103640590064524e-09, | |
| "loss": 0.0003, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 14.856910569105692, | |
| "grad_norm": 0.028158572046181538, | |
| "learning_rate": 6.466369178614873e-10, | |
| "loss": 0.0002, | |
| "step": 1136 | |
| }, | |
| { | |
| "epoch": 14.869918699186991, | |
| "grad_norm": 0.02706991421217001, | |
| "learning_rate": 3.637349813467861e-10, | |
| "loss": 0.0002, | |
| "step": 1137 | |
| }, | |
| { | |
| "epoch": 14.882926829268293, | |
| "grad_norm": 0.051082395177727204, | |
| "learning_rate": 1.616605361720591e-10, | |
| "loss": 0.0002, | |
| "step": 1138 | |
| }, | |
| { | |
| "epoch": 14.895934959349594, | |
| "grad_norm": 0.028377159346977227, | |
| "learning_rate": 4.041521571296336e-11, | |
| "loss": 0.0002, | |
| "step": 1139 | |
| }, | |
| { | |
| "epoch": 14.908943089430894, | |
| "grad_norm": 0.03112857719903251, | |
| "learning_rate": 0.0, | |
| "loss": 0.0003, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 14.908943089430894, | |
| "step": 1140, | |
| "total_flos": 650452104151040.0, | |
| "train_loss": 0.0012602176121027586, | |
| "train_runtime": 17614.0367, | |
| "train_samples_per_second": 8.375, | |
| "train_steps_per_second": 0.065 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 650452104151040.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |