diff --git "a/checkpoint-2152/trainer_state.json" "b/checkpoint-2152/trainer_state.json" new file mode 100644--- /dev/null +++ "b/checkpoint-2152/trainer_state.json" @@ -0,0 +1,15121 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5001016702977488, + "eval_steps": 1076, + "global_step": 2152, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00023238925199709515, + "grad_norm": 4.826773643493652, + "learning_rate": 4.6511627906976744e-08, + "loss": 18.0337, + "step": 1 + }, + { + "epoch": 0.00023238925199709515, + "eval_loss": 2.3483338356018066, + "eval_runtime": 2036.9341, + "eval_samples_per_second": 0.544, + "eval_steps_per_second": 0.544, + "step": 1 + }, + { + "epoch": 0.0004647785039941903, + "grad_norm": 5.355953216552734, + "learning_rate": 9.302325581395349e-08, + "loss": 17.9918, + "step": 2 + }, + { + "epoch": 0.0006971677559912854, + "grad_norm": 4.6318488121032715, + "learning_rate": 1.3953488372093024e-07, + "loss": 18.7367, + "step": 3 + }, + { + "epoch": 0.0009295570079883806, + "grad_norm": 4.7754597663879395, + "learning_rate": 1.8604651162790698e-07, + "loss": 18.5534, + "step": 4 + }, + { + "epoch": 0.0011619462599854757, + "grad_norm": 4.8395280838012695, + "learning_rate": 2.3255813953488374e-07, + "loss": 18.5242, + "step": 5 + }, + { + "epoch": 0.0013943355119825707, + "grad_norm": 4.71777868270874, + "learning_rate": 2.790697674418605e-07, + "loss": 18.1564, + "step": 6 + }, + { + "epoch": 0.001626724763979666, + "grad_norm": 5.019932270050049, + "learning_rate": 3.2558139534883724e-07, + "loss": 19.061, + "step": 7 + }, + { + "epoch": 0.0018591140159767612, + "grad_norm": 4.731651306152344, + "learning_rate": 3.7209302325581396e-07, + "loss": 17.9371, + "step": 8 + }, + { + "epoch": 0.0020915032679738564, + "grad_norm": 4.543302536010742, + "learning_rate": 4.186046511627907e-07, + "loss": 18.1708, + "step": 9 + }, + { + "epoch": 0.0023238925199709514, + "grad_norm": 7.167609691619873, + "learning_rate": 4.651162790697675e-07, + "loss": 19.0929, + "step": 10 + }, + { + "epoch": 0.0025562817719680464, + "grad_norm": 4.735901832580566, + "learning_rate": 5.116279069767442e-07, + "loss": 18.1614, + "step": 11 + }, + { + "epoch": 0.0027886710239651414, + "grad_norm": 4.51426362991333, + "learning_rate": 5.58139534883721e-07, + "loss": 18.5446, + "step": 12 + }, + { + "epoch": 0.003021060275962237, + "grad_norm": 4.444960594177246, + "learning_rate": 6.046511627906977e-07, + "loss": 18.9741, + "step": 13 + }, + { + "epoch": 0.003253449527959332, + "grad_norm": 5.289010524749756, + "learning_rate": 6.511627906976745e-07, + "loss": 18.0228, + "step": 14 + }, + { + "epoch": 0.003485838779956427, + "grad_norm": 4.729256629943848, + "learning_rate": 6.976744186046513e-07, + "loss": 18.7732, + "step": 15 + }, + { + "epoch": 0.0037182280319535224, + "grad_norm": 4.557053089141846, + "learning_rate": 7.441860465116279e-07, + "loss": 19.069, + "step": 16 + }, + { + "epoch": 0.003950617283950617, + "grad_norm": 4.550162315368652, + "learning_rate": 7.906976744186047e-07, + "loss": 18.4084, + "step": 17 + }, + { + "epoch": 0.004183006535947713, + "grad_norm": 4.477033615112305, + "learning_rate": 8.372093023255814e-07, + "loss": 17.8078, + "step": 18 + }, + { + "epoch": 0.004415395787944807, + "grad_norm": 4.7952799797058105, + "learning_rate": 8.837209302325582e-07, + "loss": 18.5532, + "step": 19 + }, + { + "epoch": 0.004647785039941903, + "grad_norm": 4.343478679656982, + "learning_rate": 9.30232558139535e-07, + "loss": 18.8798, + "step": 20 + }, + { + "epoch": 0.004880174291938997, + "grad_norm": 4.732629776000977, + "learning_rate": 9.767441860465117e-07, + "loss": 17.7198, + "step": 21 + }, + { + "epoch": 0.005112563543936093, + "grad_norm": 4.382180213928223, + "learning_rate": 1.0232558139534884e-06, + "loss": 17.4395, + "step": 22 + }, + { + "epoch": 0.005344952795933188, + "grad_norm": 5.549356937408447, + "learning_rate": 1.0697674418604653e-06, + "loss": 18.809, + "step": 23 + }, + { + "epoch": 0.005577342047930283, + "grad_norm": 4.294637203216553, + "learning_rate": 1.116279069767442e-06, + "loss": 17.6014, + "step": 24 + }, + { + "epoch": 0.005809731299927378, + "grad_norm": 4.29804801940918, + "learning_rate": 1.1627906976744188e-06, + "loss": 18.5444, + "step": 25 + }, + { + "epoch": 0.006042120551924474, + "grad_norm": 4.753503322601318, + "learning_rate": 1.2093023255813954e-06, + "loss": 17.8405, + "step": 26 + }, + { + "epoch": 0.006274509803921568, + "grad_norm": 5.097325801849365, + "learning_rate": 1.2558139534883723e-06, + "loss": 18.5617, + "step": 27 + }, + { + "epoch": 0.006506899055918664, + "grad_norm": 4.243263244628906, + "learning_rate": 1.302325581395349e-06, + "loss": 18.7032, + "step": 28 + }, + { + "epoch": 0.006739288307915759, + "grad_norm": 4.283297538757324, + "learning_rate": 1.3488372093023258e-06, + "loss": 18.4555, + "step": 29 + }, + { + "epoch": 0.006971677559912854, + "grad_norm": 4.078311920166016, + "learning_rate": 1.3953488372093025e-06, + "loss": 17.9139, + "step": 30 + }, + { + "epoch": 0.007204066811909949, + "grad_norm": 4.375993251800537, + "learning_rate": 1.4418604651162794e-06, + "loss": 17.7527, + "step": 31 + }, + { + "epoch": 0.007436456063907045, + "grad_norm": 4.0124077796936035, + "learning_rate": 1.4883720930232558e-06, + "loss": 18.322, + "step": 32 + }, + { + "epoch": 0.007668845315904139, + "grad_norm": 3.86627459526062, + "learning_rate": 1.534883720930233e-06, + "loss": 17.9401, + "step": 33 + }, + { + "epoch": 0.007901234567901235, + "grad_norm": 4.429265022277832, + "learning_rate": 1.5813953488372093e-06, + "loss": 18.2766, + "step": 34 + }, + { + "epoch": 0.00813362381989833, + "grad_norm": 3.9379115104675293, + "learning_rate": 1.6279069767441862e-06, + "loss": 18.3024, + "step": 35 + }, + { + "epoch": 0.008366013071895426, + "grad_norm": 4.058019161224365, + "learning_rate": 1.6744186046511629e-06, + "loss": 19.1466, + "step": 36 + }, + { + "epoch": 0.00859840232389252, + "grad_norm": 3.989349603652954, + "learning_rate": 1.7209302325581397e-06, + "loss": 17.9797, + "step": 37 + }, + { + "epoch": 0.008830791575889615, + "grad_norm": 3.7827227115631104, + "learning_rate": 1.7674418604651164e-06, + "loss": 18.2318, + "step": 38 + }, + { + "epoch": 0.00906318082788671, + "grad_norm": 3.9660282135009766, + "learning_rate": 1.8139534883720933e-06, + "loss": 18.4063, + "step": 39 + }, + { + "epoch": 0.009295570079883806, + "grad_norm": 4.788650989532471, + "learning_rate": 1.86046511627907e-06, + "loss": 19.2214, + "step": 40 + }, + { + "epoch": 0.0095279593318809, + "grad_norm": 3.9173619747161865, + "learning_rate": 1.9069767441860468e-06, + "loss": 18.1429, + "step": 41 + }, + { + "epoch": 0.009760348583877995, + "grad_norm": 4.3305559158325195, + "learning_rate": 1.9534883720930235e-06, + "loss": 17.8158, + "step": 42 + }, + { + "epoch": 0.009992737835875091, + "grad_norm": 4.023404121398926, + "learning_rate": 2.0000000000000003e-06, + "loss": 17.5303, + "step": 43 + }, + { + "epoch": 0.010225127087872186, + "grad_norm": 4.021667003631592, + "learning_rate": 2.0465116279069768e-06, + "loss": 19.2794, + "step": 44 + }, + { + "epoch": 0.01045751633986928, + "grad_norm": 4.590447425842285, + "learning_rate": 2.0930232558139536e-06, + "loss": 18.7483, + "step": 45 + }, + { + "epoch": 0.010689905591866377, + "grad_norm": 4.171151161193848, + "learning_rate": 2.1395348837209305e-06, + "loss": 17.8852, + "step": 46 + }, + { + "epoch": 0.010922294843863471, + "grad_norm": 4.543071269989014, + "learning_rate": 2.1860465116279074e-06, + "loss": 18.7839, + "step": 47 + }, + { + "epoch": 0.011154684095860566, + "grad_norm": 3.855454921722412, + "learning_rate": 2.232558139534884e-06, + "loss": 18.2656, + "step": 48 + }, + { + "epoch": 0.011387073347857662, + "grad_norm": 3.925652503967285, + "learning_rate": 2.2790697674418607e-06, + "loss": 19.4735, + "step": 49 + }, + { + "epoch": 0.011619462599854757, + "grad_norm": 4.232825756072998, + "learning_rate": 2.3255813953488376e-06, + "loss": 19.4267, + "step": 50 + }, + { + "epoch": 0.011851851851851851, + "grad_norm": 3.672619104385376, + "learning_rate": 2.3720930232558144e-06, + "loss": 17.7112, + "step": 51 + }, + { + "epoch": 0.012084241103848948, + "grad_norm": 3.773676633834839, + "learning_rate": 2.418604651162791e-06, + "loss": 18.7178, + "step": 52 + }, + { + "epoch": 0.012316630355846042, + "grad_norm": 3.5722291469573975, + "learning_rate": 2.4651162790697678e-06, + "loss": 18.1965, + "step": 53 + }, + { + "epoch": 0.012549019607843137, + "grad_norm": 3.782663106918335, + "learning_rate": 2.5116279069767446e-06, + "loss": 17.65, + "step": 54 + }, + { + "epoch": 0.012781408859840233, + "grad_norm": 4.054288864135742, + "learning_rate": 2.558139534883721e-06, + "loss": 18.5404, + "step": 55 + }, + { + "epoch": 0.013013798111837328, + "grad_norm": 3.9328956604003906, + "learning_rate": 2.604651162790698e-06, + "loss": 18.4829, + "step": 56 + }, + { + "epoch": 0.013246187363834422, + "grad_norm": 3.830869197845459, + "learning_rate": 2.6511627906976744e-06, + "loss": 18.342, + "step": 57 + }, + { + "epoch": 0.013478576615831519, + "grad_norm": 3.846304416656494, + "learning_rate": 2.6976744186046517e-06, + "loss": 18.6783, + "step": 58 + }, + { + "epoch": 0.013710965867828613, + "grad_norm": 3.54778790473938, + "learning_rate": 2.744186046511628e-06, + "loss": 17.0081, + "step": 59 + }, + { + "epoch": 0.013943355119825708, + "grad_norm": 3.6792736053466797, + "learning_rate": 2.790697674418605e-06, + "loss": 18.429, + "step": 60 + }, + { + "epoch": 0.014175744371822804, + "grad_norm": 3.748500347137451, + "learning_rate": 2.8372093023255815e-06, + "loss": 18.9352, + "step": 61 + }, + { + "epoch": 0.014408133623819899, + "grad_norm": 4.094432353973389, + "learning_rate": 2.8837209302325587e-06, + "loss": 18.4245, + "step": 62 + }, + { + "epoch": 0.014640522875816993, + "grad_norm": 3.975245714187622, + "learning_rate": 2.930232558139535e-06, + "loss": 19.2286, + "step": 63 + }, + { + "epoch": 0.01487291212781409, + "grad_norm": 3.781132936477661, + "learning_rate": 2.9767441860465116e-06, + "loss": 17.4799, + "step": 64 + }, + { + "epoch": 0.015105301379811184, + "grad_norm": 3.779134750366211, + "learning_rate": 3.0232558139534885e-06, + "loss": 18.57, + "step": 65 + }, + { + "epoch": 0.015337690631808279, + "grad_norm": 3.7684786319732666, + "learning_rate": 3.069767441860466e-06, + "loss": 18.1794, + "step": 66 + }, + { + "epoch": 0.015570079883805373, + "grad_norm": 3.833418130874634, + "learning_rate": 3.1162790697674423e-06, + "loss": 18.7417, + "step": 67 + }, + { + "epoch": 0.01580246913580247, + "grad_norm": 4.2276716232299805, + "learning_rate": 3.1627906976744187e-06, + "loss": 17.9758, + "step": 68 + }, + { + "epoch": 0.016034858387799566, + "grad_norm": 3.7345006465911865, + "learning_rate": 3.2093023255813956e-06, + "loss": 17.7711, + "step": 69 + }, + { + "epoch": 0.01626724763979666, + "grad_norm": 3.856187582015991, + "learning_rate": 3.2558139534883724e-06, + "loss": 18.6337, + "step": 70 + }, + { + "epoch": 0.016499636891793755, + "grad_norm": 3.7723805904388428, + "learning_rate": 3.3023255813953493e-06, + "loss": 18.6308, + "step": 71 + }, + { + "epoch": 0.01673202614379085, + "grad_norm": 3.7913661003112793, + "learning_rate": 3.3488372093023258e-06, + "loss": 18.7918, + "step": 72 + }, + { + "epoch": 0.016964415395787944, + "grad_norm": 3.8991329669952393, + "learning_rate": 3.3953488372093026e-06, + "loss": 17.6551, + "step": 73 + }, + { + "epoch": 0.01719680464778504, + "grad_norm": 3.4951093196868896, + "learning_rate": 3.4418604651162795e-06, + "loss": 17.9654, + "step": 74 + }, + { + "epoch": 0.017429193899782137, + "grad_norm": 3.819011926651001, + "learning_rate": 3.4883720930232564e-06, + "loss": 18.0407, + "step": 75 + }, + { + "epoch": 0.01766158315177923, + "grad_norm": 4.984830856323242, + "learning_rate": 3.534883720930233e-06, + "loss": 18.6303, + "step": 76 + }, + { + "epoch": 0.017893972403776326, + "grad_norm": 3.766205310821533, + "learning_rate": 3.5813953488372093e-06, + "loss": 18.8954, + "step": 77 + }, + { + "epoch": 0.01812636165577342, + "grad_norm": 3.6298305988311768, + "learning_rate": 3.6279069767441866e-06, + "loss": 18.5944, + "step": 78 + }, + { + "epoch": 0.018358750907770515, + "grad_norm": 3.898404836654663, + "learning_rate": 3.674418604651163e-06, + "loss": 18.1442, + "step": 79 + }, + { + "epoch": 0.01859114015976761, + "grad_norm": 3.623739719390869, + "learning_rate": 3.72093023255814e-06, + "loss": 18.9476, + "step": 80 + }, + { + "epoch": 0.018823529411764704, + "grad_norm": 6.967983722686768, + "learning_rate": 3.7674418604651163e-06, + "loss": 17.9254, + "step": 81 + }, + { + "epoch": 0.0190559186637618, + "grad_norm": 3.4042253494262695, + "learning_rate": 3.8139534883720936e-06, + "loss": 17.9072, + "step": 82 + }, + { + "epoch": 0.019288307915758897, + "grad_norm": 4.377119064331055, + "learning_rate": 3.86046511627907e-06, + "loss": 19.631, + "step": 83 + }, + { + "epoch": 0.01952069716775599, + "grad_norm": 3.7917795181274414, + "learning_rate": 3.906976744186047e-06, + "loss": 18.2591, + "step": 84 + }, + { + "epoch": 0.019753086419753086, + "grad_norm": 4.970120906829834, + "learning_rate": 3.953488372093024e-06, + "loss": 18.105, + "step": 85 + }, + { + "epoch": 0.019985475671750182, + "grad_norm": 3.6605401039123535, + "learning_rate": 4.000000000000001e-06, + "loss": 18.3682, + "step": 86 + }, + { + "epoch": 0.020217864923747275, + "grad_norm": 4.051941394805908, + "learning_rate": 4.0465116279069775e-06, + "loss": 18.373, + "step": 87 + }, + { + "epoch": 0.02045025417574437, + "grad_norm": 4.177452564239502, + "learning_rate": 4.0930232558139536e-06, + "loss": 17.8459, + "step": 88 + }, + { + "epoch": 0.020682643427741468, + "grad_norm": 4.378493309020996, + "learning_rate": 4.1395348837209304e-06, + "loss": 19.2196, + "step": 89 + }, + { + "epoch": 0.02091503267973856, + "grad_norm": 3.646289348602295, + "learning_rate": 4.186046511627907e-06, + "loss": 17.0739, + "step": 90 + }, + { + "epoch": 0.021147421931735657, + "grad_norm": 3.7239840030670166, + "learning_rate": 4.232558139534884e-06, + "loss": 17.5915, + "step": 91 + }, + { + "epoch": 0.021379811183732753, + "grad_norm": 4.490355968475342, + "learning_rate": 4.279069767441861e-06, + "loss": 18.2486, + "step": 92 + }, + { + "epoch": 0.021612200435729846, + "grad_norm": 3.666999578475952, + "learning_rate": 4.325581395348837e-06, + "loss": 19.6076, + "step": 93 + }, + { + "epoch": 0.021844589687726942, + "grad_norm": 4.011026859283447, + "learning_rate": 4.372093023255815e-06, + "loss": 18.4306, + "step": 94 + }, + { + "epoch": 0.02207697893972404, + "grad_norm": 3.7540533542633057, + "learning_rate": 4.418604651162791e-06, + "loss": 18.0137, + "step": 95 + }, + { + "epoch": 0.02230936819172113, + "grad_norm": 3.856630563735962, + "learning_rate": 4.465116279069768e-06, + "loss": 18.6499, + "step": 96 + }, + { + "epoch": 0.022541757443718228, + "grad_norm": 3.6867048740386963, + "learning_rate": 4.5116279069767445e-06, + "loss": 18.9826, + "step": 97 + }, + { + "epoch": 0.022774146695715324, + "grad_norm": 4.09191370010376, + "learning_rate": 4.558139534883721e-06, + "loss": 18.7069, + "step": 98 + }, + { + "epoch": 0.023006535947712417, + "grad_norm": 3.7967641353607178, + "learning_rate": 4.604651162790698e-06, + "loss": 18.1055, + "step": 99 + }, + { + "epoch": 0.023238925199709513, + "grad_norm": 3.7054009437561035, + "learning_rate": 4.651162790697675e-06, + "loss": 18.1974, + "step": 100 + }, + { + "epoch": 0.02347131445170661, + "grad_norm": 3.82721209526062, + "learning_rate": 4.697674418604651e-06, + "loss": 18.2085, + "step": 101 + }, + { + "epoch": 0.023703703703703703, + "grad_norm": 3.3627007007598877, + "learning_rate": 4.744186046511629e-06, + "loss": 18.0158, + "step": 102 + }, + { + "epoch": 0.0239360929557008, + "grad_norm": 3.7685751914978027, + "learning_rate": 4.790697674418605e-06, + "loss": 19.0023, + "step": 103 + }, + { + "epoch": 0.024168482207697895, + "grad_norm": 3.6617753505706787, + "learning_rate": 4.837209302325582e-06, + "loss": 18.6602, + "step": 104 + }, + { + "epoch": 0.024400871459694988, + "grad_norm": 4.088813781738281, + "learning_rate": 4.883720930232559e-06, + "loss": 17.1044, + "step": 105 + }, + { + "epoch": 0.024633260711692084, + "grad_norm": 3.5502986907958984, + "learning_rate": 4.9302325581395355e-06, + "loss": 17.8663, + "step": 106 + }, + { + "epoch": 0.02486564996368918, + "grad_norm": 4.260704040527344, + "learning_rate": 4.976744186046512e-06, + "loss": 17.957, + "step": 107 + }, + { + "epoch": 0.025098039215686273, + "grad_norm": 3.56135892868042, + "learning_rate": 5.023255813953489e-06, + "loss": 18.6663, + "step": 108 + }, + { + "epoch": 0.02533042846768337, + "grad_norm": 3.77662992477417, + "learning_rate": 5.069767441860466e-06, + "loss": 18.1214, + "step": 109 + }, + { + "epoch": 0.025562817719680466, + "grad_norm": 3.8269248008728027, + "learning_rate": 5.116279069767442e-06, + "loss": 17.4203, + "step": 110 + }, + { + "epoch": 0.02579520697167756, + "grad_norm": 3.662304401397705, + "learning_rate": 5.162790697674419e-06, + "loss": 18.3529, + "step": 111 + }, + { + "epoch": 0.026027596223674655, + "grad_norm": 4.031530857086182, + "learning_rate": 5.209302325581396e-06, + "loss": 18.0449, + "step": 112 + }, + { + "epoch": 0.02625998547567175, + "grad_norm": 3.7221145629882812, + "learning_rate": 5.255813953488372e-06, + "loss": 17.9809, + "step": 113 + }, + { + "epoch": 0.026492374727668844, + "grad_norm": 3.8018558025360107, + "learning_rate": 5.302325581395349e-06, + "loss": 18.2681, + "step": 114 + }, + { + "epoch": 0.02672476397966594, + "grad_norm": 3.9166598320007324, + "learning_rate": 5.348837209302326e-06, + "loss": 18.3554, + "step": 115 + }, + { + "epoch": 0.026957153231663037, + "grad_norm": 3.8337974548339844, + "learning_rate": 5.395348837209303e-06, + "loss": 18.7037, + "step": 116 + }, + { + "epoch": 0.02718954248366013, + "grad_norm": 3.872405767440796, + "learning_rate": 5.44186046511628e-06, + "loss": 17.857, + "step": 117 + }, + { + "epoch": 0.027421931735657226, + "grad_norm": 4.466931343078613, + "learning_rate": 5.488372093023256e-06, + "loss": 18.8517, + "step": 118 + }, + { + "epoch": 0.027654320987654323, + "grad_norm": 3.73626446723938, + "learning_rate": 5.534883720930233e-06, + "loss": 18.107, + "step": 119 + }, + { + "epoch": 0.027886710239651415, + "grad_norm": 3.899413585662842, + "learning_rate": 5.58139534883721e-06, + "loss": 17.9095, + "step": 120 + }, + { + "epoch": 0.02811909949164851, + "grad_norm": 4.487497329711914, + "learning_rate": 5.627906976744186e-06, + "loss": 18.1361, + "step": 121 + }, + { + "epoch": 0.028351488743645608, + "grad_norm": 4.008020877838135, + "learning_rate": 5.674418604651163e-06, + "loss": 18.583, + "step": 122 + }, + { + "epoch": 0.0285838779956427, + "grad_norm": 4.088570594787598, + "learning_rate": 5.72093023255814e-06, + "loss": 18.4914, + "step": 123 + }, + { + "epoch": 0.028816267247639797, + "grad_norm": 3.800532341003418, + "learning_rate": 5.7674418604651175e-06, + "loss": 18.4844, + "step": 124 + }, + { + "epoch": 0.029048656499636893, + "grad_norm": 3.720247268676758, + "learning_rate": 5.8139534883720935e-06, + "loss": 18.3857, + "step": 125 + }, + { + "epoch": 0.029281045751633986, + "grad_norm": 4.299480438232422, + "learning_rate": 5.86046511627907e-06, + "loss": 18.6198, + "step": 126 + }, + { + "epoch": 0.029513435003631083, + "grad_norm": 3.809549331665039, + "learning_rate": 5.906976744186047e-06, + "loss": 18.004, + "step": 127 + }, + { + "epoch": 0.02974582425562818, + "grad_norm": 4.035370349884033, + "learning_rate": 5.953488372093023e-06, + "loss": 18.424, + "step": 128 + }, + { + "epoch": 0.029978213507625272, + "grad_norm": 3.853370189666748, + "learning_rate": 6e-06, + "loss": 17.702, + "step": 129 + }, + { + "epoch": 0.030210602759622368, + "grad_norm": 4.164186000823975, + "learning_rate": 6.046511627906977e-06, + "loss": 17.9452, + "step": 130 + }, + { + "epoch": 0.03044299201161946, + "grad_norm": 3.9935178756713867, + "learning_rate": 6.093023255813954e-06, + "loss": 18.6598, + "step": 131 + }, + { + "epoch": 0.030675381263616557, + "grad_norm": 4.021765232086182, + "learning_rate": 6.139534883720932e-06, + "loss": 17.9165, + "step": 132 + }, + { + "epoch": 0.030907770515613654, + "grad_norm": 4.0428466796875, + "learning_rate": 6.186046511627908e-06, + "loss": 17.4565, + "step": 133 + }, + { + "epoch": 0.031140159767610746, + "grad_norm": 3.701664447784424, + "learning_rate": 6.2325581395348845e-06, + "loss": 17.3643, + "step": 134 + }, + { + "epoch": 0.03137254901960784, + "grad_norm": 3.6789638996124268, + "learning_rate": 6.279069767441861e-06, + "loss": 18.3717, + "step": 135 + }, + { + "epoch": 0.03160493827160494, + "grad_norm": 7.434831619262695, + "learning_rate": 6.325581395348837e-06, + "loss": 18.1118, + "step": 136 + }, + { + "epoch": 0.031837327523602035, + "grad_norm": 3.375972270965576, + "learning_rate": 6.372093023255814e-06, + "loss": 18.5297, + "step": 137 + }, + { + "epoch": 0.03206971677559913, + "grad_norm": 3.9011728763580322, + "learning_rate": 6.418604651162791e-06, + "loss": 18.7396, + "step": 138 + }, + { + "epoch": 0.03230210602759622, + "grad_norm": 3.8863630294799805, + "learning_rate": 6.465116279069767e-06, + "loss": 19.3742, + "step": 139 + }, + { + "epoch": 0.03253449527959332, + "grad_norm": 3.7838830947875977, + "learning_rate": 6.511627906976745e-06, + "loss": 18.7132, + "step": 140 + }, + { + "epoch": 0.032766884531590414, + "grad_norm": 4.480525493621826, + "learning_rate": 6.558139534883722e-06, + "loss": 18.2748, + "step": 141 + }, + { + "epoch": 0.03299927378358751, + "grad_norm": 3.7885990142822266, + "learning_rate": 6.604651162790699e-06, + "loss": 17.6893, + "step": 142 + }, + { + "epoch": 0.033231663035584606, + "grad_norm": 4.079428672790527, + "learning_rate": 6.651162790697675e-06, + "loss": 18.9298, + "step": 143 + }, + { + "epoch": 0.0334640522875817, + "grad_norm": 4.470268249511719, + "learning_rate": 6.6976744186046515e-06, + "loss": 17.8702, + "step": 144 + }, + { + "epoch": 0.03369644153957879, + "grad_norm": 3.9488701820373535, + "learning_rate": 6.744186046511628e-06, + "loss": 18.5271, + "step": 145 + }, + { + "epoch": 0.03392883079157589, + "grad_norm": 4.103010177612305, + "learning_rate": 6.790697674418605e-06, + "loss": 18.0733, + "step": 146 + }, + { + "epoch": 0.034161220043572985, + "grad_norm": 3.9823577404022217, + "learning_rate": 6.837209302325581e-06, + "loss": 18.6785, + "step": 147 + }, + { + "epoch": 0.03439360929557008, + "grad_norm": 4.032834529876709, + "learning_rate": 6.883720930232559e-06, + "loss": 18.3398, + "step": 148 + }, + { + "epoch": 0.03462599854756718, + "grad_norm": 3.7148752212524414, + "learning_rate": 6.930232558139536e-06, + "loss": 19.0179, + "step": 149 + }, + { + "epoch": 0.034858387799564274, + "grad_norm": 3.7471864223480225, + "learning_rate": 6.976744186046513e-06, + "loss": 18.9157, + "step": 150 + }, + { + "epoch": 0.03509077705156136, + "grad_norm": 3.540553569793701, + "learning_rate": 7.023255813953489e-06, + "loss": 17.3528, + "step": 151 + }, + { + "epoch": 0.03532316630355846, + "grad_norm": 3.787635326385498, + "learning_rate": 7.069767441860466e-06, + "loss": 18.0866, + "step": 152 + }, + { + "epoch": 0.035555555555555556, + "grad_norm": 4.178308486938477, + "learning_rate": 7.1162790697674425e-06, + "loss": 17.8226, + "step": 153 + }, + { + "epoch": 0.03578794480755265, + "grad_norm": 4.081904411315918, + "learning_rate": 7.1627906976744185e-06, + "loss": 18.4004, + "step": 154 + }, + { + "epoch": 0.03602033405954975, + "grad_norm": 4.225133895874023, + "learning_rate": 7.209302325581395e-06, + "loss": 18.5298, + "step": 155 + }, + { + "epoch": 0.03625272331154684, + "grad_norm": 3.927924394607544, + "learning_rate": 7.255813953488373e-06, + "loss": 18.1634, + "step": 156 + }, + { + "epoch": 0.036485112563543934, + "grad_norm": 3.9503018856048584, + "learning_rate": 7.30232558139535e-06, + "loss": 19.4021, + "step": 157 + }, + { + "epoch": 0.03671750181554103, + "grad_norm": 4.002676486968994, + "learning_rate": 7.348837209302326e-06, + "loss": 17.6334, + "step": 158 + }, + { + "epoch": 0.036949891067538126, + "grad_norm": 3.9479165077209473, + "learning_rate": 7.395348837209303e-06, + "loss": 18.1556, + "step": 159 + }, + { + "epoch": 0.03718228031953522, + "grad_norm": 3.725552797317505, + "learning_rate": 7.44186046511628e-06, + "loss": 17.4197, + "step": 160 + }, + { + "epoch": 0.03741466957153232, + "grad_norm": 4.373473644256592, + "learning_rate": 7.488372093023256e-06, + "loss": 17.8992, + "step": 161 + }, + { + "epoch": 0.03764705882352941, + "grad_norm": 3.8760123252868652, + "learning_rate": 7.534883720930233e-06, + "loss": 17.4422, + "step": 162 + }, + { + "epoch": 0.037879448075526505, + "grad_norm": 4.9901814460754395, + "learning_rate": 7.5813953488372095e-06, + "loss": 18.8833, + "step": 163 + }, + { + "epoch": 0.0381118373275236, + "grad_norm": 7.956139087677002, + "learning_rate": 7.627906976744187e-06, + "loss": 17.5677, + "step": 164 + }, + { + "epoch": 0.0383442265795207, + "grad_norm": 3.5493853092193604, + "learning_rate": 7.674418604651164e-06, + "loss": 17.4545, + "step": 165 + }, + { + "epoch": 0.038576615831517794, + "grad_norm": 3.8137173652648926, + "learning_rate": 7.72093023255814e-06, + "loss": 18.0882, + "step": 166 + }, + { + "epoch": 0.03880900508351489, + "grad_norm": 3.5082895755767822, + "learning_rate": 7.767441860465116e-06, + "loss": 18.3232, + "step": 167 + }, + { + "epoch": 0.03904139433551198, + "grad_norm": 3.712940216064453, + "learning_rate": 7.813953488372094e-06, + "loss": 18.4312, + "step": 168 + }, + { + "epoch": 0.039273783587509076, + "grad_norm": 55.97513198852539, + "learning_rate": 7.86046511627907e-06, + "loss": 18.0431, + "step": 169 + }, + { + "epoch": 0.03950617283950617, + "grad_norm": 4.08044958114624, + "learning_rate": 7.906976744186048e-06, + "loss": 17.5119, + "step": 170 + }, + { + "epoch": 0.03973856209150327, + "grad_norm": 3.9160163402557373, + "learning_rate": 7.953488372093024e-06, + "loss": 18.1432, + "step": 171 + }, + { + "epoch": 0.039970951343500365, + "grad_norm": 3.952627658843994, + "learning_rate": 8.000000000000001e-06, + "loss": 18.7564, + "step": 172 + }, + { + "epoch": 0.04020334059549746, + "grad_norm": 3.9183871746063232, + "learning_rate": 8.046511627906977e-06, + "loss": 18.4662, + "step": 173 + }, + { + "epoch": 0.04043572984749455, + "grad_norm": 5.941267013549805, + "learning_rate": 8.093023255813955e-06, + "loss": 18.6135, + "step": 174 + }, + { + "epoch": 0.04066811909949165, + "grad_norm": 3.799644708633423, + "learning_rate": 8.139534883720931e-06, + "loss": 17.3283, + "step": 175 + }, + { + "epoch": 0.04090050835148874, + "grad_norm": 3.992521047592163, + "learning_rate": 8.186046511627907e-06, + "loss": 17.756, + "step": 176 + }, + { + "epoch": 0.04113289760348584, + "grad_norm": 3.6203501224517822, + "learning_rate": 8.232558139534885e-06, + "loss": 18.6235, + "step": 177 + }, + { + "epoch": 0.041365286855482936, + "grad_norm": 4.4006524085998535, + "learning_rate": 8.279069767441861e-06, + "loss": 18.2632, + "step": 178 + }, + { + "epoch": 0.04159767610748003, + "grad_norm": 3.679471969604492, + "learning_rate": 8.325581395348837e-06, + "loss": 17.847, + "step": 179 + }, + { + "epoch": 0.04183006535947712, + "grad_norm": 3.8845980167388916, + "learning_rate": 8.372093023255815e-06, + "loss": 17.9081, + "step": 180 + }, + { + "epoch": 0.04206245461147422, + "grad_norm": 3.749680280685425, + "learning_rate": 8.418604651162792e-06, + "loss": 17.864, + "step": 181 + }, + { + "epoch": 0.042294843863471314, + "grad_norm": 3.8312864303588867, + "learning_rate": 8.465116279069768e-06, + "loss": 17.8628, + "step": 182 + }, + { + "epoch": 0.04252723311546841, + "grad_norm": 3.833279609680176, + "learning_rate": 8.511627906976744e-06, + "loss": 18.0876, + "step": 183 + }, + { + "epoch": 0.04275962236746551, + "grad_norm": 3.915433406829834, + "learning_rate": 8.558139534883722e-06, + "loss": 18.5144, + "step": 184 + }, + { + "epoch": 0.0429920116194626, + "grad_norm": 3.6742122173309326, + "learning_rate": 8.604651162790698e-06, + "loss": 18.1838, + "step": 185 + }, + { + "epoch": 0.04322440087145969, + "grad_norm": 4.06402063369751, + "learning_rate": 8.651162790697674e-06, + "loss": 19.4298, + "step": 186 + }, + { + "epoch": 0.04345679012345679, + "grad_norm": 3.926457166671753, + "learning_rate": 8.697674418604652e-06, + "loss": 17.6556, + "step": 187 + }, + { + "epoch": 0.043689179375453885, + "grad_norm": 10.585919380187988, + "learning_rate": 8.74418604651163e-06, + "loss": 18.2775, + "step": 188 + }, + { + "epoch": 0.04392156862745098, + "grad_norm": 4.503403186798096, + "learning_rate": 8.790697674418606e-06, + "loss": 17.1401, + "step": 189 + }, + { + "epoch": 0.04415395787944808, + "grad_norm": 3.8102328777313232, + "learning_rate": 8.837209302325582e-06, + "loss": 18.1714, + "step": 190 + }, + { + "epoch": 0.044386347131445174, + "grad_norm": 3.976154327392578, + "learning_rate": 8.88372093023256e-06, + "loss": 18.9635, + "step": 191 + }, + { + "epoch": 0.04461873638344226, + "grad_norm": 3.595686912536621, + "learning_rate": 8.930232558139535e-06, + "loss": 17.8785, + "step": 192 + }, + { + "epoch": 0.04485112563543936, + "grad_norm": 4.056515693664551, + "learning_rate": 8.976744186046511e-06, + "loss": 18.3616, + "step": 193 + }, + { + "epoch": 0.045083514887436456, + "grad_norm": 4.4187116622924805, + "learning_rate": 9.023255813953489e-06, + "loss": 19.3423, + "step": 194 + }, + { + "epoch": 0.04531590413943355, + "grad_norm": 3.688554286956787, + "learning_rate": 9.069767441860465e-06, + "loss": 18.2929, + "step": 195 + }, + { + "epoch": 0.04554829339143065, + "grad_norm": 3.9759202003479004, + "learning_rate": 9.116279069767443e-06, + "loss": 18.345, + "step": 196 + }, + { + "epoch": 0.045780682643427745, + "grad_norm": 4.467806339263916, + "learning_rate": 9.162790697674419e-06, + "loss": 18.562, + "step": 197 + }, + { + "epoch": 0.046013071895424834, + "grad_norm": 3.988555431365967, + "learning_rate": 9.209302325581397e-06, + "loss": 18.3927, + "step": 198 + }, + { + "epoch": 0.04624546114742193, + "grad_norm": 15.954890251159668, + "learning_rate": 9.255813953488373e-06, + "loss": 18.6679, + "step": 199 + }, + { + "epoch": 0.04647785039941903, + "grad_norm": 4.471603870391846, + "learning_rate": 9.30232558139535e-06, + "loss": 17.4827, + "step": 200 + }, + { + "epoch": 0.04671023965141612, + "grad_norm": 3.6261868476867676, + "learning_rate": 9.348837209302326e-06, + "loss": 18.2001, + "step": 201 + }, + { + "epoch": 0.04694262890341322, + "grad_norm": 3.767289400100708, + "learning_rate": 9.395348837209302e-06, + "loss": 18.6224, + "step": 202 + }, + { + "epoch": 0.047175018155410316, + "grad_norm": 3.8248770236968994, + "learning_rate": 9.44186046511628e-06, + "loss": 17.7011, + "step": 203 + }, + { + "epoch": 0.047407407407407405, + "grad_norm": 3.590832233428955, + "learning_rate": 9.488372093023258e-06, + "loss": 18.036, + "step": 204 + }, + { + "epoch": 0.0476397966594045, + "grad_norm": 4.646628379821777, + "learning_rate": 9.534883720930234e-06, + "loss": 16.8497, + "step": 205 + }, + { + "epoch": 0.0478721859114016, + "grad_norm": 3.9789347648620605, + "learning_rate": 9.58139534883721e-06, + "loss": 17.415, + "step": 206 + }, + { + "epoch": 0.048104575163398694, + "grad_norm": 3.9552767276763916, + "learning_rate": 9.627906976744188e-06, + "loss": 18.4444, + "step": 207 + }, + { + "epoch": 0.04833696441539579, + "grad_norm": 3.891606092453003, + "learning_rate": 9.674418604651164e-06, + "loss": 18.8504, + "step": 208 + }, + { + "epoch": 0.04856935366739288, + "grad_norm": 4.134636402130127, + "learning_rate": 9.72093023255814e-06, + "loss": 17.997, + "step": 209 + }, + { + "epoch": 0.048801742919389976, + "grad_norm": 3.9658987522125244, + "learning_rate": 9.767441860465117e-06, + "loss": 16.9771, + "step": 210 + }, + { + "epoch": 0.04903413217138707, + "grad_norm": 3.9821062088012695, + "learning_rate": 9.813953488372093e-06, + "loss": 18.9259, + "step": 211 + }, + { + "epoch": 0.04926652142338417, + "grad_norm": 6.14623498916626, + "learning_rate": 9.860465116279071e-06, + "loss": 18.7599, + "step": 212 + }, + { + "epoch": 0.049498910675381265, + "grad_norm": 3.779343843460083, + "learning_rate": 9.906976744186047e-06, + "loss": 18.3731, + "step": 213 + }, + { + "epoch": 0.04973129992737836, + "grad_norm": 3.8019888401031494, + "learning_rate": 9.953488372093025e-06, + "loss": 17.974, + "step": 214 + }, + { + "epoch": 0.04996368917937545, + "grad_norm": 4.052139759063721, + "learning_rate": 1e-05, + "loss": 18.9149, + "step": 215 + }, + { + "epoch": 0.05019607843137255, + "grad_norm": 3.7587244510650635, + "learning_rate": 1.0046511627906979e-05, + "loss": 17.7365, + "step": 216 + }, + { + "epoch": 0.05042846768336964, + "grad_norm": 4.045208930969238, + "learning_rate": 1.0093023255813955e-05, + "loss": 18.4882, + "step": 217 + }, + { + "epoch": 0.05066085693536674, + "grad_norm": 3.585341453552246, + "learning_rate": 1.0139534883720932e-05, + "loss": 17.8596, + "step": 218 + }, + { + "epoch": 0.050893246187363836, + "grad_norm": 3.68152117729187, + "learning_rate": 1.0186046511627907e-05, + "loss": 18.8928, + "step": 219 + }, + { + "epoch": 0.05112563543936093, + "grad_norm": 4.054990291595459, + "learning_rate": 1.0232558139534884e-05, + "loss": 18.532, + "step": 220 + }, + { + "epoch": 0.05135802469135802, + "grad_norm": 3.9595746994018555, + "learning_rate": 1.027906976744186e-05, + "loss": 18.2693, + "step": 221 + }, + { + "epoch": 0.05159041394335512, + "grad_norm": 4.048892021179199, + "learning_rate": 1.0325581395348838e-05, + "loss": 17.3393, + "step": 222 + }, + { + "epoch": 0.051822803195352214, + "grad_norm": 4.051593780517578, + "learning_rate": 1.0372093023255816e-05, + "loss": 18.2408, + "step": 223 + }, + { + "epoch": 0.05205519244734931, + "grad_norm": 4.414335250854492, + "learning_rate": 1.0418604651162792e-05, + "loss": 18.7123, + "step": 224 + }, + { + "epoch": 0.05228758169934641, + "grad_norm": 5.07412576675415, + "learning_rate": 1.046511627906977e-05, + "loss": 16.6155, + "step": 225 + }, + { + "epoch": 0.0525199709513435, + "grad_norm": 3.668973922729492, + "learning_rate": 1.0511627906976744e-05, + "loss": 18.3681, + "step": 226 + }, + { + "epoch": 0.05275236020334059, + "grad_norm": 6.131514072418213, + "learning_rate": 1.0558139534883722e-05, + "loss": 18.824, + "step": 227 + }, + { + "epoch": 0.05298474945533769, + "grad_norm": 4.538069725036621, + "learning_rate": 1.0604651162790698e-05, + "loss": 17.5431, + "step": 228 + }, + { + "epoch": 0.053217138707334785, + "grad_norm": 3.847882032394409, + "learning_rate": 1.0651162790697675e-05, + "loss": 19.0491, + "step": 229 + }, + { + "epoch": 0.05344952795933188, + "grad_norm": 3.795137643814087, + "learning_rate": 1.0697674418604651e-05, + "loss": 18.3475, + "step": 230 + }, + { + "epoch": 0.05368191721132898, + "grad_norm": 4.4361348152160645, + "learning_rate": 1.0744186046511629e-05, + "loss": 17.745, + "step": 231 + }, + { + "epoch": 0.053914306463326074, + "grad_norm": 4.0975542068481445, + "learning_rate": 1.0790697674418607e-05, + "loss": 17.6229, + "step": 232 + }, + { + "epoch": 0.05414669571532316, + "grad_norm": 4.226440906524658, + "learning_rate": 1.0837209302325583e-05, + "loss": 18.6331, + "step": 233 + }, + { + "epoch": 0.05437908496732026, + "grad_norm": 3.621438503265381, + "learning_rate": 1.088372093023256e-05, + "loss": 19.0109, + "step": 234 + }, + { + "epoch": 0.054611474219317356, + "grad_norm": 3.5329031944274902, + "learning_rate": 1.0930232558139535e-05, + "loss": 18.3227, + "step": 235 + }, + { + "epoch": 0.05484386347131445, + "grad_norm": 4.027487277984619, + "learning_rate": 1.0976744186046513e-05, + "loss": 18.0667, + "step": 236 + }, + { + "epoch": 0.05507625272331155, + "grad_norm": 3.74536395072937, + "learning_rate": 1.1023255813953489e-05, + "loss": 17.709, + "step": 237 + }, + { + "epoch": 0.055308641975308645, + "grad_norm": 4.6305060386657715, + "learning_rate": 1.1069767441860466e-05, + "loss": 18.5675, + "step": 238 + }, + { + "epoch": 0.055541031227305734, + "grad_norm": 4.070378303527832, + "learning_rate": 1.1116279069767444e-05, + "loss": 17.6444, + "step": 239 + }, + { + "epoch": 0.05577342047930283, + "grad_norm": 4.208585262298584, + "learning_rate": 1.116279069767442e-05, + "loss": 18.6357, + "step": 240 + }, + { + "epoch": 0.05600580973129993, + "grad_norm": 3.9329683780670166, + "learning_rate": 1.1209302325581398e-05, + "loss": 18.3609, + "step": 241 + }, + { + "epoch": 0.05623819898329702, + "grad_norm": 4.081618309020996, + "learning_rate": 1.1255813953488372e-05, + "loss": 18.7046, + "step": 242 + }, + { + "epoch": 0.05647058823529412, + "grad_norm": 3.6541929244995117, + "learning_rate": 1.130232558139535e-05, + "loss": 19.4889, + "step": 243 + }, + { + "epoch": 0.056702977487291216, + "grad_norm": 3.585862398147583, + "learning_rate": 1.1348837209302326e-05, + "loss": 18.7815, + "step": 244 + }, + { + "epoch": 0.056935366739288305, + "grad_norm": 3.773101329803467, + "learning_rate": 1.1395348837209304e-05, + "loss": 17.7526, + "step": 245 + }, + { + "epoch": 0.0571677559912854, + "grad_norm": 6.568117618560791, + "learning_rate": 1.144186046511628e-05, + "loss": 17.9325, + "step": 246 + }, + { + "epoch": 0.0574001452432825, + "grad_norm": 3.74017333984375, + "learning_rate": 1.1488372093023257e-05, + "loss": 18.2002, + "step": 247 + }, + { + "epoch": 0.057632534495279594, + "grad_norm": 3.741321325302124, + "learning_rate": 1.1534883720930235e-05, + "loss": 18.1325, + "step": 248 + }, + { + "epoch": 0.05786492374727669, + "grad_norm": 3.975311756134033, + "learning_rate": 1.158139534883721e-05, + "loss": 18.8206, + "step": 249 + }, + { + "epoch": 0.05809731299927379, + "grad_norm": 4.234350681304932, + "learning_rate": 1.1627906976744187e-05, + "loss": 19.074, + "step": 250 + }, + { + "epoch": 0.058329702251270876, + "grad_norm": 3.5002377033233643, + "learning_rate": 1.1674418604651163e-05, + "loss": 18.4681, + "step": 251 + }, + { + "epoch": 0.05856209150326797, + "grad_norm": 3.9251744747161865, + "learning_rate": 1.172093023255814e-05, + "loss": 17.9312, + "step": 252 + }, + { + "epoch": 0.05879448075526507, + "grad_norm": 3.7096736431121826, + "learning_rate": 1.1767441860465117e-05, + "loss": 17.9474, + "step": 253 + }, + { + "epoch": 0.059026870007262165, + "grad_norm": 7.313652992248535, + "learning_rate": 1.1813953488372095e-05, + "loss": 17.3137, + "step": 254 + }, + { + "epoch": 0.05925925925925926, + "grad_norm": 3.8632583618164062, + "learning_rate": 1.1860465116279072e-05, + "loss": 18.5632, + "step": 255 + }, + { + "epoch": 0.05949164851125636, + "grad_norm": 3.753480911254883, + "learning_rate": 1.1906976744186047e-05, + "loss": 18.2069, + "step": 256 + }, + { + "epoch": 0.05972403776325345, + "grad_norm": 3.6856508255004883, + "learning_rate": 1.1953488372093024e-05, + "loss": 18.3825, + "step": 257 + }, + { + "epoch": 0.059956427015250544, + "grad_norm": 3.899477243423462, + "learning_rate": 1.2e-05, + "loss": 18.6924, + "step": 258 + }, + { + "epoch": 0.06018881626724764, + "grad_norm": 4.0708136558532715, + "learning_rate": 1.2046511627906978e-05, + "loss": 17.9385, + "step": 259 + }, + { + "epoch": 0.060421205519244736, + "grad_norm": 3.7562873363494873, + "learning_rate": 1.2093023255813954e-05, + "loss": 18.6306, + "step": 260 + }, + { + "epoch": 0.06065359477124183, + "grad_norm": 3.478846311569214, + "learning_rate": 1.2139534883720932e-05, + "loss": 17.6045, + "step": 261 + }, + { + "epoch": 0.06088598402323892, + "grad_norm": 3.856374740600586, + "learning_rate": 1.2186046511627908e-05, + "loss": 18.0965, + "step": 262 + }, + { + "epoch": 0.06111837327523602, + "grad_norm": 3.801011800765991, + "learning_rate": 1.2232558139534886e-05, + "loss": 17.9616, + "step": 263 + }, + { + "epoch": 0.061350762527233114, + "grad_norm": 3.5122885704040527, + "learning_rate": 1.2279069767441863e-05, + "loss": 18.4966, + "step": 264 + }, + { + "epoch": 0.06158315177923021, + "grad_norm": 3.5582761764526367, + "learning_rate": 1.2325581395348838e-05, + "loss": 18.7009, + "step": 265 + }, + { + "epoch": 0.06181554103122731, + "grad_norm": 3.692471504211426, + "learning_rate": 1.2372093023255815e-05, + "loss": 18.3971, + "step": 266 + }, + { + "epoch": 0.0620479302832244, + "grad_norm": 3.5772359371185303, + "learning_rate": 1.2418604651162791e-05, + "loss": 17.9516, + "step": 267 + }, + { + "epoch": 0.06228031953522149, + "grad_norm": 3.8218705654144287, + "learning_rate": 1.2465116279069769e-05, + "loss": 18.3463, + "step": 268 + }, + { + "epoch": 0.0625127087872186, + "grad_norm": 4.316270351409912, + "learning_rate": 1.2511627906976745e-05, + "loss": 18.3133, + "step": 269 + }, + { + "epoch": 0.06274509803921569, + "grad_norm": 3.8528950214385986, + "learning_rate": 1.2558139534883723e-05, + "loss": 18.2704, + "step": 270 + }, + { + "epoch": 0.06297748729121277, + "grad_norm": 3.6803700923919678, + "learning_rate": 1.26046511627907e-05, + "loss": 17.9739, + "step": 271 + }, + { + "epoch": 0.06320987654320988, + "grad_norm": 3.8369193077087402, + "learning_rate": 1.2651162790697675e-05, + "loss": 18.2926, + "step": 272 + }, + { + "epoch": 0.06344226579520697, + "grad_norm": 3.720733165740967, + "learning_rate": 1.2697674418604653e-05, + "loss": 18.0671, + "step": 273 + }, + { + "epoch": 0.06367465504720407, + "grad_norm": 3.9842491149902344, + "learning_rate": 1.2744186046511629e-05, + "loss": 17.6356, + "step": 274 + }, + { + "epoch": 0.06390704429920116, + "grad_norm": 3.9499080181121826, + "learning_rate": 1.2790697674418606e-05, + "loss": 18.4675, + "step": 275 + }, + { + "epoch": 0.06413943355119826, + "grad_norm": 3.5684282779693604, + "learning_rate": 1.2837209302325582e-05, + "loss": 17.8636, + "step": 276 + }, + { + "epoch": 0.06437182280319535, + "grad_norm": 3.379713773727417, + "learning_rate": 1.288372093023256e-05, + "loss": 17.2395, + "step": 277 + }, + { + "epoch": 0.06460421205519244, + "grad_norm": 3.9376871585845947, + "learning_rate": 1.2930232558139534e-05, + "loss": 18.4145, + "step": 278 + }, + { + "epoch": 0.06483660130718955, + "grad_norm": 3.3383421897888184, + "learning_rate": 1.2976744186046512e-05, + "loss": 17.2742, + "step": 279 + }, + { + "epoch": 0.06506899055918663, + "grad_norm": 3.6591813564300537, + "learning_rate": 1.302325581395349e-05, + "loss": 18.0751, + "step": 280 + }, + { + "epoch": 0.06530137981118374, + "grad_norm": 3.480224847793579, + "learning_rate": 1.3069767441860466e-05, + "loss": 18.3957, + "step": 281 + }, + { + "epoch": 0.06553376906318083, + "grad_norm": 3.4964263439178467, + "learning_rate": 1.3116279069767443e-05, + "loss": 17.7124, + "step": 282 + }, + { + "epoch": 0.06576615831517792, + "grad_norm": 3.809523105621338, + "learning_rate": 1.316279069767442e-05, + "loss": 18.2031, + "step": 283 + }, + { + "epoch": 0.06599854756717502, + "grad_norm": 3.656151056289673, + "learning_rate": 1.3209302325581397e-05, + "loss": 18.3264, + "step": 284 + }, + { + "epoch": 0.06623093681917211, + "grad_norm": 3.467252016067505, + "learning_rate": 1.3255813953488372e-05, + "loss": 17.9996, + "step": 285 + }, + { + "epoch": 0.06646332607116921, + "grad_norm": 3.634566307067871, + "learning_rate": 1.330232558139535e-05, + "loss": 17.4897, + "step": 286 + }, + { + "epoch": 0.0666957153231663, + "grad_norm": 3.9336273670196533, + "learning_rate": 1.3348837209302327e-05, + "loss": 18.1633, + "step": 287 + }, + { + "epoch": 0.0669281045751634, + "grad_norm": 3.555816173553467, + "learning_rate": 1.3395348837209303e-05, + "loss": 17.0052, + "step": 288 + }, + { + "epoch": 0.0671604938271605, + "grad_norm": 4.001568794250488, + "learning_rate": 1.344186046511628e-05, + "loss": 17.1214, + "step": 289 + }, + { + "epoch": 0.06739288307915758, + "grad_norm": 3.6928117275238037, + "learning_rate": 1.3488372093023257e-05, + "loss": 18.6073, + "step": 290 + }, + { + "epoch": 0.06762527233115469, + "grad_norm": 6.437382698059082, + "learning_rate": 1.3534883720930234e-05, + "loss": 19.0403, + "step": 291 + }, + { + "epoch": 0.06785766158315178, + "grad_norm": 3.9120633602142334, + "learning_rate": 1.358139534883721e-05, + "loss": 18.1861, + "step": 292 + }, + { + "epoch": 0.06809005083514888, + "grad_norm": 3.575441598892212, + "learning_rate": 1.3627906976744188e-05, + "loss": 17.5766, + "step": 293 + }, + { + "epoch": 0.06832244008714597, + "grad_norm": 3.8892085552215576, + "learning_rate": 1.3674418604651163e-05, + "loss": 17.6582, + "step": 294 + }, + { + "epoch": 0.06855482933914306, + "grad_norm": 4.147434234619141, + "learning_rate": 1.372093023255814e-05, + "loss": 17.6783, + "step": 295 + }, + { + "epoch": 0.06878721859114016, + "grad_norm": 3.7185921669006348, + "learning_rate": 1.3767441860465118e-05, + "loss": 18.598, + "step": 296 + }, + { + "epoch": 0.06901960784313725, + "grad_norm": 3.547592878341675, + "learning_rate": 1.3813953488372094e-05, + "loss": 17.2241, + "step": 297 + }, + { + "epoch": 0.06925199709513435, + "grad_norm": 3.567194700241089, + "learning_rate": 1.3860465116279072e-05, + "loss": 17.6632, + "step": 298 + }, + { + "epoch": 0.06948438634713144, + "grad_norm": 3.6078646183013916, + "learning_rate": 1.3906976744186048e-05, + "loss": 17.3342, + "step": 299 + }, + { + "epoch": 0.06971677559912855, + "grad_norm": 5.060980796813965, + "learning_rate": 1.3953488372093025e-05, + "loss": 18.248, + "step": 300 + }, + { + "epoch": 0.06994916485112564, + "grad_norm": 3.8163092136383057, + "learning_rate": 1.4e-05, + "loss": 18.8651, + "step": 301 + }, + { + "epoch": 0.07018155410312273, + "grad_norm": 7.5272979736328125, + "learning_rate": 1.4046511627906978e-05, + "loss": 18.5087, + "step": 302 + }, + { + "epoch": 0.07041394335511983, + "grad_norm": 3.8674848079681396, + "learning_rate": 1.4093023255813955e-05, + "loss": 18.0118, + "step": 303 + }, + { + "epoch": 0.07064633260711692, + "grad_norm": 3.3658862113952637, + "learning_rate": 1.4139534883720931e-05, + "loss": 17.9206, + "step": 304 + }, + { + "epoch": 0.07087872185911402, + "grad_norm": 3.450105667114258, + "learning_rate": 1.4186046511627909e-05, + "loss": 17.9865, + "step": 305 + }, + { + "epoch": 0.07111111111111111, + "grad_norm": 3.656397819519043, + "learning_rate": 1.4232558139534885e-05, + "loss": 17.7723, + "step": 306 + }, + { + "epoch": 0.0713435003631082, + "grad_norm": 3.608548879623413, + "learning_rate": 1.4279069767441863e-05, + "loss": 17.7717, + "step": 307 + }, + { + "epoch": 0.0715758896151053, + "grad_norm": 4.149332523345947, + "learning_rate": 1.4325581395348837e-05, + "loss": 17.2335, + "step": 308 + }, + { + "epoch": 0.07180827886710239, + "grad_norm": 3.7570385932922363, + "learning_rate": 1.4372093023255815e-05, + "loss": 19.1757, + "step": 309 + }, + { + "epoch": 0.0720406681190995, + "grad_norm": 3.7134764194488525, + "learning_rate": 1.441860465116279e-05, + "loss": 18.5106, + "step": 310 + }, + { + "epoch": 0.07227305737109659, + "grad_norm": 4.089855670928955, + "learning_rate": 1.4465116279069768e-05, + "loss": 18.2535, + "step": 311 + }, + { + "epoch": 0.07250544662309368, + "grad_norm": 3.771491527557373, + "learning_rate": 1.4511627906976746e-05, + "loss": 17.9823, + "step": 312 + }, + { + "epoch": 0.07273783587509078, + "grad_norm": 3.530592918395996, + "learning_rate": 1.4558139534883722e-05, + "loss": 18.0873, + "step": 313 + }, + { + "epoch": 0.07297022512708787, + "grad_norm": 3.4882304668426514, + "learning_rate": 1.46046511627907e-05, + "loss": 17.7156, + "step": 314 + }, + { + "epoch": 0.07320261437908497, + "grad_norm": 3.911482334136963, + "learning_rate": 1.4651162790697674e-05, + "loss": 17.4516, + "step": 315 + }, + { + "epoch": 0.07343500363108206, + "grad_norm": 5.0393147468566895, + "learning_rate": 1.4697674418604652e-05, + "loss": 18.7077, + "step": 316 + }, + { + "epoch": 0.07366739288307916, + "grad_norm": 3.5663230419158936, + "learning_rate": 1.4744186046511628e-05, + "loss": 19.1063, + "step": 317 + }, + { + "epoch": 0.07389978213507625, + "grad_norm": 3.516441583633423, + "learning_rate": 1.4790697674418606e-05, + "loss": 17.5238, + "step": 318 + }, + { + "epoch": 0.07413217138707334, + "grad_norm": 3.8650007247924805, + "learning_rate": 1.4837209302325583e-05, + "loss": 18.3545, + "step": 319 + }, + { + "epoch": 0.07436456063907045, + "grad_norm": 3.677690029144287, + "learning_rate": 1.488372093023256e-05, + "loss": 18.2536, + "step": 320 + }, + { + "epoch": 0.07459694989106753, + "grad_norm": 3.4910953044891357, + "learning_rate": 1.4930232558139537e-05, + "loss": 17.8629, + "step": 321 + }, + { + "epoch": 0.07482933914306464, + "grad_norm": 3.432175636291504, + "learning_rate": 1.4976744186046512e-05, + "loss": 18.4669, + "step": 322 + }, + { + "epoch": 0.07506172839506173, + "grad_norm": 3.305755376815796, + "learning_rate": 1.5023255813953491e-05, + "loss": 17.3632, + "step": 323 + }, + { + "epoch": 0.07529411764705882, + "grad_norm": 3.517207622528076, + "learning_rate": 1.5069767441860465e-05, + "loss": 18.1465, + "step": 324 + }, + { + "epoch": 0.07552650689905592, + "grad_norm": 3.4206652641296387, + "learning_rate": 1.5116279069767443e-05, + "loss": 17.8764, + "step": 325 + }, + { + "epoch": 0.07575889615105301, + "grad_norm": 3.4705026149749756, + "learning_rate": 1.5162790697674419e-05, + "loss": 18.6085, + "step": 326 + }, + { + "epoch": 0.07599128540305011, + "grad_norm": 3.3913893699645996, + "learning_rate": 1.5209302325581397e-05, + "loss": 18.0571, + "step": 327 + }, + { + "epoch": 0.0762236746550472, + "grad_norm": 3.3311445713043213, + "learning_rate": 1.5255813953488374e-05, + "loss": 18.5188, + "step": 328 + }, + { + "epoch": 0.0764560639070443, + "grad_norm": 3.480900764465332, + "learning_rate": 1.530232558139535e-05, + "loss": 18.5841, + "step": 329 + }, + { + "epoch": 0.0766884531590414, + "grad_norm": 3.3120267391204834, + "learning_rate": 1.5348837209302328e-05, + "loss": 17.695, + "step": 330 + }, + { + "epoch": 0.07692084241103848, + "grad_norm": 3.7028563022613525, + "learning_rate": 1.5395348837209303e-05, + "loss": 17.2543, + "step": 331 + }, + { + "epoch": 0.07715323166303559, + "grad_norm": 3.984405040740967, + "learning_rate": 1.544186046511628e-05, + "loss": 17.3793, + "step": 332 + }, + { + "epoch": 0.07738562091503268, + "grad_norm": 3.6556973457336426, + "learning_rate": 1.5488372093023255e-05, + "loss": 17.352, + "step": 333 + }, + { + "epoch": 0.07761801016702978, + "grad_norm": 3.5273361206054688, + "learning_rate": 1.5534883720930232e-05, + "loss": 17.478, + "step": 334 + }, + { + "epoch": 0.07785039941902687, + "grad_norm": 3.508176326751709, + "learning_rate": 1.558139534883721e-05, + "loss": 18.4643, + "step": 335 + }, + { + "epoch": 0.07808278867102396, + "grad_norm": 3.5183770656585693, + "learning_rate": 1.5627906976744188e-05, + "loss": 18.5463, + "step": 336 + }, + { + "epoch": 0.07831517792302106, + "grad_norm": 3.6263458728790283, + "learning_rate": 1.5674418604651165e-05, + "loss": 17.6755, + "step": 337 + }, + { + "epoch": 0.07854756717501815, + "grad_norm": 4.315125465393066, + "learning_rate": 1.572093023255814e-05, + "loss": 17.7361, + "step": 338 + }, + { + "epoch": 0.07877995642701525, + "grad_norm": 5.864964962005615, + "learning_rate": 1.5767441860465117e-05, + "loss": 18.4478, + "step": 339 + }, + { + "epoch": 0.07901234567901234, + "grad_norm": 3.566304922103882, + "learning_rate": 1.5813953488372095e-05, + "loss": 17.9369, + "step": 340 + }, + { + "epoch": 0.07924473493100945, + "grad_norm": 3.186277151107788, + "learning_rate": 1.5860465116279073e-05, + "loss": 18.0213, + "step": 341 + }, + { + "epoch": 0.07947712418300654, + "grad_norm": 3.483596086502075, + "learning_rate": 1.5906976744186047e-05, + "loss": 18.0873, + "step": 342 + }, + { + "epoch": 0.07970951343500363, + "grad_norm": 3.721497058868408, + "learning_rate": 1.5953488372093025e-05, + "loss": 18.7007, + "step": 343 + }, + { + "epoch": 0.07994190268700073, + "grad_norm": 3.614356517791748, + "learning_rate": 1.6000000000000003e-05, + "loss": 16.7364, + "step": 344 + }, + { + "epoch": 0.08017429193899782, + "grad_norm": 3.3342583179473877, + "learning_rate": 1.6046511627906977e-05, + "loss": 17.7285, + "step": 345 + }, + { + "epoch": 0.08040668119099492, + "grad_norm": 3.4198083877563477, + "learning_rate": 1.6093023255813955e-05, + "loss": 18.9526, + "step": 346 + }, + { + "epoch": 0.08063907044299201, + "grad_norm": 4.748954772949219, + "learning_rate": 1.6139534883720932e-05, + "loss": 19.0985, + "step": 347 + }, + { + "epoch": 0.0808714596949891, + "grad_norm": 3.3348329067230225, + "learning_rate": 1.618604651162791e-05, + "loss": 17.8259, + "step": 348 + }, + { + "epoch": 0.0811038489469862, + "grad_norm": 3.5097804069519043, + "learning_rate": 1.6232558139534884e-05, + "loss": 19.6798, + "step": 349 + }, + { + "epoch": 0.0813362381989833, + "grad_norm": 3.5242037773132324, + "learning_rate": 1.6279069767441862e-05, + "loss": 18.9695, + "step": 350 + }, + { + "epoch": 0.0815686274509804, + "grad_norm": 3.4178953170776367, + "learning_rate": 1.632558139534884e-05, + "loss": 17.6828, + "step": 351 + }, + { + "epoch": 0.08180101670297749, + "grad_norm": 3.345144748687744, + "learning_rate": 1.6372093023255814e-05, + "loss": 18.4595, + "step": 352 + }, + { + "epoch": 0.08203340595497459, + "grad_norm": 3.29679274559021, + "learning_rate": 1.6418604651162792e-05, + "loss": 18.262, + "step": 353 + }, + { + "epoch": 0.08226579520697168, + "grad_norm": 3.293379306793213, + "learning_rate": 1.646511627906977e-05, + "loss": 18.639, + "step": 354 + }, + { + "epoch": 0.08249818445896877, + "grad_norm": 3.8169469833374023, + "learning_rate": 1.6511627906976747e-05, + "loss": 17.9769, + "step": 355 + }, + { + "epoch": 0.08273057371096587, + "grad_norm": 3.8283629417419434, + "learning_rate": 1.6558139534883722e-05, + "loss": 19.0479, + "step": 356 + }, + { + "epoch": 0.08296296296296296, + "grad_norm": 3.4971818923950195, + "learning_rate": 1.66046511627907e-05, + "loss": 18.0541, + "step": 357 + }, + { + "epoch": 0.08319535221496006, + "grad_norm": 3.2270302772521973, + "learning_rate": 1.6651162790697674e-05, + "loss": 18.2322, + "step": 358 + }, + { + "epoch": 0.08342774146695715, + "grad_norm": 3.2319812774658203, + "learning_rate": 1.669767441860465e-05, + "loss": 18.3206, + "step": 359 + }, + { + "epoch": 0.08366013071895424, + "grad_norm": 5.238990306854248, + "learning_rate": 1.674418604651163e-05, + "loss": 18.2816, + "step": 360 + }, + { + "epoch": 0.08389251997095135, + "grad_norm": 8.066431999206543, + "learning_rate": 1.6790697674418607e-05, + "loss": 18.7904, + "step": 361 + }, + { + "epoch": 0.08412490922294844, + "grad_norm": 3.591968059539795, + "learning_rate": 1.6837209302325585e-05, + "loss": 18.0727, + "step": 362 + }, + { + "epoch": 0.08435729847494554, + "grad_norm": 3.8969624042510986, + "learning_rate": 1.688372093023256e-05, + "loss": 18.2316, + "step": 363 + }, + { + "epoch": 0.08458968772694263, + "grad_norm": 3.7996835708618164, + "learning_rate": 1.6930232558139537e-05, + "loss": 16.9886, + "step": 364 + }, + { + "epoch": 0.08482207697893972, + "grad_norm": 3.3400421142578125, + "learning_rate": 1.697674418604651e-05, + "loss": 17.7432, + "step": 365 + }, + { + "epoch": 0.08505446623093682, + "grad_norm": 3.5794003009796143, + "learning_rate": 1.702325581395349e-05, + "loss": 18.4217, + "step": 366 + }, + { + "epoch": 0.08528685548293391, + "grad_norm": 3.3261191844940186, + "learning_rate": 1.7069767441860466e-05, + "loss": 17.9001, + "step": 367 + }, + { + "epoch": 0.08551924473493101, + "grad_norm": 4.441987037658691, + "learning_rate": 1.7116279069767444e-05, + "loss": 18.3131, + "step": 368 + }, + { + "epoch": 0.0857516339869281, + "grad_norm": 3.258875608444214, + "learning_rate": 1.7162790697674422e-05, + "loss": 17.6206, + "step": 369 + }, + { + "epoch": 0.0859840232389252, + "grad_norm": 3.3434982299804688, + "learning_rate": 1.7209302325581396e-05, + "loss": 18.1855, + "step": 370 + }, + { + "epoch": 0.0862164124909223, + "grad_norm": 3.2634081840515137, + "learning_rate": 1.7255813953488374e-05, + "loss": 18.6688, + "step": 371 + }, + { + "epoch": 0.08644880174291938, + "grad_norm": 3.3531720638275146, + "learning_rate": 1.7302325581395348e-05, + "loss": 17.8542, + "step": 372 + }, + { + "epoch": 0.08668119099491649, + "grad_norm": 3.393190622329712, + "learning_rate": 1.7348837209302326e-05, + "loss": 18.5051, + "step": 373 + }, + { + "epoch": 0.08691358024691358, + "grad_norm": 3.655961751937866, + "learning_rate": 1.7395348837209304e-05, + "loss": 18.0783, + "step": 374 + }, + { + "epoch": 0.08714596949891068, + "grad_norm": 3.3484907150268555, + "learning_rate": 1.744186046511628e-05, + "loss": 18.5244, + "step": 375 + }, + { + "epoch": 0.08737835875090777, + "grad_norm": 3.4280431270599365, + "learning_rate": 1.748837209302326e-05, + "loss": 17.7738, + "step": 376 + }, + { + "epoch": 0.08761074800290486, + "grad_norm": 3.2714524269104004, + "learning_rate": 1.7534883720930233e-05, + "loss": 18.7599, + "step": 377 + }, + { + "epoch": 0.08784313725490196, + "grad_norm": 3.214895725250244, + "learning_rate": 1.758139534883721e-05, + "loss": 18.0765, + "step": 378 + }, + { + "epoch": 0.08807552650689905, + "grad_norm": 3.33461594581604, + "learning_rate": 1.7627906976744185e-05, + "loss": 18.3254, + "step": 379 + }, + { + "epoch": 0.08830791575889615, + "grad_norm": 3.2023751735687256, + "learning_rate": 1.7674418604651163e-05, + "loss": 18.1327, + "step": 380 + }, + { + "epoch": 0.08854030501089324, + "grad_norm": 3.530059814453125, + "learning_rate": 1.772093023255814e-05, + "loss": 19.1009, + "step": 381 + }, + { + "epoch": 0.08877269426289035, + "grad_norm": 3.381943464279175, + "learning_rate": 1.776744186046512e-05, + "loss": 18.6865, + "step": 382 + }, + { + "epoch": 0.08900508351488744, + "grad_norm": 3.1378443241119385, + "learning_rate": 1.7813953488372096e-05, + "loss": 18.4367, + "step": 383 + }, + { + "epoch": 0.08923747276688453, + "grad_norm": 3.4055888652801514, + "learning_rate": 1.786046511627907e-05, + "loss": 17.9776, + "step": 384 + }, + { + "epoch": 0.08946986201888163, + "grad_norm": 3.1735641956329346, + "learning_rate": 1.790697674418605e-05, + "loss": 17.9923, + "step": 385 + }, + { + "epoch": 0.08970225127087872, + "grad_norm": 3.3726327419281006, + "learning_rate": 1.7953488372093023e-05, + "loss": 18.1302, + "step": 386 + }, + { + "epoch": 0.08993464052287582, + "grad_norm": 3.9069607257843018, + "learning_rate": 1.8e-05, + "loss": 19.4718, + "step": 387 + }, + { + "epoch": 0.09016702977487291, + "grad_norm": 3.4644503593444824, + "learning_rate": 1.8046511627906978e-05, + "loss": 18.3016, + "step": 388 + }, + { + "epoch": 0.09039941902687, + "grad_norm": 3.298508644104004, + "learning_rate": 1.8093023255813956e-05, + "loss": 17.2642, + "step": 389 + }, + { + "epoch": 0.0906318082788671, + "grad_norm": 3.0324482917785645, + "learning_rate": 1.813953488372093e-05, + "loss": 17.922, + "step": 390 + }, + { + "epoch": 0.0908641975308642, + "grad_norm": 3.658705472946167, + "learning_rate": 1.8186046511627908e-05, + "loss": 18.2138, + "step": 391 + }, + { + "epoch": 0.0910965867828613, + "grad_norm": 3.451089859008789, + "learning_rate": 1.8232558139534886e-05, + "loss": 18.2493, + "step": 392 + }, + { + "epoch": 0.09132897603485839, + "grad_norm": 3.2850892543792725, + "learning_rate": 1.827906976744186e-05, + "loss": 16.9391, + "step": 393 + }, + { + "epoch": 0.09156136528685549, + "grad_norm": 3.198296546936035, + "learning_rate": 1.8325581395348838e-05, + "loss": 17.7039, + "step": 394 + }, + { + "epoch": 0.09179375453885258, + "grad_norm": 4.173604488372803, + "learning_rate": 1.8372093023255815e-05, + "loss": 17.1875, + "step": 395 + }, + { + "epoch": 0.09202614379084967, + "grad_norm": 3.087350368499756, + "learning_rate": 1.8418604651162793e-05, + "loss": 17.1559, + "step": 396 + }, + { + "epoch": 0.09225853304284677, + "grad_norm": 3.278406858444214, + "learning_rate": 1.8465116279069767e-05, + "loss": 18.0708, + "step": 397 + }, + { + "epoch": 0.09249092229484386, + "grad_norm": 3.374535322189331, + "learning_rate": 1.8511627906976745e-05, + "loss": 18.4028, + "step": 398 + }, + { + "epoch": 0.09272331154684096, + "grad_norm": 3.2857275009155273, + "learning_rate": 1.8558139534883723e-05, + "loss": 17.6422, + "step": 399 + }, + { + "epoch": 0.09295570079883805, + "grad_norm": 3.283919334411621, + "learning_rate": 1.86046511627907e-05, + "loss": 17.0072, + "step": 400 + }, + { + "epoch": 0.09318809005083514, + "grad_norm": 3.3224189281463623, + "learning_rate": 1.865116279069768e-05, + "loss": 18.1239, + "step": 401 + }, + { + "epoch": 0.09342047930283225, + "grad_norm": 3.6017894744873047, + "learning_rate": 1.8697674418604653e-05, + "loss": 18.983, + "step": 402 + }, + { + "epoch": 0.09365286855482934, + "grad_norm": 3.19246506690979, + "learning_rate": 1.874418604651163e-05, + "loss": 17.5918, + "step": 403 + }, + { + "epoch": 0.09388525780682644, + "grad_norm": 3.675748825073242, + "learning_rate": 1.8790697674418605e-05, + "loss": 18.2238, + "step": 404 + }, + { + "epoch": 0.09411764705882353, + "grad_norm": 3.162240505218506, + "learning_rate": 1.8837209302325582e-05, + "loss": 18.1303, + "step": 405 + }, + { + "epoch": 0.09435003631082063, + "grad_norm": 3.448535680770874, + "learning_rate": 1.888372093023256e-05, + "loss": 18.6549, + "step": 406 + }, + { + "epoch": 0.09458242556281772, + "grad_norm": 3.1251165866851807, + "learning_rate": 1.8930232558139538e-05, + "loss": 17.5927, + "step": 407 + }, + { + "epoch": 0.09481481481481481, + "grad_norm": 3.1586577892303467, + "learning_rate": 1.8976744186046516e-05, + "loss": 17.7957, + "step": 408 + }, + { + "epoch": 0.09504720406681191, + "grad_norm": 3.1509134769439697, + "learning_rate": 1.902325581395349e-05, + "loss": 18.1667, + "step": 409 + }, + { + "epoch": 0.095279593318809, + "grad_norm": 6.760782241821289, + "learning_rate": 1.9069767441860468e-05, + "loss": 17.4292, + "step": 410 + }, + { + "epoch": 0.0955119825708061, + "grad_norm": 3.123307228088379, + "learning_rate": 1.9116279069767442e-05, + "loss": 18.2401, + "step": 411 + }, + { + "epoch": 0.0957443718228032, + "grad_norm": 4.043407917022705, + "learning_rate": 1.916279069767442e-05, + "loss": 17.909, + "step": 412 + }, + { + "epoch": 0.09597676107480028, + "grad_norm": 3.2319583892822266, + "learning_rate": 1.9209302325581397e-05, + "loss": 18.0798, + "step": 413 + }, + { + "epoch": 0.09620915032679739, + "grad_norm": 3.2952518463134766, + "learning_rate": 1.9255813953488375e-05, + "loss": 17.1568, + "step": 414 + }, + { + "epoch": 0.09644153957879448, + "grad_norm": 3.120741844177246, + "learning_rate": 1.9302325581395353e-05, + "loss": 17.2377, + "step": 415 + }, + { + "epoch": 0.09667392883079158, + "grad_norm": 3.3381829261779785, + "learning_rate": 1.9348837209302327e-05, + "loss": 17.6726, + "step": 416 + }, + { + "epoch": 0.09690631808278867, + "grad_norm": 3.284946918487549, + "learning_rate": 1.9395348837209305e-05, + "loss": 17.41, + "step": 417 + }, + { + "epoch": 0.09713870733478576, + "grad_norm": 3.778778553009033, + "learning_rate": 1.944186046511628e-05, + "loss": 17.3003, + "step": 418 + }, + { + "epoch": 0.09737109658678286, + "grad_norm": 3.160585641860962, + "learning_rate": 1.9488372093023257e-05, + "loss": 17.4826, + "step": 419 + }, + { + "epoch": 0.09760348583877995, + "grad_norm": 3.195775270462036, + "learning_rate": 1.9534883720930235e-05, + "loss": 17.8377, + "step": 420 + }, + { + "epoch": 0.09783587509077706, + "grad_norm": 3.23506498336792, + "learning_rate": 1.9581395348837212e-05, + "loss": 17.7652, + "step": 421 + }, + { + "epoch": 0.09806826434277414, + "grad_norm": 3.013066053390503, + "learning_rate": 1.9627906976744187e-05, + "loss": 17.5734, + "step": 422 + }, + { + "epoch": 0.09830065359477125, + "grad_norm": 3.2095870971679688, + "learning_rate": 1.9674418604651164e-05, + "loss": 17.8652, + "step": 423 + }, + { + "epoch": 0.09853304284676834, + "grad_norm": 3.1595847606658936, + "learning_rate": 1.9720930232558142e-05, + "loss": 17.936, + "step": 424 + }, + { + "epoch": 0.09876543209876543, + "grad_norm": 3.494704484939575, + "learning_rate": 1.9767441860465116e-05, + "loss": 18.3488, + "step": 425 + }, + { + "epoch": 0.09899782135076253, + "grad_norm": 3.071258783340454, + "learning_rate": 1.9813953488372094e-05, + "loss": 18.1062, + "step": 426 + }, + { + "epoch": 0.09923021060275962, + "grad_norm": 3.035994291305542, + "learning_rate": 1.9860465116279072e-05, + "loss": 18.3351, + "step": 427 + }, + { + "epoch": 0.09946259985475672, + "grad_norm": 3.0994319915771484, + "learning_rate": 1.990697674418605e-05, + "loss": 17.2118, + "step": 428 + }, + { + "epoch": 0.09969498910675381, + "grad_norm": 3.075526475906372, + "learning_rate": 1.9953488372093024e-05, + "loss": 18.4037, + "step": 429 + }, + { + "epoch": 0.0999273783587509, + "grad_norm": 7.554640293121338, + "learning_rate": 2e-05, + "loss": 18.054, + "step": 430 + }, + { + "epoch": 0.100159767610748, + "grad_norm": 3.0975537300109863, + "learning_rate": 1.999999926177631e-05, + "loss": 17.7861, + "step": 431 + }, + { + "epoch": 0.1003921568627451, + "grad_norm": 2.921966314315796, + "learning_rate": 1.9999997047105345e-05, + "loss": 18.0135, + "step": 432 + }, + { + "epoch": 0.1006245461147422, + "grad_norm": 3.687349796295166, + "learning_rate": 1.9999993355987432e-05, + "loss": 17.9585, + "step": 433 + }, + { + "epoch": 0.10085693536673929, + "grad_norm": 2.9744203090667725, + "learning_rate": 1.9999988188423115e-05, + "loss": 17.8611, + "step": 434 + }, + { + "epoch": 0.10108932461873639, + "grad_norm": 3.1407835483551025, + "learning_rate": 1.999998154441316e-05, + "loss": 18.2899, + "step": 435 + }, + { + "epoch": 0.10132171387073348, + "grad_norm": 4.216432094573975, + "learning_rate": 1.9999973423958545e-05, + "loss": 18.9724, + "step": 436 + }, + { + "epoch": 0.10155410312273057, + "grad_norm": 3.1987805366516113, + "learning_rate": 1.9999963827060473e-05, + "loss": 18.4337, + "step": 437 + }, + { + "epoch": 0.10178649237472767, + "grad_norm": 3.2519288063049316, + "learning_rate": 1.999995275372036e-05, + "loss": 17.8635, + "step": 438 + }, + { + "epoch": 0.10201888162672476, + "grad_norm": 3.271782398223877, + "learning_rate": 1.9999940203939836e-05, + "loss": 17.9394, + "step": 439 + }, + { + "epoch": 0.10225127087872186, + "grad_norm": 3.437530755996704, + "learning_rate": 1.9999926177720756e-05, + "loss": 17.3496, + "step": 440 + }, + { + "epoch": 0.10248366013071895, + "grad_norm": 3.1285107135772705, + "learning_rate": 1.9999910675065197e-05, + "loss": 17.1369, + "step": 441 + }, + { + "epoch": 0.10271604938271604, + "grad_norm": 3.3575356006622314, + "learning_rate": 1.9999893695975442e-05, + "loss": 17.3691, + "step": 442 + }, + { + "epoch": 0.10294843863471315, + "grad_norm": 3.1434097290039062, + "learning_rate": 1.9999875240453995e-05, + "loss": 18.7483, + "step": 443 + }, + { + "epoch": 0.10318082788671024, + "grad_norm": 3.138368606567383, + "learning_rate": 1.9999855308503587e-05, + "loss": 18.5809, + "step": 444 + }, + { + "epoch": 0.10341321713870734, + "grad_norm": 3.0776402950286865, + "learning_rate": 1.999983390012716e-05, + "loss": 18.4092, + "step": 445 + }, + { + "epoch": 0.10364560639070443, + "grad_norm": 2.965453624725342, + "learning_rate": 1.9999811015327872e-05, + "loss": 17.4226, + "step": 446 + }, + { + "epoch": 0.10387799564270153, + "grad_norm": 3.2347495555877686, + "learning_rate": 1.99997866541091e-05, + "loss": 17.4158, + "step": 447 + }, + { + "epoch": 0.10411038489469862, + "grad_norm": 2.953941822052002, + "learning_rate": 1.999976081647445e-05, + "loss": 18.2575, + "step": 448 + }, + { + "epoch": 0.10434277414669571, + "grad_norm": 3.069338798522949, + "learning_rate": 1.9999733502427728e-05, + "loss": 18.4498, + "step": 449 + }, + { + "epoch": 0.10457516339869281, + "grad_norm": 2.965364694595337, + "learning_rate": 1.9999704711972973e-05, + "loss": 18.0754, + "step": 450 + }, + { + "epoch": 0.1048075526506899, + "grad_norm": 3.32725191116333, + "learning_rate": 1.9999674445114428e-05, + "loss": 17.5431, + "step": 451 + }, + { + "epoch": 0.105039941902687, + "grad_norm": 20.52411460876465, + "learning_rate": 1.9999642701856568e-05, + "loss": 17.4651, + "step": 452 + }, + { + "epoch": 0.1052723311546841, + "grad_norm": 3.5454232692718506, + "learning_rate": 1.9999609482204075e-05, + "loss": 18.9815, + "step": 453 + }, + { + "epoch": 0.10550472040668119, + "grad_norm": 3.418797492980957, + "learning_rate": 1.9999574786161863e-05, + "loss": 17.371, + "step": 454 + }, + { + "epoch": 0.10573710965867829, + "grad_norm": 3.0474841594696045, + "learning_rate": 1.9999538613735043e-05, + "loss": 16.5582, + "step": 455 + }, + { + "epoch": 0.10596949891067538, + "grad_norm": 3.2310688495635986, + "learning_rate": 1.9999500964928963e-05, + "loss": 18.616, + "step": 456 + }, + { + "epoch": 0.10620188816267248, + "grad_norm": 3.333477258682251, + "learning_rate": 1.9999461839749176e-05, + "loss": 18.6183, + "step": 457 + }, + { + "epoch": 0.10643427741466957, + "grad_norm": 3.0272600650787354, + "learning_rate": 1.9999421238201465e-05, + "loss": 18.133, + "step": 458 + }, + { + "epoch": 0.10666666666666667, + "grad_norm": 3.1247332096099854, + "learning_rate": 1.9999379160291827e-05, + "loss": 17.8756, + "step": 459 + }, + { + "epoch": 0.10689905591866376, + "grad_norm": 3.3831725120544434, + "learning_rate": 1.9999335606026462e-05, + "loss": 17.5948, + "step": 460 + }, + { + "epoch": 0.10713144517066085, + "grad_norm": 3.1394691467285156, + "learning_rate": 1.999929057541181e-05, + "loss": 18.3517, + "step": 461 + }, + { + "epoch": 0.10736383442265796, + "grad_norm": 3.3611927032470703, + "learning_rate": 1.999924406845452e-05, + "loss": 17.8499, + "step": 462 + }, + { + "epoch": 0.10759622367465504, + "grad_norm": 3.1807494163513184, + "learning_rate": 1.9999196085161454e-05, + "loss": 18.6841, + "step": 463 + }, + { + "epoch": 0.10782861292665215, + "grad_norm": 5.262155055999756, + "learning_rate": 1.99991466255397e-05, + "loss": 18.2198, + "step": 464 + }, + { + "epoch": 0.10806100217864924, + "grad_norm": 3.229748010635376, + "learning_rate": 1.9999095689596556e-05, + "loss": 18.5307, + "step": 465 + }, + { + "epoch": 0.10829339143064633, + "grad_norm": 3.0456931591033936, + "learning_rate": 1.9999043277339546e-05, + "loss": 17.422, + "step": 466 + }, + { + "epoch": 0.10852578068264343, + "grad_norm": 3.2565791606903076, + "learning_rate": 1.999898938877641e-05, + "loss": 18.0352, + "step": 467 + }, + { + "epoch": 0.10875816993464052, + "grad_norm": 3.2834503650665283, + "learning_rate": 1.99989340239151e-05, + "loss": 17.3778, + "step": 468 + }, + { + "epoch": 0.10899055918663762, + "grad_norm": 3.2067325115203857, + "learning_rate": 1.9998877182763794e-05, + "loss": 17.9919, + "step": 469 + }, + { + "epoch": 0.10922294843863471, + "grad_norm": 2.902224540710449, + "learning_rate": 1.9998818865330883e-05, + "loss": 17.7875, + "step": 470 + }, + { + "epoch": 0.1094553376906318, + "grad_norm": 3.1095948219299316, + "learning_rate": 1.9998759071624974e-05, + "loss": 18.4646, + "step": 471 + }, + { + "epoch": 0.1096877269426289, + "grad_norm": 3.2787251472473145, + "learning_rate": 1.99986978016549e-05, + "loss": 17.7591, + "step": 472 + }, + { + "epoch": 0.109920116194626, + "grad_norm": 3.2579798698425293, + "learning_rate": 1.999863505542971e-05, + "loss": 17.4869, + "step": 473 + }, + { + "epoch": 0.1101525054466231, + "grad_norm": 3.0950372219085693, + "learning_rate": 1.9998570832958654e-05, + "loss": 17.7208, + "step": 474 + }, + { + "epoch": 0.11038489469862019, + "grad_norm": 3.1104252338409424, + "learning_rate": 1.999850513425123e-05, + "loss": 18.4309, + "step": 475 + }, + { + "epoch": 0.11061728395061729, + "grad_norm": 3.1015267372131348, + "learning_rate": 1.999843795931713e-05, + "loss": 18.4988, + "step": 476 + }, + { + "epoch": 0.11084967320261438, + "grad_norm": 4.105751991271973, + "learning_rate": 1.9998369308166277e-05, + "loss": 18.2708, + "step": 477 + }, + { + "epoch": 0.11108206245461147, + "grad_norm": 3.0888772010803223, + "learning_rate": 1.99982991808088e-05, + "loss": 18.2811, + "step": 478 + }, + { + "epoch": 0.11131445170660857, + "grad_norm": 3.7492012977600098, + "learning_rate": 1.999822757725506e-05, + "loss": 19.673, + "step": 479 + }, + { + "epoch": 0.11154684095860566, + "grad_norm": 3.1698732376098633, + "learning_rate": 1.9998154497515622e-05, + "loss": 17.3466, + "step": 480 + }, + { + "epoch": 0.11177923021060276, + "grad_norm": 5.324582576751709, + "learning_rate": 1.9998079941601282e-05, + "loss": 18.9234, + "step": 481 + }, + { + "epoch": 0.11201161946259985, + "grad_norm": 2.9719929695129395, + "learning_rate": 1.9998003909523046e-05, + "loss": 18.3768, + "step": 482 + }, + { + "epoch": 0.11224400871459694, + "grad_norm": 3.201737880706787, + "learning_rate": 1.9997926401292137e-05, + "loss": 18.0386, + "step": 483 + }, + { + "epoch": 0.11247639796659405, + "grad_norm": 3.036372423171997, + "learning_rate": 1.999784741692e-05, + "loss": 17.7368, + "step": 484 + }, + { + "epoch": 0.11270878721859114, + "grad_norm": 3.0685172080993652, + "learning_rate": 1.9997766956418298e-05, + "loss": 17.9101, + "step": 485 + }, + { + "epoch": 0.11294117647058824, + "grad_norm": 3.395789861679077, + "learning_rate": 1.9997685019798913e-05, + "loss": 18.4521, + "step": 486 + }, + { + "epoch": 0.11317356572258533, + "grad_norm": 2.961766004562378, + "learning_rate": 1.9997601607073933e-05, + "loss": 18.2782, + "step": 487 + }, + { + "epoch": 0.11340595497458243, + "grad_norm": 3.098738193511963, + "learning_rate": 1.9997516718255686e-05, + "loss": 17.7447, + "step": 488 + }, + { + "epoch": 0.11363834422657952, + "grad_norm": 4.200319766998291, + "learning_rate": 1.9997430353356692e-05, + "loss": 18.3112, + "step": 489 + }, + { + "epoch": 0.11387073347857661, + "grad_norm": 3.1535415649414062, + "learning_rate": 1.9997342512389716e-05, + "loss": 19.1743, + "step": 490 + }, + { + "epoch": 0.11410312273057371, + "grad_norm": 3.1857833862304688, + "learning_rate": 1.999725319536772e-05, + "loss": 18.7033, + "step": 491 + }, + { + "epoch": 0.1143355119825708, + "grad_norm": 2.9382424354553223, + "learning_rate": 1.999716240230389e-05, + "loss": 17.6167, + "step": 492 + }, + { + "epoch": 0.1145679012345679, + "grad_norm": 3.0145058631896973, + "learning_rate": 1.9997070133211635e-05, + "loss": 18.2509, + "step": 493 + }, + { + "epoch": 0.114800290486565, + "grad_norm": 3.117936611175537, + "learning_rate": 1.9996976388104573e-05, + "loss": 16.9005, + "step": 494 + }, + { + "epoch": 0.11503267973856209, + "grad_norm": 3.017090320587158, + "learning_rate": 1.999688116699655e-05, + "loss": 17.7208, + "step": 495 + }, + { + "epoch": 0.11526506899055919, + "grad_norm": 2.8525919914245605, + "learning_rate": 1.999678446990162e-05, + "loss": 18.1989, + "step": 496 + }, + { + "epoch": 0.11549745824255628, + "grad_norm": 3.464137077331543, + "learning_rate": 1.9996686296834066e-05, + "loss": 18.7222, + "step": 497 + }, + { + "epoch": 0.11572984749455338, + "grad_norm": 3.0478742122650146, + "learning_rate": 1.999658664780838e-05, + "loss": 17.6723, + "step": 498 + }, + { + "epoch": 0.11596223674655047, + "grad_norm": 3.0696768760681152, + "learning_rate": 1.9996485522839275e-05, + "loss": 18.9471, + "step": 499 + }, + { + "epoch": 0.11619462599854757, + "grad_norm": 4.1362833976745605, + "learning_rate": 1.999638292194168e-05, + "loss": 19.6111, + "step": 500 + }, + { + "epoch": 0.11642701525054466, + "grad_norm": 2.9504284858703613, + "learning_rate": 1.9996278845130742e-05, + "loss": 17.7491, + "step": 501 + }, + { + "epoch": 0.11665940450254175, + "grad_norm": 3.36262845993042, + "learning_rate": 1.999617329242183e-05, + "loss": 18.1068, + "step": 502 + }, + { + "epoch": 0.11689179375453886, + "grad_norm": 3.5156407356262207, + "learning_rate": 1.9996066263830533e-05, + "loss": 19.4341, + "step": 503 + }, + { + "epoch": 0.11712418300653595, + "grad_norm": 2.880293130874634, + "learning_rate": 1.9995957759372642e-05, + "loss": 18.2237, + "step": 504 + }, + { + "epoch": 0.11735657225853305, + "grad_norm": 3.0980148315429688, + "learning_rate": 1.9995847779064185e-05, + "loss": 18.458, + "step": 505 + }, + { + "epoch": 0.11758896151053014, + "grad_norm": 3.4051296710968018, + "learning_rate": 1.9995736322921398e-05, + "loss": 17.7479, + "step": 506 + }, + { + "epoch": 0.11782135076252723, + "grad_norm": 3.110182285308838, + "learning_rate": 1.999562339096074e-05, + "loss": 17.4237, + "step": 507 + }, + { + "epoch": 0.11805374001452433, + "grad_norm": 2.9809770584106445, + "learning_rate": 1.9995508983198878e-05, + "loss": 18.0953, + "step": 508 + }, + { + "epoch": 0.11828612926652142, + "grad_norm": 3.088197708129883, + "learning_rate": 1.999539309965271e-05, + "loss": 18.5404, + "step": 509 + }, + { + "epoch": 0.11851851851851852, + "grad_norm": 3.12239933013916, + "learning_rate": 1.9995275740339345e-05, + "loss": 18.2537, + "step": 510 + }, + { + "epoch": 0.11875090777051561, + "grad_norm": 2.7445249557495117, + "learning_rate": 1.9995156905276106e-05, + "loss": 18.0771, + "step": 511 + }, + { + "epoch": 0.11898329702251272, + "grad_norm": 2.8789167404174805, + "learning_rate": 1.999503659448054e-05, + "loss": 18.4819, + "step": 512 + }, + { + "epoch": 0.1192156862745098, + "grad_norm": 3.218357801437378, + "learning_rate": 1.9994914807970412e-05, + "loss": 17.6529, + "step": 513 + }, + { + "epoch": 0.1194480755265069, + "grad_norm": 3.3868248462677, + "learning_rate": 1.9994791545763707e-05, + "loss": 17.8093, + "step": 514 + }, + { + "epoch": 0.119680464778504, + "grad_norm": 3.1012020111083984, + "learning_rate": 1.9994666807878613e-05, + "loss": 17.9908, + "step": 515 + }, + { + "epoch": 0.11991285403050109, + "grad_norm": 3.985236644744873, + "learning_rate": 1.999454059433356e-05, + "loss": 18.151, + "step": 516 + }, + { + "epoch": 0.12014524328249819, + "grad_norm": 2.9063408374786377, + "learning_rate": 1.9994412905147172e-05, + "loss": 17.5124, + "step": 517 + }, + { + "epoch": 0.12037763253449528, + "grad_norm": 2.829680919647217, + "learning_rate": 1.999428374033831e-05, + "loss": 18.8793, + "step": 518 + }, + { + "epoch": 0.12061002178649237, + "grad_norm": 3.2908544540405273, + "learning_rate": 1.9994153099926032e-05, + "loss": 18.0214, + "step": 519 + }, + { + "epoch": 0.12084241103848947, + "grad_norm": 2.940373182296753, + "learning_rate": 1.999402098392964e-05, + "loss": 18.2692, + "step": 520 + }, + { + "epoch": 0.12107480029048656, + "grad_norm": 3.0552494525909424, + "learning_rate": 1.9993887392368636e-05, + "loss": 18.1523, + "step": 521 + }, + { + "epoch": 0.12130718954248366, + "grad_norm": 3.0401675701141357, + "learning_rate": 1.9993752325262742e-05, + "loss": 18.0113, + "step": 522 + }, + { + "epoch": 0.12153957879448075, + "grad_norm": 2.948077440261841, + "learning_rate": 1.9993615782631903e-05, + "loss": 18.2563, + "step": 523 + }, + { + "epoch": 0.12177196804647784, + "grad_norm": 2.9541962146759033, + "learning_rate": 1.9993477764496273e-05, + "loss": 19.1928, + "step": 524 + }, + { + "epoch": 0.12200435729847495, + "grad_norm": 3.2816431522369385, + "learning_rate": 1.9993338270876235e-05, + "loss": 19.0167, + "step": 525 + }, + { + "epoch": 0.12223674655047204, + "grad_norm": 2.9239914417266846, + "learning_rate": 1.9993197301792383e-05, + "loss": 18.0323, + "step": 526 + }, + { + "epoch": 0.12246913580246914, + "grad_norm": 2.9831740856170654, + "learning_rate": 1.999305485726553e-05, + "loss": 17.3766, + "step": 527 + }, + { + "epoch": 0.12270152505446623, + "grad_norm": 2.8943960666656494, + "learning_rate": 1.999291093731671e-05, + "loss": 18.7907, + "step": 528 + }, + { + "epoch": 0.12293391430646333, + "grad_norm": 2.9303321838378906, + "learning_rate": 1.9992765541967167e-05, + "loss": 16.9966, + "step": 529 + }, + { + "epoch": 0.12316630355846042, + "grad_norm": 3.1285953521728516, + "learning_rate": 1.9992618671238372e-05, + "loss": 17.9535, + "step": 530 + }, + { + "epoch": 0.12339869281045751, + "grad_norm": 3.144336462020874, + "learning_rate": 1.9992470325152005e-05, + "loss": 18.6857, + "step": 531 + }, + { + "epoch": 0.12363108206245461, + "grad_norm": 3.0163660049438477, + "learning_rate": 1.9992320503729975e-05, + "loss": 18.7912, + "step": 532 + }, + { + "epoch": 0.1238634713144517, + "grad_norm": 3.077420473098755, + "learning_rate": 1.9992169206994395e-05, + "loss": 18.6245, + "step": 533 + }, + { + "epoch": 0.1240958605664488, + "grad_norm": 2.932382822036743, + "learning_rate": 1.9992016434967612e-05, + "loss": 18.5288, + "step": 534 + }, + { + "epoch": 0.1243282498184459, + "grad_norm": 2.9145593643188477, + "learning_rate": 1.9991862187672174e-05, + "loss": 18.3664, + "step": 535 + }, + { + "epoch": 0.12456063907044299, + "grad_norm": 3.068211793899536, + "learning_rate": 1.9991706465130857e-05, + "loss": 18.8179, + "step": 536 + }, + { + "epoch": 0.12479302832244009, + "grad_norm": 2.797337293624878, + "learning_rate": 1.9991549267366655e-05, + "loss": 17.527, + "step": 537 + }, + { + "epoch": 0.1250254175744372, + "grad_norm": 3.061183452606201, + "learning_rate": 1.9991390594402778e-05, + "loss": 17.832, + "step": 538 + }, + { + "epoch": 0.12525780682643428, + "grad_norm": 2.754063367843628, + "learning_rate": 1.9991230446262647e-05, + "loss": 17.4085, + "step": 539 + }, + { + "epoch": 0.12549019607843137, + "grad_norm": 2.7730295658111572, + "learning_rate": 1.9991068822969915e-05, + "loss": 18.969, + "step": 540 + }, + { + "epoch": 0.12572258533042846, + "grad_norm": 3.0470497608184814, + "learning_rate": 1.9990905724548438e-05, + "loss": 18.9989, + "step": 541 + }, + { + "epoch": 0.12595497458242555, + "grad_norm": 2.9356095790863037, + "learning_rate": 1.9990741151022302e-05, + "loss": 18.2135, + "step": 542 + }, + { + "epoch": 0.12618736383442267, + "grad_norm": 2.9353420734405518, + "learning_rate": 1.99905751024158e-05, + "loss": 17.733, + "step": 543 + }, + { + "epoch": 0.12641975308641976, + "grad_norm": 3.1570091247558594, + "learning_rate": 1.9990407578753456e-05, + "loss": 18.2592, + "step": 544 + }, + { + "epoch": 0.12665214233841685, + "grad_norm": 2.803720235824585, + "learning_rate": 1.9990238580059995e-05, + "loss": 17.7557, + "step": 545 + }, + { + "epoch": 0.12688453159041393, + "grad_norm": 3.611623525619507, + "learning_rate": 1.9990068106360375e-05, + "loss": 18.5292, + "step": 546 + }, + { + "epoch": 0.12711692084241105, + "grad_norm": 2.696885824203491, + "learning_rate": 1.9989896157679763e-05, + "loss": 18.7943, + "step": 547 + }, + { + "epoch": 0.12734931009440814, + "grad_norm": 2.9010086059570312, + "learning_rate": 1.9989722734043546e-05, + "loss": 17.3537, + "step": 548 + }, + { + "epoch": 0.12758169934640523, + "grad_norm": 3.157743453979492, + "learning_rate": 1.9989547835477328e-05, + "loss": 17.8421, + "step": 549 + }, + { + "epoch": 0.12781408859840232, + "grad_norm": 2.952998399734497, + "learning_rate": 1.9989371462006938e-05, + "loss": 19.3104, + "step": 550 + }, + { + "epoch": 0.1280464778503994, + "grad_norm": 3.0870354175567627, + "learning_rate": 1.9989193613658412e-05, + "loss": 18.2206, + "step": 551 + }, + { + "epoch": 0.12827886710239653, + "grad_norm": 3.4160077571868896, + "learning_rate": 1.998901429045801e-05, + "loss": 18.2056, + "step": 552 + }, + { + "epoch": 0.12851125635439362, + "grad_norm": 2.9436073303222656, + "learning_rate": 1.99888334924322e-05, + "loss": 18.7401, + "step": 553 + }, + { + "epoch": 0.1287436456063907, + "grad_norm": 2.952244758605957, + "learning_rate": 1.9988651219607688e-05, + "loss": 17.9825, + "step": 554 + }, + { + "epoch": 0.1289760348583878, + "grad_norm": 2.936718702316284, + "learning_rate": 1.998846747201138e-05, + "loss": 17.2751, + "step": 555 + }, + { + "epoch": 0.12920842411038488, + "grad_norm": 3.0740232467651367, + "learning_rate": 1.998828224967041e-05, + "loss": 17.5598, + "step": 556 + }, + { + "epoch": 0.129440813362382, + "grad_norm": 2.7879512310028076, + "learning_rate": 1.9988095552612114e-05, + "loss": 17.9406, + "step": 557 + }, + { + "epoch": 0.1296732026143791, + "grad_norm": 3.0110926628112793, + "learning_rate": 1.9987907380864063e-05, + "loss": 17.9349, + "step": 558 + }, + { + "epoch": 0.12990559186637618, + "grad_norm": 2.95853590965271, + "learning_rate": 1.9987717734454044e-05, + "loss": 18.5748, + "step": 559 + }, + { + "epoch": 0.13013798111837327, + "grad_norm": 3.13789439201355, + "learning_rate": 1.998752661341005e-05, + "loss": 18.2327, + "step": 560 + }, + { + "epoch": 0.13037037037037036, + "grad_norm": 2.8655247688293457, + "learning_rate": 1.998733401776031e-05, + "loss": 18.5794, + "step": 561 + }, + { + "epoch": 0.13060275962236748, + "grad_norm": 2.7477946281433105, + "learning_rate": 1.9987139947533248e-05, + "loss": 18.4549, + "step": 562 + }, + { + "epoch": 0.13083514887436457, + "grad_norm": 2.80985951423645, + "learning_rate": 1.998694440275752e-05, + "loss": 18.0796, + "step": 563 + }, + { + "epoch": 0.13106753812636165, + "grad_norm": 3.143578290939331, + "learning_rate": 1.9986747383462e-05, + "loss": 18.1999, + "step": 564 + }, + { + "epoch": 0.13129992737835874, + "grad_norm": 2.801487684249878, + "learning_rate": 1.9986548889675778e-05, + "loss": 17.7674, + "step": 565 + }, + { + "epoch": 0.13153231663035583, + "grad_norm": 2.9859771728515625, + "learning_rate": 1.998634892142816e-05, + "loss": 18.5026, + "step": 566 + }, + { + "epoch": 0.13176470588235295, + "grad_norm": 3.895986557006836, + "learning_rate": 1.9986147478748663e-05, + "loss": 19.0591, + "step": 567 + }, + { + "epoch": 0.13199709513435004, + "grad_norm": 2.8709545135498047, + "learning_rate": 1.9985944561667037e-05, + "loss": 18.4713, + "step": 568 + }, + { + "epoch": 0.13222948438634713, + "grad_norm": 2.9398419857025146, + "learning_rate": 1.998574017021324e-05, + "loss": 18.565, + "step": 569 + }, + { + "epoch": 0.13246187363834422, + "grad_norm": 3.043682813644409, + "learning_rate": 1.9985534304417448e-05, + "loss": 17.4909, + "step": 570 + }, + { + "epoch": 0.1326942628903413, + "grad_norm": 2.9130845069885254, + "learning_rate": 1.9985326964310054e-05, + "loss": 17.9512, + "step": 571 + }, + { + "epoch": 0.13292665214233843, + "grad_norm": 2.7633562088012695, + "learning_rate": 1.998511814992168e-05, + "loss": 17.8811, + "step": 572 + }, + { + "epoch": 0.13315904139433551, + "grad_norm": 2.7892661094665527, + "learning_rate": 1.9984907861283143e-05, + "loss": 18.0146, + "step": 573 + }, + { + "epoch": 0.1333914306463326, + "grad_norm": 3.9010612964630127, + "learning_rate": 1.99846960984255e-05, + "loss": 17.6527, + "step": 574 + }, + { + "epoch": 0.1336238198983297, + "grad_norm": 2.839122772216797, + "learning_rate": 1.9984482861380014e-05, + "loss": 18.3494, + "step": 575 + }, + { + "epoch": 0.1338562091503268, + "grad_norm": 3.141352891921997, + "learning_rate": 1.998426815017817e-05, + "loss": 17.5747, + "step": 576 + }, + { + "epoch": 0.1340885984023239, + "grad_norm": 2.712263822555542, + "learning_rate": 1.9984051964851662e-05, + "loss": 17.3247, + "step": 577 + }, + { + "epoch": 0.134320987654321, + "grad_norm": 3.0783400535583496, + "learning_rate": 1.998383430543242e-05, + "loss": 18.5336, + "step": 578 + }, + { + "epoch": 0.13455337690631808, + "grad_norm": 2.935525894165039, + "learning_rate": 1.998361517195257e-05, + "loss": 17.7972, + "step": 579 + }, + { + "epoch": 0.13478576615831517, + "grad_norm": 2.855074882507324, + "learning_rate": 1.9983394564444473e-05, + "loss": 18.0138, + "step": 580 + }, + { + "epoch": 0.13501815541031228, + "grad_norm": 2.8953263759613037, + "learning_rate": 1.99831724829407e-05, + "loss": 18.6876, + "step": 581 + }, + { + "epoch": 0.13525054466230937, + "grad_norm": 2.9411399364471436, + "learning_rate": 1.9982948927474036e-05, + "loss": 18.0006, + "step": 582 + }, + { + "epoch": 0.13548293391430646, + "grad_norm": 3.454739570617676, + "learning_rate": 1.998272389807749e-05, + "loss": 18.7943, + "step": 583 + }, + { + "epoch": 0.13571532316630355, + "grad_norm": 2.7670388221740723, + "learning_rate": 1.9982497394784285e-05, + "loss": 18.5692, + "step": 584 + }, + { + "epoch": 0.13594771241830064, + "grad_norm": 2.850893497467041, + "learning_rate": 1.9982269417627865e-05, + "loss": 18.51, + "step": 585 + }, + { + "epoch": 0.13618010167029776, + "grad_norm": 2.912470817565918, + "learning_rate": 1.998203996664189e-05, + "loss": 18.1899, + "step": 586 + }, + { + "epoch": 0.13641249092229485, + "grad_norm": 2.8883731365203857, + "learning_rate": 1.9981809041860236e-05, + "loss": 17.879, + "step": 587 + }, + { + "epoch": 0.13664488017429194, + "grad_norm": 2.821519136428833, + "learning_rate": 1.9981576643316996e-05, + "loss": 18.862, + "step": 588 + }, + { + "epoch": 0.13687726942628903, + "grad_norm": 3.1182096004486084, + "learning_rate": 1.9981342771046485e-05, + "loss": 17.8643, + "step": 589 + }, + { + "epoch": 0.13710965867828612, + "grad_norm": 3.2032463550567627, + "learning_rate": 1.9981107425083234e-05, + "loss": 17.9616, + "step": 590 + }, + { + "epoch": 0.13734204793028323, + "grad_norm": 2.9030349254608154, + "learning_rate": 1.9980870605461988e-05, + "loss": 18.8269, + "step": 591 + }, + { + "epoch": 0.13757443718228032, + "grad_norm": 2.7331626415252686, + "learning_rate": 1.9980632312217714e-05, + "loss": 18.0802, + "step": 592 + }, + { + "epoch": 0.1378068264342774, + "grad_norm": 3.1486124992370605, + "learning_rate": 1.9980392545385593e-05, + "loss": 18.3353, + "step": 593 + }, + { + "epoch": 0.1380392156862745, + "grad_norm": 3.609165668487549, + "learning_rate": 1.9980151305001028e-05, + "loss": 18.3181, + "step": 594 + }, + { + "epoch": 0.1382716049382716, + "grad_norm": 4.008858680725098, + "learning_rate": 1.997990859109963e-05, + "loss": 18.4314, + "step": 595 + }, + { + "epoch": 0.1385039941902687, + "grad_norm": 2.78974986076355, + "learning_rate": 1.9979664403717244e-05, + "loss": 17.3333, + "step": 596 + }, + { + "epoch": 0.1387363834422658, + "grad_norm": 2.827324628829956, + "learning_rate": 1.997941874288992e-05, + "loss": 18.6103, + "step": 597 + }, + { + "epoch": 0.1389687726942629, + "grad_norm": 2.7437796592712402, + "learning_rate": 1.9979171608653926e-05, + "loss": 18.1903, + "step": 598 + }, + { + "epoch": 0.13920116194625998, + "grad_norm": 2.7712392807006836, + "learning_rate": 1.9978923001045746e-05, + "loss": 18.1303, + "step": 599 + }, + { + "epoch": 0.1394335511982571, + "grad_norm": 2.8424813747406006, + "learning_rate": 1.9978672920102094e-05, + "loss": 17.7946, + "step": 600 + }, + { + "epoch": 0.13966594045025418, + "grad_norm": 2.782062530517578, + "learning_rate": 1.9978421365859892e-05, + "loss": 17.8595, + "step": 601 + }, + { + "epoch": 0.13989832970225127, + "grad_norm": 2.869297742843628, + "learning_rate": 1.9978168338356276e-05, + "loss": 17.4101, + "step": 602 + }, + { + "epoch": 0.14013071895424836, + "grad_norm": 2.710911512374878, + "learning_rate": 1.9977913837628608e-05, + "loss": 19.2557, + "step": 603 + }, + { + "epoch": 0.14036310820624545, + "grad_norm": 2.841189384460449, + "learning_rate": 1.997765786371446e-05, + "loss": 18.2527, + "step": 604 + }, + { + "epoch": 0.14059549745824257, + "grad_norm": 2.8594632148742676, + "learning_rate": 1.997740041665163e-05, + "loss": 18.0188, + "step": 605 + }, + { + "epoch": 0.14082788671023966, + "grad_norm": 3.0448238849639893, + "learning_rate": 1.9977141496478124e-05, + "loss": 18.5565, + "step": 606 + }, + { + "epoch": 0.14106027596223675, + "grad_norm": 2.9903404712677, + "learning_rate": 1.9976881103232174e-05, + "loss": 17.7872, + "step": 607 + }, + { + "epoch": 0.14129266521423384, + "grad_norm": 2.7240772247314453, + "learning_rate": 1.9976619236952225e-05, + "loss": 18.1148, + "step": 608 + }, + { + "epoch": 0.14152505446623093, + "grad_norm": 2.7726688385009766, + "learning_rate": 1.9976355897676936e-05, + "loss": 17.9911, + "step": 609 + }, + { + "epoch": 0.14175744371822804, + "grad_norm": 2.74287486076355, + "learning_rate": 1.9976091085445196e-05, + "loss": 17.9736, + "step": 610 + }, + { + "epoch": 0.14198983297022513, + "grad_norm": 2.919844627380371, + "learning_rate": 1.9975824800296097e-05, + "loss": 17.9724, + "step": 611 + }, + { + "epoch": 0.14222222222222222, + "grad_norm": 2.7291178703308105, + "learning_rate": 1.9975557042268955e-05, + "loss": 18.4252, + "step": 612 + }, + { + "epoch": 0.1424546114742193, + "grad_norm": 2.9070780277252197, + "learning_rate": 1.9975287811403302e-05, + "loss": 18.1904, + "step": 613 + }, + { + "epoch": 0.1426870007262164, + "grad_norm": 3.0127999782562256, + "learning_rate": 1.997501710773889e-05, + "loss": 17.3572, + "step": 614 + }, + { + "epoch": 0.14291938997821352, + "grad_norm": 2.672187566757202, + "learning_rate": 1.997474493131569e-05, + "loss": 17.0157, + "step": 615 + }, + { + "epoch": 0.1431517792302106, + "grad_norm": 3.083625078201294, + "learning_rate": 1.9974471282173882e-05, + "loss": 18.319, + "step": 616 + }, + { + "epoch": 0.1433841684822077, + "grad_norm": 3.297109603881836, + "learning_rate": 1.9974196160353872e-05, + "loss": 18.6075, + "step": 617 + }, + { + "epoch": 0.14361655773420479, + "grad_norm": 2.933663845062256, + "learning_rate": 1.9973919565896282e-05, + "loss": 18.2744, + "step": 618 + }, + { + "epoch": 0.14384894698620188, + "grad_norm": 2.8162341117858887, + "learning_rate": 1.9973641498841948e-05, + "loss": 16.5755, + "step": 619 + }, + { + "epoch": 0.144081336238199, + "grad_norm": 2.97687029838562, + "learning_rate": 1.997336195923192e-05, + "loss": 16.8672, + "step": 620 + }, + { + "epoch": 0.14431372549019608, + "grad_norm": 2.8831429481506348, + "learning_rate": 1.9973080947107483e-05, + "loss": 17.2895, + "step": 621 + }, + { + "epoch": 0.14454611474219317, + "grad_norm": 3.0448381900787354, + "learning_rate": 1.9972798462510114e-05, + "loss": 18.0001, + "step": 622 + }, + { + "epoch": 0.14477850399419026, + "grad_norm": 2.829512596130371, + "learning_rate": 1.9972514505481525e-05, + "loss": 18.3486, + "step": 623 + }, + { + "epoch": 0.14501089324618735, + "grad_norm": 6.292139053344727, + "learning_rate": 1.9972229076063644e-05, + "loss": 17.3262, + "step": 624 + }, + { + "epoch": 0.14524328249818447, + "grad_norm": 3.149273157119751, + "learning_rate": 1.9971942174298607e-05, + "loss": 17.9883, + "step": 625 + }, + { + "epoch": 0.14547567175018156, + "grad_norm": 2.894739866256714, + "learning_rate": 1.9971653800228782e-05, + "loss": 18.052, + "step": 626 + }, + { + "epoch": 0.14570806100217865, + "grad_norm": 2.953296422958374, + "learning_rate": 1.9971363953896733e-05, + "loss": 17.9716, + "step": 627 + }, + { + "epoch": 0.14594045025417574, + "grad_norm": 2.678398847579956, + "learning_rate": 1.997107263534527e-05, + "loss": 17.3898, + "step": 628 + }, + { + "epoch": 0.14617283950617285, + "grad_norm": 2.7700698375701904, + "learning_rate": 1.9970779844617393e-05, + "loss": 18.6072, + "step": 629 + }, + { + "epoch": 0.14640522875816994, + "grad_norm": 2.9212048053741455, + "learning_rate": 1.9970485581756337e-05, + "loss": 17.8928, + "step": 630 + }, + { + "epoch": 0.14663761801016703, + "grad_norm": 3.280808210372925, + "learning_rate": 1.9970189846805547e-05, + "loss": 18.283, + "step": 631 + }, + { + "epoch": 0.14687000726216412, + "grad_norm": 2.8070614337921143, + "learning_rate": 1.9969892639808683e-05, + "loss": 17.6852, + "step": 632 + }, + { + "epoch": 0.1471023965141612, + "grad_norm": 3.912789821624756, + "learning_rate": 1.996959396080963e-05, + "loss": 17.3576, + "step": 633 + }, + { + "epoch": 0.14733478576615833, + "grad_norm": 2.938298463821411, + "learning_rate": 1.9969293809852486e-05, + "loss": 18.6605, + "step": 634 + }, + { + "epoch": 0.14756717501815542, + "grad_norm": 2.795853614807129, + "learning_rate": 1.9968992186981567e-05, + "loss": 18.5334, + "step": 635 + }, + { + "epoch": 0.1477995642701525, + "grad_norm": 2.879486322402954, + "learning_rate": 1.99686890922414e-05, + "loss": 17.7618, + "step": 636 + }, + { + "epoch": 0.1480319535221496, + "grad_norm": 2.9893834590911865, + "learning_rate": 1.9968384525676744e-05, + "loss": 18.6412, + "step": 637 + }, + { + "epoch": 0.14826434277414668, + "grad_norm": 2.7966160774230957, + "learning_rate": 1.996807848733257e-05, + "loss": 19.5131, + "step": 638 + }, + { + "epoch": 0.1484967320261438, + "grad_norm": 2.9780690670013428, + "learning_rate": 1.9967770977254048e-05, + "loss": 18.3601, + "step": 639 + }, + { + "epoch": 0.1487291212781409, + "grad_norm": 2.7552342414855957, + "learning_rate": 1.996746199548659e-05, + "loss": 18.238, + "step": 640 + }, + { + "epoch": 0.14896151053013798, + "grad_norm": 2.7649216651916504, + "learning_rate": 1.996715154207581e-05, + "loss": 18.287, + "step": 641 + }, + { + "epoch": 0.14919389978213507, + "grad_norm": 2.7808516025543213, + "learning_rate": 1.9966839617067554e-05, + "loss": 18.124, + "step": 642 + }, + { + "epoch": 0.14942628903413216, + "grad_norm": 2.865553379058838, + "learning_rate": 1.996652622050787e-05, + "loss": 17.695, + "step": 643 + }, + { + "epoch": 0.14965867828612928, + "grad_norm": 2.9896483421325684, + "learning_rate": 1.996621135244303e-05, + "loss": 18.6045, + "step": 644 + }, + { + "epoch": 0.14989106753812637, + "grad_norm": 3.2423551082611084, + "learning_rate": 1.9965895012919524e-05, + "loss": 18.2977, + "step": 645 + }, + { + "epoch": 0.15012345679012346, + "grad_norm": 2.72836971282959, + "learning_rate": 1.9965577201984054e-05, + "loss": 19.464, + "step": 646 + }, + { + "epoch": 0.15035584604212054, + "grad_norm": 3.2376420497894287, + "learning_rate": 1.996525791968354e-05, + "loss": 18.0403, + "step": 647 + }, + { + "epoch": 0.15058823529411763, + "grad_norm": 3.3537232875823975, + "learning_rate": 1.996493716606514e-05, + "loss": 17.9176, + "step": 648 + }, + { + "epoch": 0.15082062454611475, + "grad_norm": 2.7713470458984375, + "learning_rate": 1.9964614941176194e-05, + "loss": 18.3915, + "step": 649 + }, + { + "epoch": 0.15105301379811184, + "grad_norm": 2.907902479171753, + "learning_rate": 1.996429124506428e-05, + "loss": 18.9959, + "step": 650 + }, + { + "epoch": 0.15128540305010893, + "grad_norm": 2.88332462310791, + "learning_rate": 1.99639660777772e-05, + "loss": 17.4989, + "step": 651 + }, + { + "epoch": 0.15151779230210602, + "grad_norm": 2.7088139057159424, + "learning_rate": 1.996363943936295e-05, + "loss": 18.1999, + "step": 652 + }, + { + "epoch": 0.15175018155410314, + "grad_norm": 2.92370867729187, + "learning_rate": 1.996331132986976e-05, + "loss": 18.2373, + "step": 653 + }, + { + "epoch": 0.15198257080610023, + "grad_norm": 2.683324098587036, + "learning_rate": 1.996298174934608e-05, + "loss": 17.9052, + "step": 654 + }, + { + "epoch": 0.15221496005809731, + "grad_norm": 4.355493545532227, + "learning_rate": 1.9962650697840563e-05, + "loss": 18.4954, + "step": 655 + }, + { + "epoch": 0.1524473493100944, + "grad_norm": 2.799452304840088, + "learning_rate": 1.9962318175402095e-05, + "loss": 17.7535, + "step": 656 + }, + { + "epoch": 0.1526797385620915, + "grad_norm": 2.8357386589050293, + "learning_rate": 1.9961984182079767e-05, + "loss": 17.3468, + "step": 657 + }, + { + "epoch": 0.1529121278140886, + "grad_norm": 2.8899292945861816, + "learning_rate": 1.9961648717922886e-05, + "loss": 18.5352, + "step": 658 + }, + { + "epoch": 0.1531445170660857, + "grad_norm": 2.9208061695098877, + "learning_rate": 1.996131178298099e-05, + "loss": 18.6234, + "step": 659 + }, + { + "epoch": 0.1533769063180828, + "grad_norm": 2.9949893951416016, + "learning_rate": 1.9960973377303823e-05, + "loss": 18.744, + "step": 660 + }, + { + "epoch": 0.15360929557007988, + "grad_norm": 2.77293062210083, + "learning_rate": 1.9960633500941347e-05, + "loss": 17.8814, + "step": 661 + }, + { + "epoch": 0.15384168482207697, + "grad_norm": 3.055614948272705, + "learning_rate": 1.9960292153943746e-05, + "loss": 17.6879, + "step": 662 + }, + { + "epoch": 0.15407407407407409, + "grad_norm": 2.989140272140503, + "learning_rate": 1.9959949336361414e-05, + "loss": 17.2015, + "step": 663 + }, + { + "epoch": 0.15430646332607117, + "grad_norm": 2.9825425148010254, + "learning_rate": 1.995960504824497e-05, + "loss": 18.1539, + "step": 664 + }, + { + "epoch": 0.15453885257806826, + "grad_norm": 2.8158645629882812, + "learning_rate": 1.9959259289645242e-05, + "loss": 18.0071, + "step": 665 + }, + { + "epoch": 0.15477124183006535, + "grad_norm": 2.78641414642334, + "learning_rate": 1.9958912060613284e-05, + "loss": 17.6983, + "step": 666 + }, + { + "epoch": 0.15500363108206244, + "grad_norm": 2.8356528282165527, + "learning_rate": 1.9958563361200362e-05, + "loss": 18.1806, + "step": 667 + }, + { + "epoch": 0.15523602033405956, + "grad_norm": 3.0194766521453857, + "learning_rate": 1.9958213191457958e-05, + "loss": 17.8911, + "step": 668 + }, + { + "epoch": 0.15546840958605665, + "grad_norm": 2.9541428089141846, + "learning_rate": 1.9957861551437772e-05, + "loss": 18.1039, + "step": 669 + }, + { + "epoch": 0.15570079883805374, + "grad_norm": 2.8022499084472656, + "learning_rate": 1.9957508441191722e-05, + "loss": 18.7734, + "step": 670 + }, + { + "epoch": 0.15593318809005083, + "grad_norm": 2.9086506366729736, + "learning_rate": 1.9957153860771944e-05, + "loss": 18.3214, + "step": 671 + }, + { + "epoch": 0.15616557734204792, + "grad_norm": 2.841510057449341, + "learning_rate": 1.9956797810230792e-05, + "loss": 18.9352, + "step": 672 + }, + { + "epoch": 0.15639796659404503, + "grad_norm": 3.076390266418457, + "learning_rate": 1.9956440289620833e-05, + "loss": 17.6648, + "step": 673 + }, + { + "epoch": 0.15663035584604212, + "grad_norm": 2.845917224884033, + "learning_rate": 1.9956081298994853e-05, + "loss": 18.6045, + "step": 674 + }, + { + "epoch": 0.1568627450980392, + "grad_norm": 2.6307528018951416, + "learning_rate": 1.9955720838405853e-05, + "loss": 18.5538, + "step": 675 + }, + { + "epoch": 0.1570951343500363, + "grad_norm": 2.885551929473877, + "learning_rate": 1.9955358907907054e-05, + "loss": 17.5943, + "step": 676 + }, + { + "epoch": 0.1573275236020334, + "grad_norm": 3.00240159034729, + "learning_rate": 1.9954995507551894e-05, + "loss": 17.4987, + "step": 677 + }, + { + "epoch": 0.1575599128540305, + "grad_norm": 2.861766815185547, + "learning_rate": 1.9954630637394027e-05, + "loss": 18.5384, + "step": 678 + }, + { + "epoch": 0.1577923021060276, + "grad_norm": 3.4827632904052734, + "learning_rate": 1.995426429748733e-05, + "loss": 18.248, + "step": 679 + }, + { + "epoch": 0.1580246913580247, + "grad_norm": 3.052103042602539, + "learning_rate": 1.995389648788588e-05, + "loss": 18.3641, + "step": 680 + }, + { + "epoch": 0.15825708061002178, + "grad_norm": 3.0805912017822266, + "learning_rate": 1.995352720864399e-05, + "loss": 19.875, + "step": 681 + }, + { + "epoch": 0.1584894698620189, + "grad_norm": 2.8581507205963135, + "learning_rate": 1.995315645981618e-05, + "loss": 17.6726, + "step": 682 + }, + { + "epoch": 0.15872185911401598, + "grad_norm": 2.8412435054779053, + "learning_rate": 1.9952784241457187e-05, + "loss": 17.3819, + "step": 683 + }, + { + "epoch": 0.15895424836601307, + "grad_norm": 8.43795394897461, + "learning_rate": 1.9952410553621967e-05, + "loss": 18.2731, + "step": 684 + }, + { + "epoch": 0.15918663761801016, + "grad_norm": 2.8452131748199463, + "learning_rate": 1.99520353963657e-05, + "loss": 18.4487, + "step": 685 + }, + { + "epoch": 0.15941902687000725, + "grad_norm": 2.728714942932129, + "learning_rate": 1.995165876974377e-05, + "loss": 18.1177, + "step": 686 + }, + { + "epoch": 0.15965141612200437, + "grad_norm": 2.877495765686035, + "learning_rate": 1.995128067381178e-05, + "loss": 18.6149, + "step": 687 + }, + { + "epoch": 0.15988380537400146, + "grad_norm": 2.641606092453003, + "learning_rate": 1.9950901108625564e-05, + "loss": 17.7348, + "step": 688 + }, + { + "epoch": 0.16011619462599855, + "grad_norm": 2.7167680263519287, + "learning_rate": 1.9950520074241157e-05, + "loss": 17.9017, + "step": 689 + }, + { + "epoch": 0.16034858387799564, + "grad_norm": 2.858625888824463, + "learning_rate": 1.9950137570714817e-05, + "loss": 18.8778, + "step": 690 + }, + { + "epoch": 0.16058097312999273, + "grad_norm": 2.776167631149292, + "learning_rate": 1.994975359810302e-05, + "loss": 17.4513, + "step": 691 + }, + { + "epoch": 0.16081336238198984, + "grad_norm": 2.8554530143737793, + "learning_rate": 1.9949368156462454e-05, + "loss": 18.1039, + "step": 692 + }, + { + "epoch": 0.16104575163398693, + "grad_norm": 2.751213550567627, + "learning_rate": 1.994898124585003e-05, + "loss": 18.1264, + "step": 693 + }, + { + "epoch": 0.16127814088598402, + "grad_norm": 2.822524309158325, + "learning_rate": 1.9948592866322875e-05, + "loss": 17.9335, + "step": 694 + }, + { + "epoch": 0.1615105301379811, + "grad_norm": 2.8693859577178955, + "learning_rate": 1.994820301793833e-05, + "loss": 16.8857, + "step": 695 + }, + { + "epoch": 0.1617429193899782, + "grad_norm": 2.953662633895874, + "learning_rate": 1.9947811700753955e-05, + "loss": 18.9042, + "step": 696 + }, + { + "epoch": 0.16197530864197532, + "grad_norm": 2.913361072540283, + "learning_rate": 1.994741891482752e-05, + "loss": 17.4475, + "step": 697 + }, + { + "epoch": 0.1622076978939724, + "grad_norm": 2.711160898208618, + "learning_rate": 1.9947024660217025e-05, + "loss": 17.6527, + "step": 698 + }, + { + "epoch": 0.1624400871459695, + "grad_norm": 3.0052194595336914, + "learning_rate": 1.9946628936980677e-05, + "loss": 18.9021, + "step": 699 + }, + { + "epoch": 0.1626724763979666, + "grad_norm": 2.631972074508667, + "learning_rate": 1.99462317451769e-05, + "loss": 18.0962, + "step": 700 + }, + { + "epoch": 0.16290486564996368, + "grad_norm": 2.7524895668029785, + "learning_rate": 1.9945833084864344e-05, + "loss": 17.8874, + "step": 701 + }, + { + "epoch": 0.1631372549019608, + "grad_norm": 3.4751687049865723, + "learning_rate": 1.994543295610186e-05, + "loss": 18.2095, + "step": 702 + }, + { + "epoch": 0.16336964415395788, + "grad_norm": 2.762866258621216, + "learning_rate": 1.9945031358948532e-05, + "loss": 18.3421, + "step": 703 + }, + { + "epoch": 0.16360203340595497, + "grad_norm": 3.6840274333953857, + "learning_rate": 1.994462829346365e-05, + "loss": 18.0353, + "step": 704 + }, + { + "epoch": 0.16383442265795206, + "grad_norm": 2.7081425189971924, + "learning_rate": 1.9944223759706728e-05, + "loss": 18.2468, + "step": 705 + }, + { + "epoch": 0.16406681190994918, + "grad_norm": 2.8804073333740234, + "learning_rate": 1.994381775773749e-05, + "loss": 18.0649, + "step": 706 + }, + { + "epoch": 0.16429920116194627, + "grad_norm": 4.437283992767334, + "learning_rate": 1.9943410287615882e-05, + "loss": 17.5685, + "step": 707 + }, + { + "epoch": 0.16453159041394336, + "grad_norm": 2.9928603172302246, + "learning_rate": 1.994300134940206e-05, + "loss": 18.0798, + "step": 708 + }, + { + "epoch": 0.16476397966594045, + "grad_norm": 2.6296799182891846, + "learning_rate": 1.994259094315641e-05, + "loss": 18.0406, + "step": 709 + }, + { + "epoch": 0.16499636891793754, + "grad_norm": 3.0125551223754883, + "learning_rate": 1.994217906893952e-05, + "loss": 17.2032, + "step": 710 + }, + { + "epoch": 0.16522875816993465, + "grad_norm": 2.7542524337768555, + "learning_rate": 1.9941765726812203e-05, + "loss": 17.8861, + "step": 711 + }, + { + "epoch": 0.16546114742193174, + "grad_norm": 2.8780219554901123, + "learning_rate": 1.9941350916835487e-05, + "loss": 18.2782, + "step": 712 + }, + { + "epoch": 0.16569353667392883, + "grad_norm": 2.6947550773620605, + "learning_rate": 1.9940934639070618e-05, + "loss": 17.49, + "step": 713 + }, + { + "epoch": 0.16592592592592592, + "grad_norm": 2.8547770977020264, + "learning_rate": 1.9940516893579055e-05, + "loss": 18.5843, + "step": 714 + }, + { + "epoch": 0.166158315177923, + "grad_norm": 3.0855331420898438, + "learning_rate": 1.9940097680422475e-05, + "loss": 18.3423, + "step": 715 + }, + { + "epoch": 0.16639070442992013, + "grad_norm": 2.8855645656585693, + "learning_rate": 1.9939676999662774e-05, + "loss": 19.1609, + "step": 716 + }, + { + "epoch": 0.16662309368191722, + "grad_norm": 2.8654608726501465, + "learning_rate": 1.9939254851362063e-05, + "loss": 17.2833, + "step": 717 + }, + { + "epoch": 0.1668554829339143, + "grad_norm": 2.612332344055176, + "learning_rate": 1.9938831235582673e-05, + "loss": 17.3906, + "step": 718 + }, + { + "epoch": 0.1670878721859114, + "grad_norm": 2.7734720706939697, + "learning_rate": 1.993840615238714e-05, + "loss": 18.6413, + "step": 719 + }, + { + "epoch": 0.16732026143790849, + "grad_norm": 2.7946829795837402, + "learning_rate": 1.9937979601838234e-05, + "loss": 18.7204, + "step": 720 + }, + { + "epoch": 0.1675526506899056, + "grad_norm": 2.8178184032440186, + "learning_rate": 1.9937551583998934e-05, + "loss": 18.4479, + "step": 721 + }, + { + "epoch": 0.1677850399419027, + "grad_norm": 3.2416820526123047, + "learning_rate": 1.9937122098932428e-05, + "loss": 18.2476, + "step": 722 + }, + { + "epoch": 0.16801742919389978, + "grad_norm": 2.9113428592681885, + "learning_rate": 1.993669114670213e-05, + "loss": 17.6628, + "step": 723 + }, + { + "epoch": 0.16824981844589687, + "grad_norm": 2.9109878540039062, + "learning_rate": 1.9936258727371667e-05, + "loss": 18.7459, + "step": 724 + }, + { + "epoch": 0.16848220769789396, + "grad_norm": 4.8288397789001465, + "learning_rate": 1.9935824841004884e-05, + "loss": 18.3403, + "step": 725 + }, + { + "epoch": 0.16871459694989108, + "grad_norm": 2.8178861141204834, + "learning_rate": 1.9935389487665845e-05, + "loss": 17.7636, + "step": 726 + }, + { + "epoch": 0.16894698620188817, + "grad_norm": 2.742717981338501, + "learning_rate": 1.9934952667418825e-05, + "loss": 17.9501, + "step": 727 + }, + { + "epoch": 0.16917937545388526, + "grad_norm": 2.7493958473205566, + "learning_rate": 1.9934514380328312e-05, + "loss": 18.3378, + "step": 728 + }, + { + "epoch": 0.16941176470588235, + "grad_norm": 2.6544125080108643, + "learning_rate": 1.9934074626459027e-05, + "loss": 18.0423, + "step": 729 + }, + { + "epoch": 0.16964415395787943, + "grad_norm": 2.6616995334625244, + "learning_rate": 1.9933633405875893e-05, + "loss": 18.663, + "step": 730 + }, + { + "epoch": 0.16987654320987655, + "grad_norm": 2.6970863342285156, + "learning_rate": 1.9933190718644054e-05, + "loss": 17.7935, + "step": 731 + }, + { + "epoch": 0.17010893246187364, + "grad_norm": 2.96567702293396, + "learning_rate": 1.9932746564828873e-05, + "loss": 18.7407, + "step": 732 + }, + { + "epoch": 0.17034132171387073, + "grad_norm": 3.0526671409606934, + "learning_rate": 1.993230094449592e-05, + "loss": 18.2893, + "step": 733 + }, + { + "epoch": 0.17057371096586782, + "grad_norm": 2.640695571899414, + "learning_rate": 1.9931853857710996e-05, + "loss": 17.6847, + "step": 734 + }, + { + "epoch": 0.17080610021786494, + "grad_norm": 2.604551315307617, + "learning_rate": 1.993140530454011e-05, + "loss": 18.3005, + "step": 735 + }, + { + "epoch": 0.17103848946986203, + "grad_norm": 2.8730525970458984, + "learning_rate": 1.9930955285049483e-05, + "loss": 18.4957, + "step": 736 + }, + { + "epoch": 0.17127087872185912, + "grad_norm": 3.0433573722839355, + "learning_rate": 1.993050379930556e-05, + "loss": 18.8115, + "step": 737 + }, + { + "epoch": 0.1715032679738562, + "grad_norm": 2.9607744216918945, + "learning_rate": 1.993005084737501e-05, + "loss": 18.5096, + "step": 738 + }, + { + "epoch": 0.1717356572258533, + "grad_norm": 2.682396173477173, + "learning_rate": 1.9929596429324693e-05, + "loss": 18.9024, + "step": 739 + }, + { + "epoch": 0.1719680464778504, + "grad_norm": 2.620882987976074, + "learning_rate": 1.9929140545221713e-05, + "loss": 18.5603, + "step": 740 + }, + { + "epoch": 0.1722004357298475, + "grad_norm": 2.8384382724761963, + "learning_rate": 1.9928683195133373e-05, + "loss": 18.1056, + "step": 741 + }, + { + "epoch": 0.1724328249818446, + "grad_norm": 2.770620346069336, + "learning_rate": 1.9928224379127203e-05, + "loss": 18.6186, + "step": 742 + }, + { + "epoch": 0.17266521423384168, + "grad_norm": 2.664231061935425, + "learning_rate": 1.9927764097270944e-05, + "loss": 18.0166, + "step": 743 + }, + { + "epoch": 0.17289760348583877, + "grad_norm": 2.7593092918395996, + "learning_rate": 1.9927302349632548e-05, + "loss": 18.1048, + "step": 744 + }, + { + "epoch": 0.17312999273783589, + "grad_norm": 2.8378801345825195, + "learning_rate": 1.9926839136280195e-05, + "loss": 17.9741, + "step": 745 + }, + { + "epoch": 0.17336238198983298, + "grad_norm": 2.746194362640381, + "learning_rate": 1.992637445728228e-05, + "loss": 18.649, + "step": 746 + }, + { + "epoch": 0.17359477124183006, + "grad_norm": 2.7503626346588135, + "learning_rate": 1.9925908312707404e-05, + "loss": 18.1542, + "step": 747 + }, + { + "epoch": 0.17382716049382715, + "grad_norm": 2.7475967407226562, + "learning_rate": 1.9925440702624387e-05, + "loss": 18.8892, + "step": 748 + }, + { + "epoch": 0.17405954974582424, + "grad_norm": 2.7589261531829834, + "learning_rate": 1.992497162710228e-05, + "loss": 18.2188, + "step": 749 + }, + { + "epoch": 0.17429193899782136, + "grad_norm": 2.717372417449951, + "learning_rate": 1.9924501086210334e-05, + "loss": 18.1052, + "step": 750 + }, + { + "epoch": 0.17452432824981845, + "grad_norm": 2.9678900241851807, + "learning_rate": 1.992402908001802e-05, + "loss": 17.0838, + "step": 751 + }, + { + "epoch": 0.17475671750181554, + "grad_norm": 2.6439297199249268, + "learning_rate": 1.992355560859503e-05, + "loss": 18.6967, + "step": 752 + }, + { + "epoch": 0.17498910675381263, + "grad_norm": 2.8549234867095947, + "learning_rate": 1.992308067201127e-05, + "loss": 19.3089, + "step": 753 + }, + { + "epoch": 0.17522149600580972, + "grad_norm": 3.2110579013824463, + "learning_rate": 1.992260427033686e-05, + "loss": 18.1072, + "step": 754 + }, + { + "epoch": 0.17545388525780684, + "grad_norm": 2.772761821746826, + "learning_rate": 1.9922126403642138e-05, + "loss": 18.4768, + "step": 755 + }, + { + "epoch": 0.17568627450980392, + "grad_norm": 2.8113958835601807, + "learning_rate": 1.9921647071997663e-05, + "loss": 17.6501, + "step": 756 + }, + { + "epoch": 0.17591866376180101, + "grad_norm": 2.7534728050231934, + "learning_rate": 1.99211662754742e-05, + "loss": 18.8393, + "step": 757 + }, + { + "epoch": 0.1761510530137981, + "grad_norm": 2.698235034942627, + "learning_rate": 1.9920684014142736e-05, + "loss": 16.9733, + "step": 758 + }, + { + "epoch": 0.17638344226579522, + "grad_norm": 24.50564193725586, + "learning_rate": 1.992020028807448e-05, + "loss": 17.6961, + "step": 759 + }, + { + "epoch": 0.1766158315177923, + "grad_norm": 3.073601245880127, + "learning_rate": 1.9919715097340846e-05, + "loss": 17.7465, + "step": 760 + }, + { + "epoch": 0.1768482207697894, + "grad_norm": 2.773771047592163, + "learning_rate": 1.9919228442013475e-05, + "loss": 17.8776, + "step": 761 + }, + { + "epoch": 0.1770806100217865, + "grad_norm": 2.787386894226074, + "learning_rate": 1.9918740322164213e-05, + "loss": 17.8756, + "step": 762 + }, + { + "epoch": 0.17731299927378358, + "grad_norm": 2.6047582626342773, + "learning_rate": 1.9918250737865134e-05, + "loss": 17.9856, + "step": 763 + }, + { + "epoch": 0.1775453885257807, + "grad_norm": 2.783803701400757, + "learning_rate": 1.9917759689188516e-05, + "loss": 17.5059, + "step": 764 + }, + { + "epoch": 0.17777777777777778, + "grad_norm": 3.113325595855713, + "learning_rate": 1.9917267176206868e-05, + "loss": 17.2257, + "step": 765 + }, + { + "epoch": 0.17801016702977487, + "grad_norm": 2.997460126876831, + "learning_rate": 1.99167731989929e-05, + "loss": 17.3609, + "step": 766 + }, + { + "epoch": 0.17824255628177196, + "grad_norm": 2.852473020553589, + "learning_rate": 1.991627775761955e-05, + "loss": 18.7325, + "step": 767 + }, + { + "epoch": 0.17847494553376905, + "grad_norm": 2.680943727493286, + "learning_rate": 1.991578085215997e-05, + "loss": 18.5097, + "step": 768 + }, + { + "epoch": 0.17870733478576617, + "grad_norm": 2.9002373218536377, + "learning_rate": 1.991528248268751e-05, + "loss": 17.7687, + "step": 769 + }, + { + "epoch": 0.17893972403776326, + "grad_norm": 2.6856627464294434, + "learning_rate": 1.991478264927577e-05, + "loss": 19.5634, + "step": 770 + }, + { + "epoch": 0.17917211328976035, + "grad_norm": 2.892932415008545, + "learning_rate": 1.9914281351998536e-05, + "loss": 18.5324, + "step": 771 + }, + { + "epoch": 0.17940450254175744, + "grad_norm": 2.820997476577759, + "learning_rate": 1.991377859092983e-05, + "loss": 17.8472, + "step": 772 + }, + { + "epoch": 0.17963689179375453, + "grad_norm": 3.11661696434021, + "learning_rate": 1.9913274366143876e-05, + "loss": 18.7087, + "step": 773 + }, + { + "epoch": 0.17986928104575164, + "grad_norm": 3.3554420471191406, + "learning_rate": 1.9912768677715123e-05, + "loss": 17.3233, + "step": 774 + }, + { + "epoch": 0.18010167029774873, + "grad_norm": 2.573513984680176, + "learning_rate": 1.991226152571823e-05, + "loss": 18.3383, + "step": 775 + }, + { + "epoch": 0.18033405954974582, + "grad_norm": 2.9328253269195557, + "learning_rate": 1.9911752910228083e-05, + "loss": 17.3962, + "step": 776 + }, + { + "epoch": 0.1805664488017429, + "grad_norm": 2.8780391216278076, + "learning_rate": 1.991124283131977e-05, + "loss": 18.4054, + "step": 777 + }, + { + "epoch": 0.18079883805374, + "grad_norm": 2.7865068912506104, + "learning_rate": 1.9910731289068598e-05, + "loss": 17.8683, + "step": 778 + }, + { + "epoch": 0.18103122730573712, + "grad_norm": 2.733776807785034, + "learning_rate": 1.99102182835501e-05, + "loss": 17.8108, + "step": 779 + }, + { + "epoch": 0.1812636165577342, + "grad_norm": 2.914644718170166, + "learning_rate": 1.990970381484002e-05, + "loss": 17.7439, + "step": 780 + }, + { + "epoch": 0.1814960058097313, + "grad_norm": 2.748121738433838, + "learning_rate": 1.990918788301431e-05, + "loss": 17.6378, + "step": 781 + }, + { + "epoch": 0.1817283950617284, + "grad_norm": 2.847041606903076, + "learning_rate": 1.990867048814915e-05, + "loss": 18.4706, + "step": 782 + }, + { + "epoch": 0.18196078431372548, + "grad_norm": 2.8649580478668213, + "learning_rate": 1.9908151630320926e-05, + "loss": 17.4643, + "step": 783 + }, + { + "epoch": 0.1821931735657226, + "grad_norm": 6.724813938140869, + "learning_rate": 1.9907631309606247e-05, + "loss": 17.6867, + "step": 784 + }, + { + "epoch": 0.18242556281771968, + "grad_norm": 2.925027847290039, + "learning_rate": 1.9907109526081937e-05, + "loss": 17.5132, + "step": 785 + }, + { + "epoch": 0.18265795206971677, + "grad_norm": 3.0528039932250977, + "learning_rate": 1.9906586279825034e-05, + "loss": 18.8691, + "step": 786 + }, + { + "epoch": 0.18289034132171386, + "grad_norm": 2.773509979248047, + "learning_rate": 1.9906061570912792e-05, + "loss": 18.5403, + "step": 787 + }, + { + "epoch": 0.18312273057371098, + "grad_norm": 2.707103967666626, + "learning_rate": 1.9905535399422683e-05, + "loss": 19.3287, + "step": 788 + }, + { + "epoch": 0.18335511982570807, + "grad_norm": 2.7667856216430664, + "learning_rate": 1.990500776543239e-05, + "loss": 17.5928, + "step": 789 + }, + { + "epoch": 0.18358750907770516, + "grad_norm": 2.784635066986084, + "learning_rate": 1.9904478669019817e-05, + "loss": 17.2793, + "step": 790 + }, + { + "epoch": 0.18381989832970225, + "grad_norm": 3.0057311058044434, + "learning_rate": 1.9903948110263082e-05, + "loss": 18.018, + "step": 791 + }, + { + "epoch": 0.18405228758169934, + "grad_norm": 2.9280285835266113, + "learning_rate": 1.9903416089240522e-05, + "loss": 17.7112, + "step": 792 + }, + { + "epoch": 0.18428467683369645, + "grad_norm": 2.8164873123168945, + "learning_rate": 1.9902882606030684e-05, + "loss": 18.0578, + "step": 793 + }, + { + "epoch": 0.18451706608569354, + "grad_norm": 2.8074052333831787, + "learning_rate": 1.9902347660712336e-05, + "loss": 19.3933, + "step": 794 + }, + { + "epoch": 0.18474945533769063, + "grad_norm": 2.7588579654693604, + "learning_rate": 1.9901811253364458e-05, + "loss": 18.2022, + "step": 795 + }, + { + "epoch": 0.18498184458968772, + "grad_norm": 2.968214511871338, + "learning_rate": 1.9901273384066248e-05, + "loss": 19.4076, + "step": 796 + }, + { + "epoch": 0.1852142338416848, + "grad_norm": 2.9096667766571045, + "learning_rate": 1.990073405289712e-05, + "loss": 19.1813, + "step": 797 + }, + { + "epoch": 0.18544662309368193, + "grad_norm": 2.9107306003570557, + "learning_rate": 1.9900193259936706e-05, + "loss": 18.0752, + "step": 798 + }, + { + "epoch": 0.18567901234567902, + "grad_norm": 2.890368700027466, + "learning_rate": 1.9899651005264843e-05, + "loss": 18.3916, + "step": 799 + }, + { + "epoch": 0.1859114015976761, + "grad_norm": 2.8140761852264404, + "learning_rate": 1.98991072889616e-05, + "loss": 18.4267, + "step": 800 + }, + { + "epoch": 0.1861437908496732, + "grad_norm": 2.7769887447357178, + "learning_rate": 1.9898562111107255e-05, + "loss": 17.9461, + "step": 801 + }, + { + "epoch": 0.18637618010167029, + "grad_norm": 3.2120025157928467, + "learning_rate": 1.9898015471782294e-05, + "loss": 18.839, + "step": 802 + }, + { + "epoch": 0.1866085693536674, + "grad_norm": 2.690804958343506, + "learning_rate": 1.989746737106743e-05, + "loss": 18.5276, + "step": 803 + }, + { + "epoch": 0.1868409586056645, + "grad_norm": 2.698444366455078, + "learning_rate": 1.9896917809043586e-05, + "loss": 17.7183, + "step": 804 + }, + { + "epoch": 0.18707334785766158, + "grad_norm": 2.9174838066101074, + "learning_rate": 1.9896366785791905e-05, + "loss": 17.8009, + "step": 805 + }, + { + "epoch": 0.18730573710965867, + "grad_norm": 3.273326873779297, + "learning_rate": 1.9895814301393735e-05, + "loss": 18.6997, + "step": 806 + }, + { + "epoch": 0.18753812636165576, + "grad_norm": 2.6921920776367188, + "learning_rate": 1.9895260355930654e-05, + "loss": 17.7523, + "step": 807 + }, + { + "epoch": 0.18777051561365288, + "grad_norm": 2.731468677520752, + "learning_rate": 1.9894704949484444e-05, + "loss": 17.2492, + "step": 808 + }, + { + "epoch": 0.18800290486564997, + "grad_norm": 2.8441574573516846, + "learning_rate": 1.989414808213711e-05, + "loss": 18.8142, + "step": 809 + }, + { + "epoch": 0.18823529411764706, + "grad_norm": 2.747932195663452, + "learning_rate": 1.9893589753970876e-05, + "loss": 19.0308, + "step": 810 + }, + { + "epoch": 0.18846768336964415, + "grad_norm": 2.6152307987213135, + "learning_rate": 1.989302996506817e-05, + "loss": 17.9911, + "step": 811 + }, + { + "epoch": 0.18870007262164126, + "grad_norm": 2.9535281658172607, + "learning_rate": 1.9892468715511643e-05, + "loss": 18.4117, + "step": 812 + }, + { + "epoch": 0.18893246187363835, + "grad_norm": 3.4120044708251953, + "learning_rate": 1.9891906005384163e-05, + "loss": 17.297, + "step": 813 + }, + { + "epoch": 0.18916485112563544, + "grad_norm": 2.700476884841919, + "learning_rate": 1.9891341834768807e-05, + "loss": 17.7787, + "step": 814 + }, + { + "epoch": 0.18939724037763253, + "grad_norm": 2.8919637203216553, + "learning_rate": 1.9890776203748877e-05, + "loss": 17.8789, + "step": 815 + }, + { + "epoch": 0.18962962962962962, + "grad_norm": 2.8382375240325928, + "learning_rate": 1.989020911240788e-05, + "loss": 18.7895, + "step": 816 + }, + { + "epoch": 0.18986201888162674, + "grad_norm": 2.8589768409729004, + "learning_rate": 1.9889640560829547e-05, + "loss": 17.3547, + "step": 817 + }, + { + "epoch": 0.19009440813362383, + "grad_norm": 2.745948314666748, + "learning_rate": 1.988907054909782e-05, + "loss": 17.3077, + "step": 818 + }, + { + "epoch": 0.19032679738562092, + "grad_norm": 2.8361899852752686, + "learning_rate": 1.9888499077296857e-05, + "loss": 17.8554, + "step": 819 + }, + { + "epoch": 0.190559186637618, + "grad_norm": 3.9128031730651855, + "learning_rate": 1.9887926145511042e-05, + "loss": 17.5979, + "step": 820 + }, + { + "epoch": 0.1907915758896151, + "grad_norm": 2.908224582672119, + "learning_rate": 1.9887351753824955e-05, + "loss": 18.1072, + "step": 821 + }, + { + "epoch": 0.1910239651416122, + "grad_norm": 2.8586928844451904, + "learning_rate": 1.9886775902323405e-05, + "loss": 18.0035, + "step": 822 + }, + { + "epoch": 0.1912563543936093, + "grad_norm": 2.971315860748291, + "learning_rate": 1.9886198591091416e-05, + "loss": 18.5261, + "step": 823 + }, + { + "epoch": 0.1914887436456064, + "grad_norm": 3.039060592651367, + "learning_rate": 1.988561982021422e-05, + "loss": 18.2065, + "step": 824 + }, + { + "epoch": 0.19172113289760348, + "grad_norm": 3.121358871459961, + "learning_rate": 1.9885039589777278e-05, + "loss": 18.1211, + "step": 825 + }, + { + "epoch": 0.19195352214960057, + "grad_norm": 2.7872729301452637, + "learning_rate": 1.9884457899866246e-05, + "loss": 18.108, + "step": 826 + }, + { + "epoch": 0.1921859114015977, + "grad_norm": 2.745032787322998, + "learning_rate": 1.9883874750567014e-05, + "loss": 18.6213, + "step": 827 + }, + { + "epoch": 0.19241830065359478, + "grad_norm": 2.660445213317871, + "learning_rate": 1.988329014196569e-05, + "loss": 17.6154, + "step": 828 + }, + { + "epoch": 0.19265068990559187, + "grad_norm": 2.885798454284668, + "learning_rate": 1.988270407414857e-05, + "loss": 17.2001, + "step": 829 + }, + { + "epoch": 0.19288307915758895, + "grad_norm": 14.581377983093262, + "learning_rate": 1.9882116547202194e-05, + "loss": 17.3981, + "step": 830 + }, + { + "epoch": 0.19311546840958604, + "grad_norm": 3.110332727432251, + "learning_rate": 1.988152756121331e-05, + "loss": 17.8289, + "step": 831 + }, + { + "epoch": 0.19334785766158316, + "grad_norm": 5.1018476486206055, + "learning_rate": 1.988093711626887e-05, + "loss": 17.094, + "step": 832 + }, + { + "epoch": 0.19358024691358025, + "grad_norm": 3.0707380771636963, + "learning_rate": 1.988034521245606e-05, + "loss": 18.6094, + "step": 833 + }, + { + "epoch": 0.19381263616557734, + "grad_norm": 2.716965436935425, + "learning_rate": 1.9879751849862263e-05, + "loss": 18.7025, + "step": 834 + }, + { + "epoch": 0.19404502541757443, + "grad_norm": 3.003596544265747, + "learning_rate": 1.987915702857509e-05, + "loss": 19.1273, + "step": 835 + }, + { + "epoch": 0.19427741466957152, + "grad_norm": 2.7866885662078857, + "learning_rate": 1.9878560748682363e-05, + "loss": 17.0644, + "step": 836 + }, + { + "epoch": 0.19450980392156864, + "grad_norm": 2.7065389156341553, + "learning_rate": 1.9877963010272118e-05, + "loss": 18.3778, + "step": 837 + }, + { + "epoch": 0.19474219317356573, + "grad_norm": 3.332064390182495, + "learning_rate": 1.987736381343261e-05, + "loss": 18.6278, + "step": 838 + }, + { + "epoch": 0.19497458242556281, + "grad_norm": 3.8398921489715576, + "learning_rate": 1.987676315825231e-05, + "loss": 18.3107, + "step": 839 + }, + { + "epoch": 0.1952069716775599, + "grad_norm": 3.9322915077209473, + "learning_rate": 1.9876161044819892e-05, + "loss": 17.5455, + "step": 840 + }, + { + "epoch": 0.19543936092955702, + "grad_norm": 3.5166754722595215, + "learning_rate": 1.9875557473224266e-05, + "loss": 18.3259, + "step": 841 + }, + { + "epoch": 0.1956717501815541, + "grad_norm": 2.7665393352508545, + "learning_rate": 1.987495244355454e-05, + "loss": 18.4708, + "step": 842 + }, + { + "epoch": 0.1959041394335512, + "grad_norm": 2.8909752368927, + "learning_rate": 1.9874345955900042e-05, + "loss": 18.3273, + "step": 843 + }, + { + "epoch": 0.1961365286855483, + "grad_norm": 2.7418200969696045, + "learning_rate": 1.987373801035032e-05, + "loss": 18.689, + "step": 844 + }, + { + "epoch": 0.19636891793754538, + "grad_norm": 2.6124491691589355, + "learning_rate": 1.987312860699513e-05, + "loss": 17.3919, + "step": 845 + }, + { + "epoch": 0.1966013071895425, + "grad_norm": 2.9232676029205322, + "learning_rate": 1.9872517745924457e-05, + "loss": 18.5149, + "step": 846 + }, + { + "epoch": 0.19683369644153959, + "grad_norm": 2.6895668506622314, + "learning_rate": 1.987190542722848e-05, + "loss": 18.8069, + "step": 847 + }, + { + "epoch": 0.19706608569353667, + "grad_norm": 3.0646812915802, + "learning_rate": 1.987129165099761e-05, + "loss": 17.4359, + "step": 848 + }, + { + "epoch": 0.19729847494553376, + "grad_norm": 2.940828800201416, + "learning_rate": 1.9870676417322468e-05, + "loss": 18.6727, + "step": 849 + }, + { + "epoch": 0.19753086419753085, + "grad_norm": 3.1332623958587646, + "learning_rate": 1.9870059726293892e-05, + "loss": 18.2974, + "step": 850 + }, + { + "epoch": 0.19776325344952797, + "grad_norm": 2.687251329421997, + "learning_rate": 1.9869441578002925e-05, + "loss": 17.9861, + "step": 851 + }, + { + "epoch": 0.19799564270152506, + "grad_norm": 2.831639289855957, + "learning_rate": 1.986882197254084e-05, + "loss": 17.2889, + "step": 852 + }, + { + "epoch": 0.19822803195352215, + "grad_norm": 2.9307103157043457, + "learning_rate": 1.986820090999912e-05, + "loss": 19.1216, + "step": 853 + }, + { + "epoch": 0.19846042120551924, + "grad_norm": 3.2320990562438965, + "learning_rate": 1.986757839046946e-05, + "loss": 17.6505, + "step": 854 + }, + { + "epoch": 0.19869281045751633, + "grad_norm": 2.7291526794433594, + "learning_rate": 1.9866954414043764e-05, + "loss": 18.235, + "step": 855 + }, + { + "epoch": 0.19892519970951344, + "grad_norm": 2.8747034072875977, + "learning_rate": 1.986632898081417e-05, + "loss": 18.5916, + "step": 856 + }, + { + "epoch": 0.19915758896151053, + "grad_norm": 2.6149837970733643, + "learning_rate": 1.9865702090873016e-05, + "loss": 18.646, + "step": 857 + }, + { + "epoch": 0.19938997821350762, + "grad_norm": 2.9423668384552, + "learning_rate": 1.986507374431286e-05, + "loss": 18.2974, + "step": 858 + }, + { + "epoch": 0.1996223674655047, + "grad_norm": 3.0791101455688477, + "learning_rate": 1.9864443941226467e-05, + "loss": 17.7146, + "step": 859 + }, + { + "epoch": 0.1998547567175018, + "grad_norm": 2.7805016040802, + "learning_rate": 1.9863812681706835e-05, + "loss": 17.0194, + "step": 860 + }, + { + "epoch": 0.20008714596949892, + "grad_norm": 2.7965452671051025, + "learning_rate": 1.9863179965847156e-05, + "loss": 17.4347, + "step": 861 + }, + { + "epoch": 0.200319535221496, + "grad_norm": 2.9932761192321777, + "learning_rate": 1.9862545793740854e-05, + "loss": 18.25, + "step": 862 + }, + { + "epoch": 0.2005519244734931, + "grad_norm": 3.676751136779785, + "learning_rate": 1.986191016548156e-05, + "loss": 17.7259, + "step": 863 + }, + { + "epoch": 0.2007843137254902, + "grad_norm": 2.70297908782959, + "learning_rate": 1.9861273081163116e-05, + "loss": 18.2112, + "step": 864 + }, + { + "epoch": 0.2010167029774873, + "grad_norm": 2.7047760486602783, + "learning_rate": 1.986063454087959e-05, + "loss": 17.9737, + "step": 865 + }, + { + "epoch": 0.2012490922294844, + "grad_norm": 2.746269941329956, + "learning_rate": 1.9859994544725262e-05, + "loss": 18.062, + "step": 866 + }, + { + "epoch": 0.20148148148148148, + "grad_norm": 2.667325019836426, + "learning_rate": 1.9859353092794614e-05, + "loss": 18.0632, + "step": 867 + }, + { + "epoch": 0.20171387073347857, + "grad_norm": 3.330446720123291, + "learning_rate": 1.985871018518236e-05, + "loss": 18.4239, + "step": 868 + }, + { + "epoch": 0.20194625998547566, + "grad_norm": 3.2152600288391113, + "learning_rate": 1.985806582198342e-05, + "loss": 18.752, + "step": 869 + }, + { + "epoch": 0.20217864923747278, + "grad_norm": 2.729445457458496, + "learning_rate": 1.9857420003292934e-05, + "loss": 18.9834, + "step": 870 + }, + { + "epoch": 0.20241103848946987, + "grad_norm": 2.7163493633270264, + "learning_rate": 1.985677272920625e-05, + "loss": 17.4205, + "step": 871 + }, + { + "epoch": 0.20264342774146696, + "grad_norm": 2.579937219619751, + "learning_rate": 1.985612399981893e-05, + "loss": 17.4149, + "step": 872 + }, + { + "epoch": 0.20287581699346405, + "grad_norm": 2.7646312713623047, + "learning_rate": 1.985547381522677e-05, + "loss": 18.3502, + "step": 873 + }, + { + "epoch": 0.20310820624546114, + "grad_norm": 2.728283166885376, + "learning_rate": 1.9854822175525754e-05, + "loss": 17.6555, + "step": 874 + }, + { + "epoch": 0.20334059549745825, + "grad_norm": 2.9810009002685547, + "learning_rate": 1.9854169080812095e-05, + "loss": 18.2266, + "step": 875 + }, + { + "epoch": 0.20357298474945534, + "grad_norm": 2.639723300933838, + "learning_rate": 1.9853514531182222e-05, + "loss": 17.6565, + "step": 876 + }, + { + "epoch": 0.20380537400145243, + "grad_norm": 2.7163772583007812, + "learning_rate": 1.9852858526732774e-05, + "loss": 17.6805, + "step": 877 + }, + { + "epoch": 0.20403776325344952, + "grad_norm": 4.063429832458496, + "learning_rate": 1.9852201067560607e-05, + "loss": 17.5774, + "step": 878 + }, + { + "epoch": 0.2042701525054466, + "grad_norm": 2.9095442295074463, + "learning_rate": 1.985154215376279e-05, + "loss": 17.8999, + "step": 879 + }, + { + "epoch": 0.20450254175744373, + "grad_norm": 2.7858338356018066, + "learning_rate": 1.9850881785436614e-05, + "loss": 18.5547, + "step": 880 + }, + { + "epoch": 0.20473493100944082, + "grad_norm": 3.020890712738037, + "learning_rate": 1.9850219962679572e-05, + "loss": 17.2526, + "step": 881 + }, + { + "epoch": 0.2049673202614379, + "grad_norm": 4.250825881958008, + "learning_rate": 1.984955668558938e-05, + "loss": 19.3622, + "step": 882 + }, + { + "epoch": 0.205199709513435, + "grad_norm": 2.785552501678467, + "learning_rate": 1.984889195426397e-05, + "loss": 17.4252, + "step": 883 + }, + { + "epoch": 0.2054320987654321, + "grad_norm": 2.671238422393799, + "learning_rate": 1.9848225768801485e-05, + "loss": 18.1126, + "step": 884 + }, + { + "epoch": 0.2056644880174292, + "grad_norm": 3.859194278717041, + "learning_rate": 1.9847558129300282e-05, + "loss": 18.7485, + "step": 885 + }, + { + "epoch": 0.2058968772694263, + "grad_norm": 3.6047685146331787, + "learning_rate": 1.9846889035858934e-05, + "loss": 18.1148, + "step": 886 + }, + { + "epoch": 0.20612926652142338, + "grad_norm": 2.627878427505493, + "learning_rate": 1.9846218488576233e-05, + "loss": 19.3255, + "step": 887 + }, + { + "epoch": 0.20636165577342047, + "grad_norm": 2.659205436706543, + "learning_rate": 1.984554648755118e-05, + "loss": 17.433, + "step": 888 + }, + { + "epoch": 0.20659404502541756, + "grad_norm": 2.6286838054656982, + "learning_rate": 1.984487303288299e-05, + "loss": 17.8329, + "step": 889 + }, + { + "epoch": 0.20682643427741468, + "grad_norm": 3.3140780925750732, + "learning_rate": 1.98441981246711e-05, + "loss": 18.3944, + "step": 890 + }, + { + "epoch": 0.20705882352941177, + "grad_norm": 3.0743050575256348, + "learning_rate": 1.984352176301515e-05, + "loss": 17.6478, + "step": 891 + }, + { + "epoch": 0.20729121278140886, + "grad_norm": 2.8070759773254395, + "learning_rate": 1.9842843948015013e-05, + "loss": 18.1063, + "step": 892 + }, + { + "epoch": 0.20752360203340595, + "grad_norm": 2.6020281314849854, + "learning_rate": 1.984216467977075e-05, + "loss": 17.4455, + "step": 893 + }, + { + "epoch": 0.20775599128540306, + "grad_norm": 3.0307846069335938, + "learning_rate": 1.984148395838266e-05, + "loss": 18.6929, + "step": 894 + }, + { + "epoch": 0.20798838053740015, + "grad_norm": 2.8762261867523193, + "learning_rate": 1.9840801783951247e-05, + "loss": 18.0194, + "step": 895 + }, + { + "epoch": 0.20822076978939724, + "grad_norm": 2.8584470748901367, + "learning_rate": 1.9840118156577224e-05, + "loss": 17.9424, + "step": 896 + }, + { + "epoch": 0.20845315904139433, + "grad_norm": 2.7711126804351807, + "learning_rate": 1.983943307636154e-05, + "loss": 18.2868, + "step": 897 + }, + { + "epoch": 0.20868554829339142, + "grad_norm": 2.6316299438476562, + "learning_rate": 1.9838746543405327e-05, + "loss": 17.9664, + "step": 898 + }, + { + "epoch": 0.20891793754538854, + "grad_norm": 2.788313865661621, + "learning_rate": 1.9838058557809957e-05, + "loss": 18.6875, + "step": 899 + }, + { + "epoch": 0.20915032679738563, + "grad_norm": 3.0054898262023926, + "learning_rate": 1.9837369119677007e-05, + "loss": 18.7958, + "step": 900 + }, + { + "epoch": 0.20938271604938272, + "grad_norm": 2.867945671081543, + "learning_rate": 1.983667822910827e-05, + "loss": 18.3746, + "step": 901 + }, + { + "epoch": 0.2096151053013798, + "grad_norm": 2.731003761291504, + "learning_rate": 1.9835985886205744e-05, + "loss": 18.4385, + "step": 902 + }, + { + "epoch": 0.2098474945533769, + "grad_norm": 2.653074026107788, + "learning_rate": 1.983529209107166e-05, + "loss": 18.4291, + "step": 903 + }, + { + "epoch": 0.210079883805374, + "grad_norm": 2.9147040843963623, + "learning_rate": 1.9834596843808446e-05, + "loss": 18.46, + "step": 904 + }, + { + "epoch": 0.2103122730573711, + "grad_norm": 2.8738112449645996, + "learning_rate": 1.9833900144518756e-05, + "loss": 18.1601, + "step": 905 + }, + { + "epoch": 0.2105446623093682, + "grad_norm": 2.7682204246520996, + "learning_rate": 1.9833201993305452e-05, + "loss": 18.2834, + "step": 906 + }, + { + "epoch": 0.21077705156136528, + "grad_norm": 2.60133957862854, + "learning_rate": 1.9832502390271612e-05, + "loss": 17.5904, + "step": 907 + }, + { + "epoch": 0.21100944081336237, + "grad_norm": 2.831829309463501, + "learning_rate": 1.983180133552053e-05, + "loss": 17.6362, + "step": 908 + }, + { + "epoch": 0.2112418300653595, + "grad_norm": 2.942401885986328, + "learning_rate": 1.9831098829155712e-05, + "loss": 17.539, + "step": 909 + }, + { + "epoch": 0.21147421931735658, + "grad_norm": 2.82086443901062, + "learning_rate": 1.983039487128088e-05, + "loss": 18.9714, + "step": 910 + }, + { + "epoch": 0.21170660856935367, + "grad_norm": 3.037534475326538, + "learning_rate": 1.982968946199997e-05, + "loss": 19.2781, + "step": 911 + }, + { + "epoch": 0.21193899782135076, + "grad_norm": 2.5860981941223145, + "learning_rate": 1.9828982601417133e-05, + "loss": 17.8225, + "step": 912 + }, + { + "epoch": 0.21217138707334784, + "grad_norm": 2.8388826847076416, + "learning_rate": 1.982827428963673e-05, + "loss": 17.548, + "step": 913 + }, + { + "epoch": 0.21240377632534496, + "grad_norm": 2.658578634262085, + "learning_rate": 1.982756452676334e-05, + "loss": 18.1203, + "step": 914 + }, + { + "epoch": 0.21263616557734205, + "grad_norm": 3.024143695831299, + "learning_rate": 1.982685331290176e-05, + "loss": 17.1455, + "step": 915 + }, + { + "epoch": 0.21286855482933914, + "grad_norm": 2.6399099826812744, + "learning_rate": 1.982614064815699e-05, + "loss": 17.66, + "step": 916 + }, + { + "epoch": 0.21310094408133623, + "grad_norm": 2.7627549171447754, + "learning_rate": 1.982542653263426e-05, + "loss": 18.1892, + "step": 917 + }, + { + "epoch": 0.21333333333333335, + "grad_norm": 2.6444053649902344, + "learning_rate": 1.9824710966438996e-05, + "loss": 17.1571, + "step": 918 + }, + { + "epoch": 0.21356572258533044, + "grad_norm": 2.829646110534668, + "learning_rate": 1.9823993949676853e-05, + "loss": 17.8955, + "step": 919 + }, + { + "epoch": 0.21379811183732753, + "grad_norm": 3.051607847213745, + "learning_rate": 1.98232754824537e-05, + "loss": 18.2293, + "step": 920 + }, + { + "epoch": 0.21403050108932462, + "grad_norm": 2.8169991970062256, + "learning_rate": 1.9822555564875602e-05, + "loss": 17.6133, + "step": 921 + }, + { + "epoch": 0.2142628903413217, + "grad_norm": 2.8673994541168213, + "learning_rate": 1.9821834197048863e-05, + "loss": 18.5522, + "step": 922 + }, + { + "epoch": 0.21449527959331882, + "grad_norm": 2.7544004917144775, + "learning_rate": 1.982111137907998e-05, + "loss": 17.1968, + "step": 923 + }, + { + "epoch": 0.2147276688453159, + "grad_norm": 3.5282986164093018, + "learning_rate": 1.9820387111075678e-05, + "loss": 17.9664, + "step": 924 + }, + { + "epoch": 0.214960058097313, + "grad_norm": 2.7704966068267822, + "learning_rate": 1.981966139314289e-05, + "loss": 18.1793, + "step": 925 + }, + { + "epoch": 0.2151924473493101, + "grad_norm": 2.842048406600952, + "learning_rate": 1.981893422538877e-05, + "loss": 17.9022, + "step": 926 + }, + { + "epoch": 0.21542483660130718, + "grad_norm": 2.7174320220947266, + "learning_rate": 1.9818205607920672e-05, + "loss": 18.2526, + "step": 927 + }, + { + "epoch": 0.2156572258533043, + "grad_norm": 2.6691386699676514, + "learning_rate": 1.9817475540846173e-05, + "loss": 17.9574, + "step": 928 + }, + { + "epoch": 0.21588961510530139, + "grad_norm": 2.6409597396850586, + "learning_rate": 1.981674402427307e-05, + "loss": 17.7628, + "step": 929 + }, + { + "epoch": 0.21612200435729848, + "grad_norm": 2.855926752090454, + "learning_rate": 1.9816011058309367e-05, + "loss": 18.4304, + "step": 930 + }, + { + "epoch": 0.21635439360929556, + "grad_norm": 2.6726229190826416, + "learning_rate": 1.9815276643063274e-05, + "loss": 17.9464, + "step": 931 + }, + { + "epoch": 0.21658678286129265, + "grad_norm": 2.554442882537842, + "learning_rate": 1.9814540778643234e-05, + "loss": 18.3058, + "step": 932 + }, + { + "epoch": 0.21681917211328977, + "grad_norm": 2.9910216331481934, + "learning_rate": 1.9813803465157885e-05, + "loss": 18.8156, + "step": 933 + }, + { + "epoch": 0.21705156136528686, + "grad_norm": 2.737035036087036, + "learning_rate": 1.9813064702716094e-05, + "loss": 18.0298, + "step": 934 + }, + { + "epoch": 0.21728395061728395, + "grad_norm": 2.625088930130005, + "learning_rate": 1.9812324491426933e-05, + "loss": 17.5916, + "step": 935 + }, + { + "epoch": 0.21751633986928104, + "grad_norm": 2.8049981594085693, + "learning_rate": 1.9811582831399693e-05, + "loss": 19.1473, + "step": 936 + }, + { + "epoch": 0.21774872912127813, + "grad_norm": 2.672614574432373, + "learning_rate": 1.9810839722743866e-05, + "loss": 18.5441, + "step": 937 + }, + { + "epoch": 0.21798111837327525, + "grad_norm": 2.629331588745117, + "learning_rate": 1.981009516556918e-05, + "loss": 18.0259, + "step": 938 + }, + { + "epoch": 0.21821350762527233, + "grad_norm": 2.697220802307129, + "learning_rate": 1.9809349159985558e-05, + "loss": 18.219, + "step": 939 + }, + { + "epoch": 0.21844589687726942, + "grad_norm": 2.6735761165618896, + "learning_rate": 1.9808601706103146e-05, + "loss": 18.4162, + "step": 940 + }, + { + "epoch": 0.2186782861292665, + "grad_norm": 2.550657033920288, + "learning_rate": 1.9807852804032306e-05, + "loss": 18.2983, + "step": 941 + }, + { + "epoch": 0.2189106753812636, + "grad_norm": 2.66929292678833, + "learning_rate": 1.9807102453883602e-05, + "loss": 18.6575, + "step": 942 + }, + { + "epoch": 0.21914306463326072, + "grad_norm": 2.8106236457824707, + "learning_rate": 1.9806350655767823e-05, + "loss": 18.4026, + "step": 943 + }, + { + "epoch": 0.2193754538852578, + "grad_norm": 2.6772494316101074, + "learning_rate": 1.980559740979597e-05, + "loss": 17.7282, + "step": 944 + }, + { + "epoch": 0.2196078431372549, + "grad_norm": 2.648648500442505, + "learning_rate": 1.980484271607925e-05, + "loss": 17.7747, + "step": 945 + }, + { + "epoch": 0.219840232389252, + "grad_norm": 3.016998052597046, + "learning_rate": 1.980408657472909e-05, + "loss": 18.0141, + "step": 946 + }, + { + "epoch": 0.2200726216412491, + "grad_norm": 2.570601463317871, + "learning_rate": 1.9803328985857138e-05, + "loss": 17.4839, + "step": 947 + }, + { + "epoch": 0.2203050108932462, + "grad_norm": 2.6659224033355713, + "learning_rate": 1.980256994957524e-05, + "loss": 18.48, + "step": 948 + }, + { + "epoch": 0.22053740014524328, + "grad_norm": 2.753664493560791, + "learning_rate": 1.980180946599547e-05, + "loss": 17.6998, + "step": 949 + }, + { + "epoch": 0.22076978939724037, + "grad_norm": 3.1067020893096924, + "learning_rate": 1.9801047535230105e-05, + "loss": 17.0781, + "step": 950 + }, + { + "epoch": 0.22100217864923746, + "grad_norm": 2.7597146034240723, + "learning_rate": 1.980028415739164e-05, + "loss": 17.6951, + "step": 951 + }, + { + "epoch": 0.22123456790123458, + "grad_norm": 2.6039109230041504, + "learning_rate": 1.9799519332592787e-05, + "loss": 17.4123, + "step": 952 + }, + { + "epoch": 0.22146695715323167, + "grad_norm": 2.9055662155151367, + "learning_rate": 1.9798753060946466e-05, + "loss": 18.7203, + "step": 953 + }, + { + "epoch": 0.22169934640522876, + "grad_norm": 2.6992409229278564, + "learning_rate": 1.979798534256581e-05, + "loss": 17.1914, + "step": 954 + }, + { + "epoch": 0.22193173565722585, + "grad_norm": 3.7623507976531982, + "learning_rate": 1.9797216177564175e-05, + "loss": 17.3058, + "step": 955 + }, + { + "epoch": 0.22216412490922294, + "grad_norm": 2.643664836883545, + "learning_rate": 1.9796445566055123e-05, + "loss": 18.3197, + "step": 956 + }, + { + "epoch": 0.22239651416122005, + "grad_norm": 2.5799484252929688, + "learning_rate": 1.9795673508152426e-05, + "loss": 17.2346, + "step": 957 + }, + { + "epoch": 0.22262890341321714, + "grad_norm": 2.7163543701171875, + "learning_rate": 1.9794900003970076e-05, + "loss": 17.2251, + "step": 958 + }, + { + "epoch": 0.22286129266521423, + "grad_norm": 2.7480368614196777, + "learning_rate": 1.979412505362228e-05, + "loss": 18.1263, + "step": 959 + }, + { + "epoch": 0.22309368191721132, + "grad_norm": 2.6813254356384277, + "learning_rate": 1.9793348657223455e-05, + "loss": 17.9447, + "step": 960 + }, + { + "epoch": 0.2233260711692084, + "grad_norm": 2.623523235321045, + "learning_rate": 1.9792570814888225e-05, + "loss": 17.4628, + "step": 961 + }, + { + "epoch": 0.22355846042120553, + "grad_norm": 2.7949087619781494, + "learning_rate": 1.9791791526731444e-05, + "loss": 18.5888, + "step": 962 + }, + { + "epoch": 0.22379084967320262, + "grad_norm": 2.7014503479003906, + "learning_rate": 1.9791010792868163e-05, + "loss": 17.8393, + "step": 963 + }, + { + "epoch": 0.2240232389251997, + "grad_norm": 2.935681104660034, + "learning_rate": 1.9790228613413656e-05, + "loss": 17.3928, + "step": 964 + }, + { + "epoch": 0.2242556281771968, + "grad_norm": 2.746608018875122, + "learning_rate": 1.978944498848341e-05, + "loss": 18.3586, + "step": 965 + }, + { + "epoch": 0.2244880174291939, + "grad_norm": 2.9577393531799316, + "learning_rate": 1.9788659918193117e-05, + "loss": 17.783, + "step": 966 + }, + { + "epoch": 0.224720406681191, + "grad_norm": 2.649531126022339, + "learning_rate": 1.9787873402658694e-05, + "loss": 18.6425, + "step": 967 + }, + { + "epoch": 0.2249527959331881, + "grad_norm": 2.7363102436065674, + "learning_rate": 1.978708544199626e-05, + "loss": 17.1217, + "step": 968 + }, + { + "epoch": 0.22518518518518518, + "grad_norm": 3.371948719024658, + "learning_rate": 1.978629603632216e-05, + "loss": 17.7055, + "step": 969 + }, + { + "epoch": 0.22541757443718227, + "grad_norm": 2.9813921451568604, + "learning_rate": 1.9785505185752942e-05, + "loss": 18.223, + "step": 970 + }, + { + "epoch": 0.2256499636891794, + "grad_norm": 2.8436615467071533, + "learning_rate": 1.978471289040537e-05, + "loss": 18.53, + "step": 971 + }, + { + "epoch": 0.22588235294117648, + "grad_norm": 2.8501763343811035, + "learning_rate": 1.9783919150396426e-05, + "loss": 18.0985, + "step": 972 + }, + { + "epoch": 0.22611474219317357, + "grad_norm": 2.7457571029663086, + "learning_rate": 1.9783123965843297e-05, + "loss": 18.4233, + "step": 973 + }, + { + "epoch": 0.22634713144517066, + "grad_norm": 2.810664415359497, + "learning_rate": 1.9782327336863393e-05, + "loss": 18.0922, + "step": 974 + }, + { + "epoch": 0.22657952069716775, + "grad_norm": 2.782231569290161, + "learning_rate": 1.9781529263574325e-05, + "loss": 18.0789, + "step": 975 + }, + { + "epoch": 0.22681190994916486, + "grad_norm": 2.6835553646087646, + "learning_rate": 1.978072974609393e-05, + "loss": 18.643, + "step": 976 + }, + { + "epoch": 0.22704429920116195, + "grad_norm": 2.7487733364105225, + "learning_rate": 1.9779928784540252e-05, + "loss": 17.5695, + "step": 977 + }, + { + "epoch": 0.22727668845315904, + "grad_norm": 2.8854894638061523, + "learning_rate": 1.977912637903155e-05, + "loss": 18.2744, + "step": 978 + }, + { + "epoch": 0.22750907770515613, + "grad_norm": 2.843376636505127, + "learning_rate": 1.9778322529686287e-05, + "loss": 18.0354, + "step": 979 + }, + { + "epoch": 0.22774146695715322, + "grad_norm": 2.8611230850219727, + "learning_rate": 1.9777517236623155e-05, + "loss": 18.0931, + "step": 980 + }, + { + "epoch": 0.22797385620915034, + "grad_norm": 2.679337739944458, + "learning_rate": 1.9776710499961052e-05, + "loss": 18.4176, + "step": 981 + }, + { + "epoch": 0.22820624546114743, + "grad_norm": 2.7813310623168945, + "learning_rate": 1.9775902319819082e-05, + "loss": 16.8014, + "step": 982 + }, + { + "epoch": 0.22843863471314452, + "grad_norm": 2.6521174907684326, + "learning_rate": 1.977509269631657e-05, + "loss": 19.1027, + "step": 983 + }, + { + "epoch": 0.2286710239651416, + "grad_norm": 2.5828592777252197, + "learning_rate": 1.9774281629573063e-05, + "loss": 17.4127, + "step": 984 + }, + { + "epoch": 0.2289034132171387, + "grad_norm": 2.801420211791992, + "learning_rate": 1.9773469119708295e-05, + "loss": 18.1216, + "step": 985 + }, + { + "epoch": 0.2291358024691358, + "grad_norm": 2.5513718128204346, + "learning_rate": 1.977265516684224e-05, + "loss": 18.5158, + "step": 986 + }, + { + "epoch": 0.2293681917211329, + "grad_norm": 2.6902835369110107, + "learning_rate": 1.9771839771095067e-05, + "loss": 18.2898, + "step": 987 + }, + { + "epoch": 0.22960058097313, + "grad_norm": 2.767847776412964, + "learning_rate": 1.977102293258717e-05, + "loss": 19.0874, + "step": 988 + }, + { + "epoch": 0.22983297022512708, + "grad_norm": 2.677229881286621, + "learning_rate": 1.977020465143915e-05, + "loss": 18.5331, + "step": 989 + }, + { + "epoch": 0.23006535947712417, + "grad_norm": 2.80055570602417, + "learning_rate": 1.976938492777182e-05, + "loss": 18.85, + "step": 990 + }, + { + "epoch": 0.2302977487291213, + "grad_norm": 3.171096086502075, + "learning_rate": 1.9768563761706207e-05, + "loss": 18.7167, + "step": 991 + }, + { + "epoch": 0.23053013798111838, + "grad_norm": 2.63980770111084, + "learning_rate": 1.9767741153363554e-05, + "loss": 17.6756, + "step": 992 + }, + { + "epoch": 0.23076252723311547, + "grad_norm": 2.655027389526367, + "learning_rate": 1.9766917102865316e-05, + "loss": 18.4443, + "step": 993 + }, + { + "epoch": 0.23099491648511256, + "grad_norm": 2.7414028644561768, + "learning_rate": 1.9766091610333157e-05, + "loss": 19.3196, + "step": 994 + }, + { + "epoch": 0.23122730573710965, + "grad_norm": 2.691096067428589, + "learning_rate": 1.9765264675888958e-05, + "loss": 18.5295, + "step": 995 + }, + { + "epoch": 0.23145969498910676, + "grad_norm": 2.905052423477173, + "learning_rate": 1.976443629965481e-05, + "loss": 18.7212, + "step": 996 + }, + { + "epoch": 0.23169208424110385, + "grad_norm": 2.8577609062194824, + "learning_rate": 1.9763606481753023e-05, + "loss": 17.7825, + "step": 997 + }, + { + "epoch": 0.23192447349310094, + "grad_norm": 2.927682876586914, + "learning_rate": 1.9762775222306106e-05, + "loss": 18.1409, + "step": 998 + }, + { + "epoch": 0.23215686274509803, + "grad_norm": 2.9463682174682617, + "learning_rate": 1.9761942521436802e-05, + "loss": 18.3484, + "step": 999 + }, + { + "epoch": 0.23238925199709515, + "grad_norm": 2.9084270000457764, + "learning_rate": 1.9761108379268043e-05, + "loss": 18.493, + "step": 1000 + }, + { + "epoch": 0.23262164124909224, + "grad_norm": 2.6054699420928955, + "learning_rate": 1.9760272795922997e-05, + "loss": 17.7086, + "step": 1001 + }, + { + "epoch": 0.23285403050108933, + "grad_norm": 3.016862154006958, + "learning_rate": 1.9759435771525024e-05, + "loss": 18.3311, + "step": 1002 + }, + { + "epoch": 0.23308641975308642, + "grad_norm": 2.6752238273620605, + "learning_rate": 1.9758597306197714e-05, + "loss": 17.6636, + "step": 1003 + }, + { + "epoch": 0.2333188090050835, + "grad_norm": 2.7982277870178223, + "learning_rate": 1.9757757400064857e-05, + "loss": 17.9843, + "step": 1004 + }, + { + "epoch": 0.23355119825708062, + "grad_norm": 2.859973192214966, + "learning_rate": 1.9756916053250462e-05, + "loss": 18.1718, + "step": 1005 + }, + { + "epoch": 0.2337835875090777, + "grad_norm": 2.7030375003814697, + "learning_rate": 1.9756073265878748e-05, + "loss": 18.5593, + "step": 1006 + }, + { + "epoch": 0.2340159767610748, + "grad_norm": 2.738955020904541, + "learning_rate": 1.9755229038074147e-05, + "loss": 17.6847, + "step": 1007 + }, + { + "epoch": 0.2342483660130719, + "grad_norm": 2.5941507816314697, + "learning_rate": 1.9754383369961313e-05, + "loss": 18.2163, + "step": 1008 + }, + { + "epoch": 0.23448075526506898, + "grad_norm": 2.6551513671875, + "learning_rate": 1.9753536261665094e-05, + "loss": 18.1708, + "step": 1009 + }, + { + "epoch": 0.2347131445170661, + "grad_norm": 2.956016778945923, + "learning_rate": 1.975268771331057e-05, + "loss": 18.0353, + "step": 1010 + }, + { + "epoch": 0.2349455337690632, + "grad_norm": 2.8045127391815186, + "learning_rate": 1.975183772502302e-05, + "loss": 17.7812, + "step": 1011 + }, + { + "epoch": 0.23517792302106028, + "grad_norm": 2.7257251739501953, + "learning_rate": 1.9750986296927938e-05, + "loss": 17.1855, + "step": 1012 + }, + { + "epoch": 0.23541031227305736, + "grad_norm": 2.7629222869873047, + "learning_rate": 1.9750133429151038e-05, + "loss": 18.7518, + "step": 1013 + }, + { + "epoch": 0.23564270152505445, + "grad_norm": 3.1885924339294434, + "learning_rate": 1.9749279121818235e-05, + "loss": 17.9011, + "step": 1014 + }, + { + "epoch": 0.23587509077705157, + "grad_norm": 2.7244787216186523, + "learning_rate": 1.9748423375055674e-05, + "loss": 18.4819, + "step": 1015 + }, + { + "epoch": 0.23610748002904866, + "grad_norm": 2.7296388149261475, + "learning_rate": 1.974756618898969e-05, + "loss": 18.0995, + "step": 1016 + }, + { + "epoch": 0.23633986928104575, + "grad_norm": 2.8435113430023193, + "learning_rate": 1.9746707563746848e-05, + "loss": 18.0968, + "step": 1017 + }, + { + "epoch": 0.23657225853304284, + "grad_norm": 2.90887451171875, + "learning_rate": 1.9745847499453918e-05, + "loss": 18.2505, + "step": 1018 + }, + { + "epoch": 0.23680464778503993, + "grad_norm": 2.6873908042907715, + "learning_rate": 1.9744985996237886e-05, + "loss": 18.7006, + "step": 1019 + }, + { + "epoch": 0.23703703703703705, + "grad_norm": 2.8837296962738037, + "learning_rate": 1.9744123054225944e-05, + "loss": 17.9535, + "step": 1020 + }, + { + "epoch": 0.23726942628903414, + "grad_norm": 2.6867494583129883, + "learning_rate": 1.9743258673545505e-05, + "loss": 17.4289, + "step": 1021 + }, + { + "epoch": 0.23750181554103122, + "grad_norm": 2.734309196472168, + "learning_rate": 1.9742392854324187e-05, + "loss": 17.8745, + "step": 1022 + }, + { + "epoch": 0.23773420479302831, + "grad_norm": 2.745474100112915, + "learning_rate": 1.9741525596689824e-05, + "loss": 17.3833, + "step": 1023 + }, + { + "epoch": 0.23796659404502543, + "grad_norm": 3.0919785499572754, + "learning_rate": 1.9740656900770468e-05, + "loss": 18.3629, + "step": 1024 + }, + { + "epoch": 0.23819898329702252, + "grad_norm": 2.6574273109436035, + "learning_rate": 1.9739786766694368e-05, + "loss": 17.9955, + "step": 1025 + }, + { + "epoch": 0.2384313725490196, + "grad_norm": 2.6862306594848633, + "learning_rate": 1.9738915194590003e-05, + "loss": 17.3947, + "step": 1026 + }, + { + "epoch": 0.2386637618010167, + "grad_norm": 2.8395731449127197, + "learning_rate": 1.973804218458605e-05, + "loss": 17.7909, + "step": 1027 + }, + { + "epoch": 0.2388961510530138, + "grad_norm": 2.7234833240509033, + "learning_rate": 1.973716773681141e-05, + "loss": 18.4236, + "step": 1028 + }, + { + "epoch": 0.2391285403050109, + "grad_norm": 2.698927164077759, + "learning_rate": 1.9736291851395185e-05, + "loss": 17.7963, + "step": 1029 + }, + { + "epoch": 0.239360929557008, + "grad_norm": 2.7281150817871094, + "learning_rate": 1.9735414528466698e-05, + "loss": 17.3337, + "step": 1030 + }, + { + "epoch": 0.23959331880900508, + "grad_norm": 2.6214382648468018, + "learning_rate": 1.9734535768155482e-05, + "loss": 18.0319, + "step": 1031 + }, + { + "epoch": 0.23982570806100217, + "grad_norm": 3.142338275909424, + "learning_rate": 1.9733655570591277e-05, + "loss": 18.8988, + "step": 1032 + }, + { + "epoch": 0.24005809731299926, + "grad_norm": 2.8821640014648438, + "learning_rate": 1.9732773935904045e-05, + "loss": 18.4415, + "step": 1033 + }, + { + "epoch": 0.24029048656499638, + "grad_norm": 3.733879327774048, + "learning_rate": 1.9731890864223948e-05, + "loss": 17.6007, + "step": 1034 + }, + { + "epoch": 0.24052287581699347, + "grad_norm": 2.66302227973938, + "learning_rate": 1.9731006355681374e-05, + "loss": 18.7451, + "step": 1035 + }, + { + "epoch": 0.24075526506899056, + "grad_norm": 2.7150638103485107, + "learning_rate": 1.973012041040691e-05, + "loss": 17.7791, + "step": 1036 + }, + { + "epoch": 0.24098765432098765, + "grad_norm": 2.8026976585388184, + "learning_rate": 1.9729233028531367e-05, + "loss": 18.5959, + "step": 1037 + }, + { + "epoch": 0.24122004357298474, + "grad_norm": 2.8063056468963623, + "learning_rate": 1.972834421018576e-05, + "loss": 18.0153, + "step": 1038 + }, + { + "epoch": 0.24145243282498186, + "grad_norm": 2.8247153759002686, + "learning_rate": 1.9727453955501315e-05, + "loss": 18.0974, + "step": 1039 + }, + { + "epoch": 0.24168482207697894, + "grad_norm": 2.7521045207977295, + "learning_rate": 1.9726562264609475e-05, + "loss": 17.6551, + "step": 1040 + }, + { + "epoch": 0.24191721132897603, + "grad_norm": 2.7574963569641113, + "learning_rate": 1.9725669137641897e-05, + "loss": 18.4391, + "step": 1041 + }, + { + "epoch": 0.24214960058097312, + "grad_norm": 2.7774767875671387, + "learning_rate": 1.9724774574730446e-05, + "loss": 18.288, + "step": 1042 + }, + { + "epoch": 0.2423819898329702, + "grad_norm": 2.830610513687134, + "learning_rate": 1.9723878576007198e-05, + "loss": 18.5033, + "step": 1043 + }, + { + "epoch": 0.24261437908496733, + "grad_norm": 3.0046799182891846, + "learning_rate": 1.972298114160444e-05, + "loss": 18.5145, + "step": 1044 + }, + { + "epoch": 0.24284676833696442, + "grad_norm": 3.037642240524292, + "learning_rate": 1.9722082271654674e-05, + "loss": 19.2149, + "step": 1045 + }, + { + "epoch": 0.2430791575889615, + "grad_norm": 2.9783971309661865, + "learning_rate": 1.9721181966290614e-05, + "loss": 17.4921, + "step": 1046 + }, + { + "epoch": 0.2433115468409586, + "grad_norm": 2.7479193210601807, + "learning_rate": 1.972028022564519e-05, + "loss": 17.9032, + "step": 1047 + }, + { + "epoch": 0.2435439360929557, + "grad_norm": 2.7321572303771973, + "learning_rate": 1.9719377049851535e-05, + "loss": 17.6792, + "step": 1048 + }, + { + "epoch": 0.2437763253449528, + "grad_norm": 2.587839126586914, + "learning_rate": 1.9718472439042995e-05, + "loss": 17.6696, + "step": 1049 + }, + { + "epoch": 0.2440087145969499, + "grad_norm": 13.632503509521484, + "learning_rate": 1.971756639335314e-05, + "loss": 18.9636, + "step": 1050 + }, + { + "epoch": 0.24424110384894698, + "grad_norm": 3.4635634422302246, + "learning_rate": 1.9716658912915735e-05, + "loss": 18.6477, + "step": 1051 + }, + { + "epoch": 0.24447349310094407, + "grad_norm": 2.7911570072174072, + "learning_rate": 1.9715749997864767e-05, + "loss": 17.3233, + "step": 1052 + }, + { + "epoch": 0.2447058823529412, + "grad_norm": 2.7791969776153564, + "learning_rate": 1.9714839648334434e-05, + "loss": 17.8999, + "step": 1053 + }, + { + "epoch": 0.24493827160493828, + "grad_norm": 2.8506526947021484, + "learning_rate": 1.971392786445914e-05, + "loss": 18.0104, + "step": 1054 + }, + { + "epoch": 0.24517066085693537, + "grad_norm": 2.6494767665863037, + "learning_rate": 1.9713014646373513e-05, + "loss": 17.9713, + "step": 1055 + }, + { + "epoch": 0.24540305010893246, + "grad_norm": 2.74342679977417, + "learning_rate": 1.971209999421238e-05, + "loss": 17.3014, + "step": 1056 + }, + { + "epoch": 0.24563543936092955, + "grad_norm": 2.7098147869110107, + "learning_rate": 1.971118390811078e-05, + "loss": 18.5655, + "step": 1057 + }, + { + "epoch": 0.24586782861292666, + "grad_norm": 2.6673710346221924, + "learning_rate": 1.971026638820398e-05, + "loss": 18.4531, + "step": 1058 + }, + { + "epoch": 0.24610021786492375, + "grad_norm": 2.7956790924072266, + "learning_rate": 1.970934743462743e-05, + "loss": 17.5842, + "step": 1059 + }, + { + "epoch": 0.24633260711692084, + "grad_norm": 2.749547004699707, + "learning_rate": 1.9708427047516827e-05, + "loss": 17.9872, + "step": 1060 + }, + { + "epoch": 0.24656499636891793, + "grad_norm": 2.8223278522491455, + "learning_rate": 1.9707505227008053e-05, + "loss": 17.952, + "step": 1061 + }, + { + "epoch": 0.24679738562091502, + "grad_norm": 2.678607225418091, + "learning_rate": 1.9706581973237207e-05, + "loss": 17.612, + "step": 1062 + }, + { + "epoch": 0.24702977487291214, + "grad_norm": 2.696660280227661, + "learning_rate": 1.9705657286340605e-05, + "loss": 18.0267, + "step": 1063 + }, + { + "epoch": 0.24726216412490923, + "grad_norm": 2.641040086746216, + "learning_rate": 1.9704731166454777e-05, + "loss": 18.4456, + "step": 1064 + }, + { + "epoch": 0.24749455337690632, + "grad_norm": 2.8809282779693604, + "learning_rate": 1.970380361371645e-05, + "loss": 17.108, + "step": 1065 + }, + { + "epoch": 0.2477269426289034, + "grad_norm": 2.6413040161132812, + "learning_rate": 1.9702874628262578e-05, + "loss": 17.8584, + "step": 1066 + }, + { + "epoch": 0.2479593318809005, + "grad_norm": 2.771082878112793, + "learning_rate": 1.9701944210230324e-05, + "loss": 18.6592, + "step": 1067 + }, + { + "epoch": 0.2481917211328976, + "grad_norm": 2.9665164947509766, + "learning_rate": 1.9701012359757054e-05, + "loss": 17.6167, + "step": 1068 + }, + { + "epoch": 0.2484241103848947, + "grad_norm": 2.614575147628784, + "learning_rate": 1.970007907698035e-05, + "loss": 17.9031, + "step": 1069 + }, + { + "epoch": 0.2486564996368918, + "grad_norm": 3.2977495193481445, + "learning_rate": 1.9699144362038015e-05, + "loss": 18.021, + "step": 1070 + }, + { + "epoch": 0.24888888888888888, + "grad_norm": 2.861895799636841, + "learning_rate": 1.9698208215068044e-05, + "loss": 18.6176, + "step": 1071 + }, + { + "epoch": 0.24912127814088597, + "grad_norm": 2.815309762954712, + "learning_rate": 1.969727063620866e-05, + "loss": 18.7935, + "step": 1072 + }, + { + "epoch": 0.2493536673928831, + "grad_norm": 2.730794668197632, + "learning_rate": 1.969633162559829e-05, + "loss": 16.8955, + "step": 1073 + }, + { + "epoch": 0.24958605664488018, + "grad_norm": 3.2897138595581055, + "learning_rate": 1.9695391183375575e-05, + "loss": 18.0176, + "step": 1074 + }, + { + "epoch": 0.24981844589687727, + "grad_norm": 9.284709930419922, + "learning_rate": 1.9694449309679365e-05, + "loss": 17.9572, + "step": 1075 + }, + { + "epoch": 0.2500508351488744, + "grad_norm": 3.034679651260376, + "learning_rate": 1.9693506004648724e-05, + "loss": 17.3325, + "step": 1076 + }, + { + "epoch": 0.2500508351488744, + "eval_loss": 2.305210828781128, + "eval_runtime": 2063.3496, + "eval_samples_per_second": 0.537, + "eval_steps_per_second": 0.537, + "step": 1076 + }, + { + "epoch": 0.2502832244008715, + "grad_norm": 2.8040289878845215, + "learning_rate": 1.9692561268422923e-05, + "loss": 18.0157, + "step": 1077 + }, + { + "epoch": 0.25051561365286856, + "grad_norm": 2.6974167823791504, + "learning_rate": 1.9691615101141454e-05, + "loss": 18.424, + "step": 1078 + }, + { + "epoch": 0.25074800290486565, + "grad_norm": 2.673659086227417, + "learning_rate": 1.9690667502944007e-05, + "loss": 18.0486, + "step": 1079 + }, + { + "epoch": 0.25098039215686274, + "grad_norm": 2.8749191761016846, + "learning_rate": 1.9689718473970494e-05, + "loss": 18.2001, + "step": 1080 + }, + { + "epoch": 0.25121278140885983, + "grad_norm": 3.009227752685547, + "learning_rate": 1.968876801436103e-05, + "loss": 17.7649, + "step": 1081 + }, + { + "epoch": 0.2514451706608569, + "grad_norm": 2.7214910984039307, + "learning_rate": 1.9687816124255947e-05, + "loss": 17.5472, + "step": 1082 + }, + { + "epoch": 0.251677559912854, + "grad_norm": 2.6958837509155273, + "learning_rate": 1.9686862803795794e-05, + "loss": 17.9074, + "step": 1083 + }, + { + "epoch": 0.2519099491648511, + "grad_norm": 3.097454071044922, + "learning_rate": 1.968590805312131e-05, + "loss": 16.9187, + "step": 1084 + }, + { + "epoch": 0.25214233841684824, + "grad_norm": 2.7947542667388916, + "learning_rate": 1.9684951872373467e-05, + "loss": 18.9367, + "step": 1085 + }, + { + "epoch": 0.25237472766884533, + "grad_norm": 2.758460760116577, + "learning_rate": 1.968399426169344e-05, + "loss": 18.3559, + "step": 1086 + }, + { + "epoch": 0.2526071169208424, + "grad_norm": 2.695456027984619, + "learning_rate": 1.9683035221222617e-05, + "loss": 18.0897, + "step": 1087 + }, + { + "epoch": 0.2528395061728395, + "grad_norm": 5.00083065032959, + "learning_rate": 1.9682074751102588e-05, + "loss": 17.5169, + "step": 1088 + }, + { + "epoch": 0.2530718954248366, + "grad_norm": 3.170748710632324, + "learning_rate": 1.9681112851475167e-05, + "loss": 18.4674, + "step": 1089 + }, + { + "epoch": 0.2533042846768337, + "grad_norm": 2.804842710494995, + "learning_rate": 1.9680149522482376e-05, + "loss": 17.5218, + "step": 1090 + }, + { + "epoch": 0.2535366739288308, + "grad_norm": 2.7871761322021484, + "learning_rate": 1.967918476426644e-05, + "loss": 17.7956, + "step": 1091 + }, + { + "epoch": 0.25376906318082787, + "grad_norm": 2.7231833934783936, + "learning_rate": 1.96782185769698e-05, + "loss": 17.6212, + "step": 1092 + }, + { + "epoch": 0.25400145243282496, + "grad_norm": 2.732640027999878, + "learning_rate": 1.967725096073511e-05, + "loss": 18.4219, + "step": 1093 + }, + { + "epoch": 0.2542338416848221, + "grad_norm": 2.6985230445861816, + "learning_rate": 1.967628191570524e-05, + "loss": 17.7784, + "step": 1094 + }, + { + "epoch": 0.2544662309368192, + "grad_norm": 2.791283130645752, + "learning_rate": 1.9675311442023254e-05, + "loss": 17.9562, + "step": 1095 + }, + { + "epoch": 0.2546986201888163, + "grad_norm": 2.692122459411621, + "learning_rate": 1.9674339539832443e-05, + "loss": 17.9367, + "step": 1096 + }, + { + "epoch": 0.25493100944081337, + "grad_norm": 2.623812198638916, + "learning_rate": 1.9673366209276302e-05, + "loss": 18.3742, + "step": 1097 + }, + { + "epoch": 0.25516339869281046, + "grad_norm": 2.7299909591674805, + "learning_rate": 1.967239145049854e-05, + "loss": 18.1952, + "step": 1098 + }, + { + "epoch": 0.25539578794480755, + "grad_norm": 4.988456726074219, + "learning_rate": 1.9671415263643068e-05, + "loss": 18.8992, + "step": 1099 + }, + { + "epoch": 0.25562817719680464, + "grad_norm": 2.759430170059204, + "learning_rate": 1.9670437648854023e-05, + "loss": 18.4921, + "step": 1100 + }, + { + "epoch": 0.25586056644880173, + "grad_norm": 13.956753730773926, + "learning_rate": 1.9669458606275742e-05, + "loss": 18.1111, + "step": 1101 + }, + { + "epoch": 0.2560929557007988, + "grad_norm": 3.1948976516723633, + "learning_rate": 1.9668478136052776e-05, + "loss": 18.0099, + "step": 1102 + }, + { + "epoch": 0.2563253449527959, + "grad_norm": 2.7297792434692383, + "learning_rate": 1.9667496238329887e-05, + "loss": 18.0539, + "step": 1103 + }, + { + "epoch": 0.25655773420479305, + "grad_norm": 11.683053016662598, + "learning_rate": 1.9666512913252043e-05, + "loss": 17.7003, + "step": 1104 + }, + { + "epoch": 0.25679012345679014, + "grad_norm": 2.939318895339966, + "learning_rate": 1.9665528160964432e-05, + "loss": 18.1341, + "step": 1105 + }, + { + "epoch": 0.25702251270878723, + "grad_norm": 2.753755569458008, + "learning_rate": 1.9664541981612442e-05, + "loss": 18.2718, + "step": 1106 + }, + { + "epoch": 0.2572549019607843, + "grad_norm": 2.7016444206237793, + "learning_rate": 1.966355437534168e-05, + "loss": 18.3489, + "step": 1107 + }, + { + "epoch": 0.2574872912127814, + "grad_norm": 2.663677453994751, + "learning_rate": 1.9662565342297962e-05, + "loss": 18.0542, + "step": 1108 + }, + { + "epoch": 0.2577196804647785, + "grad_norm": 2.7217938899993896, + "learning_rate": 1.9661574882627312e-05, + "loss": 18.2343, + "step": 1109 + }, + { + "epoch": 0.2579520697167756, + "grad_norm": 2.5180177688598633, + "learning_rate": 1.9660582996475966e-05, + "loss": 18.5245, + "step": 1110 + }, + { + "epoch": 0.2581844589687727, + "grad_norm": 2.7163028717041016, + "learning_rate": 1.965958968399037e-05, + "loss": 17.6027, + "step": 1111 + }, + { + "epoch": 0.25841684822076977, + "grad_norm": 2.8232102394104004, + "learning_rate": 1.9658594945317187e-05, + "loss": 17.1441, + "step": 1112 + }, + { + "epoch": 0.25864923747276686, + "grad_norm": 2.8396527767181396, + "learning_rate": 1.965759878060328e-05, + "loss": 18.5613, + "step": 1113 + }, + { + "epoch": 0.258881626724764, + "grad_norm": 2.7223854064941406, + "learning_rate": 1.9656601189995728e-05, + "loss": 18.3085, + "step": 1114 + }, + { + "epoch": 0.2591140159767611, + "grad_norm": 2.888478994369507, + "learning_rate": 1.965560217364182e-05, + "loss": 17.2311, + "step": 1115 + }, + { + "epoch": 0.2593464052287582, + "grad_norm": 2.654066801071167, + "learning_rate": 1.9654601731689055e-05, + "loss": 18.1083, + "step": 1116 + }, + { + "epoch": 0.25957879448075527, + "grad_norm": 2.6757664680480957, + "learning_rate": 1.965359986428514e-05, + "loss": 18.3502, + "step": 1117 + }, + { + "epoch": 0.25981118373275236, + "grad_norm": 2.8154163360595703, + "learning_rate": 1.9652596571578003e-05, + "loss": 17.8488, + "step": 1118 + }, + { + "epoch": 0.26004357298474945, + "grad_norm": 3.190863609313965, + "learning_rate": 1.965159185371577e-05, + "loss": 18.1107, + "step": 1119 + }, + { + "epoch": 0.26027596223674654, + "grad_norm": 3.7157013416290283, + "learning_rate": 1.9650585710846783e-05, + "loss": 17.6562, + "step": 1120 + }, + { + "epoch": 0.26050835148874363, + "grad_norm": 2.9531502723693848, + "learning_rate": 1.9649578143119595e-05, + "loss": 18.7787, + "step": 1121 + }, + { + "epoch": 0.2607407407407407, + "grad_norm": 2.644339084625244, + "learning_rate": 1.964856915068297e-05, + "loss": 18.8478, + "step": 1122 + }, + { + "epoch": 0.26097312999273786, + "grad_norm": 2.7001073360443115, + "learning_rate": 1.964755873368587e-05, + "loss": 17.2715, + "step": 1123 + }, + { + "epoch": 0.26120551924473495, + "grad_norm": 2.811069965362549, + "learning_rate": 1.964654689227749e-05, + "loss": 17.1359, + "step": 1124 + }, + { + "epoch": 0.26143790849673204, + "grad_norm": 2.7280845642089844, + "learning_rate": 1.964553362660722e-05, + "loss": 17.4963, + "step": 1125 + }, + { + "epoch": 0.26167029774872913, + "grad_norm": 2.6970436573028564, + "learning_rate": 1.9644518936824658e-05, + "loss": 18.2669, + "step": 1126 + }, + { + "epoch": 0.2619026870007262, + "grad_norm": 2.8671813011169434, + "learning_rate": 1.9643502823079623e-05, + "loss": 18.1004, + "step": 1127 + }, + { + "epoch": 0.2621350762527233, + "grad_norm": 2.630970001220703, + "learning_rate": 1.9642485285522138e-05, + "loss": 18.6531, + "step": 1128 + }, + { + "epoch": 0.2623674655047204, + "grad_norm": 3.0771849155426025, + "learning_rate": 1.9641466324302432e-05, + "loss": 18.7217, + "step": 1129 + }, + { + "epoch": 0.2625998547567175, + "grad_norm": 2.830427646636963, + "learning_rate": 1.964044593957096e-05, + "loss": 18.853, + "step": 1130 + }, + { + "epoch": 0.2628322440087146, + "grad_norm": 2.832292318344116, + "learning_rate": 1.9639424131478364e-05, + "loss": 17.7439, + "step": 1131 + }, + { + "epoch": 0.26306463326071167, + "grad_norm": 3.075279474258423, + "learning_rate": 1.9638400900175515e-05, + "loss": 18.5229, + "step": 1132 + }, + { + "epoch": 0.2632970225127088, + "grad_norm": 2.665015935897827, + "learning_rate": 1.963737624581349e-05, + "loss": 17.556, + "step": 1133 + }, + { + "epoch": 0.2635294117647059, + "grad_norm": 2.8629262447357178, + "learning_rate": 1.9636350168543572e-05, + "loss": 18.6381, + "step": 1134 + }, + { + "epoch": 0.263761801016703, + "grad_norm": 3.0017077922821045, + "learning_rate": 1.9635322668517252e-05, + "loss": 17.6374, + "step": 1135 + }, + { + "epoch": 0.2639941902687001, + "grad_norm": 2.7101891040802, + "learning_rate": 1.963429374588624e-05, + "loss": 18.8373, + "step": 1136 + }, + { + "epoch": 0.26422657952069717, + "grad_norm": 2.7983713150024414, + "learning_rate": 1.9633263400802448e-05, + "loss": 17.7678, + "step": 1137 + }, + { + "epoch": 0.26445896877269426, + "grad_norm": 2.7481110095977783, + "learning_rate": 1.9632231633418e-05, + "loss": 18.3625, + "step": 1138 + }, + { + "epoch": 0.26469135802469135, + "grad_norm": 2.6947569847106934, + "learning_rate": 1.9631198443885235e-05, + "loss": 18.1899, + "step": 1139 + }, + { + "epoch": 0.26492374727668844, + "grad_norm": 2.6989967823028564, + "learning_rate": 1.9630163832356695e-05, + "loss": 18.3934, + "step": 1140 + }, + { + "epoch": 0.2651561365286855, + "grad_norm": 2.861443042755127, + "learning_rate": 1.9629127798985138e-05, + "loss": 17.6479, + "step": 1141 + }, + { + "epoch": 0.2653885257806826, + "grad_norm": 2.9003515243530273, + "learning_rate": 1.9628090343923524e-05, + "loss": 18.7313, + "step": 1142 + }, + { + "epoch": 0.26562091503267976, + "grad_norm": 2.7660462856292725, + "learning_rate": 1.962705146732503e-05, + "loss": 17.7862, + "step": 1143 + }, + { + "epoch": 0.26585330428467685, + "grad_norm": 2.850257158279419, + "learning_rate": 1.9626011169343043e-05, + "loss": 17.1312, + "step": 1144 + }, + { + "epoch": 0.26608569353667394, + "grad_norm": 2.986015558242798, + "learning_rate": 1.9624969450131158e-05, + "loss": 17.2481, + "step": 1145 + }, + { + "epoch": 0.26631808278867103, + "grad_norm": 2.7682676315307617, + "learning_rate": 1.9623926309843173e-05, + "loss": 18.5408, + "step": 1146 + }, + { + "epoch": 0.2665504720406681, + "grad_norm": 2.578712224960327, + "learning_rate": 1.9622881748633106e-05, + "loss": 18.8052, + "step": 1147 + }, + { + "epoch": 0.2667828612926652, + "grad_norm": 2.8068959712982178, + "learning_rate": 1.9621835766655187e-05, + "loss": 18.3682, + "step": 1148 + }, + { + "epoch": 0.2670152505446623, + "grad_norm": 2.5985074043273926, + "learning_rate": 1.9620788364063838e-05, + "loss": 18.3464, + "step": 1149 + }, + { + "epoch": 0.2672476397966594, + "grad_norm": 2.9226760864257812, + "learning_rate": 1.961973954101371e-05, + "loss": 19.2737, + "step": 1150 + }, + { + "epoch": 0.2674800290486565, + "grad_norm": 2.6255605220794678, + "learning_rate": 1.9618689297659655e-05, + "loss": 18.879, + "step": 1151 + }, + { + "epoch": 0.2677124183006536, + "grad_norm": 2.8399786949157715, + "learning_rate": 1.961763763415674e-05, + "loss": 19.123, + "step": 1152 + }, + { + "epoch": 0.2679448075526507, + "grad_norm": 2.659423589706421, + "learning_rate": 1.9616584550660226e-05, + "loss": 17.878, + "step": 1153 + }, + { + "epoch": 0.2681771968046478, + "grad_norm": 2.7323806285858154, + "learning_rate": 1.9615530047325605e-05, + "loss": 17.608, + "step": 1154 + }, + { + "epoch": 0.2684095860566449, + "grad_norm": 3.398449420928955, + "learning_rate": 1.961447412430857e-05, + "loss": 18.5458, + "step": 1155 + }, + { + "epoch": 0.268641975308642, + "grad_norm": 2.67085337638855, + "learning_rate": 1.9613416781765015e-05, + "loss": 17.7091, + "step": 1156 + }, + { + "epoch": 0.26887436456063907, + "grad_norm": 2.851060390472412, + "learning_rate": 1.9612358019851055e-05, + "loss": 18.649, + "step": 1157 + }, + { + "epoch": 0.26910675381263616, + "grad_norm": 2.6622703075408936, + "learning_rate": 1.961129783872301e-05, + "loss": 17.5042, + "step": 1158 + }, + { + "epoch": 0.26933914306463325, + "grad_norm": 2.6876323223114014, + "learning_rate": 1.961023623853741e-05, + "loss": 17.5228, + "step": 1159 + }, + { + "epoch": 0.26957153231663034, + "grad_norm": 2.669571876525879, + "learning_rate": 1.9609173219450998e-05, + "loss": 18.4425, + "step": 1160 + }, + { + "epoch": 0.2698039215686274, + "grad_norm": 2.505260944366455, + "learning_rate": 1.9608108781620718e-05, + "loss": 17.5051, + "step": 1161 + }, + { + "epoch": 0.27003631082062457, + "grad_norm": 2.70170521736145, + "learning_rate": 1.9607042925203733e-05, + "loss": 18.6485, + "step": 1162 + }, + { + "epoch": 0.27026870007262166, + "grad_norm": 3.2406890392303467, + "learning_rate": 1.9605975650357406e-05, + "loss": 18.0665, + "step": 1163 + }, + { + "epoch": 0.27050108932461875, + "grad_norm": 3.918522596359253, + "learning_rate": 1.960490695723932e-05, + "loss": 16.6395, + "step": 1164 + }, + { + "epoch": 0.27073347857661584, + "grad_norm": 2.817770481109619, + "learning_rate": 1.9603836846007264e-05, + "loss": 17.359, + "step": 1165 + }, + { + "epoch": 0.2709658678286129, + "grad_norm": 2.613375425338745, + "learning_rate": 1.9602765316819222e-05, + "loss": 17.6974, + "step": 1166 + }, + { + "epoch": 0.27119825708061, + "grad_norm": 2.771059989929199, + "learning_rate": 1.9601692369833413e-05, + "loss": 18.9099, + "step": 1167 + }, + { + "epoch": 0.2714306463326071, + "grad_norm": 2.638205051422119, + "learning_rate": 1.9600618005208242e-05, + "loss": 17.8257, + "step": 1168 + }, + { + "epoch": 0.2716630355846042, + "grad_norm": 2.8628177642822266, + "learning_rate": 1.959954222310234e-05, + "loss": 18.5998, + "step": 1169 + }, + { + "epoch": 0.2718954248366013, + "grad_norm": 2.8419461250305176, + "learning_rate": 1.9598465023674543e-05, + "loss": 17.203, + "step": 1170 + }, + { + "epoch": 0.27212781408859843, + "grad_norm": 2.759065866470337, + "learning_rate": 1.9597386407083883e-05, + "loss": 17.2724, + "step": 1171 + }, + { + "epoch": 0.2723602033405955, + "grad_norm": 2.8294684886932373, + "learning_rate": 1.959630637348962e-05, + "loss": 18.6747, + "step": 1172 + }, + { + "epoch": 0.2725925925925926, + "grad_norm": 3.0434865951538086, + "learning_rate": 1.9595224923051214e-05, + "loss": 17.7965, + "step": 1173 + }, + { + "epoch": 0.2728249818445897, + "grad_norm": 2.6340315341949463, + "learning_rate": 1.9594142055928333e-05, + "loss": 17.7125, + "step": 1174 + }, + { + "epoch": 0.2730573710965868, + "grad_norm": 2.7137928009033203, + "learning_rate": 1.9593057772280863e-05, + "loss": 18.6426, + "step": 1175 + }, + { + "epoch": 0.2732897603485839, + "grad_norm": 2.746319532394409, + "learning_rate": 1.9591972072268886e-05, + "loss": 18.2879, + "step": 1176 + }, + { + "epoch": 0.27352214960058097, + "grad_norm": 2.6291425228118896, + "learning_rate": 1.9590884956052703e-05, + "loss": 18.342, + "step": 1177 + }, + { + "epoch": 0.27375453885257806, + "grad_norm": 2.694920301437378, + "learning_rate": 1.958979642379282e-05, + "loss": 18.5093, + "step": 1178 + }, + { + "epoch": 0.27398692810457514, + "grad_norm": 2.568187713623047, + "learning_rate": 1.9588706475649953e-05, + "loss": 17.7371, + "step": 1179 + }, + { + "epoch": 0.27421931735657223, + "grad_norm": 2.75687837600708, + "learning_rate": 1.9587615111785025e-05, + "loss": 18.0752, + "step": 1180 + }, + { + "epoch": 0.2744517066085694, + "grad_norm": 2.8251612186431885, + "learning_rate": 1.9586522332359177e-05, + "loss": 16.7577, + "step": 1181 + }, + { + "epoch": 0.27468409586056647, + "grad_norm": 2.8744001388549805, + "learning_rate": 1.9585428137533743e-05, + "loss": 17.4328, + "step": 1182 + }, + { + "epoch": 0.27491648511256356, + "grad_norm": 2.8328065872192383, + "learning_rate": 1.9584332527470282e-05, + "loss": 17.7276, + "step": 1183 + }, + { + "epoch": 0.27514887436456065, + "grad_norm": 2.836658477783203, + "learning_rate": 1.9583235502330557e-05, + "loss": 18.3261, + "step": 1184 + }, + { + "epoch": 0.27538126361655774, + "grad_norm": 2.745314121246338, + "learning_rate": 1.9582137062276527e-05, + "loss": 18.7159, + "step": 1185 + }, + { + "epoch": 0.2756136528685548, + "grad_norm": 2.6966049671173096, + "learning_rate": 1.9581037207470382e-05, + "loss": 17.7126, + "step": 1186 + }, + { + "epoch": 0.2758460421205519, + "grad_norm": 2.8128702640533447, + "learning_rate": 1.9579935938074506e-05, + "loss": 17.5735, + "step": 1187 + }, + { + "epoch": 0.276078431372549, + "grad_norm": 2.681072235107422, + "learning_rate": 1.9578833254251494e-05, + "loss": 17.9317, + "step": 1188 + }, + { + "epoch": 0.2763108206245461, + "grad_norm": 2.657115936279297, + "learning_rate": 1.957772915616415e-05, + "loss": 17.7029, + "step": 1189 + }, + { + "epoch": 0.2765432098765432, + "grad_norm": 2.875098943710327, + "learning_rate": 1.9576623643975495e-05, + "loss": 18.4189, + "step": 1190 + }, + { + "epoch": 0.27677559912854033, + "grad_norm": 2.960441827774048, + "learning_rate": 1.9575516717848747e-05, + "loss": 18.9932, + "step": 1191 + }, + { + "epoch": 0.2770079883805374, + "grad_norm": 2.733006000518799, + "learning_rate": 1.957440837794734e-05, + "loss": 19.1968, + "step": 1192 + }, + { + "epoch": 0.2772403776325345, + "grad_norm": 3.130537509918213, + "learning_rate": 1.957329862443491e-05, + "loss": 17.9485, + "step": 1193 + }, + { + "epoch": 0.2774727668845316, + "grad_norm": 3.166273355484009, + "learning_rate": 1.9572187457475312e-05, + "loss": 18.3273, + "step": 1194 + }, + { + "epoch": 0.2777051561365287, + "grad_norm": 2.725391387939453, + "learning_rate": 1.9571074877232604e-05, + "loss": 18.5423, + "step": 1195 + }, + { + "epoch": 0.2779375453885258, + "grad_norm": 2.857874631881714, + "learning_rate": 1.9569960883871045e-05, + "loss": 18.6977, + "step": 1196 + }, + { + "epoch": 0.27816993464052286, + "grad_norm": 2.550870895385742, + "learning_rate": 1.9568845477555117e-05, + "loss": 18.2677, + "step": 1197 + }, + { + "epoch": 0.27840232389251995, + "grad_norm": 2.654736280441284, + "learning_rate": 1.9567728658449504e-05, + "loss": 17.9039, + "step": 1198 + }, + { + "epoch": 0.27863471314451704, + "grad_norm": 3.026247262954712, + "learning_rate": 1.9566610426719096e-05, + "loss": 17.2334, + "step": 1199 + }, + { + "epoch": 0.2788671023965142, + "grad_norm": 2.57108736038208, + "learning_rate": 1.9565490782528997e-05, + "loss": 17.782, + "step": 1200 + }, + { + "epoch": 0.2790994916485113, + "grad_norm": 2.8631293773651123, + "learning_rate": 1.956436972604451e-05, + "loss": 18.1667, + "step": 1201 + }, + { + "epoch": 0.27933188090050837, + "grad_norm": 2.649979591369629, + "learning_rate": 1.956324725743116e-05, + "loss": 18.1978, + "step": 1202 + }, + { + "epoch": 0.27956427015250546, + "grad_norm": 2.825294256210327, + "learning_rate": 1.9562123376854672e-05, + "loss": 18.0384, + "step": 1203 + }, + { + "epoch": 0.27979665940450255, + "grad_norm": 2.7904956340789795, + "learning_rate": 1.9560998084480978e-05, + "loss": 17.3487, + "step": 1204 + }, + { + "epoch": 0.28002904865649964, + "grad_norm": 2.6146864891052246, + "learning_rate": 1.9559871380476222e-05, + "loss": 17.5741, + "step": 1205 + }, + { + "epoch": 0.2802614379084967, + "grad_norm": 2.8157687187194824, + "learning_rate": 1.9558743265006764e-05, + "loss": 18.4253, + "step": 1206 + }, + { + "epoch": 0.2804938271604938, + "grad_norm": 2.740403890609741, + "learning_rate": 1.9557613738239154e-05, + "loss": 17.7028, + "step": 1207 + }, + { + "epoch": 0.2807262164124909, + "grad_norm": 2.6971988677978516, + "learning_rate": 1.9556482800340164e-05, + "loss": 17.9329, + "step": 1208 + }, + { + "epoch": 0.280958605664488, + "grad_norm": 2.6941328048706055, + "learning_rate": 1.9555350451476773e-05, + "loss": 17.5033, + "step": 1209 + }, + { + "epoch": 0.28119099491648514, + "grad_norm": 2.6896114349365234, + "learning_rate": 1.9554216691816162e-05, + "loss": 18.6217, + "step": 1210 + }, + { + "epoch": 0.2814233841684822, + "grad_norm": 2.7777483463287354, + "learning_rate": 1.955308152152573e-05, + "loss": 18.269, + "step": 1211 + }, + { + "epoch": 0.2816557734204793, + "grad_norm": 2.6957993507385254, + "learning_rate": 1.955194494077308e-05, + "loss": 17.7401, + "step": 1212 + }, + { + "epoch": 0.2818881626724764, + "grad_norm": 2.6419339179992676, + "learning_rate": 1.955080694972601e-05, + "loss": 19.2057, + "step": 1213 + }, + { + "epoch": 0.2821205519244735, + "grad_norm": 2.768893003463745, + "learning_rate": 1.9549667548552557e-05, + "loss": 17.4666, + "step": 1214 + }, + { + "epoch": 0.2823529411764706, + "grad_norm": 2.8013827800750732, + "learning_rate": 1.954852673742093e-05, + "loss": 18.3021, + "step": 1215 + }, + { + "epoch": 0.2825853304284677, + "grad_norm": 2.7597415447235107, + "learning_rate": 1.9547384516499575e-05, + "loss": 17.4539, + "step": 1216 + }, + { + "epoch": 0.28281771968046476, + "grad_norm": 2.6941261291503906, + "learning_rate": 1.954624088595713e-05, + "loss": 18.4988, + "step": 1217 + }, + { + "epoch": 0.28305010893246185, + "grad_norm": 2.565075635910034, + "learning_rate": 1.9545095845962447e-05, + "loss": 18.882, + "step": 1218 + }, + { + "epoch": 0.28328249818445894, + "grad_norm": 2.7298007011413574, + "learning_rate": 1.9543949396684586e-05, + "loss": 19.6902, + "step": 1219 + }, + { + "epoch": 0.2835148874364561, + "grad_norm": 2.6918556690216064, + "learning_rate": 1.9542801538292814e-05, + "loss": 18.8984, + "step": 1220 + }, + { + "epoch": 0.2837472766884532, + "grad_norm": 2.6573944091796875, + "learning_rate": 1.9541652270956605e-05, + "loss": 18.4256, + "step": 1221 + }, + { + "epoch": 0.28397966594045027, + "grad_norm": 2.541451930999756, + "learning_rate": 1.9540501594845645e-05, + "loss": 18.3211, + "step": 1222 + }, + { + "epoch": 0.28421205519244735, + "grad_norm": 3.037428617477417, + "learning_rate": 1.9539349510129823e-05, + "loss": 18.8091, + "step": 1223 + }, + { + "epoch": 0.28444444444444444, + "grad_norm": 2.7327475547790527, + "learning_rate": 1.9538196016979237e-05, + "loss": 18.2871, + "step": 1224 + }, + { + "epoch": 0.28467683369644153, + "grad_norm": 2.9571120738983154, + "learning_rate": 1.95370411155642e-05, + "loss": 18.1502, + "step": 1225 + }, + { + "epoch": 0.2849092229484386, + "grad_norm": 3.5274949073791504, + "learning_rate": 1.9535884806055218e-05, + "loss": 18.1392, + "step": 1226 + }, + { + "epoch": 0.2851416122004357, + "grad_norm": 2.614056348800659, + "learning_rate": 1.9534727088623023e-05, + "loss": 18.1853, + "step": 1227 + }, + { + "epoch": 0.2853740014524328, + "grad_norm": 2.671213388442993, + "learning_rate": 1.953356796343854e-05, + "loss": 18.7949, + "step": 1228 + }, + { + "epoch": 0.28560639070442995, + "grad_norm": 2.6803665161132812, + "learning_rate": 1.953240743067291e-05, + "loss": 19.0924, + "step": 1229 + }, + { + "epoch": 0.28583877995642704, + "grad_norm": 2.602985143661499, + "learning_rate": 1.9531245490497478e-05, + "loss": 17.5888, + "step": 1230 + }, + { + "epoch": 0.2860711692084241, + "grad_norm": 2.7344906330108643, + "learning_rate": 1.9530082143083803e-05, + "loss": 18.666, + "step": 1231 + }, + { + "epoch": 0.2863035584604212, + "grad_norm": 3.060042142868042, + "learning_rate": 1.9528917388603637e-05, + "loss": 17.5915, + "step": 1232 + }, + { + "epoch": 0.2865359477124183, + "grad_norm": 2.789668560028076, + "learning_rate": 1.9527751227228964e-05, + "loss": 17.2495, + "step": 1233 + }, + { + "epoch": 0.2867683369644154, + "grad_norm": 2.5812766551971436, + "learning_rate": 1.9526583659131953e-05, + "loss": 18.5166, + "step": 1234 + }, + { + "epoch": 0.2870007262164125, + "grad_norm": 3.474550724029541, + "learning_rate": 1.952541468448499e-05, + "loss": 16.8306, + "step": 1235 + }, + { + "epoch": 0.28723311546840957, + "grad_norm": 2.6407828330993652, + "learning_rate": 1.9524244303460665e-05, + "loss": 17.5835, + "step": 1236 + }, + { + "epoch": 0.28746550472040666, + "grad_norm": 2.6977381706237793, + "learning_rate": 1.9523072516231785e-05, + "loss": 17.6081, + "step": 1237 + }, + { + "epoch": 0.28769789397240375, + "grad_norm": 2.8074584007263184, + "learning_rate": 1.9521899322971353e-05, + "loss": 17.4959, + "step": 1238 + }, + { + "epoch": 0.2879302832244009, + "grad_norm": 2.695405960083008, + "learning_rate": 1.9520724723852588e-05, + "loss": 18.2449, + "step": 1239 + }, + { + "epoch": 0.288162672476398, + "grad_norm": 2.6557514667510986, + "learning_rate": 1.951954871904891e-05, + "loss": 18.6824, + "step": 1240 + }, + { + "epoch": 0.2883950617283951, + "grad_norm": 2.6687233448028564, + "learning_rate": 1.951837130873396e-05, + "loss": 18.734, + "step": 1241 + }, + { + "epoch": 0.28862745098039216, + "grad_norm": 3.3019521236419678, + "learning_rate": 1.9517192493081563e-05, + "loss": 18.4633, + "step": 1242 + }, + { + "epoch": 0.28885984023238925, + "grad_norm": 2.554884672164917, + "learning_rate": 1.9516012272265775e-05, + "loss": 18.5065, + "step": 1243 + }, + { + "epoch": 0.28909222948438634, + "grad_norm": 2.833883285522461, + "learning_rate": 1.951483064646084e-05, + "loss": 17.4342, + "step": 1244 + }, + { + "epoch": 0.28932461873638343, + "grad_norm": 2.8443264961242676, + "learning_rate": 1.9513647615841228e-05, + "loss": 17.2773, + "step": 1245 + }, + { + "epoch": 0.2895570079883805, + "grad_norm": 2.532630443572998, + "learning_rate": 1.95124631805816e-05, + "loss": 18.9163, + "step": 1246 + }, + { + "epoch": 0.2897893972403776, + "grad_norm": 2.93961501121521, + "learning_rate": 1.9511277340856837e-05, + "loss": 17.8922, + "step": 1247 + }, + { + "epoch": 0.2900217864923747, + "grad_norm": 2.7334625720977783, + "learning_rate": 1.9510090096842016e-05, + "loss": 17.6384, + "step": 1248 + }, + { + "epoch": 0.29025417574437185, + "grad_norm": 2.6728386878967285, + "learning_rate": 1.9508901448712432e-05, + "loss": 17.6415, + "step": 1249 + }, + { + "epoch": 0.29048656499636893, + "grad_norm": 2.586010217666626, + "learning_rate": 1.9507711396643587e-05, + "loss": 17.9291, + "step": 1250 + }, + { + "epoch": 0.290718954248366, + "grad_norm": 5.098442554473877, + "learning_rate": 1.9506519940811176e-05, + "loss": 18.0688, + "step": 1251 + }, + { + "epoch": 0.2909513435003631, + "grad_norm": 2.795992612838745, + "learning_rate": 1.950532708139112e-05, + "loss": 17.9786, + "step": 1252 + }, + { + "epoch": 0.2911837327523602, + "grad_norm": 3.030015707015991, + "learning_rate": 1.950413281855953e-05, + "loss": 18.2476, + "step": 1253 + }, + { + "epoch": 0.2914161220043573, + "grad_norm": 2.761051893234253, + "learning_rate": 1.950293715249274e-05, + "loss": 17.6822, + "step": 1254 + }, + { + "epoch": 0.2916485112563544, + "grad_norm": 2.7051243782043457, + "learning_rate": 1.950174008336728e-05, + "loss": 18.768, + "step": 1255 + }, + { + "epoch": 0.29188090050835147, + "grad_norm": 2.722601890563965, + "learning_rate": 1.950054161135989e-05, + "loss": 17.9508, + "step": 1256 + }, + { + "epoch": 0.29211328976034856, + "grad_norm": 2.9556562900543213, + "learning_rate": 1.9499341736647522e-05, + "loss": 18.3258, + "step": 1257 + }, + { + "epoch": 0.2923456790123457, + "grad_norm": 2.620591163635254, + "learning_rate": 1.9498140459407328e-05, + "loss": 19.0312, + "step": 1258 + }, + { + "epoch": 0.2925780682643428, + "grad_norm": 2.611633777618408, + "learning_rate": 1.9496937779816672e-05, + "loss": 17.9745, + "step": 1259 + }, + { + "epoch": 0.2928104575163399, + "grad_norm": 2.748063564300537, + "learning_rate": 1.949573369805312e-05, + "loss": 17.7029, + "step": 1260 + }, + { + "epoch": 0.293042846768337, + "grad_norm": 2.890711545944214, + "learning_rate": 1.9494528214294454e-05, + "loss": 18.3762, + "step": 1261 + }, + { + "epoch": 0.29327523602033406, + "grad_norm": 3.1515963077545166, + "learning_rate": 1.9493321328718653e-05, + "loss": 18.5886, + "step": 1262 + }, + { + "epoch": 0.29350762527233115, + "grad_norm": 2.758014440536499, + "learning_rate": 1.9492113041503908e-05, + "loss": 17.7631, + "step": 1263 + }, + { + "epoch": 0.29374001452432824, + "grad_norm": 4.247521877288818, + "learning_rate": 1.9490903352828615e-05, + "loss": 18.1917, + "step": 1264 + }, + { + "epoch": 0.29397240377632533, + "grad_norm": 2.6076953411102295, + "learning_rate": 1.9489692262871385e-05, + "loss": 18.4178, + "step": 1265 + }, + { + "epoch": 0.2942047930283224, + "grad_norm": 2.8053927421569824, + "learning_rate": 1.948847977181102e-05, + "loss": 18.458, + "step": 1266 + }, + { + "epoch": 0.2944371822803195, + "grad_norm": 2.570727825164795, + "learning_rate": 1.9487265879826546e-05, + "loss": 17.5984, + "step": 1267 + }, + { + "epoch": 0.29466957153231665, + "grad_norm": 2.658029794692993, + "learning_rate": 1.9486050587097177e-05, + "loss": 18.7382, + "step": 1268 + }, + { + "epoch": 0.29490196078431374, + "grad_norm": 2.628006935119629, + "learning_rate": 1.9484833893802356e-05, + "loss": 19.348, + "step": 1269 + }, + { + "epoch": 0.29513435003631083, + "grad_norm": 2.661255121231079, + "learning_rate": 1.9483615800121717e-05, + "loss": 18.3125, + "step": 1270 + }, + { + "epoch": 0.2953667392883079, + "grad_norm": 2.6200990676879883, + "learning_rate": 1.9482396306235107e-05, + "loss": 18.596, + "step": 1271 + }, + { + "epoch": 0.295599128540305, + "grad_norm": 2.934023857116699, + "learning_rate": 1.9481175412322568e-05, + "loss": 19.6138, + "step": 1272 + }, + { + "epoch": 0.2958315177923021, + "grad_norm": 3.8292996883392334, + "learning_rate": 1.9479953118564373e-05, + "loss": 16.9604, + "step": 1273 + }, + { + "epoch": 0.2960639070442992, + "grad_norm": 2.830195665359497, + "learning_rate": 1.9478729425140977e-05, + "loss": 18.0353, + "step": 1274 + }, + { + "epoch": 0.2962962962962963, + "grad_norm": 2.7125766277313232, + "learning_rate": 1.9477504332233056e-05, + "loss": 17.3193, + "step": 1275 + }, + { + "epoch": 0.29652868554829337, + "grad_norm": 3.0772597789764404, + "learning_rate": 1.947627784002149e-05, + "loss": 18.2941, + "step": 1276 + }, + { + "epoch": 0.2967610748002905, + "grad_norm": 2.9498908519744873, + "learning_rate": 1.947504994868736e-05, + "loss": 17.4705, + "step": 1277 + }, + { + "epoch": 0.2969934640522876, + "grad_norm": 2.7297773361206055, + "learning_rate": 1.947382065841196e-05, + "loss": 17.1178, + "step": 1278 + }, + { + "epoch": 0.2972258533042847, + "grad_norm": 2.6776981353759766, + "learning_rate": 1.9472589969376784e-05, + "loss": 18.2241, + "step": 1279 + }, + { + "epoch": 0.2974582425562818, + "grad_norm": 2.918119192123413, + "learning_rate": 1.9471357881763545e-05, + "loss": 17.7669, + "step": 1280 + }, + { + "epoch": 0.29769063180827887, + "grad_norm": 2.6810083389282227, + "learning_rate": 1.947012439575415e-05, + "loss": 17.4983, + "step": 1281 + }, + { + "epoch": 0.29792302106027596, + "grad_norm": 2.5841212272644043, + "learning_rate": 1.9468889511530714e-05, + "loss": 17.8264, + "step": 1282 + }, + { + "epoch": 0.29815541031227305, + "grad_norm": 2.9803521633148193, + "learning_rate": 1.9467653229275567e-05, + "loss": 18.8553, + "step": 1283 + }, + { + "epoch": 0.29838779956427014, + "grad_norm": 2.799368381500244, + "learning_rate": 1.9466415549171235e-05, + "loss": 18.0535, + "step": 1284 + }, + { + "epoch": 0.29862018881626723, + "grad_norm": 2.7487308979034424, + "learning_rate": 1.9465176471400458e-05, + "loss": 18.2469, + "step": 1285 + }, + { + "epoch": 0.2988525780682643, + "grad_norm": 2.6511518955230713, + "learning_rate": 1.9463935996146173e-05, + "loss": 17.8408, + "step": 1286 + }, + { + "epoch": 0.29908496732026146, + "grad_norm": 2.625608444213867, + "learning_rate": 1.9462694123591536e-05, + "loss": 17.7313, + "step": 1287 + }, + { + "epoch": 0.29931735657225855, + "grad_norm": 2.7401413917541504, + "learning_rate": 1.9461450853919904e-05, + "loss": 17.6695, + "step": 1288 + }, + { + "epoch": 0.29954974582425564, + "grad_norm": 2.616044282913208, + "learning_rate": 1.9460206187314835e-05, + "loss": 18.2849, + "step": 1289 + }, + { + "epoch": 0.29978213507625273, + "grad_norm": 2.797055244445801, + "learning_rate": 1.94589601239601e-05, + "loss": 18.3359, + "step": 1290 + }, + { + "epoch": 0.3000145243282498, + "grad_norm": 2.639103889465332, + "learning_rate": 1.9457712664039673e-05, + "loss": 17.3035, + "step": 1291 + }, + { + "epoch": 0.3002469135802469, + "grad_norm": 2.7659640312194824, + "learning_rate": 1.945646380773773e-05, + "loss": 18.2498, + "step": 1292 + }, + { + "epoch": 0.300479302832244, + "grad_norm": 2.7303411960601807, + "learning_rate": 1.9455213555238667e-05, + "loss": 18.1439, + "step": 1293 + }, + { + "epoch": 0.3007116920842411, + "grad_norm": 2.757176637649536, + "learning_rate": 1.9453961906727073e-05, + "loss": 18.1116, + "step": 1294 + }, + { + "epoch": 0.3009440813362382, + "grad_norm": 2.6020755767822266, + "learning_rate": 1.9452708862387743e-05, + "loss": 17.4664, + "step": 1295 + }, + { + "epoch": 0.30117647058823527, + "grad_norm": 2.7149736881256104, + "learning_rate": 1.9451454422405687e-05, + "loss": 17.4026, + "step": 1296 + }, + { + "epoch": 0.3014088598402324, + "grad_norm": 2.6479318141937256, + "learning_rate": 1.945019858696612e-05, + "loss": 17.6401, + "step": 1297 + }, + { + "epoch": 0.3016412490922295, + "grad_norm": 6.362758636474609, + "learning_rate": 1.9448941356254453e-05, + "loss": 17.6893, + "step": 1298 + }, + { + "epoch": 0.3018736383442266, + "grad_norm": 2.5947444438934326, + "learning_rate": 1.9447682730456315e-05, + "loss": 18.1685, + "step": 1299 + }, + { + "epoch": 0.3021060275962237, + "grad_norm": 2.8130593299865723, + "learning_rate": 1.9446422709757527e-05, + "loss": 17.284, + "step": 1300 + }, + { + "epoch": 0.30233841684822077, + "grad_norm": 2.7108702659606934, + "learning_rate": 1.9445161294344134e-05, + "loss": 17.6325, + "step": 1301 + }, + { + "epoch": 0.30257080610021786, + "grad_norm": 2.891650438308716, + "learning_rate": 1.944389848440237e-05, + "loss": 17.7856, + "step": 1302 + }, + { + "epoch": 0.30280319535221495, + "grad_norm": 2.851879119873047, + "learning_rate": 1.9442634280118687e-05, + "loss": 18.3475, + "step": 1303 + }, + { + "epoch": 0.30303558460421204, + "grad_norm": 2.6549670696258545, + "learning_rate": 1.9441368681679738e-05, + "loss": 18.3784, + "step": 1304 + }, + { + "epoch": 0.3032679738562091, + "grad_norm": 2.653907537460327, + "learning_rate": 1.944010168927238e-05, + "loss": 17.9982, + "step": 1305 + }, + { + "epoch": 0.3035003631082063, + "grad_norm": 2.6736950874328613, + "learning_rate": 1.9438833303083677e-05, + "loss": 18.2955, + "step": 1306 + }, + { + "epoch": 0.30373275236020336, + "grad_norm": 2.608851671218872, + "learning_rate": 1.9437563523300902e-05, + "loss": 17.6814, + "step": 1307 + }, + { + "epoch": 0.30396514161220045, + "grad_norm": 2.656111478805542, + "learning_rate": 1.9436292350111528e-05, + "loss": 17.8819, + "step": 1308 + }, + { + "epoch": 0.30419753086419754, + "grad_norm": 2.6619653701782227, + "learning_rate": 1.9435019783703243e-05, + "loss": 18.2081, + "step": 1309 + }, + { + "epoch": 0.30442992011619463, + "grad_norm": 2.868046283721924, + "learning_rate": 1.943374582426393e-05, + "loss": 18.6239, + "step": 1310 + }, + { + "epoch": 0.3046623093681917, + "grad_norm": 3.067265033721924, + "learning_rate": 1.943247047198168e-05, + "loss": 18.4497, + "step": 1311 + }, + { + "epoch": 0.3048946986201888, + "grad_norm": 2.8489935398101807, + "learning_rate": 1.9431193727044796e-05, + "loss": 17.5261, + "step": 1312 + }, + { + "epoch": 0.3051270878721859, + "grad_norm": 2.665961742401123, + "learning_rate": 1.9429915589641782e-05, + "loss": 18.3288, + "step": 1313 + }, + { + "epoch": 0.305359477124183, + "grad_norm": 2.759645462036133, + "learning_rate": 1.942863605996135e-05, + "loss": 18.6588, + "step": 1314 + }, + { + "epoch": 0.3055918663761801, + "grad_norm": 2.677046537399292, + "learning_rate": 1.9427355138192416e-05, + "loss": 17.9561, + "step": 1315 + }, + { + "epoch": 0.3058242556281772, + "grad_norm": 2.6628079414367676, + "learning_rate": 1.9426072824524097e-05, + "loss": 16.6571, + "step": 1316 + }, + { + "epoch": 0.3060566448801743, + "grad_norm": 2.684413194656372, + "learning_rate": 1.9424789119145725e-05, + "loss": 18.4095, + "step": 1317 + }, + { + "epoch": 0.3062890341321714, + "grad_norm": 2.849973201751709, + "learning_rate": 1.9423504022246825e-05, + "loss": 18.3662, + "step": 1318 + }, + { + "epoch": 0.3065214233841685, + "grad_norm": 2.8122828006744385, + "learning_rate": 1.942221753401714e-05, + "loss": 18.5742, + "step": 1319 + }, + { + "epoch": 0.3067538126361656, + "grad_norm": 2.7962443828582764, + "learning_rate": 1.9420929654646617e-05, + "loss": 17.9744, + "step": 1320 + }, + { + "epoch": 0.30698620188816267, + "grad_norm": 5.498431205749512, + "learning_rate": 1.9419640384325397e-05, + "loss": 18.4478, + "step": 1321 + }, + { + "epoch": 0.30721859114015976, + "grad_norm": 2.6207456588745117, + "learning_rate": 1.941834972324384e-05, + "loss": 18.1886, + "step": 1322 + }, + { + "epoch": 0.30745098039215685, + "grad_norm": 2.854128360748291, + "learning_rate": 1.9417057671592498e-05, + "loss": 17.9347, + "step": 1323 + }, + { + "epoch": 0.30768336964415394, + "grad_norm": 2.6453003883361816, + "learning_rate": 1.9415764229562144e-05, + "loss": 18.6858, + "step": 1324 + }, + { + "epoch": 0.307915758896151, + "grad_norm": 2.770293712615967, + "learning_rate": 1.9414469397343746e-05, + "loss": 19.2701, + "step": 1325 + }, + { + "epoch": 0.30814814814814817, + "grad_norm": 2.8560290336608887, + "learning_rate": 1.9413173175128472e-05, + "loss": 18.0244, + "step": 1326 + }, + { + "epoch": 0.30838053740014526, + "grad_norm": 2.6951217651367188, + "learning_rate": 1.941187556310771e-05, + "loss": 17.8841, + "step": 1327 + }, + { + "epoch": 0.30861292665214235, + "grad_norm": 2.9934041500091553, + "learning_rate": 1.9410576561473046e-05, + "loss": 16.9173, + "step": 1328 + }, + { + "epoch": 0.30884531590413944, + "grad_norm": 2.604275703430176, + "learning_rate": 1.940927617041626e-05, + "loss": 18.1921, + "step": 1329 + }, + { + "epoch": 0.30907770515613653, + "grad_norm": 2.607879161834717, + "learning_rate": 1.9407974390129366e-05, + "loss": 17.6717, + "step": 1330 + }, + { + "epoch": 0.3093100944081336, + "grad_norm": 2.71572208404541, + "learning_rate": 1.9406671220804548e-05, + "loss": 17.8307, + "step": 1331 + }, + { + "epoch": 0.3095424836601307, + "grad_norm": 2.7490270137786865, + "learning_rate": 1.9405366662634223e-05, + "loss": 17.8837, + "step": 1332 + }, + { + "epoch": 0.3097748729121278, + "grad_norm": 2.8279645442962646, + "learning_rate": 1.9404060715810996e-05, + "loss": 18.2987, + "step": 1333 + }, + { + "epoch": 0.3100072621641249, + "grad_norm": 3.668870687484741, + "learning_rate": 1.940275338052769e-05, + "loss": 18.0465, + "step": 1334 + }, + { + "epoch": 0.31023965141612203, + "grad_norm": 2.6479082107543945, + "learning_rate": 1.940144465697731e-05, + "loss": 18.8054, + "step": 1335 + }, + { + "epoch": 0.3104720406681191, + "grad_norm": 2.5605053901672363, + "learning_rate": 1.9400134545353104e-05, + "loss": 18.1433, + "step": 1336 + }, + { + "epoch": 0.3107044299201162, + "grad_norm": 3.404607057571411, + "learning_rate": 1.939882304584849e-05, + "loss": 18.247, + "step": 1337 + }, + { + "epoch": 0.3109368191721133, + "grad_norm": 2.7869720458984375, + "learning_rate": 1.939751015865711e-05, + "loss": 18.0084, + "step": 1338 + }, + { + "epoch": 0.3111692084241104, + "grad_norm": 2.7985081672668457, + "learning_rate": 1.9396195883972798e-05, + "loss": 17.1241, + "step": 1339 + }, + { + "epoch": 0.3114015976761075, + "grad_norm": 6.5461225509643555, + "learning_rate": 1.9394880221989604e-05, + "loss": 17.3255, + "step": 1340 + }, + { + "epoch": 0.31163398692810457, + "grad_norm": 3.6769049167633057, + "learning_rate": 1.939356317290178e-05, + "loss": 17.1342, + "step": 1341 + }, + { + "epoch": 0.31186637618010166, + "grad_norm": 2.788935661315918, + "learning_rate": 1.9392244736903774e-05, + "loss": 17.3929, + "step": 1342 + }, + { + "epoch": 0.31209876543209875, + "grad_norm": 2.7015626430511475, + "learning_rate": 1.9390924914190256e-05, + "loss": 16.9774, + "step": 1343 + }, + { + "epoch": 0.31233115468409584, + "grad_norm": 2.5367355346679688, + "learning_rate": 1.9389603704956082e-05, + "loss": 17.7303, + "step": 1344 + }, + { + "epoch": 0.312563543936093, + "grad_norm": 2.8259289264678955, + "learning_rate": 1.938828110939633e-05, + "loss": 17.5121, + "step": 1345 + }, + { + "epoch": 0.31279593318809007, + "grad_norm": 2.86380672454834, + "learning_rate": 1.938695712770627e-05, + "loss": 18.2409, + "step": 1346 + }, + { + "epoch": 0.31302832244008716, + "grad_norm": 2.709808111190796, + "learning_rate": 1.938563176008138e-05, + "loss": 17.8183, + "step": 1347 + }, + { + "epoch": 0.31326071169208425, + "grad_norm": 2.806187868118286, + "learning_rate": 1.9384305006717348e-05, + "loss": 17.7006, + "step": 1348 + }, + { + "epoch": 0.31349310094408134, + "grad_norm": 2.711740016937256, + "learning_rate": 1.9382976867810054e-05, + "loss": 18.1973, + "step": 1349 + }, + { + "epoch": 0.3137254901960784, + "grad_norm": 3.1429660320281982, + "learning_rate": 1.9381647343555597e-05, + "loss": 17.385, + "step": 1350 + }, + { + "epoch": 0.3139578794480755, + "grad_norm": 2.699995517730713, + "learning_rate": 1.9380316434150276e-05, + "loss": 17.7131, + "step": 1351 + }, + { + "epoch": 0.3141902687000726, + "grad_norm": 2.658123731613159, + "learning_rate": 1.9378984139790585e-05, + "loss": 18.1525, + "step": 1352 + }, + { + "epoch": 0.3144226579520697, + "grad_norm": 2.84690260887146, + "learning_rate": 1.9377650460673236e-05, + "loss": 17.7555, + "step": 1353 + }, + { + "epoch": 0.3146550472040668, + "grad_norm": 2.785778760910034, + "learning_rate": 1.937631539699514e-05, + "loss": 17.4669, + "step": 1354 + }, + { + "epoch": 0.31488743645606393, + "grad_norm": 2.789342164993286, + "learning_rate": 1.937497894895341e-05, + "loss": 17.2128, + "step": 1355 + }, + { + "epoch": 0.315119825708061, + "grad_norm": 3.110088348388672, + "learning_rate": 1.937364111674537e-05, + "loss": 17.6286, + "step": 1356 + }, + { + "epoch": 0.3153522149600581, + "grad_norm": 6.71177339553833, + "learning_rate": 1.9372301900568537e-05, + "loss": 18.1001, + "step": 1357 + }, + { + "epoch": 0.3155846042120552, + "grad_norm": 2.613722324371338, + "learning_rate": 1.9370961300620637e-05, + "loss": 17.6312, + "step": 1358 + }, + { + "epoch": 0.3158169934640523, + "grad_norm": 2.8940136432647705, + "learning_rate": 1.9369619317099615e-05, + "loss": 18.7455, + "step": 1359 + }, + { + "epoch": 0.3160493827160494, + "grad_norm": 2.5670461654663086, + "learning_rate": 1.93682759502036e-05, + "loss": 17.732, + "step": 1360 + }, + { + "epoch": 0.31628177196804647, + "grad_norm": 2.7562105655670166, + "learning_rate": 1.936693120013093e-05, + "loss": 19.0739, + "step": 1361 + }, + { + "epoch": 0.31651416122004356, + "grad_norm": 4.250255584716797, + "learning_rate": 1.936558506708016e-05, + "loss": 18.0981, + "step": 1362 + }, + { + "epoch": 0.31674655047204064, + "grad_norm": 3.147610902786255, + "learning_rate": 1.9364237551250026e-05, + "loss": 18.6042, + "step": 1363 + }, + { + "epoch": 0.3169789397240378, + "grad_norm": 2.935199022293091, + "learning_rate": 1.9362888652839495e-05, + "loss": 18.2102, + "step": 1364 + }, + { + "epoch": 0.3172113289760349, + "grad_norm": 2.5453124046325684, + "learning_rate": 1.9361538372047717e-05, + "loss": 17.7511, + "step": 1365 + }, + { + "epoch": 0.31744371822803197, + "grad_norm": 2.646955728530884, + "learning_rate": 1.9360186709074055e-05, + "loss": 18.0599, + "step": 1366 + }, + { + "epoch": 0.31767610748002906, + "grad_norm": 3.180393695831299, + "learning_rate": 1.9358833664118078e-05, + "loss": 17.6646, + "step": 1367 + }, + { + "epoch": 0.31790849673202615, + "grad_norm": 2.8756964206695557, + "learning_rate": 1.9357479237379552e-05, + "loss": 18.3952, + "step": 1368 + }, + { + "epoch": 0.31814088598402324, + "grad_norm": 4.634639263153076, + "learning_rate": 1.935612342905845e-05, + "loss": 18.2752, + "step": 1369 + }, + { + "epoch": 0.3183732752360203, + "grad_norm": 2.8355753421783447, + "learning_rate": 1.9354766239354953e-05, + "loss": 18.4796, + "step": 1370 + }, + { + "epoch": 0.3186056644880174, + "grad_norm": 2.8994481563568115, + "learning_rate": 1.9353407668469446e-05, + "loss": 17.5202, + "step": 1371 + }, + { + "epoch": 0.3188380537400145, + "grad_norm": 2.6208701133728027, + "learning_rate": 1.935204771660251e-05, + "loss": 17.7283, + "step": 1372 + }, + { + "epoch": 0.3190704429920116, + "grad_norm": 3.043182373046875, + "learning_rate": 1.9350686383954935e-05, + "loss": 17.5373, + "step": 1373 + }, + { + "epoch": 0.31930283224400874, + "grad_norm": 2.828977584838867, + "learning_rate": 1.934932367072772e-05, + "loss": 18.1831, + "step": 1374 + }, + { + "epoch": 0.31953522149600583, + "grad_norm": 2.5716400146484375, + "learning_rate": 1.934795957712205e-05, + "loss": 17.5566, + "step": 1375 + }, + { + "epoch": 0.3197676107480029, + "grad_norm": 2.7313709259033203, + "learning_rate": 1.934659410333934e-05, + "loss": 18.8256, + "step": 1376 + }, + { + "epoch": 0.32, + "grad_norm": 3.051750421524048, + "learning_rate": 1.9345227249581188e-05, + "loss": 18.6158, + "step": 1377 + }, + { + "epoch": 0.3202323892519971, + "grad_norm": 3.0237507820129395, + "learning_rate": 1.9343859016049405e-05, + "loss": 18.2302, + "step": 1378 + }, + { + "epoch": 0.3204647785039942, + "grad_norm": 2.7739081382751465, + "learning_rate": 1.9342489402945997e-05, + "loss": 18.1055, + "step": 1379 + }, + { + "epoch": 0.3206971677559913, + "grad_norm": 2.8193116188049316, + "learning_rate": 1.9341118410473192e-05, + "loss": 18.662, + "step": 1380 + }, + { + "epoch": 0.32092955700798836, + "grad_norm": 2.8380446434020996, + "learning_rate": 1.9339746038833404e-05, + "loss": 17.5835, + "step": 1381 + }, + { + "epoch": 0.32116194625998545, + "grad_norm": 2.7873470783233643, + "learning_rate": 1.9338372288229253e-05, + "loss": 18.0938, + "step": 1382 + }, + { + "epoch": 0.3213943355119826, + "grad_norm": 2.7497153282165527, + "learning_rate": 1.933699715886357e-05, + "loss": 17.8931, + "step": 1383 + }, + { + "epoch": 0.3216267247639797, + "grad_norm": 2.8392584323883057, + "learning_rate": 1.9335620650939385e-05, + "loss": 18.57, + "step": 1384 + }, + { + "epoch": 0.3218591140159768, + "grad_norm": 2.8287980556488037, + "learning_rate": 1.9334242764659932e-05, + "loss": 17.7727, + "step": 1385 + }, + { + "epoch": 0.32209150326797387, + "grad_norm": 2.7618680000305176, + "learning_rate": 1.933286350022865e-05, + "loss": 17.8597, + "step": 1386 + }, + { + "epoch": 0.32232389251997096, + "grad_norm": 2.611485004425049, + "learning_rate": 1.9331482857849172e-05, + "loss": 17.3185, + "step": 1387 + }, + { + "epoch": 0.32255628177196805, + "grad_norm": 2.944995880126953, + "learning_rate": 1.9330100837725356e-05, + "loss": 18.4094, + "step": 1388 + }, + { + "epoch": 0.32278867102396513, + "grad_norm": 2.8774220943450928, + "learning_rate": 1.9328717440061243e-05, + "loss": 18.34, + "step": 1389 + }, + { + "epoch": 0.3230210602759622, + "grad_norm": 6.884574890136719, + "learning_rate": 1.9327332665061083e-05, + "loss": 17.3742, + "step": 1390 + }, + { + "epoch": 0.3232534495279593, + "grad_norm": 2.7450387477874756, + "learning_rate": 1.932594651292933e-05, + "loss": 18.5774, + "step": 1391 + }, + { + "epoch": 0.3234858387799564, + "grad_norm": 2.5967512130737305, + "learning_rate": 1.932455898387065e-05, + "loss": 18.765, + "step": 1392 + }, + { + "epoch": 0.32371822803195355, + "grad_norm": 2.819774627685547, + "learning_rate": 1.932317007808989e-05, + "loss": 18.5387, + "step": 1393 + }, + { + "epoch": 0.32395061728395064, + "grad_norm": 2.936725616455078, + "learning_rate": 1.9321779795792134e-05, + "loss": 17.6527, + "step": 1394 + }, + { + "epoch": 0.3241830065359477, + "grad_norm": 2.6996681690216064, + "learning_rate": 1.932038813718263e-05, + "loss": 18.0419, + "step": 1395 + }, + { + "epoch": 0.3244153957879448, + "grad_norm": 2.648125648498535, + "learning_rate": 1.9318995102466865e-05, + "loss": 18.0345, + "step": 1396 + }, + { + "epoch": 0.3246477850399419, + "grad_norm": 3.0304086208343506, + "learning_rate": 1.9317600691850504e-05, + "loss": 18.5204, + "step": 1397 + }, + { + "epoch": 0.324880174291939, + "grad_norm": 2.8215489387512207, + "learning_rate": 1.9316204905539425e-05, + "loss": 17.0857, + "step": 1398 + }, + { + "epoch": 0.3251125635439361, + "grad_norm": 3.718080520629883, + "learning_rate": 1.9314807743739715e-05, + "loss": 15.5705, + "step": 1399 + }, + { + "epoch": 0.3253449527959332, + "grad_norm": 2.6568443775177, + "learning_rate": 1.931340920665765e-05, + "loss": 17.653, + "step": 1400 + }, + { + "epoch": 0.32557734204793026, + "grad_norm": 2.983358383178711, + "learning_rate": 1.9312009294499717e-05, + "loss": 18.8752, + "step": 1401 + }, + { + "epoch": 0.32580973129992735, + "grad_norm": 2.84587025642395, + "learning_rate": 1.9310608007472616e-05, + "loss": 18.1706, + "step": 1402 + }, + { + "epoch": 0.3260421205519245, + "grad_norm": 2.5494728088378906, + "learning_rate": 1.9309205345783225e-05, + "loss": 17.8574, + "step": 1403 + }, + { + "epoch": 0.3262745098039216, + "grad_norm": 3.201385259628296, + "learning_rate": 1.930780130963865e-05, + "loss": 18.2058, + "step": 1404 + }, + { + "epoch": 0.3265068990559187, + "grad_norm": 2.672520399093628, + "learning_rate": 1.9306395899246184e-05, + "loss": 18.3161, + "step": 1405 + }, + { + "epoch": 0.32673928830791577, + "grad_norm": 2.667039394378662, + "learning_rate": 1.9304989114813333e-05, + "loss": 17.7412, + "step": 1406 + }, + { + "epoch": 0.32697167755991285, + "grad_norm": 2.849771738052368, + "learning_rate": 1.9303580956547797e-05, + "loss": 18.9628, + "step": 1407 + }, + { + "epoch": 0.32720406681190994, + "grad_norm": 2.9126622676849365, + "learning_rate": 1.9302171424657488e-05, + "loss": 18.5425, + "step": 1408 + }, + { + "epoch": 0.32743645606390703, + "grad_norm": 2.8616855144500732, + "learning_rate": 1.9300760519350514e-05, + "loss": 17.0299, + "step": 1409 + }, + { + "epoch": 0.3276688453159041, + "grad_norm": 2.6573877334594727, + "learning_rate": 1.9299348240835182e-05, + "loss": 17.3825, + "step": 1410 + }, + { + "epoch": 0.3279012345679012, + "grad_norm": 2.7996184825897217, + "learning_rate": 1.9297934589320015e-05, + "loss": 17.8006, + "step": 1411 + }, + { + "epoch": 0.32813362381989836, + "grad_norm": 2.8206546306610107, + "learning_rate": 1.9296519565013727e-05, + "loss": 18.1752, + "step": 1412 + }, + { + "epoch": 0.32836601307189545, + "grad_norm": 2.625739336013794, + "learning_rate": 1.9295103168125245e-05, + "loss": 18.2445, + "step": 1413 + }, + { + "epoch": 0.32859840232389254, + "grad_norm": 2.664795160293579, + "learning_rate": 1.9293685398863685e-05, + "loss": 18.1501, + "step": 1414 + }, + { + "epoch": 0.3288307915758896, + "grad_norm": 2.667412281036377, + "learning_rate": 1.9292266257438373e-05, + "loss": 18.6067, + "step": 1415 + }, + { + "epoch": 0.3290631808278867, + "grad_norm": 2.7108328342437744, + "learning_rate": 1.9290845744058845e-05, + "loss": 17.9806, + "step": 1416 + }, + { + "epoch": 0.3292955700798838, + "grad_norm": 3.157613754272461, + "learning_rate": 1.928942385893483e-05, + "loss": 17.2963, + "step": 1417 + }, + { + "epoch": 0.3295279593318809, + "grad_norm": 3.071427345275879, + "learning_rate": 1.9288000602276254e-05, + "loss": 17.6479, + "step": 1418 + }, + { + "epoch": 0.329760348583878, + "grad_norm": 2.6383848190307617, + "learning_rate": 1.9286575974293262e-05, + "loss": 18.0034, + "step": 1419 + }, + { + "epoch": 0.32999273783587507, + "grad_norm": 2.70089054107666, + "learning_rate": 1.928514997519619e-05, + "loss": 17.5512, + "step": 1420 + }, + { + "epoch": 0.33022512708787216, + "grad_norm": 2.779785633087158, + "learning_rate": 1.928372260519558e-05, + "loss": 18.1252, + "step": 1421 + }, + { + "epoch": 0.3304575163398693, + "grad_norm": 2.7961220741271973, + "learning_rate": 1.9282293864502176e-05, + "loss": 17.8478, + "step": 1422 + }, + { + "epoch": 0.3306899055918664, + "grad_norm": 2.8463892936706543, + "learning_rate": 1.9280863753326925e-05, + "loss": 18.0891, + "step": 1423 + }, + { + "epoch": 0.3309222948438635, + "grad_norm": 2.837322235107422, + "learning_rate": 1.9279432271880972e-05, + "loss": 18.6099, + "step": 1424 + }, + { + "epoch": 0.3311546840958606, + "grad_norm": 2.7309539318084717, + "learning_rate": 1.9277999420375667e-05, + "loss": 18.8326, + "step": 1425 + }, + { + "epoch": 0.33138707334785766, + "grad_norm": 2.9667742252349854, + "learning_rate": 1.9276565199022567e-05, + "loss": 18.2508, + "step": 1426 + }, + { + "epoch": 0.33161946259985475, + "grad_norm": 2.618475914001465, + "learning_rate": 1.9275129608033427e-05, + "loss": 17.2201, + "step": 1427 + }, + { + "epoch": 0.33185185185185184, + "grad_norm": 3.3466062545776367, + "learning_rate": 1.92736926476202e-05, + "loss": 18.0763, + "step": 1428 + }, + { + "epoch": 0.33208424110384893, + "grad_norm": 2.8450562953948975, + "learning_rate": 1.9272254317995053e-05, + "loss": 18.8489, + "step": 1429 + }, + { + "epoch": 0.332316630355846, + "grad_norm": 2.5888991355895996, + "learning_rate": 1.9270814619370342e-05, + "loss": 18.313, + "step": 1430 + }, + { + "epoch": 0.3325490196078431, + "grad_norm": 2.7822482585906982, + "learning_rate": 1.9269373551958634e-05, + "loss": 17.5797, + "step": 1431 + }, + { + "epoch": 0.33278140885984026, + "grad_norm": 2.7829434871673584, + "learning_rate": 1.926793111597269e-05, + "loss": 18.7471, + "step": 1432 + }, + { + "epoch": 0.33301379811183734, + "grad_norm": 3.219958543777466, + "learning_rate": 1.926648731162548e-05, + "loss": 18.0795, + "step": 1433 + }, + { + "epoch": 0.33324618736383443, + "grad_norm": 2.6541805267333984, + "learning_rate": 1.926504213913018e-05, + "loss": 18.2094, + "step": 1434 + }, + { + "epoch": 0.3334785766158315, + "grad_norm": 2.821719169616699, + "learning_rate": 1.9263595598700156e-05, + "loss": 17.9341, + "step": 1435 + }, + { + "epoch": 0.3337109658678286, + "grad_norm": 2.912463426589966, + "learning_rate": 1.9262147690548982e-05, + "loss": 18.3072, + "step": 1436 + }, + { + "epoch": 0.3339433551198257, + "grad_norm": 2.9063985347747803, + "learning_rate": 1.926069841489044e-05, + "loss": 16.8455, + "step": 1437 + }, + { + "epoch": 0.3341757443718228, + "grad_norm": 2.6828651428222656, + "learning_rate": 1.92592477719385e-05, + "loss": 17.3441, + "step": 1438 + }, + { + "epoch": 0.3344081336238199, + "grad_norm": 2.497270345687866, + "learning_rate": 1.9257795761907346e-05, + "loss": 17.8479, + "step": 1439 + }, + { + "epoch": 0.33464052287581697, + "grad_norm": 3.0261456966400146, + "learning_rate": 1.925634238501136e-05, + "loss": 18.8881, + "step": 1440 + }, + { + "epoch": 0.3348729121278141, + "grad_norm": 2.7449302673339844, + "learning_rate": 1.9254887641465124e-05, + "loss": 18.1708, + "step": 1441 + }, + { + "epoch": 0.3351053013798112, + "grad_norm": 2.681832790374756, + "learning_rate": 1.925343153148343e-05, + "loss": 17.699, + "step": 1442 + }, + { + "epoch": 0.3353376906318083, + "grad_norm": 2.625877618789673, + "learning_rate": 1.925197405528125e-05, + "loss": 17.6032, + "step": 1443 + }, + { + "epoch": 0.3355700798838054, + "grad_norm": 2.9987564086914062, + "learning_rate": 1.9250515213073787e-05, + "loss": 18.8524, + "step": 1444 + }, + { + "epoch": 0.3358024691358025, + "grad_norm": 4.036731243133545, + "learning_rate": 1.9249055005076426e-05, + "loss": 18.0217, + "step": 1445 + }, + { + "epoch": 0.33603485838779956, + "grad_norm": 2.51263427734375, + "learning_rate": 1.9247593431504756e-05, + "loss": 18.1475, + "step": 1446 + }, + { + "epoch": 0.33626724763979665, + "grad_norm": 2.8921401500701904, + "learning_rate": 1.9246130492574572e-05, + "loss": 17.8987, + "step": 1447 + }, + { + "epoch": 0.33649963689179374, + "grad_norm": 2.741197109222412, + "learning_rate": 1.9244666188501876e-05, + "loss": 17.9249, + "step": 1448 + }, + { + "epoch": 0.33673202614379083, + "grad_norm": 2.7425572872161865, + "learning_rate": 1.924320051950286e-05, + "loss": 18.718, + "step": 1449 + }, + { + "epoch": 0.3369644153957879, + "grad_norm": 2.74794340133667, + "learning_rate": 1.9241733485793917e-05, + "loss": 18.0263, + "step": 1450 + }, + { + "epoch": 0.33719680464778506, + "grad_norm": 2.8204305171966553, + "learning_rate": 1.924026508759165e-05, + "loss": 18.1465, + "step": 1451 + }, + { + "epoch": 0.33742919389978215, + "grad_norm": 3.0321693420410156, + "learning_rate": 1.9238795325112867e-05, + "loss": 17.4179, + "step": 1452 + }, + { + "epoch": 0.33766158315177924, + "grad_norm": 2.5130741596221924, + "learning_rate": 1.9237324198574567e-05, + "loss": 17.263, + "step": 1453 + }, + { + "epoch": 0.33789397240377633, + "grad_norm": 3.2489585876464844, + "learning_rate": 1.923585170819395e-05, + "loss": 18.4782, + "step": 1454 + }, + { + "epoch": 0.3381263616557734, + "grad_norm": 2.8963537216186523, + "learning_rate": 1.9234377854188428e-05, + "loss": 17.2981, + "step": 1455 + }, + { + "epoch": 0.3383587509077705, + "grad_norm": 4.361184597015381, + "learning_rate": 1.9232902636775598e-05, + "loss": 17.4101, + "step": 1456 + }, + { + "epoch": 0.3385911401597676, + "grad_norm": 2.677983045578003, + "learning_rate": 1.9231426056173278e-05, + "loss": 18.0635, + "step": 1457 + }, + { + "epoch": 0.3388235294117647, + "grad_norm": 2.979785203933716, + "learning_rate": 1.9229948112599473e-05, + "loss": 17.7454, + "step": 1458 + }, + { + "epoch": 0.3390559186637618, + "grad_norm": 2.9248123168945312, + "learning_rate": 1.9228468806272393e-05, + "loss": 17.6809, + "step": 1459 + }, + { + "epoch": 0.33928830791575887, + "grad_norm": 2.8411977291107178, + "learning_rate": 1.9226988137410453e-05, + "loss": 18.1479, + "step": 1460 + }, + { + "epoch": 0.339520697167756, + "grad_norm": 2.641925573348999, + "learning_rate": 1.922550610623226e-05, + "loss": 18.345, + "step": 1461 + }, + { + "epoch": 0.3397530864197531, + "grad_norm": 3.2563822269439697, + "learning_rate": 1.922402271295664e-05, + "loss": 17.2736, + "step": 1462 + }, + { + "epoch": 0.3399854756717502, + "grad_norm": 2.7713558673858643, + "learning_rate": 1.9222537957802592e-05, + "loss": 16.9249, + "step": 1463 + }, + { + "epoch": 0.3402178649237473, + "grad_norm": 2.661097764968872, + "learning_rate": 1.922105184098934e-05, + "loss": 18.024, + "step": 1464 + }, + { + "epoch": 0.34045025417574437, + "grad_norm": 2.6499674320220947, + "learning_rate": 1.921956436273631e-05, + "loss": 17.7613, + "step": 1465 + }, + { + "epoch": 0.34068264342774146, + "grad_norm": 2.466653823852539, + "learning_rate": 1.9218075523263104e-05, + "loss": 17.4342, + "step": 1466 + }, + { + "epoch": 0.34091503267973855, + "grad_norm": 2.5101006031036377, + "learning_rate": 1.9216585322789556e-05, + "loss": 17.9408, + "step": 1467 + }, + { + "epoch": 0.34114742193173564, + "grad_norm": 2.7215540409088135, + "learning_rate": 1.9215093761535674e-05, + "loss": 17.0023, + "step": 1468 + }, + { + "epoch": 0.34137981118373273, + "grad_norm": 3.1941168308258057, + "learning_rate": 1.921360083972169e-05, + "loss": 18.1025, + "step": 1469 + }, + { + "epoch": 0.3416122004357299, + "grad_norm": 2.5745136737823486, + "learning_rate": 1.9212106557568018e-05, + "loss": 18.9616, + "step": 1470 + }, + { + "epoch": 0.34184458968772696, + "grad_norm": 2.892577886581421, + "learning_rate": 1.9210610915295284e-05, + "loss": 17.5409, + "step": 1471 + }, + { + "epoch": 0.34207697893972405, + "grad_norm": 2.888017177581787, + "learning_rate": 1.920911391312431e-05, + "loss": 18.6628, + "step": 1472 + }, + { + "epoch": 0.34230936819172114, + "grad_norm": 2.8145320415496826, + "learning_rate": 1.9207615551276123e-05, + "loss": 17.7443, + "step": 1473 + }, + { + "epoch": 0.34254175744371823, + "grad_norm": 2.6758594512939453, + "learning_rate": 1.920611582997195e-05, + "loss": 18.1382, + "step": 1474 + }, + { + "epoch": 0.3427741466957153, + "grad_norm": 2.4919235706329346, + "learning_rate": 1.9204614749433214e-05, + "loss": 17.7408, + "step": 1475 + }, + { + "epoch": 0.3430065359477124, + "grad_norm": 2.554189920425415, + "learning_rate": 1.920311230988154e-05, + "loss": 18.0055, + "step": 1476 + }, + { + "epoch": 0.3432389251997095, + "grad_norm": 2.871497869491577, + "learning_rate": 1.9201608511538756e-05, + "loss": 18.4097, + "step": 1477 + }, + { + "epoch": 0.3434713144517066, + "grad_norm": 2.8544952869415283, + "learning_rate": 1.9200103354626892e-05, + "loss": 18.3864, + "step": 1478 + }, + { + "epoch": 0.3437037037037037, + "grad_norm": 2.8135530948638916, + "learning_rate": 1.919859683936818e-05, + "loss": 17.77, + "step": 1479 + }, + { + "epoch": 0.3439360929557008, + "grad_norm": 2.728922128677368, + "learning_rate": 1.9197088965985037e-05, + "loss": 18.0183, + "step": 1480 + }, + { + "epoch": 0.3441684822076979, + "grad_norm": 2.6209256649017334, + "learning_rate": 1.9195579734700104e-05, + "loss": 17.953, + "step": 1481 + }, + { + "epoch": 0.344400871459695, + "grad_norm": 2.6821038722991943, + "learning_rate": 1.9194069145736208e-05, + "loss": 17.9402, + "step": 1482 + }, + { + "epoch": 0.3446332607116921, + "grad_norm": 2.7012012004852295, + "learning_rate": 1.919255719931638e-05, + "loss": 17.9473, + "step": 1483 + }, + { + "epoch": 0.3448656499636892, + "grad_norm": 2.633033275604248, + "learning_rate": 1.9191043895663847e-05, + "loss": 18.1008, + "step": 1484 + }, + { + "epoch": 0.34509803921568627, + "grad_norm": 4.083813667297363, + "learning_rate": 1.9189529235002043e-05, + "loss": 17.439, + "step": 1485 + }, + { + "epoch": 0.34533042846768336, + "grad_norm": 2.886998176574707, + "learning_rate": 1.91880132175546e-05, + "loss": 18.46, + "step": 1486 + }, + { + "epoch": 0.34556281771968045, + "grad_norm": 2.7374260425567627, + "learning_rate": 1.918649584354535e-05, + "loss": 17.8566, + "step": 1487 + }, + { + "epoch": 0.34579520697167754, + "grad_norm": 2.7285921573638916, + "learning_rate": 1.9184977113198324e-05, + "loss": 18.2671, + "step": 1488 + }, + { + "epoch": 0.3460275962236747, + "grad_norm": 2.7702975273132324, + "learning_rate": 1.9183457026737756e-05, + "loss": 17.3396, + "step": 1489 + }, + { + "epoch": 0.34625998547567177, + "grad_norm": 2.7584497928619385, + "learning_rate": 1.9181935584388084e-05, + "loss": 18.4859, + "step": 1490 + }, + { + "epoch": 0.34649237472766886, + "grad_norm": 2.979781150817871, + "learning_rate": 1.918041278637393e-05, + "loss": 20.4715, + "step": 1491 + }, + { + "epoch": 0.34672476397966595, + "grad_norm": 2.6506500244140625, + "learning_rate": 1.9178888632920132e-05, + "loss": 17.8213, + "step": 1492 + }, + { + "epoch": 0.34695715323166304, + "grad_norm": 2.8157870769500732, + "learning_rate": 1.9177363124251723e-05, + "loss": 18.0213, + "step": 1493 + }, + { + "epoch": 0.34718954248366013, + "grad_norm": 2.7381606101989746, + "learning_rate": 1.9175836260593937e-05, + "loss": 17.7535, + "step": 1494 + }, + { + "epoch": 0.3474219317356572, + "grad_norm": 3.2032670974731445, + "learning_rate": 1.917430804217221e-05, + "loss": 18.381, + "step": 1495 + }, + { + "epoch": 0.3476543209876543, + "grad_norm": 2.7264556884765625, + "learning_rate": 1.9172778469212173e-05, + "loss": 16.9469, + "step": 1496 + }, + { + "epoch": 0.3478867102396514, + "grad_norm": 2.870966911315918, + "learning_rate": 1.9171247541939658e-05, + "loss": 17.9268, + "step": 1497 + }, + { + "epoch": 0.3481190994916485, + "grad_norm": 2.721798896789551, + "learning_rate": 1.91697152605807e-05, + "loss": 18.5435, + "step": 1498 + }, + { + "epoch": 0.34835148874364563, + "grad_norm": 2.6311140060424805, + "learning_rate": 1.9168181625361527e-05, + "loss": 17.9138, + "step": 1499 + }, + { + "epoch": 0.3485838779956427, + "grad_norm": 3.234046459197998, + "learning_rate": 1.9166646636508583e-05, + "loss": 17.6294, + "step": 1500 + }, + { + "epoch": 0.3488162672476398, + "grad_norm": 2.7257933616638184, + "learning_rate": 1.9165110294248493e-05, + "loss": 18.3597, + "step": 1501 + }, + { + "epoch": 0.3490486564996369, + "grad_norm": 2.6328213214874268, + "learning_rate": 1.9163572598808093e-05, + "loss": 17.8985, + "step": 1502 + }, + { + "epoch": 0.349281045751634, + "grad_norm": 2.711695909500122, + "learning_rate": 1.916203355041441e-05, + "loss": 17.2229, + "step": 1503 + }, + { + "epoch": 0.3495134350036311, + "grad_norm": 2.5844080448150635, + "learning_rate": 1.9160493149294685e-05, + "loss": 18.4071, + "step": 1504 + }, + { + "epoch": 0.34974582425562817, + "grad_norm": 2.956489086151123, + "learning_rate": 1.9158951395676347e-05, + "loss": 17.5847, + "step": 1505 + }, + { + "epoch": 0.34997821350762526, + "grad_norm": 2.5160934925079346, + "learning_rate": 1.9157408289787026e-05, + "loss": 17.8638, + "step": 1506 + }, + { + "epoch": 0.35021060275962235, + "grad_norm": 2.627399206161499, + "learning_rate": 1.9155863831854553e-05, + "loss": 17.3013, + "step": 1507 + }, + { + "epoch": 0.35044299201161944, + "grad_norm": 2.8349084854125977, + "learning_rate": 1.915431802210696e-05, + "loss": 18.1202, + "step": 1508 + }, + { + "epoch": 0.3506753812636166, + "grad_norm": 2.7014899253845215, + "learning_rate": 1.9152770860772478e-05, + "loss": 18.8776, + "step": 1509 + }, + { + "epoch": 0.35090777051561367, + "grad_norm": 2.838991165161133, + "learning_rate": 1.915122234807954e-05, + "loss": 17.4908, + "step": 1510 + }, + { + "epoch": 0.35114015976761076, + "grad_norm": 2.672055721282959, + "learning_rate": 1.914967248425677e-05, + "loss": 16.9308, + "step": 1511 + }, + { + "epoch": 0.35137254901960785, + "grad_norm": 2.6592893600463867, + "learning_rate": 1.9148121269533e-05, + "loss": 18.7794, + "step": 1512 + }, + { + "epoch": 0.35160493827160494, + "grad_norm": 2.675353765487671, + "learning_rate": 1.914656870413726e-05, + "loss": 18.3784, + "step": 1513 + }, + { + "epoch": 0.35183732752360203, + "grad_norm": 9.245499610900879, + "learning_rate": 1.9145014788298777e-05, + "loss": 18.3103, + "step": 1514 + }, + { + "epoch": 0.3520697167755991, + "grad_norm": 2.7229273319244385, + "learning_rate": 1.9143459522246978e-05, + "loss": 17.7117, + "step": 1515 + }, + { + "epoch": 0.3523021060275962, + "grad_norm": 2.6847164630889893, + "learning_rate": 1.9141902906211493e-05, + "loss": 17.9993, + "step": 1516 + }, + { + "epoch": 0.3525344952795933, + "grad_norm": 39.393795013427734, + "learning_rate": 1.9140344940422145e-05, + "loss": 18.2937, + "step": 1517 + }, + { + "epoch": 0.35276688453159044, + "grad_norm": 3.3348228931427, + "learning_rate": 1.913878562510896e-05, + "loss": 17.2186, + "step": 1518 + }, + { + "epoch": 0.35299927378358753, + "grad_norm": 2.569110631942749, + "learning_rate": 1.9137224960502158e-05, + "loss": 17.8528, + "step": 1519 + }, + { + "epoch": 0.3532316630355846, + "grad_norm": 2.709864854812622, + "learning_rate": 1.913566294683217e-05, + "loss": 18.473, + "step": 1520 + }, + { + "epoch": 0.3534640522875817, + "grad_norm": 2.7412831783294678, + "learning_rate": 1.913409958432962e-05, + "loss": 19.0062, + "step": 1521 + }, + { + "epoch": 0.3536964415395788, + "grad_norm": 2.5968966484069824, + "learning_rate": 1.9132534873225323e-05, + "loss": 17.587, + "step": 1522 + }, + { + "epoch": 0.3539288307915759, + "grad_norm": 3.576718807220459, + "learning_rate": 1.9130968813750308e-05, + "loss": 17.3766, + "step": 1523 + }, + { + "epoch": 0.354161220043573, + "grad_norm": 2.4956555366516113, + "learning_rate": 1.912940140613579e-05, + "loss": 17.1297, + "step": 1524 + }, + { + "epoch": 0.35439360929557007, + "grad_norm": 2.7701027393341064, + "learning_rate": 1.912783265061319e-05, + "loss": 18.0547, + "step": 1525 + }, + { + "epoch": 0.35462599854756716, + "grad_norm": 2.657628059387207, + "learning_rate": 1.912626254741413e-05, + "loss": 18.9887, + "step": 1526 + }, + { + "epoch": 0.35485838779956425, + "grad_norm": 2.6173150539398193, + "learning_rate": 1.912469109677042e-05, + "loss": 18.2239, + "step": 1527 + }, + { + "epoch": 0.3550907770515614, + "grad_norm": 2.619696617126465, + "learning_rate": 1.912311829891408e-05, + "loss": 17.9674, + "step": 1528 + }, + { + "epoch": 0.3553231663035585, + "grad_norm": 2.5448930263519287, + "learning_rate": 1.912154415407733e-05, + "loss": 18.6521, + "step": 1529 + }, + { + "epoch": 0.35555555555555557, + "grad_norm": 2.9876575469970703, + "learning_rate": 1.9119968662492575e-05, + "loss": 17.301, + "step": 1530 + }, + { + "epoch": 0.35578794480755266, + "grad_norm": 2.9635486602783203, + "learning_rate": 1.911839182439244e-05, + "loss": 18.0754, + "step": 1531 + }, + { + "epoch": 0.35602033405954975, + "grad_norm": 3.1118173599243164, + "learning_rate": 1.9116813640009725e-05, + "loss": 18.4912, + "step": 1532 + }, + { + "epoch": 0.35625272331154684, + "grad_norm": 2.8055455684661865, + "learning_rate": 1.9115234109577446e-05, + "loss": 18.2471, + "step": 1533 + }, + { + "epoch": 0.3564851125635439, + "grad_norm": 2.698336362838745, + "learning_rate": 1.9113653233328816e-05, + "loss": 18.7813, + "step": 1534 + }, + { + "epoch": 0.356717501815541, + "grad_norm": 2.7736973762512207, + "learning_rate": 1.9112071011497236e-05, + "loss": 18.1052, + "step": 1535 + }, + { + "epoch": 0.3569498910675381, + "grad_norm": 2.7159690856933594, + "learning_rate": 1.9110487444316317e-05, + "loss": 18.0952, + "step": 1536 + }, + { + "epoch": 0.3571822803195352, + "grad_norm": 6.253219127655029, + "learning_rate": 1.910890253201986e-05, + "loss": 18.4596, + "step": 1537 + }, + { + "epoch": 0.35741466957153234, + "grad_norm": 2.971802234649658, + "learning_rate": 1.9107316274841876e-05, + "loss": 17.1682, + "step": 1538 + }, + { + "epoch": 0.35764705882352943, + "grad_norm": 2.844343423843384, + "learning_rate": 1.9105728673016563e-05, + "loss": 18.2655, + "step": 1539 + }, + { + "epoch": 0.3578794480755265, + "grad_norm": 2.852891445159912, + "learning_rate": 1.9104139726778323e-05, + "loss": 18.6855, + "step": 1540 + }, + { + "epoch": 0.3581118373275236, + "grad_norm": 2.7389719486236572, + "learning_rate": 1.9102549436361755e-05, + "loss": 18.6931, + "step": 1541 + }, + { + "epoch": 0.3583442265795207, + "grad_norm": 2.6654505729675293, + "learning_rate": 1.9100957802001655e-05, + "loss": 17.3659, + "step": 1542 + }, + { + "epoch": 0.3585766158315178, + "grad_norm": 2.618885040283203, + "learning_rate": 1.9099364823933024e-05, + "loss": 19.3174, + "step": 1543 + }, + { + "epoch": 0.3588090050835149, + "grad_norm": 2.5617544651031494, + "learning_rate": 1.9097770502391057e-05, + "loss": 18.0342, + "step": 1544 + }, + { + "epoch": 0.35904139433551197, + "grad_norm": 2.8811492919921875, + "learning_rate": 1.909617483761114e-05, + "loss": 17.9283, + "step": 1545 + }, + { + "epoch": 0.35927378358750905, + "grad_norm": 2.737301826477051, + "learning_rate": 1.9094577829828873e-05, + "loss": 17.9606, + "step": 1546 + }, + { + "epoch": 0.3595061728395062, + "grad_norm": 2.68180251121521, + "learning_rate": 1.909297947928004e-05, + "loss": 18.2271, + "step": 1547 + }, + { + "epoch": 0.3597385620915033, + "grad_norm": 2.7401599884033203, + "learning_rate": 1.909137978620063e-05, + "loss": 18.193, + "step": 1548 + }, + { + "epoch": 0.3599709513435004, + "grad_norm": 3.24330472946167, + "learning_rate": 1.9089778750826835e-05, + "loss": 17.2189, + "step": 1549 + }, + { + "epoch": 0.36020334059549747, + "grad_norm": 2.653073787689209, + "learning_rate": 1.908817637339503e-05, + "loss": 17.9313, + "step": 1550 + }, + { + "epoch": 0.36043572984749456, + "grad_norm": 2.781587600708008, + "learning_rate": 1.9086572654141805e-05, + "loss": 18.8789, + "step": 1551 + }, + { + "epoch": 0.36066811909949165, + "grad_norm": 2.6619434356689453, + "learning_rate": 1.9084967593303937e-05, + "loss": 17.7716, + "step": 1552 + }, + { + "epoch": 0.36090050835148874, + "grad_norm": 2.7018961906433105, + "learning_rate": 1.9083361191118406e-05, + "loss": 17.4657, + "step": 1553 + }, + { + "epoch": 0.3611328976034858, + "grad_norm": 5.461801528930664, + "learning_rate": 1.908175344782239e-05, + "loss": 19.0184, + "step": 1554 + }, + { + "epoch": 0.3613652868554829, + "grad_norm": 2.915682315826416, + "learning_rate": 1.9080144363653265e-05, + "loss": 17.0203, + "step": 1555 + }, + { + "epoch": 0.36159767610748, + "grad_norm": 5.166565895080566, + "learning_rate": 1.9078533938848595e-05, + "loss": 18.2279, + "step": 1556 + }, + { + "epoch": 0.36183006535947715, + "grad_norm": 2.938796043395996, + "learning_rate": 1.9076922173646163e-05, + "loss": 18.0019, + "step": 1557 + }, + { + "epoch": 0.36206245461147424, + "grad_norm": 2.847368001937866, + "learning_rate": 1.907530906828393e-05, + "loss": 18.2061, + "step": 1558 + }, + { + "epoch": 0.3622948438634713, + "grad_norm": 2.652155876159668, + "learning_rate": 1.907369462300006e-05, + "loss": 18.5756, + "step": 1559 + }, + { + "epoch": 0.3625272331154684, + "grad_norm": 2.7576167583465576, + "learning_rate": 1.9072078838032927e-05, + "loss": 17.5461, + "step": 1560 + }, + { + "epoch": 0.3627596223674655, + "grad_norm": 2.683663845062256, + "learning_rate": 1.9070461713621087e-05, + "loss": 18.087, + "step": 1561 + }, + { + "epoch": 0.3629920116194626, + "grad_norm": 2.7220165729522705, + "learning_rate": 1.90688432500033e-05, + "loss": 18.0303, + "step": 1562 + }, + { + "epoch": 0.3632244008714597, + "grad_norm": 2.833481550216675, + "learning_rate": 1.9067223447418523e-05, + "loss": 18.3329, + "step": 1563 + }, + { + "epoch": 0.3634567901234568, + "grad_norm": 2.669325828552246, + "learning_rate": 1.9065602306105914e-05, + "loss": 19.3017, + "step": 1564 + }, + { + "epoch": 0.36368917937545386, + "grad_norm": 2.7947998046875, + "learning_rate": 1.9063979826304826e-05, + "loss": 17.9714, + "step": 1565 + }, + { + "epoch": 0.36392156862745095, + "grad_norm": 2.6699211597442627, + "learning_rate": 1.906235600825481e-05, + "loss": 18.2219, + "step": 1566 + }, + { + "epoch": 0.3641539578794481, + "grad_norm": 2.5561530590057373, + "learning_rate": 1.9060730852195607e-05, + "loss": 18.1566, + "step": 1567 + }, + { + "epoch": 0.3643863471314452, + "grad_norm": 3.085075855255127, + "learning_rate": 1.905910435836717e-05, + "loss": 18.5826, + "step": 1568 + }, + { + "epoch": 0.3646187363834423, + "grad_norm": 2.6433708667755127, + "learning_rate": 1.9057476527009645e-05, + "loss": 17.7705, + "step": 1569 + }, + { + "epoch": 0.36485112563543937, + "grad_norm": 3.856313705444336, + "learning_rate": 1.9055847358363363e-05, + "loss": 17.4219, + "step": 1570 + }, + { + "epoch": 0.36508351488743646, + "grad_norm": 2.80856990814209, + "learning_rate": 1.905421685266887e-05, + "loss": 17.8684, + "step": 1571 + }, + { + "epoch": 0.36531590413943354, + "grad_norm": 2.519892692565918, + "learning_rate": 1.9052585010166896e-05, + "loss": 17.6449, + "step": 1572 + }, + { + "epoch": 0.36554829339143063, + "grad_norm": 2.462331533432007, + "learning_rate": 1.9050951831098377e-05, + "loss": 17.0875, + "step": 1573 + }, + { + "epoch": 0.3657806826434277, + "grad_norm": 3.3676140308380127, + "learning_rate": 1.9049317315704447e-05, + "loss": 18.4281, + "step": 1574 + }, + { + "epoch": 0.3660130718954248, + "grad_norm": 2.6408889293670654, + "learning_rate": 1.9047681464226427e-05, + "loss": 18.5938, + "step": 1575 + }, + { + "epoch": 0.36624546114742196, + "grad_norm": 2.892698049545288, + "learning_rate": 1.904604427690585e-05, + "loss": 17.932, + "step": 1576 + }, + { + "epoch": 0.36647785039941905, + "grad_norm": 2.792633056640625, + "learning_rate": 1.9044405753984427e-05, + "loss": 17.5544, + "step": 1577 + }, + { + "epoch": 0.36671023965141614, + "grad_norm": 2.8334591388702393, + "learning_rate": 1.9042765895704085e-05, + "loss": 18.9496, + "step": 1578 + }, + { + "epoch": 0.3669426289034132, + "grad_norm": 3.190624237060547, + "learning_rate": 1.9041124702306938e-05, + "loss": 19.5292, + "step": 1579 + }, + { + "epoch": 0.3671750181554103, + "grad_norm": 2.75179386138916, + "learning_rate": 1.9039482174035303e-05, + "loss": 19.3205, + "step": 1580 + }, + { + "epoch": 0.3674074074074074, + "grad_norm": 2.738203763961792, + "learning_rate": 1.9037838311131685e-05, + "loss": 19.1261, + "step": 1581 + }, + { + "epoch": 0.3676397966594045, + "grad_norm": 2.619943618774414, + "learning_rate": 1.9036193113838792e-05, + "loss": 17.9381, + "step": 1582 + }, + { + "epoch": 0.3678721859114016, + "grad_norm": 2.6862685680389404, + "learning_rate": 1.9034546582399537e-05, + "loss": 17.508, + "step": 1583 + }, + { + "epoch": 0.3681045751633987, + "grad_norm": 2.6663990020751953, + "learning_rate": 1.9032898717057012e-05, + "loss": 18.7399, + "step": 1584 + }, + { + "epoch": 0.36833696441539576, + "grad_norm": 2.9699299335479736, + "learning_rate": 1.903124951805452e-05, + "loss": 18.3708, + "step": 1585 + }, + { + "epoch": 0.3685693536673929, + "grad_norm": 2.7225606441497803, + "learning_rate": 1.9029598985635557e-05, + "loss": 17.4191, + "step": 1586 + }, + { + "epoch": 0.36880174291939, + "grad_norm": 3.034079074859619, + "learning_rate": 1.9027947120043816e-05, + "loss": 17.2781, + "step": 1587 + }, + { + "epoch": 0.3690341321713871, + "grad_norm": 2.7721738815307617, + "learning_rate": 1.902629392152318e-05, + "loss": 17.4522, + "step": 1588 + }, + { + "epoch": 0.3692665214233842, + "grad_norm": 2.8319687843322754, + "learning_rate": 1.9024639390317743e-05, + "loss": 17.6716, + "step": 1589 + }, + { + "epoch": 0.36949891067538126, + "grad_norm": 2.666980504989624, + "learning_rate": 1.9022983526671786e-05, + "loss": 18.5322, + "step": 1590 + }, + { + "epoch": 0.36973129992737835, + "grad_norm": 2.793344736099243, + "learning_rate": 1.9021326330829786e-05, + "loss": 17.0299, + "step": 1591 + }, + { + "epoch": 0.36996368917937544, + "grad_norm": 2.771684408187866, + "learning_rate": 1.901966780303642e-05, + "loss": 19.4473, + "step": 1592 + }, + { + "epoch": 0.37019607843137253, + "grad_norm": 2.8118553161621094, + "learning_rate": 1.9018007943536562e-05, + "loss": 18.4003, + "step": 1593 + }, + { + "epoch": 0.3704284676833696, + "grad_norm": 2.7693839073181152, + "learning_rate": 1.9016346752575277e-05, + "loss": 19.1235, + "step": 1594 + }, + { + "epoch": 0.37066085693536677, + "grad_norm": 2.6887314319610596, + "learning_rate": 1.9014684230397843e-05, + "loss": 17.7615, + "step": 1595 + }, + { + "epoch": 0.37089324618736386, + "grad_norm": 2.82722806930542, + "learning_rate": 1.9013020377249708e-05, + "loss": 17.5244, + "step": 1596 + }, + { + "epoch": 0.37112563543936095, + "grad_norm": 2.7996702194213867, + "learning_rate": 1.901135519337654e-05, + "loss": 19.1623, + "step": 1597 + }, + { + "epoch": 0.37135802469135804, + "grad_norm": 2.598944664001465, + "learning_rate": 1.900968867902419e-05, + "loss": 18.6193, + "step": 1598 + }, + { + "epoch": 0.3715904139433551, + "grad_norm": 3.3133385181427, + "learning_rate": 1.900802083443872e-05, + "loss": 17.4578, + "step": 1599 + }, + { + "epoch": 0.3718228031953522, + "grad_norm": 2.8383798599243164, + "learning_rate": 1.9006351659866365e-05, + "loss": 18.9733, + "step": 1600 + }, + { + "epoch": 0.3720551924473493, + "grad_norm": 2.8804430961608887, + "learning_rate": 1.9004681155553575e-05, + "loss": 17.4799, + "step": 1601 + }, + { + "epoch": 0.3722875816993464, + "grad_norm": 2.609308958053589, + "learning_rate": 1.9003009321746995e-05, + "loss": 17.9792, + "step": 1602 + }, + { + "epoch": 0.3725199709513435, + "grad_norm": 2.9023094177246094, + "learning_rate": 1.900133615869346e-05, + "loss": 18.5048, + "step": 1603 + }, + { + "epoch": 0.37275236020334057, + "grad_norm": 2.620133876800537, + "learning_rate": 1.8999661666640002e-05, + "loss": 17.6613, + "step": 1604 + }, + { + "epoch": 0.3729847494553377, + "grad_norm": 2.7229537963867188, + "learning_rate": 1.899798584583385e-05, + "loss": 18.0723, + "step": 1605 + }, + { + "epoch": 0.3732171387073348, + "grad_norm": 2.67822527885437, + "learning_rate": 1.8996308696522435e-05, + "loss": 16.8535, + "step": 1606 + }, + { + "epoch": 0.3734495279593319, + "grad_norm": 6.78834867477417, + "learning_rate": 1.8994630218953377e-05, + "loss": 18.6321, + "step": 1607 + }, + { + "epoch": 0.373681917211329, + "grad_norm": 3.0443644523620605, + "learning_rate": 1.899295041337449e-05, + "loss": 18.0024, + "step": 1608 + }, + { + "epoch": 0.3739143064633261, + "grad_norm": 2.549776315689087, + "learning_rate": 1.8991269280033796e-05, + "loss": 18.1396, + "step": 1609 + }, + { + "epoch": 0.37414669571532316, + "grad_norm": 2.632744312286377, + "learning_rate": 1.8989586819179502e-05, + "loss": 17.8412, + "step": 1610 + }, + { + "epoch": 0.37437908496732025, + "grad_norm": 2.641294479370117, + "learning_rate": 1.8987903031060014e-05, + "loss": 17.5524, + "step": 1611 + }, + { + "epoch": 0.37461147421931734, + "grad_norm": 2.8469340801239014, + "learning_rate": 1.8986217915923934e-05, + "loss": 18.9041, + "step": 1612 + }, + { + "epoch": 0.37484386347131443, + "grad_norm": 2.7705013751983643, + "learning_rate": 1.8984531474020063e-05, + "loss": 17.9353, + "step": 1613 + }, + { + "epoch": 0.3750762527233115, + "grad_norm": 2.736008882522583, + "learning_rate": 1.898284370559739e-05, + "loss": 18.4192, + "step": 1614 + }, + { + "epoch": 0.37530864197530867, + "grad_norm": 3.014071464538574, + "learning_rate": 1.8981154610905113e-05, + "loss": 17.4468, + "step": 1615 + }, + { + "epoch": 0.37554103122730575, + "grad_norm": 2.633457660675049, + "learning_rate": 1.897946419019261e-05, + "loss": 17.6687, + "step": 1616 + }, + { + "epoch": 0.37577342047930284, + "grad_norm": 2.8199470043182373, + "learning_rate": 1.8977772443709468e-05, + "loss": 18.1162, + "step": 1617 + }, + { + "epoch": 0.37600580973129993, + "grad_norm": 2.58135724067688, + "learning_rate": 1.8976079371705463e-05, + "loss": 17.6391, + "step": 1618 + }, + { + "epoch": 0.376238198983297, + "grad_norm": 4.281137943267822, + "learning_rate": 1.8974384974430567e-05, + "loss": 17.6996, + "step": 1619 + }, + { + "epoch": 0.3764705882352941, + "grad_norm": 2.6821115016937256, + "learning_rate": 1.897268925213495e-05, + "loss": 18.8578, + "step": 1620 + }, + { + "epoch": 0.3767029774872912, + "grad_norm": 2.666731595993042, + "learning_rate": 1.8970992205068977e-05, + "loss": 18.0795, + "step": 1621 + }, + { + "epoch": 0.3769353667392883, + "grad_norm": 2.8150720596313477, + "learning_rate": 1.8969293833483204e-05, + "loss": 17.8022, + "step": 1622 + }, + { + "epoch": 0.3771677559912854, + "grad_norm": 2.6610825061798096, + "learning_rate": 1.8967594137628395e-05, + "loss": 18.633, + "step": 1623 + }, + { + "epoch": 0.3774001452432825, + "grad_norm": 2.630290985107422, + "learning_rate": 1.896589311775549e-05, + "loss": 16.9228, + "step": 1624 + }, + { + "epoch": 0.3776325344952796, + "grad_norm": 2.7052838802337646, + "learning_rate": 1.8964190774115648e-05, + "loss": 18.715, + "step": 1625 + }, + { + "epoch": 0.3778649237472767, + "grad_norm": 2.607733964920044, + "learning_rate": 1.8962487106960205e-05, + "loss": 19.0447, + "step": 1626 + }, + { + "epoch": 0.3780973129992738, + "grad_norm": 2.879608154296875, + "learning_rate": 1.8960782116540692e-05, + "loss": 16.6812, + "step": 1627 + }, + { + "epoch": 0.3783297022512709, + "grad_norm": 2.649786949157715, + "learning_rate": 1.8959075803108855e-05, + "loss": 16.6778, + "step": 1628 + }, + { + "epoch": 0.378562091503268, + "grad_norm": 2.6187515258789062, + "learning_rate": 1.895736816691661e-05, + "loss": 17.8015, + "step": 1629 + }, + { + "epoch": 0.37879448075526506, + "grad_norm": 2.812026262283325, + "learning_rate": 1.8955659208216087e-05, + "loss": 18.1679, + "step": 1630 + }, + { + "epoch": 0.37902687000726215, + "grad_norm": 2.708247184753418, + "learning_rate": 1.8953948927259608e-05, + "loss": 18.5734, + "step": 1631 + }, + { + "epoch": 0.37925925925925924, + "grad_norm": 2.721845865249634, + "learning_rate": 1.8952237324299675e-05, + "loss": 19.2631, + "step": 1632 + }, + { + "epoch": 0.37949164851125633, + "grad_norm": 2.581289052963257, + "learning_rate": 1.8950524399589012e-05, + "loss": 18.1822, + "step": 1633 + }, + { + "epoch": 0.3797240377632535, + "grad_norm": 2.71779727935791, + "learning_rate": 1.8948810153380514e-05, + "loss": 17.4231, + "step": 1634 + }, + { + "epoch": 0.37995642701525056, + "grad_norm": 2.701995849609375, + "learning_rate": 1.8947094585927283e-05, + "loss": 17.7308, + "step": 1635 + }, + { + "epoch": 0.38018881626724765, + "grad_norm": 2.6805856227874756, + "learning_rate": 1.894537769748261e-05, + "loss": 18.8761, + "step": 1636 + }, + { + "epoch": 0.38042120551924474, + "grad_norm": 2.662533760070801, + "learning_rate": 1.8943659488299987e-05, + "loss": 18.1222, + "step": 1637 + }, + { + "epoch": 0.38065359477124183, + "grad_norm": 2.9270122051239014, + "learning_rate": 1.89419399586331e-05, + "loss": 18.1054, + "step": 1638 + }, + { + "epoch": 0.3808859840232389, + "grad_norm": 2.5942444801330566, + "learning_rate": 1.8940219108735833e-05, + "loss": 17.8878, + "step": 1639 + }, + { + "epoch": 0.381118373275236, + "grad_norm": 2.877002477645874, + "learning_rate": 1.893849693886225e-05, + "loss": 18.5728, + "step": 1640 + }, + { + "epoch": 0.3813507625272331, + "grad_norm": 2.613847494125366, + "learning_rate": 1.893677344926663e-05, + "loss": 17.8305, + "step": 1641 + }, + { + "epoch": 0.3815831517792302, + "grad_norm": 2.5315093994140625, + "learning_rate": 1.8935048640203425e-05, + "loss": 17.7309, + "step": 1642 + }, + { + "epoch": 0.3818155410312273, + "grad_norm": 2.570868968963623, + "learning_rate": 1.8933322511927307e-05, + "loss": 17.9031, + "step": 1643 + }, + { + "epoch": 0.3820479302832244, + "grad_norm": 2.7958178520202637, + "learning_rate": 1.8931595064693124e-05, + "loss": 18.7866, + "step": 1644 + }, + { + "epoch": 0.3822803195352215, + "grad_norm": 2.866544246673584, + "learning_rate": 1.8929866298755924e-05, + "loss": 17.7441, + "step": 1645 + }, + { + "epoch": 0.3825127087872186, + "grad_norm": 2.670757532119751, + "learning_rate": 1.892813621437095e-05, + "loss": 19.1379, + "step": 1646 + }, + { + "epoch": 0.3827450980392157, + "grad_norm": 2.9301650524139404, + "learning_rate": 1.8926404811793642e-05, + "loss": 18.0471, + "step": 1647 + }, + { + "epoch": 0.3829774872912128, + "grad_norm": 2.5805399417877197, + "learning_rate": 1.892467209127963e-05, + "loss": 18.1041, + "step": 1648 + }, + { + "epoch": 0.38320987654320987, + "grad_norm": 2.703791618347168, + "learning_rate": 1.8922938053084743e-05, + "loss": 18.1013, + "step": 1649 + }, + { + "epoch": 0.38344226579520696, + "grad_norm": 2.7776103019714355, + "learning_rate": 1.8921202697465e-05, + "loss": 18.1108, + "step": 1650 + }, + { + "epoch": 0.38367465504720405, + "grad_norm": 2.556861400604248, + "learning_rate": 1.8919466024676625e-05, + "loss": 17.6889, + "step": 1651 + }, + { + "epoch": 0.38390704429920114, + "grad_norm": 2.640739679336548, + "learning_rate": 1.891772803497602e-05, + "loss": 18.8079, + "step": 1652 + }, + { + "epoch": 0.3841394335511983, + "grad_norm": 2.705061197280884, + "learning_rate": 1.891598872861979e-05, + "loss": 17.194, + "step": 1653 + }, + { + "epoch": 0.3843718228031954, + "grad_norm": 2.6746459007263184, + "learning_rate": 1.891424810586474e-05, + "loss": 18.1622, + "step": 1654 + }, + { + "epoch": 0.38460421205519246, + "grad_norm": 2.720571994781494, + "learning_rate": 1.891250616696786e-05, + "loss": 17.985, + "step": 1655 + }, + { + "epoch": 0.38483660130718955, + "grad_norm": 2.5740578174591064, + "learning_rate": 1.891076291218634e-05, + "loss": 18.5125, + "step": 1656 + }, + { + "epoch": 0.38506899055918664, + "grad_norm": 2.8093812465667725, + "learning_rate": 1.8909018341777564e-05, + "loss": 17.3734, + "step": 1657 + }, + { + "epoch": 0.38530137981118373, + "grad_norm": 2.8407905101776123, + "learning_rate": 1.89072724559991e-05, + "loss": 17.9975, + "step": 1658 + }, + { + "epoch": 0.3855337690631808, + "grad_norm": 2.8425071239471436, + "learning_rate": 1.8905525255108728e-05, + "loss": 19.0589, + "step": 1659 + }, + { + "epoch": 0.3857661583151779, + "grad_norm": 2.882556438446045, + "learning_rate": 1.890377673936441e-05, + "loss": 18.1505, + "step": 1660 + }, + { + "epoch": 0.385998547567175, + "grad_norm": 2.703934669494629, + "learning_rate": 1.8902026909024308e-05, + "loss": 18.2356, + "step": 1661 + }, + { + "epoch": 0.3862309368191721, + "grad_norm": 2.7261712551116943, + "learning_rate": 1.890027576434677e-05, + "loss": 17.8706, + "step": 1662 + }, + { + "epoch": 0.38646332607116923, + "grad_norm": 2.906208038330078, + "learning_rate": 1.8898523305590343e-05, + "loss": 17.7296, + "step": 1663 + }, + { + "epoch": 0.3866957153231663, + "grad_norm": 3.4011571407318115, + "learning_rate": 1.8896769533013775e-05, + "loss": 17.1911, + "step": 1664 + }, + { + "epoch": 0.3869281045751634, + "grad_norm": 2.593872308731079, + "learning_rate": 1.8895014446875995e-05, + "loss": 18.2826, + "step": 1665 + }, + { + "epoch": 0.3871604938271605, + "grad_norm": 2.6821587085723877, + "learning_rate": 1.8893258047436135e-05, + "loss": 18.417, + "step": 1666 + }, + { + "epoch": 0.3873928830791576, + "grad_norm": 2.795106887817383, + "learning_rate": 1.8891500334953518e-05, + "loss": 17.6479, + "step": 1667 + }, + { + "epoch": 0.3876252723311547, + "grad_norm": 2.9028940200805664, + "learning_rate": 1.888974130968766e-05, + "loss": 17.721, + "step": 1668 + }, + { + "epoch": 0.38785766158315177, + "grad_norm": 2.5872721672058105, + "learning_rate": 1.8887980971898273e-05, + "loss": 17.6609, + "step": 1669 + }, + { + "epoch": 0.38809005083514886, + "grad_norm": 2.6820878982543945, + "learning_rate": 1.8886219321845263e-05, + "loss": 18.4145, + "step": 1670 + }, + { + "epoch": 0.38832244008714595, + "grad_norm": 2.699972629547119, + "learning_rate": 1.8884456359788725e-05, + "loss": 17.6272, + "step": 1671 + }, + { + "epoch": 0.38855482933914304, + "grad_norm": 2.6704788208007812, + "learning_rate": 1.888269208598895e-05, + "loss": 18.0014, + "step": 1672 + }, + { + "epoch": 0.3887872185911402, + "grad_norm": 2.8225414752960205, + "learning_rate": 1.8880926500706432e-05, + "loss": 18.4812, + "step": 1673 + }, + { + "epoch": 0.38901960784313727, + "grad_norm": 7.964527606964111, + "learning_rate": 1.887915960420184e-05, + "loss": 17.7175, + "step": 1674 + }, + { + "epoch": 0.38925199709513436, + "grad_norm": 2.61468505859375, + "learning_rate": 1.8877391396736052e-05, + "loss": 18.1182, + "step": 1675 + }, + { + "epoch": 0.38948438634713145, + "grad_norm": 2.6922333240509033, + "learning_rate": 1.8875621878570135e-05, + "loss": 17.5063, + "step": 1676 + }, + { + "epoch": 0.38971677559912854, + "grad_norm": 2.8319008350372314, + "learning_rate": 1.8873851049965347e-05, + "loss": 17.8642, + "step": 1677 + }, + { + "epoch": 0.38994916485112563, + "grad_norm": 2.7505154609680176, + "learning_rate": 1.887207891118315e-05, + "loss": 18.3979, + "step": 1678 + }, + { + "epoch": 0.3901815541031227, + "grad_norm": 2.6307523250579834, + "learning_rate": 1.8870305462485175e-05, + "loss": 18.6972, + "step": 1679 + }, + { + "epoch": 0.3904139433551198, + "grad_norm": 2.701371192932129, + "learning_rate": 1.8868530704133274e-05, + "loss": 19.0378, + "step": 1680 + }, + { + "epoch": 0.3906463326071169, + "grad_norm": 2.7877326011657715, + "learning_rate": 1.8866754636389478e-05, + "loss": 18.4174, + "step": 1681 + }, + { + "epoch": 0.39087872185911404, + "grad_norm": 2.7495834827423096, + "learning_rate": 1.8864977259516015e-05, + "loss": 18.2672, + "step": 1682 + }, + { + "epoch": 0.39111111111111113, + "grad_norm": 2.755943536758423, + "learning_rate": 1.88631985737753e-05, + "loss": 18.2802, + "step": 1683 + }, + { + "epoch": 0.3913435003631082, + "grad_norm": 2.782775640487671, + "learning_rate": 1.8861418579429955e-05, + "loss": 17.6854, + "step": 1684 + }, + { + "epoch": 0.3915758896151053, + "grad_norm": 3.0379271507263184, + "learning_rate": 1.885963727674278e-05, + "loss": 17.6475, + "step": 1685 + }, + { + "epoch": 0.3918082788671024, + "grad_norm": 2.936838388442993, + "learning_rate": 1.885785466597678e-05, + "loss": 18.7151, + "step": 1686 + }, + { + "epoch": 0.3920406681190995, + "grad_norm": 2.7436928749084473, + "learning_rate": 1.8856070747395146e-05, + "loss": 18.6559, + "step": 1687 + }, + { + "epoch": 0.3922730573710966, + "grad_norm": 2.6796131134033203, + "learning_rate": 1.885428552126126e-05, + "loss": 17.4877, + "step": 1688 + }, + { + "epoch": 0.39250544662309367, + "grad_norm": 2.778062343597412, + "learning_rate": 1.885249898783871e-05, + "loss": 18.9888, + "step": 1689 + }, + { + "epoch": 0.39273783587509076, + "grad_norm": 2.61979603767395, + "learning_rate": 1.8850711147391257e-05, + "loss": 18.0088, + "step": 1690 + }, + { + "epoch": 0.39297022512708785, + "grad_norm": 2.7765774726867676, + "learning_rate": 1.884892200018288e-05, + "loss": 18.7495, + "step": 1691 + }, + { + "epoch": 0.393202614379085, + "grad_norm": 2.651996374130249, + "learning_rate": 1.8847131546477725e-05, + "loss": 18.0496, + "step": 1692 + }, + { + "epoch": 0.3934350036310821, + "grad_norm": 3.030207872390747, + "learning_rate": 1.8845339786540152e-05, + "loss": 18.1378, + "step": 1693 + }, + { + "epoch": 0.39366739288307917, + "grad_norm": 2.720344066619873, + "learning_rate": 1.8843546720634695e-05, + "loss": 16.9347, + "step": 1694 + }, + { + "epoch": 0.39389978213507626, + "grad_norm": 2.5724148750305176, + "learning_rate": 1.8841752349026098e-05, + "loss": 17.7387, + "step": 1695 + }, + { + "epoch": 0.39413217138707335, + "grad_norm": 2.8666014671325684, + "learning_rate": 1.8839956671979293e-05, + "loss": 17.8439, + "step": 1696 + }, + { + "epoch": 0.39436456063907044, + "grad_norm": 2.9308931827545166, + "learning_rate": 1.8838159689759393e-05, + "loss": 18.2453, + "step": 1697 + }, + { + "epoch": 0.3945969498910675, + "grad_norm": 2.64799427986145, + "learning_rate": 1.8836361402631726e-05, + "loss": 18.2465, + "step": 1698 + }, + { + "epoch": 0.3948293391430646, + "grad_norm": 2.688286781311035, + "learning_rate": 1.8834561810861785e-05, + "loss": 17.3874, + "step": 1699 + }, + { + "epoch": 0.3950617283950617, + "grad_norm": 2.704339027404785, + "learning_rate": 1.883276091471528e-05, + "loss": 17.6905, + "step": 1700 + }, + { + "epoch": 0.3952941176470588, + "grad_norm": 2.7387335300445557, + "learning_rate": 1.88309587144581e-05, + "loss": 18.7396, + "step": 1701 + }, + { + "epoch": 0.39552650689905594, + "grad_norm": 2.7882912158966064, + "learning_rate": 1.8829155210356332e-05, + "loss": 18.0746, + "step": 1702 + }, + { + "epoch": 0.39575889615105303, + "grad_norm": 2.7375805377960205, + "learning_rate": 1.8827350402676253e-05, + "loss": 17.6262, + "step": 1703 + }, + { + "epoch": 0.3959912854030501, + "grad_norm": 2.508265495300293, + "learning_rate": 1.8825544291684332e-05, + "loss": 16.7542, + "step": 1704 + }, + { + "epoch": 0.3962236746550472, + "grad_norm": 2.781491756439209, + "learning_rate": 1.8823736877647238e-05, + "loss": 18.4105, + "step": 1705 + }, + { + "epoch": 0.3964560639070443, + "grad_norm": 3.0136749744415283, + "learning_rate": 1.8821928160831814e-05, + "loss": 17.4242, + "step": 1706 + }, + { + "epoch": 0.3966884531590414, + "grad_norm": 2.81421160697937, + "learning_rate": 1.8820118141505123e-05, + "loss": 18.4017, + "step": 1707 + }, + { + "epoch": 0.3969208424110385, + "grad_norm": 2.7095000743865967, + "learning_rate": 1.8818306819934394e-05, + "loss": 19.1066, + "step": 1708 + }, + { + "epoch": 0.39715323166303557, + "grad_norm": 2.9010143280029297, + "learning_rate": 1.881649419638706e-05, + "loss": 18.5473, + "step": 1709 + }, + { + "epoch": 0.39738562091503266, + "grad_norm": 2.5895707607269287, + "learning_rate": 1.881468027113075e-05, + "loss": 17.9106, + "step": 1710 + }, + { + "epoch": 0.3976180101670298, + "grad_norm": 2.7376651763916016, + "learning_rate": 1.8812865044433277e-05, + "loss": 19.0757, + "step": 1711 + }, + { + "epoch": 0.3978503994190269, + "grad_norm": 2.6656851768493652, + "learning_rate": 1.881104851656265e-05, + "loss": 18.5879, + "step": 1712 + }, + { + "epoch": 0.398082788671024, + "grad_norm": 2.6696650981903076, + "learning_rate": 1.880923068778707e-05, + "loss": 18.5305, + "step": 1713 + }, + { + "epoch": 0.39831517792302107, + "grad_norm": 2.5904784202575684, + "learning_rate": 1.8807411558374933e-05, + "loss": 18.8006, + "step": 1714 + }, + { + "epoch": 0.39854756717501816, + "grad_norm": 2.6478652954101562, + "learning_rate": 1.8805591128594818e-05, + "loss": 18.1513, + "step": 1715 + }, + { + "epoch": 0.39877995642701525, + "grad_norm": 2.657780170440674, + "learning_rate": 1.8803769398715508e-05, + "loss": 17.7288, + "step": 1716 + }, + { + "epoch": 0.39901234567901234, + "grad_norm": 2.796685218811035, + "learning_rate": 1.880194636900597e-05, + "loss": 18.7162, + "step": 1717 + }, + { + "epoch": 0.3992447349310094, + "grad_norm": 2.6038451194763184, + "learning_rate": 1.880012203973536e-05, + "loss": 17.7594, + "step": 1718 + }, + { + "epoch": 0.3994771241830065, + "grad_norm": 3.177173376083374, + "learning_rate": 1.8798296411173033e-05, + "loss": 17.54, + "step": 1719 + }, + { + "epoch": 0.3997095134350036, + "grad_norm": 2.5864531993865967, + "learning_rate": 1.8796469483588535e-05, + "loss": 18.1535, + "step": 1720 + }, + { + "epoch": 0.39994190268700075, + "grad_norm": 2.9481122493743896, + "learning_rate": 1.8794641257251604e-05, + "loss": 17.8263, + "step": 1721 + }, + { + "epoch": 0.40017429193899784, + "grad_norm": 2.816401481628418, + "learning_rate": 1.8792811732432165e-05, + "loss": 17.8285, + "step": 1722 + }, + { + "epoch": 0.40040668119099493, + "grad_norm": 2.8123955726623535, + "learning_rate": 1.8790980909400338e-05, + "loss": 18.0106, + "step": 1723 + }, + { + "epoch": 0.400639070442992, + "grad_norm": 2.635674476623535, + "learning_rate": 1.8789148788426437e-05, + "loss": 18.5865, + "step": 1724 + }, + { + "epoch": 0.4008714596949891, + "grad_norm": 2.5790886878967285, + "learning_rate": 1.878731536978096e-05, + "loss": 18.3352, + "step": 1725 + }, + { + "epoch": 0.4011038489469862, + "grad_norm": 3.3816299438476562, + "learning_rate": 1.8785480653734608e-05, + "loss": 18.4219, + "step": 1726 + }, + { + "epoch": 0.4013362381989833, + "grad_norm": 2.756624698638916, + "learning_rate": 1.8783644640558263e-05, + "loss": 18.1278, + "step": 1727 + }, + { + "epoch": 0.4015686274509804, + "grad_norm": 2.6611080169677734, + "learning_rate": 1.8781807330523003e-05, + "loss": 17.8549, + "step": 1728 + }, + { + "epoch": 0.40180101670297746, + "grad_norm": 2.5704550743103027, + "learning_rate": 1.87799687239001e-05, + "loss": 17.8862, + "step": 1729 + }, + { + "epoch": 0.4020334059549746, + "grad_norm": 2.7542383670806885, + "learning_rate": 1.8778128820961004e-05, + "loss": 17.4779, + "step": 1730 + }, + { + "epoch": 0.4022657952069717, + "grad_norm": 2.8651185035705566, + "learning_rate": 1.8776287621977384e-05, + "loss": 18.5387, + "step": 1731 + }, + { + "epoch": 0.4024981844589688, + "grad_norm": 2.903196096420288, + "learning_rate": 1.877444512722107e-05, + "loss": 17.9797, + "step": 1732 + }, + { + "epoch": 0.4027305737109659, + "grad_norm": 2.8033628463745117, + "learning_rate": 1.8772601336964102e-05, + "loss": 18.6843, + "step": 1733 + }, + { + "epoch": 0.40296296296296297, + "grad_norm": 2.826962471008301, + "learning_rate": 1.8770756251478705e-05, + "loss": 18.4508, + "step": 1734 + }, + { + "epoch": 0.40319535221496006, + "grad_norm": 2.6802456378936768, + "learning_rate": 1.87689098710373e-05, + "loss": 18.4348, + "step": 1735 + }, + { + "epoch": 0.40342774146695715, + "grad_norm": 2.771972417831421, + "learning_rate": 1.8767062195912484e-05, + "loss": 17.5158, + "step": 1736 + }, + { + "epoch": 0.40366013071895424, + "grad_norm": 2.726731061935425, + "learning_rate": 1.8765213226377073e-05, + "loss": 18.4233, + "step": 1737 + }, + { + "epoch": 0.4038925199709513, + "grad_norm": 2.5825564861297607, + "learning_rate": 1.876336296270404e-05, + "loss": 17.9451, + "step": 1738 + }, + { + "epoch": 0.4041249092229484, + "grad_norm": 2.7042062282562256, + "learning_rate": 1.8761511405166582e-05, + "loss": 17.3975, + "step": 1739 + }, + { + "epoch": 0.40435729847494556, + "grad_norm": 2.8027637004852295, + "learning_rate": 1.8759658554038065e-05, + "loss": 17.0453, + "step": 1740 + }, + { + "epoch": 0.40458968772694265, + "grad_norm": 2.479893207550049, + "learning_rate": 1.875780440959205e-05, + "loss": 17.632, + "step": 1741 + }, + { + "epoch": 0.40482207697893974, + "grad_norm": 2.7748022079467773, + "learning_rate": 1.8755948972102297e-05, + "loss": 17.9472, + "step": 1742 + }, + { + "epoch": 0.4050544662309368, + "grad_norm": 2.633770227432251, + "learning_rate": 1.875409224184275e-05, + "loss": 17.3771, + "step": 1743 + }, + { + "epoch": 0.4052868554829339, + "grad_norm": 3.1996192932128906, + "learning_rate": 1.8752234219087538e-05, + "loss": 18.441, + "step": 1744 + }, + { + "epoch": 0.405519244734931, + "grad_norm": 2.5415611267089844, + "learning_rate": 1.8750374904111e-05, + "loss": 18.3185, + "step": 1745 + }, + { + "epoch": 0.4057516339869281, + "grad_norm": 3.25425124168396, + "learning_rate": 1.874851429718765e-05, + "loss": 17.4954, + "step": 1746 + }, + { + "epoch": 0.4059840232389252, + "grad_norm": 2.828871726989746, + "learning_rate": 1.874665239859219e-05, + "loss": 18.0347, + "step": 1747 + }, + { + "epoch": 0.4062164124909223, + "grad_norm": 2.5553321838378906, + "learning_rate": 1.8744789208599533e-05, + "loss": 17.8746, + "step": 1748 + }, + { + "epoch": 0.40644880174291936, + "grad_norm": 2.9386520385742188, + "learning_rate": 1.8742924727484755e-05, + "loss": 18.6838, + "step": 1749 + }, + { + "epoch": 0.4066811909949165, + "grad_norm": 2.782116174697876, + "learning_rate": 1.8741058955523147e-05, + "loss": 18.4904, + "step": 1750 + }, + { + "epoch": 0.4069135802469136, + "grad_norm": 2.7307722568511963, + "learning_rate": 1.8739191892990177e-05, + "loss": 18.3448, + "step": 1751 + }, + { + "epoch": 0.4071459694989107, + "grad_norm": 2.7537124156951904, + "learning_rate": 1.8737323540161507e-05, + "loss": 18.1434, + "step": 1752 + }, + { + "epoch": 0.4073783587509078, + "grad_norm": 2.6603455543518066, + "learning_rate": 1.873545389731299e-05, + "loss": 17.1656, + "step": 1753 + }, + { + "epoch": 0.40761074800290487, + "grad_norm": 2.582676887512207, + "learning_rate": 1.8733582964720664e-05, + "loss": 17.0893, + "step": 1754 + }, + { + "epoch": 0.40784313725490196, + "grad_norm": 2.676561117172241, + "learning_rate": 1.873171074266077e-05, + "loss": 17.7669, + "step": 1755 + }, + { + "epoch": 0.40807552650689904, + "grad_norm": 3.0582563877105713, + "learning_rate": 1.8729837231409726e-05, + "loss": 17.1837, + "step": 1756 + }, + { + "epoch": 0.40830791575889613, + "grad_norm": 2.7760090827941895, + "learning_rate": 1.8727962431244152e-05, + "loss": 17.443, + "step": 1757 + }, + { + "epoch": 0.4085403050108932, + "grad_norm": 2.69791579246521, + "learning_rate": 1.8726086342440847e-05, + "loss": 18.3657, + "step": 1758 + }, + { + "epoch": 0.40877269426289037, + "grad_norm": 2.74931263923645, + "learning_rate": 1.8724208965276803e-05, + "loss": 18.3954, + "step": 1759 + }, + { + "epoch": 0.40900508351488746, + "grad_norm": 2.566579818725586, + "learning_rate": 1.872233030002921e-05, + "loss": 18.2463, + "step": 1760 + }, + { + "epoch": 0.40923747276688455, + "grad_norm": 2.572366952896118, + "learning_rate": 1.872045034697545e-05, + "loss": 18.4987, + "step": 1761 + }, + { + "epoch": 0.40946986201888164, + "grad_norm": 2.8358025550842285, + "learning_rate": 1.8718569106393073e-05, + "loss": 17.9169, + "step": 1762 + }, + { + "epoch": 0.4097022512708787, + "grad_norm": 2.723405361175537, + "learning_rate": 1.8716686578559842e-05, + "loss": 19.1537, + "step": 1763 + }, + { + "epoch": 0.4099346405228758, + "grad_norm": 4.466728687286377, + "learning_rate": 1.871480276375371e-05, + "loss": 18.6361, + "step": 1764 + }, + { + "epoch": 0.4101670297748729, + "grad_norm": 2.592050552368164, + "learning_rate": 1.8712917662252796e-05, + "loss": 17.4098, + "step": 1765 + }, + { + "epoch": 0.41039941902687, + "grad_norm": 2.7175352573394775, + "learning_rate": 1.8711031274335438e-05, + "loss": 18.7299, + "step": 1766 + }, + { + "epoch": 0.4106318082788671, + "grad_norm": 2.621626615524292, + "learning_rate": 1.870914360028014e-05, + "loss": 18.1286, + "step": 1767 + }, + { + "epoch": 0.4108641975308642, + "grad_norm": 2.7423760890960693, + "learning_rate": 1.870725464036562e-05, + "loss": 16.872, + "step": 1768 + }, + { + "epoch": 0.4110965867828613, + "grad_norm": 2.6429708003997803, + "learning_rate": 1.8705364394870765e-05, + "loss": 18.6149, + "step": 1769 + }, + { + "epoch": 0.4113289760348584, + "grad_norm": 2.7917087078094482, + "learning_rate": 1.8703472864074666e-05, + "loss": 17.5914, + "step": 1770 + }, + { + "epoch": 0.4115613652868555, + "grad_norm": 2.8056273460388184, + "learning_rate": 1.8701580048256588e-05, + "loss": 17.2965, + "step": 1771 + }, + { + "epoch": 0.4117937545388526, + "grad_norm": 2.953885793685913, + "learning_rate": 1.8699685947696005e-05, + "loss": 17.8355, + "step": 1772 + }, + { + "epoch": 0.4120261437908497, + "grad_norm": 2.7922091484069824, + "learning_rate": 1.869779056267256e-05, + "loss": 19.2194, + "step": 1773 + }, + { + "epoch": 0.41225853304284676, + "grad_norm": 2.730123281478882, + "learning_rate": 1.869589389346611e-05, + "loss": 17.3102, + "step": 1774 + }, + { + "epoch": 0.41249092229484385, + "grad_norm": 2.8229196071624756, + "learning_rate": 1.8693995940356683e-05, + "loss": 17.6757, + "step": 1775 + }, + { + "epoch": 0.41272331154684094, + "grad_norm": 2.7147936820983887, + "learning_rate": 1.8692096703624495e-05, + "loss": 17.9042, + "step": 1776 + }, + { + "epoch": 0.41295570079883803, + "grad_norm": 2.678223133087158, + "learning_rate": 1.8690196183549965e-05, + "loss": 18.5438, + "step": 1777 + }, + { + "epoch": 0.4131880900508351, + "grad_norm": 2.522353410720825, + "learning_rate": 1.8688294380413693e-05, + "loss": 16.8686, + "step": 1778 + }, + { + "epoch": 0.41342047930283227, + "grad_norm": 2.626436948776245, + "learning_rate": 1.8686391294496473e-05, + "loss": 18.2609, + "step": 1779 + }, + { + "epoch": 0.41365286855482936, + "grad_norm": 2.6416733264923096, + "learning_rate": 1.868448692607928e-05, + "loss": 17.3281, + "step": 1780 + }, + { + "epoch": 0.41388525780682645, + "grad_norm": 2.5513112545013428, + "learning_rate": 1.868258127544329e-05, + "loss": 17.211, + "step": 1781 + }, + { + "epoch": 0.41411764705882353, + "grad_norm": 2.6544766426086426, + "learning_rate": 1.868067434286986e-05, + "loss": 17.9749, + "step": 1782 + }, + { + "epoch": 0.4143500363108206, + "grad_norm": 2.625002861022949, + "learning_rate": 1.867876612864054e-05, + "loss": 18.489, + "step": 1783 + }, + { + "epoch": 0.4145824255628177, + "grad_norm": 2.8041939735412598, + "learning_rate": 1.8676856633037063e-05, + "loss": 18.2137, + "step": 1784 + }, + { + "epoch": 0.4148148148148148, + "grad_norm": 2.687110424041748, + "learning_rate": 1.8674945856341354e-05, + "loss": 17.5974, + "step": 1785 + }, + { + "epoch": 0.4150472040668119, + "grad_norm": 2.621633529663086, + "learning_rate": 1.8673033798835542e-05, + "loss": 17.48, + "step": 1786 + }, + { + "epoch": 0.415279593318809, + "grad_norm": 2.618889570236206, + "learning_rate": 1.8671120460801918e-05, + "loss": 17.9409, + "step": 1787 + }, + { + "epoch": 0.4155119825708061, + "grad_norm": 2.8399219512939453, + "learning_rate": 1.8669205842522986e-05, + "loss": 17.8244, + "step": 1788 + }, + { + "epoch": 0.4157443718228032, + "grad_norm": 3.0272843837738037, + "learning_rate": 1.8667289944281427e-05, + "loss": 18.2669, + "step": 1789 + }, + { + "epoch": 0.4159767610748003, + "grad_norm": 3.131261110305786, + "learning_rate": 1.866537276636011e-05, + "loss": 17.4948, + "step": 1790 + }, + { + "epoch": 0.4162091503267974, + "grad_norm": 2.7181396484375, + "learning_rate": 1.8663454309042098e-05, + "loss": 18.3818, + "step": 1791 + }, + { + "epoch": 0.4164415395787945, + "grad_norm": 2.8261353969573975, + "learning_rate": 1.8661534572610644e-05, + "loss": 17.3288, + "step": 1792 + }, + { + "epoch": 0.4166739288307916, + "grad_norm": 3.753758668899536, + "learning_rate": 1.8659613557349183e-05, + "loss": 17.4606, + "step": 1793 + }, + { + "epoch": 0.41690631808278866, + "grad_norm": 3.063558578491211, + "learning_rate": 1.8657691263541343e-05, + "loss": 17.103, + "step": 1794 + }, + { + "epoch": 0.41713870733478575, + "grad_norm": 2.678561210632324, + "learning_rate": 1.8655767691470944e-05, + "loss": 17.1866, + "step": 1795 + }, + { + "epoch": 0.41737109658678284, + "grad_norm": 2.8937790393829346, + "learning_rate": 1.8653842841421987e-05, + "loss": 18.2837, + "step": 1796 + }, + { + "epoch": 0.41760348583877993, + "grad_norm": 3.042573928833008, + "learning_rate": 1.865191671367867e-05, + "loss": 17.3436, + "step": 1797 + }, + { + "epoch": 0.4178358750907771, + "grad_norm": 2.9486069679260254, + "learning_rate": 1.8649989308525374e-05, + "loss": 18.7052, + "step": 1798 + }, + { + "epoch": 0.41806826434277417, + "grad_norm": 2.7035937309265137, + "learning_rate": 1.8648060626246666e-05, + "loss": 17.2567, + "step": 1799 + }, + { + "epoch": 0.41830065359477125, + "grad_norm": 2.6541781425476074, + "learning_rate": 1.8646130667127316e-05, + "loss": 18.5249, + "step": 1800 + }, + { + "epoch": 0.41853304284676834, + "grad_norm": 2.692859649658203, + "learning_rate": 1.8644199431452265e-05, + "loss": 18.8626, + "step": 1801 + }, + { + "epoch": 0.41876543209876543, + "grad_norm": 2.862452745437622, + "learning_rate": 1.8642266919506644e-05, + "loss": 17.7183, + "step": 1802 + }, + { + "epoch": 0.4189978213507625, + "grad_norm": 2.6084461212158203, + "learning_rate": 1.8640333131575793e-05, + "loss": 18.1275, + "step": 1803 + }, + { + "epoch": 0.4192302106027596, + "grad_norm": 2.5947065353393555, + "learning_rate": 1.8638398067945214e-05, + "loss": 17.9812, + "step": 1804 + }, + { + "epoch": 0.4194625998547567, + "grad_norm": 2.8150882720947266, + "learning_rate": 1.8636461728900613e-05, + "loss": 18.7585, + "step": 1805 + }, + { + "epoch": 0.4196949891067538, + "grad_norm": 2.594536066055298, + "learning_rate": 1.863452411472788e-05, + "loss": 17.9611, + "step": 1806 + }, + { + "epoch": 0.4199273783587509, + "grad_norm": 2.9060418605804443, + "learning_rate": 1.8632585225713095e-05, + "loss": 18.209, + "step": 1807 + }, + { + "epoch": 0.420159767610748, + "grad_norm": 2.7172679901123047, + "learning_rate": 1.8630645062142522e-05, + "loss": 17.9768, + "step": 1808 + }, + { + "epoch": 0.4203921568627451, + "grad_norm": 2.7394840717315674, + "learning_rate": 1.8628703624302617e-05, + "loss": 17.6921, + "step": 1809 + }, + { + "epoch": 0.4206245461147422, + "grad_norm": 2.7070484161376953, + "learning_rate": 1.8626760912480022e-05, + "loss": 17.6976, + "step": 1810 + }, + { + "epoch": 0.4208569353667393, + "grad_norm": 3.5156712532043457, + "learning_rate": 1.862481692696157e-05, + "loss": 18.2633, + "step": 1811 + }, + { + "epoch": 0.4210893246187364, + "grad_norm": 3.1375672817230225, + "learning_rate": 1.862287166803428e-05, + "loss": 18.7606, + "step": 1812 + }, + { + "epoch": 0.42132171387073347, + "grad_norm": 2.7018823623657227, + "learning_rate": 1.8620925135985358e-05, + "loss": 17.4897, + "step": 1813 + }, + { + "epoch": 0.42155410312273056, + "grad_norm": 2.688610553741455, + "learning_rate": 1.8618977331102207e-05, + "loss": 18.4972, + "step": 1814 + }, + { + "epoch": 0.42178649237472765, + "grad_norm": 2.681816816329956, + "learning_rate": 1.8617028253672396e-05, + "loss": 17.5129, + "step": 1815 + }, + { + "epoch": 0.42201888162672474, + "grad_norm": 2.6960532665252686, + "learning_rate": 1.8615077903983703e-05, + "loss": 18.2004, + "step": 1816 + }, + { + "epoch": 0.4222512708787219, + "grad_norm": 2.6948342323303223, + "learning_rate": 1.8613126282324092e-05, + "loss": 18.5063, + "step": 1817 + }, + { + "epoch": 0.422483660130719, + "grad_norm": 2.6531901359558105, + "learning_rate": 1.8611173388981702e-05, + "loss": 18.3753, + "step": 1818 + }, + { + "epoch": 0.42271604938271606, + "grad_norm": 2.9749631881713867, + "learning_rate": 1.860921922424487e-05, + "loss": 17.2295, + "step": 1819 + }, + { + "epoch": 0.42294843863471315, + "grad_norm": 2.6893131732940674, + "learning_rate": 1.860726378840212e-05, + "loss": 18.1065, + "step": 1820 + }, + { + "epoch": 0.42318082788671024, + "grad_norm": 2.6785824298858643, + "learning_rate": 1.8605307081742158e-05, + "loss": 17.872, + "step": 1821 + }, + { + "epoch": 0.42341321713870733, + "grad_norm": 2.5959341526031494, + "learning_rate": 1.8603349104553884e-05, + "loss": 17.576, + "step": 1822 + }, + { + "epoch": 0.4236456063907044, + "grad_norm": 3.0281405448913574, + "learning_rate": 1.8601389857126383e-05, + "loss": 20.2794, + "step": 1823 + }, + { + "epoch": 0.4238779956427015, + "grad_norm": 2.8816497325897217, + "learning_rate": 1.859942933974893e-05, + "loss": 18.6499, + "step": 1824 + }, + { + "epoch": 0.4241103848946986, + "grad_norm": 2.546600580215454, + "learning_rate": 1.8597467552710976e-05, + "loss": 18.3706, + "step": 1825 + }, + { + "epoch": 0.4243427741466957, + "grad_norm": 2.6717042922973633, + "learning_rate": 1.859550449630218e-05, + "loss": 18.812, + "step": 1826 + }, + { + "epoch": 0.42457516339869283, + "grad_norm": 2.8787641525268555, + "learning_rate": 1.8593540170812373e-05, + "loss": 17.3556, + "step": 1827 + }, + { + "epoch": 0.4248075526506899, + "grad_norm": 2.714219093322754, + "learning_rate": 1.8591574576531575e-05, + "loss": 18.4761, + "step": 1828 + }, + { + "epoch": 0.425039941902687, + "grad_norm": 2.639188051223755, + "learning_rate": 1.8589607713749994e-05, + "loss": 17.9292, + "step": 1829 + }, + { + "epoch": 0.4252723311546841, + "grad_norm": 2.7114675045013428, + "learning_rate": 1.8587639582758032e-05, + "loss": 17.8662, + "step": 1830 + }, + { + "epoch": 0.4255047204066812, + "grad_norm": 3.1710472106933594, + "learning_rate": 1.858567018384627e-05, + "loss": 17.7695, + "step": 1831 + }, + { + "epoch": 0.4257371096586783, + "grad_norm": 2.6161727905273438, + "learning_rate": 1.858369951730548e-05, + "loss": 17.8809, + "step": 1832 + }, + { + "epoch": 0.42596949891067537, + "grad_norm": 4.649213790893555, + "learning_rate": 1.8581727583426624e-05, + "loss": 18.3566, + "step": 1833 + }, + { + "epoch": 0.42620188816267246, + "grad_norm": 2.700385808944702, + "learning_rate": 1.857975438250084e-05, + "loss": 18.0948, + "step": 1834 + }, + { + "epoch": 0.42643427741466955, + "grad_norm": 2.507991313934326, + "learning_rate": 1.857777991481947e-05, + "loss": 17.7686, + "step": 1835 + }, + { + "epoch": 0.4266666666666667, + "grad_norm": 2.7275681495666504, + "learning_rate": 1.8575804180674025e-05, + "loss": 18.3016, + "step": 1836 + }, + { + "epoch": 0.4268990559186638, + "grad_norm": 2.5587050914764404, + "learning_rate": 1.8573827180356217e-05, + "loss": 17.6196, + "step": 1837 + }, + { + "epoch": 0.4271314451706609, + "grad_norm": 2.677377700805664, + "learning_rate": 1.857184891415794e-05, + "loss": 17.6685, + "step": 1838 + }, + { + "epoch": 0.42736383442265796, + "grad_norm": 2.736077070236206, + "learning_rate": 1.856986938237127e-05, + "loss": 18.4994, + "step": 1839 + }, + { + "epoch": 0.42759622367465505, + "grad_norm": 2.7943191528320312, + "learning_rate": 1.856788858528848e-05, + "loss": 18.3445, + "step": 1840 + }, + { + "epoch": 0.42782861292665214, + "grad_norm": 2.6557745933532715, + "learning_rate": 1.856590652320202e-05, + "loss": 18.6886, + "step": 1841 + }, + { + "epoch": 0.42806100217864923, + "grad_norm": 2.6900365352630615, + "learning_rate": 1.8563923196404535e-05, + "loss": 18.5001, + "step": 1842 + }, + { + "epoch": 0.4282933914306463, + "grad_norm": 2.555007219314575, + "learning_rate": 1.856193860518885e-05, + "loss": 18.4564, + "step": 1843 + }, + { + "epoch": 0.4285257806826434, + "grad_norm": 2.602250576019287, + "learning_rate": 1.855995274984798e-05, + "loss": 18.7733, + "step": 1844 + }, + { + "epoch": 0.4287581699346405, + "grad_norm": 2.524055004119873, + "learning_rate": 1.8557965630675127e-05, + "loss": 17.6114, + "step": 1845 + }, + { + "epoch": 0.42899055918663764, + "grad_norm": 2.548616886138916, + "learning_rate": 1.8555977247963674e-05, + "loss": 17.5432, + "step": 1846 + }, + { + "epoch": 0.42922294843863473, + "grad_norm": 2.730487823486328, + "learning_rate": 1.8553987602007203e-05, + "loss": 18.4115, + "step": 1847 + }, + { + "epoch": 0.4294553376906318, + "grad_norm": 2.62644624710083, + "learning_rate": 1.8551996693099468e-05, + "loss": 17.6383, + "step": 1848 + }, + { + "epoch": 0.4296877269426289, + "grad_norm": 2.6501293182373047, + "learning_rate": 1.855000452153442e-05, + "loss": 18.5124, + "step": 1849 + }, + { + "epoch": 0.429920116194626, + "grad_norm": 2.6142899990081787, + "learning_rate": 1.854801108760619e-05, + "loss": 18.2629, + "step": 1850 + }, + { + "epoch": 0.4301525054466231, + "grad_norm": 2.8171145915985107, + "learning_rate": 1.8546016391609104e-05, + "loss": 19.3997, + "step": 1851 + }, + { + "epoch": 0.4303848946986202, + "grad_norm": 2.5904417037963867, + "learning_rate": 1.854402043383766e-05, + "loss": 17.7199, + "step": 1852 + }, + { + "epoch": 0.43061728395061727, + "grad_norm": 2.733609914779663, + "learning_rate": 1.8542023214586557e-05, + "loss": 18.6484, + "step": 1853 + }, + { + "epoch": 0.43084967320261436, + "grad_norm": 3.5600876808166504, + "learning_rate": 1.8540024734150673e-05, + "loss": 17.7838, + "step": 1854 + }, + { + "epoch": 0.43108206245461145, + "grad_norm": 2.7168614864349365, + "learning_rate": 1.853802499282507e-05, + "loss": 17.7107, + "step": 1855 + }, + { + "epoch": 0.4313144517066086, + "grad_norm": 3.2245097160339355, + "learning_rate": 1.8536023990905e-05, + "loss": 18.8398, + "step": 1856 + }, + { + "epoch": 0.4315468409586057, + "grad_norm": 2.6820480823516846, + "learning_rate": 1.8534021728685904e-05, + "loss": 17.9219, + "step": 1857 + }, + { + "epoch": 0.43177923021060277, + "grad_norm": 2.957275390625, + "learning_rate": 1.8532018206463404e-05, + "loss": 17.7728, + "step": 1858 + }, + { + "epoch": 0.43201161946259986, + "grad_norm": 2.695570945739746, + "learning_rate": 1.8530013424533306e-05, + "loss": 18.5272, + "step": 1859 + }, + { + "epoch": 0.43224400871459695, + "grad_norm": 2.9047796726226807, + "learning_rate": 1.8528007383191605e-05, + "loss": 16.4833, + "step": 1860 + }, + { + "epoch": 0.43247639796659404, + "grad_norm": 2.763972282409668, + "learning_rate": 1.852600008273449e-05, + "loss": 18.1994, + "step": 1861 + }, + { + "epoch": 0.43270878721859113, + "grad_norm": 2.8818552494049072, + "learning_rate": 1.852399152345832e-05, + "loss": 18.0071, + "step": 1862 + }, + { + "epoch": 0.4329411764705882, + "grad_norm": 2.911031723022461, + "learning_rate": 1.8521981705659656e-05, + "loss": 18.2787, + "step": 1863 + }, + { + "epoch": 0.4331735657225853, + "grad_norm": 2.8949790000915527, + "learning_rate": 1.8519970629635233e-05, + "loss": 18.4731, + "step": 1864 + }, + { + "epoch": 0.43340595497458245, + "grad_norm": 2.7165064811706543, + "learning_rate": 1.8517958295681976e-05, + "loss": 17.9981, + "step": 1865 + }, + { + "epoch": 0.43363834422657954, + "grad_norm": 2.7146990299224854, + "learning_rate": 1.851594470409699e-05, + "loss": 18.5162, + "step": 1866 + }, + { + "epoch": 0.43387073347857663, + "grad_norm": 8.523813247680664, + "learning_rate": 1.851392985517758e-05, + "loss": 18.1178, + "step": 1867 + }, + { + "epoch": 0.4341031227305737, + "grad_norm": 2.5365285873413086, + "learning_rate": 1.8511913749221225e-05, + "loss": 18.1051, + "step": 1868 + }, + { + "epoch": 0.4343355119825708, + "grad_norm": 2.6480889320373535, + "learning_rate": 1.8509896386525592e-05, + "loss": 17.4935, + "step": 1869 + }, + { + "epoch": 0.4345679012345679, + "grad_norm": 2.6718742847442627, + "learning_rate": 1.8507877767388533e-05, + "loss": 18.9706, + "step": 1870 + }, + { + "epoch": 0.434800290486565, + "grad_norm": 2.5389811992645264, + "learning_rate": 1.8505857892108088e-05, + "loss": 17.1553, + "step": 1871 + }, + { + "epoch": 0.4350326797385621, + "grad_norm": 2.937171220779419, + "learning_rate": 1.850383676098248e-05, + "loss": 17.7374, + "step": 1872 + }, + { + "epoch": 0.43526506899055917, + "grad_norm": 2.912898063659668, + "learning_rate": 1.8501814374310115e-05, + "loss": 18.5208, + "step": 1873 + }, + { + "epoch": 0.43549745824255626, + "grad_norm": 2.5574746131896973, + "learning_rate": 1.8499790732389597e-05, + "loss": 18.4744, + "step": 1874 + }, + { + "epoch": 0.4357298474945534, + "grad_norm": 2.625535011291504, + "learning_rate": 1.8497765835519698e-05, + "loss": 18.7151, + "step": 1875 + }, + { + "epoch": 0.4359622367465505, + "grad_norm": 2.6306920051574707, + "learning_rate": 1.8495739683999386e-05, + "loss": 18.743, + "step": 1876 + }, + { + "epoch": 0.4361946259985476, + "grad_norm": 2.724123954772949, + "learning_rate": 1.849371227812781e-05, + "loss": 17.7647, + "step": 1877 + }, + { + "epoch": 0.43642701525054467, + "grad_norm": 2.7641963958740234, + "learning_rate": 1.849168361820431e-05, + "loss": 17.5661, + "step": 1878 + }, + { + "epoch": 0.43665940450254176, + "grad_norm": 2.6530964374542236, + "learning_rate": 1.8489653704528404e-05, + "loss": 17.809, + "step": 1879 + }, + { + "epoch": 0.43689179375453885, + "grad_norm": 2.6013083457946777, + "learning_rate": 1.8487622537399795e-05, + "loss": 18.4613, + "step": 1880 + }, + { + "epoch": 0.43712418300653594, + "grad_norm": 2.741227149963379, + "learning_rate": 1.8485590117118382e-05, + "loss": 18.6043, + "step": 1881 + }, + { + "epoch": 0.437356572258533, + "grad_norm": 2.6666247844696045, + "learning_rate": 1.8483556443984232e-05, + "loss": 17.6306, + "step": 1882 + }, + { + "epoch": 0.4375889615105301, + "grad_norm": 5.4164018630981445, + "learning_rate": 1.8481521518297614e-05, + "loss": 17.9671, + "step": 1883 + }, + { + "epoch": 0.4378213507625272, + "grad_norm": 2.701261043548584, + "learning_rate": 1.847948534035897e-05, + "loss": 18.0872, + "step": 1884 + }, + { + "epoch": 0.43805374001452435, + "grad_norm": 2.862126588821411, + "learning_rate": 1.847744791046893e-05, + "loss": 18.5293, + "step": 1885 + }, + { + "epoch": 0.43828612926652144, + "grad_norm": 2.8577239513397217, + "learning_rate": 1.8475409228928314e-05, + "loss": 18.8984, + "step": 1886 + }, + { + "epoch": 0.43851851851851853, + "grad_norm": 2.737917423248291, + "learning_rate": 1.8473369296038117e-05, + "loss": 18.1861, + "step": 1887 + }, + { + "epoch": 0.4387509077705156, + "grad_norm": 2.8628334999084473, + "learning_rate": 1.847132811209953e-05, + "loss": 18.1881, + "step": 1888 + }, + { + "epoch": 0.4389832970225127, + "grad_norm": 2.77000093460083, + "learning_rate": 1.846928567741392e-05, + "loss": 18.0365, + "step": 1889 + }, + { + "epoch": 0.4392156862745098, + "grad_norm": 2.781992197036743, + "learning_rate": 1.8467241992282842e-05, + "loss": 18.5107, + "step": 1890 + }, + { + "epoch": 0.4394480755265069, + "grad_norm": 2.7887966632843018, + "learning_rate": 1.8465197057008037e-05, + "loss": 17.0436, + "step": 1891 + }, + { + "epoch": 0.439680464778504, + "grad_norm": 2.6824944019317627, + "learning_rate": 1.8463150871891426e-05, + "loss": 18.3045, + "step": 1892 + }, + { + "epoch": 0.43991285403050107, + "grad_norm": 2.837049961090088, + "learning_rate": 1.846110343723512e-05, + "loss": 17.3733, + "step": 1893 + }, + { + "epoch": 0.4401452432824982, + "grad_norm": 2.6552846431732178, + "learning_rate": 1.845905475334141e-05, + "loss": 17.7491, + "step": 1894 + }, + { + "epoch": 0.4403776325344953, + "grad_norm": 2.695802688598633, + "learning_rate": 1.8457004820512777e-05, + "loss": 17.8557, + "step": 1895 + }, + { + "epoch": 0.4406100217864924, + "grad_norm": 2.8053324222564697, + "learning_rate": 1.845495363905188e-05, + "loss": 17.9843, + "step": 1896 + }, + { + "epoch": 0.4408424110384895, + "grad_norm": 2.722421884536743, + "learning_rate": 1.8452901209261563e-05, + "loss": 17.9356, + "step": 1897 + }, + { + "epoch": 0.44107480029048657, + "grad_norm": 2.603238582611084, + "learning_rate": 1.845084753144486e-05, + "loss": 17.9167, + "step": 1898 + }, + { + "epoch": 0.44130718954248366, + "grad_norm": 2.6899819374084473, + "learning_rate": 1.8448792605904985e-05, + "loss": 18.5739, + "step": 1899 + }, + { + "epoch": 0.44153957879448075, + "grad_norm": 2.6586344242095947, + "learning_rate": 1.8446736432945335e-05, + "loss": 18.2113, + "step": 1900 + }, + { + "epoch": 0.44177196804647784, + "grad_norm": 2.6044061183929443, + "learning_rate": 1.8444679012869496e-05, + "loss": 18.1661, + "step": 1901 + }, + { + "epoch": 0.4420043572984749, + "grad_norm": 2.950739860534668, + "learning_rate": 1.8442620345981232e-05, + "loss": 18.4208, + "step": 1902 + }, + { + "epoch": 0.442236746550472, + "grad_norm": 2.7911012172698975, + "learning_rate": 1.8440560432584498e-05, + "loss": 18.1196, + "step": 1903 + }, + { + "epoch": 0.44246913580246916, + "grad_norm": 2.6144535541534424, + "learning_rate": 1.843849927298343e-05, + "loss": 18.9785, + "step": 1904 + }, + { + "epoch": 0.44270152505446625, + "grad_norm": 2.5778696537017822, + "learning_rate": 1.8436436867482336e-05, + "loss": 17.7104, + "step": 1905 + }, + { + "epoch": 0.44293391430646334, + "grad_norm": 4.7912983894348145, + "learning_rate": 1.8434373216385737e-05, + "loss": 18.6495, + "step": 1906 + }, + { + "epoch": 0.44316630355846043, + "grad_norm": 3.1925854682922363, + "learning_rate": 1.843230831999831e-05, + "loss": 17.4854, + "step": 1907 + }, + { + "epoch": 0.4433986928104575, + "grad_norm": 3.010145425796509, + "learning_rate": 1.8430242178624924e-05, + "loss": 18.9821, + "step": 1908 + }, + { + "epoch": 0.4436310820624546, + "grad_norm": 2.818645477294922, + "learning_rate": 1.8428174792570643e-05, + "loss": 18.193, + "step": 1909 + }, + { + "epoch": 0.4438634713144517, + "grad_norm": 2.6752328872680664, + "learning_rate": 1.8426106162140693e-05, + "loss": 18.0626, + "step": 1910 + }, + { + "epoch": 0.4440958605664488, + "grad_norm": 2.6292543411254883, + "learning_rate": 1.842403628764051e-05, + "loss": 19.0676, + "step": 1911 + }, + { + "epoch": 0.4443282498184459, + "grad_norm": 2.9242563247680664, + "learning_rate": 1.842196516937569e-05, + "loss": 18.6272, + "step": 1912 + }, + { + "epoch": 0.44456063907044296, + "grad_norm": 2.7301714420318604, + "learning_rate": 1.8419892807652025e-05, + "loss": 17.8578, + "step": 1913 + }, + { + "epoch": 0.4447930283224401, + "grad_norm": 2.8857028484344482, + "learning_rate": 1.8417819202775497e-05, + "loss": 18.013, + "step": 1914 + }, + { + "epoch": 0.4450254175744372, + "grad_norm": 2.646326780319214, + "learning_rate": 1.8415744355052248e-05, + "loss": 18.0389, + "step": 1915 + }, + { + "epoch": 0.4452578068264343, + "grad_norm": 2.7268576622009277, + "learning_rate": 1.841366826478863e-05, + "loss": 17.3136, + "step": 1916 + }, + { + "epoch": 0.4454901960784314, + "grad_norm": 2.5076050758361816, + "learning_rate": 1.8411590932291158e-05, + "loss": 17.8536, + "step": 1917 + }, + { + "epoch": 0.44572258533042847, + "grad_norm": 2.744349241256714, + "learning_rate": 1.8409512357866548e-05, + "loss": 18.1719, + "step": 1918 + }, + { + "epoch": 0.44595497458242556, + "grad_norm": 2.8562638759613037, + "learning_rate": 1.8407432541821688e-05, + "loss": 18.1303, + "step": 1919 + }, + { + "epoch": 0.44618736383442265, + "grad_norm": 2.930025577545166, + "learning_rate": 1.8405351484463646e-05, + "loss": 17.8431, + "step": 1920 + }, + { + "epoch": 0.44641975308641973, + "grad_norm": 2.817387104034424, + "learning_rate": 1.8403269186099683e-05, + "loss": 17.4091, + "step": 1921 + }, + { + "epoch": 0.4466521423384168, + "grad_norm": 3.1754236221313477, + "learning_rate": 1.8401185647037245e-05, + "loss": 17.1067, + "step": 1922 + }, + { + "epoch": 0.44688453159041397, + "grad_norm": 2.609959602355957, + "learning_rate": 1.8399100867583947e-05, + "loss": 18.1257, + "step": 1923 + }, + { + "epoch": 0.44711692084241106, + "grad_norm": 2.680690288543701, + "learning_rate": 1.83970148480476e-05, + "loss": 17.5766, + "step": 1924 + }, + { + "epoch": 0.44734931009440815, + "grad_norm": 2.609489679336548, + "learning_rate": 1.8394927588736192e-05, + "loss": 17.4283, + "step": 1925 + }, + { + "epoch": 0.44758169934640524, + "grad_norm": 2.62855863571167, + "learning_rate": 1.83928390899579e-05, + "loss": 18.1551, + "step": 1926 + }, + { + "epoch": 0.4478140885984023, + "grad_norm": 2.7389187812805176, + "learning_rate": 1.8390749352021073e-05, + "loss": 19.1559, + "step": 1927 + }, + { + "epoch": 0.4480464778503994, + "grad_norm": 2.6150121688842773, + "learning_rate": 1.8388658375234255e-05, + "loss": 16.7684, + "step": 1928 + }, + { + "epoch": 0.4482788671023965, + "grad_norm": 2.7872626781463623, + "learning_rate": 1.8386566159906168e-05, + "loss": 17.5165, + "step": 1929 + }, + { + "epoch": 0.4485112563543936, + "grad_norm": 2.5628035068511963, + "learning_rate": 1.8384472706345715e-05, + "loss": 18.3498, + "step": 1930 + }, + { + "epoch": 0.4487436456063907, + "grad_norm": 2.7601661682128906, + "learning_rate": 1.8382378014861978e-05, + "loss": 18.0366, + "step": 1931 + }, + { + "epoch": 0.4489760348583878, + "grad_norm": 2.7268199920654297, + "learning_rate": 1.8380282085764236e-05, + "loss": 18.1528, + "step": 1932 + }, + { + "epoch": 0.4492084241103849, + "grad_norm": 2.4917678833007812, + "learning_rate": 1.8378184919361937e-05, + "loss": 17.8551, + "step": 1933 + }, + { + "epoch": 0.449440813362382, + "grad_norm": 2.8849825859069824, + "learning_rate": 1.837608651596472e-05, + "loss": 17.7598, + "step": 1934 + }, + { + "epoch": 0.4496732026143791, + "grad_norm": 2.8059825897216797, + "learning_rate": 1.83739868758824e-05, + "loss": 17.7657, + "step": 1935 + }, + { + "epoch": 0.4499055918663762, + "grad_norm": 3.0376455783843994, + "learning_rate": 1.8371885999424978e-05, + "loss": 17.1232, + "step": 1936 + }, + { + "epoch": 0.4501379811183733, + "grad_norm": 2.5982420444488525, + "learning_rate": 1.8369783886902637e-05, + "loss": 19.4863, + "step": 1937 + }, + { + "epoch": 0.45037037037037037, + "grad_norm": 2.695051670074463, + "learning_rate": 1.836768053862575e-05, + "loss": 18.5046, + "step": 1938 + }, + { + "epoch": 0.45060275962236745, + "grad_norm": 2.8089773654937744, + "learning_rate": 1.8365575954904854e-05, + "loss": 17.4325, + "step": 1939 + }, + { + "epoch": 0.45083514887436454, + "grad_norm": 2.6918423175811768, + "learning_rate": 1.836347013605069e-05, + "loss": 18.568, + "step": 1940 + }, + { + "epoch": 0.45106753812636163, + "grad_norm": 2.5743377208709717, + "learning_rate": 1.8361363082374163e-05, + "loss": 17.8139, + "step": 1941 + }, + { + "epoch": 0.4512999273783588, + "grad_norm": 2.8895833492279053, + "learning_rate": 1.8359254794186368e-05, + "loss": 19.1621, + "step": 1942 + }, + { + "epoch": 0.45153231663035587, + "grad_norm": 2.630213975906372, + "learning_rate": 1.8357145271798592e-05, + "loss": 18.023, + "step": 1943 + }, + { + "epoch": 0.45176470588235296, + "grad_norm": 2.606792449951172, + "learning_rate": 1.8355034515522286e-05, + "loss": 18.7861, + "step": 1944 + }, + { + "epoch": 0.45199709513435005, + "grad_norm": 2.909409523010254, + "learning_rate": 1.83529225256691e-05, + "loss": 18.6629, + "step": 1945 + }, + { + "epoch": 0.45222948438634714, + "grad_norm": 2.734227180480957, + "learning_rate": 1.8350809302550846e-05, + "loss": 17.8591, + "step": 1946 + }, + { + "epoch": 0.4524618736383442, + "grad_norm": 3.9135847091674805, + "learning_rate": 1.8348694846479543e-05, + "loss": 17.2495, + "step": 1947 + }, + { + "epoch": 0.4526942628903413, + "grad_norm": 2.66337513923645, + "learning_rate": 1.834657915776737e-05, + "loss": 17.9695, + "step": 1948 + }, + { + "epoch": 0.4529266521423384, + "grad_norm": 2.7302515506744385, + "learning_rate": 1.8344462236726708e-05, + "loss": 18.588, + "step": 1949 + }, + { + "epoch": 0.4531590413943355, + "grad_norm": 2.7031354904174805, + "learning_rate": 1.8342344083670097e-05, + "loss": 18.2624, + "step": 1950 + }, + { + "epoch": 0.4533914306463326, + "grad_norm": 2.5954105854034424, + "learning_rate": 1.834022469891028e-05, + "loss": 18.3602, + "step": 1951 + }, + { + "epoch": 0.4536238198983297, + "grad_norm": 2.971444845199585, + "learning_rate": 1.8338104082760168e-05, + "loss": 18.8785, + "step": 1952 + }, + { + "epoch": 0.4538562091503268, + "grad_norm": 2.5853588581085205, + "learning_rate": 1.8335982235532862e-05, + "loss": 17.7079, + "step": 1953 + }, + { + "epoch": 0.4540885984023239, + "grad_norm": 2.482562303543091, + "learning_rate": 1.8333859157541635e-05, + "loss": 18.7091, + "step": 1954 + }, + { + "epoch": 0.454320987654321, + "grad_norm": 2.9864745140075684, + "learning_rate": 1.8331734849099957e-05, + "loss": 18.4236, + "step": 1955 + }, + { + "epoch": 0.4545533769063181, + "grad_norm": 2.6079392433166504, + "learning_rate": 1.832960931052147e-05, + "loss": 18.7909, + "step": 1956 + }, + { + "epoch": 0.4547857661583152, + "grad_norm": 2.705084800720215, + "learning_rate": 1.8327482542119993e-05, + "loss": 18.2868, + "step": 1957 + }, + { + "epoch": 0.45501815541031226, + "grad_norm": 2.5154192447662354, + "learning_rate": 1.8325354544209534e-05, + "loss": 17.7071, + "step": 1958 + }, + { + "epoch": 0.45525054466230935, + "grad_norm": 2.6557092666625977, + "learning_rate": 1.8323225317104283e-05, + "loss": 18.396, + "step": 1959 + }, + { + "epoch": 0.45548293391430644, + "grad_norm": 2.664965867996216, + "learning_rate": 1.832109486111861e-05, + "loss": 17.9519, + "step": 1960 + }, + { + "epoch": 0.45571532316630353, + "grad_norm": 2.906787872314453, + "learning_rate": 1.831896317656706e-05, + "loss": 17.4006, + "step": 1961 + }, + { + "epoch": 0.4559477124183007, + "grad_norm": 2.993309736251831, + "learning_rate": 1.8316830263764372e-05, + "loss": 17.5329, + "step": 1962 + }, + { + "epoch": 0.45618010167029777, + "grad_norm": 2.8420746326446533, + "learning_rate": 1.8314696123025456e-05, + "loss": 18.6217, + "step": 1963 + }, + { + "epoch": 0.45641249092229486, + "grad_norm": 2.8350162506103516, + "learning_rate": 1.8312560754665402e-05, + "loss": 18.1693, + "step": 1964 + }, + { + "epoch": 0.45664488017429194, + "grad_norm": 2.7759478092193604, + "learning_rate": 1.8310424158999494e-05, + "loss": 17.8841, + "step": 1965 + }, + { + "epoch": 0.45687726942628903, + "grad_norm": 2.8410747051239014, + "learning_rate": 1.8308286336343187e-05, + "loss": 18.9804, + "step": 1966 + }, + { + "epoch": 0.4571096586782861, + "grad_norm": 2.639976739883423, + "learning_rate": 1.8306147287012116e-05, + "loss": 17.8477, + "step": 1967 + }, + { + "epoch": 0.4573420479302832, + "grad_norm": 2.6701533794403076, + "learning_rate": 1.8304007011322102e-05, + "loss": 17.4478, + "step": 1968 + }, + { + "epoch": 0.4575744371822803, + "grad_norm": 2.7040133476257324, + "learning_rate": 1.8301865509589145e-05, + "loss": 18.2275, + "step": 1969 + }, + { + "epoch": 0.4578068264342774, + "grad_norm": 2.6390140056610107, + "learning_rate": 1.8299722782129428e-05, + "loss": 19.3041, + "step": 1970 + }, + { + "epoch": 0.45803921568627454, + "grad_norm": 2.8994383811950684, + "learning_rate": 1.8297578829259315e-05, + "loss": 17.8209, + "step": 1971 + }, + { + "epoch": 0.4582716049382716, + "grad_norm": 2.72615909576416, + "learning_rate": 1.8295433651295344e-05, + "loss": 17.5367, + "step": 1972 + }, + { + "epoch": 0.4585039941902687, + "grad_norm": 2.5855941772460938, + "learning_rate": 1.8293287248554243e-05, + "loss": 19.017, + "step": 1973 + }, + { + "epoch": 0.4587363834422658, + "grad_norm": 2.6860601902008057, + "learning_rate": 1.8291139621352916e-05, + "loss": 18.0313, + "step": 1974 + }, + { + "epoch": 0.4589687726942629, + "grad_norm": 2.774320602416992, + "learning_rate": 1.828899077000845e-05, + "loss": 17.9628, + "step": 1975 + }, + { + "epoch": 0.45920116194626, + "grad_norm": 2.5355448722839355, + "learning_rate": 1.828684069483811e-05, + "loss": 18.0091, + "step": 1976 + }, + { + "epoch": 0.4594335511982571, + "grad_norm": 2.902353286743164, + "learning_rate": 1.8284689396159347e-05, + "loss": 17.5333, + "step": 1977 + }, + { + "epoch": 0.45966594045025416, + "grad_norm": 2.694568157196045, + "learning_rate": 1.828253687428978e-05, + "loss": 18.0322, + "step": 1978 + }, + { + "epoch": 0.45989832970225125, + "grad_norm": 2.642726421356201, + "learning_rate": 1.8280383129547227e-05, + "loss": 17.1842, + "step": 1979 + }, + { + "epoch": 0.46013071895424834, + "grad_norm": 2.805283784866333, + "learning_rate": 1.8278228162249677e-05, + "loss": 19.4129, + "step": 1980 + }, + { + "epoch": 0.4603631082062455, + "grad_norm": 2.6384499073028564, + "learning_rate": 1.827607197271529e-05, + "loss": 18.1316, + "step": 1981 + }, + { + "epoch": 0.4605954974582426, + "grad_norm": 7.491140365600586, + "learning_rate": 1.8273914561262425e-05, + "loss": 19.1247, + "step": 1982 + }, + { + "epoch": 0.46082788671023966, + "grad_norm": 2.8533003330230713, + "learning_rate": 1.827175592820961e-05, + "loss": 17.709, + "step": 1983 + }, + { + "epoch": 0.46106027596223675, + "grad_norm": 2.6934049129486084, + "learning_rate": 1.8269596073875555e-05, + "loss": 18.475, + "step": 1984 + }, + { + "epoch": 0.46129266521423384, + "grad_norm": 2.545699119567871, + "learning_rate": 1.8267434998579153e-05, + "loss": 16.8773, + "step": 1985 + }, + { + "epoch": 0.46152505446623093, + "grad_norm": 3.2463786602020264, + "learning_rate": 1.826527270263947e-05, + "loss": 17.9538, + "step": 1986 + }, + { + "epoch": 0.461757443718228, + "grad_norm": 2.580634593963623, + "learning_rate": 1.8263109186375762e-05, + "loss": 18.4547, + "step": 1987 + }, + { + "epoch": 0.4619898329702251, + "grad_norm": 2.6427128314971924, + "learning_rate": 1.8260944450107464e-05, + "loss": 18.6124, + "step": 1988 + }, + { + "epoch": 0.4622222222222222, + "grad_norm": 2.653930187225342, + "learning_rate": 1.8258778494154185e-05, + "loss": 18.2517, + "step": 1989 + }, + { + "epoch": 0.4624546114742193, + "grad_norm": 2.6679952144622803, + "learning_rate": 1.825661131883571e-05, + "loss": 18.4285, + "step": 1990 + }, + { + "epoch": 0.46268700072621644, + "grad_norm": 2.707772970199585, + "learning_rate": 1.8254442924472024e-05, + "loss": 17.8878, + "step": 1991 + }, + { + "epoch": 0.4629193899782135, + "grad_norm": 2.938368082046509, + "learning_rate": 1.8252273311383268e-05, + "loss": 17.4115, + "step": 1992 + }, + { + "epoch": 0.4631517792302106, + "grad_norm": 2.774916887283325, + "learning_rate": 1.825010247988978e-05, + "loss": 17.6986, + "step": 1993 + }, + { + "epoch": 0.4633841684822077, + "grad_norm": 2.646451473236084, + "learning_rate": 1.824793043031207e-05, + "loss": 18.4035, + "step": 1994 + }, + { + "epoch": 0.4636165577342048, + "grad_norm": 2.7206203937530518, + "learning_rate": 1.824575716297083e-05, + "loss": 17.9039, + "step": 1995 + }, + { + "epoch": 0.4638489469862019, + "grad_norm": 2.871112108230591, + "learning_rate": 1.8243582678186934e-05, + "loss": 18.7751, + "step": 1996 + }, + { + "epoch": 0.46408133623819897, + "grad_norm": 2.631702423095703, + "learning_rate": 1.8241406976281424e-05, + "loss": 18.2917, + "step": 1997 + }, + { + "epoch": 0.46431372549019606, + "grad_norm": 4.942800998687744, + "learning_rate": 1.8239230057575542e-05, + "loss": 18.592, + "step": 1998 + }, + { + "epoch": 0.46454611474219315, + "grad_norm": 2.755873203277588, + "learning_rate": 1.8237051922390695e-05, + "loss": 18.2608, + "step": 1999 + }, + { + "epoch": 0.4647785039941903, + "grad_norm": 2.4857287406921387, + "learning_rate": 1.823487257104847e-05, + "loss": 18.4212, + "step": 2000 + }, + { + "epoch": 0.4650108932461874, + "grad_norm": 2.800438165664673, + "learning_rate": 1.8232692003870643e-05, + "loss": 18.2952, + "step": 2001 + }, + { + "epoch": 0.4652432824981845, + "grad_norm": 2.704630136489868, + "learning_rate": 1.8230510221179156e-05, + "loss": 17.9363, + "step": 2002 + }, + { + "epoch": 0.46547567175018156, + "grad_norm": 2.6051011085510254, + "learning_rate": 1.822832722329614e-05, + "loss": 17.8196, + "step": 2003 + }, + { + "epoch": 0.46570806100217865, + "grad_norm": 7.121522426605225, + "learning_rate": 1.8226143010543906e-05, + "loss": 18.2183, + "step": 2004 + }, + { + "epoch": 0.46594045025417574, + "grad_norm": 2.8716158866882324, + "learning_rate": 1.822395758324494e-05, + "loss": 17.4795, + "step": 2005 + }, + { + "epoch": 0.46617283950617283, + "grad_norm": 2.7486207485198975, + "learning_rate": 1.8221770941721907e-05, + "loss": 17.449, + "step": 2006 + }, + { + "epoch": 0.4664052287581699, + "grad_norm": 2.53607177734375, + "learning_rate": 1.8219583086297656e-05, + "loss": 17.6957, + "step": 2007 + }, + { + "epoch": 0.466637618010167, + "grad_norm": 2.6456756591796875, + "learning_rate": 1.821739401729521e-05, + "loss": 17.278, + "step": 2008 + }, + { + "epoch": 0.4668700072621641, + "grad_norm": 2.6350581645965576, + "learning_rate": 1.8215203735037773e-05, + "loss": 18.3127, + "step": 2009 + }, + { + "epoch": 0.46710239651416124, + "grad_norm": 2.6291298866271973, + "learning_rate": 1.8213012239848735e-05, + "loss": 18.0024, + "step": 2010 + }, + { + "epoch": 0.46733478576615833, + "grad_norm": 2.6941285133361816, + "learning_rate": 1.821081953205165e-05, + "loss": 18.4918, + "step": 2011 + }, + { + "epoch": 0.4675671750181554, + "grad_norm": 2.587236166000366, + "learning_rate": 1.8208625611970268e-05, + "loss": 18.6728, + "step": 2012 + }, + { + "epoch": 0.4677995642701525, + "grad_norm": 2.7253835201263428, + "learning_rate": 1.82064304799285e-05, + "loss": 18.1474, + "step": 2013 + }, + { + "epoch": 0.4680319535221496, + "grad_norm": 3.000276803970337, + "learning_rate": 1.8204234136250454e-05, + "loss": 18.9516, + "step": 2014 + }, + { + "epoch": 0.4682643427741467, + "grad_norm": 2.760423183441162, + "learning_rate": 1.8202036581260407e-05, + "loss": 18.0962, + "step": 2015 + }, + { + "epoch": 0.4684967320261438, + "grad_norm": 2.60528302192688, + "learning_rate": 1.819983781528281e-05, + "loss": 17.8546, + "step": 2016 + }, + { + "epoch": 0.46872912127814087, + "grad_norm": 2.568103313446045, + "learning_rate": 1.819763783864231e-05, + "loss": 17.729, + "step": 2017 + }, + { + "epoch": 0.46896151053013796, + "grad_norm": 2.702641010284424, + "learning_rate": 1.8195436651663718e-05, + "loss": 18.1662, + "step": 2018 + }, + { + "epoch": 0.46919389978213505, + "grad_norm": 2.789153575897217, + "learning_rate": 1.819323425467202e-05, + "loss": 19.5739, + "step": 2019 + }, + { + "epoch": 0.4694262890341322, + "grad_norm": 2.6753711700439453, + "learning_rate": 1.8191030647992396e-05, + "loss": 17.0255, + "step": 2020 + }, + { + "epoch": 0.4696586782861293, + "grad_norm": 2.805243968963623, + "learning_rate": 1.81888258319502e-05, + "loss": 18.1501, + "step": 2021 + }, + { + "epoch": 0.4698910675381264, + "grad_norm": 2.771352767944336, + "learning_rate": 1.818661980687095e-05, + "loss": 16.7946, + "step": 2022 + }, + { + "epoch": 0.47012345679012346, + "grad_norm": 2.835704803466797, + "learning_rate": 1.8184412573080362e-05, + "loss": 18.1201, + "step": 2023 + }, + { + "epoch": 0.47035584604212055, + "grad_norm": 2.977607011795044, + "learning_rate": 1.8182204130904325e-05, + "loss": 18.9244, + "step": 2024 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 3.1755809783935547, + "learning_rate": 1.81799944806689e-05, + "loss": 17.4233, + "step": 2025 + }, + { + "epoch": 0.47082062454611473, + "grad_norm": 2.698629140853882, + "learning_rate": 1.8177783622700328e-05, + "loss": 17.8506, + "step": 2026 + }, + { + "epoch": 0.4710530137981118, + "grad_norm": 2.5977108478546143, + "learning_rate": 1.8175571557325033e-05, + "loss": 17.7977, + "step": 2027 + }, + { + "epoch": 0.4712854030501089, + "grad_norm": 2.600313186645508, + "learning_rate": 1.8173358284869614e-05, + "loss": 18.2907, + "step": 2028 + }, + { + "epoch": 0.47151779230210605, + "grad_norm": 2.8946712017059326, + "learning_rate": 1.817114380566085e-05, + "loss": 18.1691, + "step": 2029 + }, + { + "epoch": 0.47175018155410314, + "grad_norm": 2.8817384243011475, + "learning_rate": 1.8168928120025698e-05, + "loss": 18.3221, + "step": 2030 + }, + { + "epoch": 0.47198257080610023, + "grad_norm": 2.6879100799560547, + "learning_rate": 1.8166711228291293e-05, + "loss": 17.7929, + "step": 2031 + }, + { + "epoch": 0.4722149600580973, + "grad_norm": 2.8556084632873535, + "learning_rate": 1.8164493130784943e-05, + "loss": 18.7594, + "step": 2032 + }, + { + "epoch": 0.4724473493100944, + "grad_norm": 2.696258544921875, + "learning_rate": 1.8162273827834146e-05, + "loss": 19.1855, + "step": 2033 + }, + { + "epoch": 0.4726797385620915, + "grad_norm": 2.6293859481811523, + "learning_rate": 1.816005331976656e-05, + "loss": 18.1607, + "step": 2034 + }, + { + "epoch": 0.4729121278140886, + "grad_norm": 2.5121963024139404, + "learning_rate": 1.815783160691004e-05, + "loss": 18.4911, + "step": 2035 + }, + { + "epoch": 0.4731445170660857, + "grad_norm": 2.856426477432251, + "learning_rate": 1.8155608689592604e-05, + "loss": 18.1052, + "step": 2036 + }, + { + "epoch": 0.47337690631808277, + "grad_norm": 2.667649269104004, + "learning_rate": 1.8153384568142458e-05, + "loss": 18.0353, + "step": 2037 + }, + { + "epoch": 0.47360929557007986, + "grad_norm": 2.8098912239074707, + "learning_rate": 1.8151159242887983e-05, + "loss": 17.417, + "step": 2038 + }, + { + "epoch": 0.473841684822077, + "grad_norm": 2.7492566108703613, + "learning_rate": 1.8148932714157733e-05, + "loss": 19.0779, + "step": 2039 + }, + { + "epoch": 0.4740740740740741, + "grad_norm": 2.718379020690918, + "learning_rate": 1.8146704982280444e-05, + "loss": 18.7461, + "step": 2040 + }, + { + "epoch": 0.4743064633260712, + "grad_norm": 3.0294268131256104, + "learning_rate": 1.814447604758503e-05, + "loss": 18.6187, + "step": 2041 + }, + { + "epoch": 0.47453885257806827, + "grad_norm": 2.7106854915618896, + "learning_rate": 1.8142245910400583e-05, + "loss": 18.912, + "step": 2042 + }, + { + "epoch": 0.47477124183006536, + "grad_norm": 3.6196651458740234, + "learning_rate": 1.8140014571056366e-05, + "loss": 17.4031, + "step": 2043 + }, + { + "epoch": 0.47500363108206245, + "grad_norm": 2.763767957687378, + "learning_rate": 1.813778202988183e-05, + "loss": 18.0468, + "step": 2044 + }, + { + "epoch": 0.47523602033405954, + "grad_norm": 2.849088191986084, + "learning_rate": 1.8135548287206596e-05, + "loss": 18.1498, + "step": 2045 + }, + { + "epoch": 0.47546840958605663, + "grad_norm": 2.7737603187561035, + "learning_rate": 1.8133313343360462e-05, + "loss": 17.9774, + "step": 2046 + }, + { + "epoch": 0.4757007988380537, + "grad_norm": 2.5802247524261475, + "learning_rate": 1.8131077198673408e-05, + "loss": 18.6328, + "step": 2047 + }, + { + "epoch": 0.47593318809005086, + "grad_norm": 2.603492259979248, + "learning_rate": 1.812883985347559e-05, + "loss": 17.6434, + "step": 2048 + }, + { + "epoch": 0.47616557734204795, + "grad_norm": 2.8488054275512695, + "learning_rate": 1.8126601308097335e-05, + "loss": 18.5056, + "step": 2049 + }, + { + "epoch": 0.47639796659404504, + "grad_norm": 2.587865114212036, + "learning_rate": 1.812436156286916e-05, + "loss": 16.8736, + "step": 2050 + }, + { + "epoch": 0.47663035584604213, + "grad_norm": 2.7845852375030518, + "learning_rate": 1.812212061812175e-05, + "loss": 17.6799, + "step": 2051 + }, + { + "epoch": 0.4768627450980392, + "grad_norm": 2.7543160915374756, + "learning_rate": 1.8119878474185963e-05, + "loss": 17.5682, + "step": 2052 + }, + { + "epoch": 0.4770951343500363, + "grad_norm": 2.6557743549346924, + "learning_rate": 1.8117635131392845e-05, + "loss": 16.9991, + "step": 2053 + }, + { + "epoch": 0.4773275236020334, + "grad_norm": 2.757446527481079, + "learning_rate": 1.8115390590073612e-05, + "loss": 17.788, + "step": 2054 + }, + { + "epoch": 0.4775599128540305, + "grad_norm": 2.826930284500122, + "learning_rate": 1.811314485055966e-05, + "loss": 17.6676, + "step": 2055 + }, + { + "epoch": 0.4777923021060276, + "grad_norm": 2.828922986984253, + "learning_rate": 1.8110897913182556e-05, + "loss": 18.6916, + "step": 2056 + }, + { + "epoch": 0.47802469135802467, + "grad_norm": 2.6349294185638428, + "learning_rate": 1.8108649778274054e-05, + "loss": 18.2408, + "step": 2057 + }, + { + "epoch": 0.4782570806100218, + "grad_norm": 2.5968828201293945, + "learning_rate": 1.8106400446166077e-05, + "loss": 17.5951, + "step": 2058 + }, + { + "epoch": 0.4784894698620189, + "grad_norm": 2.6875524520874023, + "learning_rate": 1.810414991719073e-05, + "loss": 18.6045, + "step": 2059 + }, + { + "epoch": 0.478721859114016, + "grad_norm": 2.8593692779541016, + "learning_rate": 1.8101898191680285e-05, + "loss": 17.6201, + "step": 2060 + }, + { + "epoch": 0.4789542483660131, + "grad_norm": 2.7004926204681396, + "learning_rate": 1.8099645269967207e-05, + "loss": 18.8391, + "step": 2061 + }, + { + "epoch": 0.47918663761801017, + "grad_norm": 2.6227025985717773, + "learning_rate": 1.8097391152384117e-05, + "loss": 18.1177, + "step": 2062 + }, + { + "epoch": 0.47941902687000726, + "grad_norm": 2.7739593982696533, + "learning_rate": 1.809513583926383e-05, + "loss": 17.5317, + "step": 2063 + }, + { + "epoch": 0.47965141612200435, + "grad_norm": 2.7660632133483887, + "learning_rate": 1.8092879330939333e-05, + "loss": 17.6551, + "step": 2064 + }, + { + "epoch": 0.47988380537400144, + "grad_norm": 2.679807186126709, + "learning_rate": 1.809062162774378e-05, + "loss": 18.317, + "step": 2065 + }, + { + "epoch": 0.4801161946259985, + "grad_norm": 2.751734972000122, + "learning_rate": 1.8088362730010518e-05, + "loss": 17.9753, + "step": 2066 + }, + { + "epoch": 0.4803485838779956, + "grad_norm": 2.672069549560547, + "learning_rate": 1.8086102638073058e-05, + "loss": 18.2102, + "step": 2067 + }, + { + "epoch": 0.48058097312999276, + "grad_norm": 2.9070823192596436, + "learning_rate": 1.8083841352265085e-05, + "loss": 17.82, + "step": 2068 + }, + { + "epoch": 0.48081336238198985, + "grad_norm": 5.496854305267334, + "learning_rate": 1.8081578872920476e-05, + "loss": 18.1595, + "step": 2069 + }, + { + "epoch": 0.48104575163398694, + "grad_norm": 2.7550408840179443, + "learning_rate": 1.8079315200373266e-05, + "loss": 17.8158, + "step": 2070 + }, + { + "epoch": 0.48127814088598403, + "grad_norm": 2.6955904960632324, + "learning_rate": 1.807705033495768e-05, + "loss": 18.4845, + "step": 2071 + }, + { + "epoch": 0.4815105301379811, + "grad_norm": 2.6067776679992676, + "learning_rate": 1.8074784277008107e-05, + "loss": 17.7228, + "step": 2072 + }, + { + "epoch": 0.4817429193899782, + "grad_norm": 2.8138630390167236, + "learning_rate": 1.8072517026859127e-05, + "loss": 19.0205, + "step": 2073 + }, + { + "epoch": 0.4819753086419753, + "grad_norm": 2.70108699798584, + "learning_rate": 1.807024858484548e-05, + "loss": 18.5783, + "step": 2074 + }, + { + "epoch": 0.4822076978939724, + "grad_norm": 2.6634702682495117, + "learning_rate": 1.8067978951302093e-05, + "loss": 17.9581, + "step": 2075 + }, + { + "epoch": 0.4824400871459695, + "grad_norm": 4.988211631774902, + "learning_rate": 1.8065708126564064e-05, + "loss": 19.0835, + "step": 2076 + }, + { + "epoch": 0.4826724763979666, + "grad_norm": 2.575108528137207, + "learning_rate": 1.8063436110966672e-05, + "loss": 18.6995, + "step": 2077 + }, + { + "epoch": 0.4829048656499637, + "grad_norm": 3.3099422454833984, + "learning_rate": 1.806116290484536e-05, + "loss": 18.0511, + "step": 2078 + }, + { + "epoch": 0.4831372549019608, + "grad_norm": 2.8645849227905273, + "learning_rate": 1.8058888508535764e-05, + "loss": 19.5064, + "step": 2079 + }, + { + "epoch": 0.4833696441539579, + "grad_norm": 2.881154775619507, + "learning_rate": 1.8056612922373684e-05, + "loss": 18.2353, + "step": 2080 + }, + { + "epoch": 0.483602033405955, + "grad_norm": 2.715059757232666, + "learning_rate": 1.8054336146695094e-05, + "loss": 17.2756, + "step": 2081 + }, + { + "epoch": 0.48383442265795207, + "grad_norm": 2.6100614070892334, + "learning_rate": 1.8052058181836152e-05, + "loss": 18.3054, + "step": 2082 + }, + { + "epoch": 0.48406681190994916, + "grad_norm": 2.633958578109741, + "learning_rate": 1.804977902813319e-05, + "loss": 18.8909, + "step": 2083 + }, + { + "epoch": 0.48429920116194625, + "grad_norm": 2.671159029006958, + "learning_rate": 1.8047498685922708e-05, + "loss": 18.1971, + "step": 2084 + }, + { + "epoch": 0.48453159041394334, + "grad_norm": 2.8081891536712646, + "learning_rate": 1.8045217155541386e-05, + "loss": 18.2985, + "step": 2085 + }, + { + "epoch": 0.4847639796659404, + "grad_norm": 2.707839012145996, + "learning_rate": 1.8042934437326085e-05, + "loss": 17.6697, + "step": 2086 + }, + { + "epoch": 0.48499636891793757, + "grad_norm": 2.482354164123535, + "learning_rate": 1.804065053161383e-05, + "loss": 16.9608, + "step": 2087 + }, + { + "epoch": 0.48522875816993466, + "grad_norm": 2.769469738006592, + "learning_rate": 1.8038365438741838e-05, + "loss": 18.2152, + "step": 2088 + }, + { + "epoch": 0.48546114742193175, + "grad_norm": 2.7129385471343994, + "learning_rate": 1.8036079159047476e-05, + "loss": 16.7643, + "step": 2089 + }, + { + "epoch": 0.48569353667392884, + "grad_norm": 2.64201021194458, + "learning_rate": 1.8033791692868315e-05, + "loss": 18.0505, + "step": 2090 + }, + { + "epoch": 0.48592592592592593, + "grad_norm": 2.8513760566711426, + "learning_rate": 1.803150304054208e-05, + "loss": 18.3812, + "step": 2091 + }, + { + "epoch": 0.486158315177923, + "grad_norm": 2.7083656787872314, + "learning_rate": 1.802921320240668e-05, + "loss": 17.6797, + "step": 2092 + }, + { + "epoch": 0.4863907044299201, + "grad_norm": 2.9206225872039795, + "learning_rate": 1.80269221788002e-05, + "loss": 18.6444, + "step": 2093 + }, + { + "epoch": 0.4866230936819172, + "grad_norm": 2.729994773864746, + "learning_rate": 1.802462997006089e-05, + "loss": 19.9952, + "step": 2094 + }, + { + "epoch": 0.4868554829339143, + "grad_norm": 2.627027988433838, + "learning_rate": 1.8022336576527192e-05, + "loss": 18.1961, + "step": 2095 + }, + { + "epoch": 0.4870878721859114, + "grad_norm": 2.8679757118225098, + "learning_rate": 1.8020041998537708e-05, + "loss": 18.9078, + "step": 2096 + }, + { + "epoch": 0.4873202614379085, + "grad_norm": 2.6585121154785156, + "learning_rate": 1.8017746236431224e-05, + "loss": 18.0756, + "step": 2097 + }, + { + "epoch": 0.4875526506899056, + "grad_norm": 2.8065950870513916, + "learning_rate": 1.8015449290546695e-05, + "loss": 18.5, + "step": 2098 + }, + { + "epoch": 0.4877850399419027, + "grad_norm": 2.980757713317871, + "learning_rate": 1.801315116122325e-05, + "loss": 17.3705, + "step": 2099 + }, + { + "epoch": 0.4880174291938998, + "grad_norm": 2.6312546730041504, + "learning_rate": 1.80108518488002e-05, + "loss": 17.4613, + "step": 2100 + }, + { + "epoch": 0.4882498184458969, + "grad_norm": 2.886648178100586, + "learning_rate": 1.8008551353617023e-05, + "loss": 18.3412, + "step": 2101 + }, + { + "epoch": 0.48848220769789397, + "grad_norm": 2.7315986156463623, + "learning_rate": 1.8006249676013378e-05, + "loss": 18.4303, + "step": 2102 + }, + { + "epoch": 0.48871459694989106, + "grad_norm": 2.756695032119751, + "learning_rate": 1.8003946816329095e-05, + "loss": 17.8647, + "step": 2103 + }, + { + "epoch": 0.48894698620188815, + "grad_norm": 2.6471176147460938, + "learning_rate": 1.800164277490418e-05, + "loss": 18.5846, + "step": 2104 + }, + { + "epoch": 0.48917937545388523, + "grad_norm": 2.9293415546417236, + "learning_rate": 1.799933755207881e-05, + "loss": 18.1823, + "step": 2105 + }, + { + "epoch": 0.4894117647058824, + "grad_norm": 2.7203807830810547, + "learning_rate": 1.7997031148193343e-05, + "loss": 18.4241, + "step": 2106 + }, + { + "epoch": 0.48964415395787947, + "grad_norm": 2.5846431255340576, + "learning_rate": 1.7994723563588305e-05, + "loss": 18.03, + "step": 2107 + }, + { + "epoch": 0.48987654320987656, + "grad_norm": 2.854041337966919, + "learning_rate": 1.7992414798604393e-05, + "loss": 18.5809, + "step": 2108 + }, + { + "epoch": 0.49010893246187365, + "grad_norm": 2.7144815921783447, + "learning_rate": 1.7990104853582494e-05, + "loss": 17.5734, + "step": 2109 + }, + { + "epoch": 0.49034132171387074, + "grad_norm": 2.851343870162964, + "learning_rate": 1.798779372886365e-05, + "loss": 18.399, + "step": 2110 + }, + { + "epoch": 0.4905737109658678, + "grad_norm": 2.723722219467163, + "learning_rate": 1.7985481424789094e-05, + "loss": 17.759, + "step": 2111 + }, + { + "epoch": 0.4908061002178649, + "grad_norm": 2.7029874324798584, + "learning_rate": 1.798316794170022e-05, + "loss": 18.5179, + "step": 2112 + }, + { + "epoch": 0.491038489469862, + "grad_norm": 2.7589964866638184, + "learning_rate": 1.798085327993861e-05, + "loss": 18.84, + "step": 2113 + }, + { + "epoch": 0.4912708787218591, + "grad_norm": 2.8721683025360107, + "learning_rate": 1.7978537439846004e-05, + "loss": 18.553, + "step": 2114 + }, + { + "epoch": 0.4915032679738562, + "grad_norm": 2.9199161529541016, + "learning_rate": 1.7976220421764322e-05, + "loss": 19.0186, + "step": 2115 + }, + { + "epoch": 0.49173565722585333, + "grad_norm": 2.818902015686035, + "learning_rate": 1.7973902226035665e-05, + "loss": 17.4646, + "step": 2116 + }, + { + "epoch": 0.4919680464778504, + "grad_norm": 2.4862301349639893, + "learning_rate": 1.7971582853002303e-05, + "loss": 18.5072, + "step": 2117 + }, + { + "epoch": 0.4922004357298475, + "grad_norm": 2.7545325756073, + "learning_rate": 1.796926230300667e-05, + "loss": 17.9279, + "step": 2118 + }, + { + "epoch": 0.4924328249818446, + "grad_norm": 3.3738901615142822, + "learning_rate": 1.7966940576391394e-05, + "loss": 17.3117, + "step": 2119 + }, + { + "epoch": 0.4926652142338417, + "grad_norm": 2.9718384742736816, + "learning_rate": 1.796461767349926e-05, + "loss": 18.1931, + "step": 2120 + }, + { + "epoch": 0.4928976034858388, + "grad_norm": 2.6503396034240723, + "learning_rate": 1.7962293594673236e-05, + "loss": 17.6746, + "step": 2121 + }, + { + "epoch": 0.49312999273783586, + "grad_norm": 2.746389150619507, + "learning_rate": 1.795996834025646e-05, + "loss": 18.2984, + "step": 2122 + }, + { + "epoch": 0.49336238198983295, + "grad_norm": 2.603107213973999, + "learning_rate": 1.7957641910592234e-05, + "loss": 17.9531, + "step": 2123 + }, + { + "epoch": 0.49359477124183004, + "grad_norm": 2.6964290142059326, + "learning_rate": 1.7955314306024055e-05, + "loss": 17.9452, + "step": 2124 + }, + { + "epoch": 0.49382716049382713, + "grad_norm": 2.74261212348938, + "learning_rate": 1.7952985526895576e-05, + "loss": 17.7496, + "step": 2125 + }, + { + "epoch": 0.4940595497458243, + "grad_norm": 3.025585174560547, + "learning_rate": 1.795065557355063e-05, + "loss": 19.1719, + "step": 2126 + }, + { + "epoch": 0.49429193899782137, + "grad_norm": 2.889352560043335, + "learning_rate": 1.794832444633322e-05, + "loss": 17.4476, + "step": 2127 + }, + { + "epoch": 0.49452432824981846, + "grad_norm": 2.813096284866333, + "learning_rate": 1.794599214558753e-05, + "loss": 18.4258, + "step": 2128 + }, + { + "epoch": 0.49475671750181555, + "grad_norm": 2.9474117755889893, + "learning_rate": 1.794365867165791e-05, + "loss": 18.3029, + "step": 2129 + }, + { + "epoch": 0.49498910675381264, + "grad_norm": 2.580050468444824, + "learning_rate": 1.7941324024888884e-05, + "loss": 18.1977, + "step": 2130 + }, + { + "epoch": 0.4952214960058097, + "grad_norm": 2.6270110607147217, + "learning_rate": 1.7938988205625145e-05, + "loss": 17.9073, + "step": 2131 + }, + { + "epoch": 0.4954538852578068, + "grad_norm": 2.717113733291626, + "learning_rate": 1.7936651214211573e-05, + "loss": 18.1994, + "step": 2132 + }, + { + "epoch": 0.4956862745098039, + "grad_norm": 3.358515501022339, + "learning_rate": 1.793431305099321e-05, + "loss": 17.168, + "step": 2133 + }, + { + "epoch": 0.495918663761801, + "grad_norm": 2.7318615913391113, + "learning_rate": 1.7931973716315272e-05, + "loss": 18.1039, + "step": 2134 + }, + { + "epoch": 0.49615105301379814, + "grad_norm": 2.7842211723327637, + "learning_rate": 1.792963321052315e-05, + "loss": 18.9202, + "step": 2135 + }, + { + "epoch": 0.4963834422657952, + "grad_norm": 3.4922525882720947, + "learning_rate": 1.7927291533962406e-05, + "loss": 18.3232, + "step": 2136 + }, + { + "epoch": 0.4966158315177923, + "grad_norm": 2.701808214187622, + "learning_rate": 1.7924948686978784e-05, + "loss": 18.6876, + "step": 2137 + }, + { + "epoch": 0.4968482207697894, + "grad_norm": 2.9109604358673096, + "learning_rate": 1.792260466991818e-05, + "loss": 18.144, + "step": 2138 + }, + { + "epoch": 0.4970806100217865, + "grad_norm": 2.6406795978546143, + "learning_rate": 1.7920259483126688e-05, + "loss": 17.2686, + "step": 2139 + }, + { + "epoch": 0.4973129992737836, + "grad_norm": 2.61078143119812, + "learning_rate": 1.7917913126950553e-05, + "loss": 19.1234, + "step": 2140 + }, + { + "epoch": 0.4975453885257807, + "grad_norm": 2.732743501663208, + "learning_rate": 1.791556560173621e-05, + "loss": 19.0651, + "step": 2141 + }, + { + "epoch": 0.49777777777777776, + "grad_norm": 2.8862452507019043, + "learning_rate": 1.7913216907830252e-05, + "loss": 18.4747, + "step": 2142 + }, + { + "epoch": 0.49801016702977485, + "grad_norm": 2.712170124053955, + "learning_rate": 1.7910867045579454e-05, + "loss": 17.8576, + "step": 2143 + }, + { + "epoch": 0.49824255628177194, + "grad_norm": 2.574406385421753, + "learning_rate": 1.790851601533076e-05, + "loss": 17.6334, + "step": 2144 + }, + { + "epoch": 0.4984749455337691, + "grad_norm": 2.6642630100250244, + "learning_rate": 1.7906163817431294e-05, + "loss": 17.6602, + "step": 2145 + }, + { + "epoch": 0.4987073347857662, + "grad_norm": 2.7368922233581543, + "learning_rate": 1.7903810452228333e-05, + "loss": 18.1224, + "step": 2146 + }, + { + "epoch": 0.49893972403776327, + "grad_norm": 2.555699586868286, + "learning_rate": 1.790145592006935e-05, + "loss": 17.8479, + "step": 2147 + }, + { + "epoch": 0.49917211328976036, + "grad_norm": 2.7129018306732178, + "learning_rate": 1.7899100221301973e-05, + "loss": 18.6961, + "step": 2148 + }, + { + "epoch": 0.49940450254175744, + "grad_norm": 2.771254539489746, + "learning_rate": 1.7896743356274013e-05, + "loss": 17.9719, + "step": 2149 + }, + { + "epoch": 0.49963689179375453, + "grad_norm": 2.9509992599487305, + "learning_rate": 1.7894385325333447e-05, + "loss": 17.8225, + "step": 2150 + }, + { + "epoch": 0.4998692810457516, + "grad_norm": 2.51737380027771, + "learning_rate": 1.7892026128828424e-05, + "loss": 18.2968, + "step": 2151 + }, + { + "epoch": 0.5001016702977488, + "grad_norm": 2.8937084674835205, + "learning_rate": 1.7889665767107267e-05, + "loss": 18.5819, + "step": 2152 + }, + { + "epoch": 0.5001016702977488, + "eval_loss": 2.2998576164245605, + "eval_runtime": 2067.2234, + "eval_samples_per_second": 0.536, + "eval_steps_per_second": 0.536, + "step": 2152 + } + ], + "logging_steps": 1, + "max_steps": 8606, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 2152, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.989196921207521e+18, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +}