| { | |
| "best_metric": 0.5695301294326782, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.7017543859649122, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007017543859649123, | |
| "grad_norm": 2.7762348651885986, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3903, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007017543859649123, | |
| "eval_loss": 0.9683788418769836, | |
| "eval_runtime": 17.6946, | |
| "eval_samples_per_second": 13.563, | |
| "eval_steps_per_second": 3.391, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014035087719298246, | |
| "grad_norm": 2.8924126625061035, | |
| "learning_rate": 2e-05, | |
| "loss": 2.356, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.021052631578947368, | |
| "grad_norm": 3.4745891094207764, | |
| "learning_rate": 3e-05, | |
| "loss": 2.5984, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": 3.46642804145813, | |
| "learning_rate": 4e-05, | |
| "loss": 2.4721, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 2.7118122577667236, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8837, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.042105263157894736, | |
| "grad_norm": 1.8579764366149902, | |
| "learning_rate": 6e-05, | |
| "loss": 2.2862, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04912280701754386, | |
| "grad_norm": 1.3937697410583496, | |
| "learning_rate": 7e-05, | |
| "loss": 2.1112, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 1.0277411937713623, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5434, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06315789473684211, | |
| "grad_norm": 1.0102975368499756, | |
| "learning_rate": 9e-05, | |
| "loss": 2.4365, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 1.0124120712280273, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07719298245614035, | |
| "grad_norm": 1.0789661407470703, | |
| "learning_rate": 9.998605186060137e-05, | |
| "loss": 2.4538, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08421052631578947, | |
| "grad_norm": 1.1773967742919922, | |
| "learning_rate": 9.99442152244292e-05, | |
| "loss": 2.5744, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0912280701754386, | |
| "grad_norm": 1.0121546983718872, | |
| "learning_rate": 9.987451343321279e-05, | |
| "loss": 2.4692, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09824561403508772, | |
| "grad_norm": 1.3383002281188965, | |
| "learning_rate": 9.977698537536419e-05, | |
| "loss": 2.9323, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 1.177334189414978, | |
| "learning_rate": 9.965168546428121e-05, | |
| "loss": 2.2799, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 0.9295145869255066, | |
| "learning_rate": 9.949868360798893e-05, | |
| "loss": 2.3713, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11929824561403508, | |
| "grad_norm": 0.9561142921447754, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 2.615, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12631578947368421, | |
| "grad_norm": 0.9804189801216125, | |
| "learning_rate": 9.910993092236878e-05, | |
| "loss": 2.6586, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 1.0032782554626465, | |
| "learning_rate": 9.887439698810693e-05, | |
| "loss": 2.6251, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 1.1459952592849731, | |
| "learning_rate": 9.861159477775653e-05, | |
| "loss": 2.6155, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14736842105263157, | |
| "grad_norm": 0.9445633292198181, | |
| "learning_rate": 9.832167091539214e-05, | |
| "loss": 2.5463, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1543859649122807, | |
| "grad_norm": 0.9772726893424988, | |
| "learning_rate": 9.800478715695163e-05, | |
| "loss": 2.4464, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16140350877192983, | |
| "grad_norm": 0.8855580687522888, | |
| "learning_rate": 9.766112029998846e-05, | |
| "loss": 2.4683, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 1.0070710182189941, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 2.8086, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 1.0289078950881958, | |
| "learning_rate": 9.689421908860927e-05, | |
| "loss": 2.7138, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1824561403508772, | |
| "grad_norm": 1.0180659294128418, | |
| "learning_rate": 9.64714126079933e-05, | |
| "loss": 2.6071, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18947368421052632, | |
| "grad_norm": 0.9560624957084656, | |
| "learning_rate": 9.602267853773301e-05, | |
| "loss": 2.3464, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19649122807017544, | |
| "grad_norm": 1.3721864223480225, | |
| "learning_rate": 9.554826723804303e-05, | |
| "loss": 2.6763, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20350877192982456, | |
| "grad_norm": 1.3725249767303467, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 2.8626, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 1.265424132347107, | |
| "learning_rate": 9.452348587347224e-05, | |
| "loss": 2.502, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21754385964912282, | |
| "grad_norm": 1.2181262969970703, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 2.3714, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22456140350877193, | |
| "grad_norm": 1.321036458015442, | |
| "learning_rate": 9.339935520221816e-05, | |
| "loss": 2.2873, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23157894736842105, | |
| "grad_norm": 1.5463135242462158, | |
| "learning_rate": 9.280080923386501e-05, | |
| "loss": 2.3626, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23859649122807017, | |
| "grad_norm": 1.3238377571105957, | |
| "learning_rate": 9.217838359936914e-05, | |
| "loss": 2.2543, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 2.2101263999938965, | |
| "learning_rate": 9.153242556591116e-05, | |
| "loss": 1.8211, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25263157894736843, | |
| "grad_norm": 0.9670763611793518, | |
| "learning_rate": 9.086329552999891e-05, | |
| "loss": 2.0042, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2596491228070175, | |
| "grad_norm": 0.7848258018493652, | |
| "learning_rate": 9.017136681639307e-05, | |
| "loss": 1.7858, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.729593813419342, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.1785, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2736842105263158, | |
| "grad_norm": 0.6895172595977783, | |
| "learning_rate": 8.872067003958598e-05, | |
| "loss": 2.3695, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.8260446786880493, | |
| "learning_rate": 8.796271135721944e-05, | |
| "loss": 1.9042, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28771929824561404, | |
| "grad_norm": 1.0478273630142212, | |
| "learning_rate": 8.718357230725449e-05, | |
| "loss": 1.8239, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.29473684210526313, | |
| "grad_norm": 0.6120851039886475, | |
| "learning_rate": 8.638368759129432e-05, | |
| "loss": 2.078, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3017543859649123, | |
| "grad_norm": 0.7053998708724976, | |
| "learning_rate": 8.556350348547977e-05, | |
| "loss": 2.2686, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3087719298245614, | |
| "grad_norm": 0.6118577718734741, | |
| "learning_rate": 8.472347759150043e-05, | |
| "loss": 1.9846, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.6109419465065002, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.9423, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32280701754385965, | |
| "grad_norm": 0.6774243712425232, | |
| "learning_rate": 8.298578593552737e-05, | |
| "loss": 2.6628, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3298245614035088, | |
| "grad_norm": 0.7050437331199646, | |
| "learning_rate": 8.208908967615159e-05, | |
| "loss": 2.2159, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.8880307674407959, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 2.0407, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.34385964912280703, | |
| "grad_norm": 0.789176344871521, | |
| "learning_rate": 8.024249746438188e-05, | |
| "loss": 2.3735, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 1.0776917934417725, | |
| "learning_rate": 7.929363177301124e-05, | |
| "loss": 2.1694, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "eval_loss": 0.5783611536026001, | |
| "eval_runtime": 17.9725, | |
| "eval_samples_per_second": 13.354, | |
| "eval_steps_per_second": 3.338, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35789473684210527, | |
| "grad_norm": 0.8510519862174988, | |
| "learning_rate": 7.832842241526212e-05, | |
| "loss": 2.4368, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3649122807017544, | |
| "grad_norm": 0.7064984440803528, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 2.2657, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.3719298245614035, | |
| "grad_norm": 0.7655551433563232, | |
| "learning_rate": 7.635113557867395e-05, | |
| "loss": 2.2036, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.37894736842105264, | |
| "grad_norm": 0.7803980708122253, | |
| "learning_rate": 7.534016127873201e-05, | |
| "loss": 2.4267, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 0.7970924377441406, | |
| "learning_rate": 7.431504905471408e-05, | |
| "loss": 2.5336, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3929824561403509, | |
| "grad_norm": 0.7999897003173828, | |
| "learning_rate": 7.327637084294817e-05, | |
| "loss": 2.6374, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.8058353662490845, | |
| "learning_rate": 7.22247061485738e-05, | |
| "loss": 2.6301, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4070175438596491, | |
| "grad_norm": 0.8530853986740112, | |
| "learning_rate": 7.116064172222125e-05, | |
| "loss": 2.6473, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.41403508771929826, | |
| "grad_norm": 0.9347732067108154, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 2.7603, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.8796826004981995, | |
| "learning_rate": 6.8997694935518e-05, | |
| "loss": 2.4875, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4280701754385965, | |
| "grad_norm": 0.9310798048973083, | |
| "learning_rate": 6.790001933849899e-05, | |
| "loss": 2.4794, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.43508771929824563, | |
| "grad_norm": 0.9056044816970825, | |
| "learning_rate": 6.679235686288114e-05, | |
| "loss": 2.5706, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4421052631578947, | |
| "grad_norm": 0.9717352986335754, | |
| "learning_rate": 6.567532550188907e-05, | |
| "loss": 2.3916, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.44912280701754387, | |
| "grad_norm": 1.0113260746002197, | |
| "learning_rate": 6.454954847588824e-05, | |
| "loss": 2.5943, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 1.1161454916000366, | |
| "learning_rate": 6.341565388467425e-05, | |
| "loss": 2.4713, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4631578947368421, | |
| "grad_norm": 1.0935138463974, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 2.4408, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.47017543859649125, | |
| "grad_norm": 1.1171753406524658, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 2.594, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.47719298245614034, | |
| "grad_norm": 1.2532185316085815, | |
| "learning_rate": 5.997161153257963e-05, | |
| "loss": 2.6315, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4842105263157895, | |
| "grad_norm": 1.1737571954727173, | |
| "learning_rate": 5.8811612950236096e-05, | |
| "loss": 2.3575, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 1.5828299522399902, | |
| "learning_rate": 5.76466981436623e-05, | |
| "loss": 2.3481, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4982456140350877, | |
| "grad_norm": 0.5896500945091248, | |
| "learning_rate": 5.647751704862263e-05, | |
| "loss": 1.786, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.6132327914237976, | |
| "learning_rate": 5.5304721981152906e-05, | |
| "loss": 1.6966, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.512280701754386, | |
| "grad_norm": 0.6747874021530151, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 2.312, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.519298245614035, | |
| "grad_norm": 0.7108948826789856, | |
| "learning_rate": 5.2950908909636146e-05, | |
| "loss": 2.0016, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.6152532696723938, | |
| "learning_rate": 5.1771204158102705e-05, | |
| "loss": 1.712, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.6101934313774109, | |
| "learning_rate": 5.059051120646924e-05, | |
| "loss": 2.1353, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.5403508771929825, | |
| "grad_norm": 0.5694242715835571, | |
| "learning_rate": 4.940948879353078e-05, | |
| "loss": 2.2486, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5473684210526316, | |
| "grad_norm": 0.5999569892883301, | |
| "learning_rate": 4.822879584189731e-05, | |
| "loss": 1.9464, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5543859649122806, | |
| "grad_norm": 0.5646923184394836, | |
| "learning_rate": 4.7049091090363865e-05, | |
| "loss": 2.1126, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.6812761425971985, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 2.0419, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5684210526315789, | |
| "grad_norm": 0.6502499580383301, | |
| "learning_rate": 4.4695278018847105e-05, | |
| "loss": 2.0716, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5754385964912281, | |
| "grad_norm": 0.5896376967430115, | |
| "learning_rate": 4.352248295137739e-05, | |
| "loss": 1.9859, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5824561403508772, | |
| "grad_norm": 0.6512247323989868, | |
| "learning_rate": 4.23533018563377e-05, | |
| "loss": 2.3233, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5894736842105263, | |
| "grad_norm": 0.6478447318077087, | |
| "learning_rate": 4.118838704976392e-05, | |
| "loss": 2.0947, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.7491245865821838, | |
| "learning_rate": 4.0028388467420385e-05, | |
| "loss": 2.4953, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6035087719298246, | |
| "grad_norm": 0.7526668310165405, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 2.4461, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.6105263157894737, | |
| "grad_norm": 0.6946207880973816, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 2.4925, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6175438596491228, | |
| "grad_norm": 0.7764760851860046, | |
| "learning_rate": 3.658434611532578e-05, | |
| "loss": 2.4452, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.624561403508772, | |
| "grad_norm": 0.7967379093170166, | |
| "learning_rate": 3.5450451524111775e-05, | |
| "loss": 2.5828, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.8338074684143066, | |
| "learning_rate": 3.4324674498110954e-05, | |
| "loss": 2.3247, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6385964912280702, | |
| "grad_norm": 0.7553719282150269, | |
| "learning_rate": 3.3207643137118874e-05, | |
| "loss": 2.4807, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6456140350877193, | |
| "grad_norm": 0.811700165271759, | |
| "learning_rate": 3.209998066150102e-05, | |
| "loss": 2.4316, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.6526315789473685, | |
| "grad_norm": 0.8489969968795776, | |
| "learning_rate": 3.100230506448201e-05, | |
| "loss": 2.2822, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6596491228070176, | |
| "grad_norm": 0.8480799198150635, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 2.549, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.8709715604782104, | |
| "learning_rate": 2.8839358277778755e-05, | |
| "loss": 2.7395, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.892209529876709, | |
| "learning_rate": 2.7775293851426232e-05, | |
| "loss": 2.3252, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.6807017543859649, | |
| "grad_norm": 0.8704090118408203, | |
| "learning_rate": 2.6723629157051844e-05, | |
| "loss": 2.5855, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6877192982456141, | |
| "grad_norm": 1.0494251251220703, | |
| "learning_rate": 2.5684950945285935e-05, | |
| "loss": 2.4473, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6947368421052632, | |
| "grad_norm": 0.9874880909919739, | |
| "learning_rate": 2.4659838721268004e-05, | |
| "loss": 2.5214, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 1.0498487949371338, | |
| "learning_rate": 2.364886442132606e-05, | |
| "loss": 2.4562, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "eval_loss": 0.5695301294326782, | |
| "eval_runtime": 17.7268, | |
| "eval_samples_per_second": 13.539, | |
| "eval_steps_per_second": 3.385, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 143, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.761096106573824e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |