| { | |
| "best_metric": 0.34307238459587097, | |
| "best_model_checkpoint": "autotrain-ht4es-gbvmt/checkpoint-3000", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 7.62260103225708, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.7053, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 9.429513931274414, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.7098, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 5.347685813903809, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.597, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 5.363152503967285, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.6223, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 9.079790115356445, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.6182, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 6.9367547035217285, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6298, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.175, | |
| "grad_norm": 4.488036632537842, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.582, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 6.229537487030029, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5998, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.225, | |
| "grad_norm": 14.98177433013916, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.6034, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 8.947093963623047, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5486, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.275, | |
| "grad_norm": 5.548841953277588, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.5592, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 6.519041538238525, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4745, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.325, | |
| "grad_norm": 6.388887405395508, | |
| "learning_rate": 4.9537037037037035e-05, | |
| "loss": 0.6121, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 4.3396315574646, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.5122, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 12.209185600280762, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.5585, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 6.66325044631958, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.6133, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.425, | |
| "grad_norm": 7.374906063079834, | |
| "learning_rate": 4.768518518518519e-05, | |
| "loss": 0.5779, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 6.596988677978516, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.58, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.475, | |
| "grad_norm": 8.377278327941895, | |
| "learning_rate": 4.675925925925926e-05, | |
| "loss": 0.4981, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 7.247930526733398, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.6069, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.525, | |
| "grad_norm": 6.867646217346191, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.6142, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 5.440280437469482, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.5109, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.575, | |
| "grad_norm": 8.325813293457031, | |
| "learning_rate": 4.490740740740741e-05, | |
| "loss": 0.5326, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 8.603256225585938, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5622, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 10.510509490966797, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.675, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 7.54085636138916, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.5269, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.675, | |
| "grad_norm": 25.22871971130371, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.5974, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 7.171282768249512, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.5236, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.725, | |
| "grad_norm": 5.170557022094727, | |
| "learning_rate": 4.212962962962963e-05, | |
| "loss": 0.4763, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 4.286471843719482, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5664, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.775, | |
| "grad_norm": 7.5836286544799805, | |
| "learning_rate": 4.1203703703703705e-05, | |
| "loss": 0.5413, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 7.180052757263184, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.5323, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.825, | |
| "grad_norm": 8.674583435058594, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.5381, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 5.117196559906006, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.5539, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 6.353272914886475, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.4588, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 5.968225002288818, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.5228, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.925, | |
| "grad_norm": 17.49488639831543, | |
| "learning_rate": 3.8425925925925924e-05, | |
| "loss": 0.4842, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 5.153933048248291, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.4993, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.975, | |
| "grad_norm": 7.89682149887085, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.5157, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.91286039352417, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5277, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.787, | |
| "eval_auc": 0.8603820000000001, | |
| "eval_f1": 0.7905604719764012, | |
| "eval_loss": 0.4363800287246704, | |
| "eval_precision": 0.7775628626692457, | |
| "eval_recall": 0.804, | |
| "eval_runtime": 663.7473, | |
| "eval_samples_per_second": 3.013, | |
| "eval_steps_per_second": 0.188, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.025, | |
| "grad_norm": 24.21603775024414, | |
| "learning_rate": 3.6574074074074076e-05, | |
| "loss": 0.487, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "grad_norm": 11.67587947845459, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.4983, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.075, | |
| "grad_norm": 9.920230865478516, | |
| "learning_rate": 3.564814814814815e-05, | |
| "loss": 0.5016, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 6.970316410064697, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.4673, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 7.130370616912842, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3898, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 9.946027755737305, | |
| "learning_rate": 3.425925925925926e-05, | |
| "loss": 0.4404, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.175, | |
| "grad_norm": 1.6654151678085327, | |
| "learning_rate": 3.3796296296296295e-05, | |
| "loss": 0.4961, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 5.618824481964111, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4828, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.225, | |
| "grad_norm": 7.5699334144592285, | |
| "learning_rate": 3.2870370370370375e-05, | |
| "loss": 0.4093, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 7.351467609405518, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.4939, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.275, | |
| "grad_norm": 6.4059648513793945, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.3547, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 4.268542289733887, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.3945, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.325, | |
| "grad_norm": 4.965268611907959, | |
| "learning_rate": 3.101851851851852e-05, | |
| "loss": 0.3791, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "grad_norm": 9.438615798950195, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.3727, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 6.795106410980225, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.4429, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 6.984402656555176, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.4231, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.425, | |
| "grad_norm": 4.931349277496338, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.4342, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "grad_norm": 5.537110805511475, | |
| "learning_rate": 2.8703703703703706e-05, | |
| "loss": 0.4478, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.475, | |
| "grad_norm": 4.687628269195557, | |
| "learning_rate": 2.824074074074074e-05, | |
| "loss": 0.3871, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 5.930976390838623, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4005, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.525, | |
| "grad_norm": 9.062422752380371, | |
| "learning_rate": 2.7314814814814816e-05, | |
| "loss": 0.4503, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "grad_norm": 5.416477203369141, | |
| "learning_rate": 2.6851851851851855e-05, | |
| "loss": 0.4317, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.575, | |
| "grad_norm": 14.157992362976074, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.382, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 4.8775177001953125, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.4017, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 5.229184150695801, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.5269, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 10.698781967163086, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4021, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.675, | |
| "grad_norm": 4.068216800689697, | |
| "learning_rate": 2.4537037037037038e-05, | |
| "loss": 0.3971, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 9.067376136779785, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.434, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.725, | |
| "grad_norm": 5.414083957672119, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.4614, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 9.188199043273926, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.4149, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.775, | |
| "grad_norm": 6.829360008239746, | |
| "learning_rate": 2.2685185185185187e-05, | |
| "loss": 0.4274, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 5.337634563446045, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.3448, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.825, | |
| "grad_norm": 7.2519850730896, | |
| "learning_rate": 2.175925925925926e-05, | |
| "loss": 0.4263, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "grad_norm": 5.725991725921631, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 0.4307, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 5.500362396240234, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.3874, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 7.834714412689209, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.3281, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.925, | |
| "grad_norm": 10.548686981201172, | |
| "learning_rate": 1.990740740740741e-05, | |
| "loss": 0.4047, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "grad_norm": 8.157145500183105, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.4335, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.975, | |
| "grad_norm": 9.798107147216797, | |
| "learning_rate": 1.8981481481481482e-05, | |
| "loss": 0.41, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 10.720842361450195, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4131, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.826, | |
| "eval_auc": 0.9061560000000001, | |
| "eval_f1": 0.84051329055912, | |
| "eval_loss": 0.3920663595199585, | |
| "eval_precision": 0.7758037225042301, | |
| "eval_recall": 0.917, | |
| "eval_runtime": 518.777, | |
| "eval_samples_per_second": 3.855, | |
| "eval_steps_per_second": 0.241, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.025, | |
| "grad_norm": 2.1612956523895264, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.2708, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "grad_norm": 16.25421714782715, | |
| "learning_rate": 1.7592592592592595e-05, | |
| "loss": 0.4438, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.075, | |
| "grad_norm": 22.16561508178711, | |
| "learning_rate": 1.712962962962963e-05, | |
| "loss": 0.2589, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "grad_norm": 13.343395233154297, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.3357, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 8.876195907592773, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.3356, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 7.499932765960693, | |
| "learning_rate": 1.574074074074074e-05, | |
| "loss": 0.3052, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.175, | |
| "grad_norm": 3.757966995239258, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.2836, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 10.760390281677246, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.2933, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.225, | |
| "grad_norm": 8.144658088684082, | |
| "learning_rate": 1.4351851851851853e-05, | |
| "loss": 0.3104, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 7.362667083740234, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.2983, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.275, | |
| "grad_norm": 4.645088195800781, | |
| "learning_rate": 1.3425925925925928e-05, | |
| "loss": 0.3655, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "grad_norm": 1.1926023960113525, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.2441, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.325, | |
| "grad_norm": 13.049036979675293, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.215, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "grad_norm": 9.891176223754883, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 0.3903, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.375, | |
| "grad_norm": 5.911032199859619, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.2469, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 10.652032852172852, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3542, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.425, | |
| "grad_norm": 5.722354888916016, | |
| "learning_rate": 1.0648148148148148e-05, | |
| "loss": 0.2719, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "grad_norm": 7.493654727935791, | |
| "learning_rate": 1.0185185185185185e-05, | |
| "loss": 0.3102, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.475, | |
| "grad_norm": 7.553443908691406, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.2539, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 3.0468859672546387, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.3312, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.525, | |
| "grad_norm": 9.9094820022583, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.3174, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "grad_norm": 3.5765790939331055, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.3598, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.575, | |
| "grad_norm": 6.845639228820801, | |
| "learning_rate": 7.87037037037037e-06, | |
| "loss": 0.2898, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "grad_norm": 6.846150875091553, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.2469, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.625, | |
| "grad_norm": 10.330842018127441, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.4315, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "grad_norm": 6.001290321350098, | |
| "learning_rate": 6.481481481481481e-06, | |
| "loss": 0.4615, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.675, | |
| "grad_norm": 4.979047775268555, | |
| "learning_rate": 6.0185185185185185e-06, | |
| "loss": 0.358, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "grad_norm": 5.183391094207764, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.3412, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.725, | |
| "grad_norm": 7.089044094085693, | |
| "learning_rate": 5.092592592592592e-06, | |
| "loss": 0.297, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 11.442684173583984, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.2933, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.775, | |
| "grad_norm": 4.924402713775635, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.3735, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 12.057656288146973, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2839, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.825, | |
| "grad_norm": 9.038887977600098, | |
| "learning_rate": 3.2407407407407406e-06, | |
| "loss": 0.2204, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "grad_norm": 3.07694673538208, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.33, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "grad_norm": 1.35588800907135, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.2462, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "grad_norm": 10.075614929199219, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.2932, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.925, | |
| "grad_norm": 5.351684093475342, | |
| "learning_rate": 1.388888888888889e-06, | |
| "loss": 0.2768, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "grad_norm": 11.825695037841797, | |
| "learning_rate": 9.259259259259259e-07, | |
| "loss": 0.2972, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.975, | |
| "grad_norm": 14.367501258850098, | |
| "learning_rate": 4.6296296296296297e-07, | |
| "loss": 0.2454, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 5.5341925621032715, | |
| "learning_rate": 0.0, | |
| "loss": 0.2264, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8655, | |
| "eval_auc": 0.9263070000000001, | |
| "eval_f1": 0.8702363724071394, | |
| "eval_loss": 0.34307238459587097, | |
| "eval_precision": 0.8406337371854613, | |
| "eval_recall": 0.902, | |
| "eval_runtime": 560.0101, | |
| "eval_samples_per_second": 3.571, | |
| "eval_steps_per_second": 0.223, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 3000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.859807750750208e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |