| { | |
| "best_metric": 0.2574561536312103, | |
| "best_model_checkpoint": "prostate-mri-T2w-v03/checkpoint-528", | |
| "epoch": 33.0, | |
| "eval_steps": 500, | |
| "global_step": 528, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 110.21771240234375, | |
| "learning_rate": 6.25e-07, | |
| "loss": 0.6921, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 39.45058822631836, | |
| "learning_rate": 1.25e-06, | |
| "loss": 0.6934, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1875, | |
| "grad_norm": 25.318283081054688, | |
| "learning_rate": 1.875e-06, | |
| "loss": 0.6819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 60.688926696777344, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.6904, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 61.651947021484375, | |
| "learning_rate": 3.125e-06, | |
| "loss": 0.6924, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 114.38175201416016, | |
| "learning_rate": 3.75e-06, | |
| "loss": 0.6997, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4375, | |
| "grad_norm": 129.98809814453125, | |
| "learning_rate": 4.375e-06, | |
| "loss": 0.6907, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 27.817869186401367, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6943, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5625, | |
| "grad_norm": 30.465864181518555, | |
| "learning_rate": 5.625e-06, | |
| "loss": 0.7056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 85.87218475341797, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.6987, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6875, | |
| "grad_norm": 126.83247375488281, | |
| "learning_rate": 6.875000000000001e-06, | |
| "loss": 0.7019, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 55.31666564941406, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.6875, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8125, | |
| "grad_norm": 76.3473129272461, | |
| "learning_rate": 8.125000000000001e-06, | |
| "loss": 0.6877, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.875, | |
| "grad_norm": 61.97464370727539, | |
| "learning_rate": 8.75e-06, | |
| "loss": 0.6907, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 72.70734405517578, | |
| "learning_rate": 9.375000000000001e-06, | |
| "loss": 0.6963, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 187.76124572753906, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6849, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.4838709677419355, | |
| "eval_auc": 0.39548319327731096, | |
| "eval_f1": 0.6444444444444445, | |
| "eval_loss": 0.6953126192092896, | |
| "eval_precision": 0.5178571428571429, | |
| "eval_recall": 0.8529411764705882, | |
| "eval_runtime": 1.8981, | |
| "eval_samples_per_second": 32.665, | |
| "eval_steps_per_second": 1.054, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0625, | |
| "grad_norm": 64.36949920654297, | |
| "learning_rate": 1.0625e-05, | |
| "loss": 0.6953, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.125, | |
| "grad_norm": 100.7771987915039, | |
| "learning_rate": 1.125e-05, | |
| "loss": 0.6824, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1875, | |
| "grad_norm": 85.3595962524414, | |
| "learning_rate": 1.1875e-05, | |
| "loss": 0.6865, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 63.85357666015625, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.6899, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3125, | |
| "grad_norm": 41.52039337158203, | |
| "learning_rate": 1.3125e-05, | |
| "loss": 0.697, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.375, | |
| "grad_norm": 46.41688537597656, | |
| "learning_rate": 1.3750000000000002e-05, | |
| "loss": 0.6851, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4375, | |
| "grad_norm": 48.81169128417969, | |
| "learning_rate": 1.4374999999999999e-05, | |
| "loss": 0.6919, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 44.77475357055664, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.6873, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5625, | |
| "grad_norm": 152.93743896484375, | |
| "learning_rate": 1.5625e-05, | |
| "loss": 0.6997, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.625, | |
| "grad_norm": 56.11520767211914, | |
| "learning_rate": 1.6250000000000002e-05, | |
| "loss": 0.6973, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.6875, | |
| "grad_norm": 224.677734375, | |
| "learning_rate": 1.6875000000000004e-05, | |
| "loss": 0.6912, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 48.88201904296875, | |
| "learning_rate": 1.75e-05, | |
| "loss": 0.6946, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8125, | |
| "grad_norm": 69.78736877441406, | |
| "learning_rate": 1.8125e-05, | |
| "loss": 0.6838, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 94.947021484375, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.7002, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9375, | |
| "grad_norm": 84.53536987304688, | |
| "learning_rate": 1.9375e-05, | |
| "loss": 0.6865, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 158.0510711669922, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7018, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5483870967741935, | |
| "eval_auc": 0.5530462184873949, | |
| "eval_f1": 0.6585365853658537, | |
| "eval_loss": 0.6887602806091309, | |
| "eval_precision": 0.5625, | |
| "eval_recall": 0.7941176470588235, | |
| "eval_runtime": 1.8847, | |
| "eval_samples_per_second": 32.897, | |
| "eval_steps_per_second": 1.061, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0625, | |
| "grad_norm": 55.63325881958008, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 0.6812, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.125, | |
| "grad_norm": 76.34017944335938, | |
| "learning_rate": 2.125e-05, | |
| "loss": 0.6929, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.1875, | |
| "grad_norm": 161.55897521972656, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 0.6743, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 49.372947692871094, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.687, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3125, | |
| "grad_norm": 59.057132720947266, | |
| "learning_rate": 2.3125000000000003e-05, | |
| "loss": 0.689, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.375, | |
| "grad_norm": 49.84357452392578, | |
| "learning_rate": 2.375e-05, | |
| "loss": 0.6677, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4375, | |
| "grad_norm": 321.417724609375, | |
| "learning_rate": 2.4375e-05, | |
| "loss": 0.6729, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 117.68087768554688, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.6787, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.5625, | |
| "grad_norm": 32.05921936035156, | |
| "learning_rate": 2.5625e-05, | |
| "loss": 0.7009, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.625, | |
| "grad_norm": 77.77110290527344, | |
| "learning_rate": 2.625e-05, | |
| "loss": 0.6897, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.6875, | |
| "grad_norm": 80.83302307128906, | |
| "learning_rate": 2.6875e-05, | |
| "loss": 0.7002, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 43.50077438354492, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.6938, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.8125, | |
| "grad_norm": 98.61802673339844, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 0.6787, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.875, | |
| "grad_norm": 42.48042678833008, | |
| "learning_rate": 2.8749999999999997e-05, | |
| "loss": 0.6807, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.9375, | |
| "grad_norm": 34.907432556152344, | |
| "learning_rate": 2.9375000000000003e-05, | |
| "loss": 0.7095, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 55.62687683105469, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7181, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5483870967741935, | |
| "eval_auc": 0.6307773109243697, | |
| "eval_f1": 0.7083333333333334, | |
| "eval_loss": 0.6826488375663757, | |
| "eval_precision": 0.5483870967741935, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.9113, | |
| "eval_samples_per_second": 32.439, | |
| "eval_steps_per_second": 1.046, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.0625, | |
| "grad_norm": 33.758544921875, | |
| "learning_rate": 3.0625000000000006e-05, | |
| "loss": 0.6763, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.125, | |
| "grad_norm": 49.062286376953125, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.6807, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.1875, | |
| "grad_norm": 56.35905838012695, | |
| "learning_rate": 3.1875e-05, | |
| "loss": 0.7012, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "grad_norm": 46.76564025878906, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.686, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.3125, | |
| "grad_norm": 33.05558395385742, | |
| "learning_rate": 3.3125e-05, | |
| "loss": 0.6731, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.375, | |
| "grad_norm": 35.67483901977539, | |
| "learning_rate": 3.375000000000001e-05, | |
| "loss": 0.6968, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.4375, | |
| "grad_norm": 42.819549560546875, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 0.6938, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "grad_norm": 36.487857818603516, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.6777, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.5625, | |
| "grad_norm": 27.21498680114746, | |
| "learning_rate": 3.5625000000000005e-05, | |
| "loss": 0.6929, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.625, | |
| "grad_norm": 33.59840774536133, | |
| "learning_rate": 3.625e-05, | |
| "loss": 0.6897, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.6875, | |
| "grad_norm": 44.81986618041992, | |
| "learning_rate": 3.6875e-05, | |
| "loss": 0.6973, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "grad_norm": 34.137603759765625, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.7063, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.8125, | |
| "grad_norm": 28.17397117614746, | |
| "learning_rate": 3.8125e-05, | |
| "loss": 0.6851, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.875, | |
| "grad_norm": 31.33745002746582, | |
| "learning_rate": 3.875e-05, | |
| "loss": 0.6912, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 3.9375, | |
| "grad_norm": 29.169218063354492, | |
| "learning_rate": 3.9375e-05, | |
| "loss": 0.6726, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 21.54955291748047, | |
| "learning_rate": 4e-05, | |
| "loss": 0.6465, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.532258064516129, | |
| "eval_auc": 0.4889705882352941, | |
| "eval_f1": 0.6947368421052632, | |
| "eval_loss": 0.6890751123428345, | |
| "eval_precision": 0.5409836065573771, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 1.9254, | |
| "eval_samples_per_second": 32.201, | |
| "eval_steps_per_second": 1.039, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.0625, | |
| "grad_norm": 27.51595115661621, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.6736, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.125, | |
| "grad_norm": 30.91176414489746, | |
| "learning_rate": 4.125e-05, | |
| "loss": 0.7058, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.1875, | |
| "grad_norm": 30.3780574798584, | |
| "learning_rate": 4.1875e-05, | |
| "loss": 0.6824, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "grad_norm": 24.23114013671875, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.6511, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.3125, | |
| "grad_norm": 29.467042922973633, | |
| "learning_rate": 4.3125000000000005e-05, | |
| "loss": 0.668, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.375, | |
| "grad_norm": 33.71297073364258, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.6836, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.4375, | |
| "grad_norm": 37.32026290893555, | |
| "learning_rate": 4.4375e-05, | |
| "loss": 0.6907, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 35.53947067260742, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6746, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.5625, | |
| "grad_norm": 19.044368743896484, | |
| "learning_rate": 4.5625e-05, | |
| "loss": 0.6924, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.625, | |
| "grad_norm": 28.231525421142578, | |
| "learning_rate": 4.6250000000000006e-05, | |
| "loss": 0.6499, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.6875, | |
| "grad_norm": 34.95646667480469, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.6882, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "grad_norm": 27.18376350402832, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.6821, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.8125, | |
| "grad_norm": 36.19109344482422, | |
| "learning_rate": 4.8125000000000004e-05, | |
| "loss": 0.7251, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.875, | |
| "grad_norm": 43.81327819824219, | |
| "learning_rate": 4.875e-05, | |
| "loss": 0.6829, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 4.9375, | |
| "grad_norm": 49.45500564575195, | |
| "learning_rate": 4.937500000000001e-05, | |
| "loss": 0.6931, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 63.39349365234375, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6484, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5483870967741935, | |
| "eval_auc": 0.4149159663865547, | |
| "eval_f1": 0.7083333333333334, | |
| "eval_loss": 0.697076678276062, | |
| "eval_precision": 0.5483870967741935, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.9324, | |
| "eval_samples_per_second": 32.084, | |
| "eval_steps_per_second": 1.035, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0625, | |
| "grad_norm": 30.904890060424805, | |
| "learning_rate": 4.993055555555556e-05, | |
| "loss": 0.6575, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 5.125, | |
| "grad_norm": 28.443708419799805, | |
| "learning_rate": 4.986111111111111e-05, | |
| "loss": 0.6843, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 5.1875, | |
| "grad_norm": 31.65029525756836, | |
| "learning_rate": 4.979166666666667e-05, | |
| "loss": 0.6775, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "grad_norm": 41.979393005371094, | |
| "learning_rate": 4.972222222222223e-05, | |
| "loss": 0.6704, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 5.3125, | |
| "grad_norm": 57.692604064941406, | |
| "learning_rate": 4.965277777777778e-05, | |
| "loss": 0.6951, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 5.375, | |
| "grad_norm": 29.71929359436035, | |
| "learning_rate": 4.958333333333334e-05, | |
| "loss": 0.7029, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 5.4375, | |
| "grad_norm": 21.230836868286133, | |
| "learning_rate": 4.951388888888889e-05, | |
| "loss": 0.6818, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 28.481653213500977, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.6799, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 5.5625, | |
| "grad_norm": 28.052490234375, | |
| "learning_rate": 4.937500000000001e-05, | |
| "loss": 0.6133, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 5.625, | |
| "grad_norm": 32.066349029541016, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 0.6906, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 5.6875, | |
| "grad_norm": 35.96651840209961, | |
| "learning_rate": 4.923611111111112e-05, | |
| "loss": 0.674, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "grad_norm": 47.34099197387695, | |
| "learning_rate": 4.9166666666666665e-05, | |
| "loss": 0.646, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 5.8125, | |
| "grad_norm": 25.086402893066406, | |
| "learning_rate": 4.909722222222222e-05, | |
| "loss": 0.6914, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 5.875, | |
| "grad_norm": 41.258033752441406, | |
| "learning_rate": 4.902777777777778e-05, | |
| "loss": 0.7019, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 5.9375, | |
| "grad_norm": 41.83433532714844, | |
| "learning_rate": 4.8958333333333335e-05, | |
| "loss": 0.6639, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 58.20046615600586, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.6855, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5483870967741935, | |
| "eval_auc": 0.5115546218487395, | |
| "eval_f1": 0.7083333333333334, | |
| "eval_loss": 0.6881301999092102, | |
| "eval_precision": 0.5483870967741935, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 1.9596, | |
| "eval_samples_per_second": 31.639, | |
| "eval_steps_per_second": 1.021, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 6.0625, | |
| "grad_norm": 46.368438720703125, | |
| "learning_rate": 4.8819444444444444e-05, | |
| "loss": 0.674, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 6.125, | |
| "grad_norm": 24.048921585083008, | |
| "learning_rate": 4.875e-05, | |
| "loss": 0.616, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 6.1875, | |
| "grad_norm": 61.79984664916992, | |
| "learning_rate": 4.8680555555555554e-05, | |
| "loss": 0.6044, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 55.52322769165039, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.7114, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.3125, | |
| "grad_norm": 52.9608268737793, | |
| "learning_rate": 4.854166666666667e-05, | |
| "loss": 0.7129, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 6.375, | |
| "grad_norm": 36.51575469970703, | |
| "learning_rate": 4.8472222222222224e-05, | |
| "loss": 0.6807, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 6.4375, | |
| "grad_norm": 34.925045013427734, | |
| "learning_rate": 4.840277777777778e-05, | |
| "loss": 0.7192, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "grad_norm": 54.098388671875, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.64, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 6.5625, | |
| "grad_norm": 42.83259201049805, | |
| "learning_rate": 4.8263888888888895e-05, | |
| "loss": 0.6606, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 6.625, | |
| "grad_norm": 52.560943603515625, | |
| "learning_rate": 4.819444444444445e-05, | |
| "loss": 0.6775, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 6.6875, | |
| "grad_norm": 47.502281188964844, | |
| "learning_rate": 4.8125000000000004e-05, | |
| "loss": 0.6632, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "grad_norm": 45.004520416259766, | |
| "learning_rate": 4.805555555555556e-05, | |
| "loss": 0.6558, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 6.8125, | |
| "grad_norm": 37.94780349731445, | |
| "learning_rate": 4.7986111111111113e-05, | |
| "loss": 0.6586, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 6.875, | |
| "grad_norm": 43.655487060546875, | |
| "learning_rate": 4.791666666666667e-05, | |
| "loss": 0.619, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 6.9375, | |
| "grad_norm": 38.0520133972168, | |
| "learning_rate": 4.784722222222223e-05, | |
| "loss": 0.7035, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 107.8686752319336, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.6764, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5483870967741935, | |
| "eval_auc": 0.7468487394957983, | |
| "eval_f1": 0.7021276595744681, | |
| "eval_loss": 0.6627079844474792, | |
| "eval_precision": 0.55, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 4.1619, | |
| "eval_samples_per_second": 14.897, | |
| "eval_steps_per_second": 0.481, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 7.0625, | |
| "grad_norm": 58.015350341796875, | |
| "learning_rate": 4.770833333333334e-05, | |
| "loss": 0.6333, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 7.125, | |
| "grad_norm": 38.808807373046875, | |
| "learning_rate": 4.7638888888888887e-05, | |
| "loss": 0.736, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 7.1875, | |
| "grad_norm": 44.99721145629883, | |
| "learning_rate": 4.756944444444444e-05, | |
| "loss": 0.6514, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "grad_norm": 49.331939697265625, | |
| "learning_rate": 4.75e-05, | |
| "loss": 0.6732, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 7.3125, | |
| "grad_norm": 42.08985900878906, | |
| "learning_rate": 4.743055555555556e-05, | |
| "loss": 0.686, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 7.375, | |
| "grad_norm": 35.44804382324219, | |
| "learning_rate": 4.736111111111111e-05, | |
| "loss": 0.6517, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 7.4375, | |
| "grad_norm": 68.73687744140625, | |
| "learning_rate": 4.7291666666666666e-05, | |
| "loss": 0.6578, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 37.671722412109375, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.6545, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.5625, | |
| "grad_norm": 30.469106674194336, | |
| "learning_rate": 4.7152777777777776e-05, | |
| "loss": 0.616, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 7.625, | |
| "grad_norm": 46.04682540893555, | |
| "learning_rate": 4.708333333333334e-05, | |
| "loss": 0.6775, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 7.6875, | |
| "grad_norm": 75.76403045654297, | |
| "learning_rate": 4.701388888888889e-05, | |
| "loss": 0.6191, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "grad_norm": 54.207244873046875, | |
| "learning_rate": 4.6944444444444446e-05, | |
| "loss": 0.6384, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 7.8125, | |
| "grad_norm": 33.48508071899414, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.6265, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 7.875, | |
| "grad_norm": 35.78009033203125, | |
| "learning_rate": 4.6805555555555556e-05, | |
| "loss": 0.6279, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 7.9375, | |
| "grad_norm": 56.53678894042969, | |
| "learning_rate": 4.673611111111112e-05, | |
| "loss": 0.6654, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 68.72865295410156, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.6589, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5806451612903226, | |
| "eval_auc": 0.7064075630252102, | |
| "eval_f1": 0.717391304347826, | |
| "eval_loss": 0.6593685746192932, | |
| "eval_precision": 0.5689655172413793, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 2.9827, | |
| "eval_samples_per_second": 20.787, | |
| "eval_steps_per_second": 0.671, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 8.0625, | |
| "grad_norm": 69.71391296386719, | |
| "learning_rate": 4.6597222222222226e-05, | |
| "loss": 0.634, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 8.125, | |
| "grad_norm": 60.223880767822266, | |
| "learning_rate": 4.652777777777778e-05, | |
| "loss": 0.631, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 8.1875, | |
| "grad_norm": 36.413326263427734, | |
| "learning_rate": 4.6458333333333335e-05, | |
| "loss": 0.6221, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "grad_norm": 46.27412414550781, | |
| "learning_rate": 4.638888888888889e-05, | |
| "loss": 0.619, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 8.3125, | |
| "grad_norm": 39.7827262878418, | |
| "learning_rate": 4.631944444444445e-05, | |
| "loss": 0.719, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 8.375, | |
| "grad_norm": 87.59008026123047, | |
| "learning_rate": 4.6250000000000006e-05, | |
| "loss": 0.5983, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 8.4375, | |
| "grad_norm": 62.683250427246094, | |
| "learning_rate": 4.618055555555556e-05, | |
| "loss": 0.6635, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "grad_norm": 29.072847366333008, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.6459, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 8.5625, | |
| "grad_norm": 54.492469787597656, | |
| "learning_rate": 4.604166666666666e-05, | |
| "loss": 0.701, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 8.625, | |
| "grad_norm": 38.17914962768555, | |
| "learning_rate": 4.5972222222222225e-05, | |
| "loss": 0.6271, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 8.6875, | |
| "grad_norm": 72.31561279296875, | |
| "learning_rate": 4.590277777777778e-05, | |
| "loss": 0.6277, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "grad_norm": 69.48700714111328, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.6243, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.8125, | |
| "grad_norm": 45.070735931396484, | |
| "learning_rate": 4.576388888888889e-05, | |
| "loss": 0.6534, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 8.875, | |
| "grad_norm": 54.82920455932617, | |
| "learning_rate": 4.569444444444444e-05, | |
| "loss": 0.6283, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 8.9375, | |
| "grad_norm": 83.2965087890625, | |
| "learning_rate": 4.5625e-05, | |
| "loss": 0.6478, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 163.7074737548828, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.5977, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5967741935483871, | |
| "eval_auc": 0.7064075630252101, | |
| "eval_f1": 0.7191011235955056, | |
| "eval_loss": 0.6552733182907104, | |
| "eval_precision": 0.5818181818181818, | |
| "eval_recall": 0.9411764705882353, | |
| "eval_runtime": 1.9183, | |
| "eval_samples_per_second": 32.321, | |
| "eval_steps_per_second": 1.043, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 9.0625, | |
| "grad_norm": 79.20127868652344, | |
| "learning_rate": 4.5486111111111114e-05, | |
| "loss": 0.5693, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 9.125, | |
| "grad_norm": 39.74399185180664, | |
| "learning_rate": 4.541666666666667e-05, | |
| "loss": 0.6826, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 9.1875, | |
| "grad_norm": 48.851234436035156, | |
| "learning_rate": 4.534722222222222e-05, | |
| "loss": 0.681, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "grad_norm": 32.17538833618164, | |
| "learning_rate": 4.527777777777778e-05, | |
| "loss": 0.593, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 9.3125, | |
| "grad_norm": 84.288330078125, | |
| "learning_rate": 4.520833333333334e-05, | |
| "loss": 0.6222, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 9.375, | |
| "grad_norm": 41.05829620361328, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.6035, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 9.4375, | |
| "grad_norm": 61.59003829956055, | |
| "learning_rate": 4.506944444444445e-05, | |
| "loss": 0.6007, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 78.13147735595703, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6533, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 9.5625, | |
| "grad_norm": 58.18182373046875, | |
| "learning_rate": 4.493055555555556e-05, | |
| "loss": 0.6033, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 9.625, | |
| "grad_norm": 43.28728485107422, | |
| "learning_rate": 4.486111111111111e-05, | |
| "loss": 0.6, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 9.6875, | |
| "grad_norm": 48.38688278198242, | |
| "learning_rate": 4.4791666666666673e-05, | |
| "loss": 0.6678, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "grad_norm": 60.13078689575195, | |
| "learning_rate": 4.472222222222223e-05, | |
| "loss": 0.6273, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 9.8125, | |
| "grad_norm": 42.91427230834961, | |
| "learning_rate": 4.465277777777778e-05, | |
| "loss": 0.6301, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 9.875, | |
| "grad_norm": 48.625492095947266, | |
| "learning_rate": 4.458333333333334e-05, | |
| "loss": 0.5844, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 9.9375, | |
| "grad_norm": 34.01121139526367, | |
| "learning_rate": 4.4513888888888885e-05, | |
| "loss": 0.7302, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 89.23443603515625, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.6165, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7258064516129032, | |
| "eval_auc": 0.8161764705882353, | |
| "eval_f1": 0.7951807228915663, | |
| "eval_loss": 0.609186053276062, | |
| "eval_precision": 0.673469387755102, | |
| "eval_recall": 0.9705882352941176, | |
| "eval_runtime": 1.9257, | |
| "eval_samples_per_second": 32.196, | |
| "eval_steps_per_second": 1.039, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 10.0625, | |
| "grad_norm": 33.16124725341797, | |
| "learning_rate": 4.4375e-05, | |
| "loss": 0.6516, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 10.125, | |
| "grad_norm": 44.67818832397461, | |
| "learning_rate": 4.4305555555555556e-05, | |
| "loss": 0.7222, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 10.1875, | |
| "grad_norm": 44.10664749145508, | |
| "learning_rate": 4.423611111111111e-05, | |
| "loss": 0.6145, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "grad_norm": 44.849090576171875, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.6475, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 10.3125, | |
| "grad_norm": 42.657108306884766, | |
| "learning_rate": 4.4097222222222226e-05, | |
| "loss": 0.5923, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 10.375, | |
| "grad_norm": 60.3536262512207, | |
| "learning_rate": 4.402777777777778e-05, | |
| "loss": 0.7048, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 10.4375, | |
| "grad_norm": 89.41458892822266, | |
| "learning_rate": 4.3958333333333336e-05, | |
| "loss": 0.5677, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "grad_norm": 73.32341003417969, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.7057, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 10.5625, | |
| "grad_norm": 42.202144622802734, | |
| "learning_rate": 4.3819444444444445e-05, | |
| "loss": 0.6323, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 10.625, | |
| "grad_norm": 33.11185073852539, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.5757, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 10.6875, | |
| "grad_norm": 37.71356201171875, | |
| "learning_rate": 4.368055555555556e-05, | |
| "loss": 0.5549, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "grad_norm": 65.49434661865234, | |
| "learning_rate": 4.3611111111111116e-05, | |
| "loss": 0.5752, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 10.8125, | |
| "grad_norm": 52.854515075683594, | |
| "learning_rate": 4.354166666666667e-05, | |
| "loss": 0.6448, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 10.875, | |
| "grad_norm": 93.11141204833984, | |
| "learning_rate": 4.3472222222222225e-05, | |
| "loss": 0.7771, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 10.9375, | |
| "grad_norm": 48.91088104248047, | |
| "learning_rate": 4.340277777777778e-05, | |
| "loss": 0.5415, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 178.06539916992188, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.7217, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5967741935483871, | |
| "eval_auc": 0.6701680672268908, | |
| "eval_f1": 0.691358024691358, | |
| "eval_loss": 0.659967303276062, | |
| "eval_precision": 0.5957446808510638, | |
| "eval_recall": 0.8235294117647058, | |
| "eval_runtime": 1.9464, | |
| "eval_samples_per_second": 31.854, | |
| "eval_steps_per_second": 1.028, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 11.0625, | |
| "grad_norm": 67.89295959472656, | |
| "learning_rate": 4.3263888888888895e-05, | |
| "loss": 0.6306, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 11.125, | |
| "grad_norm": 36.25627517700195, | |
| "learning_rate": 4.319444444444445e-05, | |
| "loss": 0.4834, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 11.1875, | |
| "grad_norm": 43.655174255371094, | |
| "learning_rate": 4.3125000000000005e-05, | |
| "loss": 0.5637, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "grad_norm": 51.83556365966797, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.5269, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 11.3125, | |
| "grad_norm": 50.347084045410156, | |
| "learning_rate": 4.2986111111111114e-05, | |
| "loss": 0.5744, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 11.375, | |
| "grad_norm": 71.25247192382812, | |
| "learning_rate": 4.291666666666667e-05, | |
| "loss": 0.6053, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 11.4375, | |
| "grad_norm": 48.39303970336914, | |
| "learning_rate": 4.284722222222222e-05, | |
| "loss": 0.6816, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "grad_norm": 51.63835525512695, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.6187, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 11.5625, | |
| "grad_norm": 50.23905563354492, | |
| "learning_rate": 4.270833333333333e-05, | |
| "loss": 0.6252, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 11.625, | |
| "grad_norm": 81.17058563232422, | |
| "learning_rate": 4.263888888888889e-05, | |
| "loss": 0.6522, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 11.6875, | |
| "grad_norm": 74.09992218017578, | |
| "learning_rate": 4.256944444444445e-05, | |
| "loss": 0.5702, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "grad_norm": 32.29295349121094, | |
| "learning_rate": 4.25e-05, | |
| "loss": 0.5317, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 11.8125, | |
| "grad_norm": 64.11018371582031, | |
| "learning_rate": 4.243055555555556e-05, | |
| "loss": 0.5979, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 11.875, | |
| "grad_norm": 131.69041442871094, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 0.5775, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 11.9375, | |
| "grad_norm": 49.00139236450195, | |
| "learning_rate": 4.229166666666667e-05, | |
| "loss": 0.6661, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 154.61660766601562, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.6667, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6935483870967742, | |
| "eval_auc": 0.7804621848739496, | |
| "eval_f1": 0.759493670886076, | |
| "eval_loss": 0.5980972051620483, | |
| "eval_precision": 0.6666666666666666, | |
| "eval_recall": 0.8823529411764706, | |
| "eval_runtime": 1.9477, | |
| "eval_samples_per_second": 31.832, | |
| "eval_steps_per_second": 1.027, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 12.0625, | |
| "grad_norm": 80.12366485595703, | |
| "learning_rate": 4.215277777777778e-05, | |
| "loss": 0.5312, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 12.125, | |
| "grad_norm": 81.18545532226562, | |
| "learning_rate": 4.208333333333334e-05, | |
| "loss": 0.608, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 12.1875, | |
| "grad_norm": 63.287353515625, | |
| "learning_rate": 4.201388888888889e-05, | |
| "loss": 0.5273, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "grad_norm": 45.18925857543945, | |
| "learning_rate": 4.194444444444445e-05, | |
| "loss": 0.6504, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 12.3125, | |
| "grad_norm": 72.20451354980469, | |
| "learning_rate": 4.1875e-05, | |
| "loss": 0.5665, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 12.375, | |
| "grad_norm": 65.66788482666016, | |
| "learning_rate": 4.1805555555555556e-05, | |
| "loss": 0.527, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 12.4375, | |
| "grad_norm": 50.52779769897461, | |
| "learning_rate": 4.173611111111112e-05, | |
| "loss": 0.4926, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 73.23728942871094, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5988, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 12.5625, | |
| "grad_norm": 61.189208984375, | |
| "learning_rate": 4.159722222222223e-05, | |
| "loss": 0.562, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 12.625, | |
| "grad_norm": 62.635154724121094, | |
| "learning_rate": 4.152777777777778e-05, | |
| "loss": 0.6054, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 12.6875, | |
| "grad_norm": 50.976192474365234, | |
| "learning_rate": 4.1458333333333336e-05, | |
| "loss": 0.5327, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "grad_norm": 60.057830810546875, | |
| "learning_rate": 4.138888888888889e-05, | |
| "loss": 0.5172, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 12.8125, | |
| "grad_norm": 64.1837158203125, | |
| "learning_rate": 4.1319444444444445e-05, | |
| "loss": 0.5976, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 12.875, | |
| "grad_norm": 46.790653228759766, | |
| "learning_rate": 4.125e-05, | |
| "loss": 0.576, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 12.9375, | |
| "grad_norm": 227.32740783691406, | |
| "learning_rate": 4.1180555555555554e-05, | |
| "loss": 0.6454, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 102.79993438720703, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.5299, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7419354838709677, | |
| "eval_auc": 0.8508403361344538, | |
| "eval_f1": 0.7948717948717948, | |
| "eval_loss": 0.5460716485977173, | |
| "eval_precision": 0.7045454545454546, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.9335, | |
| "eval_samples_per_second": 32.066, | |
| "eval_steps_per_second": 1.034, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 13.0625, | |
| "grad_norm": 48.264347076416016, | |
| "learning_rate": 4.104166666666667e-05, | |
| "loss": 0.5178, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 13.125, | |
| "grad_norm": 110.42784118652344, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 0.608, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 13.1875, | |
| "grad_norm": 220.24856567382812, | |
| "learning_rate": 4.090277777777778e-05, | |
| "loss": 0.584, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "grad_norm": 114.8612060546875, | |
| "learning_rate": 4.0833333333333334e-05, | |
| "loss": 0.5646, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 13.3125, | |
| "grad_norm": 58.41973114013672, | |
| "learning_rate": 4.076388888888889e-05, | |
| "loss": 0.5574, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 13.375, | |
| "grad_norm": 100.16024780273438, | |
| "learning_rate": 4.0694444444444444e-05, | |
| "loss": 0.5134, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 13.4375, | |
| "grad_norm": 80.44810485839844, | |
| "learning_rate": 4.0625000000000005e-05, | |
| "loss": 0.5714, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "grad_norm": 67.43321228027344, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.5523, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 13.5625, | |
| "grad_norm": 43.3171501159668, | |
| "learning_rate": 4.0486111111111114e-05, | |
| "loss": 0.4604, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 13.625, | |
| "grad_norm": 40.656898498535156, | |
| "learning_rate": 4.041666666666667e-05, | |
| "loss": 0.5281, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 13.6875, | |
| "grad_norm": 84.43306732177734, | |
| "learning_rate": 4.0347222222222223e-05, | |
| "loss": 0.5104, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "grad_norm": 54.887840270996094, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.592, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 13.8125, | |
| "grad_norm": 53.76454162597656, | |
| "learning_rate": 4.020833333333334e-05, | |
| "loss": 0.4651, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 13.875, | |
| "grad_norm": 36.3071403503418, | |
| "learning_rate": 4.0138888888888894e-05, | |
| "loss": 0.492, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 13.9375, | |
| "grad_norm": 107.2224349975586, | |
| "learning_rate": 4.006944444444445e-05, | |
| "loss": 0.6049, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 131.88079833984375, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4969, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7580645161290323, | |
| "eval_auc": 0.8109243697478992, | |
| "eval_f1": 0.7540983606557377, | |
| "eval_loss": 0.5879219770431519, | |
| "eval_precision": 0.8518518518518519, | |
| "eval_recall": 0.6764705882352942, | |
| "eval_runtime": 1.9506, | |
| "eval_samples_per_second": 31.785, | |
| "eval_steps_per_second": 1.025, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 14.0625, | |
| "grad_norm": 58.407073974609375, | |
| "learning_rate": 3.993055555555556e-05, | |
| "loss": 0.5254, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 14.125, | |
| "grad_norm": 80.39613342285156, | |
| "learning_rate": 3.986111111111111e-05, | |
| "loss": 0.5312, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 14.1875, | |
| "grad_norm": 61.52587890625, | |
| "learning_rate": 3.979166666666667e-05, | |
| "loss": 0.5522, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "grad_norm": 99.368896484375, | |
| "learning_rate": 3.972222222222222e-05, | |
| "loss": 0.5006, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 14.3125, | |
| "grad_norm": 88.41030883789062, | |
| "learning_rate": 3.9652777777777776e-05, | |
| "loss": 0.5121, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 14.375, | |
| "grad_norm": 60.34226989746094, | |
| "learning_rate": 3.958333333333333e-05, | |
| "loss": 0.4733, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 14.4375, | |
| "grad_norm": 51.18446731567383, | |
| "learning_rate": 3.951388888888889e-05, | |
| "loss": 0.5245, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "grad_norm": 72.11532592773438, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.5194, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 14.5625, | |
| "grad_norm": 40.04228210449219, | |
| "learning_rate": 3.9375e-05, | |
| "loss": 0.705, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 14.625, | |
| "grad_norm": 37.71114730834961, | |
| "learning_rate": 3.9305555555555556e-05, | |
| "loss": 0.4384, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 14.6875, | |
| "grad_norm": 121.4798812866211, | |
| "learning_rate": 3.923611111111111e-05, | |
| "loss": 0.5156, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "grad_norm": 42.07125473022461, | |
| "learning_rate": 3.9166666666666665e-05, | |
| "loss": 0.55, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 14.8125, | |
| "grad_norm": 29.359413146972656, | |
| "learning_rate": 3.909722222222223e-05, | |
| "loss": 0.5123, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 14.875, | |
| "grad_norm": 44.849979400634766, | |
| "learning_rate": 3.902777777777778e-05, | |
| "loss": 0.525, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 14.9375, | |
| "grad_norm": 55.50422668457031, | |
| "learning_rate": 3.8958333333333336e-05, | |
| "loss": 0.5289, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 139.26576232910156, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.5433, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7903225806451613, | |
| "eval_auc": 0.8771008403361344, | |
| "eval_f1": 0.8, | |
| "eval_loss": 0.5240045189857483, | |
| "eval_precision": 0.8387096774193549, | |
| "eval_recall": 0.7647058823529411, | |
| "eval_runtime": 1.931, | |
| "eval_samples_per_second": 32.108, | |
| "eval_steps_per_second": 1.036, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 15.0625, | |
| "grad_norm": 78.3478775024414, | |
| "learning_rate": 3.8819444444444445e-05, | |
| "loss": 0.496, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 15.125, | |
| "grad_norm": 83.29708099365234, | |
| "learning_rate": 3.875e-05, | |
| "loss": 0.5401, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 15.1875, | |
| "grad_norm": 40.72947692871094, | |
| "learning_rate": 3.868055555555556e-05, | |
| "loss": 0.4114, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "grad_norm": 34.38518524169922, | |
| "learning_rate": 3.8611111111111116e-05, | |
| "loss": 0.4647, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 15.3125, | |
| "grad_norm": 45.165794372558594, | |
| "learning_rate": 3.854166666666667e-05, | |
| "loss": 0.5248, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 15.375, | |
| "grad_norm": 63.5728759765625, | |
| "learning_rate": 3.8472222222222225e-05, | |
| "loss": 0.5442, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 15.4375, | |
| "grad_norm": 58.13555908203125, | |
| "learning_rate": 3.840277777777778e-05, | |
| "loss": 0.6143, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "grad_norm": 36.5289421081543, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.4758, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 15.5625, | |
| "grad_norm": 54.04985046386719, | |
| "learning_rate": 3.826388888888889e-05, | |
| "loss": 0.4218, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 15.625, | |
| "grad_norm": 72.28607940673828, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.5893, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 15.6875, | |
| "grad_norm": 74.44154357910156, | |
| "learning_rate": 3.8125e-05, | |
| "loss": 0.6552, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "grad_norm": 44.40108871459961, | |
| "learning_rate": 3.805555555555555e-05, | |
| "loss": 0.4867, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 15.8125, | |
| "grad_norm": 73.97761535644531, | |
| "learning_rate": 3.7986111111111114e-05, | |
| "loss": 0.6184, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 15.875, | |
| "grad_norm": 141.63430786132812, | |
| "learning_rate": 3.791666666666667e-05, | |
| "loss": 0.4479, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 15.9375, | |
| "grad_norm": 71.14151763916016, | |
| "learning_rate": 3.7847222222222224e-05, | |
| "loss": 0.3983, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 72.08846282958984, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.3454, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7419354838709677, | |
| "eval_auc": 0.8261554621848739, | |
| "eval_f1": 0.7714285714285715, | |
| "eval_loss": 0.5412834286689758, | |
| "eval_precision": 0.75, | |
| "eval_recall": 0.7941176470588235, | |
| "eval_runtime": 1.9248, | |
| "eval_samples_per_second": 32.212, | |
| "eval_steps_per_second": 1.039, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 16.0625, | |
| "grad_norm": 51.053855895996094, | |
| "learning_rate": 3.770833333333333e-05, | |
| "loss": 0.4064, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 16.125, | |
| "grad_norm": 61.72437286376953, | |
| "learning_rate": 3.763888888888889e-05, | |
| "loss": 0.5844, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 16.1875, | |
| "grad_norm": 68.33097076416016, | |
| "learning_rate": 3.756944444444445e-05, | |
| "loss": 0.5247, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "grad_norm": 72.65277862548828, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.492, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 16.3125, | |
| "grad_norm": 48.784759521484375, | |
| "learning_rate": 3.743055555555556e-05, | |
| "loss": 0.5779, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 16.375, | |
| "grad_norm": 94.48021697998047, | |
| "learning_rate": 3.736111111111111e-05, | |
| "loss": 0.6233, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 16.4375, | |
| "grad_norm": 123.79901885986328, | |
| "learning_rate": 3.729166666666667e-05, | |
| "loss": 0.5248, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "grad_norm": 42.541114807128906, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.4769, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 16.5625, | |
| "grad_norm": 40.07915115356445, | |
| "learning_rate": 3.715277777777778e-05, | |
| "loss": 0.411, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 16.625, | |
| "grad_norm": 66.4336929321289, | |
| "learning_rate": 3.708333333333334e-05, | |
| "loss": 0.4531, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 16.6875, | |
| "grad_norm": 36.28628158569336, | |
| "learning_rate": 3.701388888888889e-05, | |
| "loss": 0.4582, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "grad_norm": 43.74733352661133, | |
| "learning_rate": 3.694444444444445e-05, | |
| "loss": 0.3818, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 16.8125, | |
| "grad_norm": 61.93031692504883, | |
| "learning_rate": 3.6875e-05, | |
| "loss": 0.4218, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 16.875, | |
| "grad_norm": 47.1074333190918, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 0.4234, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 16.9375, | |
| "grad_norm": 91.64878845214844, | |
| "learning_rate": 3.673611111111112e-05, | |
| "loss": 0.5807, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 85.23784637451172, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.6552, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7580645161290323, | |
| "eval_auc": 0.8692226890756303, | |
| "eval_f1": 0.7945205479452054, | |
| "eval_loss": 0.4790668785572052, | |
| "eval_precision": 0.7435897435897436, | |
| "eval_recall": 0.8529411764705882, | |
| "eval_runtime": 1.9244, | |
| "eval_samples_per_second": 32.217, | |
| "eval_steps_per_second": 1.039, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 17.0625, | |
| "grad_norm": 73.90734100341797, | |
| "learning_rate": 3.659722222222222e-05, | |
| "loss": 0.79, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 17.125, | |
| "grad_norm": 94.85003662109375, | |
| "learning_rate": 3.6527777777777775e-05, | |
| "loss": 0.6025, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 17.1875, | |
| "grad_norm": 75.04529571533203, | |
| "learning_rate": 3.6458333333333336e-05, | |
| "loss": 0.4477, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "grad_norm": 37.73780059814453, | |
| "learning_rate": 3.638888888888889e-05, | |
| "loss": 0.5583, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 17.3125, | |
| "grad_norm": 97.058349609375, | |
| "learning_rate": 3.6319444444444446e-05, | |
| "loss": 0.4121, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 17.375, | |
| "grad_norm": 41.515113830566406, | |
| "learning_rate": 3.625e-05, | |
| "loss": 0.4931, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 17.4375, | |
| "grad_norm": 89.66553497314453, | |
| "learning_rate": 3.6180555555555555e-05, | |
| "loss": 0.5748, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "grad_norm": 45.831058502197266, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.5429, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 17.5625, | |
| "grad_norm": 37.5870246887207, | |
| "learning_rate": 3.604166666666667e-05, | |
| "loss": 0.4326, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 17.625, | |
| "grad_norm": 69.45463562011719, | |
| "learning_rate": 3.5972222222222225e-05, | |
| "loss": 0.4083, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 17.6875, | |
| "grad_norm": 89.9836654663086, | |
| "learning_rate": 3.590277777777778e-05, | |
| "loss": 0.6454, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "grad_norm": 157.84072875976562, | |
| "learning_rate": 3.5833333333333335e-05, | |
| "loss": 0.4036, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 17.8125, | |
| "grad_norm": 144.50209045410156, | |
| "learning_rate": 3.576388888888889e-05, | |
| "loss": 0.5848, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 17.875, | |
| "grad_norm": 89.03966522216797, | |
| "learning_rate": 3.5694444444444444e-05, | |
| "loss": 0.3845, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 17.9375, | |
| "grad_norm": 43.99159622192383, | |
| "learning_rate": 3.5625000000000005e-05, | |
| "loss": 0.5129, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 47.54975891113281, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.4147, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8064516129032258, | |
| "eval_auc": 0.8939075630252101, | |
| "eval_f1": 0.8181818181818182, | |
| "eval_loss": 0.43667498230934143, | |
| "eval_precision": 0.84375, | |
| "eval_recall": 0.7941176470588235, | |
| "eval_runtime": 1.9961, | |
| "eval_samples_per_second": 31.06, | |
| "eval_steps_per_second": 1.002, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 18.0625, | |
| "grad_norm": 103.01007080078125, | |
| "learning_rate": 3.5486111111111115e-05, | |
| "loss": 0.5238, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 18.125, | |
| "grad_norm": 108.39590454101562, | |
| "learning_rate": 3.541666666666667e-05, | |
| "loss": 0.5119, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 18.1875, | |
| "grad_norm": 36.57012176513672, | |
| "learning_rate": 3.5347222222222224e-05, | |
| "loss": 0.375, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 18.25, | |
| "grad_norm": 64.35926818847656, | |
| "learning_rate": 3.527777777777778e-05, | |
| "loss": 0.7708, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 18.3125, | |
| "grad_norm": 57.50725555419922, | |
| "learning_rate": 3.520833333333334e-05, | |
| "loss": 0.4307, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 18.375, | |
| "grad_norm": 94.58295440673828, | |
| "learning_rate": 3.513888888888889e-05, | |
| "loss": 0.5037, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 18.4375, | |
| "grad_norm": 66.14063262939453, | |
| "learning_rate": 3.506944444444444e-05, | |
| "loss": 0.3167, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "grad_norm": 101.09774017333984, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.504, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 18.5625, | |
| "grad_norm": 60.17547607421875, | |
| "learning_rate": 3.493055555555556e-05, | |
| "loss": 0.4903, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 18.625, | |
| "grad_norm": 83.2125015258789, | |
| "learning_rate": 3.486111111111111e-05, | |
| "loss": 0.605, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 18.6875, | |
| "grad_norm": 65.9618911743164, | |
| "learning_rate": 3.479166666666667e-05, | |
| "loss": 0.4312, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "grad_norm": 29.95576286315918, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3029, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 18.8125, | |
| "grad_norm": 100.61408996582031, | |
| "learning_rate": 3.465277777777778e-05, | |
| "loss": 0.4785, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 18.875, | |
| "grad_norm": 73.51964569091797, | |
| "learning_rate": 3.458333333333333e-05, | |
| "loss": 0.3882, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 18.9375, | |
| "grad_norm": 43.713768005371094, | |
| "learning_rate": 3.451388888888889e-05, | |
| "loss": 0.6225, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 246.18128967285156, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.5218, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.7580645161290323, | |
| "eval_auc": 0.8660714285714286, | |
| "eval_f1": 0.7457627118644068, | |
| "eval_loss": 0.4833846688270569, | |
| "eval_precision": 0.88, | |
| "eval_recall": 0.6470588235294118, | |
| "eval_runtime": 1.9511, | |
| "eval_samples_per_second": 31.776, | |
| "eval_steps_per_second": 1.025, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 19.0625, | |
| "grad_norm": 106.1519546508789, | |
| "learning_rate": 3.4375e-05, | |
| "loss": 0.5315, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 19.125, | |
| "grad_norm": 65.67142486572266, | |
| "learning_rate": 3.430555555555556e-05, | |
| "loss": 0.6993, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 19.1875, | |
| "grad_norm": 36.1142692565918, | |
| "learning_rate": 3.423611111111111e-05, | |
| "loss": 0.3465, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 19.25, | |
| "grad_norm": 46.80392837524414, | |
| "learning_rate": 3.4166666666666666e-05, | |
| "loss": 0.3667, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 19.3125, | |
| "grad_norm": 55.320953369140625, | |
| "learning_rate": 3.409722222222223e-05, | |
| "loss": 0.4295, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 19.375, | |
| "grad_norm": 40.02817153930664, | |
| "learning_rate": 3.402777777777778e-05, | |
| "loss": 0.3958, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 19.4375, | |
| "grad_norm": 84.88871002197266, | |
| "learning_rate": 3.3958333333333337e-05, | |
| "loss": 0.4724, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "grad_norm": 63.09480667114258, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.4288, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 19.5625, | |
| "grad_norm": 61.246192932128906, | |
| "learning_rate": 3.3819444444444446e-05, | |
| "loss": 0.3882, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 19.625, | |
| "grad_norm": 56.286766052246094, | |
| "learning_rate": 3.375000000000001e-05, | |
| "loss": 0.506, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 19.6875, | |
| "grad_norm": 65.18053436279297, | |
| "learning_rate": 3.368055555555556e-05, | |
| "loss": 0.4222, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 19.75, | |
| "grad_norm": 71.56250762939453, | |
| "learning_rate": 3.3611111111111116e-05, | |
| "loss": 0.4521, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 19.8125, | |
| "grad_norm": 79.5528564453125, | |
| "learning_rate": 3.3541666666666664e-05, | |
| "loss": 0.5815, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 19.875, | |
| "grad_norm": 80.54459381103516, | |
| "learning_rate": 3.347222222222222e-05, | |
| "loss": 0.5034, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 19.9375, | |
| "grad_norm": 46.42332458496094, | |
| "learning_rate": 3.340277777777778e-05, | |
| "loss": 0.3943, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 265.7347412109375, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.8294, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.7419354838709677, | |
| "eval_auc": 0.8277310924369747, | |
| "eval_f1": 0.75, | |
| "eval_loss": 0.5033332705497742, | |
| "eval_precision": 0.8, | |
| "eval_recall": 0.7058823529411765, | |
| "eval_runtime": 1.9359, | |
| "eval_samples_per_second": 32.026, | |
| "eval_steps_per_second": 1.033, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 20.0625, | |
| "grad_norm": 80.59957122802734, | |
| "learning_rate": 3.326388888888889e-05, | |
| "loss": 0.55, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 20.125, | |
| "grad_norm": 59.34410858154297, | |
| "learning_rate": 3.3194444444444444e-05, | |
| "loss": 0.4545, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 20.1875, | |
| "grad_norm": 190.26165771484375, | |
| "learning_rate": 3.3125e-05, | |
| "loss": 0.5782, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 20.25, | |
| "grad_norm": 73.1745834350586, | |
| "learning_rate": 3.3055555555555553e-05, | |
| "loss": 0.42, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 20.3125, | |
| "grad_norm": 41.371578216552734, | |
| "learning_rate": 3.2986111111111115e-05, | |
| "loss": 0.2567, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 20.375, | |
| "grad_norm": 59.37371063232422, | |
| "learning_rate": 3.291666666666667e-05, | |
| "loss": 0.4721, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 20.4375, | |
| "grad_norm": 64.93104553222656, | |
| "learning_rate": 3.2847222222222224e-05, | |
| "loss": 0.4373, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 20.5, | |
| "grad_norm": 86.97407531738281, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.3585, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 20.5625, | |
| "grad_norm": 65.34368896484375, | |
| "learning_rate": 3.270833333333333e-05, | |
| "loss": 0.3815, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 20.625, | |
| "grad_norm": 62.39166259765625, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 0.3582, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 20.6875, | |
| "grad_norm": 71.4781265258789, | |
| "learning_rate": 3.256944444444445e-05, | |
| "loss": 0.3781, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 20.75, | |
| "grad_norm": 34.324867248535156, | |
| "learning_rate": 3.2500000000000004e-05, | |
| "loss": 0.3129, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 20.8125, | |
| "grad_norm": 86.5385971069336, | |
| "learning_rate": 3.243055555555556e-05, | |
| "loss": 0.3903, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 20.875, | |
| "grad_norm": 97.72544860839844, | |
| "learning_rate": 3.236111111111111e-05, | |
| "loss": 0.3329, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 20.9375, | |
| "grad_norm": 124.9569091796875, | |
| "learning_rate": 3.229166666666667e-05, | |
| "loss": 0.5095, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 197.2810516357422, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.7458, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8064516129032258, | |
| "eval_auc": 0.9028361344537815, | |
| "eval_f1": 0.8378378378378378, | |
| "eval_loss": 0.4212134778499603, | |
| "eval_precision": 0.775, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.9253, | |
| "eval_samples_per_second": 32.203, | |
| "eval_steps_per_second": 1.039, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 21.0625, | |
| "grad_norm": 78.05635070800781, | |
| "learning_rate": 3.2152777777777784e-05, | |
| "loss": 0.3589, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 21.125, | |
| "grad_norm": 114.2430191040039, | |
| "learning_rate": 3.208333333333334e-05, | |
| "loss": 0.6472, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 21.1875, | |
| "grad_norm": 74.19608306884766, | |
| "learning_rate": 3.2013888888888886e-05, | |
| "loss": 0.4214, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 21.25, | |
| "grad_norm": 75.80211639404297, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.384, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 21.3125, | |
| "grad_norm": 43.8707389831543, | |
| "learning_rate": 3.1875e-05, | |
| "loss": 0.3883, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 21.375, | |
| "grad_norm": 145.6295166015625, | |
| "learning_rate": 3.180555555555556e-05, | |
| "loss": 0.392, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 21.4375, | |
| "grad_norm": 41.334449768066406, | |
| "learning_rate": 3.173611111111111e-05, | |
| "loss": 0.3186, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 21.5, | |
| "grad_norm": 114.87351989746094, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.5843, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 21.5625, | |
| "grad_norm": 38.9747200012207, | |
| "learning_rate": 3.159722222222222e-05, | |
| "loss": 0.2425, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 21.625, | |
| "grad_norm": 60.7866096496582, | |
| "learning_rate": 3.1527777777777775e-05, | |
| "loss": 0.3217, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 21.6875, | |
| "grad_norm": 106.74617004394531, | |
| "learning_rate": 3.145833333333334e-05, | |
| "loss": 0.504, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 21.75, | |
| "grad_norm": 135.9730224609375, | |
| "learning_rate": 3.138888888888889e-05, | |
| "loss": 0.3214, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 21.8125, | |
| "grad_norm": 110.94549560546875, | |
| "learning_rate": 3.1319444444444446e-05, | |
| "loss": 0.3475, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 21.875, | |
| "grad_norm": 96.92147064208984, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.5358, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 21.9375, | |
| "grad_norm": 71.57472229003906, | |
| "learning_rate": 3.1180555555555555e-05, | |
| "loss": 0.4589, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 164.44607543945312, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.5776, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8387096774193549, | |
| "eval_auc": 0.9269957983193277, | |
| "eval_f1": 0.8529411764705882, | |
| "eval_loss": 0.39069586992263794, | |
| "eval_precision": 0.8529411764705882, | |
| "eval_recall": 0.8529411764705882, | |
| "eval_runtime": 1.9366, | |
| "eval_samples_per_second": 32.015, | |
| "eval_steps_per_second": 1.033, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 22.0625, | |
| "grad_norm": 118.7387924194336, | |
| "learning_rate": 3.104166666666667e-05, | |
| "loss": 0.4948, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 22.125, | |
| "grad_norm": 98.81047821044922, | |
| "learning_rate": 3.0972222222222226e-05, | |
| "loss": 0.3103, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 22.1875, | |
| "grad_norm": 26.512624740600586, | |
| "learning_rate": 3.090277777777778e-05, | |
| "loss": 0.2216, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 22.25, | |
| "grad_norm": 53.15692138671875, | |
| "learning_rate": 3.0833333333333335e-05, | |
| "loss": 0.4647, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 22.3125, | |
| "grad_norm": 78.6286392211914, | |
| "learning_rate": 3.076388888888889e-05, | |
| "loss": 0.365, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 22.375, | |
| "grad_norm": 55.01898193359375, | |
| "learning_rate": 3.069444444444445e-05, | |
| "loss": 0.3692, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 22.4375, | |
| "grad_norm": 39.68163299560547, | |
| "learning_rate": 3.0625000000000006e-05, | |
| "loss": 0.2894, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "grad_norm": 120.19679260253906, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.4181, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 22.5625, | |
| "grad_norm": 68.91941833496094, | |
| "learning_rate": 3.0486111111111115e-05, | |
| "loss": 0.5036, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 22.625, | |
| "grad_norm": 72.7096176147461, | |
| "learning_rate": 3.0416666666666666e-05, | |
| "loss": 0.5384, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 22.6875, | |
| "grad_norm": 100.89299774169922, | |
| "learning_rate": 3.034722222222222e-05, | |
| "loss": 0.3722, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 22.75, | |
| "grad_norm": 68.78106689453125, | |
| "learning_rate": 3.0277777777777776e-05, | |
| "loss": 0.55, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 22.8125, | |
| "grad_norm": 54.39569091796875, | |
| "learning_rate": 3.0208333333333334e-05, | |
| "loss": 0.4194, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 22.875, | |
| "grad_norm": 31.410484313964844, | |
| "learning_rate": 3.0138888888888888e-05, | |
| "loss": 0.2857, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 22.9375, | |
| "grad_norm": 57.578338623046875, | |
| "learning_rate": 3.0069444444444446e-05, | |
| "loss": 0.4926, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "grad_norm": 151.53012084960938, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4875, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8225806451612904, | |
| "eval_auc": 0.926470588235294, | |
| "eval_f1": 0.8450704225352113, | |
| "eval_loss": 0.36559081077575684, | |
| "eval_precision": 0.8108108108108109, | |
| "eval_recall": 0.8823529411764706, | |
| "eval_runtime": 1.9594, | |
| "eval_samples_per_second": 31.642, | |
| "eval_steps_per_second": 1.021, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 23.0625, | |
| "grad_norm": 44.12751770019531, | |
| "learning_rate": 2.9930555555555555e-05, | |
| "loss": 0.3138, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 23.125, | |
| "grad_norm": 58.954830169677734, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 0.3775, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 23.1875, | |
| "grad_norm": 26.135852813720703, | |
| "learning_rate": 2.9791666666666668e-05, | |
| "loss": 0.2591, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 23.25, | |
| "grad_norm": 62.40138626098633, | |
| "learning_rate": 2.9722222222222223e-05, | |
| "loss": 0.3695, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 23.3125, | |
| "grad_norm": 60.646183013916016, | |
| "learning_rate": 2.965277777777778e-05, | |
| "loss": 0.3589, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 23.375, | |
| "grad_norm": 88.36126708984375, | |
| "learning_rate": 2.9583333333333335e-05, | |
| "loss": 0.5168, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 23.4375, | |
| "grad_norm": 46.5753288269043, | |
| "learning_rate": 2.951388888888889e-05, | |
| "loss": 0.3464, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 23.5, | |
| "grad_norm": 91.99535369873047, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.4247, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 23.5625, | |
| "grad_norm": 49.523929595947266, | |
| "learning_rate": 2.9375000000000003e-05, | |
| "loss": 0.4344, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 23.625, | |
| "grad_norm": 54.50424575805664, | |
| "learning_rate": 2.9305555555555557e-05, | |
| "loss": 0.4092, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 23.6875, | |
| "grad_norm": 43.38228988647461, | |
| "learning_rate": 2.9236111111111115e-05, | |
| "loss": 0.2469, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 23.75, | |
| "grad_norm": 48.993412017822266, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.3167, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 23.8125, | |
| "grad_norm": 67.48350524902344, | |
| "learning_rate": 2.9097222222222224e-05, | |
| "loss": 0.2573, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 23.875, | |
| "grad_norm": 57.00615692138672, | |
| "learning_rate": 2.9027777777777782e-05, | |
| "loss": 0.4354, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 23.9375, | |
| "grad_norm": 75.92513275146484, | |
| "learning_rate": 2.8958333333333337e-05, | |
| "loss": 0.4081, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 174.88877868652344, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.5516, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8064516129032258, | |
| "eval_auc": 0.9243697478991597, | |
| "eval_f1": 0.8333333333333334, | |
| "eval_loss": 0.3794221878051758, | |
| "eval_precision": 0.7894736842105263, | |
| "eval_recall": 0.8823529411764706, | |
| "eval_runtime": 1.9326, | |
| "eval_samples_per_second": 32.081, | |
| "eval_steps_per_second": 1.035, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 24.0625, | |
| "grad_norm": 63.44384002685547, | |
| "learning_rate": 2.8819444444444443e-05, | |
| "loss": 0.4828, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 24.125, | |
| "grad_norm": 56.574588775634766, | |
| "learning_rate": 2.8749999999999997e-05, | |
| "loss": 0.5755, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 24.1875, | |
| "grad_norm": 45.03982925415039, | |
| "learning_rate": 2.8680555555555555e-05, | |
| "loss": 0.3155, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 24.25, | |
| "grad_norm": 75.03779602050781, | |
| "learning_rate": 2.861111111111111e-05, | |
| "loss": 0.3325, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 24.3125, | |
| "grad_norm": 53.46479797363281, | |
| "learning_rate": 2.8541666666666668e-05, | |
| "loss": 0.3432, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 24.375, | |
| "grad_norm": 65.31179809570312, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 0.4144, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 24.4375, | |
| "grad_norm": 93.96704864501953, | |
| "learning_rate": 2.8402777777777777e-05, | |
| "loss": 0.4689, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 24.5, | |
| "grad_norm": 53.54984664916992, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.4174, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 24.5625, | |
| "grad_norm": 84.127197265625, | |
| "learning_rate": 2.826388888888889e-05, | |
| "loss": 0.4033, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 24.625, | |
| "grad_norm": 100.4719009399414, | |
| "learning_rate": 2.8194444444444445e-05, | |
| "loss": 0.4023, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 24.6875, | |
| "grad_norm": 48.454376220703125, | |
| "learning_rate": 2.8125000000000003e-05, | |
| "loss": 0.3631, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 24.75, | |
| "grad_norm": 97.61786651611328, | |
| "learning_rate": 2.8055555555555557e-05, | |
| "loss": 0.4391, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 24.8125, | |
| "grad_norm": 90.77650451660156, | |
| "learning_rate": 2.7986111111111112e-05, | |
| "loss": 0.3198, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 24.875, | |
| "grad_norm": 56.34316635131836, | |
| "learning_rate": 2.791666666666667e-05, | |
| "loss": 0.3028, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 24.9375, | |
| "grad_norm": 56.22303009033203, | |
| "learning_rate": 2.7847222222222224e-05, | |
| "loss": 0.3363, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 94.18289947509766, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.2376, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8064516129032258, | |
| "eval_auc": 0.9275210084033613, | |
| "eval_f1": 0.8421052631578947, | |
| "eval_loss": 0.38999098539352417, | |
| "eval_precision": 0.7619047619047619, | |
| "eval_recall": 0.9411764705882353, | |
| "eval_runtime": 1.9189, | |
| "eval_samples_per_second": 32.31, | |
| "eval_steps_per_second": 1.042, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 25.0625, | |
| "grad_norm": 37.627017974853516, | |
| "learning_rate": 2.7708333333333337e-05, | |
| "loss": 0.3413, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 25.125, | |
| "grad_norm": 30.828754425048828, | |
| "learning_rate": 2.7638888888888892e-05, | |
| "loss": 0.3494, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 25.1875, | |
| "grad_norm": 62.38092803955078, | |
| "learning_rate": 2.7569444444444446e-05, | |
| "loss": 0.4031, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 25.25, | |
| "grad_norm": 61.06608581542969, | |
| "learning_rate": 2.7500000000000004e-05, | |
| "loss": 0.4108, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 25.3125, | |
| "grad_norm": 48.06837844848633, | |
| "learning_rate": 2.743055555555556e-05, | |
| "loss": 0.3223, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 25.375, | |
| "grad_norm": 38.35547637939453, | |
| "learning_rate": 2.7361111111111114e-05, | |
| "loss": 0.5251, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 25.4375, | |
| "grad_norm": 89.24491119384766, | |
| "learning_rate": 2.7291666666666665e-05, | |
| "loss": 0.5164, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 25.5, | |
| "grad_norm": 50.19062423706055, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.293, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 25.5625, | |
| "grad_norm": 75.44627380371094, | |
| "learning_rate": 2.7152777777777777e-05, | |
| "loss": 0.3971, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 25.625, | |
| "grad_norm": 42.66498565673828, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.2638, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 25.6875, | |
| "grad_norm": 46.950252532958984, | |
| "learning_rate": 2.701388888888889e-05, | |
| "loss": 0.4027, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 25.75, | |
| "grad_norm": 35.579078674316406, | |
| "learning_rate": 2.6944444444444445e-05, | |
| "loss": 0.3861, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 25.8125, | |
| "grad_norm": 64.6947021484375, | |
| "learning_rate": 2.6875e-05, | |
| "loss": 0.3807, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 25.875, | |
| "grad_norm": 78.13638305664062, | |
| "learning_rate": 2.6805555555555557e-05, | |
| "loss": 0.4848, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 25.9375, | |
| "grad_norm": 52.792789459228516, | |
| "learning_rate": 2.6736111111111112e-05, | |
| "loss": 0.3578, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 153.54739379882812, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.275, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8225806451612904, | |
| "eval_auc": 0.9322478991596639, | |
| "eval_f1": 0.8450704225352113, | |
| "eval_loss": 0.3614147901535034, | |
| "eval_precision": 0.8108108108108109, | |
| "eval_recall": 0.8823529411764706, | |
| "eval_runtime": 1.923, | |
| "eval_samples_per_second": 32.24, | |
| "eval_steps_per_second": 1.04, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 26.0625, | |
| "grad_norm": 117.4349136352539, | |
| "learning_rate": 2.6597222222222225e-05, | |
| "loss": 0.3249, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 26.125, | |
| "grad_norm": 43.56279373168945, | |
| "learning_rate": 2.652777777777778e-05, | |
| "loss": 0.3057, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 26.1875, | |
| "grad_norm": 36.80549240112305, | |
| "learning_rate": 2.6458333333333334e-05, | |
| "loss": 0.2349, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 26.25, | |
| "grad_norm": 50.33206558227539, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.3677, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 26.3125, | |
| "grad_norm": 90.7452163696289, | |
| "learning_rate": 2.6319444444444446e-05, | |
| "loss": 0.2694, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 26.375, | |
| "grad_norm": 79.48680877685547, | |
| "learning_rate": 2.625e-05, | |
| "loss": 0.5367, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 26.4375, | |
| "grad_norm": 76.93234252929688, | |
| "learning_rate": 2.618055555555556e-05, | |
| "loss": 0.3667, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 26.5, | |
| "grad_norm": 74.08578491210938, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.288, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 26.5625, | |
| "grad_norm": 77.3045654296875, | |
| "learning_rate": 2.604166666666667e-05, | |
| "loss": 0.4342, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 26.625, | |
| "grad_norm": 68.01839447021484, | |
| "learning_rate": 2.5972222222222226e-05, | |
| "loss": 0.3474, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 26.6875, | |
| "grad_norm": 19.478015899658203, | |
| "learning_rate": 2.590277777777778e-05, | |
| "loss": 0.2049, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 26.75, | |
| "grad_norm": 97.51011657714844, | |
| "learning_rate": 2.5833333333333336e-05, | |
| "loss": 0.6356, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 26.8125, | |
| "grad_norm": 69.35116577148438, | |
| "learning_rate": 2.5763888888888887e-05, | |
| "loss": 0.328, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 26.875, | |
| "grad_norm": 72.81779479980469, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 0.5902, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 26.9375, | |
| "grad_norm": 43.3619499206543, | |
| "learning_rate": 2.5625e-05, | |
| "loss": 0.3038, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "grad_norm": 253.28797912597656, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.5285, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8548387096774194, | |
| "eval_auc": 0.9359243697478992, | |
| "eval_f1": 0.8732394366197183, | |
| "eval_loss": 0.33258941769599915, | |
| "eval_precision": 0.8378378378378378, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.9261, | |
| "eval_samples_per_second": 32.19, | |
| "eval_steps_per_second": 1.038, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 27.0625, | |
| "grad_norm": 85.61891174316406, | |
| "learning_rate": 2.5486111111111112e-05, | |
| "loss": 0.4318, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 27.125, | |
| "grad_norm": 50.95888137817383, | |
| "learning_rate": 2.5416666666666667e-05, | |
| "loss": 0.4233, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 27.1875, | |
| "grad_norm": 92.60533142089844, | |
| "learning_rate": 2.534722222222222e-05, | |
| "loss": 0.7241, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 27.25, | |
| "grad_norm": 41.785282135009766, | |
| "learning_rate": 2.527777777777778e-05, | |
| "loss": 0.234, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 27.3125, | |
| "grad_norm": 78.1746826171875, | |
| "learning_rate": 2.5208333333333334e-05, | |
| "loss": 0.6551, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 27.375, | |
| "grad_norm": 111.29540252685547, | |
| "learning_rate": 2.513888888888889e-05, | |
| "loss": 0.6107, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 27.4375, | |
| "grad_norm": 27.14556884765625, | |
| "learning_rate": 2.5069444444444447e-05, | |
| "loss": 0.1846, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 27.5, | |
| "grad_norm": 56.8499870300293, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.3405, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 27.5625, | |
| "grad_norm": 18.762271881103516, | |
| "learning_rate": 2.4930555555555556e-05, | |
| "loss": 0.1898, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 27.625, | |
| "grad_norm": 119.3090591430664, | |
| "learning_rate": 2.4861111111111114e-05, | |
| "loss": 0.4205, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 27.6875, | |
| "grad_norm": 36.69664001464844, | |
| "learning_rate": 2.479166666666667e-05, | |
| "loss": 0.2131, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 27.75, | |
| "grad_norm": 67.54560852050781, | |
| "learning_rate": 2.4722222222222223e-05, | |
| "loss": 0.3711, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 27.8125, | |
| "grad_norm": 47.20517349243164, | |
| "learning_rate": 2.465277777777778e-05, | |
| "loss": 0.2076, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 27.875, | |
| "grad_norm": 54.34505081176758, | |
| "learning_rate": 2.4583333333333332e-05, | |
| "loss": 0.2704, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 27.9375, | |
| "grad_norm": 67.48538970947266, | |
| "learning_rate": 2.451388888888889e-05, | |
| "loss": 0.2752, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "grad_norm": 142.4190216064453, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.4273, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.8709677419354839, | |
| "eval_auc": 0.98109243697479, | |
| "eval_f1": 0.8888888888888888, | |
| "eval_loss": 0.2646819055080414, | |
| "eval_precision": 0.8421052631578947, | |
| "eval_recall": 0.9411764705882353, | |
| "eval_runtime": 1.9507, | |
| "eval_samples_per_second": 31.784, | |
| "eval_steps_per_second": 1.025, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 28.0625, | |
| "grad_norm": 75.59832763671875, | |
| "learning_rate": 2.4375e-05, | |
| "loss": 0.3276, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 28.125, | |
| "grad_norm": 40.402252197265625, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.2804, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 28.1875, | |
| "grad_norm": 95.81023406982422, | |
| "learning_rate": 2.4236111111111112e-05, | |
| "loss": 0.4781, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 28.25, | |
| "grad_norm": 39.70941925048828, | |
| "learning_rate": 2.4166666666666667e-05, | |
| "loss": 0.1875, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 28.3125, | |
| "grad_norm": 40.53486251831055, | |
| "learning_rate": 2.4097222222222225e-05, | |
| "loss": 0.2517, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 28.375, | |
| "grad_norm": 56.1978759765625, | |
| "learning_rate": 2.402777777777778e-05, | |
| "loss": 0.1931, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 28.4375, | |
| "grad_norm": 111.22602081298828, | |
| "learning_rate": 2.3958333333333334e-05, | |
| "loss": 0.4768, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 28.5, | |
| "grad_norm": 59.05950927734375, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.6638, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 28.5625, | |
| "grad_norm": 64.51776885986328, | |
| "learning_rate": 2.3819444444444443e-05, | |
| "loss": 0.3341, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 28.625, | |
| "grad_norm": 67.53648376464844, | |
| "learning_rate": 2.375e-05, | |
| "loss": 0.4273, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 28.6875, | |
| "grad_norm": 78.49746704101562, | |
| "learning_rate": 2.3680555555555556e-05, | |
| "loss": 0.3185, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "grad_norm": 77.06168365478516, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.6245, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 28.8125, | |
| "grad_norm": 96.53307342529297, | |
| "learning_rate": 2.354166666666667e-05, | |
| "loss": 0.4567, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 28.875, | |
| "grad_norm": 111.6141586303711, | |
| "learning_rate": 2.3472222222222223e-05, | |
| "loss": 0.2718, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 28.9375, | |
| "grad_norm": 20.222061157226562, | |
| "learning_rate": 2.3402777777777778e-05, | |
| "loss": 0.1668, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "grad_norm": 140.95428466796875, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.31, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.8387096774193549, | |
| "eval_auc": 0.9396008403361344, | |
| "eval_f1": 0.8529411764705882, | |
| "eval_loss": 0.3340640664100647, | |
| "eval_precision": 0.8529411764705882, | |
| "eval_recall": 0.8529411764705882, | |
| "eval_runtime": 1.9401, | |
| "eval_samples_per_second": 31.958, | |
| "eval_steps_per_second": 1.031, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 29.0625, | |
| "grad_norm": 102.17808532714844, | |
| "learning_rate": 2.326388888888889e-05, | |
| "loss": 0.4793, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 29.125, | |
| "grad_norm": 194.98696899414062, | |
| "learning_rate": 2.3194444444444445e-05, | |
| "loss": 0.3459, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 29.1875, | |
| "grad_norm": 130.52801513671875, | |
| "learning_rate": 2.3125000000000003e-05, | |
| "loss": 0.5329, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 29.25, | |
| "grad_norm": 42.69224548339844, | |
| "learning_rate": 2.3055555555555558e-05, | |
| "loss": 0.1876, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 29.3125, | |
| "grad_norm": 64.0096664428711, | |
| "learning_rate": 2.2986111111111112e-05, | |
| "loss": 0.2573, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 29.375, | |
| "grad_norm": 69.68462371826172, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.377, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 29.4375, | |
| "grad_norm": 66.27143096923828, | |
| "learning_rate": 2.284722222222222e-05, | |
| "loss": 0.3805, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 29.5, | |
| "grad_norm": 33.939876556396484, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.3259, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 29.5625, | |
| "grad_norm": 58.171016693115234, | |
| "learning_rate": 2.2708333333333334e-05, | |
| "loss": 0.6124, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 29.625, | |
| "grad_norm": 62.77367401123047, | |
| "learning_rate": 2.263888888888889e-05, | |
| "loss": 0.3582, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 29.6875, | |
| "grad_norm": 57.211177825927734, | |
| "learning_rate": 2.2569444444444447e-05, | |
| "loss": 0.4051, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 29.75, | |
| "grad_norm": 98.49055480957031, | |
| "learning_rate": 2.25e-05, | |
| "loss": 0.2648, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 29.8125, | |
| "grad_norm": 32.86750411987305, | |
| "learning_rate": 2.2430555555555556e-05, | |
| "loss": 0.24, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 29.875, | |
| "grad_norm": 62.225521087646484, | |
| "learning_rate": 2.2361111111111114e-05, | |
| "loss": 0.2557, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 29.9375, | |
| "grad_norm": 98.8927001953125, | |
| "learning_rate": 2.229166666666667e-05, | |
| "loss": 0.425, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 231.0799102783203, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.7769, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8548387096774194, | |
| "eval_auc": 0.9506302521008404, | |
| "eval_f1": 0.8732394366197183, | |
| "eval_loss": 0.2989482879638672, | |
| "eval_precision": 0.8378378378378378, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.9367, | |
| "eval_samples_per_second": 32.013, | |
| "eval_steps_per_second": 1.033, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 30.0625, | |
| "grad_norm": 97.84791564941406, | |
| "learning_rate": 2.2152777777777778e-05, | |
| "loss": 0.6821, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 30.125, | |
| "grad_norm": 97.56119537353516, | |
| "learning_rate": 2.2083333333333333e-05, | |
| "loss": 0.298, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 30.1875, | |
| "grad_norm": 102.7960205078125, | |
| "learning_rate": 2.201388888888889e-05, | |
| "loss": 0.4884, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 30.25, | |
| "grad_norm": 73.4170150756836, | |
| "learning_rate": 2.1944444444444445e-05, | |
| "loss": 0.319, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 30.3125, | |
| "grad_norm": 157.68368530273438, | |
| "learning_rate": 2.1875e-05, | |
| "loss": 0.3973, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 30.375, | |
| "grad_norm": 55.67268371582031, | |
| "learning_rate": 2.1805555555555558e-05, | |
| "loss": 0.288, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 30.4375, | |
| "grad_norm": 71.78160858154297, | |
| "learning_rate": 2.1736111111111112e-05, | |
| "loss": 0.533, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 30.5, | |
| "grad_norm": 128.58132934570312, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.32, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 30.5625, | |
| "grad_norm": 84.67550659179688, | |
| "learning_rate": 2.1597222222222225e-05, | |
| "loss": 0.3051, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 30.625, | |
| "grad_norm": 29.67072296142578, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 0.3061, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 30.6875, | |
| "grad_norm": 21.23928451538086, | |
| "learning_rate": 2.1458333333333334e-05, | |
| "loss": 0.1565, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 30.75, | |
| "grad_norm": 75.22709655761719, | |
| "learning_rate": 2.138888888888889e-05, | |
| "loss": 0.3763, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 30.8125, | |
| "grad_norm": 68.2527084350586, | |
| "learning_rate": 2.1319444444444444e-05, | |
| "loss": 0.3484, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 30.875, | |
| "grad_norm": 93.65040588378906, | |
| "learning_rate": 2.125e-05, | |
| "loss": 0.5086, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 30.9375, | |
| "grad_norm": 91.93578338623047, | |
| "learning_rate": 2.1180555555555556e-05, | |
| "loss": 0.6098, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "grad_norm": 396.6805114746094, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.4993, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8709677419354839, | |
| "eval_auc": 0.9632352941176471, | |
| "eval_f1": 0.8888888888888888, | |
| "eval_loss": 0.2791585624217987, | |
| "eval_precision": 0.8421052631578947, | |
| "eval_recall": 0.9411764705882353, | |
| "eval_runtime": 1.8964, | |
| "eval_samples_per_second": 32.694, | |
| "eval_steps_per_second": 1.055, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 31.0625, | |
| "grad_norm": 218.7271728515625, | |
| "learning_rate": 2.104166666666667e-05, | |
| "loss": 0.5967, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 31.125, | |
| "grad_norm": 85.2174072265625, | |
| "learning_rate": 2.0972222222222223e-05, | |
| "loss": 0.2821, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 31.1875, | |
| "grad_norm": 55.23520278930664, | |
| "learning_rate": 2.0902777777777778e-05, | |
| "loss": 0.1794, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 31.25, | |
| "grad_norm": 58.78559112548828, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.2058, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 31.3125, | |
| "grad_norm": 100.98091888427734, | |
| "learning_rate": 2.076388888888889e-05, | |
| "loss": 0.287, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 31.375, | |
| "grad_norm": 48.73373031616211, | |
| "learning_rate": 2.0694444444444445e-05, | |
| "loss": 0.1958, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 31.4375, | |
| "grad_norm": 47.07331848144531, | |
| "learning_rate": 2.0625e-05, | |
| "loss": 0.3669, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 31.5, | |
| "grad_norm": 68.89096069335938, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.2905, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 31.5625, | |
| "grad_norm": 51.24907302856445, | |
| "learning_rate": 2.0486111111111113e-05, | |
| "loss": 0.3512, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 31.625, | |
| "grad_norm": 73.44024658203125, | |
| "learning_rate": 2.0416666666666667e-05, | |
| "loss": 0.2269, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 31.6875, | |
| "grad_norm": 71.18965148925781, | |
| "learning_rate": 2.0347222222222222e-05, | |
| "loss": 0.3371, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 31.75, | |
| "grad_norm": 98.83439636230469, | |
| "learning_rate": 2.027777777777778e-05, | |
| "loss": 0.5882, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 31.8125, | |
| "grad_norm": 111.71282958984375, | |
| "learning_rate": 2.0208333333333334e-05, | |
| "loss": 0.3465, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 31.875, | |
| "grad_norm": 159.08973693847656, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.6081, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 31.9375, | |
| "grad_norm": 68.47103881835938, | |
| "learning_rate": 2.0069444444444447e-05, | |
| "loss": 0.3763, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "grad_norm": 43.89309310913086, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2188, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8709677419354839, | |
| "eval_auc": 0.9663865546218487, | |
| "eval_f1": 0.8857142857142857, | |
| "eval_loss": 0.26347893476486206, | |
| "eval_precision": 0.8611111111111112, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.939, | |
| "eval_samples_per_second": 31.976, | |
| "eval_steps_per_second": 1.031, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 32.0625, | |
| "grad_norm": 46.497779846191406, | |
| "learning_rate": 1.9930555555555556e-05, | |
| "loss": 0.3708, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 32.125, | |
| "grad_norm": 167.9232940673828, | |
| "learning_rate": 1.986111111111111e-05, | |
| "loss": 0.4261, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 32.1875, | |
| "grad_norm": 61.328529357910156, | |
| "learning_rate": 1.9791666666666665e-05, | |
| "loss": 0.3391, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 32.25, | |
| "grad_norm": 170.238037109375, | |
| "learning_rate": 1.9722222222222224e-05, | |
| "loss": 0.4698, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 32.3125, | |
| "grad_norm": 35.044010162353516, | |
| "learning_rate": 1.9652777777777778e-05, | |
| "loss": 0.1823, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 32.375, | |
| "grad_norm": 77.83676147460938, | |
| "learning_rate": 1.9583333333333333e-05, | |
| "loss": 0.3278, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 32.4375, | |
| "grad_norm": 46.95936965942383, | |
| "learning_rate": 1.951388888888889e-05, | |
| "loss": 0.3318, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 32.5, | |
| "grad_norm": 149.09030151367188, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.3393, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 32.5625, | |
| "grad_norm": 67.16770935058594, | |
| "learning_rate": 1.9375e-05, | |
| "loss": 0.4492, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 32.625, | |
| "grad_norm": 55.898834228515625, | |
| "learning_rate": 1.9305555555555558e-05, | |
| "loss": 0.3798, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 32.6875, | |
| "grad_norm": 28.289344787597656, | |
| "learning_rate": 1.9236111111111113e-05, | |
| "loss": 0.1741, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 32.75, | |
| "grad_norm": 86.767333984375, | |
| "learning_rate": 1.9166666666666667e-05, | |
| "loss": 0.3531, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 32.8125, | |
| "grad_norm": 53.152278900146484, | |
| "learning_rate": 1.9097222222222222e-05, | |
| "loss": 0.1571, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 32.875, | |
| "grad_norm": 30.3239688873291, | |
| "learning_rate": 1.9027777777777776e-05, | |
| "loss": 0.2651, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 32.9375, | |
| "grad_norm": 83.10792541503906, | |
| "learning_rate": 1.8958333333333334e-05, | |
| "loss": 0.2756, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "grad_norm": 55.581485748291016, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.1285, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8709677419354839, | |
| "eval_auc": 0.9705882352941176, | |
| "eval_f1": 0.8857142857142857, | |
| "eval_loss": 0.2574561536312103, | |
| "eval_precision": 0.8611111111111112, | |
| "eval_recall": 0.9117647058823529, | |
| "eval_runtime": 1.9165, | |
| "eval_samples_per_second": 32.351, | |
| "eval_steps_per_second": 1.044, | |
| "step": 528 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 15, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.2633566842967654e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |