| { | |
| "best_metric": 0.04287773743271828, | |
| "best_model_checkpoint": "autotrain-5ozhd-efa4o/checkpoint-72", | |
| "epoch": 18.0, | |
| "eval_steps": 500, | |
| "global_step": 72, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.6818, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.8124, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.5196, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.8215, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_auc": 0.41666666666666663, | |
| "eval_f1": 0.75, | |
| "eval_loss": 0.5936104655265808, | |
| "eval_precision": 0.75, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 0.2459, | |
| "eval_samples_per_second": 28.47, | |
| "eval_steps_per_second": 4.067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.9638, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.659, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.9674, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.9059, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7142857142857143, | |
| "eval_auc": 0.5, | |
| "eval_f1": 0.75, | |
| "eval_loss": 0.5316336750984192, | |
| "eval_precision": 0.75, | |
| "eval_recall": 0.75, | |
| "eval_runtime": 0.2429, | |
| "eval_samples_per_second": 28.813, | |
| "eval_steps_per_second": 4.116, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.7961, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6182, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.930555555555556e-05, | |
| "loss": 0.5245, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 0.3528, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 0.7500000000000001, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.4492535889148712, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2334, | |
| "eval_samples_per_second": 29.991, | |
| "eval_steps_per_second": 4.284, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 4.791666666666667e-05, | |
| "loss": 0.5171, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.4058, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 4.652777777777778e-05, | |
| "loss": 0.2961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.5833333333333334e-05, | |
| "loss": 0.6474, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 0.9166666666666667, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.348563015460968, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2304, | |
| "eval_samples_per_second": 30.388, | |
| "eval_steps_per_second": 4.341, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 4.5138888888888894e-05, | |
| "loss": 0.244, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.2783, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.75, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.3117, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.305555555555556e-05, | |
| "loss": 0.178, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.2634625732898712, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2419, | |
| "eval_samples_per_second": 28.936, | |
| "eval_steps_per_second": 4.134, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.25, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 0.2442, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.2336, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 4.0972222222222225e-05, | |
| "loss": 0.1733, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.027777777777778e-05, | |
| "loss": 0.3612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.2078421264886856, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.23, | |
| "eval_samples_per_second": 30.428, | |
| "eval_steps_per_second": 4.347, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 3.958333333333333e-05, | |
| "loss": 0.1645, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1022, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.75, | |
| "learning_rate": 3.8194444444444444e-05, | |
| "loss": 0.1811, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.044, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.172084242105484, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2324, | |
| "eval_samples_per_second": 30.126, | |
| "eval_steps_per_second": 4.304, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "learning_rate": 3.6805555555555556e-05, | |
| "loss": 0.217, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.1082, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "learning_rate": 3.541666666666667e-05, | |
| "loss": 0.1583, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3623, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.1323634535074234, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.235, | |
| "eval_samples_per_second": 29.785, | |
| "eval_steps_per_second": 4.255, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.25, | |
| "learning_rate": 3.402777777777778e-05, | |
| "loss": 0.035, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1694, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.75, | |
| "learning_rate": 3.263888888888889e-05, | |
| "loss": 0.0791, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.194444444444444e-05, | |
| "loss": 0.043, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.1202654168009758, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2369, | |
| "eval_samples_per_second": 29.552, | |
| "eval_steps_per_second": 4.222, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.1728, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.2055, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 9.75, | |
| "learning_rate": 2.9861111111111113e-05, | |
| "loss": 0.0609, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.0123, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.1008061096072197, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2372, | |
| "eval_samples_per_second": 29.514, | |
| "eval_steps_per_second": 4.216, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 2.8472222222222223e-05, | |
| "loss": 0.1631, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0666, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.0095, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 2.6388888888888892e-05, | |
| "loss": 0.0165, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.086181640625, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2365, | |
| "eval_samples_per_second": 29.599, | |
| "eval_steps_per_second": 4.228, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 11.25, | |
| "learning_rate": 2.5694444444444445e-05, | |
| "loss": 0.0071, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0273, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 11.75, | |
| "learning_rate": 2.4305555555555558e-05, | |
| "loss": 0.0077, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 2.361111111111111e-05, | |
| "loss": 0.0156, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0849238708615303, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2379, | |
| "eval_samples_per_second": 29.419, | |
| "eval_steps_per_second": 4.203, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 12.25, | |
| "learning_rate": 2.2916666666666667e-05, | |
| "loss": 0.0043, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 12.75, | |
| "learning_rate": 2.152777777777778e-05, | |
| "loss": 0.0095, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.0052, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.07886940985918045, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2319, | |
| "eval_samples_per_second": 30.181, | |
| "eval_steps_per_second": 4.312, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 13.25, | |
| "learning_rate": 2.013888888888889e-05, | |
| "loss": 0.0147, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0156, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 13.75, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 0.0188, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.8055555555555555e-05, | |
| "loss": 0.0017, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0678296759724617, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2316, | |
| "eval_samples_per_second": 30.221, | |
| "eval_steps_per_second": 4.317, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.0117, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0072, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 14.75, | |
| "learning_rate": 1.597222222222222e-05, | |
| "loss": 0.004, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.527777777777778e-05, | |
| "loss": 0.0028, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.05511965602636337, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2451, | |
| "eval_samples_per_second": 28.561, | |
| "eval_steps_per_second": 4.08, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 15.25, | |
| "learning_rate": 1.4583333333333335e-05, | |
| "loss": 0.0099, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0082, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 1.3194444444444446e-05, | |
| "loss": 0.005, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.25e-05, | |
| "loss": 0.0043, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.04743194580078125, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2312, | |
| "eval_samples_per_second": 30.271, | |
| "eval_steps_per_second": 4.324, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 16.25, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.2229, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0214, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 16.75, | |
| "learning_rate": 1.0416666666666668e-05, | |
| "loss": 0.0079, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.0022, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.04407283291220665, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.231, | |
| "eval_samples_per_second": 30.304, | |
| "eval_steps_per_second": 4.329, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 17.25, | |
| "learning_rate": 9.027777777777777e-06, | |
| "loss": 0.0155, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0181, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 17.75, | |
| "learning_rate": 7.63888888888889e-06, | |
| "loss": 0.0042, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.0035, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 1.0, | |
| "eval_auc": 1.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.04287773743271828, | |
| "eval_precision": 1.0, | |
| "eval_recall": 1.0, | |
| "eval_runtime": 0.2292, | |
| "eval_samples_per_second": 30.539, | |
| "eval_steps_per_second": 4.363, | |
| "step": 72 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 80, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 3.766110695269171e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |