| { | |
| "best_metric": 0.40832215547561646, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-8000", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6721, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1e-05, | |
| "loss": 0.5211, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.5088, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4878, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4926, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5278, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.4698, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5079, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.5097, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5008, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.583, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.5405, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.5719, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.5587, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.5935, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.6098, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.5785, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.5504, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.528, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5097, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.82325, | |
| "eval_auc": 0.7562535655558911, | |
| "eval_f1": 0.4812912692589876, | |
| "eval_loss": 0.46430468559265137, | |
| "eval_precision": 0.8793565683646113, | |
| "eval_recall": 0.33131313131313134, | |
| "eval_runtime": 732.6664, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 0.341, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.4879, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.4754, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.4998, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.491, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.4905, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.4822, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.4856, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4613, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.4575, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4852, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.4677, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.471, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.5252, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.4541, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.4445, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.4596, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.4849, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.4627, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.4527, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.5032, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.81575, | |
| "eval_auc": 0.6002357461659787, | |
| "eval_f1": 0.43088803088803085, | |
| "eval_loss": 0.4803480803966522, | |
| "eval_precision": 0.9147540983606557, | |
| "eval_recall": 0.2818181818181818, | |
| "eval_runtime": 839.8305, | |
| "eval_samples_per_second": 4.763, | |
| "eval_steps_per_second": 0.298, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.4538, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.5285, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.521, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.4688, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.475, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 3e-05, | |
| "loss": 0.4601, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.4704, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.4612, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.5431, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.4435, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.5247, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.4707, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.4859, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.4493, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4551, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.4418, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.4, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.4447, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 2.95, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.4662, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.4614, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8225, | |
| "eval_auc": 0.8300171146682774, | |
| "eval_f1": 0.4637462235649546, | |
| "eval_loss": 0.4134385883808136, | |
| "eval_precision": 0.9191616766467066, | |
| "eval_recall": 0.3101010101010101, | |
| "eval_runtime": 1074.678, | |
| "eval_samples_per_second": 3.722, | |
| "eval_steps_per_second": 0.233, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.3887, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.4219, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.4113, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4091, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.4306, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.3961, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.4306, | |
| "step": 6700 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.3746, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 3.45, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.3861, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.4354, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.55, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 0.426, | |
| "step": 7100 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.3891, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 3.65, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.4191, | |
| "step": 7300 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.3823, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 3.75, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.4206, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.374, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.3572, | |
| "step": 7700 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.395, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 3.95, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.3888, | |
| "step": 7900 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.3896, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.82275, | |
| "eval_auc": 0.8514470284237725, | |
| "eval_f1": 0.6293779404077365, | |
| "eval_loss": 0.40832215547561646, | |
| "eval_precision": 0.6522210184182016, | |
| "eval_recall": 0.6080808080808081, | |
| "eval_runtime": 1078.952, | |
| "eval_samples_per_second": 3.707, | |
| "eval_steps_per_second": 0.232, | |
| "step": 8000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10000, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 382369628160000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |