| { | |
| "best_metric": 0.29150861501693726, | |
| "best_model_checkpoint": "/content/aptner_securebert/checkpoint-1000", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 8430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.881376037959668e-05, | |
| "loss": 0.8252, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.9112066064355795, | |
| "eval_f1": 0.43980307325078327, | |
| "eval_loss": 0.37714093923568726, | |
| "eval_precision": 0.4382991376746952, | |
| "eval_recall": 0.4413173652694611, | |
| "eval_runtime": 9.5105, | |
| "eval_samples_per_second": 183.902, | |
| "eval_steps_per_second": 23.027, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.762752075919336e-05, | |
| "loss": 0.3593, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.921147324548914, | |
| "eval_f1": 0.5621327218002007, | |
| "eval_loss": 0.29150861501693726, | |
| "eval_precision": 0.5391806433874072, | |
| "eval_recall": 0.587125748502994, | |
| "eval_runtime": 8.0468, | |
| "eval_samples_per_second": 217.354, | |
| "eval_steps_per_second": 27.216, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.6441281138790037e-05, | |
| "loss": 0.2704, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.9202930440860494, | |
| "eval_f1": 0.5818232897878916, | |
| "eval_loss": 0.29487740993499756, | |
| "eval_precision": 0.5480285789891506, | |
| "eval_recall": 0.620059880239521, | |
| "eval_runtime": 8.4381, | |
| "eval_samples_per_second": 207.274, | |
| "eval_steps_per_second": 25.954, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.5255041518386714e-05, | |
| "loss": 0.2308, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_accuracy": 0.9187139195940873, | |
| "eval_f1": 0.5872949095498528, | |
| "eval_loss": 0.2987907826900482, | |
| "eval_precision": 0.5523608546557637, | |
| "eval_recall": 0.6269461077844312, | |
| "eval_runtime": 9.164, | |
| "eval_samples_per_second": 190.856, | |
| "eval_steps_per_second": 23.898, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.4068801897983393e-05, | |
| "loss": 0.1934, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.9152191358823681, | |
| "eval_f1": 0.5884261763115197, | |
| "eval_loss": 0.3123273551464081, | |
| "eval_precision": 0.5364891518737672, | |
| "eval_recall": 0.651497005988024, | |
| "eval_runtime": 8.3207, | |
| "eval_samples_per_second": 210.198, | |
| "eval_steps_per_second": 26.32, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.2882562277580073e-05, | |
| "loss": 0.1567, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_accuracy": 0.9210178881151466, | |
| "eval_f1": 0.60329995769285, | |
| "eval_loss": 0.3127841353416443, | |
| "eval_precision": 0.5702479338842975, | |
| "eval_recall": 0.6404191616766467, | |
| "eval_runtime": 9.3047, | |
| "eval_samples_per_second": 187.97, | |
| "eval_steps_per_second": 23.537, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.169632265717675e-05, | |
| "loss": 0.1471, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_accuracy": 0.911724352170649, | |
| "eval_f1": 0.5778824833702882, | |
| "eval_loss": 0.36513394117355347, | |
| "eval_precision": 0.5379256965944272, | |
| "eval_recall": 0.624251497005988, | |
| "eval_runtime": 8.1308, | |
| "eval_samples_per_second": 215.109, | |
| "eval_steps_per_second": 26.935, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.0510083036773429e-05, | |
| "loss": 0.1249, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_accuracy": 0.9124750834864997, | |
| "eval_f1": 0.5903890160183066, | |
| "eval_loss": 0.37713900208473206, | |
| "eval_precision": 0.5363169479090242, | |
| "eval_recall": 0.6565868263473054, | |
| "eval_runtime": 8.3407, | |
| "eval_samples_per_second": 209.696, | |
| "eval_steps_per_second": 26.257, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 9.323843416370107e-06, | |
| "loss": 0.1106, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "eval_accuracy": 0.9155556706101633, | |
| "eval_f1": 0.5961159583450605, | |
| "eval_loss": 0.38660773634910583, | |
| "eval_precision": 0.5624004248539565, | |
| "eval_recall": 0.6341317365269461, | |
| "eval_runtime": 9.5112, | |
| "eval_samples_per_second": 183.888, | |
| "eval_steps_per_second": 23.025, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.137603795966786e-06, | |
| "loss": 0.1063, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_accuracy": 0.9190504543218825, | |
| "eval_f1": 0.6034311640436694, | |
| "eval_loss": 0.3753737509250641, | |
| "eval_precision": 0.5731214651225425, | |
| "eval_recall": 0.637125748502994, | |
| "eval_runtime": 9.1697, | |
| "eval_samples_per_second": 190.738, | |
| "eval_steps_per_second": 23.883, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 6.951364175563464e-06, | |
| "loss": 0.0835, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_accuracy": 0.9164617256465349, | |
| "eval_f1": 0.5957269700332963, | |
| "eval_loss": 0.4014611542224884, | |
| "eval_precision": 0.5550672182006204, | |
| "eval_recall": 0.6428143712574851, | |
| "eval_runtime": 8.292, | |
| "eval_samples_per_second": 210.925, | |
| "eval_steps_per_second": 26.411, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 5.765124555160143e-06, | |
| "loss": 0.0854, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.913847109684434, | |
| "eval_f1": 0.5903713892709767, | |
| "eval_loss": 0.4325053095817566, | |
| "eval_precision": 0.546055979643766, | |
| "eval_recall": 0.6425149700598802, | |
| "eval_runtime": 8.4954, | |
| "eval_samples_per_second": 205.876, | |
| "eval_steps_per_second": 25.779, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 4.5788849347568215e-06, | |
| "loss": 0.0743, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_accuracy": 0.9178596391312227, | |
| "eval_f1": 0.6029001673173453, | |
| "eval_loss": 0.4183894395828247, | |
| "eval_precision": 0.56419624217119, | |
| "eval_recall": 0.6473053892215569, | |
| "eval_runtime": 9.3097, | |
| "eval_samples_per_second": 187.868, | |
| "eval_steps_per_second": 23.524, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 3.3926453143535e-06, | |
| "loss": 0.0704, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "eval_accuracy": 0.9172124569623857, | |
| "eval_f1": 0.594678304941574, | |
| "eval_loss": 0.43149828910827637, | |
| "eval_precision": 0.5612543183630082, | |
| "eval_recall": 0.6323353293413174, | |
| "eval_runtime": 8.504, | |
| "eval_samples_per_second": 205.668, | |
| "eval_steps_per_second": 25.753, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 2.2064056939501782e-06, | |
| "loss": 0.06, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_accuracy": 0.9175748789769345, | |
| "eval_f1": 0.5993832352116626, | |
| "eval_loss": 0.4353819489479065, | |
| "eval_precision": 0.5635213494992093, | |
| "eval_recall": 0.640119760479042, | |
| "eval_runtime": 9.2124, | |
| "eval_samples_per_second": 189.854, | |
| "eval_steps_per_second": 23.772, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 1.0201660735468566e-06, | |
| "loss": 0.0612, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "eval_accuracy": 0.9179114137047296, | |
| "eval_f1": 0.6020393909763935, | |
| "eval_loss": 0.4452006220817566, | |
| "eval_precision": 0.5642838439382037, | |
| "eval_recall": 0.6452095808383234, | |
| "eval_runtime": 7.969, | |
| "eval_samples_per_second": 219.474, | |
| "eval_steps_per_second": 27.481, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 8430, | |
| "total_flos": 2295335431882416.0, | |
| "train_loss": 0.17847706194025767, | |
| "train_runtime": 1432.5205, | |
| "train_samples_per_second": 47.078, | |
| "train_steps_per_second": 5.885 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8430, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 2295335431882416.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |