| { | |
| "best_metric": 0.3229984641075134, | |
| "best_model_checkpoint": "/content/aptner_secbert/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": 0.6662, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_accuracy": 0.911311819052302, | |
| "eval_f1": 0.47436855477507095, | |
| "eval_loss": 0.3586784601211548, | |
| "eval_precision": 0.4744394618834081, | |
| "eval_recall": 0.4742976688583383, | |
| "eval_runtime": 4.8219, | |
| "eval_samples_per_second": 362.722, | |
| "eval_steps_per_second": 45.418, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.762752075919336e-05, | |
| "loss": 0.3128, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.9142102947646282, | |
| "eval_f1": 0.5237468946368552, | |
| "eval_loss": 0.3229984641075134, | |
| "eval_precision": 0.5124392336288247, | |
| "eval_recall": 0.5355648535564853, | |
| "eval_runtime": 5.7669, | |
| "eval_samples_per_second": 303.284, | |
| "eval_steps_per_second": 37.976, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 1.6441281138790037e-05, | |
| "loss": 0.2374, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.9082580678553868, | |
| "eval_f1": 0.5187898521231854, | |
| "eval_loss": 0.34285473823547363, | |
| "eval_precision": 0.4750310559006211, | |
| "eval_recall": 0.5714285714285714, | |
| "eval_runtime": 4.9866, | |
| "eval_samples_per_second": 350.74, | |
| "eval_steps_per_second": 43.918, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "learning_rate": 1.5255041518386714e-05, | |
| "loss": 0.1904, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.37, | |
| "eval_accuracy": 0.9090085660308999, | |
| "eval_f1": 0.5250911129800953, | |
| "eval_loss": 0.3649776577949524, | |
| "eval_precision": 0.4944561774023231, | |
| "eval_recall": 0.5597728631201434, | |
| "eval_runtime": 6.0964, | |
| "eval_samples_per_second": 286.889, | |
| "eval_steps_per_second": 35.923, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 1.4068801897983393e-05, | |
| "loss": 0.1521, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.9055148676276494, | |
| "eval_f1": 0.5193236714975844, | |
| "eval_loss": 0.3764529228210449, | |
| "eval_precision": 0.47126156843643446, | |
| "eval_recall": 0.578302450687388, | |
| "eval_runtime": 4.7083, | |
| "eval_samples_per_second": 371.472, | |
| "eval_steps_per_second": 46.514, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 1.2882562277580073e-05, | |
| "loss": 0.1101, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "eval_accuracy": 0.9067053130094976, | |
| "eval_f1": 0.5186184565569347, | |
| "eval_loss": 0.4022673964500427, | |
| "eval_precision": 0.47270044269552386, | |
| "eval_recall": 0.5744172145845786, | |
| "eval_runtime": 6.0924, | |
| "eval_samples_per_second": 287.079, | |
| "eval_steps_per_second": 35.946, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 1.169632265717675e-05, | |
| "loss": 0.1019, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "eval_accuracy": 0.9056183846173753, | |
| "eval_f1": 0.5113854595336077, | |
| "eval_loss": 0.4321642816066742, | |
| "eval_precision": 0.4726166328600406, | |
| "eval_recall": 0.557083084279737, | |
| "eval_runtime": 4.6968, | |
| "eval_samples_per_second": 372.38, | |
| "eval_steps_per_second": 46.627, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 1.0510083036773429e-05, | |
| "loss": 0.0764, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "eval_accuracy": 0.9039103542868974, | |
| "eval_f1": 0.5162894151511187, | |
| "eval_loss": 0.45951634645462036, | |
| "eval_precision": 0.45915755178031187, | |
| "eval_recall": 0.5896592946802152, | |
| "eval_runtime": 5.335, | |
| "eval_samples_per_second": 327.836, | |
| "eval_steps_per_second": 41.05, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "learning_rate": 9.323843416370107e-06, | |
| "loss": 0.0619, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.34, | |
| "eval_accuracy": 0.9062394865557309, | |
| "eval_f1": 0.5210016155088852, | |
| "eval_loss": 0.4754575192928314, | |
| "eval_precision": 0.4740323370896619, | |
| "eval_recall": 0.578302450687388, | |
| "eval_runtime": 4.7666, | |
| "eval_samples_per_second": 366.931, | |
| "eval_steps_per_second": 45.945, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "learning_rate": 8.137603795966786e-06, | |
| "loss": 0.059, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.93, | |
| "eval_accuracy": 0.9126057814238762, | |
| "eval_f1": 0.5335215243472125, | |
| "eval_loss": 0.4513537883758545, | |
| "eval_precision": 0.5054827493982348, | |
| "eval_recall": 0.5648535564853556, | |
| "eval_runtime": 5.2044, | |
| "eval_samples_per_second": 336.062, | |
| "eval_steps_per_second": 42.08, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 6.951364175563464e-06, | |
| "loss": 0.0429, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "eval_accuracy": 0.9064982790300458, | |
| "eval_f1": 0.5161992921317724, | |
| "eval_loss": 0.5036054849624634, | |
| "eval_precision": 0.474, | |
| "eval_recall": 0.56664674237896, | |
| "eval_runtime": 5.0417, | |
| "eval_samples_per_second": 346.906, | |
| "eval_steps_per_second": 43.438, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "learning_rate": 5.765124555160143e-06, | |
| "loss": 0.0425, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.12, | |
| "eval_accuracy": 0.9064465205351828, | |
| "eval_f1": 0.5202987101154106, | |
| "eval_loss": 0.5248968601226807, | |
| "eval_precision": 0.4767355063448619, | |
| "eval_recall": 0.5726240286909743, | |
| "eval_runtime": 5.2522, | |
| "eval_samples_per_second": 333.002, | |
| "eval_steps_per_second": 41.697, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "learning_rate": 4.5788849347568215e-06, | |
| "loss": 0.0349, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "eval_accuracy": 0.9038068372971714, | |
| "eval_f1": 0.5129436882839604, | |
| "eval_loss": 0.5536536574363708, | |
| "eval_precision": 0.4633558341369335, | |
| "eval_recall": 0.5744172145845786, | |
| "eval_runtime": 6.0569, | |
| "eval_samples_per_second": 288.76, | |
| "eval_steps_per_second": 36.157, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 3.3926453143535e-06, | |
| "loss": 0.0338, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "eval_accuracy": 0.9089050490411739, | |
| "eval_f1": 0.5222894881673087, | |
| "eval_loss": 0.5301496982574463, | |
| "eval_precision": 0.48393676695563487, | |
| "eval_recall": 0.5672444710101614, | |
| "eval_runtime": 4.7724, | |
| "eval_samples_per_second": 366.479, | |
| "eval_steps_per_second": 45.888, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 2.2064056939501782e-06, | |
| "loss": 0.0255, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_accuracy": 0.9059030563391216, | |
| "eval_f1": 0.5185085112131855, | |
| "eval_loss": 0.5545291900634766, | |
| "eval_precision": 0.47312623274161736, | |
| "eval_recall": 0.5735206216377764, | |
| "eval_runtime": 6.0864, | |
| "eval_samples_per_second": 287.36, | |
| "eval_steps_per_second": 35.982, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "learning_rate": 1.0201660735468566e-06, | |
| "loss": 0.0253, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 9.49, | |
| "eval_accuracy": 0.9074040526901478, | |
| "eval_f1": 0.5206002728512961, | |
| "eval_loss": 0.5526126623153687, | |
| "eval_precision": 0.4789156626506024, | |
| "eval_recall": 0.5702331141661685, | |
| "eval_runtime": 4.9232, | |
| "eval_samples_per_second": 355.259, | |
| "eval_steps_per_second": 44.483, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 8430, | |
| "total_flos": 1073540244786240.0, | |
| "train_loss": 0.1301219513690627, | |
| "train_runtime": 784.9898, | |
| "train_samples_per_second": 85.912, | |
| "train_steps_per_second": 10.739 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 8430, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1073540244786240.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |