| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.90049751243781, | |
| "global_step": 12000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.792703150912106e-05, | |
| "loss": 1.636, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9660949257998066, | |
| "eval_f1": 0.9648470438617105, | |
| "eval_loss": 0.40596073865890503, | |
| "eval_precision": 0.9632890778105937, | |
| "eval_recall": 0.9664100575985822, | |
| "eval_runtime": 12.913, | |
| "eval_samples_per_second": 114.381, | |
| "eval_steps_per_second": 4.801, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 4.5854063018242126e-05, | |
| "loss": 0.3601, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9747971581115735, | |
| "eval_f1": 0.9757520460075205, | |
| "eval_loss": 0.16257813572883606, | |
| "eval_precision": 0.9742435954063604, | |
| "eval_recall": 0.9772651750110767, | |
| "eval_runtime": 13.0776, | |
| "eval_samples_per_second": 112.941, | |
| "eval_steps_per_second": 4.741, | |
| "step": 1206 | |
| }, | |
| { | |
| "epoch": 2.49, | |
| "learning_rate": 4.3781094527363184e-05, | |
| "loss": 0.1654, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9755118341951486, | |
| "eval_f1": 0.9770373954517177, | |
| "eval_loss": 0.11993579566478729, | |
| "eval_precision": 0.9755404025066946, | |
| "eval_recall": 0.9785389898094816, | |
| "eval_runtime": 12.7573, | |
| "eval_samples_per_second": 115.777, | |
| "eval_steps_per_second": 4.86, | |
| "step": 1809 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "learning_rate": 4.170812603648425e-05, | |
| "loss": 0.1051, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9774877033673856, | |
| "eval_f1": 0.9789900275245854, | |
| "eval_loss": 0.10314257442951202, | |
| "eval_precision": 0.9779755160693067, | |
| "eval_recall": 0.9800066459902526, | |
| "eval_runtime": 12.7609, | |
| "eval_samples_per_second": 115.744, | |
| "eval_steps_per_second": 4.859, | |
| "step": 2412 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 3.9635157545605314e-05, | |
| "loss": 0.072, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 4.98, | |
| "learning_rate": 3.756218905472637e-05, | |
| "loss": 0.0557, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9762895699331567, | |
| "eval_f1": 0.979079382198808, | |
| "eval_loss": 0.10313071310520172, | |
| "eval_precision": 0.9777679582424259, | |
| "eval_recall": 0.9803943287549844, | |
| "eval_runtime": 12.8291, | |
| "eval_samples_per_second": 115.129, | |
| "eval_steps_per_second": 4.833, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 3.548922056384743e-05, | |
| "loss": 0.0406, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.977109345440787, | |
| "eval_f1": 0.9801621337465068, | |
| "eval_loss": 0.10502293705940247, | |
| "eval_precision": 0.9793221650909493, | |
| "eval_recall": 0.9810035445281347, | |
| "eval_runtime": 12.7666, | |
| "eval_samples_per_second": 115.693, | |
| "eval_steps_per_second": 4.856, | |
| "step": 3618 | |
| }, | |
| { | |
| "epoch": 6.63, | |
| "learning_rate": 3.341625207296849e-05, | |
| "loss": 0.0332, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9776558624458738, | |
| "eval_f1": 0.9800943409276397, | |
| "eval_loss": 0.10666096210479736, | |
| "eval_precision": 0.9791868210840543, | |
| "eval_recall": 0.9810035445281347, | |
| "eval_runtime": 12.7474, | |
| "eval_samples_per_second": 115.867, | |
| "eval_steps_per_second": 4.864, | |
| "step": 4221 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 3.1343283582089554e-05, | |
| "loss": 0.0248, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9782654391053937, | |
| "eval_f1": 0.9810459324847814, | |
| "eval_loss": 0.10935021936893463, | |
| "eval_precision": 0.9802864410528644, | |
| "eval_recall": 0.9818066016836509, | |
| "eval_runtime": 12.9986, | |
| "eval_samples_per_second": 113.628, | |
| "eval_steps_per_second": 4.77, | |
| "step": 4824 | |
| }, | |
| { | |
| "epoch": 8.29, | |
| "learning_rate": 2.9270315091210616e-05, | |
| "loss": 0.0209, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9786648169168033, | |
| "eval_f1": 0.9818035894668382, | |
| "eval_loss": 0.1135268285870552, | |
| "eval_precision": 0.9812197483059051, | |
| "eval_recall": 0.9823881258307487, | |
| "eval_runtime": 12.5526, | |
| "eval_samples_per_second": 117.665, | |
| "eval_steps_per_second": 4.939, | |
| "step": 5427 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 2.7197346600331674e-05, | |
| "loss": 0.0177, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "learning_rate": 2.512437810945274e-05, | |
| "loss": 0.0145, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9779291209484172, | |
| "eval_f1": 0.9809597608900205, | |
| "eval_loss": 0.12104799598455429, | |
| "eval_precision": 0.980362871999115, | |
| "eval_recall": 0.9815573770491803, | |
| "eval_runtime": 12.8411, | |
| "eval_samples_per_second": 115.021, | |
| "eval_steps_per_second": 4.828, | |
| "step": 6030 | |
| }, | |
| { | |
| "epoch": 10.78, | |
| "learning_rate": 2.3051409618573798e-05, | |
| "loss": 0.0112, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9774246437129525, | |
| "eval_f1": 0.9806444472114999, | |
| "eval_loss": 0.12379806488752365, | |
| "eval_precision": 0.9798988027760113, | |
| "eval_recall": 0.9813912272928667, | |
| "eval_runtime": 12.8231, | |
| "eval_samples_per_second": 115.183, | |
| "eval_steps_per_second": 4.835, | |
| "step": 6633 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 2.097844112769486e-05, | |
| "loss": 0.0105, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9780552402572834, | |
| "eval_f1": 0.9810323598179328, | |
| "eval_loss": 0.1279357671737671, | |
| "eval_precision": 0.9802593381072189, | |
| "eval_recall": 0.9818066016836509, | |
| "eval_runtime": 12.5624, | |
| "eval_samples_per_second": 117.573, | |
| "eval_steps_per_second": 4.935, | |
| "step": 7236 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 1.890547263681592e-05, | |
| "loss": 0.0088, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9773405641737083, | |
| "eval_f1": 0.9802169221404461, | |
| "eval_loss": 0.1307593435049057, | |
| "eval_precision": 0.9794039588632091, | |
| "eval_recall": 0.981031236154187, | |
| "eval_runtime": 12.6149, | |
| "eval_samples_per_second": 117.084, | |
| "eval_steps_per_second": 4.915, | |
| "step": 7839 | |
| }, | |
| { | |
| "epoch": 13.27, | |
| "learning_rate": 1.6832504145936983e-05, | |
| "loss": 0.0078, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9781182999117165, | |
| "eval_f1": 0.980741027698608, | |
| "eval_loss": 0.13244280219078064, | |
| "eval_precision": 0.9800088480893657, | |
| "eval_recall": 0.9814743021710235, | |
| "eval_runtime": 12.7732, | |
| "eval_samples_per_second": 115.633, | |
| "eval_steps_per_second": 4.854, | |
| "step": 8442 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 1.4759535655058043e-05, | |
| "loss": 0.0063, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 1.2686567164179105e-05, | |
| "loss": 0.0056, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9781393197965275, | |
| "eval_f1": 0.9811566131710017, | |
| "eval_loss": 0.13830867409706116, | |
| "eval_precision": 0.9803970360539703, | |
| "eval_recall": 0.98191736818786, | |
| "eval_runtime": 12.5885, | |
| "eval_samples_per_second": 117.329, | |
| "eval_steps_per_second": 4.925, | |
| "step": 9045 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 1.0613598673300167e-05, | |
| "loss": 0.0046, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9780972800269054, | |
| "eval_f1": 0.9813613029099613, | |
| "eval_loss": 0.1351945400238037, | |
| "eval_precision": 0.9807506153718505, | |
| "eval_recall": 0.9819727514399645, | |
| "eval_runtime": 12.6382, | |
| "eval_samples_per_second": 116.868, | |
| "eval_steps_per_second": 4.906, | |
| "step": 9648 | |
| }, | |
| { | |
| "epoch": 16.58, | |
| "learning_rate": 8.540630182421228e-06, | |
| "loss": 0.0046, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.977845041409173, | |
| "eval_f1": 0.9810062666869561, | |
| "eval_loss": 0.14340569078922272, | |
| "eval_precision": 0.9801520387007602, | |
| "eval_recall": 0.9818619849357554, | |
| "eval_runtime": 12.6576, | |
| "eval_samples_per_second": 116.688, | |
| "eval_steps_per_second": 4.898, | |
| "step": 10251 | |
| }, | |
| { | |
| "epoch": 17.41, | |
| "learning_rate": 6.467661691542288e-06, | |
| "loss": 0.0033, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9776979022154959, | |
| "eval_f1": 0.9810448835021307, | |
| "eval_loss": 0.1425262689590454, | |
| "eval_precision": 0.9803395642074991, | |
| "eval_recall": 0.9817512184315463, | |
| "eval_runtime": 12.8452, | |
| "eval_samples_per_second": 114.985, | |
| "eval_steps_per_second": 4.827, | |
| "step": 10854 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 4.39469320066335e-06, | |
| "loss": 0.0032, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9780972800269054, | |
| "eval_f1": 0.9813638816253684, | |
| "eval_loss": 0.14492034912109375, | |
| "eval_precision": 0.9806176901595377, | |
| "eval_recall": 0.982111209570226, | |
| "eval_runtime": 12.4458, | |
| "eval_samples_per_second": 118.675, | |
| "eval_steps_per_second": 4.982, | |
| "step": 11457 | |
| }, | |
| { | |
| "epoch": 19.07, | |
| "learning_rate": 2.3217247097844113e-06, | |
| "loss": 0.003, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 2.4875621890547267e-07, | |
| "loss": 0.0029, | |
| "step": 12000 | |
| } | |
| ], | |
| "max_steps": 12060, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.21984229568579e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |