| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 328, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.060606060606061e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.0303030303030306e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.060606060606061e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00012121212121212122, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00015151515151515152, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001999773186295914, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019972227135924052, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019918455047624847, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019836568020887964, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019726798173387415, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019589456659682057, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019424932789214157, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019233692922769496, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00019016279150527044, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018773307755445465, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001850546746634211, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00018213517505616338, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001789828543715116, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00017560664820493498, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001720161267796256, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016822146781866098, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00016423342769514228, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001600633109420861, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00015572293820849753, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001512246127524561, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014658108556619417, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00014180551923202405, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00013691145061156844, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00013191275247405527, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001268235941724463, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00012165840147886656, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011643181569318595, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00011115865214066414, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00010585385817630137, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.00010053247081493685, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.520957410719632e-05, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.990025638211179e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.461956747761374e-05, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.938247608013021e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.420382729421883e-05, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.408036805520801e-05, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.916425364719975e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.436389259888841e-05, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.969289205520778e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.516449247468666e-05, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.0791530097930676e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.658640056190378e-05, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.256102376314824e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.872681006954315e-05, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.5094627976376927e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.167477329841633e-05, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8476939985301256e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.5510192642991073e-05, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2782940839154111e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0302915265334723e-05, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.077145823467924e-06, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.111941698858681e-06, | |
| "loss": 0.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.412873476110702e-06, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.0, | |
| "learning_rate": 2.984757348699152e-06, | |
| "loss": 0.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.8316414669469539e-06, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.567944631029169e-07, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3.6269618604847233e-07, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5.103067189662358e-08, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 206.1766, | |
| "eval_samples_per_second": 11.204, | |
| "eval_steps_per_second": 0.703, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 328, | |
| "total_flos": 3721404806070272.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 649.5581, | |
| "train_samples_per_second": 32.285, | |
| "train_steps_per_second": 0.505 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 328, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "total_flos": 3721404806070272.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |