| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5207485760781123, | |
| "global_step": 320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 7.894736842105263e-06, | |
| "loss": 0.8762, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.5789473684210526e-05, | |
| "loss": 0.7783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.7497, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9999790913463623e-05, | |
| "loss": 0.6797, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.6140000224113464, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6632643938064575, | |
| "eval_runtime": 64.3151, | |
| "eval_samples_per_second": 7.774, | |
| "eval_steps_per_second": 0.249, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.9992473496712718e-05, | |
| "loss": 0.676, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9974707581369814e-05, | |
| "loss": 0.6647, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2.994650554879023e-05, | |
| "loss": 0.6657, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.9907887053429107e-05, | |
| "loss": 0.6742, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.6060000061988831, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6763938069343567, | |
| "eval_runtime": 64.3111, | |
| "eval_samples_per_second": 7.775, | |
| "eval_steps_per_second": 0.249, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.985887900914388e-05, | |
| "loss": 0.6677, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 2.9799515570437597e-05, | |
| "loss": 0.6838, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2.972983810865608e-05, | |
| "loss": 0.6872, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 2.9649895183155556e-05, | |
| "loss": 0.6794, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.5860000252723694, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6799845099449158, | |
| "eval_runtime": 64.3206, | |
| "eval_samples_per_second": 7.774, | |
| "eval_steps_per_second": 0.249, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.9559742507460873e-05, | |
| "loss": 0.6693, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.9459442910437798e-05, | |
| "loss": 0.6751, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2.9349066292506613e-05, | |
| "loss": 0.6702, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.9228689576927327e-05, | |
| "loss": 0.6596, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.5879999995231628, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6791808009147644, | |
| "eval_runtime": 64.2883, | |
| "eval_samples_per_second": 7.777, | |
| "eval_steps_per_second": 0.249, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 2.909839665619062e-05, | |
| "loss": 0.6523, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.8958278333551827e-05, | |
| "loss": 0.668, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.8808432259748648e-05, | |
| "loss": 0.6351, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.864896286494674e-05, | |
| "loss": 0.6585, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.5820000171661377, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6792215704917908, | |
| "eval_runtime": 64.2728, | |
| "eval_samples_per_second": 7.779, | |
| "eval_steps_per_second": 0.249, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.8479981285960694e-05, | |
| "loss": 0.697, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2.830160528880093e-05, | |
| "loss": 0.6539, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.8113959186600674e-05, | |
| "loss": 0.6727, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.7917173752980103e-05, | |
| "loss": 0.6458, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.5699999928474426, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6816621422767639, | |
| "eval_runtime": 64.3027, | |
| "eval_samples_per_second": 7.776, | |
| "eval_steps_per_second": 0.249, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2.77113861309081e-05, | |
| "loss": 0.682, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2.7496739737125063e-05, | |
| "loss": 0.6664, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 2.7273384162193462e-05, | |
| "loss": 0.6493, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 2.7041475066245742e-05, | |
| "loss": 0.6585, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_accuracy": 0.5659999847412109, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.679412841796875, | |
| "eval_runtime": 64.3077, | |
| "eval_samples_per_second": 7.775, | |
| "eval_steps_per_second": 0.249, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.6801174070502248e-05, | |
| "loss": 0.6326, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.6552648644634765e-05, | |
| "loss": 0.6597, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 2.6296071990054167e-05, | |
| "loss": 0.6495, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 2.603162291920356e-05, | |
| "loss": 0.6953, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.5619999766349792, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6798678636550903, | |
| "eval_runtime": 64.3074, | |
| "eval_samples_per_second": 7.775, | |
| "eval_steps_per_second": 0.249, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2.575948573094098e-05, | |
| "loss": 0.6436, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.5479850082098485e-05, | |
| "loss": 0.6527, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.5192910855307295e-05, | |
| "loss": 0.6434, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 2.4898868023180844e-05, | |
| "loss": 0.6586, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.5879999995231628, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6790176033973694, | |
| "eval_runtime": 64.3234, | |
| "eval_samples_per_second": 7.773, | |
| "eval_steps_per_second": 0.249, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2.4597926508950648e-05, | |
| "loss": 0.6444, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 2.429029604365198e-05, | |
| "loss": 0.657, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 2.3976191019958896e-05, | |
| "loss": 0.6346, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.3655830342770463e-05, | |
| "loss": 0.669, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.6119999885559082, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6743248105049133, | |
| "eval_runtime": 64.2981, | |
| "eval_samples_per_second": 7.776, | |
| "eval_steps_per_second": 0.249, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2.3329437276652424e-05, | |
| "loss": 0.6295, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 2.299723929024046e-05, | |
| "loss": 0.6244, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 2.2659467897713604e-05, | |
| "loss": 0.6341, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 2.231635849744825e-05, | |
| "loss": 0.6376, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_accuracy": 0.5839999914169312, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6735034584999084, | |
| "eval_runtime": 64.3161, | |
| "eval_samples_per_second": 7.774, | |
| "eval_steps_per_second": 0.249, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.196815020796519e-05, | |
| "loss": 0.6264, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.161508570128403e-05, | |
| "loss": 0.6178, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 2.1257411033801125e-05, | |
| "loss": 0.6578, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.0895375474808857e-05, | |
| "loss": 0.6173, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_accuracy": 0.5740000009536743, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6771048903465271, | |
| "eval_runtime": 64.3005, | |
| "eval_samples_per_second": 7.776, | |
| "eval_steps_per_second": 0.249, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.052923133277581e-05, | |
| "loss": 0.64, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.0159233779508923e-05, | |
| "loss": 0.6173, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.9785640672320074e-05, | |
| "loss": 0.6104, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 1.9408712374321155e-05, | |
| "loss": 0.6295, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.5960000157356262, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6679331064224243, | |
| "eval_runtime": 64.1981, | |
| "eval_samples_per_second": 7.788, | |
| "eval_steps_per_second": 0.249, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.9028711572972753e-05, | |
| "loss": 0.6366, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.864590309701302e-05, | |
| "loss": 0.6567, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 1.82605537318942e-05, | |
| "loss": 0.6397, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.7872932033855518e-05, | |
| "loss": 0.6311, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_accuracy": 0.6000000238418579, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6692066788673401, | |
| "eval_runtime": 64.3111, | |
| "eval_samples_per_second": 7.775, | |
| "eval_steps_per_second": 0.249, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.748330814276195e-05, | |
| "loss": 0.6361, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 1.7091953593839383e-05, | |
| "loss": 0.6583, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6699141128437286e-05, | |
| "loss": 0.6321, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.630514450395084e-05, | |
| "loss": 0.6294, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_accuracy": 0.5899999737739563, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6700637340545654, | |
| "eval_runtime": 64.3279, | |
| "eval_samples_per_second": 7.773, | |
| "eval_steps_per_second": 0.249, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.591023830303493e-05, | |
| "loss": 0.6479, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.5514697742243067e-05, | |
| "loss": 0.6332, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.511879848022446e-05, | |
| "loss": 0.6076, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.4722816425613054e-05, | |
| "loss": 0.6526, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_accuracy": 0.6039999723434448, | |
| "eval_label_positive_rate": 0.5199999809265137, | |
| "eval_loss": 0.6673489212989807, | |
| "eval_runtime": 64.2956, | |
| "eval_samples_per_second": 7.777, | |
| "eval_steps_per_second": 0.249, | |
| "step": 320 | |
| } | |
| ], | |
| "max_steps": 614, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.1109883301467259e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |