| { | |
| "best_metric": 0.009224997833371162, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-1530", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1530, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.169934640522877e-06, | |
| "loss": 0.2238, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.6339869281045753e-05, | |
| "loss": 0.1052, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4509803921568626e-05, | |
| "loss": 0.0724, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.2679738562091506e-05, | |
| "loss": 0.0251, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.084967320261438e-05, | |
| "loss": 0.0326, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.901960784313725e-05, | |
| "loss": 0.0421, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.920116194625999e-05, | |
| "loss": 0.003, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.829339143064633e-05, | |
| "loss": 0.0415, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.742193173565723e-05, | |
| "loss": 0.0138, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.651416122004357e-05, | |
| "loss": 0.0002, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.5606390704429926e-05, | |
| "loss": 0.0015, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.469862018881627e-05, | |
| "loss": 0.0002, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.379084967320262e-05, | |
| "loss": 0.0164, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 4.295570079883805e-05, | |
| "loss": 0.039, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.20479302832244e-05, | |
| "loss": 0.0115, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.1140159767610744e-05, | |
| "loss": 0.0002, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.02323892519971e-05, | |
| "loss": 0.0001, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.932461873638344e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.841684822076979e-05, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 3.7509077705156135e-05, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9980411361410382, | |
| "eval_auc": 0.9945804195804195, | |
| "eval_f1": 0.9473684210526316, | |
| "eval_loss": 0.016766857355833054, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.9, | |
| "eval_runtime": 1.4347, | |
| "eval_samples_per_second": 711.629, | |
| "eval_steps_per_second": 44.608, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.6601307189542484e-05, | |
| "loss": 0.0066, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.5693536673928834e-05, | |
| "loss": 0.0093, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.478576615831518e-05, | |
| "loss": 0.0001, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.3877995642701525e-05, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 3.2970225127087875e-05, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.206245461147422e-05, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.115468409586057e-05, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0246913580246916e-05, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.9339143064633262e-05, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.8431372549019608e-05, | |
| "loss": 0.0457, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "learning_rate": 2.7523602033405954e-05, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.6615831517792306e-05, | |
| "loss": 0.0471, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 2.5708061002178652e-05, | |
| "loss": 0.0008, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.4800290486564998e-05, | |
| "loss": 0.0001, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 2.3892519970951344e-05, | |
| "loss": 0.0001, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.2984749455337693e-05, | |
| "loss": 0.0001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.207697893972404e-05, | |
| "loss": 0.0333, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.116920842411039e-05, | |
| "loss": 0.0003, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.0261437908496734e-05, | |
| "loss": 0.0002, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "learning_rate": 1.935366739288308e-05, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9990205680705191, | |
| "eval_auc": 0.9973276723276723, | |
| "eval_f1": 0.9743589743589743, | |
| "eval_loss": 0.010454983450472355, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.95, | |
| "eval_runtime": 1.4324, | |
| "eval_samples_per_second": 712.791, | |
| "eval_steps_per_second": 44.68, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.844589687726943e-05, | |
| "loss": 0.0001, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 1.7538126361655776e-05, | |
| "loss": 0.0001, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.663035584604212e-05, | |
| "loss": 0.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5722585330428467e-05, | |
| "loss": 0.0001, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 1.3907044299201164e-05, | |
| "loss": 0.0001, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 1.299927378358751e-05, | |
| "loss": 0.0001, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 1.2091503267973856e-05, | |
| "loss": 0.0373, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 1.1183732752360204e-05, | |
| "loss": 0.0547, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0275962236746551e-05, | |
| "loss": 0.0002, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.368191721132897e-06, | |
| "loss": 0.0005, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 8.460421205519245e-06, | |
| "loss": 0.0001, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 7.5526506899055924e-06, | |
| "loss": 0.0001, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 6.64488017429194e-06, | |
| "loss": 0.0028, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 5.737109658678287e-06, | |
| "loss": 0.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 4.8293391430646336e-06, | |
| "loss": 0.0001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.92156862745098e-06, | |
| "loss": 0.0001, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 3.0137981118373275e-06, | |
| "loss": 0.0001, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 2.1060275962236747e-06, | |
| "loss": 0.0001, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 1.1982570806100219e-06, | |
| "loss": 0.0001, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 2.904865649963689e-07, | |
| "loss": 0.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9990205680705191, | |
| "eval_auc": 0.9993006993006993, | |
| "eval_f1": 0.9743589743589743, | |
| "eval_loss": 0.009224997833371162, | |
| "eval_precision": 1.0, | |
| "eval_recall": 0.95, | |
| "eval_runtime": 1.4372, | |
| "eval_samples_per_second": 710.404, | |
| "eval_steps_per_second": 44.531, | |
| "step": 1530 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1530, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 805119829401600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |