| { | |
| "best_metric": 2.2717580795288086, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_stsb_128/checkpoint-360", | |
| "epoch": 13.0, | |
| "global_step": 585, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 4.9e-05, | |
| "loss": 5.1866, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": -0.03419951535811661, | |
| "eval_loss": 2.516068458557129, | |
| "eval_pearson": -0.03551705055328359, | |
| "eval_runtime": 3.3337, | |
| "eval_samples_per_second": 449.945, | |
| "eval_spearmanr": -0.03288198016294964, | |
| "eval_steps_per_second": 3.6, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 2.1786, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.04006226088701736, | |
| "eval_loss": 2.3526787757873535, | |
| "eval_pearson": 0.040667683121476145, | |
| "eval_runtime": 3.332, | |
| "eval_samples_per_second": 450.186, | |
| "eval_spearmanr": 0.03945683865255857, | |
| "eval_steps_per_second": 3.601, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 2.1136, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.054871119033915686, | |
| "eval_loss": 2.3100574016571045, | |
| "eval_pearson": 0.05425082240043679, | |
| "eval_runtime": 3.3316, | |
| "eval_samples_per_second": 450.233, | |
| "eval_spearmanr": 0.05549141566739457, | |
| "eval_steps_per_second": 3.602, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 2.1, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.0640228286317318, | |
| "eval_loss": 2.4468700885772705, | |
| "eval_pearson": 0.062403904668015854, | |
| "eval_runtime": 3.3312, | |
| "eval_samples_per_second": 450.285, | |
| "eval_spearmanr": 0.06564175259544773, | |
| "eval_steps_per_second": 3.602, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.9564, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.08159900576887284, | |
| "eval_loss": 2.864647388458252, | |
| "eval_pearson": 0.08149726024270469, | |
| "eval_runtime": 3.3276, | |
| "eval_samples_per_second": 450.778, | |
| "eval_spearmanr": 0.081700751295041, | |
| "eval_steps_per_second": 3.606, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.8611, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.10714300129913198, | |
| "eval_loss": 2.5597310066223145, | |
| "eval_pearson": 0.10886761855371686, | |
| "eval_runtime": 3.33, | |
| "eval_samples_per_second": 450.453, | |
| "eval_spearmanr": 0.10541838404454709, | |
| "eval_steps_per_second": 3.604, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 1.6702, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.16545786652824848, | |
| "eval_loss": 2.7086517810821533, | |
| "eval_pearson": 0.16435132629367552, | |
| "eval_runtime": 3.3354, | |
| "eval_samples_per_second": 449.718, | |
| "eval_spearmanr": 0.16656440676282144, | |
| "eval_steps_per_second": 3.598, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 1.385, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.22276448760492518, | |
| "eval_loss": 2.2717580795288086, | |
| "eval_pearson": 0.22248120048402384, | |
| "eval_runtime": 3.3336, | |
| "eval_samples_per_second": 449.959, | |
| "eval_spearmanr": 0.22304777472582654, | |
| "eval_steps_per_second": 3.6, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 1.2518, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.20775779205236106, | |
| "eval_loss": 2.4105288982391357, | |
| "eval_pearson": 0.21335013337998907, | |
| "eval_runtime": 3.3266, | |
| "eval_samples_per_second": 450.91, | |
| "eval_spearmanr": 0.20216545072473302, | |
| "eval_steps_per_second": 3.607, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4e-05, | |
| "loss": 1.143, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.20401599479580373, | |
| "eval_loss": 2.583439350128174, | |
| "eval_pearson": 0.199757100307282, | |
| "eval_runtime": 3.3001, | |
| "eval_samples_per_second": 454.528, | |
| "eval_spearmanr": 0.20827488928432544, | |
| "eval_steps_per_second": 3.636, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 1.0191, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.18757445818785518, | |
| "eval_loss": 2.6131715774536133, | |
| "eval_pearson": 0.1855518355233361, | |
| "eval_runtime": 3.3246, | |
| "eval_samples_per_second": 451.182, | |
| "eval_spearmanr": 0.18959708085237428, | |
| "eval_steps_per_second": 3.609, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.9431, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_combined_score": 0.18281609256386636, | |
| "eval_loss": 2.818650960922241, | |
| "eval_pearson": 0.1784366005924437, | |
| "eval_runtime": 3.3302, | |
| "eval_samples_per_second": 450.422, | |
| "eval_spearmanr": 0.187195584535289, | |
| "eval_steps_per_second": 3.603, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.8725, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_combined_score": 0.18470921539603302, | |
| "eval_loss": 2.8360345363616943, | |
| "eval_pearson": 0.18149675678836885, | |
| "eval_runtime": 3.3258, | |
| "eval_samples_per_second": 451.016, | |
| "eval_spearmanr": 0.1879216740036972, | |
| "eval_steps_per_second": 3.608, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 585, | |
| "total_flos": 1781311270289408.0, | |
| "train_loss": 1.821616702609592, | |
| "train_runtime": 670.1493, | |
| "train_samples_per_second": 428.934, | |
| "train_steps_per_second": 3.357 | |
| } | |
| ], | |
| "max_steps": 2250, | |
| "num_train_epochs": 50, | |
| "total_flos": 1781311270289408.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |