| { | |
| "best_metric": 1.1476225852966309, | |
| "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_logit_kd_stsb_256/checkpoint-45", | |
| "epoch": 6.0, | |
| "global_step": 270, | |
| "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": 2.1451, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.011296355493048138, | |
| "eval_loss": 1.1476225852966309, | |
| "eval_pearson": 0.01750932835053105, | |
| "eval_runtime": 3.3155, | |
| "eval_samples_per_second": 452.427, | |
| "eval_spearmanr": 0.005083382635565227, | |
| "eval_steps_per_second": 3.619, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 1.0864, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.03161066921739511, | |
| "eval_loss": 1.2303156852722168, | |
| "eval_pearson": 0.03644726383331289, | |
| "eval_runtime": 3.305, | |
| "eval_samples_per_second": 453.858, | |
| "eval_spearmanr": 0.02677407460147733, | |
| "eval_steps_per_second": 3.631, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 1.0669, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.03419907335382424, | |
| "eval_loss": 1.2794137001037598, | |
| "eval_pearson": 0.03850207156348873, | |
| "eval_runtime": 3.288, | |
| "eval_samples_per_second": 456.207, | |
| "eval_spearmanr": 0.029896075144159744, | |
| "eval_steps_per_second": 3.65, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 1.0484, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.03905091919881927, | |
| "eval_loss": 1.275455117225647, | |
| "eval_pearson": 0.03936968630424099, | |
| "eval_runtime": 3.3038, | |
| "eval_samples_per_second": 454.024, | |
| "eval_spearmanr": 0.03873215209339756, | |
| "eval_steps_per_second": 3.632, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0377, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.045002649058300634, | |
| "eval_loss": 1.2931312322616577, | |
| "eval_pearson": 0.046381350168603466, | |
| "eval_runtime": 3.3026, | |
| "eval_samples_per_second": 454.193, | |
| "eval_spearmanr": 0.043623947947997795, | |
| "eval_steps_per_second": 3.634, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 1.0279, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.053244499824454575, | |
| "eval_loss": 1.2146743535995483, | |
| "eval_pearson": 0.049081381537594684, | |
| "eval_runtime": 3.3084, | |
| "eval_samples_per_second": 453.393, | |
| "eval_spearmanr": 0.05740761811131446, | |
| "eval_steps_per_second": 3.627, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 270, | |
| "total_flos": 889076550991872.0, | |
| "train_loss": 1.235396307486075, | |
| "train_runtime": 303.3307, | |
| "train_samples_per_second": 947.646, | |
| "train_steps_per_second": 7.418 | |
| } | |
| ], | |
| "max_steps": 2250, | |
| "num_train_epochs": 50, | |
| "total_flos": 889076550991872.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |