| { | |
| "best_metric": 2.3024191856384277, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_stsb/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": 4.906666666666667e-05, | |
| "loss": 4.0455, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.07431917071856006, | |
| "eval_loss": 2.3024191856384277, | |
| "eval_pearson": 0.06713111124655088, | |
| "eval_runtime": 2.4381, | |
| "eval_samples_per_second": 615.238, | |
| "eval_spearmanr": 0.08150723019056925, | |
| "eval_steps_per_second": 4.922, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.806666666666667e-05, | |
| "loss": 2.1712, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.06681067529441857, | |
| "eval_loss": 2.6643781661987305, | |
| "eval_pearson": 0.0611865012551173, | |
| "eval_runtime": 2.4348, | |
| "eval_samples_per_second": 616.068, | |
| "eval_spearmanr": 0.07243484933371984, | |
| "eval_steps_per_second": 4.929, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.706666666666667e-05, | |
| "loss": 2.0637, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.06251030424678386, | |
| "eval_loss": 2.3624558448791504, | |
| "eval_pearson": 0.058165468295460696, | |
| "eval_runtime": 2.4296, | |
| "eval_samples_per_second": 617.389, | |
| "eval_spearmanr": 0.06685514019810702, | |
| "eval_steps_per_second": 4.939, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.606666666666667e-05, | |
| "loss": 1.996, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.07203733674672383, | |
| "eval_loss": 2.8670907020568848, | |
| "eval_pearson": 0.0712976536645173, | |
| "eval_runtime": 2.4406, | |
| "eval_samples_per_second": 614.594, | |
| "eval_spearmanr": 0.07277701982893034, | |
| "eval_steps_per_second": 4.917, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5066666666666667e-05, | |
| "loss": 1.908, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.09261579480394588, | |
| "eval_loss": 2.662240982055664, | |
| "eval_pearson": 0.09544442363952416, | |
| "eval_runtime": 2.4348, | |
| "eval_samples_per_second": 616.07, | |
| "eval_spearmanr": 0.08978716596836762, | |
| "eval_steps_per_second": 4.929, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.406666666666667e-05, | |
| "loss": 1.7068, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.2001877685151721, | |
| "eval_loss": 2.388475179672241, | |
| "eval_pearson": 0.19980969966905146, | |
| "eval_runtime": 2.4335, | |
| "eval_samples_per_second": 616.4, | |
| "eval_spearmanr": 0.20056583736129271, | |
| "eval_steps_per_second": 4.931, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 270, | |
| "total_flos": 1081506722217984.0, | |
| "train_loss": 2.3151992232711227, | |
| "train_runtime": 277.2499, | |
| "train_samples_per_second": 1036.79, | |
| "train_steps_per_second": 8.115 | |
| } | |
| ], | |
| "max_steps": 2250, | |
| "num_train_epochs": 50, | |
| "total_flos": 1081506722217984.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |