| { | |
| "best_metric": 0.6131083965301514, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_cola/checkpoint-238", | |
| "epoch": 12.0, | |
| "global_step": 408, | |
| "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": 0.6197, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6238651871681213, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.5899, | |
| "eval_samples_per_second": 656.009, | |
| "eval_steps_per_second": 3.145, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.6078, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.6178815364837646, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.5812, | |
| "eval_samples_per_second": 659.606, | |
| "eval_steps_per_second": 3.162, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.6064, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.6179934144020081, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 2.4438, | |
| "eval_samples_per_second": 426.802, | |
| "eval_steps_per_second": 2.046, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.6073, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.6175711750984192, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.7323, | |
| "eval_samples_per_second": 602.096, | |
| "eval_steps_per_second": 2.886, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6069, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.6172661781311035, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.7156, | |
| "eval_samples_per_second": 607.942, | |
| "eval_steps_per_second": 2.914, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6043, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.6166184544563293, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.9408, | |
| "eval_samples_per_second": 537.405, | |
| "eval_steps_per_second": 2.576, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.6004, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.6131083965301514, | |
| "eval_matthews_correlation": 0.0, | |
| "eval_runtime": 1.7507, | |
| "eval_samples_per_second": 595.751, | |
| "eval_steps_per_second": 2.856, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.5842, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6240708231925964, | |
| "eval_matthews_correlation": 0.0951039122870703, | |
| "eval_runtime": 1.7156, | |
| "eval_samples_per_second": 607.967, | |
| "eval_steps_per_second": 2.915, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.5192, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.6361746191978455, | |
| "eval_matthews_correlation": 0.059760920069176514, | |
| "eval_runtime": 1.9833, | |
| "eval_samples_per_second": 525.879, | |
| "eval_steps_per_second": 2.521, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4884, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.7009902596473694, | |
| "eval_matthews_correlation": 0.08008155523655092, | |
| "eval_runtime": 1.7208, | |
| "eval_samples_per_second": 606.103, | |
| "eval_steps_per_second": 2.906, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.4559, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.6731011867523193, | |
| "eval_matthews_correlation": 0.09051190856095573, | |
| "eval_runtime": 1.7848, | |
| "eval_samples_per_second": 584.391, | |
| "eval_steps_per_second": 2.801, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.4367, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.6893478035926819, | |
| "eval_matthews_correlation": 0.09007205990892461, | |
| "eval_runtime": 1.959, | |
| "eval_samples_per_second": 532.427, | |
| "eval_steps_per_second": 2.552, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "step": 408, | |
| "total_flos": 3258721140473856.0, | |
| "train_loss": 0.5614397408915501, | |
| "train_runtime": 608.6002, | |
| "train_samples_per_second": 702.514, | |
| "train_steps_per_second": 2.793 | |
| } | |
| ], | |
| "max_steps": 1700, | |
| "num_train_epochs": 50, | |
| "total_flos": 3258721140473856.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |