| { |
| "best_metric": 2.7703847885131836, |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_data_aug_stsb_128/checkpoint-2518", |
| "epoch": 6.0, |
| "global_step": 15108, |
| "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": 1.1017, |
| "step": 2518 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.1897741802874401, |
| "eval_loss": 2.7703847885131836, |
| "eval_pearson": 0.18112845869500624, |
| "eval_runtime": 2.1213, |
| "eval_samples_per_second": 707.113, |
| "eval_spearmanr": 0.19841990187987396, |
| "eval_steps_per_second": 5.657, |
| "step": 2518 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.8e-05, |
| "loss": 0.654, |
| "step": 5036 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.16416465300198851, |
| "eval_loss": 3.050649404525757, |
| "eval_pearson": 0.1579809732937041, |
| "eval_runtime": 2.0965, |
| "eval_samples_per_second": 715.463, |
| "eval_spearmanr": 0.1703483327102729, |
| "eval_steps_per_second": 5.724, |
| "step": 5036 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.7e-05, |
| "loss": 0.5737, |
| "step": 7554 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.15255022595886847, |
| "eval_loss": 3.167938232421875, |
| "eval_pearson": 0.14820292029299578, |
| "eval_runtime": 2.1073, |
| "eval_samples_per_second": 711.811, |
| "eval_spearmanr": 0.15689753162474115, |
| "eval_steps_per_second": 5.694, |
| "step": 7554 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.4954, |
| "step": 10072 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.15904710762611007, |
| "eval_loss": 3.317542314529419, |
| "eval_pearson": 0.15641946859114605, |
| "eval_runtime": 2.1083, |
| "eval_samples_per_second": 711.471, |
| "eval_spearmanr": 0.1616747466610741, |
| "eval_steps_per_second": 5.692, |
| "step": 10072 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.5e-05, |
| "loss": 0.3722, |
| "step": 12590 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.14714255977769714, |
| "eval_loss": 2.955753803253174, |
| "eval_pearson": 0.14257641254642917, |
| "eval_runtime": 2.0985, |
| "eval_samples_per_second": 714.803, |
| "eval_spearmanr": 0.15170870700896513, |
| "eval_steps_per_second": 5.718, |
| "step": 12590 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.276, |
| "step": 15108 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.14957545975990919, |
| "eval_loss": 3.202052116394043, |
| "eval_pearson": 0.14619477851192536, |
| "eval_runtime": 2.0954, |
| "eval_samples_per_second": 715.856, |
| "eval_spearmanr": 0.152956141007893, |
| "eval_steps_per_second": 5.727, |
| "step": 15108 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 15108, |
| "total_flos": 4.608337666218394e+16, |
| "train_loss": 0.5788300594767156, |
| "train_runtime": 9175.0721, |
| "train_samples_per_second": 1756.101, |
| "train_steps_per_second": 13.722 |
| } |
| ], |
| "max_steps": 125900, |
| "num_train_epochs": 50, |
| "total_flos": 4.608337666218394e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
