| { | |
| "best_metric": 0.7073715562174238, | |
| "best_model_checkpoint": "final_models/glue_models/structroberta_s2_50ep//finetune/qnli/checkpoint-1800", | |
| "epoch": 5.531295487627365, | |
| "global_step": 3800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.6146106719970703, | |
| "eval_f1": 0.6827511703276917, | |
| "eval_loss": 0.656548261642456, | |
| "eval_mcc": 0.22199360087926548, | |
| "eval_runtime": 4.8836, | |
| "eval_samples_per_second": 468.098, | |
| "eval_steps_per_second": 58.563, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.6132983565330505, | |
| "eval_f1": 0.6691616766467064, | |
| "eval_loss": 0.6548586487770081, | |
| "eval_mcc": 0.21809949429968853, | |
| "eval_runtime": 4.9086, | |
| "eval_samples_per_second": 465.711, | |
| "eval_steps_per_second": 58.265, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.636098981077147e-05, | |
| "loss": 0.6749, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_accuracy": 0.6124234199523926, | |
| "eval_f1": 0.6869257950530036, | |
| "eval_loss": 0.6537702679634094, | |
| "eval_mcc": 0.2187527800424191, | |
| "eval_runtime": 4.9089, | |
| "eval_samples_per_second": 465.689, | |
| "eval_steps_per_second": 58.262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_accuracy": 0.6338582634925842, | |
| "eval_f1": 0.686399400524541, | |
| "eval_loss": 0.6308510303497314, | |
| "eval_mcc": 0.26091967633126006, | |
| "eval_runtime": 4.8817, | |
| "eval_samples_per_second": 468.284, | |
| "eval_steps_per_second": 58.587, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 4.272197962154294e-05, | |
| "loss": 0.6288, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.6176728010177612, | |
| "eval_f1": 0.5810162991371045, | |
| "eval_loss": 0.6444646120071411, | |
| "eval_mcc": 0.2582529609636007, | |
| "eval_runtime": 4.8723, | |
| "eval_samples_per_second": 469.182, | |
| "eval_steps_per_second": 58.699, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_accuracy": 0.6452318429946899, | |
| "eval_f1": 0.6884364195159431, | |
| "eval_loss": 0.6248251795768738, | |
| "eval_mcc": 0.2841162003572998, | |
| "eval_runtime": 4.856, | |
| "eval_samples_per_second": 470.754, | |
| "eval_steps_per_second": 58.896, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.6443569660186768, | |
| "eval_f1": 0.6553624417125902, | |
| "eval_loss": 0.6547794938087463, | |
| "eval_mcc": 0.28923332045259653, | |
| "eval_runtime": 4.8425, | |
| "eval_samples_per_second": 472.075, | |
| "eval_steps_per_second": 59.061, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.9082969432314415e-05, | |
| "loss": 0.5829, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "eval_accuracy": 0.6557305455207825, | |
| "eval_f1": 0.67890656874745, | |
| "eval_loss": 0.6519333124160767, | |
| "eval_mcc": 0.307966407656791, | |
| "eval_runtime": 4.8379, | |
| "eval_samples_per_second": 472.517, | |
| "eval_steps_per_second": 59.116, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.6561679840087891, | |
| "eval_f1": 0.7073715562174238, | |
| "eval_loss": 0.6741649508476257, | |
| "eval_mcc": 0.30779028305110706, | |
| "eval_runtime": 4.8516, | |
| "eval_samples_per_second": 471.182, | |
| "eval_steps_per_second": 58.949, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 3.544395924308588e-05, | |
| "loss": 0.5121, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "eval_accuracy": 0.6640419960021973, | |
| "eval_f1": 0.7034749034749035, | |
| "eval_loss": 0.7019718885421753, | |
| "eval_mcc": 0.32264171773943, | |
| "eval_runtime": 4.8827, | |
| "eval_samples_per_second": 468.184, | |
| "eval_steps_per_second": 58.574, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_accuracy": 0.6771653294563293, | |
| "eval_f1": 0.670829616413916, | |
| "eval_loss": 0.6962025165557861, | |
| "eval_mcc": 0.36331729204615415, | |
| "eval_runtime": 4.857, | |
| "eval_samples_per_second": 470.665, | |
| "eval_steps_per_second": 58.885, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "eval_accuracy": 0.6692913174629211, | |
| "eval_f1": 0.6730103806228372, | |
| "eval_loss": 0.7017433643341064, | |
| "eval_mcc": 0.3420737265934342, | |
| "eval_runtime": 4.8442, | |
| "eval_samples_per_second": 471.908, | |
| "eval_steps_per_second": 59.04, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "learning_rate": 3.1804949053857355e-05, | |
| "loss": 0.4192, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.78, | |
| "eval_accuracy": 0.6675415635108948, | |
| "eval_f1": 0.6712802768166091, | |
| "eval_loss": 0.6771557331085205, | |
| "eval_mcc": 0.3385643570211769, | |
| "eval_runtime": 4.8693, | |
| "eval_samples_per_second": 469.476, | |
| "eval_steps_per_second": 58.736, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "eval_accuracy": 0.6701662540435791, | |
| "eval_f1": 0.6986410871302957, | |
| "eval_loss": 0.9257397055625916, | |
| "eval_mcc": 0.33573292641261127, | |
| "eval_runtime": 4.8915, | |
| "eval_samples_per_second": 467.337, | |
| "eval_steps_per_second": 58.468, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 2.816593886462882e-05, | |
| "loss": 0.3517, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "eval_accuracy": 0.6706036925315857, | |
| "eval_f1": 0.6541111621497473, | |
| "eval_loss": 0.8104151487350464, | |
| "eval_mcc": 0.35637801084068055, | |
| "eval_runtime": 4.8987, | |
| "eval_samples_per_second": 466.65, | |
| "eval_steps_per_second": 58.382, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "eval_accuracy": 0.6679790019989014, | |
| "eval_f1": 0.6597938144329897, | |
| "eval_loss": 0.8328930139541626, | |
| "eval_mcc": 0.3457806676963092, | |
| "eval_runtime": 4.8964, | |
| "eval_samples_per_second": 466.871, | |
| "eval_steps_per_second": 58.41, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "eval_accuracy": 0.6815398335456848, | |
| "eval_f1": 0.6946308724832215, | |
| "eval_loss": 0.7547760009765625, | |
| "eval_mcc": 0.362460160804572, | |
| "eval_runtime": 4.8988, | |
| "eval_samples_per_second": 466.642, | |
| "eval_steps_per_second": 58.381, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "learning_rate": 2.452692867540029e-05, | |
| "loss": 0.2998, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 5.24, | |
| "eval_accuracy": 0.6863517165184021, | |
| "eval_f1": 0.6789072995969547, | |
| "eval_loss": 0.933471143245697, | |
| "eval_mcc": 0.38264274350198313, | |
| "eval_runtime": 4.8881, | |
| "eval_samples_per_second": 467.669, | |
| "eval_steps_per_second": 58.51, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "eval_accuracy": 0.6771653294563293, | |
| "eval_f1": 0.6883445945945946, | |
| "eval_loss": 0.9999232292175293, | |
| "eval_mcc": 0.3544971598234377, | |
| "eval_runtime": 4.8652, | |
| "eval_samples_per_second": 469.869, | |
| "eval_steps_per_second": 58.785, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 5.53, | |
| "step": 3800, | |
| "total_flos": 2.22547390664832e+16, | |
| "train_loss": 0.473507473594264, | |
| "train_runtime": 1395.5937, | |
| "train_samples_per_second": 314.683, | |
| "train_steps_per_second": 4.923 | |
| } | |
| ], | |
| "max_steps": 6870, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.22547390664832e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |