| { | |
| "best_metric": 0.9348677381250672, | |
| "best_model_checkpoint": "./output//27_roberta-large_nace_5__5e-6_0.01_0.06_07-21-22_10-40/checkpoint-34000", | |
| "epoch": 0.47627552539143897, | |
| "global_step": 36000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.4099488445934027e-07, | |
| "loss": 0.4133, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.7441786046511628, | |
| "eval_f1": 0.8165165383775418, | |
| "eval_loss": 0.1790679544210434, | |
| "eval_roc_auc": 0.8668411635323101, | |
| "eval_runtime": 3974.4569, | |
| "eval_samples_per_second": 33.81, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8.819897689186805e-07, | |
| "loss": 0.1406, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_accuracy": 0.8583293023255814, | |
| "eval_f1": 0.8962156482672414, | |
| "eval_loss": 0.10798993706703186, | |
| "eval_roc_auc": 0.9289601235630573, | |
| "eval_runtime": 3972.2303, | |
| "eval_samples_per_second": 33.829, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 1.3229846533780208e-06, | |
| "loss": 0.1031, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_accuracy": 0.8717916279069767, | |
| "eval_f1": 0.9098423212614298, | |
| "eval_loss": 0.09154131263494492, | |
| "eval_roc_auc": 0.9391470643074916, | |
| "eval_runtime": 3969.5037, | |
| "eval_samples_per_second": 33.852, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.763979537837361e-06, | |
| "loss": 0.0914, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.87552, | |
| "eval_f1": 0.9143850842595912, | |
| "eval_loss": 0.0857754498720169, | |
| "eval_roc_auc": 0.9432040890004426, | |
| "eval_runtime": 3972.1068, | |
| "eval_samples_per_second": 33.83, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 2.2049744222967015e-06, | |
| "loss": 0.086, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.8826344186046512, | |
| "eval_f1": 0.920503409245387, | |
| "eval_loss": 0.0785670205950737, | |
| "eval_roc_auc": 0.9476352210494301, | |
| "eval_runtime": 3972.0528, | |
| "eval_samples_per_second": 33.83, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.6459693067560417e-06, | |
| "loss": 0.081, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_accuracy": 0.8837804651162791, | |
| "eval_f1": 0.918277282234473, | |
| "eval_loss": 0.08349015563726425, | |
| "eval_roc_auc": 0.9447499943075987, | |
| "eval_runtime": 3972.0596, | |
| "eval_samples_per_second": 33.83, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 3.086964191215382e-06, | |
| "loss": 0.0775, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_accuracy": 0.8872781395348838, | |
| "eval_f1": 0.924948609604294, | |
| "eval_loss": 0.07447060197591782, | |
| "eval_roc_auc": 0.9511275412456767, | |
| "eval_runtime": 3972.9024, | |
| "eval_samples_per_second": 33.823, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.527959075674722e-06, | |
| "loss": 0.0744, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_accuracy": 0.889086511627907, | |
| "eval_f1": 0.9263051031642764, | |
| "eval_loss": 0.07151775807142258, | |
| "eval_roc_auc": 0.9513749320912529, | |
| "eval_runtime": 3975.2319, | |
| "eval_samples_per_second": 33.803, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.968953960134063e-06, | |
| "loss": 0.0723, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.8928074418604651, | |
| "eval_f1": 0.9283796074162661, | |
| "eval_loss": 0.07034408301115036, | |
| "eval_roc_auc": 0.9520370566636712, | |
| "eval_runtime": 3974.9398, | |
| "eval_samples_per_second": 33.806, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.409948844593403e-06, | |
| "loss": 0.0722, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_accuracy": 0.8941618604651163, | |
| "eval_f1": 0.9288924323300072, | |
| "eval_loss": 0.07033304870128632, | |
| "eval_roc_auc": 0.9528704562178443, | |
| "eval_runtime": 3975.8569, | |
| "eval_samples_per_second": 33.798, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.850943729052743e-06, | |
| "loss": 0.0712, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_accuracy": 0.8931051162790697, | |
| "eval_f1": 0.9289362051897834, | |
| "eval_loss": 0.0682619959115982, | |
| "eval_roc_auc": 0.9530403961143167, | |
| "eval_runtime": 3976.3274, | |
| "eval_samples_per_second": 33.794, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.981365445568524e-06, | |
| "loss": 0.0702, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_accuracy": 0.8928148837209302, | |
| "eval_f1": 0.9308045330418591, | |
| "eval_loss": 0.06587515771389008, | |
| "eval_roc_auc": 0.9554682784194162, | |
| "eval_runtime": 3978.615, | |
| "eval_samples_per_second": 33.774, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.953216571804962e-06, | |
| "loss": 0.0674, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.8974288372093023, | |
| "eval_f1": 0.9315761200444078, | |
| "eval_loss": 0.06575693190097809, | |
| "eval_roc_auc": 0.9538906122563938, | |
| "eval_runtime": 3980.7661, | |
| "eval_samples_per_second": 33.756, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.925067698041402e-06, | |
| "loss": 0.0675, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.8975553488372093, | |
| "eval_f1": 0.932992948317415, | |
| "eval_loss": 0.06388908624649048, | |
| "eval_roc_auc": 0.9557926401320601, | |
| "eval_runtime": 3982.9209, | |
| "eval_samples_per_second": 33.738, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.8969188242778405e-06, | |
| "loss": 0.0655, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_accuracy": 0.8983144186046511, | |
| "eval_f1": 0.9333932847298796, | |
| "eval_loss": 0.06425502896308899, | |
| "eval_roc_auc": 0.9562226953341786, | |
| "eval_runtime": 3986.7123, | |
| "eval_samples_per_second": 33.706, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.868769950514281e-06, | |
| "loss": 0.0664, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_accuracy": 0.8958660465116279, | |
| "eval_f1": 0.9332072735544592, | |
| "eval_loss": 0.06699266284704208, | |
| "eval_roc_auc": 0.957509923295693, | |
| "eval_runtime": 3985.7329, | |
| "eval_samples_per_second": 33.714, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 4.84062107675072e-06, | |
| "loss": 0.0654, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_accuracy": 0.9013953488372093, | |
| "eval_f1": 0.9348677381250672, | |
| "eval_loss": 0.06359969079494476, | |
| "eval_roc_auc": 0.9560356988087838, | |
| "eval_runtime": 3983.3139, | |
| "eval_samples_per_second": 33.734, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.812472202987159e-06, | |
| "loss": 0.0631, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.9006883720930232, | |
| "eval_f1": 0.9346494894714654, | |
| "eval_loss": 0.062248293310403824, | |
| "eval_roc_auc": 0.9565755762058906, | |
| "eval_runtime": 3983.6656, | |
| "eval_samples_per_second": 33.731, | |
| "step": 36000 | |
| } | |
| ], | |
| "max_steps": 377930, | |
| "num_train_epochs": 5, | |
| "total_flos": 6.9867777687552e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |