| { | |
| "best_metric": 0.8481262327416174, | |
| "best_model_checkpoint": "omarmomen/sf_babylm_1/finetune/sst2/checkpoint-1200", | |
| "epoch": 4.050632911392405, | |
| "global_step": 3200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "eval_accuracy": 0.7775590419769287, | |
| "eval_f1": 0.7855787476280834, | |
| "eval_loss": 0.47054141759872437, | |
| "eval_mcc": 0.5571623075978556, | |
| "eval_runtime": 0.9009, | |
| "eval_samples_per_second": 563.86, | |
| "eval_steps_per_second": 71.037, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.7972440719604492, | |
| "eval_f1": 0.818342151675485, | |
| "eval_loss": 0.516063392162323, | |
| "eval_mcc": 0.6127643523723303, | |
| "eval_runtime": 0.8832, | |
| "eval_samples_per_second": 575.189, | |
| "eval_steps_per_second": 72.465, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.683544303797468e-05, | |
| "loss": 0.4417, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.7952755689620972, | |
| "eval_f1": 0.8022813688212928, | |
| "eval_loss": 0.4550493657588959, | |
| "eval_mcc": 0.5925102852024335, | |
| "eval_runtime": 0.9129, | |
| "eval_samples_per_second": 556.495, | |
| "eval_steps_per_second": 70.11, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.8208661675453186, | |
| "eval_f1": 0.8139059304703476, | |
| "eval_loss": 0.4225212037563324, | |
| "eval_mcc": 0.6430750513685719, | |
| "eval_runtime": 0.8829, | |
| "eval_samples_per_second": 575.39, | |
| "eval_steps_per_second": 72.49, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 4.367088607594937e-05, | |
| "loss": 0.2829, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_accuracy": 0.8287401795387268, | |
| "eval_f1": 0.8342857142857143, | |
| "eval_loss": 0.5139408707618713, | |
| "eval_mcc": 0.6594223100685462, | |
| "eval_runtime": 0.8789, | |
| "eval_samples_per_second": 578.009, | |
| "eval_steps_per_second": 72.82, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "eval_accuracy": 0.8484252095222473, | |
| "eval_f1": 0.8481262327416174, | |
| "eval_loss": 0.43108150362968445, | |
| "eval_mcc": 0.6968557943649227, | |
| "eval_runtime": 0.8802, | |
| "eval_samples_per_second": 577.15, | |
| "eval_steps_per_second": 72.712, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.836614191532135, | |
| "eval_f1": 0.8382066276803118, | |
| "eval_loss": 0.4951391816139221, | |
| "eval_mcc": 0.6735145020970784, | |
| "eval_runtime": 0.9084, | |
| "eval_samples_per_second": 559.197, | |
| "eval_steps_per_second": 70.45, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 4.050632911392405e-05, | |
| "loss": 0.22, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_accuracy": 0.834645688533783, | |
| "eval_f1": 0.83399209486166, | |
| "eval_loss": 0.5284639000892639, | |
| "eval_mcc": 0.6692862125087189, | |
| "eval_runtime": 0.8969, | |
| "eval_samples_per_second": 566.418, | |
| "eval_steps_per_second": 71.36, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.8208661675453186, | |
| "eval_f1": 0.8292682926829268, | |
| "eval_loss": 0.5978161096572876, | |
| "eval_mcc": 0.6455311108800015, | |
| "eval_runtime": 0.9125, | |
| "eval_samples_per_second": 556.733, | |
| "eval_steps_per_second": 70.14, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 3.7341772151898736e-05, | |
| "loss": 0.1552, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_accuracy": 0.8248031735420227, | |
| "eval_f1": 0.8187372708757638, | |
| "eval_loss": 0.5309514403343201, | |
| "eval_mcc": 0.6506555175660951, | |
| "eval_runtime": 0.8778, | |
| "eval_samples_per_second": 578.748, | |
| "eval_steps_per_second": 72.913, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "eval_accuracy": 0.8464567065238953, | |
| "eval_f1": 0.842741935483871, | |
| "eval_loss": 0.5334874987602234, | |
| "eval_mcc": 0.6933987955035008, | |
| "eval_runtime": 0.8839, | |
| "eval_samples_per_second": 574.755, | |
| "eval_steps_per_second": 72.41, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_accuracy": 0.836614191532135, | |
| "eval_f1": 0.8349900596421471, | |
| "eval_loss": 0.5910332202911377, | |
| "eval_mcc": 0.6732550524130743, | |
| "eval_runtime": 0.8933, | |
| "eval_samples_per_second": 568.67, | |
| "eval_steps_per_second": 71.644, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 3.4177215189873416e-05, | |
| "loss": 0.1361, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 3.29, | |
| "eval_accuracy": 0.8287401795387268, | |
| "eval_f1": 0.8176100628930818, | |
| "eval_loss": 0.6343502998352051, | |
| "eval_mcc": 0.6616516436112455, | |
| "eval_runtime": 0.8796, | |
| "eval_samples_per_second": 577.541, | |
| "eval_steps_per_second": 72.761, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 3.54, | |
| "eval_accuracy": 0.8405511975288391, | |
| "eval_f1": 0.8421052631578947, | |
| "eval_loss": 0.6291764378547668, | |
| "eval_mcc": 0.6813907766611972, | |
| "eval_runtime": 0.9128, | |
| "eval_samples_per_second": 556.521, | |
| "eval_steps_per_second": 70.113, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 3.10126582278481e-05, | |
| "loss": 0.1, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "eval_accuracy": 0.8051180839538574, | |
| "eval_f1": 0.818348623853211, | |
| "eval_loss": 0.6933022737503052, | |
| "eval_mcc": 0.6177826999510055, | |
| "eval_runtime": 0.8871, | |
| "eval_samples_per_second": 572.626, | |
| "eval_steps_per_second": 72.142, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "eval_accuracy": 0.8169291615486145, | |
| "eval_f1": 0.8312159709618875, | |
| "eval_loss": 0.7717190384864807, | |
| "eval_mcc": 0.644285698842054, | |
| "eval_runtime": 0.8848, | |
| "eval_samples_per_second": 574.172, | |
| "eval_steps_per_second": 72.337, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 4.05, | |
| "step": 3200, | |
| "total_flos": 5245023150342144.0, | |
| "train_loss": 0.21442661702632904, | |
| "train_runtime": 701.1398, | |
| "train_samples_per_second": 720.655, | |
| "train_steps_per_second": 11.267 | |
| } | |
| ], | |
| "max_steps": 7900, | |
| "num_train_epochs": 10, | |
| "total_flos": 5245023150342144.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |