| { | |
| "best_metric": 0.611058235168457, | |
| "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_mrpc_256/checkpoint-232", | |
| "epoch": 13.0, | |
| "global_step": 377, | |
| "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": 0.6431, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.626089870929718, | |
| "eval_runtime": 0.9456, | |
| "eval_samples_per_second": 431.492, | |
| "eval_steps_per_second": 4.23, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.6296, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6234638094902039, | |
| "eval_runtime": 0.9411, | |
| "eval_samples_per_second": 433.528, | |
| "eval_steps_per_second": 4.25, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.6306, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6237208247184753, | |
| "eval_runtime": 0.937, | |
| "eval_samples_per_second": 435.41, | |
| "eval_steps_per_second": 4.269, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.6297, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6237556338310242, | |
| "eval_runtime": 0.9403, | |
| "eval_samples_per_second": 433.895, | |
| "eval_steps_per_second": 4.254, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.6276, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6206657290458679, | |
| "eval_runtime": 0.9389, | |
| "eval_samples_per_second": 434.555, | |
| "eval_steps_per_second": 4.26, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.6197, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6838235294117647, | |
| "eval_combined_score": 0.7480253018237863, | |
| "eval_f1": 0.8122270742358079, | |
| "eval_loss": 0.6212654709815979, | |
| "eval_runtime": 0.9398, | |
| "eval_samples_per_second": 434.126, | |
| "eval_steps_per_second": 4.256, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 4.3e-05, | |
| "loss": 0.6065, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6911764705882353, | |
| "eval_combined_score": 0.7477621483375959, | |
| "eval_f1": 0.8043478260869565, | |
| "eval_loss": 0.6284083724021912, | |
| "eval_runtime": 0.9178, | |
| "eval_samples_per_second": 444.537, | |
| "eval_steps_per_second": 4.358, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.2e-05, | |
| "loss": 0.5258, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6911764705882353, | |
| "eval_combined_score": 0.7429823721019352, | |
| "eval_f1": 0.7947882736156351, | |
| "eval_loss": 0.611058235168457, | |
| "eval_runtime": 0.9172, | |
| "eval_samples_per_second": 444.815, | |
| "eval_steps_per_second": 4.361, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 4.1e-05, | |
| "loss": 0.4596, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.7034313725490197, | |
| "eval_combined_score": 0.7542921758075211, | |
| "eval_f1": 0.8051529790660225, | |
| "eval_loss": 0.6506468057632446, | |
| "eval_runtime": 0.9479, | |
| "eval_samples_per_second": 430.438, | |
| "eval_steps_per_second": 4.22, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3953, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.7034313725490197, | |
| "eval_combined_score": 0.7482968828557064, | |
| "eval_f1": 0.7931623931623932, | |
| "eval_loss": 0.7271472811698914, | |
| "eval_runtime": 0.9357, | |
| "eval_samples_per_second": 436.055, | |
| "eval_steps_per_second": 4.275, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.9000000000000006e-05, | |
| "loss": 0.3426, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6740196078431373, | |
| "eval_combined_score": 0.7140892863614947, | |
| "eval_f1": 0.7541589648798522, | |
| "eval_loss": 0.9509055018424988, | |
| "eval_runtime": 0.944, | |
| "eval_samples_per_second": 432.196, | |
| "eval_steps_per_second": 4.237, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.2821, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6862745098039216, | |
| "eval_combined_score": 0.7335482138060704, | |
| "eval_f1": 0.7808219178082192, | |
| "eval_loss": 1.0021162033081055, | |
| "eval_runtime": 0.9425, | |
| "eval_samples_per_second": 432.902, | |
| "eval_steps_per_second": 4.244, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.7e-05, | |
| "loss": 0.2177, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6691176470588235, | |
| "eval_combined_score": 0.7183798218082413, | |
| "eval_f1": 0.7676419965576592, | |
| "eval_loss": 1.0359125137329102, | |
| "eval_runtime": 0.9408, | |
| "eval_samples_per_second": 433.683, | |
| "eval_steps_per_second": 4.252, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 377, | |
| "total_flos": 1256051433275392.0, | |
| "train_loss": 0.5084376322495843, | |
| "train_runtime": 493.204, | |
| "train_samples_per_second": 371.854, | |
| "train_steps_per_second": 2.94 | |
| } | |
| ], | |
| "max_steps": 1450, | |
| "num_train_epochs": 50, | |
| "total_flos": 1256051433275392.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |