| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.030917575675597338, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.999226963512678e-06, | |
| "loss": 1.1361, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.998453927025357e-06, | |
| "loss": 0.7353, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.997680890538034e-06, | |
| "loss": 0.6909, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.996907854050712e-06, | |
| "loss": 0.6498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.99613481756339e-06, | |
| "loss": 0.6414, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 9.995361781076068e-06, | |
| "loss": 0.6415, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.994588744588745e-06, | |
| "loss": 0.6317, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.993815708101423e-06, | |
| "loss": 0.6378, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.9930426716141e-06, | |
| "loss": 0.6347, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.992269635126779e-06, | |
| "loss": 0.5924, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.991496598639456e-06, | |
| "loss": 0.6046, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.990723562152135e-06, | |
| "loss": 0.6045, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.989950525664813e-06, | |
| "loss": 0.6, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.98917748917749e-06, | |
| "loss": 0.5504, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.988404452690169e-06, | |
| "loss": 0.5747, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.987631416202846e-06, | |
| "loss": 0.5526, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.986858379715523e-06, | |
| "loss": 0.5958, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.9860853432282e-06, | |
| "loss": 0.608, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 9.985312306740878e-06, | |
| "loss": 0.5988, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.984539270253557e-06, | |
| "loss": 0.5861, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.983766233766234e-06, | |
| "loss": 0.5749, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.982993197278913e-06, | |
| "loss": 0.5498, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.98222016079159e-06, | |
| "loss": 0.5841, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.981447124304268e-06, | |
| "loss": 0.5973, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.980674087816947e-06, | |
| "loss": 0.5954, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.979901051329624e-06, | |
| "loss": 0.527, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.979128014842301e-06, | |
| "loss": 0.5321, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.978354978354979e-06, | |
| "loss": 0.5781, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.977581941867656e-06, | |
| "loss": 0.5119, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.976808905380335e-06, | |
| "loss": 0.5271, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.976035868893012e-06, | |
| "loss": 0.5814, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.97526283240569e-06, | |
| "loss": 0.518, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.974489795918369e-06, | |
| "loss": 0.5335, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.973716759431046e-06, | |
| "loss": 0.5062, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.972943722943725e-06, | |
| "loss": 0.5253, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.972170686456402e-06, | |
| "loss": 0.5856, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.97139764996908e-06, | |
| "loss": 0.5196, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.970624613481757e-06, | |
| "loss": 0.4764, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.969851576994434e-06, | |
| "loss": 0.5254, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 9.969078540507111e-06, | |
| "loss": 0.5442, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.5804400673190799, | |
| "eval_accuracy_sklearn": 0.5804400673190799, | |
| "eval_f1": 0.5294915349019279, | |
| "eval_loss": 0.7918509840965271, | |
| "eval_precision": 0.6370946036872561, | |
| "eval_recall": 0.45298409281186464, | |
| "eval_runtime": 4914.2737, | |
| "eval_samples_per_second": 16.323, | |
| "eval_steps_per_second": 2.04, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 64680, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.37535583797248e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |