| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6578249336870026, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 8e-08, | |
| "loss": 1.5996, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.6e-07, | |
| "loss": 1.5931, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.4e-07, | |
| "loss": 1.5999, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.2e-07, | |
| "loss": 1.5866, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4e-07, | |
| "loss": 1.5968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.8e-07, | |
| "loss": 1.5939, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 5.6e-07, | |
| "loss": 1.5908, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 6.4e-07, | |
| "loss": 1.5891, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.2e-07, | |
| "loss": 1.5905, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 8e-07, | |
| "loss": 1.5829, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 8.799999999999999e-07, | |
| "loss": 1.584, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 9.6e-07, | |
| "loss": 1.5809, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.04e-06, | |
| "loss": 1.5723, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.12e-06, | |
| "loss": 1.5701, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2e-06, | |
| "loss": 1.5596, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.28e-06, | |
| "loss": 1.5489, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 1.3600000000000001e-06, | |
| "loss": 1.5285, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.44e-06, | |
| "loss": 1.4786, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.48771580345285526, | |
| "eval_f1": 0.2737123798082793, | |
| "eval_loss": 1.285125970840454, | |
| "eval_precision": 0.24587570192745484, | |
| "eval_recall": 0.3530598608905197, | |
| "eval_runtime": 10.0932, | |
| "eval_samples_per_second": 298.42, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 1.5199999999999998e-06, | |
| "loss": 1.4376, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "learning_rate": 1.6e-06, | |
| "loss": 1.2187, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.6799999999999998e-06, | |
| "loss": 1.0491, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 1.7599999999999999e-06, | |
| "loss": 0.8798, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.84e-06, | |
| "loss": 0.8012, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.92e-06, | |
| "loss": 0.6217, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2e-06, | |
| "loss": 0.6098, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 2.08e-06, | |
| "loss": 0.5121, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.16e-06, | |
| "loss": 0.4405, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.24e-06, | |
| "loss": 0.4499, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.32e-06, | |
| "loss": 0.4434, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.4e-06, | |
| "loss": 0.4022, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.48e-06, | |
| "loss": 0.3539, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.56e-06, | |
| "loss": 0.4215, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.64e-06, | |
| "loss": 0.3787, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 2.7200000000000002e-06, | |
| "loss": 0.342, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 2.8e-06, | |
| "loss": 0.3453, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.91, | |
| "learning_rate": 2.88e-06, | |
| "loss": 0.2968, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 2.96e-06, | |
| "loss": 0.3228, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9193227091633466, | |
| "eval_f1": 0.9151621474863376, | |
| "eval_loss": 0.2782401442527771, | |
| "eval_precision": 0.9212350273670207, | |
| "eval_recall": 0.910189857029304, | |
| "eval_runtime": 10.104, | |
| "eval_samples_per_second": 298.1, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 3.0399999999999997e-06, | |
| "loss": 0.3294, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 3.1199999999999998e-06, | |
| "loss": 0.3161, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 3.2e-06, | |
| "loss": 0.2536, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 3.2799999999999995e-06, | |
| "loss": 0.2895, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.3599999999999996e-06, | |
| "loss": 0.3272, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 3.4399999999999997e-06, | |
| "loss": 0.331, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 3.5199999999999998e-06, | |
| "loss": 0.2644, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 3.6e-06, | |
| "loss": 0.2741, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.68e-06, | |
| "loss": 0.2711, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.7599999999999996e-06, | |
| "loss": 0.2607, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.84e-06, | |
| "loss": 0.2705, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 3.92e-06, | |
| "loss": 0.2833, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "learning_rate": 4e-06, | |
| "loss": 0.2395, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 940, | |
| "num_train_epochs": 5, | |
| "total_flos": 9367043222881344, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |