| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.9600000000000002e-05, | |
| "loss": 3.169, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 1.9924, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.88e-05, | |
| "loss": 0.9846, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.3159, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.1231, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.76e-05, | |
| "loss": 0.0848, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.72e-05, | |
| "loss": 0.0536, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.0381, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.64e-05, | |
| "loss": 0.0339, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.0222, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 1.5600000000000003e-05, | |
| "loss": 0.0214, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0836, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 1.48e-05, | |
| "loss": 0.0851, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 1.4400000000000001e-05, | |
| "loss": 0.1763, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 1.4e-05, | |
| "loss": 0.113, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.1091, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 0.0988, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.2800000000000001e-05, | |
| "loss": 0.1031, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 1.2400000000000002e-05, | |
| "loss": 0.0878, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.1203, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.16e-05, | |
| "loss": 0.0863, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 0.081, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 1.0800000000000002e-05, | |
| "loss": 0.0763, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0792, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0726, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.0687, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.0776, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.0692, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.067, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0632, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.0662, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.062, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.0594, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.0598, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0544, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 0.0532, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "learning_rate": 5.2e-06, | |
| "loss": 0.0179, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 0.0129, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "learning_rate": 4.4e-06, | |
| "loss": 0.0077, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0069, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 0.004, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 0.016, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 0.0025, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 0.0025, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0017, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 0.0016, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 0.0015, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 0.0014, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 0.0014, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0014, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 1000, | |
| "total_flos": 6536571125760.0, | |
| "train_loss": 0.17982604479789735, | |
| "train_runtime": 23967.503, | |
| "train_samples_per_second": 0.328, | |
| "train_steps_per_second": 0.042 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 50, | |
| "total_flos": 6536571125760.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |