| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 21000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.761904761904762e-08, | |
| "loss": 30.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-06, | |
| "loss": 29.2188, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1e-05, | |
| "loss": 27.9484, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.5e-05, | |
| "loss": 25.4971, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 21.1988, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 15.2033, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 7.4762, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.5e-05, | |
| "loss": 1.8812, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5258, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.347, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2779, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.33707377314567566, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.804, | |
| "eval_samples_per_second": 436.567, | |
| "eval_steps_per_second": 13.682, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.2162, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1397, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.1035, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0765, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.035, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0481, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0285, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0305, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.034, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0346, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.01727573201060295, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.9791, | |
| "eval_samples_per_second": 358.485, | |
| "eval_steps_per_second": 11.235, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 9.944444444444446e-05, | |
| "loss": 0.0147, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.888888888888889e-05, | |
| "loss": 0.0125, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.3, | |
| "learning_rate": 9.833333333333333e-05, | |
| "loss": 0.0139, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 9.777777777777778e-05, | |
| "loss": 0.0129, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.722222222222223e-05, | |
| "loss": 0.0086, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 9.666666666666667e-05, | |
| "loss": 0.0118, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 9.611111111111112e-05, | |
| "loss": 0.0198, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 9.555555555555557e-05, | |
| "loss": 0.0082, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0074, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.444444444444444e-05, | |
| "loss": 0.0072, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.007698288187384605, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.773, | |
| "eval_samples_per_second": 454.074, | |
| "eval_steps_per_second": 14.23, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 9.388888888888889e-05, | |
| "loss": 0.0146, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 9.333333333333334e-05, | |
| "loss": 0.0072, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "learning_rate": 9.277777777777778e-05, | |
| "loss": 0.0065, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 3.4, | |
| "learning_rate": 9.222222222222223e-05, | |
| "loss": 0.0092, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 3.5, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 0.0065, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 3.6, | |
| "learning_rate": 9.111111111111112e-05, | |
| "loss": 0.0083, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 9.055555555555556e-05, | |
| "loss": 0.009, | |
| "step": 3885 | |
| }, | |
| { | |
| "epoch": 3.8, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0027, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "learning_rate": 8.944444444444446e-05, | |
| "loss": 0.0073, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.888888888888889e-05, | |
| "loss": 0.0057, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.009315615519881248, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.7737, | |
| "eval_samples_per_second": 453.665, | |
| "eval_steps_per_second": 14.217, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 8.833333333333333e-05, | |
| "loss": 0.0072, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 4.2, | |
| "learning_rate": 8.777777777777778e-05, | |
| "loss": 0.0072, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 4.3, | |
| "learning_rate": 8.722222222222223e-05, | |
| "loss": 0.0109, | |
| "step": 4515 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 8.666666666666667e-05, | |
| "loss": 0.01, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "learning_rate": 8.611111111111112e-05, | |
| "loss": 0.0013, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 4.6, | |
| "learning_rate": 8.555555555555556e-05, | |
| "loss": 0.017, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0061, | |
| "step": 4935 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 8.444444444444444e-05, | |
| "loss": 0.0078, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "learning_rate": 8.38888888888889e-05, | |
| "loss": 0.0028, | |
| "step": 5145 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.005, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.005270855501294136, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.584, | |
| "eval_samples_per_second": 601.029, | |
| "eval_steps_per_second": 18.836, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 8.277777777777778e-05, | |
| "loss": 0.006, | |
| "step": 5355 | |
| }, | |
| { | |
| "epoch": 5.2, | |
| "learning_rate": 8.222222222222222e-05, | |
| "loss": 0.0068, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 8.166666666666667e-05, | |
| "loss": 0.0029, | |
| "step": 5565 | |
| }, | |
| { | |
| "epoch": 5.4, | |
| "learning_rate": 8.111111111111112e-05, | |
| "loss": 0.0016, | |
| "step": 5670 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "learning_rate": 8.055555555555556e-05, | |
| "loss": 0.0055, | |
| "step": 5775 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0029, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 5.7, | |
| "learning_rate": 7.944444444444444e-05, | |
| "loss": 0.006, | |
| "step": 5985 | |
| }, | |
| { | |
| "epoch": 5.8, | |
| "learning_rate": 7.88888888888889e-05, | |
| "loss": 0.0028, | |
| "step": 6090 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 7.833333333333333e-05, | |
| "loss": 0.0067, | |
| "step": 6195 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.777777777777778e-05, | |
| "loss": 0.002, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.005636307876557112, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.5895, | |
| "eval_samples_per_second": 595.407, | |
| "eval_steps_per_second": 18.659, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.722222222222223e-05, | |
| "loss": 0.0003, | |
| "step": 6405 | |
| }, | |
| { | |
| "epoch": 6.2, | |
| "learning_rate": 7.666666666666667e-05, | |
| "loss": 0.002, | |
| "step": 6510 | |
| }, | |
| { | |
| "epoch": 6.3, | |
| "learning_rate": 7.61111111111111e-05, | |
| "loss": 0.0011, | |
| "step": 6615 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 7.555555555555556e-05, | |
| "loss": 0.0028, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 6.5, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0062, | |
| "step": 6825 | |
| }, | |
| { | |
| "epoch": 6.6, | |
| "learning_rate": 7.444444444444444e-05, | |
| "loss": 0.0006, | |
| "step": 6930 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 7.38888888888889e-05, | |
| "loss": 0.003, | |
| "step": 7035 | |
| }, | |
| { | |
| "epoch": 6.8, | |
| "learning_rate": 7.333333333333333e-05, | |
| "loss": 0.0048, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 6.9, | |
| "learning_rate": 7.277777777777778e-05, | |
| "loss": 0.0038, | |
| "step": 7245 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 0.002, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.009145626798272133, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.605, | |
| "eval_samples_per_second": 580.167, | |
| "eval_steps_per_second": 18.182, | |
| "step": 7350 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 7.166666666666667e-05, | |
| "loss": 0.005, | |
| "step": 7455 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 7.111111111111112e-05, | |
| "loss": 0.0018, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 7.3, | |
| "learning_rate": 7.055555555555556e-05, | |
| "loss": 0.0031, | |
| "step": 7665 | |
| }, | |
| { | |
| "epoch": 7.4, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0027, | |
| "step": 7770 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "learning_rate": 6.944444444444444e-05, | |
| "loss": 0.0011, | |
| "step": 7875 | |
| }, | |
| { | |
| "epoch": 7.6, | |
| "learning_rate": 6.88888888888889e-05, | |
| "loss": 0.0032, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 7.7, | |
| "learning_rate": 6.833333333333333e-05, | |
| "loss": 0.0018, | |
| "step": 8085 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "learning_rate": 6.777777777777778e-05, | |
| "loss": 0.0032, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 7.9, | |
| "learning_rate": 6.722222222222223e-05, | |
| "loss": 0.0045, | |
| "step": 8295 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0018, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.0010060666827484965, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.618, | |
| "eval_samples_per_second": 567.961, | |
| "eval_steps_per_second": 17.799, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "learning_rate": 6.611111111111111e-05, | |
| "loss": 0.003, | |
| "step": 8505 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 6.555555555555556e-05, | |
| "loss": 0.0023, | |
| "step": 8610 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0028, | |
| "step": 8715 | |
| }, | |
| { | |
| "epoch": 8.4, | |
| "learning_rate": 6.444444444444446e-05, | |
| "loss": 0.002, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 8.5, | |
| "learning_rate": 6.388888888888888e-05, | |
| "loss": 0.0012, | |
| "step": 8925 | |
| }, | |
| { | |
| "epoch": 8.6, | |
| "learning_rate": 6.333333333333333e-05, | |
| "loss": 0.0013, | |
| "step": 9030 | |
| }, | |
| { | |
| "epoch": 8.7, | |
| "learning_rate": 6.277777777777778e-05, | |
| "loss": 0.0011, | |
| "step": 9135 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 6.222222222222222e-05, | |
| "loss": 0.0008, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "learning_rate": 6.166666666666667e-05, | |
| "loss": 0.0029, | |
| "step": 9345 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.111111111111112e-05, | |
| "loss": 0.0044, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.004300011787563562, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.7083, | |
| "eval_samples_per_second": 495.526, | |
| "eval_steps_per_second": 15.529, | |
| "step": 9450 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 6.055555555555555e-05, | |
| "loss": 0.0012, | |
| "step": 9555 | |
| }, | |
| { | |
| "epoch": 9.2, | |
| "learning_rate": 6e-05, | |
| "loss": 0.002, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 9.3, | |
| "learning_rate": 5.9444444444444445e-05, | |
| "loss": 0.0017, | |
| "step": 9765 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 5.8888888888888896e-05, | |
| "loss": 0.0002, | |
| "step": 9870 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 0.0015, | |
| "step": 9975 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 5.7777777777777776e-05, | |
| "loss": 0.003, | |
| "step": 10080 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 5.722222222222222e-05, | |
| "loss": 0.0011, | |
| "step": 10185 | |
| }, | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 5.666666666666667e-05, | |
| "loss": 0.0018, | |
| "step": 10290 | |
| }, | |
| { | |
| "epoch": 9.9, | |
| "learning_rate": 5.6111111111111114e-05, | |
| "loss": 0.0003, | |
| "step": 10395 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.0024, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.004753963556140661, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.593, | |
| "eval_samples_per_second": 591.906, | |
| "eval_steps_per_second": 18.55, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0004, | |
| "step": 10605 | |
| }, | |
| { | |
| "epoch": 10.2, | |
| "learning_rate": 5.4444444444444446e-05, | |
| "loss": 0.0022, | |
| "step": 10710 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 5.388888888888889e-05, | |
| "loss": 0.0016, | |
| "step": 10815 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 5.333333333333333e-05, | |
| "loss": 0.0008, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 10.5, | |
| "learning_rate": 5.2777777777777784e-05, | |
| "loss": 0.0002, | |
| "step": 11025 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 5.222222222222223e-05, | |
| "loss": 0.0023, | |
| "step": 11130 | |
| }, | |
| { | |
| "epoch": 10.7, | |
| "learning_rate": 5.166666666666667e-05, | |
| "loss": 0.0009, | |
| "step": 11235 | |
| }, | |
| { | |
| "epoch": 10.8, | |
| "learning_rate": 5.111111111111111e-05, | |
| "loss": 0.0036, | |
| "step": 11340 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 5.055555555555556e-05, | |
| "loss": 0.0049, | |
| "step": 11445 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0032, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.0022743879817426205, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.656, | |
| "eval_samples_per_second": 535.061, | |
| "eval_steps_per_second": 16.768, | |
| "step": 11550 | |
| }, | |
| { | |
| "epoch": 11.1, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.0036, | |
| "step": 11655 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.0014, | |
| "step": 11760 | |
| }, | |
| { | |
| "epoch": 11.3, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.0022, | |
| "step": 11865 | |
| }, | |
| { | |
| "epoch": 11.4, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.0034, | |
| "step": 11970 | |
| }, | |
| { | |
| "epoch": 11.5, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.0009, | |
| "step": 12075 | |
| }, | |
| { | |
| "epoch": 11.6, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0012, | |
| "step": 12180 | |
| }, | |
| { | |
| "epoch": 11.7, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.0012, | |
| "step": 12285 | |
| }, | |
| { | |
| "epoch": 11.8, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.0023, | |
| "step": 12390 | |
| }, | |
| { | |
| "epoch": 11.9, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0003, | |
| "step": 12495 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0028, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.00027711206348612905, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.5911, | |
| "eval_samples_per_second": 593.792, | |
| "eval_steps_per_second": 18.609, | |
| "step": 12600 | |
| }, | |
| { | |
| "epoch": 12.1, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.001, | |
| "step": 12705 | |
| }, | |
| { | |
| "epoch": 12.2, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.0011, | |
| "step": 12810 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.0028, | |
| "step": 12915 | |
| }, | |
| { | |
| "epoch": 12.4, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.0009, | |
| "step": 13020 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 13125 | |
| }, | |
| { | |
| "epoch": 12.6, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.0005, | |
| "step": 13230 | |
| }, | |
| { | |
| "epoch": 12.7, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.003, | |
| "step": 13335 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 13440 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.0038, | |
| "step": 13545 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0005, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.0007963060052134097, | |
| "eval_max_distance": 0, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.66, | |
| "eval_samples_per_second": 531.819, | |
| "eval_steps_per_second": 16.667, | |
| "step": 13650 | |
| }, | |
| { | |
| "epoch": 13.1, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.0009, | |
| "step": 13755 | |
| }, | |
| { | |
| "epoch": 13.2, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.0004, | |
| "step": 13860 | |
| }, | |
| { | |
| "epoch": 13.3, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.0085, | |
| "step": 13965 | |
| }, | |
| { | |
| "epoch": 13.4, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.0028, | |
| "step": 14070 | |
| }, | |
| { | |
| "epoch": 13.5, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.0019, | |
| "step": 14175 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0008, | |
| "step": 14280 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0001, | |
| "step": 14385 | |
| }, | |
| { | |
| "epoch": 13.8, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.0014, | |
| "step": 14490 | |
| }, | |
| { | |
| "epoch": 13.9, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.002, | |
| "step": 14595 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0026, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.0011878299992531538, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.599, | |
| "eval_samples_per_second": 585.977, | |
| "eval_steps_per_second": 18.364, | |
| "step": 14700 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.0016, | |
| "step": 14805 | |
| }, | |
| { | |
| "epoch": 14.2, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.0008, | |
| "step": 14910 | |
| }, | |
| { | |
| "epoch": 14.3, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.0005, | |
| "step": 15015 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0005, | |
| "step": 15120 | |
| }, | |
| { | |
| "epoch": 14.5, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.001, | |
| "step": 15225 | |
| }, | |
| { | |
| "epoch": 14.6, | |
| "learning_rate": 3e-05, | |
| "loss": 0.002, | |
| "step": 15330 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.0001, | |
| "step": 15435 | |
| }, | |
| { | |
| "epoch": 14.8, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.0, | |
| "step": 15540 | |
| }, | |
| { | |
| "epoch": 14.9, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 15645 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0011, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.017123280093073845, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.6147, | |
| "eval_samples_per_second": 570.998, | |
| "eval_steps_per_second": 17.895, | |
| "step": 15750 | |
| }, | |
| { | |
| "epoch": 15.1, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.0001, | |
| "step": 15855 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0031, | |
| "step": 15960 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.0001, | |
| "step": 16065 | |
| }, | |
| { | |
| "epoch": 15.4, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.0016, | |
| "step": 16170 | |
| }, | |
| { | |
| "epoch": 15.5, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0006, | |
| "step": 16275 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0002, | |
| "step": 16380 | |
| }, | |
| { | |
| "epoch": 15.7, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.0008, | |
| "step": 16485 | |
| }, | |
| { | |
| "epoch": 15.8, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0016, | |
| "step": 16590 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.0002, | |
| "step": 16695 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.011970149353146553, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.591, | |
| "eval_samples_per_second": 593.899, | |
| "eval_steps_per_second": 18.612, | |
| "step": 16800 | |
| }, | |
| { | |
| "epoch": 16.1, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.0009, | |
| "step": 16905 | |
| }, | |
| { | |
| "epoch": 16.2, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.0009, | |
| "step": 17010 | |
| }, | |
| { | |
| "epoch": 16.3, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.0004, | |
| "step": 17115 | |
| }, | |
| { | |
| "epoch": 16.4, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0001, | |
| "step": 17220 | |
| }, | |
| { | |
| "epoch": 16.5, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0032, | |
| "step": 17325 | |
| }, | |
| { | |
| "epoch": 16.6, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0, | |
| "step": 17430 | |
| }, | |
| { | |
| "epoch": 16.7, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.0002, | |
| "step": 17535 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0, | |
| "step": 17640 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.001, | |
| "step": 17745 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0001, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.003116948762908578, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.6156, | |
| "eval_samples_per_second": 570.218, | |
| "eval_steps_per_second": 17.87, | |
| "step": 17850 | |
| }, | |
| { | |
| "epoch": 17.1, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 0.0011, | |
| "step": 17955 | |
| }, | |
| { | |
| "epoch": 17.2, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0004, | |
| "step": 18060 | |
| }, | |
| { | |
| "epoch": 17.3, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0003, | |
| "step": 18165 | |
| }, | |
| { | |
| "epoch": 17.4, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0001, | |
| "step": 18270 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0001, | |
| "step": 18375 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0004, | |
| "step": 18480 | |
| }, | |
| { | |
| "epoch": 17.7, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.0007, | |
| "step": 18585 | |
| }, | |
| { | |
| "epoch": 17.8, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0, | |
| "step": 18690 | |
| }, | |
| { | |
| "epoch": 17.9, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.0, | |
| "step": 18795 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0007, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.016535792499780655, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.5881, | |
| "eval_samples_per_second": 596.809, | |
| "eval_steps_per_second": 18.703, | |
| "step": 18900 | |
| }, | |
| { | |
| "epoch": 18.1, | |
| "learning_rate": 1.0555555555555555e-05, | |
| "loss": 0.0004, | |
| "step": 19005 | |
| }, | |
| { | |
| "epoch": 18.2, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0002, | |
| "step": 19110 | |
| }, | |
| { | |
| "epoch": 18.3, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.0001, | |
| "step": 19215 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0009, | |
| "step": 19320 | |
| }, | |
| { | |
| "epoch": 18.5, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0149, | |
| "step": 19425 | |
| }, | |
| { | |
| "epoch": 18.6, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0003, | |
| "step": 19530 | |
| }, | |
| { | |
| "epoch": 18.7, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 0.0, | |
| "step": 19635 | |
| }, | |
| { | |
| "epoch": 18.8, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 19740 | |
| }, | |
| { | |
| "epoch": 18.9, | |
| "learning_rate": 6.111111111111111e-06, | |
| "loss": 0.0, | |
| "step": 19845 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.001, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.01935943029820919, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.6346, | |
| "eval_samples_per_second": 553.109, | |
| "eval_steps_per_second": 17.334, | |
| "step": 19950 | |
| }, | |
| { | |
| "epoch": 19.1, | |
| "learning_rate": 5e-06, | |
| "loss": 0.001, | |
| "step": 20055 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0, | |
| "step": 20160 | |
| }, | |
| { | |
| "epoch": 19.3, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.0004, | |
| "step": 20265 | |
| }, | |
| { | |
| "epoch": 19.4, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0, | |
| "step": 20370 | |
| }, | |
| { | |
| "epoch": 19.5, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0011, | |
| "step": 20475 | |
| }, | |
| { | |
| "epoch": 19.6, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.0011, | |
| "step": 20580 | |
| }, | |
| { | |
| "epoch": 19.7, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0, | |
| "step": 20685 | |
| }, | |
| { | |
| "epoch": 19.8, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0003, | |
| "step": 20790 | |
| }, | |
| { | |
| "epoch": 19.9, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 0.0004, | |
| "step": 20895 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0001, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.010230864398181438, | |
| "eval_max_distance": 1, | |
| "eval_mean_distance": 0, | |
| "eval_runtime": 0.597, | |
| "eval_samples_per_second": 587.939, | |
| "eval_steps_per_second": 18.425, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 21000, | |
| "total_flos": 3.345253371675648e+16, | |
| "train_loss": 0.6543119361943335, | |
| "train_runtime": 2482.634, | |
| "train_samples_per_second": 270.592, | |
| "train_steps_per_second": 8.459 | |
| } | |
| ], | |
| "logging_steps": 105, | |
| "max_steps": 21000, | |
| "num_train_epochs": 20, | |
| "save_steps": 210, | |
| "total_flos": 3.345253371675648e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |