| { | |
| "best_metric": 1.4071465730667114, | |
| "best_model_checkpoint": "/kaggle/working/amr-tst-indo/AMRBART-id/fine-tune/../outputs/mbart-en-id-smaller-fted/checkpoint-1520", | |
| "epoch": 15.9958071278826, | |
| "global_step": 1520, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-09, | |
| "loss": 6.0549, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1e-07, | |
| "loss": 5.9202, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2e-07, | |
| "loss": 5.3467, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3e-07, | |
| "loss": 4.6465, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4e-07, | |
| "loss": 4.3418, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.378068447113037, | |
| "eval_runtime": 2.5518, | |
| "eval_samples_per_second": 103.849, | |
| "eval_steps_per_second": 20.77, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 5e-07, | |
| "loss": 4.0362, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 6e-07, | |
| "loss": 3.469, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 7e-07, | |
| "loss": 2.8971, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 8e-07, | |
| "loss": 2.4616, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 9e-07, | |
| "loss": 2.2282, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.078709840774536, | |
| "eval_runtime": 2.5357, | |
| "eval_samples_per_second": 104.508, | |
| "eval_steps_per_second": 20.902, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1e-06, | |
| "loss": 2.2418, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 9.863636363636363e-07, | |
| "loss": 2.0575, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 9.727272727272727e-07, | |
| "loss": 2.0621, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 9.59090909090909e-07, | |
| "loss": 1.9103, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 9.454545454545455e-07, | |
| "loss": 1.947, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.817661166191101, | |
| "eval_runtime": 2.5208, | |
| "eval_samples_per_second": 105.125, | |
| "eval_steps_per_second": 21.025, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 9.318181818181817e-07, | |
| "loss": 1.9331, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 9.181818181818181e-07, | |
| "loss": 1.7866, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 9.045454545454545e-07, | |
| "loss": 1.8531, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 8.909090909090909e-07, | |
| "loss": 1.7661, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.772727272727273e-07, | |
| "loss": 1.7924, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.6833910942077637, | |
| "eval_runtime": 2.5259, | |
| "eval_samples_per_second": 104.913, | |
| "eval_steps_per_second": 20.983, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 8.636363636363636e-07, | |
| "loss": 1.7426, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.42, | |
| "learning_rate": 8.5e-07, | |
| "loss": 1.6863, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 8.363636363636363e-07, | |
| "loss": 1.6788, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.84, | |
| "learning_rate": 8.227272727272727e-07, | |
| "loss": 1.6764, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.613844633102417, | |
| "eval_runtime": 2.526, | |
| "eval_samples_per_second": 104.911, | |
| "eval_steps_per_second": 20.982, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "learning_rate": 8.09090909090909e-07, | |
| "loss": 1.7464, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 5.26, | |
| "learning_rate": 7.954545454545454e-07, | |
| "loss": 1.6661, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.47, | |
| "learning_rate": 7.818181818181818e-07, | |
| "loss": 1.6213, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.68, | |
| "learning_rate": 7.681818181818182e-07, | |
| "loss": 1.5895, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.89, | |
| "learning_rate": 7.545454545454546e-07, | |
| "loss": 1.5868, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.5621322393417358, | |
| "eval_runtime": 2.5161, | |
| "eval_samples_per_second": 105.322, | |
| "eval_steps_per_second": 21.064, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "learning_rate": 7.409090909090909e-07, | |
| "loss": 1.6402, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 6.31, | |
| "learning_rate": 7.272727272727274e-07, | |
| "loss": 1.5571, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.52, | |
| "learning_rate": 7.136363636363637e-07, | |
| "loss": 1.6449, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 1.5674, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 6.863636363636363e-07, | |
| "loss": 1.605, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.530236005783081, | |
| "eval_runtime": 2.5271, | |
| "eval_samples_per_second": 104.864, | |
| "eval_steps_per_second": 20.973, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 6.727272727272727e-07, | |
| "loss": 1.5795, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 7.37, | |
| "learning_rate": 6.590909090909091e-07, | |
| "loss": 1.5291, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.58, | |
| "learning_rate": 6.454545454545455e-07, | |
| "loss": 1.5663, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.79, | |
| "learning_rate": 6.318181818181818e-07, | |
| "loss": 1.5326, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.181818181818181e-07, | |
| "loss": 1.5897, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.5036414861679077, | |
| "eval_runtime": 2.5257, | |
| "eval_samples_per_second": 104.921, | |
| "eval_steps_per_second": 20.984, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 6.045454545454545e-07, | |
| "loss": 1.5629, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 8.42, | |
| "learning_rate": 5.909090909090909e-07, | |
| "loss": 1.5069, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.63, | |
| "learning_rate": 5.772727272727273e-07, | |
| "loss": 1.5059, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.84, | |
| "learning_rate": 5.636363636363636e-07, | |
| "loss": 1.5103, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.4787436723709106, | |
| "eval_runtime": 2.5377, | |
| "eval_samples_per_second": 104.427, | |
| "eval_steps_per_second": 20.885, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 9.05, | |
| "learning_rate": 5.5e-07, | |
| "loss": 1.5148, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 9.26, | |
| "learning_rate": 5.363636363636363e-07, | |
| "loss": 1.4927, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 9.47, | |
| "learning_rate": 5.227272727272728e-07, | |
| "loss": 1.4826, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "learning_rate": 5.090909090909092e-07, | |
| "loss": 1.4854, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.89, | |
| "learning_rate": 4.954545454545455e-07, | |
| "loss": 1.4713, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.4612189531326294, | |
| "eval_runtime": 2.5505, | |
| "eval_samples_per_second": 103.9, | |
| "eval_steps_per_second": 20.78, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.1, | |
| "learning_rate": 4.818181818181817e-07, | |
| "loss": 1.4923, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 10.31, | |
| "learning_rate": 4.6818181818181814e-07, | |
| "loss": 1.4864, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 4.545454545454545e-07, | |
| "loss": 1.4972, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.73, | |
| "learning_rate": 4.409090909090909e-07, | |
| "loss": 1.4156, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "learning_rate": 4.272727272727273e-07, | |
| "loss": 1.4455, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.44575035572052, | |
| "eval_runtime": 2.5276, | |
| "eval_samples_per_second": 104.843, | |
| "eval_steps_per_second": 20.969, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 11.16, | |
| "learning_rate": 4.1363636363636366e-07, | |
| "loss": 1.5115, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 11.37, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 1.4458, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 11.58, | |
| "learning_rate": 3.863636363636364e-07, | |
| "loss": 1.461, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 3.727272727272727e-07, | |
| "loss": 1.4437, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.5909090909090907e-07, | |
| "loss": 1.4553, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.432648777961731, | |
| "eval_runtime": 2.5587, | |
| "eval_samples_per_second": 103.568, | |
| "eval_steps_per_second": 20.714, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 12.21, | |
| "learning_rate": 3.4545454545454544e-07, | |
| "loss": 1.4858, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 12.42, | |
| "learning_rate": 3.3181818181818177e-07, | |
| "loss": 1.4193, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 12.63, | |
| "learning_rate": 3.1818181818181815e-07, | |
| "loss": 1.4363, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 3.0454545454545453e-07, | |
| "loss": 1.4501, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.4239989519119263, | |
| "eval_runtime": 2.5751, | |
| "eval_samples_per_second": 102.907, | |
| "eval_steps_per_second": 20.581, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 13.05, | |
| "learning_rate": 2.909090909090909e-07, | |
| "loss": 1.4586, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 13.26, | |
| "learning_rate": 2.772727272727273e-07, | |
| "loss": 1.4263, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 13.47, | |
| "learning_rate": 2.6363636363636356e-07, | |
| "loss": 1.4484, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 13.68, | |
| "learning_rate": 2.4999999999999994e-07, | |
| "loss": 1.3985, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 13.89, | |
| "learning_rate": 2.3636363636363634e-07, | |
| "loss": 1.4134, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.4161295890808105, | |
| "eval_runtime": 2.5462, | |
| "eval_samples_per_second": 104.076, | |
| "eval_steps_per_second": 20.815, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 2.2272727272727272e-07, | |
| "loss": 1.4115, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 14.31, | |
| "learning_rate": 2.0909090909090907e-07, | |
| "loss": 1.4126, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 14.52, | |
| "learning_rate": 1.9545454545454545e-07, | |
| "loss": 1.4652, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 14.73, | |
| "learning_rate": 1.8181818181818186e-07, | |
| "loss": 1.4327, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 14.94, | |
| "learning_rate": 1.681818181818182e-07, | |
| "loss": 1.422, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.4098496437072754, | |
| "eval_runtime": 2.5612, | |
| "eval_samples_per_second": 103.468, | |
| "eval_steps_per_second": 20.694, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 15.16, | |
| "learning_rate": 1.5454545454545448e-07, | |
| "loss": 1.4582, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 1.4090909090909086e-07, | |
| "loss": 1.4484, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 15.58, | |
| "learning_rate": 1.2727272727272724e-07, | |
| "loss": 1.3937, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 15.79, | |
| "learning_rate": 1.1363636363636362e-07, | |
| "loss": 1.416, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1e-07, | |
| "loss": 1.4139, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.4071465730667114, | |
| "eval_runtime": 2.5382, | |
| "eval_samples_per_second": 104.404, | |
| "eval_steps_per_second": 20.881, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 1520, | |
| "total_flos": 1443270331367424.0, | |
| "train_loss": 1.854057946016914, | |
| "train_runtime": 1311.705, | |
| "train_samples_per_second": 29.055, | |
| "train_steps_per_second": 1.159 | |
| } | |
| ], | |
| "max_steps": 1520, | |
| "num_train_epochs": 16, | |
| "total_flos": 1443270331367424.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |