| { | |
| "best_metric": 2.1030609607696533, | |
| "best_model_checkpoint": "detr-r50-mist1-bg-8ah-6l/checkpoint-2875", | |
| "epoch": 25.0, | |
| "eval_steps": 500, | |
| "global_step": 2875, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.620869565217393e-06, | |
| "loss": 3.6794, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.8221545219421387, | |
| "eval_runtime": 6.0762, | |
| "eval_samples_per_second": 6.583, | |
| "eval_steps_per_second": 0.823, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.224347826086957e-06, | |
| "loss": 3.0269, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.8120057582855225, | |
| "eval_runtime": 5.8393, | |
| "eval_samples_per_second": 6.85, | |
| "eval_steps_per_second": 0.856, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.824347826086957e-06, | |
| "loss": 2.8681, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.7979869842529297, | |
| "eval_runtime": 5.8717, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 0.852, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.424347826086958e-06, | |
| "loss": 2.752, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.485291004180908, | |
| "eval_runtime": 5.9082, | |
| "eval_samples_per_second": 6.77, | |
| "eval_steps_per_second": 0.846, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 8.027826086956523e-06, | |
| "loss": 2.7715, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.413987159729004, | |
| "eval_runtime": 5.8023, | |
| "eval_samples_per_second": 6.894, | |
| "eval_steps_per_second": 0.862, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.627826086956522e-06, | |
| "loss": 2.6846, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.4714808464050293, | |
| "eval_runtime": 5.8424, | |
| "eval_samples_per_second": 6.847, | |
| "eval_steps_per_second": 0.856, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 7.231304347826088e-06, | |
| "loss": 2.6236, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.461406946182251, | |
| "eval_runtime": 5.862, | |
| "eval_samples_per_second": 6.824, | |
| "eval_steps_per_second": 0.853, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.8313043478260874e-06, | |
| "loss": 2.5318, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.3440959453582764, | |
| "eval_runtime": 5.9348, | |
| "eval_samples_per_second": 6.74, | |
| "eval_steps_per_second": 0.842, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 6.431304347826087e-06, | |
| "loss": 2.5224, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.283745765686035, | |
| "eval_runtime": 5.872, | |
| "eval_samples_per_second": 6.812, | |
| "eval_steps_per_second": 0.851, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 6.031304347826088e-06, | |
| "loss": 2.4661, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.250960111618042, | |
| "eval_runtime": 5.9135, | |
| "eval_samples_per_second": 6.764, | |
| "eval_steps_per_second": 0.846, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 5.631304347826088e-06, | |
| "loss": 2.4313, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.333876132965088, | |
| "eval_runtime": 5.8831, | |
| "eval_samples_per_second": 6.799, | |
| "eval_steps_per_second": 0.85, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5.2313043478260875e-06, | |
| "loss": 2.4125, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.2956740856170654, | |
| "eval_runtime": 5.9965, | |
| "eval_samples_per_second": 6.671, | |
| "eval_steps_per_second": 0.834, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 4.831304347826087e-06, | |
| "loss": 2.4113, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.235807180404663, | |
| "eval_runtime": 5.8572, | |
| "eval_samples_per_second": 6.829, | |
| "eval_steps_per_second": 0.854, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.4313043478260875e-06, | |
| "loss": 2.3784, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.263479232788086, | |
| "eval_runtime": 5.9302, | |
| "eval_samples_per_second": 6.745, | |
| "eval_steps_per_second": 0.843, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 4.031304347826087e-06, | |
| "loss": 2.3199, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 2.232009172439575, | |
| "eval_runtime": 5.8956, | |
| "eval_samples_per_second": 6.785, | |
| "eval_steps_per_second": 0.848, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.631304347826087e-06, | |
| "loss": 2.3321, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 2.2249927520751953, | |
| "eval_runtime": 5.9501, | |
| "eval_samples_per_second": 6.723, | |
| "eval_steps_per_second": 0.84, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 3.2313043478260876e-06, | |
| "loss": 2.3305, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 2.202038288116455, | |
| "eval_runtime": 5.8864, | |
| "eval_samples_per_second": 6.795, | |
| "eval_steps_per_second": 0.849, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 2.831304347826087e-06, | |
| "loss": 2.2932, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 2.1825520992279053, | |
| "eval_runtime": 5.8462, | |
| "eval_samples_per_second": 6.842, | |
| "eval_steps_per_second": 0.855, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 2.431304347826087e-06, | |
| "loss": 2.2952, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 2.1626458168029785, | |
| "eval_runtime": 5.963, | |
| "eval_samples_per_second": 6.708, | |
| "eval_steps_per_second": 0.839, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 2.0313043478260872e-06, | |
| "loss": 2.2663, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 2.157285213470459, | |
| "eval_runtime": 5.9246, | |
| "eval_samples_per_second": 6.751, | |
| "eval_steps_per_second": 0.844, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "learning_rate": 1.631304347826087e-06, | |
| "loss": 2.2916, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 2.1653225421905518, | |
| "eval_runtime": 5.8815, | |
| "eval_samples_per_second": 6.801, | |
| "eval_steps_per_second": 0.85, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "learning_rate": 1.231304347826087e-06, | |
| "loss": 2.2703, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 2.1443889141082764, | |
| "eval_runtime": 5.8599, | |
| "eval_samples_per_second": 6.826, | |
| "eval_steps_per_second": 0.853, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "learning_rate": 8.347826086956523e-07, | |
| "loss": 2.2431, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_loss": 2.1373696327209473, | |
| "eval_runtime": 5.8436, | |
| "eval_samples_per_second": 6.845, | |
| "eval_steps_per_second": 0.856, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 4.347826086956522e-07, | |
| "loss": 2.2243, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_loss": 2.1275973320007324, | |
| "eval_runtime": 5.9461, | |
| "eval_samples_per_second": 6.727, | |
| "eval_steps_per_second": 0.841, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "learning_rate": 3.478260869565218e-08, | |
| "loss": 2.2413, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_loss": 2.1030609607696533, | |
| "eval_runtime": 5.9121, | |
| "eval_samples_per_second": 6.766, | |
| "eval_steps_per_second": 0.846, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 2875, | |
| "total_flos": 5.49474551424e+18, | |
| "train_loss": 2.50671312945822, | |
| "train_runtime": 2370.7956, | |
| "train_samples_per_second": 4.851, | |
| "train_steps_per_second": 1.213 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2875, | |
| "num_train_epochs": 25, | |
| "save_steps": 500, | |
| "total_flos": 5.49474551424e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |