| { | |
| "best_metric": 1.5881637334823608, | |
| "best_model_checkpoint": "detr-r50-cd45rb-all-4ah\\checkpoint-46060", | |
| "epoch": 20.0, | |
| "global_step": 46060, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 9.501519756838906e-06, | |
| "loss": 2.4171, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.8409900665283203, | |
| "eval_runtime": 206.0212, | |
| "eval_samples_per_second": 8.645, | |
| "eval_steps_per_second": 1.082, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.001953973078595e-06, | |
| "loss": 2.1862, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7626707553863525, | |
| "eval_runtime": 208.1902, | |
| "eval_samples_per_second": 8.555, | |
| "eval_steps_per_second": 1.071, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.502171081198437e-06, | |
| "loss": 2.1252, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.7528759241104126, | |
| "eval_runtime": 207.3023, | |
| "eval_samples_per_second": 8.591, | |
| "eval_steps_per_second": 1.076, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.002171081198438e-06, | |
| "loss": 2.1065, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.7416059970855713, | |
| "eval_runtime": 207.0434, | |
| "eval_samples_per_second": 8.602, | |
| "eval_steps_per_second": 1.077, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7.502388189318282e-06, | |
| "loss": 2.0764, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.699079990386963, | |
| "eval_runtime": 391.8586, | |
| "eval_samples_per_second": 4.545, | |
| "eval_steps_per_second": 0.569, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.002605297438124e-06, | |
| "loss": 2.051, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.6862515211105347, | |
| "eval_runtime": 383.5485, | |
| "eval_samples_per_second": 4.643, | |
| "eval_steps_per_second": 0.581, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 6.502822405557968e-06, | |
| "loss": 2.039, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6824065446853638, | |
| "eval_runtime": 379.3509, | |
| "eval_samples_per_second": 4.695, | |
| "eval_steps_per_second": 0.588, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.002822405557969e-06, | |
| "loss": 2.0266, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6705697774887085, | |
| "eval_runtime": 387.7566, | |
| "eval_samples_per_second": 4.593, | |
| "eval_steps_per_second": 0.575, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.503039513677813e-06, | |
| "loss": 2.0177, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6724380254745483, | |
| "eval_runtime": 388.2463, | |
| "eval_samples_per_second": 4.587, | |
| "eval_steps_per_second": 0.574, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.003256621797655e-06, | |
| "loss": 2.006, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6438802480697632, | |
| "eval_runtime": 381.3527, | |
| "eval_samples_per_second": 4.67, | |
| "eval_steps_per_second": 0.585, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.503690838037343e-06, | |
| "loss": 1.9853, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.6503098011016846, | |
| "eval_runtime": 371.6041, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 0.6, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.003690838037343e-06, | |
| "loss": 1.9794, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6337422132492065, | |
| "eval_runtime": 367.1164, | |
| "eval_samples_per_second": 4.851, | |
| "eval_steps_per_second": 0.607, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.5039079461571867e-06, | |
| "loss": 1.9676, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6212905645370483, | |
| "eval_runtime": 384.5295, | |
| "eval_samples_per_second": 4.632, | |
| "eval_steps_per_second": 0.58, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.004342162396874e-06, | |
| "loss": 1.9646, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.6212937831878662, | |
| "eval_runtime": 366.0496, | |
| "eval_samples_per_second": 4.865, | |
| "eval_steps_per_second": 0.609, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.504342162396874e-06, | |
| "loss": 1.9551, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.614364743232727, | |
| "eval_runtime": 201.7258, | |
| "eval_samples_per_second": 8.829, | |
| "eval_steps_per_second": 1.105, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.0043421623968738e-06, | |
| "loss": 1.9448, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6080951690673828, | |
| "eval_runtime": 202.5165, | |
| "eval_samples_per_second": 8.794, | |
| "eval_steps_per_second": 1.101, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.504776378636561e-06, | |
| "loss": 1.9347, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.5986374616622925, | |
| "eval_runtime": 375.2604, | |
| "eval_samples_per_second": 4.746, | |
| "eval_steps_per_second": 0.594, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.0047763786365611e-06, | |
| "loss": 1.9287, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.5923762321472168, | |
| "eval_runtime": 382.3809, | |
| "eval_samples_per_second": 4.658, | |
| "eval_steps_per_second": 0.583, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.052105948762484e-07, | |
| "loss": 1.9177, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.590692162513733, | |
| "eval_runtime": 371.0354, | |
| "eval_samples_per_second": 4.8, | |
| "eval_steps_per_second": 0.601, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5.210594876248372e-09, | |
| "loss": 1.9216, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.5881637334823608, | |
| "eval_runtime": 379.3818, | |
| "eval_samples_per_second": 4.694, | |
| "eval_steps_per_second": 0.588, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 46060, | |
| "total_flos": 1.7606512956165125e+20, | |
| "train_loss": 2.027567579142694, | |
| "train_runtime": 94939.1754, | |
| "train_samples_per_second": 3.881, | |
| "train_steps_per_second": 0.485 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.7606512956165125e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |