| { | |
| "best_metric": 1.596240758895874, | |
| "best_model_checkpoint": "detr-r101-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": 9.0034737299175e-06, | |
| "loss": 2.3757, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.822200059890747, | |
| "eval_runtime": 713.8422, | |
| "eval_samples_per_second": 2.495, | |
| "eval_steps_per_second": 0.312, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.004342162396874e-06, | |
| "loss": 2.1779, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7999826669692993, | |
| "eval_runtime": 728.2283, | |
| "eval_samples_per_second": 2.446, | |
| "eval_steps_per_second": 0.306, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.005210594876249e-06, | |
| "loss": 2.1259, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.73061203956604, | |
| "eval_runtime": 745.2135, | |
| "eval_samples_per_second": 2.39, | |
| "eval_steps_per_second": 0.299, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.005644811115936e-06, | |
| "loss": 2.0969, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.6853969097137451, | |
| "eval_runtime": 742.3303, | |
| "eval_samples_per_second": 2.399, | |
| "eval_steps_per_second": 0.3, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.005644811115936e-06, | |
| "loss": 2.0699, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.6933584213256836, | |
| "eval_runtime": 218.19, | |
| "eval_samples_per_second": 8.163, | |
| "eval_steps_per_second": 1.022, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.005644811115936e-06, | |
| "loss": 2.0398, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.6654878854751587, | |
| "eval_runtime": 217.319, | |
| "eval_samples_per_second": 8.195, | |
| "eval_steps_per_second": 1.026, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.005644811115936e-06, | |
| "loss": 2.0203, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.657590627670288, | |
| "eval_runtime": 220.5653, | |
| "eval_samples_per_second": 8.075, | |
| "eval_steps_per_second": 1.011, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0065132435953105e-06, | |
| "loss": 2.009, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6401054859161377, | |
| "eval_runtime": 221.9532, | |
| "eval_samples_per_second": 8.024, | |
| "eval_steps_per_second": 1.005, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0069474598349978e-06, | |
| "loss": 1.9923, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6319390535354614, | |
| "eval_runtime": 220.4641, | |
| "eval_samples_per_second": 8.078, | |
| "eval_steps_per_second": 1.012, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 7.381676074685194e-09, | |
| "loss": 1.9802, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6264243125915527, | |
| "eval_runtime": 219.9308, | |
| "eval_samples_per_second": 8.098, | |
| "eval_steps_per_second": 1.014, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.503690838037343e-06, | |
| "loss": 2.0027, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.6538771390914917, | |
| "eval_runtime": 653.5646, | |
| "eval_samples_per_second": 2.725, | |
| "eval_steps_per_second": 0.341, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.003907946157187e-06, | |
| "loss": 2.0005, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.6563668251037598, | |
| "eval_runtime": 217.5695, | |
| "eval_samples_per_second": 8.186, | |
| "eval_steps_per_second": 1.025, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.50412505427703e-06, | |
| "loss": 1.9861, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6382570266723633, | |
| "eval_runtime": 220.9586, | |
| "eval_samples_per_second": 8.06, | |
| "eval_steps_per_second": 1.009, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.004342162396874e-06, | |
| "loss": 1.9778, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.6245843172073364, | |
| "eval_runtime": 765.4452, | |
| "eval_samples_per_second": 2.327, | |
| "eval_steps_per_second": 0.291, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.504342162396874e-06, | |
| "loss": 1.9602, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.6119104623794556, | |
| "eval_runtime": 762.5288, | |
| "eval_samples_per_second": 2.336, | |
| "eval_steps_per_second": 0.292, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.0045592705167173e-06, | |
| "loss": 1.9599, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6097208261489868, | |
| "eval_runtime": 767.5249, | |
| "eval_samples_per_second": 2.32, | |
| "eval_steps_per_second": 0.291, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.504776378636561e-06, | |
| "loss": 1.9464, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6114660501480103, | |
| "eval_runtime": 768.6581, | |
| "eval_samples_per_second": 2.317, | |
| "eval_steps_per_second": 0.29, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.0052105948762484e-06, | |
| "loss": 1.9376, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.6017816066741943, | |
| "eval_runtime": 636.6555, | |
| "eval_samples_per_second": 2.797, | |
| "eval_steps_per_second": 0.35, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.054277029960921e-07, | |
| "loss": 1.9273, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.5967309474945068, | |
| "eval_runtime": 741.1917, | |
| "eval_samples_per_second": 2.403, | |
| "eval_steps_per_second": 0.301, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5.644811115935737e-09, | |
| "loss": 1.928, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.596240758895874, | |
| "eval_runtime": 718.7174, | |
| "eval_samples_per_second": 2.478, | |
| "eval_steps_per_second": 0.31, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 46060, | |
| "total_flos": 2.5644983981460485e+20, | |
| "train_loss": 0.9813270691421515, | |
| "train_runtime": 81506.6025, | |
| "train_samples_per_second": 4.52, | |
| "train_steps_per_second": 0.565 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 20, | |
| "total_flos": 2.5644983981460485e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |