| { | |
| "best_metric": 1.6073237657546997, | |
| "best_model_checkpoint": "detr-r50-cd45rb-all-16ah\\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": 2.3982, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.852927327156067, | |
| "eval_runtime": 206.1695, | |
| "eval_samples_per_second": 8.639, | |
| "eval_steps_per_second": 1.082, | |
| "step": 2303 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 9.002171081198437e-06, | |
| "loss": 2.1913, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.7870194911956787, | |
| "eval_runtime": 204.1755, | |
| "eval_samples_per_second": 8.723, | |
| "eval_steps_per_second": 1.092, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.502171081198437e-06, | |
| "loss": 2.1311, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.7360913753509521, | |
| "eval_runtime": 204.2256, | |
| "eval_samples_per_second": 8.721, | |
| "eval_steps_per_second": 1.092, | |
| "step": 6909 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 8.002388189318281e-06, | |
| "loss": 2.1099, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.7354556322097778, | |
| "eval_runtime": 202.8637, | |
| "eval_samples_per_second": 8.779, | |
| "eval_steps_per_second": 1.099, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 7.502605297438124e-06, | |
| "loss": 2.0772, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7197104692459106, | |
| "eval_runtime": 202.8095, | |
| "eval_samples_per_second": 8.782, | |
| "eval_steps_per_second": 1.1, | |
| "step": 11515 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 7.0028224055579685e-06, | |
| "loss": 2.0559, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.6910244226455688, | |
| "eval_runtime": 203.0668, | |
| "eval_samples_per_second": 8.771, | |
| "eval_steps_per_second": 1.098, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 6.502822405557968e-06, | |
| "loss": 2.0406, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.7068419456481934, | |
| "eval_runtime": 203.1838, | |
| "eval_samples_per_second": 8.765, | |
| "eval_steps_per_second": 1.098, | |
| "step": 16121 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 6.003256621797656e-06, | |
| "loss": 2.0332, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6706095933914185, | |
| "eval_runtime": 203.6268, | |
| "eval_samples_per_second": 8.746, | |
| "eval_steps_per_second": 1.095, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 5.5036908380373435e-06, | |
| "loss": 2.0238, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6654621362686157, | |
| "eval_runtime": 203.4048, | |
| "eval_samples_per_second": 8.756, | |
| "eval_steps_per_second": 1.096, | |
| "step": 20727 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.003907946157187e-06, | |
| "loss": 2.0049, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.6604490280151367, | |
| "eval_runtime": 203.0353, | |
| "eval_samples_per_second": 8.772, | |
| "eval_steps_per_second": 1.098, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 4.50412505427703e-06, | |
| "loss": 1.9879, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 1.6595245599746704, | |
| "eval_runtime": 202.8344, | |
| "eval_samples_per_second": 8.781, | |
| "eval_steps_per_second": 1.099, | |
| "step": 25333 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 1.9898, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 1.68044912815094, | |
| "eval_runtime": 202.8883, | |
| "eval_samples_per_second": 8.778, | |
| "eval_steps_per_second": 1.099, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 3.5045592705167173e-06, | |
| "loss": 1.9818, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 1.6360925436019897, | |
| "eval_runtime": 202.7291, | |
| "eval_samples_per_second": 8.785, | |
| "eval_steps_per_second": 1.1, | |
| "step": 29939 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 3.0045592705167175e-06, | |
| "loss": 1.9731, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 1.64567232131958, | |
| "eval_runtime": 202.3788, | |
| "eval_samples_per_second": 8.8, | |
| "eval_steps_per_second": 1.102, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.5045592705167176e-06, | |
| "loss": 1.9584, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 1.6221011877059937, | |
| "eval_runtime": 202.3912, | |
| "eval_samples_per_second": 8.8, | |
| "eval_steps_per_second": 1.102, | |
| "step": 34545 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.0047763786365613e-06, | |
| "loss": 1.9536, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 1.6137330532073975, | |
| "eval_runtime": 202.4992, | |
| "eval_samples_per_second": 8.795, | |
| "eval_steps_per_second": 1.101, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.5049934867564047e-06, | |
| "loss": 1.9396, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 1.6114263534545898, | |
| "eval_runtime": 203.0004, | |
| "eval_samples_per_second": 8.773, | |
| "eval_steps_per_second": 1.099, | |
| "step": 39151 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 1.0049934867564047e-06, | |
| "loss": 1.9332, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 1.6084880828857422, | |
| "eval_runtime": 208.0168, | |
| "eval_samples_per_second": 8.562, | |
| "eval_steps_per_second": 1.072, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 5.054277029960921e-07, | |
| "loss": 1.9205, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 1.60756516456604, | |
| "eval_runtime": 207.5092, | |
| "eval_samples_per_second": 8.583, | |
| "eval_steps_per_second": 1.075, | |
| "step": 43757 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 5.644811115935737e-09, | |
| "loss": 1.924, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 1.6073237657546997, | |
| "eval_runtime": 209.9183, | |
| "eval_samples_per_second": 8.484, | |
| "eval_steps_per_second": 1.062, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 46060, | |
| "total_flos": 1.7606512956165125e+20, | |
| "train_loss": 0.28888339640211136, | |
| "train_runtime": 8210.4778, | |
| "train_samples_per_second": 44.872, | |
| "train_steps_per_second": 5.61 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 20, | |
| "total_flos": 1.7606512956165125e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |