| { | |
| "best_metric": 1.639158010482788, | |
| "best_model_checkpoint": "detr-r50-cd45rb-8ah-6l-gelu-corrected\\checkpoint-46060", | |
| "epoch": 10.0, | |
| "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": 9.00238818931828e-06, | |
| "loss": 3.0438, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.9413050413131714, | |
| "eval_runtime": 201.9196, | |
| "eval_samples_per_second": 8.82, | |
| "eval_steps_per_second": 1.104, | |
| "step": 4606 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8.002822405557968e-06, | |
| "loss": 2.3933, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.8238338232040405, | |
| "eval_runtime": 202.1836, | |
| "eval_samples_per_second": 8.809, | |
| "eval_steps_per_second": 1.103, | |
| "step": 9212 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 7.003039513677812e-06, | |
| "loss": 2.2782, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.771848440170288, | |
| "eval_runtime": 202.1516, | |
| "eval_samples_per_second": 8.81, | |
| "eval_steps_per_second": 1.103, | |
| "step": 13818 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 6.003473729917499e-06, | |
| "loss": 2.2383, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.752848505973816, | |
| "eval_runtime": 202.2922, | |
| "eval_samples_per_second": 8.804, | |
| "eval_steps_per_second": 1.102, | |
| "step": 18424 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 5.003690838037343e-06, | |
| "loss": 2.2046, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.7264593839645386, | |
| "eval_runtime": 201.788, | |
| "eval_samples_per_second": 8.826, | |
| "eval_steps_per_second": 1.105, | |
| "step": 23030 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 4.0041250542770305e-06, | |
| "loss": 2.1659, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 1.7125098705291748, | |
| "eval_runtime": 202.0053, | |
| "eval_samples_per_second": 8.817, | |
| "eval_steps_per_second": 1.104, | |
| "step": 27636 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.0045592705167175e-06, | |
| "loss": 2.1457, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 1.6760411262512207, | |
| "eval_runtime": 201.2859, | |
| "eval_samples_per_second": 8.848, | |
| "eval_steps_per_second": 1.108, | |
| "step": 32242 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 2.0047763786365613e-06, | |
| "loss": 2.1111, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 1.6621686220169067, | |
| "eval_runtime": 201.2613, | |
| "eval_samples_per_second": 8.849, | |
| "eval_steps_per_second": 1.108, | |
| "step": 36848 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.0052105948762484e-06, | |
| "loss": 2.0959, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 1.6466784477233887, | |
| "eval_runtime": 201.3173, | |
| "eval_samples_per_second": 8.847, | |
| "eval_steps_per_second": 1.108, | |
| "step": 41454 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 5.427702996092055e-09, | |
| "loss": 2.0826, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 1.639158010482788, | |
| "eval_runtime": 201.0423, | |
| "eval_samples_per_second": 8.859, | |
| "eval_steps_per_second": 1.109, | |
| "step": 46060 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 46060, | |
| "total_flos": 8.803256478082562e+19, | |
| "train_loss": 2.275937762904364, | |
| "train_runtime": 29381.2037, | |
| "train_samples_per_second": 6.27, | |
| "train_steps_per_second": 1.568 | |
| } | |
| ], | |
| "max_steps": 46060, | |
| "num_train_epochs": 10, | |
| "total_flos": 8.803256478082562e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |